From dc55e35f9e810f23dd69cfdc91a3d636023f57a2 Mon Sep 17 00:00:00 2001
From: Alexey Gladkov <legion@kernel.org>
Date: Mon, 14 Feb 2022 19:18:14 +0100
Subject: ipc: Store mqueue sysctls in the ipc namespace

Right now, the mqueue sysctls take ipc namespaces into account in a
rather hacky way. This works in most cases, but does not respect the
user namespace.

Within the user namespace, the user cannot change the /proc/sys/fs/mqueue/*
parametres. This poses a problem in the rootless containers.

To solve this I changed the implementation of the mqueue sysctls just
like some other sysctls.

So far, the changes do not provide additional access to files. This will
be done in a future patch.

v3:
* Don't implemenet set_permissions to keep the current behavior.

v2:
* Fixed compilation problem if CONFIG_POSIX_MQUEUE_SYSCTL is not
  specified.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Alexey Gladkov <legion@kernel.org>
Link: https://lkml.kernel.org/r/b0ccbb2489119f1f20c737cf1930c3a9c4e4243a.1644862280.git.legion@kernel.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 include/linux/ipc_namespace.h | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index b75395ec8d52..fa787d97d60a 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -10,6 +10,7 @@
 #include <linux/ns_common.h>
 #include <linux/refcount.h>
 #include <linux/rhashtable-types.h>
+#include <linux/sysctl.h>
 
 struct user_namespace;
 
@@ -63,6 +64,9 @@ struct ipc_namespace {
 	unsigned int    mq_msg_default;
 	unsigned int    mq_msgsize_default;
 
+	struct ctl_table_set	mq_set;
+	struct ctl_table_header	*mq_sysctls;
+
 	/* user_ns which owns the ipc ns */
 	struct user_namespace *user_ns;
 	struct ucounts *ucounts;
@@ -169,14 +173,18 @@ static inline void put_ipc_ns(struct ipc_namespace *ns)
 
 #ifdef CONFIG_POSIX_MQUEUE_SYSCTL
 
-struct ctl_table_header;
-extern struct ctl_table_header *mq_register_sysctl_table(void);
+void retire_mq_sysctls(struct ipc_namespace *ns);
+bool setup_mq_sysctls(struct ipc_namespace *ns);
 
 #else /* CONFIG_POSIX_MQUEUE_SYSCTL */
 
-static inline struct ctl_table_header *mq_register_sysctl_table(void)
+static inline void retire_mq_sysctls(struct ipc_namespace *ns)
 {
-	return NULL;
+}
+
+static inline bool setup_mq_sysctls(struct ipc_namespace *ns)
+{
+	return true;
 }
 
 #endif /* CONFIG_POSIX_MQUEUE_SYSCTL */
-- 
cgit v1.2.3


From 1f5c135ee509e89e0cc274333a65f73c62cb16e5 Mon Sep 17 00:00:00 2001
From: Alexey Gladkov <legion@kernel.org>
Date: Mon, 14 Feb 2022 19:18:15 +0100
Subject: ipc: Store ipc sysctls in the ipc namespace

The ipc sysctls are not available for modification inside the user
namespace. Following the mqueue sysctls, we changed the implementation
to be more userns friendly.

So far, the changes do not provide additional access to files. This
will be done in a future patch.

Signed-off-by: Alexey Gladkov <legion@kernel.org>
Link: https://lkml.kernel.org/r/be6f9d014276f4dddd0c3aa05a86052856c1c555.1644862280.git.legion@kernel.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 include/linux/ipc_namespace.h |  21 +++++
 ipc/ipc_sysctl.c              | 189 +++++++++++++++++++++++++++---------------
 ipc/namespace.c               |   4 +
 3 files changed, 147 insertions(+), 67 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index fa787d97d60a..e3e8c8662b49 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -67,6 +67,9 @@ struct ipc_namespace {
 	struct ctl_table_set	mq_set;
 	struct ctl_table_header	*mq_sysctls;
 
+	struct ctl_table_set	ipc_set;
+	struct ctl_table_header	*ipc_sysctls;
+
 	/* user_ns which owns the ipc ns */
 	struct user_namespace *user_ns;
 	struct ucounts *ucounts;
@@ -188,4 +191,22 @@ static inline bool setup_mq_sysctls(struct ipc_namespace *ns)
 }
 
 #endif /* CONFIG_POSIX_MQUEUE_SYSCTL */
+
+#ifdef CONFIG_SYSVIPC_SYSCTL
+
+bool setup_ipc_sysctls(struct ipc_namespace *ns);
+void retire_ipc_sysctls(struct ipc_namespace *ns);
+
+#else /* CONFIG_SYSVIPC_SYSCTL */
+
+static inline void retire_ipc_sysctls(struct ipc_namespace *ns)
+{
+}
+
+static inline bool setup_ipc_sysctls(struct ipc_namespace *ns)
+{
+	return true;
+}
+
+#endif /* CONFIG_SYSVIPC_SYSCTL */
 #endif
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index f101c171753f..15210ac47e9e 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -13,43 +13,22 @@
 #include <linux/capability.h>
 #include <linux/ipc_namespace.h>
 #include <linux/msg.h>
+#include <linux/slab.h>
 #include "util.h"
 
-static void *get_ipc(struct ctl_table *table)
-{
-	char *which = table->data;
-	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
-	which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns;
-	return which;
-}
-
-static int proc_ipc_dointvec(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table ipc_table;
-
-	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-
-	return proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
-}
-
-static int proc_ipc_dointvec_minmax(struct ctl_table *table, int write,
+static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct ipc_namespace *ns = table->extra1;
 	struct ctl_table ipc_table;
+	int err;
 
 	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
 
-	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
-}
+	ipc_table.extra1 = SYSCTL_ZERO;
+	ipc_table.extra2 = SYSCTL_ONE;
 
-static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ipc_namespace *ns = current->nsproxy->ipc_ns;
-	int err = proc_ipc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	err = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 
 	if (err < 0)
 		return err;
@@ -58,17 +37,6 @@ static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 	return err;
 }
 
-static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table ipc_table;
-	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-
-	return proc_doulongvec_minmax(&ipc_table, write, buffer,
-					lenp, ppos);
-}
-
 static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -87,11 +55,17 @@ static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
 	void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct ipc_namespace *ns = table->extra1;
+	struct ctl_table ipc_table;
 	int ret, semmni;
-	struct ipc_namespace *ns = current->nsproxy->ipc_ns;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+
+	ipc_table.extra1 = NULL;
+	ipc_table.extra2 = NULL;
 
 	semmni = ns->sem_ctls[3];
-	ret = proc_ipc_dointvec(table, write, buffer, lenp, ppos);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (!ret)
 		ret = sem_check_semmni(current->nsproxy->ipc_ns);
@@ -108,12 +82,18 @@ static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
 static int proc_ipc_dointvec_minmax_checkpoint_restore(struct ctl_table *table,
 		int write, void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct user_namespace *user_ns = current->nsproxy->ipc_ns->user_ns;
+	struct ipc_namespace *ns = table->extra1;
+	struct ctl_table ipc_table;
 
-	if (write && !checkpoint_restore_ns_capable(user_ns))
+	if (write && !checkpoint_restore_ns_capable(ns->user_ns))
 		return -EPERM;
 
-	return proc_ipc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+
+	ipc_table.extra1 = SYSCTL_ZERO;
+	ipc_table.extra2 = SYSCTL_INT_MAX;
+
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 }
 #endif
 
@@ -121,27 +101,27 @@ int ipc_mni = IPCMNI;
 int ipc_mni_shift = IPCMNI_SHIFT;
 int ipc_min_cycle = RADIX_TREE_MAP_SIZE;
 
-static struct ctl_table ipc_kern_table[] = {
+static struct ctl_table ipc_sysctls[] = {
 	{
 		.procname	= "shmmax",
 		.data		= &init_ipc_ns.shm_ctlmax,
 		.maxlen		= sizeof(init_ipc_ns.shm_ctlmax),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_doulongvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
 		.procname	= "shmall",
 		.data		= &init_ipc_ns.shm_ctlall,
 		.maxlen		= sizeof(init_ipc_ns.shm_ctlall),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_doulongvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
 		.procname	= "shmmni",
 		.data		= &init_ipc_ns.shm_ctlmni,
 		.maxlen		= sizeof(init_ipc_ns.shm_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &ipc_mni,
 	},
@@ -151,15 +131,13 @@ static struct ctl_table ipc_kern_table[] = {
 		.maxlen		= sizeof(init_ipc_ns.shm_rmid_forced),
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_dointvec_minmax_orphans,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "msgmax",
 		.data		= &init_ipc_ns.msg_ctlmax,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmax),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_INT_MAX,
 	},
@@ -168,7 +146,7 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmni,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &ipc_mni,
 	},
@@ -186,7 +164,7 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmnb,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmnb),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_INT_MAX,
 	},
@@ -204,8 +182,6 @@ static struct ctl_table ipc_kern_table[] = {
 		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id),
 		.mode		= 0666,
 		.proc_handler	= proc_ipc_dointvec_minmax_checkpoint_restore,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "msg_next_id",
@@ -213,8 +189,6 @@ static struct ctl_table ipc_kern_table[] = {
 		.maxlen		= sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id),
 		.mode		= 0666,
 		.proc_handler	= proc_ipc_dointvec_minmax_checkpoint_restore,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "shm_next_id",
@@ -222,25 +196,106 @@ static struct ctl_table ipc_kern_table[] = {
 		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id),
 		.mode		= 0666,
 		.proc_handler	= proc_ipc_dointvec_minmax_checkpoint_restore,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_INT_MAX,
 	},
 #endif
 	{}
 };
 
-static struct ctl_table ipc_root_table[] = {
-	{
-		.procname	= "kernel",
-		.mode		= 0555,
-		.child		= ipc_kern_table,
-	},
-	{}
+static struct ctl_table_set *set_lookup(struct ctl_table_root *root)
+{
+	return &current->nsproxy->ipc_ns->ipc_set;
+}
+
+static int set_is_seen(struct ctl_table_set *set)
+{
+	return &current->nsproxy->ipc_ns->ipc_set == set;
+}
+
+static struct ctl_table_root set_root = {
+	.lookup = set_lookup,
 };
 
+bool setup_ipc_sysctls(struct ipc_namespace *ns)
+{
+	struct ctl_table *tbl;
+
+	setup_sysctl_set(&ns->ipc_set, &set_root, set_is_seen);
+
+	tbl = kmemdup(ipc_sysctls, sizeof(ipc_sysctls), GFP_KERNEL);
+	if (tbl) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(ipc_sysctls); i++) {
+			if (tbl[i].data == &init_ipc_ns.shm_ctlmax) {
+				tbl[i].data = &ns->shm_ctlmax;
+
+			} else if (tbl[i].data == &init_ipc_ns.shm_ctlall) {
+				tbl[i].data = &ns->shm_ctlall;
+
+			} else if (tbl[i].data == &init_ipc_ns.shm_ctlmni) {
+				tbl[i].data = &ns->shm_ctlmni;
+
+			} else if (tbl[i].data == &init_ipc_ns.shm_rmid_forced) {
+				tbl[i].data = &ns->shm_rmid_forced;
+				tbl[i].extra1 = ns;
+
+			} else if (tbl[i].data == &init_ipc_ns.msg_ctlmax) {
+				tbl[i].data = &ns->msg_ctlmax;
+
+			} else if (tbl[i].data == &init_ipc_ns.msg_ctlmni) {
+				tbl[i].data = &ns->msg_ctlmni;
+
+			} else if (tbl[i].data == &init_ipc_ns.msg_ctlmnb) {
+				tbl[i].data = &ns->msg_ctlmnb;
+
+			} else if (tbl[i].data == &init_ipc_ns.sem_ctls) {
+				tbl[i].data = &ns->sem_ctls;
+				tbl[i].extra1 = ns;
+#ifdef CONFIG_CHECKPOINT_RESTORE
+			} else if (tbl[i].data == &init_ipc_ns.ids[IPC_SEM_IDS].next_id) {
+				tbl[i].data = &ns->ids[IPC_SEM_IDS].next_id;
+				tbl[i].extra1 = ns;
+
+			} else if (tbl[i].data == &init_ipc_ns.ids[IPC_MSG_IDS].next_id) {
+				tbl[i].data = &ns->ids[IPC_MSG_IDS].next_id;
+				tbl[i].extra1 = ns;
+
+			} else if (tbl[i].data == &init_ipc_ns.ids[IPC_SHM_IDS].next_id) {
+				tbl[i].data = &ns->ids[IPC_SHM_IDS].next_id;
+				tbl[i].extra1 = ns;
+#endif
+			} else {
+				tbl[i].data = NULL;
+			}
+		}
+
+		ns->ipc_sysctls = __register_sysctl_table(&ns->ipc_set, "kernel", tbl);
+	}
+	if (!ns->ipc_sysctls) {
+		kfree(tbl);
+		retire_sysctl_set(&ns->ipc_set);
+		return false;
+	}
+
+	return true;
+}
+
+void retire_ipc_sysctls(struct ipc_namespace *ns)
+{
+	struct ctl_table *tbl;
+
+	tbl = ns->ipc_sysctls->ctl_table_arg;
+	unregister_sysctl_table(ns->ipc_sysctls);
+	retire_sysctl_set(&ns->ipc_set);
+	kfree(tbl);
+}
+
 static int __init ipc_sysctl_init(void)
 {
-	register_sysctl_table(ipc_root_table);
+	if (!setup_ipc_sysctls(&init_ipc_ns)) {
+		pr_warn("ipc sysctl registration failed\n");
+		return -ENOMEM;
+	}
 	return 0;
 }
 
diff --git a/ipc/namespace.c b/ipc/namespace.c
index f760243ca685..754f3237194a 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -63,6 +63,9 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	if (!setup_mq_sysctls(ns))
 		goto fail_put;
 
+	if (!setup_ipc_sysctls(ns))
+		goto fail_put;
+
 	sem_init_ns(ns);
 	msg_init_ns(ns);
 	shm_init_ns(ns);
@@ -130,6 +133,7 @@ static void free_ipc_ns(struct ipc_namespace *ns)
 	shm_exit_ns(ns);
 
 	retire_mq_sysctls(ns);
+	retire_ipc_sysctls(ns);
 
 	dec_ipc_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
-- 
cgit v1.2.3


From 8733068b9bdbc7a54f02dcc59eb0e4789cd60942 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Thu, 3 Mar 2022 15:41:17 +0000
Subject: KVM: x86/xen: Make kvm_xen_set_evtchn() reusable from other places

Clean it up to return -errno on error consistently, while still being
compatible with the return conventions for kvm_arch_set_irq_inatomic()
and the kvm_set_irq() callback.

We use -ENOTCONN to indicate when the port is masked. No existing users
care, except that it's negative.

Also allow it to optimise the vCPU lookup. Unless we abuse the lapic
map, there is no quick lookup from APIC ID to a vCPU; the logic in
kvm_get_vcpu_by_id() will just iterate over all vCPUs till it finds
the one it wants. So do that just once and stash the result in the
struct kvm_xen_evtchn for next time.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220303154127.202856-8-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/irq_comm.c  |  2 +-
 arch/x86/kvm/xen.c       | 83 +++++++++++++++++++++++++++++++++---------------
 arch/x86/kvm/xen.h       |  2 +-
 include/linux/kvm_host.h |  3 +-
 4 files changed, 62 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 6e0dab04320e..0687162c4f22 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -181,7 +181,7 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 		if (!level)
 			return -1;
 
-		return kvm_xen_set_evtchn_fast(e, kvm);
+		return kvm_xen_set_evtchn_fast(&e->xen_evtchn, kvm);
 #endif
 	default:
 		break;
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 65ffba89441a..9c87263a5be2 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -859,13 +859,16 @@ static inline int max_evtchn_port(struct kvm *kvm)
 }
 
 /*
- * This follows the kvm_set_irq() API, so it returns:
+ * The return value from this function is propagated to kvm_set_irq() API,
+ * so it returns:
  *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
  *  = 0   Interrupt was coalesced (previous irq is still pending)
  *  > 0   Number of CPUs interrupt was delivered to
+ *
+ * It is also called directly from kvm_arch_set_irq_inatomic(), where the
+ * only check on its return value is a comparison with -EWOULDBLOCK'.
  */
-int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
-			    struct kvm *kvm)
+int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, struct kvm *kvm)
 {
 	struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache;
 	struct kvm_vcpu *vcpu;
@@ -873,18 +876,23 @@ int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
 	unsigned long flags;
 	int port_word_bit;
 	bool kick_vcpu = false;
-	int idx;
-	int rc;
+	int vcpu_idx, idx, rc;
 
-	vcpu = kvm_get_vcpu_by_id(kvm, e->xen_evtchn.vcpu);
-	if (!vcpu)
-		return -1;
+	vcpu_idx = READ_ONCE(xe->vcpu_idx);
+	if (vcpu_idx >= 0)
+		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
+	else {
+		vcpu = kvm_get_vcpu_by_id(kvm, xe->vcpu_id);
+		if (!vcpu)
+			return -EINVAL;
+		WRITE_ONCE(xe->vcpu_idx, kvm_vcpu_get_idx(vcpu));
+	}
 
 	if (!vcpu->arch.xen.vcpu_info_cache.active)
-		return -1;
+		return -EINVAL;
 
-	if (e->xen_evtchn.port >= max_evtchn_port(kvm))
-		return -1;
+	if (xe->port >= max_evtchn_port(kvm))
+		return -EINVAL;
 
 	rc = -EWOULDBLOCK;
 
@@ -898,12 +906,12 @@ int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
 		struct shared_info *shinfo = gpc->khva;
 		pending_bits = (unsigned long *)&shinfo->evtchn_pending;
 		mask_bits = (unsigned long *)&shinfo->evtchn_mask;
-		port_word_bit = e->xen_evtchn.port / 64;
+		port_word_bit = xe->port / 64;
 	} else {
 		struct compat_shared_info *shinfo = gpc->khva;
 		pending_bits = (unsigned long *)&shinfo->evtchn_pending;
 		mask_bits = (unsigned long *)&shinfo->evtchn_mask;
-		port_word_bit = e->xen_evtchn.port / 32;
+		port_word_bit = xe->port / 32;
 	}
 
 	/*
@@ -913,10 +921,10 @@ int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
 	 * already set, then we kick the vCPU in question to write to the
 	 * *real* evtchn_pending_sel in its own guest vcpu_info struct.
 	 */
-	if (test_and_set_bit(e->xen_evtchn.port, pending_bits)) {
+	if (test_and_set_bit(xe->port, pending_bits)) {
 		rc = 0; /* It was already raised */
-	} else if (test_bit(e->xen_evtchn.port, mask_bits)) {
-		rc = -1; /* Masked */
+	} else if (test_bit(xe->port, mask_bits)) {
+		rc = -ENOTCONN; /* Masked */
 	} else {
 		rc = 1; /* Delivered to the bitmap in shared_info. */
 		/* Now switch to the vCPU's vcpu_info to set the index and pending_sel */
@@ -962,17 +970,12 @@ int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
 	return rc;
 }
 
-/* This is the version called from kvm_set_irq() as the .set function */
-static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
-			 int irq_source_id, int level, bool line_status)
+static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
 {
 	bool mm_borrowed = false;
 	int rc;
 
-	if (!level)
-		return -1;
-
-	rc = kvm_xen_set_evtchn_fast(e, kvm);
+	rc = kvm_xen_set_evtchn_fast(xe, kvm);
 	if (rc != -EWOULDBLOCK)
 		return rc;
 
@@ -1016,7 +1019,7 @@ static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm
 		struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache;
 		int idx;
 
-		rc = kvm_xen_set_evtchn_fast(e, kvm);
+		rc = kvm_xen_set_evtchn_fast(xe, kvm);
 		if (rc != -EWOULDBLOCK)
 			break;
 
@@ -1033,11 +1036,27 @@ static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm
 	return rc;
 }
 
+/* This is the version called from kvm_set_irq() as the .set function */
+static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+			 int irq_source_id, int level, bool line_status)
+{
+	if (!level)
+		return -EINVAL;
+
+	return kvm_xen_set_evtchn(&e->xen_evtchn, kvm);
+}
+
+/*
+ * Set up an event channel interrupt from the KVM IRQ routing table.
+ * Used for e.g. PIRQ from passed through physical devices.
+ */
 int kvm_xen_setup_evtchn(struct kvm *kvm,
 			 struct kvm_kernel_irq_routing_entry *e,
 			 const struct kvm_irq_routing_entry *ue)
 
 {
+	struct kvm_vcpu *vcpu;
+
 	if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
 		return -EINVAL;
 
@@ -1045,8 +1064,22 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
 	if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
 		return -EINVAL;
 
+	/*
+	 * Xen gives us interesting mappings from vCPU index to APIC ID,
+	 * which means kvm_get_vcpu_by_id() has to iterate over all vCPUs
+	 * to find it. Do that once at setup time, instead of every time.
+	 * But beware that on live update / live migration, the routing
+	 * table might be reinstated before the vCPU threads have finished
+	 * recreating their vCPUs.
+	 */
+	vcpu = kvm_get_vcpu_by_id(kvm, ue->u.xen_evtchn.vcpu);
+	if (vcpu)
+		e->xen_evtchn.vcpu_idx = kvm_vcpu_get_idx(vcpu);
+	else
+		e->xen_evtchn.vcpu_idx = -1;
+
 	e->xen_evtchn.port = ue->u.xen_evtchn.port;
-	e->xen_evtchn.vcpu = ue->u.xen_evtchn.vcpu;
+	e->xen_evtchn.vcpu_id = ue->u.xen_evtchn.vcpu;
 	e->xen_evtchn.priority = ue->u.xen_evtchn.priority;
 	e->set = evtchn_set_fn;
 
diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index 7dd0590f93e1..e28feb32add6 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -25,7 +25,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc);
 void kvm_xen_init_vm(struct kvm *kvm);
 void kvm_xen_destroy_vm(struct kvm *kvm);
 void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu);
-int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
+int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe,
 			    struct kvm *kvm);
 int kvm_xen_setup_evtchn(struct kvm *kvm,
 			 struct kvm_kernel_irq_routing_entry *e,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3f9b22c4983a..252ee4a61b58 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -611,7 +611,8 @@ struct kvm_hv_sint {
 
 struct kvm_xen_evtchn {
 	u32 port;
-	u32 vcpu;
+	u32 vcpu_id;
+	int vcpu_idx;
 	u32 priority;
 };
 
-- 
cgit v1.2.3


From 8bea9af887de4c99a95f93f2ce400ef63e8b4e9b Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 22 Mar 2022 12:50:27 +0200
Subject: iio: adc: ad_sigma_delta: Add sequencer support

Some sigma-delta chips support sampling of multiple
channels in continuous mode.

When the operating with more than one channel enabled,
the channel sequencer cycles through the enabled channels
in sequential order, from first channel to the last one.
If a channel is disabled, it is skipped by the sequencer.

If more than one channel is used in continuous mode,
instruct the device to append the status to the SPI transfer
(1 extra byte) every time we receive a sample.
All sigma-delta chips possessing a sampling sequencer have
this ability. Inside the status register there will be
the number of the converted channel. In this way, even
if the CPU won't keep up with the sampling rate, it won't
send to userspace wrong channel samples.

When multiple channels are enabled in continuous mode,
the device needs to perform a measurement on all slots
before we can push to userspace the sample.

If, during sequencing and data reading, a channel measurement
is lost, a desync occurred. In this case, ad_sigma_delta drops
the incomplete sample and waits for the device to send the
measurement on the first active slot.

Co-developed-by: Alexandru Tachici <alexandru.tachici@analog.com>
Signed-off-by: Alexandru Tachici <alexandru.tachici@analog.com>
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Link: https://lore.kernel.org/r/20220322105029.86389-5-alexandru.tachici@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad_sigma_delta.c       | 143 ++++++++++++++++++++++++++++++---
 include/linux/iio/adc/ad_sigma_delta.h |  38 +++++++++
 2 files changed, 171 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index ebcd52526cac..261a9a6b45e1 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -6,6 +6,7 @@
  *  Author: Lars-Peter Clausen <lars@metafoo.de>
  */
 
+#include <linux/align.h>
 #include <linux/interrupt.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
@@ -342,15 +343,49 @@ EXPORT_SYMBOL_NS_GPL(ad_sigma_delta_single_conversion, IIO_AD_SIGMA_DELTA);
 static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
+	unsigned int i, slot, samples_buf_size;
 	unsigned int channel;
+	uint8_t *samples_buf;
 	int ret;
 
-	channel = find_first_bit(indio_dev->active_scan_mask,
-				 indio_dev->masklength);
-	ret = ad_sigma_delta_set_channel(sigma_delta,
-		indio_dev->channels[channel].address);
-	if (ret)
-		return ret;
+	if (sigma_delta->num_slots == 1) {
+		channel = find_first_bit(indio_dev->active_scan_mask,
+					 indio_dev->masklength);
+		ret = ad_sigma_delta_set_channel(sigma_delta,
+						 indio_dev->channels[channel].address);
+		if (ret)
+			return ret;
+		slot = 1;
+	} else {
+		/*
+		 * At this point update_scan_mode already enabled the required channels.
+		 * For sigma-delta sequencer drivers with multiple slots, an update_scan_mode
+		 * implementation is mandatory.
+		 */
+		slot = 0;
+		for_each_set_bit(i, indio_dev->active_scan_mask, indio_dev->masklength) {
+			sigma_delta->slots[slot] = indio_dev->channels[i].address;
+			slot++;
+		}
+	}
+
+	sigma_delta->active_slots = slot;
+	sigma_delta->current_slot = 0;
+
+	if (sigma_delta->active_slots > 1) {
+		ret = ad_sigma_delta_append_status(sigma_delta, true);
+		if (ret)
+			return ret;
+	}
+
+	samples_buf_size = ALIGN(slot * indio_dev->channels[0].scan_type.storagebits, 8);
+	samples_buf_size += sizeof(int64_t);
+	samples_buf = devm_krealloc(&sigma_delta->spi->dev, sigma_delta->samples_buf,
+				    samples_buf_size, GFP_KERNEL);
+	if (!samples_buf)
+		return -ENOMEM;
+
+	sigma_delta->samples_buf = samples_buf;
 
 	spi_bus_lock(sigma_delta->spi->master);
 	sigma_delta->bus_locked = true;
@@ -386,6 +421,10 @@ static int ad_sd_buffer_postdisable(struct iio_dev *indio_dev)
 	sigma_delta->keep_cs_asserted = false;
 	ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_IDLE);
 
+	if (sigma_delta->status_appended)
+		ad_sigma_delta_append_status(sigma_delta, false);
+
+	ad_sigma_delta_disable_all(sigma_delta);
 	sigma_delta->bus_locked = false;
 	return spi_bus_unlock(sigma_delta->spi->master);
 }
@@ -396,6 +435,10 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
 	uint8_t *data = sigma_delta->rx_buf;
+	unsigned int transfer_size;
+	unsigned int sample_size;
+	unsigned int sample_pos;
+	unsigned int status_pos;
 	unsigned int reg_size;
 	unsigned int data_reg;
 
@@ -408,21 +451,69 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 	else
 		data_reg = AD_SD_REG_DATA;
 
+	/* Status word will be appended to the sample during transfer */
+	if (sigma_delta->status_appended)
+		transfer_size = reg_size + 1;
+	else
+		transfer_size = reg_size;
+
 	switch (reg_size) {
 	case 4:
 	case 2:
 	case 1:
-		ad_sd_read_reg_raw(sigma_delta, data_reg, reg_size, &data[0]);
+		status_pos = reg_size;
+		ad_sd_read_reg_raw(sigma_delta, data_reg, transfer_size, &data[0]);
 		break;
 	case 3:
+		/*
+		 * Data array after transfer will look like (if status is appended):
+		 * data[] = { [0][sample][sample][sample][status] }
+		 * Keeping the first byte 0 shifts the status postion by 1 byte to the right.
+		 */
+		status_pos = reg_size + 1;
+
 		/* We store 24 bit samples in a 32 bit word. Keep the upper
 		 * byte set to zero. */
-		ad_sd_read_reg_raw(sigma_delta, data_reg, reg_size, &data[1]);
+		ad_sd_read_reg_raw(sigma_delta, data_reg, transfer_size, &data[1]);
 		break;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, data, pf->timestamp);
+	/*
+	 * For devices sampling only one channel at
+	 * once, there is no need for sample number tracking.
+	 */
+	if (sigma_delta->active_slots == 1) {
+		iio_push_to_buffers_with_timestamp(indio_dev, data, pf->timestamp);
+		goto irq_handled;
+	}
+
+	if (sigma_delta->status_appended) {
+		u8 converted_channel;
+
+		converted_channel = data[status_pos] & sigma_delta->info->status_ch_mask;
+		if (converted_channel != sigma_delta->slots[sigma_delta->current_slot]) {
+			/*
+			 * Desync occurred during continuous sampling of multiple channels.
+			 * Drop this incomplete sample and start from first channel again.
+			 */
+
+			sigma_delta->current_slot = 0;
+			goto irq_handled;
+		}
+	}
+
+	sample_size = indio_dev->channels[0].scan_type.storagebits / 8;
+	sample_pos = sample_size * sigma_delta->current_slot;
+	memcpy(&sigma_delta->samples_buf[sample_pos], data, sample_size);
+	sigma_delta->current_slot++;
 
+	if (sigma_delta->current_slot == sigma_delta->active_slots) {
+		sigma_delta->current_slot = 0;
+		iio_push_to_buffers_with_timestamp(indio_dev, sigma_delta->samples_buf,
+						   pf->timestamp);
+	}
+
+irq_handled:
 	iio_trigger_notify_done(indio_dev->trig);
 	sigma_delta->irq_dis = false;
 	enable_irq(sigma_delta->spi->irq);
@@ -430,10 +521,17 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 	return IRQ_HANDLED;
 }
 
+static bool ad_sd_validate_scan_mask(struct iio_dev *indio_dev, const unsigned long *mask)
+{
+	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
+
+	return bitmap_weight(mask, indio_dev->masklength) <= sigma_delta->num_slots;
+}
+
 static const struct iio_buffer_setup_ops ad_sd_buffer_setup_ops = {
 	.postenable = &ad_sd_buffer_postenable,
 	.postdisable = &ad_sd_buffer_postdisable,
-	.validate_scan_mask = &iio_validate_scan_mask_onehot,
+	.validate_scan_mask = &ad_sd_validate_scan_mask,
 };
 
 static irqreturn_t ad_sd_data_rdy_trig_poll(int irq, void *private)
@@ -513,8 +611,14 @@ static int devm_ad_sd_probe_trigger(struct device *dev, struct iio_dev *indio_de
  */
 int devm_ad_sd_setup_buffer_and_trigger(struct device *dev, struct iio_dev *indio_dev)
 {
+	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
 	int ret;
 
+	sigma_delta->slots = devm_kcalloc(dev, sigma_delta->num_slots,
+					  sizeof(*sigma_delta->slots), GFP_KERNEL);
+	if (!sigma_delta->slots)
+		return -ENOMEM;
+
 	ret = devm_iio_triggered_buffer_setup(dev, indio_dev,
 					      &iio_pollfunc_store_time,
 					      &ad_sd_trigger_handler,
@@ -541,6 +645,25 @@ int ad_sd_init(struct ad_sigma_delta *sigma_delta, struct iio_dev *indio_dev,
 {
 	sigma_delta->spi = spi;
 	sigma_delta->info = info;
+
+	/* If the field is unset in ad_sigma_delta_info, asume there can only be 1 slot. */
+	if (!info->num_slots)
+		sigma_delta->num_slots = 1;
+	else
+		sigma_delta->num_slots = info->num_slots;
+
+	if (sigma_delta->num_slots > 1) {
+		if (!indio_dev->info->update_scan_mode) {
+			dev_err(&spi->dev, "iio_dev lacks update_scan_mode().\n");
+			return -EINVAL;
+		}
+
+		if (!info->disable_all) {
+			dev_err(&spi->dev, "ad_sigma_delta_info lacks disable_all().\n");
+			return -EINVAL;
+		}
+	}
+
 	iio_device_set_drvdata(indio_dev, sigma_delta);
 
 	return 0;
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index c525fd51652f..7852f6c9a714 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -32,26 +32,34 @@ struct iio_dev;
 /**
  * struct ad_sigma_delta_info - Sigma Delta driver specific callbacks and options
  * @set_channel: Will be called to select the current channel, may be NULL.
+ * @append_status: Will be called to enable status append at the end of the sample, may be NULL.
  * @set_mode: Will be called to select the current mode, may be NULL.
+ * @disable_all: Will be called to disable all channels, may be NULL.
  * @postprocess_sample: Is called for each sampled data word, can be used to
  *		modify or drop the sample data, it, may be NULL.
  * @has_registers: true if the device has writable and readable registers, false
  *		if there is just one read-only sample data shift register.
  * @addr_shift: Shift of the register address in the communications register.
  * @read_mask: Mask for the communications register having the read bit set.
+ * @status_ch_mask: Mask for the channel number stored in status register.
  * @data_reg: Address of the data register, if 0 the default address of 0x3 will
  *   be used.
  * @irq_flags: flags for the interrupt used by the triggered buffer
+ * @num_slots: Number of sequencer slots
  */
 struct ad_sigma_delta_info {
 	int (*set_channel)(struct ad_sigma_delta *, unsigned int channel);
+	int (*append_status)(struct ad_sigma_delta *, bool append);
 	int (*set_mode)(struct ad_sigma_delta *, enum ad_sigma_delta_mode mode);
+	int (*disable_all)(struct ad_sigma_delta *);
 	int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample);
 	bool has_registers;
 	unsigned int addr_shift;
 	unsigned int read_mask;
+	unsigned int status_ch_mask;
 	unsigned int data_reg;
 	unsigned long irq_flags;
+	unsigned int num_slots;
 };
 
 /**
@@ -76,6 +84,13 @@ struct ad_sigma_delta {
 	uint8_t			comm;
 
 	const struct ad_sigma_delta_info *info;
+	unsigned int		active_slots;
+	unsigned int		current_slot;
+	unsigned int		num_slots;
+	bool			status_appended;
+	/* map slots to channels in order to know what to expect from devices */
+	unsigned int		*slots;
+	uint8_t			*samples_buf;
 
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
@@ -97,6 +112,29 @@ static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd,
 	return 0;
 }
 
+static inline int ad_sigma_delta_append_status(struct ad_sigma_delta *sd, bool append)
+{
+	int ret;
+
+	if (sd->info->append_status) {
+		ret = sd->info->append_status(sd, append);
+		if (ret < 0)
+			return ret;
+
+		sd->status_appended = append;
+	}
+
+	return 0;
+}
+
+static inline int ad_sigma_delta_disable_all(struct ad_sigma_delta *sd)
+{
+	if (sd->info->disable_all)
+		return sd->info->disable_all(sd);
+
+	return 0;
+}
+
 static inline int ad_sigma_delta_set_mode(struct ad_sigma_delta *sd,
 	unsigned int mode)
 {
-- 
cgit v1.2.3


From e87f4152e542610d0b4c6c8548964a68a59d2040 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Wed, 23 Mar 2022 20:02:41 +0100
Subject: task_stack, x86/cea: Force-inline stack helpers

Force-inline two stack helpers to fix the following objtool warnings:

  vmlinux.o: warning: objtool: in_task_stack()+0xc: call to task_stack_page() leaves .noinstr.text section
  vmlinux.o: warning: objtool: in_entry_stack()+0x10: call to cpu_entry_stack() leaves .noinstr.text section

Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220324183607.31717-2-bp@alien8.de
---
 arch/x86/include/asm/cpu_entry_area.h | 2 +-
 include/linux/sched/task_stack.h      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index dd5ea1bdf04c..75efc4c6f076 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -143,7 +143,7 @@ extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
 
 extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
 
-static inline struct entry_stack *cpu_entry_stack(int cpu)
+static __always_inline struct entry_stack *cpu_entry_stack(int cpu)
 {
 	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
 }
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index 892562ebbd3a..5e799a47431e 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -16,7 +16,7 @@
  * try_get_task_stack() instead.  task_stack_page will return a pointer
  * that could get freed out from under you.
  */
-static inline void *task_stack_page(const struct task_struct *task)
+static __always_inline void *task_stack_page(const struct task_struct *task)
 {
 	return task->stack;
 }
-- 
cgit v1.2.3


From f0e3c6261af183f0c2246cfe691abec78377622c Mon Sep 17 00:00:00 2001
From: Johnson Wang <johnson.wang@mediatek.com>
Date: Fri, 1 Apr 2022 16:02:11 +0800
Subject: regulator: mt6366: Add support for MT6366 regulator

The MT6366 is a regulator found on boards based on MediaTek MT8186 and
probably other SoCs. It is a so called pmic and connects as a slave to
SoC using SPI, wrapped inside the pmic-wrapper.

Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Johnson Wang <johnson.wang@mediatek.com>
Link: https://lore.kernel.org/r/20220401080212.27383-2-johnson.wang@mediatek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/mt6358-regulator.c       | 213 ++++++++++++++++++++++++++++-
 include/linux/regulator/mt6358-regulator.h |  45 ++++++
 2 files changed, 253 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/regulator/mt6358-regulator.c b/drivers/regulator/mt6358-regulator.c
index eb8027813b99..8a5ce990f1bf 100644
--- a/drivers/regulator/mt6358-regulator.c
+++ b/drivers/regulator/mt6358-regulator.c
@@ -130,6 +130,102 @@ struct mt6358_regulator_info {
 	.qi = BIT(15),							\
 }
 
+#define MT6366_BUCK(match, vreg, min, max, step,		\
+	volt_ranges, vosel_mask, _da_vsel_reg, _da_vsel_mask,	\
+	_modeset_reg, _modeset_shift)		\
+[MT6366_ID_##vreg] = {	\
+	.desc = {	\
+		.name = #vreg,	\
+		.of_match = of_match_ptr(match),	\
+		.ops = &mt6358_volt_range_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = MT6366_ID_##vreg,		\
+		.owner = THIS_MODULE,		\
+		.n_voltages = ((max) - (min)) / (step) + 1,	\
+		.linear_ranges = volt_ranges,		\
+		.n_linear_ranges = ARRAY_SIZE(volt_ranges),	\
+		.vsel_reg = MT6358_BUCK_##vreg##_ELR0,	\
+		.vsel_mask = vosel_mask,	\
+		.enable_reg = MT6358_BUCK_##vreg##_CON0,	\
+		.enable_mask = BIT(0),	\
+		.of_map_mode = mt6358_map_mode,	\
+	},	\
+	.status_reg = MT6358_BUCK_##vreg##_DBG1,	\
+	.qi = BIT(0),	\
+	.da_vsel_reg = _da_vsel_reg,	\
+	.da_vsel_mask = _da_vsel_mask,	\
+	.modeset_reg = _modeset_reg,	\
+	.modeset_mask = BIT(_modeset_shift),	\
+}
+
+#define MT6366_LDO(match, vreg, ldo_volt_table,	\
+	ldo_index_table, enreg, enbit, vosel,	\
+	vosel_mask)	\
+[MT6366_ID_##vreg] = {	\
+	.desc = {	\
+		.name = #vreg,	\
+		.of_match = of_match_ptr(match),	\
+		.ops = &mt6358_volt_table_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = MT6366_ID_##vreg,	\
+		.owner = THIS_MODULE,	\
+		.n_voltages = ARRAY_SIZE(ldo_volt_table),	\
+		.volt_table = ldo_volt_table,	\
+		.vsel_reg = vosel,	\
+		.vsel_mask = vosel_mask,	\
+		.enable_reg = enreg,	\
+		.enable_mask = BIT(enbit),	\
+	},	\
+	.status_reg = MT6358_LDO_##vreg##_CON1,	\
+	.qi = BIT(15),	\
+	.index_table = ldo_index_table,	\
+	.n_table = ARRAY_SIZE(ldo_index_table),	\
+}
+
+#define MT6366_LDO1(match, vreg, min, max, step,	\
+	volt_ranges, _da_vsel_reg, _da_vsel_mask,	\
+	vosel, vosel_mask)	\
+[MT6366_ID_##vreg] = {	\
+	.desc = {	\
+		.name = #vreg,	\
+		.of_match = of_match_ptr(match),	\
+		.ops = &mt6358_volt_range_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = MT6366_ID_##vreg,	\
+		.owner = THIS_MODULE,	\
+		.n_voltages = ((max) - (min)) / (step) + 1,	\
+		.linear_ranges = volt_ranges,	\
+		.n_linear_ranges = ARRAY_SIZE(volt_ranges),	\
+		.vsel_reg = vosel,	\
+		.vsel_mask = vosel_mask,	\
+		.enable_reg = MT6358_LDO_##vreg##_CON0,	\
+		.enable_mask = BIT(0),	\
+	},	\
+	.da_vsel_reg = _da_vsel_reg,	\
+	.da_vsel_mask = _da_vsel_mask,	\
+	.status_reg = MT6358_LDO_##vreg##_DBG1,	\
+	.qi = BIT(0),	\
+}
+
+#define MT6366_REG_FIXED(match, vreg,	\
+	enreg, enbit, volt)	\
+[MT6366_ID_##vreg] = {	\
+	.desc = {	\
+		.name = #vreg,	\
+		.of_match = of_match_ptr(match),	\
+		.ops = &mt6358_volt_fixed_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = MT6366_ID_##vreg,	\
+		.owner = THIS_MODULE,	\
+		.n_voltages = 1,	\
+		.enable_reg = enreg,	\
+		.enable_mask = BIT(enbit),	\
+		.min_uV = volt,	\
+	},	\
+	.status_reg = MT6358_LDO_##vreg##_CON1,	\
+	.qi = BIT(15),							\
+}
+
 static const struct linear_range buck_volt_range1[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0, 0x7f, 6250),
 };
@@ -409,6 +505,9 @@ static struct mt6358_regulator_info mt6358_regulators[] = {
 	MT6358_BUCK("buck_vcore", VCORE, 500000, 1293750, 6250,
 		    buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f,
 		    MT6358_VCORE_VGPU_ANA_CON0, 1),
+	MT6358_BUCK("buck_vcore_sshub", VCORE_SSHUB, 500000, 1293750, 6250,
+		    buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_SSHUB_ELR0, 0x7f,
+		    MT6358_VCORE_VGPU_ANA_CON0, 1),
 	MT6358_BUCK("buck_vpa", VPA, 500000, 3650000, 50000,
 		    buck_volt_range3, 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f,
 		    MT6358_VPA_ANA_CON0, 3),
@@ -488,6 +587,10 @@ static struct mt6358_regulator_info mt6358_regulators[] = {
 	MT6358_LDO1("ldo_vsram_others", VSRAM_OTHERS, 500000, 1293750, 6250,
 		    buck_volt_range1, MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00,
 		    MT6358_LDO_VSRAM_CON2, 0x7f),
+	MT6358_LDO1("ldo_vsram_others_sshub", VSRAM_OTHERS_SSHUB, 500000,
+		    1293750, 6250, buck_volt_range1,
+		    MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f,
+		    MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f),
 	MT6358_LDO1("ldo_vsram_gpu", VSRAM_GPU, 500000, 1293750, 6250,
 		    buck_volt_range1, MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00,
 		    MT6358_LDO_VSRAM_CON3, 0x7f),
@@ -496,24 +599,124 @@ static struct mt6358_regulator_info mt6358_regulators[] = {
 		    MT6358_LDO_VSRAM_CON1, 0x7f),
 };
 
+/* The array is indexed by id(MT6366_ID_XXX) */
+static struct mt6358_regulator_info mt6366_regulators[] = {
+	MT6366_BUCK("buck_vdram1", VDRAM1, 500000, 2087500, 12500,
+		    buck_volt_range2, 0x7f, MT6358_BUCK_VDRAM1_DBG0, 0x7f,
+		    MT6358_VDRAM1_ANA_CON0, 8),
+	MT6366_BUCK("buck_vcore", VCORE, 500000, 1293750, 6250,
+		    buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f,
+		    MT6358_VCORE_VGPU_ANA_CON0, 1),
+	MT6366_BUCK("buck_vcore_sshub", VCORE_SSHUB, 500000, 1293750, 6250,
+		    buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_SSHUB_ELR0, 0x7f,
+		    MT6358_VCORE_VGPU_ANA_CON0, 1),
+	MT6366_BUCK("buck_vpa", VPA, 500000, 3650000, 50000,
+		    buck_volt_range3, 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f,
+		    MT6358_VPA_ANA_CON0, 3),
+	MT6366_BUCK("buck_vproc11", VPROC11, 500000, 1293750, 6250,
+		    buck_volt_range1, 0x7f, MT6358_BUCK_VPROC11_DBG0, 0x7f,
+		    MT6358_VPROC_ANA_CON0, 1),
+	MT6366_BUCK("buck_vproc12", VPROC12, 500000, 1293750, 6250,
+		    buck_volt_range1, 0x7f, MT6358_BUCK_VPROC12_DBG0, 0x7f,
+		    MT6358_VPROC_ANA_CON0, 2),
+	MT6366_BUCK("buck_vgpu", VGPU, 500000, 1293750, 6250,
+		    buck_volt_range1, 0x7f, MT6358_BUCK_VGPU_ELR0, 0x7f,
+		    MT6358_VCORE_VGPU_ANA_CON0, 2),
+	MT6366_BUCK("buck_vs2", VS2, 500000, 2087500, 12500,
+		    buck_volt_range2, 0x7f, MT6358_BUCK_VS2_DBG0, 0x7f,
+		    MT6358_VS2_ANA_CON0, 8),
+	MT6366_BUCK("buck_vmodem", VMODEM, 500000, 1293750, 6250,
+		    buck_volt_range1, 0x7f, MT6358_BUCK_VMODEM_DBG0, 0x7f,
+		    MT6358_VMODEM_ANA_CON0, 8),
+	MT6366_BUCK("buck_vs1", VS1, 1000000, 2587500, 12500,
+		    buck_volt_range4, 0x7f, MT6358_BUCK_VS1_DBG0, 0x7f,
+		    MT6358_VS1_ANA_CON0, 8),
+	MT6366_REG_FIXED("ldo_vrf12", VRF12,
+			 MT6358_LDO_VRF12_CON0, 0, 1200000),
+	MT6366_REG_FIXED("ldo_vio18", VIO18,
+			 MT6358_LDO_VIO18_CON0, 0, 1800000),
+	MT6366_REG_FIXED("ldo_vcn18", VCN18, MT6358_LDO_VCN18_CON0, 0, 1800000),
+	MT6366_REG_FIXED("ldo_vfe28", VFE28, MT6358_LDO_VFE28_CON0, 0, 2800000),
+	MT6366_REG_FIXED("ldo_vcn28", VCN28, MT6358_LDO_VCN28_CON0, 0, 2800000),
+	MT6366_REG_FIXED("ldo_vxo22", VXO22, MT6358_LDO_VXO22_CON0, 0, 2200000),
+	MT6366_REG_FIXED("ldo_vaux18", VAUX18,
+			 MT6358_LDO_VAUX18_CON0, 0, 1800000),
+	MT6366_REG_FIXED("ldo_vbif28", VBIF28,
+			 MT6358_LDO_VBIF28_CON0, 0, 2800000),
+	MT6366_REG_FIXED("ldo_vio28", VIO28, MT6358_LDO_VIO28_CON0, 0, 2800000),
+	MT6366_REG_FIXED("ldo_va12", VA12, MT6358_LDO_VA12_CON0, 0, 1200000),
+	MT6366_REG_FIXED("ldo_vrf18", VRF18, MT6358_LDO_VRF18_CON0, 0, 1800000),
+	MT6366_REG_FIXED("ldo_vaud28", VAUD28,
+			 MT6358_LDO_VAUD28_CON0, 0, 2800000),
+	MT6366_LDO("ldo_vdram2", VDRAM2, vdram2_voltages, vdram2_idx,
+		   MT6358_LDO_VDRAM2_CON0, 0, MT6358_LDO_VDRAM2_ELR0, 0x10),
+	MT6366_LDO("ldo_vsim1", VSIM1, vsim_voltages, vsim_idx,
+		   MT6358_LDO_VSIM1_CON0, 0, MT6358_VSIM1_ANA_CON0, 0xf00),
+	MT6366_LDO("ldo_vibr", VIBR, vibr_voltages, vibr_idx,
+		   MT6358_LDO_VIBR_CON0, 0, MT6358_VIBR_ANA_CON0, 0xf00),
+	MT6366_LDO("ldo_vusb", VUSB, vusb_voltages, vusb_idx,
+		   MT6358_LDO_VUSB_CON0_0, 0, MT6358_VUSB_ANA_CON0, 0x700),
+	MT6366_LDO("ldo_vefuse", VEFUSE, vefuse_voltages, vefuse_idx,
+		   MT6358_LDO_VEFUSE_CON0, 0, MT6358_VEFUSE_ANA_CON0, 0xf00),
+	MT6366_LDO("ldo_vmch", VMCH, vmch_vemc_voltages, vmch_vemc_idx,
+		   MT6358_LDO_VMCH_CON0, 0, MT6358_VMCH_ANA_CON0, 0x700),
+	MT6366_LDO("ldo_vemc", VEMC, vmch_vemc_voltages, vmch_vemc_idx,
+		   MT6358_LDO_VEMC_CON0, 0, MT6358_VEMC_ANA_CON0, 0x700),
+	MT6366_LDO("ldo_vcn33_bt", VCN33_BT, vcn33_bt_wifi_voltages,
+		   vcn33_bt_wifi_idx, MT6358_LDO_VCN33_CON0_0,
+		   0, MT6358_VCN33_ANA_CON0, 0x300),
+	MT6366_LDO("ldo_vcn33_wifi", VCN33_WIFI, vcn33_bt_wifi_voltages,
+		   vcn33_bt_wifi_idx, MT6358_LDO_VCN33_CON0_1,
+		   0, MT6358_VCN33_ANA_CON0, 0x300),
+	MT6366_LDO("ldo_vmc", VMC, vmc_voltages, vmc_idx,
+		   MT6358_LDO_VMC_CON0, 0, MT6358_VMC_ANA_CON0, 0xf00),
+	MT6366_LDO("ldo_vsim2", VSIM2, vsim_voltages, vsim_idx,
+		   MT6358_LDO_VSIM2_CON0, 0, MT6358_VSIM2_ANA_CON0, 0xf00),
+	MT6366_LDO1("ldo_vsram_proc11", VSRAM_PROC11, 500000, 1293750, 6250,
+		    buck_volt_range1, MT6358_LDO_VSRAM_PROC11_DBG0, 0x7f00,
+		    MT6358_LDO_VSRAM_CON0, 0x7f),
+	MT6366_LDO1("ldo_vsram_others", VSRAM_OTHERS, 500000, 1293750, 6250,
+		    buck_volt_range1, MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00,
+		    MT6358_LDO_VSRAM_CON2, 0x7f),
+	MT6366_LDO1("ldo_vsram_others_sshub", VSRAM_OTHERS_SSHUB, 500000,
+		    1293750, 6250, buck_volt_range1,
+		    MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f,
+		    MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f),
+	MT6366_LDO1("ldo_vsram_gpu", VSRAM_GPU, 500000, 1293750, 6250,
+		    buck_volt_range1, MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00,
+		    MT6358_LDO_VSRAM_CON3, 0x7f),
+	MT6366_LDO1("ldo_vsram_proc12", VSRAM_PROC12, 500000, 1293750, 6250,
+		    buck_volt_range1, MT6358_LDO_VSRAM_PROC12_DBG0, 0x7f00,
+		    MT6358_LDO_VSRAM_CON1, 0x7f),
+};
+
 static int mt6358_regulator_probe(struct platform_device *pdev)
 {
 	struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent);
 	struct regulator_config config = {};
 	struct regulator_dev *rdev;
-	int i;
+	struct mt6358_regulator_info *mt6358_info;
+	int i, max_regulator;
+
+	if (mt6397->chip_id == MT6366_CHIP_ID) {
+		max_regulator = MT6366_MAX_REGULATOR;
+		mt6358_info = mt6366_regulators;
+	} else {
+		max_regulator = MT6358_MAX_REGULATOR;
+		mt6358_info = mt6358_regulators;
+	}
 
-	for (i = 0; i < MT6358_MAX_REGULATOR; i++) {
+	for (i = 0; i < max_regulator; i++) {
 		config.dev = &pdev->dev;
-		config.driver_data = &mt6358_regulators[i];
+		config.driver_data = &mt6358_info[i];
 		config.regmap = mt6397->regmap;
 
 		rdev = devm_regulator_register(&pdev->dev,
-					       &mt6358_regulators[i].desc,
+					       &mt6358_info[i].desc,
 					       &config);
 		if (IS_ERR(rdev)) {
 			dev_err(&pdev->dev, "failed to register %s\n",
-				mt6358_regulators[i].desc.name);
+				mt6358_info[i].desc.name);
 			return PTR_ERR(rdev);
 		}
 	}
diff --git a/include/linux/regulator/mt6358-regulator.h b/include/linux/regulator/mt6358-regulator.h
index 1cc304946d09..bdcf83cd719e 100644
--- a/include/linux/regulator/mt6358-regulator.h
+++ b/include/linux/regulator/mt6358-regulator.h
@@ -48,9 +48,54 @@ enum {
 	MT6358_ID_VLDO28,
 	MT6358_ID_VAUD28,
 	MT6358_ID_VSIM2,
+	MT6358_ID_VCORE_SSHUB,
+	MT6358_ID_VSRAM_OTHERS_SSHUB,
 	MT6358_ID_RG_MAX,
 };
 
+enum {
+	MT6366_ID_VDRAM1 = 0,
+	MT6366_ID_VCORE,
+	MT6366_ID_VPA,
+	MT6366_ID_VPROC11,
+	MT6366_ID_VPROC12,
+	MT6366_ID_VGPU,
+	MT6366_ID_VS2,
+	MT6366_ID_VMODEM,
+	MT6366_ID_VS1,
+	MT6366_ID_VDRAM2,
+	MT6366_ID_VSIM1,
+	MT6366_ID_VIBR,
+	MT6366_ID_VRF12,
+	MT6366_ID_VIO18,
+	MT6366_ID_VUSB,
+	MT6366_ID_VCN18,
+	MT6366_ID_VFE28,
+	MT6366_ID_VSRAM_PROC11,
+	MT6366_ID_VCN28,
+	MT6366_ID_VSRAM_OTHERS,
+	MT6366_ID_VSRAM_GPU,
+	MT6366_ID_VXO22,
+	MT6366_ID_VEFUSE,
+	MT6366_ID_VAUX18,
+	MT6366_ID_VMCH,
+	MT6366_ID_VBIF28,
+	MT6366_ID_VSRAM_PROC12,
+	MT6366_ID_VEMC,
+	MT6366_ID_VIO28,
+	MT6366_ID_VA12,
+	MT6366_ID_VRF18,
+	MT6366_ID_VCN33_BT,
+	MT6366_ID_VCN33_WIFI,
+	MT6366_ID_VMC,
+	MT6366_ID_VAUD28,
+	MT6366_ID_VSIM2,
+	MT6366_ID_VCORE_SSHUB,
+	MT6366_ID_VSRAM_OTHERS_SSHUB,
+	MT6366_ID_RG_MAX,
+};
+
 #define MT6358_MAX_REGULATOR	MT6358_ID_RG_MAX
+#define MT6366_MAX_REGULATOR	MT6366_ID_RG_MAX
 
 #endif /* __LINUX_REGULATOR_MT6358_H */
-- 
cgit v1.2.3


From 8b023accc8df70e72f7704d29fead7ca914d6837 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Mon, 14 Mar 2022 15:19:03 -0700
Subject: lockdep: Fix -Wunused-parameter for _THIS_IP_

While looking into a bug related to the compiler's handling of addresses
of labels, I noticed some uses of _THIS_IP_ seemed unused in lockdep.
Drive by cleanup.

-Wunused-parameter:
kernel/locking/lockdep.c:1383:22: warning: unused parameter 'ip'
kernel/locking/lockdep.c:4246:48: warning: unused parameter 'ip'
kernel/locking/lockdep.c:4844:19: warning: unused parameter 'ip'

Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20220314221909.2027027-1-ndesaulniers@google.com
---
 arch/arm64/kernel/entry-common.c |  8 ++++----
 include/linux/irqflags.h         |  4 ++--
 include/linux/kvm_host.h         |  2 +-
 kernel/entry/common.c            |  6 +++---
 kernel/locking/lockdep.c         | 22 ++++++++--------------
 kernel/sched/idle.c              |  2 +-
 kernel/trace/trace_preemptirq.c  |  4 ++--
 7 files changed, 21 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 878c65aa7206..e04602ea4629 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -75,7 +75,7 @@ static __always_inline void __exit_to_kernel_mode(struct pt_regs *regs)
 	if (interrupts_enabled(regs)) {
 		if (regs->exit_rcu) {
 			trace_hardirqs_on_prepare();
-			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			lockdep_hardirqs_on_prepare();
 			rcu_irq_exit();
 			lockdep_hardirqs_on(CALLER_ADDR0);
 			return;
@@ -121,7 +121,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
 static __always_inline void __exit_to_user_mode(void)
 {
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	user_enter_irqoff();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
@@ -179,7 +179,7 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs)
 	ftrace_nmi_exit();
 	if (restore) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 
 	rcu_nmi_exit();
@@ -215,7 +215,7 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
 
 	if (restore) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 
 	rcu_nmi_exit();
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 4b140938b03e..5ec0fa71399e 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -20,13 +20,13 @@
 #ifdef CONFIG_PROVE_LOCKING
   extern void lockdep_softirqs_on(unsigned long ip);
   extern void lockdep_softirqs_off(unsigned long ip);
-  extern void lockdep_hardirqs_on_prepare(unsigned long ip);
+  extern void lockdep_hardirqs_on_prepare(void);
   extern void lockdep_hardirqs_on(unsigned long ip);
   extern void lockdep_hardirqs_off(unsigned long ip);
 #else
   static inline void lockdep_softirqs_on(unsigned long ip) { }
   static inline void lockdep_softirqs_off(unsigned long ip) { }
-  static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { }
+  static inline void lockdep_hardirqs_on_prepare(void) { }
   static inline void lockdep_hardirqs_on(unsigned long ip) { }
   static inline void lockdep_hardirqs_off(unsigned long ip) { }
 #endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3f9b22c4983a..e1b2413750c0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -450,7 +450,7 @@ static __always_inline void guest_state_enter_irqoff(void)
 {
 	instrumentation_begin();
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
 	guest_context_enter_irqoff();
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index e57a224d6b79..2eef7b22e02a 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -126,7 +126,7 @@ static __always_inline void __exit_to_user_mode(void)
 {
 	instrumentation_begin();
 	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
 	user_enter_irqoff();
@@ -416,7 +416,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 			instrumentation_begin();
 			/* Tell the tracer that IRET will enable interrupts */
 			trace_hardirqs_on_prepare();
-			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			lockdep_hardirqs_on_prepare();
 			instrumentation_end();
 			rcu_irq_exit();
 			lockdep_hardirqs_on(CALLER_ADDR0);
@@ -465,7 +465,7 @@ void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
 	ftrace_nmi_exit();
 	if (irq_state.lockdep) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 	instrumentation_end();
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c06cab6546ed..3cbd49216174 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1380,7 +1380,7 @@ static struct lock_list *alloc_list_entry(void)
  */
 static int add_lock_to_list(struct lock_class *this,
 			    struct lock_class *links_to, struct list_head *head,
-			    unsigned long ip, u16 distance, u8 dep,
+			    u16 distance, u8 dep,
 			    const struct lock_trace *trace)
 {
 	struct lock_list *entry;
@@ -3133,19 +3133,15 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * to the previous lock's dependency list:
 	 */
 	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
-			       &hlock_class(prev)->locks_after,
-			       next->acquire_ip, distance,
-			       calc_dep(prev, next),
-			       *trace);
+			       &hlock_class(prev)->locks_after, distance,
+			       calc_dep(prev, next), *trace);
 
 	if (!ret)
 		return 0;
 
 	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
-			       &hlock_class(next)->locks_before,
-			       next->acquire_ip, distance,
-			       calc_depb(prev, next),
-			       *trace);
+			       &hlock_class(next)->locks_before, distance,
+			       calc_depb(prev, next), *trace);
 	if (!ret)
 		return 0;
 
@@ -4236,14 +4232,13 @@ static void __trace_hardirqs_on_caller(void)
 
 /**
  * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts
- * @ip:		Caller address
  *
  * Invoked before a possible transition to RCU idle from exit to user or
  * guest mode. This ensures that all RCU operations are done before RCU
  * stops watching. After the RCU transition lockdep_hardirqs_on() has to be
  * invoked to set the final state.
  */
-void lockdep_hardirqs_on_prepare(unsigned long ip)
+void lockdep_hardirqs_on_prepare(void)
 {
 	if (unlikely(!debug_locks))
 		return;
@@ -4840,8 +4835,7 @@ EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
 
 static void
 print_lock_nested_lock_not_held(struct task_struct *curr,
-				struct held_lock *hlock,
-				unsigned long ip)
+				struct held_lock *hlock)
 {
 	if (!debug_locks_off())
 		return;
@@ -5017,7 +5011,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	chain_key = iterate_chain_key(chain_key, hlock_id(hlock));
 
 	if (nest_lock && !__lock_is_held(nest_lock, -1)) {
-		print_lock_nested_lock_not_held(curr, hlock, ip);
+		print_lock_nested_lock_not_held(curr, hlock);
 		return 0;
 	}
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8f8b5020e76a..3984dd21a5aa 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -102,7 +102,7 @@ void __cpuidle default_idle_call(void)
 		 * last -- this is very similar to the entry code.
 		 */
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(_THIS_IP_);
+		lockdep_hardirqs_on_prepare();
 		rcu_idle_enter();
 		lockdep_hardirqs_on(_THIS_IP_);
 
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index f4938040c228..95b58bd757ce 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -46,7 +46,7 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
@@ -94,7 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
-- 
cgit v1.2.3


From bfe4daf850f45d92dcd3da477f0b0456620294c3 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Tue, 22 Mar 2022 15:15:05 -0700
Subject: perf/core: Add perf_clear_branch_entry_bitfields() helper

Make it simpler to reset all the info fields on the
perf_branch_entry by adding a helper inline function.

The goal is to centralize the initialization to avoid missing
a field in case more are added.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-2-eranian@google.com
---
 arch/x86/events/intel/lbr.c | 36 +++++++++++++++++-------------------
 include/linux/perf_event.h  | 16 ++++++++++++++++
 2 files changed, 33 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index fe1742c4ca49..13179f31fe10 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -769,6 +769,7 @@ void intel_pmu_lbr_disable_all(void)
 void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 {
 	unsigned long mask = x86_pmu.lbr_nr - 1;
+	struct perf_branch_entry *br = cpuc->lbr_entries;
 	u64 tos = intel_pmu_lbr_tos();
 	int i;
 
@@ -784,15 +785,11 @@ void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
-		cpuc->lbr_entries[i].from	= msr_lastbranch.from;
-		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
-		cpuc->lbr_entries[i].mispred	= 0;
-		cpuc->lbr_entries[i].predicted	= 0;
-		cpuc->lbr_entries[i].in_tx	= 0;
-		cpuc->lbr_entries[i].abort	= 0;
-		cpuc->lbr_entries[i].cycles	= 0;
-		cpuc->lbr_entries[i].type	= 0;
-		cpuc->lbr_entries[i].reserved	= 0;
+		perf_clear_branch_entry_bitfields(br);
+
+		br->from	= msr_lastbranch.from;
+		br->to		= msr_lastbranch.to;
+		br++;
 	}
 	cpuc->lbr_stack.nr = i;
 	cpuc->lbr_stack.hw_idx = tos;
@@ -807,6 +804,7 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
 	bool need_info = false, call_stack = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
+	struct perf_branch_entry *br = cpuc->lbr_entries;
 	u64 tos = intel_pmu_lbr_tos();
 	int i;
 	int out = 0;
@@ -878,15 +876,14 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		if (abort && x86_pmu.lbr_double_abort && out > 0)
 			out--;
 
-		cpuc->lbr_entries[out].from	 = from;
-		cpuc->lbr_entries[out].to	 = to;
-		cpuc->lbr_entries[out].mispred	 = mis;
-		cpuc->lbr_entries[out].predicted = pred;
-		cpuc->lbr_entries[out].in_tx	 = in_tx;
-		cpuc->lbr_entries[out].abort	 = abort;
-		cpuc->lbr_entries[out].cycles	 = cycles;
-		cpuc->lbr_entries[out].type	 = 0;
-		cpuc->lbr_entries[out].reserved	 = 0;
+		perf_clear_branch_entry_bitfields(br+out);
+		br[out].from	 = from;
+		br[out].to	 = to;
+		br[out].mispred	 = mis;
+		br[out].predicted = pred;
+		br[out].in_tx	 = in_tx;
+		br[out].abort	 = abort;
+		br[out].cycles	 = cycles;
 		out++;
 	}
 	cpuc->lbr_stack.nr = out;
@@ -951,6 +948,8 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		to = rdlbr_to(i, lbr);
 		info = rdlbr_info(i, lbr);
 
+		perf_clear_branch_entry_bitfields(e);
+
 		e->from		= from;
 		e->to		= to;
 		e->mispred	= get_lbr_mispred(info);
@@ -959,7 +958,6 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		e->abort	= !!(info & LBR_INFO_ABORT);
 		e->cycles	= get_lbr_cycles(info);
 		e->type		= get_lbr_br_type(info);
-		e->reserved	= 0;
 	}
 
 	cpuc->lbr_stack.nr = i;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index af97dd427501..a411080d5169 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1063,6 +1063,22 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->txn = 0;
 }
 
+/*
+ * Clear all bitfields in the perf_branch_entry.
+ * The to and from fields are not cleared because they are
+ * systematically modified by caller.
+ */
+static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br)
+{
+	br->mispred = 0;
+	br->predicted = 0;
+	br->in_tx = 0;
+	br->abort = 0;
+	br->cycles = 0;
+	br->type = 0;
+	br->reserved = 0;
+}
+
 extern void perf_output_sample(struct perf_output_handle *handle,
 			       struct perf_event_header *header,
 			       struct perf_sample_data *data,
-- 
cgit v1.2.3


From 2a606a18cd672a16343d146a126721b34cc6adbd Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Tue, 22 Mar 2022 15:15:12 -0700
Subject: ACPI: Add perf low power callback

Add an optional callback needed by some PMU features, e.g., AMD
BRS, to give a chance to the perf_events code to change its state before
a CPU goes to low power and after it comes back.

The callback is void when the PERF_NEEDS_LOPWR_CB flag is not set.
This flag must be set in arch specific perf_event.h header whenever needed.
When not set, there is no impact on the ACPI code.

Signed-off-by: Stephane Eranian <eranian@google.com>
[peterz: build fix]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-9-eranian@google.com
---
 drivers/acpi/acpi_pad.c       | 7 +++++++
 drivers/acpi/processor_idle.c | 5 +++++
 include/linux/perf_event.h    | 6 ++++++
 3 files changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index f45979aa2d64..ec0e22a1e25d 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -17,6 +17,7 @@
 #include <linux/tick.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/perf_event.h>
 #include <asm/mwait.h>
 #include <xen/xen.h>
 
@@ -164,6 +165,9 @@ static int power_saving_thread(void *data)
 				tsc_marked_unstable = 1;
 			}
 			local_irq_disable();
+
+			perf_lopwr_cb(true);
+
 			tick_broadcast_enable();
 			tick_broadcast_enter();
 			stop_critical_timings();
@@ -172,6 +176,9 @@ static int power_saving_thread(void *data)
 
 			start_critical_timings();
 			tick_broadcast_exit();
+
+			perf_lopwr_cb(false);
+
 			local_irq_enable();
 
 			if (time_before(expire_time, jiffies)) {
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 32b20efff5f8..05dc0e148f02 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -21,6 +21,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpu.h>
 #include <linux/minmax.h>
+#include <linux/perf_event.h>
 #include <acpi/processor.h>
 
 /*
@@ -549,6 +550,8 @@ static void wait_for_freeze(void)
  */
 static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
 {
+	perf_lopwr_cb(true);
+
 	if (cx->entry_method == ACPI_CSTATE_FFH) {
 		/* Call into architectural FFH based C-state */
 		acpi_processor_ffh_cstate_enter(cx);
@@ -559,6 +562,8 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
 		inb(cx->address);
 		wait_for_freeze();
 	}
+
+	perf_lopwr_cb(false);
 }
 
 /**
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a411080d5169..da759560eec5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1676,4 +1676,10 @@ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries,
 					   unsigned int cnt);
 DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
 
+#ifndef PERF_NEEDS_LOPWR_CB
+static inline void perf_lopwr_cb(bool mode)
+{
+}
+#endif
+
 #endif /* _LINUX_PERF_EVENT_H */
-- 
cgit v1.2.3


From cfe43f478b79ba45573ca22d52d0d8823be068fa Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Fri, 12 Nov 2021 18:52:01 +0000
Subject: preempt/dynamic: Introduce preemption model accessors

CONFIG_PREEMPT{_NONE, _VOLUNTARY} designate either:
o The build-time preemption model when !PREEMPT_DYNAMIC
o The default boot-time preemption model when PREEMPT_DYNAMIC

IOW, using those on PREEMPT_DYNAMIC kernels is meaningless - the actual
model could have been set to something else by the "preempt=foo" cmdline
parameter. Same problem applies to CONFIG_PREEMPTION.

Introduce a set of helpers to determine the actual preemption model used by
the live kernel.

Suggested-by: Marco Elver <elver@google.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Marco Elver <elver@google.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20211112185203.280040-3-valentin.schneider@arm.com
---
 include/linux/sched.h | 41 +++++++++++++++++++++++++++++++++++++++++
 kernel/sched/core.c   | 12 ++++++++++++
 2 files changed, 53 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d5e3c00b74e1..67f06f72c50e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2117,6 +2117,47 @@ static inline void cond_resched_rcu(void)
 #endif
 }
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+
+extern bool preempt_model_none(void);
+extern bool preempt_model_voluntary(void);
+extern bool preempt_model_full(void);
+
+#else
+
+static inline bool preempt_model_none(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_NONE);
+}
+static inline bool preempt_model_voluntary(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
+}
+static inline bool preempt_model_full(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT);
+}
+
+#endif
+
+static inline bool preempt_model_rt(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_RT);
+}
+
+/*
+ * Does the preemption model allow non-cooperative preemption?
+ *
+ * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with
+ * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the
+ * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the
+ * PREEMPT_NONE model.
+ */
+static inline bool preempt_model_preemptible(void)
+{
+	return preempt_model_full() || preempt_model_rt();
+}
+
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d575b4914925..068c088e9584 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8409,6 +8409,18 @@ static void __init preempt_dynamic_init(void)
 	}
 }
 
+#define PREEMPT_MODEL_ACCESSOR(mode) \
+	bool preempt_model_##mode(void)						 \
+	{									 \
+		WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \
+		return preempt_dynamic_mode == preempt_dynamic_##mode;		 \
+	}									 \
+	EXPORT_SYMBOL_GPL(preempt_model_##mode)
+
+PREEMPT_MODEL_ACCESSOR(none);
+PREEMPT_MODEL_ACCESSOR(voluntary);
+PREEMPT_MODEL_ACCESSOR(full);
+
 #else /* !CONFIG_PREEMPT_DYNAMIC */
 
 static inline void preempt_dynamic_init(void) { }
-- 
cgit v1.2.3


From 8c756a0a2de17f1535ef885ac7e556e016735eb2 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Thu, 31 Mar 2022 15:54:47 +0300
Subject: device property: Convert device_{dma_supported,get_dma_attr} to
 fwnode

Make the device_dma_supported and device_get_dma_attr functions to use the
fwnode ops, and move the implementation to ACPI and OF frameworks.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c | 14 ++++++++++++++
 drivers/base/property.c | 25 ++++---------------------
 drivers/of/property.c   | 17 +++++++++++++++++
 include/linux/fwnode.h  |  3 +++
 4 files changed, 38 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 12bbfe833609..24983c379aba 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1256,6 +1256,17 @@ static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode)
 	return acpi_device_is_present(to_acpi_device_node(fwnode));
 }
 
+static bool acpi_fwnode_device_dma_supported(const struct fwnode_handle *fwnode)
+{
+	return acpi_dma_supported(to_acpi_device_node(fwnode));
+}
+
+static enum dev_dma_attr
+acpi_fwnode_device_get_dma_attr(const struct fwnode_handle *fwnode)
+{
+	return acpi_get_dma_attr(to_acpi_device_node(fwnode));
+}
+
 static bool acpi_fwnode_property_present(const struct fwnode_handle *fwnode,
 					 const char *propname)
 {
@@ -1387,6 +1398,9 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 	const struct fwnode_operations ops = {				\
 		.device_is_available = acpi_fwnode_device_is_available, \
 		.device_get_match_data = acpi_fwnode_device_get_match_data, \
+		.device_dma_supported =				\
+			acpi_fwnode_device_dma_supported,		\
+		.device_get_dma_attr = acpi_fwnode_device_get_dma_attr,	\
 		.property_present = acpi_fwnode_property_present,	\
 		.property_read_int_array =				\
 			acpi_fwnode_property_read_int_array,		\
diff --git a/drivers/base/property.c b/drivers/base/property.c
index c0e94cce9c29..09686e2e903e 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -823,33 +823,16 @@ EXPORT_SYMBOL_GPL(device_get_child_node_count);
 
 bool device_dma_supported(struct device *dev)
 {
-	const struct fwnode_handle *fwnode = dev_fwnode(dev);
-
-	/* For DT, this is always supported.
-	 * For ACPI, this depends on CCA, which
-	 * is determined by the acpi_dma_supported().
-	 */
-	if (is_of_node(fwnode))
-		return true;
-
-	return acpi_dma_supported(to_acpi_device_node(fwnode));
+	return fwnode_call_bool_op(dev_fwnode(dev), device_dma_supported);
 }
 EXPORT_SYMBOL_GPL(device_dma_supported);
 
 enum dev_dma_attr device_get_dma_attr(struct device *dev)
 {
-	const struct fwnode_handle *fwnode = dev_fwnode(dev);
-	enum dev_dma_attr attr = DEV_DMA_NOT_SUPPORTED;
-
-	if (is_of_node(fwnode)) {
-		if (of_dma_is_coherent(to_of_node(fwnode)))
-			attr = DEV_DMA_COHERENT;
-		else
-			attr = DEV_DMA_NON_COHERENT;
-	} else
-		attr = acpi_get_dma_attr(to_acpi_device_node(fwnode));
+	if (!fwnode_has_op(dev_fwnode(dev), device_get_dma_attr))
+		return DEV_DMA_NOT_SUPPORTED;
 
-	return attr;
+	return fwnode_call_int_op(dev_fwnode(dev), device_get_dma_attr);
 }
 EXPORT_SYMBOL_GPL(device_get_dma_attr);
 
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 8e90071de6ed..676899566f7c 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -22,6 +22,7 @@
 #define pr_fmt(fmt)	"OF: " fmt
 
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
 #include <linux/of_irq.h>
@@ -872,6 +873,20 @@ static bool of_fwnode_device_is_available(const struct fwnode_handle *fwnode)
 	return of_device_is_available(to_of_node(fwnode));
 }
 
+static bool of_fwnode_device_dma_supported(const struct fwnode_handle *fwnode)
+{
+	return true;
+}
+
+static enum dev_dma_attr
+of_fwnode_device_get_dma_attr(const struct fwnode_handle *fwnode)
+{
+	if (of_dma_is_coherent(to_of_node(fwnode)))
+		return DEV_DMA_COHERENT;
+	else
+		return DEV_DMA_NON_COHERENT;
+}
+
 static bool of_fwnode_property_present(const struct fwnode_handle *fwnode,
 				       const char *propname)
 {
@@ -1472,6 +1487,8 @@ const struct fwnode_operations of_fwnode_ops = {
 	.put = of_fwnode_put,
 	.device_is_available = of_fwnode_device_is_available,
 	.device_get_match_data = of_fwnode_device_get_match_data,
+	.device_dma_supported = of_fwnode_device_dma_supported,
+	.device_get_dma_attr = of_fwnode_device_get_dma_attr,
 	.property_present = of_fwnode_property_present,
 	.property_read_int_array = of_fwnode_property_read_int_array,
 	.property_read_string_array = of_fwnode_property_read_string_array,
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 3a532ba66f6c..6f307f21fc65 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -113,6 +113,9 @@ struct fwnode_operations {
 	bool (*device_is_available)(const struct fwnode_handle *fwnode);
 	const void *(*device_get_match_data)(const struct fwnode_handle *fwnode,
 					     const struct device *dev);
+	bool (*device_dma_supported)(const struct fwnode_handle *fwnode);
+	enum dev_dma_attr
+	(*device_get_dma_attr)(const struct fwnode_handle *fwnode);
 	bool (*property_present)(const struct fwnode_handle *fwnode,
 				 const char *propname);
 	int (*property_read_int_array)(const struct fwnode_handle *fwnode,
-- 
cgit v1.2.3


From 68b979d068d3d0dceb14c446f664433d96f20a7e Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Thu, 31 Mar 2022 15:54:49 +0300
Subject: device property: Add iomap to fwnode operations

Add iomap() fwnode operation to implement fwnode_iomap() through fwnode
operations, moving the code in fwnode_iomap() to OF framework.

Note that the IS_ENABLED(CONFIG_OF_ADDRESS) && is_of_node(fwnode) check is
needed for Sparc that has its own implementation of of_iomap anyway. Let
the pre-compiler to handle that check.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/property.c |  5 +----
 drivers/of/property.c   | 10 ++++++++++
 include/linux/fwnode.h  |  1 +
 3 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 09686e2e903e..83dd22e7cb81 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -887,10 +887,7 @@ EXPORT_SYMBOL_GPL(device_get_phy_mode);
  */
 void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index)
 {
-	if (IS_ENABLED(CONFIG_OF_ADDRESS) && is_of_node(fwnode))
-		return of_iomap(to_of_node(fwnode), index);
-
-	return NULL;
+	return fwnode_call_ptr_op(fwnode, iomap, index);
 }
 EXPORT_SYMBOL(fwnode_iomap);
 
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 676899566f7c..ac2aa5221069 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1465,6 +1465,15 @@ static int of_link_property(struct device_node *con_np, const char *prop_name)
 	return 0;
 }
 
+static void __iomem *of_fwnode_iomap(struct fwnode_handle *fwnode, int index)
+{
+#ifdef CONFIG_OF_ADDRESS
+	return of_iomap(to_of_node(fwnode), index);
+#else
+	return NULL;
+#endif
+}
+
 static int of_fwnode_add_links(struct fwnode_handle *fwnode)
 {
 	struct property *p;
@@ -1502,6 +1511,7 @@ const struct fwnode_operations of_fwnode_ops = {
 	.graph_get_remote_endpoint = of_fwnode_graph_get_remote_endpoint,
 	.graph_get_port_parent = of_fwnode_graph_get_port_parent,
 	.graph_parse_endpoint = of_fwnode_graph_parse_endpoint,
+	.iomap = of_fwnode_iomap,
 	.add_links = of_fwnode_add_links,
 };
 EXPORT_SYMBOL_GPL(of_fwnode_ops);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 6f307f21fc65..ebbc3bf03f95 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -148,6 +148,7 @@ struct fwnode_operations {
 	(*graph_get_port_parent)(struct fwnode_handle *fwnode);
 	int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode,
 				    struct fwnode_endpoint *endpoint);
+	void __iomem *(*iomap)(struct fwnode_handle *fwnode, int index);
 	int (*add_links)(struct fwnode_handle *fwnode);
 };
 
-- 
cgit v1.2.3


From 99c63707bafd15bcf97fbd6bef1c92d5bfa01d28 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Thu, 31 Mar 2022 15:54:50 +0300
Subject: device property: Add irq_get to fwnode operation

Add irq_get() fwnode operation to implement fwnode_irq_get() through
fwnode operations, moving the code in fwnode_irq_get() to OF and ACPI
frameworks.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c | 14 ++++++++++++++
 drivers/base/property.c | 12 +-----------
 drivers/of/property.c   |  7 +++++++
 include/linux/fwnode.h  |  1 +
 4 files changed, 23 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 9f7ca34b7a95..292364c991a8 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1394,6 +1394,19 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return 0;
 }
 
+static int acpi_fwnode_irq_get(const struct fwnode_handle *fwnode,
+			       unsigned int index)
+{
+	struct resource res;
+	int ret;
+
+	ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res);
+	if (ret)
+		return ret;
+
+	return res.start;
+}
+
 #define DECLARE_ACPI_FWNODE_OPS(ops) \
 	const struct fwnode_operations ops = {				\
 		.device_is_available = acpi_fwnode_device_is_available, \
@@ -1418,6 +1431,7 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 			acpi_graph_get_remote_endpoint,			\
 		.graph_get_port_parent = acpi_fwnode_get_parent,	\
 		.graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \
+		.irq_get = acpi_fwnode_irq_get,				\
 	};								\
 	EXPORT_SYMBOL_GPL(ops)
 
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 83dd22e7cb81..3560c4419d11 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -901,17 +901,7 @@ EXPORT_SYMBOL(fwnode_iomap);
  */
 int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index)
 {
-	struct resource res;
-	int ret;
-
-	if (is_of_node(fwnode))
-		return of_irq_get(to_of_node(fwnode), index);
-
-	ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res);
-	if (ret)
-		return ret;
-
-	return res.start;
+	return fwnode_call_int_op(fwnode, irq_get, index);
 }
 EXPORT_SYMBOL(fwnode_irq_get);
 
diff --git a/drivers/of/property.c b/drivers/of/property.c
index ac2aa5221069..9a50ad25906e 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1474,6 +1474,12 @@ static void __iomem *of_fwnode_iomap(struct fwnode_handle *fwnode, int index)
 #endif
 }
 
+static int of_fwnode_irq_get(const struct fwnode_handle *fwnode,
+			     unsigned int index)
+{
+	return of_irq_get(to_of_node(fwnode), index);
+}
+
 static int of_fwnode_add_links(struct fwnode_handle *fwnode)
 {
 	struct property *p;
@@ -1512,6 +1518,7 @@ const struct fwnode_operations of_fwnode_ops = {
 	.graph_get_port_parent = of_fwnode_graph_get_port_parent,
 	.graph_parse_endpoint = of_fwnode_graph_parse_endpoint,
 	.iomap = of_fwnode_iomap,
+	.irq_get = of_fwnode_irq_get,
 	.add_links = of_fwnode_add_links,
 };
 EXPORT_SYMBOL_GPL(of_fwnode_ops);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index ebbc3bf03f95..6ab69871b06d 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -149,6 +149,7 @@ struct fwnode_operations {
 	int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode,
 				    struct fwnode_endpoint *endpoint);
 	void __iomem *(*iomap)(struct fwnode_handle *fwnode, int index);
+	int (*irq_get)(const struct fwnode_handle *fwnode, unsigned int index);
 	int (*add_links)(struct fwnode_handle *fwnode);
 };
 
-- 
cgit v1.2.3


From 1be9473e31ab87ad1b6ecf9fd11df461930ede85 Mon Sep 17 00:00:00 2001
From: Aaron Tomlin <atomlin@redhat.com>
Date: Tue, 22 Mar 2022 14:03:34 +0000
Subject: module: Move livepatch support to a separate file

No functional change.

This patch migrates livepatch support (i.e. used during module
add/or load and remove/or deletion) from core module code into
kernel/module/livepatch.c. At the moment it contains code to
persist Elf information about a given livepatch module, only.
The new file was added to MAINTAINERS.

Reviewed-by: Petr Mladek <pmladek@suse.com>
Tested-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 MAINTAINERS               |   1 +
 include/linux/module.h    |   9 ++--
 kernel/module/Makefile    |   1 +
 kernel/module/internal.h  |  22 ++++++++++
 kernel/module/livepatch.c |  74 +++++++++++++++++++++++++++++++++
 kernel/module/main.c      | 102 +++++-----------------------------------------
 6 files changed, 111 insertions(+), 98 deletions(-)
 create mode 100644 kernel/module/livepatch.c

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 5e7778cd437f..6dcd93fb3a96 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11360,6 +11360,7 @@ F:	arch/s390/include/asm/livepatch.h
 F:	arch/x86/include/asm/livepatch.h
 F:	include/linux/livepatch.h
 F:	kernel/livepatch/
+F:	kernel/module/livepatch.c
 F:	lib/livepatch/
 F:	samples/livepatch/
 F:	tools/testing/selftests/livepatch/
diff --git a/include/linux/module.h b/include/linux/module.h
index 1e135fd5c076..7ec9715de7dc 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -663,17 +663,14 @@ static inline bool module_requested_async_probing(struct module *module)
 	return module && module->async_probe_requested;
 }
 
-#ifdef CONFIG_LIVEPATCH
 static inline bool is_livepatch_module(struct module *mod)
 {
+#ifdef CONFIG_LIVEPATCH
 	return mod->klp;
-}
-#else /* !CONFIG_LIVEPATCH */
-static inline bool is_livepatch_module(struct module *mod)
-{
+#else
 	return false;
+#endif
 }
-#endif /* CONFIG_LIVEPATCH */
 
 bool is_module_sig_enforced(void);
 void set_module_sig_enforced(void);
diff --git a/kernel/module/Makefile b/kernel/module/Makefile
index cdd5c61b8c7f..ed3aacb04f17 100644
--- a/kernel/module/Makefile
+++ b/kernel/module/Makefile
@@ -10,3 +10,4 @@ KCOV_INSTRUMENT_module.o := n
 obj-y += main.o
 obj-$(CONFIG_MODULE_DECOMPRESS) += decompress.o
 obj-$(CONFIG_MODULE_SIG) += signing.o
+obj-$(CONFIG_LIVEPATCH) += livepatch.o
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index e0775e66bcf7..ad7a444253ed 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -57,6 +57,28 @@ struct load_info {
 
 int mod_verify_sig(const void *mod, struct load_info *info);
 
+#ifdef CONFIG_LIVEPATCH
+int copy_module_elf(struct module *mod, struct load_info *info);
+void free_module_elf(struct module *mod);
+#else /* !CONFIG_LIVEPATCH */
+static inline int copy_module_elf(struct module *mod, struct load_info *info)
+{
+	return 0;
+}
+
+static inline void free_module_elf(struct module *mod) { }
+#endif /* CONFIG_LIVEPATCH */
+
+static inline bool set_livepatch_module(struct module *mod)
+{
+#ifdef CONFIG_LIVEPATCH
+	mod->klp = true;
+	return true;
+#else
+	return false;
+#endif
+}
+
 #ifdef CONFIG_MODULE_DECOMPRESS
 int module_decompress(struct load_info *info, const void *buf, size_t size);
 void module_decompress_cleanup(struct load_info *info);
diff --git a/kernel/module/livepatch.c b/kernel/module/livepatch.c
new file mode 100644
index 000000000000..486d4ff92719
--- /dev/null
+++ b/kernel/module/livepatch.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module livepatch support
+ *
+ * Copyright (C) 2016 Jessica Yu <jeyu@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+/*
+ * Persist Elf information about a module. Copy the Elf header,
+ * section header table, section string table, and symtab section
+ * index from info to mod->klp_info.
+ */
+int copy_module_elf(struct module *mod, struct load_info *info)
+{
+	unsigned int size, symndx;
+	int ret;
+
+	size = sizeof(*mod->klp_info);
+	mod->klp_info = kmalloc(size, GFP_KERNEL);
+	if (!mod->klp_info)
+		return -ENOMEM;
+
+	/* Elf header */
+	size = sizeof(mod->klp_info->hdr);
+	memcpy(&mod->klp_info->hdr, info->hdr, size);
+
+	/* Elf section header table */
+	size = sizeof(*info->sechdrs) * info->hdr->e_shnum;
+	mod->klp_info->sechdrs = kmemdup(info->sechdrs, size, GFP_KERNEL);
+	if (!mod->klp_info->sechdrs) {
+		ret = -ENOMEM;
+		goto free_info;
+	}
+
+	/* Elf section name string table */
+	size = info->sechdrs[info->hdr->e_shstrndx].sh_size;
+	mod->klp_info->secstrings = kmemdup(info->secstrings, size, GFP_KERNEL);
+	if (!mod->klp_info->secstrings) {
+		ret = -ENOMEM;
+		goto free_sechdrs;
+	}
+
+	/* Elf symbol section index */
+	symndx = info->index.sym;
+	mod->klp_info->symndx = symndx;
+
+	/*
+	 * For livepatch modules, core_kallsyms.symtab is a complete
+	 * copy of the original symbol table. Adjust sh_addr to point
+	 * to core_kallsyms.symtab since the copy of the symtab in module
+	 * init memory is freed at the end of do_init_module().
+	 */
+	mod->klp_info->sechdrs[symndx].sh_addr = (unsigned long)mod->core_kallsyms.symtab;
+
+	return 0;
+
+free_sechdrs:
+	kfree(mod->klp_info->sechdrs);
+free_info:
+	kfree(mod->klp_info);
+	return ret;
+}
+
+void free_module_elf(struct module *mod)
+{
+	kfree(mod->klp_info->sechdrs);
+	kfree(mod->klp_info->secstrings);
+	kfree(mod->klp_info);
+}
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 5898a1af41a9..915143827069 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2043,81 +2043,6 @@ static int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 }
 #endif /*  CONFIG_STRICT_MODULE_RWX */
 
-#ifdef CONFIG_LIVEPATCH
-/*
- * Persist Elf information about a module. Copy the Elf header,
- * section header table, section string table, and symtab section
- * index from info to mod->klp_info.
- */
-static int copy_module_elf(struct module *mod, struct load_info *info)
-{
-	unsigned int size, symndx;
-	int ret;
-
-	size = sizeof(*mod->klp_info);
-	mod->klp_info = kmalloc(size, GFP_KERNEL);
-	if (mod->klp_info == NULL)
-		return -ENOMEM;
-
-	/* Elf header */
-	size = sizeof(mod->klp_info->hdr);
-	memcpy(&mod->klp_info->hdr, info->hdr, size);
-
-	/* Elf section header table */
-	size = sizeof(*info->sechdrs) * info->hdr->e_shnum;
-	mod->klp_info->sechdrs = kmemdup(info->sechdrs, size, GFP_KERNEL);
-	if (mod->klp_info->sechdrs == NULL) {
-		ret = -ENOMEM;
-		goto free_info;
-	}
-
-	/* Elf section name string table */
-	size = info->sechdrs[info->hdr->e_shstrndx].sh_size;
-	mod->klp_info->secstrings = kmemdup(info->secstrings, size, GFP_KERNEL);
-	if (mod->klp_info->secstrings == NULL) {
-		ret = -ENOMEM;
-		goto free_sechdrs;
-	}
-
-	/* Elf symbol section index */
-	symndx = info->index.sym;
-	mod->klp_info->symndx = symndx;
-
-	/*
-	 * For livepatch modules, core_kallsyms.symtab is a complete
-	 * copy of the original symbol table. Adjust sh_addr to point
-	 * to core_kallsyms.symtab since the copy of the symtab in module
-	 * init memory is freed at the end of do_init_module().
-	 */
-	mod->klp_info->sechdrs[symndx].sh_addr = \
-		(unsigned long) mod->core_kallsyms.symtab;
-
-	return 0;
-
-free_sechdrs:
-	kfree(mod->klp_info->sechdrs);
-free_info:
-	kfree(mod->klp_info);
-	return ret;
-}
-
-static void free_module_elf(struct module *mod)
-{
-	kfree(mod->klp_info->sechdrs);
-	kfree(mod->klp_info->secstrings);
-	kfree(mod->klp_info);
-}
-#else /* !CONFIG_LIVEPATCH */
-static int copy_module_elf(struct module *mod, struct load_info *info)
-{
-	return 0;
-}
-
-static void free_module_elf(struct module *mod)
-{
-}
-#endif /* CONFIG_LIVEPATCH */
-
 void __weak module_memfree(void *module_region)
 {
 	/*
@@ -3092,30 +3017,23 @@ static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned l
 	return 0;
 }
 
-#ifdef CONFIG_LIVEPATCH
 static int check_modinfo_livepatch(struct module *mod, struct load_info *info)
 {
-	if (get_modinfo(info, "livepatch")) {
-		mod->klp = true;
+	if (!get_modinfo(info, "livepatch"))
+		/* Nothing more to do */
+		return 0;
+
+	if (set_livepatch_module(mod)) {
 		add_taint_module(mod, TAINT_LIVEPATCH, LOCKDEP_STILL_OK);
 		pr_notice_once("%s: tainting kernel with TAINT_LIVEPATCH\n",
-			       mod->name);
-	}
-
-	return 0;
-}
-#else /* !CONFIG_LIVEPATCH */
-static int check_modinfo_livepatch(struct module *mod, struct load_info *info)
-{
-	if (get_modinfo(info, "livepatch")) {
-		pr_err("%s: module is marked as livepatch module, but livepatch support is disabled",
-		       mod->name);
-		return -ENOEXEC;
+				mod->name);
+		return 0;
 	}
 
-	return 0;
+	pr_err("%s: module is marked as livepatch module, but livepatch support is disabled",
+	       mod->name);
+	return -ENOEXEC;
 }
-#endif /* CONFIG_LIVEPATCH */
 
 static void check_modinfo_retpoline(struct module *mod, struct load_info *info)
 {
-- 
cgit v1.2.3


From 0c1e42805c25c87eb7a6f3b18bdbf3b3b7840aff Mon Sep 17 00:00:00 2001
From: Aaron Tomlin <atomlin@redhat.com>
Date: Tue, 22 Mar 2022 14:03:37 +0000
Subject: module: Move extra signature support out of core code

No functional change.

This patch migrates additional module signature check
code from core module code into kernel/module/signing.c.

Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/module.h   | 12 ++++---
 kernel/module/internal.h |  9 +++++
 kernel/module/main.c     | 87 ------------------------------------------------
 kernel/module/signing.c  | 77 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 93 insertions(+), 92 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 7ec9715de7dc..5e2059f3afc7 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -672,7 +672,6 @@ static inline bool is_livepatch_module(struct module *mod)
 #endif
 }
 
-bool is_module_sig_enforced(void);
 void set_module_sig_enforced(void);
 
 #else /* !CONFIG_MODULES... */
@@ -799,10 +798,6 @@ static inline bool module_requested_async_probing(struct module *module)
 	return false;
 }
 
-static inline bool is_module_sig_enforced(void)
-{
-	return false;
-}
 
 static inline void set_module_sig_enforced(void)
 {
@@ -854,11 +849,18 @@ static inline bool retpoline_module_ok(bool has_retpoline)
 #endif
 
 #ifdef CONFIG_MODULE_SIG
+bool is_module_sig_enforced(void);
+
 static inline bool module_sig_ok(struct module *module)
 {
 	return module->sig_ok;
 }
 #else	/* !CONFIG_MODULE_SIG */
+static inline bool is_module_sig_enforced(void)
+{
+	return false;
+}
+
 static inline bool module_sig_ok(struct module *module)
 {
 	return true;
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index a6895bb5598a..d6f646a5da41 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -158,3 +158,12 @@ static inline int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 	return 0;
 }
 #endif /* CONFIG_STRICT_MODULE_RWX */
+
+#ifdef CONFIG_MODULE_SIG
+int module_sig_check(struct load_info *info, int flags);
+#else /* !CONFIG_MODULE_SIG */
+static inline int module_sig_check(struct load_info *info, int flags)
+{
+	return 0;
+}
+#endif /* !CONFIG_MODULE_SIG */
diff --git a/kernel/module/main.c b/kernel/module/main.c
index d55a2a8338a1..c349c91e53fa 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -23,7 +23,6 @@
 #include <linux/vmalloc.h>
 #include <linux/elf.h>
 #include <linux/proc_fs.h>
-#include <linux/security.h>
 #include <linux/seq_file.h>
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
@@ -127,28 +126,6 @@ static void module_assert_mutex_or_preempt(void)
 #endif
 }
 
-#ifdef CONFIG_MODULE_SIG
-static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE);
-module_param(sig_enforce, bool_enable_only, 0644);
-
-void set_module_sig_enforced(void)
-{
-	sig_enforce = true;
-}
-#else
-#define sig_enforce false
-#endif
-
-/*
- * Export sig_enforce kernel cmdline parameter to allow other subsystems rely
- * on that instead of directly to CONFIG_MODULE_SIG_FORCE config.
- */
-bool is_module_sig_enforced(void)
-{
-	return sig_enforce;
-}
-EXPORT_SYMBOL(is_module_sig_enforced);
-
 /* Block module loading/unloading? */
 int modules_disabled = 0;
 core_param(nomodule, modules_disabled, bint, 0);
@@ -2569,70 +2546,6 @@ static inline void kmemleak_load_module(const struct module *mod,
 }
 #endif
 
-#ifdef CONFIG_MODULE_SIG
-static int module_sig_check(struct load_info *info, int flags)
-{
-	int err = -ENODATA;
-	const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1;
-	const char *reason;
-	const void *mod = info->hdr;
-	bool mangled_module = flags & (MODULE_INIT_IGNORE_MODVERSIONS |
-				       MODULE_INIT_IGNORE_VERMAGIC);
-	/*
-	 * Do not allow mangled modules as a module with version information
-	 * removed is no longer the module that was signed.
-	 */
-	if (!mangled_module &&
-	    info->len > markerlen &&
-	    memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
-		/* We truncate the module to discard the signature */
-		info->len -= markerlen;
-		err = mod_verify_sig(mod, info);
-		if (!err) {
-			info->sig_ok = true;
-			return 0;
-		}
-	}
-
-	/*
-	 * We don't permit modules to be loaded into the trusted kernels
-	 * without a valid signature on them, but if we're not enforcing,
-	 * certain errors are non-fatal.
-	 */
-	switch (err) {
-	case -ENODATA:
-		reason = "unsigned module";
-		break;
-	case -ENOPKG:
-		reason = "module with unsupported crypto";
-		break;
-	case -ENOKEY:
-		reason = "module with unavailable key";
-		break;
-
-	default:
-		/*
-		 * All other errors are fatal, including lack of memory,
-		 * unparseable signatures, and signature check failures --
-		 * even if signatures aren't required.
-		 */
-		return err;
-	}
-
-	if (is_module_sig_enforced()) {
-		pr_notice("Loading of %s is rejected\n", reason);
-		return -EKEYREJECTED;
-	}
-
-	return security_locked_down(LOCKDOWN_MODULE_SIGNATURE);
-}
-#else /* !CONFIG_MODULE_SIG */
-static int module_sig_check(struct load_info *info, int flags)
-{
-	return 0;
-}
-#endif /* !CONFIG_MODULE_SIG */
-
 static int validate_section_offset(struct load_info *info, Elf_Shdr *shdr)
 {
 #if defined(CONFIG_64BIT)
diff --git a/kernel/module/signing.c b/kernel/module/signing.c
index 8aeb6d2ee94b..85c8999dfecf 100644
--- a/kernel/module/signing.c
+++ b/kernel/module/signing.c
@@ -11,9 +11,29 @@
 #include <linux/module_signature.h>
 #include <linux/string.h>
 #include <linux/verification.h>
+#include <linux/security.h>
 #include <crypto/public_key.h>
+#include <uapi/linux/module.h>
 #include "internal.h"
 
+static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE);
+module_param(sig_enforce, bool_enable_only, 0644);
+
+/*
+ * Export sig_enforce kernel cmdline parameter to allow other subsystems rely
+ * on that instead of directly to CONFIG_MODULE_SIG_FORCE config.
+ */
+bool is_module_sig_enforced(void)
+{
+	return sig_enforce;
+}
+EXPORT_SYMBOL(is_module_sig_enforced);
+
+void set_module_sig_enforced(void)
+{
+	sig_enforce = true;
+}
+
 /*
  * Verify the signature on a module.
  */
@@ -43,3 +63,60 @@ int mod_verify_sig(const void *mod, struct load_info *info)
 				      VERIFYING_MODULE_SIGNATURE,
 				      NULL, NULL);
 }
+
+int module_sig_check(struct load_info *info, int flags)
+{
+	int err = -ENODATA;
+	const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1;
+	const char *reason;
+	const void *mod = info->hdr;
+	bool mangled_module = flags & (MODULE_INIT_IGNORE_MODVERSIONS |
+				       MODULE_INIT_IGNORE_VERMAGIC);
+	/*
+	 * Do not allow mangled modules as a module with version information
+	 * removed is no longer the module that was signed.
+	 */
+	if (!mangled_module &&
+	    info->len > markerlen &&
+	    memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
+		/* We truncate the module to discard the signature */
+		info->len -= markerlen;
+		err = mod_verify_sig(mod, info);
+		if (!err) {
+			info->sig_ok = true;
+			return 0;
+		}
+	}
+
+	/*
+	 * We don't permit modules to be loaded into the trusted kernels
+	 * without a valid signature on them, but if we're not enforcing,
+	 * certain errors are non-fatal.
+	 */
+	switch (err) {
+	case -ENODATA:
+		reason = "unsigned module";
+		break;
+	case -ENOPKG:
+		reason = "module with unsupported crypto";
+		break;
+	case -ENOKEY:
+		reason = "module with unavailable key";
+		break;
+
+	default:
+		/*
+		 * All other errors are fatal, including lack of memory,
+		 * unparseable signatures, and signature check failures --
+		 * even if signatures aren't required.
+		 */
+		return err;
+	}
+
+	if (is_module_sig_enforced()) {
+		pr_notice("Loading of %s is rejected\n", reason);
+		return -EKEYREJECTED;
+	}
+
+	return security_locked_down(LOCKDOWN_MODULE_SIGNATURE);
+}
-- 
cgit v1.2.3


From f64205a42046d3802c423fa2059e7fca39af127c Mon Sep 17 00:00:00 2001
From: Aaron Tomlin <atomlin@redhat.com>
Date: Tue, 22 Mar 2022 14:03:43 +0000
Subject: module: Move kdb module related code out of main kdb code

No functional change.

This patch migrates the kdb 'lsmod' command support out of main
kdb code into its own file under kernel/module. In addition to
the above, a minor style warning i.e. missing a blank line after
declarations, was resolved too. The new file was added to
MAINTAINERS. Finally we remove linux/module.h as it is entirely
redundant.

Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Acked-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 MAINTAINERS                     |  1 +
 include/linux/kdb.h             |  1 +
 kernel/debug/kdb/kdb_io.c       |  1 -
 kernel/debug/kdb/kdb_keyboard.c |  1 -
 kernel/debug/kdb/kdb_main.c     | 49 ------------------------------------
 kernel/debug/kdb/kdb_private.h  |  4 ---
 kernel/debug/kdb/kdb_support.c  |  1 -
 kernel/module/Makefile          |  1 +
 kernel/module/kdb.c             | 56 +++++++++++++++++++++++++++++++++++++++++
 kernel/module/main.c            |  4 ---
 10 files changed, 59 insertions(+), 60 deletions(-)
 create mode 100644 kernel/module/kdb.c

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 6dcd93fb3a96..87cc05c6b462 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10907,6 +10907,7 @@ F:	drivers/tty/serial/kgdboc.c
 F:	include/linux/kdb.h
 F:	include/linux/kgdb.h
 F:	kernel/debug/
+F:	kernel/module/kdb.c
 
 KHADAS MCU MFD DRIVER
 M:	Neil Armstrong <narmstrong@baylibre.com>
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index ea0f5e580fac..07dfb6a20a1c 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -222,5 +222,6 @@ enum {
 
 extern int kdbgetintenv(const char *, int *);
 extern int kdb_set(int, const char **);
+int kdb_lsmod(int argc, const char **argv);
 
 #endif	/* !_KDB_H */
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 6735ac36b718..67d3c48a1522 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -9,7 +9,6 @@
  * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
  */
 
-#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/ctype.h>
 #include <linux/kernel.h>
diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c
index f877a0a0d7cf..f87c750d3eb3 100644
--- a/kernel/debug/kdb/kdb_keyboard.c
+++ b/kernel/debug/kdb/kdb_keyboard.c
@@ -11,7 +11,6 @@
 #include <linux/kdb.h>
 #include <linux/keyboard.h>
 #include <linux/ctype.h>
-#include <linux/module.h>
 #include <linux/io.h>
 
 /* Keyboard Controller Registers on normal PCs. */
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 0852a537dad4..f3a30cd5037f 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -26,7 +26,6 @@
 #include <linux/utsname.h>
 #include <linux/vmalloc.h>
 #include <linux/atomic.h>
-#include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/mm.h>
 #include <linux/init.h>
@@ -2004,54 +2003,6 @@ static int kdb_ef(int argc, const char **argv)
 	return 0;
 }
 
-#if defined(CONFIG_MODULES)
-/*
- * kdb_lsmod - This function implements the 'lsmod' command.  Lists
- *	currently loaded kernel modules.
- *	Mostly taken from userland lsmod.
- */
-static int kdb_lsmod(int argc, const char **argv)
-{
-	struct module *mod;
-
-	if (argc != 0)
-		return KDB_ARGCOUNT;
-
-	kdb_printf("Module                  Size  modstruct     Used by\n");
-	list_for_each_entry(mod, kdb_modules, list) {
-		if (mod->state == MODULE_STATE_UNFORMED)
-			continue;
-
-		kdb_printf("%-20s%8u  0x%px ", mod->name,
-			   mod->core_layout.size, (void *)mod);
-#ifdef CONFIG_MODULE_UNLOAD
-		kdb_printf("%4d ", module_refcount(mod));
-#endif
-		if (mod->state == MODULE_STATE_GOING)
-			kdb_printf(" (Unloading)");
-		else if (mod->state == MODULE_STATE_COMING)
-			kdb_printf(" (Loading)");
-		else
-			kdb_printf(" (Live)");
-		kdb_printf(" 0x%px", mod->core_layout.base);
-
-#ifdef CONFIG_MODULE_UNLOAD
-		{
-			struct module_use *use;
-			kdb_printf(" [ ");
-			list_for_each_entry(use, &mod->source_list,
-					    source_list)
-				kdb_printf("%s ", use->target->name);
-			kdb_printf("]\n");
-		}
-#endif
-	}
-
-	return 0;
-}
-
-#endif	/* CONFIG_MODULES */
-
 /*
  * kdb_env - This function implements the 'env' command.  Display the
  *	current environment variables.
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 0d2f9feea0a4..1f8c519a5f81 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -226,10 +226,6 @@ extern void kdb_kbd_cleanup_state(void);
 #define kdb_kbd_cleanup_state()
 #endif /* ! CONFIG_KDB_KEYBOARD */
 
-#ifdef CONFIG_MODULES
-extern struct list_head *kdb_modules;
-#endif /* CONFIG_MODULES */
-
 extern char kdb_prompt_str[];
 
 #define	KDB_WORD_SIZE	((int)sizeof(unsigned long))
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 85cb51c4a17e..0a39497140bf 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -17,7 +17,6 @@
 #include <linux/stddef.h>
 #include <linux/vmalloc.h>
 #include <linux/ptrace.h>
-#include <linux/module.h>
 #include <linux/highmem.h>
 #include <linux/hardirq.h>
 #include <linux/delay.h>
diff --git a/kernel/module/Makefile b/kernel/module/Makefile
index cf8dcdc6b55f..88f5cdcdb067 100644
--- a/kernel/module/Makefile
+++ b/kernel/module/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_DEBUG_KMEMLEAK) += debug_kmemleak.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_PROC_FS) += procfs.o
 obj-$(CONFIG_SYSFS) += sysfs.o
+obj-$(CONFIG_KGDB_KDB) += kdb.o
diff --git a/kernel/module/kdb.c b/kernel/module/kdb.c
new file mode 100644
index 000000000000..a446c699db0a
--- /dev/null
+++ b/kernel/module/kdb.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module kdb support
+ *
+ * Copyright (C) 2010 Jason Wessel
+ */
+
+#include <linux/module.h>
+#include <linux/kdb.h>
+#include "internal.h"
+
+/*
+ * kdb_lsmod - This function implements the 'lsmod' command.  Lists
+ *	currently loaded kernel modules.
+ *	Mostly taken from userland lsmod.
+ */
+int kdb_lsmod(int argc, const char **argv)
+{
+	struct module *mod;
+
+	if (argc != 0)
+		return KDB_ARGCOUNT;
+
+	kdb_printf("Module                  Size  modstruct     Used by\n");
+	list_for_each_entry(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
+
+		kdb_printf("%-20s%8u  0x%px ", mod->name,
+			   mod->core_layout.size, (void *)mod);
+#ifdef CONFIG_MODULE_UNLOAD
+		kdb_printf("%4d ", module_refcount(mod));
+#endif
+		if (mod->state == MODULE_STATE_GOING)
+			kdb_printf(" (Unloading)");
+		else if (mod->state == MODULE_STATE_COMING)
+			kdb_printf(" (Loading)");
+		else
+			kdb_printf(" (Live)");
+		kdb_printf(" 0x%px", mod->core_layout.base);
+
+#ifdef CONFIG_MODULE_UNLOAD
+		{
+			struct module_use *use;
+
+			kdb_printf(" [ ");
+			list_for_each_entry(use, &mod->source_list,
+					    source_list)
+				kdb_printf("%s ", use->target->name);
+			kdb_printf("]\n");
+		}
+#endif
+	}
+
+	return 0;
+}
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 0cd0590dd411..a2dc54726621 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -108,10 +108,6 @@ static void mod_update_bounds(struct module *mod)
 		__mod_update_bounds(mod->init_layout.base, mod->init_layout.size);
 }
 
-#ifdef CONFIG_KGDB_KDB
-struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */
-#endif /* CONFIG_KGDB_KDB */
-
 static void module_assert_mutex_or_preempt(void)
 {
 #ifdef CONFIG_LOCKDEP
-- 
cgit v1.2.3


From 01dc0386efb769056257410ba5754558384006a7 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Wed, 23 Feb 2022 13:02:14 +0100
Subject: module: Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC

Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC to allow architectures
to request having modules data in vmalloc area instead of module area.

This is required on powerpc book3s/32 in order to set data non
executable, because it is not possible to set executability on page
basis, this is done per 256 Mbytes segments. The module area has exec
right, vmalloc area has noexec.

This can also be useful on other powerpc/32 in order to maximize the
chance of code being close enough to kernel core to avoid branch
trampolines.

Cc: Jason Wessel <jason.wessel@windriver.com>
Acked-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
[mcgrof: rebased in light of kernel/module/kdb.c move]
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 arch/Kconfig                |  6 +++++
 include/linux/module.h      |  8 +++++++
 kernel/module/internal.h    |  3 +++
 kernel/module/kdb.c         | 10 ++++++--
 kernel/module/main.c        | 58 +++++++++++++++++++++++++++++++++++++++++++--
 kernel/module/procfs.c      |  8 +++++--
 kernel/module/strict_rwx.c  |  1 +
 kernel/module/tree_lookup.c |  8 +++++++
 8 files changed, 96 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 29b0167c088b..24945cee808b 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -888,6 +888,12 @@ config MODULES_USE_ELF_REL
 	  Modules only use ELF REL relocations.  Modules with ELF RELA
 	  relocations will give an error.
 
+config ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	bool
+	help
+	  For architectures like powerpc/32 which have constraints on module
+	  allocation and need to allocate module data outside of module area.
+
 config HAVE_IRQ_EXIT_ON_IRQ_STACK
 	bool
 	help
diff --git a/include/linux/module.h b/include/linux/module.h
index 5e2059f3afc7..46d4d5f2516e 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -422,6 +422,9 @@ struct module {
 	/* Core layout: rbtree is accessed frequently, so keep together. */
 	struct module_layout core_layout __module_layout_align;
 	struct module_layout init_layout;
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	struct module_layout data_layout;
+#endif
 
 	/* Arch-specific module values */
 	struct mod_arch_specific arch;
@@ -569,6 +572,11 @@ bool is_module_text_address(unsigned long addr);
 static inline bool within_module_core(unsigned long addr,
 				      const struct module *mod)
 {
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	if ((unsigned long)mod->data_layout.base <= addr &&
+	    addr < (unsigned long)mod->data_layout.base + mod->data_layout.size)
+		return true;
+#endif
 	return (unsigned long)mod->core_layout.base <= addr &&
 	       addr < (unsigned long)mod->core_layout.base + mod->core_layout.size;
 }
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index 0aabbf5cbcd1..3e23bef5884d 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -20,7 +20,9 @@
 /* Maximum number of characters written by module_flags() */
 #define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4)
 
+#ifndef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
 #define	data_layout core_layout
+#endif
 
 /*
  * Modules' sections will be aligned on page boundaries
@@ -154,6 +156,7 @@ struct mod_tree_root {
 };
 
 extern struct mod_tree_root mod_tree;
+extern struct mod_tree_root mod_data_tree;
 
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 void mod_tree_insert(struct module *mod);
diff --git a/kernel/module/kdb.c b/kernel/module/kdb.c
index a446c699db0a..f4317f92e189 100644
--- a/kernel/module/kdb.c
+++ b/kernel/module/kdb.c
@@ -26,8 +26,11 @@ int kdb_lsmod(int argc, const char **argv)
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
 
-		kdb_printf("%-20s%8u  0x%px ", mod->name,
-			   mod->core_layout.size, (void *)mod);
+		kdb_printf("%-20s%8u", mod->name, mod->core_layout.size);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+		kdb_printf("/%8u", mod->data_layout.size);
+#endif
+		kdb_printf("  0x%px ", (void *)mod);
 #ifdef CONFIG_MODULE_UNLOAD
 		kdb_printf("%4d ", module_refcount(mod));
 #endif
@@ -38,6 +41,9 @@ int kdb_lsmod(int argc, const char **argv)
 		else
 			kdb_printf(" (Live)");
 		kdb_printf(" 0x%px", mod->core_layout.base);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+		kdb_printf("/0x%px", mod->data_layout.base);
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 		{
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 78658283408d..84b828431dcb 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -78,6 +78,12 @@ struct mod_tree_root mod_tree __cacheline_aligned = {
 	.addr_min = -1UL,
 };
 
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+struct mod_tree_root mod_data_tree __cacheline_aligned = {
+	.addr_min = -1UL,
+};
+#endif
+
 #define module_addr_min mod_tree.addr_min
 #define module_addr_max mod_tree.addr_max
 
@@ -107,6 +113,9 @@ static void mod_update_bounds(struct module *mod)
 	__mod_update_bounds(mod->core_layout.base, mod->core_layout.size, &mod_tree);
 	if (mod->init_layout.size)
 		__mod_update_bounds(mod->init_layout.base, mod->init_layout.size, &mod_tree);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	__mod_update_bounds(mod->data_layout.base, mod->data_layout.size, &mod_data_tree);
+#endif
 }
 
 static void module_assert_mutex_or_preempt(void)
@@ -940,6 +949,17 @@ static ssize_t show_coresize(struct module_attribute *mattr,
 static struct module_attribute modinfo_coresize =
 	__ATTR(coresize, 0444, show_coresize, NULL);
 
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+static ssize_t show_datasize(struct module_attribute *mattr,
+			     struct module_kobject *mk, char *buffer)
+{
+	return sprintf(buffer, "%u\n", mk->mod->data_layout.size);
+}
+
+static struct module_attribute modinfo_datasize =
+	__ATTR(datasize, 0444, show_datasize, NULL);
+#endif
+
 static ssize_t show_initsize(struct module_attribute *mattr,
 			     struct module_kobject *mk, char *buffer)
 {
@@ -968,6 +988,9 @@ struct module_attribute *modinfo_attrs[] = {
 	&modinfo_srcversion,
 	&modinfo_initstate,
 	&modinfo_coresize,
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	&modinfo_datasize,
+#endif
 	&modinfo_initsize,
 	&modinfo_taint,
 #ifdef CONFIG_MODULE_UNLOAD
@@ -1194,6 +1217,9 @@ static void free_module(struct module *mod)
 
 	/* Finally, free the core (containing the module structure) */
 	module_memfree(mod->core_layout.base);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	vfree(mod->data_layout.base);
+#endif
 }
 
 void *__symbol_get(const char *symbol)
@@ -2124,6 +2150,24 @@ static int move_module(struct module *mod, struct load_info *info)
 	} else
 		mod->init_layout.base = NULL;
 
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	/* Do the allocs. */
+	ptr = vmalloc(mod->data_layout.size);
+	/*
+	 * The pointer to this block is stored in the module structure
+	 * which is inside the block. Just mark it as not being a
+	 * leak.
+	 */
+	kmemleak_not_leak(ptr);
+	if (!ptr) {
+		module_memfree(mod->core_layout.base);
+		module_memfree(mod->init_layout.base);
+		return -ENOMEM;
+	}
+
+	memset(ptr, 0, mod->data_layout.size);
+	mod->data_layout.base = ptr;
+#endif
 	/* Transfer each section which specifies SHF_ALLOC */
 	pr_debug("final section addresses:\n");
 	for (i = 0; i < info->hdr->e_shnum; i++) {
@@ -2299,6 +2343,9 @@ static void module_deallocate(struct module *mod, struct load_info *info)
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
 	module_memfree(mod->core_layout.base);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	vfree(mod->data_layout.base);
+#endif
 }
 
 int __weak module_finalize(const Elf_Ehdr *hdr,
@@ -3015,13 +3062,20 @@ bool is_module_address(unsigned long addr)
 struct module *__module_address(unsigned long addr)
 {
 	struct module *mod;
+	struct mod_tree_root *tree;
 
-	if (addr < module_addr_min || addr > module_addr_max)
+	if (addr >= mod_tree.addr_min && addr <= mod_tree.addr_max)
+		tree = &mod_tree;
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	else if (addr >= mod_data_tree.addr_min && addr <= mod_data_tree.addr_max)
+		tree = &mod_data_tree;
+#endif
+	else
 		return NULL;
 
 	module_assert_mutex_or_preempt();
 
-	mod = mod_find(addr, &mod_tree);
+	mod = mod_find(addr, tree);
 	if (mod) {
 		BUG_ON(!within_module(addr, mod));
 		if (mod->state == MODULE_STATE_UNFORMED)
diff --git a/kernel/module/procfs.c b/kernel/module/procfs.c
index 2717e130788e..9a8f4f0f6329 100644
--- a/kernel/module/procfs.c
+++ b/kernel/module/procfs.c
@@ -67,13 +67,17 @@ static int m_show(struct seq_file *m, void *p)
 	struct module *mod = list_entry(p, struct module, list);
 	char buf[MODULE_FLAGS_BUF_SIZE];
 	void *value;
+	unsigned int size;
 
 	/* We always ignore unformed modules. */
 	if (mod->state == MODULE_STATE_UNFORMED)
 		return 0;
 
-	seq_printf(m, "%s %u",
-		   mod->name, mod->init_layout.size + mod->core_layout.size);
+	size = mod->init_layout.size + mod->core_layout.size;
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	size += mod->data_layout.size;
+#endif
+	seq_printf(m, "%s %u", mod->name, size);
 	print_unload_info(m, mod);
 
 	/* Informative for users. */
diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c
index fe3c10891407..14fbea66f12f 100644
--- a/kernel/module/strict_rwx.c
+++ b/kernel/module/strict_rwx.c
@@ -75,6 +75,7 @@ bool module_check_misalignment(const struct module *mod)
 		return false;
 
 	return layout_check_misalignment(&mod->core_layout) ||
+	       layout_check_misalignment(&mod->data_layout) ||
 	       layout_check_misalignment(&mod->init_layout);
 }
 
diff --git a/kernel/module/tree_lookup.c b/kernel/module/tree_lookup.c
index 995fe68059db..8ec5cfd60496 100644
--- a/kernel/module/tree_lookup.c
+++ b/kernel/module/tree_lookup.c
@@ -83,6 +83,11 @@ void mod_tree_insert(struct module *mod)
 	__mod_tree_insert(&mod->core_layout.mtn, &mod_tree);
 	if (mod->init_layout.size)
 		__mod_tree_insert(&mod->init_layout.mtn, &mod_tree);
+
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	mod->data_layout.mtn.mod = mod;
+	__mod_tree_insert(&mod->data_layout.mtn, &mod_data_tree);
+#endif
 }
 
 void mod_tree_remove_init(struct module *mod)
@@ -95,6 +100,9 @@ void mod_tree_remove(struct module *mod)
 {
 	__mod_tree_remove(&mod->core_layout.mtn, &mod_tree);
 	mod_tree_remove_init(mod);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	__mod_tree_remove(&mod->data_layout.mtn, &mod_data_tree);
+#endif
 }
 
 struct module *mod_find(unsigned long addr, struct mod_tree_root *tree)
-- 
cgit v1.2.3


From baa914cd81f51f4e4f3bae5bb59764b32ad8c353 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Tue, 5 Apr 2022 16:22:20 +0900
Subject: firewire: add kernel API to access CYCLE_TIME register

1394 OHCI specification defined Isochronous Cycle Timer Register to get
value of CYCLE_TIME register defined by IEEE 1394 for CSR architecture
defined by ISO/IEC 13213. Unit driver can calculate packet time by
compute with the value of CYCLE_TIME and timeStamp field in descriptor
of each isochronous and asynchronous context. The resolution of CYCLE_TIME
is 49.576 MHz, while the one of timeStamp is 8,000 Hz.

Current implementation of Linux FireWire subsystem allows the driver to
get the value of CYCLE_TIMER CSR register by transaction service. The
transaction service has overhead in regard of access to MMIO register.

This commit adds kernel API for unit driver to access the register
directly.

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Link: https://lore.kernel.org/r/20220405072221.226217-3-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 drivers/firewire/core-card.c | 28 ++++++++++++++++++++++++++++
 drivers/firewire/core-cdev.c |  6 ++++--
 include/linux/firewire.h     |  2 ++
 3 files changed, 34 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c
index d994da6cf465..cd09de61bc4f 100644
--- a/drivers/firewire/core-card.c
+++ b/drivers/firewire/core-card.c
@@ -702,3 +702,31 @@ void fw_core_remove_card(struct fw_card *card)
 	WARN_ON(!list_empty(&card->transaction_list));
 }
 EXPORT_SYMBOL(fw_core_remove_card);
+
+/**
+ * fw_card_read_cycle_time: read from Isochronous Cycle Timer Register of 1394 OHCI in MMIO region
+ *			    for controller card.
+ * @card: The instance of card for 1394 OHCI controller.
+ * @cycle_time: The mutual reference to value of cycle time for the read operation.
+ *
+ * Read value from Isochronous Cycle Timer Register of 1394 OHCI in MMIO region for the given
+ * controller card. This function accesses the region without any lock primitives or IRQ mask.
+ * When returning successfully, the content of @value argument has value aligned to host endianness,
+ * formetted by CYCLE_TIME CSR Register of IEEE 1394 std.
+ *
+ * Context: Any context.
+ * Return:
+ * * 0 - Read successfully.
+ * * -ENODEV - The controller is unavailable due to being removed or unbound.
+ */
+int fw_card_read_cycle_time(struct fw_card *card, u32 *cycle_time)
+{
+	if (card->driver->read_csr == dummy_read_csr)
+		return -ENODEV;
+
+	// It's possible to switch to dummy driver between the above and the below. This is the best
+	// effort to return -ENODEV.
+	*cycle_time = card->driver->read_csr(card, CSR_CYCLE_TIME);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fw_card_read_cycle_time);
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index 9f89c17730b1..8e9670036e5c 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -1216,7 +1216,9 @@ static int ioctl_get_cycle_timer2(struct client *client, union ioctl_arg *arg)
 
 	local_irq_disable();
 
-	cycle_time = card->driver->read_csr(card, CSR_CYCLE_TIME);
+	ret = fw_card_read_cycle_time(card, &cycle_time);
+	if (ret < 0)
+		goto end;
 
 	switch (a->clk_id) {
 	case CLOCK_REALTIME:      ktime_get_real_ts64(&ts);	break;
@@ -1225,7 +1227,7 @@ static int ioctl_get_cycle_timer2(struct client *client, union ioctl_arg *arg)
 	default:
 		ret = -EINVAL;
 	}
-
+end:
 	local_irq_enable();
 
 	a->tv_sec      = ts.tv_sec;
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 07967a450eaa..2f467c52bdec 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -150,6 +150,8 @@ static inline void fw_card_put(struct fw_card *card)
 	kref_put(&card->kref, fw_card_release);
 }
 
+int fw_card_read_cycle_time(struct fw_card *card, u32 *cycle_time);
+
 struct fw_attribute_group {
 	struct attribute_group *groups[2];
 	struct attribute_group group;
-- 
cgit v1.2.3


From b2405aa948b95afc5246fa56fc05c3512cd6185c Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Tue, 5 Apr 2022 16:22:21 +0900
Subject: firewire: add kernel API to access packet structure in request
 structure for AR context

In 1394 OHCI specification, descriptor of Asynchronous Receive DMA context
has timeStamp field in its trailer quadlet. The field is written by
the host controller for the time to receive asynchronous request
subaction in isochronous cycle time.

In Linux FireWire subsystem, the value of field is stored to fw_packet
structure and copied to fw_request structure as the part. The fw_request
structure is hidden from unit driver and passed as opaque pointer when
calling registered handler. It's inconvenient to the unit driver which
needs timestamp of packet.

This commit adds kernel API to pick up timestamp from opaque pointer to
fw_request structure.

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Link: https://lore.kernel.org/r/20220405072221.226217-4-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 drivers/firewire/core-transaction.c | 18 ++++++++++++++++++
 include/linux/firewire.h            |  1 +
 2 files changed, 19 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c
index ac487c96bb71..e12a0a4c33f7 100644
--- a/drivers/firewire/core-transaction.c
+++ b/drivers/firewire/core-transaction.c
@@ -619,6 +619,7 @@ struct fw_request {
 	struct fw_packet response;
 	u32 request_header[4];
 	int ack;
+	u32 timestamp;
 	u32 length;
 	u32 data[];
 };
@@ -788,6 +789,7 @@ static struct fw_request *allocate_request(struct fw_card *card,
 	request->response.ack = 0;
 	request->response.callback = free_response_callback;
 	request->ack = p->ack;
+	request->timestamp = p->timestamp;
 	request->length = length;
 	if (data)
 		memcpy(request->data, data, length);
@@ -832,6 +834,22 @@ int fw_get_request_speed(struct fw_request *request)
 }
 EXPORT_SYMBOL(fw_get_request_speed);
 
+/**
+ * fw_request_get_timestamp: Get timestamp of the request.
+ * @request: The opaque pointer to request structure.
+ *
+ * Get timestamp when 1394 OHCI controller receives the asynchronous request subaction. The
+ * timestamp consists of the low order 3 bits of second field and the full 13 bits of count
+ * field of isochronous cycle time register.
+ *
+ * Returns: timestamp of the request.
+ */
+u32 fw_request_get_timestamp(const struct fw_request *request)
+{
+	return request->timestamp;
+}
+EXPORT_SYMBOL_GPL(fw_request_get_timestamp);
+
 static void handle_exclusive_region_request(struct fw_card *card,
 					    struct fw_packet *p,
 					    struct fw_request *request,
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 2f467c52bdec..980019053e54 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -354,6 +354,7 @@ void fw_core_remove_address_handler(struct fw_address_handler *handler);
 void fw_send_response(struct fw_card *card,
 		      struct fw_request *request, int rcode);
 int fw_get_request_speed(struct fw_request *request);
+u32 fw_request_get_timestamp(const struct fw_request *request);
 void fw_send_request(struct fw_card *card, struct fw_transaction *t,
 		     int tcode, int destination_id, int generation, int speed,
 		     unsigned long long offset, void *payload, size_t length,
-- 
cgit v1.2.3


From a8e2512efc65892a1cbf608d9c03c8bcbe5a623a Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Fri, 1 Apr 2022 15:06:04 +0100
Subject: PM: core: Add NS varients of EXPORT[_GPL]_SIMPLE_DEV_PM_OPS and
 runtime pm equiv

As more drivers start to use namespaces, we need to have varients of these
useful macros that allow the export to be in a particular namespace.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h         | 14 +++++++++-----
 include/linux/pm_runtime.h | 10 ++++++++--
 2 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index e65b3ab28377..ffe941958501 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -368,13 +368,13 @@ const struct dev_pm_ops name = { \
 
 #ifdef CONFIG_PM
 #define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \
-			   runtime_resume_fn, idle_fn, sec) \
+			   runtime_resume_fn, idle_fn, sec, ns)		\
 	_DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \
 			   runtime_resume_fn, idle_fn); \
-	_EXPORT_SYMBOL(name, sec)
+	__EXPORT_SYMBOL(name, sec, ns)
 #else
 #define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \
-			   runtime_resume_fn, idle_fn, sec) \
+			   runtime_resume_fn, idle_fn, sec, ns) \
 static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \
 					 resume_fn, runtime_suspend_fn, \
 					 runtime_resume_fn, idle_fn)
@@ -391,9 +391,13 @@ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \
 	_DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL)
 
 #define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
-	_EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "")
+	_EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", "")
 #define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
-	_EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl")
+	_EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", "")
+#define EXPORT_NS_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns)	\
+	_EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", #ns)
+#define EXPORT_NS_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns)	\
+	_EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", #ns)
 
 /* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */
 #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 2bff6a10095d..9e4d056967c6 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -41,10 +41,16 @@
 
 #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \
 	_EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \
-			   suspend_fn, resume_fn, idle_fn, "")
+			   suspend_fn, resume_fn, idle_fn, "", "")
 #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \
 	_EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \
-			   suspend_fn, resume_fn, idle_fn, "_gpl")
+			   suspend_fn, resume_fn, idle_fn, "_gpl", "")
+#define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \
+	_EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \
+			   suspend_fn, resume_fn, idle_fn, "", #ns)
+#define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \
+	_EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \
+			   suspend_fn, resume_fn, idle_fn, "_gpl", #ns)
 
 #ifdef CONFIG_PM
 extern struct workqueue_struct *pm_wq;
-- 
cgit v1.2.3


From 0b5c21bbc01e92745ca1ca4f6fd87d878fa3ea5e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 4 Apr 2022 11:38:47 +0200
Subject: net: ensure net_todo_list is processed quickly

In [1], Will raised a potential issue that the cfg80211 code,
which does (from a locking perspective)

  rtnl_lock()
  wiphy_lock()
  rtnl_unlock()

might be suspectible to ABBA deadlocks, because rtnl_unlock()
calls netdev_run_todo(), which might end up calling rtnl_lock()
again, which could then deadlock (see the comment in the code
added here for the scenario).

Some back and forth and thinking ensued, but clearly this can't
happen if the net_todo_list is empty at the rtnl_unlock() here.
Clearly, the code here cannot actually put an entry on it, and
all other users of rtnl_unlock() will empty it since that will
always go through netdev_run_todo(), emptying the list.

So the only other way to get there would be to add to the list
and then unlock the RTNL without going through rtnl_unlock(),
which is only possible through __rtnl_unlock(). However, this
isn't exported and not used in many places, and none of them
seem to be able to unregister before using it.

Therefore, add a WARN_ON() in the code to ensure this invariant
won't be broken, so that the cfg80211 (or any similar) code
stays safe.

[1] https://lore.kernel.org/r/Yjzpo3TfZxtKPMAG@google.com

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://lore.kernel.org/r/20220404113847.0ee02e4a70da.Ic73d206e217db20fd22dcec14fe5442ca732804b@changeid
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  3 ++-
 net/core/dev.c            |  2 +-
 net/core/rtnetlink.c      | 33 +++++++++++++++++++++++++++++++++
 3 files changed, 36 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 59e27a2b7bf0..b6a1e7f643da 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3894,7 +3894,8 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
 extern int		netdev_budget;
 extern unsigned int	netdev_budget_usecs;
 
-/* Called by rtnetlink.c:rtnl_unlock() */
+/* Used by rtnetlink.c:__rtnl_unlock()/rtnl_unlock() */
+extern struct list_head net_todo_list;
 void netdev_run_todo(void);
 
 static inline void __dev_put(struct net_device *dev)
diff --git a/net/core/dev.c b/net/core/dev.c
index 8c6c08446556..2ec17358d7b4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9431,7 +9431,7 @@ static int dev_new_index(struct net *net)
 }
 
 /* Delayed registration/unregisteration */
-static LIST_HEAD(net_todo_list);
+LIST_HEAD(net_todo_list);
 DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 
 static void net_set_todo(struct net_device *dev)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 159c9c61e6af..0e4502d641eb 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -95,6 +95,39 @@ void __rtnl_unlock(void)
 
 	defer_kfree_skb_list = NULL;
 
+	/* Ensure that we didn't actually add any TODO item when __rtnl_unlock()
+	 * is used. In some places, e.g. in cfg80211, we have code that will do
+	 * something like
+	 *   rtnl_lock()
+	 *   wiphy_lock()
+	 *   ...
+	 *   rtnl_unlock()
+	 *
+	 * and because netdev_run_todo() acquires the RTNL for items on the list
+	 * we could cause a situation such as this:
+	 * Thread 1			Thread 2
+	 *				  rtnl_lock()
+	 *				  unregister_netdevice()
+	 *				  __rtnl_unlock()
+	 * rtnl_lock()
+	 * wiphy_lock()
+	 * rtnl_unlock()
+	 *   netdev_run_todo()
+	 *     __rtnl_unlock()
+	 *
+	 *     // list not empty now
+	 *     // because of thread 2
+	 *				  rtnl_lock()
+	 *     while (!list_empty(...))
+	 *       rtnl_lock()
+	 *				  wiphy_lock()
+	 * **** DEADLOCK ****
+	 *
+	 * However, usage of __rtnl_unlock() is rare, and so we can ensure that
+	 * it's not used in cases where something is added to do the list.
+	 */
+	WARN_ON(!list_empty(&net_todo_list));
+
 	mutex_unlock(&rtnl_mutex);
 
 	while (head) {
-- 
cgit v1.2.3


From 40379a0084c2f65eb62c102f5bbf5cdc14a50410 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 4 Apr 2022 15:08:15 +0300
Subject: net/mlx5_fpga: Drop INNOVA TLS support

Mellanox INNOVA TLS cards are EOL in May, 2018 [1]. As such, the code
is unmaintained, untested and not in-use by any upstream/distro oriented
customers. In order to reduce code complexity, drop the kernel code.

[1] https://network.nvidia.com/related-docs/eol/LCR-000286.pdf

Link: https://lore.kernel.org/r/b88add368def721ea9d054cb69def72d9e3f67aa.1649073691.git.leonro@nvidia.com
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    |  14 -
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   1 -
 .../net/ethernet/mellanox/mlx5/core/accel/tls.c    |  47 --
 .../net/ethernet/mellanox/mlx5/core/accel/tls.h    |  56 --
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   1 -
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls.c | 180 +-----
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls.h |  48 +-
 .../mellanox/mlx5/core/en_accel/tls_rxtx.c         | 324 +----------
 .../mellanox/mlx5/core/en_accel/tls_rxtx.h         |   8 +-
 .../mellanox/mlx5/core/en_accel/tls_stats.c        |  17 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |   3 -
 .../net/ethernet/mellanox/mlx5/core/fpga/core.h    |   1 -
 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c | 622 ---------------------
 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h |  74 ---
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  10 -
 include/linux/mlx5/mlx5_ifc_fpga.h                 |  63 ---
 16 files changed, 10 insertions(+), 1459 deletions(-)
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 4ba1a78c6515..21df10bb14c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -177,20 +177,6 @@ config MLX5_EN_IPSEC
 	  Note: Support for hardware with this capability needs to be selected
 	  for this option to become available.
 
-config MLX5_FPGA_TLS
-	bool "Mellanox Technologies TLS Innova support"
-	depends on TLS_DEVICE
-	depends on TLS=y || MLX5_CORE=m
-	depends on MLX5_CORE_EN
-	depends on MLX5_FPGA
-	select MLX5_EN_TLS
-	help
-	Build TLS support for the Innova family of network cards by Mellanox
-	Technologies. Innova network cards are comprised of a ConnectX chip
-	and an FPGA chip on one board. If you select this option, the
-	mlx5_core driver will include the Innova FPGA core and allow building
-	sandbox-specific client drivers.
-
 config MLX5_TLS
 	bool "Mellanox Technologies TLS Connect-X support"
 	depends on TLS_DEVICE
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 4bc666714a35..33525f7d0aa0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -90,7 +90,6 @@ mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib
 #
 mlx5_core-$(CONFIG_MLX5_IPSEC) += accel/ipsec_offload.o
 mlx5_core-$(CONFIG_MLX5_FPGA_IPSEC) += fpga/ipsec.o
-mlx5_core-$(CONFIG_MLX5_FPGA_TLS)   += fpga/tls.o
 mlx5_core-$(CONFIG_MLX5_ACCEL)      += lib/crypto.o accel/tls.o accel/ipsec.o
 
 mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
index 6c2b86a26863..fe82c4140d85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
@@ -37,53 +37,6 @@
 #include "mlx5_core.h"
 #include "lib/mlx5.h"
 
-#ifdef CONFIG_MLX5_FPGA_TLS
-#include "fpga/tls.h"
-
-int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-			    struct tls_crypto_info *crypto_info,
-			    u32 start_offload_tcp_sn, u32 *p_swid,
-			    bool direction_sx)
-{
-	return mlx5_fpga_tls_add_flow(mdev, flow, crypto_info,
-				      start_offload_tcp_sn, p_swid,
-				      direction_sx);
-}
-
-void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
-			     bool direction_sx)
-{
-	mlx5_fpga_tls_del_flow(mdev, swid, GFP_KERNEL, direction_sx);
-}
-
-int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
-			     u32 seq, __be64 rcd_sn)
-{
-	return mlx5_fpga_tls_resync_rx(mdev, handle, seq, rcd_sn);
-}
-
-bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
-{
-	return mlx5_fpga_is_tls_device(mdev) ||
-		mlx5_accel_is_ktls_device(mdev);
-}
-
-u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev)
-{
-	return mlx5_fpga_tls_device_caps(mdev);
-}
-
-int mlx5_accel_tls_init(struct mlx5_core_dev *mdev)
-{
-	return mlx5_fpga_tls_init(mdev);
-}
-
-void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev)
-{
-	mlx5_fpga_tls_cleanup(mdev);
-}
-#endif
-
 #ifdef CONFIG_MLX5_TLS
 int mlx5_ktls_create_key(struct mlx5_core_dev *mdev,
 			 struct tls_crypto_info *crypto_info,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index fd874f0c380a..6f92ebe3cc82 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -97,60 +97,4 @@ static inline bool
 mlx5e_ktls_type_check(struct mlx5_core_dev *mdev,
 		      struct tls_crypto_info *crypto_info) { return false; }
 #endif
-
-enum {
-	MLX5_ACCEL_TLS_TX = BIT(0),
-	MLX5_ACCEL_TLS_RX = BIT(1),
-	MLX5_ACCEL_TLS_V12 = BIT(2),
-	MLX5_ACCEL_TLS_V13 = BIT(3),
-	MLX5_ACCEL_TLS_LRO = BIT(4),
-	MLX5_ACCEL_TLS_IPV6 = BIT(5),
-	MLX5_ACCEL_TLS_AES_GCM128 = BIT(30),
-	MLX5_ACCEL_TLS_AES_GCM256 = BIT(31),
-};
-
-struct mlx5_ifc_tls_flow_bits {
-	u8         src_port[0x10];
-	u8         dst_port[0x10];
-	union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6;
-	union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6;
-	u8         ipv6[0x1];
-	u8         direction_sx[0x1];
-	u8         reserved_at_2[0x1e];
-};
-
-#ifdef CONFIG_MLX5_FPGA_TLS
-int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-			    struct tls_crypto_info *crypto_info,
-			    u32 start_offload_tcp_sn, u32 *p_swid,
-			    bool direction_sx);
-void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
-			     bool direction_sx);
-int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
-			     u32 seq, __be64 rcd_sn);
-bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev);
-u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev);
-int mlx5_accel_tls_init(struct mlx5_core_dev *mdev);
-void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev);
-
-#else
-
-static inline int
-mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-			struct tls_crypto_info *crypto_info,
-			u32 start_offload_tcp_sn, u32 *p_swid,
-			bool direction_sx) { return -ENOTSUPP; }
-static inline void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
-					   bool direction_sx) { }
-static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
-					   u32 seq, __be64 rcd_sn) { return 0; }
-static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
-{
-	return mlx5_accel_is_ktls_device(mdev);
-}
-static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; }
-static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; }
-static inline void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev) { }
-#endif
-
 #endif	/* __MLX5_ACCEL_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8653ac0fd865..50818081bdc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -354,7 +354,6 @@ enum {
 	MLX5E_RQ_STATE_AM,
 	MLX5E_RQ_STATE_NO_CSUM_COMPLETE,
 	MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */
-	MLX5E_RQ_STATE_FPGA_TLS, /* FPGA TLS enabled */
 	MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, /* set when mini_cqe_resp_stride_index cap is used */
 	MLX5E_RQ_STATE_SHAMPO, /* set when SHAMPO cap is used */
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index b8fc863aa68d..0c6e165c154e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -36,188 +36,12 @@
 #include "en_accel/tls.h"
 #include "accel/tls.h"
 
-static void mlx5e_tls_set_ipv4_flow(void *flow, struct sock *sk)
-{
-	struct inet_sock *inet = inet_sk(sk);
-
-	MLX5_SET(tls_flow, flow, ipv6, 0);
-	memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
-	       &inet->inet_daddr, MLX5_FLD_SZ_BYTES(ipv4_layout, ipv4));
-	memcpy(MLX5_ADDR_OF(tls_flow, flow, src_ipv4_src_ipv6.ipv4_layout.ipv4),
-	       &inet->inet_rcv_saddr, MLX5_FLD_SZ_BYTES(ipv4_layout, ipv4));
-}
-
-#if IS_ENABLED(CONFIG_IPV6)
-static void mlx5e_tls_set_ipv6_flow(void *flow, struct sock *sk)
-{
-	struct ipv6_pinfo *np = inet6_sk(sk);
-
-	MLX5_SET(tls_flow, flow, ipv6, 1);
-	memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-	       &sk->sk_v6_daddr, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
-	memcpy(MLX5_ADDR_OF(tls_flow, flow, src_ipv4_src_ipv6.ipv6_layout.ipv6),
-	       &np->saddr, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
-}
-#endif
-
-static void mlx5e_tls_set_flow_tcp_ports(void *flow, struct sock *sk)
-{
-	struct inet_sock *inet = inet_sk(sk);
-
-	memcpy(MLX5_ADDR_OF(tls_flow, flow, src_port), &inet->inet_sport,
-	       MLX5_FLD_SZ_BYTES(tls_flow, src_port));
-	memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_port), &inet->inet_dport,
-	       MLX5_FLD_SZ_BYTES(tls_flow, dst_port));
-}
-
-static int mlx5e_tls_set_flow(void *flow, struct sock *sk, u32 caps)
-{
-	switch (sk->sk_family) {
-	case AF_INET:
-		mlx5e_tls_set_ipv4_flow(flow, sk);
-		break;
-#if IS_ENABLED(CONFIG_IPV6)
-	case AF_INET6:
-		if (!sk->sk_ipv6only &&
-		    ipv6_addr_type(&sk->sk_v6_daddr) == IPV6_ADDR_MAPPED) {
-			mlx5e_tls_set_ipv4_flow(flow, sk);
-			break;
-		}
-		if (!(caps & MLX5_ACCEL_TLS_IPV6))
-			goto error_out;
-
-		mlx5e_tls_set_ipv6_flow(flow, sk);
-		break;
-#endif
-	default:
-		goto error_out;
-	}
-
-	mlx5e_tls_set_flow_tcp_ports(flow, sk);
-	return 0;
-error_out:
-	return -EINVAL;
-}
-
-static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
-			 enum tls_offload_ctx_dir direction,
-			 struct tls_crypto_info *crypto_info,
-			 u32 start_offload_tcp_sn)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 caps = mlx5_accel_tls_device_caps(mdev);
-	int ret = -ENOMEM;
-	void *flow;
-	u32 swid;
-
-	flow = kzalloc(MLX5_ST_SZ_BYTES(tls_flow), GFP_KERNEL);
-	if (!flow)
-		return ret;
-
-	ret = mlx5e_tls_set_flow(flow, sk, caps);
-	if (ret)
-		goto free_flow;
-
-	ret = mlx5_accel_tls_add_flow(mdev, flow, crypto_info,
-				      start_offload_tcp_sn, &swid,
-				      direction == TLS_OFFLOAD_CTX_DIR_TX);
-	if (ret < 0)
-		goto free_flow;
-
-	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
-		struct mlx5e_tls_offload_context_tx *tx_ctx =
-		    mlx5e_get_tls_tx_context(tls_ctx);
-
-		tx_ctx->swid = htonl(swid);
-		tx_ctx->expected_seq = start_offload_tcp_sn;
-	} else {
-		struct mlx5e_tls_offload_context_rx *rx_ctx =
-		    mlx5e_get_tls_rx_context(tls_ctx);
-
-		rx_ctx->handle = htonl(swid);
-	}
-
-	return 0;
-free_flow:
-	kfree(flow);
-	return ret;
-}
-
-static void mlx5e_tls_del(struct net_device *netdev,
-			  struct tls_context *tls_ctx,
-			  enum tls_offload_ctx_dir direction)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	unsigned int handle;
-
-	handle = ntohl((direction == TLS_OFFLOAD_CTX_DIR_TX) ?
-		       mlx5e_get_tls_tx_context(tls_ctx)->swid :
-		       mlx5e_get_tls_rx_context(tls_ctx)->handle);
-
-	mlx5_accel_tls_del_flow(priv->mdev, handle,
-				direction == TLS_OFFLOAD_CTX_DIR_TX);
-}
-
-static int mlx5e_tls_resync(struct net_device *netdev, struct sock *sk,
-			    u32 seq, u8 *rcd_sn_data,
-			    enum tls_offload_ctx_dir direction)
-{
-	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_tls_offload_context_rx *rx_ctx;
-	__be64 rcd_sn = *(__be64 *)rcd_sn_data;
-
-	if (WARN_ON_ONCE(direction != TLS_OFFLOAD_CTX_DIR_RX))
-		return -EINVAL;
-	rx_ctx = mlx5e_get_tls_rx_context(tls_ctx);
-
-	netdev_info(netdev, "resyncing seq %d rcd %lld\n", seq,
-		    be64_to_cpu(rcd_sn));
-	mlx5_accel_tls_resync_rx(priv->mdev, rx_ctx->handle, seq, rcd_sn);
-	atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_reply);
-
-	return 0;
-}
-
-static const struct tlsdev_ops mlx5e_tls_ops = {
-	.tls_dev_add = mlx5e_tls_add,
-	.tls_dev_del = mlx5e_tls_del,
-	.tls_dev_resync = mlx5e_tls_resync,
-};
-
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 {
-	struct net_device *netdev = priv->netdev;
-	u32 caps;
-
-	if (mlx5e_accel_is_ktls_device(priv->mdev)) {
-		mlx5e_ktls_build_netdev(priv);
+	if (!mlx5e_accel_is_ktls_device(priv->mdev))
 		return;
-	}
-
-	/* FPGA */
-	if (!mlx5e_accel_is_tls_device(priv->mdev))
-		return;
-
-	caps = mlx5_accel_tls_device_caps(priv->mdev);
-	if (caps & MLX5_ACCEL_TLS_TX) {
-		netdev->features          |= NETIF_F_HW_TLS_TX;
-		netdev->hw_features       |= NETIF_F_HW_TLS_TX;
-	}
-
-	if (caps & MLX5_ACCEL_TLS_RX) {
-		netdev->features          |= NETIF_F_HW_TLS_RX;
-		netdev->hw_features       |= NETIF_F_HW_TLS_RX;
-	}
-
-	if (!(caps & MLX5_ACCEL_TLS_LRO)) {
-		netdev->features          &= ~NETIF_F_LRO;
-		netdev->hw_features       &= ~NETIF_F_LRO;
-	}
 
-	netdev->tlsdev_ops = &mlx5e_tls_ops;
+	mlx5e_ktls_build_netdev(priv);
 }
 
 int mlx5e_tls_init(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index 62ecf14bf86a..fc13b2ebe6b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -43,16 +43,8 @@
 struct mlx5e_tls_sw_stats {
 	atomic64_t tx_tls_ctx;
 	atomic64_t tx_tls_del;
-	atomic64_t tx_tls_drop_metadata;
-	atomic64_t tx_tls_drop_resync_alloc;
-	atomic64_t tx_tls_drop_no_sync_data;
-	atomic64_t tx_tls_drop_bypass_required;
 	atomic64_t rx_tls_ctx;
 	atomic64_t rx_tls_del;
-	atomic64_t rx_tls_drop_resync_request;
-	atomic64_t rx_tls_resync_request;
-	atomic64_t rx_tls_resync_reply;
-	atomic64_t rx_tls_auth_fail;
 };
 
 struct mlx5e_tls {
@@ -60,42 +52,6 @@ struct mlx5e_tls {
 	struct workqueue_struct *rx_wq;
 };
 
-struct mlx5e_tls_offload_context_tx {
-	struct tls_offload_context_tx base;
-	u32 expected_seq;
-	__be32 swid;
-};
-
-static inline struct mlx5e_tls_offload_context_tx *
-mlx5e_get_tls_tx_context(struct tls_context *tls_ctx)
-{
-	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_tx) >
-		     TLS_OFFLOAD_CONTEXT_SIZE_TX);
-	return container_of(tls_offload_ctx_tx(tls_ctx),
-			    struct mlx5e_tls_offload_context_tx,
-			    base);
-}
-
-struct mlx5e_tls_offload_context_rx {
-	struct tls_offload_context_rx base;
-	__be32 handle;
-};
-
-static inline struct mlx5e_tls_offload_context_rx *
-mlx5e_get_tls_rx_context(struct tls_context *tls_ctx)
-{
-	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_rx) >
-		     TLS_OFFLOAD_CONTEXT_SIZE_RX);
-	return container_of(tls_offload_ctx_rx(tls_ctx),
-			    struct mlx5e_tls_offload_context_rx,
-			    base);
-}
-
-static inline bool mlx5e_is_tls_on(struct mlx5e_priv *priv)
-{
-	return priv->tls;
-}
-
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv);
 int mlx5e_tls_init(struct mlx5e_priv *priv);
 void mlx5e_tls_cleanup(struct mlx5e_priv *priv);
@@ -106,8 +62,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data);
 
 static inline bool mlx5e_accel_is_tls_device(struct mlx5_core_dev *mdev)
 {
-	return !is_kdump_kernel() &&
-		mlx5_accel_is_tls_device(mdev);
+	return !is_kdump_kernel() && mlx5_accel_is_ktls_device(mdev);
 }
 
 #else
@@ -119,7 +74,6 @@ static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 		mlx5e_ktls_build_netdev(priv);
 }
 
-static inline bool mlx5e_is_tls_on(struct mlx5e_priv *priv) { return false; }
 static inline int mlx5e_tls_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tls_cleanup(struct mlx5e_priv *priv) { }
 static inline int mlx5e_tls_get_count(struct mlx5e_priv *priv) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index a05580cea481..39412fafa860 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -38,230 +38,11 @@
 #include <net/inet6_hashtables.h>
 #include <linux/ipv6.h>
 
-#define SYNDROM_DECRYPTED  0x30
-#define SYNDROM_RESYNC_REQUEST 0x31
-#define SYNDROM_AUTH_FAILED 0x32
-
-#define SYNDROME_OFFLOAD_REQUIRED 32
-#define SYNDROME_SYNC 33
-
-struct sync_info {
-	u64 rcd_sn;
-	s32 sync_len;
-	int nr_frags;
-	skb_frag_t frags[MAX_SKB_FRAGS];
-};
-
-struct recv_metadata_content {
-	u8 syndrome;
-	u8 reserved;
-	__be32 sync_seq;
-} __packed;
-
-struct send_metadata_content {
-	/* One byte of syndrome followed by 3 bytes of swid */
-	__be32 syndrome_swid;
-	__be16 first_seq;
-} __packed;
-
-struct mlx5e_tls_metadata {
-	union {
-		/* from fpga to host */
-		struct recv_metadata_content recv;
-		/* from host to fpga */
-		struct send_metadata_content send;
-		unsigned char raw[6];
-	} __packed content;
-	/* packet type ID field	*/
-	__be16 ethertype;
-} __packed;
-
-static int mlx5e_tls_add_metadata(struct sk_buff *skb, __be32 swid)
-{
-	struct mlx5e_tls_metadata *pet;
-	struct ethhdr *eth;
-
-	if (skb_cow_head(skb, sizeof(struct mlx5e_tls_metadata)))
-		return -ENOMEM;
-
-	eth = (struct ethhdr *)skb_push(skb, sizeof(struct mlx5e_tls_metadata));
-	skb->mac_header -= sizeof(struct mlx5e_tls_metadata);
-	pet = (struct mlx5e_tls_metadata *)(eth + 1);
-
-	memmove(skb->data, skb->data + sizeof(struct mlx5e_tls_metadata),
-		2 * ETH_ALEN);
-
-	eth->h_proto = cpu_to_be16(MLX5E_METADATA_ETHER_TYPE);
-	pet->content.send.syndrome_swid =
-		htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
-
-	return 0;
-}
-
-static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context_tx *context,
-				   u32 tcp_seq, struct sync_info *info)
-{
-	int remaining, i = 0, ret = -EINVAL;
-	struct tls_record_info *record;
-	unsigned long flags;
-	s32 sync_size;
-
-	spin_lock_irqsave(&context->base.lock, flags);
-	record = tls_get_record(&context->base, tcp_seq, &info->rcd_sn);
-
-	if (unlikely(!record))
-		goto out;
-
-	sync_size = tcp_seq - tls_record_start_seq(record);
-	info->sync_len = sync_size;
-	if (unlikely(sync_size < 0)) {
-		if (tls_record_is_start_marker(record))
-			goto done;
-
-		goto out;
-	}
-
-	remaining = sync_size;
-	while (remaining > 0) {
-		info->frags[i] = record->frags[i];
-		__skb_frag_ref(&info->frags[i]);
-		remaining -= skb_frag_size(&info->frags[i]);
-
-		if (remaining < 0)
-			skb_frag_size_add(&info->frags[i], remaining);
-
-		i++;
-	}
-	info->nr_frags = i;
-done:
-	ret = 0;
-out:
-	spin_unlock_irqrestore(&context->base.lock, flags);
-	return ret;
-}
-
-static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
-					struct sk_buff *nskb, u32 tcp_seq,
-					int headln, __be64 rcd_sn)
-{
-	struct mlx5e_tls_metadata *pet;
-	u8 syndrome = SYNDROME_SYNC;
-	struct iphdr *iph;
-	struct tcphdr *th;
-	int data_len, mss;
-
-	nskb->dev = skb->dev;
-	skb_reset_mac_header(nskb);
-	skb_set_network_header(nskb, skb_network_offset(skb));
-	skb_set_transport_header(nskb, skb_transport_offset(skb));
-	memcpy(nskb->data, skb->data, headln);
-	memcpy(nskb->data + headln, &rcd_sn, sizeof(rcd_sn));
-
-	iph = ip_hdr(nskb);
-	iph->tot_len = htons(nskb->len - skb_network_offset(nskb));
-	th = tcp_hdr(nskb);
-	data_len = nskb->len - headln;
-	tcp_seq -= data_len;
-	th->seq = htonl(tcp_seq);
-
-	mss = nskb->dev->mtu - (headln - skb_network_offset(nskb));
-	skb_shinfo(nskb)->gso_size = 0;
-	if (data_len > mss) {
-		skb_shinfo(nskb)->gso_size = mss;
-		skb_shinfo(nskb)->gso_segs = DIV_ROUND_UP(data_len, mss);
-	}
-	skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type;
-
-	pet = (struct mlx5e_tls_metadata *)(nskb->data + sizeof(struct ethhdr));
-	memcpy(pet, &syndrome, sizeof(syndrome));
-	pet->content.send.first_seq = htons(tcp_seq);
-
-	/* MLX5 devices don't care about the checksum partial start, offset
-	 * and pseudo header
-	 */
-	nskb->ip_summed = CHECKSUM_PARTIAL;
-
-	nskb->queue_mapping = skb->queue_mapping;
-}
-
-static bool mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
-				 struct mlx5e_txqsq *sq, struct sk_buff *skb,
-				 struct mlx5e_tls *tls)
-{
-	u32 tcp_seq = ntohl(tcp_hdr(skb)->seq);
-	struct sync_info info;
-	struct sk_buff *nskb;
-	int linear_len = 0;
-	int headln;
-	int i;
-
-	sq->stats->tls_ooo++;
-
-	if (mlx5e_tls_get_sync_data(context, tcp_seq, &info)) {
-		/* We might get here if a retransmission reaches the driver
-		 * after the relevant record is acked.
-		 * It should be safe to drop the packet in this case
-		 */
-		atomic64_inc(&tls->sw_stats.tx_tls_drop_no_sync_data);
-		goto err_out;
-	}
-
-	if (unlikely(info.sync_len < 0)) {
-		u32 payload;
-
-		headln = skb_transport_offset(skb) + tcp_hdrlen(skb);
-		payload = skb->len - headln;
-		if (likely(payload <= -info.sync_len))
-			/* SKB payload doesn't require offload
-			 */
-			return true;
-
-		atomic64_inc(&tls->sw_stats.tx_tls_drop_bypass_required);
-		goto err_out;
-	}
-
-	if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) {
-		atomic64_inc(&tls->sw_stats.tx_tls_drop_metadata);
-		goto err_out;
-	}
-
-	headln = skb_transport_offset(skb) + tcp_hdrlen(skb);
-	linear_len += headln + sizeof(info.rcd_sn);
-	nskb = alloc_skb(linear_len, GFP_ATOMIC);
-	if (unlikely(!nskb)) {
-		atomic64_inc(&tls->sw_stats.tx_tls_drop_resync_alloc);
-		goto err_out;
-	}
-
-	context->expected_seq = tcp_seq + skb->len - headln;
-	skb_put(nskb, linear_len);
-	for (i = 0; i < info.nr_frags; i++)
-		skb_shinfo(nskb)->frags[i] = info.frags[i];
-
-	skb_shinfo(nskb)->nr_frags = info.nr_frags;
-	nskb->data_len = info.sync_len;
-	nskb->len += info.sync_len;
-	sq->stats->tls_resync_bytes += nskb->len;
-	mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln,
-				    cpu_to_be64(info.rcd_sn));
-	mlx5e_sq_xmit_simple(sq, nskb, true);
-
-	return true;
-
-err_out:
-	dev_kfree_skb_any(skb);
-	return false;
-}
-
 bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 			     struct sk_buff *skb, struct mlx5e_accel_tx_tls_state *state)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_tls_offload_context_tx *context;
 	struct tls_context *tls_ctx;
-	u32 expected_seq;
 	int datalen;
-	u32 skb_seq;
 
 	datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb));
 	if (!datalen)
@@ -273,118 +54,17 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 	if (WARN_ON_ONCE(tls_ctx->netdev != netdev))
 		goto err_out;
 
-	if (mlx5e_accel_is_ktls_tx(sq->mdev))
-		return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, datalen, state);
-
-	/* FPGA */
-	skb_seq = ntohl(tcp_hdr(skb)->seq);
-	context = mlx5e_get_tls_tx_context(tls_ctx);
-	expected_seq = context->expected_seq;
-
-	if (unlikely(expected_seq != skb_seq))
-		return mlx5e_tls_handle_ooo(context, sq, skb, priv->tls);
-
-	if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) {
-		atomic64_inc(&priv->tls->sw_stats.tx_tls_drop_metadata);
-		dev_kfree_skb_any(skb);
-		return false;
-	}
-
-	context->expected_seq = skb_seq + datalen;
-	return true;
+	return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, datalen, state);
 
 err_out:
 	dev_kfree_skb_any(skb);
 	return false;
 }
 
-static int tls_update_resync_sn(struct net_device *netdev,
-				struct sk_buff *skb,
-				struct mlx5e_tls_metadata *mdata)
-{
-	struct sock *sk = NULL;
-	struct iphdr *iph;
-	struct tcphdr *th;
-	__be32 seq;
-
-	if (mdata->ethertype != htons(ETH_P_IP))
-		return -EINVAL;
-
-	iph = (struct iphdr *)(mdata + 1);
-
-	th = ((void *)iph) + iph->ihl * 4;
-
-	if (iph->version == 4) {
-		sk = inet_lookup_established(dev_net(netdev), &tcp_hashinfo,
-					     iph->saddr, th->source, iph->daddr,
-					     th->dest, netdev->ifindex);
-#if IS_ENABLED(CONFIG_IPV6)
-	} else {
-		struct ipv6hdr *ipv6h = (struct ipv6hdr *)iph;
-
-		sk = __inet6_lookup_established(dev_net(netdev), &tcp_hashinfo,
-						&ipv6h->saddr, th->source,
-						&ipv6h->daddr, ntohs(th->dest),
-						netdev->ifindex, 0);
-#endif
-	}
-	if (!sk || sk->sk_state == TCP_TIME_WAIT) {
-		struct mlx5e_priv *priv = netdev_priv(netdev);
-
-		atomic64_inc(&priv->tls->sw_stats.rx_tls_drop_resync_request);
-		goto out;
-	}
-
-	skb->sk = sk;
-	skb->destructor = sock_edemux;
-
-	memcpy(&seq, &mdata->content.recv.sync_seq, sizeof(seq));
-	tls_offload_rx_resync_request(sk, seq);
-out:
-	return 0;
-}
-
-/* FPGA tls rx handler */
-void mlx5e_tls_handle_rx_skb_metadata(struct mlx5e_rq *rq, struct sk_buff *skb,
-				      u32 *cqe_bcnt)
-{
-	struct mlx5e_tls_metadata *mdata;
-	struct mlx5e_priv *priv;
-
-	/* Use the metadata */
-	mdata = (struct mlx5e_tls_metadata *)(skb->data + ETH_HLEN);
-	switch (mdata->content.recv.syndrome) {
-	case SYNDROM_DECRYPTED:
-		skb->decrypted = 1;
-		break;
-	case SYNDROM_RESYNC_REQUEST:
-		tls_update_resync_sn(rq->netdev, skb, mdata);
-		priv = netdev_priv(rq->netdev);
-		atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_request);
-		break;
-	case SYNDROM_AUTH_FAILED:
-		/* Authentication failure will be observed and verified by kTLS */
-		priv = netdev_priv(rq->netdev);
-		atomic64_inc(&priv->tls->sw_stats.rx_tls_auth_fail);
-		break;
-	default:
-		/* Bypass the metadata header to others */
-		return;
-	}
-
-	remove_metadata_hdr(skb);
-	*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
-}
-
 u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 {
 	if (!mlx5e_accel_is_tls_device(mdev))
 		return 0;
 
-	if (mlx5e_accel_is_ktls_device(mdev))
-		return mlx5e_ktls_get_stop_room(mdev, params);
-
-	/* FPGA */
-	/* Resync SKB. */
-	return mlx5e_stop_room_for_max_wqe(mdev);
+	return mlx5e_ktls_get_stop_room(mdev, params);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
index 0ca0a023fb8d..168acceb0d28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
@@ -60,18 +60,12 @@ mlx5e_tls_handle_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg,
 	cseg->tis_tir_num = cpu_to_be32(state->tls_tisn << 8);
 }
 
-void mlx5e_tls_handle_rx_skb_metadata(struct mlx5e_rq *rq, struct sk_buff *skb,
-				      u32 *cqe_bcnt);
-
 static inline void
 mlx5e_tls_handle_rx_skb(struct mlx5e_rq *rq, struct sk_buff *skb,
 			struct mlx5_cqe64 *cqe, u32 *cqe_bcnt)
 {
 	if (unlikely(get_cqe_tls_offload(cqe))) /* cqe bit indicates a TLS device */
-		return mlx5e_ktls_handle_rx_skb(rq, skb, cqe, cqe_bcnt);
-
-	if (unlikely(test_bit(MLX5E_RQ_STATE_FPGA_TLS, &rq->state) && is_metadata_hdr_valid(skb)))
-		return mlx5e_tls_handle_rx_skb_metadata(rq, skb, cqe_bcnt);
+		mlx5e_ktls_handle_rx_skb(rq, skb, cqe, cqe_bcnt);
 }
 
 #else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index 56e7b2aee85f..c25e8742bbbf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -38,13 +38,6 @@
 #include "fpga/sdk.h"
 #include "en_accel/tls.h"
 
-static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
-	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_metadata) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_resync_alloc) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_no_sync_data) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_bypass_required) },
-};
-
 static const struct counter_desc mlx5e_ktls_sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_ctx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_del) },
@@ -59,18 +52,16 @@ static const struct counter_desc *get_tls_atomic_stats(struct mlx5e_priv *priv)
 {
 	if (!priv->tls)
 		return NULL;
-	if (mlx5e_accel_is_ktls_device(priv->mdev))
-		return mlx5e_ktls_sw_stats_desc;
-	return mlx5e_tls_sw_stats_desc;
+
+	return mlx5e_ktls_sw_stats_desc;
 }
 
 int mlx5e_tls_get_count(struct mlx5e_priv *priv)
 {
 	if (!priv->tls)
 		return 0;
-	if (mlx5e_accel_is_ktls_device(priv->mdev))
-		return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc);
-	return ARRAY_SIZE(mlx5e_tls_sw_stats_desc);
+
+	return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc);
 }
 
 int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2f1dedc721d1..7423c6830c4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1036,9 +1036,6 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 	if (err)
 		goto err_destroy_rq;
 
-	if (mlx5e_is_tls_on(rq->priv) && !mlx5e_accel_is_ktls_device(mdev))
-		__set_bit(MLX5E_RQ_STATE_FPGA_TLS, &rq->state); /* must be FPGA */
-
 	if (MLX5_CAP_ETH(mdev, cqe_checksum_full))
 		__set_bit(MLX5E_RQ_STATE_CSUM_FULL, &rq->state);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
index 2a984e82ae16..e9e72d260681 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
@@ -59,7 +59,6 @@ struct mlx5_fpga_device {
 	} conn_res;
 
 	struct mlx5_fpga_ipsec *ipsec;
-	struct mlx5_fpga_tls *tls;
 };
 
 #define mlx5_fpga_dbg(__adev, format, ...) \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
deleted file mode 100644
index 29b7339ebfa3..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ /dev/null
@@ -1,622 +0,0 @@
-/*
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#include <linux/mlx5/device.h>
-#include "fpga/tls.h"
-#include "fpga/cmd.h"
-#include "fpga/sdk.h"
-#include "fpga/core.h"
-#include "accel/tls.h"
-
-struct mlx5_fpga_tls_command_context;
-
-typedef void (*mlx5_fpga_tls_command_complete)
-	(struct mlx5_fpga_conn *conn, struct mlx5_fpga_device *fdev,
-	 struct mlx5_fpga_tls_command_context *ctx,
-	 struct mlx5_fpga_dma_buf *resp);
-
-struct mlx5_fpga_tls_command_context {
-	struct list_head list;
-	/* There is no guarantee on the order between the TX completion
-	 * and the command response.
-	 * The TX completion is going to touch cmd->buf even in
-	 * the case of successful transmission.
-	 * So instead of requiring separate allocations for cmd
-	 * and cmd->buf we've decided to use a reference counter
-	 */
-	refcount_t ref;
-	struct mlx5_fpga_dma_buf buf;
-	mlx5_fpga_tls_command_complete complete;
-};
-
-static void
-mlx5_fpga_tls_put_command_ctx(struct mlx5_fpga_tls_command_context *ctx)
-{
-	if (refcount_dec_and_test(&ctx->ref))
-		kfree(ctx);
-}
-
-static void mlx5_fpga_tls_cmd_complete(struct mlx5_fpga_device *fdev,
-				       struct mlx5_fpga_dma_buf *resp)
-{
-	struct mlx5_fpga_conn *conn = fdev->tls->conn;
-	struct mlx5_fpga_tls_command_context *ctx;
-	struct mlx5_fpga_tls *tls = fdev->tls;
-	unsigned long flags;
-
-	spin_lock_irqsave(&tls->pending_cmds_lock, flags);
-	ctx = list_first_entry(&tls->pending_cmds,
-			       struct mlx5_fpga_tls_command_context, list);
-	list_del(&ctx->list);
-	spin_unlock_irqrestore(&tls->pending_cmds_lock, flags);
-	ctx->complete(conn, fdev, ctx, resp);
-}
-
-static void mlx5_fpga_cmd_send_complete(struct mlx5_fpga_conn *conn,
-					struct mlx5_fpga_device *fdev,
-					struct mlx5_fpga_dma_buf *buf,
-					u8 status)
-{
-	struct mlx5_fpga_tls_command_context *ctx =
-	    container_of(buf, struct mlx5_fpga_tls_command_context, buf);
-
-	mlx5_fpga_tls_put_command_ctx(ctx);
-
-	if (unlikely(status))
-		mlx5_fpga_tls_cmd_complete(fdev, NULL);
-}
-
-static void mlx5_fpga_tls_cmd_send(struct mlx5_fpga_device *fdev,
-				   struct mlx5_fpga_tls_command_context *cmd,
-				   mlx5_fpga_tls_command_complete complete)
-{
-	struct mlx5_fpga_tls *tls = fdev->tls;
-	unsigned long flags;
-	int ret;
-
-	refcount_set(&cmd->ref, 2);
-	cmd->complete = complete;
-	cmd->buf.complete = mlx5_fpga_cmd_send_complete;
-
-	spin_lock_irqsave(&tls->pending_cmds_lock, flags);
-	/* mlx5_fpga_sbu_conn_sendmsg is called under pending_cmds_lock
-	 * to make sure commands are inserted to the tls->pending_cmds list
-	 * and the command QP in the same order.
-	 */
-	ret = mlx5_fpga_sbu_conn_sendmsg(tls->conn, &cmd->buf);
-	if (likely(!ret))
-		list_add_tail(&cmd->list, &tls->pending_cmds);
-	else
-		complete(tls->conn, fdev, cmd, NULL);
-	spin_unlock_irqrestore(&tls->pending_cmds_lock, flags);
-}
-
-/* Start of context identifiers range (inclusive) */
-#define SWID_START	0
-/* End of context identifiers range (exclusive) */
-#define SWID_END	BIT(24)
-
-static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
-				    void *ptr)
-{
-	unsigned long flags;
-	int ret;
-
-	/* TLS metadata format is 1 byte for syndrome followed
-	 * by 3 bytes of swid (software ID)
-	 * swid must not exceed 3 bytes.
-	 * See tls_rxtx.c:insert_pet() for details
-	 */
-	BUILD_BUG_ON((SWID_END - 1) & 0xFF000000);
-
-	idr_preload(GFP_KERNEL);
-	spin_lock_irqsave(idr_spinlock, flags);
-	ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC);
-	spin_unlock_irqrestore(idr_spinlock, flags);
-	idr_preload_end();
-
-	return ret;
-}
-
-static void *mlx5_fpga_tls_release_swid(struct idr *idr,
-					spinlock_t *idr_spinlock, u32 swid)
-{
-	unsigned long flags;
-	void *ptr;
-
-	spin_lock_irqsave(idr_spinlock, flags);
-	ptr = idr_remove(idr, swid);
-	spin_unlock_irqrestore(idr_spinlock, flags);
-	return ptr;
-}
-
-static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
-				   struct mlx5_fpga_device *fdev,
-				   struct mlx5_fpga_dma_buf *buf, u8 status)
-{
-	kfree(buf);
-}
-
-static void
-mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
-				  struct mlx5_fpga_device *fdev,
-				  struct mlx5_fpga_tls_command_context *cmd,
-				  struct mlx5_fpga_dma_buf *resp)
-{
-	if (resp) {
-		u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
-
-		if (syndrome)
-			mlx5_fpga_err(fdev,
-				      "Teardown stream failed with syndrome = %d",
-				      syndrome);
-	}
-	mlx5_fpga_tls_put_command_ctx(cmd);
-}
-
-static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd)
-{
-	memcpy(MLX5_ADDR_OF(tls_cmd, cmd, src_port), flow,
-	       MLX5_BYTE_OFF(tls_flow, ipv6));
-
-	MLX5_SET(tls_cmd, cmd, ipv6, MLX5_GET(tls_flow, flow, ipv6));
-	MLX5_SET(tls_cmd, cmd, direction_sx,
-		 MLX5_GET(tls_flow, flow, direction_sx));
-}
-
-int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
-			    u32 seq, __be64 rcd_sn)
-{
-	struct mlx5_fpga_dma_buf *buf;
-	int size = sizeof(*buf) + MLX5_TLS_COMMAND_SIZE;
-	void *flow;
-	void *cmd;
-	int ret;
-
-	buf = kzalloc(size, GFP_ATOMIC);
-	if (!buf)
-		return -ENOMEM;
-
-	cmd = (buf + 1);
-
-	rcu_read_lock();
-	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	if (unlikely(!flow)) {
-		rcu_read_unlock();
-		WARN_ONCE(1, "Received NULL pointer for handle\n");
-		kfree(buf);
-		return -EINVAL;
-	}
-	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
-	rcu_read_unlock();
-
-	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
-	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
-	MLX5_SET(tls_cmd, cmd, tcp_sn, seq);
-	MLX5_SET(tls_cmd, cmd, command_type, CMD_RESYNC_RX);
-
-	buf->sg[0].data = cmd;
-	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
-	buf->complete = mlx_tls_kfree_complete;
-
-	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
-	if (ret < 0)
-		kfree(buf);
-
-	return ret;
-}
-
-static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
-					    void *flow, u32 swid, gfp_t flags)
-{
-	struct mlx5_fpga_tls_command_context *ctx;
-	struct mlx5_fpga_dma_buf *buf;
-	void *cmd;
-
-	ctx = kzalloc(sizeof(*ctx) + MLX5_TLS_COMMAND_SIZE, flags);
-	if (!ctx)
-		return;
-
-	buf = &ctx->buf;
-	cmd = (ctx + 1);
-	MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
-	MLX5_SET(tls_cmd, cmd, swid, swid);
-
-	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
-	kfree(flow);
-
-	buf->sg[0].data = cmd;
-	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
-
-	mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
-			       mlx5_fpga_tls_teardown_completion);
-}
-
-void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
-			    gfp_t flags, bool direction_sx)
-{
-	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
-	void *flow;
-
-	if (direction_sx)
-		flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
-						  &tls->tx_idr_spinlock,
-						  swid);
-	else
-		flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
-						  &tls->rx_idr_spinlock,
-						  swid);
-
-	if (!flow) {
-		mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
-			      swid);
-		return;
-	}
-
-	synchronize_rcu(); /* before kfree(flow) */
-	mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
-}
-
-enum mlx5_fpga_setup_stream_status {
-	MLX5_FPGA_CMD_PENDING,
-	MLX5_FPGA_CMD_SEND_FAILED,
-	MLX5_FPGA_CMD_RESPONSE_RECEIVED,
-	MLX5_FPGA_CMD_ABANDONED,
-};
-
-struct mlx5_setup_stream_context {
-	struct mlx5_fpga_tls_command_context cmd;
-	atomic_t status;
-	u32 syndrome;
-	struct completion comp;
-};
-
-static void
-mlx5_fpga_tls_setup_completion(struct mlx5_fpga_conn *conn,
-			       struct mlx5_fpga_device *fdev,
-			       struct mlx5_fpga_tls_command_context *cmd,
-			       struct mlx5_fpga_dma_buf *resp)
-{
-	struct mlx5_setup_stream_context *ctx =
-	    container_of(cmd, struct mlx5_setup_stream_context, cmd);
-	int status = MLX5_FPGA_CMD_SEND_FAILED;
-	void *tls_cmd = ctx + 1;
-
-	/* If we failed to send to command resp == NULL */
-	if (resp) {
-		ctx->syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
-		status = MLX5_FPGA_CMD_RESPONSE_RECEIVED;
-	}
-
-	status = atomic_xchg_release(&ctx->status, status);
-	if (likely(status != MLX5_FPGA_CMD_ABANDONED)) {
-		complete(&ctx->comp);
-		return;
-	}
-
-	mlx5_fpga_err(fdev, "Command was abandoned, syndrome = %u\n",
-		      ctx->syndrome);
-
-	if (!ctx->syndrome) {
-		/* The process was killed while waiting for the context to be
-		 * added, and the add completed successfully.
-		 * We need to destroy the HW context, and we can't can't reuse
-		 * the command context because we might not have received
-		 * the tx completion yet.
-		 */
-		mlx5_fpga_tls_del_flow(fdev->mdev,
-				       MLX5_GET(tls_cmd, tls_cmd, swid),
-				       GFP_ATOMIC,
-				       MLX5_GET(tls_cmd, tls_cmd,
-						direction_sx));
-	}
-
-	mlx5_fpga_tls_put_command_ctx(cmd);
-}
-
-static int mlx5_fpga_tls_setup_stream_cmd(struct mlx5_core_dev *mdev,
-					  struct mlx5_setup_stream_context *ctx)
-{
-	struct mlx5_fpga_dma_buf *buf;
-	void *cmd = ctx + 1;
-	int status, ret = 0;
-
-	buf = &ctx->cmd.buf;
-	buf->sg[0].data = cmd;
-	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
-	MLX5_SET(tls_cmd, cmd, command_type, CMD_SETUP_STREAM);
-
-	init_completion(&ctx->comp);
-	atomic_set(&ctx->status, MLX5_FPGA_CMD_PENDING);
-	ctx->syndrome = -1;
-
-	mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
-			       mlx5_fpga_tls_setup_completion);
-	wait_for_completion_killable(&ctx->comp);
-
-	status = atomic_xchg_acquire(&ctx->status, MLX5_FPGA_CMD_ABANDONED);
-	if (unlikely(status == MLX5_FPGA_CMD_PENDING))
-	/* ctx is going to be released in mlx5_fpga_tls_setup_completion */
-		return -EINTR;
-
-	if (unlikely(ctx->syndrome))
-		ret = -ENOMEM;
-
-	mlx5_fpga_tls_put_command_ctx(&ctx->cmd);
-	return ret;
-}
-
-static void mlx5_fpga_tls_hw_qp_recv_cb(void *cb_arg,
-					struct mlx5_fpga_dma_buf *buf)
-{
-	struct mlx5_fpga_device *fdev = (struct mlx5_fpga_device *)cb_arg;
-
-	mlx5_fpga_tls_cmd_complete(fdev, buf);
-}
-
-bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev)
-{
-	if (!mdev->fpga || !MLX5_CAP_GEN(mdev, fpga))
-		return false;
-
-	if (MLX5_CAP_FPGA(mdev, ieee_vendor_id) !=
-	    MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX)
-		return false;
-
-	if (MLX5_CAP_FPGA(mdev, sandbox_product_id) !=
-	    MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS)
-		return false;
-
-	if (MLX5_CAP_FPGA(mdev, sandbox_product_version) != 0)
-		return false;
-
-	return true;
-}
-
-static int mlx5_fpga_tls_get_caps(struct mlx5_fpga_device *fdev,
-				  u32 *p_caps)
-{
-	int err, cap_size = MLX5_ST_SZ_BYTES(tls_extended_cap);
-	u32 caps = 0;
-	void *buf;
-
-	buf = kzalloc(cap_size, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	err = mlx5_fpga_get_sbu_caps(fdev, cap_size, buf);
-	if (err)
-		goto out;
-
-	if (MLX5_GET(tls_extended_cap, buf, tx))
-		caps |= MLX5_ACCEL_TLS_TX;
-	if (MLX5_GET(tls_extended_cap, buf, rx))
-		caps |= MLX5_ACCEL_TLS_RX;
-	if (MLX5_GET(tls_extended_cap, buf, tls_v12))
-		caps |= MLX5_ACCEL_TLS_V12;
-	if (MLX5_GET(tls_extended_cap, buf, tls_v13))
-		caps |= MLX5_ACCEL_TLS_V13;
-	if (MLX5_GET(tls_extended_cap, buf, lro))
-		caps |= MLX5_ACCEL_TLS_LRO;
-	if (MLX5_GET(tls_extended_cap, buf, ipv6))
-		caps |= MLX5_ACCEL_TLS_IPV6;
-
-	if (MLX5_GET(tls_extended_cap, buf, aes_gcm_128))
-		caps |= MLX5_ACCEL_TLS_AES_GCM128;
-	if (MLX5_GET(tls_extended_cap, buf, aes_gcm_256))
-		caps |= MLX5_ACCEL_TLS_AES_GCM256;
-
-	*p_caps = caps;
-	err = 0;
-out:
-	kfree(buf);
-	return err;
-}
-
-int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-	struct mlx5_fpga_conn_attr init_attr = {0};
-	struct mlx5_fpga_conn *conn;
-	struct mlx5_fpga_tls *tls;
-	int err = 0;
-
-	if (!mlx5_fpga_is_tls_device(mdev) || !fdev)
-		return 0;
-
-	tls = kzalloc(sizeof(*tls), GFP_KERNEL);
-	if (!tls)
-		return -ENOMEM;
-
-	err = mlx5_fpga_tls_get_caps(fdev, &tls->caps);
-	if (err)
-		goto error;
-
-	if (!(tls->caps & (MLX5_ACCEL_TLS_V12 | MLX5_ACCEL_TLS_AES_GCM128))) {
-		err = -ENOTSUPP;
-		goto error;
-	}
-
-	init_attr.rx_size = SBU_QP_QUEUE_SIZE;
-	init_attr.tx_size = SBU_QP_QUEUE_SIZE;
-	init_attr.recv_cb = mlx5_fpga_tls_hw_qp_recv_cb;
-	init_attr.cb_arg = fdev;
-	conn = mlx5_fpga_sbu_conn_create(fdev, &init_attr);
-	if (IS_ERR(conn)) {
-		err = PTR_ERR(conn);
-		mlx5_fpga_err(fdev, "Error creating TLS command connection %d\n",
-			      err);
-		goto error;
-	}
-
-	tls->conn = conn;
-	spin_lock_init(&tls->pending_cmds_lock);
-	INIT_LIST_HEAD(&tls->pending_cmds);
-
-	idr_init(&tls->tx_idr);
-	idr_init(&tls->rx_idr);
-	spin_lock_init(&tls->tx_idr_spinlock);
-	spin_lock_init(&tls->rx_idr_spinlock);
-	fdev->tls = tls;
-	return 0;
-
-error:
-	kfree(tls);
-	return err;
-}
-
-void mlx5_fpga_tls_cleanup(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-
-	if (!fdev || !fdev->tls)
-		return;
-
-	mlx5_fpga_sbu_conn_destroy(fdev->tls->conn);
-	kfree(fdev->tls);
-	fdev->tls = NULL;
-}
-
-static void mlx5_fpga_tls_set_aes_gcm128_ctx(void *cmd,
-					     struct tls_crypto_info *info,
-					     __be64 *rcd_sn)
-{
-	struct tls12_crypto_info_aes_gcm_128 *crypto_info =
-	    (struct tls12_crypto_info_aes_gcm_128 *)info;
-
-	memcpy(MLX5_ADDR_OF(tls_cmd, cmd, tls_rcd_sn), crypto_info->rec_seq,
-	       TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE);
-
-	memcpy(MLX5_ADDR_OF(tls_cmd, cmd, tls_implicit_iv),
-	       crypto_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
-	memcpy(MLX5_ADDR_OF(tls_cmd, cmd, encryption_key),
-	       crypto_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
-
-	/* in AES-GCM 128 we need to write the key twice */
-	memcpy(MLX5_ADDR_OF(tls_cmd, cmd, encryption_key) +
-		   TLS_CIPHER_AES_GCM_128_KEY_SIZE,
-	       crypto_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
-
-	MLX5_SET(tls_cmd, cmd, alg, MLX5_TLS_ALG_AES_GCM_128);
-}
-
-static int mlx5_fpga_tls_set_key_material(void *cmd, u32 caps,
-					  struct tls_crypto_info *crypto_info)
-{
-	__be64 rcd_sn;
-
-	switch (crypto_info->cipher_type) {
-	case TLS_CIPHER_AES_GCM_128:
-		if (!(caps & MLX5_ACCEL_TLS_AES_GCM128))
-			return -EINVAL;
-		mlx5_fpga_tls_set_aes_gcm128_ctx(cmd, crypto_info, &rcd_sn);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int _mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-				   struct tls_crypto_info *crypto_info,
-				   u32 swid, u32 tcp_sn)
-{
-	u32 caps = mlx5_fpga_tls_device_caps(mdev);
-	struct mlx5_setup_stream_context *ctx;
-	int ret = -ENOMEM;
-	size_t cmd_size;
-	void *cmd;
-
-	cmd_size = MLX5_TLS_COMMAND_SIZE + sizeof(*ctx);
-	ctx = kzalloc(cmd_size, GFP_KERNEL);
-	if (!ctx)
-		goto out;
-
-	cmd = ctx + 1;
-	ret = mlx5_fpga_tls_set_key_material(cmd, caps, crypto_info);
-	if (ret)
-		goto free_ctx;
-
-	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
-
-	MLX5_SET(tls_cmd, cmd, swid, swid);
-	MLX5_SET(tls_cmd, cmd, tcp_sn, tcp_sn);
-
-	return mlx5_fpga_tls_setup_stream_cmd(mdev, ctx);
-
-free_ctx:
-	kfree(ctx);
-out:
-	return ret;
-}
-
-int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-			   struct tls_crypto_info *crypto_info,
-			   u32 start_offload_tcp_sn, u32 *p_swid,
-			   bool direction_sx)
-{
-	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
-	int ret = -ENOMEM;
-	u32 swid;
-
-	if (direction_sx)
-		ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr,
-					       &tls->tx_idr_spinlock, flow);
-	else
-		ret = mlx5_fpga_tls_alloc_swid(&tls->rx_idr,
-					       &tls->rx_idr_spinlock, flow);
-
-	if (ret < 0)
-		return ret;
-
-	swid = ret;
-	MLX5_SET(tls_flow, flow, direction_sx, direction_sx ? 1 : 0);
-
-	ret = _mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
-				      start_offload_tcp_sn);
-	if (ret && ret != -EINTR)
-		goto free_swid;
-
-	*p_swid = swid;
-	return 0;
-free_swid:
-	if (direction_sx)
-		mlx5_fpga_tls_release_swid(&tls->tx_idr,
-					   &tls->tx_idr_spinlock, swid);
-	else
-		mlx5_fpga_tls_release_swid(&tls->rx_idr,
-					   &tls->rx_idr_spinlock, swid);
-
-	return ret;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
deleted file mode 100644
index 5714cf391d1b..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
+++ /dev/null
@@ -1,74 +0,0 @@
-/*
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#ifndef __MLX5_FPGA_TLS_H__
-#define __MLX5_FPGA_TLS_H__
-
-#include <linux/mlx5/driver.h>
-
-#include <net/tls.h>
-#include "fpga/core.h"
-
-struct mlx5_fpga_tls {
-	struct list_head pending_cmds;
-	spinlock_t pending_cmds_lock; /* Protects pending_cmds */
-	u32 caps;
-	struct mlx5_fpga_conn *conn;
-
-	struct idr tx_idr;
-	struct idr rx_idr;
-	spinlock_t tx_idr_spinlock; /* protects the IDR */
-	spinlock_t rx_idr_spinlock; /* protects the IDR */
-};
-
-int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-			   struct tls_crypto_info *crypto_info,
-			   u32 start_offload_tcp_sn, u32 *p_swid,
-			   bool direction_sx);
-
-void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
-			    gfp_t flags, bool direction_sx);
-
-bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev);
-int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev);
-void mlx5_fpga_tls_cleanup(struct mlx5_core_dev *mdev);
-
-static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev)
-{
-	return mdev->fpga->tls->caps;
-}
-
-int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
-			    u32 seq, __be64 rcd_sn);
-
-#endif /* __MLX5_FPGA_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 2589e39eb9c7..7f287e300fb4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -64,7 +64,6 @@
 #include "fpga/core.h"
 #include "fpga/ipsec.h"
 #include "accel/ipsec.h"
-#include "accel/tls.h"
 #include "lib/clock.h"
 #include "lib/vxlan.h"
 #include "lib/geneve.h"
@@ -1185,12 +1184,6 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 
 	mlx5_accel_ipsec_init(dev);
 
-	err = mlx5_accel_tls_init(dev);
-	if (err) {
-		mlx5_core_err(dev, "TLS device start failed %d\n", err);
-		goto err_tls_start;
-	}
-
 	err = mlx5_init_fs(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init flow steering\n");
@@ -1238,8 +1231,6 @@ err_vhca:
 err_set_hca:
 	mlx5_cleanup_fs(dev);
 err_fs:
-	mlx5_accel_tls_cleanup(dev);
-err_tls_start:
 	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
 err_fpga_start:
@@ -1267,7 +1258,6 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_vhca_event_stop(dev);
 	mlx5_cleanup_fs(dev);
 	mlx5_accel_ipsec_cleanup(dev);
-	mlx5_accel_tls_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
 	mlx5_rsc_dump_cleanup(dev);
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h
index 07d77323f78a..e3d824f6a309 100644
--- a/include/linux/mlx5/mlx5_ifc_fpga.h
+++ b/include/linux/mlx5/mlx5_ifc_fpga.h
@@ -54,7 +54,6 @@ enum {
 
 enum {
 	MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC    = 0x2,
-	MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS      = 0x3,
 };
 
 struct mlx5_ifc_fpga_shell_caps_bits {
@@ -387,27 +386,6 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
-struct mlx5_ifc_tls_extended_cap_bits {
-	u8         aes_gcm_128[0x1];
-	u8         aes_gcm_256[0x1];
-	u8         reserved_at_2[0x1e];
-	u8         reserved_at_20[0x20];
-	u8         context_capacity_total[0x20];
-	u8         context_capacity_rx[0x20];
-	u8         context_capacity_tx[0x20];
-	u8         reserved_at_a0[0x10];
-	u8         tls_counter_size[0x10];
-	u8         tls_counters_addr_low[0x20];
-	u8         tls_counters_addr_high[0x20];
-	u8         rx[0x1];
-	u8         tx[0x1];
-	u8         tls_v12[0x1];
-	u8         tls_v13[0x1];
-	u8         lro[0x1];
-	u8         ipv6[0x1];
-	u8         reserved_at_106[0x1a];
-};
-
 struct mlx5_ifc_ipsec_extended_cap_bits {
 	u8         encapsulation[0x20];
 
@@ -572,45 +550,4 @@ struct mlx5_ifc_fpga_ipsec_sa {
 	__be16 vid;	/* only 12 bits, rest is reserved */
 	__be16 reserved2;
 } __packed;
-
-enum fpga_tls_cmds {
-	CMD_SETUP_STREAM		= 0x1001,
-	CMD_TEARDOWN_STREAM		= 0x1002,
-	CMD_RESYNC_RX			= 0x1003,
-};
-
-#define MLX5_TLS_1_2 (0)
-
-#define MLX5_TLS_ALG_AES_GCM_128 (0)
-#define MLX5_TLS_ALG_AES_GCM_256 (1)
-
-struct mlx5_ifc_tls_cmd_bits {
-	u8         command_type[0x20];
-	u8         ipv6[0x1];
-	u8         direction_sx[0x1];
-	u8         tls_version[0x2];
-	u8         reserved[0x1c];
-	u8         swid[0x20];
-	u8         src_port[0x10];
-	u8         dst_port[0x10];
-	union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6;
-	union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6;
-	u8         tls_rcd_sn[0x40];
-	u8         tcp_sn[0x20];
-	u8         tls_implicit_iv[0x20];
-	u8         tls_xor_iv[0x40];
-	u8         encryption_key[0x100];
-	u8         alg[4];
-	u8         reserved2[0x1c];
-	u8         reserved3[0x4a0];
-};
-
-struct mlx5_ifc_tls_resp_bits {
-	u8         syndrome[0x20];
-	u8         stream_id[0x20];
-	u8         reserved[0x40];
-};
-
-#define MLX5_TLS_COMMAND_SIZE (0x100)
-
 #endif /* MLX5_IFC_FPGA_H */
-- 
cgit v1.2.3


From 0276bd3a94c072de3f69b5afe6224e488cc76635 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Tue, 5 Apr 2022 17:15:16 +0200
Subject: IB/mlx5: Fix undefined behavior due to shift overflowing the constant
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix:

  drivers/infiniband/hw/mlx5/main.c: In function ‘translate_eth_legacy_proto_oper’:
  drivers/infiniband/hw/mlx5/main.c:370:2: error: case label does not reduce to an integer constant
    case MLX5E_PROT_MASK(MLX5E_50GBASE_KR2):
    ^~~~

See https://lore.kernel.org/r/YkwQ6%2BtIH8GQpuct@zn.tnic for the gory
details as to why it triggers with older gccs only.

Link: https://lore.kernel.org/all/20220405151517.29753-11-bp@alien8.de
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Saeed Mahameed <saeedm@nvidia.com>
Cc: linux-rdma@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 include/linux/mlx5/port.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 28a928b0684b..e96ee1e348cb 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -141,7 +141,7 @@ enum mlx5_ptys_width {
 	MLX5_PTYS_WIDTH_12X	= 1 << 4,
 };
 
-#define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
+#define MLX5E_PROT_MASK(link_mode) (1U << link_mode)
 #define MLX5_GET_ETH_PROTO(reg, out, ext, field)	\
 	(ext ? MLX5_GET(reg, out, ext_##field) :	\
 	MLX5_GET(reg, out, field))
-- 
cgit v1.2.3


From a285909f471d6703a04b2b3942c352e27131c92b Mon Sep 17 00:00:00 2001
From: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Date: Wed, 6 Apr 2022 15:00:03 +0900
Subject: mm/slub, kunit: Make slub_kunit unaffected by user specified flags

slub_kunit does not expect other debugging flags to be set when running
tests. When SLAB_RED_ZONE flag is set globally, test fails because the
flag affects number of errors reported.

To make slub_kunit unaffected by user specified debugging flags,
introduce SLAB_NO_USER_FLAGS to ignore them. With this flag, only flags
specified in the code are used and others are ignored.

Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/Yk0sY9yoJhFEXWOg@hyeyoo
---
 include/linux/slab.h |  7 +++++++
 lib/slub_kunit.c     | 10 +++++-----
 mm/slab.h            |  5 +++--
 mm/slub.c            |  3 +++
 4 files changed, 18 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 373b3ef99f4e..11ceddcae9f4 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -112,6 +112,13 @@
 #define SLAB_KASAN		0
 #endif
 
+/*
+ * Ignore user specified debugging flags.
+ * Intended for caches created for self-tests so they have only flags
+ * specified in the code and other flags are ignored.
+ */
+#define SLAB_NO_USER_FLAGS	((slab_flags_t __force)0x10000000U)
+
 /* The following flags affect the page allocator grouping pages by mobility */
 /* Objects are reclaimable */
 #define SLAB_RECLAIM_ACCOUNT	((slab_flags_t __force)0x00020000U)
diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c
index 8662dc6cb509..7a0564d7cb7a 100644
--- a/lib/slub_kunit.c
+++ b/lib/slub_kunit.c
@@ -12,7 +12,7 @@ static int slab_errors;
 static void test_clobber_zone(struct kunit *test)
 {
 	struct kmem_cache *s = kmem_cache_create("TestSlub_RZ_alloc", 64, 0,
-				SLAB_RED_ZONE, NULL);
+				SLAB_RED_ZONE|SLAB_NO_USER_FLAGS, NULL);
 	u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
 
 	kasan_disable_current();
@@ -30,7 +30,7 @@ static void test_clobber_zone(struct kunit *test)
 static void test_next_pointer(struct kunit *test)
 {
 	struct kmem_cache *s = kmem_cache_create("TestSlub_next_ptr_free", 64, 0,
-				SLAB_POISON, NULL);
+				SLAB_POISON|SLAB_NO_USER_FLAGS, NULL);
 	u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
 	unsigned long tmp;
 	unsigned long *ptr_addr;
@@ -75,7 +75,7 @@ static void test_next_pointer(struct kunit *test)
 static void test_first_word(struct kunit *test)
 {
 	struct kmem_cache *s = kmem_cache_create("TestSlub_1th_word_free", 64, 0,
-				SLAB_POISON, NULL);
+				SLAB_POISON|SLAB_NO_USER_FLAGS, NULL);
 	u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
 
 	kmem_cache_free(s, p);
@@ -90,7 +90,7 @@ static void test_first_word(struct kunit *test)
 static void test_clobber_50th_byte(struct kunit *test)
 {
 	struct kmem_cache *s = kmem_cache_create("TestSlub_50th_word_free", 64, 0,
-				SLAB_POISON, NULL);
+				SLAB_POISON|SLAB_NO_USER_FLAGS, NULL);
 	u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
 
 	kmem_cache_free(s, p);
@@ -106,7 +106,7 @@ static void test_clobber_50th_byte(struct kunit *test)
 static void test_clobber_redzone_free(struct kunit *test)
 {
 	struct kmem_cache *s = kmem_cache_create("TestSlub_RZ_free", 64, 0,
-				SLAB_RED_ZONE, NULL);
+				SLAB_RED_ZONE|SLAB_NO_USER_FLAGS, NULL);
 	u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
 
 	kasan_disable_current();
diff --git a/mm/slab.h b/mm/slab.h
index fd7ae2024897..f7d018100994 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -331,7 +331,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
 			  SLAB_ACCOUNT)
 #elif defined(CONFIG_SLUB)
 #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
-			  SLAB_TEMPORARY | SLAB_ACCOUNT)
+			  SLAB_TEMPORARY | SLAB_ACCOUNT | SLAB_NO_USER_FLAGS)
 #else
 #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
 #endif
@@ -350,7 +350,8 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
 			      SLAB_NOLEAKTRACE | \
 			      SLAB_RECLAIM_ACCOUNT | \
 			      SLAB_TEMPORARY | \
-			      SLAB_ACCOUNT)
+			      SLAB_ACCOUNT | \
+			      SLAB_NO_USER_FLAGS)
 
 bool __kmem_cache_empty(struct kmem_cache *);
 int __kmem_cache_shutdown(struct kmem_cache *);
diff --git a/mm/slub.c b/mm/slub.c
index 74d92aa4a3a2..4c78f5919356 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1584,6 +1584,9 @@ slab_flags_t kmem_cache_flags(unsigned int object_size,
 	slab_flags_t block_flags;
 	slab_flags_t slub_debug_local = slub_debug;
 
+	if (flags & SLAB_NO_USER_FLAGS)
+		return flags;
+
 	/*
 	 * If the slab cache is for debugging (e.g. kmemleak) then
 	 * don't store user (stack trace) information by default,
-- 
cgit v1.2.3


From a5f1783be29adae15666fd803efd7d2979130869 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 2 Mar 2022 12:02:22 +0100
Subject: lib/stackdepot: allow requesting early initialization dynamically

In a later patch we want to add stackdepot support for object owner
tracking in slub caches, which is enabled by slub_debug boot parameter.
This creates a bootstrap problem as some caches are created early in
boot when slab_is_available() is false and thus stack_depot_init()
tries to use memblock. But, as reported by Hyeonggon Yoo [1] we are
already beyond memblock_free_all(). Ideally memblock allocation should
fail, yet it succeeds, but later the system crashes, which is a
separately handled issue.

To resolve this boostrap issue in a robust way, this patch adds another
way to request stack_depot_early_init(), which happens at a well-defined
point of time. In addition to build-time CONFIG_STACKDEPOT_ALWAYS_INIT,
code that's e.g. processing boot parameters (which happens early enough)
can call a new function stack_depot_want_early_init(), which sets a flag
that stack_depot_early_init() will check.

In this patch we also convert page_owner to this approach. While it
doesn't have the bootstrap issue as slub, it's also a functionality
enabled by a boot param and can thus request stack_depot_early_init()
with memblock allocation instead of later initialization with
kvmalloc().

As suggested by Mike, make stack_depot_early_init() only attempt
memblock allocation and stack_depot_init() only attempt kvmalloc().
Also change the latter to kvcalloc(). In both cases we can lose the
explicit array zeroing, which the allocations do already.

As suggested by Marco, provide empty implementations of the init
functions for !CONFIG_STACKDEPOT builds to simplify the callers.

[1] https://lore.kernel.org/all/YhnUcqyeMgCrWZbd@ip-172-31-19-208.ap-northeast-1.compute.internal/

Reported-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Suggested-by: Mike Rapoport <rppt@linux.ibm.com>
Suggested-by: Marco Elver <elver@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Marco Elver <elver@google.com>
Reviewed-and-tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: David Rientjes <rientjes@google.com>
---
 include/linux/stackdepot.h | 26 +++++++++++++++---
 lib/stackdepot.c           | 67 +++++++++++++++++++++++++++++++---------------
 mm/page_owner.c            |  9 ++++---
 3 files changed, 73 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index 17f992fe6355..bc2797955de9 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -20,18 +20,36 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 					gfp_t gfp_flags, bool can_alloc);
 
 /*
- * Every user of stack depot has to call this during its own init when it's
- * decided that it will be calling stack_depot_save() later.
+ * Every user of stack depot has to call stack_depot_init() during its own init
+ * when it's decided that it will be calling stack_depot_save() later. This is
+ * recommended for e.g. modules initialized later in the boot process, when
+ * slab_is_available() is true.
  *
  * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot
  * enabled as part of mm_init(), for subsystems where it's known at compile time
  * that stack depot will be used.
+ *
+ * Another alternative is to call stack_depot_want_early_init(), when the
+ * decision to use stack depot is taken e.g. when evaluating kernel boot
+ * parameters, which precedes the enablement point in mm_init().
+ *
+ * stack_depot_init() and stack_depot_want_early_init() can be called regardless
+ * of CONFIG_STACKDEPOT and are no-op when disabled. The actual save/fetch/print
+ * functions should only be called from code that makes sure CONFIG_STACKDEPOT
+ * is enabled.
  */
+#ifdef CONFIG_STACKDEPOT
 int stack_depot_init(void);
 
-#ifdef CONFIG_STACKDEPOT_ALWAYS_INIT
-static inline int stack_depot_early_init(void)	{ return stack_depot_init(); }
+void __init stack_depot_want_early_init(void);
+
+/* This is supposed to be called only from mm_init() */
+int __init stack_depot_early_init(void);
 #else
+static inline int stack_depot_init(void) { return 0; }
+
+static inline void stack_depot_want_early_init(void) { }
+
 static inline int stack_depot_early_init(void)	{ return 0; }
 #endif
 
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index bf5ba9af0500..5ca0d086ef4a 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -66,6 +66,9 @@ struct stack_record {
 	unsigned long entries[];	/* Variable-sized array of entries. */
 };
 
+static bool __stack_depot_want_early_init __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT);
+static bool __stack_depot_early_init_passed __initdata;
+
 static void *stack_slabs[STACK_ALLOC_MAX_SLABS];
 
 static int depot_index;
@@ -162,38 +165,58 @@ static int __init is_stack_depot_disabled(char *str)
 }
 early_param("stack_depot_disable", is_stack_depot_disabled);
 
-/*
- * __ref because of memblock_alloc(), which will not be actually called after
- * the __init code is gone, because at that point slab_is_available() is true
- */
-__ref int stack_depot_init(void)
+void __init stack_depot_want_early_init(void)
+{
+	/* Too late to request early init now */
+	WARN_ON(__stack_depot_early_init_passed);
+
+	__stack_depot_want_early_init = true;
+}
+
+int __init stack_depot_early_init(void)
+{
+	size_t size;
+
+	/* This is supposed to be called only once, from mm_init() */
+	if (WARN_ON(__stack_depot_early_init_passed))
+		return 0;
+
+	__stack_depot_early_init_passed = true;
+
+	if (!__stack_depot_want_early_init || stack_depot_disable)
+		return 0;
+
+	size = (STACK_HASH_SIZE * sizeof(struct stack_record *));
+	pr_info("Stack Depot early init allocating hash table with memblock_alloc, %zu bytes\n",
+		size);
+	stack_table = memblock_alloc(size, SMP_CACHE_BYTES);
+
+	if (!stack_table) {
+		pr_err("Stack Depot hash table allocation failed, disabling\n");
+		stack_depot_disable = true;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int stack_depot_init(void)
 {
 	static DEFINE_MUTEX(stack_depot_init_mutex);
+	int ret = 0;
 
 	mutex_lock(&stack_depot_init_mutex);
 	if (!stack_depot_disable && !stack_table) {
-		size_t size = (STACK_HASH_SIZE * sizeof(struct stack_record *));
-		int i;
-
-		if (slab_is_available()) {
-			pr_info("Stack Depot allocating hash table with kvmalloc\n");
-			stack_table = kvmalloc(size, GFP_KERNEL);
-		} else {
-			pr_info("Stack Depot allocating hash table with memblock_alloc\n");
-			stack_table = memblock_alloc(size, SMP_CACHE_BYTES);
-		}
-		if (stack_table) {
-			for (i = 0; i < STACK_HASH_SIZE;  i++)
-				stack_table[i] = NULL;
-		} else {
+		pr_info("Stack Depot allocating hash table with kvcalloc\n");
+		stack_table = kvcalloc(STACK_HASH_SIZE, sizeof(struct stack_record *), GFP_KERNEL);
+		if (!stack_table) {
 			pr_err("Stack Depot hash table allocation failed, disabling\n");
 			stack_depot_disable = true;
-			mutex_unlock(&stack_depot_init_mutex);
-			return -ENOMEM;
+			ret = -ENOMEM;
 		}
 	}
 	mutex_unlock(&stack_depot_init_mutex);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(stack_depot_init);
 
diff --git a/mm/page_owner.c b/mm/page_owner.c
index fb3a05fdebdb..2743062e92c2 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -45,7 +45,12 @@ static void init_early_allocated_pages(void);
 
 static int __init early_page_owner_param(char *buf)
 {
-	return kstrtobool(buf, &page_owner_enabled);
+	int ret = kstrtobool(buf, &page_owner_enabled);
+
+	if (page_owner_enabled)
+		stack_depot_want_early_init();
+
+	return ret;
 }
 early_param("page_owner", early_page_owner_param);
 
@@ -83,8 +88,6 @@ static __init void init_page_owner(void)
 	if (!page_owner_enabled)
 		return;
 
-	stack_depot_init();
-
 	register_dummy_stack();
 	register_failure_stack();
 	register_early_stack();
-- 
cgit v1.2.3


From f742b90e61bb53b27771f64bdae05db03a6ab1f2 Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Thu, 24 Feb 2022 10:55:49 -0600
Subject: x86/mm: Extend cc_attr to include AMD SEV-SNP

The CC_ATTR_GUEST_SEV_SNP can be used by the guest to query whether the
SNP (Secure Nested Paging) feature is active.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20220307213356.2797205-10-brijesh.singh@amd.com
---
 arch/x86/coco/core.c             | 3 +++
 arch/x86/include/asm/msr-index.h | 2 ++
 arch/x86/mm/mem_encrypt.c        | 4 ++++
 include/linux/cc_platform.h      | 8 ++++++++
 4 files changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index fc1365dd927e..dafd4881ce29 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -57,6 +57,9 @@ static bool amd_cc_platform_has(enum cc_attr attr)
 		return (sev_status & MSR_AMD64_SEV_ENABLED) &&
 			!(sev_status & MSR_AMD64_SEV_ES_ENABLED);
 
+	case CC_ATTR_GUEST_SEV_SNP:
+		return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
+
 	default:
 		return false;
 	}
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 0eb90d21049e..ef96f166b1b6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -502,8 +502,10 @@
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
 #define MSR_AMD64_SEV_ES_ENABLED_BIT	1
+#define MSR_AMD64_SEV_SNP_ENABLED_BIT	2
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
 #define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
+#define MSR_AMD64_SEV_SNP_ENABLED	BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 50d209939c66..f85868c031c6 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -62,6 +62,10 @@ static void print_mem_encrypt_feature_info(void)
 	if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
 		pr_cont(" SEV-ES");
 
+	/* Secure Nested Paging */
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+		pr_cont(" SEV-SNP");
+
 	pr_cont("\n");
 }
 
diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h
index efd8205282da..d08dd65b5c43 100644
--- a/include/linux/cc_platform.h
+++ b/include/linux/cc_platform.h
@@ -72,6 +72,14 @@ enum cc_attr {
 	 * Examples include TDX guest & SEV.
 	 */
 	CC_ATTR_GUEST_UNROLL_STRING_IO,
+
+	/**
+	 * @CC_ATTR_SEV_SNP: Guest SNP is active.
+	 *
+	 * The platform/OS is running as a guest/virtual machine and actively
+	 * using AMD SEV-SNP features.
+	 */
+	CC_ATTR_GUEST_SEV_SNP,
 };
 
 #ifdef CONFIG_ARCH_HAS_CC_PLATFORM
-- 
cgit v1.2.3


From f4b41f062c424209e3939a81e6da022e049a45f2 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 4 Apr 2022 18:30:22 +0200
Subject: net: remove noblock parameter from skb_recv_datagram()

skb_recv_datagram() has two parameters 'flags' and 'noblock' that are
merged inside skb_recv_datagram() by 'flags | (noblock ? MSG_DONTWAIT : 0)'

As 'flags' may contain MSG_DONTWAIT as value most callers split the 'flags'
into 'flags' and 'noblock' with finally obsolete bit operations like this:

skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc);

And this is not even done consistently with the 'flags' parameter.

This patch removes the obsolete and costly splitting into two parameters
and only performs bit operations when really needed on the caller side.

One missing conversion thankfully reported by kernel test robot. I missed
to enable kunit tests to build the mctp code.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/mISDN/socket.c    | 2 +-
 drivers/net/ppp/pppoe.c        | 3 +--
 include/linux/skbuff.h         | 3 +--
 net/appletalk/ddp.c            | 3 +--
 net/atm/common.c               | 2 +-
 net/ax25/af_ax25.c             | 3 +--
 net/bluetooth/af_bluetooth.c   | 3 +--
 net/bluetooth/hci_sock.c       | 3 +--
 net/caif/caif_socket.c         | 2 +-
 net/can/bcm.c                  | 5 +----
 net/can/isotp.c                | 4 +---
 net/can/j1939/socket.c         | 2 +-
 net/can/raw.c                  | 6 +-----
 net/core/datagram.c            | 5 ++---
 net/ieee802154/socket.c        | 6 ++++--
 net/ipv4/ping.c                | 3 ++-
 net/ipv4/raw.c                 | 3 ++-
 net/ipv6/raw.c                 | 3 ++-
 net/iucv/af_iucv.c             | 3 +--
 net/key/af_key.c               | 2 +-
 net/l2tp/l2tp_ip.c             | 3 ++-
 net/l2tp/l2tp_ip6.c            | 3 ++-
 net/l2tp/l2tp_ppp.c            | 3 +--
 net/mctp/af_mctp.c             | 2 +-
 net/mctp/test/route-test.c     | 8 ++++----
 net/netlink/af_netlink.c       | 3 +--
 net/netrom/af_netrom.c         | 3 ++-
 net/nfc/llcp_sock.c            | 3 +--
 net/nfc/rawsock.c              | 3 +--
 net/packet/af_packet.c         | 2 +-
 net/phonet/datagram.c          | 3 ++-
 net/phonet/pep.c               | 6 ++++--
 net/qrtr/af_qrtr.c             | 3 +--
 net/rose/af_rose.c             | 3 ++-
 net/unix/af_unix.c             | 5 +++--
 net/vmw_vsock/vmci_transport.c | 5 +----
 net/x25/af_x25.c               | 3 +--
 37 files changed, 57 insertions(+), 70 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index a6606736d8c5..2776ca5fc33f 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -121,7 +121,7 @@ mISDN_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (sk->sk_state == MISDN_CLOSED)
 		return 0;
 
-	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		return err;
 
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 3619520340b7..1b41cd9732d7 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1011,8 +1011,7 @@ static int pppoe_recvmsg(struct socket *sock, struct msghdr *m,
 		goto end;
 	}
 
-	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
-				flags & MSG_DONTWAIT, &error);
+	skb = skb_recv_datagram(sk, flags, &error);
 	if (error < 0)
 		goto end;
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3a30cae8b0a5..2394441fa3dd 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3836,8 +3836,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk,
 struct sk_buff *__skb_recv_datagram(struct sock *sk,
 				    struct sk_buff_head *sk_queue,
 				    unsigned int flags, int *off, int *err);
-struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
-				  int *err);
+struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err);
 __poll_t datagram_poll(struct file *file, struct socket *sock,
 			   struct poll_table_struct *wait);
 int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index bf5736c1d458..a06f4d4a6f47 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1753,8 +1753,7 @@ static int atalk_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	int err = 0;
 	struct sk_buff *skb;
 
-	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
-						flags & MSG_DONTWAIT, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	lock_sock(sk);
 
 	if (!skb)
diff --git a/net/atm/common.c b/net/atm/common.c
index 1cfa9bf1d187..d0c8ab7ff8f6 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -540,7 +540,7 @@ int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	    !test_bit(ATM_VF_READY, &vcc->flags))
 		return 0;
 
-	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &error);
+	skb = skb_recv_datagram(sk, flags, &error);
 	if (!skb)
 		return error;
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 363d47f94532..116481e4da82 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1669,8 +1669,7 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	}
 
 	/* Now we can treat all alike */
-	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
-				flags & MSG_DONTWAIT, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (skb == NULL)
 		goto out;
 
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index a0cb2e3da8d4..62705734343b 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -251,7 +251,6 @@ EXPORT_SYMBOL(bt_accept_dequeue);
 int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		    int flags)
 {
-	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	size_t copied;
@@ -263,7 +262,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb) {
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			return 0;
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 33b3c0ffc339..189e3115c8c6 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1453,7 +1453,6 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg,
 static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 			    size_t len, int flags)
 {
-	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied, err;
@@ -1470,7 +1469,7 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 	if (sk->sk_state == BT_CLOSED)
 		return 0;
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		return err;
 
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 2b8892d502f7..251e666ba9a2 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -282,7 +282,7 @@ static int caif_seqpkt_recvmsg(struct socket *sock, struct msghdr *m,
 	if (flags & MSG_OOB)
 		goto read_error;
 
-	skb = skb_recv_datagram(sk, flags, 0 , &ret);
+	skb = skb_recv_datagram(sk, flags, &ret);
 	if (!skb)
 		goto read_error;
 	copylen = skb->len;
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 95d209b52e6a..64c07e650bb4 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1632,12 +1632,9 @@ static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int error = 0;
-	int noblock;
 	int err;
 
-	noblock =  flags & MSG_DONTWAIT;
-	flags   &= ~MSG_DONTWAIT;
-	skb = skb_recv_datagram(sk, flags, noblock, &error);
+	skb = skb_recv_datagram(sk, flags, &error);
 	if (!skb)
 		return error;
 
diff --git a/net/can/isotp.c b/net/can/isotp.c
index bafb0fb5f0e0..02d81effaa54 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1047,7 +1047,6 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	struct isotp_sock *so = isotp_sk(sk);
-	int noblock = flags & MSG_DONTWAIT;
 	int ret = 0;
 
 	if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK))
@@ -1056,8 +1055,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	if (!so->bound)
 		return -EADDRNOTAVAIL;
 
-	flags &= ~MSG_DONTWAIT;
-	skb = skb_recv_datagram(sk, flags, noblock, &ret);
+	skb = skb_recv_datagram(sk, flags, &ret);
 	if (!skb)
 		return ret;
 
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 6dff4510687a..0bb4fd3f6264 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -802,7 +802,7 @@ static int j1939_sk_recvmsg(struct socket *sock, struct msghdr *msg,
 		return sock_recv_errqueue(sock->sk, msg, size, SOL_CAN_J1939,
 					  SCM_J1939_ERRQUEUE);
 
-	skb = skb_recv_datagram(sk, flags, 0, &ret);
+	skb = skb_recv_datagram(sk, flags, &ret);
 	if (!skb)
 		return ret;
 
diff --git a/net/can/raw.c b/net/can/raw.c
index 7105fa4824e4..0cf728dcff36 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -846,16 +846,12 @@ static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int err = 0;
-	int noblock;
-
-	noblock = flags & MSG_DONTWAIT;
-	flags &= ~MSG_DONTWAIT;
 
 	if (flags & MSG_ERRQUEUE)
 		return sock_recv_errqueue(sk, msg, size,
 					  SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE);
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		return err;
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index ee290776c661..70126d15ca6e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -310,12 +310,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk,
 EXPORT_SYMBOL(__skb_recv_datagram);
 
 struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
-				  int noblock, int *err)
+				  int *err)
 {
 	int off = 0;
 
-	return __skb_recv_datagram(sk, &sk->sk_receive_queue,
-				   flags | (noblock ? MSG_DONTWAIT : 0),
+	return __skb_recv_datagram(sk, &sk->sk_receive_queue, flags,
 				   &off, err);
 }
 EXPORT_SYMBOL(skb_recv_datagram);
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index 3b2366a88c3c..a725dd9bbda8 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -314,7 +314,8 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int err = -EOPNOTSUPP;
 	struct sk_buff *skb;
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
@@ -703,7 +704,8 @@ static int dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	struct dgram_sock *ro = dgram_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_ieee802154 *, saddr, msg->msg_name);
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 3ee947557b88..550dc5c795c0 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -861,7 +861,8 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 	if (flags & MSG_ERRQUEUE)
 		return inet_recv_error(sk, msg, len, addr_len);
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 9f97b9cbf7b3..c9dd9603f2e7 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -769,7 +769,8 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		goto out;
 	}
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index c51d5ce3711c..8bb41f3b246a 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -477,7 +477,8 @@ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
 		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index a1760add5bf1..a0385ddbffcf 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1223,7 +1223,6 @@ static void iucv_process_message_q(struct sock *sk)
 static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 			     size_t len, int flags)
 {
-	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
 	unsigned int copied, rlen;
@@ -1242,7 +1241,7 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 
 	/* receive/dequeue next skb:
 	 * the function understands MSG_PEEK and, thus, does not dequeue skb */
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb) {
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			return 0;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index fd51db3be91c..d09ec26b1081 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3696,7 +3696,7 @@ static int pfkey_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
 		goto out;
 
-	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (skb == NULL)
 		goto out;
 
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index b3edafa5fba4..c6a5cc2d88e7 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -526,7 +526,8 @@ static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg,
 	if (flags & MSG_OOB)
 		goto out;
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 96f975777438..97fde8a9209b 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -671,7 +671,8 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len, addr_len);
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto out;
 
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index bf35710127dd..8be1fdc68a0b 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -191,8 +191,7 @@ static int pppol2tp_recvmsg(struct socket *sock, struct msghdr *msg,
 		goto end;
 
 	err = 0;
-	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
-				flags & MSG_DONTWAIT, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb)
 		goto end;
 
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index f0702d920d8d..5f204eb8abd2 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -196,7 +196,7 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK))
 		return -EOPNOTSUPP;
 
-	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &rc);
+	skb = skb_recv_datagram(sk, flags, &rc);
 	if (!skb)
 		return rc;
 
diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
index 61205cf40074..24df29e135ed 100644
--- a/net/mctp/test/route-test.c
+++ b/net/mctp/test/route-test.c
@@ -352,7 +352,7 @@ static void mctp_test_route_input_sk(struct kunit *test)
 	if (params->deliver) {
 		KUNIT_EXPECT_EQ(test, rc, 0);
 
-		skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc);
+		skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
 		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
 		KUNIT_EXPECT_EQ(test, skb->len, 1);
 
@@ -360,7 +360,7 @@ static void mctp_test_route_input_sk(struct kunit *test)
 
 	} else {
 		KUNIT_EXPECT_NE(test, rc, 0);
-		skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc);
+		skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
 		KUNIT_EXPECT_PTR_EQ(test, skb2, NULL);
 	}
 
@@ -423,7 +423,7 @@ static void mctp_test_route_input_sk_reasm(struct kunit *test)
 		rc = mctp_route_input(&rt->rt, skb);
 	}
 
-	skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc);
+	skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
 
 	if (params->rx_len) {
 		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
@@ -582,7 +582,7 @@ static void mctp_test_route_input_sk_keys(struct kunit *test)
 	rc = mctp_route_input(&rt->rt, skb);
 
 	/* (potentially) receive message */
-	skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc);
+	skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
 
 	if (params->deliver)
 		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 47a876ccd288..9fa85bb36c0e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1931,7 +1931,6 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
-	int noblock = flags & MSG_DONTWAIT;
 	size_t copied;
 	struct sk_buff *skb, *data_skb;
 	int err, ret;
@@ -1941,7 +1940,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	copied = 0;
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (skb == NULL)
 		goto out;
 
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index fa9dc2ba3941..6f7f4392cffb 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1159,7 +1159,8 @@ static int nr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	}
 
 	/* Now we can treat all alike */
-	if ((skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &er)) == NULL) {
+	skb = skb_recv_datagram(sk, flags, &er);
+	if (!skb) {
 		release_sock(sk);
 		return er;
 	}
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 4ca35791c93b..77642d18a3b4 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -821,7 +821,6 @@ static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 static int llcp_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 			     size_t len, int flags)
 {
-	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
 	unsigned int copied, rlen;
 	struct sk_buff *skb, *cskb;
@@ -842,7 +841,7 @@ static int llcp_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 	if (flags & (MSG_OOB))
 		return -EOPNOTSUPP;
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb) {
 		pr_err("Recv datagram failed state %d %d %d",
 		       sk->sk_state, err, sock_error(sk));
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 0ca214ab5aef..8dd569765f96 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -238,7 +238,6 @@ static int rawsock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 static int rawsock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			   int flags)
 {
-	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied;
@@ -246,7 +245,7 @@ static int rawsock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	pr_debug("sock=%p sk=%p len=%zu flags=%d\n", sock, sk, len, flags);
 
-	skb = skb_recv_datagram(sk, flags, noblock, &rc);
+	skb = skb_recv_datagram(sk, flags, &rc);
 	if (!skb)
 		return rc;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c39c09899fd0..d3caaf4d4b3e 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3421,7 +3421,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	 *	but then it will block.
 	 */
 
-	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 
 	/*
 	 *	An error occurred so return it. Because skb_recv_datagram()
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 393e6aa7a592..3f2e62b63dd4 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -123,7 +123,8 @@ static int pn_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			MSG_CMSG_COMPAT))
 		goto out_nofree;
 
-	skb = skb_recv_datagram(sk, flags, noblock, &rval);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &rval);
 	if (skb == NULL)
 		goto out_nofree;
 
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 65d463ad8770..441a26706592 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -772,7 +772,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
 	u8 pipe_handle, enabled, n_sb;
 	u8 aligned = 0;
 
-	skb = skb_recv_datagram(sk, 0, flags & O_NONBLOCK, errp);
+	skb = skb_recv_datagram(sk, (flags & O_NONBLOCK) ? MSG_DONTWAIT : 0,
+				errp);
 	if (!skb)
 		return NULL;
 
@@ -1267,7 +1268,8 @@ static int pep_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			return -EINVAL;
 	}
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags |= (noblock ? MSG_DONTWAIT : 0);
+	skb = skb_recv_datagram(sk, flags, &err);
 	lock_sock(sk);
 	if (skb == NULL) {
 		if (err == -ENOTCONN && sk->sk_state == TCP_CLOSE_WAIT)
diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c
index ec2322529727..5c2fb992803b 100644
--- a/net/qrtr/af_qrtr.c
+++ b/net/qrtr/af_qrtr.c
@@ -1035,8 +1035,7 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg,
 		return -EADDRNOTAVAIL;
 	}
 
-	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
-				flags & MSG_DONTWAIT, &rc);
+	skb = skb_recv_datagram(sk, flags, &rc);
 	if (!skb) {
 		release_sock(sk);
 		return rc;
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 30a1cf4c16c6..bf2d986a6bc3 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1230,7 +1230,8 @@ static int rose_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		return -ENOTCONN;
 
 	/* Now we can treat all alike */
-	if ((skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &er)) == NULL)
+	skb = skb_recv_datagram(sk, flags, &er);
+	if (!skb)
 		return er;
 
 	qbit = (skb->data[0] & ROSE_Q_BIT) == ROSE_Q_BIT;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e71a312faa1e..fecbd95da918 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1643,7 +1643,8 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 	 * so that no locks are necessary.
 	 */
 
-	skb = skb_recv_datagram(sk, 0, flags&O_NONBLOCK, &err);
+	skb = skb_recv_datagram(sk, (flags & O_NONBLOCK) ? MSG_DONTWAIT : 0,
+				&err);
 	if (!skb) {
 		/* This means receive shutdown. */
 		if (err == 0)
@@ -2500,7 +2501,7 @@ static int unix_read_sock(struct sock *sk, read_descriptor_t *desc,
 		int used, err;
 
 		mutex_lock(&u->iolock);
-		skb = skb_recv_datagram(sk, 0, 1, &err);
+		skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);
 		mutex_unlock(&u->iolock);
 		if (!skb)
 			return err;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index b17dc9745188..b14f0ed7427b 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1732,19 +1732,16 @@ static int vmci_transport_dgram_dequeue(struct vsock_sock *vsk,
 					int flags)
 {
 	int err;
-	int noblock;
 	struct vmci_datagram *dg;
 	size_t payload_len;
 	struct sk_buff *skb;
 
-	noblock = flags & MSG_DONTWAIT;
-
 	if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
 		return -EOPNOTSUPP;
 
 	/* Retrieve the head sk_buff from the socket's receive queue. */
 	err = 0;
-	skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err);
+	skb = skb_recv_datagram(&vsk->sk, flags, &err);
 	if (!skb)
 		return err;
 
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 3a171828638b..6bc2ac8d8146 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1315,8 +1315,7 @@ static int x25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	} else {
 		/* Now we can treat all alike */
 		release_sock(sk);
-		skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
-					flags & MSG_DONTWAIT, &rc);
+		skb = skb_recv_datagram(sk, flags, &rc);
 		lock_sock(sk);
 		if (!skb)
 			goto out;
-- 
cgit v1.2.3


From fe696ccb277d332dc4e625b5b20b988b04d16c04 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 3 Apr 2022 15:53:54 -0700
Subject: gpu: host1x: Fix a kernel-doc warning

Add @cache description to eliminate a kernel-doc warning.

include/linux/host1x.h:104: warning: Function parameter or member 'cache' not described in 'host1x_client'

Fixes: 1f39b1dfa53c ("drm/tegra: Implement buffer object cache")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Thierry Reding <treding@nvidia.com>
Cc: linux-tegra@vger.kernel.org
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 include/linux/host1x.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index e8dc5bc41f79..00278853eadf 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -81,6 +81,7 @@ struct host1x_client_ops {
  * @parent: pointer to parent structure
  * @usecount: reference count for this structure
  * @lock: mutex for mutually exclusive concurrency
+ * @cache: host1x buffer object cache
  */
 struct host1x_client {
 	struct list_head list;
-- 
cgit v1.2.3


From 804775dfc2885e93a0a4b35db1914c2cc25172b5 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 5 Apr 2022 21:57:47 +0200
Subject: net: ethernet: mtk_eth_soc: add support for Wireless Ethernet
 Dispatch (WED)

The Wireless Ethernet Dispatch subsystem on the MT7622 SoC can be
configured to intercept and handle access to the DMA queues and
PCIe interrupts for a MT7615/MT7915 wireless card.
It can manage the internal WDMA (Wireless DMA) controller, which allows
ethernet packets to be passed from the packet switch engine (PSE) to the
wireless card, bypassing the CPU entirely.
This can be used to implement hardware flow offloading from ethernet to
WLAN.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/Kconfig           |   4 +
 drivers/net/ethernet/mediatek/Makefile          |   5 +
 drivers/net/ethernet/mediatek/mtk_eth_soc.c     |  17 +
 drivers/net/ethernet/mediatek/mtk_eth_soc.h     |   3 +
 drivers/net/ethernet/mediatek/mtk_wed.c         | 875 ++++++++++++++++++++++++
 drivers/net/ethernet/mediatek/mtk_wed.h         | 128 ++++
 drivers/net/ethernet/mediatek/mtk_wed_debugfs.c | 175 +++++
 drivers/net/ethernet/mediatek/mtk_wed_ops.c     |   8 +
 drivers/net/ethernet/mediatek/mtk_wed_regs.h    | 251 +++++++
 include/linux/soc/mediatek/mtk_wed.h            | 131 ++++
 10 files changed, 1597 insertions(+)
 create mode 100644 drivers/net/ethernet/mediatek/mtk_wed.c
 create mode 100644 drivers/net/ethernet/mediatek/mtk_wed.h
 create mode 100644 drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
 create mode 100644 drivers/net/ethernet/mediatek/mtk_wed_ops.c
 create mode 100644 drivers/net/ethernet/mediatek/mtk_wed_regs.h
 create mode 100644 include/linux/soc/mediatek/mtk_wed.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index 86d356b4388d..da4ec235d146 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -7,6 +7,10 @@ config NET_VENDOR_MEDIATEK
 
 if NET_VENDOR_MEDIATEK
 
+config NET_MEDIATEK_SOC_WED
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	def_bool NET_MEDIATEK_SOC != n
+
 config NET_MEDIATEK_SOC
 	tristate "MediaTek SoC Gigabit Ethernet support"
 	depends on NET_DSA || !NET_DSA
diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile
index 79d4cdbbcbf5..45ba0970504a 100644
--- a/drivers/net/ethernet/mediatek/Makefile
+++ b/drivers/net/ethernet/mediatek/Makefile
@@ -5,4 +5,9 @@
 
 obj-$(CONFIG_NET_MEDIATEK_SOC) += mtk_eth.o
 mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o mtk_ppe.o mtk_ppe_debugfs.o mtk_ppe_offload.o
+mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed.o
+ifdef CONFIG_DEBUG_FS
+mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_debugfs.o
+endif
+obj-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_ops.o
 obj-$(CONFIG_NET_MEDIATEK_STAR_EMAC) += mtk_star_emac.o
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 70db217ed831..4d7c542d89fb 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -24,6 +24,7 @@
 #include <net/dsa.h>
 
 #include "mtk_eth_soc.h"
+#include "mtk_wed.h"
 
 static int mtk_msg_level = -1;
 module_param_named(msg_level, mtk_msg_level, int, 0);
@@ -3170,6 +3171,22 @@ static int mtk_probe(struct platform_device *pdev)
 		}
 	}
 
+	for (i = 0;; i++) {
+		struct device_node *np = of_parse_phandle(pdev->dev.of_node,
+							  "mediatek,wed", i);
+		static const u32 wdma_regs[] = {
+			MTK_WDMA0_BASE,
+			MTK_WDMA1_BASE
+		};
+		void __iomem *wdma;
+
+		if (!np || i >= ARRAY_SIZE(wdma_regs))
+			break;
+
+		wdma = eth->base + wdma_regs[i];
+		mtk_wed_add_hw(np, eth, wdma, i);
+	}
+
 	for (i = 0; i < 3; i++) {
 		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT) && i > 0)
 			eth->irq[i] = eth->irq[0];
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index e701544c4287..74661682fd92 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -295,6 +295,9 @@
 #define MTK_GDM1_TX_GPCNT	0x2438
 #define MTK_STAT_OFFSET		0x40
 
+#define MTK_WDMA0_BASE		0x2800
+#define MTK_WDMA1_BASE		0x2c00
+
 /* QDMA descriptor txd4 */
 #define TX_DMA_CHKSUM		(0x7 << 29)
 #define TX_DMA_TSO		BIT(28)
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
new file mode 100644
index 000000000000..f0eacf819cd9
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -0,0 +1,875 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2021 Felix Fietkau <nbd@nbd.name> */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/bitfield.h>
+#include <linux/dma-mapping.h>
+#include <linux/skbuff.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <linux/mfd/syscon.h>
+#include <linux/debugfs.h>
+#include <linux/soc/mediatek/mtk_wed.h>
+#include "mtk_eth_soc.h"
+#include "mtk_wed_regs.h"
+#include "mtk_wed.h"
+#include "mtk_ppe.h"
+
+#define MTK_PCIE_BASE(n)		(0x1a143000 + (n) * 0x2000)
+
+#define MTK_WED_PKT_SIZE		1900
+#define MTK_WED_BUF_SIZE		2048
+#define MTK_WED_BUF_PER_PAGE		(PAGE_SIZE / 2048)
+
+#define MTK_WED_TX_RING_SIZE		2048
+#define MTK_WED_WDMA_RING_SIZE		1024
+
+static struct mtk_wed_hw *hw_list[2];
+static DEFINE_MUTEX(hw_lock);
+
+static void
+wed_m32(struct mtk_wed_device *dev, u32 reg, u32 mask, u32 val)
+{
+	regmap_update_bits(dev->hw->regs, reg, mask | val, val);
+}
+
+static void
+wed_set(struct mtk_wed_device *dev, u32 reg, u32 mask)
+{
+	return wed_m32(dev, reg, 0, mask);
+}
+
+static void
+wed_clr(struct mtk_wed_device *dev, u32 reg, u32 mask)
+{
+	return wed_m32(dev, reg, mask, 0);
+}
+
+static void
+wdma_m32(struct mtk_wed_device *dev, u32 reg, u32 mask, u32 val)
+{
+	wdma_w32(dev, reg, (wdma_r32(dev, reg) & ~mask) | val);
+}
+
+static void
+wdma_set(struct mtk_wed_device *dev, u32 reg, u32 mask)
+{
+	wdma_m32(dev, reg, 0, mask);
+}
+
+static u32
+mtk_wed_read_reset(struct mtk_wed_device *dev)
+{
+	return wed_r32(dev, MTK_WED_RESET);
+}
+
+static void
+mtk_wed_reset(struct mtk_wed_device *dev, u32 mask)
+{
+	u32 status;
+
+	wed_w32(dev, MTK_WED_RESET, mask);
+	if (readx_poll_timeout(mtk_wed_read_reset, dev, status,
+			       !(status & mask), 0, 1000))
+		WARN_ON_ONCE(1);
+}
+
+static struct mtk_wed_hw *
+mtk_wed_assign(struct mtk_wed_device *dev)
+{
+	struct mtk_wed_hw *hw;
+
+	hw = hw_list[pci_domain_nr(dev->wlan.pci_dev->bus)];
+	if (!hw || hw->wed_dev)
+		return NULL;
+
+	hw->wed_dev = dev;
+	return hw;
+}
+
+static int
+mtk_wed_buffer_alloc(struct mtk_wed_device *dev)
+{
+	struct mtk_wdma_desc *desc;
+	dma_addr_t desc_phys;
+	void **page_list;
+	int token = dev->wlan.token_start;
+	int ring_size;
+	int n_pages;
+	int i, page_idx;
+
+	ring_size = dev->wlan.nbuf & ~(MTK_WED_BUF_PER_PAGE - 1);
+	n_pages = ring_size / MTK_WED_BUF_PER_PAGE;
+
+	page_list = kcalloc(n_pages, sizeof(*page_list), GFP_KERNEL);
+	if (!page_list)
+		return -ENOMEM;
+
+	dev->buf_ring.size = ring_size;
+	dev->buf_ring.pages = page_list;
+
+	desc = dma_alloc_coherent(dev->hw->dev, ring_size * sizeof(*desc),
+				  &desc_phys, GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	dev->buf_ring.desc = desc;
+	dev->buf_ring.desc_phys = desc_phys;
+
+	for (i = 0, page_idx = 0; i < ring_size; i += MTK_WED_BUF_PER_PAGE) {
+		dma_addr_t page_phys, buf_phys;
+		struct page *page;
+		void *buf;
+		int s;
+
+		page = __dev_alloc_pages(GFP_KERNEL, 0);
+		if (!page)
+			return -ENOMEM;
+
+		page_phys = dma_map_page(dev->hw->dev, page, 0, PAGE_SIZE,
+					 DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(dev->hw->dev, page_phys)) {
+			__free_page(page);
+			return -ENOMEM;
+		}
+
+		page_list[page_idx++] = page;
+		dma_sync_single_for_cpu(dev->hw->dev, page_phys, PAGE_SIZE,
+					DMA_BIDIRECTIONAL);
+
+		buf = page_to_virt(page);
+		buf_phys = page_phys;
+
+		for (s = 0; s < MTK_WED_BUF_PER_PAGE; s++) {
+			u32 txd_size;
+
+			txd_size = dev->wlan.init_buf(buf, buf_phys, token++);
+
+			desc->buf0 = buf_phys;
+			desc->buf1 = buf_phys + txd_size;
+			desc->ctrl = FIELD_PREP(MTK_WDMA_DESC_CTRL_LEN0,
+						txd_size) |
+				     FIELD_PREP(MTK_WDMA_DESC_CTRL_LEN1,
+						MTK_WED_BUF_SIZE - txd_size) |
+				     MTK_WDMA_DESC_CTRL_LAST_SEG1;
+			desc->info = 0;
+			desc++;
+
+			buf += MTK_WED_BUF_SIZE;
+			buf_phys += MTK_WED_BUF_SIZE;
+		}
+
+		dma_sync_single_for_device(dev->hw->dev, page_phys, PAGE_SIZE,
+					   DMA_BIDIRECTIONAL);
+	}
+
+	return 0;
+}
+
+static void
+mtk_wed_free_buffer(struct mtk_wed_device *dev)
+{
+	struct mtk_wdma_desc *desc = dev->buf_ring.desc;
+	void **page_list = dev->buf_ring.pages;
+	int page_idx;
+	int i;
+
+	if (!page_list)
+		return;
+
+	if (!desc)
+		goto free_pagelist;
+
+	for (i = 0, page_idx = 0; i < dev->buf_ring.size; i += MTK_WED_BUF_PER_PAGE) {
+		void *page = page_list[page_idx++];
+
+		if (!page)
+			break;
+
+		dma_unmap_page(dev->hw->dev, desc[i].buf0,
+			       PAGE_SIZE, DMA_BIDIRECTIONAL);
+		__free_page(page);
+	}
+
+	dma_free_coherent(dev->hw->dev, dev->buf_ring.size * sizeof(*desc),
+			  desc, dev->buf_ring.desc_phys);
+
+free_pagelist:
+	kfree(page_list);
+}
+
+static void
+mtk_wed_free_ring(struct mtk_wed_device *dev, struct mtk_wed_ring *ring)
+{
+	if (!ring->desc)
+		return;
+
+	dma_free_coherent(dev->hw->dev, ring->size * sizeof(*ring->desc),
+			  ring->desc, ring->desc_phys);
+}
+
+static void
+mtk_wed_free_tx_rings(struct mtk_wed_device *dev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dev->tx_ring); i++)
+		mtk_wed_free_ring(dev, &dev->tx_ring[i]);
+	for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++)
+		mtk_wed_free_ring(dev, &dev->tx_wdma[i]);
+}
+
+static void
+mtk_wed_set_ext_int(struct mtk_wed_device *dev, bool en)
+{
+	u32 mask = MTK_WED_EXT_INT_STATUS_ERROR_MASK;
+
+	if (!dev->hw->num_flows)
+		mask &= ~MTK_WED_EXT_INT_STATUS_TKID_WO_PYLD;
+
+	wed_w32(dev, MTK_WED_EXT_INT_MASK, en ? mask : 0);
+	wed_r32(dev, MTK_WED_EXT_INT_MASK);
+}
+
+static void
+mtk_wed_stop(struct mtk_wed_device *dev)
+{
+	regmap_write(dev->hw->mirror, dev->hw->index * 4, 0);
+	mtk_wed_set_ext_int(dev, false);
+
+	wed_clr(dev, MTK_WED_CTRL,
+		MTK_WED_CTRL_WDMA_INT_AGENT_EN |
+		MTK_WED_CTRL_WPDMA_INT_AGENT_EN |
+		MTK_WED_CTRL_WED_TX_BM_EN |
+		MTK_WED_CTRL_WED_TX_FREE_AGENT_EN);
+	wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER, 0);
+	wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, 0);
+	wdma_w32(dev, MTK_WDMA_INT_MASK, 0);
+	wdma_w32(dev, MTK_WDMA_INT_GRP2, 0);
+	wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0);
+
+	wed_clr(dev, MTK_WED_GLO_CFG,
+		MTK_WED_GLO_CFG_TX_DMA_EN |
+		MTK_WED_GLO_CFG_RX_DMA_EN);
+	wed_clr(dev, MTK_WED_WPDMA_GLO_CFG,
+		MTK_WED_WPDMA_GLO_CFG_TX_DRV_EN |
+		MTK_WED_WPDMA_GLO_CFG_RX_DRV_EN);
+	wed_clr(dev, MTK_WED_WDMA_GLO_CFG,
+		MTK_WED_WDMA_GLO_CFG_RX_DRV_EN);
+}
+
+static void
+mtk_wed_detach(struct mtk_wed_device *dev)
+{
+	struct device_node *wlan_node = dev->wlan.pci_dev->dev.of_node;
+	struct mtk_wed_hw *hw = dev->hw;
+
+	mutex_lock(&hw_lock);
+
+	mtk_wed_stop(dev);
+
+	wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_RX);
+	wdma_w32(dev, MTK_WDMA_RESET_IDX, 0);
+
+	mtk_wed_reset(dev, MTK_WED_RESET_WED);
+
+	mtk_wed_free_buffer(dev);
+	mtk_wed_free_tx_rings(dev);
+
+	if (of_dma_is_coherent(wlan_node))
+		regmap_update_bits(hw->hifsys, HIFSYS_DMA_AG_MAP,
+				   BIT(hw->index), BIT(hw->index));
+
+	if (!hw_list[!hw->index]->wed_dev &&
+	    hw->eth->dma_dev != hw->eth->dev)
+		mtk_eth_set_dma_device(hw->eth, hw->eth->dev);
+
+	memset(dev, 0, sizeof(*dev));
+	module_put(THIS_MODULE);
+
+	hw->wed_dev = NULL;
+	mutex_unlock(&hw_lock);
+}
+
+static void
+mtk_wed_hw_init_early(struct mtk_wed_device *dev)
+{
+	u32 mask, set;
+	u32 offset;
+
+	mtk_wed_stop(dev);
+	mtk_wed_reset(dev, MTK_WED_RESET_WED);
+
+	mask = MTK_WED_WDMA_GLO_CFG_BT_SIZE |
+	       MTK_WED_WDMA_GLO_CFG_DYNAMIC_DMAD_RECYCLE |
+	       MTK_WED_WDMA_GLO_CFG_RX_DIS_FSM_AUTO_IDLE;
+	set = FIELD_PREP(MTK_WED_WDMA_GLO_CFG_BT_SIZE, 2) |
+	      MTK_WED_WDMA_GLO_CFG_DYNAMIC_SKIP_DMAD_PREP |
+	      MTK_WED_WDMA_GLO_CFG_IDLE_DMAD_SUPPLY;
+	wed_m32(dev, MTK_WED_WDMA_GLO_CFG, mask, set);
+
+	wdma_set(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_RX_INFO_PRERES);
+
+	offset = dev->hw->index ? 0x04000400 : 0;
+	wed_w32(dev, MTK_WED_WDMA_OFFSET0, 0x2a042a20 + offset);
+	wed_w32(dev, MTK_WED_WDMA_OFFSET1, 0x29002800 + offset);
+
+	wed_w32(dev, MTK_WED_PCIE_CFG_BASE, MTK_PCIE_BASE(dev->hw->index));
+	wed_w32(dev, MTK_WED_WPDMA_CFG_BASE, dev->wlan.wpdma_phys);
+}
+
+static void
+mtk_wed_hw_init(struct mtk_wed_device *dev)
+{
+	if (dev->init_done)
+		return;
+
+	dev->init_done = true;
+	mtk_wed_set_ext_int(dev, false);
+	wed_w32(dev, MTK_WED_TX_BM_CTRL,
+		MTK_WED_TX_BM_CTRL_PAUSE |
+		FIELD_PREP(MTK_WED_TX_BM_CTRL_VLD_GRP_NUM,
+			   dev->buf_ring.size / 128) |
+		FIELD_PREP(MTK_WED_TX_BM_CTRL_RSV_GRP_NUM,
+			   MTK_WED_TX_RING_SIZE / 256));
+
+	wed_w32(dev, MTK_WED_TX_BM_BASE, dev->buf_ring.desc_phys);
+
+	wed_w32(dev, MTK_WED_TX_BM_TKID,
+		FIELD_PREP(MTK_WED_TX_BM_TKID_START,
+			   dev->wlan.token_start) |
+		FIELD_PREP(MTK_WED_TX_BM_TKID_END,
+			   dev->wlan.token_start + dev->wlan.nbuf - 1));
+
+	wed_w32(dev, MTK_WED_TX_BM_BUF_LEN, MTK_WED_PKT_SIZE);
+
+	wed_w32(dev, MTK_WED_TX_BM_DYN_THR,
+		FIELD_PREP(MTK_WED_TX_BM_DYN_THR_LO, 1) |
+		MTK_WED_TX_BM_DYN_THR_HI);
+
+	mtk_wed_reset(dev, MTK_WED_RESET_TX_BM);
+
+	wed_set(dev, MTK_WED_CTRL,
+		MTK_WED_CTRL_WED_TX_BM_EN |
+		MTK_WED_CTRL_WED_TX_FREE_AGENT_EN);
+
+	wed_clr(dev, MTK_WED_TX_BM_CTRL, MTK_WED_TX_BM_CTRL_PAUSE);
+}
+
+static void
+mtk_wed_ring_reset(struct mtk_wdma_desc *desc, int size)
+{
+	int i;
+
+	for (i = 0; i < size; i++) {
+		desc[i].buf0 = 0;
+		desc[i].ctrl = cpu_to_le32(MTK_WDMA_DESC_CTRL_DMA_DONE);
+		desc[i].buf1 = 0;
+		desc[i].info = 0;
+	}
+}
+
+static u32
+mtk_wed_check_busy(struct mtk_wed_device *dev)
+{
+	if (wed_r32(dev, MTK_WED_GLO_CFG) & MTK_WED_GLO_CFG_TX_DMA_BUSY)
+		return true;
+
+	if (wed_r32(dev, MTK_WED_WPDMA_GLO_CFG) &
+	    MTK_WED_WPDMA_GLO_CFG_TX_DRV_BUSY)
+		return true;
+
+	if (wed_r32(dev, MTK_WED_CTRL) & MTK_WED_CTRL_WDMA_INT_AGENT_BUSY)
+		return true;
+
+	if (wed_r32(dev, MTK_WED_WDMA_GLO_CFG) &
+	    MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY)
+		return true;
+
+	if (wdma_r32(dev, MTK_WDMA_GLO_CFG) &
+	    MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY)
+		return true;
+
+	if (wed_r32(dev, MTK_WED_CTRL) &
+	    (MTK_WED_CTRL_WED_TX_BM_BUSY | MTK_WED_CTRL_WED_TX_FREE_AGENT_BUSY))
+		return true;
+
+	return false;
+}
+
+static int
+mtk_wed_poll_busy(struct mtk_wed_device *dev)
+{
+	int sleep = 15000;
+	int timeout = 100 * sleep;
+	u32 val;
+
+	return read_poll_timeout(mtk_wed_check_busy, val, !val, sleep,
+				 timeout, false, dev);
+}
+
+static void
+mtk_wed_reset_dma(struct mtk_wed_device *dev)
+{
+	bool busy = false;
+	u32 val;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dev->tx_ring); i++) {
+		struct mtk_wdma_desc *desc = dev->tx_ring[i].desc;
+
+		if (!desc)
+			continue;
+
+		mtk_wed_ring_reset(desc, MTK_WED_TX_RING_SIZE);
+	}
+
+	if (mtk_wed_poll_busy(dev))
+		busy = mtk_wed_check_busy(dev);
+
+	if (busy) {
+		mtk_wed_reset(dev, MTK_WED_RESET_WED_TX_DMA);
+	} else {
+		wed_w32(dev, MTK_WED_RESET_IDX,
+			MTK_WED_RESET_IDX_TX |
+			MTK_WED_RESET_IDX_RX);
+		wed_w32(dev, MTK_WED_RESET_IDX, 0);
+	}
+
+	wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_RX);
+	wdma_w32(dev, MTK_WDMA_RESET_IDX, 0);
+
+	if (busy) {
+		mtk_wed_reset(dev, MTK_WED_RESET_WDMA_INT_AGENT);
+		mtk_wed_reset(dev, MTK_WED_RESET_WDMA_RX_DRV);
+	} else {
+		wed_w32(dev, MTK_WED_WDMA_RESET_IDX,
+			MTK_WED_WDMA_RESET_IDX_RX | MTK_WED_WDMA_RESET_IDX_DRV);
+		wed_w32(dev, MTK_WED_WDMA_RESET_IDX, 0);
+
+		wed_set(dev, MTK_WED_WDMA_GLO_CFG,
+			MTK_WED_WDMA_GLO_CFG_RST_INIT_COMPLETE);
+
+		wed_clr(dev, MTK_WED_WDMA_GLO_CFG,
+			MTK_WED_WDMA_GLO_CFG_RST_INIT_COMPLETE);
+	}
+
+	for (i = 0; i < 100; i++) {
+		val = wed_r32(dev, MTK_WED_TX_BM_INTF);
+		if (FIELD_GET(MTK_WED_TX_BM_INTF_TKFIFO_FDEP, val) == 0x40)
+			break;
+	}
+
+	mtk_wed_reset(dev, MTK_WED_RESET_TX_FREE_AGENT);
+	mtk_wed_reset(dev, MTK_WED_RESET_TX_BM);
+
+	if (busy) {
+		mtk_wed_reset(dev, MTK_WED_RESET_WPDMA_INT_AGENT);
+		mtk_wed_reset(dev, MTK_WED_RESET_WPDMA_TX_DRV);
+		mtk_wed_reset(dev, MTK_WED_RESET_WPDMA_RX_DRV);
+	} else {
+		wed_w32(dev, MTK_WED_WPDMA_RESET_IDX,
+			MTK_WED_WPDMA_RESET_IDX_TX |
+			MTK_WED_WPDMA_RESET_IDX_RX);
+		wed_w32(dev, MTK_WED_WPDMA_RESET_IDX, 0);
+	}
+
+}
+
+static int
+mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring,
+		   int size)
+{
+	ring->desc = dma_alloc_coherent(dev->hw->dev,
+					size * sizeof(*ring->desc),
+					&ring->desc_phys, GFP_KERNEL);
+	if (!ring->desc)
+		return -ENOMEM;
+
+	ring->size = size;
+	mtk_wed_ring_reset(ring->desc, size);
+
+	return 0;
+}
+
+static int
+mtk_wed_wdma_ring_setup(struct mtk_wed_device *dev, int idx, int size)
+{
+	struct mtk_wed_ring *wdma = &dev->tx_wdma[idx];
+
+	if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE))
+		return -ENOMEM;
+
+	wdma_w32(dev, MTK_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_BASE,
+		 wdma->desc_phys);
+	wdma_w32(dev, MTK_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_COUNT,
+		 size);
+	wdma_w32(dev, MTK_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_CPU_IDX, 0);
+
+	wed_w32(dev, MTK_WED_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_BASE,
+		wdma->desc_phys);
+	wed_w32(dev, MTK_WED_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_COUNT,
+		size);
+
+	return 0;
+}
+
+static void
+mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask)
+{
+	u32 wdma_mask;
+	u32 val;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++)
+		if (!dev->tx_wdma[i].desc)
+			mtk_wed_wdma_ring_setup(dev, i, 16);
+
+	wdma_mask = FIELD_PREP(MTK_WDMA_INT_MASK_RX_DONE, GENMASK(1, 0));
+
+	mtk_wed_hw_init(dev);
+
+	wed_set(dev, MTK_WED_CTRL,
+		MTK_WED_CTRL_WDMA_INT_AGENT_EN |
+		MTK_WED_CTRL_WPDMA_INT_AGENT_EN |
+		MTK_WED_CTRL_WED_TX_BM_EN |
+		MTK_WED_CTRL_WED_TX_FREE_AGENT_EN);
+
+	wed_w32(dev, MTK_WED_PCIE_INT_TRIGGER, MTK_WED_PCIE_INT_TRIGGER_STATUS);
+
+	wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER,
+		MTK_WED_WPDMA_INT_TRIGGER_RX_DONE |
+		MTK_WED_WPDMA_INT_TRIGGER_TX_DONE);
+
+	wed_set(dev, MTK_WED_WPDMA_INT_CTRL,
+		MTK_WED_WPDMA_INT_CTRL_SUBRT_ADV);
+
+	wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, wdma_mask);
+	wed_clr(dev, MTK_WED_WDMA_INT_CTRL, wdma_mask);
+
+	wdma_w32(dev, MTK_WDMA_INT_MASK, wdma_mask);
+	wdma_w32(dev, MTK_WDMA_INT_GRP2, wdma_mask);
+
+	wed_w32(dev, MTK_WED_WPDMA_INT_MASK, irq_mask);
+	wed_w32(dev, MTK_WED_INT_MASK, irq_mask);
+
+	wed_set(dev, MTK_WED_GLO_CFG,
+		MTK_WED_GLO_CFG_TX_DMA_EN |
+		MTK_WED_GLO_CFG_RX_DMA_EN);
+	wed_set(dev, MTK_WED_WPDMA_GLO_CFG,
+		MTK_WED_WPDMA_GLO_CFG_TX_DRV_EN |
+		MTK_WED_WPDMA_GLO_CFG_RX_DRV_EN);
+	wed_set(dev, MTK_WED_WDMA_GLO_CFG,
+		MTK_WED_WDMA_GLO_CFG_RX_DRV_EN);
+
+	mtk_wed_set_ext_int(dev, true);
+	val = dev->wlan.wpdma_phys |
+	      MTK_PCIE_MIRROR_MAP_EN |
+	      FIELD_PREP(MTK_PCIE_MIRROR_MAP_WED_ID, dev->hw->index);
+
+	if (dev->hw->index)
+		val |= BIT(1);
+	val |= BIT(0);
+	regmap_write(dev->hw->mirror, dev->hw->index * 4, val);
+
+	dev->running = true;
+}
+
+static int
+mtk_wed_attach(struct mtk_wed_device *dev)
+	__releases(RCU)
+{
+	struct mtk_wed_hw *hw;
+	int ret = 0;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
+			 "mtk_wed_attach without holding the RCU read lock");
+
+	if (pci_domain_nr(dev->wlan.pci_dev->bus) > 1 ||
+	    !try_module_get(THIS_MODULE))
+		ret = -ENODEV;
+
+	rcu_read_unlock();
+
+	if (ret)
+		return ret;
+
+	mutex_lock(&hw_lock);
+
+	hw = mtk_wed_assign(dev);
+	if (!hw) {
+		module_put(THIS_MODULE);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	dev_info(&dev->wlan.pci_dev->dev, "attaching wed device %d\n", hw->index);
+
+	dev->hw = hw;
+	dev->dev = hw->dev;
+	dev->irq = hw->irq;
+	dev->wdma_idx = hw->index;
+
+	if (hw->eth->dma_dev == hw->eth->dev &&
+	    of_dma_is_coherent(hw->eth->dev->of_node))
+		mtk_eth_set_dma_device(hw->eth, hw->dev);
+
+	ret = mtk_wed_buffer_alloc(dev);
+	if (ret) {
+		mtk_wed_detach(dev);
+		goto out;
+	}
+
+	mtk_wed_hw_init_early(dev);
+	regmap_update_bits(hw->hifsys, HIFSYS_DMA_AG_MAP, BIT(hw->index), 0);
+
+out:
+	mutex_unlock(&hw_lock);
+
+	return ret;
+}
+
+static int
+mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs)
+{
+	struct mtk_wed_ring *ring = &dev->tx_ring[idx];
+
+	/*
+	 * Tx ring redirection:
+	 * Instead of configuring the WLAN PDMA TX ring directly, the WLAN
+	 * driver allocated DMA ring gets configured into WED MTK_WED_RING_TX(n)
+	 * registers.
+	 *
+	 * WED driver posts its own DMA ring as WLAN PDMA TX and configures it
+	 * into MTK_WED_WPDMA_RING_TX(n) registers.
+	 * It gets filled with packets picked up from WED TX ring and from
+	 * WDMA RX.
+	 */
+
+	BUG_ON(idx > ARRAY_SIZE(dev->tx_ring));
+
+	if (mtk_wed_ring_alloc(dev, ring, MTK_WED_TX_RING_SIZE))
+		return -ENOMEM;
+
+	if (mtk_wed_wdma_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE))
+		return -ENOMEM;
+
+	ring->reg_base = MTK_WED_RING_TX(idx);
+	ring->wpdma = regs;
+
+	/* WED -> WPDMA */
+	wpdma_tx_w32(dev, idx, MTK_WED_RING_OFS_BASE, ring->desc_phys);
+	wpdma_tx_w32(dev, idx, MTK_WED_RING_OFS_COUNT, MTK_WED_TX_RING_SIZE);
+	wpdma_tx_w32(dev, idx, MTK_WED_RING_OFS_CPU_IDX, 0);
+
+	wed_w32(dev, MTK_WED_WPDMA_RING_TX(idx) + MTK_WED_RING_OFS_BASE,
+		ring->desc_phys);
+	wed_w32(dev, MTK_WED_WPDMA_RING_TX(idx) + MTK_WED_RING_OFS_COUNT,
+		MTK_WED_TX_RING_SIZE);
+	wed_w32(dev, MTK_WED_WPDMA_RING_TX(idx) + MTK_WED_RING_OFS_CPU_IDX, 0);
+
+	return 0;
+}
+
+static int
+mtk_wed_txfree_ring_setup(struct mtk_wed_device *dev, void __iomem *regs)
+{
+	struct mtk_wed_ring *ring = &dev->txfree_ring;
+	int i;
+
+	/*
+	 * For txfree event handling, the same DMA ring is shared between WED
+	 * and WLAN. The WLAN driver accesses the ring index registers through
+	 * WED
+	 */
+	ring->reg_base = MTK_WED_RING_RX(1);
+	ring->wpdma = regs;
+
+	for (i = 0; i < 12; i += 4) {
+		u32 val = readl(regs + i);
+
+		wed_w32(dev, MTK_WED_RING_RX(1) + i, val);
+		wed_w32(dev, MTK_WED_WPDMA_RING_RX(1) + i, val);
+	}
+
+	return 0;
+}
+
+static u32
+mtk_wed_irq_get(struct mtk_wed_device *dev, u32 mask)
+{
+	u32 val;
+
+	val = wed_r32(dev, MTK_WED_EXT_INT_STATUS);
+	wed_w32(dev, MTK_WED_EXT_INT_STATUS, val);
+	val &= MTK_WED_EXT_INT_STATUS_ERROR_MASK;
+	if (!dev->hw->num_flows)
+		val &= ~MTK_WED_EXT_INT_STATUS_TKID_WO_PYLD;
+	if (val && net_ratelimit())
+		pr_err("mtk_wed%d: error status=%08x\n", dev->hw->index, val);
+
+	val = wed_r32(dev, MTK_WED_INT_STATUS);
+	val &= mask;
+	wed_w32(dev, MTK_WED_INT_STATUS, val); /* ACK */
+
+	return val;
+}
+
+static void
+mtk_wed_irq_set_mask(struct mtk_wed_device *dev, u32 mask)
+{
+	if (!dev->running)
+		return;
+
+	mtk_wed_set_ext_int(dev, !!mask);
+	wed_w32(dev, MTK_WED_INT_MASK, mask);
+}
+
+int mtk_wed_flow_add(int index)
+{
+	struct mtk_wed_hw *hw = hw_list[index];
+	int ret;
+
+	if (!hw || !hw->wed_dev)
+		return -ENODEV;
+
+	if (hw->num_flows) {
+		hw->num_flows++;
+		return 0;
+	}
+
+	mutex_lock(&hw_lock);
+	if (!hw->wed_dev) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	ret = hw->wed_dev->wlan.offload_enable(hw->wed_dev);
+	if (!ret)
+		hw->num_flows++;
+	mtk_wed_set_ext_int(hw->wed_dev, true);
+
+out:
+	mutex_unlock(&hw_lock);
+
+	return ret;
+}
+
+void mtk_wed_flow_remove(int index)
+{
+	struct mtk_wed_hw *hw = hw_list[index];
+
+	if (!hw)
+		return;
+
+	if (--hw->num_flows)
+		return;
+
+	mutex_lock(&hw_lock);
+	if (!hw->wed_dev)
+		goto out;
+
+	hw->wed_dev->wlan.offload_disable(hw->wed_dev);
+	mtk_wed_set_ext_int(hw->wed_dev, true);
+
+out:
+	mutex_unlock(&hw_lock);
+}
+
+void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth,
+		    void __iomem *wdma, int index)
+{
+	static const struct mtk_wed_ops wed_ops = {
+		.attach = mtk_wed_attach,
+		.tx_ring_setup = mtk_wed_tx_ring_setup,
+		.txfree_ring_setup = mtk_wed_txfree_ring_setup,
+		.start = mtk_wed_start,
+		.stop = mtk_wed_stop,
+		.reset_dma = mtk_wed_reset_dma,
+		.reg_read = wed_r32,
+		.reg_write = wed_w32,
+		.irq_get = mtk_wed_irq_get,
+		.irq_set_mask = mtk_wed_irq_set_mask,
+		.detach = mtk_wed_detach,
+	};
+	struct device_node *eth_np = eth->dev->of_node;
+	struct platform_device *pdev;
+	struct mtk_wed_hw *hw;
+	struct regmap *regs;
+	int irq;
+
+	if (!np)
+		return;
+
+	pdev = of_find_device_by_node(np);
+	if (!pdev)
+		return;
+
+	get_device(&pdev->dev);
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return;
+
+	regs = syscon_regmap_lookup_by_phandle(np, NULL);
+	if (!regs)
+		return;
+
+	rcu_assign_pointer(mtk_soc_wed_ops, &wed_ops);
+
+	mutex_lock(&hw_lock);
+
+	if (WARN_ON(hw_list[index]))
+		goto unlock;
+
+	hw = kzalloc(sizeof(*hw), GFP_KERNEL);
+	hw->node = np;
+	hw->regs = regs;
+	hw->eth = eth;
+	hw->dev = &pdev->dev;
+	hw->wdma = wdma;
+	hw->index = index;
+	hw->irq = irq;
+	hw->mirror = syscon_regmap_lookup_by_phandle(eth_np,
+						     "mediatek,pcie-mirror");
+	hw->hifsys = syscon_regmap_lookup_by_phandle(eth_np,
+						     "mediatek,hifsys");
+	if (IS_ERR(hw->mirror) || IS_ERR(hw->hifsys)) {
+		kfree(hw);
+		goto unlock;
+	}
+
+	if (!index) {
+		regmap_write(hw->mirror, 0, 0);
+		regmap_write(hw->mirror, 4, 0);
+	}
+	mtk_wed_hw_add_debugfs(hw);
+
+	hw_list[index] = hw;
+
+unlock:
+	mutex_unlock(&hw_lock);
+}
+
+void mtk_wed_exit(void)
+{
+	int i;
+
+	rcu_assign_pointer(mtk_soc_wed_ops, NULL);
+
+	synchronize_rcu();
+
+	for (i = 0; i < ARRAY_SIZE(hw_list); i++) {
+		struct mtk_wed_hw *hw;
+
+		hw = hw_list[i];
+		if (!hw)
+			continue;
+
+		hw_list[i] = NULL;
+		debugfs_remove(hw->debugfs_dir);
+		put_device(hw->dev);
+		kfree(hw);
+	}
+}
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.h b/drivers/net/ethernet/mediatek/mtk_wed.h
new file mode 100644
index 000000000000..404c9a9b130d
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_wed.h
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2021 Felix Fietkau <nbd@nbd.name> */
+
+#ifndef __MTK_WED_PRIV_H
+#define __MTK_WED_PRIV_H
+
+#include <linux/soc/mediatek/mtk_wed.h>
+#include <linux/debugfs.h>
+#include <linux/regmap.h>
+
+struct mtk_eth;
+
+struct mtk_wed_hw {
+	struct device_node *node;
+	struct mtk_eth *eth;
+	struct regmap *regs;
+	struct regmap *hifsys;
+	struct device *dev;
+	void __iomem *wdma;
+	struct regmap *mirror;
+	struct dentry *debugfs_dir;
+	struct mtk_wed_device *wed_dev;
+	u32 debugfs_reg;
+	u32 num_flows;
+	char dirname[5];
+	int irq;
+	int index;
+};
+
+
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+static inline void
+wed_w32(struct mtk_wed_device *dev, u32 reg, u32 val)
+{
+	regmap_write(dev->hw->regs, reg, val);
+}
+
+static inline u32
+wed_r32(struct mtk_wed_device *dev, u32 reg)
+{
+	unsigned int val;
+
+	regmap_read(dev->hw->regs, reg, &val);
+
+	return val;
+}
+
+static inline void
+wdma_w32(struct mtk_wed_device *dev, u32 reg, u32 val)
+{
+	writel(val, dev->hw->wdma + reg);
+}
+
+static inline u32
+wdma_r32(struct mtk_wed_device *dev, u32 reg)
+{
+	return readl(dev->hw->wdma + reg);
+}
+
+static inline u32
+wpdma_tx_r32(struct mtk_wed_device *dev, int ring, u32 reg)
+{
+	if (!dev->tx_ring[ring].wpdma)
+		return 0;
+
+	return readl(dev->tx_ring[ring].wpdma + reg);
+}
+
+static inline void
+wpdma_tx_w32(struct mtk_wed_device *dev, int ring, u32 reg, u32 val)
+{
+	if (!dev->tx_ring[ring].wpdma)
+		return;
+
+	writel(val, dev->tx_ring[ring].wpdma + reg);
+}
+
+static inline u32
+wpdma_txfree_r32(struct mtk_wed_device *dev, u32 reg)
+{
+	if (!dev->txfree_ring.wpdma)
+		return 0;
+
+	return readl(dev->txfree_ring.wpdma + reg);
+}
+
+static inline void
+wpdma_txfree_w32(struct mtk_wed_device *dev, u32 reg, u32 val)
+{
+	if (!dev->txfree_ring.wpdma)
+		return;
+
+	writel(val, dev->txfree_ring.wpdma + reg);
+}
+
+void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth,
+		    void __iomem *wdma, int index);
+void mtk_wed_exit(void);
+int mtk_wed_flow_add(int index);
+void mtk_wed_flow_remove(int index);
+#else
+static inline void
+mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth,
+	       void __iomem *wdma, int index)
+{
+}
+static inline void
+mtk_wed_exit(void)
+{
+}
+static inline int mtk_wed_flow_add(int index)
+{
+	return -EINVAL;
+}
+static inline void mtk_wed_flow_remove(int index)
+{
+}
+#endif
+
+#ifdef CONFIG_DEBUG_FS
+void mtk_wed_hw_add_debugfs(struct mtk_wed_hw *hw);
+#else
+static inline void mtk_wed_hw_add_debugfs(struct mtk_wed_hw *hw)
+{
+}
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
new file mode 100644
index 000000000000..a81d3fd1a439
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2021 Felix Fietkau <nbd@nbd.name> */
+
+#include <linux/seq_file.h>
+#include "mtk_wed.h"
+#include "mtk_wed_regs.h"
+
+struct reg_dump {
+	const char *name;
+	u16 offset;
+	u8 type;
+	u8 base;
+};
+
+enum {
+	DUMP_TYPE_STRING,
+	DUMP_TYPE_WED,
+	DUMP_TYPE_WDMA,
+	DUMP_TYPE_WPDMA_TX,
+	DUMP_TYPE_WPDMA_TXFREE,
+};
+
+#define DUMP_STR(_str) { _str, 0, DUMP_TYPE_STRING }
+#define DUMP_REG(_reg, ...) { #_reg, MTK_##_reg, __VA_ARGS__ }
+#define DUMP_RING(_prefix, _base, ...)				\
+	{ _prefix " BASE", _base, __VA_ARGS__ },		\
+	{ _prefix " CNT",  _base + 0x4, __VA_ARGS__ },	\
+	{ _prefix " CIDX", _base + 0x8, __VA_ARGS__ },	\
+	{ _prefix " DIDX", _base + 0xc, __VA_ARGS__ }
+
+#define DUMP_WED(_reg) DUMP_REG(_reg, DUMP_TYPE_WED)
+#define DUMP_WED_RING(_base) DUMP_RING(#_base, MTK_##_base, DUMP_TYPE_WED)
+
+#define DUMP_WDMA(_reg) DUMP_REG(_reg, DUMP_TYPE_WDMA)
+#define DUMP_WDMA_RING(_base) DUMP_RING(#_base, MTK_##_base, DUMP_TYPE_WDMA)
+
+#define DUMP_WPDMA_TX_RING(_n) DUMP_RING("WPDMA_TX" #_n, 0, DUMP_TYPE_WPDMA_TX, _n)
+#define DUMP_WPDMA_TXFREE_RING DUMP_RING("WPDMA_RX1", 0, DUMP_TYPE_WPDMA_TXFREE)
+
+static void
+print_reg_val(struct seq_file *s, const char *name, u32 val)
+{
+	seq_printf(s, "%-32s %08x\n", name, val);
+}
+
+static void
+dump_wed_regs(struct seq_file *s, struct mtk_wed_device *dev,
+	      const struct reg_dump *regs, int n_regs)
+{
+	const struct reg_dump *cur;
+	u32 val;
+
+	for (cur = regs; cur < &regs[n_regs]; cur++) {
+		switch (cur->type) {
+		case DUMP_TYPE_STRING:
+			seq_printf(s, "%s======== %s:\n",
+				   cur > regs ? "\n" : "",
+				   cur->name);
+			continue;
+		case DUMP_TYPE_WED:
+			val = wed_r32(dev, cur->offset);
+			break;
+		case DUMP_TYPE_WDMA:
+			val = wdma_r32(dev, cur->offset);
+			break;
+		case DUMP_TYPE_WPDMA_TX:
+			val = wpdma_tx_r32(dev, cur->base, cur->offset);
+			break;
+		case DUMP_TYPE_WPDMA_TXFREE:
+			val = wpdma_txfree_r32(dev, cur->offset);
+			break;
+		}
+		print_reg_val(s, cur->name, val);
+	}
+}
+
+
+static int
+wed_txinfo_show(struct seq_file *s, void *data)
+{
+	static const struct reg_dump regs[] = {
+		DUMP_STR("WED TX"),
+		DUMP_WED(WED_TX_MIB(0)),
+		DUMP_WED_RING(WED_RING_TX(0)),
+
+		DUMP_WED(WED_TX_MIB(1)),
+		DUMP_WED_RING(WED_RING_TX(1)),
+
+		DUMP_STR("WPDMA TX"),
+		DUMP_WED(WED_WPDMA_TX_MIB(0)),
+		DUMP_WED_RING(WED_WPDMA_RING_TX(0)),
+		DUMP_WED(WED_WPDMA_TX_COHERENT_MIB(0)),
+
+		DUMP_WED(WED_WPDMA_TX_MIB(1)),
+		DUMP_WED_RING(WED_WPDMA_RING_TX(1)),
+		DUMP_WED(WED_WPDMA_TX_COHERENT_MIB(1)),
+
+		DUMP_STR("WPDMA TX"),
+		DUMP_WPDMA_TX_RING(0),
+		DUMP_WPDMA_TX_RING(1),
+
+		DUMP_STR("WED WDMA RX"),
+		DUMP_WED(WED_WDMA_RX_MIB(0)),
+		DUMP_WED_RING(WED_WDMA_RING_RX(0)),
+		DUMP_WED(WED_WDMA_RX_THRES(0)),
+		DUMP_WED(WED_WDMA_RX_RECYCLE_MIB(0)),
+		DUMP_WED(WED_WDMA_RX_PROCESSED_MIB(0)),
+
+		DUMP_WED(WED_WDMA_RX_MIB(1)),
+		DUMP_WED_RING(WED_WDMA_RING_RX(1)),
+		DUMP_WED(WED_WDMA_RX_THRES(1)),
+		DUMP_WED(WED_WDMA_RX_RECYCLE_MIB(1)),
+		DUMP_WED(WED_WDMA_RX_PROCESSED_MIB(1)),
+
+		DUMP_STR("WDMA RX"),
+		DUMP_WDMA(WDMA_GLO_CFG),
+		DUMP_WDMA_RING(WDMA_RING_RX(0)),
+		DUMP_WDMA_RING(WDMA_RING_RX(1)),
+	};
+	struct mtk_wed_hw *hw = s->private;
+	struct mtk_wed_device *dev = hw->wed_dev;
+
+	if (!dev)
+		return 0;
+
+	dump_wed_regs(s, dev, regs, ARRAY_SIZE(regs));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(wed_txinfo);
+
+
+static int
+mtk_wed_reg_set(void *data, u64 val)
+{
+	struct mtk_wed_hw *hw = data;
+
+	regmap_write(hw->regs, hw->debugfs_reg, val);
+
+	return 0;
+}
+
+static int
+mtk_wed_reg_get(void *data, u64 *val)
+{
+	struct mtk_wed_hw *hw = data;
+	unsigned int regval;
+	int ret;
+
+	ret = regmap_read(hw->regs, hw->debugfs_reg, &regval);
+	if (ret)
+		return ret;
+
+	*val = regval;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(fops_regval, mtk_wed_reg_get, mtk_wed_reg_set,
+             "0x%08llx\n");
+
+void mtk_wed_hw_add_debugfs(struct mtk_wed_hw *hw)
+{
+	struct dentry *dir;
+
+	snprintf(hw->dirname, sizeof(hw->dirname), "wed%d", hw->index);
+	dir = debugfs_create_dir(hw->dirname, NULL);
+	if (!dir)
+		return;
+
+	hw->debugfs_dir = dir;
+	debugfs_create_u32("regidx", 0600, dir, &hw->debugfs_reg);
+	debugfs_create_file_unsafe("regval", 0600, dir, hw, &fops_regval);
+	debugfs_create_file_unsafe("txinfo", 0400, dir, hw, &wed_txinfo_fops);
+}
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_ops.c b/drivers/net/ethernet/mediatek/mtk_wed_ops.c
new file mode 100644
index 000000000000..a5d9d8a5bce2
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_wed_ops.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Felix Fietkau <nbd@nbd.name> */
+
+#include <linux/kernel.h>
+#include <linux/soc/mediatek/mtk_wed.h>
+
+const struct mtk_wed_ops __rcu *mtk_soc_wed_ops;
+EXPORT_SYMBOL_GPL(mtk_soc_wed_ops);
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h
new file mode 100644
index 000000000000..0a0465ea58b4
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Felix Fietkau <nbd@nbd.name> */
+
+#ifndef __MTK_WED_REGS_H
+#define __MTK_WED_REGS_H
+
+#define MTK_WDMA_DESC_CTRL_LEN1			GENMASK(14, 0)
+#define MTK_WDMA_DESC_CTRL_LAST_SEG1		BIT(15)
+#define MTK_WDMA_DESC_CTRL_BURST		BIT(16)
+#define MTK_WDMA_DESC_CTRL_LEN0			GENMASK(29, 16)
+#define MTK_WDMA_DESC_CTRL_LAST_SEG0		BIT(30)
+#define MTK_WDMA_DESC_CTRL_DMA_DONE		BIT(31)
+
+struct mtk_wdma_desc {
+	__le32 buf0;
+	__le32 ctrl;
+	__le32 buf1;
+	__le32 info;
+} __packed __aligned(4);
+
+#define MTK_WED_RESET					0x008
+#define MTK_WED_RESET_TX_BM				BIT(0)
+#define MTK_WED_RESET_TX_FREE_AGENT			BIT(4)
+#define MTK_WED_RESET_WPDMA_TX_DRV			BIT(8)
+#define MTK_WED_RESET_WPDMA_RX_DRV			BIT(9)
+#define MTK_WED_RESET_WPDMA_INT_AGENT			BIT(11)
+#define MTK_WED_RESET_WED_TX_DMA			BIT(12)
+#define MTK_WED_RESET_WDMA_RX_DRV			BIT(17)
+#define MTK_WED_RESET_WDMA_INT_AGENT			BIT(19)
+#define MTK_WED_RESET_WED				BIT(31)
+
+#define MTK_WED_CTRL					0x00c
+#define MTK_WED_CTRL_WPDMA_INT_AGENT_EN			BIT(0)
+#define MTK_WED_CTRL_WPDMA_INT_AGENT_BUSY		BIT(1)
+#define MTK_WED_CTRL_WDMA_INT_AGENT_EN			BIT(2)
+#define MTK_WED_CTRL_WDMA_INT_AGENT_BUSY		BIT(3)
+#define MTK_WED_CTRL_WED_TX_BM_EN			BIT(8)
+#define MTK_WED_CTRL_WED_TX_BM_BUSY			BIT(9)
+#define MTK_WED_CTRL_WED_TX_FREE_AGENT_EN		BIT(10)
+#define MTK_WED_CTRL_WED_TX_FREE_AGENT_BUSY		BIT(11)
+#define MTK_WED_CTRL_RESERVE_EN				BIT(12)
+#define MTK_WED_CTRL_RESERVE_BUSY			BIT(13)
+#define MTK_WED_CTRL_FINAL_DIDX_READ			BIT(24)
+#define MTK_WED_CTRL_MIB_READ_CLEAR			BIT(28)
+
+#define MTK_WED_EXT_INT_STATUS				0x020
+#define MTK_WED_EXT_INT_STATUS_TF_LEN_ERR		BIT(0)
+#define MTK_WED_EXT_INT_STATUS_TKID_WO_PYLD		BIT(1)
+#define MTK_WED_EXT_INT_STATUS_TKID_TITO_INVALID	BIT(4)
+#define MTK_WED_EXT_INT_STATUS_TX_FBUF_LO_TH		BIT(8)
+#define MTK_WED_EXT_INT_STATUS_TX_FBUF_HI_TH		BIT(9)
+#define MTK_WED_EXT_INT_STATUS_RX_FBUF_LO_TH		BIT(12)
+#define MTK_WED_EXT_INT_STATUS_RX_FBUF_HI_TH		BIT(13)
+#define MTK_WED_EXT_INT_STATUS_RX_DRV_R_RESP_ERR	BIT(16)
+#define MTK_WED_EXT_INT_STATUS_RX_DRV_W_RESP_ERR	BIT(17)
+#define MTK_WED_EXT_INT_STATUS_RX_DRV_COHERENT		BIT(18)
+#define MTK_WED_EXT_INT_STATUS_RX_DRV_INIT_WDMA_EN	BIT(19)
+#define MTK_WED_EXT_INT_STATUS_RX_DRV_BM_DMAD_COHERENT	BIT(20)
+#define MTK_WED_EXT_INT_STATUS_TX_DRV_R_RESP_ERR	BIT(21)
+#define MTK_WED_EXT_INT_STATUS_TX_DRV_W_RESP_ERR	BIT(22)
+#define MTK_WED_EXT_INT_STATUS_RX_DRV_DMA_RECYCLE	BIT(24)
+#define MTK_WED_EXT_INT_STATUS_ERROR_MASK		(MTK_WED_EXT_INT_STATUS_TF_LEN_ERR | \
+							 MTK_WED_EXT_INT_STATUS_TKID_WO_PYLD | \
+							 MTK_WED_EXT_INT_STATUS_TKID_TITO_INVALID | \
+							 MTK_WED_EXT_INT_STATUS_RX_DRV_R_RESP_ERR | \
+							 MTK_WED_EXT_INT_STATUS_RX_DRV_W_RESP_ERR | \
+							 MTK_WED_EXT_INT_STATUS_RX_DRV_INIT_WDMA_EN | \
+							 MTK_WED_EXT_INT_STATUS_TX_DRV_R_RESP_ERR | \
+							 MTK_WED_EXT_INT_STATUS_TX_DRV_W_RESP_ERR)
+
+#define MTK_WED_EXT_INT_MASK				0x028
+
+#define MTK_WED_STATUS					0x060
+#define MTK_WED_STATUS_TX				GENMASK(15, 8)
+
+#define MTK_WED_TX_BM_CTRL				0x080
+#define MTK_WED_TX_BM_CTRL_VLD_GRP_NUM			GENMASK(6, 0)
+#define MTK_WED_TX_BM_CTRL_RSV_GRP_NUM			GENMASK(22, 16)
+#define MTK_WED_TX_BM_CTRL_PAUSE			BIT(28)
+
+#define MTK_WED_TX_BM_BASE				0x084
+
+#define MTK_WED_TX_BM_TKID				0x088
+#define MTK_WED_TX_BM_TKID_START			GENMASK(15, 0)
+#define MTK_WED_TX_BM_TKID_END				GENMASK(31, 16)
+
+#define MTK_WED_TX_BM_BUF_LEN				0x08c
+
+#define MTK_WED_TX_BM_INTF				0x09c
+#define MTK_WED_TX_BM_INTF_TKID				GENMASK(15, 0)
+#define MTK_WED_TX_BM_INTF_TKFIFO_FDEP			GENMASK(23, 16)
+#define MTK_WED_TX_BM_INTF_TKID_VALID			BIT(28)
+#define MTK_WED_TX_BM_INTF_TKID_READ			BIT(29)
+
+#define MTK_WED_TX_BM_DYN_THR				0x0a0
+#define MTK_WED_TX_BM_DYN_THR_LO			GENMASK(6, 0)
+#define MTK_WED_TX_BM_DYN_THR_HI			GENMASK(22, 16)
+
+#define MTK_WED_INT_STATUS				0x200
+#define MTK_WED_INT_MASK				0x204
+
+#define MTK_WED_GLO_CFG					0x208
+#define MTK_WED_GLO_CFG_TX_DMA_EN			BIT(0)
+#define MTK_WED_GLO_CFG_TX_DMA_BUSY			BIT(1)
+#define MTK_WED_GLO_CFG_RX_DMA_EN			BIT(2)
+#define MTK_WED_GLO_CFG_RX_DMA_BUSY			BIT(3)
+#define MTK_WED_GLO_CFG_RX_BT_SIZE			GENMASK(5, 4)
+#define MTK_WED_GLO_CFG_TX_WB_DDONE			BIT(6)
+#define MTK_WED_GLO_CFG_BIG_ENDIAN			BIT(7)
+#define MTK_WED_GLO_CFG_DIS_BT_SIZE_ALIGN		BIT(8)
+#define MTK_WED_GLO_CFG_TX_BT_SIZE_LO			BIT(9)
+#define MTK_WED_GLO_CFG_MULTI_DMA_EN			GENMASK(11, 10)
+#define MTK_WED_GLO_CFG_FIFO_LITTLE_ENDIAN		BIT(12)
+#define MTK_WED_GLO_CFG_MI_DEPTH_RD			GENMASK(21, 13)
+#define MTK_WED_GLO_CFG_TX_BT_SIZE_HI			GENMASK(23, 22)
+#define MTK_WED_GLO_CFG_SW_RESET			BIT(24)
+#define MTK_WED_GLO_CFG_FIRST_TOKEN_ONLY		BIT(26)
+#define MTK_WED_GLO_CFG_OMIT_RX_INFO			BIT(27)
+#define MTK_WED_GLO_CFG_OMIT_TX_INFO			BIT(28)
+#define MTK_WED_GLO_CFG_BYTE_SWAP			BIT(29)
+#define MTK_WED_GLO_CFG_RX_2B_OFFSET			BIT(31)
+
+#define MTK_WED_RESET_IDX				0x20c
+#define MTK_WED_RESET_IDX_TX				GENMASK(3, 0)
+#define MTK_WED_RESET_IDX_RX				GENMASK(17, 16)
+
+#define MTK_WED_TX_MIB(_n)				(0x2a0 + (_n) * 4)
+
+#define MTK_WED_RING_TX(_n)				(0x300 + (_n) * 0x10)
+
+#define MTK_WED_RING_RX(_n)				(0x400 + (_n) * 0x10)
+
+#define MTK_WED_WPDMA_INT_TRIGGER			0x504
+#define MTK_WED_WPDMA_INT_TRIGGER_RX_DONE		BIT(1)
+#define MTK_WED_WPDMA_INT_TRIGGER_TX_DONE		GENMASK(5, 4)
+
+#define MTK_WED_WPDMA_GLO_CFG				0x508
+#define MTK_WED_WPDMA_GLO_CFG_TX_DRV_EN			BIT(0)
+#define MTK_WED_WPDMA_GLO_CFG_TX_DRV_BUSY		BIT(1)
+#define MTK_WED_WPDMA_GLO_CFG_RX_DRV_EN			BIT(2)
+#define MTK_WED_WPDMA_GLO_CFG_RX_DRV_BUSY		BIT(3)
+#define MTK_WED_WPDMA_GLO_CFG_RX_BT_SIZE		GENMASK(5, 4)
+#define MTK_WED_WPDMA_GLO_CFG_TX_WB_DDONE		BIT(6)
+#define MTK_WED_WPDMA_GLO_CFG_BIG_ENDIAN		BIT(7)
+#define MTK_WED_WPDMA_GLO_CFG_DIS_BT_SIZE_ALIGN		BIT(8)
+#define MTK_WED_WPDMA_GLO_CFG_TX_BT_SIZE_LO		BIT(9)
+#define MTK_WED_WPDMA_GLO_CFG_MULTI_DMA_EN		GENMASK(11, 10)
+#define MTK_WED_WPDMA_GLO_CFG_FIFO_LITTLE_ENDIAN	BIT(12)
+#define MTK_WED_WPDMA_GLO_CFG_MI_DEPTH_RD		GENMASK(21, 13)
+#define MTK_WED_WPDMA_GLO_CFG_TX_BT_SIZE_HI		GENMASK(23, 22)
+#define MTK_WED_WPDMA_GLO_CFG_SW_RESET			BIT(24)
+#define MTK_WED_WPDMA_GLO_CFG_FIRST_TOKEN_ONLY		BIT(26)
+#define MTK_WED_WPDMA_GLO_CFG_OMIT_RX_INFO		BIT(27)
+#define MTK_WED_WPDMA_GLO_CFG_OMIT_TX_INFO		BIT(28)
+#define MTK_WED_WPDMA_GLO_CFG_BYTE_SWAP			BIT(29)
+#define MTK_WED_WPDMA_GLO_CFG_RX_2B_OFFSET		BIT(31)
+
+#define MTK_WED_WPDMA_RESET_IDX				0x50c
+#define MTK_WED_WPDMA_RESET_IDX_TX			GENMASK(3, 0)
+#define MTK_WED_WPDMA_RESET_IDX_RX			GENMASK(17, 16)
+
+#define MTK_WED_WPDMA_INT_CTRL				0x520
+#define MTK_WED_WPDMA_INT_CTRL_SUBRT_ADV		BIT(21)
+
+#define MTK_WED_WPDMA_INT_MASK				0x524
+
+#define MTK_WED_PCIE_CFG_BASE				0x560
+
+#define MTK_WED_PCIE_INT_TRIGGER			0x570
+#define MTK_WED_PCIE_INT_TRIGGER_STATUS			BIT(16)
+
+#define MTK_WED_WPDMA_CFG_BASE				0x580
+
+#define MTK_WED_WPDMA_TX_MIB(_n)			(0x5a0 + (_n) * 4)
+#define MTK_WED_WPDMA_TX_COHERENT_MIB(_n)		(0x5d0 + (_n) * 4)
+
+#define MTK_WED_WPDMA_RING_TX(_n)			(0x600 + (_n) * 0x10)
+#define MTK_WED_WPDMA_RING_RX(_n)			(0x700 + (_n) * 0x10)
+#define MTK_WED_WDMA_RING_RX(_n)			(0x900 + (_n) * 0x10)
+#define MTK_WED_WDMA_RX_THRES(_n)			(0x940 + (_n) * 0x4)
+
+#define MTK_WED_WDMA_GLO_CFG				0xa04
+#define MTK_WED_WDMA_GLO_CFG_TX_DRV_EN			BIT(0)
+#define MTK_WED_WDMA_GLO_CFG_RX_DRV_EN			BIT(2)
+#define MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY		BIT(3)
+#define MTK_WED_WDMA_GLO_CFG_BT_SIZE			GENMASK(5, 4)
+#define MTK_WED_WDMA_GLO_CFG_TX_WB_DDONE		BIT(6)
+#define MTK_WED_WDMA_GLO_CFG_RX_DIS_FSM_AUTO_IDLE	BIT(13)
+#define MTK_WED_WDMA_GLO_CFG_WCOMPLETE_SEL		BIT(16)
+#define MTK_WED_WDMA_GLO_CFG_INIT_PHASE_RXDMA_BYPASS	BIT(17)
+#define MTK_WED_WDMA_GLO_CFG_INIT_PHASE_BYPASS		BIT(18)
+#define MTK_WED_WDMA_GLO_CFG_FSM_RETURN_IDLE		BIT(19)
+#define MTK_WED_WDMA_GLO_CFG_WAIT_COHERENT		BIT(20)
+#define MTK_WED_WDMA_GLO_CFG_AXI_W_AFTER_AW		BIT(21)
+#define MTK_WED_WDMA_GLO_CFG_IDLE_DMAD_SUPPLY_SINGLE_W	BIT(22)
+#define MTK_WED_WDMA_GLO_CFG_IDLE_DMAD_SUPPLY		BIT(23)
+#define MTK_WED_WDMA_GLO_CFG_DYNAMIC_SKIP_DMAD_PREP	BIT(24)
+#define MTK_WED_WDMA_GLO_CFG_DYNAMIC_DMAD_RECYCLE	BIT(25)
+#define MTK_WED_WDMA_GLO_CFG_RST_INIT_COMPLETE		BIT(26)
+#define MTK_WED_WDMA_GLO_CFG_RXDRV_CLKGATE_BYPASS	BIT(30)
+
+#define MTK_WED_WDMA_RESET_IDX				0xa08
+#define MTK_WED_WDMA_RESET_IDX_RX			GENMASK(17, 16)
+#define MTK_WED_WDMA_RESET_IDX_DRV			GENMASK(25, 24)
+
+#define MTK_WED_WDMA_INT_TRIGGER			0xa28
+#define MTK_WED_WDMA_INT_TRIGGER_RX_DONE		GENMASK(17, 16)
+
+#define MTK_WED_WDMA_INT_CTRL				0xa2c
+#define MTK_WED_WDMA_INT_CTRL_POLL_SRC_SEL		GENMASK(17, 16)
+
+#define MTK_WED_WDMA_OFFSET0				0xaa4
+#define MTK_WED_WDMA_OFFSET1				0xaa8
+
+#define MTK_WED_WDMA_RX_MIB(_n)				(0xae0 + (_n) * 4)
+#define MTK_WED_WDMA_RX_RECYCLE_MIB(_n)			(0xae8 + (_n) * 4)
+#define MTK_WED_WDMA_RX_PROCESSED_MIB(_n)		(0xaf0 + (_n) * 4)
+
+#define MTK_WED_RING_OFS_BASE				0x00
+#define MTK_WED_RING_OFS_COUNT				0x04
+#define MTK_WED_RING_OFS_CPU_IDX			0x08
+#define MTK_WED_RING_OFS_DMA_IDX			0x0c
+
+#define MTK_WDMA_RING_RX(_n)				(0x100 + (_n) * 0x10)
+
+#define MTK_WDMA_GLO_CFG				0x204
+#define MTK_WDMA_GLO_CFG_RX_INFO_PRERES			GENMASK(28, 26)
+
+#define MTK_WDMA_RESET_IDX				0x208
+#define MTK_WDMA_RESET_IDX_TX				GENMASK(3, 0)
+#define MTK_WDMA_RESET_IDX_RX				GENMASK(17, 16)
+
+#define MTK_WDMA_INT_MASK				0x228
+#define MTK_WDMA_INT_MASK_TX_DONE			GENMASK(3, 0)
+#define MTK_WDMA_INT_MASK_RX_DONE			GENMASK(17, 16)
+#define MTK_WDMA_INT_MASK_TX_DELAY			BIT(28)
+#define MTK_WDMA_INT_MASK_TX_COHERENT			BIT(29)
+#define MTK_WDMA_INT_MASK_RX_DELAY			BIT(30)
+#define MTK_WDMA_INT_MASK_RX_COHERENT			BIT(31)
+
+#define MTK_WDMA_INT_GRP1				0x250
+#define MTK_WDMA_INT_GRP2				0x254
+
+#define MTK_PCIE_MIRROR_MAP(n)				((n) ? 0x4 : 0x0)
+#define MTK_PCIE_MIRROR_MAP_EN				BIT(0)
+#define MTK_PCIE_MIRROR_MAP_WED_ID			BIT(1)
+
+/* DMA channel mapping */
+#define HIFSYS_DMA_AG_MAP				0x008
+
+#endif
diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h
new file mode 100644
index 000000000000..7e00cca06709
--- /dev/null
+++ b/include/linux/soc/mediatek/mtk_wed.h
@@ -0,0 +1,131 @@
+#ifndef __MTK_WED_H
+#define __MTK_WED_H
+
+#include <linux/kernel.h>
+#include <linux/rcupdate.h>
+#include <linux/regmap.h>
+#include <linux/pci.h>
+
+#define MTK_WED_TX_QUEUES		2
+
+struct mtk_wed_hw;
+struct mtk_wdma_desc;
+
+struct mtk_wed_ring {
+	struct mtk_wdma_desc *desc;
+	dma_addr_t desc_phys;
+	int size;
+
+	u32 reg_base;
+	void __iomem *wpdma;
+};
+
+struct mtk_wed_device {
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	const struct mtk_wed_ops *ops;
+	struct device *dev;
+	struct mtk_wed_hw *hw;
+	bool init_done, running;
+	int wdma_idx;
+	int irq;
+
+	struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES];
+	struct mtk_wed_ring txfree_ring;
+	struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES];
+
+	struct {
+		int size;
+		void **pages;
+		struct mtk_wdma_desc *desc;
+		dma_addr_t desc_phys;
+	} buf_ring;
+
+	/* filled by driver: */
+	struct {
+		struct pci_dev *pci_dev;
+
+		u32 wpdma_phys;
+
+		u16 token_start;
+		unsigned int nbuf;
+
+		u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id);
+		int (*offload_enable)(struct mtk_wed_device *wed);
+		void (*offload_disable)(struct mtk_wed_device *wed);
+	} wlan;
+#endif
+};
+
+struct mtk_wed_ops {
+	int (*attach)(struct mtk_wed_device *dev);
+	int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring,
+			     void __iomem *regs);
+	int (*txfree_ring_setup)(struct mtk_wed_device *dev,
+				 void __iomem *regs);
+	void (*detach)(struct mtk_wed_device *dev);
+
+	void (*stop)(struct mtk_wed_device *dev);
+	void (*start)(struct mtk_wed_device *dev, u32 irq_mask);
+	void (*reset_dma)(struct mtk_wed_device *dev);
+
+	u32 (*reg_read)(struct mtk_wed_device *dev, u32 reg);
+	void (*reg_write)(struct mtk_wed_device *dev, u32 reg, u32 val);
+
+	u32 (*irq_get)(struct mtk_wed_device *dev, u32 mask);
+	void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask);
+};
+
+extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops;
+
+static inline int
+mtk_wed_device_attach(struct mtk_wed_device *dev)
+{
+	int ret = -ENODEV;
+
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+	rcu_read_lock();
+	dev->ops = rcu_dereference(mtk_soc_wed_ops);
+	if (dev->ops)
+		ret = dev->ops->attach(dev);
+	else
+		rcu_read_unlock();
+
+	if (ret)
+		dev->ops = NULL;
+#endif
+
+	return ret;
+}
+
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+#define mtk_wed_device_active(_dev) !!(_dev)->ops
+#define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev)
+#define mtk_wed_device_start(_dev, _mask) (_dev)->ops->start(_dev, _mask)
+#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) \
+	(_dev)->ops->tx_ring_setup(_dev, _ring, _regs)
+#define mtk_wed_device_txfree_ring_setup(_dev, _regs) \
+	(_dev)->ops->txfree_ring_setup(_dev, _regs)
+#define mtk_wed_device_reg_read(_dev, _reg) \
+	(_dev)->ops->reg_read(_dev, _reg)
+#define mtk_wed_device_reg_write(_dev, _reg, _val) \
+	(_dev)->ops->reg_write(_dev, _reg, _val)
+#define mtk_wed_device_irq_get(_dev, _mask) \
+	(_dev)->ops->irq_get(_dev, _mask)
+#define mtk_wed_device_irq_set_mask(_dev, _mask) \
+	(_dev)->ops->irq_set_mask(_dev, _mask)
+#else
+static inline bool mtk_wed_device_active(struct mtk_wed_device *dev)
+{
+	return false;
+}
+#define mtk_wed_device_detach(_dev) do {} while (0)
+#define mtk_wed_device_start(_dev, _mask) do {} while (0)
+#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) -ENODEV
+#define mtk_wed_device_txfree_ring_setup(_dev, _ring, _regs) -ENODEV
+#define mtk_wed_device_reg_read(_dev, _reg) 0
+#define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0)
+#define mtk_wed_device_irq_get(_dev, _mask) 0
+#define mtk_wed_device_irq_set_mask(_dev, _mask) do {} while (0)
+#endif
+
+#endif
-- 
cgit v1.2.3


From a333215e10cb5d3b1e0685ca117f0e9452215485 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 5 Apr 2022 21:57:48 +0200
Subject: net: ethernet: mtk_eth_soc: implement flow offloading to WED devices

This allows hardware flow offloading from Ethernet to WLAN on MT7622 SoC

Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_ppe.c         | 18 ++++++++
 drivers/net/ethernet/mediatek/mtk_ppe.h         | 14 ++++---
 drivers/net/ethernet/mediatek/mtk_ppe_offload.c | 56 ++++++++++++++++++++++++-
 drivers/net/ethernet/mediatek/mtk_wed.h         |  7 ++++
 include/linux/netdevice.h                       |  7 ++++
 net/core/dev.c                                  |  4 ++
 6 files changed, 98 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c
index 3ad10c793308..472bcd3269a7 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.c
@@ -329,6 +329,24 @@ int mtk_foe_entry_set_pppoe(struct mtk_foe_entry *entry, int sid)
 	return 0;
 }
 
+int mtk_foe_entry_set_wdma(struct mtk_foe_entry *entry, int wdma_idx, int txq,
+			   int bss, int wcid)
+{
+	struct mtk_foe_mac_info *l2 = mtk_foe_entry_l2(entry);
+	u32 *ib2 = mtk_foe_entry_ib2(entry);
+
+	*ib2 &= ~MTK_FOE_IB2_PORT_MG;
+	*ib2 |= MTK_FOE_IB2_WDMA_WINFO;
+	if (wdma_idx)
+		*ib2 |= MTK_FOE_IB2_WDMA_DEVIDX;
+
+	l2->vlan2 = FIELD_PREP(MTK_FOE_VLAN2_WINFO_BSS, bss) |
+		    FIELD_PREP(MTK_FOE_VLAN2_WINFO_WCID, wcid) |
+		    FIELD_PREP(MTK_FOE_VLAN2_WINFO_RING, txq);
+
+	return 0;
+}
+
 static inline bool mtk_foe_entry_usable(struct mtk_foe_entry *entry)
 {
 	return !(entry->ib1 & MTK_FOE_IB1_STATIC) &&
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h
index 242fb8f2ae65..df8ccaf48171 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.h
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.h
@@ -48,9 +48,9 @@ enum {
 #define MTK_FOE_IB2_DEST_PORT		GENMASK(7, 5)
 #define MTK_FOE_IB2_MULTICAST		BIT(8)
 
-#define MTK_FOE_IB2_WHNAT_QID2		GENMASK(13, 12)
-#define MTK_FOE_IB2_WHNAT_DEVIDX	BIT(16)
-#define MTK_FOE_IB2_WHNAT_NAT		BIT(17)
+#define MTK_FOE_IB2_WDMA_QID2		GENMASK(13, 12)
+#define MTK_FOE_IB2_WDMA_DEVIDX		BIT(16)
+#define MTK_FOE_IB2_WDMA_WINFO		BIT(17)
 
 #define MTK_FOE_IB2_PORT_MG		GENMASK(17, 12)
 
@@ -58,9 +58,9 @@ enum {
 
 #define MTK_FOE_IB2_DSCP		GENMASK(31, 24)
 
-#define MTK_FOE_VLAN2_WHNAT_BSS		GEMMASK(5, 0)
-#define MTK_FOE_VLAN2_WHNAT_WCID	GENMASK(13, 6)
-#define MTK_FOE_VLAN2_WHNAT_RING	GENMASK(15, 14)
+#define MTK_FOE_VLAN2_WINFO_BSS		GENMASK(5, 0)
+#define MTK_FOE_VLAN2_WINFO_WCID	GENMASK(13, 6)
+#define MTK_FOE_VLAN2_WINFO_RING	GENMASK(15, 14)
 
 enum {
 	MTK_FOE_STATE_INVALID,
@@ -281,6 +281,8 @@ int mtk_foe_entry_set_ipv6_tuple(struct mtk_foe_entry *entry,
 int mtk_foe_entry_set_dsa(struct mtk_foe_entry *entry, int port);
 int mtk_foe_entry_set_vlan(struct mtk_foe_entry *entry, int vid);
 int mtk_foe_entry_set_pppoe(struct mtk_foe_entry *entry, int sid);
+int mtk_foe_entry_set_wdma(struct mtk_foe_entry *entry, int wdma_idx, int txq,
+			   int bss, int wcid);
 int mtk_foe_entry_commit(struct mtk_ppe *ppe, struct mtk_foe_entry *entry,
 			 u16 timestamp);
 int mtk_ppe_debugfs_init(struct mtk_ppe *ppe);
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index 7bb1f20002b5..bcf342bb9051 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -10,6 +10,7 @@
 #include <net/pkt_cls.h>
 #include <net/dsa.h>
 #include "mtk_eth_soc.h"
+#include "mtk_wed.h"
 
 struct mtk_flow_data {
 	struct ethhdr eth;
@@ -39,6 +40,7 @@ struct mtk_flow_entry {
 	struct rhash_head node;
 	unsigned long cookie;
 	u16 hash;
+	s8 wed_index;
 };
 
 static const struct rhashtable_params mtk_flow_ht_params = {
@@ -80,6 +82,35 @@ mtk_flow_offload_mangle_eth(const struct flow_action_entry *act, void *eth)
 	memcpy(dest, src, act->mangle.mask ? 2 : 4);
 }
 
+static int
+mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_info *info)
+{
+	struct net_device_path_ctx ctx = {
+		.dev = dev,
+		.daddr = addr,
+	};
+	struct net_device_path path = {};
+
+	if (!IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED))
+		return -1;
+
+	if (!dev->netdev_ops->ndo_fill_forward_path)
+		return -1;
+
+	if (dev->netdev_ops->ndo_fill_forward_path(&ctx, &path))
+		return -1;
+
+	if (path.type != DEV_PATH_MTK_WDMA)
+		return -1;
+
+	info->wdma_idx = path.mtk_wdma.wdma_idx;
+	info->queue = path.mtk_wdma.queue;
+	info->bss = path.mtk_wdma.bss;
+	info->wcid = path.mtk_wdma.wcid;
+
+	return 0;
+}
+
 
 static int
 mtk_flow_mangle_ports(const struct flow_action_entry *act,
@@ -149,10 +180,20 @@ mtk_flow_get_dsa_port(struct net_device **dev)
 
 static int
 mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe,
-			   struct net_device *dev)
+			   struct net_device *dev, const u8 *dest_mac,
+			   int *wed_index)
 {
+	struct mtk_wdma_info info = {};
 	int pse_port, dsa_port;
 
+	if (mtk_flow_get_wdma_info(dev, dest_mac, &info) == 0) {
+		mtk_foe_entry_set_wdma(foe, info.wdma_idx, info.queue, info.bss,
+				       info.wcid);
+		pse_port = 3;
+		*wed_index = info.wdma_idx;
+		goto out;
+	}
+
 	dsa_port = mtk_flow_get_dsa_port(&dev);
 	if (dsa_port >= 0)
 		mtk_foe_entry_set_dsa(foe, dsa_port);
@@ -164,6 +205,7 @@ mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe,
 	else
 		return -EOPNOTSUPP;
 
+out:
 	mtk_foe_entry_set_pse_port(foe, pse_port);
 
 	return 0;
@@ -179,6 +221,7 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f)
 	struct net_device *odev = NULL;
 	struct mtk_flow_entry *entry;
 	int offload_type = 0;
+	int wed_index = -1;
 	u16 addr_type = 0;
 	u32 timestamp;
 	u8 l4proto = 0;
@@ -326,10 +369,14 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f)
 	if (data.pppoe.num == 1)
 		mtk_foe_entry_set_pppoe(&foe, data.pppoe.sid);
 
-	err = mtk_flow_set_output_device(eth, &foe, odev);
+	err = mtk_flow_set_output_device(eth, &foe, odev, data.eth.h_dest,
+					 &wed_index);
 	if (err)
 		return err;
 
+	if (wed_index >= 0 && (err = mtk_wed_flow_add(wed_index)) < 0)
+		return err;
+
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return -ENOMEM;
@@ -343,6 +390,7 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f)
 	}
 
 	entry->hash = hash;
+	entry->wed_index = wed_index;
 	err = rhashtable_insert_fast(&eth->flow_table, &entry->node,
 				     mtk_flow_ht_params);
 	if (err < 0)
@@ -353,6 +401,8 @@ clear_flow:
 	mtk_foe_entry_clear(&eth->ppe, hash);
 free:
 	kfree(entry);
+	if (wed_index >= 0)
+	    mtk_wed_flow_remove(wed_index);
 	return err;
 }
 
@@ -369,6 +419,8 @@ mtk_flow_offload_destroy(struct mtk_eth *eth, struct flow_cls_offload *f)
 	mtk_foe_entry_clear(&eth->ppe, entry->hash);
 	rhashtable_remove_fast(&eth->flow_table, &entry->node,
 			       mtk_flow_ht_params);
+	if (entry->wed_index >= 0)
+		mtk_wed_flow_remove(entry->wed_index);
 	kfree(entry);
 
 	return 0;
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.h b/drivers/net/ethernet/mediatek/mtk_wed.h
index 404c9a9b130d..981ec613f4b0 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.h
+++ b/drivers/net/ethernet/mediatek/mtk_wed.h
@@ -7,6 +7,7 @@
 #include <linux/soc/mediatek/mtk_wed.h>
 #include <linux/debugfs.h>
 #include <linux/regmap.h>
+#include <linux/netdevice.h>
 
 struct mtk_eth;
 
@@ -27,6 +28,12 @@ struct mtk_wed_hw {
 	int index;
 };
 
+struct mtk_wdma_info {
+	u8 wdma_idx;
+	u8 queue;
+	u16 wcid;
+	u8 bss;
+};
 
 #ifdef CONFIG_NET_MEDIATEK_SOC_WED
 static inline void
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b6a1e7f643da..7b2a0b739684 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -862,6 +862,7 @@ enum net_device_path_type {
 	DEV_PATH_BRIDGE,
 	DEV_PATH_PPPOE,
 	DEV_PATH_DSA,
+	DEV_PATH_MTK_WDMA,
 };
 
 struct net_device_path {
@@ -887,6 +888,12 @@ struct net_device_path {
 			int port;
 			u16 proto;
 		} dsa;
+		struct {
+			u8 wdma_idx;
+			u8 queue;
+			u16 wcid;
+			u8 bss;
+		} mtk_wdma;
 	};
 };
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 2ec17358d7b4..d5a362d53b34 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -701,6 +701,10 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
 		if (WARN_ON_ONCE(last_dev == ctx.dev))
 			return -1;
 	}
+
+	if (!ctx.dev)
+		return ret;
+
 	path = dev_fwd_path(stack);
 	if (!path)
 		return -1;
-- 
cgit v1.2.3


From 3e9c4584336149146fe15cb5703fc10a2ca2d2a0 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Thu, 24 Mar 2022 11:30:25 +0100
Subject: gpu: host1x: Do not use mapping cache for job submissions

Buffer mappings used in job submissions are usually small and not
rapidly reused as opposed to framebuffers (which are usually large and
rapidly reused, for example when page-flipping between double-buffered
framebuffers). Avoid going through the mapping cache for these buffers
since the cache would also lead to leaks if nobody is ever releasing
the cache's last reference. For DRM/KMS these last references are
dropped when the framebuffers are removed and therefore no longer
needed.

While at it, also add a note about the need to explicitly remove the
final reference to the mapping in the cache.

Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/host1x/job.c | 4 ++--
 include/linux/host1x.h   | 5 +++++
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 5e8c183167b7..b2761aa03b95 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -175,7 +175,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 			goto unpin;
 		}
 
-		map = host1x_bo_pin(dev, bo, direction, &client->cache);
+		map = host1x_bo_pin(dev, bo, direction, NULL);
 		if (IS_ERR(map)) {
 			err = PTR_ERR(map);
 			goto unpin;
@@ -222,7 +222,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 			goto unpin;
 		}
 
-		map = host1x_bo_pin(host->dev, g->bo, DMA_TO_DEVICE, &host->cache);
+		map = host1x_bo_pin(host->dev, g->bo, DMA_TO_DEVICE, NULL);
 		if (IS_ERR(map)) {
 			err = PTR_ERR(map);
 			goto unpin;
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 00278853eadf..c0bf4e581fe9 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -31,6 +31,11 @@ u64 host1x_get_dma_mask(struct host1x *host1x);
  * struct host1x_bo_cache - host1x buffer object cache
  * @mappings: list of mappings
  * @lock: synchronizes accesses to the list of mappings
+ *
+ * Note that entries are not periodically evicted from this cache and instead need to be
+ * explicitly released. This is used primarily for DRM/KMS where the cache's reference is
+ * released when the last reference to a buffer object represented by a mapping in this
+ * cache is dropped.
  */
 struct host1x_bo_cache {
 	struct list_head mappings;
-- 
cgit v1.2.3


From a60707d74bd1d119cf7bcc5101cda912fc46d5e3 Mon Sep 17 00:00:00 2001
From: Zhen Ni <nizhen@uniontech.com>
Date: Tue, 15 Feb 2022 19:45:57 +0800
Subject: sched: Move child_runs_first sysctls to fair.c

move child_runs_first sysctls to fair.c and use the new
register_sysctl_init() to register the sysctl interface.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sched/sysctl.h |  2 --
 kernel/sched/fair.c          | 19 +++++++++++++++++++
 kernel/sched/sched.h         |  2 ++
 kernel/sysctl.c              |  7 -------
 4 files changed, 21 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index c1076b5e17fb..1d2ff3cd1728 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -14,8 +14,6 @@ extern unsigned long sysctl_hung_task_timeout_secs;
 enum { sysctl_hung_task_timeout_secs = 0 };
 #endif
 
-extern unsigned int sysctl_sched_child_runs_first;
-
 enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_NONE,
 	SCHED_TUNABLESCALING_LOG,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d4bd299d67ab..788b1d6a3248 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -109,6 +109,25 @@ static unsigned int sched_nr_latency = 8;
  * parent will (try to) run first.
  */
 unsigned int sysctl_sched_child_runs_first __read_mostly;
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_child_runs_first_sysctls[] = {
+	{
+		.procname       = "sched_child_runs_first",
+		.data           = &sysctl_sched_child_runs_first,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{}
+};
+
+static int __init sched_child_runs_first_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_child_runs_first_sysctls);
+	return 0;
+}
+late_initcall(sched_child_runs_first_sysctl_init);
+#endif
 
 /*
  * SCHED_OTHER wake-up granularity.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 58263f90c559..767fc1de9646 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -108,6 +108,8 @@ extern __read_mostly int scheduler_running;
 extern unsigned long calc_load_update;
 extern atomic_long_t calc_load_tasks;
 
+extern unsigned int sysctl_sched_child_runs_first;
+
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 830aaf8ca08e..6bbb8e1af675 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1659,13 +1659,6 @@ int proc_do_static_key(struct ctl_table *table, int write,
 }
 
 static struct ctl_table kern_table[] = {
-	{
-		.procname	= "sched_child_runs_first",
-		.data		= &sysctl_sched_child_runs_first,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname	= "sched_schedstats",
-- 
cgit v1.2.3


From f5ef06d58be8311a9425e6a54a053ecb350952f3 Mon Sep 17 00:00:00 2001
From: Zhen Ni <nizhen@uniontech.com>
Date: Tue, 15 Feb 2022 19:45:58 +0800
Subject: sched: Move schedstats sysctls to core.c

move schedstats sysctls to core.c and use the new
register_sysctl_init() to register the sysctl interface.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sched/sysctl.h |  2 --
 kernel/sched/core.c          | 22 +++++++++++++++++++++-
 kernel/sysctl.c              | 11 -----------
 3 files changed, 21 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 1d2ff3cd1728..6c7a6850559b 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -64,8 +64,6 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
 int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 extern unsigned int sysctl_sched_energy_aware;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d575b4914925..04440da5955f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4430,7 +4430,7 @@ out:
 __setup("schedstats=", setup_schedstats);
 
 #ifdef CONFIG_PROC_SYSCTL
-int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
+static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
@@ -4449,6 +4449,26 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 		set_schedstats(state);
 	return err;
 }
+
+static struct ctl_table sched_schedstats_sysctls[] = {
+	{
+		.procname       = "sched_schedstats",
+		.data           = NULL,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_schedstats,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{}
+};
+
+static int __init sched_schedstats_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_schedstats_sysctls);
+	return 0;
+}
+late_initcall(sched_schedstats_sysctl_init);
 #endif /* CONFIG_PROC_SYSCTL */
 #endif /* CONFIG_SCHEDSTATS */
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6bbb8e1af675..fc0eeca20718 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1659,17 +1659,6 @@ int proc_do_static_key(struct ctl_table *table, int write,
 }
 
 static struct ctl_table kern_table[] = {
-#ifdef CONFIG_SCHEDSTATS
-	{
-		.procname	= "sched_schedstats",
-		.data		= NULL,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sysctl_schedstats,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif /* CONFIG_SCHEDSTATS */
 #ifdef CONFIG_TASK_DELAY_ACCT
 	{
 		.procname	= "task_delayacct",
-- 
cgit v1.2.3


From d9ab0e63fa7f8405fbb19e28c5191e0880a7f2db Mon Sep 17 00:00:00 2001
From: Zhen Ni <nizhen@uniontech.com>
Date: Tue, 15 Feb 2022 19:45:59 +0800
Subject: sched: Move rt_period/runtime sysctls to rt.c

move rt_period/runtime sysctls to rt.c and use the new
register_sysctl_init() to register the sysctl interface.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sched/sysctl.h | 11 -----------
 kernel/rcu/rcu.h             |  2 ++
 kernel/sched/core.c          | 13 -------------
 kernel/sched/rt.c            | 43 ++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/sched.h         |  4 ++++
 kernel/sysctl.c              | 14 --------------
 6 files changed, 48 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 6c7a6850559b..4391c1307945 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -31,15 +31,6 @@ extern int sysctl_numa_balancing_mode;
 #define sysctl_numa_balancing_mode	0
 #endif
 
-/*
- *  control realtime throttling:
- *
- *  /proc/sys/kernel/sched_rt_period_us
- *  /proc/sys/kernel/sched_rt_runtime_us
- */
-extern unsigned int sysctl_sched_rt_period;
-extern int sysctl_sched_rt_runtime;
-
 extern unsigned int sysctl_sched_dl_period_max;
 extern unsigned int sysctl_sched_dl_period_min;
 
@@ -58,8 +49,6 @@ extern int sched_rr_timeslice;
 
 int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
 int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
 int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 24b5f2c2de87..7812c740b3bf 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -23,6 +23,8 @@
 #define RCU_SEQ_CTR_SHIFT	2
 #define RCU_SEQ_STATE_MASK	((1 << RCU_SEQ_CTR_SHIFT) - 1)
 
+extern int sysctl_sched_rt_runtime;
+
 /*
  * Return the counter portion of a sequence number previously returned
  * by rcu_seq_snap() or rcu_seq_current().
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 04440da5955f..774f3229db37 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -145,12 +145,6 @@ const_debug unsigned int sysctl_sched_nr_migrate = 8;
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 #endif
 
-/*
- * period over which we measure -rt task CPU usage in us.
- * default: 1s
- */
-unsigned int sysctl_sched_rt_period = 1000000;
-
 __read_mostly int scheduler_running;
 
 #ifdef CONFIG_SCHED_CORE
@@ -444,13 +438,6 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
 
 #endif /* CONFIG_SCHED_CORE */
 
-/*
- * part of the period that we allow rt tasks to run in us.
- * default: 0.95s
- */
-int sysctl_sched_rt_runtime = 950000;
-
-
 /*
  * Serialization rules:
  *
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a32c46889af8..5663bb5ff890 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -13,6 +13,47 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
 struct rt_bandwidth def_rt_bandwidth;
 
+/*
+ * period over which we measure -rt task CPU usage in us.
+ * default: 1s
+ */
+unsigned int sysctl_sched_rt_period = 1000000;
+
+/*
+ * part of the period that we allow rt tasks to run in us.
+ * default: 0.95s
+ */
+int sysctl_sched_rt_runtime = 950000;
+
+static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_rt_sysctls[] = {
+	{
+		.procname       = "sched_rt_period_us",
+		.data           = &sysctl_sched_rt_period,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sched_rt_handler,
+	},
+	{
+		.procname       = "sched_rt_runtime_us",
+		.data           = &sysctl_sched_rt_runtime,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = sched_rt_handler,
+	},
+	{}
+};
+
+static int __init sched_rt_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_rt_sysctls);
+	return 0;
+}
+late_initcall(sched_rt_sysctl_init);
+#endif
+
 static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
@@ -2925,7 +2966,7 @@ static void sched_rt_do_global(void)
 	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 }
 
-int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int old_period, old_runtime;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 767fc1de9646..3b406c78a8e9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -114,6 +114,10 @@ extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
 extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
+
+extern unsigned int sysctl_sched_rt_period;
+extern int sysctl_sched_rt_runtime;
+
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index fc0eeca20718..029bfe06c68d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1681,20 +1681,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-	{
-		.procname	= "sched_rt_period_us",
-		.data		= &sysctl_sched_rt_period,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_rt_handler,
-	},
-	{
-		.procname	= "sched_rt_runtime_us",
-		.data		= &sysctl_sched_rt_runtime,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= sched_rt_handler,
-	},
 	{
 		.procname	= "sched_deadline_period_max_us",
 		.data		= &sysctl_sched_dl_period_max,
-- 
cgit v1.2.3


From 84227c12888b1105725cd2de14705b029bcbb4b2 Mon Sep 17 00:00:00 2001
From: Zhen Ni <nizhen@uniontech.com>
Date: Tue, 15 Feb 2022 19:46:00 +0800
Subject: sched: Move deadline_period sysctls to deadline.c

move deadline_period sysctls to deadline.c and use the new
register_sysctl_init() to register the sysctl interface.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sched/sysctl.h |  3 ---
 kernel/sched/deadline.c      | 42 ++++++++++++++++++++++++++++++++++--------
 kernel/sysctl.c              | 14 --------------
 3 files changed, 34 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 4391c1307945..7da9b94c5e1c 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -31,9 +31,6 @@ extern int sysctl_numa_balancing_mode;
 #define sysctl_numa_balancing_mode	0
 #endif
 
-extern unsigned int sysctl_sched_dl_period_max;
-extern unsigned int sysctl_sched_dl_period_min;
-
 #ifdef CONFIG_UCLAMP_TASK
 extern unsigned int sysctl_sched_uclamp_util_min;
 extern unsigned int sysctl_sched_uclamp_util_max;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fb4255ae0b2c..82e10b74a7b2 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,40 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 
+/*
+ * Default limits for DL period; on the top end we guard against small util
+ * tasks still getting ridiculously long effective runtimes, on the bottom end we
+ * guard against timer DoS.
+ */
+static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
+static unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_dl_sysctls[] = {
+	{
+		.procname       = "sched_deadline_period_max_us",
+		.data           = &sysctl_sched_dl_period_max,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{
+		.procname       = "sched_deadline_period_min_us",
+		.data           = &sysctl_sched_dl_period_min,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{}
+};
+
+static int __init sched_dl_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_dl_sysctls);
+	return 0;
+}
+late_initcall(sched_dl_sysctl_init);
+#endif
+
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
 	return container_of(dl_se, struct task_struct, dl);
@@ -2879,14 +2913,6 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 	attr->sched_flags |= dl_se->flags;
 }
 
-/*
- * Default limits for DL period; on the top end we guard against small util
- * tasks still getting ridiculously long effective runtimes, on the bottom end we
- * guard against timer DoS.
- */
-unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
-unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
-
 /*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 029bfe06c68d..2c8c75e11a37 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1681,20 +1681,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-	{
-		.procname	= "sched_deadline_period_max_us",
-		.data		= &sysctl_sched_dl_period_max,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "sched_deadline_period_min_us",
-		.data		= &sysctl_sched_dl_period_min,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "sched_rr_timeslice_ms",
 		.data		= &sysctl_sched_rr_timeslice,
-- 
cgit v1.2.3


From dafd7a9dad22fadcb290b24dff54e2eae3b89776 Mon Sep 17 00:00:00 2001
From: Zhen Ni <nizhen@uniontech.com>
Date: Tue, 15 Feb 2022 19:46:01 +0800
Subject: sched: Move rr_timeslice sysctls to rt.c

move rr_timeslice sysctls to rt.c and use the new
register_sysctl_init() to register the sysctl interface.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sched/sysctl.h |  5 -----
 kernel/sched/rt.c            | 13 +++++++++++--
 kernel/sched/sched.h         |  1 +
 kernel/sysctl.c              |  7 -------
 4 files changed, 12 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 7da9b94c5e1c..3d307e512d1f 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -41,11 +41,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
 extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #endif
 
-extern int sysctl_sched_rr_timeslice;
-extern int sched_rr_timeslice;
-
-int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
 int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
 int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 5663bb5ff890..71791be36065 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -5,7 +5,7 @@
  */
 
 int sched_rr_timeslice = RR_TIMESLICE;
-int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
 /* More than 4 hours if BW_SHIFT equals 20. */
 static const u64 max_rt_runtime = MAX_BW;
 
@@ -27,6 +27,8 @@ int sysctl_sched_rt_runtime = 950000;
 
 static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
+static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
 #ifdef CONFIG_SYSCTL
 static struct ctl_table sched_rt_sysctls[] = {
 	{
@@ -43,6 +45,13 @@ static struct ctl_table sched_rt_sysctls[] = {
 		.mode           = 0644,
 		.proc_handler   = sched_rt_handler,
 	},
+	{
+		.procname       = "sched_rr_timeslice_ms",
+		.data           = &sysctl_sched_rr_timeslice,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = sched_rr_handler,
+	},
 	{}
 };
 
@@ -3005,7 +3014,7 @@ undo:
 	return ret;
 }
 
-int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3b406c78a8e9..ae0f6e5a76f9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -117,6 +117,7 @@ extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
 
 extern unsigned int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
+extern int sched_rr_timeslice;
 
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2c8c75e11a37..b074f70a3e11 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1681,13 +1681,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-	{
-		.procname	= "sched_rr_timeslice_ms",
-		.data		= &sysctl_sched_rr_timeslice,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= sched_rr_handler,
-	},
 #ifdef CONFIG_UCLAMP_TASK
 	{
 		.procname	= "sched_util_clamp_min",
-- 
cgit v1.2.3


From 3267e0156c3341ac25b37a0f60551cdae1634b60 Mon Sep 17 00:00:00 2001
From: Zhen Ni <nizhen@uniontech.com>
Date: Tue, 15 Feb 2022 19:46:02 +0800
Subject: sched: Move uclamp_util sysctls to core.c

move uclamp_util sysctls to core.c and use the new
register_sysctl_init() to register the sysctl interface.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sched/sysctl.h |  8 --------
 kernel/sched/core.c          | 48 ++++++++++++++++++++++++++++++++++----------
 kernel/sysctl.c              | 23 ---------------------
 3 files changed, 37 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 3d307e512d1f..0934b21a57a4 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -31,18 +31,10 @@ extern int sysctl_numa_balancing_mode;
 #define sysctl_numa_balancing_mode	0
 #endif
 
-#ifdef CONFIG_UCLAMP_TASK
-extern unsigned int sysctl_sched_uclamp_util_min;
-extern unsigned int sysctl_sched_uclamp_util_max;
-extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
-#endif
-
 #ifdef CONFIG_CFS_BANDWIDTH
 extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #endif
 
-int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
 int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 774f3229db37..ef31751c5799 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1306,10 +1306,10 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 static DEFINE_MUTEX(uclamp_mutex);
 
 /* Max allowed minimum utilization */
-unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
+static unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
 
 /* Max allowed maximum utilization */
-unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
+static unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 
 /*
  * By default RT tasks run at the maximum performance point/capacity of the
@@ -1326,7 +1326,7 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
  * This knob will not override the system default sched_util_clamp_min defined
  * above.
  */
-unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
+static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
 
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
@@ -1779,7 +1779,7 @@ static void uclamp_update_root_tg(void)
 static void uclamp_update_root_tg(void) { }
 #endif
 
-int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
@@ -4436,8 +4436,12 @@ static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 		set_schedstats(state);
 	return err;
 }
+#endif /* CONFIG_PROC_SYSCTL */
+#endif /* CONFIG_SCHEDSTATS */
 
-static struct ctl_table sched_schedstats_sysctls[] = {
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_core_sysctls[] = {
+#ifdef CONFIG_SCHEDSTATS
 	{
 		.procname       = "sched_schedstats",
 		.data           = NULL,
@@ -4447,17 +4451,39 @@ static struct ctl_table sched_schedstats_sysctls[] = {
 		.extra1         = SYSCTL_ZERO,
 		.extra2         = SYSCTL_ONE,
 	},
+#endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_UCLAMP_TASK
+	{
+		.procname       = "sched_util_clamp_min",
+		.data           = &sysctl_sched_uclamp_util_min,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+	{
+		.procname       = "sched_util_clamp_max",
+		.data           = &sysctl_sched_uclamp_util_max,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+	{
+		.procname       = "sched_util_clamp_min_rt_default",
+		.data           = &sysctl_sched_uclamp_util_min_rt_default,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+#endif /* CONFIG_UCLAMP_TASK */
 	{}
 };
-
-static int __init sched_schedstats_sysctl_init(void)
+static int __init sched_core_sysctl_init(void)
 {
-	register_sysctl_init("kernel", sched_schedstats_sysctls);
+	register_sysctl_init("kernel", sched_core_sysctls);
 	return 0;
 }
-late_initcall(sched_schedstats_sysctl_init);
-#endif /* CONFIG_PROC_SYSCTL */
-#endif /* CONFIG_SCHEDSTATS */
+late_initcall(sched_core_sysctl_init);
+#endif /* CONFIG_SYSCTL */
 
 /*
  * fork()/clone()-time setup:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b074f70a3e11..a48c090d57f9 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1681,29 +1681,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-#ifdef CONFIG_UCLAMP_TASK
-	{
-		.procname	= "sched_util_clamp_min",
-		.data		= &sysctl_sched_uclamp_util_min,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sysctl_sched_uclamp_handler,
-	},
-	{
-		.procname	= "sched_util_clamp_max",
-		.data		= &sysctl_sched_uclamp_util_max,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sysctl_sched_uclamp_handler,
-	},
-	{
-		.procname	= "sched_util_clamp_min_rt_default",
-		.data		= &sysctl_sched_uclamp_util_min_rt_default,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sysctl_sched_uclamp_handler,
-	},
-#endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
 		.procname	= "sched_cfs_bandwidth_slice_us",
-- 
cgit v1.2.3


From d4ae80ffa64f87b9c355692b680b603add084e96 Mon Sep 17 00:00:00 2001
From: Zhen Ni <nizhen@uniontech.com>
Date: Tue, 15 Feb 2022 19:46:03 +0800
Subject: sched: Move cfs_bandwidth_slice sysctls to fair.c

move cfs_bandwidth_slice sysctls to fair.c and use the
new register_sysctl_init() to register the sysctl interface.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sched/sysctl.h |  4 ----
 kernel/sched/fair.c          | 51 +++++++++++++++++++++++++++-----------------
 kernel/sysctl.c              | 10 ---------
 3 files changed, 31 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 0934b21a57a4..198f77c8a873 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -31,10 +31,6 @@ extern int sysctl_numa_balancing_mode;
 #define sysctl_numa_balancing_mode	0
 #endif
 
-#ifdef CONFIG_CFS_BANDWIDTH
-extern unsigned int sysctl_sched_cfs_bandwidth_slice;
-#endif
-
 int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 788b1d6a3248..265bf7a75a37 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -109,25 +109,6 @@ static unsigned int sched_nr_latency = 8;
  * parent will (try to) run first.
  */
 unsigned int sysctl_sched_child_runs_first __read_mostly;
-#ifdef CONFIG_SYSCTL
-static struct ctl_table sched_child_runs_first_sysctls[] = {
-	{
-		.procname       = "sched_child_runs_first",
-		.data           = &sysctl_sched_child_runs_first,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
-	{}
-};
-
-static int __init sched_child_runs_first_sysctl_init(void)
-{
-	register_sysctl_init("kernel", sched_child_runs_first_sysctls);
-	return 0;
-}
-late_initcall(sched_child_runs_first_sysctl_init);
-#endif
 
 /*
  * SCHED_OTHER wake-up granularity.
@@ -192,7 +173,37 @@ int __weak arch_asym_cpu_priority(int cpu)
  *
  * (default: 5 msec, units: microseconds)
  */
-unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
+static unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
+#endif
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_fair_sysctls[] = {
+	{
+		.procname       = "sched_child_runs_first",
+		.data           = &sysctl_sched_child_runs_first,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#ifdef CONFIG_CFS_BANDWIDTH
+	{
+		.procname       = "sched_cfs_bandwidth_slice_us",
+		.data           = &sysctl_sched_cfs_bandwidth_slice,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1         = SYSCTL_ONE,
+	},
+#endif
+	{}
+};
+
+static int __init sched_fair_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_fair_sysctls);
+	return 0;
+}
+late_initcall(sched_fair_sysctl_init);
 #endif
 
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index a48c090d57f9..10ab81c7c457 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1681,16 +1681,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-#ifdef CONFIG_CFS_BANDWIDTH
-	{
-		.procname	= "sched_cfs_bandwidth_slice_us",
-		.data		= &sysctl_sched_cfs_bandwidth_slice,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ONE,
-	},
-#endif
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 	{
 		.procname	= "sched_energy_aware",
-- 
cgit v1.2.3


From 8a0441415b3f9b9a920a6a5086580ea3daa7b884 Mon Sep 17 00:00:00 2001
From: Zhen Ni <nizhen@uniontech.com>
Date: Tue, 15 Feb 2022 19:46:04 +0800
Subject: sched: Move energy_aware sysctls to topology.c

move energy_aware sysctls to topology.c and use the new
register_sysctl_init() to register the sysctl interface.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sched/sysctl.h |  6 ------
 kernel/sched/topology.c      | 25 +++++++++++++++++++++++--
 kernel/sysctl.c              | 11 -----------
 3 files changed, 23 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 198f77c8a873..e650946816d0 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -34,10 +34,4 @@ extern int sysctl_numa_balancing_mode;
 int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
 
-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
-extern unsigned int sysctl_sched_energy_aware;
-int sched_energy_aware_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-#endif
-
 #endif /* _LINUX_SCHED_SYSCTL_H */
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 810750e62118..05b6c2ad90b9 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -206,7 +206,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 DEFINE_STATIC_KEY_FALSE(sched_energy_present);
-unsigned int sysctl_sched_energy_aware = 1;
+static unsigned int sysctl_sched_energy_aware = 1;
 DEFINE_MUTEX(sched_energy_mutex);
 bool sched_energy_update;
 
@@ -220,7 +220,7 @@ void rebuild_sched_domains_energy(void)
 }
 
 #ifdef CONFIG_PROC_SYSCTL
-int sched_energy_aware_handler(struct ctl_table *table, int write,
+static int sched_energy_aware_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, state;
@@ -237,6 +237,27 @@ int sched_energy_aware_handler(struct ctl_table *table, int write,
 
 	return ret;
 }
+
+static struct ctl_table sched_energy_aware_sysctls[] = {
+	{
+		.procname       = "sched_energy_aware",
+		.data           = &sysctl_sched_energy_aware,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sched_energy_aware_handler,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{}
+};
+
+static int __init sched_energy_aware_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_energy_aware_sysctls);
+	return 0;
+}
+
+late_initcall(sched_energy_aware_sysctl_init);
 #endif
 
 static void free_pd(struct perf_domain *pd)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 10ab81c7c457..8241c5401ee8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1681,17 +1681,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
-	{
-		.procname	= "sched_energy_aware",
-		.data		= &sysctl_sched_energy_aware,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_energy_aware_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname	= "prove_locking",
-- 
cgit v1.2.3


From 06d177662fb86b80c7fc2290667b9a14cb0bd925 Mon Sep 17 00:00:00 2001
From: tangmeng <tangmeng@uniontech.com>
Date: Thu, 17 Feb 2022 12:23:21 +0800
Subject: kernel/reboot: move reboot sysctls to its own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we
just care about the core logic.

All filesystem syctls now get reviewed by fs folks. This commit
follows the commit of fs, move the poweroff_cmd and ctrl-alt-del
sysctls to its own file, kernel/reboot.c.

Signed-off-by: tangmeng <tangmeng@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/reboot.h |  4 ----
 kernel/reboot.c        | 34 ++++++++++++++++++++++++++++++++--
 kernel/sysctl.c        | 14 --------------
 3 files changed, 32 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index af907a3d68d1..a2429648d831 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -71,12 +71,8 @@ extern void kernel_restart(char *cmd);
 extern void kernel_halt(void);
 extern void kernel_power_off(void);
 
-extern int C_A_D; /* for sysctl */
 void ctrl_alt_del(void);
 
-#define POWEROFF_CMD_PATH_LEN	256
-extern char poweroff_cmd[POWEROFF_CMD_PATH_LEN];
-
 extern void orderly_poweroff(bool force);
 extern void orderly_reboot(void);
 void hw_protection_shutdown(const char *reason, int ms_until_forced);
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 6bcc5d6a6572..ed4e6dfb7d44 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -23,7 +23,7 @@
  * this indicates whether you can reboot with ctrl-alt-del: the default is yes
  */
 
-int C_A_D = 1;
+static int C_A_D = 1;
 struct pid *cad_pid;
 EXPORT_SYMBOL(cad_pid);
 
@@ -417,9 +417,37 @@ void ctrl_alt_del(void)
 		kill_cad_pid(SIGINT, 1);
 }
 
-char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
+#define POWEROFF_CMD_PATH_LEN  256
+static char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
 static const char reboot_cmd[] = "/sbin/reboot";
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kern_reboot_table[] = {
+	{
+		.procname       = "poweroff_cmd",
+		.data           = &poweroff_cmd,
+		.maxlen         = POWEROFF_CMD_PATH_LEN,
+		.mode           = 0644,
+		.proc_handler   = proc_dostring,
+	},
+	{
+		.procname       = "ctrl-alt-del",
+		.data           = &C_A_D,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{ }
+};
+
+static void __init kernel_reboot_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_reboot_table);
+}
+#else
+#define kernel_reboot_sysctls_init() do { } while (0)
+#endif /* CONFIG_SYSCTL */
+
 static int run_cmd(const char *cmd)
 {
 	char **argv;
@@ -886,6 +914,8 @@ static int __init reboot_ksysfs_init(void)
 		return ret;
 	}
 
+	kernel_reboot_sysctls_init();
+
 	return 0;
 }
 late_initcall(reboot_ksysfs_init);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8241c5401ee8..5e43569ce2be 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1798,13 +1798,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-	{
-		.procname	= "ctrl-alt-del",
-		.data		= &C_A_D,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #ifdef CONFIG_FUNCTION_TRACER
 	{
 		.procname	= "ftrace_enabled",
@@ -2111,13 +2104,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-	{
-		.procname	= "poweroff_cmd",
-		.data		= &poweroff_cmd,
-		.maxlen		= POWEROFF_CMD_PATH_LEN,
-		.mode		= 0644,
-		.proc_handler	= proc_dostring,
-	},
 #ifdef CONFIG_KEYS
 	{
 		.procname	= "keys",
-- 
cgit v1.2.3


From 43fe219aa56a2fdd8f0623c9470a32b14b0617a5 Mon Sep 17 00:00:00 2001
From: sujiaxun <sujiaxun@uniontech.com>
Date: Thu, 17 Feb 2022 18:51:48 -0800
Subject: mm: move oom_kill sysctls to their own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we just
care about the core logic.

So move the oom_kill sysctls to their own file, mm/oom_kill.c

[sfr@canb.auug.org.au: null-terminate the array]
  Link: https://lkml.kernel.org/r/20220216193202.28838626@canb.auug.org.au

Link: https://lkml.kernel.org/r/20220215093203.31032-1-sujiaxun@uniontech.com
Signed-off-by: sujiaxun <sujiaxun@uniontech.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/oom.h |  4 ----
 kernel/sysctl.c     | 23 -----------------------
 mm/oom_kill.c       | 38 +++++++++++++++++++++++++++++++++++---
 3 files changed, 35 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/oom.h b/include/linux/oom.h
index 2db9a1432511..02d1e7bbd8cd 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -123,8 +123,4 @@ extern void oom_killer_enable(void);
 
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
-/* sysctls */
-extern int sysctl_oom_dump_tasks;
-extern int sysctl_oom_kill_allocating_task;
-extern int sysctl_panic_on_oom;
 #endif /* _INCLUDE_LINUX_OOM_H */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 5e43569ce2be..a21c0ea396f3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2241,29 +2241,6 @@ static struct ctl_table vm_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
-	{
-		.procname	= "panic_on_oom",
-		.data		= &sysctl_panic_on_oom,
-		.maxlen		= sizeof(sysctl_panic_on_oom),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_TWO,
-	},
-	{
-		.procname	= "oom_kill_allocating_task",
-		.data		= &sysctl_oom_kill_allocating_task,
-		.maxlen		= sizeof(sysctl_oom_kill_allocating_task),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "oom_dump_tasks",
-		.data		= &sysctl_oom_dump_tasks,
-		.maxlen		= sizeof(sysctl_oom_dump_tasks),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "overcommit_ratio",
 		.data		= &sysctl_overcommit_ratio,
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 7ec38194f8e1..7cc338a9e9e4 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -52,9 +52,38 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/oom.h>
 
-int sysctl_panic_on_oom;
-int sysctl_oom_kill_allocating_task;
-int sysctl_oom_dump_tasks = 1;
+static int sysctl_panic_on_oom;
+static int sysctl_oom_kill_allocating_task;
+static int sysctl_oom_dump_tasks = 1;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table vm_oom_kill_table[] = {
+	{
+		.procname	= "panic_on_oom",
+		.data		= &sysctl_panic_on_oom,
+		.maxlen		= sizeof(sysctl_panic_on_oom),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
+	},
+	{
+		.procname	= "oom_kill_allocating_task",
+		.data		= &sysctl_oom_kill_allocating_task,
+		.maxlen		= sizeof(sysctl_oom_kill_allocating_task),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "oom_dump_tasks",
+		.data		= &sysctl_oom_dump_tasks,
+		.maxlen		= sizeof(sysctl_oom_dump_tasks),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{}
+};
+#endif
 
 /*
  * Serializes oom killer invocations (out_of_memory()) from all contexts to
@@ -677,6 +706,9 @@ static void wake_oom_reaper(struct task_struct *tsk)
 static int __init oom_init(void)
 {
 	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
+#ifdef CONFIG_SYSCTL
+	register_sysctl_init("vm", vm_oom_kill_table);
+#endif
 	return 0;
 }
 subsys_initcall(oom_init)
-- 
cgit v1.2.3


From aa779e5102195e1d9ade95dcbc0bfbd8f916eb59 Mon Sep 17 00:00:00 2001
From: zhanglianjie <zhanglianjie@uniontech.com>
Date: Thu, 17 Feb 2022 18:51:51 -0800
Subject: mm: move page-writeback sysctls to their own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we just
care about the core logic.

So move the page-writeback sysctls to its own file.

[akpm@linux-foundation.org: coding-style cleanups]

akpm@linux-foundation.org: fix CONFIG_SYSCTL=n warnings]
Link: https://lkml.kernel.org/r/20220129012955.26594-1-zhanglianjie@uniontech.com
Signed-off-by: zhanglianjie <zhanglianjie@uniontech.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/writeback.h |  15 -------
 kernel/sysctl.c           |  69 -------------------------------
 mm/page-writeback.c       | 103 +++++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 93 insertions(+), 94 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fec248ab1fec..dc2b94e6a94f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -345,28 +345,13 @@ void wb_domain_exit(struct wb_domain *dom);
 extern struct wb_domain global_wb_domain;
 
 /* These are exported to sysctl. */
-extern int dirty_background_ratio;
-extern unsigned long dirty_background_bytes;
-extern int vm_dirty_ratio;
-extern unsigned long vm_dirty_bytes;
 extern unsigned int dirty_writeback_interval;
 extern unsigned int dirty_expire_interval;
 extern unsigned int dirtytime_expire_interval;
-extern int vm_highmem_is_dirtyable;
 extern int laptop_mode;
 
-int dirty_background_ratio_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-int dirty_background_bytes_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-int dirty_ratio_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-int dirty_bytes_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
 int dirtytime_interval_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
-int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
 
 void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
 unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index a21c0ea396f3..36bfe1c92d44 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -100,8 +100,6 @@
 static const int six_hundred_forty_kb = 640 * 1024;
 #endif
 
-/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
-static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 
 static const int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
@@ -2263,55 +2261,6 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 	},
-	{
-		.procname	= "dirty_background_ratio",
-		.data		= &dirty_background_ratio,
-		.maxlen		= sizeof(dirty_background_ratio),
-		.mode		= 0644,
-		.proc_handler	= dirty_background_ratio_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE_HUNDRED,
-	},
-	{
-		.procname	= "dirty_background_bytes",
-		.data		= &dirty_background_bytes,
-		.maxlen		= sizeof(dirty_background_bytes),
-		.mode		= 0644,
-		.proc_handler	= dirty_background_bytes_handler,
-		.extra1		= SYSCTL_LONG_ONE,
-	},
-	{
-		.procname	= "dirty_ratio",
-		.data		= &vm_dirty_ratio,
-		.maxlen		= sizeof(vm_dirty_ratio),
-		.mode		= 0644,
-		.proc_handler	= dirty_ratio_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE_HUNDRED,
-	},
-	{
-		.procname	= "dirty_bytes",
-		.data		= &vm_dirty_bytes,
-		.maxlen		= sizeof(vm_dirty_bytes),
-		.mode		= 0644,
-		.proc_handler	= dirty_bytes_handler,
-		.extra1		= (void *)&dirty_bytes_min,
-	},
-	{
-		.procname	= "dirty_writeback_centisecs",
-		.data		= &dirty_writeback_interval,
-		.maxlen		= sizeof(dirty_writeback_interval),
-		.mode		= 0644,
-		.proc_handler	= dirty_writeback_centisecs_handler,
-	},
-	{
-		.procname	= "dirty_expire_centisecs",
-		.data		= &dirty_expire_interval,
-		.maxlen		= sizeof(dirty_expire_interval),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-	},
 	{
 		.procname	= "dirtytime_expire_seconds",
 		.data		= &dirtytime_expire_interval,
@@ -2483,13 +2432,6 @@ static struct ctl_table vm_table[] = {
 		.extra1		= SYSCTL_ZERO,
 	},
 #endif
-	{
-		.procname	= "laptop_mode",
-		.data		= &laptop_mode,
-		.maxlen		= sizeof(laptop_mode),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
 	{
 		.procname	= "vfs_cache_pressure",
 		.data		= &sysctl_vfs_cache_pressure,
@@ -2587,17 +2529,6 @@ static struct ctl_table vm_table[] = {
 		.extra1		= SYSCTL_ZERO,
 	},
 #endif
-#ifdef CONFIG_HIGHMEM
-	{
-		.procname	= "highmem_is_dirtyable",
-		.data		= &vm_highmem_is_dirtyable,
-		.maxlen		= sizeof(vm_highmem_is_dirtyable),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif
 #ifdef CONFIG_MEMORY_FAILURE
 	{
 		.procname	= "memory_failure_early_kill",
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7e2da284e427..438762173a59 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -70,30 +70,33 @@ static long ratelimit_pages = 32;
 /*
  * Start background writeback (via writeback threads) at this percentage
  */
-int dirty_background_ratio = 10;
+static int dirty_background_ratio = 10;
 
 /*
  * dirty_background_bytes starts at 0 (disabled) so that it is a function of
  * dirty_background_ratio * the amount of dirtyable memory
  */
-unsigned long dirty_background_bytes;
+static unsigned long dirty_background_bytes;
 
 /*
  * free highmem will not be subtracted from the total free memory
  * for calculating free ratios if vm_highmem_is_dirtyable is true
  */
-int vm_highmem_is_dirtyable;
+static int vm_highmem_is_dirtyable;
 
 /*
  * The generator of dirty data starts writeback at this percentage
  */
-int vm_dirty_ratio = 20;
+static int vm_dirty_ratio = 20;
+
+/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
+static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 
 /*
  * vm_dirty_bytes starts at 0 (disabled) so that it is a function of
  * vm_dirty_ratio * the amount of dirtyable memory
  */
-unsigned long vm_dirty_bytes;
+static unsigned long vm_dirty_bytes;
 
 /*
  * The interval between `kupdate'-style writebacks
@@ -491,7 +494,8 @@ bool node_dirty_ok(struct pglist_data *pgdat)
 	return nr_pages <= limit;
 }
 
-int dirty_background_ratio_handler(struct ctl_table *table, int write,
+#ifdef CONFIG_SYSCTL
+static int dirty_background_ratio_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -502,7 +506,7 @@ int dirty_background_ratio_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-int dirty_background_bytes_handler(struct ctl_table *table, int write,
+static int dirty_background_bytes_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -513,7 +517,7 @@ int dirty_background_bytes_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer,
+static int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int old_ratio = vm_dirty_ratio;
@@ -527,7 +531,7 @@ int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer,
 	return ret;
 }
 
-int dirty_bytes_handler(struct ctl_table *table, int write,
+static int dirty_bytes_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned long old_bytes = vm_dirty_bytes;
@@ -540,6 +544,7 @@ int dirty_bytes_handler(struct ctl_table *table, int write,
 	}
 	return ret;
 }
+#endif
 
 static unsigned long wp_next_time(unsigned long cur_time)
 {
@@ -1981,10 +1986,11 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 	return false;
 }
 
+#ifdef CONFIG_SYSCTL
 /*
  * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
  */
-int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
+static int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	unsigned int old_interval = dirty_writeback_interval;
@@ -2005,6 +2011,7 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
 
 	return ret;
 }
+#endif
 
 void laptop_mode_timer_fn(struct timer_list *t)
 {
@@ -2069,6 +2076,79 @@ static int page_writeback_cpu_online(unsigned int cpu)
 	return 0;
 }
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table vm_page_writeback_sysctls[] = {
+	{
+		.procname   = "dirty_background_ratio",
+		.data       = &dirty_background_ratio,
+		.maxlen     = sizeof(dirty_background_ratio),
+		.mode       = 0644,
+		.proc_handler   = dirty_background_ratio_handler,
+		.extra1     = SYSCTL_ZERO,
+		.extra2     = SYSCTL_ONE_HUNDRED,
+	},
+	{
+		.procname   = "dirty_background_bytes",
+		.data       = &dirty_background_bytes,
+		.maxlen     = sizeof(dirty_background_bytes),
+		.mode       = 0644,
+		.proc_handler   = dirty_background_bytes_handler,
+		.extra1     = SYSCTL_LONG_ONE,
+	},
+	{
+		.procname   = "dirty_ratio",
+		.data       = &vm_dirty_ratio,
+		.maxlen     = sizeof(vm_dirty_ratio),
+		.mode       = 0644,
+		.proc_handler   = dirty_ratio_handler,
+		.extra1     = SYSCTL_ZERO,
+		.extra2     = SYSCTL_ONE_HUNDRED,
+	},
+	{
+		.procname   = "dirty_bytes",
+		.data       = &vm_dirty_bytes,
+		.maxlen     = sizeof(vm_dirty_bytes),
+		.mode       = 0644,
+		.proc_handler   = dirty_bytes_handler,
+		.extra1     = (void *)&dirty_bytes_min,
+	},
+	{
+		.procname   = "dirty_writeback_centisecs",
+		.data       = &dirty_writeback_interval,
+		.maxlen     = sizeof(dirty_writeback_interval),
+		.mode       = 0644,
+		.proc_handler   = dirty_writeback_centisecs_handler,
+	},
+	{
+		.procname   = "dirty_expire_centisecs",
+		.data       = &dirty_expire_interval,
+		.maxlen     = sizeof(dirty_expire_interval),
+		.mode       = 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1     = SYSCTL_ZERO,
+	},
+#ifdef CONFIG_HIGHMEM
+	{
+		.procname	= "highmem_is_dirtyable",
+		.data		= &vm_highmem_is_dirtyable,
+		.maxlen		= sizeof(vm_highmem_is_dirtyable),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif
+	{
+		.procname	= "laptop_mode",
+		.data		= &laptop_mode,
+		.maxlen		= sizeof(laptop_mode),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{}
+};
+#endif
+
 /*
  * Called early on to tune the page writeback dirty limits.
  *
@@ -2093,6 +2173,9 @@ void __init page_writeback_init(void)
 			  page_writeback_cpu_online, NULL);
 	cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL,
 			  page_writeback_cpu_online);
+#ifdef CONFIG_SYSCTL
+	register_sysctl_init("vm", vm_page_writeback_sysctls);
+#endif
 }
 
 /**
-- 
cgit v1.2.3


From f79c9b8ae8bde10126586c1bb55b5fd027276d8e Mon Sep 17 00:00:00 2001
From: tangmeng <tangmeng@uniontech.com>
Date: Fri, 18 Feb 2022 18:58:57 +0800
Subject: kernel/lockdep: move lockdep sysctls to its own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we
just care about the core logic.

All filesystem syctls now get reviewed by fs folks. This commit
follows the commit of fs, move the prove_locking and lock_stat sysctls
to its own file, kernel/lockdep.c.

Signed-off-by: tangmeng <tangmeng@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/lockdep.h  |  4 ----
 kernel/locking/lockdep.c | 35 +++++++++++++++++++++++++++++++++--
 kernel/sysctl.c          | 21 ---------------------
 3 files changed, 33 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 467b94257105..37951c17908e 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -16,10 +16,6 @@
 
 struct task_struct;
 
-/* for sysctl */
-extern int prove_locking;
-extern int lock_stat;
-
 #ifdef CONFIG_LOCKDEP
 
 #include <linux/linkage.h>
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c06cab6546ed..a4382ae1be59 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -64,19 +64,50 @@
 #include <trace/events/lock.h>
 
 #ifdef CONFIG_PROVE_LOCKING
-int prove_locking = 1;
+static int prove_locking = 1;
 module_param(prove_locking, int, 0644);
 #else
 #define prove_locking 0
 #endif
 
 #ifdef CONFIG_LOCK_STAT
-int lock_stat = 1;
+static int lock_stat = 1;
 module_param(lock_stat, int, 0644);
 #else
 #define lock_stat 0
 #endif
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kern_lockdep_table[] = {
+#ifdef CONFIG_PROVE_LOCKING
+	{
+		.procname       = "prove_locking",
+		.data           = &prove_locking,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#endif /* CONFIG_PROVE_LOCKING */
+#ifdef CONFIG_LOCK_STAT
+	{
+		.procname       = "lock_stat",
+		.data           = &lock_stat,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#endif /* CONFIG_LOCK_STAT */
+	{ }
+};
+
+static __init int kernel_lockdep_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_lockdep_table);
+	return 0;
+}
+late_initcall(kernel_lockdep_sysctls_init);
+#endif /* CONFIG_SYSCTL */
+
 DEFINE_PER_CPU(unsigned int, lockdep_recursion);
 EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 36bfe1c92d44..95380d250c8c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -88,9 +88,6 @@
 #ifdef CONFIG_RT_MUTEXES
 #include <linux/rtmutex.h>
 #endif
-#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT)
-#include <linux/lockdep.h>
-#endif
 
 #if defined(CONFIG_SYSCTL)
 
@@ -1679,24 +1676,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-#ifdef CONFIG_PROVE_LOCKING
-	{
-		.procname	= "prove_locking",
-		.data		= &prove_locking,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
-#ifdef CONFIG_LOCK_STAT
-	{
-		.procname	= "lock_stat",
-		.data		= &lock_stat,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 	{
 		.procname	= "panic",
 		.data		= &panic_timeout,
-- 
cgit v1.2.3


From 9df918698408fd914493aba0b7858fef50eba63a Mon Sep 17 00:00:00 2001
From: tangmeng <tangmeng@uniontech.com>
Date: Fri, 18 Feb 2022 18:59:12 +0800
Subject: kernel/panic: move panic sysctls to its own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we
just care about the core logic.

All filesystem syctls now get reviewed by fs folks. This commit
follows the commit of fs, move the oops_all_cpu_backtrace sysctl to
its own file, kernel/panic.c.

Signed-off-by: tangmeng <tangmeng@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/panic.h |  6 ------
 kernel/panic.c        | 26 +++++++++++++++++++++++++-
 kernel/sysctl.c       | 11 -----------
 3 files changed, 25 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/panic.h b/include/linux/panic.h
index f5844908a089..e71161da69c4 100644
--- a/include/linux/panic.h
+++ b/include/linux/panic.h
@@ -15,12 +15,6 @@ extern void oops_enter(void);
 extern void oops_exit(void);
 extern bool oops_may_print(void);
 
-#ifdef CONFIG_SMP
-extern unsigned int sysctl_oops_all_cpu_backtrace;
-#else
-#define sysctl_oops_all_cpu_backtrace 0
-#endif /* CONFIG_SMP */
-
 extern int panic_timeout;
 extern unsigned long panic_print;
 extern int panic_on_oops;
diff --git a/kernel/panic.c b/kernel/panic.c
index eb4dfb932c85..eb3f2fe4f6d7 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -43,7 +43,9 @@
  * Should we dump all CPUs backtraces in an oops event?
  * Defaults to 0, can be changed via sysctl.
  */
-unsigned int __read_mostly sysctl_oops_all_cpu_backtrace;
+static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace;
+#else
+#define sysctl_oops_all_cpu_backtrace 0
 #endif /* CONFIG_SMP */
 
 int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
@@ -73,6 +75,28 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
 
 EXPORT_SYMBOL(panic_notifier_list);
 
+#if defined(CONFIG_SMP) && defined(CONFIG_SYSCTL)
+static struct ctl_table kern_panic_table[] = {
+	{
+		.procname       = "oops_all_cpu_backtrace",
+		.data           = &sysctl_oops_all_cpu_backtrace,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{ }
+};
+
+static __init int kernel_panic_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_panic_table);
+	return 0;
+}
+late_initcall(kernel_panic_sysctls_init);
+#endif
+
 static long no_blink(int state)
 {
 	return 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 95380d250c8c..90fc2212b536 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1922,17 +1922,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_SMP
-	{
-		.procname	= "oops_all_cpu_backtrace",
-		.data		= &sysctl_oops_all_cpu_backtrace,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif /* CONFIG_SMP */
 	{
 		.procname	= "pid_max",
 		.data		= &pid_max,
-- 
cgit v1.2.3


From 801b501439d1b366d524dee4fc1e6b3473a95b9a Mon Sep 17 00:00:00 2001
From: tangmeng <tangmeng@uniontech.com>
Date: Fri, 18 Feb 2022 18:59:23 +0800
Subject: kernel/acct: move acct sysctls to its own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we
just care about the core logic.

All filesystem syctls now get reviewed by fs folks. This commit
follows the commit of fs, move the acct sysctl to its own file,
kernel/acct.c.

Signed-off-by: tangmeng <tangmeng@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/acct.h |  1 -
 kernel/acct.c        | 22 +++++++++++++++++++++-
 kernel/sysctl.c      | 12 ------------
 3 files changed, 21 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/acct.h b/include/linux/acct.h
index bc70e81895c0..2718c4854815 100644
--- a/include/linux/acct.h
+++ b/include/linux/acct.h
@@ -21,7 +21,6 @@
 
 #ifdef CONFIG_BSD_PROCESS_ACCT
 struct pid_namespace;
-extern int acct_parm[]; /* for sysctl */
 extern void acct_collect(long exitcode, int group_dead);
 extern void acct_process(void);
 extern void acct_exit_ns(struct pid_namespace *);
diff --git a/kernel/acct.c b/kernel/acct.c
index 3df53cf1dcd5..13706356ec54 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -70,11 +70,31 @@
  * Turned into sysctl-controllable parameters. AV, 12/11/98
  */
 
-int acct_parm[3] = {4, 2, 30};
+static int acct_parm[3] = {4, 2, 30};
 #define RESUME		(acct_parm[0])	/* >foo% free space - resume */
 #define SUSPEND		(acct_parm[1])	/* <foo% free space - suspend */
 #define ACCT_TIMEOUT	(acct_parm[2])	/* foo second timeout between checks */
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kern_acct_table[] = {
+	{
+		.procname       = "acct",
+		.data           = &acct_parm,
+		.maxlen         = 3*sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{ }
+};
+
+static __init int kernel_acct_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_acct_table);
+	return 0;
+}
+late_initcall(kernel_acct_sysctls_init);
+#endif /* CONFIG_SYSCTL */
+
 /*
  * External references and all of the globals.
  */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 90fc2212b536..5421e28dbb25 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -82,9 +82,6 @@
 #ifdef CONFIG_SPARC
 #include <asm/setup.h>
 #endif
-#ifdef CONFIG_BSD_PROCESS_ACCT
-#include <linux/acct.h>
-#endif
 #ifdef CONFIG_RT_MUTEXES
 #include <linux/rtmutex.h>
 #endif
@@ -1856,15 +1853,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dostring,
 	},
 #endif
-#ifdef CONFIG_BSD_PROCESS_ACCT
-	{
-		.procname	= "acct",
-		.data		= &acct_parm,
-		.maxlen		= 3*sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 #ifdef CONFIG_MAGIC_SYSRQ
 	{
 		.procname	= "sysrq",
-- 
cgit v1.2.3


From 1186618a6a35d43a865448472a261184b608d13c Mon Sep 17 00:00:00 2001
From: tangmeng <tangmeng@uniontech.com>
Date: Fri, 18 Feb 2022 18:59:36 +0800
Subject: kernel/delayacct: move delayacct sysctls to its own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we
just care about the core logic.

All filesystem syctls now get reviewed by fs folks. This commit
follows the commit of fs, move the delayacct sysctl to its own file,
kernel/delayacct.c.

Signed-off-by: tangmeng <tangmeng@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/delayacct.h |  3 ---
 kernel/delayacct.c        | 22 +++++++++++++++++++++-
 kernel/sysctl.c           | 12 ------------
 3 files changed, 21 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 3e03d010bd2e..6b16a6930a19 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -61,9 +61,6 @@ extern int delayacct_on;	/* Delay accounting turned on/off */
 extern struct kmem_cache *delayacct_cache;
 extern void delayacct_init(void);
 
-extern int sysctl_delayacct(struct ctl_table *table, int write, void *buffer,
-			    size_t *lenp, loff_t *ppos);
-
 extern void __delayacct_tsk_init(struct task_struct *);
 extern void __delayacct_tsk_exit(struct task_struct *);
 extern void __delayacct_blkio_start(void);
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index c5e8cea9e05f..2c1e18f7c5cf 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -44,7 +44,7 @@ void delayacct_init(void)
 }
 
 #ifdef CONFIG_PROC_SYSCTL
-int sysctl_delayacct(struct ctl_table *table, int write, void *buffer,
+static int sysctl_delayacct(struct ctl_table *table, int write, void *buffer,
 		     size_t *lenp, loff_t *ppos)
 {
 	int state = delayacct_on;
@@ -63,6 +63,26 @@ int sysctl_delayacct(struct ctl_table *table, int write, void *buffer,
 		set_delayacct(state);
 	return err;
 }
+
+static struct ctl_table kern_delayacct_table[] = {
+	{
+		.procname       = "task_delayacct",
+		.data           = NULL,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_delayacct,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{ }
+};
+
+static __init int kernel_delayacct_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_delayacct_table);
+	return 0;
+}
+late_initcall(kernel_delayacct_sysctls_init);
 #endif
 
 void __delayacct_tsk_init(struct task_struct *tsk)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 5421e28dbb25..9b74ba12a711 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -67,7 +67,6 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/latencytop.h>
 #include <linux/pid.h>
-#include <linux/delayacct.h>
 
 #include "../lib/kstrtox.h"
 
@@ -1651,17 +1650,6 @@ int proc_do_static_key(struct ctl_table *table, int write,
 }
 
 static struct ctl_table kern_table[] = {
-#ifdef CONFIG_TASK_DELAY_ACCT
-	{
-		.procname	= "task_delayacct",
-		.data		= NULL,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sysctl_delayacct,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif /* CONFIG_TASK_DELAY_ACCT */
 #ifdef CONFIG_NUMA_BALANCING
 	{
 		.procname	= "numa_balancing",
-- 
cgit v1.2.3


From d772cc2c321900f3f463a124eebeb7218e66dda6 Mon Sep 17 00:00:00 2001
From: tangmeng <tangmeng@uniontech.com>
Date: Fri, 18 Feb 2022 18:59:49 +0800
Subject: kernel/do_mount_initrd: move real_root_dev sysctls to its own file

kernel/sysctl.c is a kitchen sink where everyone leaves their dirty
dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places
where they actually belong.  The proc sysctl maintainers do not want to
know what sysctl knobs you wish to add for your own piece of code, we
just care about the core logic.

All filesystem syctls now get reviewed by fs folks. This commit
follows the commit of fs, move the real_root_dev sysctl to its own file,
kernel/do_mount_initrd.c.

Signed-off-by: tangmeng <tangmeng@uniontech.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/initrd.h  |  2 --
 init/do_mounts_initrd.c | 22 +++++++++++++++++++++-
 kernel/sysctl.c         |  9 ---------
 3 files changed, 21 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/initrd.h b/include/linux/initrd.h
index 1bbe9af48dc3..f1a1f4c92ded 100644
--- a/include/linux/initrd.h
+++ b/include/linux/initrd.h
@@ -29,8 +29,6 @@ static inline void wait_for_initramfs(void) {}
 extern phys_addr_t phys_initrd_start;
 extern unsigned long phys_initrd_size;
 
-extern unsigned int real_root_dev;
-
 extern char __initramfs_start[];
 extern unsigned long __initramfs_size;
 
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 533d81ed74d4..327962ea354c 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -14,12 +14,32 @@
 
 unsigned long initrd_start, initrd_end;
 int initrd_below_start_ok;
-unsigned int real_root_dev;	/* do_proc_dointvec cannot handle kdev_t */
+static unsigned int real_root_dev;	/* do_proc_dointvec cannot handle kdev_t */
 static int __initdata mount_initrd = 1;
 
 phys_addr_t phys_initrd_start __initdata;
 unsigned long phys_initrd_size __initdata;
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kern_do_mounts_initrd_table[] = {
+	{
+		.procname       = "real-root-dev",
+		.data           = &real_root_dev,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{ }
+};
+
+static __init int kernel_do_mounts_initrd_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_do_mounts_initrd_table);
+	return 0;
+}
+late_initcall(kernel_do_mounts_initrd_sysctls_init);
+#endif /* CONFIG_SYSCTL */
+
 static int __init no_initrd(char *str)
 {
 	mount_initrd = 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9b74ba12a711..10a551f8fcab 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1693,15 +1693,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sysctl_latencytop,
 	},
-#endif
-#ifdef CONFIG_BLK_DEV_INITRD
-	{
-		.procname	= "real-root-dev",
-		.data		= &real_root_dev,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #endif
 	{
 		.procname	= "print-fatal-signals",
-- 
cgit v1.2.3


From 8e4e83b2278bdfb55cb2b13de07cf0a721ce8af7 Mon Sep 17 00:00:00 2001
From: Wei Xiao <xiaowei66@huawei.com>
Date: Wed, 23 Feb 2022 19:11:53 +0800
Subject: ftrace: move sysctl_ftrace_enabled to ftrace.c

This moves ftrace_enabled to trace/ftrace.c.

We move sysctls to places where features actually belong to improve
the readability of the code and reduce the risk of code merge conflicts.
At the same time, the proc-sysctl maintainers do not want to know what
sysctl knobs you wish to add for your owner piece of code, we just care
about the core logic.

Signed-off-by: Wei Xiao <xiaowei66@huawei.com>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/ftrace.h |  3 ---
 kernel/sysctl.c        |  9 ---------
 kernel/trace/ftrace.c  | 22 +++++++++++++++++++++-
 3 files changed, 21 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4816b7e11047..088b915853dd 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -101,9 +101,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern int ftrace_enabled;
-extern int
-ftrace_enable_sysctl(struct ctl_table *table, int write,
-		     void *buffer, size_t *lenp, loff_t *ppos);
 
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 10a551f8fcab..21172d3dad6e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1751,15 +1751,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_FUNCTION_TRACER
-	{
-		.procname	= "ftrace_enabled",
-		.data		= &ftrace_enabled,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= ftrace_enable_sysctl,
-	},
-#endif
 #ifdef CONFIG_STACK_TRACER
 	{
 		.procname	= "stack_tracer_enabled",
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f1d2f5e7263..a5efbbc289b4 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7921,7 +7921,8 @@ static bool is_permanent_ops_registered(void)
 	return false;
 }
 
-int
+#ifdef CONFIG_SYSCTL
+static int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -7964,3 +7965,22 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	mutex_unlock(&ftrace_lock);
 	return ret;
 }
+
+static struct ctl_table ftrace_sysctls[] = {
+	{
+		.procname       = "ftrace_enabled",
+		.data           = &ftrace_enabled,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = ftrace_enable_sysctl,
+	},
+	{}
+};
+
+static int __init ftrace_sysctl_init(void)
+{
+	register_sysctl_init("kernel", ftrace_sysctls);
+	return 0;
+}
+late_initcall(ftrace_sysctl_init);
+#endif
-- 
cgit v1.2.3


From 5ea98e01ab524cbc53dad8aebd27b434ebe5d074 Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Mon, 7 Mar 2022 15:33:39 -0600
Subject: x86/boot: Add Confidential Computing type to setup_data

While launching encrypted guests, the hypervisor may need to provide
some additional information during the guest boot. When booting under an
EFI-based BIOS, the EFI configuration table contains an entry for the
confidential computing blob that contains the required information.

To support booting encrypted guests on non-EFI VMs, the hypervisor
needs to pass this additional information to the guest kernel using a
different method.

For this purpose, introduce SETUP_CC_BLOB type in setup_data to hold
the physical address of the confidential computing blob location. The
boot loader or hypervisor may choose to use this method instead of an
EFI configuration table. The CC blob location scanning should give
preference to a setup_data blob over an EFI configuration table.

In AMD SEV-SNP, the CC blob contains the address of the secrets and
CPUID pages. The secrets page includes information such as a VM to PSP
communication key and the CPUID page contains PSP-filtered CPUID values.
Define the AMD SEV confidential computing blob structure.

While at it, define the EFI GUID for the confidential computing blob.

  [ bp: Massage commit message, mark struct __packed. ]

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20220307213356.2797205-30-brijesh.singh@amd.com
---
 arch/x86/include/asm/sev.h            | 18 ++++++++++++++++++
 arch/x86/include/uapi/asm/bootparam.h |  1 +
 include/linux/efi.h                   |  1 +
 3 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index a3203b2caaca..8c934bda2a90 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -42,6 +42,24 @@ struct es_em_ctxt {
 	struct es_fault_info fi;
 };
 
+/*
+ * AMD SEV Confidential computing blob structure. The structure is
+ * defined in OVMF UEFI firmware header:
+ * https://github.com/tianocore/edk2/blob/master/OvmfPkg/Include/Guid/ConfidentialComputingSevSnpBlob.h
+ */
+#define CC_BLOB_SEV_HDR_MAGIC	0x45444d41
+struct cc_blob_sev_info {
+	u32 magic;
+	u16 version;
+	u16 reserved;
+	u64 secrets_phys;
+	u32 secrets_len;
+	u32 rsvd1;
+	u64 cpuid_phys;
+	u32 cpuid_len;
+	u32 rsvd2;
+} __packed;
+
 void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code);
 
 static inline u64 lower_bits(u64 val, unsigned int bits)
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index b25d3f82c2f3..1ac5acca72ce 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -10,6 +10,7 @@
 #define SETUP_EFI			4
 #define SETUP_APPLE_PROPERTIES		5
 #define SETUP_JAILHOUSE			6
+#define SETUP_CC_BLOB			7
 
 #define SETUP_INDIRECT			(1<<31)
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index ccd4d3f91c98..984aa688997a 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -390,6 +390,7 @@ void efi_native_runtime_setup(void);
 #define EFI_CERT_SHA256_GUID			EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28)
 #define EFI_CERT_X509_GUID			EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72)
 #define EFI_CERT_X509_SHA256_GUID		EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed)
+#define EFI_CC_BLOB_GUID			EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42)
 
 /*
  * This GUID is used to pass to the kernel proper the struct screen_info
-- 
cgit v1.2.3


From bae1a962ac2c5e6be08319ff3f7d6df542584fce Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Wed, 6 Apr 2022 02:29:33 +0300
Subject: x86/topology: Disable CPU online/offline control for TDX guests

Unlike regular VMs, TDX guests use the firmware hand-off wakeup method
to wake up the APs during the boot process. This wakeup model uses a
mailbox to communicate with firmware to bring up the APs. As per the
design, this mailbox can only be used once for the given AP, which means
after the APs are booted, the same mailbox cannot be used to
offline/online the given AP. More details about this requirement can be
found in Intel TDX Virtual Firmware Design Guide, sec titled "AP
initialization in OS" and in sec titled "Hotplug Device".

Since the architecture does not support any method of offlining the
CPUs, disable CPU hotplug support in the kernel.

Since this hotplug disable feature can be re-used by other VM guests,
add a new CC attribute CC_ATTR_HOTPLUG_DISABLED and use it to disable
the hotplug support.

Attempt to offline CPU will fail with -EOPNOTSUPP.

Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20220405232939.73860-25-kirill.shutemov@linux.intel.com
---
 arch/x86/coco/core.c        |  1 +
 include/linux/cc_platform.h | 10 ++++++++++
 kernel/cpu.c                |  7 +++++++
 3 files changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index df08edc94f9b..70956f9d7c7e 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -20,6 +20,7 @@ static bool intel_cc_platform_has(enum cc_attr attr)
 {
 	switch (attr) {
 	case CC_ATTR_GUEST_UNROLL_STRING_IO:
+	case CC_ATTR_HOTPLUG_DISABLED:
 		return true;
 	default:
 		return false;
diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h
index efd8205282da..691494bbaf5a 100644
--- a/include/linux/cc_platform.h
+++ b/include/linux/cc_platform.h
@@ -72,6 +72,16 @@ enum cc_attr {
 	 * Examples include TDX guest & SEV.
 	 */
 	CC_ATTR_GUEST_UNROLL_STRING_IO,
+
+	/**
+	 * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled.
+	 *
+	 * The platform/OS is running as a guest/virtual machine does not
+	 * support CPU hotplug feature.
+	 *
+	 * Examples include TDX Guest.
+	 */
+	CC_ATTR_HOTPLUG_DISABLED,
 };
 
 #ifdef CONFIG_ARCH_HAS_CC_PLATFORM
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5797c2a7a93f..edb8c199f6a3 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -35,6 +35,7 @@
 #include <linux/percpu-rwsem.h>
 #include <linux/cpuset.h>
 #include <linux/random.h>
+#include <linux/cc_platform.h>
 
 #include <trace/events/power.h>
 #define CREATE_TRACE_POINTS
@@ -1186,6 +1187,12 @@ out:
 
 static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
 {
+	/*
+	 * If the platform does not support hotplug, report it explicitly to
+	 * differentiate it from a transient offlining failure.
+	 */
+	if (cc_platform_has(CC_ATTR_HOTPLUG_DISABLED))
+		return -EOPNOTSUPP;
 	if (cpu_hotplug_disabled)
 		return -EBUSY;
 	return _cpu_down(cpu, 0, target);
-- 
cgit v1.2.3


From 6264f58ca0e54e41d63c2d00334a48bac28fbf30 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 6 Apr 2022 14:37:54 -0700
Subject: net: extract a few internals from netdevice.h

There's a number of functions and static variables used
under net/core/ but not from the outside. We currently
dump most of them into netdevice.h. That bad for many
reasons:
 - netdevice.h is very cluttered, hard to figure out
   what the APIs are;
 - netdevice.h is very long;
 - we have to touch netdevice.h more which causes expensive
   incremental builds.

Create a header under net/core/ and move some declarations.

The new header is also a bit of a catch-all but that's
fine, if we create more specific headers people will
likely over-think where their declaration fit best.
And end up putting them in netdevice.h, again.

More work should be done on splitting netdevice.h into more
targeted headers, but that'd be more time consuming so small
steps.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h  | 72 +-----------------------------------
 net/core/dev.c             |  1 +
 net/core/dev.h             | 91 ++++++++++++++++++++++++++++++++++++++++++++++
 net/core/dev_addr_lists.c  |  2 +
 net/core/dev_ioctl.c       |  2 +
 net/core/link_watch.c      |  1 +
 net/core/net-procfs.c      |  2 +
 net/core/net-sysfs.c       |  1 +
 net/core/rtnetlink.c       |  2 +
 net/core/sock.c            |  2 +
 net/core/sysctl_net_core.c |  2 +
 11 files changed, 108 insertions(+), 70 deletions(-)
 create mode 100644 net/core/dev.h

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7b2a0b739684..7e7b2a72e473 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -59,7 +59,8 @@ struct dsa_port;
 struct ip_tunnel_parm;
 struct macsec_context;
 struct macsec_ops;
-
+struct netdev_name_node;
+struct sd_flow_limit;
 struct sfp_bus;
 /* 802.11 specific */
 struct wireless_dev;
@@ -1020,16 +1021,6 @@ struct dev_ifalias {
 struct devlink;
 struct tlsdev_ops;
 
-struct netdev_name_node {
-	struct hlist_node hlist;
-	struct list_head list;
-	struct net_device *dev;
-	const char *name;
-};
-
-int netdev_name_node_alt_create(struct net_device *dev, const char *name);
-int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
-
 struct netdev_net_notifier {
 	struct list_head list;
 	struct notifier_block *nb;
@@ -2975,7 +2966,6 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
 struct net_device *dev_get_by_napi_id(unsigned int napi_id);
-int netdev_get_name(struct net *net, char *name, int ifindex);
 int dev_restart(struct net_device *dev);
 
 
@@ -3034,19 +3024,6 @@ static inline bool dev_has_header(const struct net_device *dev)
 	return dev->header_ops && dev->header_ops->create;
 }
 
-#ifdef CONFIG_NET_FLOW_LIMIT
-#define FLOW_LIMIT_HISTORY	(1 << 7)  /* must be ^2 and !overflow buckets */
-struct sd_flow_limit {
-	u64			count;
-	unsigned int		num_buckets;
-	unsigned int		history_head;
-	u16			history[FLOW_LIMIT_HISTORY];
-	u8			buckets[];
-};
-
-extern int netdev_flow_limit_table_len;
-#endif /* CONFIG_NET_FLOW_LIMIT */
-
 /*
  * Incoming packets are placed on per-CPU queues
  */
@@ -3770,7 +3747,6 @@ int dev_change_flags(struct net_device *dev, unsigned int flags,
 		     struct netlink_ext_ack *extack);
 void __dev_notify_flags(struct net_device *, unsigned int old_flags,
 			unsigned int gchanges);
-int dev_change_name(struct net_device *, const char *);
 int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
 int __dev_change_net_namespace(struct net_device *dev, struct net *net,
@@ -3782,13 +3758,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net,
 	return __dev_change_net_namespace(dev, net, pat, 0);
 }
 int __dev_set_mtu(struct net_device *, int);
-int dev_validate_mtu(struct net_device *dev, int mtu,
-		     struct netlink_ext_ack *extack);
-int dev_set_mtu_ext(struct net_device *dev, int mtu,
-		    struct netlink_ext_ack *extack);
 int dev_set_mtu(struct net_device *, int);
-int dev_change_tx_queue_len(struct net_device *, unsigned long);
-void dev_set_group(struct net_device *, int);
 int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
 			      struct netlink_ext_ack *extack);
 int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
@@ -3796,24 +3766,13 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
 			     struct netlink_ext_ack *extack);
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
-int dev_change_carrier(struct net_device *, bool new_carrier);
-int dev_get_phys_port_id(struct net_device *dev,
-			 struct netdev_phys_item_id *ppid);
-int dev_get_phys_port_name(struct net_device *dev,
-			   char *name, size_t len);
 int dev_get_port_parent_id(struct net_device *dev,
 			   struct netdev_phys_item_id *ppid, bool recurse);
 bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
-int dev_change_proto_down(struct net_device *dev, bool proto_down);
-void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
-				  u32 value);
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
 
-typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
-int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
-		      int fd, int expected_fd, u32 flags);
 int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 u8 dev_xdp_prog_count(struct net_device *dev);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
@@ -3898,13 +3857,6 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev,
 bool dev_nit_active(struct net_device *dev);
 void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
 
-extern int		netdev_budget;
-extern unsigned int	netdev_budget_usecs;
-
-/* Used by rtnetlink.c:__rtnl_unlock()/rtnl_unlock() */
-extern struct list_head net_todo_list;
-void netdev_run_todo(void);
-
 static inline void __dev_put(struct net_device *dev)
 {
 	if (dev) {
@@ -4021,10 +3973,7 @@ static inline void dev_replace_track(struct net_device *odev,
  * called netif_lowerlayer_*() because they represent the state of any
  * kind of lower layer not just hardware media.
  */
-
-void linkwatch_init_dev(struct net_device *dev);
 void linkwatch_fire_event(struct net_device *dev);
-void linkwatch_forget_dev(struct net_device *dev);
 
 /**
  *	netif_carrier_ok - test if carrier present
@@ -4470,9 +4419,6 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr,
 		 unsigned char addr_type);
 int dev_addr_del(struct net_device *dev, const unsigned char *addr,
 		 unsigned char addr_type);
-void dev_addr_flush(struct net_device *dev);
-int dev_addr_init(struct net_device *dev);
-void dev_addr_check(struct net_device *dev);
 
 /* Functions used for unicast addresses handling */
 int dev_uc_add(struct net_device *dev, const unsigned char *addr);
@@ -4562,7 +4508,6 @@ static inline void __dev_mc_unsync(struct net_device *dev,
 
 /* Functions used for secondary unicast and multicast support */
 void dev_set_rx_mode(struct net_device *dev);
-void __dev_set_rx_mode(struct net_device *dev);
 int dev_set_promiscuity(struct net_device *dev, int inc);
 int dev_set_allmulti(struct net_device *dev, int inc);
 void netdev_state_change(struct net_device *dev);
@@ -4580,11 +4525,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
 void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s);
 
 extern int		netdev_max_backlog;
-extern int		netdev_tstamp_prequeue;
-extern int		netdev_unregister_timeout_secs;
-extern int		weight_p;
-extern int		dev_weight_rx_bias;
-extern int		dev_weight_tx_bias;
 extern int		dev_rx_weight;
 extern int		dev_tx_weight;
 extern int		gro_normal_batch;
@@ -4772,12 +4712,6 @@ static inline void netdev_rx_csum_fault(struct net_device *dev,
 void net_enable_timestamp(void);
 void net_disable_timestamp(void);
 
-#ifdef CONFIG_PROC_FS
-int __init dev_proc_init(void);
-#else
-#define dev_proc_init() 0
-#endif
-
 static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
 					      struct sk_buff *skb, struct net_device *dev,
 					      bool more)
@@ -4813,8 +4747,6 @@ extern const struct kobj_ns_type_operations net_ns_type_operations;
 
 const char *netdev_drivername(const struct net_device *dev);
 
-void linkwatch_run_queue(void);
-
 static inline netdev_features_t netdev_intersect_features(netdev_features_t f1,
 							  netdev_features_t f2)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 8755ad71be6c..f00d29856b43 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -151,6 +151,7 @@
 #include <linux/prandom.h>
 #include <linux/once_lite.h>
 
+#include "dev.h"
 #include "net-sysfs.h"
 
 
diff --git a/net/core/dev.h b/net/core/dev.h
new file mode 100644
index 000000000000..27923df00637
--- /dev/null
+++ b/net/core/dev.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _NET_CORE_DEV_H
+#define _NET_CORE_DEV_H
+
+#include <linux/types.h>
+
+struct net;
+struct net_device;
+struct netdev_bpf;
+struct netdev_phys_item_id;
+struct netlink_ext_ack;
+
+/* Random bits of netdevice that don't need to be exposed */
+#define FLOW_LIMIT_HISTORY	(1 << 7)  /* must be ^2 and !overflow buckets */
+struct sd_flow_limit {
+	u64			count;
+	unsigned int		num_buckets;
+	unsigned int		history_head;
+	u16			history[FLOW_LIMIT_HISTORY];
+	u8			buckets[];
+};
+
+extern int netdev_flow_limit_table_len;
+
+#ifdef CONFIG_PROC_FS
+int __init dev_proc_init(void);
+#else
+#define dev_proc_init() 0
+#endif
+
+void linkwatch_init_dev(struct net_device *dev);
+void linkwatch_forget_dev(struct net_device *dev);
+void linkwatch_run_queue(void);
+
+void dev_addr_flush(struct net_device *dev);
+int dev_addr_init(struct net_device *dev);
+void dev_addr_check(struct net_device *dev);
+
+/* sysctls not referred to from outside net/core/ */
+extern int		netdev_budget;
+extern unsigned int	netdev_budget_usecs;
+
+extern int		netdev_tstamp_prequeue;
+extern int		netdev_unregister_timeout_secs;
+extern int		weight_p;
+extern int		dev_weight_rx_bias;
+extern int		dev_weight_tx_bias;
+
+/* rtnl helpers */
+extern struct list_head net_todo_list;
+void netdev_run_todo(void);
+
+/* netdev management, shared between various uAPI entry points */
+struct netdev_name_node {
+	struct hlist_node hlist;
+	struct list_head list;
+	struct net_device *dev;
+	const char *name;
+};
+
+int netdev_get_name(struct net *net, char *name, int ifindex);
+int dev_change_name(struct net_device *dev, const char *newname);
+
+int netdev_name_node_alt_create(struct net_device *dev, const char *name);
+int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
+
+int dev_validate_mtu(struct net_device *dev, int mtu,
+		     struct netlink_ext_ack *extack);
+int dev_set_mtu_ext(struct net_device *dev, int mtu,
+		    struct netlink_ext_ack *extack);
+
+int dev_get_phys_port_id(struct net_device *dev,
+			 struct netdev_phys_item_id *ppid);
+int dev_get_phys_port_name(struct net_device *dev,
+			   char *name, size_t len);
+
+int dev_change_proto_down(struct net_device *dev, bool proto_down);
+void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
+				  u32 value);
+
+typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
+int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
+		      int fd, int expected_fd, u32 flags);
+
+int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len);
+void dev_set_group(struct net_device *dev, int new_group);
+int dev_change_carrier(struct net_device *dev, bool new_carrier);
+
+void __dev_set_rx_mode(struct net_device *dev);
+
+#endif
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index bead38ca50bd..baa63dee2829 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -12,6 +12,8 @@
 #include <linux/export.h>
 #include <linux/list.h>
 
+#include "dev.h"
+
 /*
  * General list handling functions
  */
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 1b807d119da5..4f6be442ae7e 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -10,6 +10,8 @@
 #include <net/dsa.h>
 #include <net/wext.h>
 
+#include "dev.h"
+
 /*
  *	Map an interface index to its name (SIOCGIFNAME)
  */
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 95098d1a49bd..a244d3bade7d 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -18,6 +18,7 @@
 #include <linux/bitops.h>
 #include <linux/types.h>
 
+#include "dev.h"
 
 enum lw_bits {
 	LW_URGENT = 0,
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 88cc0ad7d386..1ec23bf8b05c 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -4,6 +4,8 @@
 #include <linux/seq_file.h>
 #include <net/wext.h>
 
+#include "dev.h"
+
 #define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
 
 #define get_bucket(x) ((x) >> BUCKET_SPACE)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 9cbc1c8289bc..4980c3a50475 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -24,6 +24,7 @@
 #include <linux/of_net.h>
 #include <linux/cpu.h>
 
+#include "dev.h"
 #include "net-sysfs.h"
 
 #ifdef CONFIG_SYSFS
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 0e4502d641eb..4041b3e2e8ec 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -54,6 +54,8 @@
 #include <net/rtnetlink.h>
 #include <net/net_namespace.h>
 
+#include "dev.h"
+
 #define RTNL_MAX_TYPE		50
 #define RTNL_SLAVE_MAX_TYPE	40
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 1180a0cb0110..7000403eaeb2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -141,6 +141,8 @@
 
 #include <linux/ethtool.h>
 
+#include "dev.h"
+
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 7123fe7feeac..8295e5877eb3 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -23,6 +23,8 @@
 #include <net/busy_poll.h>
 #include <net/pkt_sched.h>
 
+#include "dev.h"
+
 static int two = 2;
 static int three = 3;
 static int int_3600 = 3600;
-- 
cgit v1.2.3


From 794c24e9921f32ded4422833a990ccf11dc3c00e Mon Sep 17 00:00:00 2001
From: Jeffrey Ji <jeffreyji@google.com>
Date: Wed, 6 Apr 2022 17:26:00 +0000
Subject: net-core: rx_otherhost_dropped to core_stats

Increment rx_otherhost_dropped counter when packet dropped due to
mismatched dest MAC addr.

An example when this drop can occur is when manually crafting raw
packets that will be consumed by a user space application via a tap
device. For testing purposes local traffic was generated using trafgen
for the client and netcat to start a server

Tested: Created 2 netns, sent 1 packet using trafgen from 1 to the other
with "{eth(daddr=$INCORRECT_MAC...}", verified that iproute2 showed the
counter was incremented. (Also had to modify iproute2 to show the stat,
additional patch for that coming next.)

Signed-off-by: Jeffrey Ji <jeffreyji@google.com>
Reviewed-by: Brian Vazquez <brianvv@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20220406172600.1141083-1-jeffreyjilinux@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h    | 2 ++
 include/uapi/linux/if_link.h | 5 +++++
 net/core/dev.c               | 1 +
 net/ipv4/ip_input.c          | 1 +
 net/ipv6/ip6_input.c         | 1 +
 5 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7e7b2a72e473..28ea4f8269d4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -203,6 +203,7 @@ struct net_device_core_stats {
 	local_t		rx_dropped;
 	local_t		tx_dropped;
 	local_t		rx_nohandler;
+	local_t		rx_otherhost_dropped;
 } __aligned(4 * sizeof(local_t));
 
 #include <linux/cache.h>
@@ -3837,6 +3838,7 @@ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev)		\
 DEV_CORE_STATS_INC(rx_dropped)
 DEV_CORE_STATS_INC(tx_dropped)
 DEV_CORE_STATS_INC(rx_nohandler)
+DEV_CORE_STATS_INC(rx_otherhost_dropped)
 
 static __always_inline int ____dev_forward_skb(struct net_device *dev,
 					       struct sk_buff *skb,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index cc284c048e69..d1e600816b82 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -211,6 +211,9 @@ struct rtnl_link_stats {
  * @rx_nohandler: Number of packets received on the interface
  *   but dropped by the networking stack because the device is
  *   not designated to receive packets (e.g. backup link in a bond).
+ *
+ * @rx_otherhost_dropped: Number of packets dropped due to mismatch
+ *   in destination MAC address.
  */
 struct rtnl_link_stats64 {
 	__u64	rx_packets;
@@ -243,6 +246,8 @@ struct rtnl_link_stats64 {
 	__u64	rx_compressed;
 	__u64	tx_compressed;
 	__u64	rx_nohandler;
+
+	__u64	rx_otherhost_dropped;
 };
 
 /* Subset of link stats useful for in-HW collection. Meaning of the fields is as
diff --git a/net/core/dev.c b/net/core/dev.c
index f00d29856b43..e027410e861b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10358,6 +10358,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 			storage->rx_dropped += local_read(&core_stats->rx_dropped);
 			storage->tx_dropped += local_read(&core_stats->tx_dropped);
 			storage->rx_nohandler += local_read(&core_stats->rx_nohandler);
+			storage->rx_otherhost_dropped += local_read(&core_stats->rx_otherhost_dropped);
 		}
 	}
 	return storage;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 95f7bb052784..b1165f717cd1 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -451,6 +451,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 	 * that it receives, do not try to analyse it.
 	 */
 	if (skb->pkt_type == PACKET_OTHERHOST) {
+		dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
 		drop_reason = SKB_DROP_REASON_OTHERHOST;
 		goto drop;
 	}
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 5b5ea35635f9..b4880c7c84eb 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -150,6 +150,7 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 	struct inet6_dev *idev;
 
 	if (skb->pkt_type == PACKET_OTHERHOST) {
+		dev_core_stats_rx_otherhost_dropped_inc(skb->dev);
 		kfree_skb(skb);
 		return NULL;
 	}
-- 
cgit v1.2.3


From bdae79651453df0bca20963fc2ab970146ef2a37 Mon Sep 17 00:00:00 2001
From: Shuai Xue <xueshuai@linux.alibaba.com>
Date: Tue, 8 Mar 2022 22:40:51 +0800
Subject: efi/cper: Add a cper_mem_err_status_str() to decode error description

Introduce a new helper function cper_mem_err_status_str() to decode the
error status value into a human readable string.

  [ bp: Massage. ]

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20220308144053.49090-2-xueshuai@linux.alibaba.com
---
 drivers/firmware/efi/cper.c | 30 +++++++++++++++++++++++++++++-
 include/linux/cper.h        |  1 +
 2 files changed, 30 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 6ec8edec6329..34eeaa59f04a 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -211,6 +211,32 @@ const char *cper_mem_err_type_str(unsigned int etype)
 }
 EXPORT_SYMBOL_GPL(cper_mem_err_type_str);
 
+const char *cper_mem_err_status_str(u64 status)
+{
+	switch ((status >> 8) & 0xff) {
+	case  1:	return "Error detected internal to the component";
+	case  4:	return "Storage error in DRAM memory";
+	case  5:	return "Storage error in TLB";
+	case  6:	return "Storage error in cache";
+	case  7:	return "Error in one or more functional units";
+	case  8:	return "Component failed self test";
+	case  9:	return "Overflow or undervalue of internal queue";
+	case 16:	return "Error detected in the bus";
+	case 17:	return "Virtual address not found on IO-TLB or IO-PDIR";
+	case 18:	return "Improper access error";
+	case 19:	return "Access to a memory address which is not mapped to any component";
+	case 20:	return "Loss of Lockstep";
+	case 21:	return "Response not associated with a request";
+	case 22:	return "Bus parity error - must also set the A, C, or D Bits";
+	case 23:	return "Detection of a protocol error";
+	case 24:	return "Detection of a PATH_ERROR";
+	case 25:	return "Bus operation timeout";
+	case 26:	return "A read was issued to data that has been poisoned";
+	default:	return "Reserved";
+	}
+}
+EXPORT_SYMBOL_GPL(cper_mem_err_status_str);
+
 static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 {
 	u32 len, n;
@@ -334,7 +360,9 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem,
 		return;
 	}
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
-		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
+		printk("%s error_status: %s (0x%016llx)\n",
+		       pfx, cper_mem_err_status_str(mem->error_status),
+		       mem->error_status);
 	if (mem->validation_bits & CPER_MEM_VALID_PA)
 		printk("%s""physical_address: 0x%016llx\n",
 		       pfx, mem->physical_addr);
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 6a511a1078ca..5b1dd27b317d 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -558,6 +558,7 @@ extern const char *const cper_proc_error_type_strs[4];
 u64 cper_next_record_id(void);
 const char *cper_severity_str(unsigned int);
 const char *cper_mem_err_type_str(unsigned int);
+const char *cper_mem_err_status_str(u64 status);
 void cper_print_bits(const char *prefix, unsigned int bits,
 		     const char * const strs[], unsigned int strs_size);
 void cper_mem_err_pack(const struct cper_sec_mem_err *,
-- 
cgit v1.2.3


From ed27b5df3877458eb24615fd9c202178660db009 Mon Sep 17 00:00:00 2001
From: Shuai Xue <xueshuai@linux.alibaba.com>
Date: Tue, 8 Mar 2022 22:40:52 +0800
Subject: EDAC/ghes: Unify CPER memory error location reporting

Switch the GHES EDAC memory error reporting functions to use the common
CPER ones and get rid of code duplication.

  [ bp:
      - rewrite commit message, remove useless text
      - rip out useless reformatting
      - align function params on the opening brace
      - rename function to a more descriptive name
      - drop useless function exports
      - handle buffer lengths properly when printing other detail
      - remove useless casting
  ]

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20220308144053.49090-3-xueshuai@linux.alibaba.com
---
 drivers/edac/Kconfig        |   1 +
 drivers/edac/ghes_edac.c    | 200 ++++++++------------------------------------
 drivers/firmware/efi/cper.c |   4 +-
 include/linux/cper.h        |   2 +
 4 files changed, 42 insertions(+), 165 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 58ab63642e72..23f11554f400 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -55,6 +55,7 @@ config EDAC_DECODE_MCE
 config EDAC_GHES
 	bool "Output ACPI APEI/GHES BIOS detected errors via EDAC"
 	depends on ACPI_APEI_GHES && (EDAC=y)
+	select UEFI_CPER
 	help
 	  Not all machines support hardware-driven error report. Some of those
 	  provide a BIOS-driven error report mechanism via ACPI, using the
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 6d1ddecbf0da..2805d5610300 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -15,11 +15,13 @@
 #include "edac_module.h"
 #include <ras/ras_event.h>
 
+#define OTHER_DETAIL_LEN	400
+
 struct ghes_pvt {
 	struct mem_ctl_info *mci;
 
 	/* Buffers for the error handling routine */
-	char other_detail[400];
+	char other_detail[OTHER_DETAIL_LEN];
 	char msg[80];
 };
 
@@ -235,8 +237,34 @@ static void ghes_scan_system(void)
 	system_scanned = true;
 }
 
+static int print_mem_error_other_detail(const struct cper_sec_mem_err *mem, char *msg,
+					const char *location, unsigned int len)
+{
+	u32 n;
+
+	if (!msg)
+		return 0;
+
+	n = 0;
+	len -= 1;
+
+	n += scnprintf(msg + n, len - n, "APEI location: %s ", location);
+
+	if (!(mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS))
+		goto out;
+
+	n += scnprintf(msg + n, len - n, "status(0x%016llx): ", mem->error_status);
+	n += scnprintf(msg + n, len - n, "%s ", cper_mem_err_status_str(mem->error_status));
+
+out:
+	msg[n] = '\0';
+
+	return n;
+}
+
 void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 {
+	struct cper_mem_err_compact cmem;
 	struct edac_raw_error_desc *e;
 	struct mem_ctl_info *mci;
 	struct ghes_pvt *pvt;
@@ -292,60 +320,10 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	/* Error type, mapped on e->msg */
 	if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {
+		u8 etype = mem_err->error_type;
+
 		p = pvt->msg;
-		switch (mem_err->error_type) {
-		case 0:
-			p += sprintf(p, "Unknown");
-			break;
-		case 1:
-			p += sprintf(p, "No error");
-			break;
-		case 2:
-			p += sprintf(p, "Single-bit ECC");
-			break;
-		case 3:
-			p += sprintf(p, "Multi-bit ECC");
-			break;
-		case 4:
-			p += sprintf(p, "Single-symbol ChipKill ECC");
-			break;
-		case 5:
-			p += sprintf(p, "Multi-symbol ChipKill ECC");
-			break;
-		case 6:
-			p += sprintf(p, "Master abort");
-			break;
-		case 7:
-			p += sprintf(p, "Target abort");
-			break;
-		case 8:
-			p += sprintf(p, "Parity Error");
-			break;
-		case 9:
-			p += sprintf(p, "Watchdog timeout");
-			break;
-		case 10:
-			p += sprintf(p, "Invalid address");
-			break;
-		case 11:
-			p += sprintf(p, "Mirror Broken");
-			break;
-		case 12:
-			p += sprintf(p, "Memory Sparing");
-			break;
-		case 13:
-			p += sprintf(p, "Scrub corrected error");
-			break;
-		case 14:
-			p += sprintf(p, "Scrub uncorrected error");
-			break;
-		case 15:
-			p += sprintf(p, "Physical Memory Map-out event");
-			break;
-		default:
-			p += sprintf(p, "reserved error (%d)",
-				     mem_err->error_type);
-		}
+		p += snprintf(p, sizeof(pvt->msg), "%s", cper_mem_err_type_str(etype));
 	} else {
 		strcpy(pvt->msg, "unknown error");
 	}
@@ -362,52 +340,19 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	/* Memory error location, mapped on e->location */
 	p = e->location;
-	if (mem_err->validation_bits & CPER_MEM_VALID_NODE)
-		p += sprintf(p, "node:%d ", mem_err->node);
-	if (mem_err->validation_bits & CPER_MEM_VALID_CARD)
-		p += sprintf(p, "card:%d ", mem_err->card);
-	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE)
-		p += sprintf(p, "module:%d ", mem_err->module);
-	if (mem_err->validation_bits & CPER_MEM_VALID_RANK_NUMBER)
-		p += sprintf(p, "rank:%d ", mem_err->rank);
-	if (mem_err->validation_bits & CPER_MEM_VALID_BANK)
-		p += sprintf(p, "bank:%d ", mem_err->bank);
-	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_GROUP)
-		p += sprintf(p, "bank_group:%d ",
-			     mem_err->bank >> CPER_MEM_BANK_GROUP_SHIFT);
-	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)
-		p += sprintf(p, "bank_address:%d ",
-			     mem_err->bank & CPER_MEM_BANK_ADDRESS_MASK);
-	if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
-		u32 row = mem_err->row;
-
-		row |= cper_get_mem_extension(mem_err->validation_bits, mem_err->extended);
-		p += sprintf(p, "row:%d ", row);
-	}
-	if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN)
-		p += sprintf(p, "col:%d ", mem_err->column);
-	if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION)
-		p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos);
+	cper_mem_err_pack(mem_err, &cmem);
+	p += cper_mem_err_location(&cmem, p);
+
 	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {
-		const char *bank = NULL, *device = NULL;
 		struct dimm_info *dimm;
 
-		dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device);
-		if (bank != NULL && device != NULL)
-			p += sprintf(p, "DIMM location:%s %s ", bank, device);
-		else
-			p += sprintf(p, "DIMM DMI handle: 0x%.4x ",
-				     mem_err->mem_dev_handle);
-
+		p += cper_dimm_err_location(&cmem, p);
 		dimm = find_dimm_by_handle(mci, mem_err->mem_dev_handle);
 		if (dimm) {
 			e->top_layer = dimm->idx;
 			strcpy(e->label, dimm->label);
 		}
 	}
-	if (mem_err->validation_bits & CPER_MEM_VALID_CHIP_ID)
-		p += sprintf(p, "chipID: %d ",
-			     mem_err->extended >> CPER_MEM_CHIP_ID_SHIFT);
 	if (p > e->location)
 		*(p - 1) = '\0';
 
@@ -416,78 +361,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	/* All other fields are mapped on e->other_detail */
 	p = pvt->other_detail;
-	p += snprintf(p, sizeof(pvt->other_detail),
-		"APEI location: %s ", e->location);
-	if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) {
-		u64 status = mem_err->error_status;
-
-		p += sprintf(p, "status(0x%016llx): ", (long long)status);
-		switch ((status >> 8) & 0xff) {
-		case 1:
-			p += sprintf(p, "Error detected internal to the component ");
-			break;
-		case 16:
-			p += sprintf(p, "Error detected in the bus ");
-			break;
-		case 4:
-			p += sprintf(p, "Storage error in DRAM memory ");
-			break;
-		case 5:
-			p += sprintf(p, "Storage error in TLB ");
-			break;
-		case 6:
-			p += sprintf(p, "Storage error in cache ");
-			break;
-		case 7:
-			p += sprintf(p, "Error in one or more functional units ");
-			break;
-		case 8:
-			p += sprintf(p, "component failed self test ");
-			break;
-		case 9:
-			p += sprintf(p, "Overflow or undervalue of internal queue ");
-			break;
-		case 17:
-			p += sprintf(p, "Virtual address not found on IO-TLB or IO-PDIR ");
-			break;
-		case 18:
-			p += sprintf(p, "Improper access error ");
-			break;
-		case 19:
-			p += sprintf(p, "Access to a memory address which is not mapped to any component ");
-			break;
-		case 20:
-			p += sprintf(p, "Loss of Lockstep ");
-			break;
-		case 21:
-			p += sprintf(p, "Response not associated with a request ");
-			break;
-		case 22:
-			p += sprintf(p, "Bus parity error - must also set the A, C, or D Bits ");
-			break;
-		case 23:
-			p += sprintf(p, "Detection of a PATH_ERROR ");
-			break;
-		case 25:
-			p += sprintf(p, "Bus operation timeout ");
-			break;
-		case 26:
-			p += sprintf(p, "A read was issued to data that has been poisoned ");
-			break;
-		default:
-			p += sprintf(p, "reserved ");
-			break;
-		}
-	}
-	if (mem_err->validation_bits & CPER_MEM_VALID_REQUESTOR_ID)
-		p += sprintf(p, "requestorID: 0x%016llx ",
-			     (long long)mem_err->requestor_id);
-	if (mem_err->validation_bits & CPER_MEM_VALID_RESPONDER_ID)
-		p += sprintf(p, "responderID: 0x%016llx ",
-			     (long long)mem_err->responder_id);
-	if (mem_err->validation_bits & CPER_MEM_VALID_TARGET_ID)
-		p += sprintf(p, "targetID: 0x%016llx ",
-			     (long long)mem_err->responder_id);
+	p += print_mem_error_other_detail(mem_err, p, e->location, OTHER_DETAIL_LEN);
 	if (p > pvt->other_detail)
 		*(p - 1) = '\0';
 
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 34eeaa59f04a..215c778fb33c 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -237,7 +237,7 @@ const char *cper_mem_err_status_str(u64 status)
 }
 EXPORT_SYMBOL_GPL(cper_mem_err_status_str);
 
-static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
+int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 {
 	u32 len, n;
 
@@ -291,7 +291,7 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 	return n;
 }
 
-static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg)
+int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg)
 {
 	u32 len, n;
 	const char *bank = NULL, *device = NULL;
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 5b1dd27b317d..eacb7dd7b3af 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -569,5 +569,7 @@ void cper_print_proc_arm(const char *pfx,
 			 const struct cper_sec_proc_arm *proc);
 void cper_print_proc_ia(const char *pfx,
 			const struct cper_sec_proc_ia *proc);
+int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg);
+int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg);
 
 #endif
-- 
cgit v1.2.3


From 85ebb1a6bd62147ebcfa70500d513331a8daf9e0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Apr 2022 13:35:52 +0300
Subject: gpiolib: Introduce for_each_gpiochip_node() loop helper

Introduce for_each_gpiochip_node() loop helper which iterates over
the GPIO controller child nodes of a given device.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 include/linux/gpio/driver.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 98c93510640e..bfc91f122d5f 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -3,13 +3,14 @@
 #define __LINUX_GPIO_DRIVER_H
 
 #include <linux/device.h>
-#include <linux/types.h>
 #include <linux/irq.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/lockdep.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/pinctrl/pinconf-generic.h>
+#include <linux/property.h>
+#include <linux/types.h>
 
 struct gpio_desc;
 struct of_phandle_args;
@@ -750,4 +751,8 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc,
 }
 #endif /* CONFIG_GPIOLIB */
 
+#define for_each_gpiochip_node(dev, child)					\
+	device_for_each_child_node(dev, child)					\
+		if (!fwnode_property_present(child, "gpio-controller")) {} else
+
 #endif /* __LINUX_GPIO_DRIVER_H */
-- 
cgit v1.2.3


From 0b19dde90ad004592792a928c75e80612be3e2e8 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 1 Apr 2022 13:35:53 +0300
Subject: gpiolib: Introduce gpiochip_node_count() helper

The gpiochip_node_count() helper iterates over the device child nodes that
have the "gpio-controller" property set. It returns the number of such nodes
under a given device.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 include/linux/gpio/driver.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index bfc91f122d5f..12de0b22b4ef 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -755,4 +755,15 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc,
 	device_for_each_child_node(dev, child)					\
 		if (!fwnode_property_present(child, "gpio-controller")) {} else
 
+static inline unsigned int gpiochip_node_count(struct device *dev)
+{
+	struct fwnode_handle *child;
+	unsigned int count = 0;
+
+	for_each_gpiochip_node(dev, child)
+		count++;
+
+	return count;
+}
+
 #endif /* __LINUX_GPIO_DRIVER_H */
-- 
cgit v1.2.3


From 2fa33b3518a8da0a5345b7ae0064223b5e4e156f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 6 Apr 2022 11:25:36 +0300
Subject: net/mlx5_fpga: Drop INNOVA IPsec support

Mellanox INNOVA IPsec cards are EOL in Nov, 2019 [1]. As such, the code
is unmaintained, untested and not in-use by any upstream/distro oriented
customers. In order to reduce code complexity, drop the kernel code.

[1] https://network.nvidia.com/related-docs/eol/LCR-000535.pdf

Link: https://lore.kernel.org/r/2afe88ec5020a491079eacf6fe3c89b64d65195c.1649232994.git.leonro@nvidia.com
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    |   14 +-
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |    1 -
 .../net/ethernet/mellanox/mlx5/core/accel/ipsec.c  |    6 +-
 .../net/ethernet/mellanox/mlx5/core/en/params.c    |    7 -
 .../mellanox/mlx5/core/en_accel/ipsec_stats.c      |   17 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |    7 -
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |   54 +-
 .../net/ethernet/mellanox/mlx5/core/fpga/core.h    |    2 -
 .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.c   | 1582 --------------------
 .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.h   |   62 -
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c  |    9 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |    2 -
 include/linux/mlx5/mlx5_ifc_fpga.h                 |  148 --
 13 files changed, 5 insertions(+), 1906 deletions(-)
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 0c82b376416b..e34e64a9ff4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -22,7 +22,6 @@ config MLX5_ACCEL
 config MLX5_FPGA
 	bool "Mellanox Technologies Innova support"
 	depends on MLX5_CORE
-	select MLX5_ACCEL
 	help
 	  Build support for the Innova family of network cards by Mellanox
 	  Technologies. Innova network cards are comprised of a ConnectX chip
@@ -143,17 +142,6 @@ config MLX5_CORE_IPOIB
 	help
 	  MLX5 IPoIB offloads & acceleration support.
 
-config MLX5_FPGA_IPSEC
-	bool "Mellanox Technologies IPsec Innova support"
-	depends on MLX5_CORE
-	depends on MLX5_FPGA
-	help
-	Build IPsec support for the Innova family of network cards by Mellanox
-	Technologies. Innova network cards are comprised of a ConnectX chip
-	and an FPGA chip on one board. If you select this option, the
-	mlx5_core driver will include the Innova FPGA core and allow building
-	sandbox-specific client drivers.
-
 config MLX5_IPSEC
 	bool "Mellanox Technologies IPsec Connect-X support"
 	depends on MLX5_CORE_EN
@@ -171,7 +159,7 @@ config MLX5_EN_IPSEC
 	depends on MLX5_CORE_EN
 	depends on XFRM_OFFLOAD
 	depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
-	depends on MLX5_FPGA_IPSEC || MLX5_IPSEC
+	depends on MLX5_IPSEC
 	help
 	  Build support for IPsec cryptography-offload acceleration in the NIC.
 	  Note: Support for hardware with this capability needs to be selected
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 44ff1623707a..e50361656305 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -89,7 +89,6 @@ mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib
 # Accelerations & FPGA
 #
 mlx5_core-$(CONFIG_MLX5_IPSEC) += accel/ipsec_offload.o
-mlx5_core-$(CONFIG_MLX5_FPGA_IPSEC) += fpga/ipsec.o
 mlx5_core-$(CONFIG_MLX5_ACCEL)      += lib/crypto.o accel/ipsec.o
 
 mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
index 09f5ce97af46..45296ec2d055 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
@@ -35,7 +35,6 @@
 
 #include "accel/ipsec.h"
 #include "mlx5_core.h"
-#include "fpga/ipsec.h"
 #include "accel/ipsec_offload.h"
 
 void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
@@ -43,10 +42,7 @@ void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
 	const struct mlx5_accel_ipsec_ops *ipsec_ops;
 	int err = 0;
 
-	ipsec_ops = (mlx5_ipsec_offload_ops(mdev)) ?
-		     mlx5_ipsec_offload_ops(mdev) :
-		     mlx5_fpga_ipsec_ops(mdev);
-
+	ipsec_ops = mlx5_ipsec_offload_ops(mdev);
 	if (!ipsec_ops || !ipsec_ops->init) {
 		mlx5_core_dbg(mdev, "IPsec ops is not supported\n");
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 7f76c4f9389b..ebb12817b795 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -6,7 +6,6 @@
 #include "en/port.h"
 #include "en_accel/en_accel.h"
 #include "accel/ipsec.h"
-#include "fpga/ipsec.h"
 
 static bool mlx5e_rx_is_xdp(struct mlx5e_params *params,
 			    struct mlx5e_xsk_param *xsk)
@@ -327,9 +326,6 @@ bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 	if (!mlx5e_check_fragmented_striding_rq_cap(mdev))
 		return false;
 
-	if (mlx5_fpga_is_ipsec_device(mdev))
-		return false;
-
 	if (params->xdp_prog) {
 		/* XSK params are not considered here. If striding RQ is in use,
 		 * and an XSK is being opened, mlx5e_rx_mpwqe_is_linear_skb will
@@ -423,9 +419,6 @@ static int mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
 	int max_mtu;
 	int i;
 
-	if (mlx5_fpga_is_ipsec_device(mdev))
-		byte_count += MLX5E_METADATA_ETHER_LEN;
-
 	if (mlx5e_rx_is_linear_skb(params, xsk)) {
 		int frag_stride;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
index 5cb936541b9e..1607c305d3ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
@@ -38,7 +38,6 @@
 #include "accel/ipsec.h"
 #include "fpga/sdk.h"
 #include "en_accel/ipsec.h"
-#include "fpga/ipsec.h"
 
 static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_stats, ipsec_dec_in_packets) },
@@ -105,7 +104,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_sw)
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_hw)
 {
-	return (priv->ipsec && mlx5_fpga_ipsec_device_caps(priv->mdev)) ? NUM_IPSEC_HW_COUNTERS : 0;
+	return 0;
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_hw)
@@ -121,25 +120,11 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_hw)
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec_hw)
 {
-	unsigned int i;
-
-	if (priv->ipsec && mlx5_fpga_ipsec_device_caps(priv->mdev))
-		for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++)
-			strcpy(data + (idx++) * ETH_GSTRING_LEN,
-			       mlx5e_ipsec_hw_stats_desc[i].format);
-
 	return idx;
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_hw)
 {
-	int i;
-
-	if (priv->ipsec && mlx5_fpga_ipsec_device_caps(priv->mdev))
-		for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++)
-			data[idx++] = MLX5E_READ_CTR64_CPU(&priv->ipsec->stats,
-							   mlx5e_ipsec_hw_stats_desc,
-							   i);
 	return idx;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 89a85030b0eb..0a303879d0f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -67,7 +67,6 @@
 #include "en/ptp.h"
 #include "qos.h"
 #include "en/trap.h"
-#include "fpga/ipsec.h"
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
@@ -4467,12 +4466,6 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 		return -EINVAL;
 	}
 
-	if (mlx5_fpga_is_ipsec_device(priv->mdev)) {
-		netdev_warn(netdev,
-			    "XDP is not available on Innova cards with IPsec support\n");
-		return -EINVAL;
-	}
-
 	new_params = priv->channels.params;
 	new_params.xdp_prog = prog;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 84cebf4c5ada..a180c80e9f68 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -49,7 +49,6 @@
 #include "en/rep/tc.h"
 #include "ipoib/ipoib.h"
 #include "accel/ipsec.h"
-#include "fpga/ipsec.h"
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/ktls_txrx.h"
 #include "en/xdp.h"
@@ -2384,46 +2383,6 @@ const struct mlx5e_rx_handlers mlx5i_rx_handlers = {
 };
 #endif /* CONFIG_MLX5_CORE_IPOIB */
 
-#ifdef CONFIG_MLX5_EN_IPSEC
-
-static void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
-{
-	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
-	struct mlx5e_wqe_frag_info *wi;
-	struct sk_buff *skb;
-	u32 cqe_bcnt;
-	u16 ci;
-
-	ci       = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter));
-	wi       = get_frag(rq, ci);
-	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
-
-	if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
-		rq->stats->wqe_err++;
-		goto wq_free_wqe;
-	}
-
-	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
-			      mlx5e_skb_from_cqe_linear,
-			      mlx5e_skb_from_cqe_nonlinear,
-			      rq, cqe, wi, cqe_bcnt);
-	if (unlikely(!skb)) /* a DROP, save the page-reuse checks */
-		goto wq_free_wqe;
-
-	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt);
-	if (unlikely(!skb))
-		goto wq_free_wqe;
-
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
-	napi_gro_receive(rq->cq.napi, skb);
-
-wq_free_wqe:
-	mlx5e_free_rx_wqe(rq, wi, true);
-	mlx5_wq_cyc_pop(wq);
-}
-
-#endif /* CONFIG_MLX5_EN_IPSEC */
-
 int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool xsk)
 {
 	struct net_device *netdev = rq->netdev;
@@ -2440,10 +2399,6 @@ int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool
 		rq->post_wqes = mlx5e_post_rx_mpwqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
-		if (mlx5_fpga_is_ipsec_device(mdev)) {
-			netdev_err(netdev, "MPWQE RQ with Innova IPSec offload not supported\n");
-			return -EINVAL;
-		}
 		if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) {
 			rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe_shampo;
 			if (!rq->handle_rx_cqe) {
@@ -2467,14 +2422,7 @@ int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool
 				mlx5e_skb_from_cqe_nonlinear;
 		rq->post_wqes = mlx5e_post_rx_wqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
-
-#ifdef CONFIG_MLX5_EN_IPSEC
-		if ((mlx5_fpga_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_DEVICE) &&
-		    priv->ipsec)
-			rq->handle_rx_cqe = mlx5e_ipsec_handle_rx_cqe;
-		else
-#endif
-			rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe;
+		rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe;
 		if (!rq->handle_rx_cqe) {
 			netdev_err(netdev, "RX handler of RQ is not set\n");
 			return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
index e9e72d260681..750c32050165 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
@@ -57,8 +57,6 @@ struct mlx5_fpga_device {
 		u32 mkey;
 		struct mlx5_uars_page *uar;
 	} conn_res;
-
-	struct mlx5_fpga_ipsec *ipsec;
 };
 
 #define mlx5_fpga_dbg(__adev, format, ...) \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
deleted file mode 100644
index 8ec148010d62..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ /dev/null
@@ -1,1582 +0,0 @@
-/*
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#include <linux/rhashtable.h>
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/fs_helpers.h>
-#include <linux/mlx5/fs.h>
-#include <linux/rbtree.h>
-
-#include "mlx5_core.h"
-#include "fs_cmd.h"
-#include "fpga/ipsec.h"
-#include "fpga/sdk.h"
-#include "fpga/core.h"
-
-enum mlx5_fpga_ipsec_cmd_status {
-	MLX5_FPGA_IPSEC_CMD_PENDING,
-	MLX5_FPGA_IPSEC_CMD_SEND_FAIL,
-	MLX5_FPGA_IPSEC_CMD_COMPLETE,
-};
-
-struct mlx5_fpga_ipsec_cmd_context {
-	struct mlx5_fpga_dma_buf buf;
-	enum mlx5_fpga_ipsec_cmd_status status;
-	struct mlx5_ifc_fpga_ipsec_cmd_resp resp;
-	int status_code;
-	struct completion complete;
-	struct mlx5_fpga_device *dev;
-	struct list_head list; /* Item in pending_cmds */
-	u8 command[];
-};
-
-struct mlx5_fpga_esp_xfrm;
-
-struct mlx5_fpga_ipsec_sa_ctx {
-	struct rhash_head		hash;
-	struct mlx5_ifc_fpga_ipsec_sa	hw_sa;
-	u32				sa_handle;
-	struct mlx5_core_dev		*dev;
-	struct mlx5_fpga_esp_xfrm	*fpga_xfrm;
-};
-
-struct mlx5_fpga_esp_xfrm {
-	unsigned int			num_rules;
-	struct mlx5_fpga_ipsec_sa_ctx	*sa_ctx;
-	struct mutex			lock; /* xfrm lock */
-	struct mlx5_accel_esp_xfrm	accel_xfrm;
-};
-
-struct mlx5_fpga_ipsec_rule {
-	struct rb_node			node;
-	struct fs_fte			*fte;
-	struct mlx5_fpga_ipsec_sa_ctx	*ctx;
-};
-
-static const struct rhashtable_params rhash_sa = {
-	/* Keep out "cmd" field from the key as it's
-	 * value is not constant during the lifetime
-	 * of the key object.
-	 */
-	.key_len = sizeof_field(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) -
-		   sizeof_field(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd),
-	.key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) +
-		      sizeof_field(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd),
-	.head_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hash),
-	.automatic_shrinking = true,
-	.min_size = 1,
-};
-
-struct mlx5_fpga_ipsec {
-	struct mlx5_fpga_device *fdev;
-	struct list_head pending_cmds;
-	spinlock_t pending_cmds_lock; /* Protects pending_cmds */
-	u32 caps[MLX5_ST_SZ_DW(ipsec_extended_cap)];
-	struct mlx5_fpga_conn *conn;
-
-	struct notifier_block	fs_notifier_ingress_bypass;
-	struct notifier_block	fs_notifier_egress;
-
-	/* Map hardware SA           -->  SA context
-	 *     (mlx5_fpga_ipsec_sa)       (mlx5_fpga_ipsec_sa_ctx)
-	 * We will use this hash to avoid SAs duplication in fpga which
-	 * aren't allowed
-	 */
-	struct rhashtable sa_hash;	/* hw_sa -> mlx5_fpga_ipsec_sa_ctx */
-	struct mutex sa_hash_lock;
-
-	/* Tree holding all rules for this fpga device
-	 * Key for searching a rule (mlx5_fpga_ipsec_rule) is (ft, id)
-	 */
-	struct rb_root rules_rb;
-	struct mutex rules_rb_lock; /* rules lock */
-
-	struct ida halloc;
-};
-
-bool mlx5_fpga_is_ipsec_device(struct mlx5_core_dev *mdev)
-{
-	if (!mdev->fpga || !MLX5_CAP_GEN(mdev, fpga))
-		return false;
-
-	if (MLX5_CAP_FPGA(mdev, ieee_vendor_id) !=
-	    MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX)
-		return false;
-
-	if (MLX5_CAP_FPGA(mdev, sandbox_product_id) !=
-	    MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC)
-		return false;
-
-	return true;
-}
-
-static void mlx5_fpga_ipsec_send_complete(struct mlx5_fpga_conn *conn,
-					  struct mlx5_fpga_device *fdev,
-					  struct mlx5_fpga_dma_buf *buf,
-					  u8 status)
-{
-	struct mlx5_fpga_ipsec_cmd_context *context;
-
-	if (status) {
-		context = container_of(buf, struct mlx5_fpga_ipsec_cmd_context,
-				       buf);
-		mlx5_fpga_warn(fdev, "IPSec command send failed with status %u\n",
-			       status);
-		context->status = MLX5_FPGA_IPSEC_CMD_SEND_FAIL;
-		complete(&context->complete);
-	}
-}
-
-static inline
-int syndrome_to_errno(enum mlx5_ifc_fpga_ipsec_response_syndrome syndrome)
-{
-	switch (syndrome) {
-	case MLX5_FPGA_IPSEC_RESPONSE_SUCCESS:
-		return 0;
-	case MLX5_FPGA_IPSEC_RESPONSE_SADB_ISSUE:
-		return -EEXIST;
-	case MLX5_FPGA_IPSEC_RESPONSE_ILLEGAL_REQUEST:
-		return -EINVAL;
-	case MLX5_FPGA_IPSEC_RESPONSE_WRITE_RESPONSE_ISSUE:
-		return -EIO;
-	}
-	return -EIO;
-}
-
-static void mlx5_fpga_ipsec_recv(void *cb_arg, struct mlx5_fpga_dma_buf *buf)
-{
-	struct mlx5_ifc_fpga_ipsec_cmd_resp *resp = buf->sg[0].data;
-	struct mlx5_fpga_ipsec_cmd_context *context;
-	enum mlx5_ifc_fpga_ipsec_response_syndrome syndrome;
-	struct mlx5_fpga_device *fdev = cb_arg;
-	unsigned long flags;
-
-	if (buf->sg[0].size < sizeof(*resp)) {
-		mlx5_fpga_warn(fdev, "Short receive from FPGA IPSec: %u < %zu bytes\n",
-			       buf->sg[0].size, sizeof(*resp));
-		return;
-	}
-
-	mlx5_fpga_dbg(fdev, "mlx5_ipsec recv_cb syndrome %08x\n",
-		      ntohl(resp->syndrome));
-
-	spin_lock_irqsave(&fdev->ipsec->pending_cmds_lock, flags);
-	context = list_first_entry_or_null(&fdev->ipsec->pending_cmds,
-					   struct mlx5_fpga_ipsec_cmd_context,
-					   list);
-	if (context)
-		list_del(&context->list);
-	spin_unlock_irqrestore(&fdev->ipsec->pending_cmds_lock, flags);
-
-	if (!context) {
-		mlx5_fpga_warn(fdev, "Received IPSec offload response without pending command request\n");
-		return;
-	}
-	mlx5_fpga_dbg(fdev, "Handling response for %p\n", context);
-
-	syndrome = ntohl(resp->syndrome);
-	context->status_code = syndrome_to_errno(syndrome);
-	context->status = MLX5_FPGA_IPSEC_CMD_COMPLETE;
-	memcpy(&context->resp, resp, sizeof(*resp));
-
-	if (context->status_code)
-		mlx5_fpga_warn(fdev, "IPSec command failed with syndrome %08x\n",
-			       syndrome);
-
-	complete(&context->complete);
-}
-
-static void *mlx5_fpga_ipsec_cmd_exec(struct mlx5_core_dev *mdev,
-				      const void *cmd, int cmd_size)
-{
-	struct mlx5_fpga_ipsec_cmd_context *context;
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-	unsigned long flags;
-	int res;
-
-	if (!fdev || !fdev->ipsec)
-		return ERR_PTR(-EOPNOTSUPP);
-
-	if (cmd_size & 3)
-		return ERR_PTR(-EINVAL);
-
-	context = kzalloc(sizeof(*context) + cmd_size, GFP_ATOMIC);
-	if (!context)
-		return ERR_PTR(-ENOMEM);
-
-	context->status = MLX5_FPGA_IPSEC_CMD_PENDING;
-	context->dev = fdev;
-	context->buf.complete = mlx5_fpga_ipsec_send_complete;
-	init_completion(&context->complete);
-	memcpy(&context->command, cmd, cmd_size);
-	context->buf.sg[0].size = cmd_size;
-	context->buf.sg[0].data = &context->command;
-
-	spin_lock_irqsave(&fdev->ipsec->pending_cmds_lock, flags);
-	res = mlx5_fpga_sbu_conn_sendmsg(fdev->ipsec->conn, &context->buf);
-	if (!res)
-		list_add_tail(&context->list, &fdev->ipsec->pending_cmds);
-	spin_unlock_irqrestore(&fdev->ipsec->pending_cmds_lock, flags);
-
-	if (res) {
-		mlx5_fpga_warn(fdev, "Failed to send IPSec command: %d\n", res);
-		kfree(context);
-		return ERR_PTR(res);
-	}
-
-	/* Context should be freed by the caller after completion. */
-	return context;
-}
-
-static int mlx5_fpga_ipsec_cmd_wait(void *ctx)
-{
-	struct mlx5_fpga_ipsec_cmd_context *context = ctx;
-	unsigned long timeout =
-		msecs_to_jiffies(MLX5_FPGA_CMD_TIMEOUT_MSEC);
-	int res;
-
-	res = wait_for_completion_timeout(&context->complete, timeout);
-	if (!res) {
-		mlx5_fpga_warn(context->dev, "Failure waiting for IPSec command response\n");
-		return -ETIMEDOUT;
-	}
-
-	if (context->status == MLX5_FPGA_IPSEC_CMD_COMPLETE)
-		res = context->status_code;
-	else
-		res = -EIO;
-
-	return res;
-}
-
-static inline bool is_v2_sadb_supported(struct mlx5_fpga_ipsec *fipsec)
-{
-	if (MLX5_GET(ipsec_extended_cap, fipsec->caps, v2_command))
-		return true;
-	return false;
-}
-
-static int mlx5_fpga_ipsec_update_hw_sa(struct mlx5_fpga_device *fdev,
-					struct mlx5_ifc_fpga_ipsec_sa *hw_sa,
-					int opcode)
-{
-	struct mlx5_core_dev *dev = fdev->mdev;
-	struct mlx5_ifc_fpga_ipsec_sa *sa;
-	struct mlx5_fpga_ipsec_cmd_context *cmd_context;
-	size_t sa_cmd_size;
-	int err;
-
-	hw_sa->ipsec_sa_v1.cmd = htonl(opcode);
-	if (is_v2_sadb_supported(fdev->ipsec))
-		sa_cmd_size = sizeof(*hw_sa);
-	else
-		sa_cmd_size = sizeof(hw_sa->ipsec_sa_v1);
-
-	cmd_context = (struct mlx5_fpga_ipsec_cmd_context *)
-			mlx5_fpga_ipsec_cmd_exec(dev, hw_sa, sa_cmd_size);
-	if (IS_ERR(cmd_context))
-		return PTR_ERR(cmd_context);
-
-	err = mlx5_fpga_ipsec_cmd_wait(cmd_context);
-	if (err)
-		goto out;
-
-	sa = (struct mlx5_ifc_fpga_ipsec_sa *)&cmd_context->command;
-	if (sa->ipsec_sa_v1.sw_sa_handle != cmd_context->resp.sw_sa_handle) {
-		mlx5_fpga_err(fdev, "mismatch SA handle. cmd 0x%08x vs resp 0x%08x\n",
-			      ntohl(sa->ipsec_sa_v1.sw_sa_handle),
-			      ntohl(cmd_context->resp.sw_sa_handle));
-		err = -EIO;
-	}
-
-out:
-	kfree(cmd_context);
-	return err;
-}
-
-u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-	u32 ret = 0;
-
-	if (mlx5_fpga_is_ipsec_device(mdev)) {
-		ret |= MLX5_ACCEL_IPSEC_CAP_DEVICE;
-		ret |= MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA;
-	} else {
-		return ret;
-	}
-
-	if (!fdev->ipsec)
-		return ret;
-
-	if (MLX5_GET(ipsec_extended_cap, fdev->ipsec->caps, esp))
-		ret |= MLX5_ACCEL_IPSEC_CAP_ESP;
-
-	if (MLX5_GET(ipsec_extended_cap, fdev->ipsec->caps, ipv6))
-		ret |= MLX5_ACCEL_IPSEC_CAP_IPV6;
-
-	if (MLX5_GET(ipsec_extended_cap, fdev->ipsec->caps, lso))
-		ret |= MLX5_ACCEL_IPSEC_CAP_LSO;
-
-	if (MLX5_GET(ipsec_extended_cap, fdev->ipsec->caps, rx_no_trailer))
-		ret |= MLX5_ACCEL_IPSEC_CAP_RX_NO_TRAILER;
-
-	if (MLX5_GET(ipsec_extended_cap, fdev->ipsec->caps, esn)) {
-		ret |= MLX5_ACCEL_IPSEC_CAP_ESN;
-		ret |= MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN;
-	}
-
-	return ret;
-}
-
-static unsigned int mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-
-	if (!fdev || !fdev->ipsec)
-		return 0;
-
-	return MLX5_GET(ipsec_extended_cap, fdev->ipsec->caps,
-			number_of_ipsec_counters);
-}
-
-static int mlx5_fpga_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
-					 unsigned int counters_count)
-{
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-	unsigned int i;
-	__be32 *data;
-	u32 count;
-	u64 addr;
-	int ret;
-
-	if (!fdev || !fdev->ipsec)
-		return 0;
-
-	addr = (u64)MLX5_GET(ipsec_extended_cap, fdev->ipsec->caps,
-			     ipsec_counters_addr_low) +
-	       ((u64)MLX5_GET(ipsec_extended_cap, fdev->ipsec->caps,
-			     ipsec_counters_addr_high) << 32);
-
-	count = mlx5_fpga_ipsec_counters_count(mdev);
-
-	data = kzalloc(array3_size(sizeof(*data), count, 2), GFP_KERNEL);
-	if (!data) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	ret = mlx5_fpga_mem_read(fdev, count * sizeof(u64), addr, data,
-				 MLX5_FPGA_ACCESS_TYPE_DONTCARE);
-	if (ret < 0) {
-		mlx5_fpga_err(fdev, "Failed to read IPSec counters from HW: %d\n",
-			      ret);
-		goto out;
-	}
-	ret = 0;
-
-	if (count > counters_count)
-		count = counters_count;
-
-	/* Each counter is low word, then high. But each word is big-endian */
-	for (i = 0; i < count; i++)
-		counters[i] = (u64)ntohl(data[i * 2]) |
-			      ((u64)ntohl(data[i * 2 + 1]) << 32);
-
-out:
-	kfree(data);
-	return ret;
-}
-
-static int mlx5_fpga_ipsec_set_caps(struct mlx5_core_dev *mdev, u32 flags)
-{
-	struct mlx5_fpga_ipsec_cmd_context *context;
-	struct mlx5_ifc_fpga_ipsec_cmd_cap cmd = {0};
-	int err;
-
-	cmd.cmd = htonl(MLX5_FPGA_IPSEC_CMD_OP_SET_CAP);
-	cmd.flags = htonl(flags);
-	context = mlx5_fpga_ipsec_cmd_exec(mdev, &cmd, sizeof(cmd));
-	if (IS_ERR(context))
-		return PTR_ERR(context);
-
-	err = mlx5_fpga_ipsec_cmd_wait(context);
-	if (err)
-		goto out;
-
-	if ((context->resp.flags & cmd.flags) != cmd.flags) {
-		mlx5_fpga_err(context->dev, "Failed to set capabilities. cmd 0x%08x vs resp 0x%08x\n",
-			      cmd.flags,
-			      context->resp.flags);
-		err = -EIO;
-	}
-
-out:
-	kfree(context);
-	return err;
-}
-
-static int mlx5_fpga_ipsec_enable_supported_caps(struct mlx5_core_dev *mdev)
-{
-	u32 dev_caps = mlx5_fpga_ipsec_device_caps(mdev);
-	u32 flags = 0;
-
-	if (dev_caps & MLX5_ACCEL_IPSEC_CAP_RX_NO_TRAILER)
-		flags |= MLX5_FPGA_IPSEC_CAP_NO_TRAILER;
-
-	return mlx5_fpga_ipsec_set_caps(mdev, flags);
-}
-
-static void
-mlx5_fpga_ipsec_build_hw_xfrm(struct mlx5_core_dev *mdev,
-			      const struct mlx5_accel_esp_xfrm_attrs *xfrm_attrs,
-			      struct mlx5_ifc_fpga_ipsec_sa *hw_sa)
-{
-	const struct aes_gcm_keymat *aes_gcm = &xfrm_attrs->keymat.aes_gcm;
-
-	/* key */
-	memcpy(&hw_sa->ipsec_sa_v1.key_enc, aes_gcm->aes_key,
-	       aes_gcm->key_len / 8);
-	/* Duplicate 128 bit key twice according to HW layout */
-	if (aes_gcm->key_len == 128)
-		memcpy(&hw_sa->ipsec_sa_v1.key_enc[16],
-		       aes_gcm->aes_key, aes_gcm->key_len / 8);
-
-	/* salt and seq_iv */
-	memcpy(&hw_sa->ipsec_sa_v1.gcm.salt_iv, &aes_gcm->seq_iv,
-	       sizeof(aes_gcm->seq_iv));
-	memcpy(&hw_sa->ipsec_sa_v1.gcm.salt, &aes_gcm->salt,
-	       sizeof(aes_gcm->salt));
-
-	/* esn */
-	if (xfrm_attrs->flags & MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED) {
-		hw_sa->ipsec_sa_v1.flags |= MLX5_FPGA_IPSEC_SA_ESN_EN;
-		hw_sa->ipsec_sa_v1.flags |=
-				(xfrm_attrs->flags &
-				 MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP) ?
-					MLX5_FPGA_IPSEC_SA_ESN_OVERLAP : 0;
-		hw_sa->esn = htonl(xfrm_attrs->esn);
-	} else {
-		hw_sa->ipsec_sa_v1.flags &= ~MLX5_FPGA_IPSEC_SA_ESN_EN;
-		hw_sa->ipsec_sa_v1.flags &=
-				~(xfrm_attrs->flags &
-				  MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP) ?
-					MLX5_FPGA_IPSEC_SA_ESN_OVERLAP : 0;
-		hw_sa->esn = 0;
-	}
-
-	/* rx handle */
-	hw_sa->ipsec_sa_v1.sw_sa_handle = htonl(xfrm_attrs->sa_handle);
-
-	/* enc mode */
-	switch (aes_gcm->key_len) {
-	case 128:
-		hw_sa->ipsec_sa_v1.enc_mode =
-			MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_128_AUTH_128;
-		break;
-	case 256:
-		hw_sa->ipsec_sa_v1.enc_mode =
-			MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_256_AUTH_128;
-		break;
-	}
-
-	/* flags */
-	hw_sa->ipsec_sa_v1.flags |= MLX5_FPGA_IPSEC_SA_SA_VALID |
-			MLX5_FPGA_IPSEC_SA_SPI_EN |
-			MLX5_FPGA_IPSEC_SA_IP_ESP;
-
-	if (xfrm_attrs->action & MLX5_ACCEL_ESP_ACTION_ENCRYPT)
-		hw_sa->ipsec_sa_v1.flags |= MLX5_FPGA_IPSEC_SA_DIR_SX;
-	else
-		hw_sa->ipsec_sa_v1.flags &= ~MLX5_FPGA_IPSEC_SA_DIR_SX;
-}
-
-static void
-mlx5_fpga_ipsec_build_hw_sa(struct mlx5_core_dev *mdev,
-			    struct mlx5_accel_esp_xfrm_attrs *xfrm_attrs,
-			    const __be32 saddr[4],
-			    const __be32 daddr[4],
-			    const __be32 spi, bool is_ipv6,
-			    struct mlx5_ifc_fpga_ipsec_sa *hw_sa)
-{
-	mlx5_fpga_ipsec_build_hw_xfrm(mdev, xfrm_attrs, hw_sa);
-
-	/* IPs */
-	memcpy(hw_sa->ipsec_sa_v1.sip, saddr, sizeof(hw_sa->ipsec_sa_v1.sip));
-	memcpy(hw_sa->ipsec_sa_v1.dip, daddr, sizeof(hw_sa->ipsec_sa_v1.dip));
-
-	/* SPI */
-	hw_sa->ipsec_sa_v1.spi = spi;
-
-	/* flags */
-	if (is_ipv6)
-		hw_sa->ipsec_sa_v1.flags |= MLX5_FPGA_IPSEC_SA_IPV6;
-}
-
-static bool is_full_mask(const void *p, size_t len)
-{
-	WARN_ON(len % 4);
-
-	return !memchr_inv(p, 0xff, len);
-}
-
-static bool validate_fpga_full_mask(struct mlx5_core_dev *dev,
-				    const u32 *match_c,
-				    const u32 *match_v)
-{
-	const void *misc_params_c = MLX5_ADDR_OF(fte_match_param,
-						 match_c,
-						 misc_parameters);
-	const void *headers_c = MLX5_ADDR_OF(fte_match_param,
-					     match_c,
-					     outer_headers);
-	const void *headers_v = MLX5_ADDR_OF(fte_match_param,
-					     match_v,
-					     outer_headers);
-
-	if (mlx5_fs_is_outer_ipv4_flow(dev, headers_c, headers_v)) {
-		const void *s_ipv4_c = MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-						    headers_c,
-						    src_ipv4_src_ipv6.ipv4_layout.ipv4);
-		const void *d_ipv4_c = MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-						    headers_c,
-						    dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
-
-		if (!is_full_mask(s_ipv4_c, MLX5_FLD_SZ_BYTES(ipv4_layout,
-							      ipv4)) ||
-		    !is_full_mask(d_ipv4_c, MLX5_FLD_SZ_BYTES(ipv4_layout,
-							      ipv4)))
-			return false;
-	} else {
-		const void *s_ipv6_c = MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-						    headers_c,
-						    src_ipv4_src_ipv6.ipv6_layout.ipv6);
-		const void *d_ipv6_c = MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-						    headers_c,
-						    dst_ipv4_dst_ipv6.ipv6_layout.ipv6);
-
-		if (!is_full_mask(s_ipv6_c, MLX5_FLD_SZ_BYTES(ipv6_layout,
-							      ipv6)) ||
-		    !is_full_mask(d_ipv6_c, MLX5_FLD_SZ_BYTES(ipv6_layout,
-							      ipv6)))
-			return false;
-	}
-
-	if (!is_full_mask(MLX5_ADDR_OF(fte_match_set_misc, misc_params_c,
-				       outer_esp_spi),
-			  MLX5_FLD_SZ_BYTES(fte_match_set_misc, outer_esp_spi)))
-		return false;
-
-	return true;
-}
-
-static bool mlx5_is_fpga_ipsec_rule(struct mlx5_core_dev *dev,
-				    u8 match_criteria_enable,
-				    const u32 *match_c,
-				    const u32 *match_v)
-{
-	u32 ipsec_dev_caps = mlx5_fpga_ipsec_device_caps(dev);
-	bool ipv6_flow;
-
-	ipv6_flow = mlx5_fs_is_outer_ipv6_flow(dev, match_c, match_v);
-
-	if (!(match_criteria_enable & MLX5_MATCH_OUTER_HEADERS) ||
-	    mlx5_fs_is_outer_udp_flow(match_c, match_v) ||
-	    mlx5_fs_is_outer_tcp_flow(match_c, match_v) ||
-	    mlx5_fs_is_vxlan_flow(match_c) ||
-	    !(mlx5_fs_is_outer_ipv4_flow(dev, match_c, match_v) ||
-	      ipv6_flow))
-		return false;
-
-	if (!(ipsec_dev_caps & MLX5_ACCEL_IPSEC_CAP_DEVICE))
-		return false;
-
-	if (!(ipsec_dev_caps & MLX5_ACCEL_IPSEC_CAP_ESP) &&
-	    mlx5_fs_is_outer_ipsec_flow(match_c))
-		return false;
-
-	if (!(ipsec_dev_caps & MLX5_ACCEL_IPSEC_CAP_IPV6) &&
-	    ipv6_flow)
-		return false;
-
-	if (!validate_fpga_full_mask(dev, match_c, match_v))
-		return false;
-
-	return true;
-}
-
-static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev,
-					   u8 match_criteria_enable,
-					   const u32 *match_c,
-					   const u32 *match_v,
-					   struct mlx5_flow_act *flow_act,
-					   struct mlx5_flow_context *flow_context)
-{
-	const void *outer_c = MLX5_ADDR_OF(fte_match_param, match_c,
-					   outer_headers);
-	bool is_dmac = MLX5_GET(fte_match_set_lyr_2_4, outer_c, dmac_47_16) ||
-			MLX5_GET(fte_match_set_lyr_2_4, outer_c, dmac_15_0);
-	bool is_smac = MLX5_GET(fte_match_set_lyr_2_4, outer_c, smac_47_16) ||
-			MLX5_GET(fte_match_set_lyr_2_4, outer_c, smac_15_0);
-	int ret;
-
-	ret = mlx5_is_fpga_ipsec_rule(dev, match_criteria_enable, match_c,
-				      match_v);
-	if (!ret)
-		return ret;
-
-	if (is_dmac || is_smac ||
-	    (match_criteria_enable &
-	     ~(MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS)) ||
-	    (flow_act->action & ~(MLX5_FLOW_CONTEXT_ACTION_ENCRYPT | MLX5_FLOW_CONTEXT_ACTION_ALLOW)) ||
-	     (flow_context->flags & FLOW_CONTEXT_HAS_TAG))
-		return false;
-
-	return true;
-}
-
-static void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
-					   struct mlx5_accel_esp_xfrm *accel_xfrm,
-					   const __be32 saddr[4], const __be32 daddr[4],
-					   const __be32 spi, bool is_ipv6, u32 *sa_handle)
-{
-	struct mlx5_fpga_ipsec_sa_ctx *sa_ctx;
-	struct mlx5_fpga_esp_xfrm *fpga_xfrm =
-			container_of(accel_xfrm, typeof(*fpga_xfrm),
-				     accel_xfrm);
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
-	int opcode, err;
-	void *context;
-
-	/* alloc SA */
-	sa_ctx = kzalloc(sizeof(*sa_ctx), GFP_KERNEL);
-	if (!sa_ctx)
-		return ERR_PTR(-ENOMEM);
-
-	sa_ctx->dev = mdev;
-
-	/* build candidate SA */
-	mlx5_fpga_ipsec_build_hw_sa(mdev, &accel_xfrm->attrs,
-				    saddr, daddr, spi, is_ipv6,
-				    &sa_ctx->hw_sa);
-
-	mutex_lock(&fpga_xfrm->lock);
-
-	if (fpga_xfrm->sa_ctx) {        /* multiple rules for same accel_xfrm */
-		/* all rules must be with same IPs and SPI */
-		if (memcmp(&sa_ctx->hw_sa, &fpga_xfrm->sa_ctx->hw_sa,
-			   sizeof(sa_ctx->hw_sa))) {
-			context = ERR_PTR(-EINVAL);
-			goto exists;
-		}
-
-		++fpga_xfrm->num_rules;
-		context = fpga_xfrm->sa_ctx;
-		goto exists;
-	}
-
-	if (accel_xfrm->attrs.action == MLX5_ACCEL_ESP_ACTION_DECRYPT) {
-		err = ida_alloc_min(&fipsec->halloc, 1, GFP_KERNEL);
-		if (err < 0) {
-			context = ERR_PTR(err);
-			goto exists;
-		}
-
-		sa_ctx->sa_handle = err;
-		if (sa_handle)
-			*sa_handle = sa_ctx->sa_handle;
-	}
-	/* This is unbounded fpga_xfrm, try to add to hash */
-	mutex_lock(&fipsec->sa_hash_lock);
-
-	err = rhashtable_lookup_insert_fast(&fipsec->sa_hash, &sa_ctx->hash,
-					    rhash_sa);
-	if (err) {
-		/* Can't bound different accel_xfrm to already existing sa_ctx.
-		 * This is because we can't support multiple ketmats for
-		 * same IPs and SPI
-		 */
-		context = ERR_PTR(-EEXIST);
-		goto unlock_hash;
-	}
-
-	/* Bound accel_xfrm to sa_ctx */
-	opcode = is_v2_sadb_supported(fdev->ipsec) ?
-			MLX5_FPGA_IPSEC_CMD_OP_ADD_SA_V2 :
-			MLX5_FPGA_IPSEC_CMD_OP_ADD_SA;
-	err = mlx5_fpga_ipsec_update_hw_sa(fdev, &sa_ctx->hw_sa, opcode);
-	sa_ctx->hw_sa.ipsec_sa_v1.cmd = 0;
-	if (err) {
-		context = ERR_PTR(err);
-		goto delete_hash;
-	}
-
-	mutex_unlock(&fipsec->sa_hash_lock);
-
-	++fpga_xfrm->num_rules;
-	fpga_xfrm->sa_ctx = sa_ctx;
-	sa_ctx->fpga_xfrm = fpga_xfrm;
-
-	mutex_unlock(&fpga_xfrm->lock);
-
-	return sa_ctx;
-
-delete_hash:
-	WARN_ON(rhashtable_remove_fast(&fipsec->sa_hash, &sa_ctx->hash,
-				       rhash_sa));
-unlock_hash:
-	mutex_unlock(&fipsec->sa_hash_lock);
-	if (accel_xfrm->attrs.action == MLX5_ACCEL_ESP_ACTION_DECRYPT)
-		ida_free(&fipsec->halloc, sa_ctx->sa_handle);
-exists:
-	mutex_unlock(&fpga_xfrm->lock);
-	kfree(sa_ctx);
-	return context;
-}
-
-static void *
-mlx5_fpga_ipsec_fs_create_sa_ctx(struct mlx5_core_dev *mdev,
-				 struct fs_fte *fte,
-				 bool is_egress)
-{
-	struct mlx5_accel_esp_xfrm *accel_xfrm;
-	__be32 saddr[4], daddr[4], spi;
-	struct mlx5_flow_group *fg;
-	bool is_ipv6 = false;
-
-	fs_get_obj(fg, fte->node.parent);
-	/* validate */
-	if (is_egress &&
-	    !mlx5_is_fpga_egress_ipsec_rule(mdev,
-					    fg->mask.match_criteria_enable,
-					    fg->mask.match_criteria,
-					    fte->val,
-					    &fte->action,
-					    &fte->flow_context))
-		return ERR_PTR(-EINVAL);
-	else if (!mlx5_is_fpga_ipsec_rule(mdev,
-					  fg->mask.match_criteria_enable,
-					  fg->mask.match_criteria,
-					  fte->val))
-		return ERR_PTR(-EINVAL);
-
-	/* get xfrm context */
-	accel_xfrm =
-		(struct mlx5_accel_esp_xfrm *)fte->action.esp_id;
-
-	/* IPs */
-	if (mlx5_fs_is_outer_ipv4_flow(mdev, fg->mask.match_criteria,
-				       fte->val)) {
-		memcpy(&saddr[3],
-		       MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-				    fte->val,
-				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
-				    sizeof(saddr[3]));
-		memcpy(&daddr[3],
-		       MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-				    fte->val,
-				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
-				    sizeof(daddr[3]));
-	} else {
-		memcpy(saddr,
-		       MLX5_ADDR_OF(fte_match_param,
-				    fte->val,
-				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6),
-				    sizeof(saddr));
-		memcpy(daddr,
-		       MLX5_ADDR_OF(fte_match_param,
-				    fte->val,
-				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-				    sizeof(daddr));
-		is_ipv6 = true;
-	}
-
-	/* SPI */
-	spi = MLX5_GET_BE(typeof(spi),
-			  fte_match_param, fte->val,
-			  misc_parameters.outer_esp_spi);
-
-	/* create */
-	return mlx5_fpga_ipsec_create_sa_ctx(mdev, accel_xfrm,
-					     saddr, daddr,
-					     spi, is_ipv6, NULL);
-}
-
-static void
-mlx5_fpga_ipsec_release_sa_ctx(struct mlx5_fpga_ipsec_sa_ctx *sa_ctx)
-{
-	struct mlx5_fpga_device *fdev = sa_ctx->dev->fpga;
-	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
-	int opcode = is_v2_sadb_supported(fdev->ipsec) ?
-			MLX5_FPGA_IPSEC_CMD_OP_DEL_SA_V2 :
-			MLX5_FPGA_IPSEC_CMD_OP_DEL_SA;
-	int err;
-
-	err = mlx5_fpga_ipsec_update_hw_sa(fdev, &sa_ctx->hw_sa, opcode);
-	sa_ctx->hw_sa.ipsec_sa_v1.cmd = 0;
-	if (err) {
-		WARN_ON(err);
-		return;
-	}
-
-	if (sa_ctx->fpga_xfrm->accel_xfrm.attrs.action ==
-	    MLX5_ACCEL_ESP_ACTION_DECRYPT)
-		ida_free(&fipsec->halloc, sa_ctx->sa_handle);
-
-	mutex_lock(&fipsec->sa_hash_lock);
-	WARN_ON(rhashtable_remove_fast(&fipsec->sa_hash, &sa_ctx->hash,
-				       rhash_sa));
-	mutex_unlock(&fipsec->sa_hash_lock);
-}
-
-static void mlx5_fpga_ipsec_delete_sa_ctx(void *context)
-{
-	struct mlx5_fpga_esp_xfrm *fpga_xfrm =
-			((struct mlx5_fpga_ipsec_sa_ctx *)context)->fpga_xfrm;
-
-	mutex_lock(&fpga_xfrm->lock);
-	if (!--fpga_xfrm->num_rules) {
-		mlx5_fpga_ipsec_release_sa_ctx(fpga_xfrm->sa_ctx);
-		kfree(fpga_xfrm->sa_ctx);
-		fpga_xfrm->sa_ctx = NULL;
-	}
-	mutex_unlock(&fpga_xfrm->lock);
-}
-
-static inline struct mlx5_fpga_ipsec_rule *
-_rule_search(struct rb_root *root, struct fs_fte *fte)
-{
-	struct rb_node *node = root->rb_node;
-
-	while (node) {
-		struct mlx5_fpga_ipsec_rule *rule =
-				container_of(node, struct mlx5_fpga_ipsec_rule,
-					     node);
-
-		if (rule->fte < fte)
-			node = node->rb_left;
-		else if (rule->fte > fte)
-			node = node->rb_right;
-		else
-			return rule;
-	}
-	return NULL;
-}
-
-static struct mlx5_fpga_ipsec_rule *
-rule_search(struct mlx5_fpga_ipsec *ipsec_dev, struct fs_fte *fte)
-{
-	struct mlx5_fpga_ipsec_rule *rule;
-
-	mutex_lock(&ipsec_dev->rules_rb_lock);
-	rule = _rule_search(&ipsec_dev->rules_rb, fte);
-	mutex_unlock(&ipsec_dev->rules_rb_lock);
-
-	return rule;
-}
-
-static inline int _rule_insert(struct rb_root *root,
-			       struct mlx5_fpga_ipsec_rule *rule)
-{
-	struct rb_node **new = &root->rb_node, *parent = NULL;
-
-	/* Figure out where to put new node */
-	while (*new) {
-		struct mlx5_fpga_ipsec_rule *this =
-				container_of(*new, struct mlx5_fpga_ipsec_rule,
-					     node);
-
-		parent = *new;
-		if (rule->fte < this->fte)
-			new = &((*new)->rb_left);
-		else if (rule->fte > this->fte)
-			new = &((*new)->rb_right);
-		else
-			return -EEXIST;
-	}
-
-	/* Add new node and rebalance tree. */
-	rb_link_node(&rule->node, parent, new);
-	rb_insert_color(&rule->node, root);
-
-	return 0;
-}
-
-static int rule_insert(struct mlx5_fpga_ipsec *ipsec_dev,
-		       struct mlx5_fpga_ipsec_rule *rule)
-{
-	int ret;
-
-	mutex_lock(&ipsec_dev->rules_rb_lock);
-	ret = _rule_insert(&ipsec_dev->rules_rb, rule);
-	mutex_unlock(&ipsec_dev->rules_rb_lock);
-
-	return ret;
-}
-
-static inline void _rule_delete(struct mlx5_fpga_ipsec *ipsec_dev,
-				struct mlx5_fpga_ipsec_rule *rule)
-{
-	struct rb_root *root = &ipsec_dev->rules_rb;
-
-	mutex_lock(&ipsec_dev->rules_rb_lock);
-	rb_erase(&rule->node, root);
-	mutex_unlock(&ipsec_dev->rules_rb_lock);
-}
-
-static void rule_delete(struct mlx5_fpga_ipsec *ipsec_dev,
-			struct mlx5_fpga_ipsec_rule *rule)
-{
-	_rule_delete(ipsec_dev, rule);
-	kfree(rule);
-}
-
-struct mailbox_mod {
-	uintptr_t			saved_esp_id;
-	u32				saved_action;
-	u32				saved_outer_esp_spi_value;
-};
-
-static void restore_spec_mailbox(struct fs_fte *fte,
-				 struct mailbox_mod *mbox_mod)
-{
-	char *misc_params_v = MLX5_ADDR_OF(fte_match_param,
-					   fte->val,
-					   misc_parameters);
-
-	MLX5_SET(fte_match_set_misc, misc_params_v, outer_esp_spi,
-		 mbox_mod->saved_outer_esp_spi_value);
-	fte->action.action |= mbox_mod->saved_action;
-	fte->action.esp_id = (uintptr_t)mbox_mod->saved_esp_id;
-}
-
-static void modify_spec_mailbox(struct mlx5_core_dev *mdev,
-				struct fs_fte *fte,
-				struct mailbox_mod *mbox_mod)
-{
-	char *misc_params_v = MLX5_ADDR_OF(fte_match_param,
-					   fte->val,
-					   misc_parameters);
-
-	mbox_mod->saved_esp_id = fte->action.esp_id;
-	mbox_mod->saved_action = fte->action.action &
-			(MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
-			 MLX5_FLOW_CONTEXT_ACTION_DECRYPT);
-	mbox_mod->saved_outer_esp_spi_value =
-			MLX5_GET(fte_match_set_misc, misc_params_v,
-				 outer_esp_spi);
-
-	fte->action.esp_id = 0;
-	fte->action.action &= ~(MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
-				MLX5_FLOW_CONTEXT_ACTION_DECRYPT);
-	if (!MLX5_CAP_FLOWTABLE(mdev,
-				flow_table_properties_nic_receive.ft_field_support.outer_esp_spi))
-		MLX5_SET(fte_match_set_misc, misc_params_v, outer_esp_spi, 0);
-}
-
-static enum fs_flow_table_type egress_to_fs_ft(bool egress)
-{
-	return egress ? FS_FT_NIC_TX : FS_FT_NIC_RX;
-}
-
-static int fpga_ipsec_fs_create_flow_group(struct mlx5_flow_root_namespace *ns,
-					   struct mlx5_flow_table *ft,
-					   u32 *in,
-					   struct mlx5_flow_group *fg,
-					   bool is_egress)
-{
-	int (*create_flow_group)(struct mlx5_flow_root_namespace *ns,
-				 struct mlx5_flow_table *ft, u32 *in,
-				 struct mlx5_flow_group *fg) =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->create_flow_group;
-	char *misc_params_c = MLX5_ADDR_OF(create_flow_group_in, in,
-					   match_criteria.misc_parameters);
-	struct mlx5_core_dev *dev = ns->dev;
-	u32 saved_outer_esp_spi_mask;
-	u8 match_criteria_enable;
-	int ret;
-
-	if (MLX5_CAP_FLOWTABLE(dev,
-			       flow_table_properties_nic_receive.ft_field_support.outer_esp_spi))
-		return create_flow_group(ns, ft, in, fg);
-
-	match_criteria_enable =
-		MLX5_GET(create_flow_group_in, in, match_criteria_enable);
-	saved_outer_esp_spi_mask =
-		MLX5_GET(fte_match_set_misc, misc_params_c, outer_esp_spi);
-	if (!match_criteria_enable || !saved_outer_esp_spi_mask)
-		return create_flow_group(ns, ft, in, fg);
-
-	MLX5_SET(fte_match_set_misc, misc_params_c, outer_esp_spi, 0);
-
-	if (!(*misc_params_c) &&
-	    !memcmp(misc_params_c, misc_params_c + 1, MLX5_ST_SZ_BYTES(fte_match_set_misc) - 1))
-		MLX5_SET(create_flow_group_in, in, match_criteria_enable,
-			 match_criteria_enable & ~MLX5_MATCH_MISC_PARAMETERS);
-
-	ret = create_flow_group(ns, ft, in, fg);
-
-	MLX5_SET(fte_match_set_misc, misc_params_c, outer_esp_spi, saved_outer_esp_spi_mask);
-	MLX5_SET(create_flow_group_in, in, match_criteria_enable, match_criteria_enable);
-
-	return ret;
-}
-
-static int fpga_ipsec_fs_create_fte(struct mlx5_flow_root_namespace *ns,
-				    struct mlx5_flow_table *ft,
-				    struct mlx5_flow_group *fg,
-				    struct fs_fte *fte,
-				    bool is_egress)
-{
-	int (*create_fte)(struct mlx5_flow_root_namespace *ns,
-			  struct mlx5_flow_table *ft,
-			  struct mlx5_flow_group *fg,
-			  struct fs_fte *fte) =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->create_fte;
-	struct mlx5_core_dev *dev = ns->dev;
-	struct mlx5_fpga_device *fdev = dev->fpga;
-	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
-	struct mlx5_fpga_ipsec_rule *rule;
-	bool is_esp = fte->action.esp_id;
-	struct mailbox_mod mbox_mod;
-	int ret;
-
-	if (!is_esp ||
-	    !(fte->action.action &
-	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
-	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return create_fte(ns, ft, fg, fte);
-
-	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
-	if (!rule)
-		return -ENOMEM;
-
-	rule->ctx = mlx5_fpga_ipsec_fs_create_sa_ctx(dev, fte, is_egress);
-	if (IS_ERR(rule->ctx)) {
-		int err = PTR_ERR(rule->ctx);
-
-		kfree(rule);
-		return err;
-	}
-
-	rule->fte = fte;
-	WARN_ON(rule_insert(fipsec, rule));
-
-	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = create_fte(ns, ft, fg, fte);
-	restore_spec_mailbox(fte, &mbox_mod);
-	if (ret) {
-		_rule_delete(fipsec, rule);
-		mlx5_fpga_ipsec_delete_sa_ctx(rule->ctx);
-		kfree(rule);
-	}
-
-	return ret;
-}
-
-static int fpga_ipsec_fs_update_fte(struct mlx5_flow_root_namespace *ns,
-				    struct mlx5_flow_table *ft,
-				    struct mlx5_flow_group *fg,
-				    int modify_mask,
-				    struct fs_fte *fte,
-				    bool is_egress)
-{
-	int (*update_fte)(struct mlx5_flow_root_namespace *ns,
-			  struct mlx5_flow_table *ft,
-			  struct mlx5_flow_group *fg,
-			  int modify_mask,
-			  struct fs_fte *fte) =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->update_fte;
-	struct mlx5_core_dev *dev = ns->dev;
-	bool is_esp = fte->action.esp_id;
-	struct mailbox_mod mbox_mod;
-	int ret;
-
-	if (!is_esp ||
-	    !(fte->action.action &
-	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
-	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return update_fte(ns, ft, fg, modify_mask, fte);
-
-	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = update_fte(ns, ft, fg, modify_mask, fte);
-	restore_spec_mailbox(fte, &mbox_mod);
-
-	return ret;
-}
-
-static int fpga_ipsec_fs_delete_fte(struct mlx5_flow_root_namespace *ns,
-				    struct mlx5_flow_table *ft,
-				    struct fs_fte *fte,
-				    bool is_egress)
-{
-	int (*delete_fte)(struct mlx5_flow_root_namespace *ns,
-			  struct mlx5_flow_table *ft,
-			  struct fs_fte *fte) =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->delete_fte;
-	struct mlx5_core_dev *dev = ns->dev;
-	struct mlx5_fpga_device *fdev = dev->fpga;
-	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
-	struct mlx5_fpga_ipsec_rule *rule;
-	bool is_esp = fte->action.esp_id;
-	struct mailbox_mod mbox_mod;
-	int ret;
-
-	if (!is_esp ||
-	    !(fte->action.action &
-	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
-	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return delete_fte(ns, ft, fte);
-
-	rule = rule_search(fipsec, fte);
-	if (!rule)
-		return -ENOENT;
-
-	mlx5_fpga_ipsec_delete_sa_ctx(rule->ctx);
-	rule_delete(fipsec, rule);
-
-	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = delete_fte(ns, ft, fte);
-	restore_spec_mailbox(fte, &mbox_mod);
-
-	return ret;
-}
-
-static int
-mlx5_fpga_ipsec_fs_create_flow_group_egress(struct mlx5_flow_root_namespace *ns,
-					    struct mlx5_flow_table *ft,
-					    u32 *in,
-					    struct mlx5_flow_group *fg)
-{
-	return fpga_ipsec_fs_create_flow_group(ns, ft, in, fg, true);
-}
-
-static int
-mlx5_fpga_ipsec_fs_create_fte_egress(struct mlx5_flow_root_namespace *ns,
-				     struct mlx5_flow_table *ft,
-				     struct mlx5_flow_group *fg,
-				     struct fs_fte *fte)
-{
-	return fpga_ipsec_fs_create_fte(ns, ft, fg, fte, true);
-}
-
-static int
-mlx5_fpga_ipsec_fs_update_fte_egress(struct mlx5_flow_root_namespace *ns,
-				     struct mlx5_flow_table *ft,
-				     struct mlx5_flow_group *fg,
-				     int modify_mask,
-				     struct fs_fte *fte)
-{
-	return fpga_ipsec_fs_update_fte(ns, ft, fg, modify_mask, fte,
-					true);
-}
-
-static int
-mlx5_fpga_ipsec_fs_delete_fte_egress(struct mlx5_flow_root_namespace *ns,
-				     struct mlx5_flow_table *ft,
-				     struct fs_fte *fte)
-{
-	return fpga_ipsec_fs_delete_fte(ns, ft, fte, true);
-}
-
-static int
-mlx5_fpga_ipsec_fs_create_flow_group_ingress(struct mlx5_flow_root_namespace *ns,
-					     struct mlx5_flow_table *ft,
-					     u32 *in,
-					     struct mlx5_flow_group *fg)
-{
-	return fpga_ipsec_fs_create_flow_group(ns, ft, in, fg, false);
-}
-
-static int
-mlx5_fpga_ipsec_fs_create_fte_ingress(struct mlx5_flow_root_namespace *ns,
-				      struct mlx5_flow_table *ft,
-				      struct mlx5_flow_group *fg,
-				      struct fs_fte *fte)
-{
-	return fpga_ipsec_fs_create_fte(ns, ft, fg, fte, false);
-}
-
-static int
-mlx5_fpga_ipsec_fs_update_fte_ingress(struct mlx5_flow_root_namespace *ns,
-				      struct mlx5_flow_table *ft,
-				      struct mlx5_flow_group *fg,
-				      int modify_mask,
-				      struct fs_fte *fte)
-{
-	return fpga_ipsec_fs_update_fte(ns, ft, fg, modify_mask, fte,
-					false);
-}
-
-static int
-mlx5_fpga_ipsec_fs_delete_fte_ingress(struct mlx5_flow_root_namespace *ns,
-				      struct mlx5_flow_table *ft,
-				      struct fs_fte *fte)
-{
-	return fpga_ipsec_fs_delete_fte(ns, ft, fte, false);
-}
-
-static struct mlx5_flow_cmds fpga_ipsec_ingress;
-static struct mlx5_flow_cmds fpga_ipsec_egress;
-
-const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type)
-{
-	switch (type) {
-	case FS_FT_NIC_RX:
-		return &fpga_ipsec_ingress;
-	case FS_FT_NIC_TX:
-		return &fpga_ipsec_egress;
-	default:
-		WARN_ON(true);
-		return NULL;
-	}
-}
-
-static int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_fpga_conn_attr init_attr = {0};
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-	struct mlx5_fpga_conn *conn;
-	int err;
-
-	if (!mlx5_fpga_is_ipsec_device(mdev))
-		return 0;
-
-	fdev->ipsec = kzalloc(sizeof(*fdev->ipsec), GFP_KERNEL);
-	if (!fdev->ipsec)
-		return -ENOMEM;
-
-	fdev->ipsec->fdev = fdev;
-
-	err = mlx5_fpga_get_sbu_caps(fdev, sizeof(fdev->ipsec->caps),
-				     fdev->ipsec->caps);
-	if (err) {
-		mlx5_fpga_err(fdev, "Failed to retrieve IPSec extended capabilities: %d\n",
-			      err);
-		goto error;
-	}
-
-	INIT_LIST_HEAD(&fdev->ipsec->pending_cmds);
-	spin_lock_init(&fdev->ipsec->pending_cmds_lock);
-
-	init_attr.rx_size = SBU_QP_QUEUE_SIZE;
-	init_attr.tx_size = SBU_QP_QUEUE_SIZE;
-	init_attr.recv_cb = mlx5_fpga_ipsec_recv;
-	init_attr.cb_arg = fdev;
-	conn = mlx5_fpga_sbu_conn_create(fdev, &init_attr);
-	if (IS_ERR(conn)) {
-		err = PTR_ERR(conn);
-		mlx5_fpga_err(fdev, "Error creating IPSec command connection %d\n",
-			      err);
-		goto error;
-	}
-	fdev->ipsec->conn = conn;
-
-	err = rhashtable_init(&fdev->ipsec->sa_hash, &rhash_sa);
-	if (err)
-		goto err_destroy_conn;
-	mutex_init(&fdev->ipsec->sa_hash_lock);
-
-	fdev->ipsec->rules_rb = RB_ROOT;
-	mutex_init(&fdev->ipsec->rules_rb_lock);
-
-	err = mlx5_fpga_ipsec_enable_supported_caps(mdev);
-	if (err) {
-		mlx5_fpga_err(fdev, "Failed to enable IPSec extended capabilities: %d\n",
-			      err);
-		goto err_destroy_hash;
-	}
-
-	ida_init(&fdev->ipsec->halloc);
-
-	return 0;
-
-err_destroy_hash:
-	rhashtable_destroy(&fdev->ipsec->sa_hash);
-
-err_destroy_conn:
-	mlx5_fpga_sbu_conn_destroy(conn);
-
-error:
-	kfree(fdev->ipsec);
-	fdev->ipsec = NULL;
-	return err;
-}
-
-static void destroy_rules_rb(struct rb_root *root)
-{
-	struct mlx5_fpga_ipsec_rule *r, *tmp;
-
-	rbtree_postorder_for_each_entry_safe(r, tmp, root, node) {
-		rb_erase(&r->node, root);
-		mlx5_fpga_ipsec_delete_sa_ctx(r->ctx);
-		kfree(r);
-	}
-}
-
-static void mlx5_fpga_ipsec_cleanup(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-
-	if (!mlx5_fpga_is_ipsec_device(mdev))
-		return;
-
-	ida_destroy(&fdev->ipsec->halloc);
-	destroy_rules_rb(&fdev->ipsec->rules_rb);
-	rhashtable_destroy(&fdev->ipsec->sa_hash);
-
-	mlx5_fpga_sbu_conn_destroy(fdev->ipsec->conn);
-	kfree(fdev->ipsec);
-	fdev->ipsec = NULL;
-}
-
-void mlx5_fpga_ipsec_build_fs_cmds(void)
-{
-	/* ingress */
-	fpga_ipsec_ingress.create_flow_table =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(false))->create_flow_table;
-	fpga_ipsec_ingress.destroy_flow_table =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(false))->destroy_flow_table;
-	fpga_ipsec_ingress.modify_flow_table =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(false))->modify_flow_table;
-	fpga_ipsec_ingress.create_flow_group =
-		mlx5_fpga_ipsec_fs_create_flow_group_ingress;
-	fpga_ipsec_ingress.destroy_flow_group =
-		 mlx5_fs_cmd_get_default(egress_to_fs_ft(false))->destroy_flow_group;
-	fpga_ipsec_ingress.create_fte =
-		mlx5_fpga_ipsec_fs_create_fte_ingress;
-	fpga_ipsec_ingress.update_fte =
-		mlx5_fpga_ipsec_fs_update_fte_ingress;
-	fpga_ipsec_ingress.delete_fte =
-		mlx5_fpga_ipsec_fs_delete_fte_ingress;
-	fpga_ipsec_ingress.update_root_ft =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(false))->update_root_ft;
-
-	/* egress */
-	fpga_ipsec_egress.create_flow_table =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(true))->create_flow_table;
-	fpga_ipsec_egress.destroy_flow_table =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(true))->destroy_flow_table;
-	fpga_ipsec_egress.modify_flow_table =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(true))->modify_flow_table;
-	fpga_ipsec_egress.create_flow_group =
-		mlx5_fpga_ipsec_fs_create_flow_group_egress;
-	fpga_ipsec_egress.destroy_flow_group =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(true))->destroy_flow_group;
-	fpga_ipsec_egress.create_fte =
-		mlx5_fpga_ipsec_fs_create_fte_egress;
-	fpga_ipsec_egress.update_fte =
-		mlx5_fpga_ipsec_fs_update_fte_egress;
-	fpga_ipsec_egress.delete_fte =
-		mlx5_fpga_ipsec_fs_delete_fte_egress;
-	fpga_ipsec_egress.update_root_ft =
-		mlx5_fs_cmd_get_default(egress_to_fs_ft(true))->update_root_ft;
-}
-
-static int
-mlx5_fpga_esp_validate_xfrm_attrs(struct mlx5_core_dev *mdev,
-				  const struct mlx5_accel_esp_xfrm_attrs *attrs)
-{
-	if (attrs->tfc_pad) {
-		mlx5_core_err(mdev, "Cannot offload xfrm states with tfc padding\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (attrs->replay_type != MLX5_ACCEL_ESP_REPLAY_NONE) {
-		mlx5_core_err(mdev, "Cannot offload xfrm states with anti replay\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (attrs->keymat_type != MLX5_ACCEL_ESP_KEYMAT_AES_GCM) {
-		mlx5_core_err(mdev, "Only aes gcm keymat is supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (attrs->keymat.aes_gcm.iv_algo !=
-	    MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ) {
-		mlx5_core_err(mdev, "Only iv sequence algo is supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (attrs->keymat.aes_gcm.icv_len != 128) {
-		mlx5_core_err(mdev, "Cannot offload xfrm states with AEAD ICV length other than 128bit\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (attrs->keymat.aes_gcm.key_len != 128 &&
-	    attrs->keymat.aes_gcm.key_len != 256) {
-		mlx5_core_err(mdev, "Cannot offload xfrm states with AEAD key length other than 128/256 bit\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((attrs->flags & MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED) &&
-	    (!MLX5_GET(ipsec_extended_cap, mdev->fpga->ipsec->caps,
-		       v2_command))) {
-		mlx5_core_err(mdev, "Cannot offload xfrm states with AEAD key length other than 128/256 bit\n");
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static struct mlx5_accel_esp_xfrm *
-mlx5_fpga_esp_create_xfrm(struct mlx5_core_dev *mdev,
-			  const struct mlx5_accel_esp_xfrm_attrs *attrs,
-			  u32 flags)
-{
-	struct mlx5_fpga_esp_xfrm *fpga_xfrm;
-
-	if (!(flags & MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA)) {
-		mlx5_core_warn(mdev, "Tried to create an esp action without metadata\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	if (mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) {
-		mlx5_core_warn(mdev, "Tried to create an esp with unsupported attrs\n");
-		return ERR_PTR(-EOPNOTSUPP);
-	}
-
-	fpga_xfrm = kzalloc(sizeof(*fpga_xfrm), GFP_KERNEL);
-	if (!fpga_xfrm)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_init(&fpga_xfrm->lock);
-	memcpy(&fpga_xfrm->accel_xfrm.attrs, attrs,
-	       sizeof(fpga_xfrm->accel_xfrm.attrs));
-
-	return &fpga_xfrm->accel_xfrm;
-}
-
-static void mlx5_fpga_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
-{
-	struct mlx5_fpga_esp_xfrm *fpga_xfrm =
-			container_of(xfrm, struct mlx5_fpga_esp_xfrm,
-				     accel_xfrm);
-	/* assuming no sa_ctx are connected to this xfrm_ctx */
-	kfree(fpga_xfrm);
-}
-
-static int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-				     const struct mlx5_accel_esp_xfrm_attrs *attrs)
-{
-	struct mlx5_core_dev *mdev = xfrm->mdev;
-	struct mlx5_fpga_device *fdev = mdev->fpga;
-	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
-	struct mlx5_fpga_esp_xfrm *fpga_xfrm;
-	struct mlx5_ifc_fpga_ipsec_sa org_hw_sa;
-
-	int err = 0;
-
-	if (!memcmp(&xfrm->attrs, attrs, sizeof(xfrm->attrs)))
-		return 0;
-
-	if (mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) {
-		mlx5_core_warn(mdev, "Tried to create an esp with unsupported attrs\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (is_v2_sadb_supported(fipsec)) {
-		mlx5_core_warn(mdev, "Modify esp is not supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	fpga_xfrm = container_of(xfrm, struct mlx5_fpga_esp_xfrm, accel_xfrm);
-
-	mutex_lock(&fpga_xfrm->lock);
-
-	if (!fpga_xfrm->sa_ctx)
-		/* Unbounded xfrm, change only sw attrs */
-		goto change_sw_xfrm_attrs;
-
-	/* copy original hw sa */
-	memcpy(&org_hw_sa, &fpga_xfrm->sa_ctx->hw_sa, sizeof(org_hw_sa));
-	mutex_lock(&fipsec->sa_hash_lock);
-	/* remove original hw sa from hash */
-	WARN_ON(rhashtable_remove_fast(&fipsec->sa_hash,
-				       &fpga_xfrm->sa_ctx->hash, rhash_sa));
-	/* update hw_sa with new xfrm attrs*/
-	mlx5_fpga_ipsec_build_hw_xfrm(xfrm->mdev, attrs,
-				      &fpga_xfrm->sa_ctx->hw_sa);
-	/* try to insert new hw_sa to hash */
-	err = rhashtable_insert_fast(&fipsec->sa_hash,
-				     &fpga_xfrm->sa_ctx->hash, rhash_sa);
-	if (err)
-		goto rollback_sa;
-
-	/* modify device with new hw_sa */
-	err = mlx5_fpga_ipsec_update_hw_sa(fdev, &fpga_xfrm->sa_ctx->hw_sa,
-					   MLX5_FPGA_IPSEC_CMD_OP_MOD_SA_V2);
-	fpga_xfrm->sa_ctx->hw_sa.ipsec_sa_v1.cmd = 0;
-	if (err)
-		WARN_ON(rhashtable_remove_fast(&fipsec->sa_hash,
-					       &fpga_xfrm->sa_ctx->hash,
-					       rhash_sa));
-rollback_sa:
-	if (err) {
-		/* return original hw_sa to hash */
-		memcpy(&fpga_xfrm->sa_ctx->hw_sa, &org_hw_sa,
-		       sizeof(org_hw_sa));
-		WARN_ON(rhashtable_insert_fast(&fipsec->sa_hash,
-					       &fpga_xfrm->sa_ctx->hash,
-					       rhash_sa));
-	}
-	mutex_unlock(&fipsec->sa_hash_lock);
-
-change_sw_xfrm_attrs:
-	if (!err)
-		memcpy(&xfrm->attrs, attrs, sizeof(xfrm->attrs));
-	mutex_unlock(&fpga_xfrm->lock);
-	return err;
-}
-
-static const struct mlx5_accel_ipsec_ops fpga_ipsec_ops = {
-	.device_caps = mlx5_fpga_ipsec_device_caps,
-	.counters_count = mlx5_fpga_ipsec_counters_count,
-	.counters_read = mlx5_fpga_ipsec_counters_read,
-	.create_hw_context = mlx5_fpga_ipsec_create_sa_ctx,
-	.free_hw_context = mlx5_fpga_ipsec_delete_sa_ctx,
-	.init = mlx5_fpga_ipsec_init,
-	.cleanup = mlx5_fpga_ipsec_cleanup,
-	.esp_create_xfrm = mlx5_fpga_esp_create_xfrm,
-	.esp_modify_xfrm = mlx5_fpga_esp_modify_xfrm,
-	.esp_destroy_xfrm = mlx5_fpga_esp_destroy_xfrm,
-};
-
-const struct mlx5_accel_ipsec_ops *mlx5_fpga_ipsec_ops(struct mlx5_core_dev *mdev)
-{
-	if (!mlx5_fpga_is_ipsec_device(mdev))
-		return NULL;
-
-	return &fpga_ipsec_ops;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
deleted file mode 100644
index 8931b5584477..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#ifndef __MLX5_FPGA_IPSEC_H__
-#define __MLX5_FPGA_IPSEC_H__
-
-#include "accel/ipsec.h"
-#include "fs_cmd.h"
-
-#ifdef CONFIG_MLX5_FPGA_IPSEC
-const struct mlx5_accel_ipsec_ops *mlx5_fpga_ipsec_ops(struct mlx5_core_dev *mdev);
-u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev);
-const struct mlx5_flow_cmds *
-mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type);
-void mlx5_fpga_ipsec_build_fs_cmds(void);
-bool mlx5_fpga_is_ipsec_device(struct mlx5_core_dev *mdev);
-#else
-static inline
-const struct mlx5_accel_ipsec_ops *mlx5_fpga_ipsec_ops(struct mlx5_core_dev *mdev)
-{ return NULL; }
-static inline u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev) { return 0; }
-static inline const struct mlx5_flow_cmds *
-mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type)
-{
-	return mlx5_fs_cmd_get_default(type);
-}
-
-static inline void mlx5_fpga_ipsec_build_fs_cmds(void) {};
-static inline bool mlx5_fpga_is_ipsec_device(struct mlx5_core_dev *mdev) { return false; }
-
-#endif /* CONFIG_MLX5_FPGA_IPSEC */
-#endif	/* __MLX5_FPGA_IPSEC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 816d991f7621..fe7bdccea301 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -40,8 +40,6 @@
 #include "fs_cmd.h"
 #include "fs_ft_pool.h"
 #include "diag/fs_tracepoint.h"
-#include "accel/ipsec.h"
-#include "fpga/ipsec.h"
 
 #define INIT_TREE_NODE_ARRAY_SIZE(...)	(sizeof((struct init_tree_node[]){__VA_ARGS__}) /\
 					 sizeof(struct init_tree_node))
@@ -2519,10 +2517,6 @@ static struct mlx5_flow_root_namespace
 	struct mlx5_flow_root_namespace *root_ns;
 	struct mlx5_flow_namespace *ns;
 
-	if (mlx5_fpga_ipsec_device_caps(steering->dev) & MLX5_ACCEL_IPSEC_CAP_DEVICE &&
-	    (table_type == FS_FT_NIC_RX || table_type == FS_FT_NIC_TX))
-		cmds = mlx5_fs_cmd_get_default_ipsec_fpga_cmds(table_type);
-
 	/* Create the root namespace */
 	root_ns = kzalloc(sizeof(*root_ns), GFP_KERNEL);
 	if (!root_ns)
@@ -3172,8 +3166,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (mlx5_fpga_ipsec_device_caps(steering->dev) & MLX5_ACCEL_IPSEC_CAP_DEVICE ||
-	    MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) {
+	if (MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) {
 		err = init_egress_root_ns(steering);
 		if (err)
 			goto err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7f287e300fb4..387602bbfecc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -62,7 +62,6 @@
 #include "lib/mlx5.h"
 #include "lib/tout.h"
 #include "fpga/core.h"
-#include "fpga/ipsec.h"
 #include "accel/ipsec.h"
 #include "lib/clock.h"
 #include "lib/vxlan.h"
@@ -1937,7 +1936,6 @@ static int __init init(void)
 	get_random_bytes(&sw_owner_id, sizeof(sw_owner_id));
 
 	mlx5_core_verify_params();
-	mlx5_fpga_ipsec_build_fs_cmds();
 	mlx5_register_debugfs();
 
 	err = pci_register_driver(&mlx5_core_driver);
diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h
index e3d824f6a309..45c7c0d67635 100644
--- a/include/linux/mlx5/mlx5_ifc_fpga.h
+++ b/include/linux/mlx5/mlx5_ifc_fpga.h
@@ -386,68 +386,6 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
-struct mlx5_ifc_ipsec_extended_cap_bits {
-	u8         encapsulation[0x20];
-
-	u8         reserved_0[0x12];
-	u8         v2_command[0x1];
-	u8         udp_encap[0x1];
-	u8         rx_no_trailer[0x1];
-	u8         ipv4_fragment[0x1];
-	u8         ipv6[0x1];
-	u8         esn[0x1];
-	u8         lso[0x1];
-	u8         transport_and_tunnel_mode[0x1];
-	u8         tunnel_mode[0x1];
-	u8         transport_mode[0x1];
-	u8         ah_esp[0x1];
-	u8         esp[0x1];
-	u8         ah[0x1];
-	u8         ipv4_options[0x1];
-
-	u8         auth_alg[0x20];
-
-	u8         enc_alg[0x20];
-
-	u8         sa_cap[0x20];
-
-	u8         reserved_1[0x10];
-	u8         number_of_ipsec_counters[0x10];
-
-	u8         ipsec_counters_addr_low[0x20];
-	u8         ipsec_counters_addr_high[0x20];
-};
-
-struct mlx5_ifc_ipsec_counters_bits {
-	u8         dec_in_packets[0x40];
-
-	u8         dec_out_packets[0x40];
-
-	u8         dec_bypass_packets[0x40];
-
-	u8         enc_in_packets[0x40];
-
-	u8         enc_out_packets[0x40];
-
-	u8         enc_bypass_packets[0x40];
-
-	u8         drop_dec_packets[0x40];
-
-	u8         failed_auth_dec_packets[0x40];
-
-	u8         drop_enc_packets[0x40];
-
-	u8         success_add_sa[0x40];
-
-	u8         fail_add_sa[0x40];
-
-	u8         success_delete_sa[0x40];
-
-	u8         fail_delete_sa[0x40];
-
-	u8         dropped_cmd[0x40];
-};
-
 enum {
 	MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RETRY_COUNTER_EXPIRED  = 0x1,
 	MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RNR_EXPIRED            = 0x2,
@@ -464,90 +402,4 @@ struct mlx5_ifc_fpga_qp_error_event_bits {
 	u8         reserved_at_c0[0x8];
 	u8         fpga_qpn[0x18];
 };
-enum mlx5_ifc_fpga_ipsec_response_syndrome {
-	MLX5_FPGA_IPSEC_RESPONSE_SUCCESS = 0,
-	MLX5_FPGA_IPSEC_RESPONSE_ILLEGAL_REQUEST = 1,
-	MLX5_FPGA_IPSEC_RESPONSE_SADB_ISSUE = 2,
-	MLX5_FPGA_IPSEC_RESPONSE_WRITE_RESPONSE_ISSUE = 3,
-};
-
-struct mlx5_ifc_fpga_ipsec_cmd_resp {
-	__be32 syndrome;
-	union {
-		__be32 sw_sa_handle;
-		__be32 flags;
-	};
-	u8 reserved[24];
-} __packed;
-
-enum mlx5_ifc_fpga_ipsec_cmd_opcode {
-	MLX5_FPGA_IPSEC_CMD_OP_ADD_SA = 0,
-	MLX5_FPGA_IPSEC_CMD_OP_DEL_SA = 1,
-	MLX5_FPGA_IPSEC_CMD_OP_ADD_SA_V2 = 2,
-	MLX5_FPGA_IPSEC_CMD_OP_DEL_SA_V2 = 3,
-	MLX5_FPGA_IPSEC_CMD_OP_MOD_SA_V2 = 4,
-	MLX5_FPGA_IPSEC_CMD_OP_SET_CAP = 5,
-};
-
-enum mlx5_ifc_fpga_ipsec_cap {
-	MLX5_FPGA_IPSEC_CAP_NO_TRAILER = BIT(0),
-};
-
-struct mlx5_ifc_fpga_ipsec_cmd_cap {
-	__be32 cmd;
-	__be32 flags;
-	u8 reserved[24];
-} __packed;
-
-enum mlx5_ifc_fpga_ipsec_sa_flags {
-	MLX5_FPGA_IPSEC_SA_ESN_EN = BIT(0),
-	MLX5_FPGA_IPSEC_SA_ESN_OVERLAP = BIT(1),
-	MLX5_FPGA_IPSEC_SA_IPV6 = BIT(2),
-	MLX5_FPGA_IPSEC_SA_DIR_SX = BIT(3),
-	MLX5_FPGA_IPSEC_SA_SPI_EN = BIT(4),
-	MLX5_FPGA_IPSEC_SA_SA_VALID = BIT(5),
-	MLX5_FPGA_IPSEC_SA_IP_ESP = BIT(6),
-	MLX5_FPGA_IPSEC_SA_IP_AH = BIT(7),
-};
-
-enum mlx5_ifc_fpga_ipsec_sa_enc_mode {
-	MLX5_FPGA_IPSEC_SA_ENC_MODE_NONE = 0,
-	MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_128_AUTH_128 = 1,
-	MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_256_AUTH_128 = 3,
-};
-
-struct mlx5_ifc_fpga_ipsec_sa_v1 {
-	__be32 cmd;
-	u8 key_enc[32];
-	u8 key_auth[32];
-	__be32 sip[4];
-	__be32 dip[4];
-	union {
-		struct {
-			__be32 reserved;
-			u8 salt_iv[8];
-			__be32 salt;
-		} __packed gcm;
-		struct {
-			u8 salt[16];
-		} __packed cbc;
-	};
-	__be32 spi;
-	__be32 sw_sa_handle;
-	__be16 tfclen;
-	u8 enc_mode;
-	u8 reserved1[2];
-	u8 flags;
-	u8 reserved2[2];
-};
-
-struct mlx5_ifc_fpga_ipsec_sa {
-	struct mlx5_ifc_fpga_ipsec_sa_v1 ipsec_sa_v1;
-	__be16 udp_sp;
-	__be16 udp_dp;
-	u8 reserved1[4];
-	__be32 esn;
-	__be16 vid;	/* only 12 bits, rest is reserved */
-	__be16 reserved2;
-} __packed;
 #endif /* MLX5_IFC_FPGA_H */
-- 
cgit v1.2.3


From de8bdb476908e64805df4bfbad20618cbb1f9ffa Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 6 Apr 2022 11:25:42 +0300
Subject: RDMA/mlx5: Drop crypto flow steering API

The mlx5 flow steering crypto API was intended to be used in FPGA
devices, which is not supported for years already. The removal of
mlx5 crypto FPGA code together with inability to configure encryption
keys makes the low steering API completely unusable.

So delete the code, so any ESP flow steering requests will fail with
not supported error, as it is happening now anyway as no device support
this type of API.

Link: https://lore.kernel.org/r/634a5face7734381463d809bfb89850f6998deac.1649232994.git.leonro@nvidia.com
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/fs.c                    | 223 +--------------------
 drivers/infiniband/hw/mlx5/main.c                  |  27 ---
 .../net/ethernet/mellanox/mlx5/core/accel/ipsec.c  |   5 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c   |   4 +-
 include/linux/mlx5/accel.h                         |  13 +-
 5 files changed, 10 insertions(+), 262 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c
index 661ed2b44508..9c2886bc72cb 100644
--- a/drivers/infiniband/hw/mlx5/fs.c
+++ b/drivers/infiniband/hw/mlx5/fs.c
@@ -15,7 +15,6 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/fs_helpers.h>
-#include <linux/mlx5/accel.h>
 #include <linux/mlx5/eswitch.h>
 #include <net/inet_ecn.h>
 #include "mlx5_ib.h"
@@ -148,16 +147,6 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
 {
 
 	switch (maction->ib_action.type) {
-	case IB_FLOW_ACTION_ESP:
-		if (action->action & (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
-				      MLX5_FLOW_CONTEXT_ACTION_DECRYPT))
-			return -EINVAL;
-		/* Currently only AES_GCM keymat is supported by the driver */
-		action->esp_id = (uintptr_t)maction->esp_aes_gcm.ctx;
-		action->action |= is_egress ?
-			MLX5_FLOW_CONTEXT_ACTION_ENCRYPT :
-			MLX5_FLOW_CONTEXT_ACTION_DECRYPT;
-		return 0;
 	case IB_FLOW_ACTION_UNSPECIFIED:
 		if (maction->flow_action_raw.sub_type ==
 		    MLX5_IB_FLOW_ACTION_MODIFY_HEADER) {
@@ -368,14 +357,7 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev,
 			       ib_spec->type & IB_FLOW_SPEC_INNER);
 		break;
 	case IB_FLOW_SPEC_ESP:
-		if (ib_spec->esp.mask.seq)
-			return -EOPNOTSUPP;
-
-		MLX5_SET(fte_match_set_misc, misc_params_c, outer_esp_spi,
-			 ntohl(ib_spec->esp.mask.spi));
-		MLX5_SET(fte_match_set_misc, misc_params_v, outer_esp_spi,
-			 ntohl(ib_spec->esp.val.spi));
-		break;
+		return -EOPNOTSUPP;
 	case IB_FLOW_SPEC_TCP:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
 					 LAST_TCP_UDP_FIELD))
@@ -587,47 +569,6 @@ static bool flow_is_multicast_only(const struct ib_flow_attr *ib_attr)
 	return false;
 }
 
-enum valid_spec {
-	VALID_SPEC_INVALID,
-	VALID_SPEC_VALID,
-	VALID_SPEC_NA,
-};
-
-static enum valid_spec
-is_valid_esp_aes_gcm(struct mlx5_core_dev *mdev,
-		     const struct mlx5_flow_spec *spec,
-		     const struct mlx5_flow_act *flow_act,
-		     bool egress)
-{
-	const u32 *match_c = spec->match_criteria;
-	bool is_crypto =
-		(flow_act->action & (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
-				     MLX5_FLOW_CONTEXT_ACTION_DECRYPT));
-	bool is_ipsec = mlx5_fs_is_ipsec_flow(match_c);
-	bool is_drop = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_DROP;
-
-	/*
-	 * Currently only crypto is supported in egress, when regular egress
-	 * rules would be supported, always return VALID_SPEC_NA.
-	 */
-	if (!is_crypto)
-		return VALID_SPEC_NA;
-
-	return is_crypto && is_ipsec &&
-		(!egress || (!is_drop &&
-			     !(spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG))) ?
-		VALID_SPEC_VALID : VALID_SPEC_INVALID;
-}
-
-static bool is_valid_spec(struct mlx5_core_dev *mdev,
-			  const struct mlx5_flow_spec *spec,
-			  const struct mlx5_flow_act *flow_act,
-			  bool egress)
-{
-	/* We curretly only support ipsec egress flow */
-	return is_valid_esp_aes_gcm(mdev, spec, flow_act, egress) != VALID_SPEC_INVALID;
-}
-
 static bool is_valid_ethertype(struct mlx5_core_dev *mdev,
 			       const struct ib_flow_attr *flow_attr,
 			       bool check_inner)
@@ -1154,8 +1095,7 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 
 	spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
 
-	if (is_egress &&
-	    !is_valid_spec(dev->mdev, spec, &flow_act, is_egress)) {
+	if (is_egress) {
 		err = -EINVAL;
 		goto free;
 	}
@@ -1740,149 +1680,6 @@ unlock:
 	return ERR_PTR(err);
 }
 
-static u32 mlx5_ib_flow_action_flags_to_accel_xfrm_flags(u32 mlx5_flags)
-{
-	u32 flags = 0;
-
-	if (mlx5_flags & MLX5_IB_UAPI_FLOW_ACTION_FLAGS_REQUIRE_METADATA)
-		flags |= MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA;
-
-	return flags;
-}
-
-#define MLX5_FLOW_ACTION_ESP_CREATE_LAST_SUPPORTED                             \
-	MLX5_IB_UAPI_FLOW_ACTION_FLAGS_REQUIRE_METADATA
-static struct ib_flow_action *
-mlx5_ib_create_flow_action_esp(struct ib_device *device,
-			       const struct ib_flow_action_attrs_esp *attr,
-			       struct uverbs_attr_bundle *attrs)
-{
-	struct mlx5_ib_dev *mdev = to_mdev(device);
-	struct ib_uverbs_flow_action_esp_keymat_aes_gcm *aes_gcm;
-	struct mlx5_accel_esp_xfrm_attrs accel_attrs = {};
-	struct mlx5_ib_flow_action *action;
-	u64 action_flags;
-	u64 flags;
-	int err = 0;
-
-	err = uverbs_get_flags64(
-		&action_flags, attrs, MLX5_IB_ATTR_CREATE_FLOW_ACTION_FLAGS,
-		((MLX5_FLOW_ACTION_ESP_CREATE_LAST_SUPPORTED << 1) - 1));
-	if (err)
-		return ERR_PTR(err);
-
-	flags = mlx5_ib_flow_action_flags_to_accel_xfrm_flags(action_flags);
-
-	/* We current only support a subset of the standard features. Only a
-	 * keymat of type AES_GCM, with icv_len == 16, iv_algo == SEQ and esn
-	 * (with overlap). Full offload mode isn't supported.
-	 */
-	if (!attr->keymat || attr->replay || attr->encap ||
-	    attr->spi || attr->seq || attr->tfc_pad ||
-	    attr->hard_limit_pkts ||
-	    (attr->flags & ~(IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED |
-			     IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ENCRYPT)))
-		return ERR_PTR(-EOPNOTSUPP);
-
-	if (attr->keymat->protocol !=
-	    IB_UVERBS_FLOW_ACTION_ESP_KEYMAT_AES_GCM)
-		return ERR_PTR(-EOPNOTSUPP);
-
-	aes_gcm = &attr->keymat->keymat.aes_gcm;
-
-	if (aes_gcm->icv_len != 16 ||
-	    aes_gcm->iv_algo != IB_UVERBS_FLOW_ACTION_IV_ALGO_SEQ)
-		return ERR_PTR(-EOPNOTSUPP);
-
-	action = kmalloc(sizeof(*action), GFP_KERNEL);
-	if (!action)
-		return ERR_PTR(-ENOMEM);
-
-	action->esp_aes_gcm.ib_flags = attr->flags;
-	memcpy(&accel_attrs.keymat.aes_gcm.aes_key, &aes_gcm->aes_key,
-	       sizeof(accel_attrs.keymat.aes_gcm.aes_key));
-	accel_attrs.keymat.aes_gcm.key_len = aes_gcm->key_len * 8;
-	memcpy(&accel_attrs.keymat.aes_gcm.salt, &aes_gcm->salt,
-	       sizeof(accel_attrs.keymat.aes_gcm.salt));
-	memcpy(&accel_attrs.keymat.aes_gcm.seq_iv, &aes_gcm->iv,
-	       sizeof(accel_attrs.keymat.aes_gcm.seq_iv));
-	accel_attrs.keymat.aes_gcm.icv_len = aes_gcm->icv_len * 8;
-	accel_attrs.keymat.aes_gcm.iv_algo = MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ;
-	accel_attrs.keymat_type = MLX5_ACCEL_ESP_KEYMAT_AES_GCM;
-
-	accel_attrs.esn = attr->esn;
-	if (attr->flags & IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED)
-		accel_attrs.flags |= MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED;
-	if (attr->flags & IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW)
-		accel_attrs.flags |= MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP;
-
-	if (attr->flags & IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ENCRYPT)
-		accel_attrs.action |= MLX5_ACCEL_ESP_ACTION_ENCRYPT;
-
-	action->esp_aes_gcm.ctx =
-		mlx5_accel_esp_create_xfrm(mdev->mdev, &accel_attrs, flags);
-	if (IS_ERR(action->esp_aes_gcm.ctx)) {
-		err = PTR_ERR(action->esp_aes_gcm.ctx);
-		goto err_parse;
-	}
-
-	action->esp_aes_gcm.ib_flags = attr->flags;
-
-	return &action->ib_action;
-
-err_parse:
-	kfree(action);
-	return ERR_PTR(err);
-}
-
-static int
-mlx5_ib_modify_flow_action_esp(struct ib_flow_action *action,
-			       const struct ib_flow_action_attrs_esp *attr,
-			       struct uverbs_attr_bundle *attrs)
-{
-	struct mlx5_ib_flow_action *maction = to_mflow_act(action);
-	struct mlx5_accel_esp_xfrm_attrs accel_attrs;
-	int err = 0;
-
-	if (attr->keymat || attr->replay || attr->encap ||
-	    attr->spi || attr->seq || attr->tfc_pad ||
-	    attr->hard_limit_pkts ||
-	    (attr->flags & ~(IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED |
-			     IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS |
-			     IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW)))
-		return -EOPNOTSUPP;
-
-	/* Only the ESN value or the MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP can
-	 * be modified.
-	 */
-	if (!(maction->esp_aes_gcm.ib_flags &
-	      IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED) &&
-	    attr->flags & (IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED |
-			   IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW))
-		return -EINVAL;
-
-	memcpy(&accel_attrs, &maction->esp_aes_gcm.ctx->attrs,
-	       sizeof(accel_attrs));
-
-	accel_attrs.esn = attr->esn;
-	if (attr->flags & IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW)
-		accel_attrs.flags |= MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP;
-	else
-		accel_attrs.flags &= ~MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP;
-
-	err = mlx5_accel_esp_modify_xfrm(maction->esp_aes_gcm.ctx,
-					 &accel_attrs);
-	if (err)
-		return err;
-
-	maction->esp_aes_gcm.ib_flags &=
-		~IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW;
-	maction->esp_aes_gcm.ib_flags |=
-		attr->flags & IB_UVERBS_FLOW_ACTION_ESP_FLAGS_ESN_NEW_WINDOW;
-
-	return 0;
-}
-
 static void destroy_flow_action_raw(struct mlx5_ib_flow_action *maction)
 {
 	switch (maction->flow_action_raw.sub_type) {
@@ -1906,13 +1703,6 @@ static int mlx5_ib_destroy_flow_action(struct ib_flow_action *action)
 	struct mlx5_ib_flow_action *maction = to_mflow_act(action);
 
 	switch (action->type) {
-	case IB_FLOW_ACTION_ESP:
-		/*
-		 * We only support aes_gcm by now, so we implicitly know this is
-		 * the underline crypto.
-		 */
-		mlx5_accel_esp_destroy_xfrm(maction->esp_aes_gcm.ctx);
-		break;
 	case IB_FLOW_ACTION_UNSPECIFIED:
 		destroy_flow_action_raw(maction);
 		break;
@@ -2709,11 +2499,6 @@ static const struct ib_device_ops flow_ops = {
 	.destroy_flow_action = mlx5_ib_destroy_flow_action,
 };
 
-static const struct ib_device_ops flow_ipsec_ops = {
-	.create_flow_action_esp = mlx5_ib_create_flow_action_esp,
-	.modify_flow_action_esp = mlx5_ib_modify_flow_action_esp,
-};
-
 int mlx5_ib_fs_init(struct mlx5_ib_dev *dev)
 {
 	dev->flow_db = kzalloc(sizeof(*dev->flow_db), GFP_KERNEL);
@@ -2724,9 +2509,5 @@ int mlx5_ib_fs_init(struct mlx5_ib_dev *dev)
 	mutex_init(&dev->flow_db->lock);
 
 	ib_set_device_ops(&dev->ib_dev, &flow_ops);
-	if (mlx5_accel_ipsec_device_caps(dev->mdev) &
-	    MLX5_ACCEL_IPSEC_CAP_DEVICE)
-		ib_set_device_ops(&dev->ib_dev, &flow_ipsec_ops);
-
 	return 0;
 }
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d2e67ecc5479..61aa196d6484 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -41,7 +41,6 @@
 #include "wr.h"
 #include "restrack.h"
 #include "counters.h"
-#include <linux/mlx5/accel.h>
 #include <rdma/uverbs_std_types.h>
 #include <rdma/uverbs_ioctl.h>
 #include <rdma/mlx5_user_ioctl_verbs.h>
@@ -906,10 +905,6 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 						MLX5_RX_HASH_SRC_PORT_UDP |
 						MLX5_RX_HASH_DST_PORT_UDP |
 						MLX5_RX_HASH_INNER;
-			if (mlx5_accel_ipsec_device_caps(dev->mdev) &
-			    MLX5_ACCEL_IPSEC_CAP_DEVICE)
-				resp.rss_caps.rx_hash_fields_mask |=
-					MLX5_RX_HASH_IPSEC_SPI;
 			resp.response_length += sizeof(resp.rss_caps);
 		}
 	} else {
@@ -1791,19 +1786,6 @@ static int set_ucontext_resp(struct ib_ucontext *uctx,
 	resp->num_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
 					MLX5_CAP_GEN(dev->mdev,
 						     num_of_uars_per_page) : 1;
-
-	if (mlx5_accel_ipsec_device_caps(dev->mdev) &
-				MLX5_ACCEL_IPSEC_CAP_DEVICE) {
-		if (mlx5_get_flow_namespace(dev->mdev,
-				MLX5_FLOW_NAMESPACE_EGRESS))
-			resp->flow_action_flags |= MLX5_USER_ALLOC_UCONTEXT_FLOW_ACTION_FLAGS_ESP_AES_GCM;
-		if (MLX5_CAP_FLOWTABLE(dev->mdev, flow_table_properties_nic_receive.ft_field_support.outer_esp_spi))
-			resp->flow_action_flags |= MLX5_USER_ALLOC_UCONTEXT_FLOW_ACTION_FLAGS_ESP_AES_GCM_SPI_STEERING;
-		if (mlx5_accel_ipsec_device_caps(dev->mdev) &
-				MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN)
-			resp->flow_action_flags |= MLX5_USER_ALLOC_UCONTEXT_FLOW_ACTION_FLAGS_ESP_AES_GCM_TX_IV_IS_ESN;
-	}
-
 	resp->tot_bfregs = bfregi->lib_uar_dyn ? 0 :
 			bfregi->total_num_bfregs - bfregi->num_dyn_bfregs;
 	resp->num_ports = dev->num_ports;
@@ -3600,13 +3582,6 @@ DECLARE_UVERBS_NAMED_OBJECT(MLX5_IB_OBJECT_UAR,
 			    &UVERBS_METHOD(MLX5_IB_METHOD_UAR_OBJ_ALLOC),
 			    &UVERBS_METHOD(MLX5_IB_METHOD_UAR_OBJ_DESTROY));
 
-ADD_UVERBS_ATTRIBUTES_SIMPLE(
-	mlx5_ib_flow_action,
-	UVERBS_OBJECT_FLOW_ACTION,
-	UVERBS_METHOD_FLOW_ACTION_ESP_CREATE,
-	UVERBS_ATTR_FLAGS_IN(MLX5_IB_ATTR_CREATE_FLOW_ACTION_FLAGS,
-			     enum mlx5_ib_uapi_flow_action_flags));
-
 ADD_UVERBS_ATTRIBUTES_SIMPLE(
 	mlx5_ib_query_context,
 	UVERBS_OBJECT_DEVICE,
@@ -3624,8 +3599,6 @@ static const struct uapi_definition mlx5_ib_defs[] = {
 	UAPI_DEF_CHAIN(mlx5_ib_std_types_defs),
 	UAPI_DEF_CHAIN(mlx5_ib_dm_defs),
 
-	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_FLOW_ACTION,
-				&mlx5_ib_flow_action),
 	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_DEVICE, &mlx5_ib_query_context),
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(MLX5_IB_OBJECT_VAR,
 				UAPI_DEF_IS_OBJ_SUPPORTED(var_is_supported)),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
index 45296ec2d055..387be13b2f1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
@@ -133,8 +133,7 @@ void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context)
 
 struct mlx5_accel_esp_xfrm *
 mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
-			   const struct mlx5_accel_esp_xfrm_attrs *attrs,
-			   u32 flags)
+			   const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
 	struct mlx5_accel_esp_xfrm *xfrm;
@@ -142,7 +141,7 @@ mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
 	if (!ipsec_ops || !ipsec_ops->esp_create_xfrm)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	xfrm = ipsec_ops->esp_create_xfrm(mdev, attrs, flags);
+	xfrm = ipsec_ops->esp_create_xfrm(mdev, attrs, 0);
 	if (IS_ERR(xfrm))
 		return xfrm;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 13f6fed74950..f6e3b549424f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -333,9 +333,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 
 	/* create xfrm */
 	mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &attrs);
-	sa_entry->xfrm =
-		mlx5_accel_esp_create_xfrm(priv->mdev, &attrs,
-					   MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA);
+	sa_entry->xfrm = mlx5_accel_esp_create_xfrm(priv->mdev, &attrs);
 	if (IS_ERR(sa_entry->xfrm)) {
 		err = PTR_ERR(sa_entry->xfrm);
 		goto err_sa_entry;
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index dacf69516002..af67d51308cf 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -111,10 +111,6 @@ struct mlx5_accel_esp_xfrm {
 	struct mlx5_accel_esp_xfrm_attrs attrs;
 };
 
-enum {
-	MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA = 1UL << 0,
-};
-
 enum mlx5_accel_ipsec_cap {
 	MLX5_ACCEL_IPSEC_CAP_DEVICE		= 1 << 0,
 	MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA	= 1 << 1,
@@ -132,8 +128,7 @@ u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev);
 
 struct mlx5_accel_esp_xfrm *
 mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
-			   const struct mlx5_accel_esp_xfrm_attrs *attrs,
-			   u32 flags);
+			   const struct mlx5_accel_esp_xfrm_attrs *attrs);
 void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm);
 int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 			       const struct mlx5_accel_esp_xfrm_attrs *attrs);
@@ -144,8 +139,10 @@ static inline u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev) { ret
 
 static inline struct mlx5_accel_esp_xfrm *
 mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
-			   const struct mlx5_accel_esp_xfrm_attrs *attrs,
-			   u32 flags) { return ERR_PTR(-EOPNOTSUPP); }
+			   const struct mlx5_accel_esp_xfrm_attrs *attrs)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
 static inline void
 mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {}
 static inline int
-- 
cgit v1.2.3


From 2451da081a343e079d9f5a7b063fcdf0bc439aa8 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 6 Apr 2022 11:25:46 +0300
Subject: net/mlx5: Unify device IPsec capabilities check

Merge two different function to one in order to provide coherent
picture if the device is IPsec capable or not.

Link: https://lore.kernel.org/r/8f10ea06ad19c6f651e9fb33921009658f01e1d5.1649232994.git.leonro@nvidia.com
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/accel/ipsec_offload.c       | 38 +++++++++++-----------
 .../mellanox/mlx5/core/accel/ipsec_offload.h       | 26 ---------------
 .../net/ethernet/mellanox/mlx5/core/en/params.c    |  4 +--
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c   | 12 +++----
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  2 +-
 include/linux/mlx5/accel.h                         |  7 ++--
 6 files changed, 32 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.c
index 3a85157f9f07..9dbebef19ff0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.c
@@ -6,9 +6,6 @@
 #include "lib/mlx5.h"
 #include "en_accel/ipsec_fs.h"
 
-#define MLX5_IPSEC_DEV_BASIC_CAPS (MLX5_ACCEL_IPSEC_CAP_DEVICE | MLX5_ACCEL_IPSEC_CAP_IPV6 | \
-				   MLX5_ACCEL_IPSEC_CAP_LSO)
-
 struct mlx5_ipsec_sa_ctx {
 	struct rhash_head hash;
 	u32 enc_key_id;
@@ -25,17 +22,31 @@ struct mlx5_ipsec_esp_xfrm {
 	struct mlx5_accel_esp_xfrm accel_xfrm;
 };
 
-static u32 mlx5_ipsec_offload_device_caps(struct mlx5_core_dev *mdev)
+u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 {
-	u32 caps = MLX5_IPSEC_DEV_BASIC_CAPS;
+	u32 caps;
+
+	if (!MLX5_CAP_GEN(mdev, ipsec_offload))
+		return 0;
+
+	if (!MLX5_CAP_GEN(mdev, log_max_dek))
+		return 0;
+
+	if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) &
+	    MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC))
+		return 0;
 
-	if (!mlx5_is_ipsec_device(mdev))
+	if (!MLX5_CAP_IPSEC(mdev, ipsec_crypto_offload) ||
+	    !MLX5_CAP_ETH(mdev, insert_trailer))
 		return 0;
 
 	if (!MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ipsec_encrypt) ||
 	    !MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ipsec_decrypt))
 		return 0;
 
+	caps = MLX5_ACCEL_IPSEC_CAP_DEVICE | MLX5_ACCEL_IPSEC_CAP_IPV6 |
+	       MLX5_ACCEL_IPSEC_CAP_LSO;
+
 	if (MLX5_CAP_IPSEC(mdev, ipsec_crypto_esp_aes_gcm_128_encrypt) &&
 	    MLX5_CAP_IPSEC(mdev, ipsec_crypto_esp_aes_gcm_128_decrypt))
 		caps |= MLX5_ACCEL_IPSEC_CAP_ESP;
@@ -52,6 +63,7 @@ static u32 mlx5_ipsec_offload_device_caps(struct mlx5_core_dev *mdev)
 	WARN_ON_ONCE(MLX5_CAP_IPSEC(mdev, log_max_ipsec_offload) > 24);
 	return caps;
 }
+EXPORT_SYMBOL_GPL(mlx5_ipsec_device_caps);
 
 static int
 mlx5_ipsec_offload_esp_validate_xfrm_attrs(struct mlx5_core_dev *mdev,
@@ -367,7 +379,6 @@ change_sw_xfrm_attrs:
 }
 
 static const struct mlx5_accel_ipsec_ops ipsec_offload_ops = {
-	.device_caps = mlx5_ipsec_offload_device_caps,
 	.create_hw_context = mlx5_ipsec_offload_create_sa_ctx,
 	.free_hw_context = mlx5_ipsec_offload_delete_sa_ctx,
 	.init = mlx5_ipsec_offload_init,
@@ -379,7 +390,7 @@ static const struct mlx5_accel_ipsec_ops ipsec_offload_ops = {
 static const struct mlx5_accel_ipsec_ops *
 mlx5_ipsec_offload_ops(struct mlx5_core_dev *mdev)
 {
-	if (!mlx5_ipsec_offload_device_caps(mdev))
+	if (!mlx5_ipsec_device_caps(mdev))
 		return NULL;
 
 	return &ipsec_offload_ops;
@@ -416,17 +427,6 @@ void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev)
 	ipsec_ops->cleanup(mdev);
 }
 
-u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->device_caps)
-		return 0;
-
-	return ipsec_ops->device_caps(mdev);
-}
-EXPORT_SYMBOL_GPL(mlx5_accel_ipsec_device_caps);
-
 unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev)
 {
 	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
index 4a7d49ed5604..3d13e2c136b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
@@ -9,9 +9,6 @@
 
 #ifdef CONFIG_MLX5_IPSEC
 
-#define MLX5_IPSEC_DEV(mdev) (mlx5_accel_ipsec_device_caps(mdev) & \
-			      MLX5_ACCEL_IPSEC_CAP_DEVICE)
-
 unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev);
 int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
 				   unsigned int count);
@@ -25,7 +22,6 @@ void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev);
 void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev);
 
 struct mlx5_accel_ipsec_ops {
-	u32 (*device_caps)(struct mlx5_core_dev *mdev);
 	unsigned int (*counters_count)(struct mlx5_core_dev *mdev);
 	int (*counters_read)(struct mlx5_core_dev *mdev, u64 *counters,
 			     unsigned int count);
@@ -45,25 +41,8 @@ struct mlx5_accel_ipsec_ops {
 	void (*esp_destroy_xfrm)(struct mlx5_accel_esp_xfrm *xfrm);
 };
 
-static inline bool mlx5_is_ipsec_device(struct mlx5_core_dev *mdev)
-{
-	if (!MLX5_CAP_GEN(mdev, ipsec_offload))
-		return false;
-
-	if (!MLX5_CAP_GEN(mdev, log_max_dek))
-		return false;
-
-	if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) &
-	    MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC))
-		return false;
-
-	return MLX5_CAP_IPSEC(mdev, ipsec_crypto_offload) &&
-		MLX5_CAP_ETH(mdev, insert_trailer);
-}
 #else
 
-#define MLX5_IPSEC_DEV(mdev) false
-
 static inline void *
 mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 				 struct mlx5_accel_esp_xfrm *xfrm,
@@ -80,10 +59,5 @@ static inline void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev,
 static inline void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev) {}
 
 static inline void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev) {}
-static inline bool mlx5_is_ipsec_device(struct mlx5_core_dev *mdev)
-{
-	return false;
-}
-
 #endif /* CONFIG_MLX5_IPSEC */
 #endif /* __MLX5_IPSEC_OFFLOAD_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index d2ec0961fe9e..9f4ae8bc09b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -689,8 +689,8 @@ void mlx5e_build_sq_param(struct mlx5_core_dev *mdev,
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 	bool allow_swp;
 
-	allow_swp = mlx5_geneve_tx_allowed(mdev) ||
-		    !!MLX5_IPSEC_DEV(mdev);
+	allow_swp =
+		mlx5_geneve_tx_allowed(mdev) || !!mlx5_ipsec_device_caps(mdev);
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	MLX5_SET(sqc, sqc, allow_swp, allow_swp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 1391a0c84f16..c280a18ff002 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -226,8 +226,7 @@ static inline int mlx5e_xfrm_validate_state(struct xfrm_state *x)
 		return -EINVAL;
 	}
 	if (x->props.flags & XFRM_STATE_ESN &&
-	    !(mlx5_accel_ipsec_device_caps(priv->mdev) &
-	    MLX5_ACCEL_IPSEC_CAP_ESN)) {
+	    !(mlx5_ipsec_device_caps(priv->mdev) & MLX5_ACCEL_IPSEC_CAP_ESN)) {
 		netdev_info(netdev, "Cannot offload ESN xfrm states\n");
 		return -EINVAL;
 	}
@@ -275,8 +274,7 @@ static inline int mlx5e_xfrm_validate_state(struct xfrm_state *x)
 		return -EINVAL;
 	}
 	if (x->props.family == AF_INET6 &&
-	    !(mlx5_accel_ipsec_device_caps(priv->mdev) &
-	     MLX5_ACCEL_IPSEC_CAP_IPV6)) {
+	    !(mlx5_ipsec_device_caps(priv->mdev) & MLX5_ACCEL_IPSEC_CAP_IPV6)) {
 		netdev_info(netdev, "IPv6 xfrm state offload is not supported by this device\n");
 		return -EINVAL;
 	}
@@ -406,7 +404,7 @@ int mlx5e_ipsec_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_ipsec *ipsec = NULL;
 
-	if (!MLX5_IPSEC_DEV(priv->mdev)) {
+	if (!mlx5_ipsec_device_caps(priv->mdev)) {
 		netdev_dbg(priv->netdev, "Not an IPSec offload device\n");
 		return 0;
 	}
@@ -519,7 +517,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct net_device *netdev = priv->netdev;
 
-	if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) ||
+	if (!(mlx5_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) ||
 	    !MLX5_CAP_ETH(mdev, swp)) {
 		mlx5_core_dbg(mdev, "mlx5e: ESP and SWP offload not supported\n");
 		return;
@@ -538,7 +536,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv)
 	netdev->features |= NETIF_F_HW_ESP_TX_CSUM;
 	netdev->hw_enc_features |= NETIF_F_HW_ESP_TX_CSUM;
 
-	if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_LSO) ||
+	if (!(mlx5_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_LSO) ||
 	    !MLX5_CAP_ETH(mdev, swp_lso)) {
 		mlx5_core_dbg(mdev, "mlx5e: ESP LSO not supported\n");
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 346f7034fec8..6a3a08fd8910 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1329,7 +1329,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
 	if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert))
 		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
-	if (MLX5_IPSEC_DEV(c->priv->mdev))
+	if (mlx5_ipsec_device_caps(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (param->is_mpw)
 		set_bit(MLX5E_SQ_STATE_MPWQE, &sq->state);
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index af67d51308cf..9145e2d37c0e 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -124,7 +124,7 @@ enum mlx5_accel_ipsec_cap {
 
 #ifdef CONFIG_MLX5_ACCEL
 
-u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev);
+u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev);
 
 struct mlx5_accel_esp_xfrm *
 mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
@@ -135,7 +135,10 @@ int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 
 #else
 
-static inline u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev) { return 0; }
+static inline u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
+{
+	return 0;
+}
 
 static inline struct mlx5_accel_esp_xfrm *
 mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
-- 
cgit v1.2.3


From 54deb0e77561973f4ca4515e18ab972c281eea1d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 6 Apr 2022 11:25:48 +0300
Subject: net/mlx5: Remove not-needed IPsec config

In current code, the CONFIG_MLX5_IPSEC and CONFIG_MLX5_EN_IPSEC are
the same. So remove useless indirection.

Link: https://lore.kernel.org/r/fd14492cbc01a0d51a5bfedde02bcd2154123fde.1649232994.git.leonro@nvidia.com
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig        | 16 +---------------
 drivers/net/ethernet/mellanox/mlx5/core/Makefile       |  4 ++--
 .../ethernet/mellanox/mlx5/core/accel/ipsec_offload.h  | 18 ++----------------
 include/linux/mlx5/accel.h                             |  4 ++--
 include/linux/mlx5/driver.h                            |  2 +-
 5 files changed, 8 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index e34e64a9ff4a..176883cf2827 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -142,28 +142,14 @@ config MLX5_CORE_IPOIB
 	help
 	  MLX5 IPoIB offloads & acceleration support.
 
-config MLX5_IPSEC
+config MLX5_EN_IPSEC
 	bool "Mellanox Technologies IPsec Connect-X support"
 	depends on MLX5_CORE_EN
 	depends on XFRM_OFFLOAD
 	depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
 	select MLX5_ACCEL
-	help
-	Build IPsec support for the Connect-X family of network cards by Mellanox
-	Technologies.
-	Note: If you select this option, the mlx5_core driver will include
-	IPsec support for the Connect-X family.
-
-config MLX5_EN_IPSEC
-	bool "IPSec XFRM cryptography-offload acceleration"
-	depends on MLX5_CORE_EN
-	depends on XFRM_OFFLOAD
-	depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
-	depends on MLX5_IPSEC
 	help
 	  Build support for IPsec cryptography-offload acceleration in the NIC.
-	  Note: Support for hardware with this capability needs to be selected
-	  for this option to become available.
 
 config MLX5_EN_TLS
 	bool "Mellanox Technologies TLS Connect-X support"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index ad852703a3cb..9e715a1056f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -88,13 +88,13 @@ mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib
 #
 # Accelerations & FPGA
 #
-mlx5_core-$(CONFIG_MLX5_IPSEC) += accel/ipsec_offload.o
 mlx5_core-$(CONFIG_MLX5_ACCEL) += lib/crypto.o
 
 mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
-				     en_accel/ipsec_stats.o en_accel/ipsec_fs.o
+				     en_accel/ipsec_stats.o en_accel/ipsec_fs.o \
+				     accel/ipsec_offload.o
 
 mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/ktls_stats.o \
 				   en_accel/fs_tcp.o en_accel/ktls.o en_accel/ktls_txrx.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
index 3d13e2c136b1..36e700b596d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec_offload.h
@@ -7,7 +7,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/accel.h>
 
-#ifdef CONFIG_MLX5_IPSEC
+#ifdef CONFIG_MLX5_EN_IPSEC
 
 unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev);
 int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
@@ -42,22 +42,8 @@ struct mlx5_accel_ipsec_ops {
 };
 
 #else
-
-static inline void *
-mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				 struct mlx5_accel_esp_xfrm *xfrm,
-				 u32 *sa_handle)
-{
-	return NULL;
-}
-
-static inline void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev,
-						  void *context)
-{
-}
-
 static inline void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev) {}
 
 static inline void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev) {}
-#endif /* CONFIG_MLX5_IPSEC */
+#endif /* CONFIG_MLX5_EN_IPSEC */
 #endif /* __MLX5_IPSEC_OFFLOAD_H__ */
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index 9145e2d37c0e..73e4d50a9f02 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -122,7 +122,7 @@ enum mlx5_accel_ipsec_cap {
 	MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN	= 1 << 7,
 };
 
-#ifdef CONFIG_MLX5_ACCEL
+#ifdef CONFIG_MLX5_EN_IPSEC
 
 u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev);
 
@@ -152,5 +152,5 @@ static inline int
 mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 			   const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; }
 
-#endif /* CONFIG_MLX5_ACCEL */
+#endif /* CONFIG_MLX5_EN_IPSEC */
 #endif /* __MLX5_ACCEL_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 9424503eb8d3..5af53c035949 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -778,7 +778,7 @@ struct mlx5_core_dev {
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
 #endif
-#ifdef CONFIG_MLX5_ACCEL
+#ifdef CONFIG_MLX5_EN_IPSEC
 	const struct mlx5_accel_ipsec_ops *ipsec_ops;
 #endif
 	struct mlx5_clock        clock;
-- 
cgit v1.2.3


From f2b41b32cde8453a0a26875261f0e26809c2805a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 6 Apr 2022 11:25:51 +0300
Subject: net/mlx5: Remove ipsec_ops function table

There is only one IPsec implementation and ipsec_ops is not needed
at all in this situation. Together with removal of ipsec_ops, we can
drop the entry checks as these functions are called for IPsec devices
only.

Link: https://lore.kernel.org/r/bc8dd1c8a77b65dbf5e2cf92c813ffaca2505c5f.1649232994.git.leonro@nvidia.com
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.h         |   5 -
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c    | 118 ++-------------------
 .../mellanox/mlx5/core/en_accel/ipsec_offload.h    |  35 ------
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   4 -
 include/linux/mlx5/driver.h                        |   3 -
 5 files changed, 8 insertions(+), 157 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.h
index b3e23aa5beeb..b70953979709 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.h
@@ -9,7 +9,6 @@
 #include "ipsec_offload.h"
 #include "en/fs.h"
 
-#ifdef CONFIG_MLX5_EN_IPSEC
 void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_priv *priv);
 int mlx5e_accel_ipsec_fs_init(struct mlx5e_priv *priv);
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv,
@@ -19,8 +18,4 @@ int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv,
 void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv,
 				   struct mlx5_accel_esp_xfrm_attrs *attrs,
 				   struct mlx5e_ipsec_rule *ipsec_rule);
-#else
-static inline void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_priv *priv) {}
-static inline int mlx5e_accel_ipsec_fs_init(struct mlx5e_priv *priv) { return 0; }
-#endif
 #endif /* __MLX5_IPSEC_STEERING_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 7ae2d308139e..f0f44bd95cc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -106,8 +106,7 @@ mlx5_ipsec_offload_esp_validate_xfrm_attrs(struct mlx5_core_dev *mdev,
 
 static struct mlx5_accel_esp_xfrm *
 mlx5_ipsec_offload_esp_create_xfrm(struct mlx5_core_dev *mdev,
-				   const struct mlx5_accel_esp_xfrm_attrs *attrs,
-				   u32 flags)
+				   const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_ipsec_esp_xfrm *mxfrm;
 	int err = 0;
@@ -286,11 +285,6 @@ static void mlx5_ipsec_offload_delete_sa_ctx(void *context)
 	mutex_unlock(&mxfrm->lock);
 }
 
-static int mlx5_ipsec_offload_init(struct mlx5_core_dev *mdev)
-{
-	return 0;
-}
-
 static int mlx5_modify_ipsec_obj(struct mlx5_core_dev *mdev,
 				 struct mlx5_ipsec_obj_attrs *attrs,
 				 u32 ipsec_id)
@@ -378,86 +372,12 @@ change_sw_xfrm_attrs:
 	return err;
 }
 
-static const struct mlx5_accel_ipsec_ops ipsec_offload_ops = {
-	.create_hw_context = mlx5_ipsec_offload_create_sa_ctx,
-	.free_hw_context = mlx5_ipsec_offload_delete_sa_ctx,
-	.init = mlx5_ipsec_offload_init,
-	.esp_create_xfrm = mlx5_ipsec_offload_esp_create_xfrm,
-	.esp_destroy_xfrm = mlx5_ipsec_offload_esp_destroy_xfrm,
-	.esp_modify_xfrm = mlx5_ipsec_offload_esp_modify_xfrm,
-};
-
-static const struct mlx5_accel_ipsec_ops *
-mlx5_ipsec_offload_ops(struct mlx5_core_dev *mdev)
-{
-	if (!mlx5_ipsec_device_caps(mdev))
-		return NULL;
-
-	return &ipsec_offload_ops;
-}
-
-void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops;
-	int err = 0;
-
-	ipsec_ops = mlx5_ipsec_offload_ops(mdev);
-	if (!ipsec_ops || !ipsec_ops->init) {
-		mlx5_core_dbg(mdev, "IPsec ops is not supported\n");
-		return;
-	}
-
-	err = ipsec_ops->init(mdev);
-	if (err) {
-		mlx5_core_warn_once(
-			mdev, "Failed to start IPsec device, err = %d\n", err);
-		return;
-	}
-
-	mdev->ipsec_ops = ipsec_ops;
-}
-
-void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->cleanup)
-		return;
-
-	ipsec_ops->cleanup(mdev);
-}
-
-unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->counters_count)
-		return -EOPNOTSUPP;
-
-	return ipsec_ops->counters_count(mdev);
-}
-
-int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
-				   unsigned int count)
-{
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->counters_read)
-		return -EOPNOTSUPP;
-
-	return ipsec_ops->counters_read(mdev, counters, count);
-}
-
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 				       struct mlx5_accel_esp_xfrm *xfrm,
 				       u32 *sa_handle)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
 	__be32 saddr[4] = {}, daddr[4] = {};
 
-	if (!ipsec_ops || !ipsec_ops->create_hw_context)
-		return  ERR_PTR(-EOPNOTSUPP);
-
 	if (!xfrm->attrs.is_ipv6) {
 		saddr[3] = xfrm->attrs.saddr.a4;
 		daddr[3] = xfrm->attrs.daddr.a4;
@@ -466,59 +386,37 @@ void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 		memcpy(daddr, xfrm->attrs.daddr.a6, sizeof(daddr));
 	}
 
-	return ipsec_ops->create_hw_context(mdev, xfrm, saddr, daddr,
-					    xfrm->attrs.spi,
-					    xfrm->attrs.is_ipv6, sa_handle);
+	return mlx5_ipsec_offload_create_sa_ctx(mdev, xfrm, saddr, daddr,
+						xfrm->attrs.spi,
+						xfrm->attrs.is_ipv6, sa_handle);
 }
 
 void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->free_hw_context)
-		return;
-
-	ipsec_ops->free_hw_context(context);
+	mlx5_ipsec_offload_delete_sa_ctx(context);
 }
 
 struct mlx5_accel_esp_xfrm *
 mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
 			   const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = mdev->ipsec_ops;
 	struct mlx5_accel_esp_xfrm *xfrm;
 
-	if (!ipsec_ops || !ipsec_ops->esp_create_xfrm)
-		return ERR_PTR(-EOPNOTSUPP);
-
-	xfrm = ipsec_ops->esp_create_xfrm(mdev, attrs, 0);
+	xfrm = mlx5_ipsec_offload_esp_create_xfrm(mdev, attrs);
 	if (IS_ERR(xfrm))
 		return xfrm;
 
 	xfrm->mdev = mdev;
 	return xfrm;
 }
-EXPORT_SYMBOL_GPL(mlx5_accel_esp_create_xfrm);
 
 void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = xfrm->mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->esp_destroy_xfrm)
-		return;
-
-	ipsec_ops->esp_destroy_xfrm(xfrm);
+	mlx5_ipsec_offload_esp_destroy_xfrm(xfrm);
 }
-EXPORT_SYMBOL_GPL(mlx5_accel_esp_destroy_xfrm);
 
 int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 			       const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	const struct mlx5_accel_ipsec_ops *ipsec_ops = xfrm->mdev->ipsec_ops;
-
-	if (!ipsec_ops || !ipsec_ops->esp_modify_xfrm)
-		return -EOPNOTSUPP;
-
-	return ipsec_ops->esp_modify_xfrm(xfrm, attrs);
+	return mlx5_ipsec_offload_esp_modify_xfrm(xfrm, attrs);
 }
-EXPORT_SYMBOL_GPL(mlx5_accel_esp_modify_xfrm);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
index 36e700b596d8..7dac104e6ef1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
@@ -7,43 +7,8 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/accel.h>
 
-#ifdef CONFIG_MLX5_EN_IPSEC
-
-unsigned int mlx5_accel_ipsec_counters_count(struct mlx5_core_dev *mdev);
-int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
-				   unsigned int count);
-
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 				       struct mlx5_accel_esp_xfrm *xfrm,
 				       u32 *sa_handle);
 void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context);
-
-void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev);
-void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev);
-
-struct mlx5_accel_ipsec_ops {
-	unsigned int (*counters_count)(struct mlx5_core_dev *mdev);
-	int (*counters_read)(struct mlx5_core_dev *mdev, u64 *counters,
-			     unsigned int count);
-	void *(*create_hw_context)(struct mlx5_core_dev *mdev,
-				   struct mlx5_accel_esp_xfrm *xfrm,
-				   const __be32 saddr[4], const __be32 daddr[4],
-				   const __be32 spi, bool is_ipv6,
-				   u32 *sa_handle);
-	void (*free_hw_context)(void *context);
-	int (*init)(struct mlx5_core_dev *mdev);
-	void (*cleanup)(struct mlx5_core_dev *mdev);
-	struct mlx5_accel_esp_xfrm *(*esp_create_xfrm)(
-		struct mlx5_core_dev *mdev,
-		const struct mlx5_accel_esp_xfrm_attrs *attrs, u32 flags);
-	int (*esp_modify_xfrm)(struct mlx5_accel_esp_xfrm *xfrm,
-			       const struct mlx5_accel_esp_xfrm_attrs *attrs);
-	void (*esp_destroy_xfrm)(struct mlx5_accel_esp_xfrm *xfrm);
-};
-
-#else
-static inline void mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev) {}
-
-static inline void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev) {}
-#endif /* CONFIG_MLX5_EN_IPSEC */
 #endif /* __MLX5_IPSEC_OFFLOAD_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 032de078723c..d504c8cb8f96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1181,8 +1181,6 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_fpga_start;
 	}
 
-	mlx5_accel_ipsec_init(dev);
-
 	err = mlx5_init_fs(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init flow steering\n");
@@ -1230,7 +1228,6 @@ err_vhca:
 err_set_hca:
 	mlx5_cleanup_fs(dev);
 err_fs:
-	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
 err_fpga_start:
 	mlx5_rsc_dump_cleanup(dev);
@@ -1256,7 +1253,6 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_sf_hw_table_destroy(dev);
 	mlx5_vhca_event_stop(dev);
 	mlx5_cleanup_fs(dev);
-	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
 	mlx5_rsc_dump_cleanup(dev);
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5af53c035949..ff47d49d8be4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -777,9 +777,6 @@ struct mlx5_core_dev {
 	} roce;
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
-#endif
-#ifdef CONFIG_MLX5_EN_IPSEC
-	const struct mlx5_accel_ipsec_ops *ipsec_ops;
 #endif
 	struct mlx5_clock        clock;
 	struct mlx5_ib_clock_info  *clock_info;
-- 
cgit v1.2.3


From 2984287c4c19949d7eb451dcad0bd5c54a2a376f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 6 Apr 2022 11:25:52 +0300
Subject: net/mlx5: Remove not-implemented IPsec capabilities

Clean a capabilities enum to remove not-implemented bits.

Link: https://lore.kernel.org/r/1044bb7b779107ff38e48e3f6553421104f3f819.1649232994.git.leonro@nvidia.com
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c  |  4 +---
 include/linux/mlx5/accel.h                                    | 11 ++++-------
 2 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index f0f44bd95cc9..37c9880719cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -51,10 +51,8 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 	    MLX5_CAP_IPSEC(mdev, ipsec_crypto_esp_aes_gcm_128_decrypt))
 		caps |= MLX5_ACCEL_IPSEC_CAP_ESP;
 
-	if (MLX5_CAP_IPSEC(mdev, ipsec_esn)) {
+	if (MLX5_CAP_IPSEC(mdev, ipsec_esn))
 		caps |= MLX5_ACCEL_IPSEC_CAP_ESN;
-		caps |= MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN;
-	}
 
 	/* We can accommodate up to 2^24 different IPsec objects
 	 * because we use up to 24 bit in flow table metadata
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index 73e4d50a9f02..0f2596297f6a 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -113,13 +113,10 @@ struct mlx5_accel_esp_xfrm {
 
 enum mlx5_accel_ipsec_cap {
 	MLX5_ACCEL_IPSEC_CAP_DEVICE		= 1 << 0,
-	MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA	= 1 << 1,
-	MLX5_ACCEL_IPSEC_CAP_ESP		= 1 << 2,
-	MLX5_ACCEL_IPSEC_CAP_IPV6		= 1 << 3,
-	MLX5_ACCEL_IPSEC_CAP_LSO		= 1 << 4,
-	MLX5_ACCEL_IPSEC_CAP_RX_NO_TRAILER	= 1 << 5,
-	MLX5_ACCEL_IPSEC_CAP_ESN		= 1 << 6,
-	MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN	= 1 << 7,
+	MLX5_ACCEL_IPSEC_CAP_ESP		= 1 << 1,
+	MLX5_ACCEL_IPSEC_CAP_IPV6		= 1 << 2,
+	MLX5_ACCEL_IPSEC_CAP_LSO		= 1 << 3,
+	MLX5_ACCEL_IPSEC_CAP_ESN		= 1 << 4,
 };
 
 #ifdef CONFIG_MLX5_EN_IPSEC
-- 
cgit v1.2.3


From efaa0227f6c6a5073951b20cf2f8c63c4155306c Mon Sep 17 00:00:00 2001
From: tangmeng <tangmeng@uniontech.com>
Date: Tue, 15 Feb 2022 14:50:19 +0800
Subject: timers: Move timer sysctl into the timer code

This is part of the effort to reduce kernel/sysctl.c to only contain the
core logic.

Signed-off-by: tangmeng <tangmeng@uniontech.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20220215065019.7520-1-tangmeng@uniontech.com
---
 include/linux/timer.h |  8 --------
 kernel/sysctl.c       | 11 -----------
 kernel/time/timer.c   | 53 ++++++++++++++++++++++++++++++++++++---------------
 3 files changed, 38 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timer.h b/include/linux/timer.h
index fda13c9d1256..648f00105f58 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -196,14 +196,6 @@ extern void init_timers(void);
 struct hrtimer;
 extern enum hrtimer_restart it_real_fn(struct hrtimer *);
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-struct ctl_table;
-
-extern unsigned int sysctl_timer_migration;
-int timer_migration_handler(struct ctl_table *table, int write,
-			    void *buffer, size_t *lenp, loff_t *ppos);
-#endif
-
 unsigned long __round_jiffies(unsigned long j, int cpu);
 unsigned long __round_jiffies_relative(unsigned long j, int cpu);
 unsigned long round_jiffies(unsigned long j);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 830aaf8ca08e..5b7b1a82ae6a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2288,17 +2288,6 @@ static struct ctl_table kern_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
 	},
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-	{
-		.procname	= "timer_migration",
-		.data		= &sysctl_timer_migration,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= timer_migration_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif
 #ifdef CONFIG_BPF_SYSCALL
 	{
 		.procname	= "unprivileged_bpf_disabled",
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 60aebf2b7f0a..ef082d43c307 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -44,6 +44,7 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/random.h>
+#include <linux/sysctl.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -223,7 +224,7 @@ static void timer_update_keys(struct work_struct *work);
 static DECLARE_WORK(timer_update_work, timer_update_keys);
 
 #ifdef CONFIG_SMP
-unsigned int sysctl_timer_migration = 1;
+static unsigned int sysctl_timer_migration = 1;
 
 DEFINE_STATIC_KEY_FALSE(timers_migration_enabled);
 
@@ -234,7 +235,42 @@ static void timers_update_migration(void)
 	else
 		static_branch_disable(&timers_migration_enabled);
 }
-#else
+
+#ifdef CONFIG_SYSCTL
+static int timer_migration_handler(struct ctl_table *table, int write,
+			    void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	mutex_lock(&timer_keys_mutex);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (!ret && write)
+		timers_update_migration();
+	mutex_unlock(&timer_keys_mutex);
+	return ret;
+}
+
+static struct ctl_table timer_sysctl[] = {
+	{
+		.procname	= "timer_migration",
+		.data		= &sysctl_timer_migration,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= timer_migration_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{}
+};
+
+static int __init timer_sysctl_init(void)
+{
+	register_sysctl("kernel", timer_sysctl);
+	return 0;
+}
+device_initcall(timer_sysctl_init);
+#endif /* CONFIG_SYSCTL */
+#else /* CONFIG_SMP */
 static inline void timers_update_migration(void) { }
 #endif /* !CONFIG_SMP */
 
@@ -251,19 +287,6 @@ void timers_update_nohz(void)
 	schedule_work(&timer_update_work);
 }
 
-int timer_migration_handler(struct ctl_table *table, int write,
-			    void *buffer, size_t *lenp, loff_t *ppos)
-{
-	int ret;
-
-	mutex_lock(&timer_keys_mutex);
-	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-	if (!ret && write)
-		timers_update_migration();
-	mutex_unlock(&timer_keys_mutex);
-	return ret;
-}
-
 static inline bool is_timers_nohz_active(void)
 {
 	return static_branch_unlikely(&timers_nohz_active);
-- 
cgit v1.2.3


From a8b6d6708bb682108d8c899bc0cb7873240daf8a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 7 Feb 2022 15:38:28 +0100
Subject: iio: core: Enhance the kernel doc of modes and currentmodes iio_dev
 entries

Let's provide more details about these two variables because their
understanding may not be straightforward for someone not used to the IIO
subsystem internal logic. The different modes will soon be also be more
documented for the same reason.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20220207143840.707510-2-miquel.raynal@bootlin.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index faf00f2c0be6..f191b80466cd 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -488,8 +488,15 @@ struct iio_buffer_setup_ops {
 
 /**
  * struct iio_dev - industrial I/O device
- * @modes:		[DRIVER] operating modes supported by device
- * @currentmode:	[INTERN] current operating mode
+ * @modes:		[DRIVER] bitmask listing all the operating modes
+ *			supported by the IIO device. This list should be
+ *			initialized before registering the IIO device. It can
+ *			also be filed up by the IIO core, as a result of
+ *			enabling particular features in the driver
+ *			(see iio_triggered_event_setup()).
+ * @currentmode:	[INTERN] operating mode currently in use, may be
+ *			eventually checked by device drivers but should be
+ *			considered read-only as this is a core internal bit
  * @dev:		[DRIVER] device structure, should be assigned a parent
  *			and owner
  * @buffer:		[DRIVER] any buffer present
-- 
cgit v1.2.3


From 474010127e2505fc463236470908e1ff5ddb3578 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 7 Feb 2022 15:38:33 +0100
Subject: iio: st_sensors: Add a local lock for protecting odr

Right now the (framework) mlock lock is (ab)used for multiple purposes:
1- protecting concurrent accesses over the odr local cache
2- avoid changing samplig frequency whilst buffer is running

Let's start by handling situation #1 with a local lock.

Suggested-by: Jonathan Cameron <jic23@kernel.org>
Cc: Denis Ciocca <denis.ciocca@st.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20220207143840.707510-7-miquel.raynal@bootlin.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/common/st_sensors/st_sensors_core.c | 24 ++++++++++++++++++------
 include/linux/iio/common/st_sensors.h           |  3 +++
 2 files changed, 21 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index 829ffe54d8a1..0cc66c82d58a 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -71,16 +71,18 @@ st_sensors_match_odr_error:
 
 int st_sensors_set_odr(struct iio_dev *indio_dev, unsigned int odr)
 {
-	int err;
+	int err = 0;
 	struct st_sensor_odr_avl odr_out = {0, 0};
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
 
+	mutex_lock(&sdata->odr_lock);
+
 	if (!sdata->sensor_settings->odr.mask)
-		return 0;
+		goto unlock_mutex;
 
 	err = st_sensors_match_odr(sdata->sensor_settings, odr, &odr_out);
 	if (err < 0)
-		goto st_sensors_match_odr_error;
+		goto unlock_mutex;
 
 	if ((sdata->sensor_settings->odr.addr ==
 					sdata->sensor_settings->pw.addr) &&
@@ -103,7 +105,9 @@ int st_sensors_set_odr(struct iio_dev *indio_dev, unsigned int odr)
 	if (err >= 0)
 		sdata->odr = odr_out.hz;
 
-st_sensors_match_odr_error:
+unlock_mutex:
+	mutex_unlock(&sdata->odr_lock);
+
 	return err;
 }
 EXPORT_SYMBOL_NS(st_sensors_set_odr, IIO_ST_SENSORS);
@@ -361,6 +365,8 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev,
 	struct st_sensors_platform_data *of_pdata;
 	int err = 0;
 
+	mutex_init(&sdata->odr_lock);
+
 	/* If OF/DT pdata exists, it will take precedence of anything else */
 	of_pdata = st_sensors_dev_probe(indio_dev->dev.parent, pdata);
 	if (IS_ERR(of_pdata))
@@ -554,18 +560,24 @@ int st_sensors_read_info_raw(struct iio_dev *indio_dev,
 		err = -EBUSY;
 		goto out;
 	} else {
+		mutex_lock(&sdata->odr_lock);
 		err = st_sensors_set_enable(indio_dev, true);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&sdata->odr_lock);
 			goto out;
+		}
 
 		msleep((sdata->sensor_settings->bootime * 1000) / sdata->odr);
 		err = st_sensors_read_axis_data(indio_dev, ch, val);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&sdata->odr_lock);
 			goto out;
+		}
 
 		*val = *val >> ch->scan_type.shift;
 
 		err = st_sensors_set_enable(indio_dev, false);
+		mutex_unlock(&sdata->odr_lock);
 	}
 out:
 	mutex_unlock(&indio_dev->mlock);
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index 22f67845cdd3..db4a1b260348 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -237,6 +237,7 @@ struct st_sensor_settings {
  * @hw_irq_trigger: if we're using the hardware interrupt on the sensor.
  * @hw_timestamp: Latest timestamp from the interrupt handler, when in use.
  * @buffer_data: Data used by buffer part.
+ * @odr_lock: Local lock for preventing concurrent ODR accesses/changes
  */
 struct st_sensor_data {
 	struct iio_trigger *trig;
@@ -261,6 +262,8 @@ struct st_sensor_data {
 	s64 hw_timestamp;
 
 	char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned;
+
+	struct mutex odr_lock;
 };
 
 #ifdef CONFIG_IIO_BUFFER
-- 
cgit v1.2.3


From 2f53b4adfede66f1bc1c8bb7efd7ced2bad1191a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 7 Feb 2022 15:38:36 +0100
Subject: iio: Un-inline iio_buffer_enabled()

As we are going to hide the currentmode inside the opaque structure,
this helper would soon need to call a non-inline function which would
simply drop the benefit of having the helper defined inline in a header.

One alternative is to move this helper in the core as there is no more
interest in defining it inline in a header. We will pay the minor cost
either way.

Let's do like the iio_device_id() helper which also refers to the opaque
structure and gets defined in the core.

Suggested-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20220207143840.707510-10-miquel.raynal@bootlin.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 12 ++++++++++++
 include/linux/iio/iio.h         | 11 +----------
 2 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 2f48e9a97274..c91930244915 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -184,6 +184,18 @@ int iio_device_id(struct iio_dev *indio_dev)
 }
 EXPORT_SYMBOL_GPL(iio_device_id);
 
+/**
+ * iio_buffer_enabled() - helper function to test if the buffer is enabled
+ * @indio_dev:		IIO device structure for device
+ */
+bool iio_buffer_enabled(struct iio_dev *indio_dev)
+{
+	return indio_dev->currentmode
+		& (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE |
+		   INDIO_BUFFER_SOFTWARE);
+}
+EXPORT_SYMBOL_GPL(iio_buffer_enabled);
+
 /**
  * iio_sysfs_match_string_with_gaps - matches given string in an array with gaps
  * @array: array of strings
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index f191b80466cd..faabb852128a 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -550,6 +550,7 @@ struct iio_dev {
 };
 
 int iio_device_id(struct iio_dev *indio_dev);
+bool iio_buffer_enabled(struct iio_dev *indio_dev);
 
 const struct iio_chan_spec
 *iio_find_channel_from_si(struct iio_dev *indio_dev, int si);
@@ -679,16 +680,6 @@ struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv);
 __printf(2, 3)
 struct iio_trigger *devm_iio_trigger_alloc(struct device *parent,
 					   const char *fmt, ...);
-/**
- * iio_buffer_enabled() - helper function to test if the buffer is enabled
- * @indio_dev:		IIO device structure for device
- **/
-static inline bool iio_buffer_enabled(struct iio_dev *indio_dev)
-{
-	return indio_dev->currentmode
-		& (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE |
-		   INDIO_BUFFER_SOFTWARE);
-}
 
 /**
  * iio_get_debugfs_dentry() - helper function to get the debugfs_dentry
-- 
cgit v1.2.3


From 8c576f87ad7eb639b8bd4472a9bb830e0696dda5 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 7 Feb 2022 15:38:37 +0100
Subject: iio: core: Hide read accesses to iio_dev->currentmode

In order to later move this variable within the opaque structure, let's
create a helper for accessing it in read-only mode. This helper will be
exposed to device drivers and kept accessible for the few that could need
it. The write access to this variable however should be fully reserved to
the core so in a second step we will hide this variable into the opaque
structure.

Cc: Eugen Hristev <eugen.hristev@microchip.com>
Cc: Nicolas Ferre <nicolas.ferre@microchip.com>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Ludovic Desroches <ludovic.desroches@microchip.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20220207143840.707510-11-miquel.raynal@bootlin.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/bmc150-accel-core.c |  4 ++--
 drivers/iio/adc/at91-sama5d2_adc.c    |  4 ++--
 drivers/iio/industrialio-core.c       | 11 +++++++++++
 include/linux/iio/iio.h               |  1 +
 4 files changed, 16 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index 7516d7dde1af..57e8a8350cd1 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -1525,7 +1525,7 @@ static int bmc150_accel_buffer_postenable(struct iio_dev *indio_dev)
 	struct bmc150_accel_data *data = iio_priv(indio_dev);
 	int ret = 0;
 
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED)
+	if (iio_device_get_current_mode(indio_dev) == INDIO_BUFFER_TRIGGERED)
 		return 0;
 
 	mutex_lock(&data->mutex);
@@ -1557,7 +1557,7 @@ static int bmc150_accel_buffer_predisable(struct iio_dev *indio_dev)
 {
 	struct bmc150_accel_data *data = iio_priv(indio_dev);
 
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED)
+	if (iio_device_get_current_mode(indio_dev) == INDIO_BUFFER_TRIGGERED)
 		return 0;
 
 	mutex_lock(&data->mutex);
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index 854b1f81d807..b764823ce57e 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -1117,7 +1117,7 @@ static int at91_adc_buffer_prepare(struct iio_dev *indio_dev)
 		return at91_adc_configure_touch(st, true);
 
 	/* if we are not in triggered mode, we cannot enable the buffer. */
-	if (!(indio_dev->currentmode & INDIO_ALL_TRIGGERED_MODES))
+	if (!(iio_device_get_current_mode(indio_dev) & INDIO_ALL_TRIGGERED_MODES))
 		return -EINVAL;
 
 	/* we continue with the triggered buffer */
@@ -1159,7 +1159,7 @@ static int at91_adc_buffer_postdisable(struct iio_dev *indio_dev)
 		return at91_adc_configure_touch(st, false);
 
 	/* if we are not in triggered mode, nothing to do here */
-	if (!(indio_dev->currentmode & INDIO_ALL_TRIGGERED_MODES))
+	if (!(iio_device_get_current_mode(indio_dev) & INDIO_ALL_TRIGGERED_MODES))
 		return -EINVAL;
 
 	/*
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index c91930244915..fa1e00bee787 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -2070,6 +2070,17 @@ void iio_device_release_direct_mode(struct iio_dev *indio_dev)
 }
 EXPORT_SYMBOL_GPL(iio_device_release_direct_mode);
 
+/**
+ * iio_device_get_current_mode() - helper function providing read-only access to
+ *				   the @currentmode variable
+ * @indio_dev:			   IIO device structure for device
+ */
+int iio_device_get_current_mode(struct iio_dev *indio_dev)
+{
+	return indio_dev->currentmode;
+}
+EXPORT_SYMBOL_GPL(iio_device_get_current_mode);
+
 subsys_initcall(iio_init);
 module_exit(iio_exit);
 
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index faabb852128a..31098ffa7dc9 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -550,6 +550,7 @@ struct iio_dev {
 };
 
 int iio_device_id(struct iio_dev *indio_dev);
+int iio_device_get_current_mode(struct iio_dev *indio_dev);
 bool iio_buffer_enabled(struct iio_dev *indio_dev);
 
 const struct iio_chan_spec
-- 
cgit v1.2.3


From 51570c9d4b3a678f77a50ac139f67290e946ec86 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 7 Feb 2022 15:38:38 +0100
Subject: iio: core: Move the currentmode entry to the opaque structure

This entry should, under no situation, be modified by device
drivers. Now that we have limited its read access to device drivers
really needing it and did so through a dedicated helper, we can
easily move this variable to the opaque structure in order to
prevent any further modification from non-authorized code (out of the
core, basically).

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Alexandru Ardelean <ardeleanalex@gmail.com>
Link: https://lore.kernel.org/r/20220207143840.707510-12-miquel.raynal@bootlin.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-buffer.c  | 12 ++++++------
 drivers/iio/industrialio-core.c    | 10 +++++++---
 drivers/iio/industrialio-trigger.c |  2 +-
 include/linux/iio/iio-opaque.h     |  4 ++++
 include/linux/iio/iio.h            |  4 ----
 5 files changed, 18 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 4706d0e3c954..615662d75e68 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -1065,7 +1065,7 @@ static int iio_enable_buffers(struct iio_dev *indio_dev,
 	indio_dev->active_scan_mask = config->scan_mask;
 	indio_dev->scan_timestamp = config->scan_timestamp;
 	indio_dev->scan_bytes = config->scan_bytes;
-	indio_dev->currentmode = config->mode;
+	iio_dev_opaque->currentmode = config->mode;
 
 	iio_update_demux(indio_dev);
 
@@ -1103,7 +1103,7 @@ static int iio_enable_buffers(struct iio_dev *indio_dev,
 		}
 	}
 
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
+	if (iio_dev_opaque->currentmode == INDIO_BUFFER_TRIGGERED) {
 		ret = iio_trigger_attach_poll_func(indio_dev->trig,
 						   indio_dev->pollfunc);
 		if (ret)
@@ -1122,7 +1122,7 @@ static int iio_enable_buffers(struct iio_dev *indio_dev,
 	return 0;
 
 err_detach_pollfunc:
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
+	if (iio_dev_opaque->currentmode == INDIO_BUFFER_TRIGGERED) {
 		iio_trigger_detach_poll_func(indio_dev->trig,
 					     indio_dev->pollfunc);
 	}
@@ -1135,7 +1135,7 @@ err_run_postdisable:
 	if (indio_dev->setup_ops->postdisable)
 		indio_dev->setup_ops->postdisable(indio_dev);
 err_undo_config:
-	indio_dev->currentmode = INDIO_DIRECT_MODE;
+	iio_dev_opaque->currentmode = INDIO_DIRECT_MODE;
 	indio_dev->active_scan_mask = NULL;
 
 	return ret;
@@ -1165,7 +1165,7 @@ static int iio_disable_buffers(struct iio_dev *indio_dev)
 			ret = ret2;
 	}
 
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
+	if (iio_dev_opaque->currentmode == INDIO_BUFFER_TRIGGERED) {
 		iio_trigger_detach_poll_func(indio_dev->trig,
 					     indio_dev->pollfunc);
 	}
@@ -1184,7 +1184,7 @@ static int iio_disable_buffers(struct iio_dev *indio_dev)
 
 	iio_free_scan_mask(indio_dev, indio_dev->active_scan_mask);
 	indio_dev->active_scan_mask = NULL;
-	indio_dev->currentmode = INDIO_DIRECT_MODE;
+	iio_dev_opaque->currentmode = INDIO_DIRECT_MODE;
 
 	return ret;
 }
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index fa1e00bee787..a8c4e85c2bb5 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -190,7 +190,9 @@ EXPORT_SYMBOL_GPL(iio_device_id);
  */
 bool iio_buffer_enabled(struct iio_dev *indio_dev)
 {
-	return indio_dev->currentmode
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+
+	return iio_dev_opaque->currentmode
 		& (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE |
 		   INDIO_BUFFER_SOFTWARE);
 }
@@ -2072,12 +2074,14 @@ EXPORT_SYMBOL_GPL(iio_device_release_direct_mode);
 
 /**
  * iio_device_get_current_mode() - helper function providing read-only access to
- *				   the @currentmode variable
+ *				   the opaque @currentmode variable
  * @indio_dev:			   IIO device structure for device
  */
 int iio_device_get_current_mode(struct iio_dev *indio_dev)
 {
-	return indio_dev->currentmode;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+
+	return iio_dev_opaque->currentmode;
 }
 EXPORT_SYMBOL_GPL(iio_device_get_current_mode);
 
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index f504ed351b3e..585b6cef8fcc 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -444,7 +444,7 @@ static ssize_t iio_trigger_write_current(struct device *dev,
 	int ret;
 
 	mutex_lock(&indio_dev->mlock);
-	if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
+	if (iio_dev_opaque->currentmode == INDIO_BUFFER_TRIGGERED) {
 		mutex_unlock(&indio_dev->mlock);
 		return -EBUSY;
 	}
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
index 2be12b7b5dc5..6b3586b3f952 100644
--- a/include/linux/iio/iio-opaque.h
+++ b/include/linux/iio/iio-opaque.h
@@ -7,6 +7,9 @@
  * struct iio_dev_opaque - industrial I/O device opaque information
  * @indio_dev:			public industrial I/O device information
  * @id:			used to identify device internally
+ * @currentmode:		operating mode currently in use, may be eventually
+ *				checked by device drivers but should be considered
+ *				read-only as this is a core internal bit
  * @driver_module:		used to make it harder to undercut users
  * @info_exist_lock:		lock to prevent use during removal
  * @trig_readonly:		mark the current trigger immutable
@@ -36,6 +39,7 @@
  */
 struct iio_dev_opaque {
 	struct iio_dev			indio_dev;
+	int				currentmode;
 	int				id;
 	struct module			*driver_module;
 	struct mutex			info_exist_lock;
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 31098ffa7dc9..85cb924debd9 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -494,9 +494,6 @@ struct iio_buffer_setup_ops {
  *			also be filed up by the IIO core, as a result of
  *			enabling particular features in the driver
  *			(see iio_triggered_event_setup()).
- * @currentmode:	[INTERN] operating mode currently in use, may be
- *			eventually checked by device drivers but should be
- *			considered read-only as this is a core internal bit
  * @dev:		[DRIVER] device structure, should be assigned a parent
  *			and owner
  * @buffer:		[DRIVER] any buffer present
@@ -523,7 +520,6 @@ struct iio_buffer_setup_ops {
  */
 struct iio_dev {
 	int				modes;
-	int				currentmode;
 	struct device			dev;
 
 	struct iio_buffer		*buffer;
-- 
cgit v1.2.3


From f67c6c73cb07a4778425a2064640333ef7bfa42b Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 7 Feb 2022 15:38:39 +0100
Subject: iio: core: Simplify the registration of kfifo buffers

Among all the users of the kfifo buffers, no one uses the
INDIO_BUFFER_HARDWARE mode. So let's take this as a general rule and
simplify a little bit the internals - overall the documentation - by
eliminating unused specific cases. Use the INDIO_BUFFER_SOFTWARE mode by
default with kfifo buffers, which will basically mimic what all the "non
direct" modes do.

Cc: Benson Leung <bleung@chromium.org>
Cc: Guenter Roeck <groeck@chromium.org>
Cc: Jyoti Bhayana <jbhayana@google.com>
Cc: Jean-Baptiste Maneyrol <jmaneyrol@invensense.com>
Cc: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
Cc: Michael Hennerich <Michael.Hennerich@analog.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20220207143840.707510-13-miquel.raynal@bootlin.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/adxl367.c                               |  1 -
 drivers/iio/accel/fxls8962af-core.c                       |  1 -
 drivers/iio/accel/sca3000.c                               |  1 -
 drivers/iio/accel/ssp_accel_sensor.c                      |  1 -
 drivers/iio/adc/ina2xx-adc.c                              |  1 -
 drivers/iio/adc/ti_am335x_adc.c                           |  4 +---
 drivers/iio/buffer/kfifo_buf.c                            | 10 +---------
 drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c |  3 +--
 drivers/iio/common/scmi_sensors/scmi_iio.c                |  1 -
 drivers/iio/gyro/ssp_gyro_sensor.c                        |  1 -
 drivers/iio/health/max30100.c                             |  1 -
 drivers/iio/health/max30102.c                             |  1 -
 drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c         |  1 -
 drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c          |  1 -
 drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c            |  1 -
 drivers/iio/light/apds9960.c                              |  1 -
 drivers/staging/iio/impedance-analyzer/ad5933.c           |  1 -
 include/linux/iio/kfifo_buf.h                             |  5 ++---
 18 files changed, 5 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c
index 62960134ea19..0289ed8cf2c6 100644
--- a/drivers/iio/accel/adxl367.c
+++ b/drivers/iio/accel/adxl367.c
@@ -1567,7 +1567,6 @@ int adxl367_probe(struct device *dev, const struct adxl367_ops *ops,
 		return ret;
 
 	ret = devm_iio_kfifo_buffer_setup_ext(st->dev, indio_dev,
-					      INDIO_BUFFER_SOFTWARE,
 					      &adxl367_buffer_ops,
 					      adxl367_fifo_attributes);
 	if (ret)
diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c
index a9d2f10d5d45..8874d6d61725 100644
--- a/drivers/iio/accel/fxls8962af-core.c
+++ b/drivers/iio/accel/fxls8962af-core.c
@@ -1217,7 +1217,6 @@ int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq)
 			return ret;
 
 		ret = devm_iio_kfifo_buffer_setup(dev, indio_dev,
-						  INDIO_BUFFER_SOFTWARE,
 						  &fxls8962af_buffer_ops);
 		if (ret)
 			return ret;
diff --git a/drivers/iio/accel/sca3000.c b/drivers/iio/accel/sca3000.c
index 83c81072511e..29a68a7d34cd 100644
--- a/drivers/iio/accel/sca3000.c
+++ b/drivers/iio/accel/sca3000.c
@@ -1474,7 +1474,6 @@ static int sca3000_probe(struct spi_device *spi)
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
 	ret = devm_iio_kfifo_buffer_setup(&spi->dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &sca3000_ring_setup_ops);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/accel/ssp_accel_sensor.c b/drivers/iio/accel/ssp_accel_sensor.c
index a1164b439f41..7ca9d0d543e0 100644
--- a/drivers/iio/accel/ssp_accel_sensor.c
+++ b/drivers/iio/accel/ssp_accel_sensor.c
@@ -113,7 +113,6 @@ static int ssp_accel_probe(struct platform_device *pdev)
 	indio_dev->available_scan_masks = ssp_accel_scan_mask;
 
 	ret = devm_iio_kfifo_buffer_setup(&pdev->dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &ssp_accel_buffer_ops);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c
index 8d902a32a0fd..08a2c547f0b3 100644
--- a/drivers/iio/adc/ina2xx-adc.c
+++ b/drivers/iio/adc/ina2xx-adc.c
@@ -1027,7 +1027,6 @@ static int ina2xx_probe(struct i2c_client *client,
 	indio_dev->name = id->name;
 
 	ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &ina2xx_setup_ops);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index dbdc1ef48566..567d43a30955 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -376,9 +376,7 @@ static int tiadc_iio_buffered_hardware_setup(struct device *dev,
 {
 	int ret;
 
-	ret = devm_iio_kfifo_buffer_setup(dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
-					  setup_ops);
+	ret = devm_iio_kfifo_buffer_setup(dev, indio_dev, setup_ops);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iio/buffer/kfifo_buf.c b/drivers/iio/buffer/kfifo_buf.c
index 416d35a61ae2..35d8b4077376 100644
--- a/drivers/iio/buffer/kfifo_buf.c
+++ b/drivers/iio/buffer/kfifo_buf.c
@@ -259,8 +259,6 @@ static struct iio_buffer *devm_iio_kfifo_allocate(struct device *dev)
  * devm_iio_kfifo_buffer_setup_ext - Allocate a kfifo buffer & attach it to an IIO device
  * @dev: Device object to which to attach the life-time of this kfifo buffer
  * @indio_dev: The device the buffer should be attached to
- * @mode_flags: The mode flags for this buffer (INDIO_BUFFER_SOFTWARE and/or
- *		INDIO_BUFFER_TRIGGERED).
  * @setup_ops: The setup_ops required to configure the HW part of the buffer (optional)
  * @buffer_attrs: Extra sysfs buffer attributes for this IIO buffer
  *
@@ -271,22 +269,16 @@ static struct iio_buffer *devm_iio_kfifo_allocate(struct device *dev)
  */
 int devm_iio_kfifo_buffer_setup_ext(struct device *dev,
 				    struct iio_dev *indio_dev,
-				    int mode_flags,
 				    const struct iio_buffer_setup_ops *setup_ops,
 				    const struct attribute **buffer_attrs)
 {
 	struct iio_buffer *buffer;
 
-	if (!mode_flags)
-		return -EINVAL;
-
 	buffer = devm_iio_kfifo_allocate(dev);
 	if (!buffer)
 		return -ENOMEM;
 
-	mode_flags &= kfifo_access_funcs.modes;
-
-	indio_dev->modes |= mode_flags;
+	indio_dev->modes |= INDIO_BUFFER_SOFTWARE;
 	indio_dev->setup_ops = setup_ops;
 
 	buffer->attrs = buffer_attrs;
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index b2725c6adc7f..a4cf1d9a8a49 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -333,8 +333,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev,
 			 * We can not use trigger here, as events are generated
 			 * as soon as sample_frequency is set.
 			 */
-			ret = devm_iio_kfifo_buffer_setup_ext(dev, indio_dev,
-							      INDIO_BUFFER_SOFTWARE, NULL,
+			ret = devm_iio_kfifo_buffer_setup_ext(dev, indio_dev, NULL,
 							      cros_ec_sensor_fifo_attributes);
 			if (ret)
 				return ret;
diff --git a/drivers/iio/common/scmi_sensors/scmi_iio.c b/drivers/iio/common/scmi_sensors/scmi_iio.c
index d538bf3ab1ef..793d628db55f 100644
--- a/drivers/iio/common/scmi_sensors/scmi_iio.c
+++ b/drivers/iio/common/scmi_sensors/scmi_iio.c
@@ -686,7 +686,6 @@ static int scmi_iio_dev_probe(struct scmi_device *sdev)
 
 		err = devm_iio_kfifo_buffer_setup(&scmi_iio_dev->dev,
 						  scmi_iio_dev,
-						  INDIO_BUFFER_SOFTWARE,
 						  &scmi_iio_buffer_ops);
 		if (err < 0) {
 			dev_err(dev,
diff --git a/drivers/iio/gyro/ssp_gyro_sensor.c b/drivers/iio/gyro/ssp_gyro_sensor.c
index 5fd1bf9902ea..d332474bc484 100644
--- a/drivers/iio/gyro/ssp_gyro_sensor.c
+++ b/drivers/iio/gyro/ssp_gyro_sensor.c
@@ -113,7 +113,6 @@ static int ssp_gyro_probe(struct platform_device *pdev)
 	indio_dev->available_scan_masks = ssp_gyro_scan_mask;
 
 	ret = devm_iio_kfifo_buffer_setup(&pdev->dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &ssp_gyro_buffer_ops);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/health/max30100.c b/drivers/iio/health/max30100.c
index 36ba7611d9ce..ad5717965223 100644
--- a/drivers/iio/health/max30100.c
+++ b/drivers/iio/health/max30100.c
@@ -433,7 +433,6 @@ static int max30100_probe(struct i2c_client *client,
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
 	ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &max30100_buffer_setup_ops);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/health/max30102.c b/drivers/iio/health/max30102.c
index 2292876c55e2..abbcef563807 100644
--- a/drivers/iio/health/max30102.c
+++ b/drivers/iio/health/max30102.c
@@ -542,7 +542,6 @@ static int max30102_probe(struct i2c_client *client,
 	}
 
 	ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &max30102_buffer_setup_ops);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
index 383cc3250342..c3f433ad3af6 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
@@ -731,7 +731,6 @@ struct iio_dev *inv_icm42600_accel_init(struct inv_icm42600_state *st)
 	indio_dev->available_scan_masks = inv_icm42600_accel_scan_masks;
 
 	ret = devm_iio_kfifo_buffer_setup(dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &inv_icm42600_buffer_ops);
 	if (ret)
 		return ERR_PTR(ret);
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
index cec1dd0e0464..9d94a8518e3c 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
@@ -743,7 +743,6 @@ struct iio_dev *inv_icm42600_gyro_init(struct inv_icm42600_state *st)
 	indio_dev->setup_ops = &inv_icm42600_buffer_ops;
 
 	ret = devm_iio_kfifo_buffer_setup(dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &inv_icm42600_buffer_ops);
 	if (ret)
 		return ERR_PTR(ret);
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 16730a780964..f80c62849d30 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -746,7 +746,6 @@ int st_lsm6dsx_fifo_setup(struct st_lsm6dsx_hw *hw)
 			continue;
 
 		ret = devm_iio_kfifo_buffer_setup(hw->dev, hw->iio_devs[i],
-						  INDIO_BUFFER_SOFTWARE,
 						  &st_lsm6dsx_buffer_ops);
 		if (ret)
 			return ret;
diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c
index 4141c0fa7bc4..09b831f9f40b 100644
--- a/drivers/iio/light/apds9960.c
+++ b/drivers/iio/light/apds9960.c
@@ -1003,7 +1003,6 @@ static int apds9960_probe(struct i2c_client *client,
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
 	ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &apds9960_buffer_setup_ops);
 	if (ret)
 		return ret;
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 793918e1c45f..f177b20f0f2d 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -749,7 +749,6 @@ static int ad5933_probe(struct i2c_client *client,
 	indio_dev->num_channels = ARRAY_SIZE(ad5933_channels);
 
 	ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev,
-					  INDIO_BUFFER_SOFTWARE,
 					  &ad5933_ring_setup_ops);
 	if (ret)
 		return ret;
diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h
index ccd2ceae7b25..8a83fb58232d 100644
--- a/include/linux/iio/kfifo_buf.h
+++ b/include/linux/iio/kfifo_buf.h
@@ -12,11 +12,10 @@ void iio_kfifo_free(struct iio_buffer *r);
 
 int devm_iio_kfifo_buffer_setup_ext(struct device *dev,
 				    struct iio_dev *indio_dev,
-				    int mode_flags,
 				    const struct iio_buffer_setup_ops *setup_ops,
 				    const struct attribute **buffer_attrs);
 
-#define devm_iio_kfifo_buffer_setup(dev, indio_dev, mode_flags, setup_ops)	\
-	devm_iio_kfifo_buffer_setup_ext((dev), (indio_dev), (mode_flags), (setup_ops), NULL)
+#define devm_iio_kfifo_buffer_setup(dev, indio_dev, setup_ops)	\
+	devm_iio_kfifo_buffer_setup_ext((dev), (indio_dev), (setup_ops), NULL)
 
 #endif
-- 
cgit v1.2.3


From 4f1a22ee7b576a38dc5705837c9b0de0c7b5b064 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Fri, 8 Apr 2022 17:04:12 +0800
Subject: libata: Improve ATA queued command allocation

Improve ATA queued command allocation as follows:

- For attaining a qc tag for a SAS host we need to allocate a bit in
  ata_port.sas_tag_allocated bitmap.

  However we already have a unique tag per device in range
  [0, ATA_MAX_QUEUE -1] in the scsi cmnd budget token, so just use that
  instead.

- It is a bit pointless to have ata_qc_new_init() in libata-core.c since it
  pokes scsi internals, so inline it in ata_scsi_qc_new() (in
  libata-scsi.c). Also update Doc accordingly.

- Use standard SCSI helpers set_host_byte() and set_status_byte() in
  ata_scsi_qc_new().

Christoph Hellwig originally contributed the change to inline
ata_qc_new_init().

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
 Documentation/driver-api/libata.rst | 11 ---------
 drivers/ata/libata-core.c           | 48 +------------------------------------
 drivers/ata/libata-sata.c           | 25 -------------------
 drivers/ata/libata-scsi.c           | 46 ++++++++++++++++++++++++++---------
 drivers/ata/libata.h                | 13 ----------
 include/linux/libata.h              |  1 -
 6 files changed, 36 insertions(+), 108 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst
index d477e296bda5..311af516a3fd 100644
--- a/Documentation/driver-api/libata.rst
+++ b/Documentation/driver-api/libata.rst
@@ -424,12 +424,6 @@ How commands are issued
 -----------------------
 
 Internal commands
-    First, qc is allocated and initialized using :c:func:`ata_qc_new_init`.
-    Although :c:func:`ata_qc_new_init` doesn't implement any wait or retry
-    mechanism when qc is not available, internal commands are currently
-    issued only during initialization and error recovery, so no other
-    command is active and allocation is guaranteed to succeed.
-
     Once allocated qc's taskfile is initialized for the command to be
     executed. qc currently has two mechanisms to notify completion. One
     is via ``qc->complete_fn()`` callback and the other is completion
@@ -447,11 +441,6 @@ SCSI commands
     translated. No qc is involved in processing a simulated scmd. The
     result is computed right away and the scmd is completed.
 
-    For a translated scmd, :c:func:`ata_qc_new_init` is invoked to allocate a
-    qc and the scmd is translated into the qc. SCSI midlayer's
-    completion notification function pointer is stored into
-    ``qc->scsidone``.
-
     ``qc->complete_fn()`` callback is used for completion notification. ATA
     commands use :c:func:`ata_scsi_qc_complete` while ATAPI commands use
     :c:func:`atapi_qc_complete`. Both functions end up calling ``qc->scsidone``
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index ca64837641be..23d1dc5faf73 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4566,42 +4566,6 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 #endif /* __BIG_ENDIAN */
 }
 
-/**
- *	ata_qc_new_init - Request an available ATA command, and initialize it
- *	@dev: Device from whom we request an available command structure
- *	@tag: tag
- *
- *	LOCKING:
- *	None.
- */
-
-struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag)
-{
-	struct ata_port *ap = dev->link->ap;
-	struct ata_queued_cmd *qc;
-
-	/* no command while frozen */
-	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
-		return NULL;
-
-	/* libsas case */
-	if (ap->flags & ATA_FLAG_SAS_HOST) {
-		tag = ata_sas_allocate_tag(ap);
-		if (tag < 0)
-			return NULL;
-	}
-
-	qc = __ata_qc_from_tag(ap, tag);
-	qc->tag = qc->hw_tag = tag;
-	qc->scsicmd = NULL;
-	qc->ap = ap;
-	qc->dev = dev;
-
-	ata_qc_reinit(qc);
-
-	return qc;
-}
-
 /**
  *	ata_qc_free - free unused ata_queued_cmd
  *	@qc: Command to complete
@@ -4614,19 +4578,9 @@ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag)
  */
 void ata_qc_free(struct ata_queued_cmd *qc)
 {
-	struct ata_port *ap;
-	unsigned int tag;
-
-	WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */
-	ap = qc->ap;
-
 	qc->flags = 0;
-	tag = qc->tag;
-	if (ata_tag_valid(tag)) {
+	if (ata_tag_valid(qc->tag))
 		qc->tag = ATA_TAG_POISON;
-		if (ap->flags & ATA_FLAG_SAS_HOST)
-			ata_sas_free_tag(tag, ap);
-	}
 }
 
 void __ata_qc_complete(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 044a16daa2d4..7a5fe41aa5ae 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -1268,31 +1268,6 @@ int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap)
 }
 EXPORT_SYMBOL_GPL(ata_sas_queuecmd);
 
-int ata_sas_allocate_tag(struct ata_port *ap)
-{
-	unsigned int max_queue = ap->host->n_tags;
-	unsigned int i, tag;
-
-	for (i = 0, tag = ap->sas_last_tag + 1; i < max_queue; i++, tag++) {
-		tag = tag < max_queue ? tag : 0;
-
-		/* the last tag is reserved for internal command. */
-		if (ata_tag_internal(tag))
-			continue;
-
-		if (!test_and_set_bit(tag, &ap->sas_tag_allocated)) {
-			ap->sas_last_tag = tag;
-			return tag;
-		}
-	}
-	return -1;
-}
-
-void ata_sas_free_tag(unsigned int tag, struct ata_port *ap)
-{
-	clear_bit(tag, &ap->sas_tag_allocated);
-}
-
 /**
  *	sata_async_notification - SATA async notification handler
  *	@ap: ATA port where async notification is received
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 06c9d90238d9..42cecf95a4e5 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -638,24 +638,48 @@ EXPORT_SYMBOL_GPL(ata_scsi_ioctl);
 static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev,
 					      struct scsi_cmnd *cmd)
 {
+	struct ata_port *ap = dev->link->ap;
 	struct ata_queued_cmd *qc;
+	int tag;
 
-	qc = ata_qc_new_init(dev, scsi_cmd_to_rq(cmd)->tag);
-	if (qc) {
-		qc->scsicmd = cmd;
-		qc->scsidone = scsi_done;
-
-		qc->sg = scsi_sglist(cmd);
-		qc->n_elem = scsi_sg_count(cmd);
+	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
+		goto fail;
 
-		if (scsi_cmd_to_rq(cmd)->rq_flags & RQF_QUIET)
-			qc->flags |= ATA_QCFLAG_QUIET;
+	if (ap->flags & ATA_FLAG_SAS_HOST) {
+		/*
+		 * SAS hosts may queue > ATA_MAX_QUEUE commands so use
+		 * unique per-device budget token as a tag.
+		 */
+		if (WARN_ON_ONCE(cmd->budget_token >= ATA_MAX_QUEUE))
+			goto fail;
+		tag = cmd->budget_token;
 	} else {
-		cmd->result = (DID_OK << 16) | SAM_STAT_TASK_SET_FULL;
-		scsi_done(cmd);
+		tag = scsi_cmd_to_rq(cmd)->tag;
 	}
 
+	qc = __ata_qc_from_tag(ap, tag);
+	qc->tag = qc->hw_tag = tag;
+	qc->ap = ap;
+	qc->dev = dev;
+
+	ata_qc_reinit(qc);
+
+	qc->scsicmd = cmd;
+	qc->scsidone = scsi_done;
+
+	qc->sg = scsi_sglist(cmd);
+	qc->n_elem = scsi_sg_count(cmd);
+
+	if (scsi_cmd_to_rq(cmd)->rq_flags & RQF_QUIET)
+		qc->flags |= ATA_QCFLAG_QUIET;
+
 	return qc;
+
+fail:
+	set_host_byte(cmd, DID_OK);
+	set_status_byte(cmd, SAM_STAT_TASK_SET_FULL);
+	scsi_done(cmd);
+	return NULL;
 }
 
 static void ata_qc_set_pc_nbytes(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index c9c2496d91ea..926a7f41303d 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -44,7 +44,6 @@ static inline void ata_force_cbl(struct ata_port *ap) { }
 #endif
 extern u64 ata_tf_to_lba(const struct ata_taskfile *tf);
 extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf);
-extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag);
 extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
 			   u64 block, u32 n_block, unsigned int tf_flags,
 			   unsigned int tag, int class);
@@ -91,18 +90,6 @@ extern unsigned int ata_read_log_page(struct ata_device *dev, u8 log,
 
 #define to_ata_port(d) container_of(d, struct ata_port, tdev)
 
-/* libata-sata.c */
-#ifdef CONFIG_SATA_HOST
-int ata_sas_allocate_tag(struct ata_port *ap);
-void ata_sas_free_tag(unsigned int tag, struct ata_port *ap);
-#else
-static inline int ata_sas_allocate_tag(struct ata_port *ap)
-{
-	return -EOPNOTSUPP;
-}
-static inline void ata_sas_free_tag(unsigned int tag, struct ata_port *ap) { }
-#endif
-
 /* libata-acpi.c */
 #ifdef CONFIG_ATA_ACPI
 extern unsigned int ata_acpi_gtf_filter;
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 9b1d3d8b1252..16107122e587 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -820,7 +820,6 @@ struct ata_port {
 	unsigned int		cbl;	/* cable type; ATA_CBL_xxx */
 
 	struct ata_queued_cmd	qcmd[ATA_MAX_QUEUE + 1];
-	unsigned long		sas_tag_allocated; /* for sas tag allocation only */
 	u64			qc_active;
 	int			nr_active_links; /* #links with active qcs */
 	unsigned int		sas_last_tag;	/* track next tag hw expects */
-- 
cgit v1.2.3


From 9f8ed577c28813410614b418bad42285840c1a00 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Thu, 7 Apr 2022 14:20:50 +0800
Subject: net: skb: rename SKB_DROP_REASON_PTYPE_ABSENT

As David Ahern suggested, the reasons for skb drops should be more
general and not be code based.

Therefore, rename SKB_DROP_REASON_PTYPE_ABSENT to
SKB_DROP_REASON_UNHANDLED_PROTO, which is used for the cases of no
L3 protocol handler, no L4 protocol handler, version extensions, etc.

From previous discussion, now we have the aim to make these reasons
more abstract and users based, avoiding code based.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 8 +++-----
 include/trace/events/skb.h | 2 +-
 net/core/dev.c             | 8 +++-----
 3 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2394441fa3dd..173bc35a10a3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -408,11 +408,9 @@ enum skb_drop_reason {
 					 */
 	SKB_DROP_REASON_XDP,		/* dropped by XDP in input path */
 	SKB_DROP_REASON_TC_INGRESS,	/* dropped in TC ingress HOOK */
-	SKB_DROP_REASON_PTYPE_ABSENT,	/* not packet_type found to handle
-					 * the skb. For an etner packet,
-					 * this means that L3 protocol is
-					 * not supported
-					 */
+	SKB_DROP_REASON_UNHANDLED_PROTO,	/* protocol not implemented
+						 * or not supported
+						 */
 	SKB_DROP_REASON_SKB_CSUM,	/* sk_buff checksum computation
 					 * error
 					 */
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index e1670e1e4934..85abd7cbd221 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -50,7 +50,7 @@
 	EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG)		\
 	EM(SKB_DROP_REASON_XDP, XDP)				\
 	EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS)		\
-	EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT)		\
+	EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO)	\
 	EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM)			\
 	EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG)		\
 	EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT)	\
diff --git a/net/core/dev.c b/net/core/dev.c
index e027410e861b..ba853e878007 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5375,13 +5375,11 @@ check_vlan_id:
 		*ppt_prev = pt_prev;
 	} else {
 drop:
-		if (!deliver_exact) {
+		if (!deliver_exact)
 			dev_core_stats_rx_dropped_inc(skb->dev);
-			kfree_skb_reason(skb, SKB_DROP_REASON_PTYPE_ABSENT);
-		} else {
+		else
 			dev_core_stats_rx_nohandler_inc(skb->dev);
-			kfree_skb(skb);
-		}
+		kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO);
 		/* Jamal, now you will not able to escape explaining
 		 * me how you were going to use this. :-)
 		 */
-- 
cgit v1.2.3


From b384c95a861eebf47e88695cf6a29f34e0b10b0f Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Thu, 7 Apr 2022 14:20:52 +0800
Subject: net: icmp: add skb drop reasons to icmp protocol

Replace kfree_skb() used in icmp_rcv() and icmpv6_rcv() with
kfree_skb_reason().

In order to get the reasons of the skb drops after icmp message handle,
we change the return type of 'handler()' in 'struct icmp_control' from
'bool' to 'enum skb_drop_reason'. This may change its original
intention, as 'false' means failure, but 'SKB_NOT_DROPPED_YET' means
success now. Therefore, all 'handler' and the call of them need to be
handled. Following 'handler' functions are involved:

icmp_unreach()
icmp_redirect()
icmp_echo()
icmp_timestamp()
icmp_discard()

And following new drop reasons are added:

SKB_DROP_REASON_ICMP_CSUM
SKB_DROP_REASON_INVALID_PROTO

The reason 'INVALID_PROTO' is introduced for the case that the packet
doesn't follow rfc 1122 and is dropped. This is not a common case, and
I believe we can locate the problem from the data in the packet. For now,
this 'INVALID_PROTO' is used for the icmp broadcasts with wrong types.

Maybe there should be a document file for these reasons. For example,
list all the case that causes the 'UNHANDLED_PROTO' and 'INVALID_PROTO'
drop reason. Therefore, users can locate their problems according to the
document.

Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     |  5 ++++
 include/net/ping.h         |  2 +-
 include/trace/events/skb.h |  2 ++
 net/ipv4/icmp.c            | 75 +++++++++++++++++++++++++++-------------------
 net/ipv4/ping.c            | 14 +++++----
 net/ipv6/icmp.c            | 24 +++++++++------
 6 files changed, 75 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 173bc35a10a3..9b81ba497665 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -442,6 +442,11 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_TAP_TXFILTER,	/* dropped by tx filter implemented
 					 * at tun/tap, e.g., check_filter()
 					 */
+	SKB_DROP_REASON_ICMP_CSUM,	/* ICMP checksum error */
+	SKB_DROP_REASON_INVALID_PROTO,	/* the packet doesn't follow RFC
+					 * 2211, such as a broadcasts
+					 * ICMP_TIMESTAMP
+					 */
 	SKB_DROP_REASON_MAX,
 };
 
diff --git a/include/net/ping.h b/include/net/ping.h
index 2fe78874318c..b68fbfdb606f 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -76,7 +76,7 @@ int  ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 int  ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 			 void *user_icmph, size_t icmph_len);
 int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-bool ping_rcv(struct sk_buff *skb);
+enum skb_drop_reason ping_rcv(struct sk_buff *skb);
 
 #ifdef CONFIG_PROC_FS
 void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 85abd7cbd221..42647114fffe 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -61,6 +61,8 @@
 	EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC)		\
 	EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER)		\
 	EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER)		\
+	EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM)		\
+	EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO)	\
 	EMe(SKB_DROP_REASON_MAX, MAX)
 
 #undef EM
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 72a375c7f417..236debd9fded 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -186,7 +186,7 @@ EXPORT_SYMBOL(icmp_err_convert);
  */
 
 struct icmp_control {
-	bool (*handler)(struct sk_buff *skb);
+	enum skb_drop_reason (*handler)(struct sk_buff *skb);
 	short   error;		/* This ICMP is classed as an error message */
 };
 
@@ -839,8 +839,9 @@ static bool icmp_tag_validation(int proto)
  *	ICMP_PARAMETERPROB.
  */
 
-static bool icmp_unreach(struct sk_buff *skb)
+static enum skb_drop_reason icmp_unreach(struct sk_buff *skb)
 {
+	enum skb_drop_reason reason = SKB_NOT_DROPPED_YET;
 	const struct iphdr *iph;
 	struct icmphdr *icmph;
 	struct net *net;
@@ -860,8 +861,10 @@ static bool icmp_unreach(struct sk_buff *skb)
 	icmph = icmp_hdr(skb);
 	iph   = (const struct iphdr *)skb->data;
 
-	if (iph->ihl < 5) /* Mangled header, drop. */
+	if (iph->ihl < 5)  { /* Mangled header, drop. */
+		reason = SKB_DROP_REASON_IP_INHDR;
 		goto out_err;
+	}
 
 	switch (icmph->type) {
 	case ICMP_DEST_UNREACH:
@@ -941,10 +944,10 @@ static bool icmp_unreach(struct sk_buff *skb)
 	icmp_socket_deliver(skb, info);
 
 out:
-	return true;
+	return reason;
 out_err:
 	__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-	return false;
+	return reason ?: SKB_DROP_REASON_NOT_SPECIFIED;
 }
 
 
@@ -952,20 +955,20 @@ out_err:
  *	Handle ICMP_REDIRECT.
  */
 
-static bool icmp_redirect(struct sk_buff *skb)
+static enum skb_drop_reason icmp_redirect(struct sk_buff *skb)
 {
 	if (skb->len < sizeof(struct iphdr)) {
 		__ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
-		return false;
+		return SKB_DROP_REASON_PKT_TOO_SMALL;
 	}
 
 	if (!pskb_may_pull(skb, sizeof(struct iphdr))) {
 		/* there aught to be a stat */
-		return false;
+		return SKB_DROP_REASON_NOMEM;
 	}
 
 	icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway));
-	return true;
+	return SKB_NOT_DROPPED_YET;
 }
 
 /*
@@ -982,7 +985,7 @@ static bool icmp_redirect(struct sk_buff *skb)
  *	See also WRT handling of options once they are done and working.
  */
 
-static bool icmp_echo(struct sk_buff *skb)
+static enum skb_drop_reason icmp_echo(struct sk_buff *skb)
 {
 	struct icmp_bxm icmp_param;
 	struct net *net;
@@ -990,7 +993,7 @@ static bool icmp_echo(struct sk_buff *skb)
 	net = dev_net(skb_dst(skb)->dev);
 	/* should there be an ICMP stat for ignored echos? */
 	if (net->ipv4.sysctl_icmp_echo_ignore_all)
-		return true;
+		return SKB_NOT_DROPPED_YET;
 
 	icmp_param.data.icmph	   = *icmp_hdr(skb);
 	icmp_param.skb		   = skb;
@@ -1001,10 +1004,10 @@ static bool icmp_echo(struct sk_buff *skb)
 	if (icmp_param.data.icmph.type == ICMP_ECHO)
 		icmp_param.data.icmph.type = ICMP_ECHOREPLY;
 	else if (!icmp_build_probe(skb, &icmp_param.data.icmph))
-		return true;
+		return SKB_NOT_DROPPED_YET;
 
 	icmp_reply(&icmp_param, skb);
-	return true;
+	return SKB_NOT_DROPPED_YET;
 }
 
 /*	Helper for icmp_echo and icmpv6_echo_reply.
@@ -1122,7 +1125,7 @@ EXPORT_SYMBOL_GPL(icmp_build_probe);
  *		  MUST be accurate to a few minutes.
  *		  MUST be updated at least at 15Hz.
  */
-static bool icmp_timestamp(struct sk_buff *skb)
+static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb)
 {
 	struct icmp_bxm icmp_param;
 	/*
@@ -1147,17 +1150,17 @@ static bool icmp_timestamp(struct sk_buff *skb)
 	icmp_param.data_len	   = 0;
 	icmp_param.head_len	   = sizeof(struct icmphdr) + 12;
 	icmp_reply(&icmp_param, skb);
-	return true;
+	return SKB_NOT_DROPPED_YET;
 
 out_err:
 	__ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
-	return false;
+	return SKB_DROP_REASON_PKT_TOO_SMALL;
 }
 
-static bool icmp_discard(struct sk_buff *skb)
+static enum skb_drop_reason icmp_discard(struct sk_buff *skb)
 {
 	/* pretend it was a success */
-	return true;
+	return SKB_NOT_DROPPED_YET;
 }
 
 /*
@@ -1165,18 +1168,20 @@ static bool icmp_discard(struct sk_buff *skb)
  */
 int icmp_rcv(struct sk_buff *skb)
 {
-	struct icmphdr *icmph;
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct rtable *rt = skb_rtable(skb);
 	struct net *net = dev_net(rt->dst.dev);
-	bool success;
+	struct icmphdr *icmph;
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 		struct sec_path *sp = skb_sec_path(skb);
 		int nh;
 
 		if (!(sp && sp->xvec[sp->len - 1]->props.flags &
-				 XFRM_STATE_ICMP))
+				 XFRM_STATE_ICMP)) {
+			reason = SKB_DROP_REASON_XFRM_POLICY;
 			goto drop;
+		}
 
 		if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr)))
 			goto drop;
@@ -1184,8 +1189,11 @@ int icmp_rcv(struct sk_buff *skb)
 		nh = skb_network_offset(skb);
 		skb_set_network_header(skb, sizeof(*icmph));
 
-		if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
+		if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN,
+						skb)) {
+			reason = SKB_DROP_REASON_XFRM_POLICY;
 			goto drop;
+		}
 
 		skb_set_network_header(skb, nh);
 	}
@@ -1207,13 +1215,13 @@ int icmp_rcv(struct sk_buff *skb)
 		/* We can't use icmp_pointers[].handler() because it is an array of
 		 * size NR_ICMP_TYPES + 1 (19 elements) and PROBE has code 42.
 		 */
-		success = icmp_echo(skb);
-		goto success_check;
+		reason = icmp_echo(skb);
+		goto reason_check;
 	}
 
 	if (icmph->type == ICMP_EXT_ECHOREPLY) {
-		success = ping_rcv(skb);
-		goto success_check;
+		reason = ping_rcv(skb);
+		goto reason_check;
 	}
 
 	/*
@@ -1222,8 +1230,10 @@ int icmp_rcv(struct sk_buff *skb)
 	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
 	 *		  discarded.
 	 */
-	if (icmph->type > NR_ICMP_TYPES)
+	if (icmph->type > NR_ICMP_TYPES) {
+		reason = SKB_DROP_REASON_UNHANDLED_PROTO;
 		goto error;
+	}
 
 	/*
 	 *	Parse the ICMP message
@@ -1239,27 +1249,30 @@ int icmp_rcv(struct sk_buff *skb)
 		if ((icmph->type == ICMP_ECHO ||
 		     icmph->type == ICMP_TIMESTAMP) &&
 		    net->ipv4.sysctl_icmp_echo_ignore_broadcasts) {
+			reason = SKB_DROP_REASON_INVALID_PROTO;
 			goto error;
 		}
 		if (icmph->type != ICMP_ECHO &&
 		    icmph->type != ICMP_TIMESTAMP &&
 		    icmph->type != ICMP_ADDRESS &&
 		    icmph->type != ICMP_ADDRESSREPLY) {
+			reason = SKB_DROP_REASON_INVALID_PROTO;
 			goto error;
 		}
 	}
 
-	success = icmp_pointers[icmph->type].handler(skb);
-success_check:
-	if (success)  {
+	reason = icmp_pointers[icmph->type].handler(skb);
+reason_check:
+	if (!reason)  {
 		consume_skb(skb);
 		return NET_RX_SUCCESS;
 	}
 
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return NET_RX_DROP;
 csum_error:
+	reason = SKB_DROP_REASON_ICMP_CSUM;
 	__ICMP_INC_STATS(net, ICMP_MIB_CSUMERRORS);
 error:
 	__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 9878c7696acf..2897fcf71211 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -961,12 +961,12 @@ EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
  *	All we need to do is get the socket.
  */
 
-bool ping_rcv(struct sk_buff *skb)
+enum skb_drop_reason ping_rcv(struct sk_buff *skb)
 {
+	enum skb_drop_reason reason = SKB_DROP_REASON_NO_SOCKET;
 	struct sock *sk;
 	struct net *net = dev_net(skb->dev);
 	struct icmphdr *icmph = icmp_hdr(skb);
-	bool rc = false;
 
 	/* We assume the packet has already been checked by icmp_rcv */
 
@@ -981,15 +981,17 @@ bool ping_rcv(struct sk_buff *skb)
 		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 
 		pr_debug("rcv on socket %p\n", sk);
-		if (skb2 && !ping_queue_rcv_skb(sk, skb2))
-			rc = true;
+		if (skb2)
+			reason = __ping_queue_rcv_skb(sk, skb2);
+		else
+			reason = SKB_DROP_REASON_NOMEM;
 		sock_put(sk);
 	}
 
-	if (!rc)
+	if (reason)
 		pr_debug("no socket, dropping\n");
 
-	return rc;
+	return reason;
 }
 EXPORT_SYMBOL_GPL(ping_rcv);
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index e6b978ea0e87..01c8003c9fc9 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -864,21 +864,23 @@ out:
 
 static int icmpv6_rcv(struct sk_buff *skb)
 {
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct net *net = dev_net(skb->dev);
 	struct net_device *dev = icmp6_dev(skb);
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	const struct in6_addr *saddr, *daddr;
 	struct icmp6hdr *hdr;
 	u8 type;
-	bool success = false;
 
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 		struct sec_path *sp = skb_sec_path(skb);
 		int nh;
 
 		if (!(sp && sp->xvec[sp->len - 1]->props.flags &
-				 XFRM_STATE_ICMP))
+				 XFRM_STATE_ICMP)) {
+			reason = SKB_DROP_REASON_XFRM_POLICY;
 			goto drop_no_count;
+		}
 
 		if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
 			goto drop_no_count;
@@ -886,8 +888,11 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		nh = skb_network_offset(skb);
 		skb_set_network_header(skb, sizeof(*hdr));
 
-		if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
+		if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN,
+						skb)) {
+			reason = SKB_DROP_REASON_XFRM_POLICY;
 			goto drop_no_count;
+		}
 
 		skb_set_network_header(skb, nh);
 	}
@@ -924,11 +929,11 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		break;
 
 	case ICMPV6_ECHO_REPLY:
-		success = ping_rcv(skb);
+		reason = ping_rcv(skb);
 		break;
 
 	case ICMPV6_EXT_ECHO_REPLY:
-		success = ping_rcv(skb);
+		reason = ping_rcv(skb);
 		break;
 
 	case ICMPV6_PKT_TOOBIG:
@@ -994,19 +999,20 @@ static int icmpv6_rcv(struct sk_buff *skb)
 	/* until the v6 path can be better sorted assume failure and
 	 * preserve the status quo behaviour for the rest of the paths to here
 	 */
-	if (success)
-		consume_skb(skb);
+	if (reason)
+		kfree_skb_reason(skb, reason);
 	else
-		kfree_skb(skb);
+		consume_skb(skb);
 
 	return 0;
 
 csum_error:
+	reason = SKB_DROP_REASON_ICMP_CSUM;
 	__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS);
 discard_it:
 	__ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS);
 drop_no_count:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 2e2ac4a3327479f7e2744cdd88a5c823f2057bad Mon Sep 17 00:00:00 2001
From: Laurent Vivier <laurent@vivier.eu>
Date: Wed, 6 Apr 2022 22:15:20 +0200
Subject: tty: goldfish: Introduce gf_ioread32()/gf_iowrite32()

The goldfish TTY device was clearly defined as having little-endian
registers, but the switch to __raw_{read,write}l(() broke its driver
when running on big-endian kernels (if anyone ever tried this).

The m68k qemu implementation got this wrong, and assumed native-endian
registers.  While this is a bug in qemu, it is probably impossible to
fix that since there is no way of knowing which other operating systems
have started relying on that bug over the years.

Hence revert commit da31de35cd2f ("tty: goldfish: use
__raw_writel()/__raw_readl()", and define gf_ioread32()/gf_iowrite32()
to be able to use accessors defined by the architecture.

Cc: stable@vger.kernel.org # v5.11+
Fixes: da31de35cd2fb78f ("tty: goldfish: use __raw_writel()/__raw_readl()")
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
Link: https://lore.kernel.org/r/20220406201523.243733-2-laurent@vivier.eu
[geert: Add rationale based on Arnd's comments]
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 drivers/tty/goldfish.c   | 20 ++++++++++----------
 include/linux/goldfish.h | 15 +++++++++++----
 2 files changed, 21 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c
index ad13532e92fe..9e8ccb8ed6d6 100644
--- a/drivers/tty/goldfish.c
+++ b/drivers/tty/goldfish.c
@@ -61,13 +61,13 @@ static void do_rw_io(struct goldfish_tty *qtty,
 	spin_lock_irqsave(&qtty->lock, irq_flags);
 	gf_write_ptr((void *)address, base + GOLDFISH_TTY_REG_DATA_PTR,
 		     base + GOLDFISH_TTY_REG_DATA_PTR_HIGH);
-	__raw_writel(count, base + GOLDFISH_TTY_REG_DATA_LEN);
+	gf_iowrite32(count, base + GOLDFISH_TTY_REG_DATA_LEN);
 
 	if (is_write)
-		__raw_writel(GOLDFISH_TTY_CMD_WRITE_BUFFER,
+		gf_iowrite32(GOLDFISH_TTY_CMD_WRITE_BUFFER,
 		       base + GOLDFISH_TTY_REG_CMD);
 	else
-		__raw_writel(GOLDFISH_TTY_CMD_READ_BUFFER,
+		gf_iowrite32(GOLDFISH_TTY_CMD_READ_BUFFER,
 		       base + GOLDFISH_TTY_REG_CMD);
 
 	spin_unlock_irqrestore(&qtty->lock, irq_flags);
@@ -142,7 +142,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 	unsigned char *buf;
 	u32 count;
 
-	count = __raw_readl(base + GOLDFISH_TTY_REG_BYTES_READY);
+	count = gf_ioread32(base + GOLDFISH_TTY_REG_BYTES_READY);
 	if (count == 0)
 		return IRQ_NONE;
 
@@ -159,7 +159,7 @@ static int goldfish_tty_activate(struct tty_port *port, struct tty_struct *tty)
 {
 	struct goldfish_tty *qtty = container_of(port, struct goldfish_tty,
 									port);
-	__raw_writel(GOLDFISH_TTY_CMD_INT_ENABLE, qtty->base + GOLDFISH_TTY_REG_CMD);
+	gf_iowrite32(GOLDFISH_TTY_CMD_INT_ENABLE, qtty->base + GOLDFISH_TTY_REG_CMD);
 	return 0;
 }
 
@@ -167,7 +167,7 @@ static void goldfish_tty_shutdown(struct tty_port *port)
 {
 	struct goldfish_tty *qtty = container_of(port, struct goldfish_tty,
 									port);
-	__raw_writel(GOLDFISH_TTY_CMD_INT_DISABLE, qtty->base + GOLDFISH_TTY_REG_CMD);
+	gf_iowrite32(GOLDFISH_TTY_CMD_INT_DISABLE, qtty->base + GOLDFISH_TTY_REG_CMD);
 }
 
 static int goldfish_tty_open(struct tty_struct *tty, struct file *filp)
@@ -202,7 +202,7 @@ static unsigned int goldfish_tty_chars_in_buffer(struct tty_struct *tty)
 {
 	struct goldfish_tty *qtty = &goldfish_ttys[tty->index];
 	void __iomem *base = qtty->base;
-	return __raw_readl(base + GOLDFISH_TTY_REG_BYTES_READY);
+	return gf_ioread32(base + GOLDFISH_TTY_REG_BYTES_READY);
 }
 
 static void goldfish_tty_console_write(struct console *co, const char *b,
@@ -355,7 +355,7 @@ static int goldfish_tty_probe(struct platform_device *pdev)
 	 * on Ranchu emulator (qemu2) returns 1 here and
 	 * driver will use physical addresses.
 	 */
-	qtty->version = __raw_readl(base + GOLDFISH_TTY_REG_VERSION);
+	qtty->version = gf_ioread32(base + GOLDFISH_TTY_REG_VERSION);
 
 	/*
 	 * Goldfish TTY device on Ranchu emulator (qemu2)
@@ -374,7 +374,7 @@ static int goldfish_tty_probe(struct platform_device *pdev)
 		}
 	}
 
-	__raw_writel(GOLDFISH_TTY_CMD_INT_DISABLE, base + GOLDFISH_TTY_REG_CMD);
+	gf_iowrite32(GOLDFISH_TTY_CMD_INT_DISABLE, base + GOLDFISH_TTY_REG_CMD);
 
 	ret = request_irq(irq, goldfish_tty_interrupt, IRQF_SHARED,
 			  "goldfish_tty", qtty);
@@ -436,7 +436,7 @@ static int goldfish_tty_remove(struct platform_device *pdev)
 #ifdef CONFIG_GOLDFISH_TTY_EARLY_CONSOLE
 static void gf_early_console_putchar(struct uart_port *port, unsigned char ch)
 {
-	__raw_writel(ch, port->membase);
+	gf_iowrite32(ch, port->membase);
 }
 
 static void gf_early_write(struct console *con, const char *s, unsigned int n)
diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h
index 12be1601fd84..bcc17f95b906 100644
--- a/include/linux/goldfish.h
+++ b/include/linux/goldfish.h
@@ -8,14 +8,21 @@
 
 /* Helpers for Goldfish virtual platform */
 
+#ifndef gf_ioread32
+#define gf_ioread32 ioread32
+#endif
+#ifndef gf_iowrite32
+#define gf_iowrite32 iowrite32
+#endif
+
 static inline void gf_write_ptr(const void *ptr, void __iomem *portl,
 				void __iomem *porth)
 {
 	const unsigned long addr = (unsigned long)ptr;
 
-	__raw_writel(lower_32_bits(addr), portl);
+	gf_iowrite32(lower_32_bits(addr), portl);
 #ifdef CONFIG_64BIT
-	__raw_writel(upper_32_bits(addr), porth);
+	gf_iowrite32(upper_32_bits(addr), porth);
 #endif
 }
 
@@ -23,9 +30,9 @@ static inline void gf_write_dma_addr(const dma_addr_t addr,
 				     void __iomem *portl,
 				     void __iomem *porth)
 {
-	__raw_writel(lower_32_bits(addr), portl);
+	gf_iowrite32(lower_32_bits(addr), portl);
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	__raw_writel(upper_32_bits(addr), porth);
+	gf_iowrite32(upper_32_bits(addr), porth);
 #endif
 }
 
-- 
cgit v1.2.3


From 52126d4c03798cc55aa927fea4c776ab26b5a5f0 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 6 Feb 2022 10:47:45 +0100
Subject: dmaengine: Remove a useless mutex

According to lib/idr.c,
   The IDA handles its own locking.  It is safe to call any of the IDA
   functions without synchronisation in your code.

so the 'chan_mutex' mutex can just be removed.
It is here only to protect some ida_alloc()/ida_free() calls.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/7180452c1d77b039e27b6f9418e0e7d9dd33c431.1644140845.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c   | 7 -------
 include/linux/dmaengine.h | 1 -
 2 files changed, 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 2cfa8458b51b..e80feeea0e01 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1053,9 +1053,7 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 	 * When the chan_id is a negative value, we are dynamically adding
 	 * the channel. Otherwise we are static enumerating.
 	 */
-	mutex_lock(&device->chan_mutex);
 	chan->chan_id = ida_alloc(&device->chan_ida, GFP_KERNEL);
-	mutex_unlock(&device->chan_mutex);
 	if (chan->chan_id < 0) {
 		pr_err("%s: unable to alloc ida for chan: %d\n",
 		       __func__, chan->chan_id);
@@ -1078,9 +1076,7 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 	return 0;
 
  err_out_ida:
-	mutex_lock(&device->chan_mutex);
 	ida_free(&device->chan_ida, chan->chan_id);
-	mutex_unlock(&device->chan_mutex);
  err_free_dev:
 	kfree(chan->dev);
  err_free_local:
@@ -1113,9 +1109,7 @@ static void __dma_async_device_channel_unregister(struct dma_device *device,
 	device->chancnt--;
 	chan->dev->chan = NULL;
 	mutex_unlock(&dma_list_mutex);
-	mutex_lock(&device->chan_mutex);
 	ida_free(&device->chan_ida, chan->chan_id);
-	mutex_unlock(&device->chan_mutex);
 	device_unregister(&chan->dev->device);
 	free_percpu(chan->local);
 }
@@ -1250,7 +1244,6 @@ int dma_async_device_register(struct dma_device *device)
 	if (rc != 0)
 		return rc;
 
-	mutex_init(&device->chan_mutex);
 	ida_init(&device->chan_ida);
 
 	/* represent channels in sysfs. Probably want devs too */
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 842d4f7ca752..6db9e03afd0b 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -870,7 +870,6 @@ struct dma_device {
 	struct device *dev;
 	struct module *owner;
 	struct ida chan_ida;
-	struct mutex chan_mutex;	/* to protect chan_ida */
 
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
-- 
cgit v1.2.3


From 95ebe80d99de3cb849c522a1f768e5e8befa0b7c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Thu, 20 Jan 2022 13:16:18 -0800
Subject: srcu: Fix s/is/if/ typo in srcu_node comment

This commit fixed a typo in the srcu_node structure's ->srcu_have_cbs
comment.  While in the area, redo a couple of comments to take advantage
of 100-character line lengths.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/srcutree.h | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index cb1f4351e8ba..4025840ba9a3 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -47,11 +47,9 @@ struct srcu_data {
  */
 struct srcu_node {
 	spinlock_t __private lock;
-	unsigned long srcu_have_cbs[4];		/* GP seq for children */
-						/*  having CBs, but only */
-						/*  is > ->srcu_gq_seq. */
-	unsigned long srcu_data_have_cbs[4];	/* Which srcu_data structs */
-						/*  have CBs for given GP? */
+	unsigned long srcu_have_cbs[4];		/* GP seq for children having CBs, but only */
+						/*  if greater than ->srcu_gq_seq. */
+	unsigned long srcu_data_have_cbs[4];	/* Which srcu_data structs have CBs for given GP? */
 	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	struct srcu_node *srcu_parent;		/* Next up in tree. */
 	int grplo;				/* Least CPU for node. */
-- 
cgit v1.2.3


From 994f706872e6ce080506bd795ecf783d5b617de6 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Mon, 24 Jan 2022 09:46:57 -0800
Subject: srcu: Make Tree SRCU able to operate without snp_node array

This commit makes Tree SRCU able to operate without an snp_node
array, that is, when the srcu_data structures' ->mynode pointers
are NULL.  This can result in high contention on the srcu_struct
structure's ->lock, but only when there are lots of call_srcu(),
synchronize_srcu(), and synchronize_srcu_expedited() calls.

Note that when there is no snp_node array, all SRCU callbacks use
CPU 0's callback queue.  This is optimal in the common case of low
update-side load because it removes the need to search each CPU
for the single callback that made the grace period happen.

Co-developed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/srcutree.h |  14 +++-
 kernel/rcu/srcutree.c    | 203 ++++++++++++++++++++++++++---------------------
 2 files changed, 124 insertions(+), 93 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 4025840ba9a3..8d1da136a93a 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -63,8 +63,9 @@ struct srcu_struct {
 	struct srcu_node node[NUM_RCU_NODES];	/* Combining tree. */
 	struct srcu_node *level[RCU_NUM_LVLS + 1];
 						/* First node at each level. */
+	int srcu_size_state;			/* Small-to-big transition state. */
 	struct mutex srcu_cb_mutex;		/* Serialize CB preparation. */
-	spinlock_t __private lock;		/* Protect counters */
+	spinlock_t __private lock;		/* Protect counters and size state. */
 	struct mutex srcu_gp_mutex;		/* Serialize GP work. */
 	unsigned int srcu_idx;			/* Current rdr array element. */
 	unsigned long srcu_gp_seq;		/* Grace-period seq #. */
@@ -83,6 +84,17 @@ struct srcu_struct {
 	struct lockdep_map dep_map;
 };
 
+/* Values for size state variable (->srcu_size_state). */
+#define SRCU_SIZE_SMALL		0
+#define SRCU_SIZE_ALLOC		1
+#define SRCU_SIZE_WAIT_BARRIER	2
+#define SRCU_SIZE_WAIT_CALL	3
+#define SRCU_SIZE_WAIT_CBS1	4
+#define SRCU_SIZE_WAIT_CBS2	5
+#define SRCU_SIZE_WAIT_CBS3	6
+#define SRCU_SIZE_WAIT_CBS4	7
+#define SRCU_SIZE_BIG		8
+
 /* Values for state variable (bottom bits of ->srcu_gp_seq). */
 #define SRCU_STATE_IDLE		0
 #define SRCU_STATE_SCAN1	1
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 7d13e35e5d27..e23696edd43b 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -152,16 +152,17 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp)
 		sdp->ssp = ssp;
 		sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
 	}
+	smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
 }
 
 /*
  * Initialize non-compile-time initialized fields, including the
- * associated srcu_node and srcu_data structures.  The is_static
- * parameter is passed through to init_srcu_struct_nodes(), and
- * also tells us that ->sda has already been wired up to srcu_data.
+ * associated srcu_node and srcu_data structures.  The is_static parameter
+ * tells us that ->sda has already been wired up to srcu_data.
  */
 static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 {
+	ssp->srcu_size_state = SRCU_SIZE_SMALL;
 	mutex_init(&ssp->srcu_cb_mutex);
 	mutex_init(&ssp->srcu_gp_mutex);
 	ssp->srcu_idx = 0;
@@ -175,6 +176,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	if (!ssp->sda)
 		return -ENOMEM;
 	init_srcu_struct_nodes(ssp);
+	ssp->srcu_size_state = SRCU_SIZE_BIG;
 	ssp->srcu_gp_seq_needed_exp = 0;
 	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */
@@ -391,6 +393,7 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 	}
 	free_percpu(ssp->sda);
 	ssp->sda = NULL;
+	ssp->srcu_size_state = SRCU_SIZE_SMALL;
 }
 EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
@@ -439,6 +442,10 @@ static void srcu_gp_start(struct srcu_struct *ssp)
 	struct srcu_data *sdp = this_cpu_ptr(ssp->sda);
 	int state;
 
+	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
+		sdp = per_cpu_ptr(ssp->sda, 0);
+	else
+		sdp = this_cpu_ptr(ssp->sda);
 	lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
 	WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
 	spin_lock_rcu_node(sdp);  /* Interrupts already disabled. */
@@ -539,38 +546,40 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	/* A new grace period can start at this point.  But only one. */
 
 	/* Initiate callback invocation as needed. */
-	idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
-	srcu_for_each_node_breadth_first(ssp, snp) {
-		spin_lock_irq_rcu_node(snp);
-		cbs = false;
-		last_lvl = snp >= ssp->level[rcu_num_lvls - 1];
-		if (last_lvl)
-			cbs = snp->srcu_have_cbs[idx] == gpseq;
-		snp->srcu_have_cbs[idx] = gpseq;
-		rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
-		if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq))
-			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq);
-		mask = snp->srcu_data_have_cbs[idx];
-		snp->srcu_data_have_cbs[idx] = 0;
-		spin_unlock_irq_rcu_node(snp);
-		if (cbs)
-			srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay);
-
-		/* Occasionally prevent srcu_data counter wrap. */
-		if (!(gpseq & counter_wrap_check) && last_lvl)
-			for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
-				sdp = per_cpu_ptr(ssp->sda, cpu);
-				spin_lock_irqsave_rcu_node(sdp, flags);
-				if (ULONG_CMP_GE(gpseq,
-						 sdp->srcu_gp_seq_needed + 100))
-					sdp->srcu_gp_seq_needed = gpseq;
-				if (ULONG_CMP_GE(gpseq,
-						 sdp->srcu_gp_seq_needed_exp + 100))
-					sdp->srcu_gp_seq_needed_exp = gpseq;
-				spin_unlock_irqrestore_rcu_node(sdp, flags);
-			}
+	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) {
+		srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, 0), cbdelay);
+	} else {
+		idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
+		srcu_for_each_node_breadth_first(ssp, snp) {
+			spin_lock_irq_rcu_node(snp);
+			cbs = false;
+			last_lvl = snp >= ssp->level[rcu_num_lvls - 1];
+			if (last_lvl)
+				cbs = snp->srcu_have_cbs[idx] == gpseq;
+			snp->srcu_have_cbs[idx] = gpseq;
+			rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
+			if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq))
+				WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq);
+			mask = snp->srcu_data_have_cbs[idx];
+			snp->srcu_data_have_cbs[idx] = 0;
+			spin_unlock_irq_rcu_node(snp);
+			if (cbs)
+				srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay);
+		}
 	}
 
+	/* Occasionally prevent srcu_data counter wrap. */
+	if (!(gpseq & counter_wrap_check))
+		for_each_possible_cpu(cpu) {
+			sdp = per_cpu_ptr(ssp->sda, cpu);
+			spin_lock_irqsave_rcu_node(sdp, flags);
+			if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed + 100))
+				sdp->srcu_gp_seq_needed = gpseq;
+			if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed_exp + 100))
+				sdp->srcu_gp_seq_needed_exp = gpseq;
+			spin_unlock_irqrestore_rcu_node(sdp, flags);
+		}
+
 	/* Callback initiation done, allow grace periods after next. */
 	mutex_unlock(&ssp->srcu_cb_mutex);
 
@@ -599,18 +608,19 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp
 {
 	unsigned long flags;
 
-	for (; snp != NULL; snp = snp->srcu_parent) {
-		if (rcu_seq_done(&ssp->srcu_gp_seq, s) ||
-		    ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
-			return;
-		spin_lock_irqsave_rcu_node(snp, flags);
-		if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) {
+	if (snp)
+		for (; snp != NULL; snp = snp->srcu_parent) {
+			if (rcu_seq_done(&ssp->srcu_gp_seq, s) ||
+			    ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
+				return;
+			spin_lock_irqsave_rcu_node(snp, flags);
+			if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) {
+				spin_unlock_irqrestore_rcu_node(snp, flags);
+				return;
+			}
+			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
 			spin_unlock_irqrestore_rcu_node(snp, flags);
-			return;
 		}
-		WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
-		spin_unlock_irqrestore_rcu_node(snp, flags);
-	}
 	spin_lock_irqsave_rcu_node(ssp, flags);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
 		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
@@ -633,36 +643,37 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 	unsigned long flags;
 	int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs);
 	struct srcu_node *snp;
-	struct srcu_node *snp_leaf = sdp->mynode;
+	struct srcu_node *snp_leaf = smp_load_acquire(&sdp->mynode);
 	unsigned long snp_seq;
 
-	/* Each pass through the loop does one level of the srcu_node tree. */
-	for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) {
-		if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != snp_leaf)
-			return; /* GP already done and CBs recorded. */
-		spin_lock_irqsave_rcu_node(snp, flags);
-		if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
-			snp_seq = snp->srcu_have_cbs[idx];
-			if (snp == snp_leaf && snp_seq == s)
-				snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
-			spin_unlock_irqrestore_rcu_node(snp, flags);
-			if (snp == snp_leaf && snp_seq != s) {
-				srcu_schedule_cbs_sdp(sdp, do_norm
-							   ? SRCU_INTERVAL
-							   : 0);
+	if (snp_leaf)
+		/* Each pass through the loop does one level of the srcu_node tree. */
+		for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) {
+			if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != snp_leaf)
+				return; /* GP already done and CBs recorded. */
+			spin_lock_irqsave_rcu_node(snp, flags);
+			if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
+				snp_seq = snp->srcu_have_cbs[idx];
+				if (snp == snp_leaf && snp_seq == s)
+					snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
+				spin_unlock_irqrestore_rcu_node(snp, flags);
+				if (snp == snp_leaf && snp_seq != s) {
+					srcu_schedule_cbs_sdp(sdp, do_norm
+								   ? SRCU_INTERVAL
+								   : 0);
+					return;
+				}
+				if (!do_norm)
+					srcu_funnel_exp_start(ssp, snp, s);
 				return;
 			}
-			if (!do_norm)
-				srcu_funnel_exp_start(ssp, snp, s);
-			return;
+			snp->srcu_have_cbs[idx] = s;
+			if (snp == snp_leaf)
+				snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
+			if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
+				WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
+			spin_unlock_irqrestore_rcu_node(snp, flags);
 		}
-		snp->srcu_have_cbs[idx] = s;
-		if (snp == snp_leaf)
-			snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
-		if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
-			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
-		spin_unlock_irqrestore_rcu_node(snp, flags);
-	}
 
 	/* Top of tree, must ensure the grace period will be started. */
 	spin_lock_irqsave_rcu_node(ssp, flags);
@@ -820,7 +831,10 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 
 	check_init_srcu_struct(ssp);
 	idx = srcu_read_lock(ssp);
-	sdp = raw_cpu_ptr(ssp->sda);
+	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_CALL)
+		sdp = per_cpu_ptr(ssp->sda, 0);
+	else
+		sdp = raw_cpu_ptr(ssp->sda);
 	spin_lock_irqsave_rcu_node(sdp, flags);
 	if (rhp)
 		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
@@ -840,7 +854,7 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	if (needgp)
 		srcu_funnel_gp_start(ssp, sdp, s, do_norm);
 	else if (needexp)
-		srcu_funnel_exp_start(ssp, sdp->mynode, s);
+		srcu_funnel_exp_start(ssp, smp_load_acquire(&sdp->mynode), s);
 	srcu_read_unlock(ssp, idx);
 	return s;
 }
@@ -1100,6 +1114,28 @@ static void srcu_barrier_cb(struct rcu_head *rhp)
 		complete(&ssp->srcu_barrier_completion);
 }
 
+/*
+ * Enqueue an srcu_barrier() callback on the specified srcu_data
+ * structure's ->cblist.  but only if that ->cblist already has at least one
+ * callback enqueued.  Note that if a CPU already has callbacks enqueue,
+ * it must have already registered the need for a future grace period,
+ * so all we need do is enqueue a callback that will use the same grace
+ * period as the last callback already in the queue.
+ */
+static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp)
+{
+	spin_lock_irq_rcu_node(sdp);
+	atomic_inc(&ssp->srcu_barrier_cpu_cnt);
+	sdp->srcu_barrier_head.func = srcu_barrier_cb;
+	debug_rcu_head_queue(&sdp->srcu_barrier_head);
+	if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
+				   &sdp->srcu_barrier_head)) {
+		debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
+		atomic_dec(&ssp->srcu_barrier_cpu_cnt);
+	}
+	spin_unlock_irq_rcu_node(sdp);
+}
+
 /**
  * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
  * @ssp: srcu_struct on which to wait for in-flight callbacks.
@@ -1107,7 +1143,6 @@ static void srcu_barrier_cb(struct rcu_head *rhp)
 void srcu_barrier(struct srcu_struct *ssp)
 {
 	int cpu;
-	struct srcu_data *sdp;
 	unsigned long s = rcu_seq_snap(&ssp->srcu_barrier_seq);
 
 	check_init_srcu_struct(ssp);
@@ -1123,27 +1158,11 @@ void srcu_barrier(struct srcu_struct *ssp)
 	/* Initial count prevents reaching zero until all CBs are posted. */
 	atomic_set(&ssp->srcu_barrier_cpu_cnt, 1);
 
-	/*
-	 * Each pass through this loop enqueues a callback, but only
-	 * on CPUs already having callbacks enqueued.  Note that if
-	 * a CPU already has callbacks enqueue, it must have already
-	 * registered the need for a future grace period, so all we
-	 * need do is enqueue a callback that will use the same
-	 * grace period as the last callback already in the queue.
-	 */
-	for_each_possible_cpu(cpu) {
-		sdp = per_cpu_ptr(ssp->sda, cpu);
-		spin_lock_irq_rcu_node(sdp);
-		atomic_inc(&ssp->srcu_barrier_cpu_cnt);
-		sdp->srcu_barrier_head.func = srcu_barrier_cb;
-		debug_rcu_head_queue(&sdp->srcu_barrier_head);
-		if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
-					   &sdp->srcu_barrier_head)) {
-			debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
-			atomic_dec(&ssp->srcu_barrier_cpu_cnt);
-		}
-		spin_unlock_irq_rcu_node(sdp);
-	}
+	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
+		srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, 0));
+	else
+		for_each_possible_cpu(cpu)
+			srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, cpu));
 
 	/* Remove the initial count, at which point reaching zero can happen. */
 	if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
-- 
cgit v1.2.3


From 2ec303113d978931ef368886c4c6bc854493e8bf Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 21 Jan 2022 16:13:52 -0800
Subject: srcu: Dynamically allocate srcu_node array

This commit shrinks the srcu_struct structure by converting its ->node
field from a fixed-size compile-time array to a pointer to a dynamically
allocated array.  In kernels built with large values of NR_CPUS that boot
on systems with smaller numbers of CPUs, this can save significant memory.

[ paulmck: Apply kernel test robot feedback. ]

Reported-by: A cast of thousands
Co-developed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/srcutree.h |  2 +-
 kernel/rcu/srcutree.c    | 65 +++++++++++++++++++++++++++++++++++++-----------
 2 files changed, 51 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 8d1da136a93a..8501b6b45941 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -60,7 +60,7 @@ struct srcu_node {
  * Per-SRCU-domain structure, similar in function to rcu_state.
  */
 struct srcu_struct {
-	struct srcu_node node[NUM_RCU_NODES];	/* Combining tree. */
+	struct srcu_node *node;			/* Combining tree. */
 	struct srcu_node *level[RCU_NUM_LVLS + 1];
 						/* First node at each level. */
 	int srcu_size_state;			/* Small-to-big transition state. */
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index e23696edd43b..e98cc218e42b 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -24,6 +24,7 @@
 #include <linux/smp.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/srcu.h>
 
 #include "rcu.h"
@@ -75,12 +76,42 @@ do {									\
 	spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)	\
 
 /*
- * Initialize SRCU combining tree.  Note that statically allocated
+ * Initialize SRCU per-CPU data.  Note that statically allocated
  * srcu_struct structures might already have srcu_read_lock() and
  * srcu_read_unlock() running against them.  So if the is_static parameter
  * is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[].
  */
-static void init_srcu_struct_nodes(struct srcu_struct *ssp)
+static void init_srcu_struct_data(struct srcu_struct *ssp)
+{
+	int cpu;
+	struct srcu_data *sdp;
+
+	/*
+	 * Initialize the per-CPU srcu_data array, which feeds into the
+	 * leaves of the srcu_node tree.
+	 */
+	WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
+		     ARRAY_SIZE(sdp->srcu_unlock_count));
+	for_each_possible_cpu(cpu) {
+		sdp = per_cpu_ptr(ssp->sda, cpu);
+		spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
+		rcu_segcblist_init(&sdp->srcu_cblist);
+		sdp->srcu_cblist_invoking = false;
+		sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq;
+		sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq;
+		sdp->mynode = NULL;
+		sdp->cpu = cpu;
+		INIT_WORK(&sdp->work, srcu_invoke_callbacks);
+		timer_setup(&sdp->delay_work, srcu_delay_timer, 0);
+		sdp->ssp = ssp;
+	}
+}
+
+/*
+ * Allocated and initialize SRCU combining tree.  Returns @true if
+ * allocation succeeded and @false otherwise.
+ */
+static bool init_srcu_struct_nodes(struct srcu_struct *ssp)
 {
 	int cpu;
 	int i;
@@ -92,6 +123,9 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp)
 
 	/* Initialize geometry if it has not already been initialized. */
 	rcu_init_geometry();
+	ssp->node = kcalloc(rcu_num_nodes, sizeof(*ssp->node), GFP_ATOMIC);
+	if (!ssp->node)
+		return false;
 
 	/* Work out the overall tree geometry. */
 	ssp->level[0] = &ssp->node[0];
@@ -129,30 +163,20 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp)
 	 * Initialize the per-CPU srcu_data array, which feeds into the
 	 * leaves of the srcu_node tree.
 	 */
-	WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
-		     ARRAY_SIZE(sdp->srcu_unlock_count));
 	level = rcu_num_lvls - 1;
 	snp_first = ssp->level[level];
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(ssp->sda, cpu);
-		spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
-		rcu_segcblist_init(&sdp->srcu_cblist);
-		sdp->srcu_cblist_invoking = false;
-		sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq;
-		sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq;
 		sdp->mynode = &snp_first[cpu / levelspread[level]];
 		for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
 			if (snp->grplo < 0)
 				snp->grplo = cpu;
 			snp->grphi = cpu;
 		}
-		sdp->cpu = cpu;
-		INIT_WORK(&sdp->work, srcu_invoke_callbacks);
-		timer_setup(&sdp->delay_work, srcu_delay_timer, 0);
-		sdp->ssp = ssp;
 		sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
 	}
 	smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
+	return true;
 }
 
 /*
@@ -163,6 +187,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp)
 static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 {
 	ssp->srcu_size_state = SRCU_SIZE_SMALL;
+	ssp->node = NULL;
 	mutex_init(&ssp->srcu_cb_mutex);
 	mutex_init(&ssp->srcu_gp_mutex);
 	ssp->srcu_idx = 0;
@@ -175,8 +200,16 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 		ssp->sda = alloc_percpu(struct srcu_data);
 	if (!ssp->sda)
 		return -ENOMEM;
-	init_srcu_struct_nodes(ssp);
-	ssp->srcu_size_state = SRCU_SIZE_BIG;
+	init_srcu_struct_data(ssp);
+	if (!init_srcu_struct_nodes(ssp)) {
+		if (!is_static) {
+			free_percpu(ssp->sda);
+			ssp->sda = NULL;
+			return -ENOMEM;
+		}
+	} else {
+		ssp->srcu_size_state = SRCU_SIZE_BIG;
+	}
 	ssp->srcu_gp_seq_needed_exp = 0;
 	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */
@@ -393,6 +426,8 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 	}
 	free_percpu(ssp->sda);
 	ssp->sda = NULL;
+	kfree(ssp->node);
+	ssp->node = NULL;
 	ssp->srcu_size_state = SRCU_SIZE_SMALL;
 }
 EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
-- 
cgit v1.2.3


From db8f1471c61336477e2bf74dcb00e67d650e6dea Mon Sep 17 00:00:00 2001
From: Alexander Aring <aahringo@redhat.com>
Date: Wed, 26 Jan 2022 10:03:54 -0500
Subject: srcu: Use export for srcu_struct defined by DEFINE_STATIC_SRCU()

If an srcu_struct structure defined by tree SRCU's DEFINE_STATIC_SRCU()
is used by a module, sparse will give the following diagnostic:

sparse: symbol '__srcu_struct_nodes_srcu' was not declared. Should it be static?

The problem is that a within-module DEFINE_STATIC_SRCU() must define
a non-static srcu_struct because it is exported by referencing it in a
special '__section("___srcu_struct_ptrs")'.  This reference is needed
so that module load and unloading can invoke init_srcu_struct() and
cleanup_srcu_struct(), respectively.  Unfortunately, sparse is unaware of
'__section("___srcu_struct_ptrs")', resulting in the above false-positive
diagnostic.  To avoid this false positive, this commit therefore creates
a prototype of the srcu_struct with an "extern" keyword.

Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/srcutree.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 8501b6b45941..44e998643f48 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -131,6 +131,7 @@ struct srcu_struct {
 #ifdef MODULE
 # define __DEFINE_SRCU(name, is_static)					\
 	is_static struct srcu_struct name;				\
+	extern struct srcu_struct * const __srcu_struct_##name;		\
 	struct srcu_struct * const __srcu_struct_##name			\
 		__section("___srcu_struct_ptrs") = &name
 #else
-- 
cgit v1.2.3


From 46470cf85d2b61abd37c6f66c4dacc1bc510d10f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Thu, 27 Jan 2022 13:20:49 -0800
Subject: srcu: Prevent cleanup_srcu_struct() from freeing non-dynamic ->sda

When an srcu_struct structure is created (but not in a kernel module)
by DEFINE_SRCU() and friends, the per-CPU srcu_data structure is
statically allocated.  In all other cases, that structure is obtained
from alloc_percpu(), in which case cleanup_srcu_struct() must invoke
free_percpu() on the resulting ->sda pointer in the srcu_struct pointer.

Which it does.

Except that it also invokes free_percpu() on the ->sda pointer
referencing the statically allocated per-CPU srcu_data structures.
Which free_percpu() is surprisingly OK with.

This commit nevertheless stops cleanup_srcu_struct() from freeing
statically allocated per-CPU srcu_data structures.

Co-developed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/srcutree.h | 1 +
 kernel/rcu/srcutree.c    | 9 ++++++---
 2 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 44e998643f48..44bd204498a1 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -73,6 +73,7 @@ struct srcu_struct {
 	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	unsigned long srcu_last_gp_end;		/* Last GP end timestamp (ns) */
 	struct srcu_data __percpu *sda;		/* Per-CPU srcu_data array. */
+	bool sda_is_static;			/* May ->sda be passed to free_percpu()? */
 	unsigned long srcu_barrier_seq;		/* srcu_barrier seq #. */
 	struct mutex srcu_barrier_mutex;	/* Serialize barrier ops. */
 	struct completion srcu_barrier_completion;
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index b7138dbe1a2d..7209fd95dde9 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -217,6 +217,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	mutex_init(&ssp->srcu_barrier_mutex);
 	atomic_set(&ssp->srcu_barrier_cpu_cnt, 0);
 	INIT_DELAYED_WORK(&ssp->work, process_srcu);
+	ssp->sda_is_static = is_static;
 	if (!is_static)
 		ssp->sda = alloc_percpu(struct srcu_data);
 	if (!ssp->sda)
@@ -226,7 +227,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	if (READ_ONCE(ssp->srcu_size_state) == SRCU_SIZE_SMALL && convert_to_big == 1) {
 		if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) {
-			if (!is_static) {
+			if (!ssp->sda_is_static) {
 				free_percpu(ssp->sda);
 				ssp->sda = NULL;
 				return -ENOMEM;
@@ -446,8 +447,10 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 			rcu_seq_current(&ssp->srcu_gp_seq), ssp->srcu_gp_seq_needed);
 		return; /* Caller forgot to stop doing call_srcu()? */
 	}
-	free_percpu(ssp->sda);
-	ssp->sda = NULL;
+	if (!ssp->sda_is_static) {
+		free_percpu(ssp->sda);
+		ssp->sda = NULL;
+	}
 	kfree(ssp->node);
 	ssp->node = NULL;
 	ssp->srcu_size_state = SRCU_SIZE_SMALL;
-- 
cgit v1.2.3


From 9f2e91d94c91558e3764fe4e01c5e6281a90f239 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Thu, 27 Jan 2022 20:32:05 -0800
Subject: srcu: Add contention-triggered addition of srcu_node tree

This commit instruments the acquisitions of the srcu_struct structure's
->lock, enabling the initiation of a transition from SRCU_SIZE_SMALL
to SRCU_SIZE_BIG when sufficient contention is experienced.  The
instrumentation counts the number of trylock failures within the confines
of a single jiffy.  If that number exceeds the value specified by the
srcutree.small_contention_lim kernel boot parameter (which defaults to
100), and if the value specified by the srcutree.convert_to_big kernel
boot parameter has the 0x10 bit set (defaults to 0), then a transition
will be automatically initiated.

By default, there will never be any transitions, so that none of the
srcu_struct structures ever gains an srcu_node array.

The useful values for srcutree.convert_to_big are:

0x00:  Never convert.
0x01:  Always convert at init_srcu_struct() time.
0x02:  Convert when rcutorture prints its first round of statistics.
0x03:  Decide conversion approach at boot given system size.
0x10:  Convert if contention is encountered.
0x12:  Convert if contention is encountered or when rcutorture prints
        its first round of statistics, whichever comes first.

The value 0x11 acts the same as 0x01 because the conversion happens
before there is any chance of contention.

[ paulmck: Apply "static" feedback from kernel test robot. ]

Co-developed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 Documentation/admin-guide/kernel-parameters.txt |   9 ++
 include/linux/srcutree.h                        |   2 +
 kernel/rcu/srcutree.c                           | 107 ++++++++++++++++++------
 3 files changed, 94 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 1f1fcac7777d..177e688768c0 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5616,6 +5616,7 @@
 				   0:  Never.
 				   1:  At init_srcu_struct() time.
 				   2:  When rcutorture decides to.
+				0x1X:  Above plus if high contention.
 
 			Either way, the srcu_node tree will be sized based
 			on the actual runtime number of CPUs (nr_cpu_ids)
@@ -5638,6 +5639,14 @@
 			expediting.  Set to zero to disable automatic
 			expediting.
 
+	srcutree.small_contention_lim [KNL]
+			Specifies the number of update-side contention
+			events per jiffy will be tolerated before
+			initiating a conversion of an srcu_struct
+			structure to big form.	Note that the value of
+			srcutree.convert_to_big must have the 0x10 bit
+			set for contention-based conversions to occur.
+
 	ssbd=		[ARM64,HW]
 			Speculative Store Bypass Disable control
 
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 44bd204498a1..1b9ff4ed37e4 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -72,6 +72,8 @@ struct srcu_struct {
 	unsigned long srcu_gp_seq_needed;	/* Latest gp_seq needed. */
 	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	unsigned long srcu_last_gp_end;		/* Last GP end timestamp (ns) */
+	unsigned long srcu_size_jiffies;	/* Current contention-measurement interval. */
+	unsigned long srcu_n_lock_retries;	/* Contention events in current interval. */
 	struct srcu_data __percpu *sda;		/* Per-CPU srcu_data array. */
 	bool sda_is_static;			/* May ->sda be passed to free_percpu()? */
 	unsigned long srcu_barrier_seq;		/* srcu_barrier seq #. */
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index c9460374d437..0bc6a0a3edee 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -41,13 +41,29 @@ module_param(counter_wrap_check, ulong, 0444);
 
 /*
  * Control conversion to SRCU_SIZE_BIG:
- * 0: Don't convert at all (default).
- * 1: Convert at init_srcu_struct() time.
- * 2: Convert when rcutorture invokes srcu_torture_stats_print().
+ *    0: Don't convert at all (default).
+ *    1: Convert at init_srcu_struct() time.
+ *    2: Convert when rcutorture invokes srcu_torture_stats_print().
+ *    3: Decide at boot time based on system shape.
+ * 0x1x: Convert when excessive contention encountered.
  */
-static int convert_to_big;
+#define SRCU_SIZING_NONE	0
+#define SRCU_SIZING_INIT	1
+#define SRCU_SIZING_TORTURE	2
+#define SRCU_SIZING_AUTO	3
+#define SRCU_SIZING_CONTEND	0x10
+#define SRCU_SIZING_IS(x) ((convert_to_big & ~SRCU_SIZING_CONTEND) == x)
+#define SRCU_SIZING_IS_NONE() (SRCU_SIZING_IS(SRCU_SIZING_NONE))
+#define SRCU_SIZING_IS_INIT() (SRCU_SIZING_IS(SRCU_SIZING_INIT))
+#define SRCU_SIZING_IS_TORTURE() (SRCU_SIZING_IS(SRCU_SIZING_TORTURE))
+#define SRCU_SIZING_IS_CONTEND() (convert_to_big & SRCU_SIZING_CONTEND)
+static int convert_to_big = SRCU_SIZING_NONE;
 module_param(convert_to_big, int, 0444);
 
+/* Contention events per jiffy to initiate transition to big. */
+static int small_contention_lim __read_mostly = 100;
+module_param(small_contention_lim, int, 0444);
+
 /* Early-boot callback-management, so early that no lock is required! */
 static LIST_HEAD(srcu_boot_list);
 static bool __read_mostly srcu_init_done;
@@ -58,31 +74,40 @@ static void process_srcu(struct work_struct *work);
 static void srcu_delay_timer(struct timer_list *t);
 
 /* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
-#define spin_lock_rcu_node(p)					\
-do {									\
-	spin_lock(&ACCESS_PRIVATE(p, lock));			\
-	smp_mb__after_unlock_lock();					\
+#define spin_lock_rcu_node(p)							\
+do {										\
+	spin_lock(&ACCESS_PRIVATE(p, lock));					\
+	smp_mb__after_unlock_lock();						\
 } while (0)
 
 #define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock))
 
-#define spin_lock_irq_rcu_node(p)					\
-do {									\
-	spin_lock_irq(&ACCESS_PRIVATE(p, lock));			\
-	smp_mb__after_unlock_lock();					\
+#define spin_lock_irq_rcu_node(p)						\
+do {										\
+	spin_lock_irq(&ACCESS_PRIVATE(p, lock));				\
+	smp_mb__after_unlock_lock();						\
 } while (0)
 
-#define spin_unlock_irq_rcu_node(p)					\
+#define spin_unlock_irq_rcu_node(p)						\
 	spin_unlock_irq(&ACCESS_PRIVATE(p, lock))
 
-#define spin_lock_irqsave_rcu_node(p, flags)			\
-do {									\
-	spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags);	\
-	smp_mb__after_unlock_lock();					\
+#define spin_lock_irqsave_rcu_node(p, flags)					\
+do {										\
+	spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags);			\
+	smp_mb__after_unlock_lock();						\
 } while (0)
 
-#define spin_unlock_irqrestore_rcu_node(p, flags)			\
-	spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)	\
+#define spin_trylock_irqsave_rcu_node(p, flags)					\
+({										\
+	bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags);	\
+										\
+	if (___locked)								\
+		smp_mb__after_unlock_lock();					\
+	___locked;								\
+})
+
+#define spin_unlock_irqrestore_rcu_node(p, flags)				\
+	spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)			\
 
 /*
  * Initialize SRCU per-CPU data.  Note that statically allocated
@@ -225,7 +250,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	init_srcu_struct_data(ssp);
 	ssp->srcu_gp_seq_needed_exp = 0;
 	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
-	if (READ_ONCE(ssp->srcu_size_state) == SRCU_SIZE_SMALL && convert_to_big == 1) {
+	if (READ_ONCE(ssp->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
 		if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) {
 			if (!ssp->sda_is_static) {
 				free_percpu(ssp->sda);
@@ -272,6 +297,15 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+/*
+ * Initiate a transition to SRCU_SIZE_BIG with lock held.
+ */
+static void __srcu_transition_to_big(struct srcu_struct *ssp)
+{
+	lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
+	smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_ALLOC);
+}
+
 /*
  * Initiate an idempotent transition to SRCU_SIZE_BIG.
  */
@@ -287,10 +321,35 @@ static void srcu_transition_to_big(struct srcu_struct *ssp)
 		spin_unlock_irqrestore_rcu_node(ssp, flags);
 		return;
 	}
-	smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_ALLOC);
+	__srcu_transition_to_big(ssp);
 	spin_unlock_irqrestore_rcu_node(ssp, flags);
 }
 
+/*
+ * Acquire the specified srcu_struct structure's ->lock, but check for
+ * excessive contention, which results in initiation of a transition
+ * to SRCU_SIZE_BIG.  But only if the srcutree.convert_to_big module
+ * parameter permits this.
+ */
+static void spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags)
+{
+	unsigned long j;
+
+	if (spin_trylock_irqsave_rcu_node(ssp, *flags))
+		return;
+	spin_lock_irqsave_rcu_node(ssp, *flags);
+	if (!SRCU_SIZING_IS_CONTEND() || ssp->srcu_size_state)
+		return;
+	j = jiffies;
+	if (ssp->srcu_size_jiffies != j) {
+		ssp->srcu_size_jiffies = j;
+		ssp->srcu_n_lock_retries = 0;
+	}
+	if (++ssp->srcu_n_lock_retries <= small_contention_lim)
+		return;
+	__srcu_transition_to_big(ssp);
+}
+
 /*
  * First-use initialization of statically allocated srcu_struct
  * structure.  Wiring up the combining tree is more than can be
@@ -718,7 +777,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp
 			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
 			spin_unlock_irqrestore_rcu_node(snp, flags);
 		}
-	spin_lock_irqsave_rcu_node(ssp, flags);
+	spin_lock_irqsave_ssp_contention(ssp, &flags);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
 		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
 	spin_unlock_irqrestore_rcu_node(ssp, flags);
@@ -779,7 +838,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		}
 
 	/* Top of tree, must ensure the grace period will be started. */
-	spin_lock_irqsave_rcu_node(ssp, flags);
+	spin_lock_irqsave_ssp_contention(ssp, &flags);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed, s)) {
 		/*
 		 * Record need for grace period s.  Pair with load
@@ -1542,7 +1601,7 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
 		}
 		pr_cont(" T(%ld,%ld)\n", s0, s1);
 	}
-	if (convert_to_big == 2)
+	if (SRCU_SIZING_IS_TORTURE())
 		srcu_transition_to_big(ssp);
 }
 EXPORT_SYMBOL_GPL(srcu_torture_stats_print);
-- 
cgit v1.2.3


From 5d90070816534882b9158f14154b7e2cdef1194a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 4 Mar 2022 10:41:44 -0800
Subject: rcu-tasks: Make Tasks RCU account for userspace execution

The main Tasks RCU quiescent state is voluntary context switch.  However,
userspace execution is also a valid quiescent state, and is a valuable one
for userspace applications that spin repeatedly executing light-weight
non-sleeping system calls.  Currently, such an application can delay a
Tasks RCU grace period for many tens of seconds.

This commit therefore enlists the aid of the scheduler-clock interrupt to
provide a Tasks RCU quiescent state when it interrupted a task executing
in userspace.

[ paulmck: Apply feedback from kernel test robot. ]

Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Neil Spring <ntspring@fb.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h | 1 +
 kernel/rcu/tree.c        | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index e7c39c200e2b..1a32036c918c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -196,6 +196,7 @@ void synchronize_rcu_tasks_rude(void);
 void exit_tasks_rcu_start(void);
 void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+#define rcu_tasks_classic_qs(t, preempt) do { } while (0)
 #define rcu_tasks_qs(t, preempt) do { } while (0)
 #define rcu_note_voluntary_context_switch(t) do { } while (0)
 #define call_rcu_tasks call_rcu
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a4b8189455d5..8dbfb63f0391 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2624,6 +2624,8 @@ void rcu_sched_clock_irq(int user)
 	rcu_flavor_sched_clock_irq(user);
 	if (rcu_pending(user))
 		invoke_rcu_core();
+	if (user)
+		rcu_tasks_classic_qs(current, false);
 	lockdep_assert_irqs_disabled();
 
 	trace_rcu_utilization(TPS("End scheduler-tick"));
-- 
cgit v1.2.3


From bd6c375b92c3f367e184d164e12952e4b9d9fb4f Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 15 Mar 2022 16:33:38 +0100
Subject: rcutorture: Call preempt_schedule() through static call/key

The rcutorture test suite sometimess triggers a random scheduler
preemption call while simulating a read delay.  Unfortunately, its
direct call to preempt_schedule() bypasses the static call/key filter
used by CONFIG_PREEMPT_DYNAMIC.  This breaks the no-preempt assumption
when the dynamic preemption mode is "none".

For example, rcu_blocking_is_gp() is fooled and abbreviates grace periods
when the CPU runs in no-preempt UP mode.

Fix this by making torture_preempt_schedule() call __preempt_schedule(),
which uses the static call/key.

Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/torture.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/torture.h b/include/linux/torture.h
index 63fa4196e51c..7038104463e4 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -118,7 +118,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp);
 	_torture_stop_kthread("Stopping " #n " task", &(tp))
 
 #ifdef CONFIG_PREEMPTION
-#define torture_preempt_schedule() preempt_schedule()
+#define torture_preempt_schedule() __preempt_schedule()
 #else
 #define torture_preempt_schedule()	do { } while (0)
 #endif
-- 
cgit v1.2.3


From a28c1ab312712c26a8d004af1f68628d625dafac Mon Sep 17 00:00:00 2001
From: Sergey Shtylyov <s.shtylyov@omp.ru>
Date: Sat, 9 Apr 2022 22:13:56 +0300
Subject: ata: libata-core: fix parameter type in ata_xfer_mode2shift()

The data transfer mode that corresponds to the 'xfer_mode' parameter for
ata_xfer_mode2shift() is a 8-bit *unsigned* value.  Using *unsigned long*
to declare the parameter leads to a problematic implicit *int* to *unsigned
long* cast and was most probably a result of a copy/paste mistake -- use
the 'u8' type instead, as in ata_xfer_mode2mask()...

Found by Linux Verification Center (linuxtesting.org) with the SVACE static
analysis tool.

Signed-off-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
 drivers/ata/libata-core.c | 2 +-
 include/linux/libata.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 23d1dc5faf73..eb8ff7b22616 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -898,7 +898,7 @@ EXPORT_SYMBOL_GPL(ata_xfer_mode2mask);
  *	RETURNS:
  *	Matching xfer_shift, -1 if no match found.
  */
-int ata_xfer_mode2shift(unsigned long xfer_mode)
+int ata_xfer_mode2shift(u8 xfer_mode)
 {
 	const struct ata_xfer_ent *ent;
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 16107122e587..732de9014626 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1110,7 +1110,7 @@ extern void ata_unpack_xfermask(unsigned long xfer_mask,
 			unsigned long *udma_mask);
 extern u8 ata_xfer_mask2mode(unsigned long xfer_mask);
 extern unsigned long ata_xfer_mode2mask(u8 xfer_mode);
-extern int ata_xfer_mode2shift(unsigned long xfer_mode);
+extern int ata_xfer_mode2shift(u8 xfer_mode);
 extern const char *ata_mode_string(unsigned long xfer_mask);
 extern unsigned long ata_id_xfermask(const u16 *id);
 extern int ata_std_qc_defer(struct ata_queued_cmd *qc);
-- 
cgit v1.2.3


From 1a95e04e29a116c3424988c70c441ca8ec2779ff Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 12 Apr 2022 11:24:00 +0100
Subject: net: phylink: remove phylink_helper_basex_speed()

As there are now no users of phylink_helper_basex_speed(), we can
remove this obsolete functionality.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 28 ----------------------------
 include/linux/phylink.h   |  6 ------
 2 files changed, 34 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 06943889d747..33c285252584 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -2778,34 +2778,6 @@ static const struct sfp_upstream_ops sfp_phylink_ops = {
 
 /* Helpers for MAC drivers */
 
-/**
- * phylink_helper_basex_speed() - 1000BaseX/2500BaseX helper
- * @state: a pointer to a &struct phylink_link_state
- *
- * Inspect the interface mode, advertising mask or forced speed and
- * decide whether to run at 2.5Gbit or 1Gbit appropriately, switching
- * the interface mode to suit.  @state->interface is appropriately
- * updated, and the advertising mask has the "other" baseX_Full flag
- * cleared.
- */
-void phylink_helper_basex_speed(struct phylink_link_state *state)
-{
-	if (phy_interface_mode_is_8023z(state->interface)) {
-		bool want_2500 = state->an_enabled ?
-			phylink_test(state->advertising, 2500baseX_Full) :
-			state->speed == SPEED_2500;
-
-		if (want_2500) {
-			phylink_clear(state->advertising, 1000baseX_Full);
-			state->interface = PHY_INTERFACE_MODE_2500BASEX;
-		} else {
-			phylink_clear(state->advertising, 2500baseX_Full);
-			state->interface = PHY_INTERFACE_MODE_1000BASEX;
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(phylink_helper_basex_speed);
-
 static void phylink_decode_c37_word(struct phylink_link_state *state,
 				    uint16_t config_reg, int speed)
 {
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 223781622b33..6d06896fc20d 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -160,11 +160,6 @@ struct phylink_mac_ops {
  * clearing unsupported speeds and duplex settings. The port modes
  * should not be cleared; phylink_set_port_modes() will help with this.
  *
- * If the @state->interface mode is %PHY_INTERFACE_MODE_1000BASEX
- * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode
- * based on @state->advertising and/or @state->speed and update
- * @state->interface accordingly. See phylink_helper_basex_speed().
- *
  * When @config->supported_interfaces has been set, phylink will iterate
  * over the supported interfaces to determine the full capability of the
  * MAC. The validation function must not print errors if @state->interface
@@ -579,7 +574,6 @@ int phylink_speed_up(struct phylink *pl);
 #define phylink_test(bm, mode)	__phylink_do_bit(test_bit, bm, mode)
 
 void phylink_set_port_modes(unsigned long *bits);
-void phylink_helper_basex_speed(struct phylink_link_state *state);
 
 void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state,
 				      u16 bmsr, u16 lpa);
-- 
cgit v1.2.3


From 1306d5362a591493a2d07f685ed2cc480dcda320 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Wed, 13 Apr 2022 13:51:56 +0300
Subject: net: add ndo_fdb_del_bulk

Add a new netdev op called ndo_fdb_del_bulk, it will be later used for
driver-specific bulk delete implementation dispatched from rtnetlink. The
first user will be the bridge, we need it to signal to rtnetlink from
the driver that we support bulk delete operation (NLM_F_BULK).

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 28ea4f8269d4..a602f29365b0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1260,6 +1260,10 @@ struct netdev_net_notifier {
  *		      struct net_device *dev,
  *		      const unsigned char *addr, u16 vid)
  *	Deletes the FDB entry from dev coresponding to addr.
+ * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[],
+ *			   struct net_device *dev,
+ *			   u16 vid,
+ *			   struct netlink_ext_ack *extack);
  * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
  *		       struct net_device *dev, struct net_device *filter_dev,
  *		       int *idx)
@@ -1510,6 +1514,11 @@ struct net_device_ops {
 					       struct net_device *dev,
 					       const unsigned char *addr,
 					       u16 vid);
+	int			(*ndo_fdb_del_bulk)(struct ndmsg *ndm,
+						    struct nlattr *tb[],
+						    struct net_device *dev,
+						    u16 vid,
+						    struct netlink_ext_ack *extack);
 	int			(*ndo_fdb_dump)(struct sk_buff *skb,
 						struct netlink_callback *cb,
 						struct net_device *dev,
-- 
cgit v1.2.3


From d6d3146ce532268ad0ffd8d92d2b7492898decf1 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Wed, 13 Apr 2022 16:15:52 +0800
Subject: skb: add some helpers for skb drop reasons

In order to simply the definition and assignment for
'enum skb_drop_reason', introduce some helpers.

SKB_DR() is used to define a variable of type 'enum skb_drop_reason'
with the 'SKB_DROP_REASON_NOT_SPECIFIED' initial value.

SKB_DR_SET() is used to set the value of the variable. Seems it is
a little useless? But it makes the code shorter.

SKB_DR_OR() is used to set the value of the variable if it is not set
yet, which means its value is SKB_DROP_REASON_NOT_SPECIFIED.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9b81ba497665..0cbd6ada957c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -450,6 +450,18 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_MAX,
 };
 
+#define SKB_DR_INIT(name, reason)				\
+	enum skb_drop_reason name = SKB_DROP_REASON_##reason
+#define SKB_DR(name)						\
+	SKB_DR_INIT(name, NOT_SPECIFIED)
+#define SKB_DR_SET(name, reason)				\
+	(name = SKB_DROP_REASON_##reason)
+#define SKB_DR_OR(name, reason)					\
+	do {							\
+		if (name == SKB_DROP_REASON_NOT_SPECIFIED)	\
+			SKB_DR_SET(name, reason);		\
+	} while (0)
+
 /* To allow 64K frame to be packed as single skb without frag_list we
  * require 64K/PAGE_SIZE pages plus 1 additional page to allow for
  * buffers which do not start on a page boundary.
-- 
cgit v1.2.3


From c4eb664191b4a5ff6856478f903924176697719e Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Wed, 13 Apr 2022 16:15:53 +0800
Subject: net: ipv4: add skb drop reasons to ip_error()

Eventually, I find out the handler function for inputting route lookup
fail: ip_error().

The drop reasons we used in ip_error() are almost corresponding to
IPSTATS_MIB_*, and following new reasons are introduced:

SKB_DROP_REASON_IP_INADDRERRORS
SKB_DROP_REASON_IP_INNOROUTES

Isn't the name SKB_DROP_REASON_IP_HOSTUNREACH and
SKB_DROP_REASON_IP_NETUNREACH more accurate? To make them corresponding
to IPSTATS_MIB_*, we keep their name still.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 6 ++++++
 include/trace/events/skb.h | 2 ++
 net/ipv4/route.c           | 6 +++++-
 3 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0cbd6ada957c..886e83ac4b70 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -447,6 +447,12 @@ enum skb_drop_reason {
 					 * 2211, such as a broadcasts
 					 * ICMP_TIMESTAMP
 					 */
+	SKB_DROP_REASON_IP_INADDRERRORS,	/* host unreachable, corresponding
+						 * to IPSTATS_MIB_INADDRERRORS
+						 */
+	SKB_DROP_REASON_IP_INNOROUTES,	/* network unreachable, corresponding
+					 * to IPSTATS_MIB_INADDRERRORS
+					 */
 	SKB_DROP_REASON_MAX,
 };
 
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 42647114fffe..0acac7e5a019 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -63,6 +63,8 @@
 	EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER)		\
 	EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM)		\
 	EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO)	\
+	EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS)	\
+	EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES)	\
 	EMe(SKB_DROP_REASON_MAX, MAX)
 
 #undef EM
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 80f96170876c..e839d424b861 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -945,6 +945,7 @@ static int ip_error(struct sk_buff *skb)
 	struct inet_peer *peer;
 	unsigned long now;
 	struct net *net;
+	SKB_DR(reason);
 	bool send;
 	int code;
 
@@ -964,10 +965,12 @@ static int ip_error(struct sk_buff *skb)
 	if (!IN_DEV_FORWARD(in_dev)) {
 		switch (rt->dst.error) {
 		case EHOSTUNREACH:
+			SKB_DR_SET(reason, IP_INADDRERRORS);
 			__IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS);
 			break;
 
 		case ENETUNREACH:
+			SKB_DR_SET(reason, IP_INNOROUTES);
 			__IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES);
 			break;
 		}
@@ -983,6 +986,7 @@ static int ip_error(struct sk_buff *skb)
 		break;
 	case ENETUNREACH:
 		code = ICMP_NET_UNREACH;
+		SKB_DR_SET(reason, IP_INNOROUTES);
 		__IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES);
 		break;
 	case EACCES:
@@ -1009,7 +1013,7 @@ static int ip_error(struct sk_buff *skb)
 	if (send)
 		icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
 
-out:	kfree_skb(skb);
+out:	kfree_skb_reason(skb, reason);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 2edc1a383fda8d2f580216292dfd9daeae691e47 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Wed, 13 Apr 2022 16:15:55 +0800
Subject: net: ip: add skb drop reasons to ip forwarding

Replace kfree_skb() which is used in ip6_forward() and ip_forward()
with kfree_skb_reason().

The new drop reason 'SKB_DROP_REASON_PKT_TOO_BIG' is introduced for
the case that the length of the packet exceeds MTU and can't
fragment.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     |  3 +++
 include/trace/events/skb.h |  1 +
 net/ipv4/ip_forward.c      | 13 ++++++++++---
 net/ipv6/ip6_output.c      |  9 ++++++---
 4 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 886e83ac4b70..0ef11df1bc67 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -453,6 +453,9 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_IP_INNOROUTES,	/* network unreachable, corresponding
 					 * to IPSTATS_MIB_INADDRERRORS
 					 */
+	SKB_DROP_REASON_PKT_TOO_BIG,	/* packet size is too big (maybe exceed
+					 * the MTU)
+					 */
 	SKB_DROP_REASON_MAX,
 };
 
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 0acac7e5a019..2da72a9a5764 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -65,6 +65,7 @@
 	EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO)	\
 	EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS)	\
 	EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES)	\
+	EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG)		\
 	EMe(SKB_DROP_REASON_MAX, MAX)
 
 #undef EM
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 92ba3350274b..e3aa436a1bdf 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -90,6 +90,7 @@ int ip_forward(struct sk_buff *skb)
 	struct rtable *rt;	/* Route we use */
 	struct ip_options *opt	= &(IPCB(skb)->opt);
 	struct net *net;
+	SKB_DR(reason);
 
 	/* that should never happen */
 	if (skb->pkt_type != PACKET_HOST)
@@ -101,8 +102,10 @@ int ip_forward(struct sk_buff *skb)
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
-	if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
+	if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
+		SKB_DR_SET(reason, XFRM_POLICY);
 		goto drop;
+	}
 
 	if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
 		return NET_RX_SUCCESS;
@@ -118,8 +121,10 @@ int ip_forward(struct sk_buff *skb)
 	if (ip_hdr(skb)->ttl <= 1)
 		goto too_many_hops;
 
-	if (!xfrm4_route_forward(skb))
+	if (!xfrm4_route_forward(skb)) {
+		SKB_DR_SET(reason, XFRM_POLICY);
 		goto drop;
+	}
 
 	rt = skb_rtable(skb);
 
@@ -132,6 +137,7 @@ int ip_forward(struct sk_buff *skb)
 		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			  htonl(mtu));
+		SKB_DR_SET(reason, PKT_TOO_BIG);
 		goto drop;
 	}
 
@@ -169,7 +175,8 @@ too_many_hops:
 	/* Tell the sender its packet died... */
 	__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
 	icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
+	SKB_DR_SET(reason, IP_INHDR);
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return NET_RX_DROP;
 }
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e23f058166af..3e729cee6486 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -469,6 +469,7 @@ int ip6_forward(struct sk_buff *skb)
 	struct inet6_skb_parm *opt = IP6CB(skb);
 	struct net *net = dev_net(dst->dev);
 	struct inet6_dev *idev;
+	SKB_DR(reason);
 	u32 mtu;
 
 	idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
@@ -518,7 +519,7 @@ int ip6_forward(struct sk_buff *skb)
 		icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR);
 		return -ETIMEDOUT;
 	}
 
@@ -537,6 +538,7 @@ int ip6_forward(struct sk_buff *skb)
 
 	if (!xfrm6_route_forward(skb)) {
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+		SKB_DR_SET(reason, XFRM_POLICY);
 		goto drop;
 	}
 	dst = skb_dst(skb);
@@ -596,7 +598,7 @@ int ip6_forward(struct sk_buff *skb)
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS);
 		__IP6_INC_STATS(net, ip6_dst_idev(dst),
 				IPSTATS_MIB_FRAGFAILS);
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
 		return -EMSGSIZE;
 	}
 
@@ -618,8 +620,9 @@ int ip6_forward(struct sk_buff *skb)
 
 error:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
+	SKB_DR_SET(reason, IP_INADDRERRORS);
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return -EINVAL;
 }
 
-- 
cgit v1.2.3


From 1ad6d548e2a452f21bcee4606ee4ec7afcde5f37 Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Wed, 13 Apr 2022 16:15:56 +0800
Subject: net: icmp: introduce function icmpv6_param_prob_reason()

In order to add the skb drop reasons support to icmpv6_param_prob(),
introduce the function icmpv6_param_prob_reason() and make
icmpv6_param_prob() an inline call to it. This new function will be
used in the following patches.

Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/icmpv6.h | 11 +++++++++--
 net/ipv6/icmp.c        |  7 ++++---
 2 files changed, 13 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index 9055cb380ee2..db0f4fcfdaf4 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -79,8 +79,9 @@ extern int				icmpv6_init(void);
 extern int				icmpv6_err_convert(u8 type, u8 code,
 							   int *err);
 extern void				icmpv6_cleanup(void);
-extern void				icmpv6_param_prob(struct sk_buff *skb,
-							  u8 code, int pos);
+extern void				icmpv6_param_prob_reason(struct sk_buff *skb,
+								 u8 code, int pos,
+								 enum skb_drop_reason reason);
 
 struct flowi6;
 struct in6_addr;
@@ -91,6 +92,12 @@ extern void				icmpv6_flow_init(struct sock *sk,
 							 const struct in6_addr *daddr,
 							 int oif);
 
+static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
+{
+	icmpv6_param_prob_reason(skb, code, pos,
+				 SKB_DROP_REASON_NOT_SPECIFIED);
+}
+
 static inline bool icmpv6_is_err(int type)
 {
 	switch (type) {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 01c8003c9fc9..61770220774e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -629,12 +629,13 @@ out_bh_enable:
 }
 EXPORT_SYMBOL(icmp6_send);
 
-/* Slightly more convenient version of icmp6_send.
+/* Slightly more convenient version of icmp6_send with drop reasons.
  */
-void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
+void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos,
+			      enum skb_drop_reason reason)
 {
 	icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb));
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 }
 
 /* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
-- 
cgit v1.2.3


From bdc21a4d286c6917fe966fd765de99411095b1b4 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Mon, 21 Mar 2022 09:57:22 +0000
Subject: PM: EM: Add .get_cost() callback

The Energy Model (EM) supports devices which report abstract power scale,
not only real Watts. The primary goal for EM is to enable the Energy Aware
Scheduler (EAS) for a given platform. Some of the platforms might not be
able to deliver proper power values. The only information that they might
have is the relative efficiency between CPU types.

Thus, it makes sense to remove some restrictions in the EM framework and
introduce a mechanism which would support those platforms. What is crucial
for EAS to operate is the 'cost' field in the EM. The 'cost' is calculated
internally in EM framework based on knowledge from 'power' values.
The 'cost' values must be strictly increasing. The existing API with its
'power' value size restrictions cannot guarantee that the 'cost' will meet
this requirement.

Since the platform is missing this detailed information, but has only
efficiency details, introduce a new custom callback in the EM framework.
The new callback would allow to provide the 'cost' values which reflect
efficiency of the CPUs. This would allow to provide EAS information which
has different relation than what would be forced by the EM internal
formulas calculating 'cost' values. Thanks to this new callback it is
possible to create a system view for EAS which has no overlapping
performance states across many Performance Domains.

Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/energy_model.h | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 9f3c400bc52d..0a3a5663177b 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -114,9 +114,30 @@ struct em_data_callback {
 	 */
 	int (*active_power)(unsigned long *power, unsigned long *freq,
 			    struct device *dev);
+
+	/**
+	 * get_cost() - Provide the cost at the given performance state of
+	 *		a device
+	 * @dev		: Device for which we do this operation (can be a CPU)
+	 * @freq	: Frequency at the performance state in kHz
+	 * @cost	: The cost value for the performance state
+	 *		(modified)
+	 *
+	 * In case of CPUs, the cost is the one of a single CPU in the domain.
+	 * It is expected to fit in the [0, EM_MAX_POWER] range due to internal
+	 * usage in EAS calculation.
+	 *
+	 * Return 0 on success, or appropriate error value in case of failure.
+	 */
+	int (*get_cost)(struct device *dev, unsigned long freq,
+			unsigned long *cost);
 };
-#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb }
 #define EM_SET_ACTIVE_POWER_CB(em_cb, cb) ((em_cb).active_power = cb)
+#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb)	\
+	{ .active_power = _active_power_cb,		\
+	  .get_cost = _cost_cb }
+#define EM_DATA_CB(_active_power_cb)			\
+		EM_ADV_DATA_CB(_active_power_cb, NULL)
 
 struct em_perf_domain *em_cpu_get(int cpu);
 struct em_perf_domain *em_pd_get(struct device *dev);
@@ -264,6 +285,7 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd)
 
 #else
 struct em_data_callback {};
+#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) { }
 #define EM_DATA_CB(_active_power_cb) { }
 #define EM_SET_ACTIVE_POWER_CB(em_cb, cb) do { } while (0)
 
-- 
cgit v1.2.3


From fc3a9a9858478ab5f8441765a3f9552a0ceba10c Mon Sep 17 00:00:00 2001
From: Pierre Gondois <Pierre.Gondois@arm.com>
Date: Mon, 21 Mar 2022 09:57:23 +0000
Subject: PM: EM: Add artificial EM flag

The Energy Model (EM) can be used on platforms which are missing real
power information. Those platforms would implement .get_cost() which
populates needed values for the Energy Aware Scheduler (EAS). The EAS
doesn't use 'power' fields from EM, but other frameworks might use them.
Thus, to avoid miss-usage of this specific type of EM, introduce a new
flags which can be checked by other frameworks.

Signed-off-by: Pierre Gondois <Pierre.Gondois@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/energy_model.h | 5 +++++
 kernel/power/energy_model.c  | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 0a3a5663177b..92e82a322859 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -67,11 +67,16 @@ struct em_perf_domain {
  *
  *  EM_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip inefficient states when estimating
  *  energy consumption.
+ *
+ *  EM_PERF_DOMAIN_ARTIFICIAL: The power values are artificial and might be
+ *  created by platform missing real power information
  */
 #define EM_PERF_DOMAIN_MILLIWATTS BIT(0)
 #define EM_PERF_DOMAIN_SKIP_INEFFICIENCIES BIT(1)
+#define EM_PERF_DOMAIN_ARTIFICIAL BIT(2)
 
 #define em_span_cpus(em) (to_cpumask((em)->cpus))
+#define em_is_artificial(em) ((em)->flags & EM_PERF_DOMAIN_ARTIFICIAL)
 
 #ifdef CONFIG_ENERGY_MODEL
 #define EM_MAX_POWER 0xFFFF
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 0153b0ca7b23..6ecee99af842 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -384,6 +384,8 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 
 	if (milliwatts)
 		dev->em_pd->flags |= EM_PERF_DOMAIN_MILLIWATTS;
+	else if (cb->get_cost)
+		dev->em_pd->flags |= EM_PERF_DOMAIN_ARTIFICIAL;
 
 	em_cpufreq_update_efficiencies(dev);
 
-- 
cgit v1.2.3


From 75a3a99a5a9886af13be44e640cb415ebda80db2 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Mon, 21 Mar 2022 09:57:25 +0000
Subject: PM: EM: Change the order of arguments in the .active_power() callback

The .active_power() callback passes the device pointer when it's called.
Aligned with a convetion present in other subsystems and pass the 'dev'
as a first argument. It looks more cleaner.

Adjust all affected drivers which implement that API callback.

Suggested-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/energy-model.rst  | 4 ++--
 drivers/cpufreq/mediatek-cpufreq-hw.c | 4 ++--
 drivers/cpufreq/scmi-cpufreq.c        | 4 ++--
 drivers/opp/of.c                      | 6 +++---
 include/linux/energy_model.h          | 6 +++---
 kernel/power/energy_model.c           | 2 +-
 6 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/energy-model.rst b/Documentation/power/energy-model.rst
index 49549aab41b4..fd29ed2506c0 100644
--- a/Documentation/power/energy-model.rst
+++ b/Documentation/power/energy-model.rst
@@ -181,8 +181,8 @@ EM framework::
 
   -> drivers/cpufreq/foo_cpufreq.c
 
-  01	static int est_power(unsigned long *mW, unsigned long *KHz,
-  02			struct device *dev)
+  01	static int est_power(struct device *dev, unsigned long *mW,
+  02			unsigned long *KHz)
   03	{
   04		long freq, power;
   05
diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c
index 0a94c56ddad2..813cccbfe934 100644
--- a/drivers/cpufreq/mediatek-cpufreq-hw.c
+++ b/drivers/cpufreq/mediatek-cpufreq-hw.c
@@ -51,8 +51,8 @@ static const u16 cpufreq_mtk_offsets[REG_ARRAY_SIZE] = {
 };
 
 static int __maybe_unused
-mtk_cpufreq_get_cpu_power(unsigned long *mW,
-			  unsigned long *KHz, struct device *cpu_dev)
+mtk_cpufreq_get_cpu_power(struct device *cpu_dev, unsigned long *mW,
+			  unsigned long *KHz)
 {
 	struct mtk_cpufreq_data *data;
 	struct cpufreq_policy *policy;
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 919fa6e3f462..6d2a4cf46db7 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -96,8 +96,8 @@ scmi_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 }
 
 static int __maybe_unused
-scmi_get_cpu_power(unsigned long *power, unsigned long *KHz,
-		   struct device *cpu_dev)
+scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power,
+		   unsigned long *KHz)
 {
 	unsigned long Hz;
 	int ret, domain;
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 440ab5a03df9..485ea980bde7 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -1448,7 +1448,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
  * Returns 0 on success or a proper -EINVAL value in case of error.
  */
 static int __maybe_unused
-_get_dt_power(unsigned long *mW, unsigned long *kHz, struct device *dev)
+_get_dt_power(struct device *dev, unsigned long *mW, unsigned long *kHz)
 {
 	struct dev_pm_opp *opp;
 	unsigned long opp_freq, opp_power;
@@ -1482,8 +1482,8 @@ _get_dt_power(unsigned long *mW, unsigned long *kHz, struct device *dev)
  * Returns -EINVAL if the power calculation failed because of missing
  * parameters, 0 otherwise.
  */
-static int __maybe_unused _get_power(unsigned long *mW, unsigned long *kHz,
-				     struct device *dev)
+static int __maybe_unused _get_power(struct device *dev, unsigned long *mW,
+				     unsigned long *kHz)
 {
 	struct dev_pm_opp *opp;
 	struct device_node *np;
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 92e82a322859..8419bffb4398 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -101,11 +101,11 @@ struct em_data_callback {
 	/**
 	 * active_power() - Provide power at the next performance state of
 	 *		a device
+	 * @dev		: Device for which we do this operation (can be a CPU)
 	 * @power	: Active power at the performance state
 	 *		(modified)
 	 * @freq	: Frequency at the performance state in kHz
 	 *		(modified)
-	 * @dev		: Device for which we do this operation (can be a CPU)
 	 *
 	 * active_power() must find the lowest performance state of 'dev' above
 	 * 'freq' and update 'power' and 'freq' to the matching active power
@@ -117,8 +117,8 @@ struct em_data_callback {
 	 *
 	 * Return 0 on success.
 	 */
-	int (*active_power)(unsigned long *power, unsigned long *freq,
-			    struct device *dev);
+	int (*active_power)(struct device *dev, unsigned long *power,
+			    unsigned long *freq);
 
 	/**
 	 * get_cost() - Provide the cost at the given performance state of
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 95a3b33001f6..babefc72085d 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -140,7 +140,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 		 * lowest performance state of 'dev' above 'freq' and updates
 		 * 'power' and 'freq' accordingly.
 		 */
-		ret = cb->active_power(&power, &freq, dev);
+		ret = cb->active_power(dev, &power, &freq);
 		if (ret) {
 			dev_err(dev, "EM: invalid perf. state: %d\n",
 				ret);
-- 
cgit v1.2.3


From ce1cb680ff1c5b88505f878137796b1723e00193 Mon Sep 17 00:00:00 2001
From: David Cohen <dacohen@pm.me>
Date: Thu, 24 Mar 2022 08:07:30 +0000
Subject: PM: sleep: enable dynamic debug support within pm_pr_dbg()

Currently pm_pr_dbg() is used to filter kernel pm debug messages based
on pm_debug_messages_on flag. The problem is if we enable/disable this
flag it will affect all pm_pr_dbg() calls at once, so we can't
individually control them.

This patch changes pm_pr_dbg() implementation as such:

 - If pm_debug_messages_on is enabled, print the message.
 - If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is
   enabled, only print the messages explicitly enabled on
   /sys/kernel/debug/dynamic_debug/control.
 - If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is
   disabled, don't print the message.

Signed-off-by: David Cohen <dacohen@pm.me>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/suspend.h | 44 +++++++++++++++++++++++++++++++++++++++-----
 kernel/power/main.c     | 29 -----------------------------
 2 files changed, 39 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 300273ff40cc..70f2921e2e70 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -542,22 +542,56 @@ static inline void unlock_system_sleep(void) {}
 #ifdef CONFIG_PM_SLEEP_DEBUG
 extern bool pm_print_times_enabled;
 extern bool pm_debug_messages_on;
-extern __printf(2, 3) void __pm_pr_dbg(bool defer, const char *fmt, ...);
+static inline int pm_dyn_debug_messages_on(void)
+{
+#ifdef CONFIG_DYNAMIC_DEBUG
+	return 1;
+#else
+	return 0;
+#endif
+}
+#ifndef pr_fmt
+#define pr_fmt(fmt) "PM: " fmt
+#endif
+#define __pm_pr_dbg(fmt, ...)					\
+	do {							\
+		if (pm_debug_messages_on)			\
+			printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__);	\
+		else if (pm_dyn_debug_messages_on())		\
+			pr_debug(fmt, ##__VA_ARGS__);	\
+	} while (0)
+#define __pm_deferred_pr_dbg(fmt, ...)				\
+	do {							\
+		if (pm_debug_messages_on)			\
+			printk_deferred(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__);	\
+	} while (0)
 #else
 #define pm_print_times_enabled	(false)
 #define pm_debug_messages_on	(false)
 
 #include <linux/printk.h>
 
-#define __pm_pr_dbg(defer, fmt, ...) \
-	no_printk(KERN_DEBUG fmt, ##__VA_ARGS__)
+#define __pm_pr_dbg(fmt, ...) \
+	no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
+#define __pm_deferred_pr_dbg(fmt, ...) \
+	no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #endif
 
+/**
+ * pm_pr_dbg - print pm sleep debug messages
+ *
+ * If pm_debug_messages_on is enabled, print message.
+ * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled,
+ *	print message only from instances explicitly enabled on dynamic debug's
+ *	control.
+ * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is disabled,
+ *	don't print message.
+ */
 #define pm_pr_dbg(fmt, ...) \
-	__pm_pr_dbg(false, fmt, ##__VA_ARGS__)
+	__pm_pr_dbg(fmt, ##__VA_ARGS__)
 
 #define pm_deferred_pr_dbg(fmt, ...) \
-	__pm_pr_dbg(true, fmt, ##__VA_ARGS__)
+	__pm_deferred_pr_dbg(fmt, ##__VA_ARGS__)
 
 #ifdef CONFIG_PM_AUTOSLEEP
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7e646079fbeb..5242bf2ee469 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -545,35 +545,6 @@ static int __init pm_debug_messages_setup(char *str)
 }
 __setup("pm_debug_messages", pm_debug_messages_setup);
 
-/**
- * __pm_pr_dbg - Print a suspend debug message to the kernel log.
- * @defer: Whether or not to use printk_deferred() to print the message.
- * @fmt: Message format.
- *
- * The message will be emitted if enabled through the pm_debug_messages
- * sysfs attribute.
- */
-void __pm_pr_dbg(bool defer, const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	if (!pm_debug_messages_on)
-		return;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	if (defer)
-		printk_deferred(KERN_DEBUG "PM: %pV", &vaf);
-	else
-		printk(KERN_DEBUG "PM: %pV", &vaf);
-
-	va_end(args);
-}
-
 #else /* !CONFIG_PM_SLEEP_DEBUG */
 static inline void pm_print_times_init(void) {}
 #endif /* CONFIG_PM_SLEEP_DEBUG */
-- 
cgit v1.2.3


From 1227418989346af3af179742cf42ce842e0ad484 Mon Sep 17 00:00:00 2001
From: Dov Murik <dovmurik@linux.ibm.com>
Date: Tue, 12 Apr 2022 21:21:24 +0000
Subject: efi: Save location of EFI confidential computing area

Confidential computing (coco) hardware such as AMD SEV (Secure Encrypted
Virtualization) allows a guest owner to inject secrets into the VMs
memory without the host/hypervisor being able to read them.

Firmware support for secret injection is available in OVMF, which
reserves a memory area for secret injection and includes a pointer to it
the in EFI config table entry LINUX_EFI_COCO_SECRET_TABLE_GUID.

If EFI exposes such a table entry, uefi_init() will keep a pointer to
the EFI config table entry in efi.coco_secret, so it can be used later
by the kernel (specifically drivers/virt/coco/efi_secret).  It will also
appear in the kernel log as "CocoSecret=ADDRESS"; for example:

    [    0.000000] efi: EFI v2.70 by EDK II
    [    0.000000] efi: CocoSecret=0x7f22e680 SMBIOS=0x7f541000 ACPI=0x7f77e000 ACPI 2.0=0x7f77e014 MEMATTR=0x7ea0c018

The new functionality can be enabled with CONFIG_EFI_COCO_SECRET=y.

Signed-off-by: Dov Murik <dovmurik@linux.ibm.com>
Reviewed-by: Gerd Hoffmann <kraxel@redhat.com>
Link: https://lore.kernel.org/r/20220412212127.154182-2-dovmurik@linux.ibm.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/platform/efi/efi.c  |  3 +++
 drivers/firmware/efi/Kconfig | 16 ++++++++++++++++
 drivers/firmware/efi/efi.c   |  6 ++++++
 include/linux/efi.h          | 10 ++++++++++
 4 files changed, 35 insertions(+)

(limited to 'include/linux')

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 147c30a81f15..1591d67e0bcd 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -93,6 +93,9 @@ static const unsigned long * const efi_tables[] = {
 #ifdef CONFIG_LOAD_UEFI_KEYS
 	&efi.mokvar_table,
 #endif
+#ifdef CONFIG_EFI_COCO_SECRET
+	&efi.coco_secret,
+#endif
 };
 
 u64 efi_setup;		/* efi setup_data physical address */
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 243882f5e5f9..f8ddd2259ba0 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -299,3 +299,19 @@ config EFI_DISABLE_RUNTIME
 	  an issue for Real-Time kernels.
 
 	  This default can be overridden by using the efi=runtime option.
+
+config EFI_COCO_SECRET
+	bool "EFI Confidential Computing Secret Area Support"
+	depends on EFI
+	help
+	  Confidential Computing platforms (such as AMD SEV) allow the
+	  Guest Owner to securely inject secrets during guest VM launch.
+	  The secrets are placed in a designated EFI reserved memory area.
+
+	  In order to use the secrets in the kernel, the location of the secret
+	  area (as published in the EFI config table) must be kept.
+
+	  If you say Y here, the address of the EFI secret area will be kept
+	  for usage inside the kernel.  This will allow the
+	  virt/coco/efi_secret module to access the secrets, which in turn
+	  allows userspace programs to access the injected secrets.
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index ff57db8f8d05..e0f43262d451 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -46,6 +46,9 @@ struct efi __read_mostly efi = {
 #ifdef CONFIG_LOAD_UEFI_KEYS
 	.mokvar_table		= EFI_INVALID_TABLE_ADDR,
 #endif
+#ifdef CONFIG_EFI_COCO_SECRET
+	.coco_secret		= EFI_INVALID_TABLE_ADDR,
+#endif
 };
 EXPORT_SYMBOL(efi);
 
@@ -528,6 +531,9 @@ static const efi_config_table_type_t common_tables[] __initconst = {
 #endif
 #ifdef CONFIG_LOAD_UEFI_KEYS
 	{LINUX_EFI_MOK_VARIABLE_TABLE_GUID,	&efi.mokvar_table,	"MOKvar"	},
+#endif
+#ifdef CONFIG_EFI_COCO_SECRET
+	{LINUX_EFI_COCO_SECRET_AREA_GUID,	&efi.coco_secret,	"CocoSecret"	},
 #endif
 	{},
 };
diff --git a/include/linux/efi.h b/include/linux/efi.h
index ccd4d3f91c98..771d4cd06b56 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -405,6 +405,7 @@ void efi_native_runtime_setup(void);
 #define LINUX_EFI_MEMRESERVE_TABLE_GUID		EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5,  0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2)
 #define LINUX_EFI_INITRD_MEDIA_GUID		EFI_GUID(0x5568e427, 0x68fc, 0x4f3d,  0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68)
 #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID	EFI_GUID(0xc451ed2b, 0x9694, 0x45d3,  0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89)
+#define LINUX_EFI_COCO_SECRET_AREA_GUID		EFI_GUID(0xadf956ad, 0xe98c, 0x484c,  0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47)
 
 /* OEM GUIDs */
 #define DELLEMC_EFI_RCI2_TABLE_GUID		EFI_GUID(0x2d9f28a2, 0xa886, 0x456a,  0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
@@ -596,6 +597,7 @@ extern struct efi {
 	unsigned long			tpm_log;		/* TPM2 Event Log table */
 	unsigned long			tpm_final_log;		/* TPM2 Final Events Log table */
 	unsigned long			mokvar_table;		/* MOK variable config table */
+	unsigned long			coco_secret;		/* Confidential computing secret table */
 
 	efi_get_time_t			*get_time;
 	efi_set_time_t			*set_time;
@@ -1335,4 +1337,12 @@ extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
 static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { }
 #endif
 
+struct linux_efi_coco_secret_area {
+	u64	base_pa;
+	u64	size;
+};
+
+/* Header of a populated EFI secret area */
+#define EFI_SECRET_TABLE_HEADER_GUID	EFI_GUID(0x1e74f542, 0x71dd, 0x4d66,  0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b)
+
 #endif /* _LINUX_EFI_H */
-- 
cgit v1.2.3


From aa480379d8bdb33920d68acfd90f823c8af32578 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Fri, 4 Mar 2022 07:36:37 +0100
Subject: efi: Add missing prototype for efi_capsule_setup_info

Fixes "no previous declaration for 'efi_capsule_setup_info'" warnings
under W=1.

Fixes: 2959c95d510c ("efi/capsule: Add support for Quark security header")
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Link: https://lore.kernel.org/r/c28d3f86-dd72-27d1-e2c2-40971b8da6bd@siemens.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 include/linux/efi.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/efi.h b/include/linux/efi.h
index 771d4cd06b56..fd266198f9d8 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -213,6 +213,8 @@ struct capsule_info {
 	size_t			page_bytes_remain;
 };
 
+int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff,
+                           size_t hdr_bytes);
 int __efi_capsule_setup_info(struct capsule_info *cap_info);
 
 /*
-- 
cgit v1.2.3


From 002752af7b89b74c64fe6bec8c5fde3d3a7810d8 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 8 Apr 2022 21:48:40 +0300
Subject: device property: Allow error pointer to be passed to fwnode APIs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some of the fwnode APIs might return an error pointer instead of NULL
or valid fwnode handle. The result of such API call may be considered
optional and hence the test for it is usually done in a form of

	fwnode = fwnode_find_reference(...);
	if (IS_ERR(fwnode))
		...error handling...

Nevertheless the resulting fwnode may have bumped the reference count
and hence caller of the above API is obliged to call fwnode_handle_put().
Since fwnode may be not valid either as NULL or error pointer the check
has to be performed there. This approach uglifies the code and adds
a point of making a mistake, i.e. forgetting about error point case.

To prevent this, allow an error pointer to be passed to the fwnode APIs.

Fixes: 83b34afb6b79 ("device property: Introduce fwnode_find_reference()")
Reported-by: Nuno Sá <nuno.sa@analog.com>
Tested-by: Nuno Sá <nuno.sa@analog.com>
Acked-by: Nuno Sá <nuno.sa@analog.com>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Michael Walle <michael@walle.cc>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/property.c | 89 ++++++++++++++++++++++++++++---------------------
 include/linux/fwnode.h  | 10 +++---
 2 files changed, 56 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 3560c4419d11..6ecc1398b0ba 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -47,12 +47,14 @@ bool fwnode_property_present(const struct fwnode_handle *fwnode,
 {
 	bool ret;
 
+	if (IS_ERR_OR_NULL(fwnode))
+		return false;
+
 	ret = fwnode_call_bool_op(fwnode, property_present, propname);
-	if (ret == false && !IS_ERR_OR_NULL(fwnode) &&
-	    !IS_ERR_OR_NULL(fwnode->secondary))
-		ret = fwnode_call_bool_op(fwnode->secondary, property_present,
-					 propname);
-	return ret;
+	if (ret)
+		return ret;
+
+	return fwnode_call_bool_op(fwnode->secondary, property_present, propname);
 }
 EXPORT_SYMBOL_GPL(fwnode_property_present);
 
@@ -232,15 +234,16 @@ static int fwnode_property_read_int_array(const struct fwnode_handle *fwnode,
 {
 	int ret;
 
+	if (IS_ERR_OR_NULL(fwnode))
+		return -EINVAL;
+
 	ret = fwnode_call_int_op(fwnode, property_read_int_array, propname,
 				 elem_size, val, nval);
-	if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) &&
-	    !IS_ERR_OR_NULL(fwnode->secondary))
-		ret = fwnode_call_int_op(
-			fwnode->secondary, property_read_int_array, propname,
-			elem_size, val, nval);
+	if (ret != -EINVAL)
+		return ret;
 
-	return ret;
+	return fwnode_call_int_op(fwnode->secondary, property_read_int_array, propname,
+				  elem_size, val, nval);
 }
 
 /**
@@ -371,14 +374,16 @@ int fwnode_property_read_string_array(const struct fwnode_handle *fwnode,
 {
 	int ret;
 
+	if (IS_ERR_OR_NULL(fwnode))
+		return -EINVAL;
+
 	ret = fwnode_call_int_op(fwnode, property_read_string_array, propname,
 				 val, nval);
-	if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) &&
-	    !IS_ERR_OR_NULL(fwnode->secondary))
-		ret = fwnode_call_int_op(fwnode->secondary,
-					 property_read_string_array, propname,
-					 val, nval);
-	return ret;
+	if (ret != -EINVAL)
+		return ret;
+
+	return fwnode_call_int_op(fwnode->secondary, property_read_string_array, propname,
+				  val, nval);
 }
 EXPORT_SYMBOL_GPL(fwnode_property_read_string_array);
 
@@ -480,15 +485,19 @@ int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode,
 {
 	int ret;
 
+	if (IS_ERR_OR_NULL(fwnode))
+		return -ENOENT;
+
 	ret = fwnode_call_int_op(fwnode, get_reference_args, prop, nargs_prop,
 				 nargs, index, args);
+	if (ret == 0)
+		return ret;
 
-	if (ret < 0 && !IS_ERR_OR_NULL(fwnode) &&
-	    !IS_ERR_OR_NULL(fwnode->secondary))
-		ret = fwnode_call_int_op(fwnode->secondary, get_reference_args,
-					 prop, nargs_prop, nargs, index, args);
+	if (IS_ERR_OR_NULL(fwnode->secondary))
+		return ret;
 
-	return ret;
+	return fwnode_call_int_op(fwnode->secondary, get_reference_args, prop, nargs_prop,
+				  nargs, index, args);
 }
 EXPORT_SYMBOL_GPL(fwnode_property_get_reference_args);
 
@@ -635,12 +644,13 @@ EXPORT_SYMBOL_GPL(fwnode_count_parents);
 struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode,
 					    unsigned int depth)
 {
-	unsigned int i;
-
 	fwnode_handle_get(fwnode);
 
-	for (i = 0; i < depth && fwnode; i++)
+	do {
+		if (depth-- == 0)
+			break;
 		fwnode = fwnode_get_next_parent(fwnode);
+	} while (fwnode);
 
 	return fwnode;
 }
@@ -659,17 +669,17 @@ EXPORT_SYMBOL_GPL(fwnode_get_nth_parent);
 bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor,
 				  struct fwnode_handle *test_child)
 {
-	if (!test_ancestor)
+	if (IS_ERR_OR_NULL(test_ancestor))
 		return false;
 
 	fwnode_handle_get(test_child);
-	while (test_child) {
+	do {
 		if (test_child == test_ancestor) {
 			fwnode_handle_put(test_child);
 			return true;
 		}
 		test_child = fwnode_get_next_parent(test_child);
-	}
+	} while (test_child);
 	return false;
 }
 
@@ -698,7 +708,7 @@ fwnode_get_next_available_child_node(const struct fwnode_handle *fwnode,
 {
 	struct fwnode_handle *next_child = child;
 
-	if (!fwnode)
+	if (IS_ERR_OR_NULL(fwnode))
 		return NULL;
 
 	do {
@@ -722,16 +732,16 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev,
 	const struct fwnode_handle *fwnode = dev_fwnode(dev);
 	struct fwnode_handle *next;
 
+	if (IS_ERR_OR_NULL(fwnode))
+		return NULL;
+
 	/* Try to find a child in primary fwnode */
 	next = fwnode_get_next_child_node(fwnode, child);
 	if (next)
 		return next;
 
 	/* When no more children in primary, continue with secondary */
-	if (fwnode && !IS_ERR_OR_NULL(fwnode->secondary))
-		next = fwnode_get_next_child_node(fwnode->secondary, child);
-
-	return next;
+	return fwnode_get_next_child_node(fwnode->secondary, child);
 }
 EXPORT_SYMBOL_GPL(device_get_next_child_node);
 
@@ -798,6 +808,9 @@ EXPORT_SYMBOL_GPL(fwnode_handle_put);
  */
 bool fwnode_device_is_available(const struct fwnode_handle *fwnode)
 {
+	if (IS_ERR_OR_NULL(fwnode))
+		return false;
+
 	if (!fwnode_has_op(fwnode, device_is_available))
 		return true;
 
@@ -958,14 +971,14 @@ fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
 		parent = fwnode_graph_get_port_parent(prev);
 	else
 		parent = fwnode;
+	if (IS_ERR_OR_NULL(parent))
+		return NULL;
 
 	ep = fwnode_call_ptr_op(parent, graph_get_next_endpoint, prev);
+	if (ep)
+		return ep;
 
-	if (IS_ERR_OR_NULL(ep) &&
-	    !IS_ERR_OR_NULL(parent) && !IS_ERR_OR_NULL(parent->secondary))
-		ep = fwnode_graph_get_next_endpoint(parent->secondary, NULL);
-
-	return ep;
+	return fwnode_graph_get_next_endpoint(parent->secondary, NULL);
 }
 EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
 
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 6ab69871b06d..9a81c4410b9f 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -153,12 +153,12 @@ struct fwnode_operations {
 	int (*add_links)(struct fwnode_handle *fwnode);
 };
 
-#define fwnode_has_op(fwnode, op)				\
-	((fwnode) && (fwnode)->ops && (fwnode)->ops->op)
+#define fwnode_has_op(fwnode, op)					\
+	(!IS_ERR_OR_NULL(fwnode) && (fwnode)->ops && (fwnode)->ops->op)
+
 #define fwnode_call_int_op(fwnode, op, ...)				\
-	(fwnode ? (fwnode_has_op(fwnode, op) ?				\
-		   (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \
-	 -EINVAL)
+	(fwnode_has_op(fwnode, op) ?					\
+	 (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : (IS_ERR_OR_NULL(fwnode) ? -EINVAL : -ENXIO))
 
 #define fwnode_call_bool_op(fwnode, op, ...)		\
 	(fwnode_has_op(fwnode, op) ?			\
-- 
cgit v1.2.3


From 87ffea09470d94c93dd6a5a22d4b2216b395d1ea Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 8 Apr 2022 21:48:41 +0300
Subject: device property: Introduce fwnode_for_each_parent_node()

In a few cases the functionality of fwnode_for_each_parent_node()
is already in use. Introduce a common helper macro for it.

It may be used by others as well in the future.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/property.c  | 56 +++++++++++++++++++++++++-----------------------
 include/linux/property.h |  9 ++++++--
 2 files changed, 36 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 6ecc1398b0ba..f0ac31d28798 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -596,17 +596,17 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_parent);
  */
 struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode)
 {
+	struct fwnode_handle *parent;
 	struct device *dev;
 
-	fwnode_handle_get(fwnode);
-	do {
-		fwnode = fwnode_get_next_parent(fwnode);
-		if (!fwnode)
-			return NULL;
+	fwnode_for_each_parent_node(fwnode, parent) {
 		dev = get_dev_from_fwnode(fwnode);
-	} while (!dev);
-	fwnode_handle_put(fwnode);
-	return dev;
+		if (dev) {
+			fwnode_handle_put(parent);
+			return dev;
+		}
+	}
+	return NULL;
 }
 
 /**
@@ -617,13 +617,11 @@ struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode)
  */
 unsigned int fwnode_count_parents(const struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *__fwnode;
-	unsigned int count;
-
-	__fwnode = fwnode_get_parent(fwnode);
+	struct fwnode_handle *parent;
+	unsigned int count = 0;
 
-	for (count = 0; __fwnode; count++)
-		__fwnode = fwnode_get_next_parent(__fwnode);
+	fwnode_for_each_parent_node(fwnode, parent)
+		count++;
 
 	return count;
 }
@@ -644,15 +642,16 @@ EXPORT_SYMBOL_GPL(fwnode_count_parents);
 struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode,
 					    unsigned int depth)
 {
-	fwnode_handle_get(fwnode);
+	struct fwnode_handle *parent;
 
-	do {
-		if (depth-- == 0)
-			break;
-		fwnode = fwnode_get_next_parent(fwnode);
-	} while (fwnode);
+	if (depth == 0)
+		return fwnode_handle_get(fwnode);
 
-	return fwnode;
+	fwnode_for_each_parent_node(fwnode, parent) {
+		if (--depth == 0)
+			return parent;
+	}
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(fwnode_get_nth_parent);
 
@@ -669,17 +668,20 @@ EXPORT_SYMBOL_GPL(fwnode_get_nth_parent);
 bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor,
 				  struct fwnode_handle *test_child)
 {
+	struct fwnode_handle *parent;
+
 	if (IS_ERR_OR_NULL(test_ancestor))
 		return false;
 
-	fwnode_handle_get(test_child);
-	do {
-		if (test_child == test_ancestor) {
-			fwnode_handle_put(test_child);
+	if (test_child == test_ancestor)
+		return true;
+
+	fwnode_for_each_parent_node(test_child, parent) {
+		if (parent == test_ancestor) {
+			fwnode_handle_put(parent);
 			return true;
 		}
-		test_child = fwnode_get_next_parent(test_child);
-	} while (test_child);
+	}
 	return false;
 }
 
diff --git a/include/linux/property.h b/include/linux/property.h
index 4cd4b326941f..15d6863ae962 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -83,9 +83,14 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode,
 
 const char *fwnode_get_name(const struct fwnode_handle *fwnode);
 const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode);
+
 struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode);
-struct fwnode_handle *fwnode_get_next_parent(
-	struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode);
+
+#define fwnode_for_each_parent_node(fwnode, parent)		\
+	for (parent = fwnode_get_parent(fwnode); parent;	\
+	     parent = fwnode_get_next_parent(parent))
+
 struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode);
 unsigned int fwnode_count_parents(const struct fwnode_handle *fwn);
 struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn,
-- 
cgit v1.2.3


From 022fe6bc8f3bd0f2b1f9bc778bacc38020dfd420 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 8 Apr 2022 21:48:42 +0300
Subject: device property: Drop 'test' prefix in parameters of
 fwnode_is_ancestor_of()

The part 'is' in the function name implies the test against something.
Drop unnecessary 'test' prefix in the fwnode_is_ancestor_of() parameters.

No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/property.c  | 20 +++++++++-----------
 include/linux/property.h |  3 +--
 2 files changed, 10 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index f0ac31d28798..36401cfe432c 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -656,28 +656,26 @@ struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode,
 EXPORT_SYMBOL_GPL(fwnode_get_nth_parent);
 
 /**
- * fwnode_is_ancestor_of - Test if @test_ancestor is ancestor of @test_child
- * @test_ancestor: Firmware which is tested for being an ancestor
- * @test_child: Firmware which is tested for being the child
+ * fwnode_is_ancestor_of - Test if @ancestor is ancestor of @child
+ * @ancestor: Firmware which is tested for being an ancestor
+ * @child: Firmware which is tested for being the child
  *
  * A node is considered an ancestor of itself too.
  *
- * Returns true if @test_ancestor is an ancestor of @test_child.
- * Otherwise, returns false.
+ * Returns true if @ancestor is an ancestor of @child. Otherwise, returns false.
  */
-bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor,
-				  struct fwnode_handle *test_child)
+bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child)
 {
 	struct fwnode_handle *parent;
 
-	if (IS_ERR_OR_NULL(test_ancestor))
+	if (IS_ERR_OR_NULL(ancestor))
 		return false;
 
-	if (test_child == test_ancestor)
+	if (child == ancestor)
 		return true;
 
-	fwnode_for_each_parent_node(test_child, parent) {
-		if (parent == test_ancestor) {
+	fwnode_for_each_parent_node(child, parent) {
+		if (parent == ancestor) {
 			fwnode_handle_put(parent);
 			return true;
 		}
diff --git a/include/linux/property.h b/include/linux/property.h
index 15d6863ae962..fc24d45632eb 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -95,8 +95,7 @@ struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode);
 unsigned int fwnode_count_parents(const struct fwnode_handle *fwn);
 struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn,
 					    unsigned int depth);
-bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor,
-				  struct fwnode_handle *test_child);
+bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child);
 struct fwnode_handle *fwnode_get_next_child_node(
 	const struct fwnode_handle *fwnode, struct fwnode_handle *child);
 struct fwnode_handle *fwnode_get_next_available_child_node(
-- 
cgit v1.2.3


From 4e140f59d285c1ca1e5c81b4c13e27366865bd09 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 10 Jan 2022 23:15:27 +0000
Subject: mm/usercopy: Check kmap addresses properly

If you are copying to an address in the kmap region, you may not copy
across a page boundary, no matter what the size of the underlying
allocation.  You can't kmap() a slab page because slab pages always
come from low memory.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220110231530.665970-2-willy@infradead.org
---
 arch/x86/include/asm/highmem.h   |  1 +
 include/linux/highmem-internal.h | 10 ++++++++++
 mm/usercopy.c                    | 16 ++++++++++------
 3 files changed, 21 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 032e020853aa..731ee7cc40a5 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -26,6 +26,7 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/fixmap.h>
+#include <asm/pgtable_areas.h>
 
 /* declarations for highmem.c */
 extern unsigned long highstart_pfn, highend_pfn;
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index a77be5630209..337bd9f32921 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -149,6 +149,11 @@ static inline void totalhigh_pages_add(long count)
 	atomic_long_add(count, &_totalhigh_pages);
 }
 
+static inline bool is_kmap_addr(const void *x)
+{
+	unsigned long addr = (unsigned long)x;
+	return addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP);
+}
 #else /* CONFIG_HIGHMEM */
 
 static inline struct page *kmap_to_page(void *addr)
@@ -234,6 +239,11 @@ static inline void __kunmap_atomic(void *addr)
 static inline unsigned int nr_free_highpages(void) { return 0; }
 static inline unsigned long totalhigh_pages(void) { return 0UL; }
 
+static inline bool is_kmap_addr(const void *x)
+{
+	return false;
+}
+
 #endif /* CONFIG_HIGHMEM */
 
 /*
diff --git a/mm/usercopy.c b/mm/usercopy.c
index 2c235d5c2364..ff13e7708faa 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -229,12 +229,16 @@ static inline void check_heap_object(const void *ptr, unsigned long n,
 	if (!virt_addr_valid(ptr))
 		return;
 
-	/*
-	 * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the
-	 * highmem page or fallback to virt_to_page(). The following
-	 * is effectively a highmem-aware virt_to_slab().
-	 */
-	folio = page_folio(kmap_to_page((void *)ptr));
+	if (is_kmap_addr(ptr)) {
+		unsigned long page_end = (unsigned long)ptr | (PAGE_SIZE - 1);
+
+		if ((unsigned long)ptr + n - 1 > page_end)
+			usercopy_abort("kmap", NULL, to_user,
+					offset_in_page(ptr), n);
+		return;
+	}
+
+	folio = virt_to_folio(ptr);
 
 	if (folio_test_slab(folio)) {
 		/* Check slab allocator for flags and size. */
-- 
cgit v1.2.3


From e6f3b3c9c109ed57230996cf4a4c1b8ae7e36a81 Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Tue, 5 Apr 2022 15:16:18 -0700
Subject: cfi: Use __builtin_function_start

Clang 14 added support for the __builtin_function_start function,
which allows us to implement the function_nocfi macro without
architecture-specific inline assembly and in a way that also works
with static initializers.

Change CONFIG_CFI_CLANG to depend on Clang >= 14, define
function_nocfi using __builtin_function_start, and remove the arm64
inline assembly implementation.

Link: https://github.com/llvm/llvm-project/commit/ec2e26eaf63558934f5b73a6e530edc453cf9508
Link: https://github.com/ClangBuiltLinux/linux/issues/1353
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Will Deacon <will@kernel.org> # arm64
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220405221618.633743-1-samitolvanen@google.com
---
 arch/Kconfig                      |  5 +----
 arch/arm64/include/asm/compiler.h | 16 ----------------
 include/linux/compiler-clang.h    | 10 ++++++++++
 3 files changed, 11 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 29b0167c088b..c1627bce4a3a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -723,10 +723,7 @@ config ARCH_SUPPORTS_CFI_CLANG
 config CFI_CLANG
 	bool "Use Clang's Control Flow Integrity (CFI)"
 	depends on LTO_CLANG && ARCH_SUPPORTS_CFI_CLANG
-	# Clang >= 12:
-	# - https://bugs.llvm.org/show_bug.cgi?id=46258
-	# - https://bugs.llvm.org/show_bug.cgi?id=47479
-	depends on CLANG_VERSION >= 120000
+	depends on CLANG_VERSION >= 140000
 	select KALLSYMS
 	help
 	  This option enables Clang’s forward-edge Control Flow Integrity
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
index dc3ea4080e2e..6fb2e6bcc392 100644
--- a/arch/arm64/include/asm/compiler.h
+++ b/arch/arm64/include/asm/compiler.h
@@ -23,20 +23,4 @@
 #define __builtin_return_address(val)					\
 	(void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val)))
 
-#ifdef CONFIG_CFI_CLANG
-/*
- * With CONFIG_CFI_CLANG, the compiler replaces function address
- * references with the address of the function's CFI jump table
- * entry. The function_nocfi macro always returns the address of the
- * actual function instead.
- */
-#define function_nocfi(x) ({						\
-	void *addr;							\
-	asm("adrp %0, " __stringify(x) "\n\t"				\
-	    "add  %0, %0, :lo12:" __stringify(x)			\
-	    : "=r" (addr));						\
-	addr;								\
-})
-#endif
-
 #endif /* __ASM_COMPILER_H */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index babb1347148c..c84fec767445 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -69,6 +69,16 @@
 #define __nocfi		__attribute__((__no_sanitize__("cfi")))
 #define __cficanonical	__attribute__((__cfi_canonical_jump_table__))
 
+#if defined(CONFIG_CFI_CLANG)
+/*
+ * With CONFIG_CFI_CLANG, the compiler replaces function address
+ * references with the address of the function's CFI jump table
+ * entry. The function_nocfi macro always returns the address of the
+ * actual function instead.
+ */
+#define function_nocfi(x)	__builtin_function_start(x)
+#endif
+
 /*
  * Turn individual warnings and errors on and off locally, depending
  * on version.
-- 
cgit v1.2.3


From 63cec1389e116ae0e2a15e612a5b49651e04be3f Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 4 Apr 2022 18:09:14 -0700
Subject: fscrypt: split up FS_CRYPTO_BLOCK_SIZE

FS_CRYPTO_BLOCK_SIZE is neither the filesystem block size nor the
granularity of encryption.  Rather, it defines two logically separate
constraints that both arise from the block size of the AES cipher:

- The alignment required for the lengths of file contents blocks
- The minimum input/output length for the filenames encryption modes

Since there are way too many things called the "block size", and the
connection with the AES block size is not easily understood, split
FS_CRYPTO_BLOCK_SIZE into two constants FSCRYPT_CONTENTS_ALIGNMENT and
FSCRYPT_FNAME_MIN_MSG_LEN that more clearly describe what they are.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20220405010914.18519-1-ebiggers@kernel.org
---
 fs/crypto/crypto.c      | 10 +++++-----
 fs/crypto/fname.c       | 11 +++++++++--
 fs/ubifs/ubifs.h        |  2 +-
 include/linux/fscrypt.h | 12 +++++++++++-
 4 files changed, 26 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 526a4c1bed99..e78be66bbf01 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -113,7 +113,7 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw,
 
 	if (WARN_ON_ONCE(len <= 0))
 		return -EINVAL;
-	if (WARN_ON_ONCE(len % FS_CRYPTO_BLOCK_SIZE != 0))
+	if (WARN_ON_ONCE(len % FSCRYPT_CONTENTS_ALIGNMENT != 0))
 		return -EINVAL;
 
 	fscrypt_generate_iv(&iv, lblk_num, ci);
@@ -213,8 +213,8 @@ EXPORT_SYMBOL(fscrypt_encrypt_pagecache_blocks);
  * fscrypt_encrypt_block_inplace() - Encrypt a filesystem block in-place
  * @inode:     The inode to which this block belongs
  * @page:      The page containing the block to encrypt
- * @len:       Size of block to encrypt.  Doesn't need to be a multiple of the
- *		fs block size, but must be a multiple of FS_CRYPTO_BLOCK_SIZE.
+ * @len:       Size of block to encrypt.  This must be a multiple of
+ *		FSCRYPT_CONTENTS_ALIGNMENT.
  * @offs:      Byte offset within @page at which the block to encrypt begins
  * @lblk_num:  Filesystem logical block number of the block, i.e. the 0-based
  *		number of the block within the file
@@ -283,8 +283,8 @@ EXPORT_SYMBOL(fscrypt_decrypt_pagecache_blocks);
  * fscrypt_decrypt_block_inplace() - Decrypt a filesystem block in-place
  * @inode:     The inode to which this block belongs
  * @page:      The page containing the block to decrypt
- * @len:       Size of block to decrypt.  Doesn't need to be a multiple of the
- *		fs block size, but must be a multiple of FS_CRYPTO_BLOCK_SIZE.
+ * @len:       Size of block to decrypt.  This must be a multiple of
+ *		FSCRYPT_CONTENTS_ALIGNMENT.
  * @offs:      Byte offset within @page at which the block to decrypt begins
  * @lblk_num:  Filesystem logical block number of the block, i.e. the 0-based
  *		number of the block within the file
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index a9be4bc74a94..14e0ef5e9a20 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -18,6 +18,13 @@
 #include <crypto/skcipher.h>
 #include "fscrypt_private.h"
 
+/*
+ * The minimum message length (input and output length), in bytes, for all
+ * filenames encryption modes.  Filenames shorter than this will be zero-padded
+ * before being encrypted.
+ */
+#define FSCRYPT_FNAME_MIN_MSG_LEN 16
+
 /*
  * struct fscrypt_nokey_name - identifier for directory entry when key is absent
  *
@@ -267,7 +274,7 @@ bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
 
 	if (orig_len > max_len)
 		return false;
-	encrypted_len = max(orig_len, (u32)FS_CRYPTO_BLOCK_SIZE);
+	encrypted_len = max_t(u32, orig_len, FSCRYPT_FNAME_MIN_MSG_LEN);
 	encrypted_len = round_up(encrypted_len, padding);
 	*encrypted_len_ret = min(encrypted_len, max_len);
 	return true;
@@ -350,7 +357,7 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode,
 		return 0;
 	}
 
-	if (iname->len < FS_CRYPTO_BLOCK_SIZE)
+	if (iname->len < FSCRYPT_FNAME_MIN_MSG_LEN)
 		return -EUCLEAN;
 
 	if (fscrypt_has_encryption_key(inode))
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 008fa46ef61e..7d6d2f152e03 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -132,7 +132,7 @@
 #define WORST_COMPR_FACTOR 2
 
 #ifdef CONFIG_FS_ENCRYPTION
-#define UBIFS_CIPHER_BLOCK_SIZE FS_CRYPTO_BLOCK_SIZE
+#define UBIFS_CIPHER_BLOCK_SIZE FSCRYPT_CONTENTS_ALIGNMENT
 #else
 #define UBIFS_CIPHER_BLOCK_SIZE 0
 #endif
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 50d92d805bd8..efc7f96e5e26 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -18,7 +18,17 @@
 #include <linux/slab.h>
 #include <uapi/linux/fscrypt.h>
 
-#define FS_CRYPTO_BLOCK_SIZE		16
+/*
+ * The lengths of all file contents blocks must be divisible by this value.
+ * This is needed to ensure that all contents encryption modes will work, as
+ * some of the supported modes don't support arbitrarily byte-aligned messages.
+ *
+ * Since the needed alignment is 16 bytes, most filesystems will meet this
+ * requirement naturally, as typical block sizes are powers of 2.  However, if a
+ * filesystem can generate arbitrarily byte-aligned block lengths (e.g., via
+ * compression), then it will need to pad to this alignment before encryption.
+ */
+#define FSCRYPT_CONTENTS_ALIGNMENT 16
 
 union fscrypt_policy;
 struct fscrypt_info;
-- 
cgit v1.2.3


From 9554e908fb5d02e48a681d1eca180225bf109e83 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Fri, 25 Mar 2022 11:39:51 -0400
Subject: ELF: Remove elf_core_copy_kernel_regs()

x86-32 was the last architecture that implemented separate user and
kernel registers.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220325153953.162643-3-brgerst@gmail.com
---
 arch/powerpc/kernel/fadump.c               | 2 +-
 arch/powerpc/platforms/powernv/opal-core.c | 2 +-
 include/linux/elfcore.h                    | 9 ---------
 kernel/kexec_core.c                        | 2 +-
 4 files changed, 3 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 65562c4a0a69..4c09c6688ac6 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -752,7 +752,7 @@ u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
 	 * FIXME: How do i get PID? Do I really need it?
 	 * prstatus.pr_pid = ????
 	 */
-	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+	elf_core_copy_regs(&prstatus.pr_reg, regs);
 	buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
 			      &prstatus, sizeof(prstatus));
 	return buf;
diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c
index b97bc179f65a..adcb1a1a2bfe 100644
--- a/arch/powerpc/platforms/powernv/opal-core.c
+++ b/arch/powerpc/platforms/powernv/opal-core.c
@@ -112,7 +112,7 @@ static void __init fill_prstatus(struct elf_prstatus *prstatus, int pir,
 			  struct pt_regs *regs)
 {
 	memset(prstatus, 0, sizeof(struct elf_prstatus));
-	elf_core_copy_kernel_regs(&(prstatus->pr_reg), regs);
+	elf_core_copy_regs(&(prstatus->pr_reg), regs);
 
 	/*
 	 * Overload PID with PIR value.
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index f8e206e82476..346a8b56cdc8 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -84,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re
 #endif
 }
 
-static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs)
-{
-#ifdef ELF_CORE_COPY_KERNEL_REGS
-	ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs);
-#else
-	elf_core_copy_regs(elfregs, regs);
-#endif
-}
-
 static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs)
 {
 #if defined (ELF_CORE_COPY_TASK_REGS)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 68480f731192..be4b54c2c615 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1078,7 +1078,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
 		return;
 	memset(&prstatus, 0, sizeof(prstatus));
 	prstatus.common.pr_pid = current->pid;
-	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+	elf_core_copy_regs(&prstatus.pr_reg, regs);
 	buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
 			      &prstatus, sizeof(prstatus));
 	final_note(buf);
-- 
cgit v1.2.3


From 64b97df995f0c943be469a019d6117c89e2131bc Mon Sep 17 00:00:00 2001
From: Lech Perczak <lech.perczak@gmail.com>
Date: Wed, 13 Apr 2022 03:44:14 +0200
Subject: cdc_ether: export usbnet_cdc_zte_rx_fixup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit bfe9b9d2df66 ("cdc_ether: Improve ZTE MF823/831/910 handling")
introduces a workaround for certain ZTE modems reporting invalid MAC
addresses over CDC-ECM.
The same issue was present on their RNDIS interface,which was fixed in
commit a5a18bdf7453 ("rndis_host: Set valid random MAC on buggy devices").

However, internal modem of ZTE MF286R router, on its RNDIS interface, also
exhibits a second issue fixed already in CDC-ECM, of the device not
respecting configured random MAC address. In order to share the fixup for
this with rndis_host driver, export the workaround function, which will
be re-used in the following commit in rndis_host.

Cc: Kristian Evensen <kristian.evensen@gmail.com>
Cc: Bjørn Mork <bjorn@mork.no>
Cc: Oliver Neukum <oliver@neukum.org>
Signed-off-by: Lech Perczak <lech.perczak@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/cdc_ether.c | 3 ++-
 include/linux/usb/usbnet.h  | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 9b4dfa3001d6..2de09ad5bac0 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -479,7 +479,7 @@ static int usbnet_cdc_zte_bind(struct usbnet *dev, struct usb_interface *intf)
  * device MAC address has been updated). Always set MAC address to that of the
  * device.
  */
-static int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
 	if (skb->len < ETH_HLEN || !(skb->data[0] & 0x02))
 		return 1;
@@ -489,6 +489,7 @@ static int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(usbnet_cdc_zte_rx_fixup);
 
 /* Ensure correct link state
  *
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 8336e86ce606..1b4d72d5e891 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -214,6 +214,7 @@ extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *);
 extern void usbnet_cdc_unbind(struct usbnet *, struct usb_interface *);
 extern void usbnet_cdc_status(struct usbnet *, struct urb *);
+extern int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb);
 
 /* CDC and RNDIS support the same host-chosen packet filters for IN transfers */
 #define	DEFAULT_FILTER	(USB_CDC_PACKET_TYPE_BROADCAST \
-- 
cgit v1.2.3


From 36e747972d8b4c09e6e3275e31a3acba46e2c4d2 Mon Sep 17 00:00:00 2001
From: Lech Perczak <lech.perczak@gmail.com>
Date: Wed, 13 Apr 2022 03:44:15 +0200
Subject: rndis_host: enable the bogus MAC fixup for ZTE devices from cdc_ether
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Certain ZTE modems, namely: MF823. MF831, MF910, built-in modem from
MF286R, expose both CDC-ECM and RNDIS network interfaces.
They have a trait of ignoring the locally-administered MAC address
configured on the interface both in CDC-ECM and RNDIS part,
and this leads to dropping of incoming traffic by the host.
However, the workaround was only present in CDC-ECM, and MF286R
explicitly requires it in RNDIS mode.

Re-use the workaround in rndis_host as well, to fix operation of MF286R
module, some versions of which expose only the RNDIS interface. Do so by
introducing new flag, RNDIS_DRIVER_DATA_DST_MAC_FIXUP, and testing for it
in rndis_rx_fixup. This is required, as RNDIS uses frame batching, and all
of the packets inside the batch need the fixup. This might introduce a
performance penalty, because test is done for every returned Ethernet
frame.

Apply the workaround to both "flavors" of RNDIS interfaces, as older ZTE
modems, like MF823 found in the wild, report the USB_CLASS_COMM class
interfaces, while MF286R reports USB_CLASS_WIRELESS_CONTROLLER.

Suggested-by: Bjørn Mork <bjorn@mork.no>
Cc: Kristian Evensen <kristian.evensen@gmail.com>
Cc: Oliver Neukum <oliver@neukum.org>
Signed-off-by: Lech Perczak <lech.perczak@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/rndis_host.c   | 32 ++++++++++++++++++++++++++++++++
 include/linux/usb/rndis_host.h |  1 +
 2 files changed, 33 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index 247f58cb0f84..7a9ece2de2c5 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -485,10 +485,14 @@ EXPORT_SYMBOL_GPL(rndis_unbind);
  */
 int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 {
+	bool dst_mac_fixup;
+
 	/* This check is no longer done by usbnet */
 	if (skb->len < dev->net->hard_header_len)
 		return 0;
 
+	dst_mac_fixup = !!(dev->driver_info->data & RNDIS_DRIVER_DATA_DST_MAC_FIXUP);
+
 	/* peripheral may have batched packets to us... */
 	while (likely(skb->len)) {
 		struct rndis_data_hdr	*hdr = (void *)skb->data;
@@ -523,10 +527,17 @@ int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 			break;
 		skb_pull(skb, msg_len - sizeof *hdr);
 		skb_trim(skb2, data_len);
+
+		if (unlikely(dst_mac_fixup))
+			usbnet_cdc_zte_rx_fixup(dev, skb2);
+
 		usbnet_skb_return(dev, skb2);
 	}
 
 	/* caller will usbnet_skb_return the remaining packet */
+	if (unlikely(dst_mac_fixup))
+		usbnet_cdc_zte_rx_fixup(dev, skb);
+
 	return 1;
 }
 EXPORT_SYMBOL_GPL(rndis_rx_fixup);
@@ -600,6 +611,17 @@ static const struct driver_info	rndis_poll_status_info = {
 	.tx_fixup =	rndis_tx_fixup,
 };
 
+static const struct driver_info	zte_rndis_info = {
+	.description =	"ZTE RNDIS device",
+	.flags =	FLAG_ETHER | FLAG_POINTTOPOINT | FLAG_FRAMING_RN | FLAG_NO_SETINT,
+	.data =		RNDIS_DRIVER_DATA_DST_MAC_FIXUP,
+	.bind =		rndis_bind,
+	.unbind =	rndis_unbind,
+	.status =	rndis_status,
+	.rx_fixup =	rndis_rx_fixup,
+	.tx_fixup =	rndis_tx_fixup,
+};
+
 /*-------------------------------------------------------------------------*/
 
 static const struct usb_device_id	products [] = {
@@ -613,6 +635,16 @@ static const struct usb_device_id	products [] = {
 	USB_VENDOR_AND_INTERFACE_INFO(0x238b,
 				      USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
 	.driver_info = (unsigned long)&rndis_info,
+}, {
+	/* ZTE WWAN modules */
+	USB_VENDOR_AND_INTERFACE_INFO(0x19d2,
+				      USB_CLASS_WIRELESS_CONTROLLER, 1, 3),
+	.driver_info = (unsigned long)&zte_rndis_info,
+}, {
+	/* ZTE WWAN modules, ACM flavour */
+	USB_VENDOR_AND_INTERFACE_INFO(0x19d2,
+				      USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
+	.driver_info = (unsigned long)&zte_rndis_info,
 }, {
 	/* RNDIS is MSFT's un-official variant of CDC ACM */
 	USB_INTERFACE_INFO(USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
diff --git a/include/linux/usb/rndis_host.h b/include/linux/usb/rndis_host.h
index 809bccd08455..cc42db51bbba 100644
--- a/include/linux/usb/rndis_host.h
+++ b/include/linux/usb/rndis_host.h
@@ -197,6 +197,7 @@ struct rndis_keepalive_c {	/* IN (optionally OUT) */
 
 /* Flags for driver_info::data */
 #define RNDIS_DRIVER_DATA_POLL_STATUS	1	/* poll status before control */
+#define RNDIS_DRIVER_DATA_DST_MAC_FIXUP	2	/* device ignores configured MAC address */
 
 extern void rndis_status(struct usbnet *dev, struct urb *urb);
 extern int
-- 
cgit v1.2.3


From 3dc6ffae2da201284cb24af66af77ee0bbb2efaa Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Thu, 14 Apr 2022 11:18:03 +0200
Subject: timekeeping: Introduce fast accessor to clock tai

Introduce fast/NMI safe accessor to clock tai for tracing. The Linux kernel
tracing infrastructure has support for using different clocks to generate
timestamps for trace events. Especially in TSN networks it's useful to have TAI
as trace clock, because the application scheduling is done in accordance to the
network time, which is based on TAI. With a tai trace_clock in place, it becomes
very convenient to correlate network activity with Linux kernel application
traces.

Use the same implementation as ktime_get_boot_fast_ns() does by reading the
monotonic time and adding the TAI offset. The same limitations as for the fast
boot implementation apply. The TAI offset may change at run time e.g., by
setting the time or using adjtimex() with an offset. However, these kind of
offset changes are rare events. Nevertheless, the user has to be aware and deal
with it in post processing.

An alternative approach would be to use the same implementation as
ktime_get_real_fast_ns() does. However, this requires to add an additional u64
member to the tk_read_base struct. This struct together with a seqcount is
designed to fit into a single cache line on 64 bit architectures. Adding a new
member would violate this constraint.

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20220414091805.89667-2-kurt@linutronix.de
---
 Documentation/core-api/timekeeping.rst |  1 +
 include/linux/timekeeping.h            |  1 +
 kernel/time/timekeeping.c              | 17 +++++++++++++++++
 3 files changed, 19 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/core-api/timekeeping.rst b/Documentation/core-api/timekeeping.rst
index 729e24864fe7..22ec68f24421 100644
--- a/Documentation/core-api/timekeeping.rst
+++ b/Documentation/core-api/timekeeping.rst
@@ -132,6 +132,7 @@ Some additional variants exist for more specialized cases:
 .. c:function:: u64 ktime_get_mono_fast_ns( void )
 		u64 ktime_get_raw_fast_ns( void )
 		u64 ktime_get_boot_fast_ns( void )
+		u64 ktime_get_tai_fast_ns( void )
 		u64 ktime_get_real_fast_ns( void )
 
 	These variants are safe to call from any context, including from
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 78a98bdff76d..fe1e467ba046 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -177,6 +177,7 @@ static inline u64 ktime_get_raw_ns(void)
 extern u64 ktime_get_mono_fast_ns(void);
 extern u64 ktime_get_raw_fast_ns(void);
 extern u64 ktime_get_boot_fast_ns(void);
+extern u64 ktime_get_tai_fast_ns(void);
 extern u64 ktime_get_real_fast_ns(void);
 
 /*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index dcdcb85121e4..2c22023fbf5f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -532,6 +532,23 @@ u64 notrace ktime_get_boot_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
 
+/**
+ * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock.
+ *
+ * The same limitations as described for ktime_get_boot_fast_ns() apply. The
+ * mono time and the TAI offset are not read atomically which may yield wrong
+ * readouts. However, an update of the TAI offset is an rare event e.g., caused
+ * by settime or adjtimex with an offset. The user of this function has to deal
+ * with the possibility of wrong timestamps in post processing.
+ */
+u64 notrace ktime_get_tai_fast_ns(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai)));
+}
+EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns);
+
 static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono)
 {
 	struct tk_read_base *tkr;
-- 
cgit v1.2.3


From af47d8033fc731f19600efd27ba4a7d0fdfcc77c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 14 Apr 2022 21:42:48 +0300
Subject: gpiolib: Introduce a helper to get first GPIO controller node

Introduce a helper to get first GPIO controller node which drivers
may want to use.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 include/linux/gpio/driver.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 12de0b22b4ef..83e2d72e51bb 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -766,4 +766,14 @@ static inline unsigned int gpiochip_node_count(struct device *dev)
 	return count;
 }
 
+static inline struct fwnode_handle *gpiochip_node_get_first(struct device *dev)
+{
+	struct fwnode_handle *fwnode;
+
+	for_each_gpiochip_node(dev, fwnode)
+		return fwnode;
+
+	return NULL;
+}
+
 #endif /* __LINUX_GPIO_DRIVER_H */
-- 
cgit v1.2.3


From f1724d397c60d296c0805c95a46ae7fc7163b70c Mon Sep 17 00:00:00 2001
From: Kai Ye <yekai13@huawei.com>
Date: Sat, 9 Apr 2022 16:03:18 +0800
Subject: crypto: hisilicon/qm - add register checking for ACC

Add register detection function to accelerator. Provided a tool that
user can checking differential register through Debugfs.
e.g.
    cd /sys/kernel/debug/hisi_zip/<bdf>/zip_dfx
    cat diff_regs

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Signed-off-by: Kai Ye <yekai13@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/qm.c | 182 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/hisi_acc_qm.h   |  14 ++++
 2 files changed, 195 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index c5c507f2d779..5e0695a8900c 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -253,7 +253,15 @@
 #define QM_QOS_MAX_CIR_U		6
 #define QM_QOS_MAX_CIR_S		11
 #define QM_QOS_VAL_MAX_LEN		32
-
+#define QM_DFX_BASE		0x0100000
+#define QM_DFX_STATE1		0x0104000
+#define QM_DFX_STATE2		0x01040C8
+#define QM_DFX_COMMON		0x0000
+#define QM_DFX_BASE_LEN		0x5A
+#define QM_DFX_STATE1_LEN		0x2E
+#define QM_DFX_STATE2_LEN		0x11
+#define QM_DFX_COMMON_LEN		0xC3
+#define QM_DFX_REGS_LEN		4UL
 #define QM_AUTOSUSPEND_DELAY		3000
 
 #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \
@@ -467,6 +475,23 @@ static const struct hisi_qm_hw_error qm_hw_error[] = {
 	{ /* sentinel */ }
 };
 
+/* define the QM's dfx regs region and region length */
+static struct dfx_diff_registers qm_diff_regs[] = {
+	{
+		.reg_offset = QM_DFX_BASE,
+		.reg_len = QM_DFX_BASE_LEN,
+	}, {
+		.reg_offset = QM_DFX_STATE1,
+		.reg_len = QM_DFX_STATE1_LEN,
+	}, {
+		.reg_offset = QM_DFX_STATE2,
+		.reg_len = QM_DFX_STATE2_LEN,
+	}, {
+		.reg_offset = QM_DFX_COMMON,
+		.reg_len = QM_DFX_COMMON_LEN,
+	},
+};
+
 static const char * const qm_db_timeout[] = {
 	"sq", "cq", "eq", "aeq",
 };
@@ -1625,6 +1650,156 @@ static int qm_regs_show(struct seq_file *s, void *unused)
 
 DEFINE_SHOW_ATTRIBUTE(qm_regs);
 
+static struct dfx_diff_registers *dfx_regs_init(struct hisi_qm *qm,
+	const struct dfx_diff_registers *cregs, int reg_len)
+{
+	struct dfx_diff_registers *diff_regs;
+	u32 j, base_offset;
+	int i;
+
+	diff_regs = kcalloc(reg_len, sizeof(*diff_regs), GFP_KERNEL);
+	if (!diff_regs)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < reg_len; i++) {
+		if (!cregs[i].reg_len)
+			continue;
+
+		diff_regs[i].reg_offset = cregs[i].reg_offset;
+		diff_regs[i].reg_len = cregs[i].reg_len;
+		diff_regs[i].regs = kcalloc(QM_DFX_REGS_LEN, cregs[i].reg_len,
+					 GFP_KERNEL);
+		if (!diff_regs[i].regs)
+			goto alloc_error;
+
+		for (j = 0; j < diff_regs[i].reg_len; j++) {
+			base_offset = diff_regs[i].reg_offset +
+					j * QM_DFX_REGS_LEN;
+			diff_regs[i].regs[j] = readl(qm->io_base + base_offset);
+		}
+	}
+
+	return diff_regs;
+
+alloc_error:
+	while (i > 0) {
+		i--;
+		kfree(diff_regs[i].regs);
+	}
+	kfree(diff_regs);
+	return ERR_PTR(-ENOMEM);
+}
+
+static void dfx_regs_uninit(struct hisi_qm *qm,
+		struct dfx_diff_registers *dregs, int reg_len)
+{
+	int i;
+
+	/* Setting the pointer is NULL to prevent double free */
+	for (i = 0; i < reg_len; i++) {
+		kfree(dregs[i].regs);
+		dregs[i].regs = NULL;
+	}
+	kfree(dregs);
+	dregs = NULL;
+}
+
+/**
+ * hisi_qm_diff_regs_init() - Allocate memory for registers.
+ * @qm: device qm handle.
+ * @dregs: diff registers handle.
+ * @reg_len: diff registers region length.
+ */
+int hisi_qm_diff_regs_init(struct hisi_qm *qm,
+		struct dfx_diff_registers *dregs, int reg_len)
+{
+	if (!qm || !dregs || reg_len <= 0)
+		return -EINVAL;
+
+	if (qm->fun_type != QM_HW_PF)
+		return 0;
+
+	qm->debug.qm_diff_regs = dfx_regs_init(qm, qm_diff_regs,
+						ARRAY_SIZE(qm_diff_regs));
+	if (IS_ERR(qm->debug.qm_diff_regs))
+		return PTR_ERR(qm->debug.qm_diff_regs);
+
+	qm->debug.acc_diff_regs = dfx_regs_init(qm, dregs, reg_len);
+	if (IS_ERR(qm->debug.acc_diff_regs)) {
+		dfx_regs_uninit(qm, qm->debug.qm_diff_regs,
+				ARRAY_SIZE(qm_diff_regs));
+		return PTR_ERR(qm->debug.acc_diff_regs);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_diff_regs_init);
+
+/**
+ * hisi_qm_diff_regs_uninit() - Free memory for registers.
+ * @qm: device qm handle.
+ * @reg_len: diff registers region length.
+ */
+void hisi_qm_diff_regs_uninit(struct hisi_qm *qm, int reg_len)
+{
+	if (!qm  || reg_len <= 0 || qm->fun_type != QM_HW_PF)
+		return;
+
+	dfx_regs_uninit(qm, qm->debug.acc_diff_regs, reg_len);
+	dfx_regs_uninit(qm, qm->debug.qm_diff_regs, ARRAY_SIZE(qm_diff_regs));
+}
+EXPORT_SYMBOL_GPL(hisi_qm_diff_regs_uninit);
+
+/**
+ * hisi_qm_acc_diff_regs_dump() - Dump registers's value.
+ * @qm: device qm handle.
+ * @s: Debugfs file handle.
+ * @dregs: diff registers handle.
+ * @regs_len: diff registers region length.
+ */
+void hisi_qm_acc_diff_regs_dump(struct hisi_qm *qm, struct seq_file *s,
+	struct dfx_diff_registers *dregs, int regs_len)
+{
+	u32 j, val, base_offset;
+	int i, ret;
+
+	if (!qm || !s || !dregs || regs_len <= 0)
+		return;
+
+	ret = hisi_qm_get_dfx_access(qm);
+	if (ret)
+		return;
+
+	down_read(&qm->qps_lock);
+	for (i = 0; i < regs_len; i++) {
+		if (!dregs[i].reg_len)
+			continue;
+
+		for (j = 0; j < dregs[i].reg_len; j++) {
+			base_offset = dregs[i].reg_offset + j * QM_DFX_REGS_LEN;
+			val = readl(qm->io_base + base_offset);
+			if (val != dregs[i].regs[j])
+				seq_printf(s, "0x%08x = 0x%08x ---> 0x%08x\n",
+					   base_offset, dregs[i].regs[j], val);
+		}
+	}
+	up_read(&qm->qps_lock);
+
+	hisi_qm_put_dfx_access(qm);
+}
+EXPORT_SYMBOL_GPL(hisi_qm_acc_diff_regs_dump);
+
+static int qm_diff_regs_show(struct seq_file *s, void *unused)
+{
+	struct hisi_qm *qm = s->private;
+
+	hisi_qm_acc_diff_regs_dump(qm, s, qm->debug.qm_diff_regs,
+					ARRAY_SIZE(qm_diff_regs));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(qm_diff_regs);
+
 static ssize_t qm_cmd_read(struct file *filp, char __user *buffer,
 			   size_t count, loff_t *pos)
 {
@@ -4484,6 +4659,7 @@ static void hisi_qm_set_algqos_init(struct hisi_qm *qm)
  */
 void hisi_qm_debug_init(struct hisi_qm *qm)
 {
+	struct dfx_diff_registers *qm_regs = qm->debug.qm_diff_regs;
 	struct qm_dfx *dfx = &qm->debug.dfx;
 	struct dentry *qm_d;
 	void *data;
@@ -4499,6 +4675,10 @@ void hisi_qm_debug_init(struct hisi_qm *qm)
 			qm_create_debugfs_file(qm, qm->debug.qm_d, i);
 	}
 
+	if (qm_regs)
+		debugfs_create_file("diff_regs", 0444, qm->debug.qm_d,
+					qm, &qm_diff_regs_fops);
+
 	debugfs_create_file("regs", 0444, qm->debug.qm_d, qm, &qm_regs_fops);
 
 	debugfs_create_file("cmd", 0600, qm->debug.qm_d, qm, &qm_cmd_fops);
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index 177f7b7cd414..39acc0316a60 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -168,6 +168,12 @@ enum qm_vf_state {
 	QM_NOT_READY,
 };
 
+struct dfx_diff_registers {
+	u32 *regs;
+	u32 reg_offset;
+	u32 reg_len;
+};
+
 struct qm_dfx {
 	atomic64_t err_irq_cnt;
 	atomic64_t aeq_irq_cnt;
@@ -190,6 +196,8 @@ struct qm_debug {
 	struct dentry *debug_root;
 	struct dentry *qm_d;
 	struct debugfs_file files[DEBUG_FILE_NUM];
+	struct dfx_diff_registers *qm_diff_regs;
+	struct dfx_diff_registers *acc_diff_regs;
 };
 
 struct qm_shaper_factor {
@@ -448,6 +456,12 @@ int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen);
 int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs);
 void hisi_qm_dev_err_init(struct hisi_qm *qm);
 void hisi_qm_dev_err_uninit(struct hisi_qm *qm);
+int hisi_qm_diff_regs_init(struct hisi_qm *qm,
+		struct dfx_diff_registers *dregs, int reg_len);
+void hisi_qm_diff_regs_uninit(struct hisi_qm *qm, int reg_len);
+void hisi_qm_acc_diff_regs_dump(struct hisi_qm *qm, struct seq_file *s,
+		struct dfx_diff_registers *dregs, int regs_len);
+
 pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev,
 					  pci_channel_state_t state);
 pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev);
-- 
cgit v1.2.3


From a888ccd6c66683a49977ba6a2b91fe52fbec9367 Mon Sep 17 00:00:00 2001
From: Kai Ye <yekai13@huawei.com>
Date: Sat, 9 Apr 2022 16:03:25 +0800
Subject: crypto: hisilicon/qm - add last word dumping for ACC

Add last word dumping function during acc engines controller reset.
The last words are reported to the printed information during the
reset. The dmesg information included qm debugging registers and
engine debugging registers. It can help to improve debugging
capability.

Signed-off-by: Kai Ye <yekai13@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/qm.c | 57 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/hisi_acc_qm.h   |  4 +++
 2 files changed, 61 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 5e0695a8900c..7f5c3186a895 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -3673,6 +3673,17 @@ static void hisi_qm_set_state(struct hisi_qm *qm, u8 state)
 		writel(state, qm->io_base + QM_VF_STATE);
 }
 
+static void qm_last_regs_uninit(struct hisi_qm *qm)
+{
+	struct qm_debug *debug = &qm->debug;
+
+	if (qm->fun_type == QM_HW_VF || !debug->qm_last_words)
+		return;
+
+	kfree(debug->qm_last_words);
+	debug->qm_last_words = NULL;
+}
+
 /**
  * hisi_qm_uninit() - Uninitialize qm.
  * @qm: The qm needed uninit.
@@ -3684,6 +3695,8 @@ void hisi_qm_uninit(struct hisi_qm *qm)
 	struct pci_dev *pdev = qm->pdev;
 	struct device *dev = &pdev->dev;
 
+	qm_last_regs_uninit(qm);
+
 	qm_cmd_uninit(qm);
 	kfree(qm->factor);
 	down_write(&qm->qps_lock);
@@ -5361,6 +5374,24 @@ static int qm_controller_reset_done(struct hisi_qm *qm)
 	return 0;
 }
 
+static void qm_show_last_dfx_regs(struct hisi_qm *qm)
+{
+	struct qm_debug *debug = &qm->debug;
+	struct pci_dev *pdev = qm->pdev;
+	u32 val;
+	int i;
+
+	if (qm->fun_type == QM_HW_VF || !debug->qm_last_words)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(qm_dfx_regs); i++) {
+		val = readl_relaxed(qm->io_base + qm_dfx_regs[i].offset);
+		if (debug->qm_last_words[i] != val)
+			pci_info(pdev, "%s \t= 0x%08x => 0x%08x\n",
+			qm_dfx_regs[i].name, debug->qm_last_words[i], val);
+	}
+}
+
 static int qm_controller_reset(struct hisi_qm *qm)
 {
 	struct pci_dev *pdev = qm->pdev;
@@ -5376,6 +5407,10 @@ static int qm_controller_reset(struct hisi_qm *qm)
 		return ret;
 	}
 
+	qm_show_last_dfx_regs(qm);
+	if (qm->err_ini->show_last_dfx_regs)
+		qm->err_ini->show_last_dfx_regs(qm);
+
 	ret = qm_soft_reset(qm);
 	if (ret) {
 		pci_err(pdev, "Controller reset failed (%d)\n", ret);
@@ -6086,6 +6121,26 @@ err_alloc_qdma:
 	return ret;
 }
 
+static void qm_last_regs_init(struct hisi_qm *qm)
+{
+	int dfx_regs_num = ARRAY_SIZE(qm_dfx_regs);
+	struct qm_debug *debug = &qm->debug;
+	int i;
+
+	if (qm->fun_type == QM_HW_VF)
+		return;
+
+	debug->qm_last_words = kcalloc(dfx_regs_num, sizeof(unsigned int),
+								GFP_KERNEL);
+	if (!debug->qm_last_words)
+		return;
+
+	for (i = 0; i < dfx_regs_num; i++) {
+		debug->qm_last_words[i] = readl_relaxed(qm->io_base +
+			qm_dfx_regs[i].offset);
+	}
+}
+
 /**
  * hisi_qm_init() - Initialize configures about qm.
  * @qm: The qm needing init.
@@ -6138,6 +6193,8 @@ int hisi_qm_init(struct hisi_qm *qm)
 	qm_cmd_init(qm);
 	atomic_set(&qm->status.flags, QM_INIT);
 
+	qm_last_regs_init(qm);
+
 	return 0;
 
 err_alloc_uacce:
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index 39acc0316a60..e5522eaf88fd 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -196,6 +196,9 @@ struct qm_debug {
 	struct dentry *debug_root;
 	struct dentry *qm_d;
 	struct debugfs_file files[DEBUG_FILE_NUM];
+	unsigned int *qm_last_words;
+	/* ACC engines recoreding last regs */
+	unsigned int *last_words;
 	struct dfx_diff_registers *qm_diff_regs;
 	struct dfx_diff_registers *acc_diff_regs;
 };
@@ -251,6 +254,7 @@ struct hisi_qm_err_ini {
 	void (*open_sva_prefetch)(struct hisi_qm *qm);
 	void (*close_sva_prefetch)(struct hisi_qm *qm);
 	void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts);
+	void (*show_last_dfx_regs)(struct hisi_qm *qm);
 	void (*err_info_init)(struct hisi_qm *qm);
 };
 
-- 
cgit v1.2.3


From f6f586102add59d57bcc6eea06fdeaae11bb17a1 Mon Sep 17 00:00:00 2001
From: Eric Tremblay <etremblay@distech-controls.com>
Date: Wed, 30 Mar 2022 12:46:40 +0200
Subject: serial: 8250: Handle UART without interrupt on TEMT using em485
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce the UART_CAP_NOTEMT capability. The capability indicates that
the UART doesn't have an interrupt available on TEMT.

In the case where the device does not support it, we calculate the
maximum time it could take for the transmitter to empty the
shift register. When we get in the situation where we get the
THRE interrupt, we check if the TEMT bit is set. If it's not, we start
the a timer and recall __stop_tx() after the delay.

The transmit sequence is a bit modified when the capability is set. The
new timer is used between the last interrupt(THRE) and a potential
stop_tx timer.

Signed-off-by: Giulio Benetti <giulio.benetti@micronovasrl.com>
[moved to use added UART_CAP_TEMT]
Signed-off-by: Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
[moved to use added UART_CAP_NOTEMT, improve timeout]
Signed-off-by: Eric Tremblay <etremblay@distech-controls.com>
[rebased to v5.17, making use of tty_get_frame_size]
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20220330104642.229507-2-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250.h      |  1 +
 drivers/tty/serial/8250/8250_port.c | 76 ++++++++++++++++++++++++++++++++++++-
 include/linux/serial_8250.h         |  2 +
 3 files changed, 77 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index db784ace25d8..39ffeb37786f 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -83,6 +83,7 @@ struct serial8250_config {
 #define UART_CAP_MINI	BIT(17)	/* Mini UART on BCM283X family lacks:
 					 * STOP PARITY EPAR SPAR WLEN5 WLEN6
 					 */
+#define UART_CAP_NOTEMT	BIT(18)	/* UART without interrupt on TEMT available */
 
 #define UART_BUG_QUOT	BIT(0)	/* UART has buggy quot LSB */
 #define UART_BUG_TXEN	BIT(1)	/* UART has buggy TX IIR status */
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 318af6f13605..31545cd8276e 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -571,8 +571,21 @@ static void serial8250_clear_fifos(struct uart_8250_port *p)
 	}
 }
 
+static inline void serial8250_em485_update_temt_delay(struct uart_8250_port *p,
+			unsigned int cflag, unsigned int baud)
+{
+	unsigned int bits;
+
+	if (!p->em485)
+		return;
+
+	bits = tty_get_frame_size(cflag);
+	p->em485->no_temt_delay = DIV_ROUND_UP(bits * NSEC_PER_SEC, baud);
+}
+
 static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t);
 static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t);
+static enum hrtimer_restart serial8250_em485_handle_no_temt(struct hrtimer *t);
 
 void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p)
 {
@@ -631,6 +644,16 @@ static int serial8250_em485_init(struct uart_8250_port *p)
 		     HRTIMER_MODE_REL);
 	hrtimer_init(&p->em485->start_tx_timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_REL);
+
+	if (p->capabilities & UART_CAP_NOTEMT) {
+		struct tty_struct *tty = p->port.state->port.tty;
+
+		serial8250_em485_update_temt_delay(p, tty->termios.c_cflag,
+						   tty_get_baud_rate(tty));
+		hrtimer_init(&p->em485->no_temt_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		p->em485->no_temt_timer.function = &serial8250_em485_handle_no_temt;
+	}
+
 	p->em485->stop_tx_timer.function = &serial8250_em485_handle_stop_tx;
 	p->em485->start_tx_timer.function = &serial8250_em485_handle_start_tx;
 	p->em485->port = p;
@@ -662,6 +685,7 @@ void serial8250_em485_destroy(struct uart_8250_port *p)
 
 	hrtimer_cancel(&p->em485->start_tx_timer);
 	hrtimer_cancel(&p->em485->stop_tx_timer);
+	hrtimer_cancel(&p->em485->no_temt_timer);
 
 	kfree(p->em485);
 	p->em485 = NULL;
@@ -1504,6 +1528,11 @@ static void start_hrtimer_ms(struct hrtimer *hrt, unsigned long msec)
 	hrtimer_start(hrt, ms_to_ktime(msec), HRTIMER_MODE_REL);
 }
 
+static void start_hrtimer_ns(struct hrtimer *hrt, unsigned long nsec)
+{
+	hrtimer_start(hrt, ns_to_ktime(nsec), HRTIMER_MODE_REL);
+}
+
 static void __stop_tx_rs485(struct uart_8250_port *p)
 {
 	struct uart_8250_em485 *em485 = p->em485;
@@ -1535,14 +1564,33 @@ static inline void __stop_tx(struct uart_8250_port *p)
 
 	if (em485) {
 		unsigned char lsr = serial_in(p, UART_LSR);
+
+		p->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS;
+
 		/*
-		 * To provide required timeing and allow FIFO transfer,
+		 * To provide required timing and allow FIFO transfer,
 		 * __stop_tx_rs485() must be called only when both FIFO and
 		 * shift register are empty. It is for device driver to enable
 		 * interrupt on TEMT.
 		 */
-		if ((lsr & BOTH_EMPTY) != BOTH_EMPTY)
+		if ((lsr & BOTH_EMPTY) != BOTH_EMPTY) {
+			if (!(p->capabilities & UART_CAP_NOTEMT))
+				/* __stop_tx will be called again once TEMT triggers */
+				return;
+
+			if (!(lsr & UART_LSR_THRE))
+				/* __stop_tx will be called again once THRE triggers */
+				return;
+
+			/*
+			 * On devices with no TEMT interrupt available, start
+			 * a timer for a byte time. The timer will recall
+			 * __stop_tx().
+			 */
+			em485->active_timer = &em485->no_temt_timer;
+			start_hrtimer_ns(&em485->no_temt_timer, em485->no_temt_delay);
 			return;
+		}
 
 		__stop_tx_rs485(p);
 	}
@@ -1653,6 +1701,27 @@ static inline void start_tx_rs485(struct uart_port *port)
 	__start_tx(port);
 }
 
+static enum hrtimer_restart serial8250_em485_handle_no_temt(struct hrtimer *t)
+{
+	struct uart_8250_em485 *em485;
+	struct uart_8250_port *p;
+	unsigned long flags;
+
+	em485 = container_of(t, struct uart_8250_em485, no_temt_timer);
+	p = em485->port;
+
+	serial8250_rpm_get(p);
+	spin_lock_irqsave(&p->port.lock, flags);
+	if (em485->active_timer == &em485->no_temt_timer) {
+		em485->active_timer = NULL;
+		__stop_tx(p);
+	}
+
+	spin_unlock_irqrestore(&p->port.lock, flags);
+	serial8250_rpm_put(p);
+	return HRTIMER_NORESTART;
+}
+
 static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t)
 {
 	struct uart_8250_em485 *em485 = container_of(t, struct uart_8250_em485,
@@ -2858,6 +2927,9 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 
 	serial8250_set_divisor(port, baud, quot, frac);
 
+	if (up->capabilities & UART_CAP_NOTEMT)
+		serial8250_em485_update_temt_delay(up, termios->c_cflag, baud);
+
 	/*
 	 * LCR DLAB must be set to enable 64-byte FIFO mode. If the FCR
 	 * is written without DLAB set, this mode will be disabled.
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index ff84a3ed10ea..de135852107c 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -79,7 +79,9 @@ struct uart_8250_ops {
 struct uart_8250_em485 {
 	struct hrtimer		start_tx_timer; /* "rs485 start tx" timer */
 	struct hrtimer		stop_tx_timer;  /* "rs485 stop tx" timer */
+	struct hrtimer		no_temt_timer;  /* "rs485 no TEMT interrupt" timer */
 	struct hrtimer		*active_timer;  /* pointer to active timer */
+	unsigned long		no_temt_delay;  /* Delay for no_temt_timer */
 	struct uart_8250_port	*port;          /* for hrtimer callbacks */
 	unsigned int		tx_stopped:1;	/* tx is currently stopped */
 };
-- 
cgit v1.2.3


From 4dc84c06a343fcb95fd5a0acb537aefa4ebdd1b0 Mon Sep 17 00:00:00 2001
From: Jie Wang <wangjie125@huawei.com>
Date: Tue, 12 Apr 2022 10:01:19 +0800
Subject: net: ethtool: extend ringparam set/get APIs for tx_push

Currently tx push is a standard driver feature which controls use of a fast
path descriptor push. So this patch extends the ringparam APIs and data
structures to support set/get tx push by ethtool -G/g.

Signed-off-by: Jie Wang <wangjie125@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/ethtool-netlink.rst |  8 ++++++++
 include/linux/ethtool.h                      |  4 ++++
 include/uapi/linux/ethtool_netlink.h         |  1 +
 net/ethtool/netlink.h                        |  2 +-
 net/ethtool/rings.c                          | 18 ++++++++++++++++--
 5 files changed, 30 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 24d9be69065d..dbca3e9ec782 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -862,6 +862,7 @@ Kernel response contents:
   ``ETHTOOL_A_RINGS_RX_BUF_LEN``        u32     size of buffers on the ring
   ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT``    u8      TCP header / data split
   ``ETHTOOL_A_RINGS_CQE_SIZE``          u32     Size of TX/RX CQE
+  ``ETHTOOL_A_RINGS_TX_PUSH``           u8      flag of TX Push mode
   ====================================  ======  ===========================
 
 ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with
@@ -871,6 +872,12 @@ separate buffers. The device configuration must make it possible to receive
 full memory pages of data, for example because MTU is high enough or through
 HW-GRO.
 
+``ETHTOOL_A_RINGS_TX_PUSH`` flag is used to enable descriptor fast
+path to send packets. In ordinary path, driver fills descriptors in DRAM and
+notifies NIC hardware. In fast path, driver pushes descriptors to the device
+through MMIO writes, thus reducing the latency. However, enabling this feature
+may increase the CPU cost. Drivers may enforce additional per-packet
+eligibility checks (e.g. on packet size).
 
 RINGS_SET
 =========
@@ -887,6 +894,7 @@ Request contents:
   ``ETHTOOL_A_RINGS_TX``                u32     size of TX ring
   ``ETHTOOL_A_RINGS_RX_BUF_LEN``        u32     size of buffers on the ring
   ``ETHTOOL_A_RINGS_CQE_SIZE``          u32     Size of TX/RX CQE
+  ``ETHTOOL_A_RINGS_TX_PUSH``           u8      flag of TX Push mode
   ====================================  ======  ===========================
 
 Kernel checks that requested ring sizes do not exceed limits reported by
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 4af58459a1e7..99dc7bfbcd3c 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -71,11 +71,13 @@ enum {
  * struct kernel_ethtool_ringparam - RX/TX ring configuration
  * @rx_buf_len: Current length of buffers on the rx ring.
  * @tcp_data_split: Scatter packet headers and data to separate buffers
+ * @tx_push: The flag of tx push mode
  * @cqe_size: Size of TX/RX completion queue event
  */
 struct kernel_ethtool_ringparam {
 	u32	rx_buf_len;
 	u8	tcp_data_split;
+	u8	tx_push;
 	u32	cqe_size;
 };
 
@@ -83,10 +85,12 @@ struct kernel_ethtool_ringparam {
  * enum ethtool_supported_ring_param - indicator caps for setting ring params
  * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len
  * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size
+ * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push
  */
 enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0),
 	ETHTOOL_RING_USE_CQE_SIZE   = BIT(1),
+	ETHTOOL_RING_USE_TX_PUSH    = BIT(2),
 };
 
 #define __ETH_RSS_HASH_BIT(bit)	((u32)1 << (bit))
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 979850221b8d..d2fb4f7be61b 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -338,6 +338,7 @@ enum {
 	ETHTOOL_A_RINGS_RX_BUF_LEN,                     /* u32 */
 	ETHTOOL_A_RINGS_TCP_DATA_SPLIT,			/* u8 */
 	ETHTOOL_A_RINGS_CQE_SIZE,			/* u32 */
+	ETHTOOL_A_RINGS_TX_PUSH,			/* u8 */
 
 	/* add new constants above here */
 	__ETHTOOL_A_RINGS_CNT,
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 29d01662a48b..7919ddb2371c 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -363,7 +363,7 @@ extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANT
 extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1];
 extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1];
 extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1];
-extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_CQE_SIZE + 1];
+extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX_PUSH + 1];
 extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1];
 extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1];
 extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1];
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index 9f33c9689b56..9ed60c507d97 100644
--- a/net/ethtool/rings.c
+++ b/net/ethtool/rings.c
@@ -55,7 +55,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base,
 	       nla_total_size(sizeof(u32)) +	/* _RINGS_TX */
 	       nla_total_size(sizeof(u32)) +	/* _RINGS_RX_BUF_LEN */
 	       nla_total_size(sizeof(u8))  +	/* _RINGS_TCP_DATA_SPLIT */
-	       nla_total_size(sizeof(u32));	/* _RINGS_CQE_SIZE */
+	       nla_total_size(sizeof(u32)  +	/* _RINGS_CQE_SIZE */
+	       nla_total_size(sizeof(u8)));	/* _RINGS_TX_PUSH */
 }
 
 static int rings_fill_reply(struct sk_buff *skb,
@@ -94,7 +95,8 @@ static int rings_fill_reply(struct sk_buff *skb,
 	     (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT,
 			 kr->tcp_data_split))) ||
 	    (kr->cqe_size &&
-	     (nla_put_u32(skb, ETHTOOL_A_RINGS_CQE_SIZE, kr->cqe_size))))
+	     (nla_put_u32(skb, ETHTOOL_A_RINGS_CQE_SIZE, kr->cqe_size))) ||
+	    nla_put_u8(skb, ETHTOOL_A_RINGS_TX_PUSH, !!kr->tx_push))
 		return -EMSGSIZE;
 
 	return 0;
@@ -123,6 +125,7 @@ const struct nla_policy ethnl_rings_set_policy[] = {
 	[ETHTOOL_A_RINGS_TX]			= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_RX_BUF_LEN]            = NLA_POLICY_MIN(NLA_U32, 1),
 	[ETHTOOL_A_RINGS_CQE_SIZE]		= NLA_POLICY_MIN(NLA_U32, 1),
+	[ETHTOOL_A_RINGS_TX_PUSH]		= NLA_POLICY_MAX(NLA_U8, 1),
 };
 
 int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info)
@@ -149,6 +152,15 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info)
 	if (!ops->get_ringparam || !ops->set_ringparam)
 		goto out_dev;
 
+	if (tb[ETHTOOL_A_RINGS_TX_PUSH] &&
+	    !(ops->supported_ring_params & ETHTOOL_RING_USE_TX_PUSH)) {
+		ret = -EOPNOTSUPP;
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[ETHTOOL_A_RINGS_TX_PUSH],
+				    "setting tx push not supported");
+		goto out_dev;
+	}
+
 	rtnl_lock();
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
@@ -165,6 +177,8 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info)
 			 tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod);
 	ethnl_update_u32(&kernel_ringparam.cqe_size,
 			 tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod);
+	ethnl_update_u8(&kernel_ringparam.tx_push,
+			tb[ETHTOOL_A_RINGS_TX_PUSH], &mod);
 	ret = 0;
 	if (!mod)
 		goto out_ops;
-- 
cgit v1.2.3


From f9a2fb73318eb4dbf8cd84866b8b0dd012d8b116 Mon Sep 17 00:00:00 2001
From: Arun Ajith S <aajith@arista.com>
Date: Fri, 15 Apr 2022 08:34:02 +0000
Subject: net/ipv6: Introduce accept_unsolicited_na knob to implement
 router-side changes for RFC9131

Add a new neighbour cache entry in STALE state for routers on receiving
an unsolicited (gratuitous) neighbour advertisement with
target link-layer-address option specified.
This is similar to the arp_accept configuration for IPv4.
A new sysctl endpoint is created to turn on this behaviour:
/proc/sys/net/ipv6/conf/interface/accept_unsolicited_na.

Signed-off-by: Arun Ajith S <aajith@arista.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.rst             |  27 +++
 include/linux/ipv6.h                               |   1 +
 include/uapi/linux/ipv6.h                          |   1 +
 net/ipv6/addrconf.c                                |  10 +
 net/ipv6/ndisc.c                                   |  20 +-
 tools/testing/selftests/net/Makefile               |   1 +
 .../selftests/net/ndisc_unsolicited_na_test.sh     | 255 +++++++++++++++++++++
 7 files changed, 314 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/ndisc_unsolicited_na_test.sh

(limited to 'include/linux')

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index b0024aa7b051..433f2e4a5fed 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2467,6 +2467,33 @@ drop_unsolicited_na - BOOLEAN
 
 	By default this is turned off.
 
+accept_unsolicited_na - BOOLEAN
+	Add a new neighbour cache entry in STALE state for routers on receiving an
+	unsolicited neighbour advertisement with target link-layer address option
+	specified. This is as per router-side behavior documented in RFC9131.
+	This has lower precedence than drop_unsolicited_na.
+
+	 ====   ======  ======  ==============================================
+	 drop   accept  fwding                   behaviour
+	 ----   ------  ------  ----------------------------------------------
+	    1        X       X  Drop NA packet and don't pass up the stack
+	    0        0       X  Pass NA packet up the stack, don't update NC
+	    0        1       0  Pass NA packet up the stack, don't update NC
+	    0        1       1  Pass NA packet up the stack, and add a STALE
+	                        NC entry
+	 ====   ======  ======  ==============================================
+
+	This will optimize the return path for the initial off-link communication
+	that is initiated by a directly connected host, by ensuring that
+	the first-hop router which turns on this setting doesn't have to
+	buffer the initial return packets to do neighbour-solicitation.
+	The prerequisite is that the host is configured to send
+	unsolicited neighbour advertisements on interface bringup.
+	This setting should be used in conjunction with the ndisc_notify setting
+	on the host to satisfy this prerequisite.
+
+	By default this is turned off.
+
 enhanced_dad - BOOLEAN
 	Include a nonce option in the IPv6 neighbor solicitation messages used for
 	duplicate address detection per RFC7527. A received DAD NS will only signal
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 16870f86c74d..918bfea4ef5f 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -61,6 +61,7 @@ struct ipv6_devconf {
 	__s32		suppress_frag_ndisc;
 	__s32		accept_ra_mtu;
 	__s32		drop_unsolicited_na;
+	__s32		accept_unsolicited_na;
 	struct ipv6_stable_secret {
 		bool initialized;
 		struct in6_addr secret;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index d4178dace0bf..549ddeaf788b 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -194,6 +194,7 @@ enum {
 	DEVCONF_IOAM6_ID,
 	DEVCONF_IOAM6_ID_WIDE,
 	DEVCONF_NDISC_EVICT_NOCARRIER,
+	DEVCONF_ACCEPT_UNSOLICITED_NA,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1afc4c024981..6473dc84b71d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5587,6 +5587,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_IOAM6_ID] = cnf->ioam6_id;
 	array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide;
 	array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier;
+	array[DEVCONF_ACCEPT_UNSOLICITED_NA] = cnf->accept_unsolicited_na;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -7037,6 +7038,15 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.extra1		= (void *)SYSCTL_ZERO,
 		.extra2		= (void *)SYSCTL_ONE,
 	},
+	{
+		.procname	= "accept_unsolicited_na",
+		.data		= &ipv6_devconf.accept_unsolicited_na,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= (void *)SYSCTL_ZERO,
+		.extra2		= (void *)SYSCTL_ONE,
+	},
 	{
 		/* sentinel */
 	}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index fcb288b0ae13..254addad0dd3 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -979,6 +979,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	struct inet6_ifaddr *ifp;
 	struct neighbour *neigh;
+	bool create_neigh;
 
 	if (skb->len < sizeof(struct nd_msg)) {
 		ND_PRINTK(2, warn, "NA: packet too short\n");
@@ -999,6 +1000,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 	/* For some 802.11 wireless deployments (and possibly other networks),
 	 * there will be a NA proxy and unsolicitd packets are attacks
 	 * and thus should not be accepted.
+	 * drop_unsolicited_na takes precedence over accept_unsolicited_na
 	 */
 	if (!msg->icmph.icmp6_solicited && idev &&
 	    idev->cnf.drop_unsolicited_na)
@@ -1039,7 +1041,23 @@ static void ndisc_recv_na(struct sk_buff *skb)
 		in6_ifa_put(ifp);
 		return;
 	}
-	neigh = neigh_lookup(&nd_tbl, &msg->target, dev);
+	/* RFC 9131 updates original Neighbour Discovery RFC 4861.
+	 * An unsolicited NA can now create a neighbour cache entry
+	 * on routers if it has Target LL Address option.
+	 *
+	 * drop   accept  fwding                   behaviour
+	 * ----   ------  ------  ----------------------------------------------
+	 *    1        X       X  Drop NA packet and don't pass up the stack
+	 *    0        0       X  Pass NA packet up the stack, don't update NC
+	 *    0        1       0  Pass NA packet up the stack, don't update NC
+	 *    0        1       1  Pass NA packet up the stack, and add a STALE
+	 *                          NC entry
+	 * Note that we don't do a (daddr == all-routers-mcast) check.
+	 */
+	create_neigh = !msg->icmph.icmp6_solicited && lladdr &&
+		       idev && idev->cnf.forwarding &&
+		       idev->cnf.accept_unsolicited_na;
+	neigh = __neigh_lookup(&nd_tbl, &msg->target, dev, create_neigh);
 
 	if (neigh) {
 		u8 old_flags = neigh->flags;
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 3fe2515aa616..af7f6e6ff182 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -36,6 +36,7 @@ TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
 TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
 TEST_PROGS += vrf_strict_mode_test.sh
 TEST_PROGS += arp_ndisc_evict_nocarrier.sh
+TEST_PROGS += ndisc_unsolicited_na_test.sh
 TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
 TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh
 TEST_GEN_FILES =  socket nettest
diff --git a/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh b/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
new file mode 100755
index 000000000000..f508657ee126
--- /dev/null
+++ b/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
@@ -0,0 +1,255 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for the accept_unsolicited_na feature to
+# enable RFC9131 behaviour. The following is the test-matrix.
+# drop   accept  fwding                   behaviour
+# ----   ------  ------  ----------------------------------------------
+#    1        X       X  Drop NA packet and don't pass up the stack
+#    0        0       X  Pass NA packet up the stack, don't update NC
+#    0        1       0  Pass NA packet up the stack, don't update NC
+#    0        1       1  Pass NA packet up the stack, and add a STALE
+#                           NC entry
+
+ret=0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+PAUSE_ON_FAIL=no
+PAUSE=no
+
+HOST_NS="ns-host"
+ROUTER_NS="ns-router"
+
+HOST_INTF="veth-host"
+ROUTER_INTF="veth-router"
+
+ROUTER_ADDR="2000:20::1"
+HOST_ADDR="2000:20::2"
+SUBNET_WIDTH=64
+ROUTER_ADDR_WITH_MASK="${ROUTER_ADDR}/${SUBNET_WIDTH}"
+HOST_ADDR_WITH_MASK="${HOST_ADDR}/${SUBNET_WIDTH}"
+
+IP_HOST="ip -6 -netns ${HOST_NS}"
+IP_HOST_EXEC="ip netns exec ${HOST_NS}"
+IP_ROUTER="ip -6 -netns ${ROUTER_NS}"
+IP_ROUTER_EXEC="ip netns exec ${ROUTER_NS}"
+
+tcpdump_stdout=
+tcpdump_stderr=
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		printf "    TEST: %-60s  [ OK ]\n" "${msg}"
+		nsuccess=$((nsuccess+1))
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "    TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+		echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+
+	if [ "${PAUSE}" = "yes" ]; then
+		echo
+		echo "hit enter to continue, 'q' to quit"
+		read a
+		[ "$a" = "q" ] && exit 1
+	fi
+}
+
+setup()
+{
+	set -e
+
+	local drop_unsolicited_na=$1
+	local accept_unsolicited_na=$2
+	local forwarding=$3
+
+	# Setup two namespaces and a veth tunnel across them.
+	# On end of the tunnel is a router and the other end is a host.
+	ip netns add ${HOST_NS}
+	ip netns add ${ROUTER_NS}
+	${IP_ROUTER} link add ${ROUTER_INTF} type veth \
+                peer name ${HOST_INTF} netns ${HOST_NS}
+
+	# Enable IPv6 on both router and host, and configure static addresses.
+	# The router here is the DUT
+	# Setup router configuration as specified by the arguments.
+	# forwarding=0 case is to check that a non-router
+	# doesn't add neighbour entries.
+        ROUTER_CONF=net.ipv6.conf.${ROUTER_INTF}
+	${IP_ROUTER_EXEC} sysctl -qw \
+                ${ROUTER_CONF}.forwarding=${forwarding}
+	${IP_ROUTER_EXEC} sysctl -qw \
+                ${ROUTER_CONF}.drop_unsolicited_na=${drop_unsolicited_na}
+	${IP_ROUTER_EXEC} sysctl -qw \
+                ${ROUTER_CONF}.accept_unsolicited_na=${accept_unsolicited_na}
+	${IP_ROUTER_EXEC} sysctl -qw ${ROUTER_CONF}.disable_ipv6=0
+	${IP_ROUTER} addr add ${ROUTER_ADDR_WITH_MASK} dev ${ROUTER_INTF}
+
+	# Turn on ndisc_notify on host interface so that
+	# the host sends unsolicited NAs.
+	HOST_CONF=net.ipv6.conf.${HOST_INTF}
+	${IP_HOST_EXEC} sysctl -qw ${HOST_CONF}.ndisc_notify=1
+	${IP_HOST_EXEC} sysctl -qw ${HOST_CONF}.disable_ipv6=0
+	${IP_HOST} addr add ${HOST_ADDR_WITH_MASK} dev ${HOST_INTF}
+
+	set +e
+}
+
+start_tcpdump() {
+	set -e
+	tcpdump_stdout=`mktemp`
+	tcpdump_stderr=`mktemp`
+	${IP_ROUTER_EXEC} timeout 15s \
+                tcpdump --immediate-mode -tpni ${ROUTER_INTF} -c 1 \
+                "icmp6 && icmp6[0] == 136 && src ${HOST_ADDR}" \
+                > ${tcpdump_stdout} 2> /dev/null
+	set +e
+}
+
+cleanup_tcpdump()
+{
+	set -e
+	[[ ! -z  ${tcpdump_stdout} ]] && rm -f ${tcpdump_stdout}
+	[[ ! -z  ${tcpdump_stderr} ]] && rm -f ${tcpdump_stderr}
+	tcpdump_stdout=
+	tcpdump_stderr=
+	set +e
+}
+
+cleanup()
+{
+	cleanup_tcpdump
+	ip netns del ${HOST_NS}
+	ip netns del ${ROUTER_NS}
+}
+
+link_up() {
+	set -e
+	${IP_ROUTER} link set dev ${ROUTER_INTF} up
+	${IP_HOST} link set dev ${HOST_INTF} up
+	set +e
+}
+
+verify_ndisc() {
+	local drop_unsolicited_na=$1
+	local accept_unsolicited_na=$2
+	local forwarding=$3
+
+	neigh_show_output=$(${IP_ROUTER} neigh show \
+                to ${HOST_ADDR} dev ${ROUTER_INTF} nud stale)
+	if [ ${drop_unsolicited_na} -eq 0 ] && \
+			[ ${accept_unsolicited_na} -eq 1 ] && \
+			[ ${forwarding} -eq 1 ]; then
+		# Neighbour entry expected to be present for 011 case
+		[[ ${neigh_show_output} ]]
+	else
+		# Neighbour entry expected to be absent for all other cases
+		[[ -z ${neigh_show_output} ]]
+	fi
+}
+
+test_unsolicited_na_common()
+{
+	# Setup the test bed, but keep links down
+	setup $1 $2 $3
+
+	# Bring the link up, wait for the NA,
+	# and add a delay to ensure neighbour processing is done.
+	link_up
+	start_tcpdump
+
+	# Verify the neighbour table
+	verify_ndisc $1 $2 $3
+
+}
+
+test_unsolicited_na_combination() {
+	test_unsolicited_na_common $1 $2 $3
+	test_msg=("test_unsolicited_na: "
+		"drop_unsolicited_na=$1 "
+		"accept_unsolicited_na=$2 "
+		"forwarding=$3")
+	log_test $? 0 "${test_msg[*]}"
+	cleanup
+}
+
+test_unsolicited_na_combinations() {
+	# Args: drop_unsolicited_na accept_unsolicited_na forwarding
+
+	# Expect entry
+	test_unsolicited_na_combination 0 1 1
+
+	# Expect no entry
+	test_unsolicited_na_combination 0 0 0
+	test_unsolicited_na_combination 0 0 1
+	test_unsolicited_na_combination 0 1 0
+	test_unsolicited_na_combination 1 0 0
+	test_unsolicited_na_combination 1 0 1
+	test_unsolicited_na_combination 1 1 0
+	test_unsolicited_na_combination 1 1 1
+}
+
+###############################################################################
+# usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+        -p          Pause on fail
+        -P          Pause after each test before cleanup
+EOF
+}
+
+###############################################################################
+# main
+
+while getopts :pPh o
+do
+	case $o in
+		p) PAUSE_ON_FAIL=yes;;
+		P) PAUSE=yes;;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+# make sure we don't pause twice
+[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit $ksft_skip;
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v tcpdump)" ]; then
+	echo "SKIP: Could not run test without tcpdump tool"
+	exit $ksft_skip
+fi
+
+# start clean
+cleanup &> /dev/null
+
+test_unsolicited_na_combinations
+
+printf "\nTests passed: %3d\n" ${nsuccess}
+printf "Tests failed: %3d\n"   ${nfail}
+
+exit $ret
-- 
cgit v1.2.3


From da40b613f89c43c58986e6f30560ad6573a4d569 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Apr 2022 17:10:41 -0700
Subject: tcp: add drop reason support to tcp_validate_incoming()

Creates four new drop reasons for the following cases:

1) packet being rejected by RFC 7323 PAWS check
2) packet being rejected by SEQUENCE check
3) Invalid RST packet
4) Invalid SYN packet

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 6 ++++++
 include/trace/events/skb.h | 5 +++++
 net/ipv4/tcp_input.c       | 7 ++++++-
 3 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0ef11df1bc67..a903da1fa0ed 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -381,6 +381,12 @@ enum skb_drop_reason {
 					 * the ofo queue, corresponding to
 					 * LINUX_MIB_TCPOFOMERGE
 					 */
+	SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to
+					   * LINUX_MIB_PAWSESTABREJECTED
+					   */
+	SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */
+	SKB_DROP_REASON_TCP_RESET,	/* Invalid RST packet */
+	SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */
 	SKB_DROP_REASON_IP_OUTNOROUTES,	/* route lookup failed */
 	SKB_DROP_REASON_BPF_CGROUP_EGRESS,	/* dropped by
 						 * BPF_PROG_TYPE_CGROUP_SKB
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 2da72a9a5764..820dacd14bad 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -37,6 +37,11 @@
 	EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA)		\
 	EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW)	\
 	EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE)		\
+	EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS)	\
+	EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE,		\
+	   TCP_INVALID_SEQUENCE)				\
+	EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET)		\
+	EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN)	\
 	EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES)	\
 	EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS,			\
 	   BPF_CGROUP_EGRESS)					\
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b2d5fbef6ce3..9a1cb3f48c3f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5667,6 +5667,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 				  const struct tcphdr *th, int syn_inerr)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	SKB_DR(reason);
 
 	/* RFC1323: H1. Apply PAWS check first. */
 	if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) &&
@@ -5678,6 +5679,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 						  LINUX_MIB_TCPACKSKIPPEDPAWS,
 						  &tp->last_oow_ack_time))
 				tcp_send_dupack(sk, skb);
+			SKB_DR_SET(reason, TCP_RFC7323_PAWS);
 			goto discard;
 		}
 		/* Reset is accepted even if it did not pass PAWS. */
@@ -5701,6 +5703,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		} else if (tcp_reset_check(sk, skb)) {
 			goto reset;
 		}
+		SKB_DR_SET(reason, TCP_INVALID_SEQUENCE);
 		goto discard;
 	}
 
@@ -5743,6 +5746,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		    sk->sk_state == TCP_ESTABLISHED)
 			tcp_fastopen_active_disable(sk);
 		tcp_send_challenge_ack(sk);
+		SKB_DR_SET(reason, TCP_RESET);
 		goto discard;
 	}
 
@@ -5757,6 +5761,7 @@ syn_challenge:
 			TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE);
 		tcp_send_challenge_ack(sk);
+		SKB_DR_SET(reason, TCP_INVALID_SYN);
 		goto discard;
 	}
 
@@ -5765,7 +5770,7 @@ syn_challenge:
 	return true;
 
 discard:
-	tcp_drop(sk, skb);
+	tcp_drop_reason(sk, skb, reason);
 	return false;
 
 reset:
-- 
cgit v1.2.3


From 669da7a71890b2b2a31a7e9571c0fdf1123e26ef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Apr 2022 17:10:43 -0700
Subject: tcp: add drop reasons to tcp_rcv_state_process()

Add basic support for drop reasons in tcp_rcv_state_process()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     |  3 +++
 include/trace/events/skb.h |  3 +++
 net/ipv4/tcp_input.c       | 24 +++++++++++++++++-------
 3 files changed, 23 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a903da1fa0ed..6f1410b5ff13 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -387,6 +387,9 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */
 	SKB_DROP_REASON_TCP_RESET,	/* Invalid RST packet */
 	SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */
+	SKB_DROP_REASON_TCP_CLOSE,	/* TCP socket in CLOSE state */
+	SKB_DROP_REASON_TCP_FASTOPEN,	/* dropped by FASTOPEN request socket */
+	SKB_DROP_REASON_TCP_OLD_ACK,	/* TCP ACK is old, but in window */
 	SKB_DROP_REASON_IP_OUTNOROUTES,	/* route lookup failed */
 	SKB_DROP_REASON_BPF_CGROUP_EGRESS,	/* dropped by
 						 * BPF_PROG_TYPE_CGROUP_SKB
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 820dacd14bad..fbe21ad038bc 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -42,6 +42,9 @@
 	   TCP_INVALID_SEQUENCE)				\
 	EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET)		\
 	EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN)	\
+	EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE)		\
+	EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN)		\
+	EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK)		\
 	EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES)	\
 	EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS,			\
 	   BPF_CGROUP_EGRESS)					\
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f95a8368981d..85fae79c894d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6413,21 +6413,26 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	struct request_sock *req;
 	int queued = 0;
 	bool acceptable;
+	SKB_DR(reason);
 
 	switch (sk->sk_state) {
 	case TCP_CLOSE:
+		SKB_DR_SET(reason, TCP_CLOSE);
 		goto discard;
 
 	case TCP_LISTEN:
 		if (th->ack)
 			return 1;
 
-		if (th->rst)
+		if (th->rst) {
+			SKB_DR_SET(reason, TCP_RESET);
 			goto discard;
-
+		}
 		if (th->syn) {
-			if (th->fin)
+			if (th->fin) {
+				SKB_DR_SET(reason, TCP_FLAGS);
 				goto discard;
+			}
 			/* It is possible that we process SYN packets from backlog,
 			 * so we need to make sure to disable BH and RCU right there.
 			 */
@@ -6442,6 +6447,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			consume_skb(skb);
 			return 0;
 		}
+		SKB_DR_SET(reason, TCP_FLAGS);
 		goto discard;
 
 	case TCP_SYN_SENT:
@@ -6468,13 +6474,16 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
 		    sk->sk_state != TCP_FIN_WAIT1);
 
-		if (!tcp_check_req(sk, skb, req, true, &req_stolen))
+		if (!tcp_check_req(sk, skb, req, true, &req_stolen)) {
+			SKB_DR_SET(reason, TCP_FASTOPEN);
 			goto discard;
+		}
 	}
 
-	if (!th->ack && !th->rst && !th->syn)
+	if (!th->ack && !th->rst && !th->syn) {
+		SKB_DR_SET(reason, TCP_FLAGS);
 		goto discard;
-
+	}
 	if (!tcp_validate_incoming(sk, skb, th, 0))
 		return 0;
 
@@ -6487,6 +6496,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (sk->sk_state == TCP_SYN_RECV)
 			return 1;	/* send one RST */
 		tcp_send_challenge_ack(sk);
+		SKB_DR_SET(reason, TCP_OLD_ACK);
 		goto discard;
 	}
 	switch (sk->sk_state) {
@@ -6647,7 +6657,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 	if (!queued) {
 discard:
-		tcp_drop(sk, skb);
+		tcp_drop_reason(sk, skb, reason);
 	}
 	return 0;
 
-- 
cgit v1.2.3


From 4b506af9c5b8de0da34097d50d9448dfb33d70c3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Apr 2022 17:10:44 -0700
Subject: tcp: add two drop reasons for tcp_ack()

Add TCP_TOO_OLD_ACK and TCP_ACK_UNSENT_DATA drop
reasons so that tcp_rcv_established() can report
them.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 2 ++
 include/trace/events/skb.h | 3 +++
 net/ipv4/tcp_input.c       | 7 ++++---
 3 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6f1410b5ff13..9ff5557b1909 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -390,6 +390,8 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_TCP_CLOSE,	/* TCP socket in CLOSE state */
 	SKB_DROP_REASON_TCP_FASTOPEN,	/* dropped by FASTOPEN request socket */
 	SKB_DROP_REASON_TCP_OLD_ACK,	/* TCP ACK is old, but in window */
+	SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */
+	SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */
 	SKB_DROP_REASON_IP_OUTNOROUTES,	/* route lookup failed */
 	SKB_DROP_REASON_BPF_CGROUP_EGRESS,	/* dropped by
 						 * BPF_PROG_TYPE_CGROUP_SKB
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index fbe21ad038bc..eab0b09223f3 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -45,6 +45,9 @@
 	EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE)		\
 	EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN)		\
 	EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK)		\
+	EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK)	\
+	EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA,			\
+	   TCP_ACK_UNSENT_DATA)					\
 	EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES)	\
 	EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS,			\
 	   BPF_CGROUP_EGRESS)					\
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 85fae79c894d..8a68785b0405 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3766,7 +3766,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		if (before(ack, prior_snd_una - tp->max_window)) {
 			if (!(flag & FLAG_NO_CHALLENGE_ACK))
 				tcp_send_challenge_ack(sk);
-			return -1;
+			return -SKB_DROP_REASON_TCP_TOO_OLD_ACK;
 		}
 		goto old_ack;
 	}
@@ -3775,7 +3775,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	 * this segment (RFC793 Section 3.9).
 	 */
 	if (after(ack, tp->snd_nxt))
-		return -1;
+		return -SKB_DROP_REASON_TCP_ACK_UNSENT_DATA;
 
 	if (after(ack, prior_snd_una)) {
 		flag |= FLAG_SND_UNA_ADVANCED;
@@ -5962,7 +5962,8 @@ slow_path:
 		return;
 
 step5:
-	if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0)
+	reason = tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT);
+	if (reason < 0)
 		goto discard;
 
 	tcp_rcv_rtt_measure_ts(sk, skb);
-- 
cgit v1.2.3


From e7c89ae4078eab24af71ba26b91642e819a4bd7f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Apr 2022 17:10:45 -0700
Subject: tcp: add drop reason support to tcp_prune_ofo_queue()

Add one reason for packets dropped from OFO queue because
of memory pressure.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 1 +
 include/trace/events/skb.h | 2 ++
 net/ipv4/tcp_input.c       | 3 ++-
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9ff5557b1909..ad15ad208b56 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -392,6 +392,7 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_TCP_OLD_ACK,	/* TCP ACK is old, but in window */
 	SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */
 	SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */
+	SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */
 	SKB_DROP_REASON_IP_OUTNOROUTES,	/* route lookup failed */
 	SKB_DROP_REASON_BPF_CGROUP_EGRESS,	/* dropped by
 						 * BPF_PROG_TYPE_CGROUP_SKB
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index eab0b09223f3..73d7a6e594cb 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -48,6 +48,8 @@
 	EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK)	\
 	EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA,			\
 	   TCP_ACK_UNSENT_DATA)					\
+	EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE,			\
+	  TCP_OFO_QUEUE_PRUNE)					\
 	EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES)	\
 	EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS,			\
 	   BPF_CGROUP_EGRESS)					\
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8a68785b0405..a1077adeb1b6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5334,7 +5334,8 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
 		goal -= rb_to_skb(node)->truesize;
-		tcp_drop(sk, rb_to_skb(node));
+		tcp_drop_reason(sk, rb_to_skb(node),
+				SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE);
 		if (!prev || goal <= 0) {
 			sk_mem_reclaim(sk);
 			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
-- 
cgit v1.2.3


From 8fbf195798b56e1e87f62d01be636a6425c304c2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Apr 2022 17:10:48 -0700
Subject: tcp: add drop reason support to tcp_ofo_queue()

packets in OFO queue might be redundant, and dropped.

tcp_drop() is no longer needed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 1 +
 include/trace/events/skb.h | 1 +
 net/ipv4/tcp_input.c       | 9 ++-------
 3 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ad15ad208b56..84d78df60453 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -393,6 +393,7 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */
 	SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */
 	SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */
+	SKB_DROP_REASON_TCP_OFO_DROP,	/* data already in receive queue */
 	SKB_DROP_REASON_IP_OUTNOROUTES,	/* route lookup failed */
 	SKB_DROP_REASON_BPF_CGROUP_EGRESS,	/* dropped by
 						 * BPF_PROG_TYPE_CGROUP_SKB
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 73d7a6e594cb..a477bf907498 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -37,6 +37,7 @@
 	EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA)		\
 	EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW)	\
 	EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE)		\
+	EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP)		\
 	EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS)	\
 	EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE,		\
 	   TCP_INVALID_SEQUENCE)				\
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 339cc3d40745..cf2dc19bb8c7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4674,7 +4674,7 @@ static bool tcp_ooo_try_coalesce(struct sock *sk,
 {
 	bool res = tcp_try_coalesce(sk, to, from, fragstolen);
 
-	/* In case tcp_drop() is called later, update to->gso_segs */
+	/* In case tcp_drop_reason() is called later, update to->gso_segs */
 	if (res) {
 		u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
 			       max_t(u16, 1, skb_shinfo(from)->gso_segs);
@@ -4691,11 +4691,6 @@ static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb,
 	kfree_skb_reason(skb, reason);
 }
 
-static void tcp_drop(struct sock *sk, struct sk_buff *skb)
-{
-	tcp_drop_reason(sk, skb, SKB_DROP_REASON_NOT_SPECIFIED);
-}
-
 /* This one checks to see if we can put data from the
  * out_of_order queue into the receive_queue.
  */
@@ -4723,7 +4718,7 @@ static void tcp_ofo_queue(struct sock *sk)
 		rb_erase(&skb->rbnode, &tp->out_of_order_queue);
 
 		if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
-			tcp_drop(sk, skb);
+			tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_DROP);
 			continue;
 		}
 
-- 
cgit v1.2.3


From 0df71650c051ab106c921de257f4b38e9e3dd251 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@kernel.org>
Date: Thu, 24 Mar 2022 16:35:24 -0400
Subject: block: allow using the per-cpu bio cache from bio_alloc_bioset

Replace the BIO_PERCPU_CACHE bio-internal flag with a REQ_ALLOC_CACHE
one that can be passed to bio_alloc / bio_alloc_bioset, and implement
the percpu cache allocation logic in a helper called from
bio_alloc_bioset.  This allows any bio_alloc_bioset user to use the
percpu caches instead of having the functionality tied to struct kiocb.

Signed-off-by: Mike Snitzer <snitzer@kernel.org>
[hch: refactored a bit]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220324203526.62306-2-snitzer@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c               | 86 ++++++++++++++++++++++-------------------------
 block/blk.h               |  3 +-
 block/fops.c              | 11 ++++--
 include/linux/bio.h       |  2 --
 include/linux/blk_types.h |  3 +-
 5 files changed, 52 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index 4259125e16ab..c67f47c6cc8c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -419,6 +419,28 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 	queue_work(bs->rescue_workqueue, &bs->rescue_work);
 }
 
+static struct bio *bio_alloc_percpu_cache(struct block_device *bdev,
+		unsigned short nr_vecs, unsigned int opf, gfp_t gfp,
+		struct bio_set *bs)
+{
+	struct bio_alloc_cache *cache;
+	struct bio *bio;
+
+	cache = per_cpu_ptr(bs->cache, get_cpu());
+	if (!cache->free_list) {
+		put_cpu();
+		return NULL;
+	}
+	bio = cache->free_list;
+	cache->free_list = bio->bi_next;
+	cache->nr--;
+	put_cpu();
+
+	bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs, opf);
+	bio->bi_pool = bs;
+	return bio;
+}
+
 /**
  * bio_alloc_bioset - allocate a bio for I/O
  * @bdev:	block device to allocate the bio for (can be %NULL)
@@ -451,6 +473,9 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
  * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad
  * for per bio allocations.
  *
+ * If REQ_ALLOC_CACHE is set, the final put of the bio MUST be done from process
+ * context, not hard/soft IRQ.
+ *
  * Returns: Pointer to new bio on success, NULL on failure.
  */
 struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
@@ -465,6 +490,21 @@ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
 	if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0))
 		return NULL;
 
+	if (opf & REQ_ALLOC_CACHE) {
+		if (bs->cache && nr_vecs <= BIO_INLINE_VECS) {
+			bio = bio_alloc_percpu_cache(bdev, nr_vecs, opf,
+						     gfp_mask, bs);
+			if (bio)
+				return bio;
+			/*
+			 * No cached bio available, bio returned below marked with
+			 * REQ_ALLOC_CACHE to particpate in per-cpu alloc cache.
+			 */
+		} else {
+			opf &= ~REQ_ALLOC_CACHE;
+		}
+	}
+
 	/*
 	 * submit_bio_noacct() converts recursion to iteration; this means if
 	 * we're running beneath it, any bios we allocate and submit will not be
@@ -711,7 +751,7 @@ void bio_put(struct bio *bio)
 			return;
 	}
 
-	if (bio_flagged(bio, BIO_PERCPU_CACHE)) {
+	if (bio->bi_opf & REQ_ALLOC_CACHE) {
 		struct bio_alloc_cache *cache;
 
 		bio_uninit(bio);
@@ -1732,50 +1772,6 @@ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src)
 }
 EXPORT_SYMBOL(bioset_init_from_src);
 
-/**
- * bio_alloc_kiocb - Allocate a bio from bio_set based on kiocb
- * @kiocb:	kiocb describing the IO
- * @bdev:	block device to allocate the bio for (can be %NULL)
- * @nr_vecs:	number of iovecs to pre-allocate
- * @opf:	operation and flags for bio
- * @bs:		bio_set to allocate from
- *
- * Description:
- *    Like @bio_alloc_bioset, but pass in the kiocb. The kiocb is only
- *    used to check if we should dip into the per-cpu bio_set allocation
- *    cache. The allocation uses GFP_KERNEL internally. On return, the
- *    bio is marked BIO_PERCPU_CACHEABLE, and the final put of the bio
- *    MUST be done from process context, not hard/soft IRQ.
- *
- */
-struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev,
-		unsigned short nr_vecs, unsigned int opf, struct bio_set *bs)
-{
-	struct bio_alloc_cache *cache;
-	struct bio *bio;
-
-	if (!(kiocb->ki_flags & IOCB_ALLOC_CACHE) || nr_vecs > BIO_INLINE_VECS)
-		return bio_alloc_bioset(bdev, nr_vecs, opf, GFP_KERNEL, bs);
-
-	cache = per_cpu_ptr(bs->cache, get_cpu());
-	if (cache->free_list) {
-		bio = cache->free_list;
-		cache->free_list = bio->bi_next;
-		cache->nr--;
-		put_cpu();
-		bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL,
-			 nr_vecs, opf);
-		bio->bi_pool = bs;
-		bio_set_flag(bio, BIO_PERCPU_CACHE);
-		return bio;
-	}
-	put_cpu();
-	bio = bio_alloc_bioset(bdev, nr_vecs, opf, GFP_KERNEL, bs);
-	bio_set_flag(bio, BIO_PERCPU_CACHE);
-	return bio;
-}
-EXPORT_SYMBOL_GPL(bio_alloc_kiocb);
-
 static int __init init_bio(void)
 {
 	int i;
diff --git a/block/blk.h b/block/blk.h
index 8ccbc6e07636..0d33e4ca2c52 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -453,8 +453,7 @@ extern struct device_attribute dev_attr_events_poll_msecs;
 static inline void bio_clear_polled(struct bio *bio)
 {
 	/* can't support alloc cache if we turn off polling */
-	bio_clear_flag(bio, BIO_PERCPU_CACHE);
-	bio->bi_opf &= ~REQ_POLLED;
+	bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE);
 }
 
 long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
diff --git a/block/fops.c b/block/fops.c
index 9f2ecec406b0..ba5e7d5ff9a5 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -197,8 +197,10 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	    (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
-	bio = bio_alloc_kiocb(iocb, bdev, nr_pages, opf, &blkdev_dio_pool);
-
+	if (iocb->ki_flags & IOCB_ALLOC_CACHE)
+		opf |= REQ_ALLOC_CACHE;
+	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
+			       &blkdev_dio_pool);
 	dio = container_of(bio, struct blkdev_dio, bio);
 	atomic_set(&dio->ref, 1);
 	/*
@@ -320,7 +322,10 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	    (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
-	bio = bio_alloc_kiocb(iocb, bdev, nr_pages, opf, &blkdev_dio_pool);
+	if (iocb->ki_flags & IOCB_ALLOC_CACHE)
+		opf |= REQ_ALLOC_CACHE;
+	bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL,
+			       &blkdev_dio_pool);
 	dio = container_of(bio, struct blkdev_dio, bio);
 	dio->flags = 0;
 	dio->iocb = iocb;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 278cc81cc1e7..0fe8a51a0778 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -405,8 +405,6 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src);
 struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
 			     unsigned int opf, gfp_t gfp_mask,
 			     struct bio_set *bs);
-struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev,
-		unsigned short nr_vecs, unsigned int opf, struct bio_set *bs);
 struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs);
 extern void bio_put(struct bio *);
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 1973ef9bd40f..4968cb17b13b 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -329,7 +329,6 @@ enum {
 	BIO_QOS_MERGED,		/* but went through rq_qos merge path */
 	BIO_REMAPPED,
 	BIO_ZONE_WRITE_LOCKED,	/* Owns a zoned device zone write lock */
-	BIO_PERCPU_CACHE,	/* can participate in per-cpu alloc cache */
 	BIO_FLAG_LAST
 };
 
@@ -414,6 +413,7 @@ enum req_flag_bits {
 	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
 
 	__REQ_POLLED,		/* caller polls for completion using bio_poll */
+	__REQ_ALLOC_CACHE,	/* allocate IO from cache if available */
 
 	/* for driver use */
 	__REQ_DRV,
@@ -439,6 +439,7 @@ enum req_flag_bits {
 
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
 #define REQ_POLLED		(1ULL << __REQ_POLLED)
+#define REQ_ALLOC_CACHE		(1ULL << __REQ_ALLOC_CACHE)
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
 #define REQ_SWAP		(1ULL << __REQ_SWAP)
-- 
cgit v1.2.3


From b53f3dcd705e52a07bd0311870dbfb6842e88c91 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@kernel.org>
Date: Thu, 24 Mar 2022 16:35:25 -0400
Subject: block: allow use of per-cpu bio alloc cache by block drivers

Refine per-cpu bio alloc cache interfaces so that DM and other block
drivers can properly create and use the cache:

DM uses bioset_init_from_src() to do its final bioset initialization,
so must update bioset_init_from_src() to set BIOSET_PERCPU_CACHE if
%src bioset has a cache.

Also move bio_clear_polled() to include/linux/bio.h to allow users
outside of block core.

Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220324203526.62306-3-snitzer@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c         | 2 ++
 block/blk.h         | 6 ------
 include/linux/bio.h | 6 ++++++
 3 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index c67f47c6cc8c..643a3a052c7e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1767,6 +1767,8 @@ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src)
 		flags |= BIOSET_NEED_BVECS;
 	if (src->rescue_workqueue)
 		flags |= BIOSET_NEED_RESCUER;
+	if (src->cache)
+		flags |= BIOSET_PERCPU_CACHE;
 
 	return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags);
 }
diff --git a/block/blk.h b/block/blk.h
index 0d33e4ca2c52..4ea5167dc339 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -450,12 +450,6 @@ extern struct device_attribute dev_attr_events;
 extern struct device_attribute dev_attr_events_async;
 extern struct device_attribute dev_attr_events_poll_msecs;
 
-static inline void bio_clear_polled(struct bio *bio)
-{
-	/* can't support alloc cache if we turn off polling */
-	bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE);
-}
-
 long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 0fe8a51a0778..8e87f3065042 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -780,6 +780,12 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 		bio->bi_opf |= REQ_NOWAIT;
 }
 
+static inline void bio_clear_polled(struct bio *bio)
+{
+	/* can't support alloc cache if we turn off polling */
+	bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE);
+}
+
 struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
 		unsigned int nr_pages, unsigned int opf, gfp_t gfp);
 
-- 
cgit v1.2.3


From 066ff571011d8416e903d3d4f1f41e0b5eb91e1d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 6 Apr 2022 08:12:27 +0200
Subject: block: turn bio_kmalloc into a simple kmalloc wrapper

Remove the magic autofree semantics and require the callers to explicitly
call bio_init to initialize the bio.

This allows bio_free to catch accidental bio_put calls on bio_init()ed
bios as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Coly Li <colyli@suse.de>
Acked-by: Mike Snitzer <snitzer@kernel.org>
Link: https://lore.kernel.org/r/20220406061228.410163-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                        | 47 +++++++++++++++-----------------------
 block/blk-crypto-fallback.c        | 14 +++++++-----
 block/blk-map.c                    | 42 ++++++++++++++++++++++------------
 drivers/block/pktcdvd.c            | 25 ++++++++++----------
 drivers/md/bcache/debug.c          | 10 ++++----
 drivers/md/dm-bufio.c              |  9 ++++----
 drivers/md/raid1.c                 | 12 ++++++----
 drivers/md/raid10.c                | 21 +++++++++++------
 drivers/target/target_core_pscsi.c | 10 ++++----
 fs/squashfs/block.c                | 15 ++++++------
 include/linux/bio.h                |  2 +-
 11 files changed, 112 insertions(+), 95 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index 643a3a052c7e..212ccd5b5212 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -224,24 +224,13 @@ EXPORT_SYMBOL(bio_uninit);
 static void bio_free(struct bio *bio)
 {
 	struct bio_set *bs = bio->bi_pool;
-	void *p;
-
-	bio_uninit(bio);
+	void *p = bio;
 
-	if (bs) {
-		bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs);
+	WARN_ON_ONCE(!bs);
 
-		/*
-		 * If we have front padding, adjust the bio pointer before freeing
-		 */
-		p = bio;
-		p -= bs->front_pad;
-
-		mempool_free(p, &bs->bio_pool);
-	} else {
-		/* Bio was allocated by bio_kmalloc() */
-		kfree(bio);
-	}
+	bio_uninit(bio);
+	bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs);
+	mempool_free(p - bs->front_pad, &bs->bio_pool);
 }
 
 /*
@@ -568,28 +557,28 @@ err_free:
 EXPORT_SYMBOL(bio_alloc_bioset);
 
 /**
- * bio_kmalloc - kmalloc a bio for I/O
+ * bio_kmalloc - kmalloc a bio
+ * @nr_vecs:	number of bio_vecs to allocate
  * @gfp_mask:   the GFP_* mask given to the slab allocator
- * @nr_iovecs:	number of iovecs to pre-allocate
  *
- * Use kmalloc to allocate and initialize a bio.
+ * Use kmalloc to allocate a bio (including bvecs).  The bio must be initialized
+ * using bio_init() before use.  To free a bio returned from this function use
+ * kfree() after calling bio_uninit().  A bio returned from this function can
+ * be reused by calling bio_uninit() before calling bio_init() again.
+ *
+ * Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this
+ * function are not backed by a mempool can can fail.  Do not use this function
+ * for allocations in the file system I/O path.
  *
  * Returns: Pointer to new bio on success, NULL on failure.
  */
-struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs)
+struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask)
 {
 	struct bio *bio;
 
-	if (nr_iovecs > UIO_MAXIOV)
+	if (nr_vecs > UIO_MAXIOV)
 		return NULL;
-
-	bio = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask);
-	if (unlikely(!bio))
-		return NULL;
-	bio_init(bio, NULL, nr_iovecs ? bio->bi_inline_vecs : NULL, nr_iovecs,
-		 0);
-	bio->bi_pool = NULL;
-	return bio;
+	return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask);
 }
 EXPORT_SYMBOL(bio_kmalloc);
 
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index 7c854584b52b..5d1aa5b1d30a 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -152,23 +152,25 @@ static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio)
 
 	src_bio->bi_status = enc_bio->bi_status;
 
-	bio_put(enc_bio);
+	bio_uninit(enc_bio);
+	kfree(enc_bio);
 	bio_endio(src_bio);
 }
 
 static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src)
 {
+	unsigned int nr_segs = bio_segments(bio_src);
 	struct bvec_iter iter;
 	struct bio_vec bv;
 	struct bio *bio;
 
-	bio = bio_kmalloc(GFP_NOIO, bio_segments(bio_src));
+	bio = bio_kmalloc(nr_segs, GFP_NOIO);
 	if (!bio)
 		return NULL;
-	bio->bi_bdev		= bio_src->bi_bdev;
+	bio_init(bio, bio_src->bi_bdev, bio->bi_inline_vecs, nr_segs,
+		 bio_src->bi_opf);
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
-	bio->bi_opf		= bio_src->bi_opf;
 	bio->bi_ioprio		= bio_src->bi_ioprio;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
@@ -363,8 +365,8 @@ out_release_keyslot:
 	blk_crypto_put_keyslot(slot);
 out_put_enc_bio:
 	if (enc_bio)
-		bio_put(enc_bio);
-
+		bio_uninit(enc_bio);
+	kfree(enc_bio);
 	return ret;
 }
 
diff --git a/block/blk-map.c b/block/blk-map.c
index c7f71d83eff1..7ffde64f9019 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -152,10 +152,10 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 	nr_pages = bio_max_segs(DIV_ROUND_UP(offset + len, PAGE_SIZE));
 
 	ret = -ENOMEM;
-	bio = bio_kmalloc(gfp_mask, nr_pages);
+	bio = bio_kmalloc(nr_pages, gfp_mask);
 	if (!bio)
 		goto out_bmd;
-	bio->bi_opf |= req_op(rq);
+	bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, req_op(rq));
 
 	if (map_data) {
 		nr_pages = 1 << map_data->page_order;
@@ -224,7 +224,8 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 cleanup:
 	if (!map_data)
 		bio_free_pages(bio);
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 out_bmd:
 	kfree(bmd);
 	return ret;
@@ -234,6 +235,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 		gfp_t gfp_mask)
 {
 	unsigned int max_sectors = queue_max_hw_sectors(rq->q);
+	unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS);
 	struct bio *bio;
 	int ret;
 	int j;
@@ -241,10 +243,10 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 	if (!iov_iter_count(iter))
 		return -EINVAL;
 
-	bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_VECS));
+	bio = bio_kmalloc(nr_vecs, gfp_mask);
 	if (!bio)
 		return -ENOMEM;
-	bio->bi_opf |= req_op(rq);
+	bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq));
 
 	while (iov_iter_count(iter)) {
 		struct page **pages;
@@ -303,7 +305,8 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 
  out_unmap:
 	bio_release_pages(bio, false);
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 	return ret;
 }
 
@@ -323,7 +326,8 @@ static void bio_invalidate_vmalloc_pages(struct bio *bio)
 static void bio_map_kern_endio(struct bio *bio)
 {
 	bio_invalidate_vmalloc_pages(bio);
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 }
 
 /**
@@ -348,9 +352,10 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data,
 	int offset, i;
 	struct bio *bio;
 
-	bio = bio_kmalloc(gfp_mask, nr_pages);
+	bio = bio_kmalloc(nr_pages, gfp_mask);
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
+	bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0);
 
 	if (is_vmalloc) {
 		flush_kernel_vmap_range(data, len);
@@ -374,7 +379,8 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data,
 		if (bio_add_pc_page(q, bio, page, bytes,
 				    offset) < bytes) {
 			/* we don't support partial mappings */
-			bio_put(bio);
+			bio_uninit(bio);
+			kfree(bio);
 			return ERR_PTR(-EINVAL);
 		}
 
@@ -390,7 +396,8 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data,
 static void bio_copy_kern_endio(struct bio *bio)
 {
 	bio_free_pages(bio);
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 }
 
 static void bio_copy_kern_endio_read(struct bio *bio)
@@ -435,9 +442,10 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data,
 		return ERR_PTR(-EINVAL);
 
 	nr_pages = end - start;
-	bio = bio_kmalloc(gfp_mask, nr_pages);
+	bio = bio_kmalloc(nr_pages, gfp_mask);
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
+	bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0);
 
 	while (len) {
 		struct page *page;
@@ -471,7 +479,8 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data,
 
 cleanup:
 	bio_free_pages(bio);
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -602,7 +611,8 @@ int blk_rq_unmap_user(struct bio *bio)
 
 		next_bio = bio;
 		bio = bio->bi_next;
-		bio_put(next_bio);
+		bio_uninit(next_bio);
+		kfree(next_bio);
 	}
 
 	return ret;
@@ -648,8 +658,10 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	bio->bi_opf |= req_op(rq);
 
 	ret = blk_rq_append_bio(rq, bio);
-	if (unlikely(ret))
-		bio_put(bio);
+	if (unlikely(ret)) {
+		bio_uninit(bio);
+		kfree(bio);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(blk_rq_map_kern);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 86c8794ede41..4a5b8730133c 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -522,9 +522,10 @@ static struct packet_data *pkt_alloc_packet_data(int frames)
 		goto no_pkt;
 
 	pkt->frames = frames;
-	pkt->w_bio = bio_kmalloc(GFP_KERNEL, frames);
+	pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL);
 	if (!pkt->w_bio)
 		goto no_bio;
+	bio_init(pkt->w_bio, NULL, pkt->w_bio->bi_inline_vecs, frames, 0);
 
 	for (i = 0; i < frames / FRAMES_PER_PAGE; i++) {
 		pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
@@ -536,10 +537,10 @@ static struct packet_data *pkt_alloc_packet_data(int frames)
 	bio_list_init(&pkt->orig_bios);
 
 	for (i = 0; i < frames; i++) {
-		struct bio *bio = bio_kmalloc(GFP_KERNEL, 1);
+		struct bio *bio = bio_kmalloc(1, GFP_KERNEL);
 		if (!bio)
 			goto no_rd_bio;
-
+		bio_init(bio, NULL, bio->bi_inline_vecs, 1, 0);
 		pkt->r_bios[i] = bio;
 	}
 
@@ -547,16 +548,16 @@ static struct packet_data *pkt_alloc_packet_data(int frames)
 
 no_rd_bio:
 	for (i = 0; i < frames; i++) {
-		struct bio *bio = pkt->r_bios[i];
-		if (bio)
-			bio_put(bio);
+		if (pkt->r_bios[i])
+			bio_uninit(pkt->r_bios[i]);
+		kfree(pkt->r_bios[i]);
 	}
-
 no_page:
 	for (i = 0; i < frames / FRAMES_PER_PAGE; i++)
 		if (pkt->pages[i])
 			__free_page(pkt->pages[i]);
-	bio_put(pkt->w_bio);
+	bio_uninit(pkt->w_bio);
+	kfree(pkt->w_bio);
 no_bio:
 	kfree(pkt);
 no_pkt:
@@ -571,13 +572,13 @@ static void pkt_free_packet_data(struct packet_data *pkt)
 	int i;
 
 	for (i = 0; i < pkt->frames; i++) {
-		struct bio *bio = pkt->r_bios[i];
-		if (bio)
-			bio_put(bio);
+		bio_uninit(pkt->r_bios[i]);
+		kfree(pkt->r_bios[i]);
 	}
 	for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++)
 		__free_page(pkt->pages[i]);
-	bio_put(pkt->w_bio);
+	bio_uninit(pkt->w_bio);
+	kfree(pkt->w_bio);
 	kfree(pkt);
 }
 
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 6230dfdd9286..7510d1c983a5 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -107,15 +107,16 @@ void bch_btree_verify(struct btree *b)
 
 void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 {
+	unsigned int nr_segs = bio_segments(bio);
 	struct bio *check;
 	struct bio_vec bv, cbv;
 	struct bvec_iter iter, citer = { 0 };
 
-	check = bio_kmalloc(GFP_NOIO, bio_segments(bio));
+	check = bio_kmalloc(nr_segs, GFP_NOIO);
 	if (!check)
 		return;
-	bio_set_dev(check, bio->bi_bdev);
-	check->bi_opf = REQ_OP_READ;
+	bio_init(check, bio->bi_bdev, check->bi_inline_vecs, nr_segs,
+		 REQ_OP_READ);
 	check->bi_iter.bi_sector = bio->bi_iter.bi_sector;
 	check->bi_iter.bi_size = bio->bi_iter.bi_size;
 
@@ -146,7 +147,8 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 
 	bio_free_pages(check);
 out_put:
-	bio_put(check);
+	bio_uninit(check);
+	kfree(check);
 }
 
 #endif
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index e9cbc70d5a0e..5ffa1dcf84cf 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -611,7 +611,8 @@ static void bio_complete(struct bio *bio)
 {
 	struct dm_buffer *b = bio->bi_private;
 	blk_status_t status = bio->bi_status;
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 	b->end_io(b, status);
 }
 
@@ -626,16 +627,14 @@ static void use_bio(struct dm_buffer *b, int rw, sector_t sector,
 	if (unlikely(b->c->sectors_per_block_bits < PAGE_SHIFT - SECTOR_SHIFT))
 		vec_size += 2;
 
-	bio = bio_kmalloc(GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN, vec_size);
+	bio = bio_kmalloc(vec_size, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN);
 	if (!bio) {
 dmio:
 		use_dmio(b, rw, sector, n_sectors, offset);
 		return;
 	}
-
+	bio_init(bio, b->c->bdev, bio->bi_inline_vecs, vec_size, rw);
 	bio->bi_iter.bi_sector = sector;
-	bio_set_dev(bio, b->c->bdev);
-	bio_set_op_attrs(bio, rw, 0);
 	bio->bi_end_io = bio_complete;
 	bio->bi_private = b;
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 99d5464a51f8..d785c3169426 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -165,9 +165,10 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * Allocate bios : 1 for reading, n-1 for writing
 	 */
 	for (j = pi->raid_disks ; j-- ; ) {
-		bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
+		bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
 		if (!bio)
 			goto out_free_bio;
+		bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0);
 		r1_bio->bios[j] = bio;
 	}
 	/*
@@ -206,8 +207,10 @@ out_free_pages:
 		resync_free_pages(&rps[j]);
 
 out_free_bio:
-	while (++j < pi->raid_disks)
-		bio_put(r1_bio->bios[j]);
+	while (++j < pi->raid_disks) {
+		bio_uninit(r1_bio->bios[j]);
+		kfree(r1_bio->bios[j]);
+	}
 	kfree(rps);
 
 out_free_r1bio:
@@ -225,7 +228,8 @@ static void r1buf_pool_free(void *__r1_bio, void *data)
 	for (i = pi->raid_disks; i--; ) {
 		rp = get_resync_pages(r1bio->bios[i]);
 		resync_free_pages(rp);
-		bio_put(r1bio->bios[i]);
+		bio_uninit(r1bio->bios[i]);
+		kfree(r1bio->bios[i]);
 	}
 
 	/* resync pages array stored in the 1st bio's .bi_private */
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index dfe7d62d3fbd..ee2438c0e55e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -145,15 +145,17 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * Allocate bios.
 	 */
 	for (j = nalloc ; j-- ; ) {
-		bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
+		bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
 		if (!bio)
 			goto out_free_bio;
+		bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0);
 		r10_bio->devs[j].bio = bio;
 		if (!conf->have_replacement)
 			continue;
-		bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
+		bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
 		if (!bio)
 			goto out_free_bio;
+		bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0);
 		r10_bio->devs[j].repl_bio = bio;
 	}
 	/*
@@ -197,9 +199,11 @@ out_free_pages:
 out_free_bio:
 	for ( ; j < nalloc; j++) {
 		if (r10_bio->devs[j].bio)
-			bio_put(r10_bio->devs[j].bio);
+			bio_uninit(r10_bio->devs[j].bio);
+		kfree(r10_bio->devs[j].bio);
 		if (r10_bio->devs[j].repl_bio)
-			bio_put(r10_bio->devs[j].repl_bio);
+			bio_uninit(r10_bio->devs[j].repl_bio);
+		kfree(r10_bio->devs[j].repl_bio);
 	}
 	kfree(rps);
 out_free_r10bio:
@@ -220,12 +224,15 @@ static void r10buf_pool_free(void *__r10_bio, void *data)
 		if (bio) {
 			rp = get_resync_pages(bio);
 			resync_free_pages(rp);
-			bio_put(bio);
+			bio_uninit(bio);
+			kfree(bio);
 		}
 
 		bio = r10bio->devs[j].repl_bio;
-		if (bio)
-			bio_put(bio);
+		if (bio) {
+			bio_uninit(bio);
+			kfree(bio);
+		}
 	}
 
 	/* resync pages array stored in the 1st bio's .bi_private */
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 77bd3af4b2bf..dc3007a13357 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -818,7 +818,8 @@ static ssize_t pscsi_show_configfs_dev_params(struct se_device *dev, char *b)
 
 static void pscsi_bi_endio(struct bio *bio)
 {
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 }
 
 static sense_reason_t
@@ -861,14 +862,13 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 			if (!bio) {
 new_bio:
 				nr_vecs = bio_max_segs(nr_pages);
-				bio = bio_kmalloc(GFP_KERNEL, nr_vecs);
+				bio = bio_kmalloc(nr_vecs, GFP_KERNEL);
 				if (!bio)
 					goto fail;
+				bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs,
+					 rw ? REQ_OP_WRITE : REQ_OP_READ);
 				bio->bi_end_io = pscsi_bi_endio;
 
-				if (rw)
-					bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
 				pr_debug("PSCSI: Allocated bio: %p,"
 					" dir: %s nr_vecs: %d\n", bio,
 					(rw) ? "rw" : "r", nr_vecs);
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 4311a3221892..8879d052f96c 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -86,12 +86,10 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length,
 	int error, i;
 	struct bio *bio;
 
-	bio = bio_kmalloc(GFP_NOIO, page_count);
+	bio = bio_kmalloc(page_count, GFP_NOIO);
 	if (!bio)
 		return -ENOMEM;
-	bio_set_dev(bio, sb->s_bdev);
-	bio->bi_opf = REQ_OP_READ;
-
+	bio_init(bio, sb->s_bdev, bio->bi_inline_vecs, page_count, REQ_OP_READ);
 	bio->bi_iter.bi_sector = block * (msblk->devblksize >> SECTOR_SHIFT);
 
 	for (i = 0; i < page_count; ++i) {
@@ -121,7 +119,8 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length,
 
 out_free_bio:
 	bio_free_pages(bio);
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 	return error;
 }
 
@@ -185,7 +184,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 			length |= data[0] << 8;
 		}
 		bio_free_pages(bio);
-		bio_put(bio);
+		bio_uninit(bio);
+		kfree(bio);
 
 		compressed = SQUASHFS_COMPRESSED(length);
 		length = SQUASHFS_COMPRESSED_SIZE(length);
@@ -219,7 +219,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 
 out_free_bio:
 	bio_free_pages(bio);
-	bio_put(bio);
+	bio_uninit(bio);
+	kfree(bio);
 out:
 	if (res < 0) {
 		ERROR("Failed to read block 0x%llx: %d\n", index, res);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 8e87f3065042..49eff01fb829 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -405,7 +405,7 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src);
 struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
 			     unsigned int opf, gfp_t gfp_mask,
 			     struct bio_set *bs);
-struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs);
+struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask);
 extern void bio_put(struct bio *);
 
 struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src,
-- 
cgit v1.2.3


From 10f0d2a517796b8f6dc04fb0cc3e49003ae6b0bc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:42 +0200
Subject: block: add a bdev_nonrot helper

Add a helper to check the nonrot flag based on the block_device instead
of having to poke into the block layer internal request_queue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: David Sterba <dsterba@suse.com> [btrfs]
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-12-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioctl.c                       | 2 +-
 drivers/block/loop.c                | 2 +-
 drivers/md/dm-table.c               | 4 +---
 drivers/md/md.c                     | 3 +--
 drivers/md/raid1.c                  | 2 +-
 drivers/md/raid10.c                 | 2 +-
 drivers/md/raid5.c                  | 2 +-
 drivers/target/target_core_file.c   | 3 +--
 drivers/target/target_core_iblock.c | 2 +-
 fs/btrfs/volumes.c                  | 4 ++--
 fs/ext4/mballoc.c                   | 2 +-
 include/linux/blkdev.h              | 5 +++++
 mm/swapfile.c                       | 4 ++--
 13 files changed, 19 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/block/ioctl.c b/block/ioctl.c
index f8703db99c73..19c32b763451 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -489,7 +489,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
 				    queue_max_sectors(bdev_get_queue(bdev)));
 		return put_ushort(argp, max_sectors);
 	case BLKROTATIONAL:
-		return put_ushort(argp, !blk_queue_nonrot(bdev_get_queue(bdev)));
+		return put_ushort(argp, !bdev_nonrot(bdev));
 	case BLKRASET:
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a58595f5ee2c..8d800d46e498 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -903,7 +903,7 @@ static void loop_update_rotational(struct loop_device *lo)
 
 	/* not all filesystems (e.g. tmpfs) have a sb->s_bdev */
 	if (file_bdev)
-		nonrot = blk_queue_nonrot(bdev_get_queue(file_bdev));
+		nonrot = bdev_nonrot(file_bdev);
 
 	if (nonrot)
 		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 03541cfc2317..5e38d0dd009d 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1820,9 +1820,7 @@ static int device_dax_write_cache_enabled(struct dm_target *ti,
 static int device_is_rotational(struct dm_target *ti, struct dm_dev *dev,
 				sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return !blk_queue_nonrot(q);
+	return !bdev_nonrot(dev->bdev);
 }
 
 static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 309b3af906ad..19636c2f2cda 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5991,8 +5991,7 @@ int md_run(struct mddev *mddev)
 		bool nonrot = true;
 
 		rdev_for_each(rdev, mddev) {
-			if (rdev->raid_disk >= 0 &&
-			    !blk_queue_nonrot(bdev_get_queue(rdev->bdev))) {
+			if (rdev->raid_disk >= 0 && !bdev_nonrot(rdev->bdev)) {
 				nonrot = false;
 				break;
 			}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index d785c3169426..b7b21a4793d4 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -708,7 +708,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 			/* At least two disks to choose from so failfast is OK */
 			set_bit(R1BIO_FailFast, &r1_bio->state);
 
-		nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
+		nonrot = bdev_nonrot(rdev->bdev);
 		has_nonrot_disk |= nonrot;
 		pending = atomic_read(&rdev->nr_pending);
 		dist = abs(this_sector - conf->mirrors[disk].head_position);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index ee2438c0e55e..0987916066f2 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -803,7 +803,7 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 		if (!do_balance)
 			break;
 
-		nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
+		nonrot = bdev_nonrot(rdev->bdev);
 		has_nonrot_disk |= nonrot;
 		pending = atomic_read(&rdev->nr_pending);
 		if (min_pending > pending && nonrot) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 351d341a1ffa..0bbae0e63866 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7242,7 +7242,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	rdev_for_each(rdev, mddev) {
 		if (test_bit(Journal, &rdev->flags))
 			continue;
-		if (blk_queue_nonrot(bdev_get_queue(rdev->bdev))) {
+		if (bdev_nonrot(rdev->bdev)) {
 			conf->batch_bio_dispatch = false;
 			break;
 		}
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 8d191fdc3321..b6ba582b0677 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -135,7 +135,6 @@ static int fd_configure_device(struct se_device *dev)
 	inode = file->f_mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
 		struct block_device *bdev = I_BDEV(inode);
-		struct request_queue *q = bdev_get_queue(bdev);
 		unsigned long long dev_size;
 
 		fd_dev->fd_block_size = bdev_logical_block_size(bdev);
@@ -160,7 +159,7 @@ static int fd_configure_device(struct se_device *dev)
 		 */
 		dev->dev_attrib.max_write_same_len = 0xFFFF;
 
-		if (blk_queue_nonrot(q))
+		if (bdev_nonrot(bdev))
 			dev->dev_attrib.is_nonrot = 1;
 	} else {
 		if (!(fd_dev->fbd_flags & FBDF_HAS_SIZE)) {
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index b886ce1770bf..b41ee5c3b5b8 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -133,7 +133,7 @@ static int iblock_configure_device(struct se_device *dev)
 	else
 		dev->dev_attrib.max_write_same_len = 0xFFFF;
 
-	if (blk_queue_nonrot(q))
+	if (bdev_nonrot(bd))
 		dev->dev_attrib.is_nonrot = 1;
 
 	bi = bdev_get_integrity(bd);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 678504c9055a..b6b00338037c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -642,7 +642,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 			set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 	}
 
-	if (!blk_queue_nonrot(bdev_get_queue(bdev)))
+	if (!bdev_nonrot(bdev))
 		fs_devices->rotating = true;
 
 	device->bdev = bdev;
@@ -2705,7 +2705,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
-	if (!blk_queue_nonrot(bdev_get_queue(bdev)))
+	if (!bdev_nonrot(bdev))
 		fs_devices->rotating = true;
 
 	orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 252c168454c7..c3668c977cd9 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3498,7 +3498,7 @@ int ext4_mb_init(struct super_block *sb)
 		spin_lock_init(&lg->lg_prealloc_lock);
 	}
 
-	if (blk_queue_nonrot(bdev_get_queue(sb->s_bdev)))
+	if (bdev_nonrot(sb->s_bdev))
 		sbi->s_mb_max_linear_groups = 0;
 	else
 		sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 60d016138997..3a9578e14a6b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1326,6 +1326,11 @@ static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 	return 0;
 }
 
+static inline bool bdev_nonrot(struct block_device *bdev)
+{
+	return blk_queue_nonrot(bdev_get_queue(bdev));
+}
+
 static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4c7537162af5..d5ab7ec4d92c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2466,7 +2466,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	if (p->flags & SWP_CONTINUED)
 		free_swap_count_continuations(p);
 
-	if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev)))
+	if (!p->bdev || !bdev_nonrot(p->bdev))
 		atomic_dec(&nr_rotate_swap);
 
 	mutex_lock(&swapon_mutex);
@@ -3071,7 +3071,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (p->bdev && p->bdev->bd_disk->fops->rw_page)
 		p->flags |= SWP_SYNCHRONOUS_IO;
 
-	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
+	if (p->bdev && bdev_nonrot(p->bdev)) {
 		int cpu;
 		unsigned long ci, nr_cluster;
 
-- 
cgit v1.2.3


From 08e688fdb8f7e862092ae64cee20bc8b463d1046 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:43 +0200
Subject: block: add a bdev_write_cache helper

Add a helper to check the write cache flag based on the block_device
instead of having to poke into the block layer internal request_queue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: David Sterba <dsterba@suse.com> [btrfs]
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-13-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/rnbd/rnbd-srv.c       | 2 +-
 drivers/block/xen-blkback/xenbus.c  | 2 +-
 drivers/target/target_core_iblock.c | 8 ++------
 fs/btrfs/disk-io.c                  | 3 +--
 include/linux/blkdev.h              | 5 +++++
 5 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index f04df6294650..f8cc3c5fecb4 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -558,7 +558,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 	rsp->secure_discard =
 		cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev));
 	rsp->cache_policy = 0;
-	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+	if (bdev_write_cache(rnbd_dev->bdev))
 		rsp->cache_policy |= RNBD_WRITEBACK;
 	if (blk_queue_fua(q))
 		rsp->cache_policy |= RNBD_FUA;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index f09040435e2e..8b691fe50475 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -517,7 +517,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 		vbd->type |= VDISK_REMOVABLE;
 
 	q = bdev_get_queue(bdev);
-	if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+	if (bdev_write_cache(bdev))
 		vbd->flush_support = true;
 
 	if (q && blk_queue_secure_erase(q))
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index b41ee5c3b5b8..03013e85ffc0 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -737,7 +737,7 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		if (test_bit(QUEUE_FLAG_FUA, &q->queue_flags)) {
 			if (cmd->se_cmd_flags & SCF_FUA)
 				opf |= REQ_FUA;
-			else if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+			else if (!bdev_write_cache(ib_dev->ibd_bd))
 				opf |= REQ_FUA;
 		}
 	} else {
@@ -886,11 +886,7 @@ iblock_parse_cdb(struct se_cmd *cmd)
 
 static bool iblock_get_write_cache(struct se_device *dev)
 {
-	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
-	struct block_device *bd = ib_dev->ibd_bd;
-	struct request_queue *q = bdev_get_queue(bd);
-
-	return test_bit(QUEUE_FLAG_WC, &q->queue_flags);
+	return bdev_write_cache(IBLOCK_DEV(dev)->ibd_bd);
 }
 
 static const struct target_backend_ops iblock_ops = {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index cf9b5e214d6f..0611bdf1cce7 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4249,8 +4249,7 @@ static void write_dev_flush(struct btrfs_device *device)
 	 * of simplicity, since this is a debug tool and not meant for use in
 	 * non-debug builds.
 	 */
-	struct request_queue *q = bdev_get_queue(device->bdev);
-	if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+	if (!bdev_write_cache(device->bdev))
 		return;
 #endif
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3a9578e14a6b..807a49aa5a27 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1331,6 +1331,11 @@ static inline bool bdev_nonrot(struct block_device *bdev)
 	return blk_queue_nonrot(bdev_get_queue(bdev));
 }
 
+static inline bool bdev_write_cache(struct block_device *bdev)
+{
+	return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags);
+}
+
 static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-- 
cgit v1.2.3


From a557e82e5a01826f902bd94fc925c03f253cb712 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:44 +0200
Subject: block: add a bdev_fua helper

Add a helper to check the FUA flag based on the block_device instead of
having to poke into the block layer internal request_queue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-14-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/rnbd/rnbd-srv.c       | 3 +--
 drivers/target/target_core_iblock.c | 3 +--
 fs/iomap/direct-io.c                | 3 +--
 include/linux/blkdev.h              | 6 +++++-
 4 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index f8cc3c5fecb4..beaef43a67b9 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -533,7 +533,6 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 					struct rnbd_srv_sess_dev *sess_dev)
 {
 	struct rnbd_dev *rnbd_dev = sess_dev->rnbd_dev;
-	struct request_queue *q = bdev_get_queue(rnbd_dev->bdev);
 
 	rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP);
 	rsp->device_id =
@@ -560,7 +559,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 	rsp->cache_policy = 0;
 	if (bdev_write_cache(rnbd_dev->bdev))
 		rsp->cache_policy |= RNBD_WRITEBACK;
-	if (blk_queue_fua(q))
+	if (bdev_fua(rnbd_dev->bdev))
 		rsp->cache_policy |= RNBD_FUA;
 }
 
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 03013e85ffc0..c4a903b8a47f 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -727,14 +727,13 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 
 	if (data_direction == DMA_TO_DEVICE) {
 		struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
-		struct request_queue *q = bdev_get_queue(ib_dev->ibd_bd);
 		/*
 		 * Force writethrough using REQ_FUA if a volatile write cache
 		 * is not enabled, or if initiator set the Force Unit Access bit.
 		 */
 		opf = REQ_OP_WRITE;
 		miter_dir = SG_MITER_TO_SG;
-		if (test_bit(QUEUE_FLAG_FUA, &q->queue_flags)) {
+		if (bdev_fua(ib_dev->ibd_bd)) {
 			if (cmd->se_cmd_flags & SCF_FUA)
 				opf |= REQ_FUA;
 			else if (!bdev_write_cache(ib_dev->ibd_bd))
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index b08f5dc31780..62da020d02a1 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -265,8 +265,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		 * cache flushes on IO completion.
 		 */
 		if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
-		    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
-		    blk_queue_fua(bdev_get_queue(iomap->bdev)))
+		    (dio->flags & IOMAP_DIO_WRITE_FUA) && bdev_fua(iomap->bdev))
 			use_fua = true;
 	}
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 807a49aa5a27..075b16d4560e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -602,7 +602,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 			     REQ_FAILFAST_DRIVER))
 #define blk_queue_quiesced(q)	test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
 #define blk_queue_pm_only(q)	atomic_read(&(q)->pm_only)
-#define blk_queue_fua(q)	test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
 #define blk_queue_nowait(q)	test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
 
@@ -1336,6 +1335,11 @@ static inline bool bdev_write_cache(struct block_device *bdev)
 	return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags);
 }
 
+static inline bool bdev_fua(struct block_device *bdev)
+{
+	return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags);
+}
+
 static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-- 
cgit v1.2.3


From 36d254893aa6a6e204075c3cce94bb572ac32c04 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:45 +0200
Subject: block: add a bdev_stable_writes helper

Add a helper to check the stable writes flag based on the block_device
instead of having to poke into the block layer internal request_queue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-15-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/dm-table.c  | 4 +---
 fs/super.c             | 2 +-
 include/linux/blkdev.h | 6 ++++++
 mm/swapfile.c          | 2 +-
 4 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5e38d0dd009d..d46839faa0ca 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1950,9 +1950,7 @@ static int device_requires_stable_pages(struct dm_target *ti,
 					struct dm_dev *dev, sector_t start,
 					sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return blk_queue_stable_writes(q);
+	return bdev_stable_writes(dev->bdev);
 }
 
 int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
diff --git a/fs/super.c b/fs/super.c
index f1d4a193602d..60f57c7bc0a6 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1204,7 +1204,7 @@ static int set_bdev_super(struct super_block *s, void *data)
 	s->s_dev = s->s_bdev->bd_dev;
 	s->s_bdi = bdi_get(s->s_bdev->bd_disk->bdi);
 
-	if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue))
+	if (bdev_stable_writes(s->s_bdev))
 		s->s_iflags |= SB_I_STABLE_WRITES;
 	return 0;
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 075b16d4560e..a433798c3343 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1330,6 +1330,12 @@ static inline bool bdev_nonrot(struct block_device *bdev)
 	return blk_queue_nonrot(bdev_get_queue(bdev));
 }
 
+static inline bool bdev_stable_writes(struct block_device *bdev)
+{
+	return test_bit(QUEUE_FLAG_STABLE_WRITES,
+			&bdev_get_queue(bdev)->queue_flags);
+}
+
 static inline bool bdev_write_cache(struct block_device *bdev)
 {
 	return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index d5ab7ec4d92c..4069f17a82c8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3065,7 +3065,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
-	if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue))
+	if (p->bdev && bdev_stable_writes(p->bdev))
 		p->flags |= SWP_STABLE_WRITES;
 
 	if (p->bdev && p->bdev->bd_disk->fops->rw_page)
-- 
cgit v1.2.3


From 2aba0d19f4d8c8929b4b3b94a9cfde2aa20e6ee2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:46 +0200
Subject: block: add a bdev_max_zone_append_sectors helper

Add a helper to check the max supported sectors for zone append based on
the block_device instead of having to poke into the block layer internal
request_queue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-16-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/target/zns.c | 3 +--
 fs/zonefs/super.c         | 3 +--
 include/linux/blkdev.h    | 6 ++++++
 3 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index e34718b09550..82b61acf7a72 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -34,8 +34,7 @@ static int validate_conv_zones_cb(struct blk_zone *z,
 
 bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
 {
-	struct request_queue *q = ns->bdev->bd_disk->queue;
-	u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q));
+	u8 zasl = nvmet_zasl(bdev_max_zone_append_sectors(ns->bdev));
 	struct gendisk *bd_disk = ns->bdev->bd_disk;
 	int ret;
 
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 3614c7834007..7a63807b736c 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -678,13 +678,12 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct block_device *bdev = inode->i_sb->s_bdev;
-	unsigned int max;
+	unsigned int max = bdev_max_zone_append_sectors(bdev);
 	struct bio *bio;
 	ssize_t size;
 	int nr_pages;
 	ssize_t ret;
 
-	max = queue_max_zone_append_sectors(bdev_get_queue(bdev));
 	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
 	iov_iter_truncate(from, max);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a433798c3343..f8c50b77543e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1188,6 +1188,12 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu
 	return min(l->max_zone_append_sectors, l->max_sectors);
 }
 
+static inline unsigned int
+bdev_max_zone_append_sectors(struct block_device *bdev)
+{
+	return queue_max_zone_append_sectors(bdev_get_queue(bdev));
+}
+
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
 {
 	int retval = 512;
-- 
cgit v1.2.3


From 640f2a23911b8388989547f89d055afbb910b88e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:48 +0200
Subject: block: use bdev_alignment_offset in disk_alignment_offset_show

This does the same as the open coded variant except for an extra branch,
and allows to remove queue_alignment_offset entirely.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20220415045258.199825-18-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c          | 2 +-
 include/linux/blkdev.h | 8 --------
 2 files changed, 1 insertion(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index b8b6759d670f..712031ce1907 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1010,7 +1010,7 @@ static ssize_t disk_alignment_offset_show(struct device *dev,
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue));
+	return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0));
 }
 
 static ssize_t disk_discard_alignment_show(struct device *dev,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f8c50b77543e..d5346e72e364 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1251,14 +1251,6 @@ bdev_zone_write_granularity(struct block_device *bdev)
 	return queue_zone_write_granularity(bdev_get_queue(bdev));
 }
 
-static inline int queue_alignment_offset(const struct request_queue *q)
-{
-	if (q->limits.misaligned)
-		return -1;
-
-	return q->limits.alignment_offset;
-}
-
 static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-- 
cgit v1.2.3


From 89098b075cb74a80083bc4ed6b71d0ee18b6898f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:49 +0200
Subject: block: move bdev_alignment_offset and queue_limit_alignment_offset
 out of line

No need to inline these fairly larger helpers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20220415045258.199825-19-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c   | 23 +++++++++++++++++++++++
 include/linux/blkdev.h | 21 +--------------------
 2 files changed, 24 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index b83df3d2eebc..94410a13c0de 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -468,6 +468,16 @@ void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
+static int queue_limit_alignment_offset(struct queue_limits *lim,
+		sector_t sector)
+{
+	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
+	unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT)
+		<< SECTOR_SHIFT;
+
+	return (granularity + lim->alignment_offset - alignment) % granularity;
+}
+
 static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs)
 {
 	sectors = round_down(sectors, lbs >> SECTOR_SHIFT);
@@ -901,3 +911,16 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
 	}
 }
 EXPORT_SYMBOL_GPL(blk_queue_set_zoned);
+
+int bdev_alignment_offset(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q->limits.misaligned)
+		return -1;
+	if (bdev_is_partition(bdev))
+		return queue_limit_alignment_offset(&q->limits,
+				bdev->bd_start_sect);
+	return q->limits.alignment_offset;
+}
+EXPORT_SYMBOL_GPL(bdev_alignment_offset);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d5346e72e364..0a1795ac2627 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1251,26 +1251,7 @@ bdev_zone_write_granularity(struct block_device *bdev)
 	return queue_zone_write_granularity(bdev_get_queue(bdev));
 }
 
-static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
-{
-	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-	unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT)
-		<< SECTOR_SHIFT;
-
-	return (granularity + lim->alignment_offset - alignment) % granularity;
-}
-
-static inline int bdev_alignment_offset(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q->limits.misaligned)
-		return -1;
-	if (bdev_is_partition(bdev))
-		return queue_limit_alignment_offset(&q->limits,
-				bdev->bd_start_sect);
-	return q->limits.alignment_offset;
-}
+int bdev_alignment_offset(struct block_device *bdev);
 
 static inline int queue_discard_alignment(const struct request_queue *q)
 {
-- 
cgit v1.2.3


From 4e1462ffe8998749884d61f91be251a7a8719677 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:50 +0200
Subject: block: remove queue_discard_alignment

Just use bdev_alignment_offset in disk_discard_alignment_show instead.
That helpers is the same except for an always false branch that doesn't
matter in this slow path.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20220415045258.199825-20-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c          | 2 +-
 include/linux/blkdev.h | 8 --------
 2 files changed, 1 insertion(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 712031ce1907..36532b931841 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1019,7 +1019,7 @@ static ssize_t disk_discard_alignment_show(struct device *dev,
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
+	return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0));
 }
 
 static ssize_t diskseq_show(struct device *dev,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0a1795ac2627..5a9b7aeda010 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1253,14 +1253,6 @@ bdev_zone_write_granularity(struct block_device *bdev)
 
 int bdev_alignment_offset(struct block_device *bdev);
 
-static inline int queue_discard_alignment(const struct request_queue *q)
-{
-	if (q->limits.discard_misaligned)
-		return -1;
-
-	return q->limits.discard_alignment;
-}
-
 static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int alignment, granularity, offset;
-- 
cgit v1.2.3


From 5c4b4a5c6f11c869a57c6bd977143430bc9dc43d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:52 +0200
Subject: block: move {bdev,queue_limit}_discard_alignment out of line

No need to inline these fairly larger helpers.  Also fix the return value
to be unsigned, just like the field in struct queue_limits.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20220415045258.199825-22-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c   | 35 +++++++++++++++++++++++++++++++++++
 include/linux/blkdev.h | 34 +---------------------------------
 2 files changed, 36 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 94410a13c0de..fd83d674afd0 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -478,6 +478,30 @@ static int queue_limit_alignment_offset(struct queue_limits *lim,
 	return (granularity + lim->alignment_offset - alignment) % granularity;
 }
 
+static unsigned int queue_limit_discard_alignment(struct queue_limits *lim,
+		sector_t sector)
+{
+	unsigned int alignment, granularity, offset;
+
+	if (!lim->max_discard_sectors)
+		return 0;
+
+	/* Why are these in bytes, not sectors? */
+	alignment = lim->discard_alignment >> SECTOR_SHIFT;
+	granularity = lim->discard_granularity >> SECTOR_SHIFT;
+	if (!granularity)
+		return 0;
+
+	/* Offset of the partition start in 'granularity' sectors */
+	offset = sector_div(sector, granularity);
+
+	/* And why do we do this modulus *again* in blkdev_issue_discard()? */
+	offset = (granularity + alignment - offset) % granularity;
+
+	/* Turn it back into bytes, gaah */
+	return offset << SECTOR_SHIFT;
+}
+
 static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs)
 {
 	sectors = round_down(sectors, lbs >> SECTOR_SHIFT);
@@ -924,3 +948,14 @@ int bdev_alignment_offset(struct block_device *bdev)
 	return q->limits.alignment_offset;
 }
 EXPORT_SYMBOL_GPL(bdev_alignment_offset);
+
+unsigned int bdev_discard_alignment(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (bdev_is_partition(bdev))
+		return queue_limit_discard_alignment(&q->limits,
+				bdev->bd_start_sect);
+	return q->limits.discard_alignment;
+}
+EXPORT_SYMBOL_GPL(bdev_discard_alignment);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5a9b7aeda010..34b1cfd06742 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1252,39 +1252,7 @@ bdev_zone_write_granularity(struct block_device *bdev)
 }
 
 int bdev_alignment_offset(struct block_device *bdev);
-
-static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
-{
-	unsigned int alignment, granularity, offset;
-
-	if (!lim->max_discard_sectors)
-		return 0;
-
-	/* Why are these in bytes, not sectors? */
-	alignment = lim->discard_alignment >> SECTOR_SHIFT;
-	granularity = lim->discard_granularity >> SECTOR_SHIFT;
-	if (!granularity)
-		return 0;
-
-	/* Offset of the partition start in 'granularity' sectors */
-	offset = sector_div(sector, granularity);
-
-	/* And why do we do this modulus *again* in blkdev_issue_discard()? */
-	offset = (granularity + alignment - offset) % granularity;
-
-	/* Turn it back into bytes, gaah */
-	return offset << SECTOR_SHIFT;
-}
-
-static inline int bdev_discard_alignment(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (bdev_is_partition(bdev))
-		return queue_limit_discard_alignment(&q->limits,
-				bdev->bd_start_sect);
-	return q->limits.discard_alignment;
-}
+unsigned int bdev_discard_alignment(struct block_device *bdev);
 
 static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 {
-- 
cgit v1.2.3


From cf0fbf894bb543f472f682c486be48298eccf199 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:54 +0200
Subject: block: add a bdev_max_discard_sectors helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a helper to query the number of sectors support per each discard bio
based on the block device and use this helper to stop various places from
poking into the request_queue to see if discard is supported and if so how
much.  This mirrors what is done e.g. for write zeroes as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com> [drbd]
Acked-by: Coly Li <colyli@suse.de> [bcache]
Acked-by: David Sterba <dsterba@suse.com> [btrfs]
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-24-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_nl.c        | 8 +++++---
 drivers/block/drbd/drbd_receiver.c  | 2 +-
 drivers/block/rnbd/rnbd-srv-dev.h   | 3 +--
 drivers/md/dm-io.c                  | 2 +-
 drivers/target/target_core_device.c | 7 +++----
 fs/f2fs/segment.c                   | 6 ++----
 include/linux/blkdev.h              | 5 +++++
 7 files changed, 18 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 4d00986d6f58..a0a06e238e91 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1439,7 +1439,8 @@ static bool write_ordering_changed(struct disk_conf *a, struct disk_conf *b)
 static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *disk_conf,
 			       struct drbd_backing_dev *nbc)
 {
-	struct request_queue * const q = nbc->backing_bdev->bd_disk->queue;
+	struct block_device *bdev = nbc->backing_bdev;
+	struct request_queue *q = bdev->bd_disk->queue;
 
 	if (disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
 		disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
@@ -1455,6 +1456,7 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 
 	if (disk_conf->rs_discard_granularity) {
 		int orig_value = disk_conf->rs_discard_granularity;
+		sector_t discard_size = bdev_max_discard_sectors(bdev) << 9;
 		int remainder;
 
 		if (q->limits.discard_granularity > disk_conf->rs_discard_granularity)
@@ -1463,8 +1465,8 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 		remainder = disk_conf->rs_discard_granularity % q->limits.discard_granularity;
 		disk_conf->rs_discard_granularity += remainder;
 
-		if (disk_conf->rs_discard_granularity > q->limits.max_discard_sectors << 9)
-			disk_conf->rs_discard_granularity = q->limits.max_discard_sectors << 9;
+		if (disk_conf->rs_discard_granularity > discard_size)
+			disk_conf->rs_discard_granularity = discard_size;
 
 		if (disk_conf->rs_discard_granularity != orig_value)
 			drbd_info(device, "rs_discard_granularity changed to %d\n",
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 08da922f81d1..0b4c7de46398 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1524,7 +1524,7 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
 	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
 
-	max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22));
+	max_discard_sectors = min(bdev_max_discard_sectors(bdev), (1U << 22));
 	max_discard_sectors -= max_discard_sectors % granularity;
 	if (unlikely(!max_discard_sectors))
 		goto zero_out;
diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h
index 2c3df02b5e8e..f82fbb4bbda8 100644
--- a/drivers/block/rnbd/rnbd-srv-dev.h
+++ b/drivers/block/rnbd/rnbd-srv-dev.h
@@ -52,8 +52,7 @@ static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev)
 	if (!blk_queue_discard(bdev_get_queue(dev->bdev)))
 		return 0;
 
-	return blk_queue_get_max_sectors(bdev_get_queue(dev->bdev),
-					 REQ_OP_DISCARD);
+	return bdev_max_discard_sectors(dev->bdev);
 }
 
 static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev)
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 5762366333a2..e4b95eaeec8c 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -311,7 +311,7 @@ static void do_region(int op, int op_flags, unsigned region,
 	 * Reject unsupported discard and write same requests.
 	 */
 	if (op == REQ_OP_DISCARD)
-		special_cmd_max_sectors = q->limits.max_discard_sectors;
+		special_cmd_max_sectors = bdev_max_discard_sectors(where->bdev);
 	else if (op == REQ_OP_WRITE_ZEROES)
 		special_cmd_max_sectors = q->limits.max_write_zeroes_sectors;
 	if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) &&
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 16e775bcf4a7..c3e25bac90d5 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -829,9 +829,8 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 }
 
 /*
- * Check if the underlying struct block_device request_queue supports
- * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
- * in ATA and we need to set TPE=1
+ * Check if the underlying struct block_device supports discard and if yes
+ * configure the UNMAP parameters.
  */
 bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
 				       struct block_device *bdev)
@@ -843,7 +842,7 @@ bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
 		return false;
 
 	attrib->max_unmap_lba_count =
-		q->limits.max_discard_sectors >> (ilog2(block_size) - 9);
+		bdev_max_discard_sectors(bdev) >> (ilog2(block_size) - 9);
 	/*
 	 * Currently hardcoded to 1 in Linux/SCSI code..
 	 */
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 22dfeb991529..71f09adbcba8 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1196,9 +1196,8 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 						unsigned int *issued)
 {
 	struct block_device *bdev = dc->bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
 	unsigned int max_discard_blocks =
-			SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
+			SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev));
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
 					&(dcc->fstrim_list) : &(dcc->wait_list);
@@ -1375,9 +1374,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 	struct discard_cmd *dc;
 	struct discard_info di = {0};
 	struct rb_node **insert_p = NULL, *insert_parent = NULL;
-	struct request_queue *q = bdev_get_queue(bdev);
 	unsigned int max_discard_blocks =
-			SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
+			SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev));
 	block_t end = lstart + len;
 
 	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 34b1cfd06742..ce16247d3afa 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1254,6 +1254,11 @@ bdev_zone_write_granularity(struct block_device *bdev)
 int bdev_alignment_offset(struct block_device *bdev);
 unsigned int bdev_discard_alignment(struct block_device *bdev);
 
+static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev)
+{
+	return bdev_get_queue(bdev)->limits.max_discard_sectors;
+}
+
 static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-- 
cgit v1.2.3


From 70200574cc229f6ba038259e8142af2aa09e6976 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:55 +0200
Subject: block: remove QUEUE_FLAG_DISCARD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just use a non-zero max_discard_sectors as an indicator for discard
support, similar to what is done for write zeroes.

The only places where needs special attention is the RAID5 driver,
which must clear discard support for security reasons by default,
even if the default stacking rules would allow for it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com> [drbd]
Acked-by: Jan Höppner <hoeppner@linux.ibm.com> [s390]
Acked-by: Coly Li <colyli@suse.de> [bcache]
Acked-by: David Sterba <dsterba@suse.com> [btrfs]
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-25-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 arch/um/drivers/ubd_kern.c          |  2 --
 block/blk-core.c                    |  2 +-
 block/blk-lib.c                     |  2 +-
 block/blk-mq-debugfs.c              |  1 -
 block/ioctl.c                       |  3 +--
 drivers/block/drbd/drbd_main.c      |  2 +-
 drivers/block/drbd/drbd_nl.c        | 19 ++-----------------
 drivers/block/drbd/drbd_receiver.c  |  3 +--
 drivers/block/loop.c                | 11 +++--------
 drivers/block/nbd.c                 |  5 +----
 drivers/block/null_blk/main.c       |  1 -
 drivers/block/rbd.c                 |  1 -
 drivers/block/rnbd/rnbd-clt.c       |  2 --
 drivers/block/rnbd/rnbd-srv-dev.h   |  3 ---
 drivers/block/virtio_blk.c          |  2 --
 drivers/block/xen-blkback/xenbus.c  |  2 +-
 drivers/block/xen-blkfront.c        |  3 +--
 drivers/block/zram/zram_drv.c       |  1 -
 drivers/md/bcache/request.c         |  4 ++--
 drivers/md/bcache/super.c           |  3 +--
 drivers/md/bcache/sysfs.c           |  2 +-
 drivers/md/dm-cache-target.c        |  9 +--------
 drivers/md/dm-clone-target.c        |  9 +--------
 drivers/md/dm-log-writes.c          |  3 +--
 drivers/md/dm-raid.c                |  9 ++-------
 drivers/md/dm-table.c               |  9 ++-------
 drivers/md/dm-thin.c                | 11 +----------
 drivers/md/dm.c                     |  3 +--
 drivers/md/md-linear.c              | 11 +----------
 drivers/md/raid0.c                  |  7 -------
 drivers/md/raid1.c                  | 16 +---------------
 drivers/md/raid10.c                 | 18 ++----------------
 drivers/md/raid5-cache.c            |  2 +-
 drivers/md/raid5.c                  | 12 ++++--------
 drivers/mmc/core/queue.c            |  1 -
 drivers/mtd/mtd_blkdevs.c           |  1 -
 drivers/nvme/host/core.c            |  4 ++--
 drivers/s390/block/dasd_fba.c       |  1 -
 drivers/scsi/sd.c                   |  2 --
 drivers/target/target_core_device.c |  2 +-
 fs/btrfs/extent-tree.c              |  4 ++--
 fs/btrfs/ioctl.c                    |  2 +-
 fs/exfat/file.c                     |  2 +-
 fs/exfat/super.c                    | 10 +++-------
 fs/ext4/ioctl.c                     | 10 +++-------
 fs/ext4/super.c                     | 10 +++-------
 fs/f2fs/f2fs.h                      |  3 +--
 fs/fat/file.c                       |  2 +-
 fs/fat/inode.c                      | 10 +++-------
 fs/gfs2/rgrp.c                      |  2 +-
 fs/jbd2/journal.c                   |  7 ++-----
 fs/jfs/ioctl.c                      |  2 +-
 fs/jfs/super.c                      |  8 ++------
 fs/nilfs2/ioctl.c                   |  2 +-
 fs/ntfs3/file.c                     |  2 +-
 fs/ntfs3/super.c                    |  2 +-
 fs/ocfs2/ioctl.c                    |  2 +-
 fs/xfs/xfs_discard.c                |  2 +-
 fs/xfs/xfs_super.c                  | 12 ++++--------
 include/linux/blkdev.h              |  2 --
 mm/swapfile.c                       | 17 ++---------------
 61 files changed, 73 insertions(+), 244 deletions(-)

(limited to 'include/linux')

diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index b03269faef71..085ffdf98e57 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -483,7 +483,6 @@ static void ubd_handler(void)
 			if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) {
 				blk_queue_max_discard_sectors(io_req->req->q, 0);
 				blk_queue_max_write_zeroes_sectors(io_req->req->q, 0);
-				blk_queue_flag_clear(QUEUE_FLAG_DISCARD, io_req->req->q);
 			}
 			blk_mq_end_request(io_req->req, io_req->error);
 			kfree(io_req);
@@ -803,7 +802,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 		ubd_dev->queue->limits.discard_alignment = SECTOR_SIZE;
 		blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
 		blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, ubd_dev->queue);
 	}
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue);
 	return 0;
diff --git a/block/blk-core.c b/block/blk-core.c
index 937bb6b86331..b5c3a8049134 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -820,7 +820,7 @@ void submit_bio_noacct(struct bio *bio)
 
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
-		if (!blk_queue_discard(q))
+		if (!bdev_max_discard_sectors(bdev))
 			goto not_supported;
 		break;
 	case REQ_OP_SECURE_ERASE:
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 2ae32a722851..8b4b66d3a9bf 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -53,7 +53,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			return -EOPNOTSUPP;
 		op = REQ_OP_SECURE_ERASE;
 	} else {
-		if (!blk_queue_discard(q))
+		if (!bdev_max_discard_sectors(bdev))
 			return -EOPNOTSUPP;
 		op = REQ_OP_DISCARD;
 	}
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index aa0349e9f083..fd111c500125 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -113,7 +113,6 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(FAIL_IO),
 	QUEUE_FLAG_NAME(NONROT),
 	QUEUE_FLAG_NAME(IO_STAT),
-	QUEUE_FLAG_NAME(DISCARD),
 	QUEUE_FLAG_NAME(NOXMERGES),
 	QUEUE_FLAG_NAME(ADD_RANDOM),
 	QUEUE_FLAG_NAME(SECERASE),
diff --git a/block/ioctl.c b/block/ioctl.c
index 19c32b763451..eaee0efc0bea 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -87,14 +87,13 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 {
 	uint64_t range[2];
 	uint64_t start, len;
-	struct request_queue *q = bdev_get_queue(bdev);
 	struct inode *inode = bdev->bd_inode;
 	int err;
 
 	if (!(mode & FMODE_WRITE))
 		return -EBADF;
 
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(bdev))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 7b501c8d5992..912560f611c3 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -942,7 +942,7 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu
 			cpu_to_be32(bdev_alignment_offset(bdev));
 		p->qlim->io_min = cpu_to_be32(bdev_io_min(bdev));
 		p->qlim->io_opt = cpu_to_be32(bdev_io_opt(bdev));
-		p->qlim->discard_enabled = blk_queue_discard(q);
+		p->qlim->discard_enabled = !!bdev_max_discard_sectors(bdev);
 		put_ldev(device);
 	} else {
 		struct request_queue *q = device->rq_queue;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index a0a06e238e91..0678ceb50579 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1210,7 +1210,7 @@ static void decide_on_discard_support(struct drbd_device *device,
 		first_peer_device(device)->connection;
 	struct request_queue *q = device->rq_queue;
 
-	if (bdev && !blk_queue_discard(bdev->backing_bdev->bd_disk->queue))
+	if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev))
 		goto not_supported;
 
 	if (connection->cstate >= C_CONNECTED &&
@@ -1230,30 +1230,16 @@ static void decide_on_discard_support(struct drbd_device *device,
 	 */
 	blk_queue_discard_granularity(q, 512);
 	q->limits.max_discard_sectors = drbd_max_discard_sectors(connection);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 	q->limits.max_write_zeroes_sectors =
 		drbd_max_discard_sectors(connection);
 	return;
 
 not_supported:
-	blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 	blk_queue_discard_granularity(q, 0);
 	q->limits.max_discard_sectors = 0;
 	q->limits.max_write_zeroes_sectors = 0;
 }
 
-static void fixup_discard_if_not_supported(struct request_queue *q)
-{
-	/* To avoid confusion, if this queue does not support discard, clear
-	 * max_discard_sectors, which is what lsblk -D reports to the user.
-	 * Older kernels got this wrong in "stack limits".
-	 * */
-	if (!blk_queue_discard(q)) {
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_discard_granularity(q, 0);
-	}
-}
-
 static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
 {
 	/* Fixup max_write_zeroes_sectors after blk_stack_limits():
@@ -1300,7 +1286,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 		blk_stack_limits(&q->limits, &b->limits, 0);
 		disk_update_readahead(device->vdisk);
 	}
-	fixup_discard_if_not_supported(q);
 	fixup_write_zeroes(device, q);
 }
 
@@ -1447,7 +1432,7 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 	if (disk_conf->al_extents > drbd_al_extents_max(nbc))
 		disk_conf->al_extents = drbd_al_extents_max(nbc);
 
-	if (!blk_queue_discard(q)) {
+	if (!bdev_max_discard_sectors(bdev)) {
 		if (disk_conf->rs_discard_granularity) {
 			disk_conf->rs_discard_granularity = 0; /* disable feature */
 			drbd_info(device, "rs_discard_granularity feature disabled\n");
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 0b4c7de46398..8a4a47da56fe 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1575,11 +1575,10 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u
 
 static bool can_do_reliable_discards(struct drbd_device *device)
 {
-	struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
 	struct disk_conf *dc;
 	bool can_do;
 
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(device->ldev->backing_bdev))
 		return false;
 
 	rcu_read_lock();
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 8d800d46e498..0e061c9896ef 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -314,15 +314,12 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 
 	mode |= FALLOC_FL_KEEP_SIZE;
 
-	if (!blk_queue_discard(lo->lo_queue)) {
-		ret = -EOPNOTSUPP;
-		goto out;
-	}
+	if (!bdev_max_discard_sectors(lo->lo_device))
+		return -EOPNOTSUPP;
 
 	ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq));
 	if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP))
-		ret = -EIO;
- out:
+		return -EIO;
 	return ret;
 }
 
@@ -787,12 +784,10 @@ static void loop_config_discard(struct loop_device *lo)
 		q->limits.discard_granularity = granularity;
 		blk_queue_max_discard_sectors(q, max_discard_sectors);
 		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 	} else {
 		q->limits.discard_granularity = 0;
 		blk_queue_max_discard_sectors(q, 0);
 		blk_queue_max_write_zeroes_sectors(q, 0);
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 	}
 	q->limits.discard_alignment = 0;
 }
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 5a1f98494ddd..4729aef8c646 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1231,8 +1231,6 @@ static void nbd_parse_flags(struct nbd_device *nbd)
 		set_disk_ro(nbd->disk, true);
 	else
 		set_disk_ro(nbd->disk, false);
-	if (config->flags & NBD_FLAG_SEND_TRIM)
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 	if (config->flags & NBD_FLAG_SEND_FLUSH) {
 		if (config->flags & NBD_FLAG_SEND_FUA)
 			blk_queue_write_cache(nbd->disk->queue, true, true);
@@ -1319,8 +1317,7 @@ static void nbd_config_put(struct nbd_device *nbd)
 		nbd->tag_set.timeout = 0;
 		nbd->disk->queue->limits.discard_granularity = 0;
 		nbd->disk->queue->limits.discard_alignment = 0;
-		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue);
+		blk_queue_max_discard_sectors(nbd->disk->queue, 0);
 
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index c441a4972064..5cb4c92cdffe 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1767,7 +1767,6 @@ static void null_config_discard(struct nullb *nullb)
 	nullb->q->limits.discard_granularity = nullb->dev->blocksize;
 	nullb->q->limits.discard_alignment = nullb->dev->blocksize;
 	blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q);
 }
 
 static const struct block_device_operations null_bio_ops = {
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index b844432bad20..2b21f717cce1 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4942,7 +4942,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	blk_queue_io_opt(q, rbd_dev->opts->alloc_size);
 
 	if (rbd_dev->opts->trim) {
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 		q->limits.discard_granularity = rbd_dev->opts->alloc_size;
 		blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
 		blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index b66e8840b94b..efa99a388450 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1364,8 +1364,6 @@ static void setup_request_queue(struct rnbd_clt_dev *dev)
 	blk_queue_max_discard_sectors(dev->queue, dev->max_discard_sectors);
 	dev->queue->limits.discard_granularity	= dev->discard_granularity;
 	dev->queue->limits.discard_alignment	= dev->discard_alignment;
-	if (dev->max_discard_sectors)
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, dev->queue);
 	if (dev->secure_discard)
 		blk_queue_flag_set(QUEUE_FLAG_SECERASE, dev->queue);
 
diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h
index f82fbb4bbda8..1f7e1c8fd4d9 100644
--- a/drivers/block/rnbd/rnbd-srv-dev.h
+++ b/drivers/block/rnbd/rnbd-srv-dev.h
@@ -49,9 +49,6 @@ static inline int rnbd_dev_get_secure_discard(const struct rnbd_dev *dev)
 
 static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev)
 {
-	if (!blk_queue_discard(bdev_get_queue(dev->bdev)))
-		return 0;
-
 	return bdev_max_discard_sectors(dev->bdev);
 }
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index a8bcf3f664af..6ccf15253dee 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -888,8 +888,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 			v = sg_elems;
 		blk_queue_max_discard_segments(q,
 					       min(v, MAX_DISCARD_SEGMENTS));
-
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 	}
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 8b691fe50475..83cd08041e6b 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -583,7 +583,7 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info
 	if (!xenbus_read_unsigned(dev->nodename, "discard-enable", 1))
 		return;
 
-	if (blk_queue_discard(q)) {
+	if (bdev_max_discard_sectors(bdev)) {
 		err = xenbus_printf(xbt, dev->nodename,
 			"discard-granularity", "%u",
 			q->limits.discard_granularity);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 003056d4f7f5..e13cb4d48f1e 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -944,7 +944,6 @@ static void blkif_set_queue_limits(struct blkfront_info *info)
 	blk_queue_flag_set(QUEUE_FLAG_VIRT, rq);
 
 	if (info->feature_discard) {
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, rq);
 		blk_queue_max_discard_sectors(rq, get_capacity(gd));
 		rq->limits.discard_granularity = info->discard_granularity ?:
 						 info->physical_sector_size;
@@ -1606,7 +1605,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
-				blk_queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
+				blk_queue_max_discard_sectors(rq, 0);
 				blk_queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
 			}
 			break;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e9474b02012d..59ff444bf6c7 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1952,7 +1952,6 @@ static int zram_add(void)
 	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
 	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
 	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, zram->disk->queue);
 
 	/*
 	 * zram_bio_discard() will clear all logical blocks if logical block
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index fdd0194f84dd..e27f67f06a42 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1005,7 +1005,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 		bio_get(s->iop.bio);
 
 		if (bio_op(bio) == REQ_OP_DISCARD &&
-		    !blk_queue_discard(bdev_get_queue(dc->bdev)))
+		    !bdev_max_discard_sectors(dc->bdev))
 			goto insert_data;
 
 		/* I/O request sent to backing device */
@@ -1115,7 +1115,7 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio,
 	bio->bi_private = ddip;
 
 	if ((bio_op(bio) == REQ_OP_DISCARD) &&
-	    !blk_queue_discard(bdev_get_queue(dc->bdev)))
+	    !bdev_max_discard_sectors(dc->bdev))
 		bio->bi_end_io(bio);
 	else
 		submit_bio_noacct(bio);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index bf3de149d3c9..2f49e31142f6 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -973,7 +973,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, d->disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, d->disk->queue);
 
 	blk_queue_write_cache(q, true, true);
 
@@ -2350,7 +2349,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 	ca->bdev->bd_holder = ca;
 	ca->sb_disk = sb_disk;
 
-	if (blk_queue_discard(bdev_get_queue(bdev)))
+	if (bdev_max_discard_sectors((bdev)))
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
 	ret = cache_alloc(ca);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index d1029d71ff3b..c6f677059214 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -1151,7 +1151,7 @@ STORE(__bch_cache)
 	if (attr == &sysfs_discard) {
 		bool v = strtoul_or_return(buf);
 
-		if (blk_queue_discard(bdev_get_queue(ca->bdev)))
+		if (bdev_max_discard_sectors(ca->bdev))
 			ca->discard = v;
 
 		if (v != CACHE_DISCARD(&ca->sb)) {
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 780a61bc6cc0..28c5de8eca4a 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -3329,13 +3329,6 @@ static int cache_iterate_devices(struct dm_target *ti,
 	return r;
 }
 
-static bool origin_dev_supports_discard(struct block_device *origin_bdev)
-{
-	struct request_queue *q = bdev_get_queue(origin_bdev);
-
-	return blk_queue_discard(q);
-}
-
 /*
  * If discard_passdown was enabled verify that the origin device
  * supports discards.  Disable discard_passdown if not.
@@ -3349,7 +3342,7 @@ static void disable_passdown_if_not_supported(struct cache *cache)
 	if (!cache->features.discard_passdown)
 		return;
 
-	if (!origin_dev_supports_discard(origin_bdev))
+	if (!bdev_max_discard_sectors(origin_bdev))
 		reason = "discard unsupported";
 
 	else if (origin_limits->max_discard_sectors < cache->sectors_per_block)
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index 128316a73d01..811b0a5379d0 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -2016,13 +2016,6 @@ static void clone_resume(struct dm_target *ti)
 	do_waker(&clone->waker.work);
 }
 
-static bool bdev_supports_discards(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	return (q && blk_queue_discard(q));
-}
-
 /*
  * If discard_passdown was enabled verify that the destination device supports
  * discards. Disable discard_passdown if not.
@@ -2036,7 +2029,7 @@ static void disable_passdown_if_not_supported(struct clone *clone)
 	if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags))
 		return;
 
-	if (!bdev_supports_discards(dest_dev))
+	if (!bdev_max_discard_sectors(dest_dev))
 		reason = "discard unsupported";
 	else if (dest_limits->max_discard_sectors < clone->region_size)
 		reason = "max discard sectors smaller than a region";
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index c9d036d6bb2e..e194226c89e5 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -866,9 +866,8 @@ static int log_writes_message(struct dm_target *ti, unsigned argc, char **argv,
 static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct log_writes_c *lc = ti->private;
-	struct request_queue *q = bdev_get_queue(lc->dev->bdev);
 
-	if (!q || !blk_queue_discard(q)) {
+	if (!bdev_max_discard_sectors(lc->dev->bdev)) {
 		lc->device_supports_discard = false;
 		limits->discard_granularity = lc->sectorsize;
 		limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 2b26435a6946..9526ccbedafb 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -2963,13 +2963,8 @@ static void configure_discard_support(struct raid_set *rs)
 	raid456 = rs_is_raid456(rs);
 
 	for (i = 0; i < rs->raid_disks; i++) {
-		struct request_queue *q;
-
-		if (!rs->dev[i].rdev.bdev)
-			continue;
-
-		q = bdev_get_queue(rs->dev[i].rdev.bdev);
-		if (!q || !blk_queue_discard(q))
+		if (!rs->dev[i].rdev.bdev ||
+		    !bdev_max_discard_sectors(rs->dev[i].rdev.bdev))
 			return;
 
 		if (raid456) {
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index d46839faa0ca..0dff6907fd00 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1888,9 +1888,7 @@ static bool dm_table_supports_nowait(struct dm_table *t)
 static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev,
 				      sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return !blk_queue_discard(q);
+	return !bdev_max_discard_sectors(dev->bdev);
 }
 
 static bool dm_table_supports_discards(struct dm_table *t)
@@ -1970,15 +1968,12 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
 
 	if (!dm_table_supports_discards(t)) {
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
-		/* Must also clear discard limits... */
 		q->limits.max_discard_sectors = 0;
 		q->limits.max_hw_discard_sectors = 0;
 		q->limits.discard_granularity = 0;
 		q->limits.discard_alignment = 0;
 		q->limits.discard_misaligned = 0;
-	} else
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	}
 
 	if (dm_table_supports_secure_erase(t))
 		blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 4d25d0e27031..eded4bcc4545 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2802,13 +2802,6 @@ static void requeue_bios(struct pool *pool)
 /*----------------------------------------------------------------
  * Binding of control targets to a pool object
  *--------------------------------------------------------------*/
-static bool data_dev_supports_discard(struct pool_c *pt)
-{
-	struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
-
-	return blk_queue_discard(q);
-}
-
 static bool is_factor(sector_t block_size, uint32_t n)
 {
 	return !sector_div(block_size, n);
@@ -2828,7 +2821,7 @@ static void disable_passdown_if_not_supported(struct pool_c *pt)
 	if (!pt->adjusted_pf.discard_passdown)
 		return;
 
-	if (!data_dev_supports_discard(pt))
+	if (!bdev_max_discard_sectors(pt->data_dev->bdev))
 		reason = "discard unsupported";
 
 	else if (data_limits->max_discard_sectors < pool->sectors_per_block)
@@ -4057,8 +4050,6 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 		/*
 		 * Must explicitly disallow stacking discard limits otherwise the
 		 * block layer will stack them if pool's data device has support.
-		 * QUEUE_FLAG_DISCARD wouldn't be set but there is no way for the
-		 * user to see that, so make sure to set all discard limits to 0.
 		 */
 		limits->discard_granularity = 0;
 		return;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 82957bd460e8..39081338ca61 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -955,7 +955,6 @@ void disable_discard(struct mapped_device *md)
 
 	/* device doesn't really support DISCARD, disable it */
 	limits->max_discard_sectors = 0;
-	blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue);
 }
 
 void disable_write_zeroes(struct mapped_device *md)
@@ -982,7 +981,7 @@ static void clone_endio(struct bio *bio)
 
 	if (unlikely(error == BLK_STS_TARGET)) {
 		if (bio_op(bio) == REQ_OP_DISCARD &&
-		    !q->limits.max_discard_sectors)
+		    !bdev_max_discard_sectors(bio->bi_bdev))
 			disable_discard(md);
 		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
 			 !q->limits.max_write_zeroes_sectors)
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 0f55b079371b..138a3b25c5c8 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -64,7 +64,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 	struct linear_conf *conf;
 	struct md_rdev *rdev;
 	int i, cnt;
-	bool discard_supported = false;
 
 	conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL);
 	if (!conf)
@@ -96,9 +95,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 
 		conf->array_sectors += rdev->sectors;
 		cnt++;
-
-		if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
-			discard_supported = true;
 	}
 	if (cnt != raid_disks) {
 		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
@@ -106,11 +102,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 		goto out;
 	}
 
-	if (!discard_supported)
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue);
-	else
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
-
 	/*
 	 * Here we calculate the device offsets.
 	 */
@@ -252,7 +243,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 		start_sector + data_offset;
 
 	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-		     !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) {
+		     !bdev_max_discard_sectors(bio->bi_bdev))) {
 		/* Just ignore it */
 		bio_endio(bio);
 	} else {
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index b21e101183f4..7231f5e1eaa7 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -399,7 +399,6 @@ static int raid0_run(struct mddev *mddev)
 	conf = mddev->private;
 	if (mddev->queue) {
 		struct md_rdev *rdev;
-		bool discard_supported = false;
 
 		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
@@ -412,13 +411,7 @@ static int raid0_run(struct mddev *mddev)
 		rdev_for_each(rdev, mddev) {
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
-			if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
-				discard_supported = true;
 		}
-		if (!discard_supported)
-			blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue);
-		else
-			blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
 	}
 
 	/* calculate array device size */
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index b7b21a4793d4..5aed2c8b746e 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -806,7 +806,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 		if (test_bit(Faulty, &rdev->flags)) {
 			bio_io_error(bio);
 		} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-				    !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
+				    !bdev_max_discard_sectors(bio->bi_bdev)))
 			/* Just ignore it */
 			bio_endio(bio);
 		else
@@ -1830,8 +1830,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			break;
 		}
 	}
-	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
 	print_conf(conf);
 	return err;
 }
@@ -3110,7 +3108,6 @@ static int raid1_run(struct mddev *mddev)
 	int i;
 	struct md_rdev *rdev;
 	int ret;
-	bool discard_supported = false;
 
 	if (mddev->level != 1) {
 		pr_warn("md/raid1:%s: raid level not set to mirroring (%d)\n",
@@ -3145,8 +3142,6 @@ static int raid1_run(struct mddev *mddev)
 			continue;
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
-		if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
-			discard_supported = true;
 	}
 
 	mddev->degraded = 0;
@@ -3183,15 +3178,6 @@ static int raid1_run(struct mddev *mddev)
 
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
-	if (mddev->queue) {
-		if (discard_supported)
-			blk_queue_flag_set(QUEUE_FLAG_DISCARD,
-						mddev->queue);
-		else
-			blk_queue_flag_clear(QUEUE_FLAG_DISCARD,
-						  mddev->queue);
-	}
-
 	ret = md_integrity_register(mddev);
 	if (ret) {
 		md_unregister_thread(&mddev->thread);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0987916066f2..834eb3ba95a6 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -895,7 +895,7 @@ static void flush_pending_writes(struct r10conf *conf)
 			if (test_bit(Faulty, &rdev->flags)) {
 				bio_io_error(bio);
 			} else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
-					    !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
+					    !bdev_max_discard_sectors(bio->bi_bdev)))
 				/* Just ignore it */
 				bio_endio(bio);
 			else
@@ -1090,7 +1090,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		if (test_bit(Faulty, &rdev->flags)) {
 			bio_io_error(bio);
 		} else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
-				    !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
+				    !bdev_max_discard_sectors(bio->bi_bdev)))
 			/* Just ignore it */
 			bio_endio(bio);
 		else
@@ -2151,8 +2151,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		rcu_assign_pointer(p->rdev, rdev);
 		break;
 	}
-	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
 
 	print_conf(conf);
 	return err;
@@ -4076,7 +4074,6 @@ static int raid10_run(struct mddev *mddev)
 	sector_t size;
 	sector_t min_offset_diff = 0;
 	int first = 1;
-	bool discard_supported = false;
 
 	if (mddev_init_writes_pending(mddev) < 0)
 		return -ENOMEM;
@@ -4147,20 +4144,9 @@ static int raid10_run(struct mddev *mddev)
 					  rdev->data_offset << 9);
 
 		disk->head_position = 0;
-
-		if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
-			discard_supported = true;
 		first = 0;
 	}
 
-	if (mddev->queue) {
-		if (discard_supported)
-			blk_queue_flag_set(QUEUE_FLAG_DISCARD,
-						mddev->queue);
-		else
-			blk_queue_flag_clear(QUEUE_FLAG_DISCARD,
-						  mddev->queue);
-	}
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf, -1)) {
 		pr_err("md/raid10:%s: not enough operational mirrors.\n",
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index a7d50ff9020a..c3cbf9a574a3 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1318,7 +1318,7 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
 
 	r5l_write_super(log, end);
 
-	if (!blk_queue_discard(bdev_get_queue(bdev)))
+	if (!bdev_max_discard_sectors(bdev))
 		return;
 
 	mddev = log->rdev->mddev;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0bbae0e63866..59f91e392a2a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7776,14 +7776,10 @@ static int raid5_run(struct mddev *mddev)
 		 * A better idea might be to turn DISCARD into WRITE_ZEROES
 		 * requests, as that is required to be safe.
 		 */
-		if (devices_handle_discard_safely &&
-		    mddev->queue->limits.max_discard_sectors >= (stripe >> 9) &&
-		    mddev->queue->limits.discard_granularity >= stripe)
-			blk_queue_flag_set(QUEUE_FLAG_DISCARD,
-						mddev->queue);
-		else
-			blk_queue_flag_clear(QUEUE_FLAG_DISCARD,
-						mddev->queue);
+		if (!devices_handle_discard_safely ||
+		    mddev->queue->limits.max_discard_sectors < (stripe >> 9) ||
+		    mddev->queue->limits.discard_granularity < stripe)
+			blk_queue_max_discard_sectors(mddev->queue, 0);
 
 		blk_queue_max_hw_sectors(mddev->queue, UINT_MAX);
 	}
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index c69b2d9df6f1..cac6315010a3 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -183,7 +183,6 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	if (!max_discard)
 		return;
 
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 	blk_queue_max_discard_sectors(q, max_discard);
 	q->limits.discard_granularity = card->pref_erase << 9;
 	/* granularity must not be greater than max. discard */
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 64d2b093f114..f73172111465 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -377,7 +377,6 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
 
 	if (tr->discard) {
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, new->rq);
 		blk_queue_max_discard_sectors(new->rq, UINT_MAX);
 		new->rq->limits.discard_granularity = tr->blksize;
 	}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e1846d04817f..b9b0fbde97c8 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1621,7 +1621,7 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 	u32 size = queue_logical_block_size(queue);
 
 	if (ctrl->max_discard_sectors == 0) {
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue);
+		blk_queue_max_discard_sectors(queue, 0);
 		return;
 	}
 
@@ -1632,7 +1632,7 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 	queue->limits.discard_granularity = size;
 
 	/* If discard is already enabled, don't reset queue limits */
-	if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
+	if (queue->limits.max_discard_sectors)
 		return;
 
 	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index e084f4dedddd..8bd5665db919 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -791,7 +791,6 @@ static void dasd_fba_setup_blk_queue(struct dasd_block *block)
 
 	blk_queue_max_discard_sectors(q, max_discard_sectors);
 	blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 }
 
 static int dasd_fba_pe_handler(struct dasd_device *device,
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index dc6e55761fd1..9694e2cfaf9a 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -797,7 +797,6 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	case SD_LBP_FULL:
 	case SD_LBP_DISABLE:
 		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 		return;
 
 	case SD_LBP_UNMAP:
@@ -830,7 +829,6 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	}
 
 	blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9));
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 }
 
 static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index c3e25bac90d5..6cb9f8784327 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -838,7 +838,7 @@ bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
 	struct request_queue *q = bdev_get_queue(bdev);
 	int block_size = bdev_logical_block_size(bdev);
 
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(bdev))
 		return false;
 
 	attrib->max_unmap_lba_count =
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6aa92f84f465..aba616ff953f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1291,7 +1291,7 @@ static int do_discard_extent(struct btrfs_io_stripe *stripe, u64 *bytes)
 		ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len,
 					      &discarded);
 		discarded += src_disc;
-	} else if (blk_queue_discard(bdev_get_queue(stripe->dev->bdev))) {
+	} else if (bdev_max_discard_sectors(stripe->dev->bdev)) {
 		ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded);
 	} else {
 		ret = 0;
@@ -5987,7 +5987,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
 	*trimmed = 0;
 
 	/* Discard not supported = nothing to do. */
-	if (!blk_queue_discard(bdev_get_queue(device->bdev)))
+	if (!bdev_max_discard_sectors(device->bdev))
 		return 0;
 
 	/* Not writable = nothing to do. */
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index be6c24577dbe..db2b52c20ca8 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -501,7 +501,7 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
 		if (!device->bdev)
 			continue;
 		q = bdev_get_queue(device->bdev);
-		if (blk_queue_discard(q)) {
+		if (bdev_max_discard_sectors(device->bdev)) {
 			num_devices++;
 			minlen = min_t(u64, q->limits.discard_granularity,
 				     minlen);
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 2f5130059236..765e4f63dd18 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -358,7 +358,7 @@ static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(inode->i_sb->s_bdev))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range)))
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index 8ca21e7917d1..be0788ecaf20 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -627,13 +627,9 @@ static int exfat_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (opts->allow_utime == (unsigned short)-1)
 		opts->allow_utime = ~opts->fs_dmask & 0022;
 
-	if (opts->discard) {
-		struct request_queue *q = bdev_get_queue(sb->s_bdev);
-
-		if (!blk_queue_discard(q)) {
-			exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard");
-			opts->discard = 0;
-		}
+	if (opts->discard && !bdev_max_discard_sectors(sb->s_bdev)) {
+		exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard");
+		opts->discard = 0;
 	}
 
 	sb->s_flags |= SB_NODIRATIME;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 992229ca2d83..6e3b9eea126f 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1044,7 +1044,6 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg)
 	__u32 flags = 0;
 	unsigned int flush_flags = 0;
 	struct super_block *sb = file_inode(filp)->i_sb;
-	struct request_queue *q;
 
 	if (copy_from_user(&flags, (__u32 __user *)arg,
 				sizeof(__u32)))
@@ -1065,10 +1064,8 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg)
 	if (flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID)
 		return -EINVAL;
 
-	q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev);
-	if (!q)
-		return -ENXIO;
-	if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q))
+	if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) &&
+	    !bdev_max_discard_sectors(EXT4_SB(sb)->s_journal->j_dev))
 		return -EOPNOTSUPP;
 
 	if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)
@@ -1393,14 +1390,13 @@ resizefs_out:
 
 	case FITRIM:
 	{
-		struct request_queue *q = bdev_get_queue(sb->s_bdev);
 		struct fstrim_range range;
 		int ret = 0;
 
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		if (!blk_queue_discard(q))
+		if (!bdev_max_discard_sectors(sb->s_bdev))
 			return -EOPNOTSUPP;
 
 		/*
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 81749eaddf4c..93f4e4e9e263 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5458,13 +5458,9 @@ no_journal:
 			goto failed_mount9;
 	}
 
-	if (test_opt(sb, DISCARD)) {
-		struct request_queue *q = bdev_get_queue(sb->s_bdev);
-		if (!blk_queue_discard(q))
-			ext4_msg(sb, KERN_WARNING,
-				 "mounting with \"discard\" option, but "
-				 "the device does not support discard");
-	}
+	if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev))
+		ext4_msg(sb, KERN_WARNING,
+			 "mounting with \"discard\" option, but the device does not support discard");
 
 	if (es->s_error_count)
 		mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index cd1e65bcf0b0..0ea9a5fa7c1d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4381,8 +4381,7 @@ static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
 
 static inline bool f2fs_bdev_support_discard(struct block_device *bdev)
 {
-	return blk_queue_discard(bdev_get_queue(bdev)) ||
-	       bdev_is_zoned(bdev);
+	return bdev_max_discard_sectors(bdev) || bdev_is_zoned(bdev);
 }
 
 static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi)
diff --git a/fs/fat/file.c b/fs/fat/file.c
index a5a309fcc7fa..e4c7d10e8012 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -133,7 +133,7 @@ static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(sb->s_bdev))
 		return -EOPNOTSUPP;
 
 	user_range = (struct fstrim_range __user *)arg;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index bf6051bdf1d1..3d1afb95a925 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1872,13 +1872,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 		goto out_fail;
 	}
 
-	if (sbi->options.discard) {
-		struct request_queue *q = bdev_get_queue(sb->s_bdev);
-		if (!blk_queue_discard(q))
-			fat_msg(sb, KERN_WARNING,
-					"mounting with \"discard\" option, but "
-					"the device does not support discard");
-	}
+	if (sbi->options.discard && !bdev_max_discard_sectors(sb->s_bdev))
+		fat_msg(sb, KERN_WARNING,
+			"mounting with \"discard\" option, but the device does not support discard");
 
 	fat_set_state(sb, 1, 0);
 	return 0;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 801ad9f4f2be..7f20ac9133bc 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1405,7 +1405,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
 		return -EROFS;
 
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(sdp->sd_vfs->s_bdev))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&r, argp, sizeof(r)))
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index fcacafa4510d..19d226cd4ff4 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1762,7 +1762,6 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags)
 	unsigned long block, log_offset; /* logical */
 	unsigned long long phys_block, block_start, block_stop; /* physical */
 	loff_t byte_start, byte_stop, byte_count;
-	struct request_queue *q = bdev_get_queue(journal->j_dev);
 
 	/* flags must be set to either discard or zeroout */
 	if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags ||
@@ -1770,10 +1769,8 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags)
 			(flags & JBD2_JOURNAL_FLUSH_ZEROOUT)))
 		return -EINVAL;
 
-	if (!q)
-		return -ENXIO;
-
-	if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q))
+	if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) &&
+	    !bdev_max_discard_sectors(journal->j_dev))
 		return -EOPNOTSUPP;
 
 	/*
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index 03a845ab4f00..357ae6e5c36e 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -117,7 +117,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		if (!blk_queue_discard(q)) {
+		if (!bdev_max_discard_sectors(sb->s_bdev)) {
 			jfs_warn("FITRIM not supported on device");
 			return -EOPNOTSUPP;
 		}
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index f1a13a74cddf..85d4f44f2ac4 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -372,19 +372,16 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
 		}
 
 		case Opt_discard:
-		{
-			struct request_queue *q = bdev_get_queue(sb->s_bdev);
 			/* if set to 1, even copying files will cause
 			 * trimming :O
 			 * -> user has more control over the online trimming
 			 */
 			sbi->minblks_trim = 64;
-			if (blk_queue_discard(q))
+			if (bdev_max_discard_sectors(sb->s_bdev))
 				*flag |= JFS_DISCARD;
 			else
 				pr_err("JFS: discard option not supported on device\n");
 			break;
-		}
 
 		case Opt_nodiscard:
 			*flag &= ~JFS_DISCARD;
@@ -392,10 +389,9 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
 
 		case Opt_discard_minblk:
 		{
-			struct request_queue *q = bdev_get_queue(sb->s_bdev);
 			char *minblks_trim = args[0].from;
 			int rc;
-			if (blk_queue_discard(q)) {
+			if (bdev_max_discard_sectors(sb->s_bdev)) {
 				*flag |= JFS_DISCARD;
 				rc = kstrtouint(minblks_trim, 0,
 						&sbi->minblks_trim);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index fec194a666f4..52b73f558fcb 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1059,7 +1059,7 @@ static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(nilfs->ns_bdev))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&range, argp, sizeof(range)))
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 787b53b984ee..e76323616933 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -28,7 +28,7 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(sbi->sb->s_bdev))
 		return -EOPNOTSUPP;
 
 	user_range = (struct fstrim_range __user *)arg;
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index cd30e81abbce..c734085bcce4 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -913,7 +913,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	}
 
 	rq = bdev_get_queue(bdev);
-	if (blk_queue_discard(rq) && rq->limits.discard_granularity) {
+	if (bdev_max_discard_sectors(bdev) && rq->limits.discard_granularity) {
 		sbi->discard_granularity = rq->limits.discard_granularity;
 		sbi->discard_granularity_mask_inv =
 			~(u64)(sbi->discard_granularity - 1);
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index f59461d85da4..9b78ef103ada 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -910,7 +910,7 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		if (!blk_queue_discard(q))
+		if (!bdev_max_discard_sectors(sb->s_bdev))
 			return -EOPNOTSUPP;
 
 		if (copy_from_user(&range, argp, sizeof(range)))
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 0191de8ce9ce..a4e6609d616b 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -162,7 +162,7 @@ xfs_ioc_trim(
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (!blk_queue_discard(q))
+	if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev))
 		return -EOPNOTSUPP;
 
 	/*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 54be9d64093e..a276b8111f63 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1608,14 +1608,10 @@ xfs_fs_fill_super(
 			goto out_filestream_unmount;
 	}
 
-	if (xfs_has_discard(mp)) {
-		struct request_queue *q = bdev_get_queue(sb->s_bdev);
-
-		if (!blk_queue_discard(q)) {
-			xfs_warn(mp, "mounting with \"discard\" option, but "
-					"the device does not support discard");
-			mp->m_features &= ~XFS_FEAT_DISCARD;
-		}
+	if (xfs_has_discard(mp) && !bdev_max_discard_sectors(sb->s_bdev)) {
+		xfs_warn(mp,
+	"mounting with \"discard\" option, but the device does not support discard");
+		mp->m_features &= ~XFS_FEAT_DISCARD;
 	}
 
 	if (xfs_has_reflink(mp)) {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ce16247d3afa..767ab22e1052 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -540,7 +540,6 @@ struct request_queue {
 #define QUEUE_FLAG_NONROT	6	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT		QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT	7	/* do disk/partitions IO accounting */
-#define QUEUE_FLAG_DISCARD	8	/* supports DISCARD */
 #define QUEUE_FLAG_NOXMERGES	9	/* No extended merges */
 #define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
 #define QUEUE_FLAG_SECERASE	11	/* supports secure erase */
@@ -582,7 +581,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 	test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
-#define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
 #define blk_queue_zone_resetall(q)	\
 	test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
 #define blk_queue_secure_erase(q) \
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4069f17a82c8..5d9cedf9e7b8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2957,20 +2957,6 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 	return nr_extents;
 }
 
-/*
- * Helper to sys_swapon determining if a given swap
- * backing device queue supports DISCARD operations.
- */
-static bool swap_discardable(struct swap_info_struct *si)
-{
-	struct request_queue *q = bdev_get_queue(si->bdev);
-
-	if (!blk_queue_discard(q))
-		return false;
-
-	return true;
-}
-
 SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 {
 	struct swap_info_struct *p;
@@ -3132,7 +3118,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 					 sizeof(long),
 					 GFP_KERNEL);
 
-	if (p->bdev && (swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) {
+	if ((swap_flags & SWAP_FLAG_DISCARD) &&
+	    p->bdev && bdev_max_discard_sectors(p->bdev)) {
 		/*
 		 * When discard is enabled for swap with no particular
 		 * policy flagged, we set all swap discard flags here in
-- 
cgit v1.2.3


From 7b47ef52d0a2025fd1408a8a0990933b8e1e510f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:56 +0200
Subject: block: add a bdev_discard_granularity helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Abstract away implementation details from file systems by providing a
block_device based helper to retrieve the discard granularity.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com> [drbd]
Acked-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Acked-by: David Sterba <dsterba@suse.com> [btrfs]
Link: https://lore.kernel.org/r/20220415045258.199825-26-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-lib.c                     |  5 ++---
 drivers/block/drbd/drbd_nl.c        |  9 +++++----
 drivers/block/drbd/drbd_receiver.c  |  3 +--
 drivers/block/loop.c                |  2 +-
 drivers/target/target_core_device.c |  3 +--
 fs/btrfs/ioctl.c                    | 12 ++++--------
 fs/exfat/file.c                     |  3 +--
 fs/ext4/mballoc.c                   |  6 +++---
 fs/f2fs/file.c                      |  3 +--
 fs/fat/file.c                       |  3 +--
 fs/gfs2/rgrp.c                      |  7 +++----
 fs/jfs/ioctl.c                      |  3 +--
 fs/nilfs2/ioctl.c                   |  4 ++--
 fs/ntfs3/file.c                     |  4 ++--
 fs/ntfs3/super.c                    |  6 ++----
 fs/ocfs2/ioctl.c                    |  3 +--
 fs/xfs/xfs_discard.c                |  4 ++--
 include/linux/blkdev.h              |  5 +++++
 18 files changed, 38 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 8b4b66d3a9bf..43aa4d7fe859 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -12,8 +12,7 @@
 
 static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 {
-	unsigned int discard_granularity =
-		bdev_get_queue(bdev)->limits.discard_granularity;
+	unsigned int discard_granularity = bdev_discard_granularity(bdev);
 	sector_t granularity_aligned_sector;
 
 	if (bdev_is_partition(bdev))
@@ -59,7 +58,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	}
 
 	/* In case the discard granularity isn't set by buggy device driver */
-	if (WARN_ON_ONCE(!q->limits.discard_granularity)) {
+	if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) {
 		char dev_name[BDEVNAME_SIZE];
 
 		bdevname(bdev, dev_name);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 0678ceb50579..a6280dcb3767 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1425,7 +1425,6 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 			       struct drbd_backing_dev *nbc)
 {
 	struct block_device *bdev = nbc->backing_bdev;
-	struct request_queue *q = bdev->bd_disk->queue;
 
 	if (disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
 		disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
@@ -1442,12 +1441,14 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 	if (disk_conf->rs_discard_granularity) {
 		int orig_value = disk_conf->rs_discard_granularity;
 		sector_t discard_size = bdev_max_discard_sectors(bdev) << 9;
+		unsigned int discard_granularity = bdev_discard_granularity(bdev);
 		int remainder;
 
-		if (q->limits.discard_granularity > disk_conf->rs_discard_granularity)
-			disk_conf->rs_discard_granularity = q->limits.discard_granularity;
+		if (discard_granularity > disk_conf->rs_discard_granularity)
+			disk_conf->rs_discard_granularity = discard_granularity;
 
-		remainder = disk_conf->rs_discard_granularity % q->limits.discard_granularity;
+		remainder = disk_conf->rs_discard_granularity %
+				discard_granularity;
 		disk_conf->rs_discard_granularity += remainder;
 
 		if (disk_conf->rs_discard_granularity > discard_size)
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 8a4a47da56fe..275c53c7b629 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1511,7 +1511,6 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
 int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, int flags)
 {
 	struct block_device *bdev = device->ldev->backing_bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t tmp, nr;
 	unsigned int max_discard_sectors, granularity;
 	int alignment;
@@ -1521,7 +1520,7 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u
 		goto zero_out;
 
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
+	granularity = max(bdev_discard_granularity(bdev) >> 9, 1U);
 	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
 
 	max_discard_sectors = min(bdev_max_discard_sectors(bdev), (1U << 22));
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 0e061c9896ef..976cf987b392 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -759,7 +759,7 @@ static void loop_config_discard(struct loop_device *lo)
 		struct request_queue *backingq = bdev_get_queue(I_BDEV(inode));
 
 		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
-		granularity = backingq->limits.discard_granularity ?:
+		granularity = bdev_discard_granularity(I_BDEV(inode)) ?:
 			queue_physical_block_size(backingq);
 
 	/*
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 6cb9f8784327..25f33eb25337 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -835,7 +835,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
 				       struct block_device *bdev)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
 	int block_size = bdev_logical_block_size(bdev);
 
 	if (!bdev_max_discard_sectors(bdev))
@@ -847,7 +846,7 @@ bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
 	 * Currently hardcoded to 1 in Linux/SCSI code..
 	 */
 	attrib->max_unmap_block_desc_count = 1;
-	attrib->unmap_granularity = q->limits.discard_granularity / block_size;
+	attrib->unmap_granularity = bdev_discard_granularity(bdev) / block_size;
 	attrib->unmap_granularity_alignment =
 		bdev_discard_alignment(bdev) / block_size;
 	return true;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index db2b52c20ca8..4b28aaea2702 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -468,7 +468,6 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
 					void __user *arg)
 {
 	struct btrfs_device *device;
-	struct request_queue *q;
 	struct fstrim_range range;
 	u64 minlen = ULLONG_MAX;
 	u64 num_devices = 0;
@@ -498,14 +497,11 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
 				dev_list) {
-		if (!device->bdev)
+		if (!device->bdev || !bdev_max_discard_sectors(device->bdev))
 			continue;
-		q = bdev_get_queue(device->bdev);
-		if (bdev_max_discard_sectors(device->bdev)) {
-			num_devices++;
-			minlen = min_t(u64, q->limits.discard_granularity,
-				     minlen);
-		}
+		num_devices++;
+		minlen = min_t(u64, bdev_discard_granularity(device->bdev),
+				    minlen);
 	}
 	rcu_read_unlock();
 
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 765e4f63dd18..20d4e47f57ab 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -351,7 +351,6 @@ out:
 
 static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg)
 {
-	struct request_queue *q = bdev_get_queue(inode->i_sb->s_bdev);
 	struct fstrim_range range;
 	int ret = 0;
 
@@ -365,7 +364,7 @@ static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg)
 		return -EFAULT;
 
 	range.minlen = max_t(unsigned int, range.minlen,
-				q->limits.discard_granularity);
+				bdev_discard_granularity(inode->i_sb->s_bdev));
 
 	ret = exfat_trim_fs(inode, &range);
 	if (ret < 0)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c3668c977cd9..6d1820536d88 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -6455,7 +6455,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
  */
 int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 {
-	struct request_queue *q = bdev_get_queue(sb->s_bdev);
+	unsigned int discard_granularity = bdev_discard_granularity(sb->s_bdev);
 	struct ext4_group_info *grp;
 	ext4_group_t group, first_group, last_group;
 	ext4_grpblk_t cnt = 0, first_cluster, last_cluster;
@@ -6475,9 +6475,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	    range->len < sb->s_blocksize)
 		return -EINVAL;
 	/* No point to try to trim less than discard granularity */
-	if (range->minlen < q->limits.discard_granularity) {
+	if (range->minlen < discard_granularity) {
 		minlen = EXT4_NUM_B2C(EXT4_SB(sb),
-			q->limits.discard_granularity >> sb->s_blocksize_bits);
+				discard_granularity >> sb->s_blocksize_bits);
 		if (minlen > EXT4_CLUSTERS_PER_GROUP(sb))
 			goto out;
 	}
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5b89af0f27f0..8053d99f3920 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2285,7 +2285,6 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct super_block *sb = inode->i_sb;
-	struct request_queue *q = bdev_get_queue(sb->s_bdev);
 	struct fstrim_range range;
 	int ret;
 
@@ -2304,7 +2303,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 		return ret;
 
 	range.minlen = max((unsigned int)range.minlen,
-				q->limits.discard_granularity);
+			   bdev_discard_granularity(sb->s_bdev));
 	ret = f2fs_trim_fs(F2FS_SB(sb), &range);
 	mnt_drop_write_file(filp);
 	if (ret < 0)
diff --git a/fs/fat/file.c b/fs/fat/file.c
index e4c7d10e8012..bf91f977debe 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -127,7 +127,6 @@ static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg)
 	struct super_block *sb = inode->i_sb;
 	struct fstrim_range __user *user_range;
 	struct fstrim_range range;
-	struct request_queue *q = bdev_get_queue(sb->s_bdev);
 	int err;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -141,7 +140,7 @@ static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg)
 		return -EFAULT;
 
 	range.minlen = max_t(unsigned int, range.minlen,
-			     q->limits.discard_granularity);
+			     bdev_discard_granularity(sb->s_bdev));
 
 	err = fat_trim_fs(inode, &range);
 	if (err < 0)
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 7f20ac9133bc..6d26bb525484 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1386,7 +1386,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 {
 	struct inode *inode = file_inode(filp);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct request_queue *q = bdev_get_queue(sdp->sd_vfs->s_bdev);
+	struct block_device *bdev = sdp->sd_vfs->s_bdev;
 	struct buffer_head *bh;
 	struct gfs2_rgrpd *rgd;
 	struct gfs2_rgrpd *rgd_end;
@@ -1405,7 +1405,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
 		return -EROFS;
 
-	if (!bdev_max_discard_sectors(sdp->sd_vfs->s_bdev))
+	if (!bdev_max_discard_sectors(bdev))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&r, argp, sizeof(r)))
@@ -1418,8 +1418,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 	start = r.start >> bs_shift;
 	end = start + (r.len >> bs_shift);
 	minlen = max_t(u64, r.minlen, sdp->sd_sb.sb_bsize);
-	minlen = max_t(u64, minlen,
-		       q->limits.discard_granularity) >> bs_shift;
+	minlen = max_t(u64, minlen, bdev_discard_granularity(bdev)) >> bs_shift;
 
 	if (end <= start || minlen > sdp->sd_max_rg_data)
 		return -EINVAL;
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index 357ae6e5c36e..1e7b177ece60 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -110,7 +110,6 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case FITRIM:
 	{
 		struct super_block *sb = inode->i_sb;
-		struct request_queue *q = bdev_get_queue(sb->s_bdev);
 		struct fstrim_range range;
 		s64 ret = 0;
 
@@ -127,7 +126,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			return -EFAULT;
 
 		range.minlen = max_t(unsigned int, range.minlen,
-			q->limits.discard_granularity);
+				     bdev_discard_granularity(sb->s_bdev));
 
 		ret = jfs_ioc_trim(inode, &range);
 		if (ret < 0)
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 52b73f558fcb..87e1004b606d 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1052,7 +1052,6 @@ out:
 static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
 {
 	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
-	struct request_queue *q = bdev_get_queue(nilfs->ns_bdev);
 	struct fstrim_range range;
 	int ret;
 
@@ -1065,7 +1064,8 @@ static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
 	if (copy_from_user(&range, argp, sizeof(range)))
 		return -EFAULT;
 
-	range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity);
+	range.minlen = max_t(u64, range.minlen,
+			     bdev_discard_granularity(nilfs->ns_bdev));
 
 	down_read(&nilfs->ns_segctor_sem);
 	ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range);
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index e76323616933..15806eeae217 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -22,7 +22,6 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg)
 {
 	struct fstrim_range __user *user_range;
 	struct fstrim_range range;
-	struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev);
 	int err;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -35,7 +34,8 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg)
 	if (copy_from_user(&range, user_range, sizeof(range)))
 		return -EFAULT;
 
-	range.minlen = max_t(u32, range.minlen, q->limits.discard_granularity);
+	range.minlen = max_t(u32, range.minlen,
+			     bdev_discard_granularity(sbi->sb->s_bdev));
 
 	err = ntfs_trim_fs(sbi, &range);
 	if (err < 0)
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index c734085bcce4..5f2e414cfa79 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -882,7 +882,6 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	int err;
 	struct ntfs_sb_info *sbi = sb->s_fs_info;
 	struct block_device *bdev = sb->s_bdev;
-	struct request_queue *rq;
 	struct inode *inode;
 	struct ntfs_inode *ni;
 	size_t i, tt;
@@ -912,9 +911,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
 		goto out;
 	}
 
-	rq = bdev_get_queue(bdev);
-	if (bdev_max_discard_sectors(bdev) && rq->limits.discard_granularity) {
-		sbi->discard_granularity = rq->limits.discard_granularity;
+	if (bdev_max_discard_sectors(bdev) && bdev_discard_granularity(bdev)) {
+		sbi->discard_granularity = bdev_discard_granularity(bdev);
 		sbi->discard_granularity_mask_inv =
 			~(u64)(sbi->discard_granularity - 1);
 	}
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 9b78ef103ada..afd54ec66103 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -903,7 +903,6 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case FITRIM:
 	{
 		struct super_block *sb = inode->i_sb;
-		struct request_queue *q = bdev_get_queue(sb->s_bdev);
 		struct fstrim_range range;
 		int ret = 0;
 
@@ -916,7 +915,7 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (copy_from_user(&range, argp, sizeof(range)))
 			return -EFAULT;
 
-		range.minlen = max_t(u64, q->limits.discard_granularity,
+		range.minlen = max_t(u64, bdev_discard_granularity(sb->s_bdev),
 				     range.minlen);
 		ret = ocfs2_trim_fs(sb, &range);
 		if (ret < 0)
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index a4e6609d616b..e2ada115c23f 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -152,8 +152,8 @@ xfs_ioc_trim(
 	struct xfs_mount		*mp,
 	struct fstrim_range __user	*urange)
 {
-	struct request_queue	*q = bdev_get_queue(mp->m_ddev_targp->bt_bdev);
-	unsigned int		granularity = q->limits.discard_granularity;
+	unsigned int		granularity =
+		bdev_discard_granularity(mp->m_ddev_targp->bt_bdev);
 	struct fstrim_range	range;
 	xfs_daddr_t		start, end, minlen;
 	xfs_agnumber_t		start_agno, end_agno, agno;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 767ab22e1052..f1cf557ea20e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1257,6 +1257,11 @@ static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev)
 	return bdev_get_queue(bdev)->limits.max_discard_sectors;
 }
 
+static inline unsigned int bdev_discard_granularity(struct block_device *bdev)
+{
+	return bdev_get_queue(bdev)->limits.discard_granularity;
+}
+
 static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-- 
cgit v1.2.3


From 44abff2c0b970ae3d310b97617525dc01f248d7c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Apr 2022 06:52:57 +0200
Subject: block: decouple REQ_OP_SECURE_ERASE from REQ_OP_DISCARD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Secure erase is a very different operation from discard in that it is
a data integrity operation vs hint.  Fully split the limits and helper
infrastructure to make the separation more clear.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com> [drbd]
Acked-by: Ryusuke Konishi <konishi.ryusuke@gmail.com> [nifs2]
Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> [f2fs]
Acked-by: Coly Li <colyli@suse.de> [bcache]
Acked-by: David Sterba <dsterba@suse.com> [btrfs]
Acked-by: Chao Yu <chao@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220415045258.199825-27-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c                    |  2 +-
 block/blk-lib.c                     | 64 ++++++++++++++++++++++++++-----------
 block/blk-mq-debugfs.c              |  1 -
 block/blk-settings.c                | 16 +++++++++-
 block/fops.c                        |  2 +-
 block/ioctl.c                       | 43 ++++++++++++++++++++-----
 drivers/block/drbd/drbd_receiver.c  |  5 +--
 drivers/block/rnbd/rnbd-clt.c       |  4 +--
 drivers/block/rnbd/rnbd-srv-dev.h   |  2 +-
 drivers/block/xen-blkback/blkback.c | 15 +++++----
 drivers/block/xen-blkback/xenbus.c  |  5 +--
 drivers/block/xen-blkfront.c        |  5 +--
 drivers/md/bcache/alloc.c           |  2 +-
 drivers/md/dm-table.c               |  8 ++---
 drivers/md/dm-thin.c                |  4 +--
 drivers/md/md.c                     |  2 +-
 drivers/md/raid5-cache.c            |  6 ++--
 drivers/mmc/core/queue.c            |  2 +-
 drivers/nvme/target/io-cmd-bdev.c   |  2 +-
 drivers/target/target_core_file.c   |  2 +-
 drivers/target/target_core_iblock.c |  2 +-
 fs/btrfs/extent-tree.c              |  4 +--
 fs/ext4/mballoc.c                   |  2 +-
 fs/f2fs/file.c                      | 16 +++++-----
 fs/f2fs/segment.c                   |  2 +-
 fs/jbd2/journal.c                   |  2 +-
 fs/nilfs2/sufile.c                  |  4 +--
 fs/nilfs2/the_nilfs.c               |  4 +--
 fs/ntfs3/super.c                    |  2 +-
 fs/xfs/xfs_discard.c                |  2 +-
 fs/xfs/xfs_log_cil.c                |  2 +-
 include/linux/blkdev.h              | 27 +++++++++-------
 mm/swapfile.c                       |  6 ++--
 33 files changed, 168 insertions(+), 99 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index b5c3a8049134..ee18b6a699bd 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -824,7 +824,7 @@ void submit_bio_noacct(struct bio *bio)
 			goto not_supported;
 		break;
 	case REQ_OP_SECURE_ERASE:
-		if (!blk_queue_secure_erase(q))
+		if (!bdev_max_secure_erase_sectors(bdev))
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_APPEND:
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 43aa4d7fe859..09b7e1200c0f 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -36,26 +36,15 @@ static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 }
 
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int flags,
-		struct bio **biop)
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
-	unsigned int op;
 	sector_t bs_mask;
 
 	if (bdev_read_only(bdev))
 		return -EPERM;
-
-	if (flags & BLKDEV_DISCARD_SECURE) {
-		if (!blk_queue_secure_erase(q))
-			return -EOPNOTSUPP;
-		op = REQ_OP_SECURE_ERASE;
-	} else {
-		if (!bdev_max_discard_sectors(bdev))
-			return -EOPNOTSUPP;
-		op = REQ_OP_DISCARD;
-	}
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
 
 	/* In case the discard granularity isn't set by buggy device driver */
 	if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) {
@@ -77,7 +66,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t req_sects =
 			min(nr_sects, bio_discard_limit(bdev, sector));
 
-		bio = blk_next_bio(bio, bdev, 0, op, gfp_mask);
+		bio = blk_next_bio(bio, bdev, 0, REQ_OP_DISCARD, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_iter.bi_size = req_sects << 9;
 		sector += req_sects;
@@ -103,21 +92,19 @@ EXPORT_SYMBOL(__blkdev_issue_discard);
  * @sector:	start sector
  * @nr_sects:	number of sectors to discard
  * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	BLKDEV_DISCARD_* flags to control behaviour
  *
  * Description:
  *    Issue a discard request for the sectors in question.
  */
 int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+		sector_t nr_sects, gfp_t gfp_mask)
 {
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 	int ret;
 
 	blk_start_plug(&plug);
-	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
-			&bio);
+	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, &bio);
 	if (!ret && bio) {
 		ret = submit_bio_wait(bio);
 		if (ret == -EOPNOTSUPP)
@@ -314,3 +301,42 @@ retry:
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_zeroout);
+
+int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp)
+{
+	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+	unsigned int max_sectors = bdev_max_secure_erase_sectors(bdev);
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	if (max_sectors == 0)
+		return -EOPNOTSUPP;
+	if ((sector | nr_sects) & bs_mask)
+		return -EINVAL;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
+	blk_start_plug(&plug);
+	for (;;) {
+		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
+
+		bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp);
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_iter.bi_size = len;
+
+		sector += len << SECTOR_SHIFT;
+		nr_sects -= len << SECTOR_SHIFT;
+		if (!nr_sects) {
+			ret = submit_bio_wait(bio);
+			bio_put(bio);
+			break;
+		}
+		cond_resched();
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_secure_erase);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index fd111c500125..7e4136a60e1c 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -115,7 +115,6 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(IO_STAT),
 	QUEUE_FLAG_NAME(NOXMERGES),
 	QUEUE_FLAG_NAME(ADD_RANDOM),
-	QUEUE_FLAG_NAME(SECERASE),
 	QUEUE_FLAG_NAME(SAME_FORCE),
 	QUEUE_FLAG_NAME(DEAD),
 	QUEUE_FLAG_NAME(INIT_DONE),
diff --git a/block/blk-settings.c b/block/blk-settings.c
index fd83d674afd0..6ccceb421ed2 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -46,6 +46,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_zone_append_sectors = 0;
 	lim->max_discard_sectors = 0;
 	lim->max_hw_discard_sectors = 0;
+	lim->max_secure_erase_sectors = 0;
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
@@ -176,6 +177,18 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
+/**
+ * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
+ * @q:  the request queue for the device
+ * @max_sectors: maximum number of sectors to secure_erase
+ **/
+void blk_queue_max_secure_erase_sectors(struct request_queue *q,
+		unsigned int max_sectors)
+{
+	q->limits.max_secure_erase_sectors = max_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors);
+
 /**
  * blk_queue_max_write_zeroes_sectors - set max sectors for a single
  *                                      write zeroes
@@ -661,7 +674,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
 			t->discard_granularity;
 	}
-
+	t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors,
+						   b->max_secure_erase_sectors);
 	t->zone_write_granularity = max(t->zone_write_granularity,
 					b->zone_write_granularity);
 	t->zoned = max(t->zoned, b->zoned);
diff --git a/block/fops.c b/block/fops.c
index ba5e7d5ff9a5..e3643362c244 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -677,7 +677,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 		break;
 	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
 		error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT,
-					     len >> SECTOR_SHIFT, GFP_KERNEL, 0);
+					     len >> SECTOR_SHIFT, GFP_KERNEL);
 		break;
 	default:
 		error = -EOPNOTSUPP;
diff --git a/block/ioctl.c b/block/ioctl.c
index eaee0efc0bea..46949f1b0dba 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -83,7 +83,7 @@ static int compat_blkpg_ioctl(struct block_device *bdev,
 #endif
 
 static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
-		unsigned long arg, unsigned long flags)
+		unsigned long arg)
 {
 	uint64_t range[2];
 	uint64_t start, len;
@@ -114,15 +114,43 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
 		goto fail;
-
-	err = blkdev_issue_discard(bdev, start >> 9, len >> 9,
-				   GFP_KERNEL, flags);
-
+	err = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL);
 fail:
 	filemap_invalidate_unlock(inode->i_mapping);
 	return err;
 }
 
+static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode,
+		void __user *argp)
+{
+	uint64_t start, len;
+	uint64_t range[2];
+	int err;
+
+	if (!(mode & FMODE_WRITE))
+		return -EBADF;
+	if (!bdev_max_secure_erase_sectors(bdev))
+		return -EOPNOTSUPP;
+	if (copy_from_user(range, argp, sizeof(range)))
+		return -EFAULT;
+
+	start = range[0];
+	len = range[1];
+	if ((start & 511) || (len & 511))
+		return -EINVAL;
+	if (start + len > bdev_nr_bytes(bdev))
+		return -EINVAL;
+
+	filemap_invalidate_lock(bdev->bd_inode->i_mapping);
+	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
+	if (!err)
+		err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
+						GFP_KERNEL);
+	filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
+	return err;
+}
+
+
 static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		unsigned long arg)
 {
@@ -450,10 +478,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
 	case BLKROSET:
 		return blkdev_roset(bdev, mode, cmd, arg);
 	case BLKDISCARD:
-		return blk_ioctl_discard(bdev, mode, arg, 0);
+		return blk_ioctl_discard(bdev, mode, arg);
 	case BLKSECDISCARD:
-		return blk_ioctl_discard(bdev, mode, arg,
-				BLKDEV_DISCARD_SECURE);
+		return blk_ioctl_secure_erase(bdev, mode, argp);
 	case BLKZEROOUT:
 		return blk_ioctl_zeroout(bdev, mode, arg);
 	case BLKGETDISKSEQ:
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 275c53c7b629..2957b0b68d60 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1547,7 +1547,8 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u
 		start = tmp;
 	}
 	while (nr_sectors >= max_discard_sectors) {
-		err |= blkdev_issue_discard(bdev, start, max_discard_sectors, GFP_NOIO, 0);
+		err |= blkdev_issue_discard(bdev, start, max_discard_sectors,
+					    GFP_NOIO);
 		nr_sectors -= max_discard_sectors;
 		start += max_discard_sectors;
 	}
@@ -1559,7 +1560,7 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u
 		nr = nr_sectors;
 		nr -= (unsigned int)nr % granularity;
 		if (nr) {
-			err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0);
+			err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO);
 			nr_sectors -= nr;
 			start += nr;
 		}
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index efa99a388450..d178be175ad9 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1365,8 +1365,8 @@ static void setup_request_queue(struct rnbd_clt_dev *dev)
 	dev->queue->limits.discard_granularity	= dev->discard_granularity;
 	dev->queue->limits.discard_alignment	= dev->discard_alignment;
 	if (dev->secure_discard)
-		blk_queue_flag_set(QUEUE_FLAG_SECERASE, dev->queue);
-
+		blk_queue_max_secure_erase_sectors(dev->queue,
+				dev->max_discard_sectors);
 	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
 	blk_queue_max_segments(dev->queue, dev->max_segments);
diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h
index 1f7e1c8fd4d9..d080a0de5922 100644
--- a/drivers/block/rnbd/rnbd-srv-dev.h
+++ b/drivers/block/rnbd/rnbd-srv-dev.h
@@ -44,7 +44,7 @@ static inline int rnbd_dev_get_max_hw_sects(const struct rnbd_dev *dev)
 
 static inline int rnbd_dev_get_secure_discard(const struct rnbd_dev *dev)
 {
-	return blk_queue_secure_erase(bdev_get_queue(dev->bdev));
+	return bdev_max_secure_erase_sectors(dev->bdev);
 }
 
 static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev)
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index de42458195bc..a97f2bf5b01b 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -970,7 +970,6 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring,
 	int status = BLKIF_RSP_OKAY;
 	struct xen_blkif *blkif = ring->blkif;
 	struct block_device *bdev = blkif->vbd.bdev;
-	unsigned long secure;
 	struct phys_req preq;
 
 	xen_blkif_get(blkif);
@@ -987,13 +986,15 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring,
 	}
 	ring->st_ds_req++;
 
-	secure = (blkif->vbd.discard_secure &&
-		 (req->u.discard.flag & BLKIF_DISCARD_SECURE)) ?
-		 BLKDEV_DISCARD_SECURE : 0;
+	if (blkif->vbd.discard_secure &&
+	    (req->u.discard.flag & BLKIF_DISCARD_SECURE))
+		err = blkdev_issue_secure_erase(bdev,
+				req->u.discard.sector_number,
+				req->u.discard.nr_sectors, GFP_KERNEL);
+	else
+		err = blkdev_issue_discard(bdev, req->u.discard.sector_number,
+				req->u.discard.nr_sectors, GFP_KERNEL);
 
-	err = blkdev_issue_discard(bdev, req->u.discard.sector_number,
-				   req->u.discard.nr_sectors,
-				   GFP_KERNEL, secure);
 fail_response:
 	if (err == -EOPNOTSUPP) {
 		pr_debug("discard op failed, not supported\n");
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 83cd08041e6b..b21bffc9c50b 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -484,7 +484,6 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 {
 	struct xen_vbd *vbd;
 	struct block_device *bdev;
-	struct request_queue *q;
 
 	vbd = &blkif->vbd;
 	vbd->handle   = handle;
@@ -516,11 +515,9 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE)
 		vbd->type |= VDISK_REMOVABLE;
 
-	q = bdev_get_queue(bdev);
 	if (bdev_write_cache(bdev))
 		vbd->flush_support = true;
-
-	if (q && blk_queue_secure_erase(q))
+	if (bdev_max_secure_erase_sectors(bdev))
 		vbd->discard_secure = true;
 
 	vbd->feature_gnt_persistent = feature_persistent;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index e13cb4d48f1e..0f3f5238f7bc 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -949,7 +949,8 @@ static void blkif_set_queue_limits(struct blkfront_info *info)
 						 info->physical_sector_size;
 		rq->limits.discard_alignment = info->discard_alignment;
 		if (info->feature_secdiscard)
-			blk_queue_flag_set(QUEUE_FLAG_SECERASE, rq);
+			blk_queue_max_secure_erase_sectors(rq,
+							   get_capacity(gd));
 	}
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
@@ -1606,7 +1607,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
 				blk_queue_max_discard_sectors(rq, 0);
-				blk_queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
+				blk_queue_max_secure_erase_sectors(rq, 0);
 			}
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 097577ae3c47..ce13c272c387 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -336,7 +336,7 @@ static int bch_allocator_thread(void *arg)
 				mutex_unlock(&ca->set->bucket_lock);
 				blkdev_issue_discard(ca->bdev,
 					bucket_to_sector(ca->set, bucket),
-					ca->sb.bucket_size, GFP_KERNEL, 0);
+					ca->sb.bucket_size, GFP_KERNEL);
 				mutex_lock(&ca->set->bucket_lock);
 			}
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 0dff6907fd00..e7d42f6335a2 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1920,9 +1920,7 @@ static int device_not_secure_erase_capable(struct dm_target *ti,
 					   struct dm_dev *dev, sector_t start,
 					   sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return !blk_queue_secure_erase(q);
+	return !bdev_max_secure_erase_sectors(dev->bdev);
 }
 
 static bool dm_table_supports_secure_erase(struct dm_table *t)
@@ -1975,8 +1973,8 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 		q->limits.discard_misaligned = 0;
 	}
 
-	if (dm_table_supports_secure_erase(t))
-		blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
+	if (!dm_table_supports_secure_erase(t))
+		q->limits.max_secure_erase_sectors = 0;
 
 	if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
 		wc = true;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index eded4bcc4545..84c083f76673 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -398,8 +398,8 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da
 	sector_t s = block_to_sectors(tc->pool, data_b);
 	sector_t len = block_to_sectors(tc->pool, data_e - data_b);
 
-	return __blkdev_issue_discard(tc->pool_dev->bdev, s, len,
-				      GFP_NOWAIT, 0, &op->bio);
+	return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOWAIT,
+				      &op->bio);
 }
 
 static void end_discard(struct discard_op *op, int r)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 19636c2f2cda..2587f872c088 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8584,7 +8584,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 {
 	struct bio *discard_bio = NULL;
 
-	if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, 0,
+	if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO,
 			&discard_bio) || !discard_bio)
 		return;
 
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index c3cbf9a574a3..094a4042589e 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1344,14 +1344,14 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
 	if (log->last_checkpoint < end) {
 		blkdev_issue_discard(bdev,
 				log->last_checkpoint + log->rdev->data_offset,
-				end - log->last_checkpoint, GFP_NOIO, 0);
+				end - log->last_checkpoint, GFP_NOIO);
 	} else {
 		blkdev_issue_discard(bdev,
 				log->last_checkpoint + log->rdev->data_offset,
 				log->device_size - log->last_checkpoint,
-				GFP_NOIO, 0);
+				GFP_NOIO);
 		blkdev_issue_discard(bdev, log->rdev->data_offset, end,
-				GFP_NOIO, 0);
+				GFP_NOIO);
 	}
 }
 
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index cac6315010a3..a3d446005571 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -189,7 +189,7 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	if (card->pref_erase > max_discard)
 		q->limits.discard_granularity = SECTOR_SIZE;
 	if (mmc_can_secure_erase_trim(card))
-		blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
+		blk_queue_max_secure_erase_sectors(q, max_discard);
 }
 
 static unsigned short mmc_get_max_segments(struct mmc_host *host)
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index d886c2c59554..27a72504d31c 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -360,7 +360,7 @@ static u16 nvmet_bdev_discard_range(struct nvmet_req *req,
 	ret = __blkdev_issue_discard(ns->bdev,
 			nvmet_lba_to_sect(ns, range->slba),
 			le32_to_cpu(range->nlb) << (ns->blksize_shift - 9),
-			GFP_KERNEL, 0, bio);
+			GFP_KERNEL, bio);
 	if (ret && ret != -EOPNOTSUPP) {
 		req->error_slba = le64_to_cpu(range->slba);
 		return errno_to_nvme_status(req, ret);
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index b6ba582b0677..e68f1cc8ef98 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -558,7 +558,7 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 		ret = blkdev_issue_discard(bdev,
 					   target_to_linux_sector(dev, lba),
 					   target_to_linux_sector(dev,  nolb),
-					   GFP_KERNEL, 0);
+					   GFP_KERNEL);
 		if (ret < 0) {
 			pr_warn("FILEIO: blkdev_issue_discard() failed: %d\n",
 				ret);
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index c4a903b8a47f..378c80313a0f 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -434,7 +434,7 @@ iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 	ret = blkdev_issue_discard(bdev,
 				   target_to_linux_sector(dev, lba),
 				   target_to_linux_sector(dev,  nolb),
-				   GFP_KERNEL, 0);
+				   GFP_KERNEL);
 	if (ret < 0) {
 		pr_err("blkdev_issue_discard() failed: %d\n", ret);
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index aba616ff953f..6260784e74b5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1239,7 +1239,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 
 		if (size) {
 			ret = blkdev_issue_discard(bdev, start >> 9, size >> 9,
-						   GFP_NOFS, 0);
+						   GFP_NOFS);
 			if (!ret)
 				*discarded_bytes += size;
 			else if (ret != -EOPNOTSUPP)
@@ -1256,7 +1256,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 
 	if (bytes_left) {
 		ret = blkdev_issue_discard(bdev, start >> 9, bytes_left >> 9,
-					   GFP_NOFS, 0);
+					   GFP_NOFS);
 		if (!ret)
 			*discarded_bytes += bytes_left;
 	}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 6d1820536d88..ea653d19f9ec 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3629,7 +3629,7 @@ static inline int ext4_issue_discard(struct super_block *sb,
 		return __blkdev_issue_discard(sb->s_bdev,
 			(sector_t)discard_block << (sb->s_blocksize_bits - 9),
 			(sector_t)count << (sb->s_blocksize_bits - 9),
-			GFP_NOFS, 0, biop);
+			GFP_NOFS, biop);
 	} else
 		return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
 }
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 8053d99f3920..35b6c720c2bc 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -3685,18 +3685,18 @@ out:
 static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode,
 		pgoff_t off, block_t block, block_t len, u32 flags)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t sector = SECTOR_FROM_BLOCK(block);
 	sector_t nr_sects = SECTOR_FROM_BLOCK(len);
 	int ret = 0;
 
-	if (!q)
-		return -ENXIO;
-
-	if (flags & F2FS_TRIM_FILE_DISCARD)
-		ret = blkdev_issue_discard(bdev, sector, nr_sects, GFP_NOFS,
-						blk_queue_secure_erase(q) ?
-						BLKDEV_DISCARD_SECURE : 0);
+	if (flags & F2FS_TRIM_FILE_DISCARD) {
+		if (bdev_max_secure_erase_sectors(bdev))
+			ret = blkdev_issue_secure_erase(bdev, sector, nr_sects,
+					GFP_NOFS);
+		else
+			ret = blkdev_issue_discard(bdev, sector, nr_sects,
+					GFP_NOFS);
+	}
 
 	if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) {
 		if (IS_ENCRYPTED(inode))
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 71f09adbcba8..e433c61e64b9 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1244,7 +1244,7 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 		err = __blkdev_issue_discard(bdev,
 					SECTOR_FROM_BLOCK(start),
 					SECTOR_FROM_BLOCK(len),
-					GFP_NOFS, 0, &bio);
+					GFP_NOFS, &bio);
 submit:
 		if (err) {
 			spin_lock_irqsave(&dc->lock, flags);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 19d226cd4ff4..c0cbeeaec2d1 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1825,7 +1825,7 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags)
 			err = blkdev_issue_discard(journal->j_dev,
 					byte_start >> SECTOR_SHIFT,
 					byte_count >> SECTOR_SHIFT,
-					GFP_NOFS, 0);
+					GFP_NOFS);
 		} else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) {
 			err = blkdev_issue_zeroout(journal->j_dev,
 					byte_start >> SECTOR_SHIFT,
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index e385cca2004a..77ff8e95421f 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -1100,7 +1100,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
 				ret = blkdev_issue_discard(nilfs->ns_bdev,
 						start * sects_per_block,
 						nblocks * sects_per_block,
-						GFP_NOFS, 0);
+						GFP_NOFS);
 				if (ret < 0) {
 					put_bh(su_bh);
 					goto out_sem;
@@ -1134,7 +1134,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
 			ret = blkdev_issue_discard(nilfs->ns_bdev,
 					start * sects_per_block,
 					nblocks * sects_per_block,
-					GFP_NOFS, 0);
+					GFP_NOFS);
 			if (!ret)
 				ndiscarded += nblocks;
 		}
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index dd48a8f74d57..3b4a079c9617 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -672,7 +672,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump,
 			ret = blkdev_issue_discard(nilfs->ns_bdev,
 						   start * sects_per_block,
 						   nblocks * sects_per_block,
-						   GFP_NOFS, 0);
+						   GFP_NOFS);
 			if (ret < 0)
 				return ret;
 			nblocks = 0;
@@ -682,7 +682,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump,
 		ret = blkdev_issue_discard(nilfs->ns_bdev,
 					   start * sects_per_block,
 					   nblocks * sects_per_block,
-					   GFP_NOFS, 0);
+					   GFP_NOFS);
 	return ret;
 }
 
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 5f2e414cfa79..5781b9e8e3d8 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -1333,7 +1333,7 @@ int ntfs_discard(struct ntfs_sb_info *sbi, CLST lcn, CLST len)
 		return 0;
 
 	err = blkdev_issue_discard(sb->s_bdev, start >> 9, (end - start) >> 9,
-				   GFP_NOFS, 0);
+				   GFP_NOFS);
 
 	if (err == -EOPNOTSUPP)
 		sbi->flags |= NTFS_FLAGS_NODISCARD;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index e2ada115c23f..c6fe3f6ebb6b 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -114,7 +114,7 @@ xfs_trim_extents(
 		}
 
 		trace_xfs_discard_extent(mp, agno, fbno, flen);
-		error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS, 0);
+		error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS);
 		if (error)
 			goto out_del_cursor;
 		*blocks_trimmed += flen;
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index ba57323bfdce..c9f55e4f0957 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -605,7 +605,7 @@ xlog_discard_busy_extents(
 		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
 				XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
-				GFP_NOFS, 0, &bio);
+				GFP_NOFS, &bio);
 		if (error && error != -EOPNOTSUPP) {
 			xfs_info(mp,
 	 "discard failed for extent [0x%llx,%u], error %d",
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f1cf557ea20e..c9b5925af5a3 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -248,6 +248,7 @@ struct queue_limits {
 	unsigned int		io_opt;
 	unsigned int		max_discard_sectors;
 	unsigned int		max_hw_discard_sectors;
+	unsigned int		max_secure_erase_sectors;
 	unsigned int		max_write_zeroes_sectors;
 	unsigned int		max_zone_append_sectors;
 	unsigned int		discard_granularity;
@@ -542,7 +543,6 @@ struct request_queue {
 #define QUEUE_FLAG_IO_STAT	7	/* do disk/partitions IO accounting */
 #define QUEUE_FLAG_NOXMERGES	9	/* No extended merges */
 #define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
-#define QUEUE_FLAG_SECERASE	11	/* supports secure erase */
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
 #define QUEUE_FLAG_DEAD		13	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
@@ -583,8 +583,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
 #define blk_queue_zone_resetall(q)	\
 	test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
-#define blk_queue_secure_erase(q) \
-	(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
 #define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
 #define blk_queue_pci_p2pdma(q)	\
 	test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
@@ -947,6 +945,8 @@ extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_discard_segments(struct request_queue *,
 		unsigned short);
+void blk_queue_max_secure_erase_sectors(struct request_queue *q,
+		unsigned int max_sectors);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
@@ -1087,13 +1087,12 @@ static inline long nr_blockdev_pages(void)
 
 extern void blk_io_schedule(void);
 
-#define BLKDEV_DISCARD_SECURE	(1 << 0)	/* issue a secure erase */
-
-extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
-extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int flags,
-		struct bio **biop);
+int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask);
+int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop);
+int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp);
 
 #define BLKDEV_ZERO_NOUNMAP	(1 << 0)  /* do not free blocks */
 #define BLKDEV_ZERO_NOFALLBACK	(1 << 1)  /* don't write explicit zeroes */
@@ -1112,7 +1111,7 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 					      SECTOR_SHIFT),
 				    nr_blocks << (sb->s_blocksize_bits -
 						  SECTOR_SHIFT),
-				    gfp_mask, flags);
+				    gfp_mask);
 }
 static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask)
@@ -1262,6 +1261,12 @@ static inline unsigned int bdev_discard_granularity(struct block_device *bdev)
 	return bdev_get_queue(bdev)->limits.discard_granularity;
 }
 
+static inline unsigned int
+bdev_max_secure_erase_sectors(struct block_device *bdev)
+{
+	return bdev_get_queue(bdev)->limits.max_secure_erase_sectors;
+}
+
 static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 5d9cedf9e7b8..a2b31fea0c42 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -179,7 +179,7 @@ static int discard_swap(struct swap_info_struct *si)
 	nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
 	if (nr_blocks) {
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, 0);
+				nr_blocks, GFP_KERNEL);
 		if (err)
 			return err;
 		cond_resched();
@@ -190,7 +190,7 @@ static int discard_swap(struct swap_info_struct *si)
 		nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
 
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, 0);
+				nr_blocks, GFP_KERNEL);
 		if (err)
 			break;
 
@@ -254,7 +254,7 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 		start_block <<= PAGE_SHIFT - 9;
 		nr_blocks <<= PAGE_SHIFT - 9;
 		if (blkdev_issue_discard(si->bdev, start_block,
-					nr_blocks, GFP_NOIO, 0))
+					nr_blocks, GFP_NOIO))
 			break;
 
 		se = next_se(se);
-- 
cgit v1.2.3


From a2daa27c0c6137481226aee5b3136e453c642929 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 14 Feb 2022 11:44:42 +0100
Subject: swiotlb: simplify swiotlb_max_segment

Remove the bogus Xen override that was usually larger than the actual
size and just calculate the value on demand.  Note that
swiotlb_max_segment still doesn't make sense as an interface and should
eventually be removed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/swiotlb-xen.c |  2 --
 include/linux/swiotlb.h   |  1 -
 kernel/dma/swiotlb.c      | 20 +++-----------------
 3 files changed, 3 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 47aebd98f52f..485cd06ed39e 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -202,7 +202,6 @@ retry:
 	rc = swiotlb_late_init_with_tbl(start, nslabs);
 	if (rc)
 		return rc;
-	swiotlb_set_max_segment(PAGE_SIZE);
 	return 0;
 error:
 	if (nslabs > 1024 && repeat--) {
@@ -254,7 +253,6 @@ retry:
 
 	if (swiotlb_init_with_tbl(start, nslabs, true))
 		panic("Cannot allocate SWIOTLB buffer");
-	swiotlb_set_max_segment(PAGE_SIZE);
 }
 #endif /* CONFIG_X86 */
 
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index f6c3638255d5..9fb3a568f0c5 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -164,7 +164,6 @@ static inline void swiotlb_adjust_size(unsigned long size)
 #endif /* CONFIG_SWIOTLB */
 
 extern void swiotlb_print_info(void);
-extern void swiotlb_set_max_segment(unsigned int);
 
 #ifdef CONFIG_DMA_RESTRICTED_POOL
 struct page *swiotlb_alloc(struct device *dev, size_t size);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 98bb0eb44a7b..e0127e397335 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -68,12 +68,6 @@ struct io_tlb_mem io_tlb_default_mem;
 
 phys_addr_t swiotlb_unencrypted_base;
 
-/*
- * Max segment that we can provide which (if pages are contingous) will
- * not be bounced (unless SWIOTLB_FORCE is set).
- */
-static unsigned int max_segment;
-
 static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
 
 static int __init
@@ -97,18 +91,12 @@ early_param("swiotlb", setup_io_tlb_npages);
 
 unsigned int swiotlb_max_segment(void)
 {
-	return io_tlb_default_mem.nslabs ? max_segment : 0;
+	if (!io_tlb_default_mem.nslabs)
+		return 0;
+	return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE);
 }
 EXPORT_SYMBOL_GPL(swiotlb_max_segment);
 
-void swiotlb_set_max_segment(unsigned int val)
-{
-	if (swiotlb_force == SWIOTLB_FORCE)
-		max_segment = 1;
-	else
-		max_segment = rounddown(val, PAGE_SIZE);
-}
-
 unsigned long swiotlb_size_or_default(void)
 {
 	return default_nslabs << IO_TLB_SHIFT;
@@ -258,7 +246,6 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 
 	if (verbose)
 		swiotlb_print_info();
-	swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
 	return 0;
 }
 
@@ -359,7 +346,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true);
 
 	swiotlb_print_info();
-	swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 0d5ffd9a256d8995764f9d4a35a8c3917839d169 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 14 Feb 2022 11:07:28 +0100
Subject: swiotlb: rename swiotlb_late_init_with_default_size

swiotlb_late_init_with_default_size is an overly verbose name that
doesn't even catch what the function is doing, given that the size is
not just a default but the actual requested size.

Rename it to swiotlb_init_late.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/pci/sta2x11-fixup.c | 2 +-
 include/linux/swiotlb.h      | 2 +-
 kernel/dma/swiotlb.c         | 6 ++----
 3 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 101081ad64b6..e0c039a75b2d 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -57,7 +57,7 @@ static void sta2x11_new_instance(struct pci_dev *pdev)
 		int size = STA2X11_SWIOTLB_SIZE;
 		/* First instance: register your own swiotlb area */
 		dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
-		if (swiotlb_late_init_with_default_size(size))
+		if (swiotlb_init_late(size))
 			dev_emerg(&pdev->dev, "init swiotlb failed\n");
 	}
 	list_add(&instance->list, &sta2x11_instance_list);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 9fb3a568f0c5..b48b26bfa0ed 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -40,7 +40,7 @@ extern void swiotlb_init(int verbose);
 int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
-extern int swiotlb_late_init_with_default_size(size_t default_size);
+int swiotlb_init_late(size_t size);
 extern void __init swiotlb_update_mem_attributes(void);
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index e0127e397335..9a4fe6e48a07 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -281,11 +281,9 @@ fail:
  * initialize the swiotlb later using the slab allocator if needed.
  * This should be just like above, but with some error catching.
  */
-int
-swiotlb_late_init_with_default_size(size_t default_size)
+int swiotlb_init_late(size_t size)
 {
-	unsigned long nslabs =
-		ALIGN(default_size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
+	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
 	unsigned long bytes;
 	unsigned char *vstart = NULL;
 	unsigned int order;
-- 
cgit v1.2.3


From 78013eaadf696d2105982abb4018fbae394ca08f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 14 Feb 2022 14:11:44 +0100
Subject: x86: remove the IOMMU table infrastructure

The IOMMU table tries to separate the different IOMMUs into different
backends, but actually requires various cross calls.

Rewrite the code to do the generic swiotlb/swiotlb-xen setup directly
in pci-dma.c and then just call into the IOMMU drivers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/ia64/include/asm/iommu_table.h    |   7 ---
 arch/x86/include/asm/dma-mapping.h     |   1 -
 arch/x86/include/asm/gart.h            |   5 +-
 arch/x86/include/asm/iommu.h           |   6 ++
 arch/x86/include/asm/iommu_table.h     | 102 -------------------------------
 arch/x86/include/asm/swiotlb.h         |  30 ---------
 arch/x86/include/asm/xen/swiotlb-xen.h |   2 -
 arch/x86/kernel/Makefile               |   2 -
 arch/x86/kernel/amd_gart_64.c          |   5 +-
 arch/x86/kernel/aperture_64.c          |  14 ++---
 arch/x86/kernel/pci-dma.c              | 107 ++++++++++++++++++++++++++-------
 arch/x86/kernel/pci-iommu_table.c      |  77 ------------------------
 arch/x86/kernel/pci-swiotlb.c          |  77 ------------------------
 arch/x86/kernel/tboot.c                |   1 -
 arch/x86/kernel/vmlinux.lds.S          |  12 ----
 arch/x86/xen/Makefile                  |   2 -
 arch/x86/xen/pci-swiotlb-xen.c         |  96 -----------------------------
 drivers/iommu/amd/init.c               |   6 --
 drivers/iommu/amd/iommu.c              |   5 +-
 drivers/iommu/intel/dmar.c             |   6 +-
 include/linux/dmar.h                   |   6 +-
 21 files changed, 110 insertions(+), 459 deletions(-)
 delete mode 100644 arch/ia64/include/asm/iommu_table.h
 delete mode 100644 arch/x86/include/asm/iommu_table.h
 delete mode 100644 arch/x86/include/asm/swiotlb.h
 delete mode 100644 arch/x86/kernel/pci-iommu_table.c
 delete mode 100644 arch/x86/kernel/pci-swiotlb.c
 delete mode 100644 arch/x86/xen/pci-swiotlb-xen.c

(limited to 'include/linux')

diff --git a/arch/ia64/include/asm/iommu_table.h b/arch/ia64/include/asm/iommu_table.h
deleted file mode 100644
index cc96116ac276..000000000000
--- a/arch/ia64/include/asm/iommu_table.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_IA64_IOMMU_TABLE_H
-#define _ASM_IA64_IOMMU_TABLE_H
-
-#define IOMMU_INIT_POST(_detect)
-
-#endif /* _ASM_IA64_IOMMU_TABLE_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index bb1654fe0ce7..256fd8115223 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -9,7 +9,6 @@
 
 #include <linux/scatterlist.h>
 #include <asm/io.h>
-#include <asm/swiotlb.h>
 
 extern int iommu_merge;
 extern int panic_on_overflow;
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 318556574345..5af8088a10df 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -38,7 +38,7 @@ extern int gart_iommu_aperture_disabled;
 extern void early_gart_iommu_check(void);
 extern int gart_iommu_init(void);
 extern void __init gart_parse_options(char *);
-extern int gart_iommu_hole_init(void);
+void gart_iommu_hole_init(void);
 
 #else
 #define gart_iommu_aperture            0
@@ -51,9 +51,8 @@ static inline void early_gart_iommu_check(void)
 static inline void gart_parse_options(char *options)
 {
 }
-static inline int gart_iommu_hole_init(void)
+static inline void gart_iommu_hole_init(void)
 {
-	return -ENODEV;
 }
 #endif
 
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index bf1ed2ddc74b..dba89ed40d38 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -9,6 +9,12 @@
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 
+#ifdef CONFIG_SWIOTLB
+extern bool x86_swiotlb_enable;
+#else
+#define x86_swiotlb_enable false
+#endif
+
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
 
diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h
deleted file mode 100644
index 1fb3fd1a83c2..000000000000
--- a/arch/x86/include/asm/iommu_table.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_IOMMU_TABLE_H
-#define _ASM_X86_IOMMU_TABLE_H
-
-#include <asm/swiotlb.h>
-
-/*
- * History lesson:
- * The execution chain of IOMMUs in 2.6.36 looks as so:
- *
- *            [xen-swiotlb]
- *                 |
- *         +----[swiotlb *]--+
- *        /         |         \
- *       /          |          \
- *    [GART]     [Calgary]  [Intel VT-d]
- *     /
- *    /
- * [AMD-Vi]
- *
- * *: if SWIOTLB detected 'iommu=soft'/'swiotlb=force' it would skip
- * over the rest of IOMMUs and unconditionally initialize the SWIOTLB.
- * Also it would surreptitiously initialize set the swiotlb=1 if there were
- * more than 4GB and if the user did not pass in 'iommu=off'. The swiotlb
- * flag would be turned off by all IOMMUs except the Calgary one.
- *
- * The IOMMU_INIT* macros allow a similar tree (or more complex if desired)
- * to be built by defining who we depend on.
- *
- * And all that needs to be done is to use one of the macros in the IOMMU
- * and the pci-dma.c will take care of the rest.
- */
-
-struct iommu_table_entry {
-	initcall_t	detect;
-	initcall_t	depend;
-	void		(*early_init)(void); /* No memory allocate available. */
-	void		(*late_init)(void); /* Yes, can allocate memory. */
-#define IOMMU_FINISH_IF_DETECTED (1<<0)
-#define IOMMU_DETECTED		 (1<<1)
-	int		flags;
-};
-/*
- * Macro fills out an entry in the .iommu_table that is equivalent
- * to the fields that 'struct iommu_table_entry' has. The entries
- * that are put in the .iommu_table section are not put in any order
- * hence during boot-time we will have to resort them based on
- * dependency. */
-
-
-#define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\
-	static const struct iommu_table_entry				\
-		__iommu_entry_##_detect __used				\
-	__attribute__ ((unused, __section__(".iommu_table"),		\
-			aligned((sizeof(void *)))))	\
-	= {_detect, _depend, _early_init, _late_init,			\
-	   _finish ? IOMMU_FINISH_IF_DETECTED : 0}
-/*
- * The simplest IOMMU definition. Provide the detection routine
- * and it will be run after the SWIOTLB and the other IOMMUs
- * that utilize this macro. If the IOMMU is detected (ie, the
- * detect routine returns a positive value), the other IOMMUs
- * are also checked. You can use IOMMU_INIT_POST_FINISH if you prefer
- * to stop detecting the other IOMMUs after yours has been detected.
- */
-#define IOMMU_INIT_POST(_detect)					\
-	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  NULL, NULL, 0)
-
-#define IOMMU_INIT_POST_FINISH(detect)					\
-	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  NULL, NULL, 1)
-
-/*
- * A more sophisticated version of IOMMU_INIT. This variant requires:
- *  a). A detection routine function.
- *  b). The name of the detection routine we depend on to get called
- *      before us.
- *  c). The init routine which gets called if the detection routine
- *      returns a positive value from the pci_iommu_alloc. This means
- *      no presence of a memory allocator.
- *  d). Similar to the 'init', except that this gets called from pci_iommu_init
- *      where we do have a memory allocator.
- *
- * The standard IOMMU_INIT differs from the IOMMU_INIT_FINISH variant
- * in that the former will continue detecting other IOMMUs in the call
- * list after the detection routine returns a positive number, while the
- * latter will stop the execution chain upon first successful detection.
- * Both variants will still call the 'init' and 'late_init' functions if
- * they are set.
- */
-#define IOMMU_INIT_FINISH(_detect, _depend, _init, _late_init)		\
-	__IOMMU_INIT(_detect, _depend, _init, _late_init, 1)
-
-#define IOMMU_INIT(_detect, _depend, _init, _late_init)			\
-	__IOMMU_INIT(_detect, _depend, _init, _late_init, 0)
-
-void sort_iommu_table(struct iommu_table_entry *start,
-		      struct iommu_table_entry *finish);
-
-void check_iommu_entries(struct iommu_table_entry *start,
-			 struct iommu_table_entry *finish);
-
-#endif /* _ASM_X86_IOMMU_TABLE_H */
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
deleted file mode 100644
index ff6c92eff035..000000000000
--- a/arch/x86/include/asm/swiotlb.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_SWIOTLB_H
-#define _ASM_X86_SWIOTLB_H
-
-#include <linux/swiotlb.h>
-
-#ifdef CONFIG_SWIOTLB
-extern int swiotlb;
-extern int __init pci_swiotlb_detect_override(void);
-extern int __init pci_swiotlb_detect_4gb(void);
-extern void __init pci_swiotlb_init(void);
-extern void __init pci_swiotlb_late_init(void);
-#else
-#define swiotlb 0
-static inline int pci_swiotlb_detect_override(void)
-{
-	return 0;
-}
-static inline int pci_swiotlb_detect_4gb(void)
-{
-	return 0;
-}
-static inline void pci_swiotlb_init(void)
-{
-}
-static inline void pci_swiotlb_late_init(void)
-{
-}
-#endif
-#endif /* _ASM_X86_SWIOTLB_H */
diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h
index 66b4ddde7743..e5a90b42e4dd 100644
--- a/arch/x86/include/asm/xen/swiotlb-xen.h
+++ b/arch/x86/include/asm/xen/swiotlb-xen.h
@@ -3,10 +3,8 @@
 #define _ASM_X86_SWIOTLB_XEN_H
 
 #ifdef CONFIG_SWIOTLB_XEN
-extern int __init pci_xen_swiotlb_detect(void);
 extern int pci_xen_swiotlb_init_late(void);
 #else
-#define pci_xen_swiotlb_detect NULL
 static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
 #endif
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index c41ef42adbe8..e17b7e92a3fa 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -68,7 +68,6 @@ obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o hw_breakpoint.o
 obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
-obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 obj-y			+= irqflags.o
 obj-y			+= static_call.o
@@ -134,7 +133,6 @@ obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 
 obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
 
-obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb.o
 obj-$(CONFIG_OF)			+= devicetree.o
 obj-$(CONFIG_UPROBES)			+= uprobes.o
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index ed837383de5c..194d54eed537 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -38,11 +38,9 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/set_memory.h>
-#include <asm/swiotlb.h>
 #include <asm/dma.h>
 #include <asm/amd_nb.h>
 #include <asm/x86_init.h>
-#include <asm/iommu_table.h>
 
 static unsigned long iommu_bus_base;	/* GART remapping area (physical) */
 static unsigned long iommu_size;	/* size of remapping area bytes */
@@ -808,7 +806,7 @@ int __init gart_iommu_init(void)
 	flush_gart();
 	dma_ops = &gart_dma_ops;
 	x86_platform.iommu_shutdown = gart_iommu_shutdown;
-	swiotlb = 0;
+	x86_swiotlb_enable = false;
 
 	return 0;
 }
@@ -842,4 +840,3 @@ void __init gart_parse_options(char *p)
 		}
 	}
 }
-IOMMU_INIT_POST(gart_iommu_hole_init);
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index af3ba08b684b..7a5630d904b2 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -392,7 +392,7 @@ void __init early_gart_iommu_check(void)
 
 static int __initdata printed_gart_size_msg;
 
-int __init gart_iommu_hole_init(void)
+void __init gart_iommu_hole_init(void)
 {
 	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
@@ -401,11 +401,11 @@ int __init gart_iommu_hole_init(void)
 	int i, node;
 
 	if (!amd_gart_present())
-		return -ENODEV;
+		return;
 
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
-		return -ENODEV;
+		return;
 
 	pr_info("Checking aperture...\n");
 
@@ -491,10 +491,8 @@ out:
 			 * and fixed up the northbridge
 			 */
 			exclude_from_core(last_aper_base, last_aper_order);
-
-			return 1;
 		}
-		return 0;
+		return;
 	}
 
 	if (!fallback_aper_force) {
@@ -527,7 +525,7 @@ out:
 			panic("Not enough memory for aperture");
 		}
 	} else {
-		return 0;
+		return;
 	}
 
 	/*
@@ -561,6 +559,4 @@ out:
 	}
 
 	set_up_gart_resume(aper_order, aper_alloc);
-
-	return 1;
 }
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index de234e7a8962..df96926421be 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -7,13 +7,16 @@
 #include <linux/memblock.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
+#include <linux/amd-iommu.h>
 
 #include <asm/proto.h>
 #include <asm/dma.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/x86_init.h>
-#include <asm/iommu_table.h>
+
+#include <xen/xen.h>
+#include <xen/swiotlb-xen.h>
 
 static bool disable_dac_quirk __read_mostly;
 
@@ -34,24 +37,83 @@ int no_iommu __read_mostly;
 /* Set this to 1 if there is a HW IOMMU in the system */
 int iommu_detected __read_mostly = 0;
 
-extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
+#ifdef CONFIG_SWIOTLB
+bool x86_swiotlb_enable;
+
+static void __init pci_swiotlb_detect(void)
+{
+	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
+	if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
+		x86_swiotlb_enable = true;
+
+	/*
+	 * Set swiotlb to 1 so that bounce buffers are allocated and used for
+	 * devices that can't support DMA to encrypted memory.
+	 */
+	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		x86_swiotlb_enable = true;
+
+	if (swiotlb_force == SWIOTLB_FORCE)
+		x86_swiotlb_enable = true;
+}
+#else
+static inline void __init pci_swiotlb_detect(void)
+{
+}
+#endif /* CONFIG_SWIOTLB */
+
+#ifdef CONFIG_SWIOTLB_XEN
+static bool xen_swiotlb;
+
+static void __init pci_xen_swiotlb_init(void)
+{
+	if (!xen_initial_domain() && !x86_swiotlb_enable &&
+	    swiotlb_force != SWIOTLB_FORCE)
+		return;
+	x86_swiotlb_enable = true;
+	xen_swiotlb = true;
+	xen_swiotlb_init_early();
+	dma_ops = &xen_swiotlb_dma_ops;
+	if (IS_ENABLED(CONFIG_PCI))
+		pci_request_acs();
+}
+
+int pci_xen_swiotlb_init_late(void)
+{
+	int rc;
+
+	if (xen_swiotlb)
+		return 0;
+
+	rc = xen_swiotlb_init();
+	if (rc)
+		return rc;
+
+	/* XXX: this switches the dma ops under live devices! */
+	dma_ops = &xen_swiotlb_dma_ops;
+	if (IS_ENABLED(CONFIG_PCI))
+		pci_request_acs();
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
+#else
+static inline void __init pci_xen_swiotlb_init(void)
+{
+}
+#endif /* CONFIG_SWIOTLB_XEN */
 
 void __init pci_iommu_alloc(void)
 {
-	struct iommu_table_entry *p;
-
-	sort_iommu_table(__iommu_table, __iommu_table_end);
-	check_iommu_entries(__iommu_table, __iommu_table_end);
-
-	for (p = __iommu_table; p < __iommu_table_end; p++) {
-		if (p && p->detect && p->detect() > 0) {
-			p->flags |= IOMMU_DETECTED;
-			if (p->early_init)
-				p->early_init();
-			if (p->flags & IOMMU_FINISH_IF_DETECTED)
-				break;
-		}
+	if (xen_pv_domain()) {
+		pci_xen_swiotlb_init();
+		return;
 	}
+	pci_swiotlb_detect();
+	gart_iommu_hole_init();
+	amd_iommu_detect();
+	detect_intel_iommu();
+	if (x86_swiotlb_enable)
+		swiotlb_init(0);
 }
 
 /*
@@ -102,7 +164,7 @@ static __init int iommu_setup(char *p)
 		}
 #ifdef CONFIG_SWIOTLB
 		if (!strncmp(p, "soft", 4))
-			swiotlb = 1;
+			x86_swiotlb_enable = true;
 #endif
 		if (!strncmp(p, "pt", 2))
 			iommu_set_default_passthrough(true);
@@ -121,14 +183,17 @@ early_param("iommu", iommu_setup);
 
 static int __init pci_iommu_init(void)
 {
-	struct iommu_table_entry *p;
-
 	x86_init.iommu.iommu_init();
 
-	for (p = __iommu_table; p < __iommu_table_end; p++) {
-		if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
-			p->late_init();
+#ifdef CONFIG_SWIOTLB
+	/* An IOMMU turned us off. */
+	if (x86_swiotlb_enable) {
+		pr_info("PCI-DMA: Using software bounce buffering for IO (SWIOTLB)\n");
+		swiotlb_print_info();
+	} else {
+		swiotlb_exit();
 	}
+#endif
 
 	return 0;
 }
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
deleted file mode 100644
index 42e92ec62973..000000000000
--- a/arch/x86/kernel/pci-iommu_table.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-mapping.h>
-#include <asm/iommu_table.h>
-#include <linux/string.h>
-#include <linux/kallsyms.h>
-
-static struct iommu_table_entry * __init
-find_dependents_of(struct iommu_table_entry *start,
-		   struct iommu_table_entry *finish,
-		   struct iommu_table_entry *q)
-{
-	struct iommu_table_entry *p;
-
-	if (!q)
-		return NULL;
-
-	for (p = start; p < finish; p++)
-		if (p->detect == q->depend)
-			return p;
-
-	return NULL;
-}
-
-
-void __init sort_iommu_table(struct iommu_table_entry *start,
-			     struct iommu_table_entry *finish) {
-
-	struct iommu_table_entry *p, *q, tmp;
-
-	for (p = start; p < finish; p++) {
-again:
-		q = find_dependents_of(start, finish, p);
-		/* We are bit sneaky here. We use the memory address to figure
-		 * out if the node we depend on is past our point, if so, swap.
-		 */
-		if (q > p) {
-			tmp = *p;
-			memmove(p, q, sizeof(*p));
-			*q = tmp;
-			goto again;
-		}
-	}
-
-}
-
-#ifdef DEBUG
-void __init check_iommu_entries(struct iommu_table_entry *start,
-				struct iommu_table_entry *finish)
-{
-	struct iommu_table_entry *p, *q, *x;
-
-	/* Simple cyclic dependency checker. */
-	for (p = start; p < finish; p++) {
-		q = find_dependents_of(start, finish, p);
-		x = find_dependents_of(start, finish, q);
-		if (p == x) {
-			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
-			       p->detect, q->detect);
-			/* Heavy handed way..*/
-			x->depend = NULL;
-		}
-	}
-
-	for (p = start; p < finish; p++) {
-		q = find_dependents_of(p, finish, p);
-		if (q && q > p) {
-			printk(KERN_ERR "EXECUTION ORDER INVALID! %pS should be called before %pS!\n",
-			       p->detect, q->detect);
-		}
-	}
-}
-#else
-void __init check_iommu_entries(struct iommu_table_entry *start,
-				       struct iommu_table_entry *finish)
-{
-}
-#endif
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
deleted file mode 100644
index 814ab46a0dad..000000000000
--- a/arch/x86/kernel/pci-swiotlb.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <linux/pci.h>
-#include <linux/cache.h>
-#include <linux/init.h>
-#include <linux/swiotlb.h>
-#include <linux/memblock.h>
-#include <linux/dma-direct.h>
-#include <linux/cc_platform.h>
-
-#include <asm/iommu.h>
-#include <asm/swiotlb.h>
-#include <asm/dma.h>
-#include <asm/xen/swiotlb-xen.h>
-#include <asm/iommu_table.h>
-
-int swiotlb __read_mostly;
-
-/*
- * pci_swiotlb_detect_override - set swiotlb to 1 if necessary
- *
- * This returns non-zero if we are forced to use swiotlb (by the boot
- * option).
- */
-int __init pci_swiotlb_detect_override(void)
-{
-	if (swiotlb_force == SWIOTLB_FORCE)
-		swiotlb = 1;
-
-	return swiotlb;
-}
-IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
-		  pci_xen_swiotlb_detect,
-		  pci_swiotlb_init,
-		  pci_swiotlb_late_init);
-
-/*
- * If 4GB or more detected (and iommu=off not set) or if SME is active
- * then set swiotlb to 1 and return 1.
- */
-int __init pci_swiotlb_detect_4gb(void)
-{
-	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-	if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
-		swiotlb = 1;
-
-	/*
-	 * Set swiotlb to 1 so that bounce buffers are allocated and used for
-	 * devices that can't support DMA to encrypted memory.
-	 */
-	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
-		swiotlb = 1;
-
-	return swiotlb;
-}
-IOMMU_INIT(pci_swiotlb_detect_4gb,
-	   pci_swiotlb_detect_override,
-	   pci_swiotlb_init,
-	   pci_swiotlb_late_init);
-
-void __init pci_swiotlb_init(void)
-{
-	if (swiotlb)
-		swiotlb_init(0);
-}
-
-void __init pci_swiotlb_late_init(void)
-{
-	/* An IOMMU turned us off. */
-	if (!swiotlb)
-		swiotlb_exit();
-	else {
-		printk(KERN_INFO "PCI-DMA: "
-		       "Using software bounce buffering for IO (SWIOTLB)\n");
-		swiotlb_print_info();
-	}
-}
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index f9af561c3cd4..0c1154a1c403 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -24,7 +24,6 @@
 #include <asm/processor.h>
 #include <asm/bootparam.h>
 #include <asm/pgalloc.h>
-#include <asm/swiotlb.h>
 #include <asm/fixmap.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 7fda7f27e762..f5f6dc2e8007 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -315,18 +315,6 @@ SECTIONS
 		*(.altinstr_replacement)
 	}
 
-	/*
-	 * struct iommu_table_entry entries are injected in this section.
-	 * It is an array of IOMMUs which during run time gets sorted depending
-	 * on its dependency order. After rootfs_initcall is complete
-	 * this section can be safely removed.
-	 */
-	.iommu_table : AT(ADDR(.iommu_table) - LOAD_OFFSET) {
-		__iommu_table = .;
-		*(.iommu_table)
-		__iommu_table_end = .;
-	}
-
 	. = ALIGN(8);
 	.apicdrivers : AT(ADDR(.apicdrivers) - LOAD_OFFSET) {
 		__apicdrivers = .;
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 4953260e281c..3c5b52fbe4a7 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -47,6 +47,4 @@ obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 
 obj-$(CONFIG_XEN_PV_DOM0)	+= vga.o
 
-obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
-
 obj-$(CONFIG_XEN_EFI)		+= efi.o
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
deleted file mode 100644
index 46df59aeaa06..000000000000
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ /dev/null
@@ -1,96 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-/* Glue code to lib/swiotlb-xen.c */
-
-#include <linux/dma-map-ops.h>
-#include <linux/pci.h>
-#include <xen/swiotlb-xen.h>
-
-#include <asm/xen/hypervisor.h>
-#include <xen/xen.h>
-#include <asm/iommu_table.h>
-
-
-#include <asm/xen/swiotlb-xen.h>
-#ifdef CONFIG_X86_64
-#include <asm/iommu.h>
-#include <asm/dma.h>
-#endif
-#include <linux/export.h>
-
-static int xen_swiotlb __read_mostly;
-
-/*
- * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary
- *
- * This returns non-zero if we are forced to use xen_swiotlb (by the boot
- * option).
- */
-int __init pci_xen_swiotlb_detect(void)
-{
-
-	if (!xen_pv_domain())
-		return 0;
-
-	/* If running as PV guest, either iommu=soft, or swiotlb=force will
-	 * activate this IOMMU. If running as PV privileged, activate it
-	 * irregardless.
-	 */
-	if (xen_initial_domain() || swiotlb || swiotlb_force == SWIOTLB_FORCE)
-		xen_swiotlb = 1;
-
-	/* If we are running under Xen, we MUST disable the native SWIOTLB.
-	 * Don't worry about swiotlb_force flag activating the native, as
-	 * the 'swiotlb' flag is the only one turning it on. */
-	swiotlb = 0;
-
-#ifdef CONFIG_X86_64
-	/* pci_swiotlb_detect_4gb turns on native SWIOTLB if no_iommu == 0
-	 * (so no iommu=X command line over-writes).
-	 * Considering that PV guests do not want the *native SWIOTLB* but
-	 * only Xen SWIOTLB it is not useful to us so set no_iommu=1 here.
-	 */
-	if (max_pfn > MAX_DMA32_PFN)
-		no_iommu = 1;
-#endif
-	return xen_swiotlb;
-}
-
-static void __init pci_xen_swiotlb_init(void)
-{
-	if (xen_swiotlb) {
-		xen_swiotlb_init_early();
-		dma_ops = &xen_swiotlb_dma_ops;
-
-#ifdef CONFIG_PCI
-		/* Make sure ACS will be enabled */
-		pci_request_acs();
-#endif
-	}
-}
-
-int pci_xen_swiotlb_init_late(void)
-{
-	int rc;
-
-	if (xen_swiotlb)
-		return 0;
-
-	rc = xen_swiotlb_init();
-	if (rc)
-		return rc;
-
-	dma_ops = &xen_swiotlb_dma_ops;
-#ifdef CONFIG_PCI
-	/* Make sure ACS will be enabled */
-	pci_request_acs();
-#endif
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
-
-IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
-		  NULL,
-		  pci_xen_swiotlb_init,
-		  NULL);
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index b4a798c7b347..1a3ad58ba846 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -27,7 +27,6 @@
 #include <asm/apic.h>
 #include <asm/gart.h>
 #include <asm/x86_init.h>
-#include <asm/iommu_table.h>
 #include <asm/io_apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/set_memory.h>
@@ -3257,11 +3256,6 @@ __setup("ivrs_ioapic",		parse_ivrs_ioapic);
 __setup("ivrs_hpet",		parse_ivrs_hpet);
 __setup("ivrs_acpihid",		parse_ivrs_acpihid);
 
-IOMMU_INIT_FINISH(amd_iommu_detect,
-		  gart_iommu_hole_init,
-		  NULL,
-		  NULL);
-
 bool amd_iommu_v2_supported(void)
 {
 	return amd_iommu_v2_present;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index a1ada7bff44e..b47220ac09ea 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1840,7 +1840,10 @@ void amd_iommu_domain_update(struct protection_domain *domain)
 
 static void __init amd_iommu_init_dma_ops(void)
 {
-	swiotlb = (iommu_default_passthrough() || sme_me_mask) ? 1 : 0;
+	if (iommu_default_passthrough() || sme_me_mask)
+		x86_swiotlb_enable = true;
+	else
+		x86_swiotlb_enable = false;
 }
 
 int __init amd_iommu_init_api(void)
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 4de960834a1b..592c1e1a5d4b 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -30,7 +30,6 @@
 #include <linux/numa.h>
 #include <linux/limits.h>
 #include <asm/irq_remapping.h>
-#include <asm/iommu_table.h>
 #include <trace/events/intel_iommu.h>
 
 #include "../irq_remapping.h"
@@ -912,7 +911,7 @@ dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
 	return 0;
 }
 
-int __init detect_intel_iommu(void)
+void __init detect_intel_iommu(void)
 {
 	int ret;
 	struct dmar_res_callback validate_drhd_cb = {
@@ -945,8 +944,6 @@ int __init detect_intel_iommu(void)
 		dmar_tbl = NULL;
 	}
 	up_write(&dmar_global_lock);
-
-	return ret ? ret : 1;
 }
 
 static void unmap_iommu(struct intel_iommu *iommu)
@@ -2164,7 +2161,6 @@ static int __init dmar_free_unused_resources(void)
 }
 
 late_initcall(dmar_free_unused_resources);
-IOMMU_INIT_POST(detect_intel_iommu);
 
 /*
  * DMAR Hotplug Support
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 45e903d84733..cbd714a198a0 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -121,7 +121,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
 				 u16 segment, struct dmar_dev_scope *devices,
 				 int count);
 /* Intel IOMMU detection */
-extern int detect_intel_iommu(void);
+void detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 extern int dmar_device_add(acpi_handle handle);
 extern int dmar_device_remove(acpi_handle handle);
@@ -197,6 +197,10 @@ static inline bool dmar_platform_optin(void)
 	return false;
 }
 
+static inline void detect_intel_iommu(void)
+{
+}
+
 #endif /* CONFIG_DMAR_TABLE */
 
 struct irte {
-- 
cgit v1.2.3


From c6af2aa9ffc9763826607bc2664ef3ea4475ed18 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 29 Mar 2022 17:27:33 +0200
Subject: swiotlb: make the swiotlb_init interface more useful

Pass a boolean flag to indicate if swiotlb needs to be enabled based on
the addressing needs, and replace the verbose argument with a set of
flags, including one to force enable bounce buffering.

Note that this patch removes the possibility to force xen-swiotlb use
with the swiotlb=force parameter on the command line on x86 (arm and
arm64 never supported that), but this interface will be restored shortly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/arm/mm/init.c                     |  6 +-----
 arch/arm64/mm/init.c                   |  6 +-----
 arch/ia64/mm/init.c                    |  4 +---
 arch/mips/cavium-octeon/dma-octeon.c   |  2 +-
 arch/mips/loongson64/dma.c             |  2 +-
 arch/mips/sibyte/common/dma.c          |  2 +-
 arch/powerpc/mm/mem.c                  |  3 ++-
 arch/powerpc/platforms/pseries/setup.c |  3 ---
 arch/riscv/mm/init.c                   |  8 +-------
 arch/s390/mm/init.c                    |  3 +--
 arch/x86/kernel/pci-dma.c              | 15 +++++++--------
 drivers/xen/swiotlb-xen.c              |  4 ++--
 include/linux/swiotlb.h                | 15 +++++++--------
 include/trace/events/swiotlb.h         | 29 ++++++++++------------------
 kernel/dma/swiotlb.c                   | 35 ++++++++++++++++++----------------
 15 files changed, 55 insertions(+), 82 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index fe249ea91908..ce64bdb55a16 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -271,11 +271,7 @@ static void __init free_highpages(void)
 void __init mem_init(void)
 {
 #ifdef CONFIG_ARM_LPAE
-	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > arm_dma_pfn_limit)
-		swiotlb_init(1);
-	else
-		swiotlb_force = SWIOTLB_NO_FORCE;
+	swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE);
 #endif
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 1e7b1550e2fc..bd4095b7fb40 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -398,11 +398,7 @@ void __init bootmem_init(void)
  */
 void __init mem_init(void)
 {
-	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(arm64_dma_phys_limit))
-		swiotlb_init(1);
-	else if (!xen_swiotlb_detect())
-		swiotlb_force = SWIOTLB_NO_FORCE;
+	swiotlb_init(max_pfn > PFN_DOWN(arm64_dma_phys_limit), SWIOTLB_VERBOSE);
 
 	/* this will put all unused low memory onto the freelists */
 	memblock_free_all();
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 5d165607bf35..3c3e15b22608 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -437,9 +437,7 @@ mem_init (void)
 		if (iommu_detected)
 			break;
 #endif
-#ifdef CONFIG_SWIOTLB
-		swiotlb_init(1);
-#endif
+		swiotlb_init(true, SWIOTLB_VERBOSE);
 	} while (0);
 
 #ifdef CONFIG_FLATMEM
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index fb7547e21726..9fbba6a8fa4c 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -235,5 +235,5 @@ void __init plat_swiotlb_setup(void)
 #endif
 
 	swiotlb_adjust_size(swiotlbsize);
-	swiotlb_init(1);
+	swiotlb_init(true, SWIOTLB_VERBOSE);
 }
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index 364f2f27c872..8220a1bc0db6 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -24,5 +24,5 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 
 void __init plat_swiotlb_setup(void)
 {
-	swiotlb_init(1);
+	swiotlb_init(true, SWIOTLB_VERBOSE);
 }
diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c
index eb47a94f3583..c5c2c782aff6 100644
--- a/arch/mips/sibyte/common/dma.c
+++ b/arch/mips/sibyte/common/dma.c
@@ -10,5 +10,5 @@
 
 void __init plat_swiotlb_setup(void)
 {
-	swiotlb_init(1);
+	swiotlb_init(true, SWIOTLB_VERBOSE);
 }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 4d221d033804..74ca516c3e7e 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -17,6 +17,7 @@
 #include <linux/suspend.h>
 #include <linux/dma-direct.h>
 
+#include <asm/swiotlb.h>
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/kasan.h>
@@ -251,7 +252,7 @@ void __init mem_init(void)
 	if (is_secure_guest())
 		svm_swiotlb_init();
 	else
-		swiotlb_init(0);
+		swiotlb_init(ppc_swiotlb_enable, 0);
 #endif
 
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 955ff8aa1644..0f74b2284773 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -849,9 +849,6 @@ static void __init pSeries_setup_arch(void)
 	}
 
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
-
-	if (swiotlb_force == SWIOTLB_FORCE)
-		ppc_swiotlb_enable = 1;
 }
 
 static void pseries_panic(char *str)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 9535bea8688c..181ffd322eaf 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -120,13 +120,7 @@ void __init mem_init(void)
 	BUG_ON(!mem_map);
 #endif /* CONFIG_FLATMEM */
 
-#ifdef CONFIG_SWIOTLB
-	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(dma32_phys_limit))
-		swiotlb_init(1);
-	else
-		swiotlb_force = SWIOTLB_NO_FORCE;
-#endif
+	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
 	memblock_free_all();
 
 	print_vm_layout();
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 86ffd0d51fd5..6fb6bf64326f 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -185,8 +185,7 @@ static void pv_init(void)
 		return;
 
 	/* make sure bounce buffers are shared */
-	swiotlb_force = SWIOTLB_FORCE;
-	swiotlb_init(1);
+	swiotlb_init(true, SWIOTLB_FORCE | SWIOTLB_VERBOSE);
 	swiotlb_update_mem_attributes();
 }
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 04140e20ef1a..a705a199bf8a 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -39,6 +39,7 @@ int iommu_detected __read_mostly = 0;
 
 #ifdef CONFIG_SWIOTLB
 bool x86_swiotlb_enable;
+static unsigned int x86_swiotlb_flags;
 
 static void __init pci_swiotlb_detect(void)
 {
@@ -58,16 +59,16 @@ static void __init pci_swiotlb_detect(void)
 	 * bounce buffers as the hypervisor can't access arbitrary VM memory
 	 * that is not explicitly shared with it.
 	 */
-	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
-		swiotlb_force = SWIOTLB_FORCE;
-
-	if (swiotlb_force == SWIOTLB_FORCE)
+	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
 		x86_swiotlb_enable = true;
+		x86_swiotlb_flags |= SWIOTLB_FORCE;
+	}
 }
 #else
 static inline void __init pci_swiotlb_detect(void)
 {
 }
+#define x86_swiotlb_flags 0
 #endif /* CONFIG_SWIOTLB */
 
 #ifdef CONFIG_SWIOTLB_XEN
@@ -75,8 +76,7 @@ static bool xen_swiotlb;
 
 static void __init pci_xen_swiotlb_init(void)
 {
-	if (!xen_initial_domain() && !x86_swiotlb_enable &&
-	    swiotlb_force != SWIOTLB_FORCE)
+	if (!xen_initial_domain() && !x86_swiotlb_enable)
 		return;
 	x86_swiotlb_enable = true;
 	xen_swiotlb = true;
@@ -120,8 +120,7 @@ void __init pci_iommu_alloc(void)
 	gart_iommu_hole_init();
 	amd_iommu_detect();
 	detect_intel_iommu();
-	if (x86_swiotlb_enable)
-		swiotlb_init(0);
+	swiotlb_init(x86_swiotlb_enable, x86_swiotlb_flags);
 }
 
 /*
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 485cd06ed39e..c2da3eb4826e 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -251,7 +251,7 @@ retry:
 		panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc);
 	}
 
-	if (swiotlb_init_with_tbl(start, nslabs, true))
+	if (swiotlb_init_with_tbl(start, nslabs, SWIOTLB_VERBOSE))
 		panic("Cannot allocate SWIOTLB buffer");
 }
 #endif /* CONFIG_X86 */
@@ -376,7 +376,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	/*
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
-	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+	trace_swiotlb_bounced(dev, dev_addr, size);
 
 	map = swiotlb_tbl_map_single(dev, phys, size, size, 0, dir, attrs);
 	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index b48b26bfa0ed..ae0407173e84 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -13,11 +13,8 @@ struct device;
 struct page;
 struct scatterlist;
 
-enum swiotlb_force {
-	SWIOTLB_NORMAL,		/* Default - depending on HW DMA mask etc. */
-	SWIOTLB_FORCE,		/* swiotlb=force */
-	SWIOTLB_NO_FORCE,	/* swiotlb=noforce */
-};
+#define SWIOTLB_VERBOSE	(1 << 0) /* verbose initialization */
+#define SWIOTLB_FORCE	(1 << 1) /* force bounce buffering */
 
 /*
  * Maximum allowable number of contiguous slabs to map,
@@ -36,8 +33,7 @@ enum swiotlb_force {
 /* default to 64MB */
 #define IO_TLB_DEFAULT_SIZE (64UL<<20)
 
-extern void swiotlb_init(int verbose);
-int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
+int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags);
 unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
 int swiotlb_init_late(size_t size);
@@ -126,13 +122,16 @@ static inline bool is_swiotlb_force_bounce(struct device *dev)
 	return mem && mem->force_bounce;
 }
 
+void swiotlb_init(bool addressing_limited, unsigned int flags);
 void __init swiotlb_exit(void);
 unsigned int swiotlb_max_segment(void);
 size_t swiotlb_max_mapping_size(struct device *dev);
 bool is_swiotlb_active(struct device *dev);
 void __init swiotlb_adjust_size(unsigned long size);
 #else
-#define swiotlb_force SWIOTLB_NO_FORCE
+static inline void swiotlb_init(bool addressing_limited, unsigned int flags)
+{
+}
 static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
 {
 	return false;
diff --git a/include/trace/events/swiotlb.h b/include/trace/events/swiotlb.h
index 705be43b71ab..da05c9ebd224 100644
--- a/include/trace/events/swiotlb.h
+++ b/include/trace/events/swiotlb.h
@@ -8,20 +8,15 @@
 #include <linux/tracepoint.h>
 
 TRACE_EVENT(swiotlb_bounced,
-
-	TP_PROTO(struct device *dev,
-		 dma_addr_t dev_addr,
-		 size_t size,
-		 enum swiotlb_force swiotlb_force),
-
-	TP_ARGS(dev, dev_addr, size, swiotlb_force),
+	TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size),
+	TP_ARGS(dev, dev_addr, size),
 
 	TP_STRUCT__entry(
-		__string(	dev_name,	dev_name(dev)		)
-		__field(	u64,	dma_mask			)
-		__field(	dma_addr_t,	dev_addr		)
-		__field(	size_t,	size				)
-		__field(	enum swiotlb_force,	swiotlb_force	)
+		__string(dev_name, dev_name(dev))
+		__field(u64, dma_mask)
+		__field(dma_addr_t, dev_addr)
+		__field(size_t, size)
+		__field(bool, force)
 	),
 
 	TP_fast_assign(
@@ -29,19 +24,15 @@ TRACE_EVENT(swiotlb_bounced,
 		__entry->dma_mask = (dev->dma_mask ? *dev->dma_mask : 0);
 		__entry->dev_addr = dev_addr;
 		__entry->size = size;
-		__entry->swiotlb_force = swiotlb_force;
+		__entry->force = is_swiotlb_force_bounce(dev);
 	),
 
-	TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx "
-		"size=%zu %s",
+	TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx size=%zu %s",
 		__get_str(dev_name),
 		__entry->dma_mask,
 		(unsigned long long)__entry->dev_addr,
 		__entry->size,
-		__print_symbolic(__entry->swiotlb_force,
-			{ SWIOTLB_NORMAL,	"NORMAL" },
-			{ SWIOTLB_FORCE,	"FORCE" },
-			{ SWIOTLB_NO_FORCE,	"NO_FORCE" }))
+		__entry->force ? "FORCE" : "NORMAL")
 );
 
 #endif /*  _TRACE_SWIOTLB_H */
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 9a4fe6e48a07..86e877a96b82 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -62,7 +62,8 @@
 
 #define INVALID_PHYS_ADDR (~(phys_addr_t)0)
 
-enum swiotlb_force swiotlb_force;
+static bool swiotlb_force_bounce;
+static bool swiotlb_force_disable;
 
 struct io_tlb_mem io_tlb_default_mem;
 
@@ -81,9 +82,9 @@ setup_io_tlb_npages(char *str)
 	if (*str == ',')
 		++str;
 	if (!strcmp(str, "force"))
-		swiotlb_force = SWIOTLB_FORCE;
+		swiotlb_force_bounce = true;
 	else if (!strcmp(str, "noforce"))
-		swiotlb_force = SWIOTLB_NO_FORCE;
+		swiotlb_force_disable = true;
 
 	return 0;
 }
@@ -202,7 +203,7 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 	mem->index = 0;
 	mem->late_alloc = late_alloc;
 
-	if (swiotlb_force == SWIOTLB_FORCE)
+	if (swiotlb_force_bounce)
 		mem->force_bounce = true;
 
 	spin_lock_init(&mem->lock);
@@ -224,12 +225,13 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 	return;
 }
 
-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs,
+		unsigned int flags)
 {
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	size_t alloc_size;
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
+	if (swiotlb_force_disable)
 		return 0;
 
 	/* protect against double initialization */
@@ -243,8 +245,9 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 		      __func__, alloc_size, PAGE_SIZE);
 
 	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false);
+	mem->force_bounce = flags & SWIOTLB_FORCE;
 
-	if (verbose)
+	if (flags & SWIOTLB_VERBOSE)
 		swiotlb_print_info();
 	return 0;
 }
@@ -253,20 +256,21 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
  */
-void  __init
-swiotlb_init(int verbose)
+void __init swiotlb_init(bool addressing_limit, unsigned int flags)
 {
 	size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
 	void *tlb;
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
+	if (!addressing_limit && !swiotlb_force_bounce)
+		return;
+	if (swiotlb_force_disable)
 		return;
 
 	/* Get IO TLB memory from the low pages */
 	tlb = memblock_alloc_low(bytes, PAGE_SIZE);
 	if (!tlb)
 		goto fail;
-	if (swiotlb_init_with_tbl(tlb, default_nslabs, verbose))
+	if (swiotlb_init_with_tbl(tlb, default_nslabs, flags))
 		goto fail_free_mem;
 	return;
 
@@ -289,7 +293,7 @@ int swiotlb_init_late(size_t size)
 	unsigned int order;
 	int rc = 0;
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
+	if (swiotlb_force_disable)
 		return 0;
 
 	/*
@@ -328,7 +332,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long bytes = nslabs << IO_TLB_SHIFT;
 
-	if (swiotlb_force == SWIOTLB_NO_FORCE)
+	if (swiotlb_force_disable)
 		return 0;
 
 	/* protect against double initialization */
@@ -353,7 +357,7 @@ void __init swiotlb_exit(void)
 	unsigned long tbl_vaddr;
 	size_t tbl_size, slots_size;
 
-	if (swiotlb_force == SWIOTLB_FORCE)
+	if (swiotlb_force_bounce)
 		return;
 
 	if (!mem->nslabs)
@@ -704,8 +708,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	phys_addr_t swiotlb_addr;
 	dma_addr_t dma_addr;
 
-	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
-			      swiotlb_force);
+	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size);
 
 	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir,
 			attrs);
-- 
cgit v1.2.3


From 8ba2ed1be90fc210126f68186564707478552c95 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 28 Feb 2022 13:36:57 +0200
Subject: swiotlb: add a SWIOTLB_ANY flag to lift the low memory restriction

Power SVM wants to allocate a swiotlb buffer that is not restricted to
low memory for the trusted hypervisor scheme.  Consolidate the support
for this into the swiotlb_init interface by adding a new flag.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/powerpc/include/asm/svm.h       |  4 ----
 arch/powerpc/include/asm/swiotlb.h   |  1 +
 arch/powerpc/kernel/dma-swiotlb.c    |  1 +
 arch/powerpc/mm/mem.c                |  5 +----
 arch/powerpc/platforms/pseries/svm.c | 26 +-------------------------
 include/linux/swiotlb.h              |  1 +
 kernel/dma/swiotlb.c                 | 11 +++++++++--
 7 files changed, 14 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h
index 7546402d796a..85580b30aba4 100644
--- a/arch/powerpc/include/asm/svm.h
+++ b/arch/powerpc/include/asm/svm.h
@@ -15,8 +15,6 @@ static inline bool is_secure_guest(void)
 	return mfmsr() & MSR_S;
 }
 
-void __init svm_swiotlb_init(void);
-
 void dtl_cache_ctor(void *addr);
 #define get_dtl_cache_ctor()	(is_secure_guest() ? dtl_cache_ctor : NULL)
 
@@ -27,8 +25,6 @@ static inline bool is_secure_guest(void)
 	return false;
 }
 
-static inline void svm_swiotlb_init(void) {}
-
 #define get_dtl_cache_ctor() NULL
 
 #endif /* CONFIG_PPC_SVM */
diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index 3c1a1cd16128..4203b5e0a88e 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -9,6 +9,7 @@
 #include <linux/swiotlb.h>
 
 extern unsigned int ppc_swiotlb_enable;
+extern unsigned int ppc_swiotlb_flags;
 
 #ifdef CONFIG_SWIOTLB
 void swiotlb_detect_4g(void);
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index fc7816126a40..ba256c37bcc0 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -10,6 +10,7 @@
 #include <asm/swiotlb.h>
 
 unsigned int ppc_swiotlb_enable;
+unsigned int ppc_swiotlb_flags;
 
 void __init swiotlb_detect_4g(void)
 {
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 74ca516c3e7e..46fb78e3bb36 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -249,10 +249,7 @@ void __init mem_init(void)
 	 * back to to-down.
 	 */
 	memblock_set_bottom_up(true);
-	if (is_secure_guest())
-		svm_swiotlb_init();
-	else
-		swiotlb_init(ppc_swiotlb_enable, 0);
+	swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags);
 #endif
 
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index c5228f4969eb..3b4045d508ec 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -28,7 +28,7 @@ static int __init init_svm(void)
 	 * need to use the SWIOTLB buffer for DMA even if dma_capable() says
 	 * otherwise.
 	 */
-	swiotlb_force = SWIOTLB_FORCE;
+	ppc_swiotlb_flags |= SWIOTLB_ANY | SWIOTLB_FORCE;
 
 	/* Share the SWIOTLB buffer with the host. */
 	swiotlb_update_mem_attributes();
@@ -37,30 +37,6 @@ static int __init init_svm(void)
 }
 machine_early_initcall(pseries, init_svm);
 
-/*
- * Initialize SWIOTLB. Essentially the same as swiotlb_init(), except that it
- * can allocate the buffer anywhere in memory. Since the hypervisor doesn't have
- * any addressing limitation, we don't need to allocate it in low addresses.
- */
-void __init svm_swiotlb_init(void)
-{
-	unsigned char *vstart;
-	unsigned long bytes, io_tlb_nslabs;
-
-	io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT);
-	io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
-
-	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-
-	vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE);
-	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false))
-		return;
-
-
-	memblock_free(vstart, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-	panic("SVM: Cannot allocate SWIOTLB buffer");
-}
-
 int set_memory_encrypted(unsigned long addr, int numpages)
 {
 	if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT))
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ae0407173e84..eabdd8998702 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -15,6 +15,7 @@ struct scatterlist;
 
 #define SWIOTLB_VERBOSE	(1 << 0) /* verbose initialization */
 #define SWIOTLB_FORCE	(1 << 1) /* force bounce buffering */
+#define SWIOTLB_ANY	(1 << 2) /* allow any memory for the buffer */
 
 /*
  * Maximum allowable number of contiguous slabs to map,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 86e877a96b82..f6e091424af3 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -266,8 +266,15 @@ void __init swiotlb_init(bool addressing_limit, unsigned int flags)
 	if (swiotlb_force_disable)
 		return;
 
-	/* Get IO TLB memory from the low pages */
-	tlb = memblock_alloc_low(bytes, PAGE_SIZE);
+	/*
+	 * By default allocate the bounce buffer memory from low memory, but
+	 * allow to pick a location everywhere for hypervisors with guest
+	 * memory encryption.
+	 */
+	if (flags & SWIOTLB_ANY)
+		tlb = memblock_alloc(bytes, PAGE_SIZE);
+	else
+		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
 	if (!tlb)
 		goto fail;
 	if (swiotlb_init_with_tbl(tlb, default_nslabs, flags))
-- 
cgit v1.2.3


From 742519538e6b07250c8085bbff4bd358bc03bf16 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 14 Feb 2022 11:12:59 +0100
Subject: swiotlb: pass a gfp_mask argument to swiotlb_init_late

Let the caller chose a zone to allocate from.  This will be used
later on by the xen-swiotlb initialization on arm.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/pci/sta2x11-fixup.c | 2 +-
 include/linux/swiotlb.h      | 2 +-
 kernel/dma/swiotlb.c         | 7 ++-----
 3 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index e0c039a75b2d..c7e6faf59a86 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -57,7 +57,7 @@ static void sta2x11_new_instance(struct pci_dev *pdev)
 		int size = STA2X11_SWIOTLB_SIZE;
 		/* First instance: register your own swiotlb area */
 		dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
-		if (swiotlb_init_late(size))
+		if (swiotlb_init_late(size, GFP_DMA))
 			dev_emerg(&pdev->dev, "init swiotlb failed\n");
 	}
 	list_add(&instance->list, &sta2x11_instance_list);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index eabdd8998702..ee655f2e4d28 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -37,7 +37,7 @@ struct scatterlist;
 int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags);
 unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
-int swiotlb_init_late(size_t size);
+int swiotlb_init_late(size_t size, gfp_t gfp_mask);
 extern void __init swiotlb_update_mem_attributes(void);
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index f6e091424af3..119187afc65e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -292,7 +292,7 @@ fail:
  * initialize the swiotlb later using the slab allocator if needed.
  * This should be just like above, but with some error catching.
  */
-int swiotlb_init_late(size_t size)
+int swiotlb_init_late(size_t size, gfp_t gfp_mask)
 {
 	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
 	unsigned long bytes;
@@ -303,15 +303,12 @@ int swiotlb_init_late(size_t size)
 	if (swiotlb_force_disable)
 		return 0;
 
-	/*
-	 * Get IO TLB memory from the low pages
-	 */
 	order = get_order(nslabs << IO_TLB_SHIFT);
 	nslabs = SLABS_PER_PAGE << order;
 	bytes = nslabs << IO_TLB_SHIFT;
 
 	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-		vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+		vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN,
 						  order);
 		if (vstart)
 			break;
-- 
cgit v1.2.3


From 7374153d294eb51de5a81ac38ff1c4fef8927bec Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 14 Mar 2022 08:02:57 +0100
Subject: swiotlb: provide swiotlb_init variants that remap the buffer

To shared more code between swiotlb and xen-swiotlb, offer a
swiotlb_init_remap interface and add a remap callback to
swiotlb_init_late that will allow Xen to remap the buffer without
duplicating much of the logic.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/pci/sta2x11-fixup.c |  2 +-
 include/linux/swiotlb.h      |  5 ++++-
 kernel/dma/swiotlb.c         | 36 +++++++++++++++++++++++++++++++++---
 3 files changed, 38 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index c7e6faf59a86..7368afc03998 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -57,7 +57,7 @@ static void sta2x11_new_instance(struct pci_dev *pdev)
 		int size = STA2X11_SWIOTLB_SIZE;
 		/* First instance: register your own swiotlb area */
 		dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
-		if (swiotlb_init_late(size, GFP_DMA))
+		if (swiotlb_init_late(size, GFP_DMA, NULL))
 			dev_emerg(&pdev->dev, "init swiotlb failed\n");
 	}
 	list_add(&instance->list, &sta2x11_instance_list);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ee655f2e4d28..7b50c82f84ce 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -36,8 +36,11 @@ struct scatterlist;
 
 int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags);
 unsigned long swiotlb_size_or_default(void);
+void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
+	int (*remap)(void *tlb, unsigned long nslabs));
+int swiotlb_init_late(size_t size, gfp_t gfp_mask,
+	int (*remap)(void *tlb, unsigned long nslabs));
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
-int swiotlb_init_late(size_t size, gfp_t gfp_mask);
 extern void __init swiotlb_update_mem_attributes(void);
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 119187afc65e..f6acfc7a41bf 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -256,9 +256,11 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs,
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
  */
-void __init swiotlb_init(bool addressing_limit, unsigned int flags)
+void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
+		int (*remap)(void *tlb, unsigned long nslabs))
 {
-	size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
+	unsigned long nslabs = default_nslabs;
+	size_t bytes;
 	void *tlb;
 
 	if (!addressing_limit && !swiotlb_force_bounce)
@@ -271,12 +273,23 @@ void __init swiotlb_init(bool addressing_limit, unsigned int flags)
 	 * allow to pick a location everywhere for hypervisors with guest
 	 * memory encryption.
 	 */
+retry:
+	bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
 	if (flags & SWIOTLB_ANY)
 		tlb = memblock_alloc(bytes, PAGE_SIZE);
 	else
 		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
 	if (!tlb)
 		goto fail;
+	if (remap && remap(tlb, nslabs) < 0) {
+		memblock_free(tlb, PAGE_ALIGN(bytes));
+
+		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+		if (nslabs < IO_TLB_MIN_SLABS)
+			panic("%s: Failed to remap %zu bytes\n",
+			      __func__, bytes);
+		goto retry;
+	}
 	if (swiotlb_init_with_tbl(tlb, default_nslabs, flags))
 		goto fail_free_mem;
 	return;
@@ -287,12 +300,18 @@ fail:
 	pr_warn("Cannot allocate buffer");
 }
 
+void __init swiotlb_init(bool addressing_limit, unsigned int flags)
+{
+	return swiotlb_init_remap(addressing_limit, flags, NULL);
+}
+
 /*
  * Systems with larger DMA zones (those that don't support ISA) can
  * initialize the swiotlb later using the slab allocator if needed.
  * This should be just like above, but with some error catching.
  */
-int swiotlb_init_late(size_t size, gfp_t gfp_mask)
+int swiotlb_init_late(size_t size, gfp_t gfp_mask,
+		int (*remap)(void *tlb, unsigned long nslabs))
 {
 	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
 	unsigned long bytes;
@@ -303,6 +322,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask)
 	if (swiotlb_force_disable)
 		return 0;
 
+retry:
 	order = get_order(nslabs << IO_TLB_SHIFT);
 	nslabs = SLABS_PER_PAGE << order;
 	bytes = nslabs << IO_TLB_SHIFT;
@@ -323,6 +343,16 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask)
 			(PAGE_SIZE << order) >> 20);
 		nslabs = SLABS_PER_PAGE << order;
 	}
+	if (remap)
+		rc = remap(vstart, nslabs);
+	if (rc) {
+		free_pages((unsigned long)vstart, order);
+
+		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+		if (nslabs < IO_TLB_MIN_SLABS)
+			return rc;
+		goto retry;
+	}
 	rc = swiotlb_late_init_with_tbl(vstart, nslabs);
 	if (rc)
 		free_pages((unsigned long)vstart, order);
-- 
cgit v1.2.3


From 6424e31b1c050a25aea033206d5f626f3523448c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 15 Mar 2022 07:41:04 +0100
Subject: swiotlb: remove swiotlb_init_with_tbl and swiotlb_init_late_with_tbl

No users left.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 include/linux/swiotlb.h |  2 --
 kernel/dma/swiotlb.c    | 77 +++++++++++++------------------------------------
 2 files changed, 20 insertions(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 7b50c82f84ce..7ed35dd3de6e 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -34,13 +34,11 @@ struct scatterlist;
 /* default to 64MB */
 #define IO_TLB_DEFAULT_SIZE (64UL<<20)
 
-int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags);
 unsigned long swiotlb_size_or_default(void);
 void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 	int (*remap)(void *tlb, unsigned long nslabs));
 int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 	int (*remap)(void *tlb, unsigned long nslabs));
-extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
 extern void __init swiotlb_update_mem_attributes(void);
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index f6acfc7a41bf..e2ef0864eb1e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -225,33 +225,6 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
 	return;
 }
 
-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs,
-		unsigned int flags)
-{
-	struct io_tlb_mem *mem = &io_tlb_default_mem;
-	size_t alloc_size;
-
-	if (swiotlb_force_disable)
-		return 0;
-
-	/* protect against double initialization */
-	if (WARN_ON_ONCE(mem->nslabs))
-		return -ENOMEM;
-
-	alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
-	mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
-	if (!mem->slots)
-		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
-		      __func__, alloc_size, PAGE_SIZE);
-
-	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false);
-	mem->force_bounce = flags & SWIOTLB_FORCE;
-
-	if (flags & SWIOTLB_VERBOSE)
-		swiotlb_print_info();
-	return 0;
-}
-
 /*
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
@@ -259,7 +232,9 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs,
 void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 		int (*remap)(void *tlb, unsigned long nslabs))
 {
+	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long nslabs = default_nslabs;
+	size_t alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
 	size_t bytes;
 	void *tlb;
 
@@ -280,7 +255,8 @@ retry:
 	else
 		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
 	if (!tlb)
-		goto fail;
+		panic("%s: failed to allocate tlb structure\n", __func__);
+
 	if (remap && remap(tlb, nslabs) < 0) {
 		memblock_free(tlb, PAGE_ALIGN(bytes));
 
@@ -290,14 +266,17 @@ retry:
 			      __func__, bytes);
 		goto retry;
 	}
-	if (swiotlb_init_with_tbl(tlb, default_nslabs, flags))
-		goto fail_free_mem;
-	return;
 
-fail_free_mem:
-	memblock_free(tlb, bytes);
-fail:
-	pr_warn("Cannot allocate buffer");
+	mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
+	if (!mem->slots)
+		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
+		      __func__, alloc_size, PAGE_SIZE);
+
+	swiotlb_init_io_tlb_mem(mem, __pa(tlb), default_nslabs, false);
+	mem->force_bounce = flags & SWIOTLB_FORCE;
+
+	if (flags & SWIOTLB_VERBOSE)
+		swiotlb_print_info();
 }
 
 void __init swiotlb_init(bool addressing_limit, unsigned int flags)
@@ -313,6 +292,7 @@ void __init swiotlb_init(bool addressing_limit, unsigned int flags)
 int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 		int (*remap)(void *tlb, unsigned long nslabs))
 {
+	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
 	unsigned long bytes;
 	unsigned char *vstart = NULL;
@@ -353,33 +333,16 @@ retry:
 			return rc;
 		goto retry;
 	}
-	rc = swiotlb_late_init_with_tbl(vstart, nslabs);
-	if (rc)
-		free_pages((unsigned long)vstart, order);
-
-	return rc;
-}
-
-int
-swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
-{
-	struct io_tlb_mem *mem = &io_tlb_default_mem;
-	unsigned long bytes = nslabs << IO_TLB_SHIFT;
-
-	if (swiotlb_force_disable)
-		return 0;
-
-	/* protect against double initialization */
-	if (WARN_ON_ONCE(mem->nslabs))
-		return -ENOMEM;
 
 	mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 		get_order(array_size(sizeof(*mem->slots), nslabs)));
-	if (!mem->slots)
+	if (!mem->slots) {
+		free_pages((unsigned long)vstart, order);
 		return -ENOMEM;
+	}
 
-	set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
-	swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true);
+	set_memory_decrypted((unsigned long)vstart, bytes >> PAGE_SHIFT);
+	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, true);
 
 	swiotlb_print_info();
 	return 0;
-- 
cgit v1.2.3


From f47a6113f4e87db7ca066635822e1b3ca3ed9514 Mon Sep 17 00:00:00 2001
From: Tzung-Bi Shih <tzungbi@kernel.org>
Date: Wed, 16 Feb 2022 16:03:03 +0800
Subject: platform/chrome: cros_ec: remove unused variable `was_wake_device`

Reviewed-by: Prashant Malani <pmalani@chromium.org>
Signed-off-by: Tzung-Bi Shih <tzungbi@kernel.org>
---
 drivers/platform/chrome/cros_ec.c           | 1 -
 include/linux/platform_data/cros_ec_proto.h | 3 ---
 2 files changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c
index a5cc8f24299e..836794871443 100644
--- a/drivers/platform/chrome/cros_ec.c
+++ b/drivers/platform/chrome/cros_ec.c
@@ -342,7 +342,6 @@ int cros_ec_suspend(struct cros_ec_device *ec_dev)
 		ec_dev->wake_enabled = !enable_irq_wake(ec_dev->irq);
 
 	disable_irq(ec_dev->irq);
-	ec_dev->was_wake_device = ec_dev->wake_enabled;
 	ec_dev->suspended = true;
 
 	return 0;
diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h
index df3c78c92ca2..c65971ec90ea 100644
--- a/include/linux/platform_data/cros_ec_proto.h
+++ b/include/linux/platform_data/cros_ec_proto.h
@@ -76,8 +76,6 @@ struct cros_ec_command {
  * struct cros_ec_device - Information about a ChromeOS EC device.
  * @phys_name: Name of physical comms layer (e.g. 'i2c-4').
  * @dev: Device pointer for physical comms device
- * @was_wake_device: True if this device was set to wake the system from
- *                   sleep at the last suspend.
  * @cros_class: The class structure for this device.
  * @cmd_readmem: Direct read of the EC memory-mapped region, if supported.
  *     @offset: Is within EC_LPC_ADDR_MEMMAP region.
@@ -137,7 +135,6 @@ struct cros_ec_device {
 	/* These are used by other drivers that want to talk to the EC */
 	const char *phys_name;
 	struct device *dev;
-	bool was_wake_device;
 	struct class *cros_class;
 	int (*cmd_readmem)(struct cros_ec_device *ec, unsigned int offset,
 			   unsigned int bytes, void *dest);
-- 
cgit v1.2.3


From 5f0614a55ecebdf55f1a17db0b5f6b787ed009f1 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sun, 17 Apr 2022 22:27:13 -0400
Subject: block: change exported IO accounting interface from gendisk to bdev

Export IO accounting interfaces in terms of block_device now that
gendisk has become more internal to block core.

Rename __part_{start,end}_io_acct's first argument from part to bdev.
Rename __part_{start,end}_io_acct to bdev_{start,end}_io_acct and
export them.  Remove disk_{start,end}_io_acct and update caller (zram)
to use bdev_{start,end}_io_acct.

DM can now be updated to use bdev_{start,end}_io_acct.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Link: https://lore.kernel.org/r/20220418022733.56168-2-snitzer@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c              | 52 +++++++++++++++++--------------------------
 drivers/block/zram/zram_drv.c |  5 +++--
 include/linux/blkdev.h        |  7 +++---
 3 files changed, 27 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index ee18b6a699bd..f305cb66c72a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1022,21 +1022,22 @@ again:
 	}
 }
 
-static unsigned long __part_start_io_acct(struct block_device *part,
-					  unsigned int sectors, unsigned int op,
-					  unsigned long start_time)
+unsigned long bdev_start_io_acct(struct block_device *bdev,
+				 unsigned int sectors, unsigned int op,
+				 unsigned long start_time)
 {
 	const int sgrp = op_stat_group(op);
 
 	part_stat_lock();
-	update_io_ticks(part, start_time, false);
-	part_stat_inc(part, ios[sgrp]);
-	part_stat_add(part, sectors[sgrp], sectors);
-	part_stat_local_inc(part, in_flight[op_is_write(op)]);
+	update_io_ticks(bdev, start_time, false);
+	part_stat_inc(bdev, ios[sgrp]);
+	part_stat_add(bdev, sectors[sgrp], sectors);
+	part_stat_local_inc(bdev, in_flight[op_is_write(op)]);
 	part_stat_unlock();
 
 	return start_time;
 }
+EXPORT_SYMBOL(bdev_start_io_acct);
 
 /**
  * bio_start_io_acct_time - start I/O accounting for bio based drivers
@@ -1045,8 +1046,8 @@ static unsigned long __part_start_io_acct(struct block_device *part,
  */
 void bio_start_io_acct_time(struct bio *bio, unsigned long start_time)
 {
-	__part_start_io_acct(bio->bi_bdev, bio_sectors(bio),
-			     bio_op(bio), start_time);
+	bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio),
+			   bio_op(bio), start_time);
 }
 EXPORT_SYMBOL_GPL(bio_start_io_acct_time);
 
@@ -1058,46 +1059,33 @@ EXPORT_SYMBOL_GPL(bio_start_io_acct_time);
  */
 unsigned long bio_start_io_acct(struct bio *bio)
 {
-	return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio),
-				    bio_op(bio), jiffies);
+	return bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio),
+				  bio_op(bio), jiffies);
 }
 EXPORT_SYMBOL_GPL(bio_start_io_acct);
 
-unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
-				 unsigned int op)
-{
-	return __part_start_io_acct(disk->part0, sectors, op, jiffies);
-}
-EXPORT_SYMBOL(disk_start_io_acct);
-
-static void __part_end_io_acct(struct block_device *part, unsigned int op,
-			       unsigned long start_time)
+void bdev_end_io_acct(struct block_device *bdev, unsigned int op,
+		      unsigned long start_time)
 {
 	const int sgrp = op_stat_group(op);
 	unsigned long now = READ_ONCE(jiffies);
 	unsigned long duration = now - start_time;
 
 	part_stat_lock();
-	update_io_ticks(part, now, true);
-	part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration));
-	part_stat_local_dec(part, in_flight[op_is_write(op)]);
+	update_io_ticks(bdev, now, true);
+	part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration));
+	part_stat_local_dec(bdev, in_flight[op_is_write(op)]);
 	part_stat_unlock();
 }
+EXPORT_SYMBOL(bdev_end_io_acct);
 
 void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
-		struct block_device *orig_bdev)
+			      struct block_device *orig_bdev)
 {
-	__part_end_io_acct(orig_bdev, bio_op(bio), start_time);
+	bdev_end_io_acct(orig_bdev, bio_op(bio), start_time);
 }
 EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped);
 
-void disk_end_io_acct(struct gendisk *disk, unsigned int op,
-		      unsigned long start_time)
-{
-	__part_end_io_acct(disk->part0, op, start_time);
-}
-EXPORT_SYMBOL(disk_end_io_acct);
-
 /**
  * blk_lld_busy - Check if underlying low-level drivers of a device are busy
  * @q : the queue of the device being checked
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 59ff444bf6c7..1b277308d3ec 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1675,9 +1675,10 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	start_time = disk_start_io_acct(bdev->bd_disk, SECTORS_PER_PAGE, op);
+	start_time = bdev_start_io_acct(bdev->bd_disk->part0,
+			SECTORS_PER_PAGE, op, jiffies);
 	ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL);
-	disk_end_io_acct(bdev->bd_disk, op, start_time);
+	bdev_end_io_acct(bdev->bd_disk->part0, op, start_time);
 out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c9b5925af5a3..34724b15813b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1463,9 +1463,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter)
 		wake_up_process(waiter);
 }
 
-unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
-		unsigned int op);
-void disk_end_io_acct(struct gendisk *disk, unsigned int op,
+unsigned long bdev_start_io_acct(struct block_device *bdev,
+				 unsigned int sectors, unsigned int op,
+				 unsigned long start_time);
+void bdev_end_io_acct(struct block_device *bdev, unsigned int op,
 		unsigned long start_time);
 
 void bio_start_io_acct_time(struct bio *bio, unsigned long start_time);
-- 
cgit v1.2.3


From dbdc1be32591af023db2812706f01e6cd2f42bfc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 30 Mar 2022 07:29:06 +0200
Subject: block: add a disk_openers helper

Add a helper that returns the openers for a given gendisk to avoid having
drivers poke into disk->part0 to get at this information in a somewhat
cumbersome way.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220330052917.2566582-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/nbd.c           |  4 ++--
 drivers/block/zram/zram_drv.c |  4 ++--
 include/linux/blkdev.h        | 15 +++++++++++++++
 3 files changed, 19 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index dab24c58d5cc..526389351784 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1219,7 +1219,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 
 static void nbd_bdev_reset(struct nbd_device *nbd)
 {
-	if (nbd->disk->part0->bd_openers > 1)
+	if (disk_openers(nbd->disk) > 1)
 		return;
 	set_capacity(nbd->disk, 0);
 }
@@ -1576,7 +1576,7 @@ static void nbd_release(struct gendisk *disk, fmode_t mode)
 	struct nbd_device *nbd = disk->private_data;
 
 	if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
-			disk->part0->bd_openers == 0)
+			disk_openers(disk) == 0)
 		nbd_disconnect_and_put(nbd);
 
 	nbd_config_put(nbd);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 70d4bd662ab6..dc5ac5963377 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1800,7 +1800,7 @@ static ssize_t reset_store(struct device *dev,
 
 	mutex_lock(&disk->open_mutex);
 	/* Do not reset an active device or claimed device */
-	if (disk->part0->bd_openers || zram->claim) {
+	if (disk_openers(disk) || zram->claim) {
 		mutex_unlock(&disk->open_mutex);
 		return -EBUSY;
 	}
@@ -1989,7 +1989,7 @@ static int zram_remove(struct zram *zram)
 	bool claimed;
 
 	mutex_lock(&zram->disk->open_mutex);
-	if (zram->disk->part0->bd_openers) {
+	if (disk_openers(zram->disk)) {
 		mutex_unlock(&zram->disk->open_mutex);
 		return -EBUSY;
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c9b5925af5a3..436645bde13f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -176,6 +176,21 @@ static inline bool disk_live(struct gendisk *disk)
 	return !inode_unhashed(disk->part0->bd_inode);
 }
 
+/**
+ * disk_openers - returns how many openers are there for a disk
+ * @disk: disk to check
+ *
+ * This returns the number of openers for a disk.  Note that this value is only
+ * stable if disk->open_mutex is held.
+ *
+ * Note: Due to a quirk in the block layer open code, each open partition is
+ * only counted once even if there are multiple openers.
+ */
+static inline unsigned int disk_openers(struct gendisk *disk)
+{
+	return disk->part0->bd_openers;
+}
+
 /*
  * The gendisk is refcounted by the part0 block_device, and the bd_device
  * therein is also used for device model presentation in sysfs.
-- 
cgit v1.2.3


From 9acf381f3e8f715175c29f4b6d722f6b6797d139 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 30 Mar 2022 07:29:07 +0200
Subject: block: turn bdev->bd_openers into an atomic_t

All manipulation of bd_openers is under disk->open_mutex and will remain
so for the foreseeable future.  But at least one place reads it without
the lock (blkdev_get) and there are more to be added.  So make sure the
compiler does not do turn the increments and decrements into non-atomic
sequences by using an atomic_t.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220330052917.2566582-6-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bdev.c              | 16 ++++++++--------
 block/partitions/core.c   |  2 +-
 include/linux/blk_types.h |  2 +-
 include/linux/blkdev.h    |  2 +-
 4 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/block/bdev.c b/block/bdev.c
index 13de871fa816..7bf88e591aaf 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -673,17 +673,17 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
 		}
 	}
 
-	if (!bdev->bd_openers)
+	if (!atomic_read(&bdev->bd_openers))
 		set_init_blocksize(bdev);
 	if (test_bit(GD_NEED_PART_SCAN, &disk->state))
 		bdev_disk_changed(disk, false);
-	bdev->bd_openers++;
+	atomic_inc(&bdev->bd_openers);
 	return 0;
 }
 
 static void blkdev_put_whole(struct block_device *bdev, fmode_t mode)
 {
-	if (!--bdev->bd_openers)
+	if (atomic_dec_and_test(&bdev->bd_openers))
 		blkdev_flush_mapping(bdev);
 	if (bdev->bd_disk->fops->release)
 		bdev->bd_disk->fops->release(bdev->bd_disk, mode);
@@ -694,7 +694,7 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode)
 	struct gendisk *disk = part->bd_disk;
 	int ret;
 
-	if (part->bd_openers)
+	if (atomic_read(&part->bd_openers))
 		goto done;
 
 	ret = blkdev_get_whole(bdev_whole(part), mode);
@@ -708,7 +708,7 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode)
 	disk->open_partitions++;
 	set_init_blocksize(part);
 done:
-	part->bd_openers++;
+	atomic_inc(&part->bd_openers);
 	return 0;
 
 out_blkdev_put:
@@ -720,7 +720,7 @@ static void blkdev_put_part(struct block_device *part, fmode_t mode)
 {
 	struct block_device *whole = bdev_whole(part);
 
-	if (--part->bd_openers)
+	if (!atomic_dec_and_test(&part->bd_openers))
 		return;
 	blkdev_flush_mapping(part);
 	whole->bd_disk->open_partitions--;
@@ -899,7 +899,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 	 * of the world and we want to avoid long (could be several minute)
 	 * syncs while holding the mutex.
 	 */
-	if (bdev->bd_openers == 1)
+	if (atomic_read(&bdev->bd_openers) == 1)
 		sync_blockdev(bdev);
 
 	mutex_lock(&disk->open_mutex);
@@ -1044,7 +1044,7 @@ void sync_bdevs(bool wait)
 		bdev = I_BDEV(inode);
 
 		mutex_lock(&bdev->bd_disk->open_mutex);
-		if (!bdev->bd_openers) {
+		if (!atomic_read(&bdev->bd_openers)) {
 			; /* skip */
 		} else if (wait) {
 			/*
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 70dec1c78521..8a0ec929023b 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -478,7 +478,7 @@ int bdev_del_partition(struct gendisk *disk, int partno)
 		goto out_unlock;
 
 	ret = -EBUSY;
-	if (part->bd_openers)
+	if (atomic_read(&part->bd_openers))
 		goto out_unlock;
 
 	delete_partition(part);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 4968cb17b13b..c62274466e72 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -44,7 +44,7 @@ struct block_device {
 	unsigned long		bd_stamp;
 	bool			bd_read_only;	/* read-only policy */
 	dev_t			bd_dev;
-	int			bd_openers;
+	atomic_t		bd_openers;
 	struct inode *		bd_inode;	/* will die */
 	struct super_block *	bd_super;
 	void *			bd_claiming;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 436645bde13f..afad3d1d0dac 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -188,7 +188,7 @@ static inline bool disk_live(struct gendisk *disk)
  */
 static inline unsigned int disk_openers(struct gendisk *disk)
 {
-	return disk->part0->bd_openers;
+	return atomic_read(&disk->part0->bd_openers);
 }
 
 /*
-- 
cgit v1.2.3


From 57b888ca2541785de2fcb90575b378921919b6c0 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 18 Mar 2022 09:54:22 -0700
Subject: platform/chrome: Re-introduce cros_ec_cmd_xfer and use it for ioctls

Commit 413dda8f2c6f ("platform/chrome: cros_ec_chardev: Use
cros_ec_cmd_xfer_status helper") inadvertendly changed the userspace ABI.
Previously, cros_ec ioctls would only report errors if the EC communication
failed, and otherwise return success and the result of the EC
communication. An EC command execution failure was reported in the EC
response field. The above mentioned commit changed this behavior, and the
ioctl itself would fail. This breaks userspace commands trying to analyze
the EC command execution error since the actual EC command response is no
longer reported to userspace.

Fix the problem by re-introducing the cros_ec_cmd_xfer() helper, and use it
to handle ioctl messages.

Fixes: 413dda8f2c6f ("platform/chrome: cros_ec_chardev: Use cros_ec_cmd_xfer_status helper")
Cc: Daisuke Nojiri <dnojiri@chromium.org>
Cc: Rob Barnes <robbarnes@google.com>
Cc: Rajat Jain <rajatja@google.com>
Cc: Brian Norris <briannorris@chromium.org>
Cc: Parth Malkan <parthmalkan@google.com>
Reviewed-by: Daisuke Nojiri <dnojiri@chromium.org>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Tzung-Bi Shih <tzungbi@kernel.org>
---
 drivers/platform/chrome/cros_ec_chardev.c   |  2 +-
 drivers/platform/chrome/cros_ec_proto.c     | 50 +++++++++++++++++++++++------
 include/linux/platform_data/cros_ec_proto.h |  3 ++
 3 files changed, 45 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/chrome/cros_ec_chardev.c b/drivers/platform/chrome/cros_ec_chardev.c
index e0bce869c49a..fd33de546aee 100644
--- a/drivers/platform/chrome/cros_ec_chardev.c
+++ b/drivers/platform/chrome/cros_ec_chardev.c
@@ -301,7 +301,7 @@ static long cros_ec_chardev_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg)
 	}
 
 	s_cmd->command += ec->cmd_offset;
-	ret = cros_ec_cmd_xfer_status(ec->ec_dev, s_cmd);
+	ret = cros_ec_cmd_xfer(ec->ec_dev, s_cmd);
 	/* Only copy data to userland if data was received. */
 	if (ret < 0)
 		goto exit;
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index c4caf2e2de82..ac1419881ff3 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -560,22 +560,28 @@ exit:
 EXPORT_SYMBOL(cros_ec_query_all);
 
 /**
- * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC.
+ * cros_ec_cmd_xfer() - Send a command to the ChromeOS EC.
  * @ec_dev: EC device.
  * @msg: Message to write.
  *
- * Call this to send a command to the ChromeOS EC. This should be used instead of calling the EC's
- * cmd_xfer() callback directly. It returns success status only if both the command was transmitted
- * successfully and the EC replied with success status.
+ * Call this to send a command to the ChromeOS EC. This should be used instead
+ * of calling the EC's cmd_xfer() callback directly. This function does not
+ * convert EC command execution error codes to Linux error codes. Most
+ * in-kernel users will want to use cros_ec_cmd_xfer_status() instead since
+ * that function implements the conversion.
  *
  * Return:
- * >=0 - The number of bytes transferred
- * <0 - Linux error code
+ * >0 - EC command was executed successfully. The return value is the number
+ *      of bytes returned by the EC (excluding the header).
+ * =0 - EC communication was successful. EC command execution results are
+ *      reported in msg->result. The result will be EC_RES_SUCCESS if the
+ *      command was executed successfully or report an EC command execution
+ *      error.
+ * <0 - EC communication error. Return value is the Linux error code.
  */
-int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev,
-			    struct cros_ec_command *msg)
+int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg)
 {
-	int ret, mapped;
+	int ret;
 
 	mutex_lock(&ec_dev->lock);
 	if (ec_dev->proto_version == EC_PROTO_VERSION_UNKNOWN) {
@@ -616,6 +622,32 @@ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev,
 	ret = send_command(ec_dev, msg);
 	mutex_unlock(&ec_dev->lock);
 
+	return ret;
+}
+EXPORT_SYMBOL(cros_ec_cmd_xfer);
+
+/**
+ * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC.
+ * @ec_dev: EC device.
+ * @msg: Message to write.
+ *
+ * Call this to send a command to the ChromeOS EC. This should be used instead of calling the EC's
+ * cmd_xfer() callback directly. It returns success status only if both the command was transmitted
+ * successfully and the EC replied with success status.
+ *
+ * Return:
+ * >=0 - The number of bytes transferred.
+ * <0 - Linux error code
+ */
+int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev,
+			    struct cros_ec_command *msg)
+{
+	int ret, mapped;
+
+	ret = cros_ec_cmd_xfer(ec_dev, msg);
+	if (ret < 0)
+		return ret;
+
 	mapped = cros_ec_map_error(msg->result);
 	if (mapped) {
 		dev_dbg(ec_dev->dev, "Command result (err: %d [%d])\n",
diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h
index c65971ec90ea..138fd912c808 100644
--- a/include/linux/platform_data/cros_ec_proto.h
+++ b/include/linux/platform_data/cros_ec_proto.h
@@ -213,6 +213,9 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev,
 int cros_ec_check_result(struct cros_ec_device *ec_dev,
 			 struct cros_ec_command *msg);
 
+int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
+		     struct cros_ec_command *msg);
+
 int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev,
 			    struct cros_ec_command *msg);
 
-- 
cgit v1.2.3


From 2f1e85b1aee459b7d0fd981839042c6a38ffaf0c Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Sat, 16 Apr 2022 00:40:45 +0800
Subject: net: sched: use queue_mapping to pick tx queue

This patch fixes issue:
* If we install tc filters with act_skbedit in clsact hook.
  It doesn't work, because netdev_core_pick_tx() overwrites
  queue_mapping.

  $ tc filter ... action skbedit queue_mapping 1

And this patch is useful:
* We can use FQ + EDT to implement efficient policies. Tx queues
  are picked by xps, ndo_select_queue of netdev driver, or skb hash
  in netdev_core_pick_tx(). In fact, the netdev driver, and skb
  hash are _not_ under control. xps uses the CPUs map to select Tx
  queues, but we can't figure out which task_struct of pod/containter
  running on this cpu in most case. We can use clsact filters to classify
  one pod/container traffic to one Tx queue. Why ?

  In containter networking environment, there are two kinds of pod/
  containter/net-namespace. One kind (e.g. P1, P2), the high throughput
  is key in these applications. But avoid running out of network resource,
  the outbound traffic of these pods is limited, using or sharing one
  dedicated Tx queues assigned HTB/TBF/FQ Qdisc. Other kind of pods
  (e.g. Pn), the low latency of data access is key. And the traffic is not
  limited. Pods use or share other dedicated Tx queues assigned FIFO Qdisc.
  This choice provides two benefits. First, contention on the HTB/FQ Qdisc
  lock is significantly reduced since fewer CPUs contend for the same queue.
  More importantly, Qdisc contention can be eliminated completely if each
  CPU has its own FIFO Qdisc for the second kind of pods.

  There must be a mechanism in place to support classifying traffic based on
  pods/container to different Tx queues. Note that clsact is outside of Qdisc
  while Qdisc can run a classifier to select a sub-queue under the lock.

  In general recording the decision in the skb seems a little heavy handed.
  This patch introduces a per-CPU variable, suggested by Eric.

  The xmit.skip_txqueue flag is firstly cleared in __dev_queue_xmit().
  - Tx Qdisc may install that skbedit actions, then xmit.skip_txqueue flag
    is set in qdisc->enqueue() though tx queue has been selected in
    netdev_tx_queue_mapping() or netdev_core_pick_tx(). That flag is cleared
    firstly in __dev_queue_xmit(), is useful:
  - Avoid picking Tx queue with netdev_tx_queue_mapping() in next netdev
    in such case: eth0 macvlan - eth0.3 vlan - eth0 ixgbe-phy:
    For example, eth0, macvlan in pod, which root Qdisc install skbedit
    queue_mapping, send packets to eth0.3, vlan in host. In __dev_queue_xmit() of
    eth0.3, clear the flag, does not select tx queue according to skb->queue_mapping
    because there is no filters in clsact or tx Qdisc of this netdev.
    Same action taked in eth0, ixgbe in Host.
  - Avoid picking Tx queue for next packet. If we set xmit.skip_txqueue
    in tx Qdisc (qdisc->enqueue()), the proper way to clear it is clearing it
    in __dev_queue_xmit when processing next packets.

  For performance reasons, use the static key. If user does not config the NET_EGRESS,
  the patch will not be compiled.

  +----+      +----+      +----+
  | P1 |      | P2 |      | Pn |
  +----+      +----+      +----+
    |           |           |
    +-----------+-----------+
                |
                | clsact/skbedit
                |      MQ
                v
    +-----------+-----------+
    | q0        | q1        | qn
    v           v           v
  HTB/FQ      HTB/FQ  ...  FIFO

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Talal Ahmad <talalahmad@google.com>
Cc: Kevin Hao <haokexin@gmail.com>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Antoine Tenart <atenart@kernel.org>
Cc: Wei Wang <weiwan@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h |  3 +++
 include/linux/rtnetlink.h |  1 +
 net/core/dev.c            | 31 +++++++++++++++++++++++++++++--
 net/sched/act_skbedit.c   |  6 +++++-
 4 files changed, 38 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a602f29365b0..7dccbfd1bf56 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3061,6 +3061,9 @@ struct softnet_data {
 	struct {
 		u16 recursion;
 		u8  more;
+#ifdef CONFIG_NET_EGRESS
+		u8  skip_txqueue;
+#endif
 	} xmit;
 #ifdef CONFIG_RPS
 	/* input_queue_head should be written by cpu owning this struct,
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 7f970b16da3a..ae2c6a3cec5d 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -100,6 +100,7 @@ void net_dec_ingress_queue(void);
 #ifdef CONFIG_NET_EGRESS
 void net_inc_egress_queue(void);
 void net_dec_egress_queue(void);
+void netdev_xmit_skip_txqueue(bool skip);
 #endif
 
 void rtnetlink_init(void);
diff --git a/net/core/dev.c b/net/core/dev.c
index ba853e878007..4a77ebda4fb1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3925,6 +3925,25 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 
 	return skb;
 }
+
+static struct netdev_queue *
+netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
+{
+	int qm = skb_get_queue_mapping(skb);
+
+	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
+}
+
+static bool netdev_xmit_txqueue_skipped(void)
+{
+	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
+}
+
+void netdev_xmit_skip_txqueue(bool skip)
+{
+	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
+}
+EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
 #endif /* CONFIG_NET_EGRESS */
 
 #ifdef CONFIG_XPS
@@ -4095,7 +4114,7 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
 static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 {
 	struct net_device *dev = skb->dev;
-	struct netdev_queue *txq;
+	struct netdev_queue *txq = NULL;
 	struct Qdisc *q;
 	int rc = -ENOMEM;
 	bool again = false;
@@ -4123,11 +4142,17 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 		}
+
+		netdev_xmit_skip_txqueue(false);
+
 		nf_skip_egress(skb, true);
 		skb = sch_handle_egress(skb, &rc, dev);
 		if (!skb)
 			goto out;
 		nf_skip_egress(skb, false);
+
+		if (netdev_xmit_txqueue_skipped())
+			txq = netdev_tx_queue_mapping(dev, skb);
 	}
 #endif
 	/* If device/qdisc don't need skb->dst, release it right now while
@@ -4138,7 +4163,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	else
 		skb_dst_force(skb);
 
-	txq = netdev_core_pick_tx(dev, skb, sb_dev);
+	if (!txq)
+		txq = netdev_core_pick_tx(dev, skb, sb_dev);
+
 	q = rcu_dereference_bh(txq->qdisc);
 
 	trace_net_dev_queue(skb);
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 92d0dc754207..1c5fdb6e7c2f 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -58,8 +58,12 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 		}
 	}
 	if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
-	    skb->dev->real_num_tx_queues > params->queue_mapping)
+	    skb->dev->real_num_tx_queues > params->queue_mapping) {
+#ifdef CONFIG_NET_EGRESS
+		netdev_xmit_skip_txqueue(true);
+#endif
 		skb_set_queue_mapping(skb, params->queue_mapping);
+	}
 	if (params->flags & SKBEDIT_F_MARK) {
 		skb->mark &= ~params->mask;
 		skb->mark |= params->mark & params->mask;
-- 
cgit v1.2.3


From c6547c2ed0e1487c91983faccad841611ab6a783 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Thu, 14 Apr 2022 18:22:37 +0200
Subject: dmaengine: imx: Move header to include/dma/

The i.MX DMA drivers are device tree only, nothing in
include/linux/platform_data/dma-imx.h has platform_data in it, so move
the file to include/linux/dma/imx-dma.h.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-By: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20220414162249.3934543-10-s.hauer@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/dma/imx-dma.c                 |  2 +-
 drivers/dma/imx-sdma.c                |  2 +-
 drivers/mmc/host/mxcmmc.c             |  2 +-
 drivers/spi/spi-fsl-lpspi.c           |  2 +-
 drivers/spi/spi-imx.c                 |  2 +-
 drivers/tty/serial/imx.c              |  2 +-
 drivers/video/fbdev/mx3fb.c           |  2 +-
 include/linux/dma/imx-dma.h           | 68 +++++++++++++++++++++++++++++++++++
 include/linux/platform_data/dma-imx.h | 68 -----------------------------------
 sound/soc/fsl/fsl_asrc.c              |  2 +-
 sound/soc/fsl/fsl_asrc_dma.c          |  2 +-
 sound/soc/fsl/fsl_easrc.h             |  2 +-
 sound/soc/fsl/imx-pcm.h               |  2 +-
 sound/soc/fsl/imx-ssi.h               |  2 +-
 14 files changed, 80 insertions(+), 80 deletions(-)
 create mode 100644 include/linux/dma/imx-dma.h
 delete mode 100644 include/linux/platform_data/dma-imx.h

(limited to 'include/linux')

diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 2ddc31e64db0..3bffe3ecbd1b 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -25,7 +25,7 @@
 #include <linux/of_dma.h>
 
 #include <asm/irq.h>
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 
 #include "dmaengine.h"
 #define IMXDMA_MAX_CHAN_DESCRIPTORS	16
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 70c0aa931ddf..80261a905eb5 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -35,7 +35,7 @@
 #include <linux/workqueue.h>
 
 #include <asm/irq.h>
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 #include <linux/regmap.h>
 #include <linux/mfd/syscon.h>
 #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 40b6878bea6c..de04b5afef2e 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -39,7 +39,7 @@
 #include <asm/irq.h>
 #include <linux/platform_data/mmc-mxcmmc.h>
 
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 
 #define DRIVER_NAME "mxc-mmc"
 #define MXCMCI_TIMEOUT_MS 10000
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 4c601294f8fa..19b1f3d881b0 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -20,7 +20,7 @@
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index b2dd0a4d2446..a944c787f53f 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -24,7 +24,7 @@
 #include <linux/of_device.h>
 #include <linux/property.h>
 
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 
 #define DRIVER_NAME "spi_imx"
 
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index fd38e6ed4fda..f8b5400e6267 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -30,7 +30,7 @@
 #include <linux/dma-mapping.h>
 
 #include <asm/irq.h>
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 
 #include "serial_mctrl_gpio.h"
 
diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c
index fabb271337ed..b945b68984b9 100644
--- a/drivers/video/fbdev/mx3fb.c
+++ b/drivers/video/fbdev/mx3fb.c
@@ -26,7 +26,7 @@
 #include <linux/dma/ipu-dma.h>
 #include <linux/backlight.h>
 
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 #include <linux/platform_data/video-mx3fb.h>
 
 #include <asm/io.h>
diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h
new file mode 100644
index 000000000000..b06cba85a6d4
--- /dev/null
+++ b/include/linux/dma/imx-dma.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2004-2009 Freescale Semiconductor, Inc. All Rights Reserved.
+ */
+
+#ifndef __LINUX_DMA_IMX_H
+#define __LINUX_DMA_IMX_H
+
+#include <linux/scatterlist.h>
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+
+/*
+ * This enumerates peripheral types. Used for SDMA.
+ */
+enum sdma_peripheral_type {
+	IMX_DMATYPE_SSI,	/* MCU domain SSI */
+	IMX_DMATYPE_SSI_SP,	/* Shared SSI */
+	IMX_DMATYPE_MMC,	/* MMC */
+	IMX_DMATYPE_SDHC,	/* SDHC */
+	IMX_DMATYPE_UART,	/* MCU domain UART */
+	IMX_DMATYPE_UART_SP,	/* Shared UART */
+	IMX_DMATYPE_FIRI,	/* FIRI */
+	IMX_DMATYPE_CSPI,	/* MCU domain CSPI */
+	IMX_DMATYPE_CSPI_SP,	/* Shared CSPI */
+	IMX_DMATYPE_SIM,	/* SIM */
+	IMX_DMATYPE_ATA,	/* ATA */
+	IMX_DMATYPE_CCM,	/* CCM */
+	IMX_DMATYPE_EXT,	/* External peripheral */
+	IMX_DMATYPE_MSHC,	/* Memory Stick Host Controller */
+	IMX_DMATYPE_MSHC_SP,	/* Shared Memory Stick Host Controller */
+	IMX_DMATYPE_DSP,	/* DSP */
+	IMX_DMATYPE_MEMORY,	/* Memory */
+	IMX_DMATYPE_FIFO_MEMORY,/* FIFO type Memory */
+	IMX_DMATYPE_SPDIF,	/* SPDIF */
+	IMX_DMATYPE_IPU_MEMORY,	/* IPU Memory */
+	IMX_DMATYPE_ASRC,	/* ASRC */
+	IMX_DMATYPE_ESAI,	/* ESAI */
+	IMX_DMATYPE_SSI_DUAL,	/* SSI Dual FIFO */
+	IMX_DMATYPE_ASRC_SP,	/* Shared ASRC */
+	IMX_DMATYPE_SAI,	/* SAI */
+};
+
+enum imx_dma_prio {
+	DMA_PRIO_HIGH = 0,
+	DMA_PRIO_MEDIUM = 1,
+	DMA_PRIO_LOW = 2
+};
+
+struct imx_dma_data {
+	int dma_request; /* DMA request line */
+	int dma_request2; /* secondary DMA request line */
+	enum sdma_peripheral_type peripheral_type;
+	int priority;
+};
+
+static inline int imx_dma_is_ipu(struct dma_chan *chan)
+{
+	return !strcmp(dev_name(chan->device->dev), "ipu-core");
+}
+
+static inline int imx_dma_is_general_purpose(struct dma_chan *chan)
+{
+	return !strcmp(chan->device->dev->driver->name, "imx-sdma") ||
+		!strcmp(chan->device->dev->driver->name, "imx-dma");
+}
+
+#endif /* __LINUX_DMA_IMX_H */
diff --git a/include/linux/platform_data/dma-imx.h b/include/linux/platform_data/dma-imx.h
deleted file mode 100644
index 281adbb26e6b..000000000000
--- a/include/linux/platform_data/dma-imx.h
+++ /dev/null
@@ -1,68 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright 2004-2009 Freescale Semiconductor, Inc. All Rights Reserved.
- */
-
-#ifndef __ASM_ARCH_MXC_DMA_H__
-#define __ASM_ARCH_MXC_DMA_H__
-
-#include <linux/scatterlist.h>
-#include <linux/device.h>
-#include <linux/dmaengine.h>
-
-/*
- * This enumerates peripheral types. Used for SDMA.
- */
-enum sdma_peripheral_type {
-	IMX_DMATYPE_SSI,	/* MCU domain SSI */
-	IMX_DMATYPE_SSI_SP,	/* Shared SSI */
-	IMX_DMATYPE_MMC,	/* MMC */
-	IMX_DMATYPE_SDHC,	/* SDHC */
-	IMX_DMATYPE_UART,	/* MCU domain UART */
-	IMX_DMATYPE_UART_SP,	/* Shared UART */
-	IMX_DMATYPE_FIRI,	/* FIRI */
-	IMX_DMATYPE_CSPI,	/* MCU domain CSPI */
-	IMX_DMATYPE_CSPI_SP,	/* Shared CSPI */
-	IMX_DMATYPE_SIM,	/* SIM */
-	IMX_DMATYPE_ATA,	/* ATA */
-	IMX_DMATYPE_CCM,	/* CCM */
-	IMX_DMATYPE_EXT,	/* External peripheral */
-	IMX_DMATYPE_MSHC,	/* Memory Stick Host Controller */
-	IMX_DMATYPE_MSHC_SP,	/* Shared Memory Stick Host Controller */
-	IMX_DMATYPE_DSP,	/* DSP */
-	IMX_DMATYPE_MEMORY,	/* Memory */
-	IMX_DMATYPE_FIFO_MEMORY,/* FIFO type Memory */
-	IMX_DMATYPE_SPDIF,	/* SPDIF */
-	IMX_DMATYPE_IPU_MEMORY,	/* IPU Memory */
-	IMX_DMATYPE_ASRC,	/* ASRC */
-	IMX_DMATYPE_ESAI,	/* ESAI */
-	IMX_DMATYPE_SSI_DUAL,	/* SSI Dual FIFO */
-	IMX_DMATYPE_ASRC_SP,	/* Shared ASRC */
-	IMX_DMATYPE_SAI,	/* SAI */
-};
-
-enum imx_dma_prio {
-	DMA_PRIO_HIGH = 0,
-	DMA_PRIO_MEDIUM = 1,
-	DMA_PRIO_LOW = 2
-};
-
-struct imx_dma_data {
-	int dma_request; /* DMA request line */
-	int dma_request2; /* secondary DMA request line */
-	enum sdma_peripheral_type peripheral_type;
-	int priority;
-};
-
-static inline int imx_dma_is_ipu(struct dma_chan *chan)
-{
-	return !strcmp(dev_name(chan->device->dev), "ipu-core");
-}
-
-static inline int imx_dma_is_general_purpose(struct dma_chan *chan)
-{
-	return !strcmp(chan->device->dev->driver->name, "imx-sdma") ||
-		!strcmp(chan->device->dev->driver->name, "imx-dma");
-}
-
-#endif
diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index d7d1536a4f37..ad4e6747b839 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -11,7 +11,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 #include <linux/pm_runtime.h>
 #include <sound/dmaengine_pcm.h>
 #include <sound/pcm_params.h>
diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c
index cd9b36ec0ecb..5038faf035cb 100644
--- a/sound/soc/fsl/fsl_asrc_dma.c
+++ b/sound/soc/fsl/fsl_asrc_dma.c
@@ -8,7 +8,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 #include <sound/dmaengine_pcm.h>
 #include <sound/pcm_params.h>
 
diff --git a/sound/soc/fsl/fsl_easrc.h b/sound/soc/fsl/fsl_easrc.h
index 30620d56252c..86d5c360d4f5 100644
--- a/sound/soc/fsl/fsl_easrc.h
+++ b/sound/soc/fsl/fsl_easrc.h
@@ -7,7 +7,7 @@
 #define _FSL_EASRC_H
 
 #include <sound/asound.h>
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 
 #include "fsl_asrc_common.h"
 
diff --git a/sound/soc/fsl/imx-pcm.h b/sound/soc/fsl/imx-pcm.h
index 5c6cf1ca8c8a..06b25f4b26b6 100644
--- a/sound/soc/fsl/imx-pcm.h
+++ b/sound/soc/fsl/imx-pcm.h
@@ -9,7 +9,7 @@
 #ifndef _IMX_PCM_H
 #define _IMX_PCM_H
 
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 
 /*
  * Do not change this as the FIQ handler depends on this size
diff --git a/sound/soc/fsl/imx-ssi.h b/sound/soc/fsl/imx-ssi.h
index 19cd0937e740..2d30d822451a 100644
--- a/sound/soc/fsl/imx-ssi.h
+++ b/sound/soc/fsl/imx-ssi.h
@@ -182,7 +182,7 @@
 #define DRV_NAME "imx-ssi"
 
 #include <linux/dmaengine.h>
-#include <linux/platform_data/dma-imx.h>
+#include <linux/dma/imx-dma.h>
 #include <sound/dmaengine_pcm.h>
 #include "imx-pcm.h"
 
-- 
cgit v1.2.3


From 824a0a02cd74776461aaa30d792b1ed9111c9aa5 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Thu, 14 Apr 2022 18:22:39 +0200
Subject: dmaengine: imx-sdma: Add multi fifo support

The i.MX SDMA engine can read from / write to multiple successive
hardware FIFO registers, referred to as "Multi FIFO support". This is
needed for the micfil driver and certain configurations of the SAI
driver. This patch adds support for this feature.

The number of FIFOs to read from / write to must be communicated from
the client driver to the SDMA engine. For this the struct
dma_slave_config::peripheral_config field is used.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-By: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20220414162249.3934543-12-s.hauer@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/dma/imx-sdma.c      | 57 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/dma/imx-dma.h | 20 ++++++++++++++++
 2 files changed, 77 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 0e70843567ce..95367a8a81a5 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -14,6 +14,7 @@
 #include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
@@ -73,6 +74,7 @@
 #define SDMA_CHNENBL0_IMX35	0x200
 #define SDMA_CHNENBL0_IMX31	0x080
 #define SDMA_CHNPRI_0		0x100
+#define SDMA_DONE0_CONFIG	0x1000
 
 /*
  * Buffer descriptor status values.
@@ -180,6 +182,12 @@
 				 BIT(DMA_MEM_TO_DEV) | \
 				 BIT(DMA_DEV_TO_DEV))
 
+#define SDMA_WATERMARK_LEVEL_N_FIFOS	GENMASK(15, 12)
+#define SDMA_WATERMARK_LEVEL_SW_DONE	BIT(23)
+
+#define SDMA_DONE0_CONFIG_DONE_SEL	BIT(7)
+#define SDMA_DONE0_CONFIG_DONE_DIS	BIT(6)
+
 /**
  * struct sdma_script_start_addrs - SDMA script start pointers
  *
@@ -441,6 +449,9 @@ struct sdma_channel {
 	struct work_struct		terminate_worker;
 	struct list_head                terminated;
 	bool				is_ram_script;
+	unsigned int			n_fifos_src;
+	unsigned int			n_fifos_dst;
+	bool				sw_done;
 };
 
 #define IMX_DMA_SG_LOOP		BIT(0)
@@ -778,6 +789,14 @@ static void sdma_event_enable(struct sdma_channel *sdmac, unsigned int event)
 	val = readl_relaxed(sdma->regs + chnenbl);
 	__set_bit(channel, &val);
 	writel_relaxed(val, sdma->regs + chnenbl);
+
+	/* Set SDMA_DONEx_CONFIG is sw_done enabled */
+	if (sdmac->sw_done) {
+		val = readl_relaxed(sdma->regs + SDMA_DONE0_CONFIG);
+		val |= SDMA_DONE0_CONFIG_DONE_SEL;
+		val &= ~SDMA_DONE0_CONFIG_DONE_DIS;
+		writel_relaxed(val, sdma->regs + SDMA_DONE0_CONFIG);
+	}
 }
 
 static void sdma_event_disable(struct sdma_channel *sdmac, unsigned int event)
@@ -1038,6 +1057,10 @@ static int sdma_get_pc(struct sdma_channel *sdmac,
 	case IMX_DMATYPE_IPU_MEMORY:
 		emi_2_per = sdma->script_addrs->ext_mem_2_ipu_addr;
 		break;
+	case IMX_DMATYPE_MULTI_SAI:
+		per_2_emi = sdma->script_addrs->sai_2_mcu_addr;
+		emi_2_per = sdma->script_addrs->mcu_2_sai_addr;
+		break;
 	default:
 		dev_err(sdma->dev, "Unsupported transfer type %d\n",
 			peripheral_type);
@@ -1214,6 +1237,22 @@ static void sdma_set_watermarklevel_for_p2p(struct sdma_channel *sdmac)
 	sdmac->watermark_level |= SDMA_WATERMARK_LEVEL_CONT;
 }
 
+static void sdma_set_watermarklevel_for_sais(struct sdma_channel *sdmac)
+{
+	unsigned int n_fifos;
+
+	if (sdmac->sw_done)
+		sdmac->watermark_level |= SDMA_WATERMARK_LEVEL_SW_DONE;
+
+	if (sdmac->direction == DMA_DEV_TO_MEM)
+		n_fifos = sdmac->n_fifos_src;
+	else
+		n_fifos = sdmac->n_fifos_dst;
+
+	sdmac->watermark_level |=
+			FIELD_PREP(SDMA_WATERMARK_LEVEL_N_FIFOS, n_fifos);
+}
+
 static int sdma_config_channel(struct dma_chan *chan)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
@@ -1250,6 +1289,10 @@ static int sdma_config_channel(struct dma_chan *chan)
 			    sdmac->peripheral_type == IMX_DMATYPE_ASRC)
 				sdma_set_watermarklevel_for_p2p(sdmac);
 		} else {
+			if (sdmac->peripheral_type ==
+					IMX_DMATYPE_MULTI_SAI)
+				sdma_set_watermarklevel_for_sais(sdmac);
+
 			__set_bit(sdmac->event_id0, sdmac->event_mask);
 		}
 
@@ -1707,9 +1750,23 @@ static int sdma_config(struct dma_chan *chan,
 		       struct dma_slave_config *dmaengine_cfg)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
+	struct sdma_engine *sdma = sdmac->sdma;
 
 	memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
 
+	if (dmaengine_cfg->peripheral_config) {
+		struct sdma_peripheral_config *sdmacfg = dmaengine_cfg->peripheral_config;
+		if (dmaengine_cfg->peripheral_size != sizeof(struct sdma_peripheral_config)) {
+			dev_err(sdma->dev, "Invalid peripheral size %zu, expected %zu\n",
+				dmaengine_cfg->peripheral_size,
+				sizeof(struct sdma_peripheral_config));
+			return -EINVAL;
+		}
+		sdmac->n_fifos_src = sdmacfg->n_fifos_src;
+		sdmac->n_fifos_dst = sdmacfg->n_fifos_dst;
+		sdmac->sw_done = sdmacfg->sw_done;
+	}
+
 	/* Set ENBLn earlier to make sure dma request triggered after that */
 	if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
 		return -EINVAL;
diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h
index b06cba85a6d4..8887762360d4 100644
--- a/include/linux/dma/imx-dma.h
+++ b/include/linux/dma/imx-dma.h
@@ -39,6 +39,7 @@ enum sdma_peripheral_type {
 	IMX_DMATYPE_SSI_DUAL,	/* SSI Dual FIFO */
 	IMX_DMATYPE_ASRC_SP,	/* Shared ASRC */
 	IMX_DMATYPE_SAI,	/* SAI */
+	IMX_DMATYPE_MULTI_SAI,	/* MULTI FIFOs For Audio */
 };
 
 enum imx_dma_prio {
@@ -65,4 +66,23 @@ static inline int imx_dma_is_general_purpose(struct dma_chan *chan)
 		!strcmp(chan->device->dev->driver->name, "imx-dma");
 }
 
+/**
+ * struct sdma_peripheral_config - SDMA config for audio
+ * @n_fifos_src: Number of FIFOs for recording
+ * @n_fifos_dst: Number of FIFOs for playback
+ * @sw_done: Use software done. Needed for PDM (micfil)
+ *
+ * Some i.MX Audio devices (SAI, micfil) have multiple successive FIFO
+ * registers. For multichannel recording/playback the SAI/micfil have
+ * one FIFO register per channel and the SDMA engine has to read/write
+ * the next channel from/to the next register and wrap around to the
+ * first register when all channels are handled. The number of active
+ * channels must be communicated to the SDMA engine using this struct.
+ */
+struct sdma_peripheral_config {
+	int n_fifos_src;
+	int n_fifos_dst;
+	bool sw_done;
+};
+
 #endif /* __LINUX_DMA_IMX_H */
-- 
cgit v1.2.3


From 6c846d026d490b2383d395bc8e7b06336219667b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 19 Apr 2022 15:18:37 +0100
Subject: gpio: Don't fiddle with irqchips marked as immutable

In order to move away from gpiolib messing with the internals of
unsuspecting irqchips, add a flag by which irqchips advertise
that they are not to be messed with, and do solemnly swear that
they correctly call into the gpiolib helpers when required.

Also nudge the users into converting their drivers to the
new model.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Bartosz Golaszewski <brgl@bgdev.pl>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220419141846.598305-2-maz@kernel.org
---
 drivers/gpio/gpiolib.c | 7 ++++++-
 include/linux/irq.h    | 2 ++
 kernel/irq/debugfs.c   | 1 +
 3 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index e59884cc12a7..48191e62a3cc 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1475,6 +1475,11 @@ static void gpiochip_set_irq_hooks(struct gpio_chip *gc)
 {
 	struct irq_chip *irqchip = gc->irq.chip;
 
+	if (irqchip->flags & IRQCHIP_IMMUTABLE)
+		return;
+
+	chip_warn(gc, "not an immutable chip, please consider fixing it!\n");
+
 	if (!irqchip->irq_request_resources &&
 	    !irqchip->irq_release_resources) {
 		irqchip->irq_request_resources = gpiochip_irq_reqres;
@@ -1633,7 +1638,7 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gc)
 		irq_domain_remove(gc->irq.domain);
 	}
 
-	if (irqchip) {
+	if (irqchip && !(irqchip->flags & IRQCHIP_IMMUTABLE)) {
 		if (irqchip->irq_request_resources == gpiochip_irq_reqres) {
 			irqchip->irq_request_resources = NULL;
 			irqchip->irq_release_resources = NULL;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index f92788ccdba2..505308253d23 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -569,6 +569,7 @@ struct irq_chip {
  * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND:  Invokes __enable_irq()/__disable_irq() for wake irqs
  *                                    in the suspend path if they are in disabled state
  * IRQCHIP_AFFINITY_PRE_STARTUP:      Default affinity update before startup
+ * IRQCHIP_IMMUTABLE:		      Don't ever change anything in this chip
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED			= (1 <<  0),
@@ -582,6 +583,7 @@ enum {
 	IRQCHIP_SUPPORTS_NMI			= (1 <<  8),
 	IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND	= (1 <<  9),
 	IRQCHIP_AFFINITY_PRE_STARTUP		= (1 << 10),
+	IRQCHIP_IMMUTABLE			= (1 << 11),
 };
 
 #include <linux/irqdesc.h>
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index 2b43f5f5033d..bc8e40cf2b65 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -58,6 +58,7 @@ static const struct irq_bit_descr irqchip_flags[] = {
 	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
 	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI),
 	BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND),
+	BIT_MASK_DESCR(IRQCHIP_IMMUTABLE),
 };
 
 static void
-- 
cgit v1.2.3


From 704f08753b6dcd0e08c1953af0b2c7f3fac87111 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 19 Apr 2022 15:18:38 +0100
Subject: gpio: Expose the gpiochip_irq_re[ql]res helpers

The GPIO subsystem has a couple of internal helpers to manage
resources on behalf of the irqchip. Expose them so that GPIO
drivers can use them directly.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Bartosz Golaszewski <brgl@bgdev.pl>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220419141846.598305-3-maz@kernel.org
---
 drivers/gpio/gpiolib.c      | 6 ++++--
 include/linux/gpio/driver.h | 4 ++++
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 48191e62a3cc..36e436a66e09 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1423,19 +1423,21 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset)
 	return irq_create_mapping(domain, offset);
 }
 
-static int gpiochip_irq_reqres(struct irq_data *d)
+int gpiochip_irq_reqres(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 
 	return gpiochip_reqres_irq(gc, d->hwirq);
 }
+EXPORT_SYMBOL(gpiochip_irq_reqres);
 
-static void gpiochip_irq_relres(struct irq_data *d)
+void gpiochip_irq_relres(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 
 	gpiochip_relres_irq(gc, d->hwirq);
 }
+EXPORT_SYMBOL(gpiochip_irq_relres);
 
 static void gpiochip_irq_mask(struct irq_data *d)
 {
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 98c93510640e..066bcfdf878d 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -579,6 +579,10 @@ void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset);
 void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset);
 void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset);
 
+/* irq_data versions of the above */
+int gpiochip_irq_reqres(struct irq_data *data);
+void gpiochip_irq_relres(struct irq_data *data);
+
 /* Line status inquiry for drivers */
 bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset);
 bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset);
-- 
cgit v1.2.3


From 36b78aae4bfee749bbde73be570796bfd0f56bec Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 19 Apr 2022 15:18:39 +0100
Subject: gpio: Add helpers to ease the transition towards immutable irq_chip

Add a couple of new helpers to make it slightly simpler to convert
drivers to immutable irq_chip structures:

- GPIOCHIP_IRQ_RESOURCE_HELPERS populates the irq_chip structure
  with the resource management callbacks

- gpio_irq_chip_set_chip() populates the gpio_irq_chip.chip
  structure, avoiding the proliferation of ugly casts

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Bartosz Golaszewski <brgl@bgdev.pl>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220419141846.598305-4-maz@kernel.org
---
 include/linux/gpio/driver.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 066bcfdf878d..832990099097 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -583,6 +583,18 @@ void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset);
 int gpiochip_irq_reqres(struct irq_data *data);
 void gpiochip_irq_relres(struct irq_data *data);
 
+/* Paste this in your irq_chip structure  */
+#define	GPIOCHIP_IRQ_RESOURCE_HELPERS					\
+		.irq_request_resources  = gpiochip_irq_reqres,		\
+		.irq_release_resources  = gpiochip_irq_relres
+
+static inline void gpio_irq_chip_set_chip(struct gpio_irq_chip *girq,
+					  const struct irq_chip *chip)
+{
+	/* Yes, dropping const is ugly, but it isn't like we have a choice */
+	girq->chip = (struct irq_chip *)chip;
+}
+
 /* Line status inquiry for drivers */
 bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset);
 bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset);
-- 
cgit v1.2.3


From 08d3df8c81537089fc8f21006b56f2f6fb23c6f8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 1 Sep 2019 22:26:10 +0200
Subject: ARM: pxa: split up mach/hardware.h

The mach/hardware.h is included in lots of places, and it provides
three different things on pxa:

- the cpu_is_pxa* macros
- an indirect inclusion of mach/addr-map.h
- the __REG() and io_pv2() helper macros

Split it up into separate <linux/soc/pxa/cpu.h> and mach/pxa-regs.h
headers, then change all the files that use mach/hardware.h to
include the exact set of those three headers that they actually
need, allowing for further more targeted cleanup.

linux/soc/pxa/cpu.h can remain permanently exported and is now in
a global location along with similar headers. pxa-regs.h and
addr-map.h are only used in a very small number of drivers now
and can be moved to arch/arm/mach-pxa/ directly when those drivers
are to pass the necessary data as resources.

Cc: Michael Turquette <mturquette@baylibre.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Jacek Anaszewski <jacek.anaszewski@gmail.com>
Cc: Pavel Machek <pavel@ucw.cz>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Acked-by: Mark Brown <broonie@kernel.org>
Cc: linux-clk@vger.kernel.org
Cc: linux-pm@vger.kernel.org
Cc: linux-input@vger.kernel.org
Cc: linux-leds@vger.kernel.org
Cc: linux-mmc@vger.kernel.org
Cc: linux-mtd@lists.infradead.org
Cc: linux-rtc@vger.kernel.org
Cc: linux-usb@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: linux-fbdev@vger.kernel.org
Cc: linux-watchdog@vger.kernel.org
Cc: alsa-devel@alsa-project.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/common/locomo.c                     |   1 -
 arch/arm/common/sa1111.c                     |   5 +-
 arch/arm/mach-pxa/cm-x300.c                  |   2 +
 arch/arm/mach-pxa/colibri-evalboard.c        |   1 -
 arch/arm/mach-pxa/colibri-pxa270-income.c    |   1 -
 arch/arm/mach-pxa/colibri-pxa300.c           |   1 +
 arch/arm/mach-pxa/colibri-pxa3xx.c           |   1 -
 arch/arm/mach-pxa/corgi.c                    |   1 -
 arch/arm/mach-pxa/corgi_pm.c                 |   1 -
 arch/arm/mach-pxa/csb726.c                   |   1 +
 arch/arm/mach-pxa/devices.c                  |   2 +-
 arch/arm/mach-pxa/ezx.c                      |   1 -
 arch/arm/mach-pxa/generic.c                  |   3 +-
 arch/arm/mach-pxa/gumstix.c                  |   1 -
 arch/arm/mach-pxa/hx4700.c                   |   2 +-
 arch/arm/mach-pxa/idp.c                      |   1 -
 arch/arm/mach-pxa/include/mach/hardware.h    | 305 ---------------------------
 arch/arm/mach-pxa/include/mach/pxa-regs.h    |  52 +++++
 arch/arm/mach-pxa/include/mach/pxa2xx-regs.h |   2 +-
 arch/arm/mach-pxa/include/mach/pxa3xx-regs.h |   2 +-
 arch/arm/mach-pxa/include/mach/regs-ac97.h   |   2 +-
 arch/arm/mach-pxa/include/mach/regs-ost.h    |   2 +-
 arch/arm/mach-pxa/include/mach/trizeps4.h    |   1 +
 arch/arm/mach-pxa/irq.c                      |   3 +-
 arch/arm/mach-pxa/littleton.c                |   1 -
 arch/arm/mach-pxa/lpd270.c                   |   2 +-
 arch/arm/mach-pxa/lubbock.c                  |   1 -
 arch/arm/mach-pxa/magician.c                 |   2 +-
 arch/arm/mach-pxa/mainstone.c                |   2 +-
 arch/arm/mach-pxa/mfp-pxa2xx.c               |   1 +
 arch/arm/mach-pxa/mfp-pxa3xx.c               |   1 -
 arch/arm/mach-pxa/poodle.c                   |   1 -
 arch/arm/mach-pxa/pxa-regs.h                 |   1 +
 arch/arm/mach-pxa/pxa25x.c                   |   3 +-
 arch/arm/mach-pxa/pxa25x.h                   |   2 +-
 arch/arm/mach-pxa/pxa27x-udc.h               |   2 +
 arch/arm/mach-pxa/pxa27x.c                   |   3 +-
 arch/arm/mach-pxa/pxa27x.h                   |   2 +-
 arch/arm/mach-pxa/pxa2xx.c                   |   1 -
 arch/arm/mach-pxa/pxa300.c                   |   1 +
 arch/arm/mach-pxa/pxa320.c                   |   1 +
 arch/arm/mach-pxa/pxa3xx-ulpi.c              |   2 +-
 arch/arm/mach-pxa/pxa3xx.c                   |   3 +-
 arch/arm/mach-pxa/pxa3xx.h                   |   2 +-
 arch/arm/mach-pxa/pxa930.c                   |   1 +
 arch/arm/mach-pxa/regs-rtc.h                 |   2 +-
 arch/arm/mach-pxa/regs-uart.h                |   2 +
 arch/arm/mach-pxa/sleep.S                    |   1 -
 arch/arm/mach-pxa/smemc.c                    |   2 +-
 arch/arm/mach-pxa/spitz_pm.c                 |   1 -
 arch/arm/mach-pxa/standby.S                  |   1 -
 arch/arm/mach-pxa/xcep.c                     |   2 +-
 arch/arm/mach-pxa/zylonite.c                 |   1 +
 arch/arm/mach-pxa/zylonite.h                 |   2 +
 arch/arm/mach-pxa/zylonite_pxa300.c          |   1 +
 arch/arm/mach-pxa/zylonite_pxa320.c          |   1 +
 drivers/clk/pxa/clk-pxa3xx.c                 |   1 +
 drivers/cpufreq/pxa2xx-cpufreq.c             |   1 +
 drivers/cpufreq/pxa3xx-cpufreq.c             |   1 +
 drivers/input/mouse/pxa930_trkball.c         |   1 -
 drivers/input/touchscreen/zylonite-wm97xx.c  |   2 +-
 drivers/leds/leds-locomo.c                   |   1 -
 drivers/mmc/host/pxamci.c                    |   2 +-
 drivers/mtd/maps/pxa2xx-flash.c              |   2 -
 drivers/pcmcia/pxa2xx_base.c                 |   2 +-
 drivers/pcmcia/pxa2xx_sharpsl.c              |   1 -
 drivers/pcmcia/sa1111_generic.c              |   1 -
 drivers/pcmcia/sa1111_lubbock.c              |   1 -
 drivers/pcmcia/soc_common.c                  |   2 -
 drivers/rtc/rtc-pxa.c                        |   2 -
 drivers/usb/host/ohci-pxa27x.c               |   3 +-
 drivers/video/fbdev/pxafb.c                  |   2 +-
 drivers/watchdog/sa1100_wdt.c                |   1 -
 include/linux/soc/pxa/cpu.h                  | 252 ++++++++++++++++++++++
 sound/arm/pxa2xx-ac97-lib.c                  |   1 +
 sound/soc/pxa/pxa2xx-ac97.c                  |   2 +-
 sound/soc/pxa/pxa2xx-i2s.c                   |   2 +-
 sound/soc/pxa/z2.c                           |   1 -
 78 files changed, 364 insertions(+), 365 deletions(-)
 delete mode 100644 arch/arm/mach-pxa/include/mach/hardware.h
 create mode 100644 arch/arm/mach-pxa/include/mach/pxa-regs.h
 create mode 100644 arch/arm/mach-pxa/pxa-regs.h
 create mode 100644 include/linux/soc/pxa/cpu.h

(limited to 'include/linux')

diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 24d21ba63030..da30a4d4f35c 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -23,7 +23,6 @@
 #include <linux/spinlock.h>
 #include <linux/io.h>
 
-#include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
 
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 5367f03beb46..2343e2b6214d 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -26,13 +26,16 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 
-#include <mach/hardware.h>
 #include <asm/mach/irq.h>
 #include <asm/mach-types.h>
 #include <linux/sizes.h>
 
 #include <asm/hardware/sa1111.h>
 
+#ifdef CONFIG_ARCH_SA1100
+#include <mach/hardware.h>
+#endif
+
 /* SA1111 IRQs */
 #define IRQ_GPAIN0		(0)
 #define IRQ_GPAIN1		(1)
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 2e35354b61f5..85e2537fdc15 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -40,6 +40,8 @@
 #include <linux/spi/spi_gpio.h>
 #include <linux/spi/tdo24m.h>
 
+#include <linux/soc/pxa/cpu.h>
+
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/setup.h>
diff --git a/arch/arm/mach-pxa/colibri-evalboard.c b/arch/arm/mach-pxa/colibri-evalboard.c
index b9c173ede891..b62af07b8f96 100644
--- a/arch/arm/mach-pxa/colibri-evalboard.c
+++ b/arch/arm/mach-pxa/colibri-evalboard.c
@@ -13,7 +13,6 @@
 #include <linux/interrupt.h>
 #include <linux/gpio/machine.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/mach/arch.h>
 #include <linux/i2c.h>
 #include <linux/platform_data/i2c-pxa.h>
diff --git a/arch/arm/mach-pxa/colibri-pxa270-income.c b/arch/arm/mach-pxa/colibri-pxa270-income.c
index e5879e8b0682..f6eaf464ca83 100644
--- a/arch/arm/mach-pxa/colibri-pxa270-income.c
+++ b/arch/arm/mach-pxa/colibri-pxa270-income.c
@@ -25,7 +25,6 @@
 #include <asm/irq.h>
 #include <asm/mach-types.h>
 
-#include <mach/hardware.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include "pxa27x.h"
diff --git a/arch/arm/mach-pxa/colibri-pxa300.c b/arch/arm/mach-pxa/colibri-pxa300.c
index 82052dfd96b6..4ceeea142bfd 100644
--- a/arch/arm/mach-pxa/colibri-pxa300.c
+++ b/arch/arm/mach-pxa/colibri-pxa300.c
@@ -13,6 +13,7 @@
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <asm/mach-types.h>
 #include <linux/sizes.h>
diff --git a/arch/arm/mach-pxa/colibri-pxa3xx.c b/arch/arm/mach-pxa/colibri-pxa3xx.c
index 3cead80a2b37..701dfef930eb 100644
--- a/arch/arm/mach-pxa/colibri-pxa3xx.c
+++ b/arch/arm/mach-pxa/colibri-pxa3xx.c
@@ -13,7 +13,6 @@
 #include <linux/gpio.h>
 #include <linux/etherdevice.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <linux/sizes.h>
 #include <asm/system_info.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 44659fbc37ba..f897762c8b58 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -39,7 +39,6 @@
 #include <asm/setup.h>
 #include <asm/memory.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/corgi_pm.c b/arch/arm/mach-pxa/corgi_pm.c
index 092dcb9fced5..ff1ac9bf37cb 100644
--- a/arch/arm/mach-pxa/corgi_pm.c
+++ b/arch/arm/mach-pxa/corgi_pm.c
@@ -19,7 +19,6 @@
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 
 #include <mach/corgi.h>
 #include <mach/pxa2xx-regs.h>
diff --git a/arch/arm/mach-pxa/csb726.c b/arch/arm/mach-pxa/csb726.c
index 98fcdc6e2944..d48493445ae5 100644
--- a/arch/arm/mach-pxa/csb726.c
+++ b/arch/arm/mach-pxa/csb726.c
@@ -17,6 +17,7 @@
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
+
 #include "csb726.h"
 #include "pxa27x.h"
 #include <linux/platform_data/mmc-pxamci.h>
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 09b8495f3fd9..7ca97ddef6fe 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -9,6 +9,7 @@
 #include <linux/dmaengine.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/platform_data/i2c-pxa.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include "udc.h"
 #include <linux/platform_data/usb-pxa3xx-ulpi.h>
@@ -20,7 +21,6 @@
 #include <linux/platform_data/keypad-pxa27x.h>
 #include <linux/platform_data/media/camera-pxa.h>
 #include <mach/audio.h>
-#include <mach/hardware.h>
 #include <linux/platform_data/mmp_dma.h>
 #include <linux/platform_data/mtd-nand-pxa3xx.h>
 
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index eb85950e7c0e..69c2ec02a16c 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -29,7 +29,6 @@
 #include "pxa27x.h"
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
-#include <mach/hardware.h>
 #include <linux/platform_data/keypad-pxa27x.h>
 #include <linux/platform_data/media/camera-pxa.h>
 
diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index ab7cdffd7ea8..3c3cd90bb9b4 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -17,11 +17,12 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/soc/pxa/cpu.h>
 
-#include <mach/hardware.h>
 #include <asm/mach/map.h>
 #include <asm/mach-types.h>
 
+#include <mach/addr-map.h>
 #include <mach/irqs.h>
 #include <mach/reset.h>
 #include <mach/smemc.h>
diff --git a/arch/arm/mach-pxa/gumstix.c b/arch/arm/mach-pxa/gumstix.c
index 49dd618b10f7..72b08a9bf0fd 100644
--- a/arch/arm/mach-pxa/gumstix.c
+++ b/arch/arm/mach-pxa/gumstix.c
@@ -28,7 +28,6 @@
 #include <asm/setup.h>
 #include <asm/memory.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 #include <linux/sizes.h>
 
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index e1870fbb19e7..191a6c24fe19 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -36,11 +36,11 @@
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/platform_data/i2c-pxa.h>
 
-#include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
 #include "pxa27x.h"
+#include <mach/addr-map.h>
 #include <mach/hx4700.h>
 #include <linux/platform_data/irda-pxaficp.h>
 
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index fb0850af8496..57c0511472bc 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -22,7 +22,6 @@
 #include <asm/setup.h>
 #include <asm/memory.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h
deleted file mode 100644
index ee7eab16135f..000000000000
--- a/arch/arm/mach-pxa/include/mach/hardware.h
+++ /dev/null
@@ -1,305 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  arch/arm/mach-pxa/include/mach/hardware.h
- *
- *  Author:	Nicolas Pitre
- *  Created:	Jun 15, 2001
- *  Copyright:	MontaVista Software Inc.
- */
-
-#ifndef __ASM_ARCH_HARDWARE_H
-#define __ASM_ARCH_HARDWARE_H
-
-#include <mach/addr-map.h>
-
-/*
- * Workarounds for at least 2 errata so far require this.
- * The mapping is set in mach-pxa/generic.c.
- */
-#define UNCACHED_PHYS_0		0xfe000000
-#define UNCACHED_PHYS_0_SIZE	0x00100000
-
-/*
- * Intel PXA2xx internal register mapping:
- *
- * 0x40000000 - 0x41ffffff <--> 0xf2000000 - 0xf3ffffff
- * 0x44000000 - 0x45ffffff <--> 0xf4000000 - 0xf5ffffff
- * 0x48000000 - 0x49ffffff <--> 0xf6000000 - 0xf7ffffff
- * 0x4c000000 - 0x4dffffff <--> 0xf8000000 - 0xf9ffffff
- * 0x50000000 - 0x51ffffff <--> 0xfa000000 - 0xfbffffff
- * 0x54000000 - 0x55ffffff <--> 0xfc000000 - 0xfdffffff
- * 0x58000000 - 0x59ffffff <--> 0xfe000000 - 0xffffffff
- *
- * Note that not all PXA2xx chips implement all those addresses, and the
- * kernel only maps the minimum needed range of this mapping.
- */
-#define io_v2p(x) (0x3c000000 + ((x) & 0x01ffffff) + (((x) & 0x0e000000) << 1))
-#define io_p2v(x) IOMEM(0xf2000000 + ((x) & 0x01ffffff) + (((x) & 0x1c000000) >> 1))
-
-#ifndef __ASSEMBLY__
-# define __REG(x)	(*((volatile u32 __iomem *)io_p2v(x)))
-
-/* With indexed regs we don't want to feed the index through io_p2v()
-   especially if it is a variable, otherwise horrible code will result. */
-# define __REG2(x,y)	\
-	(*(volatile u32 __iomem*)((u32)&__REG(x) + (y)))
-
-# define __PREG(x)	(io_v2p((u32)&(x)))
-
-#else
-
-# define __REG(x)	io_p2v(x)
-# define __PREG(x)	io_v2p(x)
-
-#endif
-
-#ifndef __ASSEMBLY__
-
-#include <asm/cputype.h>
-
-/*
- *   CPU     Stepping     CPU_ID         JTAG_ID
- *
- *  PXA210	B0	0x69052922	0x2926C013
- *  PXA210	B1	0x69052923	0x3926C013
- *  PXA210	B2	0x69052924	0x4926C013
- *  PXA210	C0	0x69052D25	0x5926C013
- *
- *  PXA250	A0	0x69052100	0x09264013
- *  PXA250	A1	0x69052101	0x19264013
- *  PXA250	B0	0x69052902	0x29264013
- *  PXA250	B1	0x69052903	0x39264013
- *  PXA250	B2	0x69052904	0x49264013
- *  PXA250	C0	0x69052D05	0x59264013
- *
- *  PXA255	A0	0x69052D06	0x69264013
- *
- *  PXA26x	A0	0x69052903	0x39264013
- *  PXA26x	B0	0x69052D05	0x59264013
- *
- *  PXA27x	A0	0x69054110	0x09265013
- *  PXA27x	A1	0x69054111	0x19265013
- *  PXA27x	B0	0x69054112	0x29265013
- *  PXA27x	B1	0x69054113	0x39265013
- *  PXA27x	C0	0x69054114	0x49265013
- *  PXA27x	C5	0x69054117	0x79265013
- *
- *  PXA30x	A0	0x69056880	0x0E648013
- *  PXA30x	A1	0x69056881	0x1E648013
- *  PXA31x	A0	0x69056890	0x0E649013
- *  PXA31x	A1	0x69056891	0x1E649013
- *  PXA31x	A2	0x69056892	0x2E649013
- *  PXA32x	B1	0x69056825	0x5E642013
- *  PXA32x	B2	0x69056826	0x6E642013
- *
- *  PXA930	B0	0x69056835	0x5E643013
- *  PXA930	B1	0x69056837	0x7E643013
- *  PXA930	B2	0x69056838	0x8E643013
- *
- *  PXA935	A0	0x56056931	0x1E653013
- *  PXA935	B0	0x56056936	0x6E653013
- *  PXA935	B1	0x56056938	0x8E653013
- */
-#ifdef CONFIG_PXA25x
-#define __cpu_is_pxa210(id)				\
-	({						\
-		unsigned int _id = (id) & 0xf3f0;	\
-		_id == 0x2120;				\
-	})
-
-#define __cpu_is_pxa250(id)				\
-	({						\
-		unsigned int _id = (id) & 0xf3ff;	\
-		_id <= 0x2105;				\
-	})
-
-#define __cpu_is_pxa255(id)				\
-	({						\
-		unsigned int _id = (id) & 0xffff;	\
-		_id == 0x2d06;				\
-	})
-
-#define __cpu_is_pxa25x(id)				\
-	({						\
-		unsigned int _id = (id) & 0xf300;	\
-		_id == 0x2100;				\
-	})
-#else
-#define __cpu_is_pxa210(id)	(0)
-#define __cpu_is_pxa250(id)	(0)
-#define __cpu_is_pxa255(id)	(0)
-#define __cpu_is_pxa25x(id)	(0)
-#endif
-
-#ifdef CONFIG_PXA27x
-#define __cpu_is_pxa27x(id)				\
-	({						\
-		unsigned int _id = (id) >> 4 & 0xfff;	\
-		_id == 0x411;				\
-	})
-#else
-#define __cpu_is_pxa27x(id)	(0)
-#endif
-
-#ifdef CONFIG_CPU_PXA300
-#define __cpu_is_pxa300(id)				\
-	({						\
-		unsigned int _id = (id) >> 4 & 0xfff;	\
-		_id == 0x688;				\
-	 })
-#else
-#define __cpu_is_pxa300(id)	(0)
-#endif
-
-#ifdef CONFIG_CPU_PXA310
-#define __cpu_is_pxa310(id)				\
-	({						\
-		unsigned int _id = (id) >> 4 & 0xfff;	\
-		_id == 0x689;				\
-	 })
-#else
-#define __cpu_is_pxa310(id)	(0)
-#endif
-
-#ifdef CONFIG_CPU_PXA320
-#define __cpu_is_pxa320(id)				\
-	({						\
-		unsigned int _id = (id) >> 4 & 0xfff;	\
-		_id == 0x603 || _id == 0x682;		\
-	 })
-#else
-#define __cpu_is_pxa320(id)	(0)
-#endif
-
-#ifdef CONFIG_CPU_PXA930
-#define __cpu_is_pxa930(id)				\
-	({						\
-		unsigned int _id = (id) >> 4 & 0xfff;	\
-		_id == 0x683;				\
-	 })
-#else
-#define __cpu_is_pxa930(id)	(0)
-#endif
-
-#ifdef CONFIG_CPU_PXA935
-#define __cpu_is_pxa935(id)				\
-	({						\
-		unsigned int _id = (id) >> 4 & 0xfff;	\
-		_id == 0x693;				\
-	 })
-#else
-#define __cpu_is_pxa935(id)	(0)
-#endif
-
-#define cpu_is_pxa210()					\
-	({						\
-		__cpu_is_pxa210(read_cpuid_id());	\
-	})
-
-#define cpu_is_pxa250()					\
-	({						\
-		__cpu_is_pxa250(read_cpuid_id());	\
-	})
-
-#define cpu_is_pxa255()                                 \
-	({                                              \
-		__cpu_is_pxa255(read_cpuid_id());       \
-	})
-
-#define cpu_is_pxa25x()					\
-	({						\
-		__cpu_is_pxa25x(read_cpuid_id());	\
-	})
-
-#define cpu_is_pxa27x()					\
-	({						\
-		__cpu_is_pxa27x(read_cpuid_id());	\
-	})
-
-#define cpu_is_pxa300()					\
-	({						\
-		__cpu_is_pxa300(read_cpuid_id());	\
-	 })
-
-#define cpu_is_pxa310()					\
-	({						\
-		__cpu_is_pxa310(read_cpuid_id());	\
-	 })
-
-#define cpu_is_pxa320()					\
-	({						\
-		__cpu_is_pxa320(read_cpuid_id());	\
-	 })
-
-#define cpu_is_pxa930()					\
-	({						\
-		__cpu_is_pxa930(read_cpuid_id());	\
-	 })
-
-#define cpu_is_pxa935()					\
-	({						\
-		__cpu_is_pxa935(read_cpuid_id());	\
-	 })
-
-
-
-/*
- * CPUID Core Generation Bit
- * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x
- */
-#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x)
-#define __cpu_is_pxa2xx(id)				\
-	({						\
-		unsigned int _id = (id) >> 13 & 0x7;	\
-		_id <= 0x2;				\
-	 })
-#else
-#define __cpu_is_pxa2xx(id)	(0)
-#endif
-
-#ifdef CONFIG_PXA3xx
-#define __cpu_is_pxa3xx(id)				\
-	({						\
-		__cpu_is_pxa300(id)			\
-			|| __cpu_is_pxa310(id)		\
-			|| __cpu_is_pxa320(id)		\
-			|| __cpu_is_pxa93x(id);		\
-	 })
-#else
-#define __cpu_is_pxa3xx(id)	(0)
-#endif
-
-#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935)
-#define __cpu_is_pxa93x(id)				\
-	({						\
-		__cpu_is_pxa930(id)			\
-			|| __cpu_is_pxa935(id);		\
-	 })
-#else
-#define __cpu_is_pxa93x(id)	(0)
-#endif
-
-#define cpu_is_pxa2xx()					\
-	({						\
-		__cpu_is_pxa2xx(read_cpuid_id());	\
-	 })
-
-#define cpu_is_pxa3xx()					\
-	({						\
-		__cpu_is_pxa3xx(read_cpuid_id());	\
-	 })
-
-#define cpu_is_pxa93x()					\
-	({						\
-		__cpu_is_pxa93x(read_cpuid_id());	\
-	 })
-
-
-/*
- * return current memory and LCD clock frequency in units of 10kHz
- */
-extern unsigned int get_memclk_frequency_10khz(void);
-
-#endif
-
-#endif  /* _ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-pxa/include/mach/pxa-regs.h b/arch/arm/mach-pxa/include/mach/pxa-regs.h
new file mode 100644
index 000000000000..ba5120c06b8a
--- /dev/null
+++ b/arch/arm/mach-pxa/include/mach/pxa-regs.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Author:	Nicolas Pitre
+ *  Created:	Jun 15, 2001
+ *  Copyright:	MontaVista Software Inc.
+ */
+#ifndef __ASM_MACH_PXA_REGS_H
+#define __ASM_MACH_PXA_REGS_H
+
+/*
+ * Workarounds for at least 2 errata so far require this.
+ * The mapping is set in mach-pxa/generic.c.
+ */
+#define UNCACHED_PHYS_0		0xfe000000
+#define UNCACHED_PHYS_0_SIZE	0x00100000
+
+/*
+ * Intel PXA2xx internal register mapping:
+ *
+ * 0x40000000 - 0x41ffffff <--> 0xf2000000 - 0xf3ffffff
+ * 0x44000000 - 0x45ffffff <--> 0xf4000000 - 0xf5ffffff
+ * 0x48000000 - 0x49ffffff <--> 0xf6000000 - 0xf7ffffff
+ * 0x4c000000 - 0x4dffffff <--> 0xf8000000 - 0xf9ffffff
+ * 0x50000000 - 0x51ffffff <--> 0xfa000000 - 0xfbffffff
+ * 0x54000000 - 0x55ffffff <--> 0xfc000000 - 0xfdffffff
+ * 0x58000000 - 0x59ffffff <--> 0xfe000000 - 0xffffffff
+ *
+ * Note that not all PXA2xx chips implement all those addresses, and the
+ * kernel only maps the minimum needed range of this mapping.
+ */
+#define io_v2p(x) (0x3c000000 + ((x) & 0x01ffffff) + (((x) & 0x0e000000) << 1))
+#define io_p2v(x) IOMEM(0xf2000000 + ((x) & 0x01ffffff) + (((x) & 0x1c000000) >> 1))
+
+#ifndef __ASSEMBLY__
+# define __REG(x)	(*((volatile u32 __iomem *)io_p2v(x)))
+
+/* With indexed regs we don't want to feed the index through io_p2v()
+   especially if it is a variable, otherwise horrible code will result. */
+# define __REG2(x,y)	\
+	(*(volatile u32 __iomem*)((u32)&__REG(x) + (y)))
+
+# define __PREG(x)	(io_v2p((u32)&(x)))
+
+#else
+
+# define __REG(x)	io_p2v(x)
+# define __PREG(x)	io_v2p(x)
+
+#endif
+
+
+#endif
diff --git a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
index fa121e135915..f68b573ab4a0 100644
--- a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
+++ b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
@@ -11,7 +11,7 @@
 #ifndef __PXA2XX_REGS_H
 #define __PXA2XX_REGS_H
 
-#include <mach/hardware.h>
+#include "pxa-regs.h"
 
 /*
  * Power Manager
diff --git a/arch/arm/mach-pxa/include/mach/pxa3xx-regs.h b/arch/arm/mach-pxa/include/mach/pxa3xx-regs.h
index 070f6c74196e..8eb1ba533e1c 100644
--- a/arch/arm/mach-pxa/include/mach/pxa3xx-regs.h
+++ b/arch/arm/mach-pxa/include/mach/pxa3xx-regs.h
@@ -10,7 +10,7 @@
 #ifndef __ASM_ARCH_PXA3XX_REGS_H
 #define __ASM_ARCH_PXA3XX_REGS_H
 
-#include <mach/hardware.h>
+#include "pxa-regs.h"
 
 /*
  * Oscillator Configuration Register (OSCC)
diff --git a/arch/arm/mach-pxa/include/mach/regs-ac97.h b/arch/arm/mach-pxa/include/mach/regs-ac97.h
index 1db96fd4df32..ec09b9635e25 100644
--- a/arch/arm/mach-pxa/include/mach/regs-ac97.h
+++ b/arch/arm/mach-pxa/include/mach/regs-ac97.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_ARCH_REGS_AC97_H
 #define __ASM_ARCH_REGS_AC97_H
 
-#include <mach/hardware.h>
+#include "pxa-regs.h"
 
 /*
  * AC97 Controller registers
diff --git a/arch/arm/mach-pxa/include/mach/regs-ost.h b/arch/arm/mach-pxa/include/mach/regs-ost.h
index deb564ed8ee7..109d0ed264df 100644
--- a/arch/arm/mach-pxa/include/mach/regs-ost.h
+++ b/arch/arm/mach-pxa/include/mach/regs-ost.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_MACH_REGS_OST_H
 #define __ASM_MACH_REGS_OST_H
 
-#include <mach/hardware.h>
+#include "pxa-regs.h"
 
 /*
  * OS Timer & Match Registers
diff --git a/arch/arm/mach-pxa/include/mach/trizeps4.h b/arch/arm/mach-pxa/include/mach/trizeps4.h
index 3cddb1428c5e..27926629f9c6 100644
--- a/arch/arm/mach-pxa/include/mach/trizeps4.h
+++ b/arch/arm/mach-pxa/include/mach/trizeps4.h
@@ -11,6 +11,7 @@
 #ifndef _TRIPEPS4_H_
 #define _TRIPEPS4_H_
 
+#include <mach/addr-map.h>
 #include "irqs.h" /* PXA_GPIO_TO_IRQ */
 
 /* physical memory regions */
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index 74efc3ab595f..f25c30e8a834 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -17,13 +17,14 @@
 #include <linux/irq.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <asm/exception.h>
 
-#include <mach/hardware.h>
 #include <mach/irqs.h>
 
 #include "generic.h"
+#include "pxa-regs.h"
 
 #define ICIP			(0x000)
 #define ICMR			(0x004)
diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c
index 73f5953b3bb6..f98dc61e87af 100644
--- a/arch/arm/mach-pxa/littleton.c
+++ b/arch/arm/mach-pxa/littleton.c
@@ -31,7 +31,6 @@
 #include <asm/setup.h>
 #include <asm/memory.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index 6fc40bc06910..eac32bd9e385 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -28,7 +28,6 @@
 #include <asm/setup.h>
 #include <asm/memory.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 #include <linux/sizes.h>
 
@@ -39,6 +38,7 @@
 
 #include "pxa27x.h"
 #include "lpd270.h"
+#include <mach/addr-map.h>
 #include <mach/audio.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index e2411971422d..72816e7c206f 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -34,7 +34,6 @@
 #include <asm/setup.h>
 #include <asm/memory.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 #include <linux/sizes.h>
 
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index 200fd35168e0..345a44d15a2c 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -29,12 +29,12 @@
 #include <linux/regulator/machine.h>
 #include <linux/platform_data/i2c-pxa.h>
 
-#include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/system_info.h>
 
 #include "pxa27x.h"
+#include <mach/addr-map.h>
 #include <mach/magician.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index 997f6e502201..cf74adfe65df 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -35,7 +35,6 @@
 #include <asm/setup.h>
 #include <asm/memory.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 #include <linux/sizes.h>
 
@@ -52,6 +51,7 @@
 #include <linux/platform_data/irda-pxaficp.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <linux/platform_data/keypad-pxa27x.h>
+#include <mach/addr-map.h>
 #include <mach/smemc.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c
index 6a5451b186c2..6bc7206fd2ac 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/syscore_ops.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <mach/pxa2xx-regs.h>
 #include "mfp-pxa2xx.h"
diff --git a/arch/arm/mach-pxa/mfp-pxa3xx.c b/arch/arm/mach-pxa/mfp-pxa3xx.c
index 56114df9700d..f26b5e5412cf 100644
--- a/arch/arm/mach-pxa/mfp-pxa3xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa3xx.c
@@ -16,7 +16,6 @@
 #include <linux/io.h>
 #include <linux/syscore_ops.h>
 
-#include <mach/hardware.h>
 #include "mfp-pxa3xx.h"
 #include <mach/pxa3xx-regs.h>
 
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 58cfa434afde..ca52882433d4 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -30,7 +30,6 @@
 #include <linux/mtd/sharpsl.h>
 #include <linux/memblock.h>
 
-#include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/irq.h>
 #include <asm/setup.h>
diff --git a/arch/arm/mach-pxa/pxa-regs.h b/arch/arm/mach-pxa/pxa-regs.h
new file mode 100644
index 000000000000..584d2ac592cc
--- /dev/null
+++ b/arch/arm/mach-pxa/pxa-regs.h
@@ -0,0 +1 @@
+#include <mach/pxa-regs.h>
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index 0d25cc45f825..305047ebd2f1 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -26,14 +26,15 @@
 #include <linux/irq.h>
 #include <linux/irqchip.h>
 #include <linux/platform_data/mmp_dma.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
-#include <mach/hardware.h>
 #include <mach/irqs.h>
 #include "pxa25x.h"
 #include <mach/reset.h>
 #include "pm.h"
+#include <mach/addr-map.h>
 #include <mach/smemc.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/pxa25x.h b/arch/arm/mach-pxa/pxa25x.h
index b58d0fbdb4db..403bc16c2ed2 100644
--- a/arch/arm/mach-pxa/pxa25x.h
+++ b/arch/arm/mach-pxa/pxa25x.h
@@ -2,7 +2,7 @@
 #ifndef __MACH_PXA25x_H
 #define __MACH_PXA25x_H
 
-#include <mach/hardware.h>
+#include <mach/addr-map.h>
 #include <mach/pxa2xx-regs.h>
 #include "mfp-pxa25x.h"
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-pxa/pxa27x-udc.h b/arch/arm/mach-pxa/pxa27x-udc.h
index faf73804697f..2d3df3b1cb68 100644
--- a/arch/arm/mach-pxa/pxa27x-udc.h
+++ b/arch/arm/mach-pxa/pxa27x-udc.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_ARCH_PXA27X_UDC_H
 #define _ASM_ARCH_PXA27X_UDC_H
 
+#include "pxa-regs.h"
+
 #ifdef _ASM_ARCH_PXA25X_UDC_H
 #error You cannot include both PXA25x and PXA27x UDC support
 #endif
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index f7e89831e85b..a81ac88ecbfd 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -23,9 +23,9 @@
 #include <linux/irq.h>
 #include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/mmp_dma.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <asm/mach/map.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/suspend.h>
 #include <mach/irqs.h>
@@ -33,6 +33,7 @@
 #include <mach/reset.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include "pm.h"
+#include <mach/addr-map.h>
 #include <mach/smemc.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/pxa27x.h b/arch/arm/mach-pxa/pxa27x.h
index abdc02fb4f03..6c99090647d2 100644
--- a/arch/arm/mach-pxa/pxa27x.h
+++ b/arch/arm/mach-pxa/pxa27x.h
@@ -3,7 +3,7 @@
 #define __MACH_PXA27x_H
 
 #include <linux/suspend.h>
-#include <mach/hardware.h>
+#include <mach/addr-map.h>
 #include <mach/pxa2xx-regs.h>
 #include "mfp-pxa27x.h"
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-pxa/pxa2xx.c b/arch/arm/mach-pxa/pxa2xx.c
index 2d26cd2afbf3..ac72acb43e26 100644
--- a/arch/arm/mach-pxa/pxa2xx.c
+++ b/arch/arm/mach-pxa/pxa2xx.c
@@ -12,7 +12,6 @@
 #include <linux/device.h>
 #include <linux/io.h>
 
-#include <mach/hardware.h>
 #include <mach/pxa2xx-regs.h>
 #include "mfp-pxa25x.h"
 #include <mach/reset.h>
diff --git a/arch/arm/mach-pxa/pxa300.c b/arch/arm/mach-pxa/pxa300.c
index 7f2f5a6a2263..f77ec118d5b9 100644
--- a/arch/arm/mach-pxa/pxa300.c
+++ b/arch/arm/mach-pxa/pxa300.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include "pxa300.h"
 
diff --git a/arch/arm/mach-pxa/pxa320.c b/arch/arm/mach-pxa/pxa320.c
index 78abcc741df7..e372e6c118de 100644
--- a/arch/arm/mach-pxa/pxa320.c
+++ b/arch/arm/mach-pxa/pxa320.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include "pxa320.h"
 
diff --git a/arch/arm/mach-pxa/pxa3xx-ulpi.c b/arch/arm/mach-pxa/pxa3xx-ulpi.c
index 4bd7da1f8657..c29a7f0fa1b0 100644
--- a/arch/arm/mach-pxa/pxa3xx-ulpi.c
+++ b/arch/arm/mach-pxa/pxa3xx-ulpi.c
@@ -21,8 +21,8 @@
 #include <linux/clk.h>
 #include <linux/usb.h>
 #include <linux/usb/otg.h>
+#include <linux/soc/pxa/cpu.h>
 
-#include <mach/hardware.h>
 #include "regs-u2d.h"
 #include <linux/platform_data/usb-pxa3xx-ulpi.h>
 
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 6eb1c24d7395..fc84aed99481 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -24,14 +24,15 @@
 #include <linux/syscore_ops.h>
 #include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/mmp_dma.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
-#include <mach/hardware.h>
 #include <mach/pxa3xx-regs.h>
 #include <mach/reset.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include "pm.h"
+#include <mach/addr-map.h>
 #include <mach/smemc.h>
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-pxa/pxa3xx.h b/arch/arm/mach-pxa/pxa3xx.h
index 6d4502aa9d06..22ace053ea25 100644
--- a/arch/arm/mach-pxa/pxa3xx.h
+++ b/arch/arm/mach-pxa/pxa3xx.h
@@ -2,7 +2,7 @@
 #ifndef __MACH_PXA3XX_H	
 #define __MACH_PXA3XX_H
 
-#include <mach/hardware.h>
+#include <mach/addr-map.h>
 #include <mach/pxa3xx-regs.h>
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-pxa/pxa930.c b/arch/arm/mach-pxa/pxa930.c
index bf91de4267e5..b9021a40cbd1 100644
--- a/arch/arm/mach-pxa/pxa930.c
+++ b/arch/arm/mach-pxa/pxa930.c
@@ -13,6 +13,7 @@
 #include <linux/irq.h>
 #include <linux/gpio-pxa.h>
 #include <linux/platform_device.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include "pxa930.h"
 
diff --git a/arch/arm/mach-pxa/regs-rtc.h b/arch/arm/mach-pxa/regs-rtc.h
index b1f9ff14e335..96255a0f595e 100644
--- a/arch/arm/mach-pxa/regs-rtc.h
+++ b/arch/arm/mach-pxa/regs-rtc.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_MACH_REGS_RTC_H
 #define __ASM_MACH_REGS_RTC_H
 
-#include <mach/hardware.h>
+#include "pxa-regs.h"
 
 /*
  * Real Time Clock
diff --git a/arch/arm/mach-pxa/regs-uart.h b/arch/arm/mach-pxa/regs-uart.h
index 9a168f83afeb..490e9ca16297 100644
--- a/arch/arm/mach-pxa/regs-uart.h
+++ b/arch/arm/mach-pxa/regs-uart.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_ARCH_REGS_UART_H
 #define __ASM_ARCH_REGS_UART_H
 
+#include "pxa-regs.h"
+
 /*
  * UARTs
  */
diff --git a/arch/arm/mach-pxa/sleep.S b/arch/arm/mach-pxa/sleep.S
index 6c5b3ffd2cd3..272efeb954f4 100644
--- a/arch/arm/mach-pxa/sleep.S
+++ b/arch/arm/mach-pxa/sleep.S
@@ -13,7 +13,6 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <mach/hardware.h>
 #include <mach/smemc.h>
 #include <mach/pxa2xx-regs.h>
 
diff --git a/arch/arm/mach-pxa/smemc.c b/arch/arm/mach-pxa/smemc.c
index 32e82cc92ea5..47b99549d616 100644
--- a/arch/arm/mach-pxa/smemc.c
+++ b/arch/arm/mach-pxa/smemc.c
@@ -8,8 +8,8 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/syscore_ops.h>
+#include <linux/soc/pxa/cpu.h>
 
-#include <mach/hardware.h>
 #include <mach/smemc.h>
 
 #ifdef CONFIG_PM
diff --git a/arch/arm/mach-pxa/spitz_pm.c b/arch/arm/mach-pxa/spitz_pm.c
index 25a1f8c5a738..201dabe883b6 100644
--- a/arch/arm/mach-pxa/spitz_pm.c
+++ b/arch/arm/mach-pxa/spitz_pm.c
@@ -18,7 +18,6 @@
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 
 #include <mach/spitz.h>
 #include "pxa27x.h"
diff --git a/arch/arm/mach-pxa/standby.S b/arch/arm/mach-pxa/standby.S
index eab1645bb4ad..626fecdefb1c 100644
--- a/arch/arm/mach-pxa/standby.S
+++ b/arch/arm/mach-pxa/standby.S
@@ -11,7 +11,6 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <mach/hardware.h>
 
 #include <mach/pxa2xx-regs.h>
 
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index f485146b899f..e6ab428287ae 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -24,8 +24,8 @@
 #include <asm/mach/irq.h>
 #include <asm/mach/map.h>
 
-#include <mach/hardware.h>
 #include "pxa25x.h"
+#include <mach/addr-map.h>
 #include <mach/smemc.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/zylonite.c b/arch/arm/mach-pxa/zylonite.c
index 79f0025fa17a..9bcb81688201 100644
--- a/arch/arm/mach-pxa/zylonite.c
+++ b/arch/arm/mach-pxa/zylonite.c
@@ -20,6 +20,7 @@
 #include <linux/pwm.h>
 #include <linux/pwm_backlight.h>
 #include <linux/smc91x.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/zylonite.h b/arch/arm/mach-pxa/zylonite.h
index 7300ec2aac0d..afe3efcb8e04 100644
--- a/arch/arm/mach-pxa/zylonite.h
+++ b/arch/arm/mach-pxa/zylonite.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_ARCH_ZYLONITE_H
 #define __ASM_ARCH_ZYLONITE_H
 
+#include <linux/soc/pxa/cpu.h>
+
 #define ZYLONITE_ETH_PHYS	0x14000000
 
 #define EXT_GPIO(x)		(128 + (x))
diff --git a/arch/arm/mach-pxa/zylonite_pxa300.c b/arch/arm/mach-pxa/zylonite_pxa300.c
index 956fec1c4940..50a8a3547dbc 100644
--- a/arch/arm/mach-pxa/zylonite_pxa300.c
+++ b/arch/arm/mach-pxa/zylonite_pxa300.c
@@ -17,6 +17,7 @@
 #include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/pca953x.h>
 #include <linux/gpio.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include "pxa300.h"
 #include "devices.h"
diff --git a/arch/arm/mach-pxa/zylonite_pxa320.c b/arch/arm/mach-pxa/zylonite_pxa320.c
index 94cb834f36cd..67cab4f1194b 100644
--- a/arch/arm/mach-pxa/zylonite_pxa320.c
+++ b/arch/arm/mach-pxa/zylonite_pxa320.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include "pxa320.h"
 #include "zylonite.h"
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 60db92772e72..027b78183565 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -14,6 +14,7 @@
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
+#include <linux/soc/pxa/cpu.h>
 #include <mach/smemc.h>
 #include <mach/pxa3xx-regs.h>
 
diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c
index f0b6f52eb2c3..0f0e676ff781 100644
--- a/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -24,6 +24,7 @@
 #include <linux/cpufreq.h>
 #include <linux/err.h>
 #include <linux/regulator/consumer.h>
+#include <linux/soc/pxa/cpu.h>
 #include <linux/io.h>
 
 #include <mach/pxa2xx-regs.h>
diff --git a/drivers/cpufreq/pxa3xx-cpufreq.c b/drivers/cpufreq/pxa3xx-cpufreq.c
index 32f993c94675..d3b398b4aa6a 100644
--- a/drivers/cpufreq/pxa3xx-cpufreq.c
+++ b/drivers/cpufreq/pxa3xx-cpufreq.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/cpufreq.h>
+#include <linux/soc/pxa/cpu.h>
 #include <linux/slab.h>
 #include <linux/io.h>
 
diff --git a/drivers/input/mouse/pxa930_trkball.c b/drivers/input/mouse/pxa930_trkball.c
index 3332b77eef2a..f04ba12dbfa8 100644
--- a/drivers/input/mouse/pxa930_trkball.c
+++ b/drivers/input/mouse/pxa930_trkball.c
@@ -15,7 +15,6 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 
-#include <mach/hardware.h>
 #include <linux/platform_data/mouse-pxa930_trkball.h>
 
 /* Trackball Controller Register Definitions */
diff --git a/drivers/input/touchscreen/zylonite-wm97xx.c b/drivers/input/touchscreen/zylonite-wm97xx.c
index 0f4ac7f844ce..f57bdf083188 100644
--- a/drivers/input/touchscreen/zylonite-wm97xx.c
+++ b/drivers/input/touchscreen/zylonite-wm97xx.c
@@ -21,9 +21,9 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/soc/pxa/cpu.h>
 #include <linux/wm97xx.h>
 
-#include <mach/hardware.h>
 #include <mach/mfp.h>
 #include <mach/regs-ac97.h>
 
diff --git a/drivers/leds/leds-locomo.c b/drivers/leds/leds-locomo.c
index 42dc46e3f00f..9aa3fccd71fb 100644
--- a/drivers/leds/leds-locomo.c
+++ b/drivers/leds/leds-locomo.c
@@ -11,7 +11,6 @@
 #include <linux/device.h>
 #include <linux/leds.h>
 
-#include <mach/hardware.h>
 #include <asm/hardware/locomo.h>
 
 static void locomoled_brightness_set(struct led_classdev *led_cdev,
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 316393c694d7..0db9490dc659 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -31,10 +31,10 @@
 #include <linux/gfp.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <linux/sizes.h>
 
-#include <mach/hardware.h>
 #include <linux/platform_data/mmc-pxamci.h>
 
 #include "pxamci.h"
diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c
index 7d96758a8f04..1749dbbacc13 100644
--- a/drivers/mtd/maps/pxa2xx-flash.c
+++ b/drivers/mtd/maps/pxa2xx-flash.c
@@ -16,8 +16,6 @@
 #include <linux/mtd/partitions.h>
 
 #include <asm/io.h>
-#include <mach/hardware.h>
-
 #include <asm/mach/flash.h>
 
 #define CACHELINESIZE	32
diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c
index d6d2f75f8f47..7cd1375d6087 100644
--- a/drivers/pcmcia/pxa2xx_base.c
+++ b/drivers/pcmcia/pxa2xx_base.c
@@ -23,8 +23,8 @@
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
+#include <linux/soc/pxa/cpu.h>
 
-#include <mach/hardware.h>
 #include <mach/smemc.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/drivers/pcmcia/pxa2xx_sharpsl.c b/drivers/pcmcia/pxa2xx_sharpsl.c
index 5fdd25a9e28e..66fe1d1af12a 100644
--- a/drivers/pcmcia/pxa2xx_sharpsl.c
+++ b/drivers/pcmcia/pxa2xx_sharpsl.c
@@ -15,7 +15,6 @@
 #include <linux/platform_device.h>
 
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/hardware/scoop.h>
 
diff --git a/drivers/pcmcia/sa1111_generic.c b/drivers/pcmcia/sa1111_generic.c
index 29fdd174bc23..bce664bbdc98 100644
--- a/drivers/pcmcia/sa1111_generic.c
+++ b/drivers/pcmcia/sa1111_generic.c
@@ -17,7 +17,6 @@
 
 #include <pcmcia/ss.h>
 
-#include <mach/hardware.h>
 #include <asm/hardware/sa1111.h>
 #include <asm/mach-types.h>
 #include <asm/irq.h>
diff --git a/drivers/pcmcia/sa1111_lubbock.c b/drivers/pcmcia/sa1111_lubbock.c
index 7feb8d61c639..f1b5160cb8fa 100644
--- a/drivers/pcmcia/sa1111_lubbock.c
+++ b/drivers/pcmcia/sa1111_lubbock.c
@@ -17,7 +17,6 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 
-#include <mach/hardware.h>
 #include <asm/hardware/sa1111.h>
 #include <asm/mach-types.h>
 
diff --git a/drivers/pcmcia/soc_common.c b/drivers/pcmcia/soc_common.c
index 3a8c84bb174d..9276a628473d 100644
--- a/drivers/pcmcia/soc_common.c
+++ b/drivers/pcmcia/soc_common.c
@@ -47,8 +47,6 @@
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 
-#include <mach/hardware.h>
-
 #include "soc_common.h"
 
 static irqreturn_t soc_common_pcmcia_interrupt(int irq, void *dev);
diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c
index cf8119b6d320..eeacf480cf36 100644
--- a/drivers/rtc/rtc-pxa.c
+++ b/drivers/rtc/rtc-pxa.c
@@ -16,8 +16,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <mach/hardware.h>
-
 #include "rtc-sa1100.h"
 
 #define RTC_DEF_DIVIDER		(32768 - 1)
diff --git a/drivers/usb/host/ohci-pxa27x.c b/drivers/usb/host/ohci-pxa27x.c
index 54aa5c77e549..ab4f610a0140 100644
--- a/drivers/usb/host/ohci-pxa27x.c
+++ b/drivers/usb/host/ohci-pxa27x.c
@@ -36,8 +36,7 @@
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
 #include <linux/usb/otg.h>
-
-#include <mach/hardware.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include "ohci.h"
 
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index f1551e00eb12..e3d1a184d2be 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -57,10 +57,10 @@
 #include <linux/console.h>
 #include <linux/of_graph.h>
 #include <linux/regulator/consumer.h>
+#include <linux/soc/pxa/cpu.h>
 #include <video/of_display_timing.h>
 #include <video/videomode.h>
 
-#include <mach/hardware.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/div64.h>
diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c
index 27846c6bdfb0..d33f0375112f 100644
--- a/drivers/watchdog/sa1100_wdt.c
+++ b/drivers/watchdog/sa1100_wdt.c
@@ -35,7 +35,6 @@
 #endif
 
 #include <mach/reset.h>
-#include <mach/hardware.h>
 
 static unsigned long oscr_freq;
 static unsigned long sa1100wdt_users;
diff --git a/include/linux/soc/pxa/cpu.h b/include/linux/soc/pxa/cpu.h
new file mode 100644
index 000000000000..5782450ee45c
--- /dev/null
+++ b/include/linux/soc/pxa/cpu.h
@@ -0,0 +1,252 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  Author:	Nicolas Pitre
+ *  Created:	Jun 15, 2001
+ *  Copyright:	MontaVista Software Inc.
+ */
+
+#ifndef __SOC_PXA_CPU_H
+#define __SOC_PXA_CPU_H
+
+#ifdef CONFIG_ARM
+#include <asm/cputype.h>
+#endif
+
+/*
+ *   CPU     Stepping     CPU_ID         JTAG_ID
+ *
+ *  PXA210	B0	0x69052922	0x2926C013
+ *  PXA210	B1	0x69052923	0x3926C013
+ *  PXA210	B2	0x69052924	0x4926C013
+ *  PXA210	C0	0x69052D25	0x5926C013
+ *
+ *  PXA250	A0	0x69052100	0x09264013
+ *  PXA250	A1	0x69052101	0x19264013
+ *  PXA250	B0	0x69052902	0x29264013
+ *  PXA250	B1	0x69052903	0x39264013
+ *  PXA250	B2	0x69052904	0x49264013
+ *  PXA250	C0	0x69052D05	0x59264013
+ *
+ *  PXA255	A0	0x69052D06	0x69264013
+ *
+ *  PXA26x	A0	0x69052903	0x39264013
+ *  PXA26x	B0	0x69052D05	0x59264013
+ *
+ *  PXA27x	A0	0x69054110	0x09265013
+ *  PXA27x	A1	0x69054111	0x19265013
+ *  PXA27x	B0	0x69054112	0x29265013
+ *  PXA27x	B1	0x69054113	0x39265013
+ *  PXA27x	C0	0x69054114	0x49265013
+ *  PXA27x	C5	0x69054117	0x79265013
+ *
+ *  PXA30x	A0	0x69056880	0x0E648013
+ *  PXA30x	A1	0x69056881	0x1E648013
+ *  PXA31x	A0	0x69056890	0x0E649013
+ *  PXA31x	A1	0x69056891	0x1E649013
+ *  PXA31x	A2	0x69056892	0x2E649013
+ *  PXA32x	B1	0x69056825	0x5E642013
+ *  PXA32x	B2	0x69056826	0x6E642013
+ *
+ *  PXA930	B0	0x69056835	0x5E643013
+ *  PXA930	B1	0x69056837	0x7E643013
+ *  PXA930	B2	0x69056838	0x8E643013
+ *
+ *  PXA935	A0	0x56056931	0x1E653013
+ *  PXA935	B0	0x56056936	0x6E653013
+ *  PXA935	B1	0x56056938	0x8E653013
+ */
+#ifdef CONFIG_PXA25x
+#define __cpu_is_pxa210(id)				\
+	({						\
+		unsigned int _id = (id) & 0xf3f0;	\
+		_id == 0x2120;				\
+	})
+
+#define __cpu_is_pxa250(id)				\
+	({						\
+		unsigned int _id = (id) & 0xf3ff;	\
+		_id <= 0x2105;				\
+	})
+
+#define __cpu_is_pxa255(id)				\
+	({						\
+		unsigned int _id = (id) & 0xffff;	\
+		_id == 0x2d06;				\
+	})
+
+#define __cpu_is_pxa25x(id)				\
+	({						\
+		unsigned int _id = (id) & 0xf300;	\
+		_id == 0x2100;				\
+	})
+#else
+#define __cpu_is_pxa210(id)	(0)
+#define __cpu_is_pxa250(id)	(0)
+#define __cpu_is_pxa255(id)	(0)
+#define __cpu_is_pxa25x(id)	(0)
+#endif
+
+#ifdef CONFIG_PXA27x
+#define __cpu_is_pxa27x(id)				\
+	({						\
+		unsigned int _id = (id) >> 4 & 0xfff;	\
+		_id == 0x411;				\
+	})
+#else
+#define __cpu_is_pxa27x(id)	(0)
+#endif
+
+#ifdef CONFIG_CPU_PXA300
+#define __cpu_is_pxa300(id)				\
+	({						\
+		unsigned int _id = (id) >> 4 & 0xfff;	\
+		_id == 0x688;				\
+	 })
+#else
+#define __cpu_is_pxa300(id)	(0)
+#endif
+
+#ifdef CONFIG_CPU_PXA310
+#define __cpu_is_pxa310(id)				\
+	({						\
+		unsigned int _id = (id) >> 4 & 0xfff;	\
+		_id == 0x689;				\
+	 })
+#else
+#define __cpu_is_pxa310(id)	(0)
+#endif
+
+#ifdef CONFIG_CPU_PXA320
+#define __cpu_is_pxa320(id)				\
+	({						\
+		unsigned int _id = (id) >> 4 & 0xfff;	\
+		_id == 0x603 || _id == 0x682;		\
+	 })
+#else
+#define __cpu_is_pxa320(id)	(0)
+#endif
+
+#ifdef CONFIG_CPU_PXA930
+#define __cpu_is_pxa930(id)				\
+	({						\
+		unsigned int _id = (id) >> 4 & 0xfff;	\
+		_id == 0x683;				\
+	 })
+#else
+#define __cpu_is_pxa930(id)	(0)
+#endif
+
+#ifdef CONFIG_CPU_PXA935
+#define __cpu_is_pxa935(id)				\
+	({						\
+		unsigned int _id = (id) >> 4 & 0xfff;	\
+		_id == 0x693;				\
+	 })
+#else
+#define __cpu_is_pxa935(id)	(0)
+#endif
+
+#define cpu_is_pxa210()					\
+	({						\
+		__cpu_is_pxa210(read_cpuid_id());	\
+	})
+
+#define cpu_is_pxa250()					\
+	({						\
+		__cpu_is_pxa250(read_cpuid_id());	\
+	})
+
+#define cpu_is_pxa255()                                 \
+	({                                              \
+		__cpu_is_pxa255(read_cpuid_id());       \
+	})
+
+#define cpu_is_pxa25x()					\
+	({						\
+		__cpu_is_pxa25x(read_cpuid_id());	\
+	})
+
+#define cpu_is_pxa27x()					\
+	({						\
+		__cpu_is_pxa27x(read_cpuid_id());	\
+	})
+
+#define cpu_is_pxa300()					\
+	({						\
+		__cpu_is_pxa300(read_cpuid_id());	\
+	 })
+
+#define cpu_is_pxa310()					\
+	({						\
+		__cpu_is_pxa310(read_cpuid_id());	\
+	 })
+
+#define cpu_is_pxa320()					\
+	({						\
+		__cpu_is_pxa320(read_cpuid_id());	\
+	 })
+
+#define cpu_is_pxa930()					\
+	({						\
+		__cpu_is_pxa930(read_cpuid_id());	\
+	 })
+
+#define cpu_is_pxa935()					\
+	({						\
+		__cpu_is_pxa935(read_cpuid_id());	\
+	 })
+
+
+
+/*
+ * CPUID Core Generation Bit
+ * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x
+ */
+#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x)
+#define __cpu_is_pxa2xx(id)				\
+	({						\
+		unsigned int _id = (id) >> 13 & 0x7;	\
+		_id <= 0x2;				\
+	 })
+#else
+#define __cpu_is_pxa2xx(id)	(0)
+#endif
+
+#ifdef CONFIG_PXA3xx
+#define __cpu_is_pxa3xx(id)				\
+	({						\
+		__cpu_is_pxa300(id)			\
+			|| __cpu_is_pxa310(id)		\
+			|| __cpu_is_pxa320(id)		\
+			|| __cpu_is_pxa93x(id);		\
+	 })
+#else
+#define __cpu_is_pxa3xx(id)	(0)
+#endif
+
+#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935)
+#define __cpu_is_pxa93x(id)				\
+	({						\
+		__cpu_is_pxa930(id)			\
+			|| __cpu_is_pxa935(id);		\
+	 })
+#else
+#define __cpu_is_pxa93x(id)	(0)
+#endif
+
+#define cpu_is_pxa2xx()					\
+	({						\
+		__cpu_is_pxa2xx(read_cpuid_id());	\
+	 })
+
+#define cpu_is_pxa3xx()					\
+	({						\
+		__cpu_is_pxa3xx(read_cpuid_id());	\
+	 })
+
+#define cpu_is_pxa93x()					\
+	({						\
+		__cpu_is_pxa93x(read_cpuid_id());	\
+	 })
+
+#endif
diff --git a/sound/arm/pxa2xx-ac97-lib.c b/sound/arm/pxa2xx-ac97-lib.c
index 58274b4a1f09..84d5f85073b9 100644
--- a/sound/arm/pxa2xx-ac97-lib.c
+++ b/sound/arm/pxa2xx-ac97-lib.c
@@ -17,6 +17,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/of_gpio.h>
+#include <linux/soc/pxa/cpu.h>
 
 #include <sound/pxa2xx-lib.h>
 
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 58f8541ba55c..8f78c5a359c5 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -21,7 +21,7 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-#include <mach/hardware.h>
+#include <mach/pxa-regs.h>
 #include <mach/regs-ac97.h>
 #include <mach/audio.h>
 
diff --git a/sound/soc/pxa/pxa2xx-i2s.c b/sound/soc/pxa/pxa2xx-i2s.c
index 5bfc1a966532..114a33c4a064 100644
--- a/sound/soc/pxa/pxa2xx-i2s.c
+++ b/sound/soc/pxa/pxa2xx-i2s.c
@@ -21,7 +21,7 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-#include <mach/hardware.h>
+#include <mach/pxa-regs.h>
 #include <mach/audio.h>
 
 #include "pxa2xx-i2s.h"
diff --git a/sound/soc/pxa/z2.c b/sound/soc/pxa/z2.c
index edf2b9eec5b8..7e8f33d7b83f 100644
--- a/sound/soc/pxa/z2.c
+++ b/sound/soc/pxa/z2.c
@@ -21,7 +21,6 @@
 #include <sound/jack.h>
 
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <mach/audio.h>
 #include <mach/z2.h>
 
-- 
cgit v1.2.3


From 22f0866513c2e531ae65a9d5dfc82f24497ef3b3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 2 Sep 2019 00:02:08 +0200
Subject: ARM: pxa: move mach/sound.h to linux/platform_data/

This is a basically a platform_data file, so move it out of
the mach/* header directory.

Cc: Marek Vasut <marek.vasut@gmail.com>
Cc: Tomas Cech <sleep_walker@suse.com>
Cc: Sergey Lapin <slapin@ossfans.org>
Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Cc: alsa-devel@alsa-project.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/balloon3.c           |  2 +-
 arch/arm/mach-pxa/cm-x300.c            |  2 +-
 arch/arm/mach-pxa/colibri-pxa270.c     |  2 +-
 arch/arm/mach-pxa/colibri-pxa300.c     |  2 +-
 arch/arm/mach-pxa/colibri-pxa320.c     |  2 +-
 arch/arm/mach-pxa/csb726.c             |  2 +-
 arch/arm/mach-pxa/devices.c            |  2 +-
 arch/arm/mach-pxa/eseries.c            |  2 +-
 arch/arm/mach-pxa/include/mach/audio.h | 31 -------------------------------
 arch/arm/mach-pxa/lpd270.c             |  2 +-
 arch/arm/mach-pxa/lubbock.c            |  2 +-
 arch/arm/mach-pxa/mainstone.c          |  2 +-
 arch/arm/mach-pxa/mioa701.c            |  2 +-
 arch/arm/mach-pxa/palm27x.c            |  2 +-
 arch/arm/mach-pxa/palmld.c             |  2 +-
 arch/arm/mach-pxa/palmt5.c             |  2 +-
 arch/arm/mach-pxa/palmtc.c             |  2 +-
 arch/arm/mach-pxa/palmte2.c            |  2 +-
 arch/arm/mach-pxa/palmtreo.c           |  2 +-
 arch/arm/mach-pxa/palmtx.c             |  2 +-
 arch/arm/mach-pxa/palmz72.c            |  2 +-
 arch/arm/mach-pxa/pcm990-baseboard.c   |  2 +-
 arch/arm/mach-pxa/tosa.c               |  2 +-
 arch/arm/mach-pxa/trizeps4.c           |  2 +-
 arch/arm/mach-pxa/viper.c              |  2 +-
 arch/arm/mach-pxa/vpac270.c            |  2 +-
 arch/arm/mach-pxa/zeus.c               |  2 +-
 arch/arm/mach-pxa/zylonite.c           |  2 +-
 include/linux/platform_data/asoc-pxa.h | 31 +++++++++++++++++++++++++++++++
 sound/arm/pxa2xx-ac97-lib.c            |  2 +-
 sound/arm/pxa2xx-ac97.c                |  2 +-
 sound/soc/pxa/corgi.c                  |  2 +-
 sound/soc/pxa/e740_wm9705.c            |  2 +-
 sound/soc/pxa/e750_wm9705.c            |  2 +-
 sound/soc/pxa/e800_wm9712.c            |  2 +-
 sound/soc/pxa/em-x270.c                |  2 +-
 sound/soc/pxa/mioa701_wm9713.c         |  2 +-
 sound/soc/pxa/palm27x.c                |  2 +-
 sound/soc/pxa/poodle.c                 |  2 +-
 sound/soc/pxa/pxa2xx-ac97.c            |  2 +-
 sound/soc/pxa/pxa2xx-i2s.c             |  2 +-
 sound/soc/pxa/tosa.c                   |  2 +-
 sound/soc/pxa/z2.c                     |  2 +-
 43 files changed, 72 insertions(+), 72 deletions(-)
 delete mode 100644 arch/arm/mach-pxa/include/mach/audio.h
 create mode 100644 include/linux/platform_data/asoc-pxa.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index 26140249c784..82f9299f67d3 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -41,7 +41,7 @@
 
 #include "pxa27x.h"
 #include <mach/balloon3.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include "udc.h"
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 85e2537fdc15..09a5264a27c8 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -53,7 +53,7 @@
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <linux/platform_data/mtd-nand-pxa3xx.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/usb-pxa3xx-ulpi.h>
 
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-pxa/colibri-pxa270.c b/arch/arm/mach-pxa/colibri-pxa270.c
index 2f2cd2ae4187..5dc669752836 100644
--- a/arch/arm/mach-pxa/colibri-pxa270.c
+++ b/arch/arm/mach-pxa/colibri-pxa270.c
@@ -23,7 +23,7 @@
 #include <asm/mach-types.h>
 #include <linux/sizes.h>
 
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include "colibri.h"
 #include "pxa27x.h"
 
diff --git a/arch/arm/mach-pxa/colibri-pxa300.c b/arch/arm/mach-pxa/colibri-pxa300.c
index 4ceeea142bfd..11ca6c4795e7 100644
--- a/arch/arm/mach-pxa/colibri-pxa300.c
+++ b/arch/arm/mach-pxa/colibri-pxa300.c
@@ -24,7 +24,7 @@
 #include "colibri.h"
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <linux/platform_data/video-pxafb.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 #include "generic.h"
 #include "devices.h"
diff --git a/arch/arm/mach-pxa/colibri-pxa320.c b/arch/arm/mach-pxa/colibri-pxa320.c
index 35dd3adb7712..1a59056e181e 100644
--- a/arch/arm/mach-pxa/colibri-pxa320.c
+++ b/arch/arm/mach-pxa/colibri-pxa320.c
@@ -24,7 +24,7 @@
 #include "colibri.h"
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include "pxa27x-udc.h"
 #include "udc.h"
 
diff --git a/arch/arm/mach-pxa/csb726.c b/arch/arm/mach-pxa/csb726.c
index d48493445ae5..88f2f1d96c7b 100644
--- a/arch/arm/mach-pxa/csb726.c
+++ b/arch/arm/mach-pxa/csb726.c
@@ -22,7 +22,7 @@
 #include "pxa27x.h"
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/smemc.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 7ca97ddef6fe..454523237c97 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -20,7 +20,7 @@
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include <linux/platform_data/keypad-pxa27x.h>
 #include <linux/platform_data/media/camera-pxa.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/mmp_dma.h>
 #include <linux/platform_data/mtd-nand-pxa3xx.h>
 
diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index f37c44b6139d..a8b6483ff665 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -34,7 +34,7 @@
 #include "pxa25x.h"
 #include <mach/eseries-gpio.h>
 #include "eseries-irq.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include "udc.h"
 #include <linux/platform_data/irda-pxaficp.h>
diff --git a/arch/arm/mach-pxa/include/mach/audio.h b/arch/arm/mach-pxa/include/mach/audio.h
deleted file mode 100644
index 7beebf7297b5..000000000000
--- a/arch/arm/mach-pxa/include/mach/audio.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_ARCH_AUDIO_H__
-#define __ASM_ARCH_AUDIO_H__
-
-#include <sound/core.h>
-#include <sound/pcm.h>
-#include <sound/ac97_codec.h>
-
-/*
- * @reset_gpio: AC97 reset gpio (normally gpio113 or gpio95)
- *              a -1 value means no gpio will be used for reset
- * @codec_pdata: AC97 codec platform_data
-
- * reset_gpio should only be specified for pxa27x CPUs where a silicon
- * bug prevents correct operation of the reset line. If not specified,
- * the default behaviour on these CPUs is to consider gpio 113 as the
- * AC97 reset line, which is the default on most boards.
- */
-typedef struct {
-	int (*startup)(struct snd_pcm_substream *, void *);
-	void (*shutdown)(struct snd_pcm_substream *, void *);
-	void (*suspend)(void *);
-	void (*resume)(void *);
-	void *priv;
-	int reset_gpio;
-	void *codec_pdata[AC97_BUS_MAX_DEVICES];
-} pxa2xx_audio_ops_t;
-
-extern void pxa_set_ac97_info(pxa2xx_audio_ops_t *ops);
-
-#endif
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index eac32bd9e385..7f10b86f85fd 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -39,7 +39,7 @@
 #include "pxa27x.h"
 #include "lpd270.h"
 #include <mach/addr-map.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/irda-pxaficp.h>
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index 72816e7c206f..46aef93c0615 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -45,7 +45,7 @@
 #include <asm/hardware/sa1111.h>
 
 #include "pxa25x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/lubbock.h>
 #include "udc.h"
 #include <linux/platform_data/irda-pxaficp.h>
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index cf74adfe65df..c8200fc2159d 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -45,7 +45,7 @@
 
 #include "pxa27x.h"
 #include "mainstone.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/irda-pxaficp.h>
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index a79f296e81e0..907cd7b5f58c 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -41,7 +41,7 @@
 #include "udc.h"
 #include "pxa27x-udc.h"
 #include <linux/platform_data/media/camera-pxa.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/smemc.h>
 
 #include "mioa701.h"
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 6230381a7ca0..1a8d25eecac3 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -25,7 +25,7 @@
 #include <asm/mach/map.h>
 
 #include "pxa27x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/irda-pxaficp.h>
diff --git a/arch/arm/mach-pxa/palmld.c b/arch/arm/mach-pxa/palmld.c
index 5f73716a77f0..d85146957004 100644
--- a/arch/arm/mach-pxa/palmld.c
+++ b/arch/arm/mach-pxa/palmld.c
@@ -29,7 +29,7 @@
 #include <asm/mach/map.h>
 
 #include "pxa27x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/palmld.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
diff --git a/arch/arm/mach-pxa/palmt5.c b/arch/arm/mach-pxa/palmt5.c
index 7c7cbb4e677e..460a8b1043a5 100644
--- a/arch/arm/mach-pxa/palmt5.c
+++ b/arch/arm/mach-pxa/palmt5.c
@@ -29,7 +29,7 @@
 #include <asm/mach/map.h>
 
 #include "pxa27x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include "palmt5.h"
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index 455cb8ccaf26..c59fc76c0c3d 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -29,7 +29,7 @@
 #include <asm/mach/map.h>
 
 #include "pxa25x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/palmtc.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
diff --git a/arch/arm/mach-pxa/palmte2.c b/arch/arm/mach-pxa/palmte2.c
index a2b10db4aacc..fedac670a8af 100644
--- a/arch/arm/mach-pxa/palmte2.c
+++ b/arch/arm/mach-pxa/palmte2.c
@@ -29,7 +29,7 @@
 #include <asm/mach/map.h>
 
 #include "pxa25x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include "palmte2.h"
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
diff --git a/arch/arm/mach-pxa/palmtreo.c b/arch/arm/mach-pxa/palmtreo.c
index 2bf0f7f3ea24..d6d5b90d9578 100644
--- a/arch/arm/mach-pxa/palmtreo.c
+++ b/arch/arm/mach-pxa/palmtreo.c
@@ -29,7 +29,7 @@
 
 #include "pxa27x.h"
 #include "pxa27x-udc.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include "palmtreo.h"
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c
index 07332c92c9f7..097b88638863 100644
--- a/arch/arm/mach-pxa/palmtx.c
+++ b/arch/arm/mach-pxa/palmtx.c
@@ -32,7 +32,7 @@
 #include <asm/mach/map.h>
 
 #include "pxa27x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/palmtx.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index b4a5fe02a0af..66e8fe6f1661 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -34,7 +34,7 @@
 #include <asm/mach/map.h>
 
 #include "pxa27x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include "palmz72.h"
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index 8dfcc366d0fe..33a9d2eeca1c 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -26,7 +26,7 @@
 
 #include <asm/mach/map.h>
 #include "pxa27x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
 #include "pcm990_baseboard.h"
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 431709725d02..5af980d77d39 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -45,7 +45,7 @@
 #include <linux/platform_data/mmc-pxamci.h>
 #include "udc.h"
 #include "tosa_bt.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/smemc.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index f76f8be09554..1337008cc760 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -41,7 +41,7 @@
 
 #include "pxa27x.h"
 #include <mach/trizeps4.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/irda-pxaficp.h>
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 4b81c0117971..ac94b10bf8c1 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -46,7 +46,7 @@
 #include <linux/syscore_ops.h>
 
 #include "pxa25x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include "regs-uart.h"
 #include <linux/platform_data/pcmcia-pxa2xx_viper.h>
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index 14505e83479e..7067d1464689 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -29,7 +29,7 @@
 #include <asm/mach/arch.h>
 
 #include "pxa27x.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/vpac270.h>
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 5d02f10b5b5a..67396e85bb66 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -46,7 +46,7 @@
 #include "udc.h"
 #include <linux/platform_data/video-pxafb.h>
 #include "pm.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/pcmcia-pxa2xx_viper.h>
 #include "zeus.h"
 #include <mach/smemc.h>
diff --git a/arch/arm/mach-pxa/zylonite.c b/arch/arm/mach-pxa/zylonite.c
index 9bcb81688201..c48dd6d03df9 100644
--- a/arch/arm/mach-pxa/zylonite.c
+++ b/arch/arm/mach-pxa/zylonite.c
@@ -25,7 +25,7 @@
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include "pxa3xx.h"
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include "zylonite.h"
 #include <linux/platform_data/mmc-pxamci.h>
diff --git a/include/linux/platform_data/asoc-pxa.h b/include/linux/platform_data/asoc-pxa.h
new file mode 100644
index 000000000000..327454cd8246
--- /dev/null
+++ b/include/linux/platform_data/asoc-pxa.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __SOC_PXA_AUDIO_H__
+#define __SOC_PXA_AUDIO_H__
+
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/ac97_codec.h>
+
+/*
+ * @reset_gpio: AC97 reset gpio (normally gpio113 or gpio95)
+ *              a -1 value means no gpio will be used for reset
+ * @codec_pdata: AC97 codec platform_data
+
+ * reset_gpio should only be specified for pxa27x CPUs where a silicon
+ * bug prevents correct operation of the reset line. If not specified,
+ * the default behaviour on these CPUs is to consider gpio 113 as the
+ * AC97 reset line, which is the default on most boards.
+ */
+typedef struct {
+	int (*startup)(struct snd_pcm_substream *, void *);
+	void (*shutdown)(struct snd_pcm_substream *, void *);
+	void (*suspend)(void *);
+	void (*resume)(void *);
+	void *priv;
+	int reset_gpio;
+	void *codec_pdata[AC97_BUS_MAX_DEVICES];
+} pxa2xx_audio_ops_t;
+
+extern void pxa_set_ac97_info(pxa2xx_audio_ops_t *ops);
+
+#endif
diff --git a/sound/arm/pxa2xx-ac97-lib.c b/sound/arm/pxa2xx-ac97-lib.c
index 84d5f85073b9..9b5c1f0f8998 100644
--- a/sound/arm/pxa2xx-ac97-lib.c
+++ b/sound/arm/pxa2xx-ac97-lib.c
@@ -23,7 +23,7 @@
 
 #include <mach/irqs.h>
 #include <mach/regs-ac97.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 static DEFINE_MUTEX(car_mutex);
 static DECLARE_WAIT_QUEUE_HEAD(gsr_wq);
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index c17a19fe59ed..57c3e12e6629 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -22,7 +22,7 @@
 #include <sound/dmaengine_pcm.h>
 
 #include <mach/regs-ac97.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 static void pxa2xx_ac97_legacy_reset(struct snd_ac97 *ac97)
 {
diff --git a/sound/soc/pxa/corgi.c b/sound/soc/pxa/corgi.c
index 8ee2dea25a8d..8b83709431cb 100644
--- a/sound/soc/pxa/corgi.c
+++ b/sound/soc/pxa/corgi.c
@@ -22,7 +22,7 @@
 
 #include <asm/mach-types.h>
 #include <mach/corgi.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 #include "../codecs/wm8731.h"
 #include "pxa2xx-i2s.h"
diff --git a/sound/soc/pxa/e740_wm9705.c b/sound/soc/pxa/e740_wm9705.c
index eafa1482afbe..f922be7e0016 100644
--- a/sound/soc/pxa/e740_wm9705.c
+++ b/sound/soc/pxa/e740_wm9705.c
@@ -13,7 +13,7 @@
 #include <sound/pcm.h>
 #include <sound/soc.h>
 
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/eseries-gpio.h>
 
 #include <asm/mach-types.h>
diff --git a/sound/soc/pxa/e750_wm9705.c b/sound/soc/pxa/e750_wm9705.c
index d75510d7b16b..308828cd736b 100644
--- a/sound/soc/pxa/e750_wm9705.c
+++ b/sound/soc/pxa/e750_wm9705.c
@@ -13,7 +13,7 @@
 #include <sound/pcm.h>
 #include <sound/soc.h>
 
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/eseries-gpio.h>
 
 #include <asm/mach-types.h>
diff --git a/sound/soc/pxa/e800_wm9712.c b/sound/soc/pxa/e800_wm9712.c
index 56d543da938a..d74fcceef687 100644
--- a/sound/soc/pxa/e800_wm9712.c
+++ b/sound/soc/pxa/e800_wm9712.c
@@ -14,7 +14,7 @@
 #include <sound/soc.h>
 
 #include <asm/mach-types.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/eseries-gpio.h>
 
 static int e800_spk_amp_event(struct snd_soc_dapm_widget *w,
diff --git a/sound/soc/pxa/em-x270.c b/sound/soc/pxa/em-x270.c
index 9076ea7e9339..b59ec22e1e7e 100644
--- a/sound/soc/pxa/em-x270.c
+++ b/sound/soc/pxa/em-x270.c
@@ -23,7 +23,7 @@
 #include <sound/soc.h>
 
 #include <asm/mach-types.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 SND_SOC_DAILINK_DEFS(ac97,
 	DAILINK_COMP_ARRAY(COMP_CPU("pxa2xx-ac97")),
diff --git a/sound/soc/pxa/mioa701_wm9713.c b/sound/soc/pxa/mioa701_wm9713.c
index 763db7bbd9bb..0fa37637eca9 100644
--- a/sound/soc/pxa/mioa701_wm9713.c
+++ b/sound/soc/pxa/mioa701_wm9713.c
@@ -33,7 +33,7 @@
 #include <linux/platform_device.h>
 
 #include <asm/mach-types.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
diff --git a/sound/soc/pxa/palm27x.c b/sound/soc/pxa/palm27x.c
index b92ea1a0453f..275c86379e88 100644
--- a/sound/soc/pxa/palm27x.c
+++ b/sound/soc/pxa/palm27x.c
@@ -20,7 +20,7 @@
 #include <sound/jack.h>
 
 #include <asm/mach-types.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/asoc-palm27x.h>
 
 static struct snd_soc_jack hs_jack;
diff --git a/sound/soc/pxa/poodle.c b/sound/soc/pxa/poodle.c
index 323ba3e23039..176a0441235a 100644
--- a/sound/soc/pxa/poodle.c
+++ b/sound/soc/pxa/poodle.c
@@ -22,7 +22,7 @@
 #include <asm/mach-types.h>
 #include <asm/hardware/locomo.h>
 #include <mach/poodle.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 #include "../codecs/wm8731.h"
 #include "pxa2xx-i2s.h"
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 8f78c5a359c5..9443c1390d2f 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -23,7 +23,7 @@
 
 #include <mach/pxa-regs.h>
 #include <mach/regs-ac97.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 static void pxa2xx_ac97_warm_reset(struct ac97_controller *adrv)
 {
diff --git a/sound/soc/pxa/pxa2xx-i2s.c b/sound/soc/pxa/pxa2xx-i2s.c
index 114a33c4a064..5164c60ba89f 100644
--- a/sound/soc/pxa/pxa2xx-i2s.c
+++ b/sound/soc/pxa/pxa2xx-i2s.c
@@ -22,7 +22,7 @@
 #include <sound/dmaengine_pcm.h>
 
 #include <mach/pxa-regs.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 #include "pxa2xx-i2s.h"
 
diff --git a/sound/soc/pxa/tosa.c b/sound/soc/pxa/tosa.c
index 3b40b5fa5de7..06226f9b863e 100644
--- a/sound/soc/pxa/tosa.c
+++ b/sound/soc/pxa/tosa.c
@@ -24,7 +24,7 @@
 
 #include <asm/mach-types.h>
 #include <mach/tosa.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 
 #define TOSA_HP        0
 #define TOSA_MIC_INT   1
diff --git a/sound/soc/pxa/z2.c b/sound/soc/pxa/z2.c
index 7e8f33d7b83f..dc6c48e4738b 100644
--- a/sound/soc/pxa/z2.c
+++ b/sound/soc/pxa/z2.c
@@ -21,7 +21,7 @@
 #include <sound/jack.h>
 
 #include <asm/mach-types.h>
-#include <mach/audio.h>
+#include <linux/platform_data/asoc-pxa.h>
 #include <mach/z2.h>
 
 #include "../codecs/wm8750.h"
-- 
cgit v1.2.3


From ee84cbd5df2beaf14e8af0955f1ab15ad3f81504 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 2 Sep 2019 00:15:44 +0200
Subject: ARM: pxa: move regs-lcd.h into driver

Only the pxafb driver uses this header, so move it into the
same directory. The SMART_* macros are required by some
platform data definitions and can go into the
linux/platform_data/video-pxafb.h header.

Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Cc: dri-devel@lists.freedesktop.org
Cc: linux-fbdev@vger.kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/include/mach/regs-lcd.h | 199 ------------------------------
 drivers/video/fbdev/pxa3xx-regs.h         | 180 +++++++++++++++++++++++++++
 drivers/video/fbdev/pxafb.c               |   1 +
 include/linux/platform_data/video-pxafb.h |  22 +++-
 4 files changed, 202 insertions(+), 200 deletions(-)
 delete mode 100644 arch/arm/mach-pxa/include/mach/regs-lcd.h
 create mode 100644 drivers/video/fbdev/pxa3xx-regs.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/include/mach/regs-lcd.h b/arch/arm/mach-pxa/include/mach/regs-lcd.h
deleted file mode 100644
index 6a434675f84a..000000000000
--- a/arch/arm/mach-pxa/include/mach/regs-lcd.h
+++ /dev/null
@@ -1,199 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_ARCH_REGS_LCD_H
-#define __ASM_ARCH_REGS_LCD_H
-
-/*
- * LCD Controller Registers and Bits Definitions
- */
-#define LCCR0		(0x000)	/* LCD Controller Control Register 0 */
-#define LCCR1		(0x004)	/* LCD Controller Control Register 1 */
-#define LCCR2		(0x008)	/* LCD Controller Control Register 2 */
-#define LCCR3		(0x00C)	/* LCD Controller Control Register 3 */
-#define LCCR4		(0x010)	/* LCD Controller Control Register 4 */
-#define LCCR5		(0x014)	/* LCD Controller Control Register 5 */
-#define LCSR		(0x038)	/* LCD Controller Status Register 0 */
-#define LCSR1		(0x034)	/* LCD Controller Status Register 1 */
-#define LIIDR		(0x03C)	/* LCD Controller Interrupt ID Register */
-#define TMEDRGBR	(0x040)	/* TMED RGB Seed Register */
-#define TMEDCR		(0x044)	/* TMED Control Register */
-
-#define FBR0		(0x020)	/* DMA Channel 0 Frame Branch Register */
-#define FBR1		(0x024)	/* DMA Channel 1 Frame Branch Register */
-#define FBR2		(0x028) /* DMA Channel 2 Frame Branch Register */
-#define FBR3		(0x02C) /* DMA Channel 2 Frame Branch Register */
-#define FBR4		(0x030) /* DMA Channel 2 Frame Branch Register */
-#define FBR5		(0x110) /* DMA Channel 2 Frame Branch Register */
-#define FBR6		(0x114) /* DMA Channel 2 Frame Branch Register */
-
-#define OVL1C1		(0x050)	/* Overlay 1 Control Register 1 */
-#define OVL1C2		(0x060)	/* Overlay 1 Control Register 2 */
-#define OVL2C1		(0x070)	/* Overlay 2 Control Register 1 */
-#define OVL2C2		(0x080)	/* Overlay 2 Control Register 2 */
-
-#define CMDCR		(0x100)	/* Command Control Register */
-#define PRSR		(0x104)	/* Panel Read Status Register */
-
-#define LCCR3_BPP(x)	((((x) & 0x7) << 24) | (((x) & 0x8) ? (1 << 29) : 0))
-
-#define LCCR3_PDFOR_0	(0 << 30)
-#define LCCR3_PDFOR_1	(1 << 30)
-#define LCCR3_PDFOR_2	(2 << 30)
-#define LCCR3_PDFOR_3	(3 << 30)
-
-#define LCCR4_PAL_FOR_0	(0 << 15)
-#define LCCR4_PAL_FOR_1	(1 << 15)
-#define LCCR4_PAL_FOR_2	(2 << 15)
-#define LCCR4_PAL_FOR_3	(3 << 15)
-#define LCCR4_PAL_FOR_MASK	(3 << 15)
-
-#define FDADR0		(0x200)	/* DMA Channel 0 Frame Descriptor Address Register */
-#define FDADR1		(0x210)	/* DMA Channel 1 Frame Descriptor Address Register */
-#define FDADR2		(0x220)	/* DMA Channel 2 Frame Descriptor Address Register */
-#define FDADR3		(0x230)	/* DMA Channel 3 Frame Descriptor Address Register */
-#define FDADR4		(0x240)	/* DMA Channel 4 Frame Descriptor Address Register */
-#define FDADR5		(0x250)	/* DMA Channel 5 Frame Descriptor Address Register */
-#define FDADR6		(0x260) /* DMA Channel 6 Frame Descriptor Address Register */
-
-#define LCCR0_ENB	(1 << 0)	/* LCD Controller enable */
-#define LCCR0_CMS	(1 << 1)	/* Color/Monochrome Display Select */
-#define LCCR0_Color	(LCCR0_CMS*0)	/*  Color display */
-#define LCCR0_Mono	(LCCR0_CMS*1)	/*  Monochrome display */
-#define LCCR0_SDS	(1 << 2)	/* Single/Dual Panel Display Select */
-#define LCCR0_Sngl	(LCCR0_SDS*0)	/*  Single panel display */
-#define LCCR0_Dual	(LCCR0_SDS*1)	/*  Dual panel display */
-
-#define LCCR0_LDM	(1 << 3)	/* LCD Disable Done Mask */
-#define LCCR0_SFM	(1 << 4)	/* Start of frame mask */
-#define LCCR0_IUM	(1 << 5)	/* Input FIFO underrun mask */
-#define LCCR0_EFM	(1 << 6)	/* End of Frame mask */
-#define LCCR0_PAS	(1 << 7)	/* Passive/Active display Select */
-#define LCCR0_Pas	(LCCR0_PAS*0)	/*  Passive display (STN) */
-#define LCCR0_Act	(LCCR0_PAS*1)	/*  Active display (TFT) */
-#define LCCR0_DPD	(1 << 9)	/* Double Pixel Data (monochrome) */
-#define LCCR0_4PixMono	(LCCR0_DPD*0)	/*  4-Pixel/clock Monochrome display */
-#define LCCR0_8PixMono	(LCCR0_DPD*1)	/*  8-Pixel/clock Monochrome display */
-#define LCCR0_DIS	(1 << 10)	/* LCD Disable */
-#define LCCR0_QDM	(1 << 11)	/* LCD Quick Disable mask */
-#define LCCR0_PDD	(0xff << 12)	/* Palette DMA request delay */
-#define LCCR0_PDD_S	12
-#define LCCR0_BM	(1 << 20)	/* Branch mask */
-#define LCCR0_OUM	(1 << 21)	/* Output FIFO underrun mask */
-#define LCCR0_LCDT	(1 << 22)	/* LCD panel type */
-#define LCCR0_RDSTM	(1 << 23)	/* Read status interrupt mask */
-#define LCCR0_CMDIM	(1 << 24)	/* Command interrupt mask */
-#define LCCR0_OUC	(1 << 25)	/* Overlay Underlay control bit */
-#define LCCR0_LDDALT	(1 << 26)	/* LDD alternate mapping control */
-
-#define Fld(Size, Shft)	(((Size) << 16) + (Shft))
-#define FShft(Field)	((Field) & 0x0000FFFF)
-
-#define LCCR1_PPL	Fld (10, 0)	/* Pixels Per Line - 1 */
-#define LCCR1_DisWdth(Pixel)	(((Pixel) - 1) << FShft (LCCR1_PPL))
-
-#define LCCR1_HSW	Fld (6, 10)	/* Horizontal Synchronization */
-#define LCCR1_HorSnchWdth(Tpix)	(((Tpix) - 1) << FShft (LCCR1_HSW))
-
-#define LCCR1_ELW	Fld (8, 16)	/* End-of-Line pixel clock Wait - 1 */
-#define LCCR1_EndLnDel(Tpix)	(((Tpix) - 1) << FShft (LCCR1_ELW))
-
-#define LCCR1_BLW	Fld (8, 24)	/* Beginning-of-Line pixel clock */
-#define LCCR1_BegLnDel(Tpix)	(((Tpix) - 1) << FShft (LCCR1_BLW))
-
-#define LCCR2_LPP	Fld (10, 0)	/* Line Per Panel - 1 */
-#define LCCR2_DisHght(Line)	(((Line) - 1) << FShft (LCCR2_LPP))
-
-#define LCCR2_VSW	Fld (6, 10)	/* Vertical Synchronization pulse - 1 */
-#define LCCR2_VrtSnchWdth(Tln)	(((Tln) - 1) << FShft (LCCR2_VSW))
-
-#define LCCR2_EFW	Fld (8, 16)	/* End-of-Frame line clock Wait */
-#define LCCR2_EndFrmDel(Tln)	((Tln) << FShft (LCCR2_EFW))
-
-#define LCCR2_BFW	Fld (8, 24)	/* Beginning-of-Frame line clock */
-#define LCCR2_BegFrmDel(Tln)	((Tln) << FShft (LCCR2_BFW))
-
-#define LCCR3_API	(0xf << 16)	/* AC Bias pin trasitions per interrupt */
-#define LCCR3_API_S	16
-#define LCCR3_VSP	(1 << 20)	/* vertical sync polarity */
-#define LCCR3_HSP	(1 << 21)	/* horizontal sync polarity */
-#define LCCR3_PCP	(1 << 22)	/* Pixel Clock Polarity (L_PCLK) */
-#define LCCR3_PixRsEdg	(LCCR3_PCP*0)	/*  Pixel clock Rising-Edge */
-#define LCCR3_PixFlEdg	(LCCR3_PCP*1)	/*  Pixel clock Falling-Edge */
-
-#define LCCR3_OEP	(1 << 23)	/* Output Enable Polarity */
-#define LCCR3_OutEnH	(LCCR3_OEP*0)	/*  Output Enable active High */
-#define LCCR3_OutEnL	(LCCR3_OEP*1)	/*  Output Enable active Low */
-
-#define LCCR3_DPC	(1 << 27)	/* double pixel clock mode */
-#define LCCR3_PCD	Fld (8, 0)	/* Pixel Clock Divisor */
-#define LCCR3_PixClkDiv(Div)	(((Div) << FShft (LCCR3_PCD)))
-
-#define LCCR3_ACB	Fld (8, 8)	/* AC Bias */
-#define LCCR3_Acb(Acb)	(((Acb) << FShft (LCCR3_ACB)))
-
-#define LCCR3_HorSnchH	(LCCR3_HSP*0)	/*  HSP Active High */
-#define LCCR3_HorSnchL	(LCCR3_HSP*1)	/*  HSP Active Low */
-
-#define LCCR3_VrtSnchH	(LCCR3_VSP*0)	/*  VSP Active High */
-#define LCCR3_VrtSnchL	(LCCR3_VSP*1)	/*  VSP Active Low */
-
-#define LCCR5_IUM(x)	(1 << ((x) + 23)) /* input underrun mask */
-#define LCCR5_BSM(x)	(1 << ((x) + 15)) /* branch mask */
-#define LCCR5_EOFM(x)	(1 << ((x) + 7))  /* end of frame mask */
-#define LCCR5_SOFM(x)	(1 << ((x) + 0))  /* start of frame mask */
-
-#define LCSR_LDD	(1 << 0)	/* LCD Disable Done */
-#define LCSR_SOF	(1 << 1)	/* Start of frame */
-#define LCSR_BER	(1 << 2)	/* Bus error */
-#define LCSR_ABC	(1 << 3)	/* AC Bias count */
-#define LCSR_IUL	(1 << 4)	/* input FIFO underrun Lower panel */
-#define LCSR_IUU	(1 << 5)	/* input FIFO underrun Upper panel */
-#define LCSR_OU		(1 << 6)	/* output FIFO underrun */
-#define LCSR_QD		(1 << 7)	/* quick disable */
-#define LCSR_EOF	(1 << 8)	/* end of frame */
-#define LCSR_BS		(1 << 9)	/* branch status */
-#define LCSR_SINT	(1 << 10)	/* subsequent interrupt */
-#define LCSR_RD_ST	(1 << 11)	/* read status */
-#define LCSR_CMD_INT	(1 << 12)	/* command interrupt */
-
-#define LCSR1_IU(x)	(1 << ((x) + 23)) /* Input FIFO underrun */
-#define LCSR1_BS(x)	(1 << ((x) + 15)) /* Branch Status */
-#define LCSR1_EOF(x)	(1 << ((x) + 7))  /* End of Frame Status */
-#define LCSR1_SOF(x)	(1 << ((x) - 1))  /* Start of Frame Status */
-
-#define LDCMD_PAL	(1 << 26)	/* instructs DMA to load palette buffer */
-
-/* overlay control registers */
-#define OVLxC1_PPL(x)	((((x) - 1) & 0x3ff) << 0)	/* Pixels Per Line */
-#define OVLxC1_LPO(x)	((((x) - 1) & 0x3ff) << 10)	/* Number of Lines */
-#define OVLxC1_BPP(x)	(((x) & 0xf) << 20)	/* Bits Per Pixel */
-#define OVLxC1_OEN	(1 << 31)		/* Enable bit for Overlay */
-#define OVLxC2_XPOS(x)	(((x) & 0x3ff) << 0)	/* Horizontal Position */
-#define OVLxC2_YPOS(x)	(((x) & 0x3ff) << 10)	/* Vertical Position */
-#define OVL2C2_PFOR(x)	(((x) & 0x7) << 20)	/* Pixel Format */
-
-/* smartpanel related */
-#define PRSR_DATA(x)	((x) & 0xff)	/* Panel Data */
-#define PRSR_A0		(1 << 8)	/* Read Data Source */
-#define PRSR_ST_OK	(1 << 9)	/* Status OK */
-#define PRSR_CON_NT	(1 << 10)	/* Continue to Next Command */
-
-#define SMART_CMD_A0			 (0x1 << 8)
-#define SMART_CMD_READ_STATUS_REG	 (0x0 << 9)
-#define SMART_CMD_READ_FRAME_BUFFER	((0x0 << 9) | SMART_CMD_A0)
-#define SMART_CMD_WRITE_COMMAND		 (0x1 << 9)
-#define SMART_CMD_WRITE_DATA		((0x1 << 9) | SMART_CMD_A0)
-#define SMART_CMD_WRITE_FRAME		((0x2 << 9) | SMART_CMD_A0)
-#define SMART_CMD_WAIT_FOR_VSYNC	 (0x3 << 9)
-#define SMART_CMD_NOOP			 (0x4 << 9)
-#define SMART_CMD_INTERRUPT		 (0x5 << 9)
-
-#define SMART_CMD(x)	(SMART_CMD_WRITE_COMMAND | ((x) & 0xff))
-#define SMART_DAT(x)	(SMART_CMD_WRITE_DATA | ((x) & 0xff))
-
-/* SMART_DELAY() is introduced for software controlled delay primitive which
- * can be inserted between command sequences, unused command 0x6 is used here
- * and delay ranges from 0ms ~ 255ms
- */
-#define SMART_CMD_DELAY		(0x6 << 9)
-#define SMART_DELAY(ms)		(SMART_CMD_DELAY | ((ms) & 0xff))
-#endif /* __ASM_ARCH_REGS_LCD_H */
diff --git a/drivers/video/fbdev/pxa3xx-regs.h b/drivers/video/fbdev/pxa3xx-regs.h
new file mode 100644
index 000000000000..6a96610ef9b5
--- /dev/null
+++ b/drivers/video/fbdev/pxa3xx-regs.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ARCH_REGS_LCD_H
+#define __ASM_ARCH_REGS_LCD_H
+
+/*
+ * LCD Controller Registers and Bits Definitions
+ */
+#define LCCR0		(0x000)	/* LCD Controller Control Register 0 */
+#define LCCR1		(0x004)	/* LCD Controller Control Register 1 */
+#define LCCR2		(0x008)	/* LCD Controller Control Register 2 */
+#define LCCR3		(0x00C)	/* LCD Controller Control Register 3 */
+#define LCCR4		(0x010)	/* LCD Controller Control Register 4 */
+#define LCCR5		(0x014)	/* LCD Controller Control Register 5 */
+#define LCSR		(0x038)	/* LCD Controller Status Register 0 */
+#define LCSR1		(0x034)	/* LCD Controller Status Register 1 */
+#define LIIDR		(0x03C)	/* LCD Controller Interrupt ID Register */
+#define TMEDRGBR	(0x040)	/* TMED RGB Seed Register */
+#define TMEDCR		(0x044)	/* TMED Control Register */
+
+#define FBR0		(0x020)	/* DMA Channel 0 Frame Branch Register */
+#define FBR1		(0x024)	/* DMA Channel 1 Frame Branch Register */
+#define FBR2		(0x028) /* DMA Channel 2 Frame Branch Register */
+#define FBR3		(0x02C) /* DMA Channel 2 Frame Branch Register */
+#define FBR4		(0x030) /* DMA Channel 2 Frame Branch Register */
+#define FBR5		(0x110) /* DMA Channel 2 Frame Branch Register */
+#define FBR6		(0x114) /* DMA Channel 2 Frame Branch Register */
+
+#define OVL1C1		(0x050)	/* Overlay 1 Control Register 1 */
+#define OVL1C2		(0x060)	/* Overlay 1 Control Register 2 */
+#define OVL2C1		(0x070)	/* Overlay 2 Control Register 1 */
+#define OVL2C2		(0x080)	/* Overlay 2 Control Register 2 */
+
+#define CMDCR		(0x100)	/* Command Control Register */
+#define PRSR		(0x104)	/* Panel Read Status Register */
+
+#define LCCR3_BPP(x)	((((x) & 0x7) << 24) | (((x) & 0x8) ? (1 << 29) : 0))
+
+#define LCCR3_PDFOR_0	(0 << 30)
+#define LCCR3_PDFOR_1	(1 << 30)
+#define LCCR3_PDFOR_2	(2 << 30)
+#define LCCR3_PDFOR_3	(3 << 30)
+
+#define LCCR4_PAL_FOR_0	(0 << 15)
+#define LCCR4_PAL_FOR_1	(1 << 15)
+#define LCCR4_PAL_FOR_2	(2 << 15)
+#define LCCR4_PAL_FOR_3	(3 << 15)
+#define LCCR4_PAL_FOR_MASK	(3 << 15)
+
+#define FDADR0		(0x200)	/* DMA Channel 0 Frame Descriptor Address Register */
+#define FDADR1		(0x210)	/* DMA Channel 1 Frame Descriptor Address Register */
+#define FDADR2		(0x220)	/* DMA Channel 2 Frame Descriptor Address Register */
+#define FDADR3		(0x230)	/* DMA Channel 3 Frame Descriptor Address Register */
+#define FDADR4		(0x240)	/* DMA Channel 4 Frame Descriptor Address Register */
+#define FDADR5		(0x250)	/* DMA Channel 5 Frame Descriptor Address Register */
+#define FDADR6		(0x260) /* DMA Channel 6 Frame Descriptor Address Register */
+
+#define LCCR0_ENB	(1 << 0)	/* LCD Controller enable */
+#define LCCR0_CMS	(1 << 1)	/* Color/Monochrome Display Select */
+#define LCCR0_Color	(LCCR0_CMS*0)	/*  Color display */
+#define LCCR0_Mono	(LCCR0_CMS*1)	/*  Monochrome display */
+#define LCCR0_SDS	(1 << 2)	/* Single/Dual Panel Display Select */
+#define LCCR0_Sngl	(LCCR0_SDS*0)	/*  Single panel display */
+#define LCCR0_Dual	(LCCR0_SDS*1)	/*  Dual panel display */
+
+#define LCCR0_LDM	(1 << 3)	/* LCD Disable Done Mask */
+#define LCCR0_SFM	(1 << 4)	/* Start of frame mask */
+#define LCCR0_IUM	(1 << 5)	/* Input FIFO underrun mask */
+#define LCCR0_EFM	(1 << 6)	/* End of Frame mask */
+#define LCCR0_PAS	(1 << 7)	/* Passive/Active display Select */
+#define LCCR0_Pas	(LCCR0_PAS*0)	/*  Passive display (STN) */
+#define LCCR0_Act	(LCCR0_PAS*1)	/*  Active display (TFT) */
+#define LCCR0_DPD	(1 << 9)	/* Double Pixel Data (monochrome) */
+#define LCCR0_4PixMono	(LCCR0_DPD*0)	/*  4-Pixel/clock Monochrome display */
+#define LCCR0_8PixMono	(LCCR0_DPD*1)	/*  8-Pixel/clock Monochrome display */
+#define LCCR0_DIS	(1 << 10)	/* LCD Disable */
+#define LCCR0_QDM	(1 << 11)	/* LCD Quick Disable mask */
+#define LCCR0_PDD	(0xff << 12)	/* Palette DMA request delay */
+#define LCCR0_PDD_S	12
+#define LCCR0_BM	(1 << 20)	/* Branch mask */
+#define LCCR0_OUM	(1 << 21)	/* Output FIFO underrun mask */
+#define LCCR0_LCDT	(1 << 22)	/* LCD panel type */
+#define LCCR0_RDSTM	(1 << 23)	/* Read status interrupt mask */
+#define LCCR0_CMDIM	(1 << 24)	/* Command interrupt mask */
+#define LCCR0_OUC	(1 << 25)	/* Overlay Underlay control bit */
+#define LCCR0_LDDALT	(1 << 26)	/* LDD alternate mapping control */
+
+#define Fld(Size, Shft)	(((Size) << 16) + (Shft))
+#define FShft(Field)	((Field) & 0x0000FFFF)
+
+#define LCCR1_PPL	Fld (10, 0)	/* Pixels Per Line - 1 */
+#define LCCR1_DisWdth(Pixel)	(((Pixel) - 1) << FShft (LCCR1_PPL))
+
+#define LCCR1_HSW	Fld (6, 10)	/* Horizontal Synchronization */
+#define LCCR1_HorSnchWdth(Tpix)	(((Tpix) - 1) << FShft (LCCR1_HSW))
+
+#define LCCR1_ELW	Fld (8, 16)	/* End-of-Line pixel clock Wait - 1 */
+#define LCCR1_EndLnDel(Tpix)	(((Tpix) - 1) << FShft (LCCR1_ELW))
+
+#define LCCR1_BLW	Fld (8, 24)	/* Beginning-of-Line pixel clock */
+#define LCCR1_BegLnDel(Tpix)	(((Tpix) - 1) << FShft (LCCR1_BLW))
+
+#define LCCR2_LPP	Fld (10, 0)	/* Line Per Panel - 1 */
+#define LCCR2_DisHght(Line)	(((Line) - 1) << FShft (LCCR2_LPP))
+
+#define LCCR2_VSW	Fld (6, 10)	/* Vertical Synchronization pulse - 1 */
+#define LCCR2_VrtSnchWdth(Tln)	(((Tln) - 1) << FShft (LCCR2_VSW))
+
+#define LCCR2_EFW	Fld (8, 16)	/* End-of-Frame line clock Wait */
+#define LCCR2_EndFrmDel(Tln)	((Tln) << FShft (LCCR2_EFW))
+
+#define LCCR2_BFW	Fld (8, 24)	/* Beginning-of-Frame line clock */
+#define LCCR2_BegFrmDel(Tln)	((Tln) << FShft (LCCR2_BFW))
+
+#define LCCR3_API	(0xf << 16)	/* AC Bias pin trasitions per interrupt */
+#define LCCR3_API_S	16
+#define LCCR3_VSP	(1 << 20)	/* vertical sync polarity */
+#define LCCR3_HSP	(1 << 21)	/* horizontal sync polarity */
+#define LCCR3_PCP	(1 << 22)	/* Pixel Clock Polarity (L_PCLK) */
+#define LCCR3_PixRsEdg	(LCCR3_PCP*0)	/*  Pixel clock Rising-Edge */
+#define LCCR3_PixFlEdg	(LCCR3_PCP*1)	/*  Pixel clock Falling-Edge */
+
+#define LCCR3_OEP	(1 << 23)	/* Output Enable Polarity */
+#define LCCR3_OutEnH	(LCCR3_OEP*0)	/*  Output Enable active High */
+#define LCCR3_OutEnL	(LCCR3_OEP*1)	/*  Output Enable active Low */
+
+#define LCCR3_DPC	(1 << 27)	/* double pixel clock mode */
+#define LCCR3_PCD	Fld (8, 0)	/* Pixel Clock Divisor */
+#define LCCR3_PixClkDiv(Div)	(((Div) << FShft (LCCR3_PCD)))
+
+#define LCCR3_ACB	Fld (8, 8)	/* AC Bias */
+#define LCCR3_Acb(Acb)	(((Acb) << FShft (LCCR3_ACB)))
+
+#define LCCR3_HorSnchH	(LCCR3_HSP*0)	/*  HSP Active High */
+#define LCCR3_HorSnchL	(LCCR3_HSP*1)	/*  HSP Active Low */
+
+#define LCCR3_VrtSnchH	(LCCR3_VSP*0)	/*  VSP Active High */
+#define LCCR3_VrtSnchL	(LCCR3_VSP*1)	/*  VSP Active Low */
+
+#define LCCR5_IUM(x)	(1 << ((x) + 23)) /* input underrun mask */
+#define LCCR5_BSM(x)	(1 << ((x) + 15)) /* branch mask */
+#define LCCR5_EOFM(x)	(1 << ((x) + 7))  /* end of frame mask */
+#define LCCR5_SOFM(x)	(1 << ((x) + 0))  /* start of frame mask */
+
+#define LCSR_LDD	(1 << 0)	/* LCD Disable Done */
+#define LCSR_SOF	(1 << 1)	/* Start of frame */
+#define LCSR_BER	(1 << 2)	/* Bus error */
+#define LCSR_ABC	(1 << 3)	/* AC Bias count */
+#define LCSR_IUL	(1 << 4)	/* input FIFO underrun Lower panel */
+#define LCSR_IUU	(1 << 5)	/* input FIFO underrun Upper panel */
+#define LCSR_OU		(1 << 6)	/* output FIFO underrun */
+#define LCSR_QD		(1 << 7)	/* quick disable */
+#define LCSR_EOF	(1 << 8)	/* end of frame */
+#define LCSR_BS		(1 << 9)	/* branch status */
+#define LCSR_SINT	(1 << 10)	/* subsequent interrupt */
+#define LCSR_RD_ST	(1 << 11)	/* read status */
+#define LCSR_CMD_INT	(1 << 12)	/* command interrupt */
+
+#define LCSR1_IU(x)	(1 << ((x) + 23)) /* Input FIFO underrun */
+#define LCSR1_BS(x)	(1 << ((x) + 15)) /* Branch Status */
+#define LCSR1_EOF(x)	(1 << ((x) + 7))  /* End of Frame Status */
+#define LCSR1_SOF(x)	(1 << ((x) - 1))  /* Start of Frame Status */
+
+#define LDCMD_PAL	(1 << 26)	/* instructs DMA to load palette buffer */
+
+/* overlay control registers */
+#define OVLxC1_PPL(x)	((((x) - 1) & 0x3ff) << 0)	/* Pixels Per Line */
+#define OVLxC1_LPO(x)	((((x) - 1) & 0x3ff) << 10)	/* Number of Lines */
+#define OVLxC1_BPP(x)	(((x) & 0xf) << 20)	/* Bits Per Pixel */
+#define OVLxC1_OEN	(1 << 31)		/* Enable bit for Overlay */
+#define OVLxC2_XPOS(x)	(((x) & 0x3ff) << 0)	/* Horizontal Position */
+#define OVLxC2_YPOS(x)	(((x) & 0x3ff) << 10)	/* Vertical Position */
+#define OVL2C2_PFOR(x)	(((x) & 0x7) << 20)	/* Pixel Format */
+
+/* smartpanel related */
+#define PRSR_DATA(x)	((x) & 0xff)	/* Panel Data */
+#define PRSR_A0		(1 << 8)	/* Read Data Source */
+#define PRSR_ST_OK	(1 << 9)	/* Status OK */
+#define PRSR_CON_NT	(1 << 10)	/* Continue to Next Command */
+
+#endif /* __ASM_ARCH_REGS_LCD_H */
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index edf080f64a8c..ab5bc8272d8e 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -72,6 +72,7 @@
 #define DEBUG_VAR 1
 
 #include "pxafb.h"
+#include "pxa3xx-regs.h"
 
 /* Bits which should not be set in machine configuration structures */
 #define LCCR0_INVALID_CONFIG_MASK	(LCCR0_OUM | LCCR0_BM | LCCR0_QDM |\
diff --git a/include/linux/platform_data/video-pxafb.h b/include/linux/platform_data/video-pxafb.h
index b3d574778326..6333bac166a5 100644
--- a/include/linux/platform_data/video-pxafb.h
+++ b/include/linux/platform_data/video-pxafb.h
@@ -8,7 +8,6 @@
  */
 
 #include <linux/fb.h>
-#include <mach/regs-lcd.h>
 
 /*
  * Supported LCD connections
@@ -153,6 +152,27 @@ struct pxafb_mach_info {
 void pxa_set_fb_info(struct device *, struct pxafb_mach_info *);
 unsigned long pxafb_get_hsync_time(struct device *dev);
 
+/* smartpanel related */
+#define SMART_CMD_A0			 (0x1 << 8)
+#define SMART_CMD_READ_STATUS_REG	 (0x0 << 9)
+#define SMART_CMD_READ_FRAME_BUFFER	((0x0 << 9) | SMART_CMD_A0)
+#define SMART_CMD_WRITE_COMMAND		 (0x1 << 9)
+#define SMART_CMD_WRITE_DATA		((0x1 << 9) | SMART_CMD_A0)
+#define SMART_CMD_WRITE_FRAME		((0x2 << 9) | SMART_CMD_A0)
+#define SMART_CMD_WAIT_FOR_VSYNC	 (0x3 << 9)
+#define SMART_CMD_NOOP			 (0x4 << 9)
+#define SMART_CMD_INTERRUPT		 (0x5 << 9)
+
+#define SMART_CMD(x)	(SMART_CMD_WRITE_COMMAND | ((x) & 0xff))
+#define SMART_DAT(x)	(SMART_CMD_WRITE_DATA | ((x) & 0xff))
+
+/* SMART_DELAY() is introduced for software controlled delay primitive which
+ * can be inserted between command sequences, unused command 0x6 is used here
+ * and delay ranges from 0ms ~ 255ms
+ */
+#define SMART_CMD_DELAY		(0x6 << 9)
+#define SMART_DELAY(ms)		(SMART_CMD_DELAY | ((ms) & 0xff))
+
 #ifdef CONFIG_FB_PXA_SMARTPANEL
 extern int pxafb_smart_queue(struct fb_info *info, uint16_t *cmds, int);
 extern int pxafb_smart_flush(struct fb_info *info);
-- 
cgit v1.2.3


From eb38c2053b67977844404cbbdee341dbf3a02d36 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 14 Mar 2022 23:09:10 +0100
Subject: can: rx-offload: rename can_rx_offload_queue_sorted() ->
 can_rx_offload_queue_timestamp()

This patch renames the function can_rx_offload_queue_sorted() to
can_rx_offload_queue_timestamp(). This better describes what the
function does, it adds a newly RX'ed skb to the sorted queue by its
timestamp.

Link: https://lore.kernel.org/all/20220417194327.2699059-1-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/rx-offload.c               | 6 +++---
 drivers/net/can/flexcan/flexcan-core.c         | 4 ++--
 drivers/net/can/m_can/m_can.c                  | 2 +-
 drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c | 6 +++---
 drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c   | 2 +-
 drivers/net/can/ti_hecc.c                      | 4 ++--
 include/linux/can/rx-offload.h                 | 4 ++--
 7 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c
index 7f80d8e1e750..6d0dc18c03e7 100644
--- a/drivers/net/can/dev/rx-offload.c
+++ b/drivers/net/can/dev/rx-offload.c
@@ -221,7 +221,7 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload)
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_irq_offload_fifo);
 
-int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
+int can_rx_offload_queue_timestamp(struct can_rx_offload *offload,
 				struct sk_buff *skb, u32 timestamp)
 {
 	struct can_rx_offload_cb *cb;
@@ -240,7 +240,7 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(can_rx_offload_queue_sorted);
+EXPORT_SYMBOL_GPL(can_rx_offload_queue_timestamp);
 
 unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload,
 					 unsigned int idx, u32 timestamp,
@@ -256,7 +256,7 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload,
 	if (!skb)
 		return 0;
 
-	err = can_rx_offload_queue_sorted(offload, skb, timestamp);
+	err = can_rx_offload_queue_timestamp(offload, skb, timestamp);
 	if (err) {
 		stats->rx_errors++;
 		stats->tx_fifo_errors++;
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index 74d7fcbfd065..389bd9da7e9a 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -845,7 +845,7 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr)
 	if (tx_errors)
 		dev->stats.tx_errors++;
 
-	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
 	if (err)
 		dev->stats.rx_fifo_errors++;
 }
@@ -892,7 +892,7 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr)
 	if (unlikely(new_state == CAN_STATE_BUS_OFF))
 		can_bus_off(dev);
 
-	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
 	if (err)
 		dev->stats.rx_fifo_errors++;
 }
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index b3b5bc1c803b..2779bba390f2 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -464,7 +464,7 @@ static void m_can_receive_skb(struct m_can_classdev *cdev,
 		struct net_device_stats *stats = &cdev->net->stats;
 		int err;
 
-		err = can_rx_offload_queue_sorted(&cdev->offload, skb,
+		err = can_rx_offload_queue_timestamp(&cdev->offload, skb,
 						  timestamp);
 		if (err)
 			stats->rx_fifo_errors++;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index f9dd8fdba12b..230ec60003fc 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -916,7 +916,7 @@ static int mcp251xfd_handle_rxovif(struct mcp251xfd_priv *priv)
 	cf->can_id |= CAN_ERR_CRTL;
 	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
 
-	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
 	if (err)
 		stats->rx_fifo_errors++;
 
@@ -1021,7 +1021,7 @@ static int mcp251xfd_handle_ivmif(struct mcp251xfd_priv *priv)
 		return 0;
 
 	mcp251xfd_skb_set_timestamp(priv, skb, timestamp);
-	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
 	if (err)
 		stats->rx_fifo_errors++;
 
@@ -1094,7 +1094,7 @@ static int mcp251xfd_handle_cerrif(struct mcp251xfd_priv *priv)
 		cf->data[7] = bec.rxerr;
 	}
 
-	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
 	if (err)
 		stats->rx_fifo_errors++;
 
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c
index d09f7fbf2ba7..ced8d9c81f8c 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c
@@ -173,7 +173,7 @@ mcp251xfd_handle_rxif_one(struct mcp251xfd_priv *priv,
 	}
 
 	mcp251xfd_hw_rx_obj_to_skb(priv, hw_rx_obj, skb);
-	err = can_rx_offload_queue_sorted(&priv->offload, skb, hw_rx_obj->ts);
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, hw_rx_obj->ts);
 	if (err)
 		stats->rx_fifo_errors++;
 
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index ff31b993ab17..bb3f2e3b004c 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -633,7 +633,7 @@ static int ti_hecc_error(struct net_device *ndev, int int_status,
 			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
 
 		timestamp = hecc_read(priv, HECC_CANLNT);
-		err = can_rx_offload_queue_sorted(&priv->offload, skb,
+		err = can_rx_offload_queue_timestamp(&priv->offload, skb,
 						  timestamp);
 		if (err)
 			ndev->stats.rx_fifo_errors++;
@@ -668,7 +668,7 @@ static void ti_hecc_change_state(struct net_device *ndev,
 	}
 
 	timestamp = hecc_read(priv, HECC_CANLNT);
-	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
 	if (err)
 		ndev->stats.rx_fifo_errors++;
 }
diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h
index c11477620403..c205c51d79c9 100644
--- a/include/linux/can/rx-offload.h
+++ b/include/linux/can/rx-offload.h
@@ -42,8 +42,8 @@ int can_rx_offload_add_manual(struct net_device *dev,
 int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload,
 					 u64 reg);
 int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload);
-int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
-				struct sk_buff *skb, u32 timestamp);
+int can_rx_offload_queue_timestamp(struct can_rx_offload *offload,
+				   struct sk_buff *skb, u32 timestamp);
 unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload,
 					 unsigned int idx, u32 timestamp,
 					 unsigned int *frame_len_ptr);
-- 
cgit v1.2.3


From 055eb95533273bc334794dbc598400d10800528f Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 14 Apr 2022 09:12:33 -0700
Subject: bpf: Move rcu lock management out of BPF_PROG_RUN routines

Commit 7d08c2c91171 ("bpf: Refactor BPF_PROG_RUN_ARRAY family of macros
into functions") switched a bunch of BPF_PROG_RUN macros to inline
routines. This changed the semantic a bit. Due to arguments expansion
of macros, it used to be:

	rcu_read_lock();
	array = rcu_dereference(cgrp->bpf.effective[atype]);
	...

Now, with with inline routines, we have:
	array_rcu = rcu_dereference(cgrp->bpf.effective[atype]);
	/* array_rcu can be kfree'd here */
	rcu_read_lock();
	array = rcu_dereference(array_rcu);

I'm assuming in practice rcu subsystem isn't fast enough to trigger
this but let's use rcu API properly.

Also, rename to lower caps to not confuse with macros. Additionally,
drop and expand BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY.

See [1] for more context.

  [1] https://lore.kernel.org/bpf/CAKH8qBs60fOinFdxiiQikK_q0EcVxGvNTQoWvHLEUGbgcj1UYg@mail.gmail.com/T/#u

v2
- keep rcu locks inside by passing cgroup_bpf

Fixes: 7d08c2c91171 ("bpf: Refactor BPF_PROG_RUN_ARRAY family of macros into functions")
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20220414161233.170780-1-sdf@google.com
---
 drivers/media/rc/bpf-lirc.c |   8 ++-
 include/linux/bpf.h         | 115 +++-------------------------------------
 kernel/bpf/cgroup.c         | 124 ++++++++++++++++++++++++++++++++++++++------
 kernel/trace/bpf_trace.c    |   5 +-
 4 files changed, 124 insertions(+), 128 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index 3eff08d7b8e5..fe17c7f98e81 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -216,8 +216,12 @@ void lirc_bpf_run(struct rc_dev *rcdev, u32 sample)
 
 	raw->bpf_sample = sample;
 
-	if (raw->progs)
-		BPF_PROG_RUN_ARRAY(raw->progs, &raw->bpf_sample, bpf_prog_run);
+	if (raw->progs) {
+		rcu_read_lock();
+		bpf_prog_run_array(rcu_dereference(raw->progs),
+				   &raw->bpf_sample, bpf_prog_run);
+		rcu_read_unlock();
+	}
 }
 
 /*
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bdb5298735ce..7bf441563ffc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1221,7 +1221,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 /* an array of programs to be executed under rcu_lock.
  *
  * Typical usage:
- * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run);
+ * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run);
  *
  * the structure returned by bpf_prog_array_alloc() should be populated
  * with program pointers and the last pointer must be NULL.
@@ -1315,83 +1315,22 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx)
 
 typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx);
 
-static __always_inline int
-BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu,
-			    const void *ctx, bpf_prog_run_fn run_prog,
-			    int retval, u32 *ret_flags)
-{
-	const struct bpf_prog_array_item *item;
-	const struct bpf_prog *prog;
-	const struct bpf_prog_array *array;
-	struct bpf_run_ctx *old_run_ctx;
-	struct bpf_cg_run_ctx run_ctx;
-	u32 func_ret;
-
-	run_ctx.retval = retval;
-	migrate_disable();
-	rcu_read_lock();
-	array = rcu_dereference(array_rcu);
-	item = &array->items[0];
-	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
-	while ((prog = READ_ONCE(item->prog))) {
-		run_ctx.prog_item = item;
-		func_ret = run_prog(prog, ctx);
-		if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval))
-			run_ctx.retval = -EPERM;
-		*(ret_flags) |= (func_ret >> 1);
-		item++;
-	}
-	bpf_reset_run_ctx(old_run_ctx);
-	rcu_read_unlock();
-	migrate_enable();
-	return run_ctx.retval;
-}
-
-static __always_inline int
-BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu,
-		      const void *ctx, bpf_prog_run_fn run_prog,
-		      int retval)
-{
-	const struct bpf_prog_array_item *item;
-	const struct bpf_prog *prog;
-	const struct bpf_prog_array *array;
-	struct bpf_run_ctx *old_run_ctx;
-	struct bpf_cg_run_ctx run_ctx;
-
-	run_ctx.retval = retval;
-	migrate_disable();
-	rcu_read_lock();
-	array = rcu_dereference(array_rcu);
-	item = &array->items[0];
-	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
-	while ((prog = READ_ONCE(item->prog))) {
-		run_ctx.prog_item = item;
-		if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval))
-			run_ctx.retval = -EPERM;
-		item++;
-	}
-	bpf_reset_run_ctx(old_run_ctx);
-	rcu_read_unlock();
-	migrate_enable();
-	return run_ctx.retval;
-}
-
 static __always_inline u32
-BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu,
+bpf_prog_run_array(const struct bpf_prog_array *array,
 		   const void *ctx, bpf_prog_run_fn run_prog)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
-	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_trace_run_ctx run_ctx;
 	u32 ret = 1;
 
-	migrate_disable();
-	rcu_read_lock();
-	array = rcu_dereference(array_rcu);
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held");
+
 	if (unlikely(!array))
-		goto out;
+		return ret;
+
+	migrate_disable();
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	item = &array->items[0];
 	while ((prog = READ_ONCE(item->prog))) {
@@ -1400,50 +1339,10 @@ BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu,
 		item++;
 	}
 	bpf_reset_run_ctx(old_run_ctx);
-out:
-	rcu_read_unlock();
 	migrate_enable();
 	return ret;
 }
 
-/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs
- * so BPF programs can request cwr for TCP packets.
- *
- * Current cgroup skb programs can only return 0 or 1 (0 to drop the
- * packet. This macro changes the behavior so the low order bit
- * indicates whether the packet should be dropped (0) or not (1)
- * and the next bit is a congestion notification bit. This could be
- * used by TCP to call tcp_enter_cwr()
- *
- * Hence, new allowed return values of CGROUP EGRESS BPF programs are:
- *   0: drop packet
- *   1: keep packet
- *   2: drop packet and cn
- *   3: keep packet and cn
- *
- * This macro then converts it to one of the NET_XMIT or an error
- * code that is then interpreted as drop packet (and no cn):
- *   0: NET_XMIT_SUCCESS  skb should be transmitted
- *   1: NET_XMIT_DROP     skb should be dropped and cn
- *   2: NET_XMIT_CN       skb should be transmitted and cn
- *   3: -err              skb should be dropped
- */
-#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func)		\
-	({						\
-		u32 _flags = 0;				\
-		bool _cn;				\
-		u32 _ret;				\
-		_ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \
-		_cn = _flags & BPF_RET_SET_CN;		\
-		if (_ret && !IS_ERR_VALUE((long)_ret))	\
-			_ret = -EFAULT;			\
-		if (!_ret)				\
-			_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);	\
-		else					\
-			_ret = (_cn ? NET_XMIT_DROP : _ret);		\
-		_ret;					\
-	})
-
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 extern struct mutex bpf_stats_enabled_mutex;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 128028efda64..0cb6211fcb58 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -22,6 +22,72 @@
 DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE);
 EXPORT_SYMBOL(cgroup_bpf_enabled_key);
 
+/* __always_inline is necessary to prevent indirect call through run_prog
+ * function pointer.
+ */
+static __always_inline int
+bpf_prog_run_array_cg_flags(const struct cgroup_bpf *cgrp,
+			    enum cgroup_bpf_attach_type atype,
+			    const void *ctx, bpf_prog_run_fn run_prog,
+			    int retval, u32 *ret_flags)
+{
+	const struct bpf_prog_array_item *item;
+	const struct bpf_prog *prog;
+	const struct bpf_prog_array *array;
+	struct bpf_run_ctx *old_run_ctx;
+	struct bpf_cg_run_ctx run_ctx;
+	u32 func_ret;
+
+	run_ctx.retval = retval;
+	migrate_disable();
+	rcu_read_lock();
+	array = rcu_dereference(cgrp->effective[atype]);
+	item = &array->items[0];
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	while ((prog = READ_ONCE(item->prog))) {
+		run_ctx.prog_item = item;
+		func_ret = run_prog(prog, ctx);
+		if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval))
+			run_ctx.retval = -EPERM;
+		*(ret_flags) |= (func_ret >> 1);
+		item++;
+	}
+	bpf_reset_run_ctx(old_run_ctx);
+	rcu_read_unlock();
+	migrate_enable();
+	return run_ctx.retval;
+}
+
+static __always_inline int
+bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp,
+		      enum cgroup_bpf_attach_type atype,
+		      const void *ctx, bpf_prog_run_fn run_prog,
+		      int retval)
+{
+	const struct bpf_prog_array_item *item;
+	const struct bpf_prog *prog;
+	const struct bpf_prog_array *array;
+	struct bpf_run_ctx *old_run_ctx;
+	struct bpf_cg_run_ctx run_ctx;
+
+	run_ctx.retval = retval;
+	migrate_disable();
+	rcu_read_lock();
+	array = rcu_dereference(cgrp->effective[atype]);
+	item = &array->items[0];
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	while ((prog = READ_ONCE(item->prog))) {
+		run_ctx.prog_item = item;
+		if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval))
+			run_ctx.retval = -EPERM;
+		item++;
+	}
+	bpf_reset_run_ctx(old_run_ctx);
+	rcu_read_unlock();
+	migrate_enable();
+	return run_ctx.retval;
+}
+
 void cgroup_bpf_offline(struct cgroup *cgrp)
 {
 	cgroup_get(cgrp);
@@ -1075,11 +1141,38 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	bpf_compute_and_save_data_end(skb, &saved_data_end);
 
 	if (atype == CGROUP_INET_EGRESS) {
-		ret = BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(
-			cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb);
+		u32 flags = 0;
+		bool cn;
+
+		ret = bpf_prog_run_array_cg_flags(
+			&cgrp->bpf, atype,
+			skb, __bpf_prog_run_save_cb, 0, &flags);
+
+		/* Return values of CGROUP EGRESS BPF programs are:
+		 *   0: drop packet
+		 *   1: keep packet
+		 *   2: drop packet and cn
+		 *   3: keep packet and cn
+		 *
+		 * The returned value is then converted to one of the NET_XMIT
+		 * or an error code that is then interpreted as drop packet
+		 * (and no cn):
+		 *   0: NET_XMIT_SUCCESS  skb should be transmitted
+		 *   1: NET_XMIT_DROP     skb should be dropped and cn
+		 *   2: NET_XMIT_CN       skb should be transmitted and cn
+		 *   3: -err              skb should be dropped
+		 */
+
+		cn = flags & BPF_RET_SET_CN;
+		if (ret && !IS_ERR_VALUE((long)ret))
+			ret = -EFAULT;
+		if (!ret)
+			ret = (cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);
+		else
+			ret = (cn ? NET_XMIT_DROP : ret);
 	} else {
-		ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb,
-					    __bpf_prog_run_save_cb, 0);
+		ret = bpf_prog_run_array_cg(&cgrp->bpf, atype,
+					    skb, __bpf_prog_run_save_cb, 0);
 		if (ret && !IS_ERR_VALUE((long)ret))
 			ret = -EFAULT;
 	}
@@ -1109,8 +1202,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 
-	return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk,
-				     bpf_prog_run, 0);
+	return bpf_prog_run_array_cg(&cgrp->bpf, atype, sk, bpf_prog_run, 0);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
 
@@ -1155,8 +1247,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 	}
 
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	return BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx,
-					   bpf_prog_run, 0, flags);
+	return bpf_prog_run_array_cg_flags(&cgrp->bpf, atype,
+					   &ctx, bpf_prog_run, 0, flags);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
 
@@ -1182,8 +1274,8 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 
-	return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops,
-				     bpf_prog_run, 0);
+	return bpf_prog_run_array_cg(&cgrp->bpf, atype, sock_ops, bpf_prog_run,
+				     0);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
 
@@ -1200,8 +1292,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
-	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx,
-				    bpf_prog_run, 0);
+	ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0);
 	rcu_read_unlock();
 
 	return ret;
@@ -1366,8 +1457,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
-	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx,
-				    bpf_prog_run, 0);
+	ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0);
 	rcu_read_unlock();
 
 	kfree(ctx.cur_val);
@@ -1459,7 +1549,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	}
 
 	lock_sock(sk);
-	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_SETSOCKOPT],
+	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_SETSOCKOPT,
 				    &ctx, bpf_prog_run, 0);
 	release_sock(sk);
 
@@ -1559,7 +1649,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	}
 
 	lock_sock(sk);
-	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT],
+	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT,
 				    &ctx, bpf_prog_run, retval);
 	release_sock(sk);
 
@@ -1608,7 +1698,7 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
 	 * be called if that data shouldn't be "exported".
 	 */
 
-	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT],
+	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT,
 				    &ctx, bpf_prog_run, retval);
 	if (ret < 0)
 		return ret;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b26f3da943de..f15b826f9899 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -129,7 +129,10 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 	 * out of events when it was updated in between this and the
 	 * rcu_dereference() which is accepted risk.
 	 */
-	ret = BPF_PROG_RUN_ARRAY(call->prog_array, ctx, bpf_prog_run);
+	rcu_read_lock();
+	ret = bpf_prog_run_array(rcu_dereference(call->prog_array),
+				 ctx, bpf_prog_run);
+	rcu_read_unlock();
 
  out:
 	__this_cpu_dec(bpf_prog_active);
-- 
cgit v1.2.3


From b83deaa741558babf4b8d51d34f6637ccfff1b26 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 28 May 2020 22:57:40 +0200
Subject: ARM: pxa: move pcmcia board data into mach-pxa

The drivers/pcmcia/pxa2xx_*.c are essentially part of the
board files, but for historic reasons located in drivers/pcmcia.

Move them into the same place as the actual board file to avoid
lots of machine header inclusions.

Cc: Marek Vasut <marek.vasut@gmail.com>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Jonathan Cameron <jic23@cam.ac.uk>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/Makefile                        |  18 +-
 arch/arm/mach-pxa/balloon3-pcmcia.c               | 137 +++++++++++++++
 arch/arm/mach-pxa/balloon3.c                      |   2 +-
 arch/arm/mach-pxa/balloon3.h                      | 181 ++++++++++++++++++++
 arch/arm/mach-pxa/colibri-pcmcia.c                | 165 ++++++++++++++++++
 arch/arm/mach-pxa/e740-pcmcia.c                   | 127 ++++++++++++++
 arch/arm/mach-pxa/hx4700-pcmcia.c                 | 118 +++++++++++++
 arch/arm/mach-pxa/include/mach/balloon3.h         | 181 --------------------
 arch/arm/mach-pxa/include/mach/palmtc.h           |  84 ---------
 arch/arm/mach-pxa/include/mach/palmtx.h           | 110 ------------
 arch/arm/mach-pxa/include/mach/trizeps4.h         | 166 ------------------
 arch/arm/mach-pxa/include/mach/vpac270.h          |  38 ----
 arch/arm/mach-pxa/palmld-pcmcia.c                 | 110 ++++++++++++
 arch/arm/mach-pxa/palmtc-pcmcia.c                 | 162 ++++++++++++++++++
 arch/arm/mach-pxa/palmtc.c                        |   2 +-
 arch/arm/mach-pxa/palmtc.h                        |  84 +++++++++
 arch/arm/mach-pxa/palmtx-pcmcia.c                 | 111 ++++++++++++
 arch/arm/mach-pxa/palmtx.c                        |   2 +-
 arch/arm/mach-pxa/palmtx.h                        | 110 ++++++++++++
 arch/arm/mach-pxa/trizeps4-pcmcia.c               | 200 ++++++++++++++++++++++
 arch/arm/mach-pxa/trizeps4.c                      |   2 +-
 arch/arm/mach-pxa/trizeps4.h                      | 166 ++++++++++++++++++
 arch/arm/mach-pxa/viper-pcmcia.c                  | 180 +++++++++++++++++++
 arch/arm/mach-pxa/viper-pcmcia.h                  |  12 ++
 arch/arm/mach-pxa/viper.c                         |   2 +-
 arch/arm/mach-pxa/vpac270-pcmcia.c                | 137 +++++++++++++++
 arch/arm/mach-pxa/vpac270.c                       |   2 +-
 arch/arm/mach-pxa/vpac270.h                       |  38 ++++
 arch/arm/mach-pxa/zeus.c                          |   2 +-
 drivers/pcmcia/Makefile                           |  13 --
 drivers/pcmcia/pxa2xx_balloon3.c                  | 137 ---------------
 drivers/pcmcia/pxa2xx_colibri.c                   | 165 ------------------
 drivers/pcmcia/pxa2xx_e740.c                      | 127 --------------
 drivers/pcmcia/pxa2xx_hx4700.c                    | 118 -------------
 drivers/pcmcia/pxa2xx_palmld.c                    | 110 ------------
 drivers/pcmcia/pxa2xx_palmtc.c                    | 162 ------------------
 drivers/pcmcia/pxa2xx_palmtx.c                    | 111 ------------
 drivers/pcmcia/pxa2xx_sharpsl.c                   |   2 +-
 drivers/pcmcia/pxa2xx_trizeps4.c                  | 200 ----------------------
 drivers/pcmcia/pxa2xx_viper.c                     | 182 --------------------
 drivers/pcmcia/pxa2xx_vpac270.c                   | 137 ---------------
 drivers/pcmcia/soc_common.h                       | 120 +------------
 include/linux/platform_data/pcmcia-pxa2xx_viper.h |  12 --
 include/pcmcia/soc_common.h                       | 125 ++++++++++++++
 44 files changed, 2183 insertions(+), 2187 deletions(-)
 create mode 100644 arch/arm/mach-pxa/balloon3-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/balloon3.h
 create mode 100644 arch/arm/mach-pxa/colibri-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/e740-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/hx4700-pcmcia.c
 delete mode 100644 arch/arm/mach-pxa/include/mach/balloon3.h
 delete mode 100644 arch/arm/mach-pxa/include/mach/palmtc.h
 delete mode 100644 arch/arm/mach-pxa/include/mach/palmtx.h
 delete mode 100644 arch/arm/mach-pxa/include/mach/trizeps4.h
 delete mode 100644 arch/arm/mach-pxa/include/mach/vpac270.h
 create mode 100644 arch/arm/mach-pxa/palmld-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/palmtc-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/palmtc.h
 create mode 100644 arch/arm/mach-pxa/palmtx-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/palmtx.h
 create mode 100644 arch/arm/mach-pxa/trizeps4-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/trizeps4.h
 create mode 100644 arch/arm/mach-pxa/viper-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/viper-pcmcia.h
 create mode 100644 arch/arm/mach-pxa/vpac270-pcmcia.c
 create mode 100644 arch/arm/mach-pxa/vpac270.h
 delete mode 100644 drivers/pcmcia/pxa2xx_balloon3.c
 delete mode 100644 drivers/pcmcia/pxa2xx_colibri.c
 delete mode 100644 drivers/pcmcia/pxa2xx_e740.c
 delete mode 100644 drivers/pcmcia/pxa2xx_hx4700.c
 delete mode 100644 drivers/pcmcia/pxa2xx_palmld.c
 delete mode 100644 drivers/pcmcia/pxa2xx_palmtc.c
 delete mode 100644 drivers/pcmcia/pxa2xx_palmtx.c
 delete mode 100644 drivers/pcmcia/pxa2xx_trizeps4.c
 delete mode 100644 drivers/pcmcia/pxa2xx_viper.c
 delete mode 100644 drivers/pcmcia/pxa2xx_vpac270.c
 delete mode 100644 include/linux/platform_data/pcmcia-pxa2xx_viper.h
 create mode 100644 include/pcmcia/soc_common.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile
index 68730ceb8b7c..0aec36e67dc1 100644
--- a/arch/arm/mach-pxa/Makefile
+++ b/arch/arm/mach-pxa/Makefile
@@ -37,7 +37,8 @@ obj-$(CONFIG_MACH_SAAR)		+= saar.o
 obj-$(CONFIG_ARCH_PXA_IDP)	+= idp.o
 obj-$(CONFIG_ARCH_VIPER)	+= viper.o
 obj-$(CONFIG_MACH_ARCOM_ZEUS)	+= zeus.o
-obj-$(CONFIG_MACH_BALLOON3)	+= balloon3.o
+obj-$(CONFIG_ARCOM_PCMCIA)	+= viper-pcmcia.o
+obj-$(CONFIG_MACH_BALLOON3)	+= balloon3.o balloon3-pcmcia.o
 obj-$(CONFIG_MACH_CSB726)	+= csb726.o
 obj-$(CONFIG_CSB726_CSB701)	+= csb701.o
 obj-$(CONFIG_MACH_CM_X300)      += cm-x300.o
@@ -47,18 +48,20 @@ obj-$(CONFIG_GUMSTIX_AM200EPD)	+= am200epd.o
 obj-$(CONFIG_GUMSTIX_AM300EPD)	+= am300epd.o
 obj-$(CONFIG_MACH_XCEP)         += xcep.o
 obj-$(CONFIG_MACH_TRIZEPS4)	+= trizeps4.o
+obj-$(CONFIG_TRIZEPS_PCMCIA)	+= trizeps4-pcmcia.o
 obj-$(CONFIG_MACH_LOGICPD_PXA270)	+= lpd270.o
 obj-$(CONFIG_MACH_PCM027)		+= pcm027.o
 obj-$(CONFIG_MACH_PCM990_BASEBOARD)	+= pcm990-baseboard.o
-obj-$(CONFIG_MACH_COLIBRI)			+= colibri-pxa270.o
+obj-$(CONFIG_MACH_COLIBRI)		+= colibri-pxa270.o colibri-pcmcia.o
 obj-$(CONFIG_MACH_COLIBRI_EVALBOARD)	+= colibri-evalboard.o
 obj-$(CONFIG_MACH_COLIBRI_PXA270_INCOME)	+= colibri-pxa270-income.o
 obj-$(CONFIG_MACH_COLIBRI300)	+= colibri-pxa3xx.o colibri-pxa300.o
-obj-$(CONFIG_MACH_COLIBRI320)	+= colibri-pxa3xx.o colibri-pxa320.o
-obj-$(CONFIG_MACH_VPAC270)	+= vpac270.o
+obj-$(CONFIG_MACH_COLIBRI320)	+= colibri-pxa3xx.o colibri-pxa320.o colibri-pcmcia.o
+obj-$(CONFIG_MACH_VPAC270)	+= vpac270.o vpac270-pcmcia.o
 
 # End-user Products
 obj-$(CONFIG_MACH_H4700)	+= hx4700.o
+obj-$(CONFIG_MACH_H4700)	+= hx4700-pcmcia.o
 obj-$(CONFIG_MACH_H5000)	+= h5000.o
 obj-$(CONFIG_MACH_HIMALAYA)	+= himalaya.o
 obj-$(CONFIG_MACH_MAGICIAN)	+= magician.o
@@ -66,12 +69,12 @@ obj-$(CONFIG_MACH_MIOA701)	+= mioa701.o mioa701_bootresume.o
 obj-$(CONFIG_PXA_EZX)           += ezx.o
 obj-$(CONFIG_MACH_MP900C)	+= mp900.o
 obj-$(CONFIG_MACH_PALMTE2)	+= palmte2.o
-obj-$(CONFIG_MACH_PALMTC)	+= palmtc.o
+obj-$(CONFIG_MACH_PALMTC)	+= palmtc.o palmtc-pcmcia.o
 obj-$(CONFIG_MACH_PALM27X)	+= palm27x.o
 obj-$(CONFIG_MACH_PALMT5)	+= palmt5.o
-obj-$(CONFIG_MACH_PALMTX)	+= palmtx.o
+obj-$(CONFIG_MACH_PALMTX)	+= palmtx.o palmtx-pcmcia.o
 obj-$(CONFIG_MACH_PALMZ72)	+= palmz72.o
-obj-$(CONFIG_MACH_PALMLD)	+= palmld.o
+obj-$(CONFIG_MACH_PALMLD)	+= palmld.o palmld-pcmcia.o
 obj-$(CONFIG_PALM_TREO)		+= palmtreo.o
 obj-$(CONFIG_PXA_SHARP_C7xx)	+= corgi.o sharpsl_pm.o corgi_pm.o
 obj-$(CONFIG_PXA_SHARP_Cxx00)	+= spitz.o sharpsl_pm.o spitz_pm.o
@@ -79,6 +82,7 @@ obj-$(CONFIG_MACH_POODLE)	+= poodle.o
 obj-$(CONFIG_MACH_TOSA)		+= tosa.o
 obj-$(CONFIG_MACH_ICONTROL)     += icontrol.o mxm8x10.o
 obj-$(CONFIG_ARCH_PXA_ESERIES)	+= eseries.o
+obj-$(CONFIG_MACH_E740)		+= e740-pcmcia.o
 obj-$(CONFIG_MACH_ZIPIT2)	+= z2.o
 
 obj-$(CONFIG_PXA_SYSTEMS_CPLDS)	+= pxa_cplds_irqs.o
diff --git a/arch/arm/mach-pxa/balloon3-pcmcia.c b/arch/arm/mach-pxa/balloon3-pcmcia.c
new file mode 100644
index 000000000000..6a27b76cc603
--- /dev/null
+++ b/arch/arm/mach-pxa/balloon3-pcmcia.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/drivers/pcmcia/pxa2xx_balloon3.c
+ *
+ * Balloon3 PCMCIA specific routines.
+ *
+ *  Author:	Nick Bane
+ *  Created:	June, 2006
+ *  Copyright:	Toby Churchill Ltd
+ *  Derived from pxa2xx_mainstone.c, by Nico Pitre
+ *
+ * Various modification by Marek Vasut <marek.vasut@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/gpio.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+
+#include "balloon3.h"
+
+#include <asm/mach-types.h>
+
+#include <pcmcia/soc_common.h>
+
+static int balloon3_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	uint16_t ver;
+
+	ver = __raw_readw(BALLOON3_FPGA_VER);
+	if (ver < 0x4f08)
+		pr_warn("The FPGA code, version 0x%04x, is too old. "
+			"PCMCIA/CF support might be broken in this version!",
+			ver);
+
+	skt->socket.pci_irq = BALLOON3_BP_CF_NRDY_IRQ;
+	skt->stat[SOC_STAT_CD].gpio = BALLOON3_GPIO_S0_CD;
+	skt->stat[SOC_STAT_CD].name = "PCMCIA0 CD";
+	skt->stat[SOC_STAT_BVD1].irq = BALLOON3_BP_NSTSCHG_IRQ;
+	skt->stat[SOC_STAT_BVD1].name = "PCMCIA0 STSCHG";
+
+	return 0;
+}
+
+static unsigned long balloon3_pcmcia_status[2] = {
+	BALLOON3_CF_nSTSCHG_BVD1,
+	BALLOON3_CF_nSTSCHG_BVD1
+};
+
+static void balloon3_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+				    struct pcmcia_state *state)
+{
+	uint16_t status;
+	int flip;
+
+	/* This actually reads the STATUS register */
+	status = __raw_readw(BALLOON3_CF_STATUS_REG);
+	flip = (status ^ balloon3_pcmcia_status[skt->nr])
+		& BALLOON3_CF_nSTSCHG_BVD1;
+	/*
+	 * Workaround for STSCHG which can't be deasserted:
+	 * We therefore disable/enable corresponding IRQs
+	 * as needed to avoid IRQ locks.
+	 */
+	if (flip) {
+		balloon3_pcmcia_status[skt->nr] = status;
+		if (status & BALLOON3_CF_nSTSCHG_BVD1)
+			enable_irq(BALLOON3_BP_NSTSCHG_IRQ);
+		else
+			disable_irq(BALLOON3_BP_NSTSCHG_IRQ);
+	}
+
+	state->ready	= !!(status & BALLOON3_CF_nIRQ);
+	state->bvd1	= !!(status & BALLOON3_CF_nSTSCHG_BVD1);
+	state->bvd2	= 0;	/* not available */
+	state->vs_3v	= 1;	/* Always true its a CF card */
+	state->vs_Xv	= 0;	/* not available */
+}
+
+static int balloon3_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+				       const socket_state_t *state)
+{
+	__raw_writew(BALLOON3_CF_RESET, BALLOON3_CF_CONTROL_REG +
+			((state->flags & SS_RESET) ?
+			BALLOON3_FPGA_SETnCLR : 0));
+	return 0;
+}
+
+static struct pcmcia_low_level balloon3_pcmcia_ops = {
+	.owner			= THIS_MODULE,
+	.hw_init		= balloon3_pcmcia_hw_init,
+	.socket_state		= balloon3_pcmcia_socket_state,
+	.configure_socket	= balloon3_pcmcia_configure_socket,
+	.first			= 0,
+	.nr			= 1,
+};
+
+static struct platform_device *balloon3_pcmcia_device;
+
+static int __init balloon3_pcmcia_init(void)
+{
+	int ret;
+
+	if (!machine_is_balloon3())
+		return -ENODEV;
+
+	balloon3_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!balloon3_pcmcia_device)
+		return -ENOMEM;
+
+	ret = platform_device_add_data(balloon3_pcmcia_device,
+			&balloon3_pcmcia_ops, sizeof(balloon3_pcmcia_ops));
+
+	if (!ret)
+		ret = platform_device_add(balloon3_pcmcia_device);
+
+	if (ret)
+		platform_device_put(balloon3_pcmcia_device);
+
+	return ret;
+}
+
+static void __exit balloon3_pcmcia_exit(void)
+{
+	platform_device_unregister(balloon3_pcmcia_device);
+}
+
+module_init(balloon3_pcmcia_init);
+module_exit(balloon3_pcmcia_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nick Bane <nick@cecomputing.co.uk>");
+MODULE_ALIAS("platform:pxa2xx-pcmcia");
+MODULE_DESCRIPTION("Balloon3 board CF/PCMCIA driver");
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index 82f9299f67d3..896d47d9a8dc 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -40,7 +40,7 @@
 #include <asm/mach/flash.h>
 
 #include "pxa27x.h"
-#include <mach/balloon3.h>
+#include "balloon3.h"
 #include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
diff --git a/arch/arm/mach-pxa/balloon3.h b/arch/arm/mach-pxa/balloon3.h
new file mode 100644
index 000000000000..f351358c0e5b
--- /dev/null
+++ b/arch/arm/mach-pxa/balloon3.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/include/asm-arm/arch-pxa/balloon3.h
+ *
+ *  Authors:	Nick Bane and Wookey
+ *  Created:	Oct, 2005
+ *  Copyright:	Toby Churchill Ltd
+ *  Cribbed from mainstone.c, by Nicholas Pitre
+ */
+
+#ifndef ASM_ARCH_BALLOON3_H
+#define ASM_ARCH_BALLOON3_H
+
+#include <mach/irqs.h> /* PXA_NR_BUILTIN_GPIO */
+
+enum balloon3_features {
+	BALLOON3_FEATURE_OHCI,
+	BALLOON3_FEATURE_MMC,
+	BALLOON3_FEATURE_CF,
+	BALLOON3_FEATURE_AUDIO,
+	BALLOON3_FEATURE_TOPPOLY,
+};
+
+#define BALLOON3_FPGA_PHYS	PXA_CS4_PHYS
+#define BALLOON3_FPGA_VIRT	IOMEM(0xf1000000)	/* as per balloon2 */
+#define BALLOON3_FPGA_LENGTH	0x01000000
+
+#define	BALLOON3_FPGA_SETnCLR		(0x1000)
+
+/* FPGA / CPLD registers for CF socket */
+#define	BALLOON3_CF_STATUS_REG		(BALLOON3_FPGA_VIRT + 0x00e00008)
+#define	BALLOON3_CF_CONTROL_REG		(BALLOON3_FPGA_VIRT + 0x00e00008)
+/* FPGA / CPLD version register */
+#define	BALLOON3_FPGA_VER		(BALLOON3_FPGA_VIRT + 0x00e0001c)
+/* FPGA / CPLD registers for NAND flash */
+#define	BALLOON3_NAND_BASE		(PXA_CS4_PHYS + 0x00e00000)
+#define	BALLOON3_NAND_IO_REG		(BALLOON3_FPGA_VIRT + 0x00e00000)
+#define	BALLOON3_NAND_CONTROL2_REG	(BALLOON3_FPGA_VIRT + 0x00e00010)
+#define	BALLOON3_NAND_STAT_REG		(BALLOON3_FPGA_VIRT + 0x00e00014)
+#define	BALLOON3_NAND_CONTROL_REG	(BALLOON3_FPGA_VIRT + 0x00e00014)
+
+/* fpga/cpld interrupt control register */
+#define BALLOON3_INT_CONTROL_REG	(BALLOON3_FPGA_VIRT + 0x00e0000C)
+#define BALLOON3_VERSION_REG		(BALLOON3_FPGA_VIRT + 0x00e0001c)
+
+#define BALLOON3_SAMOSA_ADDR_REG	(BALLOON3_FPGA_VIRT + 0x00c00000)
+#define BALLOON3_SAMOSA_DATA_REG	(BALLOON3_FPGA_VIRT + 0x00c00004)
+#define BALLOON3_SAMOSA_STATUS_REG	(BALLOON3_FPGA_VIRT + 0x00c0001c)
+
+/* CF Status Register bits (read-only) bits */
+#define BALLOON3_CF_nIRQ		(1 << 0)
+#define BALLOON3_CF_nSTSCHG_BVD1	(1 << 1)
+
+/* CF Control Set Register bits / CF Control Clear Register bits (write-only) */
+#define BALLOON3_CF_RESET		(1 << 0)
+#define BALLOON3_CF_ENABLE		(1 << 1)
+#define BALLOON3_CF_ADD_ENABLE		(1 << 2)
+
+/* CF Interrupt sources */
+#define BALLOON3_BP_CF_NRDY_IRQ		BALLOON3_IRQ(0)
+#define BALLOON3_BP_NSTSCHG_IRQ		BALLOON3_IRQ(1)
+
+/* NAND Control register */
+#define	BALLOON3_NAND_CONTROL_FLWP	(1 << 7)
+#define	BALLOON3_NAND_CONTROL_FLSE	(1 << 6)
+#define	BALLOON3_NAND_CONTROL_FLCE3	(1 << 5)
+#define	BALLOON3_NAND_CONTROL_FLCE2	(1 << 4)
+#define	BALLOON3_NAND_CONTROL_FLCE1	(1 << 3)
+#define	BALLOON3_NAND_CONTROL_FLCE0	(1 << 2)
+#define	BALLOON3_NAND_CONTROL_FLALE	(1 << 1)
+#define	BALLOON3_NAND_CONTROL_FLCLE	(1 << 0)
+
+/* NAND Status register */
+#define	BALLOON3_NAND_STAT_RNB		(1 << 0)
+
+/* NAND Control2 register */
+#define	BALLOON3_NAND_CONTROL2_16BIT	(1 << 0)
+
+/* GPIOs for irqs */
+#define BALLOON3_GPIO_AUX_NIRQ		(94)
+#define BALLOON3_GPIO_CODEC_IRQ		(95)
+
+/* Timer and Idle LED locations */
+#define BALLOON3_GPIO_LED_NAND		(9)
+#define BALLOON3_GPIO_LED_IDLE		(10)
+
+/* backlight control */
+#define BALLOON3_GPIO_RUN_BACKLIGHT	(99)
+
+#define BALLOON3_GPIO_S0_CD		(105)
+
+/* NAND */
+#define BALLOON3_GPIO_RUN_NAND		(102)
+
+/* PCF8574A Leds */
+#define	BALLOON3_PCF_GPIO_BASE		160
+#define	BALLOON3_PCF_GPIO_LED0		(BALLOON3_PCF_GPIO_BASE + 0)
+#define	BALLOON3_PCF_GPIO_LED1		(BALLOON3_PCF_GPIO_BASE + 1)
+#define	BALLOON3_PCF_GPIO_LED2		(BALLOON3_PCF_GPIO_BASE + 2)
+#define	BALLOON3_PCF_GPIO_LED3		(BALLOON3_PCF_GPIO_BASE + 3)
+#define	BALLOON3_PCF_GPIO_LED4		(BALLOON3_PCF_GPIO_BASE + 4)
+#define	BALLOON3_PCF_GPIO_LED5		(BALLOON3_PCF_GPIO_BASE + 5)
+#define	BALLOON3_PCF_GPIO_LED6		(BALLOON3_PCF_GPIO_BASE + 6)
+#define	BALLOON3_PCF_GPIO_LED7		(BALLOON3_PCF_GPIO_BASE + 7)
+
+/* FPGA Interrupt Mask/Acknowledge Register */
+#define BALLOON3_INT_S0_IRQ		(1 << 0)  /* PCMCIA 0 IRQ */
+#define BALLOON3_INT_S0_STSCHG		(1 << 1)  /* PCMCIA 0 status changed */
+
+/* CPLD (and FPGA) interface definitions */
+#define CPLD_LCD0_DATA_SET             0x00
+#define CPLD_LCD0_DATA_CLR             0x10
+#define CPLD_LCD0_COMMAND_SET          0x01
+#define CPLD_LCD0_COMMAND_CLR          0x11
+#define CPLD_LCD1_DATA_SET             0x02
+#define CPLD_LCD1_DATA_CLR             0x12
+#define CPLD_LCD1_COMMAND_SET          0x03
+#define CPLD_LCD1_COMMAND_CLR          0x13
+
+#define CPLD_MISC_SET                  0x07
+#define CPLD_MISC_CLR                  0x17
+#define CPLD_MISC_LOON_NRESET_BIT      0
+#define CPLD_MISC_LOON_UNSUSP_BIT      1
+#define CPLD_MISC_RUN_5V_BIT           2
+#define CPLD_MISC_CHG_D0_BIT           3
+#define CPLD_MISC_CHG_D1_BIT           4
+#define CPLD_MISC_DAC_NCS_BIT          5
+
+#define CPLD_LCD_SET                   0x08
+#define CPLD_LCD_CLR                   0x18
+#define CPLD_LCD_BACKLIGHT_EN_0_BIT    0
+#define CPLD_LCD_BACKLIGHT_EN_1_BIT    1
+#define CPLD_LCD_LED_RED_BIT           4
+#define CPLD_LCD_LED_GREEN_BIT         5
+#define CPLD_LCD_NRESET_BIT            7
+
+#define CPLD_LCD_RO_SET                0x09
+#define CPLD_LCD_RO_CLR                0x19
+#define CPLD_LCD_RO_LCD0_nWAIT_BIT     0
+#define CPLD_LCD_RO_LCD1_nWAIT_BIT     1
+
+#define CPLD_SERIAL_SET                0x0a
+#define CPLD_SERIAL_CLR                0x1a
+#define CPLD_SERIAL_GSM_RI_BIT         0
+#define CPLD_SERIAL_GSM_CTS_BIT        1
+#define CPLD_SERIAL_GSM_DTR_BIT        2
+#define CPLD_SERIAL_LPR_CTS_BIT        3
+#define CPLD_SERIAL_TC232_CTS_BIT      4
+#define CPLD_SERIAL_TC232_DSR_BIT      5
+
+#define CPLD_SROUTING_SET              0x0b
+#define CPLD_SROUTING_CLR              0x1b
+#define CPLD_SROUTING_MSP430_LPR       0
+#define CPLD_SROUTING_MSP430_TC232     1
+#define CPLD_SROUTING_MSP430_GSM       2
+#define CPLD_SROUTING_LOON_LPR         (0 << 4)
+#define CPLD_SROUTING_LOON_TC232       (1 << 4)
+#define CPLD_SROUTING_LOON_GSM         (2 << 4)
+
+#define CPLD_AROUTING_SET              0x0c
+#define CPLD_AROUTING_CLR              0x1c
+#define CPLD_AROUTING_MIC2PHONE_BIT    0
+#define CPLD_AROUTING_PHONE2INT_BIT    1
+#define CPLD_AROUTING_PHONE2EXT_BIT    2
+#define CPLD_AROUTING_LOONL2INT_BIT    3
+#define CPLD_AROUTING_LOONL2EXT_BIT    4
+#define CPLD_AROUTING_LOONR2PHONE_BIT  5
+#define CPLD_AROUTING_LOONR2INT_BIT    6
+#define CPLD_AROUTING_LOONR2EXT_BIT    7
+
+/* Balloon3 Interrupts */
+#define BALLOON3_IRQ(x)		(IRQ_BOARD_START + (x))
+
+#define BALLOON3_AUX_NIRQ	PXA_GPIO_TO_IRQ(BALLOON3_GPIO_AUX_NIRQ)
+#define BALLOON3_CODEC_IRQ	PXA_GPIO_TO_IRQ(BALLOON3_GPIO_CODEC_IRQ)
+
+#define BALLOON3_NR_IRQS	(IRQ_BOARD_START + 16)
+
+extern int balloon3_has(enum balloon3_features feature);
+
+#endif
diff --git a/arch/arm/mach-pxa/colibri-pcmcia.c b/arch/arm/mach-pxa/colibri-pcmcia.c
new file mode 100644
index 000000000000..9da7b478e5eb
--- /dev/null
+++ b/arch/arm/mach-pxa/colibri-pcmcia.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/drivers/pcmcia/pxa2xx_colibri.c
+ *
+ * Driver for Toradex Colibri PXA270 CF socket
+ *
+ * Copyright (C) 2010 Marek Vasut <marek.vasut@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/gpio.h>
+
+#include <asm/mach-types.h>
+
+#include <pcmcia/soc_common.h>
+
+#define	COLIBRI270_RESET_GPIO	53
+#define	COLIBRI270_PPEN_GPIO	107
+#define	COLIBRI270_BVD1_GPIO	83
+#define	COLIBRI270_BVD2_GPIO	82
+#define	COLIBRI270_DETECT_GPIO	84
+#define	COLIBRI270_READY_GPIO	1
+
+#define	COLIBRI320_RESET_GPIO	77
+#define	COLIBRI320_PPEN_GPIO	57
+#define	COLIBRI320_BVD1_GPIO	53
+#define	COLIBRI320_BVD2_GPIO	79
+#define	COLIBRI320_DETECT_GPIO	81
+#define	COLIBRI320_READY_GPIO	29
+
+enum {
+	DETECT = 0,
+	READY = 1,
+	BVD1 = 2,
+	BVD2 = 3,
+	PPEN = 4,
+	RESET = 5,
+};
+
+/* Contents of this array are configured on-the-fly in init function */
+static struct gpio colibri_pcmcia_gpios[] = {
+	{ 0,	GPIOF_IN,	"PCMCIA Detect" },
+	{ 0,	GPIOF_IN,	"PCMCIA Ready" },
+	{ 0,	GPIOF_IN,	"PCMCIA BVD1" },
+	{ 0,	GPIOF_IN,	"PCMCIA BVD2" },
+	{ 0,	GPIOF_INIT_LOW,	"PCMCIA PPEN" },
+	{ 0,	GPIOF_INIT_HIGH,"PCMCIA Reset" },
+};
+
+static int colibri_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	int ret;
+
+	ret = gpio_request_array(colibri_pcmcia_gpios,
+				ARRAY_SIZE(colibri_pcmcia_gpios));
+	if (ret)
+		goto err1;
+
+	skt->socket.pci_irq = gpio_to_irq(colibri_pcmcia_gpios[READY].gpio);
+	skt->stat[SOC_STAT_CD].irq = gpio_to_irq(colibri_pcmcia_gpios[DETECT].gpio);
+	skt->stat[SOC_STAT_CD].name = "PCMCIA CD";
+
+err1:
+	return ret;
+}
+
+static void colibri_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
+{
+	gpio_free_array(colibri_pcmcia_gpios,
+			ARRAY_SIZE(colibri_pcmcia_gpios));
+}
+
+static void colibri_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+					struct pcmcia_state *state)
+{
+
+	state->detect = !!gpio_get_value(colibri_pcmcia_gpios[DETECT].gpio);
+	state->ready  = !!gpio_get_value(colibri_pcmcia_gpios[READY].gpio);
+	state->bvd1   = !!gpio_get_value(colibri_pcmcia_gpios[BVD1].gpio);
+	state->bvd2   = !!gpio_get_value(colibri_pcmcia_gpios[BVD2].gpio);
+	state->vs_3v  = 1;
+	state->vs_Xv  = 0;
+}
+
+static int
+colibri_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+				const socket_state_t *state)
+{
+	gpio_set_value(colibri_pcmcia_gpios[PPEN].gpio,
+			!(state->Vcc == 33 && state->Vpp < 50));
+	gpio_set_value(colibri_pcmcia_gpios[RESET].gpio,
+			state->flags & SS_RESET);
+	return 0;
+}
+
+static struct pcmcia_low_level colibri_pcmcia_ops = {
+	.owner			= THIS_MODULE,
+
+	.first			= 0,
+	.nr			= 1,
+
+	.hw_init		= colibri_pcmcia_hw_init,
+	.hw_shutdown		= colibri_pcmcia_hw_shutdown,
+
+	.socket_state		= colibri_pcmcia_socket_state,
+	.configure_socket	= colibri_pcmcia_configure_socket,
+};
+
+static struct platform_device *colibri_pcmcia_device;
+
+static int __init colibri_pcmcia_init(void)
+{
+	int ret;
+
+	if (!machine_is_colibri() && !machine_is_colibri320())
+		return -ENODEV;
+
+	colibri_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!colibri_pcmcia_device)
+		return -ENOMEM;
+
+	/* Colibri PXA270 */
+	if (machine_is_colibri()) {
+		colibri_pcmcia_gpios[RESET].gpio	= COLIBRI270_RESET_GPIO;
+		colibri_pcmcia_gpios[PPEN].gpio		= COLIBRI270_PPEN_GPIO;
+		colibri_pcmcia_gpios[BVD1].gpio		= COLIBRI270_BVD1_GPIO;
+		colibri_pcmcia_gpios[BVD2].gpio		= COLIBRI270_BVD2_GPIO;
+		colibri_pcmcia_gpios[DETECT].gpio	= COLIBRI270_DETECT_GPIO;
+		colibri_pcmcia_gpios[READY].gpio	= COLIBRI270_READY_GPIO;
+	/* Colibri PXA320 */
+	} else if (machine_is_colibri320()) {
+		colibri_pcmcia_gpios[RESET].gpio	= COLIBRI320_RESET_GPIO;
+		colibri_pcmcia_gpios[PPEN].gpio		= COLIBRI320_PPEN_GPIO;
+		colibri_pcmcia_gpios[BVD1].gpio		= COLIBRI320_BVD1_GPIO;
+		colibri_pcmcia_gpios[BVD2].gpio		= COLIBRI320_BVD2_GPIO;
+		colibri_pcmcia_gpios[DETECT].gpio	= COLIBRI320_DETECT_GPIO;
+		colibri_pcmcia_gpios[READY].gpio	= COLIBRI320_READY_GPIO;
+	}
+
+	ret = platform_device_add_data(colibri_pcmcia_device,
+		&colibri_pcmcia_ops, sizeof(colibri_pcmcia_ops));
+
+	if (!ret)
+		ret = platform_device_add(colibri_pcmcia_device);
+
+	if (ret)
+		platform_device_put(colibri_pcmcia_device);
+
+	return ret;
+}
+
+static void __exit colibri_pcmcia_exit(void)
+{
+	platform_device_unregister(colibri_pcmcia_device);
+}
+
+module_init(colibri_pcmcia_init);
+module_exit(colibri_pcmcia_exit);
+
+MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
+MODULE_DESCRIPTION("PCMCIA support for Toradex Colibri PXA270/PXA320");
+MODULE_ALIAS("platform:pxa2xx-pcmcia");
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/mach-pxa/e740-pcmcia.c b/arch/arm/mach-pxa/e740-pcmcia.c
new file mode 100644
index 000000000000..133535d7ac05
--- /dev/null
+++ b/arch/arm/mach-pxa/e740-pcmcia.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Toshiba e740 PCMCIA specific routines.
+ *
+ * (c) 2004 Ian Molton <spyro@f2s.com>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+
+#include <mach/eseries-gpio.h>
+
+#include <asm/irq.h>
+#include <asm/mach-types.h>
+
+#include <pcmcia/soc_common.h>
+
+static int e740_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	if (skt->nr == 0) {
+		skt->stat[SOC_STAT_CD].gpio = GPIO_E740_PCMCIA_CD0;
+		skt->stat[SOC_STAT_CD].name = "CF card detect";
+		skt->stat[SOC_STAT_RDY].gpio = GPIO_E740_PCMCIA_RDY0;
+		skt->stat[SOC_STAT_RDY].name = "CF ready";
+	} else {
+		skt->stat[SOC_STAT_CD].gpio = GPIO_E740_PCMCIA_CD1;
+		skt->stat[SOC_STAT_CD].name = "Wifi switch";
+		skt->stat[SOC_STAT_RDY].gpio = GPIO_E740_PCMCIA_RDY1;
+		skt->stat[SOC_STAT_RDY].name = "Wifi ready";
+	}
+
+	return 0;
+}
+
+static void e740_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+					struct pcmcia_state *state)
+{
+	state->vs_3v  = 1;
+	state->vs_Xv  = 0;
+}
+
+static int e740_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+					const socket_state_t *state)
+{
+	if (state->flags & SS_RESET) {
+		if (skt->nr == 0)
+			gpio_set_value(GPIO_E740_PCMCIA_RST0, 1);
+		else
+			gpio_set_value(GPIO_E740_PCMCIA_RST1, 1);
+	} else {
+		if (skt->nr == 0)
+			gpio_set_value(GPIO_E740_PCMCIA_RST0, 0);
+		else
+			gpio_set_value(GPIO_E740_PCMCIA_RST1, 0);
+	}
+
+	switch (state->Vcc) {
+	case 0:	/* Socket off */
+		if (skt->nr == 0)
+			gpio_set_value(GPIO_E740_PCMCIA_PWR0, 0);
+		else
+			gpio_set_value(GPIO_E740_PCMCIA_PWR1, 1);
+		break;
+	case 50:
+	case 33: /* socket on */
+		if (skt->nr == 0)
+			gpio_set_value(GPIO_E740_PCMCIA_PWR0, 1);
+		else
+			gpio_set_value(GPIO_E740_PCMCIA_PWR1, 0);
+		break;
+	default:
+		printk(KERN_ERR "e740_cs: Unsupported Vcc: %d\n", state->Vcc);
+	}
+
+	return 0;
+}
+
+static struct pcmcia_low_level e740_pcmcia_ops = {
+	.owner            = THIS_MODULE,
+	.hw_init          = e740_pcmcia_hw_init,
+	.socket_state     = e740_pcmcia_socket_state,
+	.configure_socket = e740_pcmcia_configure_socket,
+	.nr               = 2,
+};
+
+static struct platform_device *e740_pcmcia_device;
+
+static int __init e740_pcmcia_init(void)
+{
+	int ret;
+
+	if (!machine_is_e740())
+		return -ENODEV;
+
+	e740_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!e740_pcmcia_device)
+		return -ENOMEM;
+
+	ret = platform_device_add_data(e740_pcmcia_device, &e740_pcmcia_ops,
+					sizeof(e740_pcmcia_ops));
+
+	if (!ret)
+		ret = platform_device_add(e740_pcmcia_device);
+
+	if (ret)
+		platform_device_put(e740_pcmcia_device);
+
+	return ret;
+}
+
+static void __exit e740_pcmcia_exit(void)
+{
+	platform_device_unregister(e740_pcmcia_device);
+}
+
+module_init(e740_pcmcia_init);
+module_exit(e740_pcmcia_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Ian Molton <spyro@f2s.com>");
+MODULE_ALIAS("platform:pxa2xx-pcmcia");
+MODULE_DESCRIPTION("e740 PCMCIA platform support");
diff --git a/arch/arm/mach-pxa/hx4700-pcmcia.c b/arch/arm/mach-pxa/hx4700-pcmcia.c
new file mode 100644
index 000000000000..e8acbfc9ef6c
--- /dev/null
+++ b/arch/arm/mach-pxa/hx4700-pcmcia.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Copyright (C) 2012 Paul Parsons <lost.distance@yahoo.com>
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/irq.h>
+
+#include <asm/mach-types.h>
+#include <mach/hx4700.h>
+
+#include <pcmcia/soc_common.h>
+
+static struct gpio gpios[] = {
+	{ GPIO114_HX4700_CF_RESET,    GPIOF_OUT_INIT_LOW,   "CF reset"        },
+	{ EGPIO4_CF_3V3_ON,           GPIOF_OUT_INIT_LOW,   "CF 3.3V enable"  },
+};
+
+static int hx4700_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	int ret;
+
+	ret = gpio_request_array(gpios, ARRAY_SIZE(gpios));
+	if (ret)
+		goto out;
+
+	/*
+	 * IRQ type must be set before soc_pcmcia_hw_init() calls request_irq().
+	 * The asic3 default IRQ type is level trigger low level detect, exactly
+	 * the the signal present on GPIOD4_CF_nCD when a CF card is inserted.
+	 * If the IRQ type is not changed, the asic3 interrupt handler will loop
+	 * repeatedly because it is unable to clear the level trigger interrupt.
+	 */
+	irq_set_irq_type(gpio_to_irq(GPIOD4_CF_nCD), IRQ_TYPE_EDGE_BOTH);
+
+	skt->stat[SOC_STAT_CD].gpio = GPIOD4_CF_nCD;
+	skt->stat[SOC_STAT_CD].name = "PCMCIA CD";
+	skt->stat[SOC_STAT_RDY].gpio = GPIO60_HX4700_CF_RNB;
+	skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
+
+out:
+	return ret;
+}
+
+static void hx4700_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
+{
+	gpio_free_array(gpios, ARRAY_SIZE(gpios));
+}
+
+static void hx4700_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+	struct pcmcia_state *state)
+{
+	state->vs_3v = 1;
+	state->vs_Xv = 0;
+}
+
+static int hx4700_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+	const socket_state_t *state)
+{
+	switch (state->Vcc) {
+	case 0:
+		gpio_set_value(EGPIO4_CF_3V3_ON, 0);
+		break;
+	case 33:
+		gpio_set_value(EGPIO4_CF_3V3_ON, 1);
+		break;
+	default:
+		printk(KERN_ERR "pcmcia: Unsupported Vcc: %d\n", state->Vcc);
+		return -EINVAL;
+	}
+
+	gpio_set_value(GPIO114_HX4700_CF_RESET, (state->flags & SS_RESET) != 0);
+
+	return 0;
+}
+
+static struct pcmcia_low_level hx4700_pcmcia_ops = {
+	.owner          = THIS_MODULE,
+	.nr             = 1,
+	.hw_init        = hx4700_pcmcia_hw_init,
+	.hw_shutdown    = hx4700_pcmcia_hw_shutdown,
+	.socket_state   = hx4700_pcmcia_socket_state,
+	.configure_socket = hx4700_pcmcia_configure_socket,
+};
+
+static struct platform_device *hx4700_pcmcia_device;
+
+static int __init hx4700_pcmcia_init(void)
+{
+	struct platform_device *pdev;
+
+	if (!machine_is_h4700())
+		return -ENODEV;
+
+	pdev = platform_device_register_data(NULL, "pxa2xx-pcmcia", -1,
+		&hx4700_pcmcia_ops, sizeof(hx4700_pcmcia_ops));
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	hx4700_pcmcia_device = pdev;
+
+	return 0;
+}
+
+static void __exit hx4700_pcmcia_exit(void)
+{
+	platform_device_unregister(hx4700_pcmcia_device);
+}
+
+module_init(hx4700_pcmcia_init);
+module_exit(hx4700_pcmcia_exit);
+
+MODULE_AUTHOR("Paul Parsons <lost.distance@yahoo.com>");
+MODULE_DESCRIPTION("HP iPAQ hx4700 PCMCIA driver");
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/mach-pxa/include/mach/balloon3.h b/arch/arm/mach-pxa/include/mach/balloon3.h
deleted file mode 100644
index 04f3639c4082..000000000000
--- a/arch/arm/mach-pxa/include/mach/balloon3.h
+++ /dev/null
@@ -1,181 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  linux/include/asm-arm/arch-pxa/balloon3.h
- *
- *  Authors:	Nick Bane and Wookey
- *  Created:	Oct, 2005
- *  Copyright:	Toby Churchill Ltd
- *  Cribbed from mainstone.c, by Nicholas Pitre
- */
-
-#ifndef ASM_ARCH_BALLOON3_H
-#define ASM_ARCH_BALLOON3_H
-
-#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
-
-enum balloon3_features {
-	BALLOON3_FEATURE_OHCI,
-	BALLOON3_FEATURE_MMC,
-	BALLOON3_FEATURE_CF,
-	BALLOON3_FEATURE_AUDIO,
-	BALLOON3_FEATURE_TOPPOLY,
-};
-
-#define BALLOON3_FPGA_PHYS	PXA_CS4_PHYS
-#define BALLOON3_FPGA_VIRT	IOMEM(0xf1000000)	/* as per balloon2 */
-#define BALLOON3_FPGA_LENGTH	0x01000000
-
-#define	BALLOON3_FPGA_SETnCLR		(0x1000)
-
-/* FPGA / CPLD registers for CF socket */
-#define	BALLOON3_CF_STATUS_REG		(BALLOON3_FPGA_VIRT + 0x00e00008)
-#define	BALLOON3_CF_CONTROL_REG		(BALLOON3_FPGA_VIRT + 0x00e00008)
-/* FPGA / CPLD version register */
-#define	BALLOON3_FPGA_VER		(BALLOON3_FPGA_VIRT + 0x00e0001c)
-/* FPGA / CPLD registers for NAND flash */
-#define	BALLOON3_NAND_BASE		(PXA_CS4_PHYS + 0x00e00000)
-#define	BALLOON3_NAND_IO_REG		(BALLOON3_FPGA_VIRT + 0x00e00000)
-#define	BALLOON3_NAND_CONTROL2_REG	(BALLOON3_FPGA_VIRT + 0x00e00010)
-#define	BALLOON3_NAND_STAT_REG		(BALLOON3_FPGA_VIRT + 0x00e00014)
-#define	BALLOON3_NAND_CONTROL_REG	(BALLOON3_FPGA_VIRT + 0x00e00014)
-
-/* fpga/cpld interrupt control register */
-#define BALLOON3_INT_CONTROL_REG	(BALLOON3_FPGA_VIRT + 0x00e0000C)
-#define BALLOON3_VERSION_REG		(BALLOON3_FPGA_VIRT + 0x00e0001c)
-
-#define BALLOON3_SAMOSA_ADDR_REG	(BALLOON3_FPGA_VIRT + 0x00c00000)
-#define BALLOON3_SAMOSA_DATA_REG	(BALLOON3_FPGA_VIRT + 0x00c00004)
-#define BALLOON3_SAMOSA_STATUS_REG	(BALLOON3_FPGA_VIRT + 0x00c0001c)
-
-/* CF Status Register bits (read-only) bits */
-#define BALLOON3_CF_nIRQ		(1 << 0)
-#define BALLOON3_CF_nSTSCHG_BVD1	(1 << 1)
-
-/* CF Control Set Register bits / CF Control Clear Register bits (write-only) */
-#define BALLOON3_CF_RESET		(1 << 0)
-#define BALLOON3_CF_ENABLE		(1 << 1)
-#define BALLOON3_CF_ADD_ENABLE		(1 << 2)
-
-/* CF Interrupt sources */
-#define BALLOON3_BP_CF_NRDY_IRQ		BALLOON3_IRQ(0)
-#define BALLOON3_BP_NSTSCHG_IRQ		BALLOON3_IRQ(1)
-
-/* NAND Control register */
-#define	BALLOON3_NAND_CONTROL_FLWP	(1 << 7)
-#define	BALLOON3_NAND_CONTROL_FLSE	(1 << 6)
-#define	BALLOON3_NAND_CONTROL_FLCE3	(1 << 5)
-#define	BALLOON3_NAND_CONTROL_FLCE2	(1 << 4)
-#define	BALLOON3_NAND_CONTROL_FLCE1	(1 << 3)
-#define	BALLOON3_NAND_CONTROL_FLCE0	(1 << 2)
-#define	BALLOON3_NAND_CONTROL_FLALE	(1 << 1)
-#define	BALLOON3_NAND_CONTROL_FLCLE	(1 << 0)
-
-/* NAND Status register */
-#define	BALLOON3_NAND_STAT_RNB		(1 << 0)
-
-/* NAND Control2 register */
-#define	BALLOON3_NAND_CONTROL2_16BIT	(1 << 0)
-
-/* GPIOs for irqs */
-#define BALLOON3_GPIO_AUX_NIRQ		(94)
-#define BALLOON3_GPIO_CODEC_IRQ		(95)
-
-/* Timer and Idle LED locations */
-#define BALLOON3_GPIO_LED_NAND		(9)
-#define BALLOON3_GPIO_LED_IDLE		(10)
-
-/* backlight control */
-#define BALLOON3_GPIO_RUN_BACKLIGHT	(99)
-
-#define BALLOON3_GPIO_S0_CD		(105)
-
-/* NAND */
-#define BALLOON3_GPIO_RUN_NAND		(102)
-
-/* PCF8574A Leds */
-#define	BALLOON3_PCF_GPIO_BASE		160
-#define	BALLOON3_PCF_GPIO_LED0		(BALLOON3_PCF_GPIO_BASE + 0)
-#define	BALLOON3_PCF_GPIO_LED1		(BALLOON3_PCF_GPIO_BASE + 1)
-#define	BALLOON3_PCF_GPIO_LED2		(BALLOON3_PCF_GPIO_BASE + 2)
-#define	BALLOON3_PCF_GPIO_LED3		(BALLOON3_PCF_GPIO_BASE + 3)
-#define	BALLOON3_PCF_GPIO_LED4		(BALLOON3_PCF_GPIO_BASE + 4)
-#define	BALLOON3_PCF_GPIO_LED5		(BALLOON3_PCF_GPIO_BASE + 5)
-#define	BALLOON3_PCF_GPIO_LED6		(BALLOON3_PCF_GPIO_BASE + 6)
-#define	BALLOON3_PCF_GPIO_LED7		(BALLOON3_PCF_GPIO_BASE + 7)
-
-/* FPGA Interrupt Mask/Acknowledge Register */
-#define BALLOON3_INT_S0_IRQ		(1 << 0)  /* PCMCIA 0 IRQ */
-#define BALLOON3_INT_S0_STSCHG		(1 << 1)  /* PCMCIA 0 status changed */
-
-/* CPLD (and FPGA) interface definitions */
-#define CPLD_LCD0_DATA_SET             0x00
-#define CPLD_LCD0_DATA_CLR             0x10
-#define CPLD_LCD0_COMMAND_SET          0x01
-#define CPLD_LCD0_COMMAND_CLR          0x11
-#define CPLD_LCD1_DATA_SET             0x02
-#define CPLD_LCD1_DATA_CLR             0x12
-#define CPLD_LCD1_COMMAND_SET          0x03
-#define CPLD_LCD1_COMMAND_CLR          0x13
-
-#define CPLD_MISC_SET                  0x07
-#define CPLD_MISC_CLR                  0x17
-#define CPLD_MISC_LOON_NRESET_BIT      0
-#define CPLD_MISC_LOON_UNSUSP_BIT      1
-#define CPLD_MISC_RUN_5V_BIT           2
-#define CPLD_MISC_CHG_D0_BIT           3
-#define CPLD_MISC_CHG_D1_BIT           4
-#define CPLD_MISC_DAC_NCS_BIT          5
-
-#define CPLD_LCD_SET                   0x08
-#define CPLD_LCD_CLR                   0x18
-#define CPLD_LCD_BACKLIGHT_EN_0_BIT    0
-#define CPLD_LCD_BACKLIGHT_EN_1_BIT    1
-#define CPLD_LCD_LED_RED_BIT           4
-#define CPLD_LCD_LED_GREEN_BIT         5
-#define CPLD_LCD_NRESET_BIT            7
-
-#define CPLD_LCD_RO_SET                0x09
-#define CPLD_LCD_RO_CLR                0x19
-#define CPLD_LCD_RO_LCD0_nWAIT_BIT     0
-#define CPLD_LCD_RO_LCD1_nWAIT_BIT     1
-
-#define CPLD_SERIAL_SET                0x0a
-#define CPLD_SERIAL_CLR                0x1a
-#define CPLD_SERIAL_GSM_RI_BIT         0
-#define CPLD_SERIAL_GSM_CTS_BIT        1
-#define CPLD_SERIAL_GSM_DTR_BIT        2
-#define CPLD_SERIAL_LPR_CTS_BIT        3
-#define CPLD_SERIAL_TC232_CTS_BIT      4
-#define CPLD_SERIAL_TC232_DSR_BIT      5
-
-#define CPLD_SROUTING_SET              0x0b
-#define CPLD_SROUTING_CLR              0x1b
-#define CPLD_SROUTING_MSP430_LPR       0
-#define CPLD_SROUTING_MSP430_TC232     1
-#define CPLD_SROUTING_MSP430_GSM       2
-#define CPLD_SROUTING_LOON_LPR         (0 << 4)
-#define CPLD_SROUTING_LOON_TC232       (1 << 4)
-#define CPLD_SROUTING_LOON_GSM         (2 << 4)
-
-#define CPLD_AROUTING_SET              0x0c
-#define CPLD_AROUTING_CLR              0x1c
-#define CPLD_AROUTING_MIC2PHONE_BIT    0
-#define CPLD_AROUTING_PHONE2INT_BIT    1
-#define CPLD_AROUTING_PHONE2EXT_BIT    2
-#define CPLD_AROUTING_LOONL2INT_BIT    3
-#define CPLD_AROUTING_LOONL2EXT_BIT    4
-#define CPLD_AROUTING_LOONR2PHONE_BIT  5
-#define CPLD_AROUTING_LOONR2INT_BIT    6
-#define CPLD_AROUTING_LOONR2EXT_BIT    7
-
-/* Balloon3 Interrupts */
-#define BALLOON3_IRQ(x)		(IRQ_BOARD_START + (x))
-
-#define BALLOON3_AUX_NIRQ	PXA_GPIO_TO_IRQ(BALLOON3_GPIO_AUX_NIRQ)
-#define BALLOON3_CODEC_IRQ	PXA_GPIO_TO_IRQ(BALLOON3_GPIO_CODEC_IRQ)
-
-#define BALLOON3_NR_IRQS	(IRQ_BOARD_START + 16)
-
-extern int balloon3_has(enum balloon3_features feature);
-
-#endif
diff --git a/arch/arm/mach-pxa/include/mach/palmtc.h b/arch/arm/mach-pxa/include/mach/palmtc.h
deleted file mode 100644
index 9257a02c46e5..000000000000
--- a/arch/arm/mach-pxa/include/mach/palmtc.h
+++ /dev/null
@@ -1,84 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/include/asm-arm/arch-pxa/palmtc-gpio.h
- *
- * GPIOs and interrupts for Palm Tungsten|C Handheld Computer
- *
- * Authors:	Alex Osborne <bobofdoom@gmail.com>
- *		Marek Vasut <marek.vasut@gmail.com>
- *		Holger Bocklet <bitz.email@gmx.net>
- */
-
-#ifndef _INCLUDE_PALMTC_H_
-#define _INCLUDE_PALMTC_H_
-
-#include "irqs.h" /* PXA_GPIO_TO_IRQ */
-
-/** HERE ARE GPIOs **/
-
-/* GPIOs */
-#define GPIO_NR_PALMTC_EARPHONE_DETECT	2
-#define GPIO_NR_PALMTC_CRADLE_DETECT	5
-#define GPIO_NR_PALMTC_HOTSYNC_BUTTON	7
-
-/* SD/MMC */
-#define GPIO_NR_PALMTC_SD_DETECT_N	12
-#define GPIO_NR_PALMTC_SD_POWER		32
-#define GPIO_NR_PALMTC_SD_READONLY	54
-
-/* WLAN */
-#define GPIO_NR_PALMTC_PCMCIA_READY	13
-#define GPIO_NR_PALMTC_PCMCIA_PWRREADY	14
-#define GPIO_NR_PALMTC_PCMCIA_POWER1	15
-#define GPIO_NR_PALMTC_PCMCIA_POWER2	33
-#define GPIO_NR_PALMTC_PCMCIA_POWER3	55
-#define GPIO_NR_PALMTC_PCMCIA_RESET	78
-
-/* UDC */
-#define GPIO_NR_PALMTC_USB_DETECT_N	4
-#define GPIO_NR_PALMTC_USB_POWER	36
-
-/* LCD/BACKLIGHT */
-#define GPIO_NR_PALMTC_BL_POWER		16
-#define GPIO_NR_PALMTC_LCD_POWER	44
-#define GPIO_NR_PALMTC_LCD_BLANK	38
-
-/* UART */
-#define GPIO_NR_PALMTC_RS232_POWER	37
-
-/* IRDA */
-#define GPIO_NR_PALMTC_IR_DISABLE	45
-
-/* IRQs */
-#define IRQ_GPIO_PALMTC_SD_DETECT_N	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTC_SD_DETECT_N)
-#define IRQ_GPIO_PALMTC_WLAN_READY	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTC_WLAN_READY)
-
-/* UCB1400 GPIOs */
-#define GPIO_NR_PALMTC_POWER_DETECT	(0x80 | 0x00)
-#define GPIO_NR_PALMTC_HEADPHONE_DETECT	(0x80 | 0x01)
-#define GPIO_NR_PALMTC_SPEAKER_ENABLE	(0x80 | 0x03)
-#define GPIO_NR_PALMTC_VIBRA_POWER	(0x80 | 0x05)
-#define GPIO_NR_PALMTC_LED_POWER	(0x80 | 0x07)
-
-/** HERE ARE INIT VALUES **/
-#define PALMTC_UCB1400_GPIO_OFFSET	0x80
-
-/* BATTERY */
-#define PALMTC_BAT_MAX_VOLTAGE		4000	/* 4.00V maximum voltage */
-#define PALMTC_BAT_MIN_VOLTAGE		3550	/* 3.55V critical voltage */
-#define PALMTC_BAT_MAX_CURRENT		0	/* unknown */
-#define PALMTC_BAT_MIN_CURRENT		0	/* unknown */
-#define PALMTC_BAT_MAX_CHARGE		1	/* unknown */
-#define PALMTC_BAT_MIN_CHARGE		1	/* unknown */
-#define PALMTC_MAX_LIFE_MINS		240	/* on-life in minutes */
-
-#define PALMTC_BAT_MEASURE_DELAY	(HZ * 1)
-
-/* BACKLIGHT */
-#define PALMTC_MAX_INTENSITY		0xFE
-#define PALMTC_DEFAULT_INTENSITY	0x7E
-#define PALMTC_LIMIT_MASK		0x7F
-#define PALMTC_PRESCALER		0x3F
-#define PALMTC_PERIOD_NS		3500
-
-#endif
diff --git a/arch/arm/mach-pxa/include/mach/palmtx.h b/arch/arm/mach-pxa/include/mach/palmtx.h
deleted file mode 100644
index ec88abf0fc6c..000000000000
--- a/arch/arm/mach-pxa/include/mach/palmtx.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * GPIOs and interrupts for Palm T|X Handheld Computer
- *
- * Based on palmld-gpio.h by Alex Osborne
- *
- * Authors:	Marek Vasut <marek.vasut@gmail.com>
- *		Cristiano P. <cristianop@users.sourceforge.net>
- *		Jan Herman <2hp@seznam.cz>
- */
-
-#ifndef _INCLUDE_PALMTX_H_
-#define _INCLUDE_PALMTX_H_
-
-#include "irqs.h" /* PXA_GPIO_TO_IRQ */
-
-/** HERE ARE GPIOs **/
-
-/* GPIOs */
-#define GPIO_NR_PALMTX_GPIO_RESET		1
-
-#define GPIO_NR_PALMTX_POWER_DETECT		12 /* 90 */
-#define GPIO_NR_PALMTX_HOTSYNC_BUTTON_N		10
-#define GPIO_NR_PALMTX_EARPHONE_DETECT		107
-
-/* SD/MMC */
-#define GPIO_NR_PALMTX_SD_DETECT_N		14
-#define GPIO_NR_PALMTX_SD_POWER			114 /* probably */
-#define GPIO_NR_PALMTX_SD_READONLY		115 /* probably */
-
-/* TOUCHSCREEN */
-#define GPIO_NR_PALMTX_WM9712_IRQ		27
-
-/* IRDA -  disable GPIO connected to SD pin of tranceiver (TFBS4710?) ? */
-#define GPIO_NR_PALMTX_IR_DISABLE		40
-
-/* USB */
-#define GPIO_NR_PALMTX_USB_DETECT_N		13
-#define GPIO_NR_PALMTX_USB_PULLUP		93
-
-/* LCD/BACKLIGHT */
-#define GPIO_NR_PALMTX_BL_POWER			84
-#define GPIO_NR_PALMTX_LCD_POWER		96
-
-/* LCD BORDER */
-#define GPIO_NR_PALMTX_BORDER_SWITCH		98
-#define GPIO_NR_PALMTX_BORDER_SELECT		22
-
-/* BLUETOOTH */
-#define GPIO_NR_PALMTX_BT_POWER			17
-#define GPIO_NR_PALMTX_BT_RESET			83
-
-/* PCMCIA (WiFi) */
-#define GPIO_NR_PALMTX_PCMCIA_POWER1		94
-#define GPIO_NR_PALMTX_PCMCIA_POWER2		108
-#define GPIO_NR_PALMTX_PCMCIA_RESET		79
-#define GPIO_NR_PALMTX_PCMCIA_READY		116
-
-/* NAND Flash ... this GPIO may be incorrect! */
-#define GPIO_NR_PALMTX_NAND_BUFFER_DIR		79
-
-/* INTERRUPTS */
-#define IRQ_GPIO_PALMTX_SD_DETECT_N	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTX_SD_DETECT_N)
-#define IRQ_GPIO_PALMTX_WM9712_IRQ	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTX_WM9712_IRQ)
-#define IRQ_GPIO_PALMTX_USB_DETECT	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTX_USB_DETECT)
-#define IRQ_GPIO_PALMTX_GPIO_RESET	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTX_GPIO_RESET)
-
-/** HERE ARE INIT VALUES **/
-
-/* Various addresses  */
-#define PALMTX_PCMCIA_PHYS	0x28000000
-#define PALMTX_PCMCIA_VIRT	IOMEM(0xf0000000)
-#define PALMTX_PCMCIA_SIZE	0x100000
-
-#define PALMTX_PHYS_RAM_START	0xa0000000
-#define PALMTX_PHYS_IO_START	0x40000000
-
-#define PALMTX_STR_BASE		0xa0200000
-
-#define PALMTX_PHYS_FLASH_START	PXA_CS0_PHYS	/* ChipSelect 0 */
-#define PALMTX_PHYS_NAND_START	PXA_CS1_PHYS	/* ChipSelect 1 */
-
-#define PALMTX_NAND_ALE_PHYS	(PALMTX_PHYS_NAND_START | (1 << 24))
-#define PALMTX_NAND_CLE_PHYS	(PALMTX_PHYS_NAND_START | (1 << 25))
-#define PALMTX_NAND_ALE_VIRT	IOMEM(0xff100000)
-#define PALMTX_NAND_CLE_VIRT	IOMEM(0xff200000)
-
-/* TOUCHSCREEN */
-#define AC97_LINK_FRAME			21
-
-
-/* BATTERY */
-#define PALMTX_BAT_MAX_VOLTAGE		4000	/* 4.00v current voltage */
-#define PALMTX_BAT_MIN_VOLTAGE		3550	/* 3.55v critical voltage */
-#define PALMTX_BAT_MAX_CURRENT		0	/* unknown */
-#define PALMTX_BAT_MIN_CURRENT		0	/* unknown */
-#define PALMTX_BAT_MAX_CHARGE		1	/* unknown */
-#define PALMTX_BAT_MIN_CHARGE		1	/* unknown */
-#define PALMTX_MAX_LIFE_MINS		360	/* on-life in minutes */
-
-#define PALMTX_BAT_MEASURE_DELAY	(HZ * 1)
-
-/* BACKLIGHT */
-#define PALMTX_MAX_INTENSITY		0xFE
-#define PALMTX_DEFAULT_INTENSITY	0x7E
-#define PALMTX_LIMIT_MASK		0x7F
-#define PALMTX_PRESCALER		0x3F
-#define PALMTX_PERIOD_NS		3500
-
-#endif
diff --git a/arch/arm/mach-pxa/include/mach/trizeps4.h b/arch/arm/mach-pxa/include/mach/trizeps4.h
deleted file mode 100644
index 27926629f9c6..000000000000
--- a/arch/arm/mach-pxa/include/mach/trizeps4.h
+++ /dev/null
@@ -1,166 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/************************************************************************
- * Include file for TRIZEPS4 SoM and ConXS eval-board
- * Copyright (c) Jürgen Schindele
- * 2006
- ************************************************************************/
-
-/*
- * Includes/Defines
- */
-#ifndef _TRIPEPS4_H_
-#define _TRIPEPS4_H_
-
-#include <mach/addr-map.h>
-#include "irqs.h" /* PXA_GPIO_TO_IRQ */
-
-/* physical memory regions */
-#define TRIZEPS4_FLASH_PHYS	(PXA_CS0_PHYS)  /* Flash region */
-#define TRIZEPS4_DISK_PHYS	(PXA_CS1_PHYS)  /* Disk On Chip region */
-#define TRIZEPS4_ETH_PHYS	(PXA_CS2_PHYS)  /* Ethernet DM9000 region */
-#define TRIZEPS4_PIC_PHYS	(PXA_CS3_PHYS)	/* Logic chip on ConXS-Board */
-#define TRIZEPS4_SDRAM_BASE	0xa0000000      /* SDRAM region */
-
-				/* Logic on ConXS-board CSFR register*/
-#define TRIZEPS4_CFSR_PHYS	(PXA_CS3_PHYS)
-				/* Logic on ConXS-board BOCR register*/
-#define TRIZEPS4_BOCR_PHYS	(PXA_CS3_PHYS+0x02000000)
-				/* Logic on ConXS-board IRCR register*/
-#define TRIZEPS4_IRCR_PHYS	(PXA_CS3_PHYS+0x02400000)
-				/* Logic on ConXS-board UPSR register*/
-#define TRIZEPS4_UPSR_PHYS	(PXA_CS3_PHYS+0x02800000)
-				/* Logic on ConXS-board DICR register*/
-#define TRIZEPS4_DICR_PHYS	(PXA_CS3_PHYS+0x03800000)
-
-/* virtual memory regions */
-#define TRIZEPS4_DISK_VIRT	0xF0000000	/* Disk On Chip region */
-
-#define TRIZEPS4_PIC_VIRT	0xF0100000	/* not used */
-#define TRIZEPS4_CFSR_VIRT	0xF0100000
-#define TRIZEPS4_BOCR_VIRT	0xF0200000
-#define TRIZEPS4_DICR_VIRT	0xF0300000
-#define TRIZEPS4_IRCR_VIRT	0xF0400000
-#define TRIZEPS4_UPSR_VIRT	0xF0500000
-
-/* size of flash */
-#define TRIZEPS4_FLASH_SIZE	0x02000000	/* Flash size 32 MB */
-
-/* Ethernet Controller Davicom DM9000 */
-#define GPIO_DM9000		101
-#define TRIZEPS4_ETH_IRQ	PXA_GPIO_TO_IRQ(GPIO_DM9000)
-
-/* UCB1400 audio / TS-controller */
-#define GPIO_UCB1400		1
-#define TRIZEPS4_UCB1400_IRQ	PXA_GPIO_TO_IRQ(GPIO_UCB1400)
-
-/* PCMCIA socket Compact Flash */
-#define GPIO_PCD		11		/* PCMCIA Card Detect */
-#define TRIZEPS4_CD_IRQ		PXA_GPIO_TO_IRQ(GPIO_PCD)
-#define GPIO_PRDY		13		/* READY / nINT */
-#define TRIZEPS4_READY_NINT	PXA_GPIO_TO_IRQ(GPIO_PRDY)
-
-/* MMC socket */
-#define GPIO_MMC_DET		12
-#define TRIZEPS4_MMC_IRQ	PXA_GPIO_TO_IRQ(GPIO_MMC_DET)
-
-/* DOC NAND chip */
-#define GPIO_DOC_LOCK           94
-#define GPIO_DOC_IRQ            93
-#define TRIZEPS4_DOC_IRQ        PXA_GPIO_TO_IRQ(GPIO_DOC_IRQ)
-
-/* SPI interface */
-#define GPIO_SPI                53
-#define TRIZEPS4_SPI_IRQ        PXA_GPIO_TO_IRQ(GPIO_SPI)
-
-/* LEDS using tx2 / rx2 */
-#define GPIO_SYS_BUSY_LED	46
-#define GPIO_HEARTBEAT_LED	47
-
-/* Off-module PIC on ConXS board */
-#define GPIO_PIC		0
-#define TRIZEPS4_PIC_IRQ	PXA_GPIO_TO_IRQ(GPIO_PIC)
-
-#ifdef CONFIG_MACH_TRIZEPS_CONXS
-/* for CONXS base board define these registers */
-#define CFSR_P2V(x)	((x) - TRIZEPS4_CFSR_PHYS + TRIZEPS4_CFSR_VIRT)
-#define CFSR_V2P(x)	((x) - TRIZEPS4_CFSR_VIRT + TRIZEPS4_CFSR_PHYS)
-
-#define BCR_P2V(x)	((x) - TRIZEPS4_BOCR_PHYS + TRIZEPS4_BOCR_VIRT)
-#define BCR_V2P(x)	((x) - TRIZEPS4_BOCR_VIRT + TRIZEPS4_BOCR_PHYS)
-
-#define DCR_P2V(x)	((x) - TRIZEPS4_DICR_PHYS + TRIZEPS4_DICR_VIRT)
-#define DCR_V2P(x)	((x) - TRIZEPS4_DICR_VIRT + TRIZEPS4_DICR_PHYS)
-
-#define IRCR_P2V(x)	((x) - TRIZEPS4_IRCR_PHYS + TRIZEPS4_IRCR_VIRT)
-#define IRCR_V2P(x)	((x) - TRIZEPS4_IRCR_VIRT + TRIZEPS4_IRCR_PHYS)
-
-#ifndef __ASSEMBLY__
-static inline unsigned short CFSR_readw(void)
-{
-	/* [Compact Flash Status Register] is read only */
-	return *((unsigned short *)CFSR_P2V(0x0C000000));
-}
-static inline void BCR_writew(unsigned short value)
-{
-	/* [Board Control Regsiter] is write only */
-	*((unsigned short *)BCR_P2V(0x0E000000)) = value;
-}
-static inline void DCR_writew(unsigned short value)
-{
-	/* [Display Control Register] is write only */
-	*((unsigned short *)DCR_P2V(0x0E000000)) = value;
-}
-static inline void IRCR_writew(unsigned short value)
-{
-	/* [InfraRed data Control Register] is write only */
-	*((unsigned short *)IRCR_P2V(0x0E000000)) = value;
-}
-#else
-#define ConXS_CFSR		CFSR_P2V(0x0C000000)
-#define ConXS_BCR		BCR_P2V(0x0E000000)
-#define ConXS_DCR		DCR_P2V(0x0F800000)
-#define ConXS_IRCR		IRCR_P2V(0x0F800000)
-#endif
-#else
-/* for whatever baseboard define function registers */
-static inline unsigned short CFSR_readw(void)
-{
-	return 0;
-}
-static inline void BCR_writew(unsigned short value)
-{
-	;
-}
-static inline void DCR_writew(unsigned short value)
-{
-	;
-}
-static inline void IRCR_writew(unsigned short value)
-{
-	;
-}
-#endif	/* CONFIG_MACH_TRIZEPS_CONXS */
-
-#define ConXS_CFSR_BVD_MASK	0x0003
-#define ConXS_CFSR_BVD1		(1 << 0)
-#define ConXS_CFSR_BVD2		(1 << 1)
-#define ConXS_CFSR_VS_MASK	0x000C
-#define ConXS_CFSR_VS1		(1 << 2)
-#define ConXS_CFSR_VS2		(1 << 3)
-#define ConXS_CFSR_VS_5V	(0x3 << 2)
-#define ConXS_CFSR_VS_3V3	0x0
-
-#define ConXS_BCR_S0_POW_EN0	(1 << 0)
-#define ConXS_BCR_S0_POW_EN1	(1 << 1)
-#define ConXS_BCR_L_DISP	(1 << 4)
-#define ConXS_BCR_CF_BUF_EN	(1 << 5)
-#define ConXS_BCR_CF_RESET	(1 << 7)
-#define ConXS_BCR_S0_VCC_3V3	0x1
-#define ConXS_BCR_S0_VCC_5V0	0x2
-#define ConXS_BCR_S0_VPP_12V	0x4
-#define ConXS_BCR_S0_VPP_3V3	0x8
-
-#define ConXS_IRCR_MODE		(1 << 0)
-#define ConXS_IRCR_SD		(1 << 1)
-
-#endif /* _TRIPEPS4_H_ */
diff --git a/arch/arm/mach-pxa/include/mach/vpac270.h b/arch/arm/mach-pxa/include/mach/vpac270.h
deleted file mode 100644
index 0cd094d8c553..000000000000
--- a/arch/arm/mach-pxa/include/mach/vpac270.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * GPIOs and interrupts for Voipac PXA270
- *
- * Copyright (C) 2010
- * Marek Vasut <marek.vasut@gmail.com>
- */
-
-#ifndef _INCLUDE_VPAC270_H_
-#define _INCLUDE_VPAC270_H_
-
-#define	GPIO1_VPAC270_USER_BTN		1
-
-#define	GPIO15_VPAC270_LED_ORANGE	15
-
-#define	GPIO81_VPAC270_BKL_ON		81
-#define	GPIO83_VPAC270_NL_ON		83
-
-#define	GPIO52_VPAC270_SD_READONLY	52
-#define	GPIO53_VPAC270_SD_DETECT_N	53
-
-#define	GPIO84_VPAC270_PCMCIA_CD	84
-#define	GPIO35_VPAC270_PCMCIA_RDY	35
-#define	GPIO107_VPAC270_PCMCIA_PPEN	107
-#define	GPIO11_VPAC270_PCMCIA_RESET	11
-#define	GPIO17_VPAC270_CF_CD		17
-#define	GPIO12_VPAC270_CF_RDY		12
-#define	GPIO16_VPAC270_CF_RESET		16
-
-#define	GPIO41_VPAC270_UDC_DETECT	41
-
-#define	GPIO114_VPAC270_ETH_IRQ		114
-
-#define	GPIO36_VPAC270_IDE_IRQ		36
-
-#define	GPIO113_VPAC270_TS_IRQ		113
-
-#endif
diff --git a/arch/arm/mach-pxa/palmld-pcmcia.c b/arch/arm/mach-pxa/palmld-pcmcia.c
new file mode 100644
index 000000000000..07e0f7438db1
--- /dev/null
+++ b/arch/arm/mach-pxa/palmld-pcmcia.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/drivers/pcmcia/pxa2xx_palmld.c
+ *
+ * Driver for Palm LifeDrive PCMCIA
+ *
+ * Copyright (C) 2006 Alex Osborne <ato@meshy.org>
+ * Copyright (C) 2007-2011 Marek Vasut <marek.vasut@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+
+#include <asm/mach-types.h>
+#include <mach/palmld.h>
+#include <pcmcia/soc_common.h>
+
+static struct gpio palmld_pcmcia_gpios[] = {
+	{ GPIO_NR_PALMLD_PCMCIA_POWER,	GPIOF_INIT_LOW,	"PCMCIA Power" },
+	{ GPIO_NR_PALMLD_PCMCIA_RESET,	GPIOF_INIT_HIGH,"PCMCIA Reset" },
+};
+
+static int palmld_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	int ret;
+
+	ret = gpio_request_array(palmld_pcmcia_gpios,
+				ARRAY_SIZE(palmld_pcmcia_gpios));
+
+	skt->stat[SOC_STAT_RDY].gpio = GPIO_NR_PALMLD_PCMCIA_READY;
+	skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
+
+	return ret;
+}
+
+static void palmld_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
+{
+	gpio_free_array(palmld_pcmcia_gpios, ARRAY_SIZE(palmld_pcmcia_gpios));
+}
+
+static void palmld_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+					struct pcmcia_state *state)
+{
+	state->detect = 1; /* always inserted */
+	state->vs_3v  = 1;
+	state->vs_Xv  = 0;
+}
+
+static int palmld_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+					const socket_state_t *state)
+{
+	gpio_set_value(GPIO_NR_PALMLD_PCMCIA_POWER, 1);
+	gpio_set_value(GPIO_NR_PALMLD_PCMCIA_RESET,
+			!!(state->flags & SS_RESET));
+
+	return 0;
+}
+
+static struct pcmcia_low_level palmld_pcmcia_ops = {
+	.owner			= THIS_MODULE,
+
+	.first			= 1,
+	.nr			= 1,
+
+	.hw_init		= palmld_pcmcia_hw_init,
+	.hw_shutdown		= palmld_pcmcia_hw_shutdown,
+
+	.socket_state		= palmld_pcmcia_socket_state,
+	.configure_socket	= palmld_pcmcia_configure_socket,
+};
+
+static struct platform_device *palmld_pcmcia_device;
+
+static int __init palmld_pcmcia_init(void)
+{
+	int ret;
+
+	if (!machine_is_palmld())
+		return -ENODEV;
+
+	palmld_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!palmld_pcmcia_device)
+		return -ENOMEM;
+
+	ret = platform_device_add_data(palmld_pcmcia_device, &palmld_pcmcia_ops,
+					sizeof(palmld_pcmcia_ops));
+
+	if (!ret)
+		ret = platform_device_add(palmld_pcmcia_device);
+
+	if (ret)
+		platform_device_put(palmld_pcmcia_device);
+
+	return ret;
+}
+
+static void __exit palmld_pcmcia_exit(void)
+{
+	platform_device_unregister(palmld_pcmcia_device);
+}
+
+module_init(palmld_pcmcia_init);
+module_exit(palmld_pcmcia_exit);
+
+MODULE_AUTHOR("Alex Osborne <ato@meshy.org>,"
+	    " Marek Vasut <marek.vasut@gmail.com>");
+MODULE_DESCRIPTION("PCMCIA support for Palm LifeDrive");
+MODULE_ALIAS("platform:pxa2xx-pcmcia");
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/mach-pxa/palmtc-pcmcia.c b/arch/arm/mach-pxa/palmtc-pcmcia.c
new file mode 100644
index 000000000000..8e3f382343fe
--- /dev/null
+++ b/arch/arm/mach-pxa/palmtc-pcmcia.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/drivers/pcmcia/pxa2xx_palmtc.c
+ *
+ * Driver for Palm Tungsten|C PCMCIA
+ *
+ * Copyright (C) 2008 Alex Osborne <ato@meshy.org>
+ * Copyright (C) 2009-2011 Marek Vasut <marek.vasut@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+#include <linux/delay.h>
+
+#include <asm/mach-types.h>
+#include "palmtc.h"
+#include <pcmcia/soc_common.h>
+
+static struct gpio palmtc_pcmcia_gpios[] = {
+	{ GPIO_NR_PALMTC_PCMCIA_POWER1,	GPIOF_INIT_LOW,	"PCMCIA Power 1" },
+	{ GPIO_NR_PALMTC_PCMCIA_POWER2,	GPIOF_INIT_LOW,	"PCMCIA Power 2" },
+	{ GPIO_NR_PALMTC_PCMCIA_POWER3,	GPIOF_INIT_LOW,	"PCMCIA Power 3" },
+	{ GPIO_NR_PALMTC_PCMCIA_RESET,	GPIOF_INIT_HIGH,"PCMCIA Reset" },
+	{ GPIO_NR_PALMTC_PCMCIA_PWRREADY, GPIOF_IN,	"PCMCIA Power Ready" },
+};
+
+static int palmtc_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	int ret;
+
+	ret = gpio_request_array(palmtc_pcmcia_gpios,
+				ARRAY_SIZE(palmtc_pcmcia_gpios));
+
+	skt->stat[SOC_STAT_RDY].gpio = GPIO_NR_PALMTC_PCMCIA_READY;
+	skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
+
+	return ret;
+}
+
+static void palmtc_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
+{
+	gpio_free_array(palmtc_pcmcia_gpios, ARRAY_SIZE(palmtc_pcmcia_gpios));
+}
+
+static void palmtc_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+					struct pcmcia_state *state)
+{
+	state->detect = 1; /* always inserted */
+	state->vs_3v  = 1;
+	state->vs_Xv  = 0;
+}
+
+static int palmtc_wifi_powerdown(void)
+{
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_RESET, 1);
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER2, 0);
+	mdelay(40);
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER1, 0);
+	return 0;
+}
+
+static int palmtc_wifi_powerup(void)
+{
+	int timeout = 50;
+
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER3, 1);
+	mdelay(50);
+
+	/* Power up the card, 1.8V first, after a while 3.3V */
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER1, 1);
+	mdelay(100);
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER2, 1);
+
+	/* Wait till the card is ready */
+	while (!gpio_get_value(GPIO_NR_PALMTC_PCMCIA_PWRREADY) &&
+		timeout) {
+		mdelay(1);
+		timeout--;
+	}
+
+	/* Power down the WiFi in case of error */
+	if (!timeout) {
+		palmtc_wifi_powerdown();
+		return 1;
+	}
+
+	/* Reset the card */
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_RESET, 1);
+	mdelay(20);
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_RESET, 0);
+	mdelay(25);
+
+	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER3, 0);
+
+	return 0;
+}
+
+static int palmtc_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+					const socket_state_t *state)
+{
+	int ret = 1;
+
+	if (state->Vcc == 0)
+		ret = palmtc_wifi_powerdown();
+	else if (state->Vcc == 33)
+		ret = palmtc_wifi_powerup();
+
+	return ret;
+}
+
+static struct pcmcia_low_level palmtc_pcmcia_ops = {
+	.owner			= THIS_MODULE,
+
+	.first			= 0,
+	.nr			= 1,
+
+	.hw_init		= palmtc_pcmcia_hw_init,
+	.hw_shutdown		= palmtc_pcmcia_hw_shutdown,
+
+	.socket_state		= palmtc_pcmcia_socket_state,
+	.configure_socket	= palmtc_pcmcia_configure_socket,
+};
+
+static struct platform_device *palmtc_pcmcia_device;
+
+static int __init palmtc_pcmcia_init(void)
+{
+	int ret;
+
+	if (!machine_is_palmtc())
+		return -ENODEV;
+
+	palmtc_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!palmtc_pcmcia_device)
+		return -ENOMEM;
+
+	ret = platform_device_add_data(palmtc_pcmcia_device, &palmtc_pcmcia_ops,
+					sizeof(palmtc_pcmcia_ops));
+
+	if (!ret)
+		ret = platform_device_add(palmtc_pcmcia_device);
+
+	if (ret)
+		platform_device_put(palmtc_pcmcia_device);
+
+	return ret;
+}
+
+static void __exit palmtc_pcmcia_exit(void)
+{
+	platform_device_unregister(palmtc_pcmcia_device);
+}
+
+module_init(palmtc_pcmcia_init);
+module_exit(palmtc_pcmcia_exit);
+
+MODULE_AUTHOR("Alex Osborne <ato@meshy.org>,"
+	    " Marek Vasut <marek.vasut@gmail.com>");
+MODULE_DESCRIPTION("PCMCIA support for Palm Tungsten|C");
+MODULE_ALIAS("platform:pxa2xx-pcmcia");
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index c59fc76c0c3d..3054ffa397ad 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -30,7 +30,7 @@
 
 #include "pxa25x.h"
 #include <linux/platform_data/asoc-pxa.h>
-#include <mach/palmtc.h>
+#include "palmtc.h"
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/irda-pxaficp.h>
diff --git a/arch/arm/mach-pxa/palmtc.h b/arch/arm/mach-pxa/palmtc.h
new file mode 100644
index 000000000000..afec057c2857
--- /dev/null
+++ b/arch/arm/mach-pxa/palmtc.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * linux/include/asm-arm/arch-pxa/palmtc-gpio.h
+ *
+ * GPIOs and interrupts for Palm Tungsten|C Handheld Computer
+ *
+ * Authors:	Alex Osborne <bobofdoom@gmail.com>
+ *		Marek Vasut <marek.vasut@gmail.com>
+ *		Holger Bocklet <bitz.email@gmx.net>
+ */
+
+#ifndef _INCLUDE_PALMTC_H_
+#define _INCLUDE_PALMTC_H_
+
+#include <mach/irqs.h> /* PXA_GPIO_TO_IRQ */
+
+/** HERE ARE GPIOs **/
+
+/* GPIOs */
+#define GPIO_NR_PALMTC_EARPHONE_DETECT	2
+#define GPIO_NR_PALMTC_CRADLE_DETECT	5
+#define GPIO_NR_PALMTC_HOTSYNC_BUTTON	7
+
+/* SD/MMC */
+#define GPIO_NR_PALMTC_SD_DETECT_N	12
+#define GPIO_NR_PALMTC_SD_POWER		32
+#define GPIO_NR_PALMTC_SD_READONLY	54
+
+/* WLAN */
+#define GPIO_NR_PALMTC_PCMCIA_READY	13
+#define GPIO_NR_PALMTC_PCMCIA_PWRREADY	14
+#define GPIO_NR_PALMTC_PCMCIA_POWER1	15
+#define GPIO_NR_PALMTC_PCMCIA_POWER2	33
+#define GPIO_NR_PALMTC_PCMCIA_POWER3	55
+#define GPIO_NR_PALMTC_PCMCIA_RESET	78
+
+/* UDC */
+#define GPIO_NR_PALMTC_USB_DETECT_N	4
+#define GPIO_NR_PALMTC_USB_POWER	36
+
+/* LCD/BACKLIGHT */
+#define GPIO_NR_PALMTC_BL_POWER		16
+#define GPIO_NR_PALMTC_LCD_POWER	44
+#define GPIO_NR_PALMTC_LCD_BLANK	38
+
+/* UART */
+#define GPIO_NR_PALMTC_RS232_POWER	37
+
+/* IRDA */
+#define GPIO_NR_PALMTC_IR_DISABLE	45
+
+/* IRQs */
+#define IRQ_GPIO_PALMTC_SD_DETECT_N	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTC_SD_DETECT_N)
+#define IRQ_GPIO_PALMTC_WLAN_READY	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTC_WLAN_READY)
+
+/* UCB1400 GPIOs */
+#define GPIO_NR_PALMTC_POWER_DETECT	(0x80 | 0x00)
+#define GPIO_NR_PALMTC_HEADPHONE_DETECT	(0x80 | 0x01)
+#define GPIO_NR_PALMTC_SPEAKER_ENABLE	(0x80 | 0x03)
+#define GPIO_NR_PALMTC_VIBRA_POWER	(0x80 | 0x05)
+#define GPIO_NR_PALMTC_LED_POWER	(0x80 | 0x07)
+
+/** HERE ARE INIT VALUES **/
+#define PALMTC_UCB1400_GPIO_OFFSET	0x80
+
+/* BATTERY */
+#define PALMTC_BAT_MAX_VOLTAGE		4000	/* 4.00V maximum voltage */
+#define PALMTC_BAT_MIN_VOLTAGE		3550	/* 3.55V critical voltage */
+#define PALMTC_BAT_MAX_CURRENT		0	/* unknown */
+#define PALMTC_BAT_MIN_CURRENT		0	/* unknown */
+#define PALMTC_BAT_MAX_CHARGE		1	/* unknown */
+#define PALMTC_BAT_MIN_CHARGE		1	/* unknown */
+#define PALMTC_MAX_LIFE_MINS		240	/* on-life in minutes */
+
+#define PALMTC_BAT_MEASURE_DELAY	(HZ * 1)
+
+/* BACKLIGHT */
+#define PALMTC_MAX_INTENSITY		0xFE
+#define PALMTC_DEFAULT_INTENSITY	0x7E
+#define PALMTC_LIMIT_MASK		0x7F
+#define PALMTC_PRESCALER		0x3F
+#define PALMTC_PERIOD_NS		3500
+
+#endif
diff --git a/arch/arm/mach-pxa/palmtx-pcmcia.c b/arch/arm/mach-pxa/palmtx-pcmcia.c
new file mode 100644
index 000000000000..8c2aaad93043
--- /dev/null
+++ b/arch/arm/mach-pxa/palmtx-pcmcia.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/drivers/pcmcia/pxa2xx_palmtx.c
+ *
+ * Driver for Palm T|X PCMCIA
+ *
+ * Copyright (C) 2007-2011 Marek Vasut <marek.vasut@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+
+#include <asm/mach-types.h>
+#include "palmtx.h"
+#include <pcmcia/soc_common.h>
+
+static struct gpio palmtx_pcmcia_gpios[] = {
+	{ GPIO_NR_PALMTX_PCMCIA_POWER1,	GPIOF_INIT_LOW,	"PCMCIA Power 1" },
+	{ GPIO_NR_PALMTX_PCMCIA_POWER2,	GPIOF_INIT_LOW,	"PCMCIA Power 2" },
+	{ GPIO_NR_PALMTX_PCMCIA_RESET,	GPIOF_INIT_HIGH,"PCMCIA Reset" },
+};
+
+static int palmtx_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	int ret;
+
+	ret = gpio_request_array(palmtx_pcmcia_gpios,
+				ARRAY_SIZE(palmtx_pcmcia_gpios));
+
+	skt->stat[SOC_STAT_RDY].gpio = GPIO_NR_PALMTX_PCMCIA_READY;
+	skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
+
+	return ret;
+}
+
+static void palmtx_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
+{
+	gpio_free_array(palmtx_pcmcia_gpios, ARRAY_SIZE(palmtx_pcmcia_gpios));
+}
+
+static void palmtx_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+					struct pcmcia_state *state)
+{
+	state->detect = 1; /* always inserted */
+	state->vs_3v  = 1;
+	state->vs_Xv  = 0;
+}
+
+static int
+palmtx_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+				const socket_state_t *state)
+{
+	gpio_set_value(GPIO_NR_PALMTX_PCMCIA_POWER1, 1);
+	gpio_set_value(GPIO_NR_PALMTX_PCMCIA_POWER2, 1);
+	gpio_set_value(GPIO_NR_PALMTX_PCMCIA_RESET,
+			!!(state->flags & SS_RESET));
+
+	return 0;
+}
+
+static struct pcmcia_low_level palmtx_pcmcia_ops = {
+	.owner			= THIS_MODULE,
+
+	.first			= 0,
+	.nr			= 1,
+
+	.hw_init		= palmtx_pcmcia_hw_init,
+	.hw_shutdown		= palmtx_pcmcia_hw_shutdown,
+
+	.socket_state		= palmtx_pcmcia_socket_state,
+	.configure_socket	= palmtx_pcmcia_configure_socket,
+};
+
+static struct platform_device *palmtx_pcmcia_device;
+
+static int __init palmtx_pcmcia_init(void)
+{
+	int ret;
+
+	if (!machine_is_palmtx())
+		return -ENODEV;
+
+	palmtx_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!palmtx_pcmcia_device)
+		return -ENOMEM;
+
+	ret = platform_device_add_data(palmtx_pcmcia_device, &palmtx_pcmcia_ops,
+					sizeof(palmtx_pcmcia_ops));
+
+	if (!ret)
+		ret = platform_device_add(palmtx_pcmcia_device);
+
+	if (ret)
+		platform_device_put(palmtx_pcmcia_device);
+
+	return ret;
+}
+
+static void __exit palmtx_pcmcia_exit(void)
+{
+	platform_device_unregister(palmtx_pcmcia_device);
+}
+
+module_init(palmtx_pcmcia_init);
+module_exit(palmtx_pcmcia_exit);
+
+MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
+MODULE_DESCRIPTION("PCMCIA support for Palm T|X");
+MODULE_ALIAS("platform:pxa2xx-pcmcia");
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c
index 097b88638863..86460d6ea721 100644
--- a/arch/arm/mach-pxa/palmtx.c
+++ b/arch/arm/mach-pxa/palmtx.c
@@ -33,7 +33,7 @@
 
 #include "pxa27x.h"
 #include <linux/platform_data/asoc-pxa.h>
-#include <mach/palmtx.h>
+#include "palmtx.h"
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/irda-pxaficp.h>
diff --git a/arch/arm/mach-pxa/palmtx.h b/arch/arm/mach-pxa/palmtx.h
new file mode 100644
index 000000000000..a2bb993952d9
--- /dev/null
+++ b/arch/arm/mach-pxa/palmtx.h
@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * GPIOs and interrupts for Palm T|X Handheld Computer
+ *
+ * Based on palmld-gpio.h by Alex Osborne
+ *
+ * Authors:	Marek Vasut <marek.vasut@gmail.com>
+ *		Cristiano P. <cristianop@users.sourceforge.net>
+ *		Jan Herman <2hp@seznam.cz>
+ */
+
+#ifndef _INCLUDE_PALMTX_H_
+#define _INCLUDE_PALMTX_H_
+
+#include <mach/irqs.h> /* PXA_GPIO_TO_IRQ */
+
+/** HERE ARE GPIOs **/
+
+/* GPIOs */
+#define GPIO_NR_PALMTX_GPIO_RESET		1
+
+#define GPIO_NR_PALMTX_POWER_DETECT		12 /* 90 */
+#define GPIO_NR_PALMTX_HOTSYNC_BUTTON_N		10
+#define GPIO_NR_PALMTX_EARPHONE_DETECT		107
+
+/* SD/MMC */
+#define GPIO_NR_PALMTX_SD_DETECT_N		14
+#define GPIO_NR_PALMTX_SD_POWER			114 /* probably */
+#define GPIO_NR_PALMTX_SD_READONLY		115 /* probably */
+
+/* TOUCHSCREEN */
+#define GPIO_NR_PALMTX_WM9712_IRQ		27
+
+/* IRDA -  disable GPIO connected to SD pin of tranceiver (TFBS4710?) ? */
+#define GPIO_NR_PALMTX_IR_DISABLE		40
+
+/* USB */
+#define GPIO_NR_PALMTX_USB_DETECT_N		13
+#define GPIO_NR_PALMTX_USB_PULLUP		93
+
+/* LCD/BACKLIGHT */
+#define GPIO_NR_PALMTX_BL_POWER			84
+#define GPIO_NR_PALMTX_LCD_POWER		96
+
+/* LCD BORDER */
+#define GPIO_NR_PALMTX_BORDER_SWITCH		98
+#define GPIO_NR_PALMTX_BORDER_SELECT		22
+
+/* BLUETOOTH */
+#define GPIO_NR_PALMTX_BT_POWER			17
+#define GPIO_NR_PALMTX_BT_RESET			83
+
+/* PCMCIA (WiFi) */
+#define GPIO_NR_PALMTX_PCMCIA_POWER1		94
+#define GPIO_NR_PALMTX_PCMCIA_POWER2		108
+#define GPIO_NR_PALMTX_PCMCIA_RESET		79
+#define GPIO_NR_PALMTX_PCMCIA_READY		116
+
+/* NAND Flash ... this GPIO may be incorrect! */
+#define GPIO_NR_PALMTX_NAND_BUFFER_DIR		79
+
+/* INTERRUPTS */
+#define IRQ_GPIO_PALMTX_SD_DETECT_N	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTX_SD_DETECT_N)
+#define IRQ_GPIO_PALMTX_WM9712_IRQ	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTX_WM9712_IRQ)
+#define IRQ_GPIO_PALMTX_USB_DETECT	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTX_USB_DETECT)
+#define IRQ_GPIO_PALMTX_GPIO_RESET	PXA_GPIO_TO_IRQ(GPIO_NR_PALMTX_GPIO_RESET)
+
+/** HERE ARE INIT VALUES **/
+
+/* Various addresses  */
+#define PALMTX_PCMCIA_PHYS	0x28000000
+#define PALMTX_PCMCIA_VIRT	IOMEM(0xf0000000)
+#define PALMTX_PCMCIA_SIZE	0x100000
+
+#define PALMTX_PHYS_RAM_START	0xa0000000
+#define PALMTX_PHYS_IO_START	0x40000000
+
+#define PALMTX_STR_BASE		0xa0200000
+
+#define PALMTX_PHYS_FLASH_START	PXA_CS0_PHYS	/* ChipSelect 0 */
+#define PALMTX_PHYS_NAND_START	PXA_CS1_PHYS	/* ChipSelect 1 */
+
+#define PALMTX_NAND_ALE_PHYS	(PALMTX_PHYS_NAND_START | (1 << 24))
+#define PALMTX_NAND_CLE_PHYS	(PALMTX_PHYS_NAND_START | (1 << 25))
+#define PALMTX_NAND_ALE_VIRT	IOMEM(0xff100000)
+#define PALMTX_NAND_CLE_VIRT	IOMEM(0xff200000)
+
+/* TOUCHSCREEN */
+#define AC97_LINK_FRAME			21
+
+
+/* BATTERY */
+#define PALMTX_BAT_MAX_VOLTAGE		4000	/* 4.00v current voltage */
+#define PALMTX_BAT_MIN_VOLTAGE		3550	/* 3.55v critical voltage */
+#define PALMTX_BAT_MAX_CURRENT		0	/* unknown */
+#define PALMTX_BAT_MIN_CURRENT		0	/* unknown */
+#define PALMTX_BAT_MAX_CHARGE		1	/* unknown */
+#define PALMTX_BAT_MIN_CHARGE		1	/* unknown */
+#define PALMTX_MAX_LIFE_MINS		360	/* on-life in minutes */
+
+#define PALMTX_BAT_MEASURE_DELAY	(HZ * 1)
+
+/* BACKLIGHT */
+#define PALMTX_MAX_INTENSITY		0xFE
+#define PALMTX_DEFAULT_INTENSITY	0x7E
+#define PALMTX_LIMIT_MASK		0x7F
+#define PALMTX_PRESCALER		0x3F
+#define PALMTX_PERIOD_NS		3500
+
+#endif
diff --git a/arch/arm/mach-pxa/trizeps4-pcmcia.c b/arch/arm/mach-pxa/trizeps4-pcmcia.c
new file mode 100644
index 000000000000..02d7bb0c538f
--- /dev/null
+++ b/arch/arm/mach-pxa/trizeps4-pcmcia.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/drivers/pcmcia/pxa2xx_trizeps4.c
+ *
+ * TRIZEPS PCMCIA specific routines.
+ *
+ * Author:	Jürgen Schindele
+ * Created:	20 02, 2006
+ * Copyright:	Jürgen Schindele
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach-types.h>
+#include <asm/irq.h>
+
+#include <mach/pxa2xx-regs.h>
+#include "trizeps4.h"
+
+#include <pcmcia/soc_common.h>
+
+extern void board_pcmcia_power(int power);
+
+static int trizeps_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	/* we dont have voltage/card/ready detection
+	 * so we dont need interrupts for it
+	 */
+	switch (skt->nr) {
+	case 0:
+		skt->stat[SOC_STAT_CD].gpio = GPIO_PCD;
+		skt->stat[SOC_STAT_CD].name = "cs0_cd";
+		skt->stat[SOC_STAT_RDY].gpio = GPIO_PRDY;
+		skt->stat[SOC_STAT_RDY].name = "cs0_rdy";
+		break;
+	default:
+		break;
+	}
+	/* release the reset of this card */
+	pr_debug("%s: sock %d irq %d\n", __func__, skt->nr, skt->socket.pci_irq);
+
+	return 0;
+}
+
+static unsigned long trizeps_pcmcia_status[2];
+
+static void trizeps_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+				struct pcmcia_state *state)
+{
+	unsigned short status = 0, change;
+	status = CFSR_readw();
+	change = (status ^ trizeps_pcmcia_status[skt->nr]) &
+				ConXS_CFSR_BVD_MASK;
+	if (change) {
+		trizeps_pcmcia_status[skt->nr] = status;
+		if (status & ConXS_CFSR_BVD1) {
+			/* enable_irq empty */
+		} else {
+			/* disable_irq empty */
+		}
+	}
+
+	switch (skt->nr) {
+	case 0:
+		/* just fill in fix states */
+		state->bvd1   = (status & ConXS_CFSR_BVD1) ? 1 : 0;
+		state->bvd2   = (status & ConXS_CFSR_BVD2) ? 1 : 0;
+		state->vs_3v  = (status & ConXS_CFSR_VS1) ? 0 : 1;
+		state->vs_Xv  = (status & ConXS_CFSR_VS2) ? 0 : 1;
+		break;
+
+#ifndef CONFIG_MACH_TRIZEPS_CONXS
+	/* on ConXS we only have one slot. Second is inactive */
+	case 1:
+		state->detect = 0;
+		state->ready  = 0;
+		state->bvd1   = 0;
+		state->bvd2   = 0;
+		state->vs_3v  = 0;
+		state->vs_Xv  = 0;
+		break;
+
+#endif
+	}
+}
+
+static int trizeps_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+				const socket_state_t *state)
+{
+	int ret = 0;
+	unsigned short power = 0;
+
+	/* we do nothing here just check a bit */
+	switch (state->Vcc) {
+	case 0:  power &= 0xfc; break;
+	case 33: power |= ConXS_BCR_S0_VCC_3V3; break;
+	case 50:
+		pr_err("%s(): Vcc 5V not supported in socket\n", __func__);
+		break;
+	default:
+		pr_err("%s(): bad Vcc %u\n", __func__, state->Vcc);
+		ret = -1;
+	}
+
+	switch (state->Vpp) {
+	case 0:  power &= 0xf3; break;
+	case 33: power |= ConXS_BCR_S0_VPP_3V3; break;
+	case 120:
+		pr_err("%s(): Vpp 12V not supported in socket\n", __func__);
+		break;
+	default:
+		if (state->Vpp != state->Vcc) {
+			pr_err("%s(): bad Vpp %u\n", __func__, state->Vpp);
+			ret = -1;
+		}
+	}
+
+	switch (skt->nr) {
+	case 0:			 /* we only have 3.3V */
+		board_pcmcia_power(power);
+		break;
+
+#ifndef CONFIG_MACH_TRIZEPS_CONXS
+	/* on ConXS we only have one slot. Second is inactive */
+	case 1:
+#endif
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static void trizeps_pcmcia_socket_init(struct soc_pcmcia_socket *skt)
+{
+	/* default is on */
+	board_pcmcia_power(0x9);
+}
+
+static void trizeps_pcmcia_socket_suspend(struct soc_pcmcia_socket *skt)
+{
+	board_pcmcia_power(0x0);
+}
+
+static struct pcmcia_low_level trizeps_pcmcia_ops = {
+	.owner			= THIS_MODULE,
+	.hw_init		= trizeps_pcmcia_hw_init,
+	.socket_state		= trizeps_pcmcia_socket_state,
+	.configure_socket	= trizeps_pcmcia_configure_socket,
+	.socket_init		= trizeps_pcmcia_socket_init,
+	.socket_suspend		= trizeps_pcmcia_socket_suspend,
+#ifdef CONFIG_MACH_TRIZEPS_CONXS
+	.nr			= 1,
+#else
+	.nr			= 2,
+#endif
+	.first			= 0,
+};
+
+static struct platform_device *trizeps_pcmcia_device;
+
+static int __init trizeps_pcmcia_init(void)
+{
+	int ret;
+
+	if (!machine_is_trizeps4() && !machine_is_trizeps4wl())
+		return -ENODEV;
+
+	trizeps_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!trizeps_pcmcia_device)
+		return -ENOMEM;
+
+	ret = platform_device_add_data(trizeps_pcmcia_device,
+			&trizeps_pcmcia_ops, sizeof(trizeps_pcmcia_ops));
+
+	if (ret == 0)
+		ret = platform_device_add(trizeps_pcmcia_device);
+
+	if (ret)
+		platform_device_put(trizeps_pcmcia_device);
+
+	return ret;
+}
+
+static void __exit trizeps_pcmcia_exit(void)
+{
+	platform_device_unregister(trizeps_pcmcia_device);
+}
+
+fs_initcall(trizeps_pcmcia_init);
+module_exit(trizeps_pcmcia_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Juergen Schindele");
+MODULE_ALIAS("platform:pxa2xx-pcmcia");
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index 1337008cc760..fadfbb40cd6c 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -40,7 +40,7 @@
 #include <asm/mach/flash.h>
 
 #include "pxa27x.h"
-#include <mach/trizeps4.h>
+#include "trizeps4.h"
 #include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/mmc-pxamci.h>
diff --git a/arch/arm/mach-pxa/trizeps4.h b/arch/arm/mach-pxa/trizeps4.h
new file mode 100644
index 000000000000..7597b9de11e2
--- /dev/null
+++ b/arch/arm/mach-pxa/trizeps4.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/************************************************************************
+ * Include file for TRIZEPS4 SoM and ConXS eval-board
+ * Copyright (c) Jürgen Schindele
+ * 2006
+ ************************************************************************/
+
+/*
+ * Includes/Defines
+ */
+#ifndef _TRIPEPS4_H_
+#define _TRIPEPS4_H_
+
+#include <mach/addr-map.h>
+#include <mach/irqs.h> /* PXA_GPIO_TO_IRQ */
+
+/* physical memory regions */
+#define TRIZEPS4_FLASH_PHYS	(PXA_CS0_PHYS)  /* Flash region */
+#define TRIZEPS4_DISK_PHYS	(PXA_CS1_PHYS)  /* Disk On Chip region */
+#define TRIZEPS4_ETH_PHYS	(PXA_CS2_PHYS)  /* Ethernet DM9000 region */
+#define TRIZEPS4_PIC_PHYS	(PXA_CS3_PHYS)	/* Logic chip on ConXS-Board */
+#define TRIZEPS4_SDRAM_BASE	0xa0000000      /* SDRAM region */
+
+				/* Logic on ConXS-board CSFR register*/
+#define TRIZEPS4_CFSR_PHYS	(PXA_CS3_PHYS)
+				/* Logic on ConXS-board BOCR register*/
+#define TRIZEPS4_BOCR_PHYS	(PXA_CS3_PHYS+0x02000000)
+				/* Logic on ConXS-board IRCR register*/
+#define TRIZEPS4_IRCR_PHYS	(PXA_CS3_PHYS+0x02400000)
+				/* Logic on ConXS-board UPSR register*/
+#define TRIZEPS4_UPSR_PHYS	(PXA_CS3_PHYS+0x02800000)
+				/* Logic on ConXS-board DICR register*/
+#define TRIZEPS4_DICR_PHYS	(PXA_CS3_PHYS+0x03800000)
+
+/* virtual memory regions */
+#define TRIZEPS4_DISK_VIRT	0xF0000000	/* Disk On Chip region */
+
+#define TRIZEPS4_PIC_VIRT	0xF0100000	/* not used */
+#define TRIZEPS4_CFSR_VIRT	0xF0100000
+#define TRIZEPS4_BOCR_VIRT	0xF0200000
+#define TRIZEPS4_DICR_VIRT	0xF0300000
+#define TRIZEPS4_IRCR_VIRT	0xF0400000
+#define TRIZEPS4_UPSR_VIRT	0xF0500000
+
+/* size of flash */
+#define TRIZEPS4_FLASH_SIZE	0x02000000	/* Flash size 32 MB */
+
+/* Ethernet Controller Davicom DM9000 */
+#define GPIO_DM9000		101
+#define TRIZEPS4_ETH_IRQ	PXA_GPIO_TO_IRQ(GPIO_DM9000)
+
+/* UCB1400 audio / TS-controller */
+#define GPIO_UCB1400		1
+#define TRIZEPS4_UCB1400_IRQ	PXA_GPIO_TO_IRQ(GPIO_UCB1400)
+
+/* PCMCIA socket Compact Flash */
+#define GPIO_PCD		11		/* PCMCIA Card Detect */
+#define TRIZEPS4_CD_IRQ		PXA_GPIO_TO_IRQ(GPIO_PCD)
+#define GPIO_PRDY		13		/* READY / nINT */
+#define TRIZEPS4_READY_NINT	PXA_GPIO_TO_IRQ(GPIO_PRDY)
+
+/* MMC socket */
+#define GPIO_MMC_DET		12
+#define TRIZEPS4_MMC_IRQ	PXA_GPIO_TO_IRQ(GPIO_MMC_DET)
+
+/* DOC NAND chip */
+#define GPIO_DOC_LOCK           94
+#define GPIO_DOC_IRQ            93
+#define TRIZEPS4_DOC_IRQ        PXA_GPIO_TO_IRQ(GPIO_DOC_IRQ)
+
+/* SPI interface */
+#define GPIO_SPI                53
+#define TRIZEPS4_SPI_IRQ        PXA_GPIO_TO_IRQ(GPIO_SPI)
+
+/* LEDS using tx2 / rx2 */
+#define GPIO_SYS_BUSY_LED	46
+#define GPIO_HEARTBEAT_LED	47
+
+/* Off-module PIC on ConXS board */
+#define GPIO_PIC		0
+#define TRIZEPS4_PIC_IRQ	PXA_GPIO_TO_IRQ(GPIO_PIC)
+
+#ifdef CONFIG_MACH_TRIZEPS_CONXS
+/* for CONXS base board define these registers */
+#define CFSR_P2V(x)	((x) - TRIZEPS4_CFSR_PHYS + TRIZEPS4_CFSR_VIRT)
+#define CFSR_V2P(x)	((x) - TRIZEPS4_CFSR_VIRT + TRIZEPS4_CFSR_PHYS)
+
+#define BCR_P2V(x)	((x) - TRIZEPS4_BOCR_PHYS + TRIZEPS4_BOCR_VIRT)
+#define BCR_V2P(x)	((x) - TRIZEPS4_BOCR_VIRT + TRIZEPS4_BOCR_PHYS)
+
+#define DCR_P2V(x)	((x) - TRIZEPS4_DICR_PHYS + TRIZEPS4_DICR_VIRT)
+#define DCR_V2P(x)	((x) - TRIZEPS4_DICR_VIRT + TRIZEPS4_DICR_PHYS)
+
+#define IRCR_P2V(x)	((x) - TRIZEPS4_IRCR_PHYS + TRIZEPS4_IRCR_VIRT)
+#define IRCR_V2P(x)	((x) - TRIZEPS4_IRCR_VIRT + TRIZEPS4_IRCR_PHYS)
+
+#ifndef __ASSEMBLY__
+static inline unsigned short CFSR_readw(void)
+{
+	/* [Compact Flash Status Register] is read only */
+	return *((unsigned short *)CFSR_P2V(0x0C000000));
+}
+static inline void BCR_writew(unsigned short value)
+{
+	/* [Board Control Regsiter] is write only */
+	*((unsigned short *)BCR_P2V(0x0E000000)) = value;
+}
+static inline void DCR_writew(unsigned short value)
+{
+	/* [Display Control Register] is write only */
+	*((unsigned short *)DCR_P2V(0x0E000000)) = value;
+}
+static inline void IRCR_writew(unsigned short value)
+{
+	/* [InfraRed data Control Register] is write only */
+	*((unsigned short *)IRCR_P2V(0x0E000000)) = value;
+}
+#else
+#define ConXS_CFSR		CFSR_P2V(0x0C000000)
+#define ConXS_BCR		BCR_P2V(0x0E000000)
+#define ConXS_DCR		DCR_P2V(0x0F800000)
+#define ConXS_IRCR		IRCR_P2V(0x0F800000)
+#endif
+#else
+/* for whatever baseboard define function registers */
+static inline unsigned short CFSR_readw(void)
+{
+	return 0;
+}
+static inline void BCR_writew(unsigned short value)
+{
+	;
+}
+static inline void DCR_writew(unsigned short value)
+{
+	;
+}
+static inline void IRCR_writew(unsigned short value)
+{
+	;
+}
+#endif	/* CONFIG_MACH_TRIZEPS_CONXS */
+
+#define ConXS_CFSR_BVD_MASK	0x0003
+#define ConXS_CFSR_BVD1		(1 << 0)
+#define ConXS_CFSR_BVD2		(1 << 1)
+#define ConXS_CFSR_VS_MASK	0x000C
+#define ConXS_CFSR_VS1		(1 << 2)
+#define ConXS_CFSR_VS2		(1 << 3)
+#define ConXS_CFSR_VS_5V	(0x3 << 2)
+#define ConXS_CFSR_VS_3V3	0x0
+
+#define ConXS_BCR_S0_POW_EN0	(1 << 0)
+#define ConXS_BCR_S0_POW_EN1	(1 << 1)
+#define ConXS_BCR_L_DISP	(1 << 4)
+#define ConXS_BCR_CF_BUF_EN	(1 << 5)
+#define ConXS_BCR_CF_RESET	(1 << 7)
+#define ConXS_BCR_S0_VCC_3V3	0x1
+#define ConXS_BCR_S0_VCC_5V0	0x2
+#define ConXS_BCR_S0_VPP_12V	0x4
+#define ConXS_BCR_S0_VPP_3V3	0x8
+
+#define ConXS_IRCR_MODE		(1 << 0)
+#define ConXS_IRCR_SD		(1 << 1)
+
+#endif /* _TRIPEPS4_H_ */
diff --git a/arch/arm/mach-pxa/viper-pcmcia.c b/arch/arm/mach-pxa/viper-pcmcia.c
new file mode 100644
index 000000000000..26599dcc49b3
--- /dev/null
+++ b/arch/arm/mach-pxa/viper-pcmcia.c
@@ -0,0 +1,180 @@
+/*
+ * Viper/Zeus PCMCIA support
+ *   Copyright 2004 Arcom Control Systems
+ *
+ * Maintained by Marc Zyngier <maz@misterjones.org>
+ *
+ * Based on:
+ *   iPAQ h2200 PCMCIA support
+ *   Copyright 2004 Koen Kooi <koen@vestingbar.nl>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive for
+ * more details.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+
+#include <pcmcia/ss.h>
+#include <pcmcia/soc_common.h>
+
+#include <asm/irq.h>
+
+#include "viper-pcmcia.h"
+
+static struct platform_device *arcom_pcmcia_dev;
+
+static inline struct arcom_pcmcia_pdata *viper_get_pdata(void)
+{
+	return arcom_pcmcia_dev->dev.platform_data;
+}
+
+static int viper_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	struct arcom_pcmcia_pdata *pdata = viper_get_pdata();
+	unsigned long flags;
+
+	skt->stat[SOC_STAT_CD].gpio = pdata->cd_gpio;
+	skt->stat[SOC_STAT_CD].name = "PCMCIA_CD";
+	skt->stat[SOC_STAT_RDY].gpio = pdata->rdy_gpio;
+	skt->stat[SOC_STAT_RDY].name = "CF ready";
+
+	if (gpio_request(pdata->pwr_gpio, "CF power"))
+		goto err_request_pwr;
+
+	local_irq_save(flags);
+
+	if (gpio_direction_output(pdata->pwr_gpio, 0)) {
+		local_irq_restore(flags);
+		goto err_dir;
+	}
+
+	local_irq_restore(flags);
+
+	return 0;
+
+err_dir:
+	gpio_free(pdata->pwr_gpio);
+err_request_pwr:
+	dev_err(&arcom_pcmcia_dev->dev, "Failed to setup PCMCIA GPIOs\n");
+	return -1;
+}
+
+/*
+ * Release all resources.
+ */
+static void viper_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
+{
+	struct arcom_pcmcia_pdata *pdata = viper_get_pdata();
+
+	gpio_free(pdata->pwr_gpio);
+}
+
+static void viper_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+				      struct pcmcia_state *state)
+{
+	state->vs_3v  = 1; /* Can only apply 3.3V */
+	state->vs_Xv  = 0;
+}
+
+static int viper_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+					 const socket_state_t *state)
+{
+	struct arcom_pcmcia_pdata *pdata = viper_get_pdata();
+
+	/* Silently ignore Vpp, output enable, speaker enable. */
+	pdata->reset(state->flags & SS_RESET);
+
+	/* Apply socket voltage */
+	switch (state->Vcc) {
+	case 0:
+		gpio_set_value(pdata->pwr_gpio, 0);
+		break;
+	case 33:
+		gpio_set_value(pdata->pwr_gpio, 1);
+		break;
+	default:
+		dev_err(&arcom_pcmcia_dev->dev, "Unsupported Vcc:%d\n", state->Vcc);
+		return -1;
+	}
+
+	return 0;
+}
+
+static struct pcmcia_low_level viper_pcmcia_ops = {
+	.owner          	= THIS_MODULE,
+	.hw_init        	= viper_pcmcia_hw_init,
+	.hw_shutdown		= viper_pcmcia_hw_shutdown,
+	.socket_state		= viper_pcmcia_socket_state,
+	.configure_socket	= viper_pcmcia_configure_socket,
+	.nr         		= 1,
+};
+
+static struct platform_device *viper_pcmcia_device;
+
+static int viper_pcmcia_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	/* I can't imagine more than one device, but you never know... */
+	if (arcom_pcmcia_dev)
+		return -EEXIST;
+
+	if (!pdev->dev.platform_data)
+		return -EINVAL;
+
+	viper_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!viper_pcmcia_device)
+		return -ENOMEM;
+
+	arcom_pcmcia_dev = pdev;
+
+	viper_pcmcia_device->dev.parent = &pdev->dev;
+
+	ret = platform_device_add_data(viper_pcmcia_device,
+				       &viper_pcmcia_ops,
+				       sizeof(viper_pcmcia_ops));
+
+	if (!ret)
+		ret = platform_device_add(viper_pcmcia_device);
+
+	if (ret) {
+		platform_device_put(viper_pcmcia_device);
+		arcom_pcmcia_dev = NULL;
+	}
+
+	return ret;
+}
+
+static int viper_pcmcia_remove(struct platform_device *pdev)
+{
+	platform_device_unregister(viper_pcmcia_device);
+	arcom_pcmcia_dev = NULL;
+	return 0;
+}
+
+static struct platform_device_id viper_pcmcia_id_table[] = {
+	{ .name = "viper-pcmcia", },
+	{ .name = "zeus-pcmcia",  },
+	{ },
+};
+
+static struct platform_driver viper_pcmcia_driver = {
+	.probe		= viper_pcmcia_probe,
+	.remove		= viper_pcmcia_remove,
+	.driver		= {
+		.name	= "arcom-pcmcia",
+	},
+	.id_table	= viper_pcmcia_id_table,
+};
+
+module_platform_driver(viper_pcmcia_driver);
+
+MODULE_DEVICE_TABLE(platform, viper_pcmcia_id_table);
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/mach-pxa/viper-pcmcia.h b/arch/arm/mach-pxa/viper-pcmcia.h
new file mode 100644
index 000000000000..a23b58aff9e1
--- /dev/null
+++ b/arch/arm/mach-pxa/viper-pcmcia.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCOM_PCMCIA_H
+#define __ARCOM_PCMCIA_H
+
+struct arcom_pcmcia_pdata {
+	int	cd_gpio;
+	int	rdy_gpio;
+	int	pwr_gpio;
+	void	(*reset)(int state);
+};
+
+#endif
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index ac94b10bf8c1..600d9e80b00c 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -49,7 +49,7 @@
 #include <linux/platform_data/asoc-pxa.h>
 #include <linux/platform_data/video-pxafb.h>
 #include "regs-uart.h"
-#include <linux/platform_data/pcmcia-pxa2xx_viper.h>
+#include "viper-pcmcia.h"
 #include "viper.h"
 
 #include <asm/setup.h>
diff --git a/arch/arm/mach-pxa/vpac270-pcmcia.c b/arch/arm/mach-pxa/vpac270-pcmcia.c
new file mode 100644
index 000000000000..9fd990c8a5fb
--- /dev/null
+++ b/arch/arm/mach-pxa/vpac270-pcmcia.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/drivers/pcmcia/pxa2xx_vpac270.c
+ *
+ * Driver for Voipac PXA270 PCMCIA and CF sockets
+ *
+ * Copyright (C) 2010-2011 Marek Vasut <marek.vasut@gmail.com>
+ */
+
+#include <linux/gpio.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach-types.h>
+
+#include "vpac270.h"
+
+#include <pcmcia/soc_common.h>
+
+static struct gpio vpac270_pcmcia_gpios[] = {
+	{ GPIO107_VPAC270_PCMCIA_PPEN,	GPIOF_INIT_LOW,	"PCMCIA PPEN" },
+	{ GPIO11_VPAC270_PCMCIA_RESET,	GPIOF_INIT_LOW,	"PCMCIA Reset" },
+};
+
+static struct gpio vpac270_cf_gpios[] = {
+	{ GPIO16_VPAC270_CF_RESET,	GPIOF_INIT_LOW,	"CF Reset" },
+};
+
+static int vpac270_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
+{
+	int ret;
+
+	if (skt->nr == 0) {
+		ret = gpio_request_array(vpac270_pcmcia_gpios,
+				ARRAY_SIZE(vpac270_pcmcia_gpios));
+
+		skt->stat[SOC_STAT_CD].gpio = GPIO84_VPAC270_PCMCIA_CD;
+		skt->stat[SOC_STAT_CD].name = "PCMCIA CD";
+		skt->stat[SOC_STAT_RDY].gpio = GPIO35_VPAC270_PCMCIA_RDY;
+		skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
+	} else {
+		ret = gpio_request_array(vpac270_cf_gpios,
+				ARRAY_SIZE(vpac270_cf_gpios));
+
+		skt->stat[SOC_STAT_CD].gpio = GPIO17_VPAC270_CF_CD;
+		skt->stat[SOC_STAT_CD].name = "CF CD";
+		skt->stat[SOC_STAT_RDY].gpio = GPIO12_VPAC270_CF_RDY;
+		skt->stat[SOC_STAT_RDY].name = "CF Ready";
+	}
+
+	return ret;
+}
+
+static void vpac270_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
+{
+	if (skt->nr == 0)
+		gpio_free_array(vpac270_pcmcia_gpios,
+					ARRAY_SIZE(vpac270_pcmcia_gpios));
+	else
+		gpio_free_array(vpac270_cf_gpios,
+					ARRAY_SIZE(vpac270_cf_gpios));
+}
+
+static void vpac270_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
+					struct pcmcia_state *state)
+{
+	state->vs_3v  = 1;
+	state->vs_Xv  = 0;
+}
+
+static int
+vpac270_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
+				const socket_state_t *state)
+{
+	if (skt->nr == 0) {
+		gpio_set_value(GPIO11_VPAC270_PCMCIA_RESET,
+			(state->flags & SS_RESET));
+		gpio_set_value(GPIO107_VPAC270_PCMCIA_PPEN,
+			!(state->Vcc == 33 || state->Vcc == 50));
+	} else {
+		gpio_set_value(GPIO16_VPAC270_CF_RESET,
+			(state->flags & SS_RESET));
+	}
+
+	return 0;
+}
+
+static struct pcmcia_low_level vpac270_pcmcia_ops = {
+	.owner			= THIS_MODULE,
+
+	.first			= 0,
+	.nr			= 2,
+
+	.hw_init		= vpac270_pcmcia_hw_init,
+	.hw_shutdown		= vpac270_pcmcia_hw_shutdown,
+
+	.socket_state		= vpac270_pcmcia_socket_state,
+	.configure_socket	= vpac270_pcmcia_configure_socket,
+};
+
+static struct platform_device *vpac270_pcmcia_device;
+
+static int __init vpac270_pcmcia_init(void)
+{
+	int ret;
+
+	if (!machine_is_vpac270())
+		return -ENODEV;
+
+	vpac270_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
+	if (!vpac270_pcmcia_device)
+		return -ENOMEM;
+
+	ret = platform_device_add_data(vpac270_pcmcia_device,
+		&vpac270_pcmcia_ops, sizeof(vpac270_pcmcia_ops));
+
+	if (!ret)
+		ret = platform_device_add(vpac270_pcmcia_device);
+
+	if (ret)
+		platform_device_put(vpac270_pcmcia_device);
+
+	return ret;
+}
+
+static void __exit vpac270_pcmcia_exit(void)
+{
+	platform_device_unregister(vpac270_pcmcia_device);
+}
+
+module_init(vpac270_pcmcia_init);
+module_exit(vpac270_pcmcia_exit);
+
+MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
+MODULE_DESCRIPTION("PCMCIA support for Voipac PXA270");
+MODULE_ALIAS("platform:pxa2xx-pcmcia");
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index 7067d1464689..8f74bafcf1f9 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -30,7 +30,7 @@
 
 #include "pxa27x.h"
 #include <linux/platform_data/asoc-pxa.h>
-#include <mach/vpac270.h>
+#include "vpac270.h"
 #include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/video-pxafb.h>
 #include <linux/platform_data/usb-ohci-pxa27x.h>
diff --git a/arch/arm/mach-pxa/vpac270.h b/arch/arm/mach-pxa/vpac270.h
new file mode 100644
index 000000000000..0cd094d8c553
--- /dev/null
+++ b/arch/arm/mach-pxa/vpac270.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * GPIOs and interrupts for Voipac PXA270
+ *
+ * Copyright (C) 2010
+ * Marek Vasut <marek.vasut@gmail.com>
+ */
+
+#ifndef _INCLUDE_VPAC270_H_
+#define _INCLUDE_VPAC270_H_
+
+#define	GPIO1_VPAC270_USER_BTN		1
+
+#define	GPIO15_VPAC270_LED_ORANGE	15
+
+#define	GPIO81_VPAC270_BKL_ON		81
+#define	GPIO83_VPAC270_NL_ON		83
+
+#define	GPIO52_VPAC270_SD_READONLY	52
+#define	GPIO53_VPAC270_SD_DETECT_N	53
+
+#define	GPIO84_VPAC270_PCMCIA_CD	84
+#define	GPIO35_VPAC270_PCMCIA_RDY	35
+#define	GPIO107_VPAC270_PCMCIA_PPEN	107
+#define	GPIO11_VPAC270_PCMCIA_RESET	11
+#define	GPIO17_VPAC270_CF_CD		17
+#define	GPIO12_VPAC270_CF_RDY		12
+#define	GPIO16_VPAC270_CF_RESET		16
+
+#define	GPIO41_VPAC270_UDC_DETECT	41
+
+#define	GPIO114_VPAC270_ETH_IRQ		114
+
+#define	GPIO36_VPAC270_IDE_IRQ		36
+
+#define	GPIO113_VPAC270_TS_IRQ		113
+
+#endif
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 67396e85bb66..2e6c8d156d77 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -47,7 +47,7 @@
 #include <linux/platform_data/video-pxafb.h>
 #include "pm.h"
 #include <linux/platform_data/asoc-pxa.h>
-#include <linux/platform_data/pcmcia-pxa2xx_viper.h>
+#include "viper-pcmcia.h"
 #include "zeus.h"
 #include <mach/smemc.h>
 
diff --git a/drivers/pcmcia/Makefile b/drivers/pcmcia/Makefile
index c43267b18f55..c59ddde42007 100644
--- a/drivers/pcmcia/Makefile
+++ b/drivers/pcmcia/Makefile
@@ -50,18 +50,5 @@ sa1100_cs-$(CONFIG_SA1100_SIMPAD)		+= sa1100_simpad.o
 
 pxa2xx-obj-$(CONFIG_MACH_MAINSTONE)		+= pxa2xx_mainstone.o
 pxa2xx-obj-$(CONFIG_PXA_SHARPSL)		+= pxa2xx_sharpsl.o
-pxa2xx-obj-$(CONFIG_ARCOM_PCMCIA)		+= pxa2xx_viper.o
-pxa2xx-obj-$(CONFIG_TRIZEPS_PCMCIA)		+= pxa2xx_trizeps4.o
-pxa2xx-obj-$(CONFIG_MACH_PALMTX)		+= pxa2xx_palmtx.o
-pxa2xx-obj-$(CONFIG_MACH_PALMTC)		+= pxa2xx_palmtc.o
-pxa2xx-obj-$(CONFIG_MACH_PALMLD)		+= pxa2xx_palmld.o
-pxa2xx-obj-$(CONFIG_MACH_E740)			+= pxa2xx_e740.o
-pxa2xx-obj-$(CONFIG_MACH_VPAC270)		+= pxa2xx_vpac270.o
-pxa2xx-obj-$(CONFIG_MACH_BALLOON3)		+= pxa2xx_balloon3.o
-pxa2xx-obj-$(CONFIG_MACH_COLIBRI)		+= pxa2xx_colibri.o
-pxa2xx-obj-$(CONFIG_MACH_COLIBRI320)		+= pxa2xx_colibri.o
-pxa2xx-obj-$(CONFIG_MACH_H4700)			+= pxa2xx_hx4700.o
-
 obj-$(CONFIG_PCMCIA_PXA2XX)			+= pxa2xx_base.o $(pxa2xx-obj-y)
-
 obj-$(CONFIG_PCMCIA_XXS1500)			+= xxs1500_ss.o
diff --git a/drivers/pcmcia/pxa2xx_balloon3.c b/drivers/pcmcia/pxa2xx_balloon3.c
deleted file mode 100644
index 5fe1da7a50e4..000000000000
--- a/drivers/pcmcia/pxa2xx_balloon3.c
+++ /dev/null
@@ -1,137 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/drivers/pcmcia/pxa2xx_balloon3.c
- *
- * Balloon3 PCMCIA specific routines.
- *
- *  Author:	Nick Bane
- *  Created:	June, 2006
- *  Copyright:	Toby Churchill Ltd
- *  Derived from pxa2xx_mainstone.c, by Nico Pitre
- *
- * Various modification by Marek Vasut <marek.vasut@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/gpio.h>
-#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-
-#include <mach/balloon3.h>
-
-#include <asm/mach-types.h>
-
-#include "soc_common.h"
-
-static int balloon3_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	uint16_t ver;
-
-	ver = __raw_readw(BALLOON3_FPGA_VER);
-	if (ver < 0x4f08)
-		pr_warn("The FPGA code, version 0x%04x, is too old. "
-			"PCMCIA/CF support might be broken in this version!",
-			ver);
-
-	skt->socket.pci_irq = BALLOON3_BP_CF_NRDY_IRQ;
-	skt->stat[SOC_STAT_CD].gpio = BALLOON3_GPIO_S0_CD;
-	skt->stat[SOC_STAT_CD].name = "PCMCIA0 CD";
-	skt->stat[SOC_STAT_BVD1].irq = BALLOON3_BP_NSTSCHG_IRQ;
-	skt->stat[SOC_STAT_BVD1].name = "PCMCIA0 STSCHG";
-
-	return 0;
-}
-
-static unsigned long balloon3_pcmcia_status[2] = {
-	BALLOON3_CF_nSTSCHG_BVD1,
-	BALLOON3_CF_nSTSCHG_BVD1
-};
-
-static void balloon3_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-				    struct pcmcia_state *state)
-{
-	uint16_t status;
-	int flip;
-
-	/* This actually reads the STATUS register */
-	status = __raw_readw(BALLOON3_CF_STATUS_REG);
-	flip = (status ^ balloon3_pcmcia_status[skt->nr])
-		& BALLOON3_CF_nSTSCHG_BVD1;
-	/*
-	 * Workaround for STSCHG which can't be deasserted:
-	 * We therefore disable/enable corresponding IRQs
-	 * as needed to avoid IRQ locks.
-	 */
-	if (flip) {
-		balloon3_pcmcia_status[skt->nr] = status;
-		if (status & BALLOON3_CF_nSTSCHG_BVD1)
-			enable_irq(BALLOON3_BP_NSTSCHG_IRQ);
-		else
-			disable_irq(BALLOON3_BP_NSTSCHG_IRQ);
-	}
-
-	state->ready	= !!(status & BALLOON3_CF_nIRQ);
-	state->bvd1	= !!(status & BALLOON3_CF_nSTSCHG_BVD1);
-	state->bvd2	= 0;	/* not available */
-	state->vs_3v	= 1;	/* Always true its a CF card */
-	state->vs_Xv	= 0;	/* not available */
-}
-
-static int balloon3_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-				       const socket_state_t *state)
-{
-	__raw_writew(BALLOON3_CF_RESET, BALLOON3_CF_CONTROL_REG +
-			((state->flags & SS_RESET) ?
-			BALLOON3_FPGA_SETnCLR : 0));
-	return 0;
-}
-
-static struct pcmcia_low_level balloon3_pcmcia_ops = {
-	.owner			= THIS_MODULE,
-	.hw_init		= balloon3_pcmcia_hw_init,
-	.socket_state		= balloon3_pcmcia_socket_state,
-	.configure_socket	= balloon3_pcmcia_configure_socket,
-	.first			= 0,
-	.nr			= 1,
-};
-
-static struct platform_device *balloon3_pcmcia_device;
-
-static int __init balloon3_pcmcia_init(void)
-{
-	int ret;
-
-	if (!machine_is_balloon3())
-		return -ENODEV;
-
-	balloon3_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!balloon3_pcmcia_device)
-		return -ENOMEM;
-
-	ret = platform_device_add_data(balloon3_pcmcia_device,
-			&balloon3_pcmcia_ops, sizeof(balloon3_pcmcia_ops));
-
-	if (!ret)
-		ret = platform_device_add(balloon3_pcmcia_device);
-
-	if (ret)
-		platform_device_put(balloon3_pcmcia_device);
-
-	return ret;
-}
-
-static void __exit balloon3_pcmcia_exit(void)
-{
-	platform_device_unregister(balloon3_pcmcia_device);
-}
-
-module_init(balloon3_pcmcia_init);
-module_exit(balloon3_pcmcia_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Nick Bane <nick@cecomputing.co.uk>");
-MODULE_ALIAS("platform:pxa2xx-pcmcia");
-MODULE_DESCRIPTION("Balloon3 board CF/PCMCIA driver");
diff --git a/drivers/pcmcia/pxa2xx_colibri.c b/drivers/pcmcia/pxa2xx_colibri.c
deleted file mode 100644
index f0f725e99604..000000000000
--- a/drivers/pcmcia/pxa2xx_colibri.c
+++ /dev/null
@@ -1,165 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/drivers/pcmcia/pxa2xx_colibri.c
- *
- * Driver for Toradex Colibri PXA270 CF socket
- *
- * Copyright (C) 2010 Marek Vasut <marek.vasut@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/gpio.h>
-
-#include <asm/mach-types.h>
-
-#include "soc_common.h"
-
-#define	COLIBRI270_RESET_GPIO	53
-#define	COLIBRI270_PPEN_GPIO	107
-#define	COLIBRI270_BVD1_GPIO	83
-#define	COLIBRI270_BVD2_GPIO	82
-#define	COLIBRI270_DETECT_GPIO	84
-#define	COLIBRI270_READY_GPIO	1
-
-#define	COLIBRI320_RESET_GPIO	77
-#define	COLIBRI320_PPEN_GPIO	57
-#define	COLIBRI320_BVD1_GPIO	53
-#define	COLIBRI320_BVD2_GPIO	79
-#define	COLIBRI320_DETECT_GPIO	81
-#define	COLIBRI320_READY_GPIO	29
-
-enum {
-	DETECT = 0,
-	READY = 1,
-	BVD1 = 2,
-	BVD2 = 3,
-	PPEN = 4,
-	RESET = 5,
-};
-
-/* Contents of this array are configured on-the-fly in init function */
-static struct gpio colibri_pcmcia_gpios[] = {
-	{ 0,	GPIOF_IN,	"PCMCIA Detect" },
-	{ 0,	GPIOF_IN,	"PCMCIA Ready" },
-	{ 0,	GPIOF_IN,	"PCMCIA BVD1" },
-	{ 0,	GPIOF_IN,	"PCMCIA BVD2" },
-	{ 0,	GPIOF_INIT_LOW,	"PCMCIA PPEN" },
-	{ 0,	GPIOF_INIT_HIGH,"PCMCIA Reset" },
-};
-
-static int colibri_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	int ret;
-
-	ret = gpio_request_array(colibri_pcmcia_gpios,
-				ARRAY_SIZE(colibri_pcmcia_gpios));
-	if (ret)
-		goto err1;
-
-	skt->socket.pci_irq = gpio_to_irq(colibri_pcmcia_gpios[READY].gpio);
-	skt->stat[SOC_STAT_CD].irq = gpio_to_irq(colibri_pcmcia_gpios[DETECT].gpio);
-	skt->stat[SOC_STAT_CD].name = "PCMCIA CD";
-
-err1:
-	return ret;
-}
-
-static void colibri_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
-{
-	gpio_free_array(colibri_pcmcia_gpios,
-			ARRAY_SIZE(colibri_pcmcia_gpios));
-}
-
-static void colibri_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-					struct pcmcia_state *state)
-{
-
-	state->detect = !!gpio_get_value(colibri_pcmcia_gpios[DETECT].gpio);
-	state->ready  = !!gpio_get_value(colibri_pcmcia_gpios[READY].gpio);
-	state->bvd1   = !!gpio_get_value(colibri_pcmcia_gpios[BVD1].gpio);
-	state->bvd2   = !!gpio_get_value(colibri_pcmcia_gpios[BVD2].gpio);
-	state->vs_3v  = 1;
-	state->vs_Xv  = 0;
-}
-
-static int
-colibri_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-				const socket_state_t *state)
-{
-	gpio_set_value(colibri_pcmcia_gpios[PPEN].gpio,
-			!(state->Vcc == 33 && state->Vpp < 50));
-	gpio_set_value(colibri_pcmcia_gpios[RESET].gpio,
-			state->flags & SS_RESET);
-	return 0;
-}
-
-static struct pcmcia_low_level colibri_pcmcia_ops = {
-	.owner			= THIS_MODULE,
-
-	.first			= 0,
-	.nr			= 1,
-
-	.hw_init		= colibri_pcmcia_hw_init,
-	.hw_shutdown		= colibri_pcmcia_hw_shutdown,
-
-	.socket_state		= colibri_pcmcia_socket_state,
-	.configure_socket	= colibri_pcmcia_configure_socket,
-};
-
-static struct platform_device *colibri_pcmcia_device;
-
-static int __init colibri_pcmcia_init(void)
-{
-	int ret;
-
-	if (!machine_is_colibri() && !machine_is_colibri320())
-		return -ENODEV;
-
-	colibri_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!colibri_pcmcia_device)
-		return -ENOMEM;
-
-	/* Colibri PXA270 */
-	if (machine_is_colibri()) {
-		colibri_pcmcia_gpios[RESET].gpio	= COLIBRI270_RESET_GPIO;
-		colibri_pcmcia_gpios[PPEN].gpio		= COLIBRI270_PPEN_GPIO;
-		colibri_pcmcia_gpios[BVD1].gpio		= COLIBRI270_BVD1_GPIO;
-		colibri_pcmcia_gpios[BVD2].gpio		= COLIBRI270_BVD2_GPIO;
-		colibri_pcmcia_gpios[DETECT].gpio	= COLIBRI270_DETECT_GPIO;
-		colibri_pcmcia_gpios[READY].gpio	= COLIBRI270_READY_GPIO;
-	/* Colibri PXA320 */
-	} else if (machine_is_colibri320()) {
-		colibri_pcmcia_gpios[RESET].gpio	= COLIBRI320_RESET_GPIO;
-		colibri_pcmcia_gpios[PPEN].gpio		= COLIBRI320_PPEN_GPIO;
-		colibri_pcmcia_gpios[BVD1].gpio		= COLIBRI320_BVD1_GPIO;
-		colibri_pcmcia_gpios[BVD2].gpio		= COLIBRI320_BVD2_GPIO;
-		colibri_pcmcia_gpios[DETECT].gpio	= COLIBRI320_DETECT_GPIO;
-		colibri_pcmcia_gpios[READY].gpio	= COLIBRI320_READY_GPIO;
-	}
-
-	ret = platform_device_add_data(colibri_pcmcia_device,
-		&colibri_pcmcia_ops, sizeof(colibri_pcmcia_ops));
-
-	if (!ret)
-		ret = platform_device_add(colibri_pcmcia_device);
-
-	if (ret)
-		platform_device_put(colibri_pcmcia_device);
-
-	return ret;
-}
-
-static void __exit colibri_pcmcia_exit(void)
-{
-	platform_device_unregister(colibri_pcmcia_device);
-}
-
-module_init(colibri_pcmcia_init);
-module_exit(colibri_pcmcia_exit);
-
-MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
-MODULE_DESCRIPTION("PCMCIA support for Toradex Colibri PXA270/PXA320");
-MODULE_ALIAS("platform:pxa2xx-pcmcia");
-MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/pxa2xx_e740.c b/drivers/pcmcia/pxa2xx_e740.c
deleted file mode 100644
index 72caa6d05ab9..000000000000
--- a/drivers/pcmcia/pxa2xx_e740.c
+++ /dev/null
@@ -1,127 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Toshiba e740 PCMCIA specific routines.
- *
- * (c) 2004 Ian Molton <spyro@f2s.com>
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/gpio.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-
-#include <mach/eseries-gpio.h>
-
-#include <asm/irq.h>
-#include <asm/mach-types.h>
-
-#include "soc_common.h"
-
-static int e740_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	if (skt->nr == 0) {
-		skt->stat[SOC_STAT_CD].gpio = GPIO_E740_PCMCIA_CD0;
-		skt->stat[SOC_STAT_CD].name = "CF card detect";
-		skt->stat[SOC_STAT_RDY].gpio = GPIO_E740_PCMCIA_RDY0;
-		skt->stat[SOC_STAT_RDY].name = "CF ready";
-	} else {
-		skt->stat[SOC_STAT_CD].gpio = GPIO_E740_PCMCIA_CD1;
-		skt->stat[SOC_STAT_CD].name = "Wifi switch";
-		skt->stat[SOC_STAT_RDY].gpio = GPIO_E740_PCMCIA_RDY1;
-		skt->stat[SOC_STAT_RDY].name = "Wifi ready";
-	}
-
-	return 0;
-}
-
-static void e740_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-					struct pcmcia_state *state)
-{
-	state->vs_3v  = 1;
-	state->vs_Xv  = 0;
-}
-
-static int e740_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-					const socket_state_t *state)
-{
-	if (state->flags & SS_RESET) {
-		if (skt->nr == 0)
-			gpio_set_value(GPIO_E740_PCMCIA_RST0, 1);
-		else
-			gpio_set_value(GPIO_E740_PCMCIA_RST1, 1);
-	} else {
-		if (skt->nr == 0)
-			gpio_set_value(GPIO_E740_PCMCIA_RST0, 0);
-		else
-			gpio_set_value(GPIO_E740_PCMCIA_RST1, 0);
-	}
-
-	switch (state->Vcc) {
-	case 0:	/* Socket off */
-		if (skt->nr == 0)
-			gpio_set_value(GPIO_E740_PCMCIA_PWR0, 0);
-		else
-			gpio_set_value(GPIO_E740_PCMCIA_PWR1, 1);
-		break;
-	case 50:
-	case 33: /* socket on */
-		if (skt->nr == 0)
-			gpio_set_value(GPIO_E740_PCMCIA_PWR0, 1);
-		else
-			gpio_set_value(GPIO_E740_PCMCIA_PWR1, 0);
-		break;
-	default:
-		printk(KERN_ERR "e740_cs: Unsupported Vcc: %d\n", state->Vcc);
-	}
-
-	return 0;
-}
-
-static struct pcmcia_low_level e740_pcmcia_ops = {
-	.owner            = THIS_MODULE,
-	.hw_init          = e740_pcmcia_hw_init,
-	.socket_state     = e740_pcmcia_socket_state,
-	.configure_socket = e740_pcmcia_configure_socket,
-	.nr               = 2,
-};
-
-static struct platform_device *e740_pcmcia_device;
-
-static int __init e740_pcmcia_init(void)
-{
-	int ret;
-
-	if (!machine_is_e740())
-		return -ENODEV;
-
-	e740_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!e740_pcmcia_device)
-		return -ENOMEM;
-
-	ret = platform_device_add_data(e740_pcmcia_device, &e740_pcmcia_ops,
-					sizeof(e740_pcmcia_ops));
-
-	if (!ret)
-		ret = platform_device_add(e740_pcmcia_device);
-
-	if (ret)
-		platform_device_put(e740_pcmcia_device);
-
-	return ret;
-}
-
-static void __exit e740_pcmcia_exit(void)
-{
-	platform_device_unregister(e740_pcmcia_device);
-}
-
-module_init(e740_pcmcia_init);
-module_exit(e740_pcmcia_exit);
-
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Ian Molton <spyro@f2s.com>");
-MODULE_ALIAS("platform:pxa2xx-pcmcia");
-MODULE_DESCRIPTION("e740 PCMCIA platform support");
diff --git a/drivers/pcmcia/pxa2xx_hx4700.c b/drivers/pcmcia/pxa2xx_hx4700.c
deleted file mode 100644
index 87b6a1639d94..000000000000
--- a/drivers/pcmcia/pxa2xx_hx4700.c
+++ /dev/null
@@ -1,118 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Copyright (C) 2012 Paul Parsons <lost.distance@yahoo.com>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/err.h>
-#include <linux/gpio.h>
-#include <linux/irq.h>
-
-#include <asm/mach-types.h>
-#include <mach/hx4700.h>
-
-#include "soc_common.h"
-
-static struct gpio gpios[] = {
-	{ GPIO114_HX4700_CF_RESET,    GPIOF_OUT_INIT_LOW,   "CF reset"        },
-	{ EGPIO4_CF_3V3_ON,           GPIOF_OUT_INIT_LOW,   "CF 3.3V enable"  },
-};
-
-static int hx4700_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	int ret;
-
-	ret = gpio_request_array(gpios, ARRAY_SIZE(gpios));
-	if (ret)
-		goto out;
-
-	/*
-	 * IRQ type must be set before soc_pcmcia_hw_init() calls request_irq().
-	 * The asic3 default IRQ type is level trigger low level detect, exactly
-	 * the the signal present on GPIOD4_CF_nCD when a CF card is inserted.
-	 * If the IRQ type is not changed, the asic3 interrupt handler will loop
-	 * repeatedly because it is unable to clear the level trigger interrupt.
-	 */
-	irq_set_irq_type(gpio_to_irq(GPIOD4_CF_nCD), IRQ_TYPE_EDGE_BOTH);
-
-	skt->stat[SOC_STAT_CD].gpio = GPIOD4_CF_nCD;
-	skt->stat[SOC_STAT_CD].name = "PCMCIA CD";
-	skt->stat[SOC_STAT_RDY].gpio = GPIO60_HX4700_CF_RNB;
-	skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
-
-out:
-	return ret;
-}
-
-static void hx4700_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
-{
-	gpio_free_array(gpios, ARRAY_SIZE(gpios));
-}
-
-static void hx4700_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-	struct pcmcia_state *state)
-{
-	state->vs_3v = 1;
-	state->vs_Xv = 0;
-}
-
-static int hx4700_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-	const socket_state_t *state)
-{
-	switch (state->Vcc) {
-	case 0:
-		gpio_set_value(EGPIO4_CF_3V3_ON, 0);
-		break;
-	case 33:
-		gpio_set_value(EGPIO4_CF_3V3_ON, 1);
-		break;
-	default:
-		printk(KERN_ERR "pcmcia: Unsupported Vcc: %d\n", state->Vcc);
-		return -EINVAL;
-	}
-
-	gpio_set_value(GPIO114_HX4700_CF_RESET, (state->flags & SS_RESET) != 0);
-
-	return 0;
-}
-
-static struct pcmcia_low_level hx4700_pcmcia_ops = {
-	.owner          = THIS_MODULE,
-	.nr             = 1,
-	.hw_init        = hx4700_pcmcia_hw_init,
-	.hw_shutdown    = hx4700_pcmcia_hw_shutdown,
-	.socket_state   = hx4700_pcmcia_socket_state,
-	.configure_socket = hx4700_pcmcia_configure_socket,
-};
-
-static struct platform_device *hx4700_pcmcia_device;
-
-static int __init hx4700_pcmcia_init(void)
-{
-	struct platform_device *pdev;
-
-	if (!machine_is_h4700())
-		return -ENODEV;
-
-	pdev = platform_device_register_data(NULL, "pxa2xx-pcmcia", -1,
-		&hx4700_pcmcia_ops, sizeof(hx4700_pcmcia_ops));
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
-
-	hx4700_pcmcia_device = pdev;
-
-	return 0;
-}
-
-static void __exit hx4700_pcmcia_exit(void)
-{
-	platform_device_unregister(hx4700_pcmcia_device);
-}
-
-module_init(hx4700_pcmcia_init);
-module_exit(hx4700_pcmcia_exit);
-
-MODULE_AUTHOR("Paul Parsons <lost.distance@yahoo.com>");
-MODULE_DESCRIPTION("HP iPAQ hx4700 PCMCIA driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/pxa2xx_palmld.c b/drivers/pcmcia/pxa2xx_palmld.c
deleted file mode 100644
index cfff41ac9ca2..000000000000
--- a/drivers/pcmcia/pxa2xx_palmld.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/drivers/pcmcia/pxa2xx_palmld.c
- *
- * Driver for Palm LifeDrive PCMCIA
- *
- * Copyright (C) 2006 Alex Osborne <ato@meshy.org>
- * Copyright (C) 2007-2011 Marek Vasut <marek.vasut@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/gpio.h>
-
-#include <asm/mach-types.h>
-#include <mach/palmld.h>
-#include "soc_common.h"
-
-static struct gpio palmld_pcmcia_gpios[] = {
-	{ GPIO_NR_PALMLD_PCMCIA_POWER,	GPIOF_INIT_LOW,	"PCMCIA Power" },
-	{ GPIO_NR_PALMLD_PCMCIA_RESET,	GPIOF_INIT_HIGH,"PCMCIA Reset" },
-};
-
-static int palmld_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	int ret;
-
-	ret = gpio_request_array(palmld_pcmcia_gpios,
-				ARRAY_SIZE(palmld_pcmcia_gpios));
-
-	skt->stat[SOC_STAT_RDY].gpio = GPIO_NR_PALMLD_PCMCIA_READY;
-	skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
-
-	return ret;
-}
-
-static void palmld_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
-{
-	gpio_free_array(palmld_pcmcia_gpios, ARRAY_SIZE(palmld_pcmcia_gpios));
-}
-
-static void palmld_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-					struct pcmcia_state *state)
-{
-	state->detect = 1; /* always inserted */
-	state->vs_3v  = 1;
-	state->vs_Xv  = 0;
-}
-
-static int palmld_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-					const socket_state_t *state)
-{
-	gpio_set_value(GPIO_NR_PALMLD_PCMCIA_POWER, 1);
-	gpio_set_value(GPIO_NR_PALMLD_PCMCIA_RESET,
-			!!(state->flags & SS_RESET));
-
-	return 0;
-}
-
-static struct pcmcia_low_level palmld_pcmcia_ops = {
-	.owner			= THIS_MODULE,
-
-	.first			= 1,
-	.nr			= 1,
-
-	.hw_init		= palmld_pcmcia_hw_init,
-	.hw_shutdown		= palmld_pcmcia_hw_shutdown,
-
-	.socket_state		= palmld_pcmcia_socket_state,
-	.configure_socket	= palmld_pcmcia_configure_socket,
-};
-
-static struct platform_device *palmld_pcmcia_device;
-
-static int __init palmld_pcmcia_init(void)
-{
-	int ret;
-
-	if (!machine_is_palmld())
-		return -ENODEV;
-
-	palmld_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!palmld_pcmcia_device)
-		return -ENOMEM;
-
-	ret = platform_device_add_data(palmld_pcmcia_device, &palmld_pcmcia_ops,
-					sizeof(palmld_pcmcia_ops));
-
-	if (!ret)
-		ret = platform_device_add(palmld_pcmcia_device);
-
-	if (ret)
-		platform_device_put(palmld_pcmcia_device);
-
-	return ret;
-}
-
-static void __exit palmld_pcmcia_exit(void)
-{
-	platform_device_unregister(palmld_pcmcia_device);
-}
-
-module_init(palmld_pcmcia_init);
-module_exit(palmld_pcmcia_exit);
-
-MODULE_AUTHOR("Alex Osborne <ato@meshy.org>,"
-	    " Marek Vasut <marek.vasut@gmail.com>");
-MODULE_DESCRIPTION("PCMCIA support for Palm LifeDrive");
-MODULE_ALIAS("platform:pxa2xx-pcmcia");
-MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/pxa2xx_palmtc.c b/drivers/pcmcia/pxa2xx_palmtc.c
deleted file mode 100644
index 8fe05613ed04..000000000000
--- a/drivers/pcmcia/pxa2xx_palmtc.c
+++ /dev/null
@@ -1,162 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/drivers/pcmcia/pxa2xx_palmtc.c
- *
- * Driver for Palm Tungsten|C PCMCIA
- *
- * Copyright (C) 2008 Alex Osborne <ato@meshy.org>
- * Copyright (C) 2009-2011 Marek Vasut <marek.vasut@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/gpio.h>
-#include <linux/delay.h>
-
-#include <asm/mach-types.h>
-#include <mach/palmtc.h>
-#include "soc_common.h"
-
-static struct gpio palmtc_pcmcia_gpios[] = {
-	{ GPIO_NR_PALMTC_PCMCIA_POWER1,	GPIOF_INIT_LOW,	"PCMCIA Power 1" },
-	{ GPIO_NR_PALMTC_PCMCIA_POWER2,	GPIOF_INIT_LOW,	"PCMCIA Power 2" },
-	{ GPIO_NR_PALMTC_PCMCIA_POWER3,	GPIOF_INIT_LOW,	"PCMCIA Power 3" },
-	{ GPIO_NR_PALMTC_PCMCIA_RESET,	GPIOF_INIT_HIGH,"PCMCIA Reset" },
-	{ GPIO_NR_PALMTC_PCMCIA_PWRREADY, GPIOF_IN,	"PCMCIA Power Ready" },
-};
-
-static int palmtc_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	int ret;
-
-	ret = gpio_request_array(palmtc_pcmcia_gpios,
-				ARRAY_SIZE(palmtc_pcmcia_gpios));
-
-	skt->stat[SOC_STAT_RDY].gpio = GPIO_NR_PALMTC_PCMCIA_READY;
-	skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
-
-	return ret;
-}
-
-static void palmtc_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
-{
-	gpio_free_array(palmtc_pcmcia_gpios, ARRAY_SIZE(palmtc_pcmcia_gpios));
-}
-
-static void palmtc_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-					struct pcmcia_state *state)
-{
-	state->detect = 1; /* always inserted */
-	state->vs_3v  = 1;
-	state->vs_Xv  = 0;
-}
-
-static int palmtc_wifi_powerdown(void)
-{
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_RESET, 1);
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER2, 0);
-	mdelay(40);
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER1, 0);
-	return 0;
-}
-
-static int palmtc_wifi_powerup(void)
-{
-	int timeout = 50;
-
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER3, 1);
-	mdelay(50);
-
-	/* Power up the card, 1.8V first, after a while 3.3V */
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER1, 1);
-	mdelay(100);
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER2, 1);
-
-	/* Wait till the card is ready */
-	while (!gpio_get_value(GPIO_NR_PALMTC_PCMCIA_PWRREADY) &&
-		timeout) {
-		mdelay(1);
-		timeout--;
-	}
-
-	/* Power down the WiFi in case of error */
-	if (!timeout) {
-		palmtc_wifi_powerdown();
-		return 1;
-	}
-
-	/* Reset the card */
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_RESET, 1);
-	mdelay(20);
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_RESET, 0);
-	mdelay(25);
-
-	gpio_set_value(GPIO_NR_PALMTC_PCMCIA_POWER3, 0);
-
-	return 0;
-}
-
-static int palmtc_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-					const socket_state_t *state)
-{
-	int ret = 1;
-
-	if (state->Vcc == 0)
-		ret = palmtc_wifi_powerdown();
-	else if (state->Vcc == 33)
-		ret = palmtc_wifi_powerup();
-
-	return ret;
-}
-
-static struct pcmcia_low_level palmtc_pcmcia_ops = {
-	.owner			= THIS_MODULE,
-
-	.first			= 0,
-	.nr			= 1,
-
-	.hw_init		= palmtc_pcmcia_hw_init,
-	.hw_shutdown		= palmtc_pcmcia_hw_shutdown,
-
-	.socket_state		= palmtc_pcmcia_socket_state,
-	.configure_socket	= palmtc_pcmcia_configure_socket,
-};
-
-static struct platform_device *palmtc_pcmcia_device;
-
-static int __init palmtc_pcmcia_init(void)
-{
-	int ret;
-
-	if (!machine_is_palmtc())
-		return -ENODEV;
-
-	palmtc_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!palmtc_pcmcia_device)
-		return -ENOMEM;
-
-	ret = platform_device_add_data(palmtc_pcmcia_device, &palmtc_pcmcia_ops,
-					sizeof(palmtc_pcmcia_ops));
-
-	if (!ret)
-		ret = platform_device_add(palmtc_pcmcia_device);
-
-	if (ret)
-		platform_device_put(palmtc_pcmcia_device);
-
-	return ret;
-}
-
-static void __exit palmtc_pcmcia_exit(void)
-{
-	platform_device_unregister(palmtc_pcmcia_device);
-}
-
-module_init(palmtc_pcmcia_init);
-module_exit(palmtc_pcmcia_exit);
-
-MODULE_AUTHOR("Alex Osborne <ato@meshy.org>,"
-	    " Marek Vasut <marek.vasut@gmail.com>");
-MODULE_DESCRIPTION("PCMCIA support for Palm Tungsten|C");
-MODULE_ALIAS("platform:pxa2xx-pcmcia");
-MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/pxa2xx_palmtx.c b/drivers/pcmcia/pxa2xx_palmtx.c
deleted file mode 100644
index c449ca72cb87..000000000000
--- a/drivers/pcmcia/pxa2xx_palmtx.c
+++ /dev/null
@@ -1,111 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/drivers/pcmcia/pxa2xx_palmtx.c
- *
- * Driver for Palm T|X PCMCIA
- *
- * Copyright (C) 2007-2011 Marek Vasut <marek.vasut@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/gpio.h>
-
-#include <asm/mach-types.h>
-#include <mach/palmtx.h>
-#include "soc_common.h"
-
-static struct gpio palmtx_pcmcia_gpios[] = {
-	{ GPIO_NR_PALMTX_PCMCIA_POWER1,	GPIOF_INIT_LOW,	"PCMCIA Power 1" },
-	{ GPIO_NR_PALMTX_PCMCIA_POWER2,	GPIOF_INIT_LOW,	"PCMCIA Power 2" },
-	{ GPIO_NR_PALMTX_PCMCIA_RESET,	GPIOF_INIT_HIGH,"PCMCIA Reset" },
-};
-
-static int palmtx_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	int ret;
-
-	ret = gpio_request_array(palmtx_pcmcia_gpios,
-				ARRAY_SIZE(palmtx_pcmcia_gpios));
-
-	skt->stat[SOC_STAT_RDY].gpio = GPIO_NR_PALMTX_PCMCIA_READY;
-	skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
-
-	return ret;
-}
-
-static void palmtx_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
-{
-	gpio_free_array(palmtx_pcmcia_gpios, ARRAY_SIZE(palmtx_pcmcia_gpios));
-}
-
-static void palmtx_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-					struct pcmcia_state *state)
-{
-	state->detect = 1; /* always inserted */
-	state->vs_3v  = 1;
-	state->vs_Xv  = 0;
-}
-
-static int
-palmtx_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-				const socket_state_t *state)
-{
-	gpio_set_value(GPIO_NR_PALMTX_PCMCIA_POWER1, 1);
-	gpio_set_value(GPIO_NR_PALMTX_PCMCIA_POWER2, 1);
-	gpio_set_value(GPIO_NR_PALMTX_PCMCIA_RESET,
-			!!(state->flags & SS_RESET));
-
-	return 0;
-}
-
-static struct pcmcia_low_level palmtx_pcmcia_ops = {
-	.owner			= THIS_MODULE,
-
-	.first			= 0,
-	.nr			= 1,
-
-	.hw_init		= palmtx_pcmcia_hw_init,
-	.hw_shutdown		= palmtx_pcmcia_hw_shutdown,
-
-	.socket_state		= palmtx_pcmcia_socket_state,
-	.configure_socket	= palmtx_pcmcia_configure_socket,
-};
-
-static struct platform_device *palmtx_pcmcia_device;
-
-static int __init palmtx_pcmcia_init(void)
-{
-	int ret;
-
-	if (!machine_is_palmtx())
-		return -ENODEV;
-
-	palmtx_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!palmtx_pcmcia_device)
-		return -ENOMEM;
-
-	ret = platform_device_add_data(palmtx_pcmcia_device, &palmtx_pcmcia_ops,
-					sizeof(palmtx_pcmcia_ops));
-
-	if (!ret)
-		ret = platform_device_add(palmtx_pcmcia_device);
-
-	if (ret)
-		platform_device_put(palmtx_pcmcia_device);
-
-	return ret;
-}
-
-static void __exit palmtx_pcmcia_exit(void)
-{
-	platform_device_unregister(palmtx_pcmcia_device);
-}
-
-module_init(palmtx_pcmcia_init);
-module_exit(palmtx_pcmcia_exit);
-
-MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
-MODULE_DESCRIPTION("PCMCIA support for Palm T|X");
-MODULE_ALIAS("platform:pxa2xx-pcmcia");
-MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/pxa2xx_sharpsl.c b/drivers/pcmcia/pxa2xx_sharpsl.c
index 66fe1d1af12a..b3ba858f70cb 100644
--- a/drivers/pcmcia/pxa2xx_sharpsl.c
+++ b/drivers/pcmcia/pxa2xx_sharpsl.c
@@ -18,7 +18,7 @@
 #include <asm/irq.h>
 #include <asm/hardware/scoop.h>
 
-#include "soc_common.h"
+#include <pcmcia/soc_common.h>
 
 #define	NO_KEEP_VS 0x0001
 #define SCOOP_DEV platform_scoop_config->devs
diff --git a/drivers/pcmcia/pxa2xx_trizeps4.c b/drivers/pcmcia/pxa2xx_trizeps4.c
deleted file mode 100644
index 6db8fe880ed4..000000000000
--- a/drivers/pcmcia/pxa2xx_trizeps4.c
+++ /dev/null
@@ -1,200 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/drivers/pcmcia/pxa2xx_trizeps4.c
- *
- * TRIZEPS PCMCIA specific routines.
- *
- * Author:	Jürgen Schindele
- * Created:	20 02, 2006
- * Copyright:	Jürgen Schindele
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/gpio.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-
-#include <asm/mach-types.h>
-#include <asm/irq.h>
-
-#include <mach/pxa2xx-regs.h>
-#include <mach/trizeps4.h>
-
-#include "soc_common.h"
-
-extern void board_pcmcia_power(int power);
-
-static int trizeps_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	/* we dont have voltage/card/ready detection
-	 * so we dont need interrupts for it
-	 */
-	switch (skt->nr) {
-	case 0:
-		skt->stat[SOC_STAT_CD].gpio = GPIO_PCD;
-		skt->stat[SOC_STAT_CD].name = "cs0_cd";
-		skt->stat[SOC_STAT_RDY].gpio = GPIO_PRDY;
-		skt->stat[SOC_STAT_RDY].name = "cs0_rdy";
-		break;
-	default:
-		break;
-	}
-	/* release the reset of this card */
-	pr_debug("%s: sock %d irq %d\n", __func__, skt->nr, skt->socket.pci_irq);
-
-	return 0;
-}
-
-static unsigned long trizeps_pcmcia_status[2];
-
-static void trizeps_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-				struct pcmcia_state *state)
-{
-	unsigned short status = 0, change;
-	status = CFSR_readw();
-	change = (status ^ trizeps_pcmcia_status[skt->nr]) &
-				ConXS_CFSR_BVD_MASK;
-	if (change) {
-		trizeps_pcmcia_status[skt->nr] = status;
-		if (status & ConXS_CFSR_BVD1) {
-			/* enable_irq empty */
-		} else {
-			/* disable_irq empty */
-		}
-	}
-
-	switch (skt->nr) {
-	case 0:
-		/* just fill in fix states */
-		state->bvd1   = (status & ConXS_CFSR_BVD1) ? 1 : 0;
-		state->bvd2   = (status & ConXS_CFSR_BVD2) ? 1 : 0;
-		state->vs_3v  = (status & ConXS_CFSR_VS1) ? 0 : 1;
-		state->vs_Xv  = (status & ConXS_CFSR_VS2) ? 0 : 1;
-		break;
-
-#ifndef CONFIG_MACH_TRIZEPS_CONXS
-	/* on ConXS we only have one slot. Second is inactive */
-	case 1:
-		state->detect = 0;
-		state->ready  = 0;
-		state->bvd1   = 0;
-		state->bvd2   = 0;
-		state->vs_3v  = 0;
-		state->vs_Xv  = 0;
-		break;
-
-#endif
-	}
-}
-
-static int trizeps_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-				const socket_state_t *state)
-{
-	int ret = 0;
-	unsigned short power = 0;
-
-	/* we do nothing here just check a bit */
-	switch (state->Vcc) {
-	case 0:  power &= 0xfc; break;
-	case 33: power |= ConXS_BCR_S0_VCC_3V3; break;
-	case 50:
-		pr_err("%s(): Vcc 5V not supported in socket\n", __func__);
-		break;
-	default:
-		pr_err("%s(): bad Vcc %u\n", __func__, state->Vcc);
-		ret = -1;
-	}
-
-	switch (state->Vpp) {
-	case 0:  power &= 0xf3; break;
-	case 33: power |= ConXS_BCR_S0_VPP_3V3; break;
-	case 120:
-		pr_err("%s(): Vpp 12V not supported in socket\n", __func__);
-		break;
-	default:
-		if (state->Vpp != state->Vcc) {
-			pr_err("%s(): bad Vpp %u\n", __func__, state->Vpp);
-			ret = -1;
-		}
-	}
-
-	switch (skt->nr) {
-	case 0:			 /* we only have 3.3V */
-		board_pcmcia_power(power);
-		break;
-
-#ifndef CONFIG_MACH_TRIZEPS_CONXS
-	/* on ConXS we only have one slot. Second is inactive */
-	case 1:
-#endif
-	default:
-		break;
-	}
-
-	return ret;
-}
-
-static void trizeps_pcmcia_socket_init(struct soc_pcmcia_socket *skt)
-{
-	/* default is on */
-	board_pcmcia_power(0x9);
-}
-
-static void trizeps_pcmcia_socket_suspend(struct soc_pcmcia_socket *skt)
-{
-	board_pcmcia_power(0x0);
-}
-
-static struct pcmcia_low_level trizeps_pcmcia_ops = {
-	.owner			= THIS_MODULE,
-	.hw_init		= trizeps_pcmcia_hw_init,
-	.socket_state		= trizeps_pcmcia_socket_state,
-	.configure_socket	= trizeps_pcmcia_configure_socket,
-	.socket_init		= trizeps_pcmcia_socket_init,
-	.socket_suspend		= trizeps_pcmcia_socket_suspend,
-#ifdef CONFIG_MACH_TRIZEPS_CONXS
-	.nr			= 1,
-#else
-	.nr			= 2,
-#endif
-	.first			= 0,
-};
-
-static struct platform_device *trizeps_pcmcia_device;
-
-static int __init trizeps_pcmcia_init(void)
-{
-	int ret;
-
-	if (!machine_is_trizeps4() && !machine_is_trizeps4wl())
-		return -ENODEV;
-
-	trizeps_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!trizeps_pcmcia_device)
-		return -ENOMEM;
-
-	ret = platform_device_add_data(trizeps_pcmcia_device,
-			&trizeps_pcmcia_ops, sizeof(trizeps_pcmcia_ops));
-
-	if (ret == 0)
-		ret = platform_device_add(trizeps_pcmcia_device);
-
-	if (ret)
-		platform_device_put(trizeps_pcmcia_device);
-
-	return ret;
-}
-
-static void __exit trizeps_pcmcia_exit(void)
-{
-	platform_device_unregister(trizeps_pcmcia_device);
-}
-
-fs_initcall(trizeps_pcmcia_init);
-module_exit(trizeps_pcmcia_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Juergen Schindele");
-MODULE_ALIAS("platform:pxa2xx-pcmcia");
diff --git a/drivers/pcmcia/pxa2xx_viper.c b/drivers/pcmcia/pxa2xx_viper.c
deleted file mode 100644
index 7ac6647d286e..000000000000
--- a/drivers/pcmcia/pxa2xx_viper.c
+++ /dev/null
@@ -1,182 +0,0 @@
-/*
- * Viper/Zeus PCMCIA support
- *   Copyright 2004 Arcom Control Systems
- *
- * Maintained by Marc Zyngier <maz@misterjones.org>
- *
- * Based on:
- *   iPAQ h2200 PCMCIA support
- *   Copyright 2004 Koen Kooi <koen@vestingbar.nl>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive for
- * more details.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/gpio.h>
-
-#include <pcmcia/ss.h>
-
-#include <asm/irq.h>
-
-#include <linux/platform_data/pcmcia-pxa2xx_viper.h>
-
-#include "soc_common.h"
-#include "pxa2xx_base.h"
-
-static struct platform_device *arcom_pcmcia_dev;
-
-static inline struct arcom_pcmcia_pdata *viper_get_pdata(void)
-{
-	return arcom_pcmcia_dev->dev.platform_data;
-}
-
-static int viper_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	struct arcom_pcmcia_pdata *pdata = viper_get_pdata();
-	unsigned long flags;
-
-	skt->stat[SOC_STAT_CD].gpio = pdata->cd_gpio;
-	skt->stat[SOC_STAT_CD].name = "PCMCIA_CD";
-	skt->stat[SOC_STAT_RDY].gpio = pdata->rdy_gpio;
-	skt->stat[SOC_STAT_RDY].name = "CF ready";
-
-	if (gpio_request(pdata->pwr_gpio, "CF power"))
-		goto err_request_pwr;
-
-	local_irq_save(flags);
-
-	if (gpio_direction_output(pdata->pwr_gpio, 0)) {
-		local_irq_restore(flags);
-		goto err_dir;
-	}
-
-	local_irq_restore(flags);
-
-	return 0;
-
-err_dir:
-	gpio_free(pdata->pwr_gpio);
-err_request_pwr:
-	dev_err(&arcom_pcmcia_dev->dev, "Failed to setup PCMCIA GPIOs\n");
-	return -1;
-}
-
-/*
- * Release all resources.
- */
-static void viper_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
-{
-	struct arcom_pcmcia_pdata *pdata = viper_get_pdata();
-
-	gpio_free(pdata->pwr_gpio);
-}
-
-static void viper_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-				      struct pcmcia_state *state)
-{
-	state->vs_3v  = 1; /* Can only apply 3.3V */
-	state->vs_Xv  = 0;
-}
-
-static int viper_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-					 const socket_state_t *state)
-{
-	struct arcom_pcmcia_pdata *pdata = viper_get_pdata();
-
-	/* Silently ignore Vpp, output enable, speaker enable. */
-	pdata->reset(state->flags & SS_RESET);
-
-	/* Apply socket voltage */
-	switch (state->Vcc) {
-	case 0:
-		gpio_set_value(pdata->pwr_gpio, 0);
-		break;
-	case 33:
-		gpio_set_value(pdata->pwr_gpio, 1);
-		break;
-	default:
-		dev_err(&arcom_pcmcia_dev->dev, "Unsupported Vcc:%d\n", state->Vcc);
-		return -1;
-	}
-
-	return 0;
-}
-
-static struct pcmcia_low_level viper_pcmcia_ops = {
-	.owner          	= THIS_MODULE,
-	.hw_init        	= viper_pcmcia_hw_init,
-	.hw_shutdown		= viper_pcmcia_hw_shutdown,
-	.socket_state		= viper_pcmcia_socket_state,
-	.configure_socket	= viper_pcmcia_configure_socket,
-	.nr         		= 1,
-};
-
-static struct platform_device *viper_pcmcia_device;
-
-static int viper_pcmcia_probe(struct platform_device *pdev)
-{
-	int ret;
-
-	/* I can't imagine more than one device, but you never know... */
-	if (arcom_pcmcia_dev)
-		return -EEXIST;
-
-	if (!pdev->dev.platform_data)
-		return -EINVAL;
-
-	viper_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!viper_pcmcia_device)
-		return -ENOMEM;
-
-	arcom_pcmcia_dev = pdev;
-
-	viper_pcmcia_device->dev.parent = &pdev->dev;
-
-	ret = platform_device_add_data(viper_pcmcia_device,
-				       &viper_pcmcia_ops,
-				       sizeof(viper_pcmcia_ops));
-
-	if (!ret)
-		ret = platform_device_add(viper_pcmcia_device);
-
-	if (ret) {
-		platform_device_put(viper_pcmcia_device);
-		arcom_pcmcia_dev = NULL;
-	}
-
-	return ret;
-}
-
-static int viper_pcmcia_remove(struct platform_device *pdev)
-{
-	platform_device_unregister(viper_pcmcia_device);
-	arcom_pcmcia_dev = NULL;
-	return 0;
-}
-
-static struct platform_device_id viper_pcmcia_id_table[] = {
-	{ .name = "viper-pcmcia", },
-	{ .name = "zeus-pcmcia",  },
-	{ },
-};
-
-static struct platform_driver viper_pcmcia_driver = {
-	.probe		= viper_pcmcia_probe,
-	.remove		= viper_pcmcia_remove,
-	.driver		= {
-		.name	= "arcom-pcmcia",
-	},
-	.id_table	= viper_pcmcia_id_table,
-};
-
-module_platform_driver(viper_pcmcia_driver);
-
-MODULE_DEVICE_TABLE(platform, viper_pcmcia_id_table);
-MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/pxa2xx_vpac270.c b/drivers/pcmcia/pxa2xx_vpac270.c
deleted file mode 100644
index 3565add03a5e..000000000000
--- a/drivers/pcmcia/pxa2xx_vpac270.c
+++ /dev/null
@@ -1,137 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/drivers/pcmcia/pxa2xx_vpac270.c
- *
- * Driver for Voipac PXA270 PCMCIA and CF sockets
- *
- * Copyright (C) 2010-2011 Marek Vasut <marek.vasut@gmail.com>
- */
-
-#include <linux/gpio.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-
-#include <asm/mach-types.h>
-
-#include <mach/vpac270.h>
-
-#include "soc_common.h"
-
-static struct gpio vpac270_pcmcia_gpios[] = {
-	{ GPIO107_VPAC270_PCMCIA_PPEN,	GPIOF_INIT_LOW,	"PCMCIA PPEN" },
-	{ GPIO11_VPAC270_PCMCIA_RESET,	GPIOF_INIT_LOW,	"PCMCIA Reset" },
-};
-
-static struct gpio vpac270_cf_gpios[] = {
-	{ GPIO16_VPAC270_CF_RESET,	GPIOF_INIT_LOW,	"CF Reset" },
-};
-
-static int vpac270_pcmcia_hw_init(struct soc_pcmcia_socket *skt)
-{
-	int ret;
-
-	if (skt->nr == 0) {
-		ret = gpio_request_array(vpac270_pcmcia_gpios,
-				ARRAY_SIZE(vpac270_pcmcia_gpios));
-
-		skt->stat[SOC_STAT_CD].gpio = GPIO84_VPAC270_PCMCIA_CD;
-		skt->stat[SOC_STAT_CD].name = "PCMCIA CD";
-		skt->stat[SOC_STAT_RDY].gpio = GPIO35_VPAC270_PCMCIA_RDY;
-		skt->stat[SOC_STAT_RDY].name = "PCMCIA Ready";
-	} else {
-		ret = gpio_request_array(vpac270_cf_gpios,
-				ARRAY_SIZE(vpac270_cf_gpios));
-
-		skt->stat[SOC_STAT_CD].gpio = GPIO17_VPAC270_CF_CD;
-		skt->stat[SOC_STAT_CD].name = "CF CD";
-		skt->stat[SOC_STAT_RDY].gpio = GPIO12_VPAC270_CF_RDY;
-		skt->stat[SOC_STAT_RDY].name = "CF Ready";
-	}
-
-	return ret;
-}
-
-static void vpac270_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt)
-{
-	if (skt->nr == 0)
-		gpio_free_array(vpac270_pcmcia_gpios,
-					ARRAY_SIZE(vpac270_pcmcia_gpios));
-	else
-		gpio_free_array(vpac270_cf_gpios,
-					ARRAY_SIZE(vpac270_cf_gpios));
-}
-
-static void vpac270_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
-					struct pcmcia_state *state)
-{
-	state->vs_3v  = 1;
-	state->vs_Xv  = 0;
-}
-
-static int
-vpac270_pcmcia_configure_socket(struct soc_pcmcia_socket *skt,
-				const socket_state_t *state)
-{
-	if (skt->nr == 0) {
-		gpio_set_value(GPIO11_VPAC270_PCMCIA_RESET,
-			(state->flags & SS_RESET));
-		gpio_set_value(GPIO107_VPAC270_PCMCIA_PPEN,
-			!(state->Vcc == 33 || state->Vcc == 50));
-	} else {
-		gpio_set_value(GPIO16_VPAC270_CF_RESET,
-			(state->flags & SS_RESET));
-	}
-
-	return 0;
-}
-
-static struct pcmcia_low_level vpac270_pcmcia_ops = {
-	.owner			= THIS_MODULE,
-
-	.first			= 0,
-	.nr			= 2,
-
-	.hw_init		= vpac270_pcmcia_hw_init,
-	.hw_shutdown		= vpac270_pcmcia_hw_shutdown,
-
-	.socket_state		= vpac270_pcmcia_socket_state,
-	.configure_socket	= vpac270_pcmcia_configure_socket,
-};
-
-static struct platform_device *vpac270_pcmcia_device;
-
-static int __init vpac270_pcmcia_init(void)
-{
-	int ret;
-
-	if (!machine_is_vpac270())
-		return -ENODEV;
-
-	vpac270_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
-	if (!vpac270_pcmcia_device)
-		return -ENOMEM;
-
-	ret = platform_device_add_data(vpac270_pcmcia_device,
-		&vpac270_pcmcia_ops, sizeof(vpac270_pcmcia_ops));
-
-	if (!ret)
-		ret = platform_device_add(vpac270_pcmcia_device);
-
-	if (ret)
-		platform_device_put(vpac270_pcmcia_device);
-
-	return ret;
-}
-
-static void __exit vpac270_pcmcia_exit(void)
-{
-	platform_device_unregister(vpac270_pcmcia_device);
-}
-
-module_init(vpac270_pcmcia_init);
-module_exit(vpac270_pcmcia_exit);
-
-MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
-MODULE_DESCRIPTION("PCMCIA support for Voipac PXA270");
-MODULE_ALIAS("platform:pxa2xx-pcmcia");
-MODULE_LICENSE("GPL");
diff --git a/drivers/pcmcia/soc_common.h b/drivers/pcmcia/soc_common.h
index 222e81c79365..17ef05aa8afe 100644
--- a/drivers/pcmcia/soc_common.h
+++ b/drivers/pcmcia/soc_common.h
@@ -13,137 +13,19 @@
 /* include the world */
 #include <linux/clk.h>
 #include <linux/cpufreq.h>
-#include <pcmcia/ss.h>
 #include <pcmcia/cistpl.h>
-
+#include <pcmcia/soc_common.h>
 
 struct device;
 struct gpio_desc;
 struct pcmcia_low_level;
 struct regulator;
 
-struct soc_pcmcia_regulator {
-	struct regulator	*reg;
-	bool			on;
-};
-
-/*
- * This structure encapsulates per-socket state which we might need to
- * use when responding to a Card Services query of some kind.
- */
-struct soc_pcmcia_socket {
-	struct pcmcia_socket	socket;
-
-	/*
-	 * Info from low level handler
-	 */
-	unsigned int		nr;
-	struct clk		*clk;
-
-	/*
-	 * Core PCMCIA state
-	 */
-	const struct pcmcia_low_level *ops;
-
-	unsigned int		status;
-	socket_state_t		cs_state;
-
-	unsigned short		spd_io[MAX_IO_WIN];
-	unsigned short		spd_mem[MAX_WIN];
-	unsigned short		spd_attr[MAX_WIN];
-
-	struct resource		res_skt;
-	struct resource		res_io;
-	struct resource		res_mem;
-	struct resource		res_attr;
-	void __iomem		*virt_io;
-
-	struct {
-		int		gpio;
-		struct gpio_desc *desc;
-		unsigned int	irq;
-		const char	*name;
-	} stat[6];
-#define SOC_STAT_CD		0	/* Card detect */
-#define SOC_STAT_BVD1		1	/* BATDEAD / IOSTSCHG */
-#define SOC_STAT_BVD2		2	/* BATWARN / IOSPKR */
-#define SOC_STAT_RDY		3	/* Ready / Interrupt */
-#define SOC_STAT_VS1		4	/* Voltage sense 1 */
-#define SOC_STAT_VS2		5	/* Voltage sense 2 */
-
-	struct gpio_desc	*gpio_reset;
-	struct gpio_desc	*gpio_bus_enable;
-	struct soc_pcmcia_regulator vcc;
-	struct soc_pcmcia_regulator vpp;
-
-	unsigned int		irq_state;
-
-#ifdef CONFIG_CPU_FREQ
-	struct notifier_block	cpufreq_nb;
-#endif
-	struct timer_list	poll_timer;
-	struct list_head	node;
-	void *driver_data;
-};
-
 struct skt_dev_info {
 	int nskt;
 	struct soc_pcmcia_socket skt[];
 };
 
-struct pcmcia_state {
-  unsigned detect: 1,
-            ready: 1,
-             bvd1: 1,
-             bvd2: 1,
-           wrprot: 1,
-            vs_3v: 1,
-            vs_Xv: 1;
-};
-
-struct pcmcia_low_level {
-	struct module *owner;
-
-	/* first socket in system */
-	int first;
-	/* nr of sockets */
-	int nr;
-
-	int (*hw_init)(struct soc_pcmcia_socket *);
-	void (*hw_shutdown)(struct soc_pcmcia_socket *);
-
-	void (*socket_state)(struct soc_pcmcia_socket *, struct pcmcia_state *);
-	int (*configure_socket)(struct soc_pcmcia_socket *, const socket_state_t *);
-
-	/*
-	 * Enable card status IRQs on (re-)initialisation.  This can
-	 * be called at initialisation, power management event, or
-	 * pcmcia event.
-	 */
-	void (*socket_init)(struct soc_pcmcia_socket *);
-
-	/*
-	 * Disable card status IRQs and PCMCIA bus on suspend.
-	 */
-	void (*socket_suspend)(struct soc_pcmcia_socket *);
-
-	/*
-	 * Hardware specific timing routines.
-	 * If provided, the get_timing routine overrides the SOC default.
-	 */
-	unsigned int (*get_timing)(struct soc_pcmcia_socket *, unsigned int, unsigned int);
-	int (*set_timing)(struct soc_pcmcia_socket *);
-	int (*show_timing)(struct soc_pcmcia_socket *, char *);
-
-#ifdef CONFIG_CPU_FREQ
-	/*
-	 * CPUFREQ support.
-	 */
-	int (*frequency_change)(struct soc_pcmcia_socket *, unsigned long, struct cpufreq_freqs *);
-#endif
-};
-
-
 struct soc_pcmcia_timing {
 	unsigned short io;
 	unsigned short mem;
diff --git a/include/linux/platform_data/pcmcia-pxa2xx_viper.h b/include/linux/platform_data/pcmcia-pxa2xx_viper.h
deleted file mode 100644
index a23b58aff9e1..000000000000
--- a/include/linux/platform_data/pcmcia-pxa2xx_viper.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ARCOM_PCMCIA_H
-#define __ARCOM_PCMCIA_H
-
-struct arcom_pcmcia_pdata {
-	int	cd_gpio;
-	int	rdy_gpio;
-	int	pwr_gpio;
-	void	(*reset)(int state);
-};
-
-#endif
diff --git a/include/pcmcia/soc_common.h b/include/pcmcia/soc_common.h
new file mode 100644
index 000000000000..26f1473a06c5
--- /dev/null
+++ b/include/pcmcia/soc_common.h
@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <pcmcia/ss.h>
+
+struct module;
+struct cpufreq_freqs;
+
+struct soc_pcmcia_regulator {
+	struct regulator	*reg;
+	bool			on;
+};
+
+struct pcmcia_state {
+  unsigned detect: 1,
+            ready: 1,
+             bvd1: 1,
+             bvd2: 1,
+           wrprot: 1,
+            vs_3v: 1,
+            vs_Xv: 1;
+};
+
+/*
+ * This structure encapsulates per-socket state which we might need to
+ * use when responding to a Card Services query of some kind.
+ */
+struct soc_pcmcia_socket {
+	struct pcmcia_socket	socket;
+
+	/*
+	 * Info from low level handler
+	 */
+	unsigned int		nr;
+	struct clk		*clk;
+
+	/*
+	 * Core PCMCIA state
+	 */
+	const struct pcmcia_low_level *ops;
+
+	unsigned int		status;
+	socket_state_t		cs_state;
+
+	unsigned short		spd_io[MAX_IO_WIN];
+	unsigned short		spd_mem[MAX_WIN];
+	unsigned short		spd_attr[MAX_WIN];
+
+	struct resource		res_skt;
+	struct resource		res_io;
+	struct resource		res_mem;
+	struct resource		res_attr;
+	void __iomem		*virt_io;
+
+	struct {
+		int		gpio;
+		struct gpio_desc *desc;
+		unsigned int	irq;
+		const char	*name;
+	} stat[6];
+#define SOC_STAT_CD		0	/* Card detect */
+#define SOC_STAT_BVD1		1	/* BATDEAD / IOSTSCHG */
+#define SOC_STAT_BVD2		2	/* BATWARN / IOSPKR */
+#define SOC_STAT_RDY		3	/* Ready / Interrupt */
+#define SOC_STAT_VS1		4	/* Voltage sense 1 */
+#define SOC_STAT_VS2		5	/* Voltage sense 2 */
+
+	struct gpio_desc	*gpio_reset;
+	struct gpio_desc	*gpio_bus_enable;
+	struct soc_pcmcia_regulator vcc;
+	struct soc_pcmcia_regulator vpp;
+
+	unsigned int		irq_state;
+
+#ifdef CONFIG_CPU_FREQ
+	struct notifier_block	cpufreq_nb;
+#endif
+	struct timer_list	poll_timer;
+	struct list_head	node;
+	void *driver_data;
+};
+
+
+struct pcmcia_low_level {
+	struct module *owner;
+
+	/* first socket in system */
+	int first;
+	/* nr of sockets */
+	int nr;
+
+	int (*hw_init)(struct soc_pcmcia_socket *);
+	void (*hw_shutdown)(struct soc_pcmcia_socket *);
+
+	void (*socket_state)(struct soc_pcmcia_socket *, struct pcmcia_state *);
+	int (*configure_socket)(struct soc_pcmcia_socket *, const socket_state_t *);
+
+	/*
+	 * Enable card status IRQs on (re-)initialisation.  This can
+	 * be called at initialisation, power management event, or
+	 * pcmcia event.
+	 */
+	void (*socket_init)(struct soc_pcmcia_socket *);
+
+	/*
+	 * Disable card status IRQs and PCMCIA bus on suspend.
+	 */
+	void (*socket_suspend)(struct soc_pcmcia_socket *);
+
+	/*
+	 * Hardware specific timing routines.
+	 * If provided, the get_timing routine overrides the SOC default.
+	 */
+	unsigned int (*get_timing)(struct soc_pcmcia_socket *, unsigned int, unsigned int);
+	int (*set_timing)(struct soc_pcmcia_socket *);
+	int (*show_timing)(struct soc_pcmcia_socket *, char *);
+
+#ifdef CONFIG_CPU_FREQ
+	/*
+	 * CPUFREQ support.
+	 */
+	int (*frequency_change)(struct soc_pcmcia_socket *, unsigned long, struct cpufreq_freqs *);
+#endif
+};
+
+
+
-- 
cgit v1.2.3


From dcf456c9a095a6e71f53d6f6f004133ee851ee70 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@kernel.org>
Date: Mon, 18 Apr 2022 15:51:58 +0000
Subject: bpf: Fix usage of trace RCU in local storage.

bpf_{sk,task,inode}_storage_free() do not need to use
call_rcu_tasks_trace as no BPF program should be accessing the owner
as it's being destroyed. The only other reader at this point is
bpf_local_storage_map_free() which uses normal RCU.

The only path that needs trace RCU are:

* bpf_local_storage_{delete,update} helpers
* map_{delete,update}_elem() syscalls

Fixes: 0fe4b381a59e ("bpf: Allow bpf_local_storage to be used by sleepable programs")
Signed-off-by: KP Singh <kpsingh@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20220418155158.2865678-1-kpsingh@kernel.org
---
 include/linux/bpf_local_storage.h |  4 ++--
 kernel/bpf/bpf_inode_storage.c    |  4 ++--
 kernel/bpf/bpf_local_storage.c    | 29 +++++++++++++++++++----------
 kernel/bpf/bpf_task_storage.c     |  4 ++--
 net/core/bpf_sk_storage.c         |  6 +++---
 5 files changed, 28 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 493e63258497..7ea18d4da84b 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -143,9 +143,9 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
 
 bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 				     struct bpf_local_storage_elem *selem,
-				     bool uncharge_omem);
+				     bool uncharge_omem, bool use_trace_rcu);
 
-void bpf_selem_unlink(struct bpf_local_storage_elem *selem);
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu);
 
 void bpf_selem_link_map(struct bpf_local_storage_map *smap,
 			struct bpf_local_storage_elem *selem);
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 96be8d518885..10424a1cda51 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -90,7 +90,7 @@ void bpf_inode_storage_free(struct inode *inode)
 		 */
 		bpf_selem_unlink_map(selem);
 		free_inode_storage = bpf_selem_unlink_storage_nolock(
-			local_storage, selem, false);
+			local_storage, selem, false, false);
 	}
 	raw_spin_unlock_bh(&local_storage->lock);
 	rcu_read_unlock();
@@ -149,7 +149,7 @@ static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
 	if (!sdata)
 		return -ENOENT;
 
-	bpf_selem_unlink(SELEM(sdata));
+	bpf_selem_unlink(SELEM(sdata), true);
 
 	return 0;
 }
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 01aa2b51ec4d..8ce40fd869f6 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -106,7 +106,7 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu)
  */
 bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 				     struct bpf_local_storage_elem *selem,
-				     bool uncharge_mem)
+				     bool uncharge_mem, bool use_trace_rcu)
 {
 	struct bpf_local_storage_map *smap;
 	bool free_local_storage;
@@ -150,11 +150,16 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
 	    SDATA(selem))
 		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
 
-	call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu);
+	if (use_trace_rcu)
+		call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu);
+	else
+		kfree_rcu(selem, rcu);
+
 	return free_local_storage;
 }
 
-static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
+static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem,
+				       bool use_trace_rcu)
 {
 	struct bpf_local_storage *local_storage;
 	bool free_local_storage = false;
@@ -169,12 +174,16 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
 	raw_spin_lock_irqsave(&local_storage->lock, flags);
 	if (likely(selem_linked_to_storage(selem)))
 		free_local_storage = bpf_selem_unlink_storage_nolock(
-			local_storage, selem, true);
+			local_storage, selem, true, use_trace_rcu);
 	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 
-	if (free_local_storage)
-		call_rcu_tasks_trace(&local_storage->rcu,
+	if (free_local_storage) {
+		if (use_trace_rcu)
+			call_rcu_tasks_trace(&local_storage->rcu,
 				     bpf_local_storage_free_rcu);
+		else
+			kfree_rcu(local_storage, rcu);
+	}
 }
 
 void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
@@ -214,14 +223,14 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap,
 	raw_spin_unlock_irqrestore(&b->lock, flags);
 }
 
-void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu)
 {
 	/* Always unlink from map before unlinking from local_storage
 	 * because selem will be freed after successfully unlinked from
 	 * the local_storage.
 	 */
 	bpf_selem_unlink_map(selem);
-	__bpf_selem_unlink_storage(selem);
+	__bpf_selem_unlink_storage(selem, use_trace_rcu);
 }
 
 struct bpf_local_storage_data *
@@ -466,7 +475,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 	if (old_sdata) {
 		bpf_selem_unlink_map(SELEM(old_sdata));
 		bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
-						false);
+						false, true);
 	}
 
 unlock:
@@ -548,7 +557,7 @@ void bpf_local_storage_map_free(struct bpf_local_storage_map *smap,
 				migrate_disable();
 				__this_cpu_inc(*busy_counter);
 			}
-			bpf_selem_unlink(selem);
+			bpf_selem_unlink(selem, false);
 			if (busy_counter) {
 				__this_cpu_dec(*busy_counter);
 				migrate_enable();
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index 6638a0ecc3d2..57904263a710 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -102,7 +102,7 @@ void bpf_task_storage_free(struct task_struct *task)
 		 */
 		bpf_selem_unlink_map(selem);
 		free_task_storage = bpf_selem_unlink_storage_nolock(
-			local_storage, selem, false);
+			local_storage, selem, false, false);
 	}
 	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
 	bpf_task_storage_unlock();
@@ -192,7 +192,7 @@ static int task_storage_delete(struct task_struct *task, struct bpf_map *map)
 	if (!sdata)
 		return -ENOENT;
 
-	bpf_selem_unlink(SELEM(sdata));
+	bpf_selem_unlink(SELEM(sdata), true);
 
 	return 0;
 }
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index e3ac36380520..83d7641ef67b 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -40,7 +40,7 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
 	if (!sdata)
 		return -ENOENT;
 
-	bpf_selem_unlink(SELEM(sdata));
+	bpf_selem_unlink(SELEM(sdata), true);
 
 	return 0;
 }
@@ -75,8 +75,8 @@ void bpf_sk_storage_free(struct sock *sk)
 		 * sk_storage.
 		 */
 		bpf_selem_unlink_map(selem);
-		free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage,
-								  selem, true);
+		free_sk_storage = bpf_selem_unlink_storage_nolock(
+			sk_storage, selem, true, false);
 	}
 	raw_spin_unlock_bh(&sk_storage->lock);
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 3abfaefb9a6dda5e0bfa6160f55abfd0e32d8b0a Mon Sep 17 00:00:00 2001
From: Liu Ying <victor.liu@nxp.com>
Date: Tue, 19 Apr 2022 09:08:49 +0800
Subject: phy: Add LVDS configuration options

This patch allows LVDS PHYs to be configured through
the generic functions and through a custom structure
added to the generic union.

The parameters added here are based on common LVDS PHY
implementation practices.  The set of parameters
should cover all potential users.

Cc: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: NXP Linux Team <linux-imx@nxp.com>
Signed-off-by: Liu Ying <victor.liu@nxp.com>
Link: https://lore.kernel.org/r/20220419010852.452169-3-victor.liu@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/phy/phy-lvds.h | 32 ++++++++++++++++++++++++++++++++
 include/linux/phy/phy.h      |  4 ++++
 2 files changed, 36 insertions(+)
 create mode 100644 include/linux/phy/phy-lvds.h

(limited to 'include/linux')

diff --git a/include/linux/phy/phy-lvds.h b/include/linux/phy/phy-lvds.h
new file mode 100644
index 000000000000..09931d080a6d
--- /dev/null
+++ b/include/linux/phy/phy-lvds.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020,2022 NXP
+ */
+
+#ifndef __PHY_LVDS_H_
+#define __PHY_LVDS_H_
+
+/**
+ * struct phy_configure_opts_lvds - LVDS configuration set
+ * @bits_per_lane_and_dclk_cycle:	Number of bits per lane per differential
+ *					clock cycle.
+ * @differential_clk_rate:		Clock rate, in Hertz, of the LVDS
+ *					differential clock.
+ * @lanes:				Number of active, consecutive,
+ *					data lanes, starting from lane 0,
+ *					used for the transmissions.
+ * @is_slave:				Boolean, true if the phy is a slave
+ *					which works together with a master
+ *					phy to support dual link transmission,
+ *					otherwise a regular phy or a master phy.
+ *
+ * This structure is used to represent the configuration state of a LVDS phy.
+ */
+struct phy_configure_opts_lvds {
+	unsigned int	bits_per_lane_and_dclk_cycle;
+	unsigned long	differential_clk_rate;
+	unsigned int	lanes;
+	bool		is_slave;
+};
+
+#endif /* __PHY_LVDS_H_ */
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index f3286f4cd306..b1413757fcc3 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -17,6 +17,7 @@
 #include <linux/regulator/consumer.h>
 
 #include <linux/phy/phy-dp.h>
+#include <linux/phy/phy-lvds.h>
 #include <linux/phy/phy-mipi-dphy.h>
 
 struct phy;
@@ -57,10 +58,13 @@ enum phy_media {
  *		the MIPI_DPHY phy mode.
  * @dp:		Configuration set applicable for phys supporting
  *		the DisplayPort protocol.
+ * @lvds:	Configuration set applicable for phys supporting
+ *		the LVDS phy mode.
  */
 union phy_configure_opts {
 	struct phy_configure_opts_mipi_dphy	mipi_dphy;
 	struct phy_configure_opts_dp		dp;
+	struct phy_configure_opts_lvds		lvds;
 };
 
 /**
-- 
cgit v1.2.3


From fc44ff0ae9f2aa20b64c4e63ab4614156df80240 Mon Sep 17 00:00:00 2001
From: Ben Walker <benjamin.walker@intel.com>
Date: Tue, 1 Mar 2022 11:25:48 -0700
Subject: dmaengine: Document dmaengine_prep_dma_memset

Document this function to make clear the expected behavior of the
'value' parameter. It was intended to match the behavior of POSIX memset
as laid out here:

https://lore.kernel.org/dmaengine/YejrA5ZWZ3lTRO%2F1@matsya/

Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Link: https://lore.kernel.org/r/20220301182551.883474-2-benjamin.walker@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/driver-api/dmaengine/provider.rst | 6 ++++++
 include/linux/dmaengine.h                       | 8 ++++++++
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst
index d3fa80e333b1..1e0f1f85d10e 100644
--- a/Documentation/driver-api/dmaengine/provider.rst
+++ b/Documentation/driver-api/dmaengine/provider.rst
@@ -206,6 +206,12 @@ Currently, the types available are:
   - The device is able to perform parity check using RAID6 P+Q
     algorithm against a memory buffer.
 
+- DMA_MEMSET
+
+  - The device is able to fill memory with the provided pattern
+
+  - The pattern is treated as a single byte signed value.
+
 - DMA_INTERRUPT
 
   - The device is able to trigger a dummy transfer that will
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 6db9e03afd0b..b46b88e6aa0d 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -1030,6 +1030,14 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma(
 	return chan->device->device_prep_interleaved_dma(chan, xt, flags);
 }
 
+/**
+ * dmaengine_prep_dma_memset() - Prepare a DMA memset descriptor.
+ * @chan: The channel to be used for this descriptor
+ * @dest: Address of buffer to be set
+ * @value: Treated as a single byte value that fills the destination buffer
+ * @len: The total size of dest
+ * @flags: DMA engine flags
+ */
 static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset(
 		struct dma_chan *chan, dma_addr_t dest, int value, size_t len,
 		unsigned long flags)
-- 
cgit v1.2.3


From 5252c1c5a08e583ab1363f809002cd8a59272b35 Mon Sep 17 00:00:00 2001
From: Chun-Kuang Hu <chunkuang.hu@kernel.org>
Date: Sat, 16 Apr 2022 17:54:28 +0800
Subject: soc: mediatek: cmdq: Use mailbox rx_callback instead of cmdq_task_cb

rx_callback is a standard mailbox callback mechanism and could cover the
function of proprietary cmdq_task_cb, so use the standard one instead of
the proprietary one. Client has changed to use the standard callback
machanism and sync dma buffer in client driver, so remove the proprietary
callback in cmdq helper.

Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
Reviewed-by: jason-jh.lin <jason-jh.lin@mediatek.com>
Tested-by: jason-jh.lin <jason-jh.lin@mediatek.com>
Link: https://lore.kernel.org/r/1650102868-26219-1-git-send-email-chunkuang.hu@kernel.org
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c | 25 +------------------------
 include/linux/soc/mediatek/mtk-cmdq.h  |  5 +----
 2 files changed, 2 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 3c8e4212d941..c1837a468267 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -425,34 +425,11 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
 }
 EXPORT_SYMBOL(cmdq_pkt_finalize);
 
-static void cmdq_pkt_flush_async_cb(struct cmdq_cb_data data)
-{
-	struct cmdq_pkt *pkt = (struct cmdq_pkt *)data.data;
-	struct cmdq_task_cb *cb = &pkt->cb;
-	struct cmdq_client *client = (struct cmdq_client *)pkt->cl;
-
-	dma_sync_single_for_cpu(client->chan->mbox->dev, pkt->pa_base,
-				pkt->cmd_buf_size, DMA_TO_DEVICE);
-	if (cb->cb) {
-		data.data = cb->data;
-		cb->cb(data);
-	}
-}
-
-int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb,
-			 void *data)
+int cmdq_pkt_flush_async(struct cmdq_pkt *pkt)
 {
 	int err;
 	struct cmdq_client *client = (struct cmdq_client *)pkt->cl;
 
-	pkt->cb.cb = cb;
-	pkt->cb.data = data;
-	pkt->async_cb.cb = cmdq_pkt_flush_async_cb;
-	pkt->async_cb.data = pkt;
-
-	dma_sync_single_for_device(client->chan->mbox->dev, pkt->pa_base,
-				   pkt->cmd_buf_size, DMA_TO_DEVICE);
-
 	err = mbox_send_message(client->chan, pkt);
 	if (err < 0)
 		return err;
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index ac6b5f3cba95..2b498f4f3946 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -268,8 +268,6 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt);
  * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ
  *                          packet and call back at the end of done packet
  * @pkt:	the CMDQ packet
- * @cb:		called at the end of done packet
- * @data:	this data will pass back to cb
  *
  * Return: 0 for success; else the error code is returned
  *
@@ -277,7 +275,6 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt);
  * at the end of done packet. Note that this is an ASYNC function. When the
  * function returned, it may or may not be finished.
  */
-int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb,
-			 void *data);
+int cmdq_pkt_flush_async(struct cmdq_pkt *pkt);
 
 #endif	/* __MTK_CMDQ_H__ */
-- 
cgit v1.2.3


From 7a107b2c6b813c3c587d1e76cb405dc637dd2b36 Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Wed, 20 Apr 2022 11:19:01 +0300
Subject: Revert "serial: 8250: Handle UART without interrupt on TEMT using
 em485"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This partially reverts commit f6f586102add. The code added by
that commit containted math overflow for 32-bit archs. In
addition, the approach used in it is unnecessarily complicated
requiring a dedicated timer just for notemt. A simpler approach
for providing UART_CAP_NOTEMT already exists (patches 1-2):
  https://lore.kernel.org/linux-serial/20220411083321.9131-3-ilpo.jarvinen@linux.intel.com/T/#u
Thus, simply revert the UART_CAP_NOTEMT change for now.

There were two driver changes within the patch series adding
UART_CAP_NOTEMT taking advantage of the newly added flag.
This does not revert the driver changes and therefore also
UART_CAP_NOTEMT define has to remain. UART_CAP_NOTEMT remains
no-op until support is again added.

Fixes: f6f586102add ("serial: 8250: Handle UART without interrupt on TEMT using em485")
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/5f874142-fb1f-bff7-f33-fac823e65e2e@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_port.c | 76 +------------------------------------
 include/linux/serial_8250.h         |  2 -
 2 files changed, 2 insertions(+), 76 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index c1f24e88ef09..33bd062140c9 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -571,21 +571,8 @@ static void serial8250_clear_fifos(struct uart_8250_port *p)
 	}
 }
 
-static inline void serial8250_em485_update_temt_delay(struct uart_8250_port *p,
-			unsigned int cflag, unsigned int baud)
-{
-	unsigned int bits;
-
-	if (!p->em485)
-		return;
-
-	bits = tty_get_frame_size(cflag);
-	p->em485->no_temt_delay = DIV_ROUND_UP(bits * NSEC_PER_SEC, baud);
-}
-
 static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t);
 static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t);
-static enum hrtimer_restart serial8250_em485_handle_no_temt(struct hrtimer *t);
 
 void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p)
 {
@@ -644,16 +631,6 @@ static int serial8250_em485_init(struct uart_8250_port *p)
 		     HRTIMER_MODE_REL);
 	hrtimer_init(&p->em485->start_tx_timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_REL);
-
-	if (p->capabilities & UART_CAP_NOTEMT) {
-		struct tty_struct *tty = p->port.state->port.tty;
-
-		serial8250_em485_update_temt_delay(p, tty->termios.c_cflag,
-						   tty_get_baud_rate(tty));
-		hrtimer_init(&p->em485->no_temt_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		p->em485->no_temt_timer.function = &serial8250_em485_handle_no_temt;
-	}
-
 	p->em485->stop_tx_timer.function = &serial8250_em485_handle_stop_tx;
 	p->em485->start_tx_timer.function = &serial8250_em485_handle_start_tx;
 	p->em485->port = p;
@@ -685,7 +662,6 @@ void serial8250_em485_destroy(struct uart_8250_port *p)
 
 	hrtimer_cancel(&p->em485->start_tx_timer);
 	hrtimer_cancel(&p->em485->stop_tx_timer);
-	hrtimer_cancel(&p->em485->no_temt_timer);
 
 	kfree(p->em485);
 	p->em485 = NULL;
@@ -1528,11 +1504,6 @@ static void start_hrtimer_ms(struct hrtimer *hrt, unsigned long msec)
 	hrtimer_start(hrt, ms_to_ktime(msec), HRTIMER_MODE_REL);
 }
 
-static void start_hrtimer_ns(struct hrtimer *hrt, unsigned long nsec)
-{
-	hrtimer_start(hrt, ns_to_ktime(nsec), HRTIMER_MODE_REL);
-}
-
 static void __stop_tx_rs485(struct uart_8250_port *p)
 {
 	struct uart_8250_em485 *em485 = p->em485;
@@ -1564,33 +1535,14 @@ static inline void __stop_tx(struct uart_8250_port *p)
 
 	if (em485) {
 		unsigned char lsr = serial_in(p, UART_LSR);
-
-		p->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS;
-
 		/*
-		 * To provide required timing and allow FIFO transfer,
+		 * To provide required timeing and allow FIFO transfer,
 		 * __stop_tx_rs485() must be called only when both FIFO and
 		 * shift register are empty. It is for device driver to enable
 		 * interrupt on TEMT.
 		 */
-		if ((lsr & BOTH_EMPTY) != BOTH_EMPTY) {
-			if (!(p->capabilities & UART_CAP_NOTEMT))
-				/* __stop_tx will be called again once TEMT triggers */
-				return;
-
-			if (!(lsr & UART_LSR_THRE))
-				/* __stop_tx will be called again once THRE triggers */
-				return;
-
-			/*
-			 * On devices with no TEMT interrupt available, start
-			 * a timer for a byte time. The timer will recall
-			 * __stop_tx().
-			 */
-			em485->active_timer = &em485->no_temt_timer;
-			start_hrtimer_ns(&em485->no_temt_timer, em485->no_temt_delay);
+		if ((lsr & BOTH_EMPTY) != BOTH_EMPTY)
 			return;
-		}
 
 		__stop_tx_rs485(p);
 	}
@@ -1701,27 +1653,6 @@ static inline void start_tx_rs485(struct uart_port *port)
 	__start_tx(port);
 }
 
-static enum hrtimer_restart serial8250_em485_handle_no_temt(struct hrtimer *t)
-{
-	struct uart_8250_em485 *em485;
-	struct uart_8250_port *p;
-	unsigned long flags;
-
-	em485 = container_of(t, struct uart_8250_em485, no_temt_timer);
-	p = em485->port;
-
-	serial8250_rpm_get(p);
-	spin_lock_irqsave(&p->port.lock, flags);
-	if (em485->active_timer == &em485->no_temt_timer) {
-		em485->active_timer = NULL;
-		__stop_tx(p);
-	}
-
-	spin_unlock_irqrestore(&p->port.lock, flags);
-	serial8250_rpm_put(p);
-	return HRTIMER_NORESTART;
-}
-
 static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t)
 {
 	struct uart_8250_em485 *em485 = container_of(t, struct uart_8250_em485,
@@ -2927,9 +2858,6 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 
 	serial8250_set_divisor(port, baud, quot, frac);
 
-	if (up->capabilities & UART_CAP_NOTEMT)
-		serial8250_em485_update_temt_delay(up, termios->c_cflag, baud);
-
 	/*
 	 * LCR DLAB must be set to enable 64-byte FIFO mode. If the FCR
 	 * is written without DLAB set, this mode will be disabled.
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index de135852107c..ff84a3ed10ea 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -79,9 +79,7 @@ struct uart_8250_ops {
 struct uart_8250_em485 {
 	struct hrtimer		start_tx_timer; /* "rs485 start tx" timer */
 	struct hrtimer		stop_tx_timer;  /* "rs485 stop tx" timer */
-	struct hrtimer		no_temt_timer;  /* "rs485 no TEMT interrupt" timer */
 	struct hrtimer		*active_timer;  /* pointer to active timer */
-	unsigned long		no_temt_delay;  /* Delay for no_temt_timer */
 	struct uart_8250_port	*port;          /* for hrtimer callbacks */
 	unsigned int		tx_stopped:1;	/* tx is currently stopped */
 };
-- 
cgit v1.2.3


From 92ece28072f18f30099770c5d4b8e300ea6820fa Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Sat, 16 Apr 2022 18:58:00 +0800
Subject: net: Change skb_ensure_writable()'s write_len param to unsigned int
 type

Both pskb_may_pull() and skb_clone_writable()'s length parameters are of
type unsigned int already. Therefore, change this function's write_len
param to unsigned int type.

Signed-off-by: Liu Jian <liujian56@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20220416105801.88708-3-liujian56@huawei.com
---
 include/linux/skbuff.h | 2 +-
 net/core/skbuff.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2394441fa3dd..b37c829d08e1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3885,7 +3885,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
 struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features,
 				 unsigned int offset);
 struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
-int skb_ensure_writable(struct sk_buff *skb, int write_len);
+int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 30b523fa4ad2..a84e00e44ad2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5601,7 +5601,7 @@ err_free:
 }
 EXPORT_SYMBOL(skb_vlan_untag);
 
-int skb_ensure_writable(struct sk_buff *skb, int write_len)
+int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 {
 	if (!pskb_may_pull(skb, write_len))
 		return -ENOMEM;
-- 
cgit v1.2.3


From f4c5c7f9d2e5ab005d57826b740b694b042a737c Mon Sep 17 00:00:00 2001
From: Felix Matouschek <felix@matouschek.org>
Date: Mon, 18 Apr 2022 15:28:03 +0200
Subject: mtd: spinand: Add support for XTX XT26G0xA

Add support for XTX Technology XT26G01AXXXXX, XTX26G02AXXXXX and
XTX26G04AXXXXX SPI NAND.

These are 3V, 1G/2G/4Gbit serial SLC NAND flash devices with on-die ECC
(8bit strength per 512bytes).

Tested on Teltonika RUTX10 flashed with OpenWrt.

Links:
  - http://www.xtxtech.com/download/?AId=225
  - https://datasheet.lcsc.com/szlcsc/2005251034_XTX-XT26G01AWSEGA_C558841.pdf
Signed-off-by: Felix Matouschek <felix@matouschek.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20220418132803.664103-1-felix@matouschek.org
---
 drivers/mtd/nand/spi/Makefile |   2 +-
 drivers/mtd/nand/spi/core.c   |   1 +
 drivers/mtd/nand/spi/xtx.c    | 129 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/spinand.h   |   1 +
 4 files changed, 132 insertions(+), 1 deletion(-)
 create mode 100644 drivers/mtd/nand/spi/xtx.c

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
index 9662b9c1d5a9..80dabe6ff0f3 100644
--- a/drivers/mtd/nand/spi/Makefile
+++ b/drivers/mtd/nand/spi/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
-spinand-objs := core.o gigadevice.o macronix.o micron.o paragon.o toshiba.o winbond.o
+spinand-objs := core.o gigadevice.o macronix.o micron.o paragon.o toshiba.o winbond.o xtx.o
 obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index ff8336870bc0..d5b685d1605e 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -933,6 +933,7 @@ static const struct spinand_manufacturer *spinand_manufacturers[] = {
 	&paragon_spinand_manufacturer,
 	&toshiba_spinand_manufacturer,
 	&winbond_spinand_manufacturer,
+	&xtx_spinand_manufacturer,
 };
 
 static int spinand_manufacturer_match(struct spinand_device *spinand,
diff --git a/drivers/mtd/nand/spi/xtx.c b/drivers/mtd/nand/spi/xtx.c
new file mode 100644
index 000000000000..3911520f718c
--- /dev/null
+++ b/drivers/mtd/nand/spi/xtx.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author:
+ * Felix Matouschek <felix@matouschek.org>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_XTX	0x0B
+
+#define XT26G0XA_STATUS_ECC_MASK	GENMASK(5, 2)
+#define XT26G0XA_STATUS_ECC_NO_DETECTED	(0 << 2)
+#define XT26G0XA_STATUS_ECC_8_CORRECTED	(3 << 4)
+#define XT26G0XA_STATUS_ECC_UNCOR_ERROR	(2 << 4)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int xt26g0xa_ooblayout_ecc(struct mtd_info *mtd, int section,
+				   struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 48;
+	region->length = 16;
+
+	return 0;
+}
+
+static int xt26g0xa_ooblayout_free(struct mtd_info *mtd, int section,
+				   struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 1;
+	region->length = 47;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops xt26g0xa_ooblayout = {
+	.ecc = xt26g0xa_ooblayout_ecc,
+	.free = xt26g0xa_ooblayout_free,
+};
+
+static int xt26g0xa_ecc_get_status(struct spinand_device *spinand,
+					 u8 status)
+{
+	status = status & XT26G0XA_STATUS_ECC_MASK;
+
+	switch (status) {
+	case XT26G0XA_STATUS_ECC_NO_DETECTED:
+		return 0;
+	case XT26G0XA_STATUS_ECC_8_CORRECTED:
+		return 8;
+	case XT26G0XA_STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+	default:
+		break;
+	}
+
+	/* At this point values greater than (2 << 4) are invalid  */
+	if (status > XT26G0XA_STATUS_ECC_UNCOR_ERROR)
+		return -EINVAL;
+
+	/* (1 << 2) through (7 << 2) are 1-7 corrected errors */
+	return status >> 2;
+}
+
+static const struct spinand_info xtx_spinand_table[] = {
+	SPINAND_INFO("XT26G01A",
+		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xE1),
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&xt26g0xa_ooblayout,
+				     xt26g0xa_ecc_get_status)),
+	SPINAND_INFO("XT26G02A",
+		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xE2),
+		     NAND_MEMORG(1, 2048, 64, 64, 2048, 40, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&xt26g0xa_ooblayout,
+				     xt26g0xa_ecc_get_status)),
+	SPINAND_INFO("XT26G04A",
+		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0xE3),
+		     NAND_MEMORG(1, 2048, 64, 128, 2048, 40, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&xt26g0xa_ooblayout,
+				     xt26g0xa_ecc_get_status)),
+};
+
+static const struct spinand_manufacturer_ops xtx_spinand_manuf_ops = {
+};
+
+const struct spinand_manufacturer xtx_spinand_manufacturer = {
+	.id = SPINAND_MFR_XTX,
+	.name = "XTX",
+	.chips = xtx_spinand_table,
+	.nchips = ARRAY_SIZE(xtx_spinand_table),
+	.ops = &xtx_spinand_manuf_ops,
+};
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 3aa28240a77f..5584d3bb6556 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -266,6 +266,7 @@ extern const struct spinand_manufacturer micron_spinand_manufacturer;
 extern const struct spinand_manufacturer paragon_spinand_manufacturer;
 extern const struct spinand_manufacturer toshiba_spinand_manufacturer;
 extern const struct spinand_manufacturer winbond_spinand_manufacturer;
+extern const struct spinand_manufacturer xtx_spinand_manufacturer;
 
 /**
  * struct spinand_op_variants - SPI NAND operation variants
-- 
cgit v1.2.3


From 0b0002315adfea3d9eb102665a4441727d4d2621 Mon Sep 17 00:00:00 2001
From: Weili Qian <qianweili@huawei.com>
Date: Sat, 16 Apr 2022 18:45:56 +0800
Subject: crypto: hisilicon/qm - remove unused function declaration

The 'hisi_qm_get_hw_version' function is unused, so remove the function
declaration.

Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/hisi_acc_qm.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index e5522eaf88fd..5177858aeea9 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -453,7 +453,6 @@ int hisi_qp_send(struct hisi_qp *qp, const void *msg);
 int hisi_qm_get_free_qp_num(struct hisi_qm *qm);
 int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number);
 void hisi_qm_debug_init(struct hisi_qm *qm);
-enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev);
 void hisi_qm_debug_regs_clear(struct hisi_qm *qm);
 int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs);
 int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen);
-- 
cgit v1.2.3


From fb06eb9727d67eac16e6b6aff35362476389cb88 Mon Sep 17 00:00:00 2001
From: Weili Qian <qianweili@huawei.com>
Date: Sat, 16 Apr 2022 18:45:57 +0800
Subject: crypto: hisilicon/qm - set function with static

These functions 'hisi_qm_create_qp' and 'hisi_qm_set_vft' are not
used outside qm.c, so they are marked as static.

Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/qm.c | 6 ++----
 include/linux/hisi_acc_qm.h   | 2 --
 2 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 7f5c3186a895..2a6df6374c91 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -2835,7 +2835,7 @@ static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type)
  * return created qp, -EBUSY if all qps in qm allocated, -ENOMEM if allocating
  * qp memory fails.
  */
-struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type)
+static struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type)
 {
 	struct hisi_qp *qp;
 	int ret;
@@ -2853,7 +2853,6 @@ struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type)
 
 	return qp;
 }
-EXPORT_SYMBOL_GPL(hisi_qm_create_qp);
 
 /**
  * hisi_qm_release_qp() - Release a qp back to its qm.
@@ -3738,7 +3737,7 @@ EXPORT_SYMBOL_GPL(hisi_qm_uninit);
  *
  * qm hw v1 does not support this interface.
  */
-int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number)
+static int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number)
 {
 	if (!base || !number)
 		return -EINVAL;
@@ -3750,7 +3749,6 @@ int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number)
 
 	return qm->ops->get_vft(qm, base, number);
 }
-EXPORT_SYMBOL_GPL(hisi_qm_get_vft);
 
 /**
  * hisi_qm_set_vft() - Set vft to a qm.
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index 5177858aeea9..e99b286b50bc 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -445,13 +445,11 @@ int hisi_qm_init(struct hisi_qm *qm);
 void hisi_qm_uninit(struct hisi_qm *qm);
 int hisi_qm_start(struct hisi_qm *qm);
 int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r);
-struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type);
 int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg);
 int hisi_qm_stop_qp(struct hisi_qp *qp);
 void hisi_qm_release_qp(struct hisi_qp *qp);
 int hisi_qp_send(struct hisi_qp *qp, const void *msg);
 int hisi_qm_get_free_qp_num(struct hisi_qm *qm);
-int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number);
 void hisi_qm_debug_init(struct hisi_qm *qm);
 void hisi_qm_debug_regs_clear(struct hisi_qm *qm);
 int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs);
-- 
cgit v1.2.3


From 7982996c5b0812cbf7846deff0e2f5dcbf290129 Mon Sep 17 00:00:00 2001
From: Weili Qian <qianweili@huawei.com>
Date: Sat, 16 Apr 2022 18:45:58 +0800
Subject: crypto: hisilicon/qm - replace hisi_qm_release_qp() with
 hisi_qm_free_qps()

hisi_qm_free_qps() can release multiple queues in one call, and it is
already exported. So, replace hisi_qm_release_qp() with hisi_qm_free_qps()
in zip_crypto.c, and do not export hisi_qm_release_qp() outside qm.c.

Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/qm.c             | 3 +--
 drivers/crypto/hisilicon/zip/zip_crypto.c | 2 +-
 include/linux/hisi_acc_qm.h               | 1 -
 3 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 2a6df6374c91..286550086c77 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -2860,7 +2860,7 @@ static struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type)
  *
  * This function releases the resource of a qp.
  */
-void hisi_qm_release_qp(struct hisi_qp *qp)
+static void hisi_qm_release_qp(struct hisi_qp *qp)
 {
 	struct hisi_qm *qm = qp->qm;
 
@@ -2878,7 +2878,6 @@ void hisi_qm_release_qp(struct hisi_qp *qp)
 
 	qm_pm_put_sync(qm);
 }
-EXPORT_SYMBOL_GPL(hisi_qm_release_qp);
 
 static int qm_sq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid)
 {
diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c
index 9520a4113c81..67869513e48c 100644
--- a/drivers/crypto/hisilicon/zip/zip_crypto.c
+++ b/drivers/crypto/hisilicon/zip/zip_crypto.c
@@ -521,7 +521,7 @@ static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *ctx,
 static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *ctx)
 {
 	hisi_qm_stop_qp(ctx->qp);
-	hisi_qm_release_qp(ctx->qp);
+	hisi_qm_free_qps(&ctx->qp, 1);
 }
 
 static const struct hisi_zip_sqe_ops hisi_zip_ops_v1 = {
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index e99b286b50bc..d2ccb11071c5 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -447,7 +447,6 @@ int hisi_qm_start(struct hisi_qm *qm);
 int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r);
 int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg);
 int hisi_qm_stop_qp(struct hisi_qp *qp);
-void hisi_qm_release_qp(struct hisi_qp *qp);
 int hisi_qp_send(struct hisi_qp *qp, const void *msg);
 int hisi_qm_get_free_qp_num(struct hisi_qm *qm);
 void hisi_qm_debug_init(struct hisi_qm *qm);
-- 
cgit v1.2.3


From b0c42232fce499ba96fbf2c5ebd2368efeb6597e Mon Sep 17 00:00:00 2001
From: Weili Qian <qianweili@huawei.com>
Date: Sat, 16 Apr 2022 18:45:59 +0800
Subject: crypto: hisilicon/qm - remove hisi_qm_get_free_qp_num()

hisi_qm_get_free_qp_num() is to get the free queue number on the function.
It is a simple function and is only called by
hisi_qm_get_available_instances().

This patch modifies to get the free queue directly in
hisi_qm_get_available_instances(), and remove hisi_qm_get_free_qp_num().

Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/qm.c | 28 +++++++++-------------------
 include/linux/hisi_acc_qm.h   |  1 -
 2 files changed, 9 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 286550086c77..b4ca2eb034d7 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -3226,9 +3226,17 @@ static void qm_qp_event_notifier(struct hisi_qp *qp)
 	wake_up_interruptible(&qp->uacce_q->wait);
 }
 
+ /* This function returns free number of qp in qm. */
 static int hisi_qm_get_available_instances(struct uacce_device *uacce)
 {
-	return hisi_qm_get_free_qp_num(uacce->priv);
+	struct hisi_qm *qm = uacce->priv;
+	int ret;
+
+	down_read(&qm->qps_lock);
+	ret = qm->qp_num - qm->qp_in_used;
+	up_read(&qm->qps_lock);
+
+	return ret;
 }
 
 static void hisi_qm_set_hw_reset(struct hisi_qm *qm, int offset)
@@ -3540,24 +3548,6 @@ void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list)
 }
 EXPORT_SYMBOL_GPL(hisi_qm_wait_task_finish);
 
-/**
- * hisi_qm_get_free_qp_num() - Get free number of qp in qm.
- * @qm: The qm which want to get free qp.
- *
- * This function return free number of qp in qm.
- */
-int hisi_qm_get_free_qp_num(struct hisi_qm *qm)
-{
-	int ret;
-
-	down_read(&qm->qps_lock);
-	ret = qm->qp_num - qm->qp_in_used;
-	up_read(&qm->qps_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(hisi_qm_get_free_qp_num);
-
 static void hisi_qp_memory_uninit(struct hisi_qm *qm, int num)
 {
 	struct device *dev = &qm->pdev->dev;
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index d2ccb11071c5..6cabafffd0dd 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -448,7 +448,6 @@ int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r);
 int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg);
 int hisi_qm_stop_qp(struct hisi_qp *qp);
 int hisi_qp_send(struct hisi_qp *qp, const void *msg);
-int hisi_qm_get_free_qp_num(struct hisi_qm *qm);
 void hisi_qm_debug_init(struct hisi_qm *qm);
 void hisi_qm_debug_regs_clear(struct hisi_qm *qm);
 int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs);
-- 
cgit v1.2.3


From 6c7f98b334a32df5cac8abac8983ac4ce17cab57 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 11 Apr 2022 16:13:59 +0200
Subject: vfio/mdev: Remove vfio_mdev.c

Now that all mdev drivers directly create their own mdev_device driver and
directly register with the vfio core's vfio_device_ops this is all dead
code.

Delete vfio_mdev.c and the mdev_parent_ops members that are connected to
it.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-31-hch@lst.de
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
---
 Documentation/driver-api/vfio-mediated-device.rst |   3 -
 drivers/vfio/mdev/Makefile                        |   2 +-
 drivers/vfio/mdev/mdev_core.c                     |  40 +-----
 drivers/vfio/mdev/mdev_driver.c                   |  10 --
 drivers/vfio/mdev/mdev_private.h                  |   2 -
 drivers/vfio/mdev/vfio_mdev.c                     | 152 ----------------------
 include/linux/mdev.h                              |  48 +------
 7 files changed, 6 insertions(+), 251 deletions(-)
 delete mode 100644 drivers/vfio/mdev/vfio_mdev.c

(limited to 'include/linux')

diff --git a/Documentation/driver-api/vfio-mediated-device.rst b/Documentation/driver-api/vfio-mediated-device.rst
index 9f26079cacae..5a6e18a651a1 100644
--- a/Documentation/driver-api/vfio-mediated-device.rst
+++ b/Documentation/driver-api/vfio-mediated-device.rst
@@ -138,9 +138,6 @@ The structures in the mdev_parent_ops structure are as follows:
 * supported_config: attributes to define supported configurations
 * device_driver: device driver to bind for mediated device instances
 
-The mdev_parent_ops also still has various functions pointers.  Theses exist
-for historical reasons only and shall not be used for new drivers.
-
 When a driver wants to add the GUID creation sysfs to an existing device it has
 probe'd to then it should call::
 
diff --git a/drivers/vfio/mdev/Makefile b/drivers/vfio/mdev/Makefile
index ff9ecd802125..7c236ba1b90e 100644
--- a/drivers/vfio/mdev/Makefile
+++ b/drivers/vfio/mdev/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-mdev-y := mdev_core.o mdev_sysfs.o mdev_driver.o vfio_mdev.o
+mdev-y := mdev_core.o mdev_sysfs.o mdev_driver.o
 
 obj-$(CONFIG_VFIO_MDEV) += mdev.o
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index b314101237fe..8b1e86b9e8bc 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -89,17 +89,10 @@ void mdev_release_parent(struct kref *kref)
 static void mdev_device_remove_common(struct mdev_device *mdev)
 {
 	struct mdev_parent *parent = mdev->type->parent;
-	int ret;
 
 	mdev_remove_sysfs_files(mdev);
 	device_del(&mdev->dev);
 	lockdep_assert_held(&parent->unreg_sem);
-	if (parent->ops->remove) {
-		ret = parent->ops->remove(mdev);
-		if (ret)
-			dev_err(&mdev->dev, "Remove failed: err=%d\n", ret);
-	}
-
 	/* Balances with device_initialize() */
 	put_device(&mdev->dev);
 }
@@ -131,7 +124,7 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	/* check for mandatory ops */
 	if (!ops || !ops->supported_type_groups)
 		return -EINVAL;
-	if (!ops->device_driver && (!ops->create || !ops->remove))
+	if (!ops->device_driver)
 		return -EINVAL;
 
 	dev = get_device(dev);
@@ -297,18 +290,10 @@ int mdev_device_create(struct mdev_type *type, const guid_t *uuid)
 		goto out_put_device;
 	}
 
-	if (parent->ops->create) {
-		ret = parent->ops->create(mdev);
-		if (ret)
-			goto out_unlock;
-	}
-
 	ret = device_add(&mdev->dev);
 	if (ret)
-		goto out_remove;
+		goto out_unlock;
 
-	if (!drv)
-		drv = &vfio_mdev_driver;
 	ret = device_driver_attach(&drv->driver, &mdev->dev);
 	if (ret)
 		goto out_del;
@@ -325,9 +310,6 @@ int mdev_device_create(struct mdev_type *type, const guid_t *uuid)
 
 out_del:
 	device_del(&mdev->dev);
-out_remove:
-	if (parent->ops->remove)
-		parent->ops->remove(mdev);
 out_unlock:
 	up_read(&parent->unreg_sem);
 out_put_device:
@@ -370,28 +352,14 @@ int mdev_device_remove(struct mdev_device *mdev)
 
 static int __init mdev_init(void)
 {
-	int rc;
-
-	rc = mdev_bus_register();
-	if (rc)
-		return rc;
-	rc = mdev_register_driver(&vfio_mdev_driver);
-	if (rc)
-		goto err_bus;
-	return 0;
-err_bus:
-	mdev_bus_unregister();
-	return rc;
+	return bus_register(&mdev_bus_type);
 }
 
 static void __exit mdev_exit(void)
 {
-	mdev_unregister_driver(&vfio_mdev_driver);
-
 	if (mdev_bus_compat_class)
 		class_compat_unregister(mdev_bus_compat_class);
-
-	mdev_bus_unregister();
+	bus_unregister(&mdev_bus_type);
 }
 
 subsys_initcall(mdev_init)
diff --git a/drivers/vfio/mdev/mdev_driver.c b/drivers/vfio/mdev/mdev_driver.c
index 7927ed4f1711..9c2af59809e2 100644
--- a/drivers/vfio/mdev/mdev_driver.c
+++ b/drivers/vfio/mdev/mdev_driver.c
@@ -74,13 +74,3 @@ void mdev_unregister_driver(struct mdev_driver *drv)
 	driver_unregister(&drv->driver);
 }
 EXPORT_SYMBOL(mdev_unregister_driver);
-
-int mdev_bus_register(void)
-{
-	return bus_register(&mdev_bus_type);
-}
-
-void mdev_bus_unregister(void)
-{
-	bus_unregister(&mdev_bus_type);
-}
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h
index afbad7b0a14a..6999c89db7b1 100644
--- a/drivers/vfio/mdev/mdev_private.h
+++ b/drivers/vfio/mdev/mdev_private.h
@@ -37,8 +37,6 @@ struct mdev_type {
 #define to_mdev_type(_kobj)		\
 	container_of(_kobj, struct mdev_type, kobj)
 
-extern struct mdev_driver vfio_mdev_driver;
-
 int  parent_create_sysfs_files(struct mdev_parent *parent);
 void parent_remove_sysfs_files(struct mdev_parent *parent);
 
diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c
deleted file mode 100644
index a90e24b0c851..000000000000
--- a/drivers/vfio/mdev/vfio_mdev.c
+++ /dev/null
@@ -1,152 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * VFIO based driver for Mediated device
- *
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *     Author: Neo Jia <cjia@nvidia.com>
- *             Kirti Wankhede <kwankhede@nvidia.com>
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/vfio.h>
-#include <linux/mdev.h>
-
-#include "mdev_private.h"
-
-static int vfio_mdev_open_device(struct vfio_device *core_vdev)
-{
-	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
-	struct mdev_parent *parent = mdev->type->parent;
-
-	if (unlikely(!parent->ops->open_device))
-		return 0;
-
-	return parent->ops->open_device(mdev);
-}
-
-static void vfio_mdev_close_device(struct vfio_device *core_vdev)
-{
-	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
-	struct mdev_parent *parent = mdev->type->parent;
-
-	if (likely(parent->ops->close_device))
-		parent->ops->close_device(mdev);
-}
-
-static long vfio_mdev_unlocked_ioctl(struct vfio_device *core_vdev,
-				     unsigned int cmd, unsigned long arg)
-{
-	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
-	struct mdev_parent *parent = mdev->type->parent;
-
-	if (unlikely(!parent->ops->ioctl))
-		return 0;
-
-	return parent->ops->ioctl(mdev, cmd, arg);
-}
-
-static ssize_t vfio_mdev_read(struct vfio_device *core_vdev, char __user *buf,
-			      size_t count, loff_t *ppos)
-{
-	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
-	struct mdev_parent *parent = mdev->type->parent;
-
-	if (unlikely(!parent->ops->read))
-		return -EINVAL;
-
-	return parent->ops->read(mdev, buf, count, ppos);
-}
-
-static ssize_t vfio_mdev_write(struct vfio_device *core_vdev,
-			       const char __user *buf, size_t count,
-			       loff_t *ppos)
-{
-	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
-	struct mdev_parent *parent = mdev->type->parent;
-
-	if (unlikely(!parent->ops->write))
-		return -EINVAL;
-
-	return parent->ops->write(mdev, buf, count, ppos);
-}
-
-static int vfio_mdev_mmap(struct vfio_device *core_vdev,
-			  struct vm_area_struct *vma)
-{
-	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
-	struct mdev_parent *parent = mdev->type->parent;
-
-	if (unlikely(!parent->ops->mmap))
-		return -EINVAL;
-
-	return parent->ops->mmap(mdev, vma);
-}
-
-static void vfio_mdev_request(struct vfio_device *core_vdev, unsigned int count)
-{
-	struct mdev_device *mdev = to_mdev_device(core_vdev->dev);
-	struct mdev_parent *parent = mdev->type->parent;
-
-	if (parent->ops->request)
-		parent->ops->request(mdev, count);
-	else if (count == 0)
-		dev_notice(mdev_dev(mdev),
-			   "No mdev vendor driver request callback support, blocked until released by user\n");
-}
-
-static const struct vfio_device_ops vfio_mdev_dev_ops = {
-	.name		= "vfio-mdev",
-	.open_device	= vfio_mdev_open_device,
-	.close_device	= vfio_mdev_close_device,
-	.ioctl		= vfio_mdev_unlocked_ioctl,
-	.read		= vfio_mdev_read,
-	.write		= vfio_mdev_write,
-	.mmap		= vfio_mdev_mmap,
-	.request	= vfio_mdev_request,
-};
-
-static int vfio_mdev_probe(struct mdev_device *mdev)
-{
-	struct vfio_device *vdev;
-	int ret;
-
-	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
-	if (!vdev)
-		return -ENOMEM;
-
-	vfio_init_group_dev(vdev, &mdev->dev, &vfio_mdev_dev_ops);
-	ret = vfio_register_emulated_iommu_dev(vdev);
-	if (ret)
-		goto out_uninit;
-
-	dev_set_drvdata(&mdev->dev, vdev);
-	return 0;
-
-out_uninit:
-	vfio_uninit_group_dev(vdev);
-	kfree(vdev);
-	return ret;
-}
-
-static void vfio_mdev_remove(struct mdev_device *mdev)
-{
-	struct vfio_device *vdev = dev_get_drvdata(&mdev->dev);
-
-	vfio_unregister_group_dev(vdev);
-	vfio_uninit_group_dev(vdev);
-	kfree(vdev);
-}
-
-struct mdev_driver vfio_mdev_driver = {
-	.driver = {
-		.name = "vfio_mdev",
-		.owner = THIS_MODULE,
-		.mod_name = KBUILD_MODNAME,
-	},
-	.probe	= vfio_mdev_probe,
-	.remove	= vfio_mdev_remove,
-};
diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index 15d03f6532d0..192aed656116 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -40,40 +40,7 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype);
  * @mdev_attr_groups:	Attributes of the mediated device.
  * @supported_type_groups: Attributes to define supported types. It is mandatory
  *			to provide supported types.
- * @create:		Called to allocate basic resources in parent device's
- *			driver for a particular mediated device. It is
- *			mandatory to provide create ops.
- *			@mdev: mdev_device structure on of mediated device
- *			      that is being created
- *			Returns integer: success (0) or error (< 0)
- * @remove:		Called to free resources in parent device's driver for
- *			a mediated device. It is mandatory to provide 'remove'
- *			ops.
- *			@mdev: mdev_device device structure which is being
- *			       destroyed
- *			Returns integer: success (0) or error (< 0)
- * @read:		Read emulation callback
- *			@mdev: mediated device structure
- *			@buf: read buffer
- *			@count: number of bytes to read
- *			@ppos: address.
- *			Retuns number on bytes read on success or error.
- * @write:		Write emulation callback
- *			@mdev: mediated device structure
- *			@buf: write buffer
- *			@count: number of bytes to be written
- *			@ppos: address.
- *			Retuns number on bytes written on success or error.
- * @ioctl:		IOCTL callback
- *			@mdev: mediated device structure
- *			@cmd: ioctl command
- *			@arg: arguments to ioctl
- * @mmap:		mmap callback
- *			@mdev: mediated device structure
- *			@vma: vma structure
- * @request:		request callback to release device
- *			@mdev: mediated device structure
- *			@count: request sequence number
+ *
  * Parent device that support mediated device should be registered with mdev
  * module with mdev_parent_ops structure.
  **/
@@ -83,19 +50,6 @@ struct mdev_parent_ops {
 	const struct attribute_group **dev_attr_groups;
 	const struct attribute_group **mdev_attr_groups;
 	struct attribute_group **supported_type_groups;
-
-	int     (*create)(struct mdev_device *mdev);
-	int     (*remove)(struct mdev_device *mdev);
-	int     (*open_device)(struct mdev_device *mdev);
-	void    (*close_device)(struct mdev_device *mdev);
-	ssize_t (*read)(struct mdev_device *mdev, char __user *buf,
-			size_t count, loff_t *ppos);
-	ssize_t (*write)(struct mdev_device *mdev, const char __user *buf,
-			 size_t count, loff_t *ppos);
-	long	(*ioctl)(struct mdev_device *mdev, unsigned int cmd,
-			 unsigned long arg);
-	int	(*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma);
-	void	(*request)(struct mdev_device *mdev, unsigned int count);
 };
 
 /* interface for exporting mdev supported type attributes */
-- 
cgit v1.2.3


From e6486939d8ea22569af942a1888aa3824f59cc5e Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 11 Apr 2022 16:14:00 +0200
Subject: vfio/mdev: Remove mdev_parent_ops dev_attr_groups

This is only used by one sample to print a fixed string that is pointless.

In general, having a device driver attach sysfs attributes to the parent
is horrific. This should never happen, and always leads to some kind of
liftime bug as it become very difficult for the sysfs attribute to go back
to any data owned by the device driver.

Remove the general mechanism to create this abuse.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-32-hch@lst.de
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
---
 drivers/vfio/mdev/mdev_sysfs.c | 12 ++----------
 include/linux/mdev.h           |  2 --
 samples/vfio-mdev/mtty.c       | 30 +-----------------------------
 3 files changed, 3 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index f5cf1931c54e..66eef08833a4 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -197,7 +197,6 @@ void parent_remove_sysfs_files(struct mdev_parent *parent)
 		remove_mdev_supported_type(type);
 	}
 
-	sysfs_remove_groups(&parent->dev->kobj, parent->ops->dev_attr_groups);
 	kset_unregister(parent->mdev_types_kset);
 }
 
@@ -213,17 +212,10 @@ int parent_create_sysfs_files(struct mdev_parent *parent)
 
 	INIT_LIST_HEAD(&parent->type_list);
 
-	ret = sysfs_create_groups(&parent->dev->kobj,
-				  parent->ops->dev_attr_groups);
-	if (ret)
-		goto create_err;
-
 	ret = add_mdev_supported_type_groups(parent);
 	if (ret)
-		sysfs_remove_groups(&parent->dev->kobj,
-				    parent->ops->dev_attr_groups);
-	else
-		return ret;
+		goto create_err;
+	return 0;
 
 create_err:
 	kset_unregister(parent->mdev_types_kset);
diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index 192aed656116..69df1fa2cb6f 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -36,7 +36,6 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype);
  *
  * @owner:		The module owner.
  * @device_driver:	Which device driver to probe() on newly created devices
- * @dev_attr_groups:	Attributes of the parent device.
  * @mdev_attr_groups:	Attributes of the mediated device.
  * @supported_type_groups: Attributes to define supported types. It is mandatory
  *			to provide supported types.
@@ -47,7 +46,6 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype);
 struct mdev_parent_ops {
 	struct module   *owner;
 	struct mdev_driver *device_driver;
-	const struct attribute_group **dev_attr_groups;
 	const struct attribute_group **mdev_attr_groups;
 	struct attribute_group **supported_type_groups;
 };
diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c
index a0e1a469bd47..4f227dc26785 100644
--- a/samples/vfio-mdev/mtty.c
+++ b/samples/vfio-mdev/mtty.c
@@ -1207,38 +1207,11 @@ static long mtty_ioctl(struct vfio_device *vdev, unsigned int cmd,
 	return -ENOTTY;
 }
 
-static ssize_t
-sample_mtty_dev_show(struct device *dev, struct device_attribute *attr,
-		     char *buf)
-{
-	return sprintf(buf, "This is phy device\n");
-}
-
-static DEVICE_ATTR_RO(sample_mtty_dev);
-
-static struct attribute *mtty_dev_attrs[] = {
-	&dev_attr_sample_mtty_dev.attr,
-	NULL,
-};
-
-static const struct attribute_group mtty_dev_group = {
-	.name  = "mtty_dev",
-	.attrs = mtty_dev_attrs,
-};
-
-static const struct attribute_group *mtty_dev_groups[] = {
-	&mtty_dev_group,
-	NULL,
-};
-
 static ssize_t
 sample_mdev_dev_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
 {
-	if (mdev_from_dev(dev))
-		return sprintf(buf, "This is MDEV %s\n", dev_name(dev));
-
-	return sprintf(buf, "\n");
+	return sprintf(buf, "This is MDEV %s\n", dev_name(dev));
 }
 
 static DEVICE_ATTR_RO(sample_mdev_dev);
@@ -1333,7 +1306,6 @@ static struct mdev_driver mtty_driver = {
 static const struct mdev_parent_ops mdev_fops = {
 	.owner                  = THIS_MODULE,
 	.device_driver		= &mtty_driver,
-	.dev_attr_groups        = mtty_dev_groups,
 	.supported_type_groups  = mdev_type_groups,
 };
 
-- 
cgit v1.2.3


From 6b42f491e17ce13f5ff7f2d1f49c73a0f4c47b20 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 11 Apr 2022 16:14:01 +0200
Subject: vfio/mdev: Remove mdev_parent_ops

The last useful member in this struct is the supported_type_groups, move
it to the mdev_driver and delete mdev_parent_ops.

Replace it with mdev_driver as an argument to mdev_register_device()

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-33-hch@lst.de
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
---
 Documentation/driver-api/vfio-mediated-device.rst | 24 +++++-----------------
 drivers/gpu/drm/i915/gvt/kvmgt.c                  |  7 +------
 drivers/s390/cio/vfio_ccw_ops.c                   |  7 +------
 drivers/s390/crypto/vfio_ap_ops.c                 |  9 ++------
 drivers/vfio/mdev/mdev_core.c                     | 13 +++++-------
 drivers/vfio/mdev/mdev_private.h                  |  2 +-
 drivers/vfio/mdev/mdev_sysfs.c                    |  6 +++---
 include/linux/mdev.h                              | 25 ++++-------------------
 samples/vfio-mdev/mbochs.c                        |  9 ++------
 samples/vfio-mdev/mdpy.c                          |  9 ++------
 samples/vfio-mdev/mtty.c                          |  9 ++------
 11 files changed, 28 insertions(+), 92 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/vfio-mediated-device.rst b/Documentation/driver-api/vfio-mediated-device.rst
index 5a6e18a651a1..784bbeb22adc 100644
--- a/Documentation/driver-api/vfio-mediated-device.rst
+++ b/Documentation/driver-api/vfio-mediated-device.rst
@@ -105,6 +105,7 @@ structure to represent a mediated device's driver::
      struct mdev_driver {
 	     int  (*probe)  (struct mdev_device *dev);
 	     void (*remove) (struct mdev_device *dev);
+	     struct attribute_group **supported_type_groups;
 	     struct device_driver    driver;
      };
 
@@ -119,30 +120,15 @@ to register and unregister itself with the core driver:
 
     extern void mdev_unregister_driver(struct mdev_driver *drv);
 
-The mediated bus driver is responsible for adding mediated devices to the VFIO
-group when devices are bound to the driver and removing mediated devices from
-the VFIO when devices are unbound from the driver.
-
-
-Physical Device Driver Interface
---------------------------------
-
-The physical device driver interface provides the mdev_parent_ops[3] structure
-to define the APIs to manage work in the mediated core driver that is related
-to the physical device.
-
-The structures in the mdev_parent_ops structure are as follows:
-
-* dev_attr_groups: attributes of the parent device
-* mdev_attr_groups: attributes of the mediated device
-* supported_config: attributes to define supported configurations
-* device_driver: device driver to bind for mediated device instances
+The mediated bus driver's probe function should create a vfio_device on top of
+the mdev_device and connect it to an appropriate implementation of
+vfio_device_ops.
 
 When a driver wants to add the GUID creation sysfs to an existing device it has
 probe'd to then it should call::
 
 	extern int  mdev_register_device(struct device *dev,
-	                                 const struct mdev_parent_ops *ops);
+	                                 struct mdev_driver *mdev_driver);
 
 This will provide the 'mdev_supported_types/XX/create' files which can then be
 used to trigger the creation of a mdev_device. The created mdev_device will be
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index f033031c676d..0787ba5c301f 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1723,12 +1723,7 @@ static struct mdev_driver intel_vgpu_mdev_driver = {
 	},
 	.probe		= intel_vgpu_probe,
 	.remove		= intel_vgpu_remove,
-};
-
-static const struct mdev_parent_ops intel_vgpu_mdev_ops = {
-	.owner			= THIS_MODULE,
 	.supported_type_groups	= gvt_vgpu_type_groups,
-	.device_driver		= &intel_vgpu_mdev_driver,
 };
 
 int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
@@ -2131,7 +2126,7 @@ static int intel_gvt_init_device(struct drm_i915_private *i915)
 	if (ret)
 		goto out_destroy_idle_vgpu;
 
-	ret = mdev_register_device(i915->drm.dev, &intel_vgpu_mdev_ops);
+	ret = mdev_register_device(i915->drm.dev, &intel_vgpu_mdev_driver);
 	if (ret)
 		goto out_cleanup_vgpu_type_groups;
 
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index d8589afac272..c4d60cdbf247 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -656,17 +656,12 @@ struct mdev_driver vfio_ccw_mdev_driver = {
 	},
 	.probe = vfio_ccw_mdev_probe,
 	.remove = vfio_ccw_mdev_remove,
-};
-
-static const struct mdev_parent_ops vfio_ccw_mdev_ops = {
-	.owner			= THIS_MODULE,
-	.device_driver		= &vfio_ccw_mdev_driver,
 	.supported_type_groups  = mdev_type_groups,
 };
 
 int vfio_ccw_mdev_reg(struct subchannel *sch)
 {
-	return mdev_register_device(&sch->dev, &vfio_ccw_mdev_ops);
+	return mdev_register_device(&sch->dev, &vfio_ccw_mdev_driver);
 }
 
 void vfio_ccw_mdev_unreg(struct subchannel *sch)
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 6e08d04b605d..ee0a3bf8f476 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -1496,12 +1496,7 @@ static struct mdev_driver vfio_ap_matrix_driver = {
 	},
 	.probe = vfio_ap_mdev_probe,
 	.remove = vfio_ap_mdev_remove,
-};
-
-static const struct mdev_parent_ops vfio_ap_matrix_ops = {
-	.owner			= THIS_MODULE,
-	.device_driver		= &vfio_ap_matrix_driver,
-	.supported_type_groups	= vfio_ap_mdev_type_groups,
+	.supported_type_groups = vfio_ap_mdev_type_groups,
 };
 
 int vfio_ap_mdev_register(void)
@@ -1514,7 +1509,7 @@ int vfio_ap_mdev_register(void)
 	if (ret)
 		return ret;
 
-	ret = mdev_register_device(&matrix_dev->device, &vfio_ap_matrix_ops);
+	ret = mdev_register_device(&matrix_dev->device, &vfio_ap_matrix_driver);
 	if (ret)
 		goto err_driver;
 	return 0;
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index 8b1e86b9e8bc..19a20ff420b7 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -109,12 +109,12 @@ static int mdev_device_remove_cb(struct device *dev, void *data)
 /*
  * mdev_register_device : Register a device
  * @dev: device structure representing parent device.
- * @ops: Parent device operation structure to be registered.
+ * @mdev_driver: Device driver to bind to the newly created mdev
  *
  * Add device to list of registered parent devices.
  * Returns a negative value on error, otherwise 0.
  */
-int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
+int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver)
 {
 	int ret;
 	struct mdev_parent *parent;
@@ -122,9 +122,7 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	char *envp[] = { env_string, NULL };
 
 	/* check for mandatory ops */
-	if (!ops || !ops->supported_type_groups)
-		return -EINVAL;
-	if (!ops->device_driver)
+	if (!mdev_driver->supported_type_groups)
 		return -EINVAL;
 
 	dev = get_device(dev);
@@ -151,7 +149,7 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	init_rwsem(&parent->unreg_sem);
 
 	parent->dev = dev;
-	parent->ops = ops;
+	parent->mdev_driver = mdev_driver;
 
 	if (!mdev_bus_compat_class) {
 		mdev_bus_compat_class = class_compat_register("mdev_bus");
@@ -249,7 +247,7 @@ int mdev_device_create(struct mdev_type *type, const guid_t *uuid)
 	int ret;
 	struct mdev_device *mdev, *tmp;
 	struct mdev_parent *parent = type->parent;
-	struct mdev_driver *drv = parent->ops->device_driver;
+	struct mdev_driver *drv = parent->mdev_driver;
 
 	mutex_lock(&mdev_list_lock);
 
@@ -271,7 +269,6 @@ int mdev_device_create(struct mdev_type *type, const guid_t *uuid)
 	mdev->dev.parent  = parent->dev;
 	mdev->dev.bus = &mdev_bus_type;
 	mdev->dev.release = mdev_device_release;
-	mdev->dev.groups = parent->ops->mdev_attr_groups;
 	mdev->type = type;
 	/* Pairs with the put in mdev_device_release() */
 	kobject_get(&type->kobj);
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h
index 6999c89db7b1..5a7ffd4e770f 100644
--- a/drivers/vfio/mdev/mdev_private.h
+++ b/drivers/vfio/mdev/mdev_private.h
@@ -15,7 +15,7 @@ void mdev_bus_unregister(void);
 
 struct mdev_parent {
 	struct device *dev;
-	const struct mdev_parent_ops *ops;
+	struct mdev_driver *mdev_driver;
 	struct kref ref;
 	struct list_head next;
 	struct kset *mdev_types_kset;
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 66eef08833a4..5a3873d1a275 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -97,7 +97,7 @@ static struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent,
 {
 	struct mdev_type *type;
 	struct attribute_group *group =
-		parent->ops->supported_type_groups[type_group_id];
+		parent->mdev_driver->supported_type_groups[type_group_id];
 	int ret;
 
 	if (!group->name) {
@@ -154,7 +154,7 @@ attr_create_failed:
 static void remove_mdev_supported_type(struct mdev_type *type)
 {
 	struct attribute_group *group =
-		type->parent->ops->supported_type_groups[type->type_group_id];
+		type->parent->mdev_driver->supported_type_groups[type->type_group_id];
 
 	sysfs_remove_files(&type->kobj,
 			   (const struct attribute **)group->attrs);
@@ -168,7 +168,7 @@ static int add_mdev_supported_type_groups(struct mdev_parent *parent)
 {
 	int i;
 
-	for (i = 0; parent->ops->supported_type_groups[i]; i++) {
+	for (i = 0; parent->mdev_driver->supported_type_groups[i]; i++) {
 		struct mdev_type *type;
 
 		type = add_mdev_supported_type(parent, i);
diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index 69df1fa2cb6f..1f6f57a3c316 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -30,26 +30,6 @@ unsigned int mdev_get_type_group_id(struct mdev_device *mdev);
 unsigned int mtype_get_type_group_id(struct mdev_type *mtype);
 struct device *mtype_get_parent_dev(struct mdev_type *mtype);
 
-/**
- * struct mdev_parent_ops - Structure to be registered for each parent device to
- * register the device to mdev module.
- *
- * @owner:		The module owner.
- * @device_driver:	Which device driver to probe() on newly created devices
- * @mdev_attr_groups:	Attributes of the mediated device.
- * @supported_type_groups: Attributes to define supported types. It is mandatory
- *			to provide supported types.
- *
- * Parent device that support mediated device should be registered with mdev
- * module with mdev_parent_ops structure.
- **/
-struct mdev_parent_ops {
-	struct module   *owner;
-	struct mdev_driver *device_driver;
-	const struct attribute_group **mdev_attr_groups;
-	struct attribute_group **supported_type_groups;
-};
-
 /* interface for exporting mdev supported type attributes */
 struct mdev_type_attribute {
 	struct attribute attr;
@@ -74,12 +54,15 @@ struct mdev_type_attribute mdev_type_attr_##_name =		\
  * struct mdev_driver - Mediated device driver
  * @probe: called when new device created
  * @remove: called when device removed
+ * @supported_type_groups: Attributes to define supported types. It is mandatory
+ *			to provide supported types.
  * @driver: device driver structure
  *
  **/
 struct mdev_driver {
 	int (*probe)(struct mdev_device *dev);
 	void (*remove)(struct mdev_device *dev);
+	struct attribute_group **supported_type_groups;
 	struct device_driver driver;
 };
 
@@ -98,7 +81,7 @@ static inline const guid_t *mdev_uuid(struct mdev_device *mdev)
 
 extern struct bus_type mdev_bus_type;
 
-int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops);
+int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver);
 void mdev_unregister_device(struct device *dev);
 
 int mdev_register_driver(struct mdev_driver *drv);
diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c
index e90c8552cc31..344c2901a82b 100644
--- a/samples/vfio-mdev/mbochs.c
+++ b/samples/vfio-mdev/mbochs.c
@@ -1412,12 +1412,7 @@ static struct mdev_driver mbochs_driver = {
 	},
 	.probe = mbochs_probe,
 	.remove	= mbochs_remove,
-};
-
-static const struct mdev_parent_ops mdev_fops = {
-	.owner			= THIS_MODULE,
-	.device_driver		= &mbochs_driver,
-	.supported_type_groups	= mdev_type_groups,
+	.supported_type_groups = mdev_type_groups,
 };
 
 static const struct file_operations vd_fops = {
@@ -1462,7 +1457,7 @@ static int __init mbochs_dev_init(void)
 	if (ret)
 		goto err_class;
 
-	ret = mdev_register_device(&mbochs_dev, &mdev_fops);
+	ret = mdev_register_device(&mbochs_dev, &mbochs_driver);
 	if (ret)
 		goto err_device;
 
diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c
index fe5d43e797b6..e8c46eb2e246 100644
--- a/samples/vfio-mdev/mdpy.c
+++ b/samples/vfio-mdev/mdpy.c
@@ -723,12 +723,7 @@ static struct mdev_driver mdpy_driver = {
 	},
 	.probe = mdpy_probe,
 	.remove	= mdpy_remove,
-};
-
-static const struct mdev_parent_ops mdev_fops = {
-	.owner			= THIS_MODULE,
-	.device_driver          = &mdpy_driver,
-	.supported_type_groups	= mdev_type_groups,
+	.supported_type_groups = mdev_type_groups,
 };
 
 static const struct file_operations vd_fops = {
@@ -771,7 +766,7 @@ static int __init mdpy_dev_init(void)
 	if (ret)
 		goto err_class;
 
-	ret = mdev_register_device(&mdpy_dev, &mdev_fops);
+	ret = mdev_register_device(&mdpy_dev, &mdpy_driver);
 	if (ret)
 		goto err_device;
 
diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c
index 4f227dc26785..f42a59ed2e3f 100644
--- a/samples/vfio-mdev/mtty.c
+++ b/samples/vfio-mdev/mtty.c
@@ -1301,12 +1301,7 @@ static struct mdev_driver mtty_driver = {
 	},
 	.probe = mtty_probe,
 	.remove	= mtty_remove,
-};
-
-static const struct mdev_parent_ops mdev_fops = {
-	.owner                  = THIS_MODULE,
-	.device_driver		= &mtty_driver,
-	.supported_type_groups  = mdev_type_groups,
+	.supported_type_groups = mdev_type_groups,
 };
 
 static void mtty_device_release(struct device *dev)
@@ -1357,7 +1352,7 @@ static int __init mtty_dev_init(void)
 	if (ret)
 		goto err_class;
 
-	ret = mdev_register_device(&mtty_dev.dev, &mdev_fops);
+	ret = mdev_register_device(&mtty_dev.dev, &mtty_driver);
 	if (ret)
 		goto err_device;
 	return 0;
-- 
cgit v1.2.3


From 2917f53113be3b7a0f374e02cebe6d6b749366b5 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 11 Apr 2022 16:14:03 +0200
Subject: vfio/mdev: Remove mdev drvdata

This is no longer used, remove it.

All usages were moved over to either use container_of() from a vfio_device
or to use dev_drvdata() directly on the mdev.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-35-hch@lst.de
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
---
 include/linux/mdev.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index 1f6f57a3c316..bb539794f54a 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -15,7 +15,6 @@ struct mdev_type;
 struct mdev_device {
 	struct device dev;
 	guid_t uuid;
-	void *driver_data;
 	struct list_head next;
 	struct mdev_type *type;
 	bool active;
@@ -66,14 +65,6 @@ struct mdev_driver {
 	struct device_driver driver;
 };
 
-static inline void *mdev_get_drvdata(struct mdev_device *mdev)
-{
-	return mdev->driver_data;
-}
-static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data)
-{
-	mdev->driver_data = data;
-}
 static inline const guid_t *mdev_uuid(struct mdev_device *mdev)
 {
 	return &mdev->uuid;
-- 
cgit v1.2.3


From 042c48848b7d8dab4f095bce2872c02f711bf5d0 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 5 Aug 2019 23:15:37 +0200
Subject: ARM: omap1: move lcd_dma code into omapfb driver

The omapfb driver is split into platform specific code for omap1, and
driver code that is also specific to omap1.

Moving both parts into the driver directory simplifies the structure
and avoids the dependency on certain omap machine header files.

As mach/lcd_dma.h can not be included from include/linux/omap-dma.h
any more now, move the omap_lcd_dma_running() declaration into the
omap-dma header, which matches where it is defined.

Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-omap1/Makefile               |   4 -
 arch/arm/mach-omap1/include/mach/lcd_dma.h |  65 -----
 arch/arm/mach-omap1/include/mach/lcdc.h    |  44 ---
 arch/arm/mach-omap1/lcd_dma.c              | 441 ----------------------------
 drivers/video/fbdev/Makefile               |   2 +-
 drivers/video/fbdev/omap/Makefile          |   5 +
 drivers/video/fbdev/omap/lcd_dma.c         | 443 +++++++++++++++++++++++++++++
 drivers/video/fbdev/omap/lcd_dma.h         |  63 ++++
 drivers/video/fbdev/omap/lcdc.c            |   2 +-
 drivers/video/fbdev/omap/lcdc.h            |  35 +++
 drivers/video/fbdev/omap/sossi.c           |   1 +
 include/linux/omap-dma.h                   |   4 +-
 12 files changed, 551 insertions(+), 558 deletions(-)
 delete mode 100644 arch/arm/mach-omap1/include/mach/lcd_dma.h
 delete mode 100644 arch/arm/mach-omap1/include/mach/lcdc.h
 delete mode 100644 arch/arm/mach-omap1/lcd_dma.c
 create mode 100644 drivers/video/fbdev/omap/lcd_dma.c
 create mode 100644 drivers/video/fbdev/omap/lcd_dma.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/Makefile b/arch/arm/mach-omap1/Makefile
index c757a52d0801..450bbf552b57 100644
--- a/arch/arm/mach-omap1/Makefile
+++ b/arch/arm/mach-omap1/Makefile
@@ -57,7 +57,3 @@ obj-$(CONFIG_ARCH_OMAP730)		+= gpio7xx.o
 obj-$(CONFIG_ARCH_OMAP850)		+= gpio7xx.o
 obj-$(CONFIG_ARCH_OMAP15XX)		+= gpio15xx.o
 obj-$(CONFIG_ARCH_OMAP16XX)		+= gpio16xx.o
-
-ifneq ($(CONFIG_FB_OMAP),)
-obj-y += lcd_dma.o
-endif
diff --git a/arch/arm/mach-omap1/include/mach/lcd_dma.h b/arch/arm/mach-omap1/include/mach/lcd_dma.h
deleted file mode 100644
index 1a3c0cf17899..000000000000
--- a/arch/arm/mach-omap1/include/mach/lcd_dma.h
+++ /dev/null
@@ -1,65 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  arch/arm/mach-omap1/include/mach/lcd_dma.h
- *
- * Extracted from arch/arm/plat-omap/include/plat/dma.h
- *  Copyright (C) 2003 Nokia Corporation
- *  Author: Juha Yrjölä <juha.yrjola@nokia.com>
- */
-#ifndef __MACH_OMAP1_LCD_DMA_H__
-#define __MACH_OMAP1_LCD_DMA_H__
-
-/* Hardware registers for LCD DMA */
-#define OMAP1510_DMA_LCD_BASE		(0xfffedb00)
-#define OMAP1510_DMA_LCD_CTRL		(OMAP1510_DMA_LCD_BASE + 0x00)
-#define OMAP1510_DMA_LCD_TOP_F1_L	(OMAP1510_DMA_LCD_BASE + 0x02)
-#define OMAP1510_DMA_LCD_TOP_F1_U	(OMAP1510_DMA_LCD_BASE + 0x04)
-#define OMAP1510_DMA_LCD_BOT_F1_L	(OMAP1510_DMA_LCD_BASE + 0x06)
-#define OMAP1510_DMA_LCD_BOT_F1_U	(OMAP1510_DMA_LCD_BASE + 0x08)
-
-#define OMAP1610_DMA_LCD_BASE		(0xfffee300)
-#define OMAP1610_DMA_LCD_CSDP		(OMAP1610_DMA_LCD_BASE + 0xc0)
-#define OMAP1610_DMA_LCD_CCR		(OMAP1610_DMA_LCD_BASE + 0xc2)
-#define OMAP1610_DMA_LCD_CTRL		(OMAP1610_DMA_LCD_BASE + 0xc4)
-#define OMAP1610_DMA_LCD_TOP_B1_L	(OMAP1610_DMA_LCD_BASE + 0xc8)
-#define OMAP1610_DMA_LCD_TOP_B1_U	(OMAP1610_DMA_LCD_BASE + 0xca)
-#define OMAP1610_DMA_LCD_BOT_B1_L	(OMAP1610_DMA_LCD_BASE + 0xcc)
-#define OMAP1610_DMA_LCD_BOT_B1_U	(OMAP1610_DMA_LCD_BASE + 0xce)
-#define OMAP1610_DMA_LCD_TOP_B2_L	(OMAP1610_DMA_LCD_BASE + 0xd0)
-#define OMAP1610_DMA_LCD_TOP_B2_U	(OMAP1610_DMA_LCD_BASE + 0xd2)
-#define OMAP1610_DMA_LCD_BOT_B2_L	(OMAP1610_DMA_LCD_BASE + 0xd4)
-#define OMAP1610_DMA_LCD_BOT_B2_U	(OMAP1610_DMA_LCD_BASE + 0xd6)
-#define OMAP1610_DMA_LCD_SRC_EI_B1	(OMAP1610_DMA_LCD_BASE + 0xd8)
-#define OMAP1610_DMA_LCD_SRC_FI_B1_L	(OMAP1610_DMA_LCD_BASE + 0xda)
-#define OMAP1610_DMA_LCD_SRC_EN_B1	(OMAP1610_DMA_LCD_BASE + 0xe0)
-#define OMAP1610_DMA_LCD_SRC_FN_B1	(OMAP1610_DMA_LCD_BASE + 0xe4)
-#define OMAP1610_DMA_LCD_LCH_CTRL	(OMAP1610_DMA_LCD_BASE + 0xea)
-#define OMAP1610_DMA_LCD_SRC_FI_B1_U	(OMAP1610_DMA_LCD_BASE + 0xf4)
-
-/* LCD DMA block numbers */
-enum {
-	OMAP_LCD_DMA_B1_TOP,
-	OMAP_LCD_DMA_B1_BOTTOM,
-	OMAP_LCD_DMA_B2_TOP,
-	OMAP_LCD_DMA_B2_BOTTOM
-};
-
-/* LCD DMA functions */
-extern int omap_request_lcd_dma(void (*callback)(u16 status, void *data),
-				void *data);
-extern void omap_free_lcd_dma(void);
-extern void omap_setup_lcd_dma(void);
-extern void omap_enable_lcd_dma(void);
-extern void omap_stop_lcd_dma(void);
-extern void omap_set_lcd_dma_ext_controller(int external);
-extern void omap_set_lcd_dma_single_transfer(int single);
-extern void omap_set_lcd_dma_b1(unsigned long addr, u16 fb_xres, u16 fb_yres,
-				int data_type);
-extern void omap_set_lcd_dma_b1_rotation(int rotate);
-extern void omap_set_lcd_dma_b1_vxres(unsigned long vxres);
-extern void omap_set_lcd_dma_b1_mirror(int mirror);
-extern void omap_set_lcd_dma_b1_scale(unsigned int xscale, unsigned int yscale);
-
-extern int omap_lcd_dma_running(void);
-
-#endif /* __MACH_OMAP1_LCD_DMA_H__ */
diff --git a/arch/arm/mach-omap1/include/mach/lcdc.h b/arch/arm/mach-omap1/include/mach/lcdc.h
deleted file mode 100644
index 7152db1f5361..000000000000
--- a/arch/arm/mach-omap1/include/mach/lcdc.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * arch/arm/mach-omap1/include/mach/lcdc.h
- *
- * Extracted from drivers/video/omap/lcdc.c
- * Copyright (C) 2004 Nokia Corporation
- * Author: Imre Deak <imre.deak@nokia.com>
- */
-#ifndef __MACH_LCDC_H__
-#define __MACH_LCDC_H__
-
-#define OMAP_LCDC_BASE			0xfffec000
-#define OMAP_LCDC_SIZE			256
-#define OMAP_LCDC_IRQ			INT_LCD_CTRL
-
-#define OMAP_LCDC_CONTROL		(OMAP_LCDC_BASE + 0x00)
-#define OMAP_LCDC_TIMING0		(OMAP_LCDC_BASE + 0x04)
-#define OMAP_LCDC_TIMING1		(OMAP_LCDC_BASE + 0x08)
-#define OMAP_LCDC_TIMING2		(OMAP_LCDC_BASE + 0x0c)
-#define OMAP_LCDC_STATUS		(OMAP_LCDC_BASE + 0x10)
-#define OMAP_LCDC_SUBPANEL		(OMAP_LCDC_BASE + 0x14)
-#define OMAP_LCDC_LINE_INT		(OMAP_LCDC_BASE + 0x18)
-#define OMAP_LCDC_DISPLAY_STATUS	(OMAP_LCDC_BASE + 0x1c)
-
-#define OMAP_LCDC_STAT_DONE		(1 << 0)
-#define OMAP_LCDC_STAT_VSYNC		(1 << 1)
-#define OMAP_LCDC_STAT_SYNC_LOST	(1 << 2)
-#define OMAP_LCDC_STAT_ABC		(1 << 3)
-#define OMAP_LCDC_STAT_LINE_INT		(1 << 4)
-#define OMAP_LCDC_STAT_FUF		(1 << 5)
-#define OMAP_LCDC_STAT_LOADED_PALETTE	(1 << 6)
-
-#define OMAP_LCDC_CTRL_LCD_EN		(1 << 0)
-#define OMAP_LCDC_CTRL_LCD_TFT		(1 << 7)
-#define OMAP_LCDC_CTRL_LINE_IRQ_CLR_SEL	(1 << 10)
-
-#define OMAP_LCDC_IRQ_VSYNC		(1 << 2)
-#define OMAP_LCDC_IRQ_DONE		(1 << 3)
-#define OMAP_LCDC_IRQ_LOADED_PALETTE	(1 << 4)
-#define OMAP_LCDC_IRQ_LINE_NIRQ		(1 << 5)
-#define OMAP_LCDC_IRQ_LINE		(1 << 6)
-#define OMAP_LCDC_IRQ_MASK		(((1 << 5) - 1) << 2)
-
-#endif /* __MACH_LCDC_H__ */
diff --git a/arch/arm/mach-omap1/lcd_dma.c b/arch/arm/mach-omap1/lcd_dma.c
deleted file mode 100644
index a72ac0c02b4f..000000000000
--- a/arch/arm/mach-omap1/lcd_dma.c
+++ /dev/null
@@ -1,441 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/arm/mach-omap1/lcd_dma.c
- *
- * Extracted from arch/arm/plat-omap/dma.c
- * Copyright (C) 2003 - 2008 Nokia Corporation
- * Author: Juha Yrjölä <juha.yrjola@nokia.com>
- * DMA channel linking for 1610 by Samuel Ortiz <samuel.ortiz@nokia.com>
- * Graphics DMA and LCD DMA graphics tranformations
- * by Imre Deak <imre.deak@nokia.com>
- * OMAP2/3 support Copyright (C) 2004-2007 Texas Instruments, Inc.
- * Merged to support both OMAP1 and OMAP2 by Tony Lindgren <tony@atomide.com>
- * Some functions based on earlier dma-omap.c Copyright (C) 2001 RidgeRun, Inc.
- *
- * Copyright (C) 2009 Texas Instruments
- * Added OMAP4 support - Santosh Shilimkar <santosh.shilimkar@ti.com>
- *
- * Support functions for the OMAP internal DMA channels.
- */
-
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-
-#include <linux/omap-dma.h>
-
-#include <mach/hardware.h>
-#include <mach/lcdc.h>
-
-int omap_lcd_dma_running(void)
-{
-	/*
-	 * On OMAP1510, internal LCD controller will start the transfer
-	 * when it gets enabled, so assume DMA running if LCD enabled.
-	 */
-	if (cpu_is_omap15xx())
-		if (omap_readw(OMAP_LCDC_CONTROL) & OMAP_LCDC_CTRL_LCD_EN)
-			return 1;
-
-	/* Check if LCD DMA is running */
-	if (cpu_is_omap16xx())
-		if (omap_readw(OMAP1610_DMA_LCD_CCR) & OMAP_DMA_CCR_EN)
-			return 1;
-
-	return 0;
-}
-
-static struct lcd_dma_info {
-	spinlock_t lock;
-	int reserved;
-	void (*callback)(u16 status, void *data);
-	void *cb_data;
-
-	int active;
-	unsigned long addr;
-	int rotate, data_type, xres, yres;
-	int vxres;
-	int mirror;
-	int xscale, yscale;
-	int ext_ctrl;
-	int src_port;
-	int single_transfer;
-} lcd_dma;
-
-void omap_set_lcd_dma_b1(unsigned long addr, u16 fb_xres, u16 fb_yres,
-			 int data_type)
-{
-	lcd_dma.addr = addr;
-	lcd_dma.data_type = data_type;
-	lcd_dma.xres = fb_xres;
-	lcd_dma.yres = fb_yres;
-}
-EXPORT_SYMBOL(omap_set_lcd_dma_b1);
-
-void omap_set_lcd_dma_ext_controller(int external)
-{
-	lcd_dma.ext_ctrl = external;
-}
-EXPORT_SYMBOL(omap_set_lcd_dma_ext_controller);
-
-void omap_set_lcd_dma_single_transfer(int single)
-{
-	lcd_dma.single_transfer = single;
-}
-EXPORT_SYMBOL(omap_set_lcd_dma_single_transfer);
-
-void omap_set_lcd_dma_b1_rotation(int rotate)
-{
-	if (cpu_is_omap15xx()) {
-		printk(KERN_ERR "DMA rotation is not supported in 1510 mode\n");
-		BUG();
-		return;
-	}
-	lcd_dma.rotate = rotate;
-}
-EXPORT_SYMBOL(omap_set_lcd_dma_b1_rotation);
-
-void omap_set_lcd_dma_b1_mirror(int mirror)
-{
-	if (cpu_is_omap15xx()) {
-		printk(KERN_ERR "DMA mirror is not supported in 1510 mode\n");
-		BUG();
-	}
-	lcd_dma.mirror = mirror;
-}
-EXPORT_SYMBOL(omap_set_lcd_dma_b1_mirror);
-
-void omap_set_lcd_dma_b1_vxres(unsigned long vxres)
-{
-	if (cpu_is_omap15xx()) {
-		pr_err("DMA virtual resolution is not supported in 1510 mode\n");
-		BUG();
-	}
-	lcd_dma.vxres = vxres;
-}
-EXPORT_SYMBOL(omap_set_lcd_dma_b1_vxres);
-
-void omap_set_lcd_dma_b1_scale(unsigned int xscale, unsigned int yscale)
-{
-	if (cpu_is_omap15xx()) {
-		printk(KERN_ERR "DMA scale is not supported in 1510 mode\n");
-		BUG();
-	}
-	lcd_dma.xscale = xscale;
-	lcd_dma.yscale = yscale;
-}
-EXPORT_SYMBOL(omap_set_lcd_dma_b1_scale);
-
-static void set_b1_regs(void)
-{
-	unsigned long top, bottom;
-	int es;
-	u16 w;
-	unsigned long en, fn;
-	long ei, fi;
-	unsigned long vxres;
-	unsigned int xscale, yscale;
-
-	switch (lcd_dma.data_type) {
-	case OMAP_DMA_DATA_TYPE_S8:
-		es = 1;
-		break;
-	case OMAP_DMA_DATA_TYPE_S16:
-		es = 2;
-		break;
-	case OMAP_DMA_DATA_TYPE_S32:
-		es = 4;
-		break;
-	default:
-		BUG();
-		return;
-	}
-
-	vxres = lcd_dma.vxres ? lcd_dma.vxres : lcd_dma.xres;
-	xscale = lcd_dma.xscale ? lcd_dma.xscale : 1;
-	yscale = lcd_dma.yscale ? lcd_dma.yscale : 1;
-	BUG_ON(vxres < lcd_dma.xres);
-
-#define PIXADDR(x, y) (lcd_dma.addr +					\
-		((y) * vxres * yscale + (x) * xscale) * es)
-#define PIXSTEP(sx, sy, dx, dy) (PIXADDR(dx, dy) - PIXADDR(sx, sy) - es + 1)
-
-	switch (lcd_dma.rotate) {
-	case 0:
-		if (!lcd_dma.mirror) {
-			top = PIXADDR(0, 0);
-			bottom = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1);
-			/* 1510 DMA requires the bottom address to be 2 more
-			 * than the actual last memory access location. */
-			if (cpu_is_omap15xx() &&
-				lcd_dma.data_type == OMAP_DMA_DATA_TYPE_S32)
-					bottom += 2;
-			ei = PIXSTEP(0, 0, 1, 0);
-			fi = PIXSTEP(lcd_dma.xres - 1, 0, 0, 1);
-		} else {
-			top = PIXADDR(lcd_dma.xres - 1, 0);
-			bottom = PIXADDR(0, lcd_dma.yres - 1);
-			ei = PIXSTEP(1, 0, 0, 0);
-			fi = PIXSTEP(0, 0, lcd_dma.xres - 1, 1);
-		}
-		en = lcd_dma.xres;
-		fn = lcd_dma.yres;
-		break;
-	case 90:
-		if (!lcd_dma.mirror) {
-			top = PIXADDR(0, lcd_dma.yres - 1);
-			bottom = PIXADDR(lcd_dma.xres - 1, 0);
-			ei = PIXSTEP(0, 1, 0, 0);
-			fi = PIXSTEP(0, 0, 1, lcd_dma.yres - 1);
-		} else {
-			top = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1);
-			bottom = PIXADDR(0, 0);
-			ei = PIXSTEP(0, 1, 0, 0);
-			fi = PIXSTEP(1, 0, 0, lcd_dma.yres - 1);
-		}
-		en = lcd_dma.yres;
-		fn = lcd_dma.xres;
-		break;
-	case 180:
-		if (!lcd_dma.mirror) {
-			top = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1);
-			bottom = PIXADDR(0, 0);
-			ei = PIXSTEP(1, 0, 0, 0);
-			fi = PIXSTEP(0, 1, lcd_dma.xres - 1, 0);
-		} else {
-			top = PIXADDR(0, lcd_dma.yres - 1);
-			bottom = PIXADDR(lcd_dma.xres - 1, 0);
-			ei = PIXSTEP(0, 0, 1, 0);
-			fi = PIXSTEP(lcd_dma.xres - 1, 1, 0, 0);
-		}
-		en = lcd_dma.xres;
-		fn = lcd_dma.yres;
-		break;
-	case 270:
-		if (!lcd_dma.mirror) {
-			top = PIXADDR(lcd_dma.xres - 1, 0);
-			bottom = PIXADDR(0, lcd_dma.yres - 1);
-			ei = PIXSTEP(0, 0, 0, 1);
-			fi = PIXSTEP(1, lcd_dma.yres - 1, 0, 0);
-		} else {
-			top = PIXADDR(0, 0);
-			bottom = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1);
-			ei = PIXSTEP(0, 0, 0, 1);
-			fi = PIXSTEP(0, lcd_dma.yres - 1, 1, 0);
-		}
-		en = lcd_dma.yres;
-		fn = lcd_dma.xres;
-		break;
-	default:
-		BUG();
-		return;	/* Suppress warning about uninitialized vars */
-	}
-
-	if (cpu_is_omap15xx()) {
-		omap_writew(top >> 16, OMAP1510_DMA_LCD_TOP_F1_U);
-		omap_writew(top, OMAP1510_DMA_LCD_TOP_F1_L);
-		omap_writew(bottom >> 16, OMAP1510_DMA_LCD_BOT_F1_U);
-		omap_writew(bottom, OMAP1510_DMA_LCD_BOT_F1_L);
-
-		return;
-	}
-
-	/* 1610 regs */
-	omap_writew(top >> 16, OMAP1610_DMA_LCD_TOP_B1_U);
-	omap_writew(top, OMAP1610_DMA_LCD_TOP_B1_L);
-	omap_writew(bottom >> 16, OMAP1610_DMA_LCD_BOT_B1_U);
-	omap_writew(bottom, OMAP1610_DMA_LCD_BOT_B1_L);
-
-	omap_writew(en, OMAP1610_DMA_LCD_SRC_EN_B1);
-	omap_writew(fn, OMAP1610_DMA_LCD_SRC_FN_B1);
-
-	w = omap_readw(OMAP1610_DMA_LCD_CSDP);
-	w &= ~0x03;
-	w |= lcd_dma.data_type;
-	omap_writew(w, OMAP1610_DMA_LCD_CSDP);
-
-	w = omap_readw(OMAP1610_DMA_LCD_CTRL);
-	/* Always set the source port as SDRAM for now*/
-	w &= ~(0x03 << 6);
-	if (lcd_dma.callback != NULL)
-		w |= 1 << 1;		/* Block interrupt enable */
-	else
-		w &= ~(1 << 1);
-	omap_writew(w, OMAP1610_DMA_LCD_CTRL);
-
-	if (!(lcd_dma.rotate || lcd_dma.mirror ||
-	      lcd_dma.vxres || lcd_dma.xscale || lcd_dma.yscale))
-		return;
-
-	w = omap_readw(OMAP1610_DMA_LCD_CCR);
-	/* Set the double-indexed addressing mode */
-	w |= (0x03 << 12);
-	omap_writew(w, OMAP1610_DMA_LCD_CCR);
-
-	omap_writew(ei, OMAP1610_DMA_LCD_SRC_EI_B1);
-	omap_writew(fi >> 16, OMAP1610_DMA_LCD_SRC_FI_B1_U);
-	omap_writew(fi, OMAP1610_DMA_LCD_SRC_FI_B1_L);
-}
-
-static irqreturn_t lcd_dma_irq_handler(int irq, void *dev_id)
-{
-	u16 w;
-
-	w = omap_readw(OMAP1610_DMA_LCD_CTRL);
-	if (unlikely(!(w & (1 << 3)))) {
-		printk(KERN_WARNING "Spurious LCD DMA IRQ\n");
-		return IRQ_NONE;
-	}
-	/* Ack the IRQ */
-	w |= (1 << 3);
-	omap_writew(w, OMAP1610_DMA_LCD_CTRL);
-	lcd_dma.active = 0;
-	if (lcd_dma.callback != NULL)
-		lcd_dma.callback(w, lcd_dma.cb_data);
-
-	return IRQ_HANDLED;
-}
-
-int omap_request_lcd_dma(void (*callback)(u16 status, void *data),
-			 void *data)
-{
-	spin_lock_irq(&lcd_dma.lock);
-	if (lcd_dma.reserved) {
-		spin_unlock_irq(&lcd_dma.lock);
-		printk(KERN_ERR "LCD DMA channel already reserved\n");
-		BUG();
-		return -EBUSY;
-	}
-	lcd_dma.reserved = 1;
-	spin_unlock_irq(&lcd_dma.lock);
-	lcd_dma.callback = callback;
-	lcd_dma.cb_data = data;
-	lcd_dma.active = 0;
-	lcd_dma.single_transfer = 0;
-	lcd_dma.rotate = 0;
-	lcd_dma.vxres = 0;
-	lcd_dma.mirror = 0;
-	lcd_dma.xscale = 0;
-	lcd_dma.yscale = 0;
-	lcd_dma.ext_ctrl = 0;
-	lcd_dma.src_port = 0;
-
-	return 0;
-}
-EXPORT_SYMBOL(omap_request_lcd_dma);
-
-void omap_free_lcd_dma(void)
-{
-	spin_lock(&lcd_dma.lock);
-	if (!lcd_dma.reserved) {
-		spin_unlock(&lcd_dma.lock);
-		printk(KERN_ERR "LCD DMA is not reserved\n");
-		BUG();
-		return;
-	}
-	if (!cpu_is_omap15xx())
-		omap_writew(omap_readw(OMAP1610_DMA_LCD_CCR) & ~1,
-			    OMAP1610_DMA_LCD_CCR);
-	lcd_dma.reserved = 0;
-	spin_unlock(&lcd_dma.lock);
-}
-EXPORT_SYMBOL(omap_free_lcd_dma);
-
-void omap_enable_lcd_dma(void)
-{
-	u16 w;
-
-	/*
-	 * Set the Enable bit only if an external controller is
-	 * connected. Otherwise the OMAP internal controller will
-	 * start the transfer when it gets enabled.
-	 */
-	if (cpu_is_omap15xx() || !lcd_dma.ext_ctrl)
-		return;
-
-	w = omap_readw(OMAP1610_DMA_LCD_CTRL);
-	w |= 1 << 8;
-	omap_writew(w, OMAP1610_DMA_LCD_CTRL);
-
-	lcd_dma.active = 1;
-
-	w = omap_readw(OMAP1610_DMA_LCD_CCR);
-	w |= 1 << 7;
-	omap_writew(w, OMAP1610_DMA_LCD_CCR);
-}
-EXPORT_SYMBOL(omap_enable_lcd_dma);
-
-void omap_setup_lcd_dma(void)
-{
-	BUG_ON(lcd_dma.active);
-	if (!cpu_is_omap15xx()) {
-		/* Set some reasonable defaults */
-		omap_writew(0x5440, OMAP1610_DMA_LCD_CCR);
-		omap_writew(0x9102, OMAP1610_DMA_LCD_CSDP);
-		omap_writew(0x0004, OMAP1610_DMA_LCD_LCH_CTRL);
-	}
-	set_b1_regs();
-	if (!cpu_is_omap15xx()) {
-		u16 w;
-
-		w = omap_readw(OMAP1610_DMA_LCD_CCR);
-		/*
-		 * If DMA was already active set the end_prog bit to have
-		 * the programmed register set loaded into the active
-		 * register set.
-		 */
-		w |= 1 << 11;		/* End_prog */
-		if (!lcd_dma.single_transfer)
-			w |= (3 << 8);	/* Auto_init, repeat */
-		omap_writew(w, OMAP1610_DMA_LCD_CCR);
-	}
-}
-EXPORT_SYMBOL(omap_setup_lcd_dma);
-
-void omap_stop_lcd_dma(void)
-{
-	u16 w;
-
-	lcd_dma.active = 0;
-	if (cpu_is_omap15xx() || !lcd_dma.ext_ctrl)
-		return;
-
-	w = omap_readw(OMAP1610_DMA_LCD_CCR);
-	w &= ~(1 << 7);
-	omap_writew(w, OMAP1610_DMA_LCD_CCR);
-
-	w = omap_readw(OMAP1610_DMA_LCD_CTRL);
-	w &= ~(1 << 8);
-	omap_writew(w, OMAP1610_DMA_LCD_CTRL);
-}
-EXPORT_SYMBOL(omap_stop_lcd_dma);
-
-static int __init omap_init_lcd_dma(void)
-{
-	int r;
-
-	if (!cpu_class_is_omap1())
-		return -ENODEV;
-
-	if (cpu_is_omap16xx()) {
-		u16 w;
-
-		/* this would prevent OMAP sleep */
-		w = omap_readw(OMAP1610_DMA_LCD_CTRL);
-		w &= ~(1 << 8);
-		omap_writew(w, OMAP1610_DMA_LCD_CTRL);
-	}
-
-	spin_lock_init(&lcd_dma.lock);
-
-	r = request_irq(INT_DMA_LCD, lcd_dma_irq_handler, 0,
-			"LCD DMA", NULL);
-	if (r != 0)
-		pr_err("unable to request IRQ for LCD DMA (error %d)\n", r);
-
-	return r;
-}
-
-arch_initcall(omap_init_lcd_dma);
-
diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile
index 477b9624b703..7795c4126706 100644
--- a/drivers/video/fbdev/Makefile
+++ b/drivers/video/fbdev/Makefile
@@ -110,7 +110,7 @@ obj-$(CONFIG_FB_UDL)		  += udlfb.o
 obj-$(CONFIG_FB_SMSCUFX)	  += smscufx.o
 obj-$(CONFIG_FB_XILINX)           += xilinxfb.o
 obj-$(CONFIG_FB_SH_MOBILE_LCDC)	  += sh_mobile_lcdcfb.o
-obj-$(CONFIG_FB_OMAP)             += omap/
+obj-y				  += omap/
 obj-y                             += omap2/
 obj-$(CONFIG_XEN_FBDEV_FRONTEND)  += xen-fbfront.o
 obj-$(CONFIG_FB_CARMINE)          += carminefb.o
diff --git a/drivers/video/fbdev/omap/Makefile b/drivers/video/fbdev/omap/Makefile
index daaa73a94e7f..b88e02f5cb1f 100644
--- a/drivers/video/fbdev/omap/Makefile
+++ b/drivers/video/fbdev/omap/Makefile
@@ -5,6 +5,11 @@
 
 obj-$(CONFIG_FB_OMAP) += omapfb.o
 
+ifdef CONFIG_FB_OMAP
+# must be built-in
+obj-y += lcd_dma.o
+endif
+
 objs-yy := omapfb_main.o lcdc.o
 
 objs-y$(CONFIG_FB_OMAP_LCDC_EXTERNAL) += sossi.o
diff --git a/drivers/video/fbdev/omap/lcd_dma.c b/drivers/video/fbdev/omap/lcd_dma.c
new file mode 100644
index 000000000000..867a63c06f42
--- /dev/null
+++ b/drivers/video/fbdev/omap/lcd_dma.c
@@ -0,0 +1,443 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/arch/arm/mach-omap1/lcd_dma.c
+ *
+ * Extracted from arch/arm/plat-omap/dma.c
+ * Copyright (C) 2003 - 2008 Nokia Corporation
+ * Author: Juha Yrjölä <juha.yrjola@nokia.com>
+ * DMA channel linking for 1610 by Samuel Ortiz <samuel.ortiz@nokia.com>
+ * Graphics DMA and LCD DMA graphics tranformations
+ * by Imre Deak <imre.deak@nokia.com>
+ * OMAP2/3 support Copyright (C) 2004-2007 Texas Instruments, Inc.
+ * Merged to support both OMAP1 and OMAP2 by Tony Lindgren <tony@atomide.com>
+ * Some functions based on earlier dma-omap.c Copyright (C) 2001 RidgeRun, Inc.
+ *
+ * Copyright (C) 2009 Texas Instruments
+ * Added OMAP4 support - Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * Support functions for the OMAP internal DMA channels.
+ */
+
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+
+#include <linux/omap-dma.h>
+
+#include <mach/hardware.h>
+
+#include "lcdc.h"
+#include "lcd_dma.h"
+
+int omap_lcd_dma_running(void)
+{
+	/*
+	 * On OMAP1510, internal LCD controller will start the transfer
+	 * when it gets enabled, so assume DMA running if LCD enabled.
+	 */
+	if (cpu_is_omap15xx())
+		if (omap_readw(OMAP_LCDC_CONTROL) & OMAP_LCDC_CTRL_LCD_EN)
+			return 1;
+
+	/* Check if LCD DMA is running */
+	if (cpu_is_omap16xx())
+		if (omap_readw(OMAP1610_DMA_LCD_CCR) & OMAP_DMA_CCR_EN)
+			return 1;
+
+	return 0;
+}
+
+static struct lcd_dma_info {
+	spinlock_t lock;
+	int reserved;
+	void (*callback)(u16 status, void *data);
+	void *cb_data;
+
+	int active;
+	unsigned long addr;
+	int rotate, data_type, xres, yres;
+	int vxres;
+	int mirror;
+	int xscale, yscale;
+	int ext_ctrl;
+	int src_port;
+	int single_transfer;
+} lcd_dma;
+
+void omap_set_lcd_dma_b1(unsigned long addr, u16 fb_xres, u16 fb_yres,
+			 int data_type)
+{
+	lcd_dma.addr = addr;
+	lcd_dma.data_type = data_type;
+	lcd_dma.xres = fb_xres;
+	lcd_dma.yres = fb_yres;
+}
+EXPORT_SYMBOL(omap_set_lcd_dma_b1);
+
+void omap_set_lcd_dma_ext_controller(int external)
+{
+	lcd_dma.ext_ctrl = external;
+}
+EXPORT_SYMBOL(omap_set_lcd_dma_ext_controller);
+
+void omap_set_lcd_dma_single_transfer(int single)
+{
+	lcd_dma.single_transfer = single;
+}
+EXPORT_SYMBOL(omap_set_lcd_dma_single_transfer);
+
+void omap_set_lcd_dma_b1_rotation(int rotate)
+{
+	if (cpu_is_omap15xx()) {
+		printk(KERN_ERR "DMA rotation is not supported in 1510 mode\n");
+		BUG();
+		return;
+	}
+	lcd_dma.rotate = rotate;
+}
+EXPORT_SYMBOL(omap_set_lcd_dma_b1_rotation);
+
+void omap_set_lcd_dma_b1_mirror(int mirror)
+{
+	if (cpu_is_omap15xx()) {
+		printk(KERN_ERR "DMA mirror is not supported in 1510 mode\n");
+		BUG();
+	}
+	lcd_dma.mirror = mirror;
+}
+EXPORT_SYMBOL(omap_set_lcd_dma_b1_mirror);
+
+void omap_set_lcd_dma_b1_vxres(unsigned long vxres)
+{
+	if (cpu_is_omap15xx()) {
+		pr_err("DMA virtual resolution is not supported in 1510 mode\n");
+		BUG();
+	}
+	lcd_dma.vxres = vxres;
+}
+EXPORT_SYMBOL(omap_set_lcd_dma_b1_vxres);
+
+void omap_set_lcd_dma_b1_scale(unsigned int xscale, unsigned int yscale)
+{
+	if (cpu_is_omap15xx()) {
+		printk(KERN_ERR "DMA scale is not supported in 1510 mode\n");
+		BUG();
+	}
+	lcd_dma.xscale = xscale;
+	lcd_dma.yscale = yscale;
+}
+EXPORT_SYMBOL(omap_set_lcd_dma_b1_scale);
+
+static void set_b1_regs(void)
+{
+	unsigned long top, bottom;
+	int es;
+	u16 w;
+	unsigned long en, fn;
+	long ei, fi;
+	unsigned long vxres;
+	unsigned int xscale, yscale;
+
+	switch (lcd_dma.data_type) {
+	case OMAP_DMA_DATA_TYPE_S8:
+		es = 1;
+		break;
+	case OMAP_DMA_DATA_TYPE_S16:
+		es = 2;
+		break;
+	case OMAP_DMA_DATA_TYPE_S32:
+		es = 4;
+		break;
+	default:
+		BUG();
+		return;
+	}
+
+	vxres = lcd_dma.vxres ? lcd_dma.vxres : lcd_dma.xres;
+	xscale = lcd_dma.xscale ? lcd_dma.xscale : 1;
+	yscale = lcd_dma.yscale ? lcd_dma.yscale : 1;
+	BUG_ON(vxres < lcd_dma.xres);
+
+#define PIXADDR(x, y) (lcd_dma.addr +					\
+		((y) * vxres * yscale + (x) * xscale) * es)
+#define PIXSTEP(sx, sy, dx, dy) (PIXADDR(dx, dy) - PIXADDR(sx, sy) - es + 1)
+
+	switch (lcd_dma.rotate) {
+	case 0:
+		if (!lcd_dma.mirror) {
+			top = PIXADDR(0, 0);
+			bottom = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1);
+			/* 1510 DMA requires the bottom address to be 2 more
+			 * than the actual last memory access location. */
+			if (cpu_is_omap15xx() &&
+				lcd_dma.data_type == OMAP_DMA_DATA_TYPE_S32)
+					bottom += 2;
+			ei = PIXSTEP(0, 0, 1, 0);
+			fi = PIXSTEP(lcd_dma.xres - 1, 0, 0, 1);
+		} else {
+			top = PIXADDR(lcd_dma.xres - 1, 0);
+			bottom = PIXADDR(0, lcd_dma.yres - 1);
+			ei = PIXSTEP(1, 0, 0, 0);
+			fi = PIXSTEP(0, 0, lcd_dma.xres - 1, 1);
+		}
+		en = lcd_dma.xres;
+		fn = lcd_dma.yres;
+		break;
+	case 90:
+		if (!lcd_dma.mirror) {
+			top = PIXADDR(0, lcd_dma.yres - 1);
+			bottom = PIXADDR(lcd_dma.xres - 1, 0);
+			ei = PIXSTEP(0, 1, 0, 0);
+			fi = PIXSTEP(0, 0, 1, lcd_dma.yres - 1);
+		} else {
+			top = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1);
+			bottom = PIXADDR(0, 0);
+			ei = PIXSTEP(0, 1, 0, 0);
+			fi = PIXSTEP(1, 0, 0, lcd_dma.yres - 1);
+		}
+		en = lcd_dma.yres;
+		fn = lcd_dma.xres;
+		break;
+	case 180:
+		if (!lcd_dma.mirror) {
+			top = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1);
+			bottom = PIXADDR(0, 0);
+			ei = PIXSTEP(1, 0, 0, 0);
+			fi = PIXSTEP(0, 1, lcd_dma.xres - 1, 0);
+		} else {
+			top = PIXADDR(0, lcd_dma.yres - 1);
+			bottom = PIXADDR(lcd_dma.xres - 1, 0);
+			ei = PIXSTEP(0, 0, 1, 0);
+			fi = PIXSTEP(lcd_dma.xres - 1, 1, 0, 0);
+		}
+		en = lcd_dma.xres;
+		fn = lcd_dma.yres;
+		break;
+	case 270:
+		if (!lcd_dma.mirror) {
+			top = PIXADDR(lcd_dma.xres - 1, 0);
+			bottom = PIXADDR(0, lcd_dma.yres - 1);
+			ei = PIXSTEP(0, 0, 0, 1);
+			fi = PIXSTEP(1, lcd_dma.yres - 1, 0, 0);
+		} else {
+			top = PIXADDR(0, 0);
+			bottom = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1);
+			ei = PIXSTEP(0, 0, 0, 1);
+			fi = PIXSTEP(0, lcd_dma.yres - 1, 1, 0);
+		}
+		en = lcd_dma.yres;
+		fn = lcd_dma.xres;
+		break;
+	default:
+		BUG();
+		return;	/* Suppress warning about uninitialized vars */
+	}
+
+	if (cpu_is_omap15xx()) {
+		omap_writew(top >> 16, OMAP1510_DMA_LCD_TOP_F1_U);
+		omap_writew(top, OMAP1510_DMA_LCD_TOP_F1_L);
+		omap_writew(bottom >> 16, OMAP1510_DMA_LCD_BOT_F1_U);
+		omap_writew(bottom, OMAP1510_DMA_LCD_BOT_F1_L);
+
+		return;
+	}
+
+	/* 1610 regs */
+	omap_writew(top >> 16, OMAP1610_DMA_LCD_TOP_B1_U);
+	omap_writew(top, OMAP1610_DMA_LCD_TOP_B1_L);
+	omap_writew(bottom >> 16, OMAP1610_DMA_LCD_BOT_B1_U);
+	omap_writew(bottom, OMAP1610_DMA_LCD_BOT_B1_L);
+
+	omap_writew(en, OMAP1610_DMA_LCD_SRC_EN_B1);
+	omap_writew(fn, OMAP1610_DMA_LCD_SRC_FN_B1);
+
+	w = omap_readw(OMAP1610_DMA_LCD_CSDP);
+	w &= ~0x03;
+	w |= lcd_dma.data_type;
+	omap_writew(w, OMAP1610_DMA_LCD_CSDP);
+
+	w = omap_readw(OMAP1610_DMA_LCD_CTRL);
+	/* Always set the source port as SDRAM for now*/
+	w &= ~(0x03 << 6);
+	if (lcd_dma.callback != NULL)
+		w |= 1 << 1;		/* Block interrupt enable */
+	else
+		w &= ~(1 << 1);
+	omap_writew(w, OMAP1610_DMA_LCD_CTRL);
+
+	if (!(lcd_dma.rotate || lcd_dma.mirror ||
+	      lcd_dma.vxres || lcd_dma.xscale || lcd_dma.yscale))
+		return;
+
+	w = omap_readw(OMAP1610_DMA_LCD_CCR);
+	/* Set the double-indexed addressing mode */
+	w |= (0x03 << 12);
+	omap_writew(w, OMAP1610_DMA_LCD_CCR);
+
+	omap_writew(ei, OMAP1610_DMA_LCD_SRC_EI_B1);
+	omap_writew(fi >> 16, OMAP1610_DMA_LCD_SRC_FI_B1_U);
+	omap_writew(fi, OMAP1610_DMA_LCD_SRC_FI_B1_L);
+}
+
+static irqreturn_t lcd_dma_irq_handler(int irq, void *dev_id)
+{
+	u16 w;
+
+	w = omap_readw(OMAP1610_DMA_LCD_CTRL);
+	if (unlikely(!(w & (1 << 3)))) {
+		printk(KERN_WARNING "Spurious LCD DMA IRQ\n");
+		return IRQ_NONE;
+	}
+	/* Ack the IRQ */
+	w |= (1 << 3);
+	omap_writew(w, OMAP1610_DMA_LCD_CTRL);
+	lcd_dma.active = 0;
+	if (lcd_dma.callback != NULL)
+		lcd_dma.callback(w, lcd_dma.cb_data);
+
+	return IRQ_HANDLED;
+}
+
+int omap_request_lcd_dma(void (*callback)(u16 status, void *data),
+			 void *data)
+{
+	spin_lock_irq(&lcd_dma.lock);
+	if (lcd_dma.reserved) {
+		spin_unlock_irq(&lcd_dma.lock);
+		printk(KERN_ERR "LCD DMA channel already reserved\n");
+		BUG();
+		return -EBUSY;
+	}
+	lcd_dma.reserved = 1;
+	spin_unlock_irq(&lcd_dma.lock);
+	lcd_dma.callback = callback;
+	lcd_dma.cb_data = data;
+	lcd_dma.active = 0;
+	lcd_dma.single_transfer = 0;
+	lcd_dma.rotate = 0;
+	lcd_dma.vxres = 0;
+	lcd_dma.mirror = 0;
+	lcd_dma.xscale = 0;
+	lcd_dma.yscale = 0;
+	lcd_dma.ext_ctrl = 0;
+	lcd_dma.src_port = 0;
+
+	return 0;
+}
+EXPORT_SYMBOL(omap_request_lcd_dma);
+
+void omap_free_lcd_dma(void)
+{
+	spin_lock(&lcd_dma.lock);
+	if (!lcd_dma.reserved) {
+		spin_unlock(&lcd_dma.lock);
+		printk(KERN_ERR "LCD DMA is not reserved\n");
+		BUG();
+		return;
+	}
+	if (!cpu_is_omap15xx())
+		omap_writew(omap_readw(OMAP1610_DMA_LCD_CCR) & ~1,
+			    OMAP1610_DMA_LCD_CCR);
+	lcd_dma.reserved = 0;
+	spin_unlock(&lcd_dma.lock);
+}
+EXPORT_SYMBOL(omap_free_lcd_dma);
+
+void omap_enable_lcd_dma(void)
+{
+	u16 w;
+
+	/*
+	 * Set the Enable bit only if an external controller is
+	 * connected. Otherwise the OMAP internal controller will
+	 * start the transfer when it gets enabled.
+	 */
+	if (cpu_is_omap15xx() || !lcd_dma.ext_ctrl)
+		return;
+
+	w = omap_readw(OMAP1610_DMA_LCD_CTRL);
+	w |= 1 << 8;
+	omap_writew(w, OMAP1610_DMA_LCD_CTRL);
+
+	lcd_dma.active = 1;
+
+	w = omap_readw(OMAP1610_DMA_LCD_CCR);
+	w |= 1 << 7;
+	omap_writew(w, OMAP1610_DMA_LCD_CCR);
+}
+EXPORT_SYMBOL(omap_enable_lcd_dma);
+
+void omap_setup_lcd_dma(void)
+{
+	BUG_ON(lcd_dma.active);
+	if (!cpu_is_omap15xx()) {
+		/* Set some reasonable defaults */
+		omap_writew(0x5440, OMAP1610_DMA_LCD_CCR);
+		omap_writew(0x9102, OMAP1610_DMA_LCD_CSDP);
+		omap_writew(0x0004, OMAP1610_DMA_LCD_LCH_CTRL);
+	}
+	set_b1_regs();
+	if (!cpu_is_omap15xx()) {
+		u16 w;
+
+		w = omap_readw(OMAP1610_DMA_LCD_CCR);
+		/*
+		 * If DMA was already active set the end_prog bit to have
+		 * the programmed register set loaded into the active
+		 * register set.
+		 */
+		w |= 1 << 11;		/* End_prog */
+		if (!lcd_dma.single_transfer)
+			w |= (3 << 8);	/* Auto_init, repeat */
+		omap_writew(w, OMAP1610_DMA_LCD_CCR);
+	}
+}
+EXPORT_SYMBOL(omap_setup_lcd_dma);
+
+void omap_stop_lcd_dma(void)
+{
+	u16 w;
+
+	lcd_dma.active = 0;
+	if (cpu_is_omap15xx() || !lcd_dma.ext_ctrl)
+		return;
+
+	w = omap_readw(OMAP1610_DMA_LCD_CCR);
+	w &= ~(1 << 7);
+	omap_writew(w, OMAP1610_DMA_LCD_CCR);
+
+	w = omap_readw(OMAP1610_DMA_LCD_CTRL);
+	w &= ~(1 << 8);
+	omap_writew(w, OMAP1610_DMA_LCD_CTRL);
+}
+EXPORT_SYMBOL(omap_stop_lcd_dma);
+
+static int __init omap_init_lcd_dma(void)
+{
+	int r;
+
+	if (!cpu_class_is_omap1())
+		return -ENODEV;
+
+	if (cpu_is_omap16xx()) {
+		u16 w;
+
+		/* this would prevent OMAP sleep */
+		w = omap_readw(OMAP1610_DMA_LCD_CTRL);
+		w &= ~(1 << 8);
+		omap_writew(w, OMAP1610_DMA_LCD_CTRL);
+	}
+
+	spin_lock_init(&lcd_dma.lock);
+
+	r = request_irq(INT_DMA_LCD, lcd_dma_irq_handler, 0,
+			"LCD DMA", NULL);
+	if (r != 0)
+		pr_err("unable to request IRQ for LCD DMA (error %d)\n", r);
+
+	return r;
+}
+
+arch_initcall(omap_init_lcd_dma);
+
diff --git a/drivers/video/fbdev/omap/lcd_dma.h b/drivers/video/fbdev/omap/lcd_dma.h
new file mode 100644
index 000000000000..1b4780197381
--- /dev/null
+++ b/drivers/video/fbdev/omap/lcd_dma.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *  arch/arm/mach-omap1/include/mach/lcd_dma.h
+ *
+ * Extracted from arch/arm/plat-omap/include/plat/dma.h
+ *  Copyright (C) 2003 Nokia Corporation
+ *  Author: Juha Yrjölä <juha.yrjola@nokia.com>
+ */
+#ifndef __MACH_OMAP1_LCD_DMA_H__
+#define __MACH_OMAP1_LCD_DMA_H__
+
+/* Hardware registers for LCD DMA */
+#define OMAP1510_DMA_LCD_BASE		(0xfffedb00)
+#define OMAP1510_DMA_LCD_CTRL		(OMAP1510_DMA_LCD_BASE + 0x00)
+#define OMAP1510_DMA_LCD_TOP_F1_L	(OMAP1510_DMA_LCD_BASE + 0x02)
+#define OMAP1510_DMA_LCD_TOP_F1_U	(OMAP1510_DMA_LCD_BASE + 0x04)
+#define OMAP1510_DMA_LCD_BOT_F1_L	(OMAP1510_DMA_LCD_BASE + 0x06)
+#define OMAP1510_DMA_LCD_BOT_F1_U	(OMAP1510_DMA_LCD_BASE + 0x08)
+
+#define OMAP1610_DMA_LCD_BASE		(0xfffee300)
+#define OMAP1610_DMA_LCD_CSDP		(OMAP1610_DMA_LCD_BASE + 0xc0)
+#define OMAP1610_DMA_LCD_CCR		(OMAP1610_DMA_LCD_BASE + 0xc2)
+#define OMAP1610_DMA_LCD_CTRL		(OMAP1610_DMA_LCD_BASE + 0xc4)
+#define OMAP1610_DMA_LCD_TOP_B1_L	(OMAP1610_DMA_LCD_BASE + 0xc8)
+#define OMAP1610_DMA_LCD_TOP_B1_U	(OMAP1610_DMA_LCD_BASE + 0xca)
+#define OMAP1610_DMA_LCD_BOT_B1_L	(OMAP1610_DMA_LCD_BASE + 0xcc)
+#define OMAP1610_DMA_LCD_BOT_B1_U	(OMAP1610_DMA_LCD_BASE + 0xce)
+#define OMAP1610_DMA_LCD_TOP_B2_L	(OMAP1610_DMA_LCD_BASE + 0xd0)
+#define OMAP1610_DMA_LCD_TOP_B2_U	(OMAP1610_DMA_LCD_BASE + 0xd2)
+#define OMAP1610_DMA_LCD_BOT_B2_L	(OMAP1610_DMA_LCD_BASE + 0xd4)
+#define OMAP1610_DMA_LCD_BOT_B2_U	(OMAP1610_DMA_LCD_BASE + 0xd6)
+#define OMAP1610_DMA_LCD_SRC_EI_B1	(OMAP1610_DMA_LCD_BASE + 0xd8)
+#define OMAP1610_DMA_LCD_SRC_FI_B1_L	(OMAP1610_DMA_LCD_BASE + 0xda)
+#define OMAP1610_DMA_LCD_SRC_EN_B1	(OMAP1610_DMA_LCD_BASE + 0xe0)
+#define OMAP1610_DMA_LCD_SRC_FN_B1	(OMAP1610_DMA_LCD_BASE + 0xe4)
+#define OMAP1610_DMA_LCD_LCH_CTRL	(OMAP1610_DMA_LCD_BASE + 0xea)
+#define OMAP1610_DMA_LCD_SRC_FI_B1_U	(OMAP1610_DMA_LCD_BASE + 0xf4)
+
+/* LCD DMA block numbers */
+enum {
+	OMAP_LCD_DMA_B1_TOP,
+	OMAP_LCD_DMA_B1_BOTTOM,
+	OMAP_LCD_DMA_B2_TOP,
+	OMAP_LCD_DMA_B2_BOTTOM
+};
+
+/* LCD DMA functions */
+extern int omap_request_lcd_dma(void (*callback)(u16 status, void *data),
+				void *data);
+extern void omap_free_lcd_dma(void);
+extern void omap_setup_lcd_dma(void);
+extern void omap_enable_lcd_dma(void);
+extern void omap_stop_lcd_dma(void);
+extern void omap_set_lcd_dma_ext_controller(int external);
+extern void omap_set_lcd_dma_single_transfer(int single);
+extern void omap_set_lcd_dma_b1(unsigned long addr, u16 fb_xres, u16 fb_yres,
+				int data_type);
+extern void omap_set_lcd_dma_b1_rotation(int rotate);
+extern void omap_set_lcd_dma_b1_vxres(unsigned long vxres);
+extern void omap_set_lcd_dma_b1_mirror(int mirror);
+extern void omap_set_lcd_dma_b1_scale(unsigned int xscale, unsigned int yscale);
+
+#endif /* __MACH_OMAP1_LCD_DMA_H__ */
diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c
index 7317c9aad677..d9a23f6cf7fc 100644
--- a/drivers/video/fbdev/omap/lcdc.c
+++ b/drivers/video/fbdev/omap/lcdc.c
@@ -17,7 +17,6 @@
 #include <linux/clk.h>
 #include <linux/gfp.h>
 
-#include <mach/lcdc.h>
 #include <linux/omap-dma.h>
 
 #include <asm/mach-types.h>
@@ -25,6 +24,7 @@
 #include "omapfb.h"
 
 #include "lcdc.h"
+#include "lcd_dma.h"
 
 #define MODULE_NAME			"lcdc"
 
diff --git a/drivers/video/fbdev/omap/lcdc.h b/drivers/video/fbdev/omap/lcdc.h
index 8a7607d861c1..cbbfd9b9e949 100644
--- a/drivers/video/fbdev/omap/lcdc.h
+++ b/drivers/video/fbdev/omap/lcdc.h
@@ -1,6 +1,41 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef LCDC_H
 #define LCDC_H
+/*
+ * Copyright (C) 2004 Nokia Corporation
+ * Author: Imre Deak <imre.deak@nokia.com>
+ */
+#define OMAP_LCDC_BASE			0xfffec000
+#define OMAP_LCDC_SIZE			256
+#define OMAP_LCDC_IRQ			INT_LCD_CTRL
+
+#define OMAP_LCDC_CONTROL		(OMAP_LCDC_BASE + 0x00)
+#define OMAP_LCDC_TIMING0		(OMAP_LCDC_BASE + 0x04)
+#define OMAP_LCDC_TIMING1		(OMAP_LCDC_BASE + 0x08)
+#define OMAP_LCDC_TIMING2		(OMAP_LCDC_BASE + 0x0c)
+#define OMAP_LCDC_STATUS		(OMAP_LCDC_BASE + 0x10)
+#define OMAP_LCDC_SUBPANEL		(OMAP_LCDC_BASE + 0x14)
+#define OMAP_LCDC_LINE_INT		(OMAP_LCDC_BASE + 0x18)
+#define OMAP_LCDC_DISPLAY_STATUS	(OMAP_LCDC_BASE + 0x1c)
+
+#define OMAP_LCDC_STAT_DONE		(1 << 0)
+#define OMAP_LCDC_STAT_VSYNC		(1 << 1)
+#define OMAP_LCDC_STAT_SYNC_LOST	(1 << 2)
+#define OMAP_LCDC_STAT_ABC		(1 << 3)
+#define OMAP_LCDC_STAT_LINE_INT		(1 << 4)
+#define OMAP_LCDC_STAT_FUF		(1 << 5)
+#define OMAP_LCDC_STAT_LOADED_PALETTE	(1 << 6)
+
+#define OMAP_LCDC_CTRL_LCD_EN		(1 << 0)
+#define OMAP_LCDC_CTRL_LCD_TFT		(1 << 7)
+#define OMAP_LCDC_CTRL_LINE_IRQ_CLR_SEL	(1 << 10)
+
+#define OMAP_LCDC_IRQ_VSYNC		(1 << 2)
+#define OMAP_LCDC_IRQ_DONE		(1 << 3)
+#define OMAP_LCDC_IRQ_LOADED_PALETTE	(1 << 4)
+#define OMAP_LCDC_IRQ_LINE_NIRQ		(1 << 5)
+#define OMAP_LCDC_IRQ_LINE		(1 << 6)
+#define OMAP_LCDC_IRQ_MASK		(((1 << 5) - 1) << 2)
 
 int omap_lcdc_set_dma_callback(void (*callback)(void *data), void *data);
 void omap_lcdc_free_dma_callback(void);
diff --git a/drivers/video/fbdev/omap/sossi.c b/drivers/video/fbdev/omap/sossi.c
index 80ac67f27f0d..d3c755b293ea 100644
--- a/drivers/video/fbdev/omap/sossi.c
+++ b/drivers/video/fbdev/omap/sossi.c
@@ -15,6 +15,7 @@
 #include <linux/omap-dma.h>
 
 #include "omapfb.h"
+#include "lcd_dma.h"
 #include "lcdc.h"
 
 #define MODULE_NAME		"omapfb-sossi"
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 5c5c93ad6b50..441f5f0919c6 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -328,8 +328,8 @@ extern dma_addr_t omap_get_dma_dst_pos(int lch);
 extern int omap_get_dma_active_status(int lch);
 extern int omap_dma_running(void);
 
-#if defined(CONFIG_ARCH_OMAP1) && IS_ENABLED(CONFIG_FB_OMAP)
-#include <mach/lcd_dma.h>
+#if IS_ENABLED(CONFIG_FB_OMAP)
+extern int omap_lcd_dma_running(void);
 #else
 static inline int omap_lcd_dma_running(void)
 {
-- 
cgit v1.2.3


From 0768fb6709343679e55f7135e2ed2c432e4500d8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 9 Aug 2019 21:42:31 +0200
Subject: ARM: omap1: declare a dummy omap_set_dma_priority

omapfb calls directly into the omap_set_dma_priority() function in
the DMA driver. This prevents compile-testing omapfb on other
architectures. Add an inline function next to the other ones
for non-omap configurations.

Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/linux/omap-dma.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 441f5f0919c6..5e228428fda1 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -338,6 +338,9 @@ static inline int omap_lcd_dma_running(void)
 #endif
 
 #else /* CONFIG_ARCH_OMAP */
+static inline void omap_set_dma_priority(int lch, int dst_port, int priority)
+{
+}
 
 static inline struct omap_system_dma_plat_info *omap_get_plat_info(void)
 {
-- 
cgit v1.2.3


From e8e77e97507bf3ec5419b8067d242b538cf75cba Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 6 Aug 2019 14:34:31 +0200
Subject: ARM: omap1: move mach/usb.h to include/linux/soc

The register definitions in this header are used in at least four
different places, with little hope of completely cleaning that up.

Split up the file into a portion that becomes a linux-wide header
under include/linux/soc/ti/, and the parts that are actually only
needed by board files.

Acked-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-omap1/board-ams-delta.c  |   2 +-
 arch/arm/mach-omap1/board-generic.c    |   2 +-
 arch/arm/mach-omap1/board-h2.c         |   2 +-
 arch/arm/mach-omap1/board-h3.c         |   2 +-
 arch/arm/mach-omap1/board-htcherald.c  |   2 +-
 arch/arm/mach-omap1/board-innovator.c  |   2 +-
 arch/arm/mach-omap1/board-nokia770.c   |   2 +-
 arch/arm/mach-omap1/board-osk.c        |   2 +-
 arch/arm/mach-omap1/board-palmte.c     |   2 +-
 arch/arm/mach-omap1/board-palmtt.c     |   2 +-
 arch/arm/mach-omap1/board-palmz71.c    |   2 +-
 arch/arm/mach-omap1/board-sx1.c        |   2 +-
 arch/arm/mach-omap1/clock_data.c       |   2 +-
 arch/arm/mach-omap1/include/mach/usb.h | 128 ---------------------------------
 arch/arm/mach-omap1/usb.c              |   2 +-
 arch/arm/mach-omap1/usb.h              |  25 +++++++
 drivers/usb/gadget/udc/omap_udc.c      |   3 +-
 drivers/usb/host/ohci-omap.c           |   4 +-
 drivers/usb/phy/phy-isp1301-omap.c     |   2 +-
 include/linux/soc/ti/omap1-usb.h       | 116 ++++++++++++++++++++++++++++++
 20 files changed, 160 insertions(+), 146 deletions(-)
 delete mode 100644 arch/arm/mach-omap1/include/mach/usb.h
 create mode 100644 arch/arm/mach-omap1/usb.h
 create mode 100644 include/linux/soc/ti/omap1-usb.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index 12d61ad98395..5b0e99319990 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -38,7 +38,7 @@
 #include <mach/mux.h>
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "ams-delta-fiq.h"
 #include "board-ams-delta.h"
diff --git a/arch/arm/mach-omap1/board-generic.c b/arch/arm/mach-omap1/board-generic.c
index c62554990115..8ef0a9b17e92 100644
--- a/arch/arm/mach-omap1/board-generic.c
+++ b/arch/arm/mach-omap1/board-generic.c
@@ -21,7 +21,7 @@
 
 #include <mach/mux.h>
 
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index 977b0b744c22..b8cf0d84f8ab 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -42,7 +42,7 @@
 #include "flash.h"
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 #include "board-h2.h"
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index 4249984f9c30..86260498c344 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -45,7 +45,7 @@
 
 #include <mach/hardware.h>
 #include <mach/irqs.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 #include "board-h3.h"
diff --git a/arch/arm/mach-omap1/board-htcherald.c b/arch/arm/mach-omap1/board-htcherald.c
index 258304edf23e..f7220b60eb61 100644
--- a/arch/arm/mach-omap1/board-htcherald.c
+++ b/arch/arm/mach-omap1/board-htcherald.c
@@ -31,7 +31,7 @@
 #include "mmc.h"
 
 #include <mach/irqs.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index 2425f1bacb33..e7d6735d4701 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -34,7 +34,7 @@
 #include <linux/platform_data/keypad-omap.h>
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "iomap.h"
 #include "common.h"
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 11511ae2e0a2..e43c852103f5 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -31,7 +31,7 @@
 #include <mach/mux.h>
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 #include "clock.h"
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index e18b6f13300e..b627a4351cf0 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -52,7 +52,7 @@
 #include <mach/tc.h>
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/board-palmte.c b/arch/arm/mach-omap1/board-palmte.c
index ce6f0fcd9d12..4ac981c5cf74 100644
--- a/arch/arm/mach-omap1/board-palmte.c
+++ b/arch/arm/mach-omap1/board-palmte.c
@@ -38,7 +38,7 @@
 #include <linux/platform_data/keypad-omap.h>
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "mmc.h"
 #include "common.h"
diff --git a/arch/arm/mach-omap1/board-palmtt.c b/arch/arm/mach-omap1/board-palmtt.c
index 8a08311c4e05..e48ae5fbe1b1 100644
--- a/arch/arm/mach-omap1/board-palmtt.c
+++ b/arch/arm/mach-omap1/board-palmtt.c
@@ -38,7 +38,7 @@
 #include <linux/platform_data/keypad-omap.h>
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/board-palmz71.c b/arch/arm/mach-omap1/board-palmz71.c
index 034e5bc6a029..37db0ab31528 100644
--- a/arch/arm/mach-omap1/board-palmz71.c
+++ b/arch/arm/mach-omap1/board-palmz71.c
@@ -40,7 +40,7 @@
 #include <linux/platform_data/keypad-omap.h>
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/board-sx1.c b/arch/arm/mach-omap1/board-sx1.c
index bb9ec345e204..0965b1b689ec 100644
--- a/arch/arm/mach-omap1/board-sx1.c
+++ b/arch/arm/mach-omap1/board-sx1.c
@@ -38,7 +38,7 @@
 #include "board-sx1.h"
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/clock_data.c b/arch/arm/mach-omap1/clock_data.c
index 3ebcd96efbff..ef46c5f67cf9 100644
--- a/arch/arm/mach-omap1/clock_data.c
+++ b/arch/arm/mach-omap1/clock_data.c
@@ -22,7 +22,7 @@
 #include "soc.h"
 
 #include <mach/hardware.h>
-#include <mach/usb.h>   /* for OTG_BASE */
+#include "usb.h"   /* for OTG_BASE */
 
 #include "iomap.h"
 #include "clock.h"
diff --git a/arch/arm/mach-omap1/include/mach/usb.h b/arch/arm/mach-omap1/include/mach/usb.h
deleted file mode 100644
index 5429d86c7190..000000000000
--- a/arch/arm/mach-omap1/include/mach/usb.h
+++ /dev/null
@@ -1,128 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * FIXME correct answer depends on hmc_mode,
- * as does (on omap1) any nonzero value for config->otg port number
- */
-#if IS_ENABLED(CONFIG_USB_OMAP)
-#define	is_usb0_device(config)	1
-#else
-#define	is_usb0_device(config)	0
-#endif
-
-#include <linux/platform_data/usb-omap1.h>
-
-#if IS_ENABLED(CONFIG_USB_SUPPORT)
-void omap1_usb_init(struct omap_usb_config *pdata);
-#else
-static inline void omap1_usb_init(struct omap_usb_config *pdata)
-{
-}
-#endif
-
-#define OMAP1_OTG_BASE			0xfffb0400
-#define OMAP1_UDC_BASE			0xfffb4000
-#define OMAP1_OHCI_BASE			0xfffba000
-
-#define OMAP2_OHCI_BASE			0x4805e000
-#define OMAP2_UDC_BASE			0x4805e200
-#define OMAP2_OTG_BASE			0x4805e300
-#define OTG_BASE			OMAP1_OTG_BASE
-#define UDC_BASE			OMAP1_UDC_BASE
-#define OMAP_OHCI_BASE			OMAP1_OHCI_BASE
-
-/*
- * OTG and transceiver registers, for OMAPs starting with ARM926
- */
-#define OTG_REV				(OTG_BASE + 0x00)
-#define OTG_SYSCON_1			(OTG_BASE + 0x04)
-#	define	 USB2_TRX_MODE(w)	(((w)>>24)&0x07)
-#	define	 USB1_TRX_MODE(w)	(((w)>>20)&0x07)
-#	define	 USB0_TRX_MODE(w)	(((w)>>16)&0x07)
-#	define	 OTG_IDLE_EN		(1 << 15)
-#	define	 HST_IDLE_EN		(1 << 14)
-#	define	 DEV_IDLE_EN		(1 << 13)
-#	define	 OTG_RESET_DONE		(1 << 2)
-#	define	 OTG_SOFT_RESET		(1 << 1)
-#define OTG_SYSCON_2			(OTG_BASE + 0x08)
-#	define	 OTG_EN			(1 << 31)
-#	define	 USBX_SYNCHRO		(1 << 30)
-#	define	 OTG_MST16		(1 << 29)
-#	define	 SRP_GPDATA		(1 << 28)
-#	define	 SRP_GPDVBUS		(1 << 27)
-#	define	 SRP_GPUVBUS(w)		(((w)>>24)&0x07)
-#	define	 A_WAIT_VRISE(w)	(((w)>>20)&0x07)
-#	define	 B_ASE_BRST(w)		(((w)>>16)&0x07)
-#	define	 SRP_DPW		(1 << 14)
-#	define	 SRP_DATA		(1 << 13)
-#	define	 SRP_VBUS		(1 << 12)
-#	define	 OTG_PADEN		(1 << 10)
-#	define	 HMC_PADEN		(1 << 9)
-#	define	 UHOST_EN		(1 << 8)
-#	define	 HMC_TLLSPEED		(1 << 7)
-#	define	 HMC_TLLATTACH		(1 << 6)
-#	define	 OTG_HMC(w)		(((w)>>0)&0x3f)
-#define OTG_CTRL			(OTG_BASE + 0x0c)
-#	define	 OTG_USB2_EN		(1 << 29)
-#	define	 OTG_USB2_DP		(1 << 28)
-#	define	 OTG_USB2_DM		(1 << 27)
-#	define	 OTG_USB1_EN		(1 << 26)
-#	define	 OTG_USB1_DP		(1 << 25)
-#	define	 OTG_USB1_DM		(1 << 24)
-#	define	 OTG_USB0_EN		(1 << 23)
-#	define	 OTG_USB0_DP		(1 << 22)
-#	define	 OTG_USB0_DM		(1 << 21)
-#	define	 OTG_ASESSVLD		(1 << 20)
-#	define	 OTG_BSESSEND		(1 << 19)
-#	define	 OTG_BSESSVLD		(1 << 18)
-#	define	 OTG_VBUSVLD		(1 << 17)
-#	define	 OTG_ID			(1 << 16)
-#	define	 OTG_DRIVER_SEL		(1 << 15)
-#	define	 OTG_A_SETB_HNPEN	(1 << 12)
-#	define	 OTG_A_BUSREQ		(1 << 11)
-#	define	 OTG_B_HNPEN		(1 << 9)
-#	define	 OTG_B_BUSREQ		(1 << 8)
-#	define	 OTG_BUSDROP		(1 << 7)
-#	define	 OTG_PULLDOWN		(1 << 5)
-#	define	 OTG_PULLUP		(1 << 4)
-#	define	 OTG_DRV_VBUS		(1 << 3)
-#	define	 OTG_PD_VBUS		(1 << 2)
-#	define	 OTG_PU_VBUS		(1 << 1)
-#	define	 OTG_PU_ID		(1 << 0)
-#define OTG_IRQ_EN			(OTG_BASE + 0x10)	/* 16-bit */
-#	define	 DRIVER_SWITCH		(1 << 15)
-#	define	 A_VBUS_ERR		(1 << 13)
-#	define	 A_REQ_TMROUT		(1 << 12)
-#	define	 A_SRP_DETECT		(1 << 11)
-#	define	 B_HNP_FAIL		(1 << 10)
-#	define	 B_SRP_TMROUT		(1 << 9)
-#	define	 B_SRP_DONE		(1 << 8)
-#	define	 B_SRP_STARTED		(1 << 7)
-#	define	 OPRT_CHG		(1 << 0)
-#define OTG_IRQ_SRC			(OTG_BASE + 0x14)	/* 16-bit */
-	// same bits as in IRQ_EN
-#define OTG_OUTCTRL			(OTG_BASE + 0x18)	/* 16-bit */
-#	define	 OTGVPD			(1 << 14)
-#	define	 OTGVPU			(1 << 13)
-#	define	 OTGPUID		(1 << 12)
-#	define	 USB2VDR		(1 << 10)
-#	define	 USB2PDEN		(1 << 9)
-#	define	 USB2PUEN		(1 << 8)
-#	define	 USB1VDR		(1 << 6)
-#	define	 USB1PDEN		(1 << 5)
-#	define	 USB1PUEN		(1 << 4)
-#	define	 USB0VDR		(1 << 2)
-#	define	 USB0PDEN		(1 << 1)
-#	define	 USB0PUEN		(1 << 0)
-#define OTG_TEST			(OTG_BASE + 0x20)	/* 16-bit */
-#define OTG_VENDOR_CODE			(OTG_BASE + 0xfc)	/* 16-bit */
-
-/*-------------------------------------------------------------------------*/
-
-/* OMAP1 */
-#define	USB_TRANSCEIVER_CTRL		(0xfffe1000 + 0x0064)
-#	define	CONF_USB2_UNI_R		(1 << 8)
-#	define	CONF_USB1_UNI_R		(1 << 7)
-#	define	CONF_USB_PORT0_R(x)	(((x)>>4)&0x7)
-#	define	CONF_USB0_ISOLATE_R	(1 << 3)
-#	define	CONF_USB_PWRDN_DM_R	(1 << 2)
-#	define	CONF_USB_PWRDN_DP_R	(1 << 1)
diff --git a/arch/arm/mach-omap1/usb.c b/arch/arm/mach-omap1/usb.c
index e60831c82b78..fa658054fc57 100644
--- a/arch/arm/mach-omap1/usb.c
+++ b/arch/arm/mach-omap1/usb.c
@@ -17,7 +17,7 @@
 
 #include <mach/mux.h>
 
-#include <mach/usb.h>
+#include "usb.h"
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/usb.h b/arch/arm/mach-omap1/usb.h
new file mode 100644
index 000000000000..08c9344c46e3
--- /dev/null
+++ b/arch/arm/mach-omap1/usb.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * fixme correct answer depends on hmc_mode,
+ * as does (on omap1) any nonzero value for config->otg port number
+ */
+#include <linux/platform_data/usb-omap1.h>
+#include <linux/soc/ti/omap1-usb.h>
+
+#if IS_ENABLED(CONFIG_USB_OMAP)
+#define	is_usb0_device(config)	1
+#else
+#define	is_usb0_device(config)	0
+#endif
+
+#if IS_ENABLED(CONFIG_USB_SUPPORT)
+void omap1_usb_init(struct omap_usb_config *pdata);
+#else
+static inline void omap1_usb_init(struct omap_usb_config *pdata)
+{
+}
+#endif
+
+#define OMAP1_OHCI_BASE			0xfffba000
+#define OMAP2_OHCI_BASE			0x4805e000
+#define OMAP_OHCI_BASE			OMAP1_OHCI_BASE
diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c
index 2d9815dad2ff..b1da584585cf 100644
--- a/drivers/usb/gadget/udc/omap_udc.c
+++ b/drivers/usb/gadget/udc/omap_udc.c
@@ -40,8 +40,9 @@
 #include <asm/mach-types.h>
 
 #include <linux/omap-dma.h>
+#include <linux/platform_data/usb-omap1.h>
 
-#include <mach/usb.h>
+#include <linux/soc/ti/omap1-usb.h>
 
 #include "omap_udc.h"
 
diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c
index 45dcf8292072..7be1ffefc40e 100644
--- a/drivers/usb/host/ohci-omap.c
+++ b/drivers/usb/host/ohci-omap.c
@@ -25,6 +25,8 @@
 #include <linux/module.h>
 #include <linux/usb/otg.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/usb-omap1.h>
+#include <linux/soc/ti/omap1-usb.h>
 #include <linux/signal.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
@@ -37,8 +39,6 @@
 #include <mach/mux.h>
 
 #include <mach/hardware.h>
-#include <mach/usb.h>
-
 
 #define DRIVER_DESC "OHCI OMAP driver"
 
diff --git a/drivers/usb/phy/phy-isp1301-omap.c b/drivers/usb/phy/phy-isp1301-omap.c
index 190699b38b41..88aade82b82b 100644
--- a/drivers/usb/phy/phy-isp1301-omap.c
+++ b/drivers/usb/phy/phy-isp1301-omap.c
@@ -25,7 +25,7 @@
 
 #include <mach/mux.h>
 
-#include <mach/usb.h>
+#include <linux/soc/ti/omap1-usb.h>
 
 #undef VERBOSE
 
diff --git a/include/linux/soc/ti/omap1-usb.h b/include/linux/soc/ti/omap1-usb.h
new file mode 100644
index 000000000000..67488698601a
--- /dev/null
+++ b/include/linux/soc/ti/omap1-usb.h
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __SOC_TI_OMAP1_USB
+#define __SOC_TI_OMAP1_USB
+/*
+ * Constants in this file are used all over the place, in platform
+ * code, as well as the udc, phy and ohci drivers.
+ * This is not a great design, but unlikely to get fixed after
+ * such a long time. Don't do this elsewhere.
+ */
+
+#define OMAP1_OTG_BASE			0xfffb0400
+#define OMAP1_UDC_BASE			0xfffb4000
+
+#define OMAP2_UDC_BASE			0x4805e200
+#define OMAP2_OTG_BASE			0x4805e300
+#define OTG_BASE			OMAP1_OTG_BASE
+#define UDC_BASE			OMAP1_UDC_BASE
+
+/*
+ * OTG and transceiver registers, for OMAPs starting with ARM926
+ */
+#define OTG_REV				(OTG_BASE + 0x00)
+#define OTG_SYSCON_1			(OTG_BASE + 0x04)
+#	define	 USB2_TRX_MODE(w)	(((w)>>24)&0x07)
+#	define	 USB1_TRX_MODE(w)	(((w)>>20)&0x07)
+#	define	 USB0_TRX_MODE(w)	(((w)>>16)&0x07)
+#	define	 OTG_IDLE_EN		(1 << 15)
+#	define	 HST_IDLE_EN		(1 << 14)
+#	define	 DEV_IDLE_EN		(1 << 13)
+#	define	 OTG_RESET_DONE		(1 << 2)
+#	define	 OTG_SOFT_RESET		(1 << 1)
+#define OTG_SYSCON_2			(OTG_BASE + 0x08)
+#	define	 OTG_EN			(1 << 31)
+#	define	 USBX_SYNCHRO		(1 << 30)
+#	define	 OTG_MST16		(1 << 29)
+#	define	 SRP_GPDATA		(1 << 28)
+#	define	 SRP_GPDVBUS		(1 << 27)
+#	define	 SRP_GPUVBUS(w)		(((w)>>24)&0x07)
+#	define	 A_WAIT_VRISE(w)	(((w)>>20)&0x07)
+#	define	 B_ASE_BRST(w)		(((w)>>16)&0x07)
+#	define	 SRP_DPW		(1 << 14)
+#	define	 SRP_DATA		(1 << 13)
+#	define	 SRP_VBUS		(1 << 12)
+#	define	 OTG_PADEN		(1 << 10)
+#	define	 HMC_PADEN		(1 << 9)
+#	define	 UHOST_EN		(1 << 8)
+#	define	 HMC_TLLSPEED		(1 << 7)
+#	define	 HMC_TLLATTACH		(1 << 6)
+#	define	 OTG_HMC(w)		(((w)>>0)&0x3f)
+#define OTG_CTRL			(OTG_BASE + 0x0c)
+#	define	 OTG_USB2_EN		(1 << 29)
+#	define	 OTG_USB2_DP		(1 << 28)
+#	define	 OTG_USB2_DM		(1 << 27)
+#	define	 OTG_USB1_EN		(1 << 26)
+#	define	 OTG_USB1_DP		(1 << 25)
+#	define	 OTG_USB1_DM		(1 << 24)
+#	define	 OTG_USB0_EN		(1 << 23)
+#	define	 OTG_USB0_DP		(1 << 22)
+#	define	 OTG_USB0_DM		(1 << 21)
+#	define	 OTG_ASESSVLD		(1 << 20)
+#	define	 OTG_BSESSEND		(1 << 19)
+#	define	 OTG_BSESSVLD		(1 << 18)
+#	define	 OTG_VBUSVLD		(1 << 17)
+#	define	 OTG_ID			(1 << 16)
+#	define	 OTG_DRIVER_SEL		(1 << 15)
+#	define	 OTG_A_SETB_HNPEN	(1 << 12)
+#	define	 OTG_A_BUSREQ		(1 << 11)
+#	define	 OTG_B_HNPEN		(1 << 9)
+#	define	 OTG_B_BUSREQ		(1 << 8)
+#	define	 OTG_BUSDROP		(1 << 7)
+#	define	 OTG_PULLDOWN		(1 << 5)
+#	define	 OTG_PULLUP		(1 << 4)
+#	define	 OTG_DRV_VBUS		(1 << 3)
+#	define	 OTG_PD_VBUS		(1 << 2)
+#	define	 OTG_PU_VBUS		(1 << 1)
+#	define	 OTG_PU_ID		(1 << 0)
+#define OTG_IRQ_EN			(OTG_BASE + 0x10)	/* 16-bit */
+#	define	 DRIVER_SWITCH		(1 << 15)
+#	define	 A_VBUS_ERR		(1 << 13)
+#	define	 A_REQ_TMROUT		(1 << 12)
+#	define	 A_SRP_DETECT		(1 << 11)
+#	define	 B_HNP_FAIL		(1 << 10)
+#	define	 B_SRP_TMROUT		(1 << 9)
+#	define	 B_SRP_DONE		(1 << 8)
+#	define	 B_SRP_STARTED		(1 << 7)
+#	define	 OPRT_CHG		(1 << 0)
+#define OTG_IRQ_SRC			(OTG_BASE + 0x14)	/* 16-bit */
+	// same bits as in IRQ_EN
+#define OTG_OUTCTRL			(OTG_BASE + 0x18)	/* 16-bit */
+#	define	 OTGVPD			(1 << 14)
+#	define	 OTGVPU			(1 << 13)
+#	define	 OTGPUID		(1 << 12)
+#	define	 USB2VDR		(1 << 10)
+#	define	 USB2PDEN		(1 << 9)
+#	define	 USB2PUEN		(1 << 8)
+#	define	 USB1VDR		(1 << 6)
+#	define	 USB1PDEN		(1 << 5)
+#	define	 USB1PUEN		(1 << 4)
+#	define	 USB0VDR		(1 << 2)
+#	define	 USB0PDEN		(1 << 1)
+#	define	 USB0PUEN		(1 << 0)
+#define OTG_TEST			(OTG_BASE + 0x20)	/* 16-bit */
+#define OTG_VENDOR_CODE			(OTG_BASE + 0xfc)	/* 16-bit */
+
+/*-------------------------------------------------------------------------*/
+
+/* OMAP1 */
+#define	USB_TRANSCEIVER_CTRL		(0xfffe1000 + 0x0064)
+#	define	CONF_USB2_UNI_R		(1 << 8)
+#	define	CONF_USB1_UNI_R		(1 << 7)
+#	define	CONF_USB_PORT0_R(x)	(((x)>>4)&0x7)
+#	define	CONF_USB0_ISOLATE_R	(1 << 3)
+#	define	CONF_USB_PWRDN_DM_R	(1 << 2)
+#	define	CONF_USB_PWRDN_DP_R	(1 << 1)
+
+#endif
-- 
cgit v1.2.3


From 1e9ca7c811f76b16c7822ad009b6b0c352227a15 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 6 Aug 2019 15:24:58 +0200
Subject: ARM: omap1: move some headers to include/linux/soc

There are three remaining header files that are used by omap1
specific device drivers:

- mach/soc.h provides cpu_is_omapXXX abstractions
- mach/hardware.h provides omap_read/omap_write functions
  and physical addresses
- mach/mux.h provides an omap specific pinctrl abstraction

This is generally not how we do platform abstractions today,
and it would be good to completely get rid of these in favor
of passing information through platform devices and the pinctrl
subsystem.

However, given that nobody is working on that, just move it
one step forward by splitting out the header files that are
used by drivers today from the machine headers that are only
used internally.

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-omap1/board-ams-delta.c       |   1 +
 arch/arm/mach-omap1/include/mach/hardware.h | 128 +-----------
 arch/arm/mach-omap1/include/mach/memory.h   |   2 +-
 arch/arm/mach-omap1/include/mach/mux.h      | 299 +-------------------------
 arch/arm/mach-omap1/include/mach/soc.h      | 220 --------------------
 arch/arm/mach-omap1/soc.h                   |   6 +-
 arch/arm/plat-omap/dma.c                    |   4 +-
 include/linux/soc/ti/omap1-io.h             | 143 +++++++++++++
 include/linux/soc/ti/omap1-mux.h            | 311 ++++++++++++++++++++++++++++
 include/linux/soc/ti/omap1-soc.h            | 198 ++++++++++++++++++
 10 files changed, 665 insertions(+), 647 deletions(-)
 delete mode 100644 arch/arm/mach-omap1/include/mach/soc.h
 create mode 100644 include/linux/soc/ti/omap1-io.h
 create mode 100644 include/linux/soc/ti/omap1-mux.h
 create mode 100644 include/linux/soc/ti/omap1-soc.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index 5b0e99319990..735f0314dc05 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -28,6 +28,7 @@
 #include <linux/omapfb.h>
 #include <linux/io.h>
 #include <linux/platform_data/gpio-omap.h>
+#include <linux/soc/ti/omap1-mux.h>
 
 #include <asm/serial.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-omap1/include/mach/hardware.h b/arch/arm/mach-omap1/include/mach/hardware.h
index e7c8ac7d83e3..05c5cd3e95f4 100644
--- a/arch/arm/mach-omap1/include/mach/hardware.h
+++ b/arch/arm/mach-omap1/include/mach/hardware.h
@@ -37,19 +37,10 @@
 #define __ASM_ARCH_OMAP_HARDWARE_H
 
 #include <linux/sizes.h>
+#include <linux/soc/ti/omap1-io.h>
 #ifndef __ASSEMBLER__
 #include <asm/types.h>
-#include <mach/soc.h>
-
-/*
- * NOTE: Please use ioremap + __raw_read/write where possible instead of these
- */
-extern u8 omap_readb(u32 pa);
-extern u16 omap_readw(u32 pa);
-extern u32 omap_readl(u32 pa);
-extern void omap_writeb(u8 v, u32 pa);
-extern void omap_writew(u16 v, u32 pa);
-extern void omap_writel(u32 v, u32 pa);
+#include <linux/soc/ti/omap1-soc.h>
 
 #include <mach/tc.h>
 
@@ -98,66 +89,6 @@ static inline u32 omap_cs3_phys(void)
 #define MPU_TIMER_AR		(1 << 1)
 #define MPU_TIMER_ST		(1 << 0)
 
-/*
- * ----------------------------------------------------------------------------
- * Clocks
- * ----------------------------------------------------------------------------
- */
-#define CLKGEN_REG_BASE		(0xfffece00)
-#define ARM_CKCTL		(CLKGEN_REG_BASE + 0x0)
-#define ARM_IDLECT1		(CLKGEN_REG_BASE + 0x4)
-#define ARM_IDLECT2		(CLKGEN_REG_BASE + 0x8)
-#define ARM_EWUPCT		(CLKGEN_REG_BASE + 0xC)
-#define ARM_RSTCT1		(CLKGEN_REG_BASE + 0x10)
-#define ARM_RSTCT2		(CLKGEN_REG_BASE + 0x14)
-#define ARM_SYSST		(CLKGEN_REG_BASE + 0x18)
-#define ARM_IDLECT3		(CLKGEN_REG_BASE + 0x24)
-
-#define CK_RATEF		1
-#define CK_IDLEF		2
-#define CK_ENABLEF		4
-#define CK_SELECTF		8
-#define SETARM_IDLE_SHIFT
-
-/* DPLL control registers */
-#define DPLL_CTL		(0xfffecf00)
-
-/* DSP clock control. Must use __raw_readw() and __raw_writew() with these */
-#define DSP_CONFIG_REG_BASE     IOMEM(0xe1008000)
-#define DSP_CKCTL		(DSP_CONFIG_REG_BASE + 0x0)
-#define DSP_IDLECT1		(DSP_CONFIG_REG_BASE + 0x4)
-#define DSP_IDLECT2		(DSP_CONFIG_REG_BASE + 0x8)
-#define DSP_RSTCT2		(DSP_CONFIG_REG_BASE + 0x14)
-
-/*
- * ---------------------------------------------------------------------------
- * UPLD
- * ---------------------------------------------------------------------------
- */
-#define ULPD_REG_BASE		(0xfffe0800)
-#define ULPD_IT_STATUS		(ULPD_REG_BASE + 0x14)
-#define ULPD_SETUP_ANALOG_CELL_3	(ULPD_REG_BASE + 0x24)
-#define ULPD_CLOCK_CTRL		(ULPD_REG_BASE + 0x30)
-#	define DIS_USB_PVCI_CLK		(1 << 5)	/* no USB/FAC synch */
-#	define USB_MCLK_EN		(1 << 4)	/* enable W4_USB_CLKO */
-#define ULPD_SOFT_REQ		(ULPD_REG_BASE + 0x34)
-#	define SOFT_UDC_REQ		(1 << 4)
-#	define SOFT_USB_CLK_REQ		(1 << 3)
-#	define SOFT_DPLL_REQ		(1 << 0)
-#define ULPD_DPLL_CTRL		(ULPD_REG_BASE + 0x3c)
-#define ULPD_STATUS_REQ		(ULPD_REG_BASE + 0x40)
-#define ULPD_APLL_CTRL		(ULPD_REG_BASE + 0x4c)
-#define ULPD_POWER_CTRL		(ULPD_REG_BASE + 0x50)
-#define ULPD_SOFT_DISABLE_REQ_REG	(ULPD_REG_BASE + 0x68)
-#	define DIS_MMC2_DPLL_REQ	(1 << 11)
-#	define DIS_MMC1_DPLL_REQ	(1 << 10)
-#	define DIS_UART3_DPLL_REQ	(1 << 9)
-#	define DIS_UART2_DPLL_REQ	(1 << 8)
-#	define DIS_UART1_DPLL_REQ	(1 << 7)
-#	define DIS_USB_HOST_DPLL_REQ	(1 << 6)
-#define ULPD_SDW_CLK_DIV_CTRL_SEL	(ULPD_REG_BASE + 0x74)
-#define ULPD_CAM_CLK_CTRL	(ULPD_REG_BASE + 0x7c)
-
 /*
  * ---------------------------------------------------------------------------
  * Watchdog timer
@@ -213,52 +144,6 @@ static inline u32 omap_cs3_phys(void)
 
 #endif
 
-/*
- * ----------------------------------------------------------------------------
- * System control registers
- * ----------------------------------------------------------------------------
- */
-#define MOD_CONF_CTRL_0		0xfffe1080
-#define MOD_CONF_CTRL_1		0xfffe1110
-
-/*
- * ----------------------------------------------------------------------------
- * Pin multiplexing registers
- * ----------------------------------------------------------------------------
- */
-#define FUNC_MUX_CTRL_0		0xfffe1000
-#define FUNC_MUX_CTRL_1		0xfffe1004
-#define FUNC_MUX_CTRL_2		0xfffe1008
-#define COMP_MODE_CTRL_0	0xfffe100c
-#define FUNC_MUX_CTRL_3		0xfffe1010
-#define FUNC_MUX_CTRL_4		0xfffe1014
-#define FUNC_MUX_CTRL_5		0xfffe1018
-#define FUNC_MUX_CTRL_6		0xfffe101C
-#define FUNC_MUX_CTRL_7		0xfffe1020
-#define FUNC_MUX_CTRL_8		0xfffe1024
-#define FUNC_MUX_CTRL_9		0xfffe1028
-#define FUNC_MUX_CTRL_A		0xfffe102C
-#define FUNC_MUX_CTRL_B		0xfffe1030
-#define FUNC_MUX_CTRL_C		0xfffe1034
-#define FUNC_MUX_CTRL_D		0xfffe1038
-#define PULL_DWN_CTRL_0		0xfffe1040
-#define PULL_DWN_CTRL_1		0xfffe1044
-#define PULL_DWN_CTRL_2		0xfffe1048
-#define PULL_DWN_CTRL_3		0xfffe104c
-#define PULL_DWN_CTRL_4		0xfffe10ac
-
-/* OMAP-1610 specific multiplexing registers */
-#define FUNC_MUX_CTRL_E		0xfffe1090
-#define FUNC_MUX_CTRL_F		0xfffe1094
-#define FUNC_MUX_CTRL_10	0xfffe1098
-#define FUNC_MUX_CTRL_11	0xfffe109c
-#define FUNC_MUX_CTRL_12	0xfffe10a0
-#define PU_PD_SEL_0		0xfffe10b4
-#define PU_PD_SEL_1		0xfffe10b8
-#define PU_PD_SEL_2		0xfffe10bc
-#define PU_PD_SEL_3		0xfffe10c0
-#define PU_PD_SEL_4		0xfffe10c4
-
 /* Timer32K for 1610 and 1710*/
 #define OMAP_TIMER32K_BASE	0xFFFBC400
 
@@ -299,15 +184,6 @@ static inline u32 omap_cs3_phys(void)
 #define OMAP_LPG2_LCR			(OMAP_LPG2_BASE + 0x00)
 #define OMAP_LPG2_PMR			(OMAP_LPG2_BASE + 0x04)
 
-/*
- * ----------------------------------------------------------------------------
- * Pulse-Width Light
- * ----------------------------------------------------------------------------
- */
-#define OMAP_PWL_BASE			0xfffb5800
-#define OMAP_PWL_ENABLE			(OMAP_PWL_BASE + 0x00)
-#define OMAP_PWL_CLK_ENABLE		(OMAP_PWL_BASE + 0x04)
-
 /*
  * ---------------------------------------------------------------------------
  * Processor specific defines
diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
index ba3a350479c8..ee91a6cb548d 100644
--- a/arch/arm/mach-omap1/include/mach/memory.h
+++ b/arch/arm/mach-omap1/include/mach/memory.h
@@ -7,6 +7,6 @@
 #define __ASM_ARCH_MEMORY_H
 
 /* REVISIT: omap1 legacy drivers still rely on this */
-#include <mach/soc.h>
+#include <mach/hardware.h>
 
 #endif
diff --git a/arch/arm/mach-omap1/include/mach/mux.h b/arch/arm/mach-omap1/include/mach/mux.h
index 3f6dc55d9898..a78282d1294c 100644
--- a/arch/arm/mach-omap1/include/mach/mux.h
+++ b/arch/arm/mach-omap1/include/mach/mux.h
@@ -20,6 +20,8 @@
 #ifndef __ASM_ARCH_MUX_H
 #define __ASM_ARCH_MUX_H
 
+#include <linux/soc/ti/omap1-mux.h>
+
 #define PU_PD_SEL_NA		0	/* No pu_pd reg available */
 #define PULL_DWN_CTRL_NA	0	/* No pull-down control needed */
 
@@ -124,301 +126,6 @@ struct pin_config {
 
 };
 
-enum omap7xx_index {
-	/* OMAP 730 keyboard */
-	E2_7XX_KBR0,
-	J7_7XX_KBR1,
-	E1_7XX_KBR2,
-	F3_7XX_KBR3,
-	D2_7XX_KBR4,
-	C2_7XX_KBC0,
-	D3_7XX_KBC1,
-	E4_7XX_KBC2,
-	F4_7XX_KBC3,
-	E3_7XX_KBC4,
-
-	/* USB */
-	AA17_7XX_USB_DM,
-	W16_7XX_USB_PU_EN,
-	W17_7XX_USB_VBUSI,
-	W18_7XX_USB_DMCK_OUT,
-	W19_7XX_USB_DCRST,
-
-	/* MMC */
-	MMC_7XX_CMD,
-	MMC_7XX_CLK,
-	MMC_7XX_DAT0,
-
-	/* I2C */
-	I2C_7XX_SCL,
-	I2C_7XX_SDA,
-
-	/* SPI */
-	SPI_7XX_1,
-	SPI_7XX_2,
-	SPI_7XX_3,
-	SPI_7XX_4,
-	SPI_7XX_5,
-	SPI_7XX_6,
-
-	/* UART */
-	UART_7XX_1,
-	UART_7XX_2,
-};
-
-enum omap1xxx_index {
-	/* UART1 (BT_UART_GATING)*/
-	UART1_TX = 0,
-	UART1_RTS,
-
-	/* UART2 (COM_UART_GATING)*/
-	UART2_TX,
-	UART2_RX,
-	UART2_CTS,
-	UART2_RTS,
-
-	/* UART3 (GIGA_UART_GATING) */
-	UART3_TX,
-	UART3_RX,
-	UART3_CTS,
-	UART3_RTS,
-	UART3_CLKREQ,
-	UART3_BCLK,	/* 12MHz clock out */
-	Y15_1610_UART3_RTS,
-
-	/* PWT & PWL */
-	PWT,
-	PWL,
-
-	/* USB master generic */
-	R18_USB_VBUS,
-	R18_1510_USB_GPIO0,
-	W4_USB_PUEN,
-	W4_USB_CLKO,
-	W4_USB_HIGHZ,
-	W4_GPIO58,
-
-	/* USB1 master */
-	USB1_SUSP,
-	USB1_SEO,
-	W13_1610_USB1_SE0,
-	USB1_TXEN,
-	USB1_TXD,
-	USB1_VP,
-	USB1_VM,
-	USB1_RCV,
-	USB1_SPEED,
-	R13_1610_USB1_SPEED,
-	R13_1710_USB1_SE0,
-
-	/* USB2 master */
-	USB2_SUSP,
-	USB2_VP,
-	USB2_TXEN,
-	USB2_VM,
-	USB2_RCV,
-	USB2_SEO,
-	USB2_TXD,
-
-	/* OMAP-1510 GPIO */
-	R18_1510_GPIO0,
-	R19_1510_GPIO1,
-	M14_1510_GPIO2,
-
-	/* OMAP1610 GPIO */
-	P18_1610_GPIO3,
-	Y15_1610_GPIO17,
-
-	/* OMAP-1710 GPIO */
-	R18_1710_GPIO0,
-	V2_1710_GPIO10,
-	N21_1710_GPIO14,
-	W15_1710_GPIO40,
-
-	/* MPUIO */
-	MPUIO2,
-	N15_1610_MPUIO2,
-	MPUIO4,
-	MPUIO5,
-	T20_1610_MPUIO5,
-	W11_1610_MPUIO6,
-	V10_1610_MPUIO7,
-	W11_1610_MPUIO9,
-	V10_1610_MPUIO10,
-	W10_1610_MPUIO11,
-	E20_1610_MPUIO13,
-	U20_1610_MPUIO14,
-	E19_1610_MPUIO15,
-
-	/* MCBSP2 */
-	MCBSP2_CLKR,
-	MCBSP2_CLKX,
-	MCBSP2_DR,
-	MCBSP2_DX,
-	MCBSP2_FSR,
-	MCBSP2_FSX,
-
-	/* MCBSP3 */
-	MCBSP3_CLKX,
-
-	/* Misc ballouts */
-	BALLOUT_V8_ARMIO3,
-	N20_HDQ,
-
-	/* OMAP-1610 MMC2 */
-	W8_1610_MMC2_DAT0,
-	V8_1610_MMC2_DAT1,
-	W15_1610_MMC2_DAT2,
-	R10_1610_MMC2_DAT3,
-	Y10_1610_MMC2_CLK,
-	Y8_1610_MMC2_CMD,
-	V9_1610_MMC2_CMDDIR,
-	V5_1610_MMC2_DATDIR0,
-	W19_1610_MMC2_DATDIR1,
-	R18_1610_MMC2_CLKIN,
-
-	/* OMAP-1610 External Trace Interface */
-	M19_1610_ETM_PSTAT0,
-	L15_1610_ETM_PSTAT1,
-	L18_1610_ETM_PSTAT2,
-	L19_1610_ETM_D0,
-	J19_1610_ETM_D6,
-	J18_1610_ETM_D7,
-
-	/* OMAP16XX GPIO */
-	P20_1610_GPIO4,
-	V9_1610_GPIO7,
-	W8_1610_GPIO9,
-	N20_1610_GPIO11,
-	N19_1610_GPIO13,
-	P10_1610_GPIO22,
-	V5_1610_GPIO24,
-	AA20_1610_GPIO_41,
-	W19_1610_GPIO48,
-	M7_1610_GPIO62,
-	V14_16XX_GPIO37,
-	R9_16XX_GPIO18,
-	L14_16XX_GPIO49,
-
-	/* OMAP-1610 uWire */
-	V19_1610_UWIRE_SCLK,
-	U18_1610_UWIRE_SDI,
-	W21_1610_UWIRE_SDO,
-	N14_1610_UWIRE_CS0,
-	P15_1610_UWIRE_CS3,
-	N15_1610_UWIRE_CS1,
-
-	/* OMAP-1610 SPI */
-	U19_1610_SPIF_SCK,
-	U18_1610_SPIF_DIN,
-	P20_1610_SPIF_DIN,
-	W21_1610_SPIF_DOUT,
-	R18_1610_SPIF_DOUT,
-	N14_1610_SPIF_CS0,
-	N15_1610_SPIF_CS1,
-	T19_1610_SPIF_CS2,
-	P15_1610_SPIF_CS3,
-
-	/* OMAP-1610 Flash */
-	L3_1610_FLASH_CS2B_OE,
-	M8_1610_FLASH_CS2B_WE,
-
-	/* First MMC */
-	MMC_CMD,
-	MMC_DAT1,
-	MMC_DAT2,
-	MMC_DAT0,
-	MMC_CLK,
-	MMC_DAT3,
-
-	/* OMAP-1710 MMC CMDDIR and DATDIR0 */
-	M15_1710_MMC_CLKI,
-	P19_1710_MMC_CMDDIR,
-	P20_1710_MMC_DATDIR0,
-
-	/* OMAP-1610 USB0 alternate pin configuration */
-	W9_USB0_TXEN,
-	AA9_USB0_VP,
-	Y5_USB0_RCV,
-	R9_USB0_VM,
-	V6_USB0_TXD,
-	W5_USB0_SE0,
-	V9_USB0_SPEED,
-	V9_USB0_SUSP,
-
-	/* USB2 */
-	W9_USB2_TXEN,
-	AA9_USB2_VP,
-	Y5_USB2_RCV,
-	R9_USB2_VM,
-	V6_USB2_TXD,
-	W5_USB2_SE0,
-
-	/* 16XX UART */
-	R13_1610_UART1_TX,
-	V14_16XX_UART1_RX,
-	R14_1610_UART1_CTS,
-	AA15_1610_UART1_RTS,
-	R9_16XX_UART2_RX,
-	L14_16XX_UART3_RX,
-
-	/* I2C OMAP-1610 */
-	I2C_SCL,
-	I2C_SDA,
-
-	/* Keypad */
-	F18_1610_KBC0,
-	D20_1610_KBC1,
-	D19_1610_KBC2,
-	E18_1610_KBC3,
-	C21_1610_KBC4,
-	G18_1610_KBR0,
-	F19_1610_KBR1,
-	H14_1610_KBR2,
-	E20_1610_KBR3,
-	E19_1610_KBR4,
-	N19_1610_KBR5,
-
-	/* Power management */
-	T20_1610_LOW_PWR,
-
-	/* MCLK Settings */
-	V5_1710_MCLK_ON,
-	V5_1710_MCLK_OFF,
-	R10_1610_MCLK_ON,
-	R10_1610_MCLK_OFF,
-
-	/* CompactFlash controller */
-	P11_1610_CF_CD2,
-	R11_1610_CF_IOIS16,
-	V10_1610_CF_IREQ,
-	W10_1610_CF_RESET,
-	W11_1610_CF_CD1,
-
-	/* parallel camera */
-	J15_1610_CAM_LCLK,
-	J18_1610_CAM_D7,
-	J19_1610_CAM_D6,
-	J14_1610_CAM_D5,
-	K18_1610_CAM_D4,
-	K19_1610_CAM_D3,
-	K15_1610_CAM_D2,
-	K14_1610_CAM_D1,
-	L19_1610_CAM_D0,
-	L18_1610_CAM_VS,
-	L15_1610_CAM_HS,
-	M19_1610_CAM_RSTZ,
-	Y15_1610_CAM_OUTCLK,
-
-	/* serial camera */
-	H19_1610_CAM_EXCLK,
-	Y12_1610_CCP_CLKP,
-	W13_1610_CCP_CLKM,
-	W14_1610_CCP_DATAP,
-	Y14_1610_CCP_DATAM,
-
-};
-
 struct omap_mux_cfg {
 	struct pin_config	*pins;
 	unsigned long		size;
@@ -429,11 +136,9 @@ struct omap_mux_cfg {
 /* setup pin muxing in Linux */
 extern int omap1_mux_init(void);
 extern int omap_mux_register(struct omap_mux_cfg *);
-extern int omap_cfg_reg(unsigned long reg_cfg);
 #else
 /* boot loader does it all (no warnings from CONFIG_OMAP_MUX_WARNINGS) */
 static inline int omap1_mux_init(void) { return 0; }
-static inline int omap_cfg_reg(unsigned long reg_cfg) { return 0; }
 #endif
 
 extern int omap2_mux_init(void);
diff --git a/arch/arm/mach-omap1/include/mach/soc.h b/arch/arm/mach-omap1/include/mach/soc.h
deleted file mode 100644
index 1897cbabfc93..000000000000
--- a/arch/arm/mach-omap1/include/mach/soc.h
+++ /dev/null
@@ -1,220 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * OMAP cpu type detection
- *
- * Copyright (C) 2004, 2008 Nokia Corporation
- *
- * Copyright (C) 2009-11 Texas Instruments.
- *
- * Written by Tony Lindgren <tony.lindgren@nokia.com>
- *
- * Added OMAP4/5 specific defines - Santosh Shilimkar<santosh.shilimkar@ti.com>
- */
-
-#ifndef __ASM_ARCH_OMAP_CPU_H
-#define __ASM_ARCH_OMAP_CPU_H
-
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <mach/irqs.h>
-
-#ifndef __ASSEMBLY__
-
-#include <linux/bitops.h>
-
-/*
- * Test if multicore OMAP support is needed
- */
-#undef MULTI_OMAP1
-#undef OMAP_NAME
-
-#ifdef CONFIG_ARCH_OMAP730
-# ifdef OMAP_NAME
-#  undef  MULTI_OMAP1
-#  define MULTI_OMAP1
-# else
-#  define OMAP_NAME omap730
-# endif
-#endif
-#ifdef CONFIG_ARCH_OMAP850
-# ifdef OMAP_NAME
-#  undef  MULTI_OMAP1
-#  define MULTI_OMAP1
-# else
-#  define OMAP_NAME omap850
-# endif
-#endif
-#ifdef CONFIG_ARCH_OMAP15XX
-# ifdef OMAP_NAME
-#  undef  MULTI_OMAP1
-#  define MULTI_OMAP1
-# else
-#  define OMAP_NAME omap1510
-# endif
-#endif
-#ifdef CONFIG_ARCH_OMAP16XX
-# ifdef OMAP_NAME
-#  undef  MULTI_OMAP1
-#  define MULTI_OMAP1
-# else
-#  define OMAP_NAME omap16xx
-# endif
-#endif
-
-/*
- * omap_rev bits:
- * CPU id bits	(0730, 1510, 1710, 2422...)	[31:16]
- * CPU revision	(See _REV_ defined in cpu.h)	[15:08]
- * CPU class bits (15xx, 16xx, 24xx, 34xx...)	[07:00]
- */
-unsigned int omap_rev(void);
-
-/*
- * Get the CPU revision for OMAP devices
- */
-#define GET_OMAP_REVISION()	((omap_rev() >> 8) & 0xff)
-
-/*
- * Macros to group OMAP into cpu classes.
- * These can be used in most places.
- * cpu_is_omap7xx():	True for OMAP730, OMAP850
- * cpu_is_omap15xx():	True for OMAP1510, OMAP5910 and OMAP310
- * cpu_is_omap16xx():	True for OMAP1610, OMAP5912 and OMAP1710
- */
-#define GET_OMAP_CLASS	(omap_rev() & 0xff)
-
-#define IS_OMAP_CLASS(class, id)			\
-static inline int is_omap ##class (void)		\
-{							\
-	return (GET_OMAP_CLASS == (id)) ? 1 : 0;	\
-}
-
-#define GET_OMAP_SUBCLASS	((omap_rev() >> 20) & 0x0fff)
-
-#define IS_OMAP_SUBCLASS(subclass, id)			\
-static inline int is_omap ##subclass (void)		\
-{							\
-	return (GET_OMAP_SUBCLASS == (id)) ? 1 : 0;	\
-}
-
-IS_OMAP_CLASS(7xx, 0x07)
-IS_OMAP_CLASS(15xx, 0x15)
-IS_OMAP_CLASS(16xx, 0x16)
-
-#define cpu_is_omap7xx()		0
-#define cpu_is_omap15xx()		0
-#define cpu_is_omap16xx()		0
-
-#if defined(MULTI_OMAP1)
-# if defined(CONFIG_ARCH_OMAP730)
-#  undef  cpu_is_omap7xx
-#  define cpu_is_omap7xx()		is_omap7xx()
-# endif
-# if defined(CONFIG_ARCH_OMAP850)
-#  undef  cpu_is_omap7xx
-#  define cpu_is_omap7xx()		is_omap7xx()
-# endif
-# if defined(CONFIG_ARCH_OMAP15XX)
-#  undef  cpu_is_omap15xx
-#  define cpu_is_omap15xx()		is_omap15xx()
-# endif
-# if defined(CONFIG_ARCH_OMAP16XX)
-#  undef  cpu_is_omap16xx
-#  define cpu_is_omap16xx()		is_omap16xx()
-# endif
-#else
-# if defined(CONFIG_ARCH_OMAP730)
-#  undef  cpu_is_omap7xx
-#  define cpu_is_omap7xx()		1
-# endif
-# if defined(CONFIG_ARCH_OMAP850)
-#  undef  cpu_is_omap7xx
-#  define cpu_is_omap7xx()		1
-# endif
-# if defined(CONFIG_ARCH_OMAP15XX)
-#  undef  cpu_is_omap15xx
-#  define cpu_is_omap15xx()		1
-# endif
-# if defined(CONFIG_ARCH_OMAP16XX)
-#  undef  cpu_is_omap16xx
-#  define cpu_is_omap16xx()		1
-# endif
-#endif
-
-/*
- * Macros to detect individual cpu types.
- * These are only rarely needed.
- * cpu_is_omap310():	True for OMAP310
- * cpu_is_omap1510():	True for OMAP1510
- * cpu_is_omap1610():	True for OMAP1610
- * cpu_is_omap1611():	True for OMAP1611
- * cpu_is_omap5912():	True for OMAP5912
- * cpu_is_omap1621():	True for OMAP1621
- * cpu_is_omap1710():	True for OMAP1710
- */
-#define GET_OMAP_TYPE	((omap_rev() >> 16) & 0xffff)
-
-#define IS_OMAP_TYPE(type, id)				\
-static inline int is_omap ##type (void)			\
-{							\
-	return (GET_OMAP_TYPE == (id)) ? 1 : 0;		\
-}
-
-IS_OMAP_TYPE(310, 0x0310)
-IS_OMAP_TYPE(1510, 0x1510)
-IS_OMAP_TYPE(1610, 0x1610)
-IS_OMAP_TYPE(1611, 0x1611)
-IS_OMAP_TYPE(5912, 0x1611)
-IS_OMAP_TYPE(1621, 0x1621)
-IS_OMAP_TYPE(1710, 0x1710)
-
-#define cpu_is_omap310()		0
-#define cpu_is_omap1510()		0
-#define cpu_is_omap1610()		0
-#define cpu_is_omap5912()		0
-#define cpu_is_omap1611()		0
-#define cpu_is_omap1621()		0
-#define cpu_is_omap1710()		0
-
-/* These are needed to compile common code */
-#ifdef CONFIG_ARCH_OMAP1
-#define cpu_is_omap242x()		0
-#define cpu_is_omap2430()		0
-#define cpu_is_omap243x()		0
-#define cpu_is_omap24xx()		0
-#define cpu_is_omap34xx()		0
-#define cpu_is_omap44xx()		0
-#define soc_is_omap54xx()		0
-#define soc_is_dra7xx()			0
-#define soc_is_am33xx()			0
-#define cpu_class_is_omap1()		1
-#define cpu_class_is_omap2()		0
-#endif
-
-/*
- * Whether we have MULTI_OMAP1 or not, we still need to distinguish
- * between 310 vs. 1510 and 1611B/5912 vs. 1710.
- */
-
-#if defined(CONFIG_ARCH_OMAP15XX)
-# undef  cpu_is_omap310
-# undef  cpu_is_omap1510
-# define cpu_is_omap310()		is_omap310()
-# define cpu_is_omap1510()		is_omap1510()
-#endif
-
-#if defined(CONFIG_ARCH_OMAP16XX)
-# undef  cpu_is_omap1610
-# undef  cpu_is_omap1611
-# undef  cpu_is_omap5912
-# undef  cpu_is_omap1621
-# undef  cpu_is_omap1710
-# define cpu_is_omap1610()		is_omap1610()
-# define cpu_is_omap1611()		is_omap1611()
-# define cpu_is_omap5912()		is_omap5912()
-# define cpu_is_omap1621()		is_omap1621()
-# define cpu_is_omap1710()		is_omap1710()
-#endif
-
-#endif	/* __ASSEMBLY__ */
-#endif
diff --git a/arch/arm/mach-omap1/soc.h b/arch/arm/mach-omap1/soc.h
index 69daf0187b1d..22931839a666 100644
--- a/arch/arm/mach-omap1/soc.h
+++ b/arch/arm/mach-omap1/soc.h
@@ -1,4 +1,6 @@
 /*
- * We can move mach/soc.h here once the drivers are fixed
+ * We can move linux/soc/ti/omap1-soc.h here once the drivers are fixed
  */
-#include <mach/soc.h>
+#include <mach/hardware.h>
+#include <mach/irqs.h>
+#include <asm/irq.h>
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index 9f11de46aaa9..700ba9b600e7 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -35,7 +35,9 @@
 #include <linux/omap-dma.h>
 
 #ifdef CONFIG_ARCH_OMAP1
-#include <mach/soc.h>
+#include <mach/hardware.h>
+#include <linux/soc/ti/omap1-io.h>
+#include <linux/soc/ti/omap1-soc.h>
 #endif
 
 /*
diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h
new file mode 100644
index 000000000000..9332c92690f4
--- /dev/null
+++ b/include/linux/soc/ti/omap1-io.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_ARCH_OMAP_IO_H
+#define __ASM_ARCH_OMAP_IO_H
+
+#ifndef __ASSEMBLER__
+#include <linux/types.h>
+
+#if defined(CONFIG_ARCH_OMAP) && defined(CONFIG_ARCH_OMAP1)
+/*
+ * NOTE: Please use ioremap + __raw_read/write where possible instead of these
+ */
+extern u8 omap_readb(u32 pa);
+extern u16 omap_readw(u32 pa);
+extern u32 omap_readl(u32 pa);
+extern void omap_writeb(u8 v, u32 pa);
+extern void omap_writew(u16 v, u32 pa);
+extern void omap_writel(u32 v, u32 pa);
+#elif defined(CONFIG_COMPILE_TEST)
+static inline u8 omap_readb(u32 pa)  { return 0; }
+static inline u16 omap_readw(u32 pa) { return 0; }
+static inline u32 omap_readl(u32 pa) { return 0; }
+static inline void omap_writeb(u8 v, u32 pa)   { }
+static inline void omap_writew(u16 v, u32 pa)  { }
+static inline void omap_writel(u32 v, u32 pa)  { }
+#endif
+#endif
+
+/*
+ * ----------------------------------------------------------------------------
+ * System control registers
+ * ----------------------------------------------------------------------------
+ */
+#define MOD_CONF_CTRL_0		0xfffe1080
+#define MOD_CONF_CTRL_1		0xfffe1110
+
+/*
+ * ---------------------------------------------------------------------------
+ * UPLD
+ * ---------------------------------------------------------------------------
+ */
+#define ULPD_REG_BASE		(0xfffe0800)
+#define ULPD_IT_STATUS		(ULPD_REG_BASE + 0x14)
+#define ULPD_SETUP_ANALOG_CELL_3	(ULPD_REG_BASE + 0x24)
+#define ULPD_CLOCK_CTRL		(ULPD_REG_BASE + 0x30)
+#	define DIS_USB_PVCI_CLK		(1 << 5)	/* no USB/FAC synch */
+#	define USB_MCLK_EN		(1 << 4)	/* enable W4_USB_CLKO */
+#define ULPD_SOFT_REQ		(ULPD_REG_BASE + 0x34)
+#	define SOFT_UDC_REQ		(1 << 4)
+#	define SOFT_USB_CLK_REQ		(1 << 3)
+#	define SOFT_DPLL_REQ		(1 << 0)
+#define ULPD_DPLL_CTRL		(ULPD_REG_BASE + 0x3c)
+#define ULPD_STATUS_REQ		(ULPD_REG_BASE + 0x40)
+#define ULPD_APLL_CTRL		(ULPD_REG_BASE + 0x4c)
+#define ULPD_POWER_CTRL		(ULPD_REG_BASE + 0x50)
+#define ULPD_SOFT_DISABLE_REQ_REG	(ULPD_REG_BASE + 0x68)
+#	define DIS_MMC2_DPLL_REQ	(1 << 11)
+#	define DIS_MMC1_DPLL_REQ	(1 << 10)
+#	define DIS_UART3_DPLL_REQ	(1 << 9)
+#	define DIS_UART2_DPLL_REQ	(1 << 8)
+#	define DIS_UART1_DPLL_REQ	(1 << 7)
+#	define DIS_USB_HOST_DPLL_REQ	(1 << 6)
+#define ULPD_SDW_CLK_DIV_CTRL_SEL	(ULPD_REG_BASE + 0x74)
+#define ULPD_CAM_CLK_CTRL	(ULPD_REG_BASE + 0x7c)
+
+/*
+ * ----------------------------------------------------------------------------
+ * Clocks
+ * ----------------------------------------------------------------------------
+ */
+#define CLKGEN_REG_BASE		(0xfffece00)
+#define ARM_CKCTL		(CLKGEN_REG_BASE + 0x0)
+#define ARM_IDLECT1		(CLKGEN_REG_BASE + 0x4)
+#define ARM_IDLECT2		(CLKGEN_REG_BASE + 0x8)
+#define ARM_EWUPCT		(CLKGEN_REG_BASE + 0xC)
+#define ARM_RSTCT1		(CLKGEN_REG_BASE + 0x10)
+#define ARM_RSTCT2		(CLKGEN_REG_BASE + 0x14)
+#define ARM_SYSST		(CLKGEN_REG_BASE + 0x18)
+#define ARM_IDLECT3		(CLKGEN_REG_BASE + 0x24)
+
+#define CK_RATEF		1
+#define CK_IDLEF		2
+#define CK_ENABLEF		4
+#define CK_SELECTF		8
+#define SETARM_IDLE_SHIFT
+
+/* DPLL control registers */
+#define DPLL_CTL		(0xfffecf00)
+
+/* DSP clock control. Must use __raw_readw() and __raw_writew() with these */
+#define DSP_CONFIG_REG_BASE     IOMEM(0xe1008000)
+#define DSP_CKCTL		(DSP_CONFIG_REG_BASE + 0x0)
+#define DSP_IDLECT1		(DSP_CONFIG_REG_BASE + 0x4)
+#define DSP_IDLECT2		(DSP_CONFIG_REG_BASE + 0x8)
+#define DSP_RSTCT2		(DSP_CONFIG_REG_BASE + 0x14)
+
+/*
+ * ----------------------------------------------------------------------------
+ * Pulse-Width Light
+ * ----------------------------------------------------------------------------
+ */
+#define OMAP_PWL_BASE			0xfffb5800
+#define OMAP_PWL_ENABLE			(OMAP_PWL_BASE + 0x00)
+#define OMAP_PWL_CLK_ENABLE		(OMAP_PWL_BASE + 0x04)
+
+/*
+ * ----------------------------------------------------------------------------
+ * Pin multiplexing registers
+ * ----------------------------------------------------------------------------
+ */
+#define FUNC_MUX_CTRL_0		0xfffe1000
+#define FUNC_MUX_CTRL_1		0xfffe1004
+#define FUNC_MUX_CTRL_2		0xfffe1008
+#define COMP_MODE_CTRL_0	0xfffe100c
+#define FUNC_MUX_CTRL_3		0xfffe1010
+#define FUNC_MUX_CTRL_4		0xfffe1014
+#define FUNC_MUX_CTRL_5		0xfffe1018
+#define FUNC_MUX_CTRL_6		0xfffe101C
+#define FUNC_MUX_CTRL_7		0xfffe1020
+#define FUNC_MUX_CTRL_8		0xfffe1024
+#define FUNC_MUX_CTRL_9		0xfffe1028
+#define FUNC_MUX_CTRL_A		0xfffe102C
+#define FUNC_MUX_CTRL_B		0xfffe1030
+#define FUNC_MUX_CTRL_C		0xfffe1034
+#define FUNC_MUX_CTRL_D		0xfffe1038
+#define PULL_DWN_CTRL_0		0xfffe1040
+#define PULL_DWN_CTRL_1		0xfffe1044
+#define PULL_DWN_CTRL_2		0xfffe1048
+#define PULL_DWN_CTRL_3		0xfffe104c
+#define PULL_DWN_CTRL_4		0xfffe10ac
+
+/* OMAP-1610 specific multiplexing registers */
+#define FUNC_MUX_CTRL_E		0xfffe1090
+#define FUNC_MUX_CTRL_F		0xfffe1094
+#define FUNC_MUX_CTRL_10	0xfffe1098
+#define FUNC_MUX_CTRL_11	0xfffe109c
+#define FUNC_MUX_CTRL_12	0xfffe10a0
+#define PU_PD_SEL_0		0xfffe10b4
+#define PU_PD_SEL_1		0xfffe10b8
+#define PU_PD_SEL_2		0xfffe10bc
+#define PU_PD_SEL_3		0xfffe10c0
+#define PU_PD_SEL_4		0xfffe10c4
+
+#endif
diff --git a/include/linux/soc/ti/omap1-mux.h b/include/linux/soc/ti/omap1-mux.h
new file mode 100644
index 000000000000..59c239b5569c
--- /dev/null
+++ b/include/linux/soc/ti/omap1-mux.h
@@ -0,0 +1,311 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef __SOC_TI_OMAP1_MUX_H
+#define __SOC_TI_OMAP1_MUX_H
+/*
+ * This should not really be a global header, it reflects the
+ * traditional way that omap1 does pin muxing without the
+ * pinctrl subsystem.
+ */
+
+enum omap7xx_index {
+	/* OMAP 730 keyboard */
+	E2_7XX_KBR0,
+	J7_7XX_KBR1,
+	E1_7XX_KBR2,
+	F3_7XX_KBR3,
+	D2_7XX_KBR4,
+	C2_7XX_KBC0,
+	D3_7XX_KBC1,
+	E4_7XX_KBC2,
+	F4_7XX_KBC3,
+	E3_7XX_KBC4,
+
+	/* USB */
+	AA17_7XX_USB_DM,
+	W16_7XX_USB_PU_EN,
+	W17_7XX_USB_VBUSI,
+	W18_7XX_USB_DMCK_OUT,
+	W19_7XX_USB_DCRST,
+
+	/* MMC */
+	MMC_7XX_CMD,
+	MMC_7XX_CLK,
+	MMC_7XX_DAT0,
+
+	/* I2C */
+	I2C_7XX_SCL,
+	I2C_7XX_SDA,
+
+	/* SPI */
+	SPI_7XX_1,
+	SPI_7XX_2,
+	SPI_7XX_3,
+	SPI_7XX_4,
+	SPI_7XX_5,
+	SPI_7XX_6,
+
+	/* UART */
+	UART_7XX_1,
+	UART_7XX_2,
+};
+
+enum omap1xxx_index {
+	/* UART1 (BT_UART_GATING)*/
+	UART1_TX = 0,
+	UART1_RTS,
+
+	/* UART2 (COM_UART_GATING)*/
+	UART2_TX,
+	UART2_RX,
+	UART2_CTS,
+	UART2_RTS,
+
+	/* UART3 (GIGA_UART_GATING) */
+	UART3_TX,
+	UART3_RX,
+	UART3_CTS,
+	UART3_RTS,
+	UART3_CLKREQ,
+	UART3_BCLK,	/* 12MHz clock out */
+	Y15_1610_UART3_RTS,
+
+	/* PWT & PWL */
+	PWT,
+	PWL,
+
+	/* USB master generic */
+	R18_USB_VBUS,
+	R18_1510_USB_GPIO0,
+	W4_USB_PUEN,
+	W4_USB_CLKO,
+	W4_USB_HIGHZ,
+	W4_GPIO58,
+
+	/* USB1 master */
+	USB1_SUSP,
+	USB1_SEO,
+	W13_1610_USB1_SE0,
+	USB1_TXEN,
+	USB1_TXD,
+	USB1_VP,
+	USB1_VM,
+	USB1_RCV,
+	USB1_SPEED,
+	R13_1610_USB1_SPEED,
+	R13_1710_USB1_SE0,
+
+	/* USB2 master */
+	USB2_SUSP,
+	USB2_VP,
+	USB2_TXEN,
+	USB2_VM,
+	USB2_RCV,
+	USB2_SEO,
+	USB2_TXD,
+
+	/* OMAP-1510 GPIO */
+	R18_1510_GPIO0,
+	R19_1510_GPIO1,
+	M14_1510_GPIO2,
+
+	/* OMAP1610 GPIO */
+	P18_1610_GPIO3,
+	Y15_1610_GPIO17,
+
+	/* OMAP-1710 GPIO */
+	R18_1710_GPIO0,
+	V2_1710_GPIO10,
+	N21_1710_GPIO14,
+	W15_1710_GPIO40,
+
+	/* MPUIO */
+	MPUIO2,
+	N15_1610_MPUIO2,
+	MPUIO4,
+	MPUIO5,
+	T20_1610_MPUIO5,
+	W11_1610_MPUIO6,
+	V10_1610_MPUIO7,
+	W11_1610_MPUIO9,
+	V10_1610_MPUIO10,
+	W10_1610_MPUIO11,
+	E20_1610_MPUIO13,
+	U20_1610_MPUIO14,
+	E19_1610_MPUIO15,
+
+	/* MCBSP2 */
+	MCBSP2_CLKR,
+	MCBSP2_CLKX,
+	MCBSP2_DR,
+	MCBSP2_DX,
+	MCBSP2_FSR,
+	MCBSP2_FSX,
+
+	/* MCBSP3 */
+	MCBSP3_CLKX,
+
+	/* Misc ballouts */
+	BALLOUT_V8_ARMIO3,
+	N20_HDQ,
+
+	/* OMAP-1610 MMC2 */
+	W8_1610_MMC2_DAT0,
+	V8_1610_MMC2_DAT1,
+	W15_1610_MMC2_DAT2,
+	R10_1610_MMC2_DAT3,
+	Y10_1610_MMC2_CLK,
+	Y8_1610_MMC2_CMD,
+	V9_1610_MMC2_CMDDIR,
+	V5_1610_MMC2_DATDIR0,
+	W19_1610_MMC2_DATDIR1,
+	R18_1610_MMC2_CLKIN,
+
+	/* OMAP-1610 External Trace Interface */
+	M19_1610_ETM_PSTAT0,
+	L15_1610_ETM_PSTAT1,
+	L18_1610_ETM_PSTAT2,
+	L19_1610_ETM_D0,
+	J19_1610_ETM_D6,
+	J18_1610_ETM_D7,
+
+	/* OMAP16XX GPIO */
+	P20_1610_GPIO4,
+	V9_1610_GPIO7,
+	W8_1610_GPIO9,
+	N20_1610_GPIO11,
+	N19_1610_GPIO13,
+	P10_1610_GPIO22,
+	V5_1610_GPIO24,
+	AA20_1610_GPIO_41,
+	W19_1610_GPIO48,
+	M7_1610_GPIO62,
+	V14_16XX_GPIO37,
+	R9_16XX_GPIO18,
+	L14_16XX_GPIO49,
+
+	/* OMAP-1610 uWire */
+	V19_1610_UWIRE_SCLK,
+	U18_1610_UWIRE_SDI,
+	W21_1610_UWIRE_SDO,
+	N14_1610_UWIRE_CS0,
+	P15_1610_UWIRE_CS3,
+	N15_1610_UWIRE_CS1,
+
+	/* OMAP-1610 SPI */
+	U19_1610_SPIF_SCK,
+	U18_1610_SPIF_DIN,
+	P20_1610_SPIF_DIN,
+	W21_1610_SPIF_DOUT,
+	R18_1610_SPIF_DOUT,
+	N14_1610_SPIF_CS0,
+	N15_1610_SPIF_CS1,
+	T19_1610_SPIF_CS2,
+	P15_1610_SPIF_CS3,
+
+	/* OMAP-1610 Flash */
+	L3_1610_FLASH_CS2B_OE,
+	M8_1610_FLASH_CS2B_WE,
+
+	/* First MMC */
+	MMC_CMD,
+	MMC_DAT1,
+	MMC_DAT2,
+	MMC_DAT0,
+	MMC_CLK,
+	MMC_DAT3,
+
+	/* OMAP-1710 MMC CMDDIR and DATDIR0 */
+	M15_1710_MMC_CLKI,
+	P19_1710_MMC_CMDDIR,
+	P20_1710_MMC_DATDIR0,
+
+	/* OMAP-1610 USB0 alternate pin configuration */
+	W9_USB0_TXEN,
+	AA9_USB0_VP,
+	Y5_USB0_RCV,
+	R9_USB0_VM,
+	V6_USB0_TXD,
+	W5_USB0_SE0,
+	V9_USB0_SPEED,
+	V9_USB0_SUSP,
+
+	/* USB2 */
+	W9_USB2_TXEN,
+	AA9_USB2_VP,
+	Y5_USB2_RCV,
+	R9_USB2_VM,
+	V6_USB2_TXD,
+	W5_USB2_SE0,
+
+	/* 16XX UART */
+	R13_1610_UART1_TX,
+	V14_16XX_UART1_RX,
+	R14_1610_UART1_CTS,
+	AA15_1610_UART1_RTS,
+	R9_16XX_UART2_RX,
+	L14_16XX_UART3_RX,
+
+	/* I2C OMAP-1610 */
+	I2C_SCL,
+	I2C_SDA,
+
+	/* Keypad */
+	F18_1610_KBC0,
+	D20_1610_KBC1,
+	D19_1610_KBC2,
+	E18_1610_KBC3,
+	C21_1610_KBC4,
+	G18_1610_KBR0,
+	F19_1610_KBR1,
+	H14_1610_KBR2,
+	E20_1610_KBR3,
+	E19_1610_KBR4,
+	N19_1610_KBR5,
+
+	/* Power management */
+	T20_1610_LOW_PWR,
+
+	/* MCLK Settings */
+	V5_1710_MCLK_ON,
+	V5_1710_MCLK_OFF,
+	R10_1610_MCLK_ON,
+	R10_1610_MCLK_OFF,
+
+	/* CompactFlash controller */
+	P11_1610_CF_CD2,
+	R11_1610_CF_IOIS16,
+	V10_1610_CF_IREQ,
+	W10_1610_CF_RESET,
+	W11_1610_CF_CD1,
+
+	/* parallel camera */
+	J15_1610_CAM_LCLK,
+	J18_1610_CAM_D7,
+	J19_1610_CAM_D6,
+	J14_1610_CAM_D5,
+	K18_1610_CAM_D4,
+	K19_1610_CAM_D3,
+	K15_1610_CAM_D2,
+	K14_1610_CAM_D1,
+	L19_1610_CAM_D0,
+	L18_1610_CAM_VS,
+	L15_1610_CAM_HS,
+	M19_1610_CAM_RSTZ,
+	Y15_1610_CAM_OUTCLK,
+
+	/* serial camera */
+	H19_1610_CAM_EXCLK,
+	Y12_1610_CCP_CLKP,
+	W13_1610_CCP_CLKM,
+	W14_1610_CCP_DATAP,
+	Y14_1610_CCP_DATAM,
+
+};
+
+#ifdef CONFIG_OMAP_MUX
+extern int omap_cfg_reg(unsigned long reg_cfg);
+#else
+static inline int omap_cfg_reg(unsigned long reg_cfg) { return 0; }
+#endif
+
+#endif
diff --git a/include/linux/soc/ti/omap1-soc.h b/include/linux/soc/ti/omap1-soc.h
new file mode 100644
index 000000000000..81008d400bb6
--- /dev/null
+++ b/include/linux/soc/ti/omap1-soc.h
@@ -0,0 +1,198 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * OMAP cpu type detection
+ *
+ * Copyright (C) 2004, 2008 Nokia Corporation
+ *
+ * Copyright (C) 2009-11 Texas Instruments.
+ *
+ * Written by Tony Lindgren <tony.lindgren@nokia.com>
+ *
+ * Added OMAP4/5 specific defines - Santosh Shilimkar<santosh.shilimkar@ti.com>
+ */
+
+#ifndef __ASM_ARCH_OMAP_CPU_H
+#define __ASM_ARCH_OMAP_CPU_H
+
+/*
+ * Test if multicore OMAP support is needed
+ */
+#undef MULTI_OMAP1
+#undef OMAP_NAME
+
+#ifdef CONFIG_ARCH_OMAP730
+# ifdef OMAP_NAME
+#  undef  MULTI_OMAP1
+#  define MULTI_OMAP1
+# else
+#  define OMAP_NAME omap730
+# endif
+#endif
+#ifdef CONFIG_ARCH_OMAP850
+# ifdef OMAP_NAME
+#  undef  MULTI_OMAP1
+#  define MULTI_OMAP1
+# else
+#  define OMAP_NAME omap850
+# endif
+#endif
+#ifdef CONFIG_ARCH_OMAP15XX
+# ifdef OMAP_NAME
+#  undef  MULTI_OMAP1
+#  define MULTI_OMAP1
+# else
+#  define OMAP_NAME omap1510
+# endif
+#endif
+#ifdef CONFIG_ARCH_OMAP16XX
+# ifdef OMAP_NAME
+#  undef  MULTI_OMAP1
+#  define MULTI_OMAP1
+# else
+#  define OMAP_NAME omap16xx
+# endif
+#endif
+
+/*
+ * omap_rev bits:
+ * CPU id bits	(0730, 1510, 1710, 2422...)	[31:16]
+ * CPU revision	(See _REV_ defined in cpu.h)	[15:08]
+ * CPU class bits (15xx, 16xx, 24xx, 34xx...)	[07:00]
+ */
+unsigned int omap_rev(void);
+
+/*
+ * Get the CPU revision for OMAP devices
+ */
+#define GET_OMAP_REVISION()	((omap_rev() >> 8) & 0xff)
+
+/*
+ * Macros to group OMAP into cpu classes.
+ * These can be used in most places.
+ * cpu_is_omap7xx():	True for OMAP730, OMAP850
+ * cpu_is_omap15xx():	True for OMAP1510, OMAP5910 and OMAP310
+ * cpu_is_omap16xx():	True for OMAP1610, OMAP5912 and OMAP1710
+ */
+#define GET_OMAP_CLASS	(omap_rev() & 0xff)
+
+#define IS_OMAP_CLASS(class, id)			\
+static inline int is_omap ##class (void)		\
+{							\
+	return (GET_OMAP_CLASS == (id)) ? 1 : 0;	\
+}
+
+#define GET_OMAP_SUBCLASS	((omap_rev() >> 20) & 0x0fff)
+
+#define IS_OMAP_SUBCLASS(subclass, id)			\
+static inline int is_omap ##subclass (void)		\
+{							\
+	return (GET_OMAP_SUBCLASS == (id)) ? 1 : 0;	\
+}
+
+IS_OMAP_CLASS(7xx, 0x07)
+IS_OMAP_CLASS(15xx, 0x15)
+IS_OMAP_CLASS(16xx, 0x16)
+
+#define cpu_is_omap7xx()		0
+#define cpu_is_omap15xx()		0
+#define cpu_is_omap16xx()		0
+
+#if defined(MULTI_OMAP1)
+# if defined(CONFIG_ARCH_OMAP730)
+#  undef  cpu_is_omap7xx
+#  define cpu_is_omap7xx()		is_omap7xx()
+# endif
+# if defined(CONFIG_ARCH_OMAP850)
+#  undef  cpu_is_omap7xx
+#  define cpu_is_omap7xx()		is_omap7xx()
+# endif
+# if defined(CONFIG_ARCH_OMAP15XX)
+#  undef  cpu_is_omap15xx
+#  define cpu_is_omap15xx()		is_omap15xx()
+# endif
+# if defined(CONFIG_ARCH_OMAP16XX)
+#  undef  cpu_is_omap16xx
+#  define cpu_is_omap16xx()		is_omap16xx()
+# endif
+#else
+# if defined(CONFIG_ARCH_OMAP730)
+#  undef  cpu_is_omap7xx
+#  define cpu_is_omap7xx()		1
+# endif
+# if defined(CONFIG_ARCH_OMAP850)
+#  undef  cpu_is_omap7xx
+#  define cpu_is_omap7xx()		1
+# endif
+# if defined(CONFIG_ARCH_OMAP15XX)
+#  undef  cpu_is_omap15xx
+#  define cpu_is_omap15xx()		1
+# endif
+# if defined(CONFIG_ARCH_OMAP16XX)
+#  undef  cpu_is_omap16xx
+#  define cpu_is_omap16xx()		1
+# endif
+#endif
+
+/*
+ * Macros to detect individual cpu types.
+ * These are only rarely needed.
+ * cpu_is_omap310():	True for OMAP310
+ * cpu_is_omap1510():	True for OMAP1510
+ * cpu_is_omap1610():	True for OMAP1610
+ * cpu_is_omap1611():	True for OMAP1611
+ * cpu_is_omap5912():	True for OMAP5912
+ * cpu_is_omap1621():	True for OMAP1621
+ * cpu_is_omap1710():	True for OMAP1710
+ */
+#define GET_OMAP_TYPE	((omap_rev() >> 16) & 0xffff)
+
+#define IS_OMAP_TYPE(type, id)				\
+static inline int is_omap ##type (void)			\
+{							\
+	return (GET_OMAP_TYPE == (id)) ? 1 : 0;		\
+}
+
+IS_OMAP_TYPE(310, 0x0310)
+IS_OMAP_TYPE(1510, 0x1510)
+IS_OMAP_TYPE(1610, 0x1610)
+IS_OMAP_TYPE(1611, 0x1611)
+IS_OMAP_TYPE(5912, 0x1611)
+IS_OMAP_TYPE(1621, 0x1621)
+IS_OMAP_TYPE(1710, 0x1710)
+
+#define cpu_is_omap310()		0
+#define cpu_is_omap1510()		0
+#define cpu_is_omap1610()		0
+#define cpu_is_omap5912()		0
+#define cpu_is_omap1611()		0
+#define cpu_is_omap1621()		0
+#define cpu_is_omap1710()		0
+
+#define cpu_class_is_omap1()		1
+
+/*
+ * Whether we have MULTI_OMAP1 or not, we still need to distinguish
+ * between 310 vs. 1510 and 1611B/5912 vs. 1710.
+ */
+
+#if defined(CONFIG_ARCH_OMAP15XX)
+# undef  cpu_is_omap310
+# undef  cpu_is_omap1510
+# define cpu_is_omap310()		is_omap310()
+# define cpu_is_omap1510()		is_omap1510()
+#endif
+
+#if defined(CONFIG_ARCH_OMAP16XX)
+# undef  cpu_is_omap1610
+# undef  cpu_is_omap1611
+# undef  cpu_is_omap5912
+# undef  cpu_is_omap1621
+# undef  cpu_is_omap1710
+# define cpu_is_omap1610()		is_omap1610()
+# define cpu_is_omap1611()		is_omap1611()
+# define cpu_is_omap5912()		is_omap5912()
+# define cpu_is_omap1621()		is_omap1621()
+# define cpu_is_omap1710()		is_omap1710()
+#endif
+
+#endif
-- 
cgit v1.2.3


From 9fe15316563cbd46601c770a7214ccc5e1925bfb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 6 Aug 2019 15:13:18 +0200
Subject: ARM: omap1: innovator: move ohci phy power handling to board file

The innovator board needs a special case for its phy control.

Move the corresponding code into the board file and out of the
common code by adding another callback.

Acked-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-omap1/board-innovator.c   | 19 +++++++++++++++++++
 drivers/usb/host/ohci-omap.c            | 31 +++++--------------------------
 include/linux/platform_data/usb-omap1.h |  2 ++
 3 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index e7d6735d4701..f169e172421d 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -290,6 +290,23 @@ static void __init innovator_init_smc91x(void)
 }
 
 #ifdef CONFIG_ARCH_OMAP15XX
+/*
+ * Board specific gang-switched transceiver power on/off.
+ */
+static int innovator_omap_ohci_transceiver_power(int on)
+{
+	if (on)
+		__raw_writeb(__raw_readb(INNOVATOR_FPGA_CAM_USB_CONTROL)
+				| ((1 << 5/*usb1*/) | (1 << 3/*usb2*/)),
+			       INNOVATOR_FPGA_CAM_USB_CONTROL);
+	else
+		__raw_writeb(__raw_readb(INNOVATOR_FPGA_CAM_USB_CONTROL)
+				& ~((1 << 5/*usb1*/) | (1 << 3/*usb2*/)),
+			       INNOVATOR_FPGA_CAM_USB_CONTROL);
+
+	return 0;
+}
+
 static struct omap_usb_config innovator1510_usb_config __initdata = {
 	/* for bundled non-standard host and peripheral cables */
 	.hmc_mode	= 4,
@@ -300,6 +317,8 @@ static struct omap_usb_config innovator1510_usb_config __initdata = {
 
 	.register_dev	= 1,
 	.pins[0]	= 2,
+
+	.transceiver_power = innovator_omap_ohci_transceiver_power,
 };
 
 static const struct omap_lcd_config innovator1510_lcd_config __initconst = {
diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c
index 750a90c41a0a..069791d25abb 100644
--- a/drivers/usb/host/ohci-omap.c
+++ b/drivers/usb/host/ohci-omap.c
@@ -67,31 +67,6 @@ static void omap_ohci_clock_power(struct ohci_omap_priv *priv, int on)
 	}
 }
 
-/*
- * Board specific gang-switched transceiver power on/off.
- * NOTE:  OSK supplies power from DC, not battery.
- */
-static int omap_ohci_transceiver_power(struct ohci_omap_priv *priv, int on)
-{
-	if (on) {
-		if (machine_is_omap_innovator() && cpu_is_omap1510())
-			__raw_writeb(__raw_readb(INNOVATOR_FPGA_CAM_USB_CONTROL)
-				| ((1 << 5/*usb1*/) | (1 << 3/*usb2*/)),
-			       INNOVATOR_FPGA_CAM_USB_CONTROL);
-		else if (priv->power)
-			gpiod_set_value_cansleep(priv->power, 0);
-	} else {
-		if (machine_is_omap_innovator() && cpu_is_omap1510())
-			__raw_writeb(__raw_readb(INNOVATOR_FPGA_CAM_USB_CONTROL)
-				& ~((1 << 5/*usb1*/) | (1 << 3/*usb2*/)),
-			       INNOVATOR_FPGA_CAM_USB_CONTROL);
-		else if (priv->power)
-			gpiod_set_value_cansleep(priv->power, 1);
-	}
-
-	return 0;
-}
-
 #ifdef	CONFIG_USB_OTG
 
 static void start_hnp(struct ohci_hcd *ohci)
@@ -202,7 +177,11 @@ static int ohci_omap_reset(struct usb_hcd *hcd)
 	}
 
 	/* FIXME hub_wq hub requests should manage power switching */
-	omap_ohci_transceiver_power(priv, 1);
+	if (config->transceiver_power)
+		return config->transceiver_power(1);
+
+	if (priv->power)
+		gpiod_set_value_cansleep(priv->power, 0);
 
 	/* board init will have already handled HMC and mux setup.
 	 * any external transceiver should already be initialized
diff --git a/include/linux/platform_data/usb-omap1.h b/include/linux/platform_data/usb-omap1.h
index 878e572a78bf..e7b8dc92a269 100644
--- a/include/linux/platform_data/usb-omap1.h
+++ b/include/linux/platform_data/usb-omap1.h
@@ -50,6 +50,8 @@ struct omap_usb_config {
 	int (*ocpi_enable)(void);
 
 	void (*lb_reset)(void);
+
+	int (*transceiver_power)(int on);
 };
 
 #endif /* __LINUX_USB_OMAP1_H */
-- 
cgit v1.2.3


From 17ea03b75e5665c9ce4945aa5afd097f3c845cdf Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 27 Nov 2020 15:46:47 +0100
Subject: ARM: omap: dma: make usb support optional

Most of the plat-omap/dma.c code is specific to the USB
driver. Hide that code when it is not in use, to make it
clearer which parts are actually still required.

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/plat-omap/dma.c       | 45 +++++++++++++++++++++---------------------
 drivers/usb/gadget/udc/Kconfig |  2 +-
 include/linux/omap-dma.h       |  5 ++++-
 3 files changed, 27 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index 700ba9b600e7..b7757864d0aa 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -66,7 +66,6 @@ enum { DMA_CHAIN_STARTED, DMA_CHAIN_NOTSTARTED };
 
 static struct omap_system_dma_plat_info *p;
 static struct omap_dma_dev_attr *d;
-static void omap_clear_dma(int lch);
 static int enable_1510_mode;
 static u32 errata;
 
@@ -90,19 +89,16 @@ static int omap_dma_reserve_channels;
 static DEFINE_SPINLOCK(dma_chan_lock);
 static struct omap_dma_lch *dma_chan;
 
-static inline void disable_lnk(int lch);
-static void omap_disable_channel_irq(int lch);
-static inline void omap_enable_channel_irq(int lch);
-
-#ifdef CONFIG_ARCH_OMAP15XX
-/* Returns 1 if the DMA module is in OMAP1510-compatible mode, 0 otherwise */
-static int omap_dma_in_1510_mode(void)
+static inline void omap_disable_channel_irq(int lch)
 {
-	return enable_1510_mode;
+	/* disable channel interrupts */
+	p->dma_write(0, CICR, lch);
+	/* Clear CSR */
+	if (dma_omap1())
+		p->dma_read(CSR, lch);
+	else
+		p->dma_write(OMAP2_DMA_CSR_CLEAR_MASK, CSR, lch);
 }
-#else
-#define omap_dma_in_1510_mode()		0
-#endif
 
 #ifdef CONFIG_ARCH_OMAP1
 static inline void set_gdma_dev(int req, int dev)
@@ -169,6 +165,17 @@ void omap_set_dma_priority(int lch, int dst_port, int priority)
 #endif
 EXPORT_SYMBOL(omap_set_dma_priority);
 
+#if IS_ENABLED(CONFIG_USB_OMAP)
+#ifdef CONFIG_ARCH_OMAP15XX
+/* Returns 1 if the DMA module is in OMAP1510-compatible mode, 0 otherwise */
+static int omap_dma_in_1510_mode(void)
+{
+	return enable_1510_mode;
+}
+#else
+#define omap_dma_in_1510_mode()		0
+#endif
+
 void omap_set_dma_transfer_params(int lch, int data_type, int elem_count,
 				  int frame_count, int sync_mode,
 				  int dma_trigger, int src_or_dst_synch)
@@ -418,17 +425,6 @@ static inline void omap_enable_channel_irq(int lch)
 	p->dma_write(dma_chan[lch].enabled_irqs, CICR, lch);
 }
 
-static inline void omap_disable_channel_irq(int lch)
-{
-	/* disable channel interrupts */
-	p->dma_write(0, CICR, lch);
-	/* Clear CSR */
-	if (dma_omap1())
-		p->dma_read(CSR, lch);
-	else
-		p->dma_write(OMAP2_DMA_CSR_CLEAR_MASK, CSR, lch);
-}
-
 void omap_disable_dma_irq(int lch, u16 bits)
 {
 	dma_chan[lch].enabled_irqs &= ~bits;
@@ -473,6 +469,7 @@ static inline void disable_lnk(int lch)
 	p->dma_write(l, CLNK_CTRL, lch);
 	dma_chan[lch].flags &= ~OMAP_DMA_ACTIVE;
 }
+#endif
 
 int omap_request_dma(int dev_id, const char *dev_name,
 		     void (*callback)(int lch, u16 ch_status, void *data),
@@ -572,6 +569,7 @@ static void omap_clear_dma(int lch)
 	local_irq_restore(flags);
 }
 
+#if IS_ENABLED(CONFIG_USB_OMAP)
 void omap_start_dma(int lch)
 {
 	u32 l;
@@ -792,6 +790,7 @@ int omap_get_dma_active_status(int lch)
 	return (p->dma_read(CCR, lch) & OMAP_DMA_CCR_EN) != 0;
 }
 EXPORT_SYMBOL(omap_get_dma_active_status);
+#endif
 
 int omap_dma_running(void)
 {
diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig
index cee934dce4f0..69394dc1cdfb 100644
--- a/drivers/usb/gadget/udc/Kconfig
+++ b/drivers/usb/gadget/udc/Kconfig
@@ -128,7 +128,7 @@ config USB_GR_UDC
 
 config USB_OMAP
 	tristate "OMAP USB Device Controller"
-	depends on ARCH_OMAP1 || (ARCH_OMAP && COMPILE_TEST)
+	depends on ARCH_OMAP1
 	depends on ISP1301_OMAP || !(MACH_OMAP_H2 || MACH_OMAP_H3)
 	help
 	   Many Texas Instruments OMAP processors have flexible full
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 5e228428fda1..07fa58ae9902 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -299,8 +299,9 @@ extern void omap_set_dma_priority(int lch, int dst_port, int priority);
 extern int omap_request_dma(int dev_id, const char *dev_name,
 			void (*callback)(int lch, u16 ch_status, void *data),
 			void *data, int *dma_ch);
-extern void omap_disable_dma_irq(int ch, u16 irq_bits);
 extern void omap_free_dma(int ch);
+#if IS_ENABLED(CONFIG_USB_OMAP)
+extern void omap_disable_dma_irq(int ch, u16 irq_bits);
 extern void omap_start_dma(int lch);
 extern void omap_stop_dma(int lch);
 extern void omap_set_dma_transfer_params(int lch, int data_type,
@@ -326,6 +327,8 @@ extern void omap_set_dma_dest_burst_mode(int lch,
 extern dma_addr_t omap_get_dma_src_pos(int lch);
 extern dma_addr_t omap_get_dma_dst_pos(int lch);
 extern int omap_get_dma_active_status(int lch);
+#endif
+
 extern int omap_dma_running(void);
 
 #if IS_ENABLED(CONFIG_FB_OMAP)
-- 
cgit v1.2.3


From 3550bba25d5587a701e6edf20e20984d2ee72c78 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Sat, 9 Apr 2022 11:51:28 +0200
Subject: gpiolib: of: Introduce hook for missing gpio-ranges

Since commit 2ab73c6d8323 ("gpio: Support GPIO controllers without pin-ranges")
the device tree nodes of GPIO controller need the gpio-ranges property to
handle gpio-hogs. Unfortunately it's impossible to guarantee that every new
kernel is shipped with an updated device tree binary.

In order to provide backward compatibility with those older DTB, we need a
callback within of_gpiochip_add_pin_range() so the relevant platform driver
can handle this case.

Fixes: 2ab73c6d8323 ("gpio: Support GPIO controllers without pin-ranges")
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Bartosz Golaszewski <brgl@bgdev.pl>
Link: https://lore.kernel.org/r/20220409095129.45786-2-stefan.wahren@i2se.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-of.c   |  5 +++++
 include/linux/gpio/driver.h | 12 ++++++++++++
 2 files changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index ae1ce319cd78..d9b235c88b54 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -931,6 +931,11 @@ static int of_gpiochip_add_pin_range(struct gpio_chip *chip)
 	if (!np)
 		return 0;
 
+	if (!of_property_read_bool(np, "gpio-ranges") &&
+	    chip->of_gpio_ranges_fallback) {
+		return chip->of_gpio_ranges_fallback(chip, np);
+	}
+
 	group_names = of_find_property(np, group_names_propname, NULL);
 
 	for (;; index++) {
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 98c93510640e..c2041bd01f90 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -492,6 +492,18 @@ struct gpio_chip {
 	 */
 	int (*of_xlate)(struct gpio_chip *gc,
 			const struct of_phandle_args *gpiospec, u32 *flags);
+
+	/**
+	 * @of_gpio_ranges_fallback:
+	 *
+	 * Optional hook for the case that no gpio-ranges property is defined
+	 * within the device tree node "np" (usually DT before introduction
+	 * of gpio-ranges). So this callback is helpful to provide the
+	 * necessary backward compatibility for the pin ranges.
+	 */
+	int (*of_gpio_ranges_fallback)(struct gpio_chip *gc,
+				       struct device_node *np);
+
 #endif /* CONFIG_OF_GPIO */
 };
 
-- 
cgit v1.2.3


From 988f11e046401f8561c4afefa506a50f0203de40 Mon Sep 17 00:00:00 2001
From: liaohua <liaohua4@huawei.com>
Date: Thu, 7 Apr 2022 15:29:48 +0800
Subject: latencytop: move sysctl to its own file

This moves latencytop sysctl to kernel/latencytop.c

Signed-off-by: liaohua <liaohua4@huawei.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/latencytop.h |  3 ---
 kernel/latencytop.c        | 41 +++++++++++++++++++++++++++++------------
 kernel/sysctl.c            | 10 ----------
 3 files changed, 29 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h
index abe3d95f795b..84f1053cf2a8 100644
--- a/include/linux/latencytop.h
+++ b/include/linux/latencytop.h
@@ -38,9 +38,6 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter)
 
 void clear_tsk_latency_tracing(struct task_struct *p);
 
-int sysctl_latencytop(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
-
 #else
 
 static inline void
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 166d7bf49666..76166df011a4 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -55,6 +55,7 @@
 #include <linux/sched/stat.h>
 #include <linux/list.h>
 #include <linux/stacktrace.h>
+#include <linux/sysctl.h>
 
 static DEFINE_RAW_SPINLOCK(latency_lock);
 
@@ -63,6 +64,31 @@ static struct latency_record latency_record[MAXLR];
 
 int latencytop_enabled;
 
+#ifdef CONFIG_SYSCTL
+static int sysctl_latencytop(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
+{
+	int err;
+
+	err = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (latencytop_enabled)
+		force_schedstat_enabled();
+
+	return err;
+}
+
+static struct ctl_table latencytop_sysctl[] = {
+	{
+		.procname   = "latencytop",
+		.data       = &latencytop_enabled,
+		.maxlen     = sizeof(int),
+		.mode       = 0644,
+		.proc_handler   = sysctl_latencytop,
+	},
+	{}
+};
+#endif
+
 void clear_tsk_latency_tracing(struct task_struct *p)
 {
 	unsigned long flags;
@@ -266,18 +292,9 @@ static const struct proc_ops lstats_proc_ops = {
 static int __init init_lstats_procfs(void)
 {
 	proc_create("latency_stats", 0644, NULL, &lstats_proc_ops);
+#ifdef CONFIG_SYSCTL
+	register_sysctl_init("kernel", latencytop_sysctl);
+#endif
 	return 0;
 }
-
-int sysctl_latencytop(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos)
-{
-	int err;
-
-	err = proc_dointvec(table, write, buffer, lenp, ppos);
-	if (latencytop_enabled)
-		force_schedstat_enabled();
-
-	return err;
-}
 device_initcall(init_lstats_procfs);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c0fdf465a93d..b60345cbadf0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -64,7 +64,6 @@
 #include <linux/kexec.h>
 #include <linux/mount.h>
 #include <linux/userfaultfd_k.h>
-#include <linux/latencytop.h>
 #include <linux/pid.h>
 
 #include "../lib/kstrtox.h"
@@ -1623,15 +1622,6 @@ static struct ctl_table kern_table[] = {
 		.extra1		= SYSCTL_NEG_ONE,
 		.extra2		= SYSCTL_ONE,
 	},
-#endif
-#ifdef CONFIG_LATENCYTOP
-	{
-		.procname	= "latencytop",
-		.data		= &latencytop_enabled,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= sysctl_latencytop,
-	},
 #endif
 	{
 		.procname	= "print-fatal-signals",
-- 
cgit v1.2.3


From 52ef8efcb75e8a8aab88e74c1376c2785d9a5452 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sat, 2 Apr 2022 00:28:23 +0200
Subject: dma: omap: hide legacy interface

The legacy interface for omap-dma is only used on OMAP1, and the
same is true for the non-DT case. Make both of these conditional on
CONFIG_ARCH_OMAP1 being set to simplify the dependency.

The non-OMAP stub functions in include/linux/omap-dma.h are note needed
any more either now, because they are only called on OMAP1.

Acked-by: Tony Lindgren <tony@atomide.com>
Acked-By: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/dma/ti/omap-dma.c | 19 +++++++++++++------
 include/linux/omap-dma.h  | 22 ----------------------
 2 files changed, 13 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index 8e52a0dc1f78..27f5019bdc1e 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -699,6 +699,11 @@ static void omap_dma_put_lch(struct omap_dmadev *od, int lch)
 	mutex_unlock(&od->lch_lock);
 }
 
+static inline bool omap_dma_legacy(struct omap_dmadev *od)
+{
+	return IS_ENABLED(CONFIG_ARCH_OMAP1) && od->legacy;
+}
+
 static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
@@ -706,7 +711,7 @@ static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 	struct device *dev = od->ddev.dev;
 	int ret;
 
-	if (od->legacy) {
+	if (omap_dma_legacy(od)) {
 		ret = omap_request_dma(c->dma_sig, "DMA engine",
 				       omap_dma_callback, c, &c->dma_ch);
 	} else {
@@ -718,7 +723,7 @@ static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 	if (ret >= 0) {
 		omap_dma_assign(od, c, c->dma_ch);
 
-		if (!od->legacy) {
+		if (!omap_dma_legacy(od)) {
 			unsigned val;
 
 			spin_lock_irq(&od->irq_lock);
@@ -757,7 +762,7 @@ static void omap_dma_free_chan_resources(struct dma_chan *chan)
 	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
 	struct omap_chan *c = to_omap_dma_chan(chan);
 
-	if (!od->legacy) {
+	if (!omap_dma_legacy(od)) {
 		spin_lock_irq(&od->irq_lock);
 		od->irq_enable_mask &= ~BIT(c->dma_ch);
 		omap_dma_glbl_write(od, IRQENABLE_L1, od->irq_enable_mask);
@@ -768,7 +773,7 @@ static void omap_dma_free_chan_resources(struct dma_chan *chan)
 	od->lch_map[c->dma_ch] = NULL;
 	vchan_free_chan_resources(&c->vc);
 
-	if (od->legacy)
+	if (omap_dma_legacy(od))
 		omap_free_dma(c->dma_ch);
 	else
 		omap_dma_put_lch(od, c->dma_ch);
@@ -1674,12 +1679,14 @@ static int omap_dma_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "omap_system_dma_plat_info is missing");
 			return -ENODEV;
 		}
-	} else {
+	} else if (IS_ENABLED(CONFIG_ARCH_OMAP1)) {
 		od->cfg = &default_cfg;
 
 		od->plat = omap_get_plat_info();
 		if (!od->plat)
 			return -EPROBE_DEFER;
+	} else {
+		return -ENODEV;
 	}
 
 	od->reg_map = od->plat->reg_map;
@@ -1855,7 +1862,7 @@ static int omap_dma_remove(struct platform_device *pdev)
 
 	dma_async_device_unregister(&od->ddev);
 
-	if (!od->legacy) {
+	if (!omap_dma_legacy(od)) {
 		/* Disable all interrupts */
 		omap_dma_glbl_write(od, IRQENABLE_L0, 0);
 	}
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 07fa58ae9902..254b4e10511b 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -292,7 +292,6 @@ struct omap_system_dma_plat_info {
 #define dma_omap15xx()	__dma_omap15xx(d)
 #define dma_omap16xx()	__dma_omap16xx(d)
 
-#if defined(CONFIG_ARCH_OMAP)
 extern struct omap_system_dma_plat_info *omap_get_plat_info(void);
 
 extern void omap_set_dma_priority(int lch, int dst_port, int priority);
@@ -340,25 +339,4 @@ static inline int omap_lcd_dma_running(void)
 }
 #endif
 
-#else /* CONFIG_ARCH_OMAP */
-static inline void omap_set_dma_priority(int lch, int dst_port, int priority)
-{
-}
-
-static inline struct omap_system_dma_plat_info *omap_get_plat_info(void)
-{
-	return NULL;
-}
-
-static inline int omap_request_dma(int dev_id, const char *dev_name,
-			void (*callback)(int lch, u16 ch_status, void *data),
-			void *data, int *dma_ch)
-{
-	return -ENODEV;
-}
-
-static inline void omap_free_dma(int ch) { }
-
-#endif /* CONFIG_ARCH_OMAP */
-
 #endif /* __LINUX_OMAP_DMA_H */
-- 
cgit v1.2.3


From 615dce5bf7369334f8c4f19f7f8f2a5634b4f911 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 12 Sep 2019 10:11:24 +0200
Subject: ARM: omap1: fix build with no SoC selected

In a multiplatform randconfig kernel, one can have
CONFIG_ARCH_OMAP1 enabled, but none of the specific SoCs.
This leads to some build issues as the code is not
meant to deal with this configuration at the moment:

arch/arm/mach-omap1/io.c:86:20: error: unused function 'omap1_map_common_io' [-Werror,-Wunused-function]
arch/arm/mach-omap1/pm.h:113:2: error: "Power management for this processor not implemented yet" [-Werror,-W#warnings]

Use the same trick as on OMAP2 and guard the actual compilation
of platform code with another Makefile ifdef check based
on an option that depends on having at least one SoC enabled.

The io.c file still needs to get compiled to allow building
device drivers with a dependency on CONFIG_ARCH_OMAP1.

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/Kconfig                | 1 -
 arch/arm/mach-omap1/Kconfig     | 4 ++++
 arch/arm/mach-omap1/Makefile    | 4 ++++
 include/linux/soc/ti/omap1-io.h | 4 ++--
 4 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index fb6afa6bbc8f..a65f2c05f01c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -485,7 +485,6 @@ config ARCH_S3C24XX
 
 config ARCH_OMAP1
 	bool "TI OMAP1"
-	select ARCH_OMAP
 	select CLKSRC_MMIO
 	select FORCE_PCI if PCCARD
 	select GENERIC_IRQ_CHIP
diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig
index 93ea86954a84..d4b0cd91a4f9 100644
--- a/arch/arm/mach-omap1/Kconfig
+++ b/arch/arm/mach-omap1/Kconfig
@@ -28,6 +28,10 @@ config ARCH_OMAP16XX
 	select CPU_ARM926T
 	select OMAP_DM_TIMER
 
+config ARCH_OMAP1_ANY
+	select ARCH_OMAP
+	def_bool ARCH_OMAP730 || ARCH_OMAP850 || ARCH_OMAP15XX || ARCH_OMAP16XX
+
 config ARCH_OMAP
 	bool
 
diff --git a/arch/arm/mach-omap1/Makefile b/arch/arm/mach-omap1/Makefile
index 0615cb0ba580..506074b86333 100644
--- a/arch/arm/mach-omap1/Makefile
+++ b/arch/arm/mach-omap1/Makefile
@@ -3,6 +3,8 @@
 # Makefile for the linux kernel.
 #
 
+ifdef CONFIG_ARCH_OMAP1_ANY
+
 # Common support
 obj-y := io.o id.o sram-init.o sram.o time.o irq.o mux.o flash.o \
 	 serial.o devices.o dma.o omap-dma.o fb.o
@@ -57,3 +59,5 @@ obj-$(CONFIG_ARCH_OMAP730)		+= gpio7xx.o
 obj-$(CONFIG_ARCH_OMAP850)		+= gpio7xx.o
 obj-$(CONFIG_ARCH_OMAP15XX)		+= gpio15xx.o
 obj-$(CONFIG_ARCH_OMAP16XX)		+= gpio16xx.o
+
+endif
diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h
index 9332c92690f4..f7f12728d4a6 100644
--- a/include/linux/soc/ti/omap1-io.h
+++ b/include/linux/soc/ti/omap1-io.h
@@ -5,7 +5,7 @@
 #ifndef __ASSEMBLER__
 #include <linux/types.h>
 
-#if defined(CONFIG_ARCH_OMAP) && defined(CONFIG_ARCH_OMAP1)
+#ifdef CONFIG_ARCH_OMAP1_ANY
 /*
  * NOTE: Please use ioremap + __raw_read/write where possible instead of these
  */
@@ -15,7 +15,7 @@ extern u32 omap_readl(u32 pa);
 extern void omap_writeb(u8 v, u32 pa);
 extern void omap_writew(u16 v, u32 pa);
 extern void omap_writel(u32 v, u32 pa);
-#elif defined(CONFIG_COMPILE_TEST)
+#else
 static inline u8 omap_readb(u32 pa)  { return 0; }
 static inline u16 omap_readw(u32 pa) { return 0; }
 static inline u32 omap_readl(u32 pa) { return 0; }
-- 
cgit v1.2.3


From 78ed93d72ded679e3caf0758357209887bda885f Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Mon, 4 Apr 2022 13:12:04 +0200
Subject: signal: Deliver SIGTRAP on perf event asynchronously if blocked

With SIGTRAP on perf events, we have encountered termination of
processes due to user space attempting to block delivery of SIGTRAP.
Consider this case:

    <set up SIGTRAP on a perf event>
    ...
    sigset_t s;
    sigemptyset(&s);
    sigaddset(&s, SIGTRAP | <and others>);
    sigprocmask(SIG_BLOCK, &s, ...);
    ...
    <perf event triggers>

When the perf event triggers, while SIGTRAP is blocked, force_sig_perf()
will force the signal, but revert back to the default handler, thus
terminating the task.

This makes sense for error conditions, but not so much for explicitly
requested monitoring. However, the expectation is still that signals
generated by perf events are synchronous, which will no longer be the
case if the signal is blocked and delivered later.

To give user space the ability to clearly distinguish synchronous from
asynchronous signals, introduce siginfo_t::si_perf_flags and
TRAP_PERF_FLAG_ASYNC (opted for flags in case more binary information is
required in future).

The resolution to the problem is then to (a) no longer force the signal
(avoiding the terminations), but (b) tell user space via si_perf_flags
if the signal was synchronous or not, so that such signals can be
handled differently (e.g. let user space decide to ignore or consider
the data imprecise).

The alternative of making the kernel ignore SIGTRAP on perf events if
the signal is blocked may work for some usecases, but likely causes
issues in others that then have to revert back to interception of
sigprocmask() (which we want to avoid). [ A concrete example: when using
breakpoint perf events to track data-flow, in a region of code where
signals are blocked, data-flow can no longer be tracked accurately.
When a relevant asynchronous signal is received after unblocking the
signal, the data-flow tracking logic needs to know its state is
imprecise. ]

Fixes: 97ba62b27867 ("perf: Add support for SIGTRAP on perf events")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Link: https://lore.kernel.org/r/20220404111204.935357-1-elver@google.com
---
 arch/arm/kernel/signal.c           |  1 +
 arch/arm64/kernel/signal.c         |  1 +
 arch/arm64/kernel/signal32.c       |  1 +
 arch/m68k/kernel/signal.c          |  1 +
 arch/sparc/kernel/signal32.c       |  1 +
 arch/sparc/kernel/signal_64.c      |  1 +
 arch/x86/kernel/signal_compat.c    |  2 ++
 include/linux/compat.h             |  1 +
 include/linux/sched/signal.h       |  2 +-
 include/uapi/asm-generic/siginfo.h |  7 +++++++
 kernel/events/core.c               |  4 ++--
 kernel/signal.c                    | 18 ++++++++++++++++--
 12 files changed, 35 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 459abc5d1819..ea128e32e8ca 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -708,6 +708,7 @@ static_assert(offsetof(siginfo_t, si_upper)	== 0x18);
 static_assert(offsetof(siginfo_t, si_pkey)	== 0x14);
 static_assert(offsetof(siginfo_t, si_perf_data)	== 0x10);
 static_assert(offsetof(siginfo_t, si_perf_type)	== 0x14);
+static_assert(offsetof(siginfo_t, si_perf_flags) == 0x18);
 static_assert(offsetof(siginfo_t, si_band)	== 0x0c);
 static_assert(offsetof(siginfo_t, si_fd)	== 0x10);
 static_assert(offsetof(siginfo_t, si_call_addr)	== 0x0c);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 4a4122ef6f39..41b5d9d3672a 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -1011,6 +1011,7 @@ static_assert(offsetof(siginfo_t, si_upper)	== 0x28);
 static_assert(offsetof(siginfo_t, si_pkey)	== 0x20);
 static_assert(offsetof(siginfo_t, si_perf_data)	== 0x18);
 static_assert(offsetof(siginfo_t, si_perf_type)	== 0x20);
+static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24);
 static_assert(offsetof(siginfo_t, si_band)	== 0x10);
 static_assert(offsetof(siginfo_t, si_fd)	== 0x18);
 static_assert(offsetof(siginfo_t, si_call_addr)	== 0x10);
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index d984282b979f..4700f8522d27 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -487,6 +487,7 @@ static_assert(offsetof(compat_siginfo_t, si_upper)	== 0x18);
 static_assert(offsetof(compat_siginfo_t, si_pkey)	== 0x14);
 static_assert(offsetof(compat_siginfo_t, si_perf_data)	== 0x10);
 static_assert(offsetof(compat_siginfo_t, si_perf_type)	== 0x14);
+static_assert(offsetof(compat_siginfo_t, si_perf_flags)	== 0x18);
 static_assert(offsetof(compat_siginfo_t, si_band)	== 0x0c);
 static_assert(offsetof(compat_siginfo_t, si_fd)		== 0x10);
 static_assert(offsetof(compat_siginfo_t, si_call_addr)	== 0x0c);
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 49533f65958a..b9f6908a31bc 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -625,6 +625,7 @@ static inline void siginfo_build_tests(void)
 	/* _sigfault._perf */
 	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x10);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x18);
 
 	/* _sigpoll */
 	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x0c);
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index f9fe502b81c6..dad38960d1a8 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -779,5 +779,6 @@ static_assert(offsetof(compat_siginfo_t, si_upper)	== 0x18);
 static_assert(offsetof(compat_siginfo_t, si_pkey)	== 0x14);
 static_assert(offsetof(compat_siginfo_t, si_perf_data)	== 0x10);
 static_assert(offsetof(compat_siginfo_t, si_perf_type)	== 0x14);
+static_assert(offsetof(compat_siginfo_t, si_perf_flags)	== 0x18);
 static_assert(offsetof(compat_siginfo_t, si_band)	== 0x0c);
 static_assert(offsetof(compat_siginfo_t, si_fd)		== 0x10);
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 8b9fc76cd3e0..570e43e6fda5 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -590,5 +590,6 @@ static_assert(offsetof(siginfo_t, si_upper)	== 0x28);
 static_assert(offsetof(siginfo_t, si_pkey)	== 0x20);
 static_assert(offsetof(siginfo_t, si_perf_data)	== 0x18);
 static_assert(offsetof(siginfo_t, si_perf_type)	== 0x20);
+static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24);
 static_assert(offsetof(siginfo_t, si_band)	== 0x10);
 static_assert(offsetof(siginfo_t, si_fd)	== 0x14);
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index b52407c56000..879ef8c72f5c 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -149,8 +149,10 @@ static inline void signal_compat_build_tests(void)
 
 	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18);
 	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x24);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_flags) != 0x18);
 
 	CHECK_CSI_OFFSET(_sigpoll);
 	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 1c758b0e0359..01fddf72a81f 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -235,6 +235,7 @@ typedef struct compat_siginfo {
 				struct {
 					compat_ulong_t _data;
 					u32 _type;
+					u32 _flags;
 				} _perf;
 			};
 		} _sigfault;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 3c8b34876744..bab7cc56b13a 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -320,7 +320,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *);
 
 int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper);
 int force_sig_pkuerr(void __user *addr, u32 pkey);
-int force_sig_perf(void __user *addr, u32 type, u64 sig_data);
+int send_sig_perf(void __user *addr, u32 type, u64 sig_data);
 
 int force_sig_ptrace_errno_trap(int errno, void __user *addr);
 int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno);
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 3ba180f550d7..ffbe4cec9f32 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -99,6 +99,7 @@ union __sifields {
 			struct {
 				unsigned long _data;
 				__u32 _type;
+				__u32 _flags;
 			} _perf;
 		};
 	} _sigfault;
@@ -164,6 +165,7 @@ typedef struct siginfo {
 #define si_pkey		_sifields._sigfault._addr_pkey._pkey
 #define si_perf_data	_sifields._sigfault._perf._data
 #define si_perf_type	_sifields._sigfault._perf._type
+#define si_perf_flags	_sifields._sigfault._perf._flags
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
 #define si_call_addr	_sifields._sigsys._call_addr
@@ -270,6 +272,11 @@ typedef struct siginfo {
  * that are of the form: ((PTRACE_EVENT_XXX << 8) | SIGTRAP)
  */
 
+/*
+ * Flags for si_perf_flags if SIGTRAP si_code is TRAP_PERF.
+ */
+#define TRAP_PERF_FLAG_ASYNC (1u << 0)
+
 /*
  * SIGCHLD si_codes
  */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cfde994ce61c..6eafb1b0ad4a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6533,8 +6533,8 @@ static void perf_sigtrap(struct perf_event *event)
 	if (current->flags & PF_EXITING)
 		return;
 
-	force_sig_perf((void __user *)event->pending_addr,
-		       event->attr.type, event->attr.sig_data);
+	send_sig_perf((void __user *)event->pending_addr,
+		      event->attr.type, event->attr.sig_data);
 }
 
 static void perf_pending_event_disable(struct perf_event *event)
diff --git a/kernel/signal.c b/kernel/signal.c
index 30cd1ca43bcd..e43bc2a692f5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1805,7 +1805,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey)
 }
 #endif
 
-int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
+int send_sig_perf(void __user *addr, u32 type, u64 sig_data)
 {
 	struct kernel_siginfo info;
 
@@ -1817,7 +1817,18 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
 	info.si_perf_data = sig_data;
 	info.si_perf_type = type;
 
-	return force_sig_info(&info);
+	/*
+	 * Signals generated by perf events should not terminate the whole
+	 * process if SIGTRAP is blocked, however, delivering the signal
+	 * asynchronously is better than not delivering at all. But tell user
+	 * space if the signal was asynchronous, so it can clearly be
+	 * distinguished from normal synchronous ones.
+	 */
+	info.si_perf_flags = sigismember(&current->blocked, info.si_signo) ?
+				     TRAP_PERF_FLAG_ASYNC :
+				     0;
+
+	return send_sig_info(info.si_signo, &info, current);
 }
 
 /**
@@ -3432,6 +3443,7 @@ void copy_siginfo_to_external32(struct compat_siginfo *to,
 		to->si_addr = ptr_to_compat(from->si_addr);
 		to->si_perf_data = from->si_perf_data;
 		to->si_perf_type = from->si_perf_type;
+		to->si_perf_flags = from->si_perf_flags;
 		break;
 	case SIL_CHLD:
 		to->si_pid = from->si_pid;
@@ -3509,6 +3521,7 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to,
 		to->si_addr = compat_ptr(from->si_addr);
 		to->si_perf_data = from->si_perf_data;
 		to->si_perf_type = from->si_perf_type;
+		to->si_perf_flags = from->si_perf_flags;
 		break;
 	case SIL_CHLD:
 		to->si_pid    = from->si_pid;
@@ -4722,6 +4735,7 @@ static inline void siginfo_buildtime_checks(void)
 	CHECK_OFFSET(si_pkey);
 	CHECK_OFFSET(si_perf_data);
 	CHECK_OFFSET(si_perf_type);
+	CHECK_OFFSET(si_perf_flags);
 
 	/* sigpoll */
 	CHECK_OFFSET(si_band);
-- 
cgit v1.2.3


From 03f16cd020eb8bb2eb837e2090086f296a9fa91d Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Mon, 18 Apr 2022 09:50:36 -0700
Subject: objtool: Add CONFIG_OBJTOOL

Now that stack validation is an optional feature of objtool, add
CONFIG_OBJTOOL and replace most usages of CONFIG_STACK_VALIDATION with
it.

CONFIG_STACK_VALIDATION can now be considered to be frame-pointer
specific.  CONFIG_UNWINDER_ORC is already inherently valid for live
patching, so no need to "validate" it.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Link: https://lkml.kernel.org/r/939bf3d85604b2a126412bf11af6e3bd3b872bcb.1650300597.git.jpoimboe@redhat.com
---
 Makefile                          |  2 +-
 arch/Kconfig                      |  8 ++++++--
 arch/x86/Kconfig                  | 18 +++++++++++-------
 arch/x86/Kconfig.debug            |  2 +-
 arch/x86/include/asm/jump_label.h |  6 +++---
 arch/x86/kernel/alternative.c     |  6 +++---
 include/linux/compiler.h          |  6 +++---
 include/linux/instrumentation.h   |  6 +++---
 include/linux/objtool.h           |  6 +++---
 kernel/trace/Kconfig              |  1 +
 lib/Kconfig.debug                 | 20 +++++++++++---------
 lib/Kconfig.kcsan                 |  3 ++-
 lib/Kconfig.ubsan                 |  2 +-
 scripts/Makefile.build            |  4 ++--
 scripts/link-vmlinux.sh           | 32 ++++++++++++++++++--------------
 scripts/package/builddeb          |  2 +-
 tools/include/linux/objtool.h     |  6 +++---
 17 files changed, 73 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/Makefile b/Makefile
index fa5112a0ec1b..250707647359 100644
--- a/Makefile
+++ b/Makefile
@@ -1302,7 +1302,7 @@ install: sub_make_done :=
 # ---------------------------------------------------------------------------
 # Tools
 
-ifdef CONFIG_STACK_VALIDATION
+ifdef CONFIG_OBJTOOL
 prepare: tools/objtool
 endif
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 29b0167c088b..04cdef16db24 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1028,11 +1028,14 @@ config ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	depends on MMU
 	select ARCH_HAS_ELF_RANDOMIZE
 
+config HAVE_OBJTOOL
+	bool
+
 config HAVE_STACK_VALIDATION
 	bool
 	help
-	  Architecture supports the 'objtool check' host tool command, which
-	  performs compile-time stack metadata validation.
+	  Architecture supports objtool compile-time frame pointer rule
+	  validation.
 
 config HAVE_RELIABLE_STACKTRACE
 	bool
@@ -1302,6 +1305,7 @@ config HAVE_STATIC_CALL
 config HAVE_STATIC_CALL_INLINE
 	bool
 	depends on HAVE_STATIC_CALL
+	select OBJTOOL
 
 config HAVE_PREEMPT_DYNAMIC
 	bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4bed3abf444d..43e26ee1611e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -188,7 +188,7 @@ config X86
 	select HAVE_CONTEXT_TRACKING		if X86_64
 	select HAVE_CONTEXT_TRACKING_OFFSTACK	if HAVE_CONTEXT_TRACKING
 	select HAVE_C_RECORDMCOUNT
-	select HAVE_OBJTOOL_MCOUNT		if STACK_VALIDATION
+	select HAVE_OBJTOOL_MCOUNT		if HAVE_OBJTOOL
 	select HAVE_BUILDTIME_MCOUNT_SORT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
@@ -231,6 +231,7 @@ config X86
 	select HAVE_MOVE_PMD
 	select HAVE_MOVE_PUD
 	select HAVE_NMI
+	select HAVE_OBJTOOL			if X86_64
 	select HAVE_OPTPROBES
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
@@ -239,17 +240,17 @@ config X86
 	select HAVE_PCI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select MMU_GATHER_RCU_TABLE_FREE		if PARAVIRT
+	select MMU_GATHER_RCU_TABLE_FREE	if PARAVIRT
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
+	select HAVE_RELIABLE_STACKTRACE		if UNWINDER_ORC || STACK_VALIDATION
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_SETUP_PER_CPU_AREA
 	select HAVE_SOFTIRQ_ON_OWN_STACK
 	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
-	select HAVE_STACK_VALIDATION		if X86_64
+	select HAVE_STACK_VALIDATION		if HAVE_OBJTOOL
 	select HAVE_STATIC_CALL
-	select HAVE_STATIC_CALL_INLINE		if HAVE_STACK_VALIDATION
+	select HAVE_STATIC_CALL_INLINE		if HAVE_OBJTOOL
 	select HAVE_PREEMPT_DYNAMIC_CALL
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -268,7 +269,6 @@ config X86
 	select RTC_MC146818_LIB
 	select SPARSE_IRQ
 	select SRCU
-	select STACK_VALIDATION			if HAVE_STACK_VALIDATION && (HAVE_STATIC_CALL_INLINE || RETPOLINE)
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
 	select TRACE_IRQFLAGS_SUPPORT
@@ -459,6 +459,7 @@ config GOLDFISH
 
 config RETPOLINE
 	bool "Avoid speculative indirect branches in kernel"
+	select OBJTOOL if HAVE_OBJTOOL
 	default y
 	help
 	  Compile kernel with the retpoline compiler options to guard against
@@ -472,6 +473,7 @@ config CC_HAS_SLS
 config SLS
 	bool "Mitigate Straight-Line-Speculation"
 	depends on CC_HAS_SLS && X86_64
+	select OBJTOOL if HAVE_OBJTOOL
 	default n
 	help
 	  Compile the kernel with straight-line-speculation options to guard
@@ -1819,6 +1821,7 @@ config ARCH_RANDOM
 config X86_SMAP
 	def_bool y
 	prompt "Supervisor Mode Access Prevention" if EXPERT
+	select OBJTOOL if HAVE_OBJTOOL
 	help
 	  Supervisor Mode Access Prevention (SMAP) is a security
 	  feature in newer Intel processors.  There is a small
@@ -1855,9 +1858,10 @@ config CC_HAS_IBT
 config X86_KERNEL_IBT
 	prompt "Indirect Branch Tracking"
 	bool
-	depends on X86_64 && CC_HAS_IBT && STACK_VALIDATION
+	depends on X86_64 && CC_HAS_IBT && HAVE_OBJTOOL
 	# https://github.com/llvm/llvm-project/commit/9d7001eba9c4cb311e03cd8cdc231f9e579f2d0f
 	depends on !LD_IS_LLD || LLD_VERSION >= 140000
+	select OBJTOOL
 	help
 	  Build the kernel with support for Indirect Branch Tracking, a
 	  hardware support course-grain forward-edge Control Flow Integrity
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index d3a6f74a94bd..d872a7522e55 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -237,7 +237,7 @@ choice
 config UNWINDER_ORC
 	bool "ORC unwinder"
 	depends on X86_64
-	select STACK_VALIDATION
+	select OBJTOOL
 	help
 	  This option enables the ORC (Oops Rewind Capability) unwinder for
 	  unwinding kernel stack traces.  It uses a custom data format which is
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 0449b125d27f..3ce0e67c579c 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -20,7 +20,7 @@
 	_ASM_PTR "%c0 + %c1 - .\n\t"			\
 	".popsection \n\t"
 
-#ifdef CONFIG_STACK_VALIDATION
+#ifdef CONFIG_OBJTOOL
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
@@ -34,7 +34,7 @@ l_yes:
 	return true;
 }
 
-#else
+#else /* !CONFIG_OBJTOOL */
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
@@ -48,7 +48,7 @@ l_yes:
 	return true;
 }
 
-#endif /* STACK_VALIDATION */
+#endif /* CONFIG_OBJTOOL */
 
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index d374cb3cf024..3c66073e7645 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -338,7 +338,7 @@ next:
 	}
 }
 
-#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION)
+#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL)
 
 /*
  * CALL/JMP *%\reg
@@ -507,11 +507,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 	}
 }
 
-#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */
+#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */
 
 void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
 
-#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */
+#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 219aa5ddbc73..01ce94b58b42 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -109,7 +109,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #endif
 
 /* Unreachable code */
-#ifdef CONFIG_STACK_VALIDATION
+#ifdef CONFIG_OBJTOOL
 /*
  * These macros help objtool understand GCC code flow for unreachable code.
  * The __COUNTER__ based labels are a hack to make each instance of the macros
@@ -128,10 +128,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 /* Annotate a C jump table to allow objtool to follow the code flow */
 #define __annotate_jump_table __section(".rodata..c_jump_table")
 
-#else
+#else /* !CONFIG_OBJTOOL */
 #define annotate_unreachable()
 #define __annotate_jump_table
-#endif
+#endif /* CONFIG_OBJTOOL */
 
 #ifndef unreachable
 # define unreachable() do {		\
diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h
index 24359b4a9605..9111a3704072 100644
--- a/include/linux/instrumentation.h
+++ b/include/linux/instrumentation.h
@@ -2,7 +2,7 @@
 #ifndef __LINUX_INSTRUMENTATION_H
 #define __LINUX_INSTRUMENTATION_H
 
-#if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION)
+#ifdef CONFIG_VMLINUX_VALIDATION
 
 #include <linux/stringify.h>
 
@@ -53,9 +53,9 @@
 		     ".popsection\n\t" : : "i" (c));			\
 })
 #define instrumentation_end() __instrumentation_end(__COUNTER__)
-#else
+#else /* !CONFIG_VMLINUX_VALIDATION */
 # define instrumentation_begin()	do { } while(0)
 # define instrumentation_end()		do { } while(0)
-#endif
+#endif /* CONFIG_VMLINUX_VALIDATION */
 
 #endif /* __LINUX_INSTRUMENTATION_H */
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 586d35720f13..977d90ba642d 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -38,7 +38,7 @@ struct unwind_hint {
 #define UNWIND_HINT_TYPE_REGS_PARTIAL	2
 #define UNWIND_HINT_TYPE_FUNC		3
 
-#ifdef CONFIG_STACK_VALIDATION
+#ifdef CONFIG_OBJTOOL
 
 #ifndef __ASSEMBLY__
 
@@ -157,7 +157,7 @@ struct unwind_hint {
 
 #endif /* __ASSEMBLY__ */
 
-#else /* !CONFIG_STACK_VALIDATION */
+#else /* !CONFIG_OBJTOOL */
 
 #ifndef __ASSEMBLY__
 
@@ -179,6 +179,6 @@ struct unwind_hint {
 .endm
 #endif
 
-#endif /* CONFIG_STACK_VALIDATION */
+#endif /* CONFIG_OBJTOOL */
 
 #endif /* _LINUX_OBJTOOL_H */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2c43e327a619..2956bc277150 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -728,6 +728,7 @@ config FTRACE_MCOUNT_USE_OBJTOOL
 	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
 	depends on !FTRACE_MCOUNT_USE_CC
 	depends on FTRACE_MCOUNT_RECORD
+	select OBJTOOL
 
 config FTRACE_MCOUNT_USE_RECORDMCOUNT
 	def_bool y
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 075cd25363ac..c0e4e47f3ce3 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -485,24 +485,25 @@ config FRAME_POINTER
 	  larger and slower, but it gives very useful debugging information
 	  in case of kernel bugs. (precise oopses/stacktraces/warnings)
 
+config OBJTOOL
+	bool
+
 config STACK_VALIDATION
 	bool "Compile-time stack metadata validation"
-	depends on HAVE_STACK_VALIDATION
+	depends on HAVE_STACK_VALIDATION && UNWINDER_FRAME_POINTER
+	select OBJTOOL
 	default n
 	help
-	  Add compile-time checks to validate stack metadata, including frame
-	  pointers (if CONFIG_FRAME_POINTER is enabled).  This helps ensure
-	  that runtime stack traces are more reliable.
-
-	  This is also a prerequisite for generation of ORC unwind data, which
-	  is needed for CONFIG_UNWINDER_ORC.
+	  Validate frame pointer rules at compile-time.  This helps ensure that
+	  runtime stack traces are more reliable.
 
 	  For more information, see
 	  tools/objtool/Documentation/stack-validation.txt.
 
 config VMLINUX_VALIDATION
 	bool
-	depends on STACK_VALIDATION && DEBUG_ENTRY
+	depends on HAVE_OBJTOOL && DEBUG_ENTRY
+	select OBJTOOL
 	default y
 
 config VMLINUX_MAP
@@ -2035,10 +2036,11 @@ config KCOV
 	bool "Code coverage for fuzzing"
 	depends on ARCH_HAS_KCOV
 	depends on CC_HAS_SANCOV_TRACE_PC || GCC_PLUGINS
-	depends on !ARCH_WANTS_NO_INSTR || STACK_VALIDATION || \
+	depends on !ARCH_WANTS_NO_INSTR || HAVE_OBJTOOL || \
 		   GCC_VERSION >= 120000 || CLANG_VERSION >= 130000
 	select DEBUG_FS
 	select GCC_PLUGIN_SANCOV if !CC_HAS_SANCOV_TRACE_PC
+	select OBJTOOL if HAVE_OBJTOOL
 	help
 	  KCOV exposes kernel code coverage information in a form suitable
 	  for coverage-guided fuzzing (randomized testing).
diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan
index de022445fbba..901c3b509aca 100644
--- a/lib/Kconfig.kcsan
+++ b/lib/Kconfig.kcsan
@@ -187,7 +187,8 @@ config KCSAN_WEAK_MEMORY
 	# We can either let objtool nop __tsan_func_{entry,exit}() and builtin
 	# atomics instrumentation in .noinstr.text, or use a compiler that can
 	# implement __no_kcsan to really remove all instrumentation.
-	depends on STACK_VALIDATION || CC_IS_GCC || CLANG_VERSION >= 140000
+	depends on HAVE_OBJTOOL || CC_IS_GCC || CLANG_VERSION >= 140000
+	select OBJTOOL if HAVE_OBJTOOL
 	help
 	  Enable support for modeling a subset of weak memory, which allows
 	  detecting a subset of data races due to missing memory barriers.
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index f3c57ed51838..c4fe15d38b60 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -94,7 +94,7 @@ config UBSAN_UNREACHABLE
 	bool "Perform checking for unreachable code"
 	# objtool already handles unreachable checking and gets angry about
 	# seeing UBSan instrumentation located in unreachable places.
-	depends on !STACK_VALIDATION
+	depends on !(OBJTOOL && (STACK_VALIDATION || UNWINDER_ORC || X86_SMAP))
 	depends on $(cc-option,-fsanitize=unreachable)
 	help
 	  This option enables -fsanitize=unreachable which checks for control
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index d5e15ae29156..0f73e02b7cf1 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -222,7 +222,7 @@ cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)),
 	$(sub_cmd_record_mcount))
 endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
 
-ifdef CONFIG_STACK_VALIDATION
+ifdef CONFIG_OBJTOOL
 
 objtool := $(objtree)/tools/objtool/objtool
 
@@ -241,7 +241,7 @@ objtool_args =								\
 cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool_args) $@)
 cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd)
 
-endif # CONFIG_STACK_VALIDATION
+endif # CONFIG_OBJTOOL
 
 ifneq ($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT),)
 
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 0140bfa32c0c..5101a7fbfaaf 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -108,8 +108,11 @@ objtool_link()
 	local objtoolcmd;
 	local objtoolopt;
 
-	if is_enabled CONFIG_STACK_VALIDATION && \
-	   ( is_enabled CONFIG_LTO_CLANG || is_enabled CONFIG_X86_KERNEL_IBT ); then
+	if ! is_enabled CONFIG_OBJTOOL; then
+		return;
+	fi
+
+	if is_enabled CONFIG_LTO_CLANG || is_enabled CONFIG_X86_KERNEL_IBT; then
 
 		# Don't perform vmlinux validation unless explicitly requested,
 		# but run objtool on vmlinux.o now that we have an object file.
@@ -126,10 +129,23 @@ objtool_link()
 			objtoolopt="${objtoolopt} --orc"
 		fi
 
+		if is_enabled CONFIG_RETPOLINE; then
+			objtoolopt="${objtoolopt} --retpoline"
+		fi
+
+		if is_enabled CONFIG_SLS; then
+			objtoolopt="${objtoolopt} --sls"
+		fi
+
 		if is_enabled CONFIG_STACK_VALIDATION; then
 			objtoolopt="${objtoolopt} --stackval"
 		fi
 
+		if is_enabled CONFIG_X86_SMAP; then
+			objtoolopt="${objtoolopt} --uaccess"
+		fi
+
+
 		objtoolopt="${objtoolopt} --lto"
 	fi
 
@@ -139,18 +155,6 @@ objtool_link()
 
 	if [ -n "${objtoolopt}" ]; then
 
-		if is_enabled CONFIG_RETPOLINE; then
-			objtoolopt="${objtoolopt} --retpoline"
-		fi
-
-		if is_enabled CONFIG_SLS; then
-			objtoolopt="${objtoolopt} --sls"
-		fi
-
-		if is_enabled CONFIG_X86_SMAP; then
-			objtoolopt="${objtoolopt} --uaccess"
-		fi
-
 		if ! is_enabled CONFIG_FRAME_POINTER; then
 			objtoolopt="${objtoolopt} --no-fp"
 		fi
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 91a502bb97e8..67cd420dcf89 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -67,7 +67,7 @@ deploy_kernel_headers () {
 	) > debian/hdrsrcfiles
 
 	{
-		if is_enabled CONFIG_STACK_VALIDATION; then
+		if is_enabled CONFIG_OBJTOOL; then
 			echo tools/objtool/objtool
 		fi
 
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
index 586d35720f13..977d90ba642d 100644
--- a/tools/include/linux/objtool.h
+++ b/tools/include/linux/objtool.h
@@ -38,7 +38,7 @@ struct unwind_hint {
 #define UNWIND_HINT_TYPE_REGS_PARTIAL	2
 #define UNWIND_HINT_TYPE_FUNC		3
 
-#ifdef CONFIG_STACK_VALIDATION
+#ifdef CONFIG_OBJTOOL
 
 #ifndef __ASSEMBLY__
 
@@ -157,7 +157,7 @@ struct unwind_hint {
 
 #endif /* __ASSEMBLY__ */
 
-#else /* !CONFIG_STACK_VALIDATION */
+#else /* !CONFIG_OBJTOOL */
 
 #ifndef __ASSEMBLY__
 
@@ -179,6 +179,6 @@ struct unwind_hint {
 .endm
 #endif
 
-#endif /* CONFIG_STACK_VALIDATION */
+#endif /* CONFIG_OBJTOOL */
 
 #endif /* _LINUX_OBJTOOL_H */
-- 
cgit v1.2.3


From 0f620cefd7753175b6258fed85f76c2014ec3799 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Mon, 18 Apr 2022 09:50:41 -0700
Subject: objtool: Rename "VMLINUX_VALIDATION" -> "NOINSTR_VALIDATION"

CONFIG_VMLINUX_VALIDATION is just the validation of the "noinstr" rules.
That name is a misnomer, because now objtool actually does vmlinux
validation for other reasons.

Rename CONFIG_VMLINUX_VALIDATION to CONFIG_NOINSTR_VALIDATION.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Link: https://lkml.kernel.org/r/173f07e2d6d1afc0874aed975a61783207c6a531.1650300597.git.jpoimboe@redhat.com
---
 include/linux/instrumentation.h | 6 +++---
 lib/Kconfig.debug               | 2 +-
 scripts/link-vmlinux.sh         | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h
index 9111a3704072..bc7babe91b2e 100644
--- a/include/linux/instrumentation.h
+++ b/include/linux/instrumentation.h
@@ -2,7 +2,7 @@
 #ifndef __LINUX_INSTRUMENTATION_H
 #define __LINUX_INSTRUMENTATION_H
 
-#ifdef CONFIG_VMLINUX_VALIDATION
+#ifdef CONFIG_NOINSTR_VALIDATION
 
 #include <linux/stringify.h>
 
@@ -53,9 +53,9 @@
 		     ".popsection\n\t" : : "i" (c));			\
 })
 #define instrumentation_end() __instrumentation_end(__COUNTER__)
-#else /* !CONFIG_VMLINUX_VALIDATION */
+#else /* !CONFIG_NOINSTR_VALIDATION */
 # define instrumentation_begin()	do { } while(0)
 # define instrumentation_end()		do { } while(0)
-#endif /* CONFIG_VMLINUX_VALIDATION */
+#endif /* CONFIG_NOINSTR_VALIDATION */
 
 #endif /* __LINUX_INSTRUMENTATION_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7d2bbc3e558e..73359d6cd9a2 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -500,7 +500,7 @@ config STACK_VALIDATION
 	  For more information, see
 	  tools/objtool/Documentation/stack-validation.txt.
 
-config VMLINUX_VALIDATION
+config NOINSTR_VALIDATION
 	bool
 	depends on HAVE_OBJTOOL && DEBUG_ENTRY
 	select OBJTOOL
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 90c9c4c05d95..fce4f41816cd 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -160,7 +160,7 @@ objtool_link()
 		objtoolopt="${objtoolopt} --lto"
 	fi
 
-	if is_enabled CONFIG_VMLINUX_VALIDATION; then
+	if is_enabled CONFIG_NOINSTR_VALIDATION; then
 		objtoolopt="${objtoolopt} --noinstr"
 	fi
 
-- 
cgit v1.2.3


From 89e9c7280075f6733b22dd0740daeddeb1256ebf Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Date: Wed, 20 Apr 2022 10:58:50 +0900
Subject: ipv6: Remove __ipv6_only_sock().

Since commit 9fe516ba3fb2 ("inet: move ipv6only in sock_common"),
ipv6_only_sock() and __ipv6_only_sock() are the same macro.  Let's
remove the one.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h | 4 +---
 net/dccp/ipv6.c      | 2 +-
 net/ipv6/datagram.c  | 4 ++--
 net/ipv6/tcp_ipv6.c  | 2 +-
 net/ipv6/udp.c       | 4 ++--
 net/sctp/ipv6.c      | 4 ++--
 6 files changed, 9 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 918bfea4ef5f..ec5ca392eaa3 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -340,8 +340,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 	return (struct raw6_sock *)sk;
 }
 
-#define __ipv6_only_sock(sk)	(sk->sk_ipv6only)
-#define ipv6_only_sock(sk)	(__ipv6_only_sock(sk))
+#define ipv6_only_sock(sk)	(sk->sk_ipv6only)
 #define ipv6_sk_rxinfo(sk)	((sk)->sk_family == PF_INET6 && \
 				 inet6_sk(sk)->rxopt.bits.rxinfo)
 
@@ -358,7 +357,6 @@ static inline int inet_v6_ipv6only(const struct sock *sk)
 	return ipv6_only_sock(sk);
 }
 #else
-#define __ipv6_only_sock(sk)	0
 #define ipv6_only_sock(sk)	0
 #define ipv6_sk_rxinfo(sk)	0
 
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index eab3bd1ee9a0..4d95b6400915 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -892,7 +892,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 		SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
 
-		if (__ipv6_only_sock(sk))
+		if (ipv6_only_sock(sk))
 			return -ENETUNREACH;
 
 		sin.sin_family = AF_INET;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 206f66310a88..39b2327edc4e 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -145,7 +145,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 	int			err;
 
 	if (usin->sin6_family == AF_INET) {
-		if (__ipv6_only_sock(sk))
+		if (ipv6_only_sock(sk))
 			return -EAFNOSUPPORT;
 		err = __ip4_datagram_connect(sk, uaddr, addr_len);
 		goto ipv4_connected;
@@ -178,7 +178,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (addr_type & IPV6_ADDR_MAPPED) {
 		struct sockaddr_in sin;
 
-		if (__ipv6_only_sock(sk)) {
+		if (ipv6_only_sock(sk)) {
 			err = -ENETUNREACH;
 			goto out;
 		}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 782df529ff69..54277de7474b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -230,7 +230,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		u32 exthdrlen = icsk->icsk_ext_hdr_len;
 		struct sockaddr_in sin;
 
-		if (__ipv6_only_sock(sk))
+		if (ipv6_only_sock(sk))
 			return -ENETUNREACH;
 
 		sin.sin_family = AF_INET;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index db9449b52dbe..688af6f809fe 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1123,7 +1123,7 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
 	 * bytes that are out of the bound specified by user in addr_len.
 	 */
 	if (uaddr->sa_family == AF_INET) {
-		if (__ipv6_only_sock(sk))
+		if (ipv6_only_sock(sk))
 			return -EAFNOSUPPORT;
 		return udp_pre_connect(sk, uaddr, addr_len);
 	}
@@ -1359,7 +1359,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			msg->msg_name = &sin;
 			msg->msg_namelen = sizeof(sin);
 do_udp_sendmsg:
-			if (__ipv6_only_sock(sk))
+			if (ipv6_only_sock(sk))
 				return -ENETUNREACH;
 			return udp_sendmsg(sk, msg, len);
 		}
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 470dbdc27d58..d081858c2d07 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -926,7 +926,7 @@ static int sctp_inet6_af_supported(sa_family_t family, struct sctp_sock *sp)
 		return 1;
 	/* v4-mapped-v6 addresses */
 	case AF_INET:
-		if (!__ipv6_only_sock(sctp_opt2sk(sp)))
+		if (!ipv6_only_sock(sctp_opt2sk(sp)))
 			return 1;
 		fallthrough;
 	default:
@@ -952,7 +952,7 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 		return 0;
 
 	/* If the socket is IPv6 only, v4 addrs will not match */
-	if (__ipv6_only_sock(sk) && af1 != af2)
+	if (ipv6_only_sock(sk) && af1 != af2)
 		return 0;
 
 	/* Today, wildcard AF_INET/AF_INET6. */
-- 
cgit v1.2.3


From b804923b7ccb9c9629703364e927b48cd02a9254 Mon Sep 17 00:00:00 2001
From: "jason-jh.lin" <jason-jh.lin@mediatek.com>
Date: Tue, 19 Apr 2022 17:41:36 +0800
Subject: soc: mediatek: add mtk-mmsys support for mt8195 vdosys0

1. Add mt8195 mmsys compatible for 2 vdosys.
2. Add io_start into each driver data of mt8195 vdosys.
3. Add get match data function to identify mmsys by io_start.
4. Add mt8195 routing table settings of vdosys0.

Signed-off-by: jason-jh.lin <jason-jh.lin@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Rex-BC Chen <rex-bc.chen@mediatek.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Link: https://lore.kernel.org/r/20220419094143.9561-2-jason-jh.lin@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mt8195-mmsys.h    | 370 +++++++++++++++++++++++++++++++++
 drivers/soc/mediatek/mtk-mmsys.c       | 152 +++++++++++++-
 drivers/soc/mediatek/mtk-mmsys.h       |   6 +
 include/linux/soc/mediatek/mtk-mmsys.h |  11 +
 4 files changed, 528 insertions(+), 11 deletions(-)
 create mode 100644 drivers/soc/mediatek/mt8195-mmsys.h

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mt8195-mmsys.h b/drivers/soc/mediatek/mt8195-mmsys.h
new file mode 100644
index 000000000000..13ab0ab64396
--- /dev/null
+++ b/drivers/soc/mediatek/mt8195-mmsys.h
@@ -0,0 +1,370 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __SOC_MEDIATEK_MT8195_MMSYS_H
+#define __SOC_MEDIATEK_MT8195_MMSYS_H
+
+#define MT8195_VDO0_OVL_MOUT_EN					0xf14
+#define MT8195_MOUT_DISP_OVL0_TO_DISP_RDMA0			BIT(0)
+#define MT8195_MOUT_DISP_OVL0_TO_DISP_WDMA0			BIT(1)
+#define MT8195_MOUT_DISP_OVL0_TO_DISP_OVL1			BIT(2)
+#define MT8195_MOUT_DISP_OVL1_TO_DISP_RDMA1			BIT(4)
+#define MT8195_MOUT_DISP_OVL1_TO_DISP_WDMA1			BIT(5)
+#define MT8195_MOUT_DISP_OVL1_TO_DISP_OVL0			BIT(6)
+
+#define MT8195_VDO0_SEL_IN					0xf34
+#define MT8195_SEL_IN_VPP_MERGE_FROM_MASK			GENMASK(1, 0)
+#define MT8195_SEL_IN_VPP_MERGE_FROM_DSC_WRAP0_OUT		(0 << 0)
+#define MT8195_SEL_IN_VPP_MERGE_FROM_DISP_DITHER1		(1 << 0)
+#define MT8195_SEL_IN_VPP_MERGE_FROM_VDO1_VIRTUAL0		(2 << 0)
+#define MT8195_SEL_IN_DSC_WRAP0_IN_FROM_MASK			GENMASK(4, 4)
+#define MT8195_SEL_IN_DSC_WRAP0_IN_FROM_DISP_DITHER0		(0 << 4)
+#define MT8195_SEL_IN_DSC_WRAP0_IN_FROM_VPP_MERGE		(1 << 4)
+#define MT8195_SEL_IN_DSC_WRAP1_IN_FROM_MASK			GENMASK(5, 5)
+#define MT8195_SEL_IN_DSC_WRAP1_IN_FROM_DISP_DITHER1		(0 << 5)
+#define MT8195_SEL_IN_DSC_WRAP1_IN_FROM_VPP_MERGE		(1 << 5)
+#define MT8195_SEL_IN_SINA_VIRTUAL0_FROM_MASK			GENMASK(8, 8)
+#define MT8195_SEL_IN_SINA_VIRTUAL0_FROM_VPP_MERGE		(0 << 8)
+#define MT8195_SEL_IN_SINA_VIRTUAL0_FROM_DSC_WRAP1_OUT		(1 << 8)
+#define MT8195_SEL_IN_SINB_VIRTUAL0_FROM_MASK			GENMASK(9, 9)
+#define MT8195_SEL_IN_SINB_VIRTUAL0_FROM_DSC_WRAP0_OUT		(0 << 9)
+#define MT8195_SEL_IN_DP_INTF0_FROM_MASK			GENMASK(13, 12)
+#define MT8195_SEL_IN_DP_INTF0_FROM_DSC_WRAP1_OUT		(0 << 0)
+#define MT8195_SEL_IN_DP_INTF0_FROM_VPP_MERGE			(1 << 12)
+#define MT8195_SEL_IN_DP_INTF0_FROM_VDO1_VIRTUAL0		(2 << 12)
+#define MT8195_SEL_IN_DSI0_FROM_MASK				GENMASK(16, 16)
+#define MT8195_SEL_IN_DSI0_FROM_DSC_WRAP0_OUT			(0 << 16)
+#define MT8195_SEL_IN_DSI0_FROM_DISP_DITHER0			(1 << 16)
+#define MT8195_SEL_IN_DSI1_FROM_MASK				GENMASK(17, 17)
+#define MT8195_SEL_IN_DSI1_FROM_DSC_WRAP1_OUT			(0 << 17)
+#define MT8195_SEL_IN_DSI1_FROM_VPP_MERGE			(1 << 17)
+#define MT8195_SEL_IN_DISP_WDMA1_FROM_MASK			GENMASK(20, 20)
+#define MT8195_SEL_IN_DISP_WDMA1_FROM_DISP_OVL1			(0 << 20)
+#define MT8195_SEL_IN_DISP_WDMA1_FROM_VPP_MERGE			(1 << 20)
+#define MT8195_SEL_IN_DSC_WRAP1_FROM_MASK			GENMASK(21, 21)
+#define MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DSC_WRAP1_IN		(0 << 21)
+#define MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DISP_DITHER1		(1 << 21)
+#define MT8195_SEL_IN_DISP_WDMA0_FROM_MASK			GENMASK(22, 22)
+#define MT8195_SEL_IN_DISP_WDMA0_FROM_DISP_OVL0			(0 << 22)
+
+#define MT8195_VDO0_SEL_OUT					0xf38
+#define MT8195_SOUT_DISP_DITHER0_TO_MASK			BIT(0)
+#define MT8195_SOUT_DISP_DITHER0_TO_DSC_WRAP0_IN		(0 << 0)
+#define MT8195_SOUT_DISP_DITHER0_TO_DSI0			(1 << 0)
+#define MT8195_SOUT_DISP_DITHER1_TO_MASK			GENMASK(2, 1)
+#define MT8195_SOUT_DISP_DITHER1_TO_DSC_WRAP1_IN		(0 << 1)
+#define MT8195_SOUT_DISP_DITHER1_TO_VPP_MERGE			(1 << 1)
+#define MT8195_SOUT_DISP_DITHER1_TO_DSC_WRAP1_OUT		(2 << 1)
+#define MT8195_SOUT_VDO1_VIRTUAL0_TO_MASK			GENMASK(4, 4)
+#define MT8195_SOUT_VDO1_VIRTUAL0_TO_VPP_MERGE			(0 << 4)
+#define MT8195_SOUT_VDO1_VIRTUAL0_TO_DP_INTF0			(1 << 4)
+#define MT8195_SOUT_VPP_MERGE_TO_MASK				GENMASK(10, 8)
+#define MT8195_SOUT_VPP_MERGE_TO_DSI1				(0 << 8)
+#define MT8195_SOUT_VPP_MERGE_TO_DP_INTF0			(1 << 8)
+#define MT8195_SOUT_VPP_MERGE_TO_SINA_VIRTUAL0			(2 << 8)
+#define MT8195_SOUT_VPP_MERGE_TO_DISP_WDMA1			(3 << 8)
+#define MT8195_SOUT_VPP_MERGE_TO_DSC_WRAP0_IN			(4 << 8)
+#define MT8195_SOUT_VPP_MERGE_TO_DSC_WRAP1_IN_MASK		GENMASK(11, 11)
+#define MT8195_SOUT_VPP_MERGE_TO_DSC_WRAP1_IN			(0 << 11)
+#define MT8195_SOUT_DSC_WRAP0_OUT_TO_MASK			GENMASK(13, 12)
+#define MT8195_SOUT_DSC_WRAP0_OUT_TO_DSI0			(0 << 12)
+#define MT8195_SOUT_DSC_WRAP0_OUT_TO_SINB_VIRTUAL0		(1 << 12)
+#define MT8195_SOUT_DSC_WRAP0_OUT_TO_VPP_MERGE			(2 << 12)
+#define MT8195_SOUT_DSC_WRAP1_OUT_TO_MASK			GENMASK(17, 16)
+#define MT8195_SOUT_DSC_WRAP1_OUT_TO_DSI1			(0 << 16)
+#define MT8195_SOUT_DSC_WRAP1_OUT_TO_DP_INTF0			(1 << 16)
+#define MT8195_SOUT_DSC_WRAP1_OUT_TO_SINA_VIRTUAL0		(2 << 16)
+#define MT8195_SOUT_DSC_WRAP1_OUT_TO_VPP_MERGE			(3 << 16)
+
+static const struct mtk_mmsys_routes mmsys_mt8195_routing_table[] = {
+	{
+		DDP_COMPONENT_OVL0, DDP_COMPONENT_RDMA0,
+		MT8195_VDO0_OVL_MOUT_EN, MT8195_MOUT_DISP_OVL0_TO_DISP_RDMA0,
+		MT8195_MOUT_DISP_OVL0_TO_DISP_RDMA0
+	}, {
+		DDP_COMPONENT_OVL0, DDP_COMPONENT_WDMA0,
+		MT8195_VDO0_OVL_MOUT_EN, MT8195_MOUT_DISP_OVL0_TO_DISP_WDMA0,
+		MT8195_MOUT_DISP_OVL0_TO_DISP_WDMA0
+	}, {
+		DDP_COMPONENT_OVL0, DDP_COMPONENT_OVL1,
+		MT8195_VDO0_OVL_MOUT_EN, MT8195_MOUT_DISP_OVL0_TO_DISP_OVL1,
+		MT8195_MOUT_DISP_OVL0_TO_DISP_OVL1
+	}, {
+		DDP_COMPONENT_OVL1, DDP_COMPONENT_RDMA1,
+		MT8195_VDO0_OVL_MOUT_EN, MT8195_MOUT_DISP_OVL1_TO_DISP_RDMA1,
+		MT8195_MOUT_DISP_OVL1_TO_DISP_RDMA1
+	}, {
+		DDP_COMPONENT_OVL1, DDP_COMPONENT_WDMA1,
+		MT8195_VDO0_OVL_MOUT_EN, MT8195_MOUT_DISP_OVL1_TO_DISP_WDMA1,
+		MT8195_MOUT_DISP_OVL1_TO_DISP_WDMA1
+	}, {
+		DDP_COMPONENT_OVL1, DDP_COMPONENT_OVL0,
+		MT8195_VDO0_OVL_MOUT_EN, MT8195_MOUT_DISP_OVL1_TO_DISP_OVL0,
+		MT8195_MOUT_DISP_OVL1_TO_DISP_OVL0
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_MERGE0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_VPP_MERGE_FROM_MASK,
+		MT8195_SEL_IN_VPP_MERGE_FROM_DSC_WRAP0_OUT
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_MERGE0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_VPP_MERGE_FROM_MASK,
+		MT8195_SEL_IN_VPP_MERGE_FROM_DISP_DITHER1
+	}, {
+		DDP_COMPONENT_MERGE5, DDP_COMPONENT_MERGE0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_VPP_MERGE_FROM_MASK,
+		MT8195_SEL_IN_VPP_MERGE_FROM_VDO1_VIRTUAL0
+	}, {
+		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSC0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP0_IN_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP0_IN_FROM_DISP_DITHER0
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DSC0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP0_IN_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP0_IN_FROM_VPP_MERGE
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DSC1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_IN_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_IN_FROM_DISP_DITHER1
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DSC1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_IN_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_IN_FROM_VPP_MERGE
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DP_INTF1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINA_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINA_VIRTUAL0_FROM_VPP_MERGE
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINA_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINA_VIRTUAL0_FROM_VPP_MERGE
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINA_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINA_VIRTUAL0_FROM_VPP_MERGE
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DP_INTF1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINA_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINA_VIRTUAL0_FROM_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINA_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINA_VIRTUAL0_FROM_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINA_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINA_VIRTUAL0_FROM_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_DP_INTF1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINB_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINB_VIRTUAL0_FROM_DSC_WRAP0_OUT
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINB_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINB_VIRTUAL0_FROM_DSC_WRAP0_OUT
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_SINB_VIRTUAL0_FROM_MASK,
+		MT8195_SEL_IN_SINB_VIRTUAL0_FROM_DSC_WRAP0_OUT
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DP_INTF0_FROM_MASK,
+		MT8195_SEL_IN_DP_INTF0_FROM_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DP_INTF0_FROM_MASK,
+		MT8195_SEL_IN_DP_INTF0_FROM_VPP_MERGE
+	}, {
+		DDP_COMPONENT_MERGE5, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DP_INTF0_FROM_MASK,
+		MT8195_SEL_IN_DP_INTF0_FROM_VDO1_VIRTUAL0
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_DSI0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSI0_FROM_MASK,
+		MT8195_SEL_IN_DSI0_FROM_DSC_WRAP0_OUT
+	}, {
+		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSI0_FROM_MASK,
+		MT8195_SEL_IN_DSI0_FROM_DISP_DITHER0
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DSI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSI1_FROM_MASK,
+		MT8195_SEL_IN_DSI1_FROM_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DSI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSI1_FROM_MASK,
+		MT8195_SEL_IN_DSI1_FROM_VPP_MERGE
+	}, {
+		DDP_COMPONENT_OVL1, DDP_COMPONENT_WDMA1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DISP_WDMA1_FROM_MASK,
+		MT8195_SEL_IN_DISP_WDMA1_FROM_DISP_OVL1
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_WDMA1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DISP_WDMA1_FROM_MASK,
+		MT8195_SEL_IN_DISP_WDMA1_FROM_VPP_MERGE
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DSI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DSC_WRAP1_IN
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DSC_WRAP1_IN
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DP_INTF1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DSC_WRAP1_IN
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DSC_WRAP1_IN
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DSC_WRAP1_IN
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_MERGE0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DSC_WRAP1_IN
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DSI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DISP_DITHER1
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DISP_DITHER1
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DISP_DITHER1
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP1_FROM_MASK,
+		MT8195_SEL_IN_DSC_WRAP1_OUT_FROM_DISP_DITHER1
+	}, {
+		DDP_COMPONENT_OVL0, DDP_COMPONENT_WDMA0,
+		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DISP_WDMA0_FROM_MASK,
+		MT8195_SEL_IN_DISP_WDMA0_FROM_DISP_OVL0
+	}, {
+		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSC0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER0_TO_MASK,
+		MT8195_SOUT_DISP_DITHER0_TO_DSC_WRAP0_IN
+	}, {
+		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER0_TO_MASK,
+		MT8195_SOUT_DISP_DITHER0_TO_DSI0
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DSC1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER1_TO_MASK,
+		MT8195_SOUT_DISP_DITHER1_TO_DSC_WRAP1_IN
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_MERGE0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER1_TO_MASK,
+		MT8195_SOUT_DISP_DITHER1_TO_VPP_MERGE
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DSI1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER1_TO_MASK,
+		MT8195_SOUT_DISP_DITHER1_TO_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER1_TO_MASK,
+		MT8195_SOUT_DISP_DITHER1_TO_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DP_INTF1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER1_TO_MASK,
+		MT8195_SOUT_DISP_DITHER1_TO_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER1_TO_MASK,
+		MT8195_SOUT_DISP_DITHER1_TO_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_DITHER1, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER1_TO_MASK,
+		MT8195_SOUT_DISP_DITHER1_TO_DSC_WRAP1_OUT
+	}, {
+		DDP_COMPONENT_MERGE5, DDP_COMPONENT_MERGE0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VDO1_VIRTUAL0_TO_MASK,
+		MT8195_SOUT_VDO1_VIRTUAL0_TO_VPP_MERGE
+	}, {
+		DDP_COMPONENT_MERGE5, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VDO1_VIRTUAL0_TO_MASK,
+		MT8195_SOUT_VDO1_VIRTUAL0_TO_DP_INTF0
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DSI1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VPP_MERGE_TO_MASK,
+		MT8195_SOUT_VPP_MERGE_TO_DSI1
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VPP_MERGE_TO_MASK,
+		MT8195_SOUT_VPP_MERGE_TO_DP_INTF0
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DP_INTF1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VPP_MERGE_TO_MASK,
+		MT8195_SOUT_VPP_MERGE_TO_SINA_VIRTUAL0
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VPP_MERGE_TO_MASK,
+		MT8195_SOUT_VPP_MERGE_TO_SINA_VIRTUAL0
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VPP_MERGE_TO_MASK,
+		MT8195_SOUT_VPP_MERGE_TO_SINA_VIRTUAL0
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_WDMA1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VPP_MERGE_TO_MASK,
+		MT8195_SOUT_VPP_MERGE_TO_DISP_WDMA1
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DSC0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VPP_MERGE_TO_MASK,
+		MT8195_SOUT_VPP_MERGE_TO_DSC_WRAP0_IN
+	}, {
+		DDP_COMPONENT_MERGE0, DDP_COMPONENT_DSC1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_VPP_MERGE_TO_DSC_WRAP1_IN_MASK,
+		MT8195_SOUT_VPP_MERGE_TO_DSC_WRAP1_IN
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_DSI0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP0_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP0_OUT_TO_DSI0
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_DP_INTF1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP0_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP0_OUT_TO_SINB_VIRTUAL0
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP0_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP0_OUT_TO_SINB_VIRTUAL0
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP0_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP0_OUT_TO_SINB_VIRTUAL0
+	}, {
+		DDP_COMPONENT_DSC0, DDP_COMPONENT_MERGE0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP0_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP0_OUT_TO_VPP_MERGE
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DSI1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP1_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP1_OUT_TO_DSI1
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DP_INTF0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP1_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP1_OUT_TO_DP_INTF0
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DP_INTF1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP1_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP1_OUT_TO_SINA_VIRTUAL0
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DPI0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP1_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP1_OUT_TO_SINA_VIRTUAL0
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_DPI1,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP1_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP1_OUT_TO_SINA_VIRTUAL0
+	}, {
+		DDP_COMPONENT_DSC1, DDP_COMPONENT_MERGE0,
+		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DSC_WRAP1_OUT_TO_MASK,
+		MT8195_SOUT_DSC_WRAP1_OUT_TO_VPP_MERGE
+	}
+};
+
+#endif /* __SOC_MEDIATEK_MT8195_MMSYS_H */
diff --git a/drivers/soc/mediatek/mtk-mmsys.c b/drivers/soc/mediatek/mtk-mmsys.c
index 4fc4c2c9ea20..548efed8dc1c 100644
--- a/drivers/soc/mediatek/mtk-mmsys.c
+++ b/drivers/soc/mediatek/mtk-mmsys.c
@@ -17,6 +17,7 @@
 #include "mt8183-mmsys.h"
 #include "mt8186-mmsys.h"
 #include "mt8192-mmsys.h"
+#include "mt8195-mmsys.h"
 #include "mt8365-mmsys.h"
 
 static const struct mtk_mmsys_driver_data mt2701_mmsys_driver_data = {
@@ -25,26 +26,61 @@ static const struct mtk_mmsys_driver_data mt2701_mmsys_driver_data = {
 	.num_routes = ARRAY_SIZE(mmsys_default_routing_table),
 };
 
+static const struct mtk_mmsys_match_data mt2701_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt2701_mmsys_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt2712_mmsys_driver_data = {
 	.clk_driver = "clk-mt2712-mm",
 	.routes = mmsys_default_routing_table,
 	.num_routes = ARRAY_SIZE(mmsys_default_routing_table),
 };
 
+static const struct mtk_mmsys_match_data mt2712_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt2712_mmsys_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt6779_mmsys_driver_data = {
 	.clk_driver = "clk-mt6779-mm",
 };
 
+static const struct mtk_mmsys_match_data mt6779_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt6779_mmsys_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt6797_mmsys_driver_data = {
 	.clk_driver = "clk-mt6797-mm",
 };
 
+static const struct mtk_mmsys_match_data mt6797_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt6797_mmsys_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt8167_mmsys_driver_data = {
 	.clk_driver = "clk-mt8167-mm",
 	.routes = mt8167_mmsys_routing_table,
 	.num_routes = ARRAY_SIZE(mt8167_mmsys_routing_table),
 };
 
+static const struct mtk_mmsys_match_data mt8167_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt8167_mmsys_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt8173_mmsys_driver_data = {
 	.clk_driver = "clk-mt8173-mm",
 	.routes = mmsys_default_routing_table,
@@ -52,6 +88,13 @@ static const struct mtk_mmsys_driver_data mt8173_mmsys_driver_data = {
 	.sw0_rst_offset = MT8183_MMSYS_SW0_RST_B,
 };
 
+static const struct mtk_mmsys_match_data mt8173_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt8173_mmsys_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt8183_mmsys_driver_data = {
 	.clk_driver = "clk-mt8183-mm",
 	.routes = mmsys_mt8183_routing_table,
@@ -59,6 +102,13 @@ static const struct mtk_mmsys_driver_data mt8183_mmsys_driver_data = {
 	.sw0_rst_offset = MT8183_MMSYS_SW0_RST_B,
 };
 
+static const struct mtk_mmsys_match_data mt8183_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt8183_mmsys_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt8186_mmsys_driver_data = {
 	.clk_driver = "clk-mt8186-mm",
 	.routes = mmsys_mt8186_routing_table,
@@ -66,25 +116,79 @@ static const struct mtk_mmsys_driver_data mt8186_mmsys_driver_data = {
 	.sw0_rst_offset = MT8186_MMSYS_SW0_RST_B,
 };
 
+static const struct mtk_mmsys_match_data mt8186_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt8186_mmsys_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt8192_mmsys_driver_data = {
 	.clk_driver = "clk-mt8192-mm",
 	.routes = mmsys_mt8192_routing_table,
 	.num_routes = ARRAY_SIZE(mmsys_mt8192_routing_table),
 };
 
+static const struct mtk_mmsys_match_data mt8192_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt8192_mmsys_driver_data,
+	},
+};
+
+static const struct mtk_mmsys_driver_data mt8195_vdosys0_driver_data = {
+	.io_start = 0x1c01a000,
+	.clk_driver = "clk-mt8195-vdo0",
+	.routes = mmsys_mt8195_routing_table,
+	.num_routes = ARRAY_SIZE(mmsys_mt8195_routing_table),
+};
+
+static const struct mtk_mmsys_driver_data mt8195_vdosys1_driver_data = {
+	.io_start = 0x1c100000,
+	.clk_driver = "clk-mt8195-vdo1",
+};
+
+static const struct mtk_mmsys_match_data mt8195_mmsys_match_data = {
+	.num_drv_data = 2,
+	.drv_data = {
+		&mt8195_vdosys0_driver_data,
+		&mt8195_vdosys1_driver_data,
+	},
+};
+
 static const struct mtk_mmsys_driver_data mt8365_mmsys_driver_data = {
 	.clk_driver = "clk-mt8365-mm",
 	.routes = mt8365_mmsys_routing_table,
 	.num_routes = ARRAY_SIZE(mt8365_mmsys_routing_table),
 };
 
+static const struct mtk_mmsys_match_data mt8365_mmsys_match_data = {
+	.num_drv_data = 1,
+	.drv_data = {
+		&mt8365_mmsys_driver_data,
+	},
+};
+
 struct mtk_mmsys {
 	void __iomem *regs;
 	const struct mtk_mmsys_driver_data *data;
 	spinlock_t lock; /* protects mmsys_sw_rst_b reg */
 	struct reset_controller_dev rcdev;
+	phys_addr_t io_start;
 };
 
+static int mtk_mmsys_find_match_drvdata(struct mtk_mmsys *mmsys,
+					const struct mtk_mmsys_match_data *match)
+{
+	int i;
+
+	for (i = 0; i < match->num_drv_data; i++)
+		if (mmsys->io_start == match->drv_data[i]->io_start)
+			return i;
+
+	return -EINVAL;
+}
+
 void mtk_mmsys_ddp_connect(struct device *dev,
 			   enum mtk_ddp_comp_id cur,
 			   enum mtk_ddp_comp_id next)
@@ -179,7 +283,9 @@ static int mtk_mmsys_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct platform_device *clks;
 	struct platform_device *drm;
+	const struct mtk_mmsys_match_data *match_data;
 	struct mtk_mmsys *mmsys;
+	struct resource *res;
 	int ret;
 
 	mmsys = devm_kzalloc(dev, sizeof(*mmsys), GFP_KERNEL);
@@ -205,7 +311,27 @@ static int mtk_mmsys_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	mmsys->data = of_device_get_match_data(&pdev->dev);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(dev, "Couldn't get mmsys resource\n");
+		return -EINVAL;
+	}
+	mmsys->io_start = res->start;
+
+	match_data = of_device_get_match_data(dev);
+	if (match_data->num_drv_data > 1) {
+		/* This SoC has multiple mmsys channels */
+		ret = mtk_mmsys_find_match_drvdata(mmsys, match_data);
+		if (ret < 0) {
+			dev_err(dev, "Couldn't get match driver data\n");
+			return ret;
+		}
+		mmsys->data = match_data->drv_data[ret];
+	} else {
+		dev_dbg(dev, "Using single mmsys channel\n");
+		mmsys->data = match_data->drv_data[0];
+	}
+
 	platform_set_drvdata(pdev, mmsys);
 
 	clks = platform_device_register_data(&pdev->dev, mmsys->data->clk_driver,
@@ -226,43 +352,47 @@ static int mtk_mmsys_probe(struct platform_device *pdev)
 static const struct of_device_id of_match_mtk_mmsys[] = {
 	{
 		.compatible = "mediatek,mt2701-mmsys",
-		.data = &mt2701_mmsys_driver_data,
+		.data = &mt2701_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt2712-mmsys",
-		.data = &mt2712_mmsys_driver_data,
+		.data = &mt2712_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt6779-mmsys",
-		.data = &mt6779_mmsys_driver_data,
+		.data = &mt6779_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt6797-mmsys",
-		.data = &mt6797_mmsys_driver_data,
+		.data = &mt6797_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt8167-mmsys",
-		.data = &mt8167_mmsys_driver_data,
+		.data = &mt8167_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt8173-mmsys",
-		.data = &mt8173_mmsys_driver_data,
+		.data = &mt8173_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt8183-mmsys",
-		.data = &mt8183_mmsys_driver_data,
+		.data = &mt8183_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt8186-mmsys",
-		.data = &mt8186_mmsys_driver_data,
+		.data = &mt8186_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt8192-mmsys",
-		.data = &mt8192_mmsys_driver_data,
+		.data = &mt8192_mmsys_match_data,
+	},
+	{
+		.compatible = "mediatek,mt8195-mmsys",
+		.data = &mt8195_mmsys_match_data,
 	},
 	{
 		.compatible = "mediatek,mt8365-mmsys",
-		.data = &mt8365_mmsys_driver_data,
+		.data = &mt8365_mmsys_match_data,
 	},
 	{ }
 };
diff --git a/drivers/soc/mediatek/mtk-mmsys.h b/drivers/soc/mediatek/mtk-mmsys.h
index 77f37f8c715b..f01ba206481d 100644
--- a/drivers/soc/mediatek/mtk-mmsys.h
+++ b/drivers/soc/mediatek/mtk-mmsys.h
@@ -87,12 +87,18 @@ struct mtk_mmsys_routes {
 };
 
 struct mtk_mmsys_driver_data {
+	const resource_size_t io_start;
 	const char *clk_driver;
 	const struct mtk_mmsys_routes *routes;
 	const unsigned int num_routes;
 	const u16 sw0_rst_offset;
 };
 
+struct mtk_mmsys_match_data {
+	unsigned short num_drv_data;
+	const struct mtk_mmsys_driver_data *drv_data[];
+};
+
 /*
  * Routes in mt8173, mt2701, mt2712 are different. That means
  * in the same register address, it controls different input/output
diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h
index 4bba275e235a..cff5c9adbf46 100644
--- a/include/linux/soc/mediatek/mtk-mmsys.h
+++ b/include/linux/soc/mediatek/mtk-mmsys.h
@@ -17,13 +17,24 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_COLOR1,
 	DDP_COMPONENT_DITHER,
+	DDP_COMPONENT_DITHER1,
+	DDP_COMPONENT_DP_INTF0,
+	DDP_COMPONENT_DP_INTF1,
 	DDP_COMPONENT_DPI0,
 	DDP_COMPONENT_DPI1,
+	DDP_COMPONENT_DSC0,
+	DDP_COMPONENT_DSC1,
 	DDP_COMPONENT_DSI0,
 	DDP_COMPONENT_DSI1,
 	DDP_COMPONENT_DSI2,
 	DDP_COMPONENT_DSI3,
 	DDP_COMPONENT_GAMMA,
+	DDP_COMPONENT_MERGE0,
+	DDP_COMPONENT_MERGE1,
+	DDP_COMPONENT_MERGE2,
+	DDP_COMPONENT_MERGE3,
+	DDP_COMPONENT_MERGE4,
+	DDP_COMPONENT_MERGE5,
 	DDP_COMPONENT_OD0,
 	DDP_COMPONENT_OD1,
 	DDP_COMPONENT_OVL0,
-- 
cgit v1.2.3


From 4e8988c634a1159e803bfdc0118578ded97e012c Mon Sep 17 00:00:00 2001
From: "jason-jh.lin" <jason-jh.lin@mediatek.com>
Date: Tue, 19 Apr 2022 17:41:41 +0800
Subject: soc: mediatek: add DDP_DOMPONENT_DITHER0 enum for mt8195 vdosys0

The mmsys routing table of mt8195 vdosys0 has 2 DITHER components,
so mmsys need to add DDP_COMPONENT_DITHER1 and change all usages of
DITHER enum form DDP_COMPONENT_DITHER to DDP_COMPONENT_DITHER0.

But its header need to keep DDP_COMPONENT_DITHER enum
until drm/mediatek also changed it.

Signed-off-by: jason-jh.lin <jason-jh.lin@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Rex-BC Chen <rex-bc.chen@mediatek.com>
Link: https://lore.kernel.org/r/20220419094143.9561-7-jason-jh.lin@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mt8167-mmsys.h    |  2 +-
 drivers/soc/mediatek/mt8183-mmsys.h    |  2 +-
 drivers/soc/mediatek/mt8186-mmsys.h    |  4 ++--
 drivers/soc/mediatek/mt8192-mmsys.h    |  4 ++--
 drivers/soc/mediatek/mt8195-mmsys.h    |  8 ++++----
 drivers/soc/mediatek/mt8365-mmsys.h    |  4 ++--
 drivers/soc/mediatek/mtk-mutex.c       | 10 +++++-----
 include/linux/soc/mediatek/mtk-mmsys.h |  1 +
 8 files changed, 18 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mt8167-mmsys.h b/drivers/soc/mediatek/mt8167-mmsys.h
index 2772ef5e3934..f7a35b3656bb 100644
--- a/drivers/soc/mediatek/mt8167-mmsys.h
+++ b/drivers/soc/mediatek/mt8167-mmsys.h
@@ -18,7 +18,7 @@ static const struct mtk_mmsys_routes mt8167_mmsys_routing_table[] = {
 		DDP_COMPONENT_OVL0, DDP_COMPONENT_COLOR0,
 		MT8167_DISP_REG_CONFIG_DISP_OVL0_MOUT_EN, OVL0_MOUT_EN_COLOR0,
 	}, {
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_RDMA0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_RDMA0,
 		MT8167_DISP_REG_CONFIG_DISP_DITHER_MOUT_EN, MT8167_DITHER_MOUT_EN_RDMA0
 	}, {
 		DDP_COMPONENT_OVL0, DDP_COMPONENT_COLOR0,
diff --git a/drivers/soc/mediatek/mt8183-mmsys.h b/drivers/soc/mediatek/mt8183-mmsys.h
index 0c021f4b76d2..ff6be1703469 100644
--- a/drivers/soc/mediatek/mt8183-mmsys.h
+++ b/drivers/soc/mediatek/mt8183-mmsys.h
@@ -41,7 +41,7 @@ static const struct mtk_mmsys_routes mmsys_mt8183_routing_table[] = {
 		MT8183_DISP_OVL1_2L_MOUT_EN, MT8183_OVL1_2L_MOUT_EN_RDMA1,
 		MT8183_OVL1_2L_MOUT_EN_RDMA1
 	}, {
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8183_DISP_DITHER0_MOUT_EN, MT8183_DITHER0_MOUT_IN_DSI0,
 		MT8183_DITHER0_MOUT_IN_DSI0
 	}, {
diff --git a/drivers/soc/mediatek/mt8186-mmsys.h b/drivers/soc/mediatek/mt8186-mmsys.h
index c72ccf86ea28..eb1ad9c37a9c 100644
--- a/drivers/soc/mediatek/mt8186-mmsys.h
+++ b/drivers/soc/mediatek/mt8186-mmsys.h
@@ -76,12 +76,12 @@ static const struct mtk_mmsys_routes mmsys_mt8186_routing_table[] = {
 		MT8186_RDMA0_SOUT_TO_COLOR0
 	},
 	{
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8186_DISP_DITHER0_MOUT_EN, MT8186_DITHER0_MOUT_EN_MASK,
 		MT8186_DITHER0_MOUT_TO_DSI0,
 	},
 	{
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8186_DISP_DSI0_SEL_IN, MT8186_DSI0_SEL_IN_MASK,
 		MT8186_DSI0_FROM_DITHER0
 	},
diff --git a/drivers/soc/mediatek/mt8192-mmsys.h b/drivers/soc/mediatek/mt8192-mmsys.h
index 6aae0b12b6ff..a016d80b4bc1 100644
--- a/drivers/soc/mediatek/mt8192-mmsys.h
+++ b/drivers/soc/mediatek/mt8192-mmsys.h
@@ -40,7 +40,7 @@ static const struct mtk_mmsys_routes mmsys_mt8192_routing_table[] = {
 		MT8192_DISP_OVL2_2L_MOUT_EN, MT8192_OVL2_2L_MOUT_EN_RDMA4,
 		MT8192_OVL2_2L_MOUT_EN_RDMA4
 	}, {
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8192_DISP_DITHER0_MOUT_EN, MT8192_DITHER0_MOUT_IN_DSI0,
 		MT8192_DITHER0_MOUT_IN_DSI0
 	}, {
@@ -52,7 +52,7 @@ static const struct mtk_mmsys_routes mmsys_mt8192_routing_table[] = {
 		MT8192_DISP_AAL0_SEL_IN, MT8192_AAL0_SEL_IN_CCORR0,
 		MT8192_AAL0_SEL_IN_CCORR0
 	}, {
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8192_DISP_DSI0_SEL_IN, MT8192_DSI0_SEL_IN_DITHER0,
 		MT8192_DSI0_SEL_IN_DITHER0
 	}, {
diff --git a/drivers/soc/mediatek/mt8195-mmsys.h b/drivers/soc/mediatek/mt8195-mmsys.h
index 13ab0ab64396..abfe94a30248 100644
--- a/drivers/soc/mediatek/mt8195-mmsys.h
+++ b/drivers/soc/mediatek/mt8195-mmsys.h
@@ -113,7 +113,7 @@ static const struct mtk_mmsys_routes mmsys_mt8195_routing_table[] = {
 		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_VPP_MERGE_FROM_MASK,
 		MT8195_SEL_IN_VPP_MERGE_FROM_VDO1_VIRTUAL0
 	}, {
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSC0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSC0,
 		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSC_WRAP0_IN_FROM_MASK,
 		MT8195_SEL_IN_DSC_WRAP0_IN_FROM_DISP_DITHER0
 	}, {
@@ -181,7 +181,7 @@ static const struct mtk_mmsys_routes mmsys_mt8195_routing_table[] = {
 		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSI0_FROM_MASK,
 		MT8195_SEL_IN_DSI0_FROM_DSC_WRAP0_OUT
 	}, {
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DSI0_FROM_MASK,
 		MT8195_SEL_IN_DSI0_FROM_DISP_DITHER0
 	}, {
@@ -245,11 +245,11 @@ static const struct mtk_mmsys_routes mmsys_mt8195_routing_table[] = {
 		MT8195_VDO0_SEL_IN, MT8195_SEL_IN_DISP_WDMA0_FROM_MASK,
 		MT8195_SEL_IN_DISP_WDMA0_FROM_DISP_OVL0
 	}, {
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSC0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSC0,
 		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER0_TO_MASK,
 		MT8195_SOUT_DISP_DITHER0_TO_DSC_WRAP0_IN
 	}, {
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8195_VDO0_SEL_OUT, MT8195_SOUT_DISP_DITHER0_TO_MASK,
 		MT8195_SOUT_DISP_DITHER0_TO_DSI0
 	}, {
diff --git a/drivers/soc/mediatek/mt8365-mmsys.h b/drivers/soc/mediatek/mt8365-mmsys.h
index 690e3fe2dee0..24129a6c25f8 100644
--- a/drivers/soc/mediatek/mt8365-mmsys.h
+++ b/drivers/soc/mediatek/mt8365-mmsys.h
@@ -41,12 +41,12 @@ static const struct mtk_mmsys_routes mt8365_mmsys_routing_table[] = {
 		MT8365_DISP_COLOR_SEL_IN_COLOR0,MT8365_DISP_COLOR_SEL_IN_COLOR0
 	},
 	{
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8365_DISP_REG_CONFIG_DISP_DITHER0_MOUT_EN,
 		MT8365_DITHER_MOUT_EN_DSI0, MT8365_DITHER_MOUT_EN_DSI0
 	},
 	{
-		DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0,
+		DDP_COMPONENT_DITHER0, DDP_COMPONENT_DSI0,
 		MT8365_DISP_REG_CONFIG_DISP_DSI0_SEL_IN,
 		MT8365_DSI0_SEL_IN_DITHER, MT8365_DSI0_SEL_IN_DITHER
 	},
diff --git a/drivers/soc/mediatek/mtk-mutex.c b/drivers/soc/mediatek/mtk-mutex.c
index 729ee88035ed..9184684baf1d 100644
--- a/drivers/soc/mediatek/mtk-mutex.c
+++ b/drivers/soc/mediatek/mtk-mutex.c
@@ -232,7 +232,7 @@ static const unsigned int mt8167_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_AAL0] = MT8167_MUTEX_MOD_DISP_AAL,
 	[DDP_COMPONENT_CCORR] = MT8167_MUTEX_MOD_DISP_CCORR,
 	[DDP_COMPONENT_COLOR0] = MT8167_MUTEX_MOD_DISP_COLOR,
-	[DDP_COMPONENT_DITHER] = MT8167_MUTEX_MOD_DISP_DITHER,
+	[DDP_COMPONENT_DITHER0] = MT8167_MUTEX_MOD_DISP_DITHER,
 	[DDP_COMPONENT_GAMMA] = MT8167_MUTEX_MOD_DISP_GAMMA,
 	[DDP_COMPONENT_OVL0] = MT8167_MUTEX_MOD_DISP_OVL0,
 	[DDP_COMPONENT_OVL1] = MT8167_MUTEX_MOD_DISP_OVL1,
@@ -265,7 +265,7 @@ static const unsigned int mt8183_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_AAL0] = MT8183_MUTEX_MOD_DISP_AAL0,
 	[DDP_COMPONENT_CCORR] = MT8183_MUTEX_MOD_DISP_CCORR0,
 	[DDP_COMPONENT_COLOR0] = MT8183_MUTEX_MOD_DISP_COLOR0,
-	[DDP_COMPONENT_DITHER] = MT8183_MUTEX_MOD_DISP_DITHER0,
+	[DDP_COMPONENT_DITHER0] = MT8183_MUTEX_MOD_DISP_DITHER0,
 	[DDP_COMPONENT_GAMMA] = MT8183_MUTEX_MOD_DISP_GAMMA0,
 	[DDP_COMPONENT_OVL0] = MT8183_MUTEX_MOD_DISP_OVL0,
 	[DDP_COMPONENT_OVL_2L0] = MT8183_MUTEX_MOD_DISP_OVL0_2L,
@@ -279,7 +279,7 @@ static const unsigned int mt8186_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_AAL0] = MT8186_MUTEX_MOD_DISP_AAL0,
 	[DDP_COMPONENT_CCORR] = MT8186_MUTEX_MOD_DISP_CCORR0,
 	[DDP_COMPONENT_COLOR0] = MT8186_MUTEX_MOD_DISP_COLOR0,
-	[DDP_COMPONENT_DITHER] = MT8186_MUTEX_MOD_DISP_DITHER0,
+	[DDP_COMPONENT_DITHER0] = MT8186_MUTEX_MOD_DISP_DITHER0,
 	[DDP_COMPONENT_GAMMA] = MT8186_MUTEX_MOD_DISP_GAMMA0,
 	[DDP_COMPONENT_OVL0] = MT8186_MUTEX_MOD_DISP_OVL0,
 	[DDP_COMPONENT_OVL_2L0] = MT8186_MUTEX_MOD_DISP_OVL0_2L,
@@ -292,7 +292,7 @@ static const unsigned int mt8192_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_AAL0] = MT8192_MUTEX_MOD_DISP_AAL0,
 	[DDP_COMPONENT_CCORR] = MT8192_MUTEX_MOD_DISP_CCORR0,
 	[DDP_COMPONENT_COLOR0] = MT8192_MUTEX_MOD_DISP_COLOR0,
-	[DDP_COMPONENT_DITHER] = MT8192_MUTEX_MOD_DISP_DITHER0,
+	[DDP_COMPONENT_DITHER0] = MT8192_MUTEX_MOD_DISP_DITHER0,
 	[DDP_COMPONENT_GAMMA] = MT8192_MUTEX_MOD_DISP_GAMMA0,
 	[DDP_COMPONENT_POSTMASK0] = MT8192_MUTEX_MOD_DISP_POSTMASK0,
 	[DDP_COMPONENT_OVL0] = MT8192_MUTEX_MOD_DISP_OVL0,
@@ -310,7 +310,7 @@ static const unsigned int mt8195_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_CCORR] = MT8195_MUTEX_MOD_DISP_CCORR0,
 	[DDP_COMPONENT_AAL0] = MT8195_MUTEX_MOD_DISP_AAL0,
 	[DDP_COMPONENT_GAMMA] = MT8195_MUTEX_MOD_DISP_GAMMA0,
-	[DDP_COMPONENT_DITHER] = MT8195_MUTEX_MOD_DISP_DITHER0,
+	[DDP_COMPONENT_DITHER0] = MT8195_MUTEX_MOD_DISP_DITHER0,
 	[DDP_COMPONENT_MERGE0] = MT8195_MUTEX_MOD_DISP_VPP_MERGE,
 	[DDP_COMPONENT_DSC0] = MT8195_MUTEX_MOD_DISP_DSC_WRAP0_CORE0,
 	[DDP_COMPONENT_DSI0] = MT8195_MUTEX_MOD_DISP_DSI0,
diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h
index cff5c9adbf46..59117d970daf 100644
--- a/include/linux/soc/mediatek/mtk-mmsys.h
+++ b/include/linux/soc/mediatek/mtk-mmsys.h
@@ -17,6 +17,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_COLOR1,
 	DDP_COMPONENT_DITHER,
+	DDP_COMPONENT_DITHER0 = DDP_COMPONENT_DITHER,
 	DDP_COMPONENT_DITHER1,
 	DDP_COMPONENT_DP_INTF0,
 	DDP_COMPONENT_DP_INTF1,
-- 
cgit v1.2.3


From bd40cbb0e3b37a4d2a2d9e2ac40122cdf619b1f3 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 19 Apr 2022 19:29:16 +0200
Subject: PM: domains: Move genpd's time-accounting to ktime_get_mono_fast_ns()

To move towards a more consistent behaviour between genpd and the runtime
PM core, let's start by converting genpd's time-accounting from ktime_get()
into ktime_get_mono_fast_ns().

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 77 +++++++++++++++++++++++++--------------------
 include/linux/pm_domain.h   |  6 ++--
 2 files changed, 46 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 1ee878d126fd..18cd7965e5d6 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -225,24 +225,23 @@ static void genpd_debug_remove(struct generic_pm_domain *genpd)
 
 static void genpd_update_accounting(struct generic_pm_domain *genpd)
 {
-	ktime_t delta, now;
+	u64 delta, now;
 
-	now = ktime_get();
-	delta = ktime_sub(now, genpd->accounting_time);
+	now = ktime_get_mono_fast_ns();
+	if (now <= genpd->accounting_time)
+		return;
+
+	delta = now - genpd->accounting_time;
 
 	/*
 	 * If genpd->status is active, it means we are just
 	 * out of off and so update the idle time and vice
 	 * versa.
 	 */
-	if (genpd->status == GENPD_STATE_ON) {
-		int state_idx = genpd->state_idx;
-
-		genpd->states[state_idx].idle_time =
-			ktime_add(genpd->states[state_idx].idle_time, delta);
-	} else {
-		genpd->on_time = ktime_add(genpd->on_time, delta);
-	}
+	if (genpd->status == GENPD_STATE_ON)
+		genpd->states[genpd->state_idx].idle_time += delta;
+	else
+		genpd->on_time += delta;
 
 	genpd->accounting_time = now;
 }
@@ -1999,7 +1998,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->max_off_time_changed = true;
 	genpd->provider = NULL;
 	genpd->has_provider = false;
-	genpd->accounting_time = ktime_get();
+	genpd->accounting_time = ktime_get_mono_fast_ns();
 	genpd->domain.ops.runtime_suspend = genpd_runtime_suspend;
 	genpd->domain.ops.runtime_resume = genpd_runtime_resume;
 	genpd->domain.ops.prepare = genpd_prepare;
@@ -3163,6 +3162,7 @@ static int sub_domains_show(struct seq_file *s, void *data)
 static int idle_states_show(struct seq_file *s, void *data)
 {
 	struct generic_pm_domain *genpd = s->private;
+	u64 now, delta, idle_time = 0;
 	unsigned int i;
 	int ret = 0;
 
@@ -3173,17 +3173,19 @@ static int idle_states_show(struct seq_file *s, void *data)
 	seq_puts(s, "State          Time Spent(ms) Usage          Rejected\n");
 
 	for (i = 0; i < genpd->state_count; i++) {
-		ktime_t delta = 0;
-		s64 msecs;
+		idle_time += genpd->states[i].idle_time;
 
-		if ((genpd->status == GENPD_STATE_OFF) &&
-				(genpd->state_idx == i))
-			delta = ktime_sub(ktime_get(), genpd->accounting_time);
+		if (genpd->status == GENPD_STATE_OFF && genpd->state_idx == i) {
+			now = ktime_get_mono_fast_ns();
+			if (now > genpd->accounting_time) {
+				delta = now - genpd->accounting_time;
+				idle_time += delta;
+			}
+		}
 
-		msecs = ktime_to_ms(
-			ktime_add(genpd->states[i].idle_time, delta));
-		seq_printf(s, "S%-13i %-14lld %-14llu %llu\n", i, msecs,
-			      genpd->states[i].usage, genpd->states[i].rejected);
+		do_div(idle_time, NSEC_PER_MSEC);
+		seq_printf(s, "S%-13i %-14llu %-14llu %llu\n", i, idle_time,
+			   genpd->states[i].usage, genpd->states[i].rejected);
 	}
 
 	genpd_unlock(genpd);
@@ -3193,18 +3195,22 @@ static int idle_states_show(struct seq_file *s, void *data)
 static int active_time_show(struct seq_file *s, void *data)
 {
 	struct generic_pm_domain *genpd = s->private;
-	ktime_t delta = 0;
+	u64 now, on_time, delta = 0;
 	int ret = 0;
 
 	ret = genpd_lock_interruptible(genpd);
 	if (ret)
 		return -ERESTARTSYS;
 
-	if (genpd->status == GENPD_STATE_ON)
-		delta = ktime_sub(ktime_get(), genpd->accounting_time);
+	if (genpd->status == GENPD_STATE_ON) {
+		now = ktime_get_mono_fast_ns();
+		if (now > genpd->accounting_time)
+			delta = now - genpd->accounting_time;
+	}
 
-	seq_printf(s, "%lld ms\n", ktime_to_ms(
-				ktime_add(genpd->on_time, delta)));
+	on_time = genpd->on_time + delta;
+	do_div(on_time, NSEC_PER_MSEC);
+	seq_printf(s, "%llu ms\n", on_time);
 
 	genpd_unlock(genpd);
 	return ret;
@@ -3213,7 +3219,7 @@ static int active_time_show(struct seq_file *s, void *data)
 static int total_idle_time_show(struct seq_file *s, void *data)
 {
 	struct generic_pm_domain *genpd = s->private;
-	ktime_t delta = 0, total = 0;
+	u64 now, delta, total = 0;
 	unsigned int i;
 	int ret = 0;
 
@@ -3222,16 +3228,19 @@ static int total_idle_time_show(struct seq_file *s, void *data)
 		return -ERESTARTSYS;
 
 	for (i = 0; i < genpd->state_count; i++) {
+		total += genpd->states[i].idle_time;
 
-		if ((genpd->status == GENPD_STATE_OFF) &&
-				(genpd->state_idx == i))
-			delta = ktime_sub(ktime_get(), genpd->accounting_time);
-
-		total = ktime_add(total, genpd->states[i].idle_time);
+		if (genpd->status == GENPD_STATE_OFF && genpd->state_idx == i) {
+			now = ktime_get_mono_fast_ns();
+			if (now > genpd->accounting_time) {
+				delta = now - genpd->accounting_time;
+				total += delta;
+			}
+		}
 	}
-	total = ktime_add(total, delta);
 
-	seq_printf(s, "%lld ms\n", ktime_to_ms(total));
+	do_div(total, NSEC_PER_MSEC);
+	seq_printf(s, "%llu ms\n", total);
 
 	genpd_unlock(genpd);
 	return ret;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 67017c9390c8..043d48e4420a 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -98,7 +98,7 @@ struct genpd_power_state {
 	u64 usage;
 	u64 rejected;
 	struct fwnode_handle *fwnode;
-	ktime_t idle_time;
+	u64 idle_time;
 	void *data;
 };
 
@@ -149,8 +149,8 @@ struct generic_pm_domain {
 			    unsigned int state_count);
 	unsigned int state_count; /* number of states */
 	unsigned int state_idx; /* state that genpd will go to when off */
-	ktime_t on_time;
-	ktime_t accounting_time;
+	u64 on_time;
+	u64 accounting_time;
 	const struct genpd_lock_ops *lock_ops;
 	union {
 		struct mutex mlock;
-- 
cgit v1.2.3


From 6c2f421174273de8f83cde4286d1c076d43a2d35 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Apr 2022 13:34:24 +0200
Subject: driver: platform: Add helper for safer setting of driver_override

Several core drivers and buses expect that driver_override is a
dynamically allocated memory thus later they can kfree() it.

However such assumption is not documented, there were in the past and
there are already users setting it to a string literal. This leads to
kfree() of static memory during device release (e.g. in error paths or
during unbind):

    kernel BUG at ../mm/slub.c:3960!
    Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM
    ...
    (kfree) from [<c058da50>] (platform_device_release+0x88/0xb4)
    (platform_device_release) from [<c0585be0>] (device_release+0x2c/0x90)
    (device_release) from [<c0a69050>] (kobject_put+0xec/0x20c)
    (kobject_put) from [<c0f2f120>] (exynos5_clk_probe+0x154/0x18c)
    (exynos5_clk_probe) from [<c058de70>] (platform_drv_probe+0x6c/0xa4)
    (platform_drv_probe) from [<c058b7ac>] (really_probe+0x280/0x414)
    (really_probe) from [<c058baf4>] (driver_probe_device+0x78/0x1c4)
    (driver_probe_device) from [<c0589854>] (bus_for_each_drv+0x74/0xb8)
    (bus_for_each_drv) from [<c058b48c>] (__device_attach+0xd4/0x16c)
    (__device_attach) from [<c058a638>] (bus_probe_device+0x88/0x90)
    (bus_probe_device) from [<c05871fc>] (device_add+0x3dc/0x62c)
    (device_add) from [<c075ff10>] (of_platform_device_create_pdata+0x94/0xbc)
    (of_platform_device_create_pdata) from [<c07600ec>] (of_platform_bus_create+0x1a8/0x4fc)
    (of_platform_bus_create) from [<c0760150>] (of_platform_bus_create+0x20c/0x4fc)
    (of_platform_bus_create) from [<c07605f0>] (of_platform_populate+0x84/0x118)
    (of_platform_populate) from [<c0f3c964>] (of_platform_default_populate_init+0xa0/0xb8)
    (of_platform_default_populate_init) from [<c01031f8>] (do_one_initcall+0x8c/0x404)

Provide a helper which clearly documents the usage of driver_override.
This will allow later to reuse the helper and reduce the amount of
duplicated code.

Convert the platform driver to use a new helper and make the
driver_override field const char (it is not modified by the core).

Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220419113435.246203-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/driver.c           | 69 +++++++++++++++++++++++++++++++++++++++++
 drivers/base/platform.c         | 28 +++--------------
 include/linux/device/driver.h   |  2 ++
 include/linux/platform_device.h |  6 +++-
 4 files changed, 80 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/driver.c b/drivers/base/driver.c
index 8c0d33e182fd..1b9d47b10bd0 100644
--- a/drivers/base/driver.c
+++ b/drivers/base/driver.c
@@ -30,6 +30,75 @@ static struct device *next_device(struct klist_iter *i)
 	return dev;
 }
 
+/**
+ * driver_set_override() - Helper to set or clear driver override.
+ * @dev: Device to change
+ * @override: Address of string to change (e.g. &device->driver_override);
+ *            The contents will be freed and hold newly allocated override.
+ * @s: NUL-terminated string, new driver name to force a match, pass empty
+ *     string to clear it ("" or "\n", where the latter is only for sysfs
+ *     interface).
+ * @len: length of @s
+ *
+ * Helper to set or clear driver override in a device, intended for the cases
+ * when the driver_override field is allocated by driver/bus code.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int driver_set_override(struct device *dev, const char **override,
+			const char *s, size_t len)
+{
+	const char *new, *old;
+	char *cp;
+
+	if (!override || !s)
+		return -EINVAL;
+
+	/*
+	 * The stored value will be used in sysfs show callback (sysfs_emit()),
+	 * which has a length limit of PAGE_SIZE and adds a trailing newline.
+	 * Thus we can store one character less to avoid truncation during sysfs
+	 * show.
+	 */
+	if (len >= (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	if (!len) {
+		/* Empty string passed - clear override */
+		device_lock(dev);
+		old = *override;
+		*override = NULL;
+		device_unlock(dev);
+		kfree(old);
+
+		return 0;
+	}
+
+	cp = strnchr(s, len, '\n');
+	if (cp)
+		len = cp - s;
+
+	new = kstrndup(s, len, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	device_lock(dev);
+	old = *override;
+	if (cp != s) {
+		*override = new;
+	} else {
+		/* "\n" passed - clear override */
+		kfree(new);
+		*override = NULL;
+	}
+	device_unlock(dev);
+
+	kfree(old);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(driver_set_override);
+
 /**
  * driver_for_each_device - Iterator for devices bound to a driver.
  * @drv: Driver we're iterating.
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 8cc272fd5c99..b684157b7f2f 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1275,31 +1275,11 @@ static ssize_t driver_override_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct platform_device *pdev = to_platform_device(dev);
-	char *driver_override, *old, *cp;
-
-	/* We need to keep extra room for a newline */
-	if (count >= (PAGE_SIZE - 1))
-		return -EINVAL;
-
-	driver_override = kstrndup(buf, count, GFP_KERNEL);
-	if (!driver_override)
-		return -ENOMEM;
-
-	cp = strchr(driver_override, '\n');
-	if (cp)
-		*cp = '\0';
-
-	device_lock(dev);
-	old = pdev->driver_override;
-	if (strlen(driver_override)) {
-		pdev->driver_override = driver_override;
-	} else {
-		kfree(driver_override);
-		pdev->driver_override = NULL;
-	}
-	device_unlock(dev);
+	int ret;
 
-	kfree(old);
+	ret = driver_set_override(dev, &pdev->driver_override, buf, count);
+	if (ret)
+		return ret;
 
 	return count;
 }
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index 15e7c5e15d62..700453017e1c 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -151,6 +151,8 @@ extern int __must_check driver_create_file(struct device_driver *driver,
 extern void driver_remove_file(struct device_driver *driver,
 			       const struct driver_attribute *attr);
 
+int driver_set_override(struct device *dev, const char **override,
+			const char *s, size_t len);
 extern int __must_check driver_for_each_device(struct device_driver *drv,
 					       struct device *start,
 					       void *data,
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 7c96f169d274..582d83ed9a91 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -31,7 +31,11 @@ struct platform_device {
 	struct resource	*resource;
 
 	const struct platform_device_id	*id_entry;
-	char *driver_override; /* Driver name to force a match */
+	/*
+	 * Driver name to force a match.  Do not set directly, because core
+	 * frees it.  Use driver_set_override() to set or clear it.
+	 */
+	const char *driver_override;
 
 	/* MFD cell pointer */
 	struct mfd_cell *mfd_cell;
-- 
cgit v1.2.3


From 6e67955087e72f1a5f64dd8014c27e1d9317fbb4 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Apr 2022 13:34:25 +0200
Subject: amba: Use driver_set_override() instead of open-coding

Use a helper to set driver_override to reduce the amount of duplicated
code.  Make the driver_override field const char, because it is not
modified by the core and it matches other subsystems.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220419113435.246203-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/amba/bus.c       | 28 ++++------------------------
 include/linux/amba/bus.h |  6 +++++-
 2 files changed, 9 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index d3bd14aaabf6..f3d26d698b77 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -94,31 +94,11 @@ static ssize_t driver_override_store(struct device *_dev,
 				     const char *buf, size_t count)
 {
 	struct amba_device *dev = to_amba_device(_dev);
-	char *driver_override, *old, *cp;
-
-	/* We need to keep extra room for a newline */
-	if (count >= (PAGE_SIZE - 1))
-		return -EINVAL;
-
-	driver_override = kstrndup(buf, count, GFP_KERNEL);
-	if (!driver_override)
-		return -ENOMEM;
-
-	cp = strchr(driver_override, '\n');
-	if (cp)
-		*cp = '\0';
-
-	device_lock(_dev);
-	old = dev->driver_override;
-	if (strlen(driver_override)) {
-		dev->driver_override = driver_override;
-	} else {
-		kfree(driver_override);
-		dev->driver_override = NULL;
-	}
-	device_unlock(_dev);
+	int ret;
 
-	kfree(old);
+	ret = driver_set_override(_dev, &dev->driver_override, buf, count);
+	if (ret)
+		return ret;
 
 	return count;
 }
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 6562f543c3e0..93799a72ff82 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -70,7 +70,11 @@ struct amba_device {
 	unsigned int		cid;
 	struct amba_cs_uci_id	uci;
 	unsigned int		irq[AMBA_NR_IRQS];
-	char			*driver_override;
+	/*
+	 * Driver name to force a match.  Do not set directly, because core
+	 * frees it.  Use driver_set_override() to set or clear it.
+	 */
+	const char		*driver_override;
 };
 
 struct amba_driver {
-- 
cgit v1.2.3


From 5688f212e98a2469583a067fa5da4312ddc4e357 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Apr 2022 13:34:26 +0200
Subject: fsl-mc: Use driver_set_override() instead of open-coding

Use a helper to set driver_override to reduce the amount of duplicated
code.  Make the driver_override field const char, because it is not
modified by the core and it matches other subsystems.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220419113435.246203-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/fsl-mc-bus.c | 25 ++++---------------------
 include/linux/fsl/mc.h          |  6 ++++--
 2 files changed, 8 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 8fd4a356a86e..ba01c7f4de92 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -166,31 +166,14 @@ static ssize_t driver_override_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
-	char *driver_override, *old = mc_dev->driver_override;
-	char *cp;
+	int ret;
 
 	if (WARN_ON(dev->bus != &fsl_mc_bus_type))
 		return -EINVAL;
 
-	if (count >= (PAGE_SIZE - 1))
-		return -EINVAL;
-
-	driver_override = kstrndup(buf, count, GFP_KERNEL);
-	if (!driver_override)
-		return -ENOMEM;
-
-	cp = strchr(driver_override, '\n');
-	if (cp)
-		*cp = '\0';
-
-	if (strlen(driver_override)) {
-		mc_dev->driver_override = driver_override;
-	} else {
-		kfree(driver_override);
-		mc_dev->driver_override = NULL;
-	}
-
-	kfree(old);
+	ret = driver_set_override(dev, &mc_dev->driver_override, buf, count);
+	if (ret)
+		return ret;
 
 	return count;
 }
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 7b6c42bfb660..7a87ab9eba99 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -170,7 +170,9 @@ struct fsl_mc_obj_desc {
  * @regions: pointer to array of MMIO region entries
  * @irqs: pointer to array of pointers to interrupts allocated to this device
  * @resource: generic resource associated with this MC object device, if any.
- * @driver_override: driver name to force a match
+ * @driver_override: driver name to force a match; do not set directly,
+ *                   because core frees it; use driver_set_override() to
+ *                   set or clear it.
  *
  * Generic device object for MC object devices that are "attached" to a
  * MC bus.
@@ -204,7 +206,7 @@ struct fsl_mc_device {
 	struct fsl_mc_device_irq **irqs;
 	struct fsl_mc_resource *resource;
 	struct device_link *consumer_link;
-	char   *driver_override;
+	const char *driver_override;
 };
 
 #define to_fsl_mc_device(_dev) \
-- 
cgit v1.2.3


From 01ed100276bdac259f1b418b998904a7486b0b68 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Apr 2022 13:34:27 +0200
Subject: hv: Use driver_set_override() instead of open-coding

Use a helper to set driver_override to the reduce amount of duplicated
code.  Make the driver_override field const char, because it is not
modified by the core and it matches other subsystems.

Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220419113435.246203-5-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/vmbus_drv.c | 28 ++++------------------------
 include/linux/hyperv.h |  6 +++++-
 2 files changed, 9 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 14de17087864..607e40aba18e 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -575,31 +575,11 @@ static ssize_t driver_override_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct hv_device *hv_dev = device_to_hv_device(dev);
-	char *driver_override, *old, *cp;
-
-	/* We need to keep extra room for a newline */
-	if (count >= (PAGE_SIZE - 1))
-		return -EINVAL;
-
-	driver_override = kstrndup(buf, count, GFP_KERNEL);
-	if (!driver_override)
-		return -ENOMEM;
-
-	cp = strchr(driver_override, '\n');
-	if (cp)
-		*cp = '\0';
-
-	device_lock(dev);
-	old = hv_dev->driver_override;
-	if (strlen(driver_override)) {
-		hv_dev->driver_override = driver_override;
-	} else {
-		kfree(driver_override);
-		hv_dev->driver_override = NULL;
-	}
-	device_unlock(dev);
+	int ret;
 
-	kfree(old);
+	ret = driver_set_override(dev, &hv_dev->driver_override, buf, count);
+	if (ret)
+		return ret;
 
 	return count;
 }
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index fe2e0179ed51..12e2336b23b7 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1257,7 +1257,11 @@ struct hv_device {
 	u16 device_id;
 
 	struct device device;
-	char *driver_override; /* Driver name to force a match */
+	/*
+	 * Driver name to force a match.  Do not set directly, because core
+	 * frees it.  Use driver_set_override() to set or clear it.
+	 */
+	const char *driver_override;
 
 	struct vmbus_channel *channel;
 	struct kset	     *channels_kset;
-- 
cgit v1.2.3


From 23d99baf9d729ca30b2fb6798a7b403a37bfb800 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Apr 2022 13:34:28 +0200
Subject: PCI: Use driver_set_override() instead of open-coding

Use a helper to set driver_override to the reduce amount of duplicated
code.  Make the driver_override field const char, because it is not
modified by the core and it matches other subsystems.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220419113435.246203-6-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/pci-sysfs.c | 28 ++++------------------------
 include/linux/pci.h     |  6 +++++-
 2 files changed, 9 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index c263ffc5884a..fc804e08e3cb 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -567,31 +567,11 @@ static ssize_t driver_override_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	char *driver_override, *old, *cp;
-
-	/* We need to keep extra room for a newline */
-	if (count >= (PAGE_SIZE - 1))
-		return -EINVAL;
-
-	driver_override = kstrndup(buf, count, GFP_KERNEL);
-	if (!driver_override)
-		return -ENOMEM;
-
-	cp = strchr(driver_override, '\n');
-	if (cp)
-		*cp = '\0';
-
-	device_lock(dev);
-	old = pdev->driver_override;
-	if (strlen(driver_override)) {
-		pdev->driver_override = driver_override;
-	} else {
-		kfree(driver_override);
-		pdev->driver_override = NULL;
-	}
-	device_unlock(dev);
+	int ret;
 
-	kfree(old);
+	ret = driver_set_override(dev, &pdev->driver_override, buf, count);
+	if (ret)
+		return ret;
 
 	return count;
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60adf42460ab..844d38f589cf 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -516,7 +516,11 @@ struct pci_dev {
 	u16		acs_cap;	/* ACS Capability offset */
 	phys_addr_t	rom;		/* Physical address if not from BAR */
 	size_t		romlen;		/* Length if not from BAR */
-	char		*driver_override; /* Driver name to force a match */
+	/*
+	 * Driver name to force a match.  Do not set directly, because core
+	 * frees it.  Use driver_set_override() to set or clear it.
+	 */
+	const char	*driver_override;
 
 	unsigned long	priv_flags;	/* Private flags for the PCI driver */
 
-- 
cgit v1.2.3


From 19368f0f23e80929691dd5b1354832c0e0494419 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Apr 2022 13:34:30 +0200
Subject: spi: Use helper for safer setting of driver_override

Use a helper to set driver_override to the reduce amount of duplicated
code.

Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220419113435.246203-8-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spi/spi.c       | 26 ++++----------------------
 include/linux/spi/spi.h |  2 ++
 2 files changed, 6 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 2e6d6bbeb784..1bbfb57d687a 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -71,29 +71,11 @@ static ssize_t driver_override_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct spi_device *spi = to_spi_device(dev);
-	const char *end = memchr(buf, '\n', count);
-	const size_t len = end ? end - buf : count;
-	const char *driver_override, *old;
-
-	/* We need to keep extra room for a newline when displaying value */
-	if (len >= (PAGE_SIZE - 1))
-		return -EINVAL;
-
-	driver_override = kstrndup(buf, len, GFP_KERNEL);
-	if (!driver_override)
-		return -ENOMEM;
+	int ret;
 
-	device_lock(dev);
-	old = spi->driver_override;
-	if (len) {
-		spi->driver_override = driver_override;
-	} else {
-		/* Empty string, disable driver override */
-		spi->driver_override = NULL;
-		kfree(driver_override);
-	}
-	device_unlock(dev);
-	kfree(old);
+	ret = driver_set_override(dev, &spi->driver_override, buf, count);
+	if (ret)
+		return ret;
 
 	return count;
 }
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 5f8c063ddff4..f0177f9b6e13 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -138,6 +138,8 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer);
  *	for driver coldplugging, and in uevents used for hotplugging
  * @driver_override: If the name of a driver is written to this attribute, then
  *	the device will bind to the named driver and only the named driver.
+ *	Do not set directly, because core frees it; use driver_set_override() to
+ *	set or clear it.
  * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when
  *	not using a GPIO line)
  * @word_delay: delay to be inserted between consecutive
-- 
cgit v1.2.3


From 240bf4e665741241983580812a2be1b033f120ee Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Apr 2022 13:34:31 +0200
Subject: vdpa: Use helper for safer setting of driver_override

Use a helper to set driver_override to the reduce amount of duplicated
code.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220419113435.246203-9-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/vdpa/vdpa.c  | 29 ++++-------------------------
 include/linux/vdpa.h |  4 +++-
 2 files changed, 7 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 2b75c00b1005..33d1ad60cba7 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -77,32 +77,11 @@ static ssize_t driver_override_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct vdpa_device *vdev = dev_to_vdpa(dev);
-	const char *driver_override, *old;
-	char *cp;
+	int ret;
 
-	/* We need to keep extra room for a newline */
-	if (count >= (PAGE_SIZE - 1))
-		return -EINVAL;
-
-	driver_override = kstrndup(buf, count, GFP_KERNEL);
-	if (!driver_override)
-		return -ENOMEM;
-
-	cp = strchr(driver_override, '\n');
-	if (cp)
-		*cp = '\0';
-
-	device_lock(dev);
-	old = vdev->driver_override;
-	if (strlen(driver_override)) {
-		vdev->driver_override = driver_override;
-	} else {
-		kfree(driver_override);
-		vdev->driver_override = NULL;
-	}
-	device_unlock(dev);
-
-	kfree(old);
+	ret = driver_set_override(dev, &vdev->driver_override, buf, count);
+	if (ret)
+		return ret;
 
 	return count;
 }
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 8943a209202e..c0a5083632ab 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -64,7 +64,9 @@ struct vdpa_mgmt_dev;
  * struct vdpa_device - representation of a vDPA device
  * @dev: underlying device
  * @dma_dev: the actual device that is performing DMA
- * @driver_override: driver name to force a match
+ * @driver_override: driver name to force a match; do not set directly,
+ *                   because core frees it; use driver_set_override() to
+ *                   set or clear it.
  * @config: the configuration ops for this device.
  * @cf_mutex: Protects get and set access to configuration layout.
  * @index: device index
-- 
cgit v1.2.3


From 42cd402b8fd4672b692400fe5f9eecd55d2794ac Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Apr 2022 13:34:35 +0200
Subject: rpmsg: Fix kfree() of static memory on setting driver_override

The driver_override field from platform driver should not be initialized
from static memory (string literal) because the core later kfree() it,
for example when driver_override is set via sysfs.

Use dedicated helper to set driver_override properly.

Fixes: 950a7388f02b ("rpmsg: Turn name service into a stand alone driver")
Fixes: c0cdc19f84a4 ("rpmsg: Driver for user space endpoint interface")
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20220419113435.246203-13-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/rpmsg/rpmsg_internal.h | 13 +++++++++++--
 drivers/rpmsg/rpmsg_ns.c       | 14 ++++++++++++--
 include/linux/rpmsg.h          |  6 ++++--
 3 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/rpmsg/rpmsg_internal.h b/drivers/rpmsg/rpmsg_internal.h
index d4b23fd019a8..3e81642238d2 100644
--- a/drivers/rpmsg/rpmsg_internal.h
+++ b/drivers/rpmsg/rpmsg_internal.h
@@ -94,10 +94,19 @@ int rpmsg_release_channel(struct rpmsg_device *rpdev,
  */
 static inline int rpmsg_ctrldev_register_device(struct rpmsg_device *rpdev)
 {
+	int ret;
+
 	strcpy(rpdev->id.name, "rpmsg_ctrl");
-	rpdev->driver_override = "rpmsg_ctrl";
+	ret = driver_set_override(&rpdev->dev, &rpdev->driver_override,
+				  rpdev->id.name, strlen(rpdev->id.name));
+	if (ret)
+		return ret;
+
+	ret = rpmsg_register_device(rpdev);
+	if (ret)
+		kfree(rpdev->driver_override);
 
-	return rpmsg_register_device(rpdev);
+	return ret;
 }
 
 #endif
diff --git a/drivers/rpmsg/rpmsg_ns.c b/drivers/rpmsg/rpmsg_ns.c
index 762ff1ae279f..8eb8f328237e 100644
--- a/drivers/rpmsg/rpmsg_ns.c
+++ b/drivers/rpmsg/rpmsg_ns.c
@@ -20,12 +20,22 @@
  */
 int rpmsg_ns_register_device(struct rpmsg_device *rpdev)
 {
+	int ret;
+
 	strcpy(rpdev->id.name, "rpmsg_ns");
-	rpdev->driver_override = "rpmsg_ns";
+	ret = driver_set_override(&rpdev->dev, &rpdev->driver_override,
+				  rpdev->id.name, strlen(rpdev->id.name));
+	if (ret)
+		return ret;
+
 	rpdev->src = RPMSG_NS_ADDR;
 	rpdev->dst = RPMSG_NS_ADDR;
 
-	return rpmsg_register_device(rpdev);
+	ret = rpmsg_register_device(rpdev);
+	if (ret)
+		kfree(rpdev->driver_override);
+
+	return ret;
 }
 EXPORT_SYMBOL(rpmsg_ns_register_device);
 
diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h
index 02fa9116cd60..20c8cd1cde21 100644
--- a/include/linux/rpmsg.h
+++ b/include/linux/rpmsg.h
@@ -41,7 +41,9 @@ struct rpmsg_channel_info {
  * rpmsg_device - device that belong to the rpmsg bus
  * @dev: the device struct
  * @id: device id (used to match between rpmsg drivers and devices)
- * @driver_override: driver name to force a match
+ * @driver_override: driver name to force a match; do not set directly,
+ *                   because core frees it; use driver_set_override() to
+ *                   set or clear it.
  * @src: local address
  * @dst: destination address
  * @ept: the rpmsg endpoint of this channel
@@ -51,7 +53,7 @@ struct rpmsg_channel_info {
 struct rpmsg_device {
 	struct device dev;
 	struct rpmsg_device_id id;
-	char *driver_override;
+	const char *driver_override;
 	u32 src;
 	u32 dst;
 	struct rpmsg_endpoint *ept;
-- 
cgit v1.2.3


From f918cfc08c1755b9e54cd6effc923fa809045cf4 Mon Sep 17 00:00:00 2001
From: Ronak Jain <ronak.jain@xilinx.com>
Date: Wed, 6 Apr 2022 03:55:23 -0700
Subject: firmware: xilinx: add support for IOCTL and QUERY ID feature check

Add support to check if IOCTL ID or QUERY ID is supported in firmware
or not.

Signed-off-by: Ronak Jain <ronak.jain@xilinx.com>
Link: https://lore.kernel.org/r/1649242526-17493-2-git-send-email-ronak.jain@xilinx.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 62 +++++++++++++++++++++++++++++++++++-
 include/linux/firmware/xlnx-zynqmp.h | 11 +++++++
 2 files changed, 72 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index f21ece56695e..41ca41697790 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -36,8 +36,16 @@
 /* BOOT_PIN_CTRL_MASK- out_val[11:8], out_en[3:0] */
 #define CRL_APB_BOOTPIN_CTRL_MASK	0xF0FU
 
+/* IOCTL/QUERY feature payload size */
+#define FEATURE_PAYLOAD_SIZE		2
+
+/* Firmware feature check version mask */
+#define FIRMWARE_VERSION_MASK		GENMASK(15, 0)
+
 static bool feature_check_enabled;
 static DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER);
+static u32 ioctl_features[FEATURE_PAYLOAD_SIZE];
+static u32 query_features[FEATURE_PAYLOAD_SIZE];
 
 static struct platform_device *em_dev;
 
@@ -168,7 +176,8 @@ static noinline int do_fw_call_hvc(u64 arg0, u64 arg1, u64 arg2,
 }
 
 /**
- * zynqmp_pm_feature() - Check weather given feature is supported or not
+ * zynqmp_pm_feature() - Check whether given feature is supported or not and
+ *			 store supported IOCTL/QUERY ID mask
  * @api_id:		API ID to check
  *
  * Return: Returns status, either success or error+reason
@@ -208,10 +217,61 @@ int zynqmp_pm_feature(const u32 api_id)
 	feature_data->feature_status = ret;
 	hash_add(pm_api_features_map, &feature_data->hentry, api_id);
 
+	if (api_id == PM_IOCTL)
+		/* Store supported IOCTL IDs mask */
+		memcpy(ioctl_features, &ret_payload[2], FEATURE_PAYLOAD_SIZE * 4);
+	else if (api_id == PM_QUERY_DATA)
+		/* Store supported QUERY IDs mask */
+		memcpy(query_features, &ret_payload[2], FEATURE_PAYLOAD_SIZE * 4);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_feature);
 
+/**
+ * zynqmp_pm_is_function_supported() - Check whether given IOCTL/QUERY function
+ *				       is supported or not
+ * @api_id:		PM_IOCTL or PM_QUERY_DATA
+ * @id:			IOCTL or QUERY function IDs
+ *
+ * Return: Returns status, either success or error+reason
+ */
+int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id)
+{
+	int ret;
+	u32 *bit_mask;
+
+	/* Input arguments validation */
+	if (id >= 64 || (api_id != PM_IOCTL && api_id != PM_QUERY_DATA))
+		return -EINVAL;
+
+	/* Check feature check API version */
+	ret = zynqmp_pm_feature(PM_FEATURE_CHECK);
+	if (ret < 0)
+		return ret;
+
+	/* Check if feature check version 2 is supported or not */
+	if ((ret & FIRMWARE_VERSION_MASK) == PM_API_VERSION_2) {
+		/*
+		 * Call feature check for IOCTL/QUERY API to get IOCTL ID or
+		 * QUERY ID feature status.
+		 */
+		ret = zynqmp_pm_feature(api_id);
+		if (ret < 0)
+			return ret;
+
+		bit_mask = (api_id == PM_IOCTL) ? ioctl_features : query_features;
+
+		if ((bit_mask[(id / 32)] & BIT((id % 32))) == 0U)
+			return -EOPNOTSUPP;
+	} else {
+		return -ENODATA;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(zynqmp_pm_is_function_supported);
+
 /**
  * zynqmp_pm_invoke_fn() - Invoke the system-level platform management layer
  *			   caller function depending on the configuration
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 14f00a7672d1..1ec73d5352c3 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -29,6 +29,11 @@
 
 /* SMC SIP service Call Function Identifier Prefix */
 #define PM_SIP_SVC			0xC2000000
+
+/* PM API versions */
+#define PM_API_VERSION_2	2
+
+/* ATF only commands */
 #define PM_GET_TRUSTZONE_VERSION	0xa03
 #define PM_SET_SUSPEND_MODE		0xa02
 #define GET_CALLBACK_DATA		0xa01
@@ -460,6 +465,7 @@ int zynqmp_pm_load_pdi(const u32 src, const u64 address);
 int zynqmp_pm_register_notifier(const u32 node, const u32 event,
 				const u32 wake, const u32 enable);
 int zynqmp_pm_feature(const u32 api_id);
+int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id);
 int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value);
 int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, u32 *payload);
 #else
@@ -678,6 +684,11 @@ static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id)
 {
 	return -ENODEV;
-- 
cgit v1.2.3


From faebd693c59387b7b765fab64b543855e15a91b4 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 21 Apr 2022 23:28:36 +0206
Subject: printk: rename cpulock functions

Since the printk cpulock is CPU-reentrant and since it is used
in all contexts, its usage must be carefully considered and
most likely will require programming locklessly. To avoid
mistaking the printk cpulock as a typical lock, rename it to
cpu_sync. The main functions then become:

    printk_cpu_sync_get_irqsave(flags);
    printk_cpu_sync_put_irqrestore(flags);

Add extra notes of caution in the function description to help
developers understand the requirements for correct usage.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20220421212250.565456-2-john.ogness@linutronix.de
---
 include/linux/printk.h | 54 +++++++++++++++++++++++---------------
 kernel/printk/printk.c | 71 +++++++++++++++++++++++++-------------------------
 lib/dump_stack.c       |  4 +--
 lib/nmi_backtrace.c    |  4 +--
 4 files changed, 73 insertions(+), 60 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/printk.h b/include/linux/printk.h
index 1522df223c0f..859323a52985 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -277,43 +277,55 @@ static inline void printk_trigger_flush(void)
 #endif
 
 #ifdef CONFIG_SMP
-extern int __printk_cpu_trylock(void);
-extern void __printk_wait_on_cpu_lock(void);
-extern void __printk_cpu_unlock(void);
+extern int __printk_cpu_sync_try_get(void);
+extern void __printk_cpu_sync_wait(void);
+extern void __printk_cpu_sync_put(void);
 
 /**
- * printk_cpu_lock_irqsave() - Acquire the printk cpu-reentrant spinning
- *                             lock and disable interrupts.
+ * printk_cpu_sync_get_irqsave() - Acquire the printk cpu-reentrant spinning
+ *                                 lock and disable interrupts.
  * @flags: Stack-allocated storage for saving local interrupt state,
- *         to be passed to printk_cpu_unlock_irqrestore().
+ *         to be passed to printk_cpu_sync_put_irqrestore().
  *
  * If the lock is owned by another CPU, spin until it becomes available.
  * Interrupts are restored while spinning.
+ *
+ * CAUTION: This function must be used carefully. It does not behave like a
+ * typical lock. Here are important things to watch out for...
+ *
+ *     * This function is reentrant on the same CPU. Therefore the calling
+ *       code must not assume exclusive access to data if code accessing the
+ *       data can run reentrant or within NMI context on the same CPU.
+ *
+ *     * If there exists usage of this function from NMI context, it becomes
+ *       unsafe to perform any type of locking or spinning to wait for other
+ *       CPUs after calling this function from any context. This includes
+ *       using spinlocks or any other busy-waiting synchronization methods.
  */
-#define printk_cpu_lock_irqsave(flags)		\
-	for (;;) {				\
-		local_irq_save(flags);		\
-		if (__printk_cpu_trylock())	\
-			break;			\
-		local_irq_restore(flags);	\
-		__printk_wait_on_cpu_lock();	\
+#define printk_cpu_sync_get_irqsave(flags)		\
+	for (;;) {					\
+		local_irq_save(flags);			\
+		if (__printk_cpu_sync_try_get())	\
+			break;				\
+		local_irq_restore(flags);		\
+		__printk_cpu_sync_wait();		\
 	}
 
 /**
- * printk_cpu_unlock_irqrestore() - Release the printk cpu-reentrant spinning
- *                                  lock and restore interrupts.
- * @flags: Caller's saved interrupt state, from printk_cpu_lock_irqsave().
+ * printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning
+ *                                    lock and restore interrupts.
+ * @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave().
  */
-#define printk_cpu_unlock_irqrestore(flags)	\
+#define printk_cpu_sync_put_irqrestore(flags)	\
 	do {					\
-		__printk_cpu_unlock();		\
+		__printk_cpu_sync_put();	\
 		local_irq_restore(flags);	\
-	} while (0)				\
+	} while (0)
 
 #else
 
-#define printk_cpu_lock_irqsave(flags) ((void)flags)
-#define printk_cpu_unlock_irqrestore(flags) ((void)flags)
+#define printk_cpu_sync_get_irqsave(flags) ((void)flags)
+#define printk_cpu_sync_put_irqrestore(flags) ((void)flags)
 
 #endif /* CONFIG_SMP */
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index da03c15ecc89..13a1eebe72af 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3667,26 +3667,26 @@ EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
 #endif
 
 #ifdef CONFIG_SMP
-static atomic_t printk_cpulock_owner = ATOMIC_INIT(-1);
-static atomic_t printk_cpulock_nested = ATOMIC_INIT(0);
+static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1);
+static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0);
 
 /**
- * __printk_wait_on_cpu_lock() - Busy wait until the printk cpu-reentrant
- *                               spinning lock is not owned by any CPU.
+ * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant
+ *                            spinning lock is not owned by any CPU.
  *
  * Context: Any context.
  */
-void __printk_wait_on_cpu_lock(void)
+void __printk_cpu_sync_wait(void)
 {
 	do {
 		cpu_relax();
-	} while (atomic_read(&printk_cpulock_owner) != -1);
+	} while (atomic_read(&printk_cpu_sync_owner) != -1);
 }
-EXPORT_SYMBOL(__printk_wait_on_cpu_lock);
+EXPORT_SYMBOL(__printk_cpu_sync_wait);
 
 /**
- * __printk_cpu_trylock() - Try to acquire the printk cpu-reentrant
- *                          spinning lock.
+ * __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant
+ *                               spinning lock.
  *
  * If no processor has the lock, the calling processor takes the lock and
  * becomes the owner. If the calling processor is already the owner of the
@@ -3695,7 +3695,7 @@ EXPORT_SYMBOL(__printk_wait_on_cpu_lock);
  * Context: Any context. Expects interrupts to be disabled.
  * Return: 1 on success, otherwise 0.
  */
-int __printk_cpu_trylock(void)
+int __printk_cpu_sync_try_get(void)
 {
 	int cpu;
 	int old;
@@ -3705,79 +3705,80 @@ int __printk_cpu_trylock(void)
 	/*
 	 * Guarantee loads and stores from this CPU when it is the lock owner
 	 * are _not_ visible to the previous lock owner. This pairs with
-	 * __printk_cpu_unlock:B.
+	 * __printk_cpu_sync_put:B.
 	 *
 	 * Memory barrier involvement:
 	 *
-	 * If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B, then
-	 * __printk_cpu_unlock:A can never read from __printk_cpu_trylock:B.
+	 * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B,
+	 * then __printk_cpu_sync_put:A can never read from
+	 * __printk_cpu_sync_try_get:B.
 	 *
 	 * Relies on:
 	 *
-	 * RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B
+	 * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B
 	 * of the previous CPU
 	 *    matching
-	 * ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B
-	 * of this CPU
+	 * ACQUIRE from __printk_cpu_sync_try_get:A to
+	 * __printk_cpu_sync_try_get:B of this CPU
 	 */
-	old = atomic_cmpxchg_acquire(&printk_cpulock_owner, -1,
-				     cpu); /* LMM(__printk_cpu_trylock:A) */
+	old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1,
+				     cpu); /* LMM(__printk_cpu_sync_try_get:A) */
 	if (old == -1) {
 		/*
 		 * This CPU is now the owner and begins loading/storing
-		 * data: LMM(__printk_cpu_trylock:B)
+		 * data: LMM(__printk_cpu_sync_try_get:B)
 		 */
 		return 1;
 
 	} else if (old == cpu) {
 		/* This CPU is already the owner. */
-		atomic_inc(&printk_cpulock_nested);
+		atomic_inc(&printk_cpu_sync_nested);
 		return 1;
 	}
 
 	return 0;
 }
-EXPORT_SYMBOL(__printk_cpu_trylock);
+EXPORT_SYMBOL(__printk_cpu_sync_try_get);
 
 /**
- * __printk_cpu_unlock() - Release the printk cpu-reentrant spinning lock.
+ * __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock.
  *
  * The calling processor must be the owner of the lock.
  *
  * Context: Any context. Expects interrupts to be disabled.
  */
-void __printk_cpu_unlock(void)
+void __printk_cpu_sync_put(void)
 {
-	if (atomic_read(&printk_cpulock_nested)) {
-		atomic_dec(&printk_cpulock_nested);
+	if (atomic_read(&printk_cpu_sync_nested)) {
+		atomic_dec(&printk_cpu_sync_nested);
 		return;
 	}
 
 	/*
 	 * This CPU is finished loading/storing data:
-	 * LMM(__printk_cpu_unlock:A)
+	 * LMM(__printk_cpu_sync_put:A)
 	 */
 
 	/*
 	 * Guarantee loads and stores from this CPU when it was the
 	 * lock owner are visible to the next lock owner. This pairs
-	 * with __printk_cpu_trylock:A.
+	 * with __printk_cpu_sync_try_get:A.
 	 *
 	 * Memory barrier involvement:
 	 *
-	 * If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B,
-	 * then __printk_cpu_trylock:B reads from __printk_cpu_unlock:A.
+	 * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B,
+	 * then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A.
 	 *
 	 * Relies on:
 	 *
-	 * RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B
+	 * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B
 	 * of this CPU
 	 *    matching
-	 * ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B
-	 * of the next CPU
+	 * ACQUIRE from __printk_cpu_sync_try_get:A to
+	 * __printk_cpu_sync_try_get:B of the next CPU
 	 */
-	atomic_set_release(&printk_cpulock_owner,
-			   -1); /* LMM(__printk_cpu_unlock:B) */
+	atomic_set_release(&printk_cpu_sync_owner,
+			   -1); /* LMM(__printk_cpu_sync_put:B) */
 }
-EXPORT_SYMBOL(__printk_cpu_unlock);
+EXPORT_SYMBOL(__printk_cpu_sync_put);
 #endif /* CONFIG_SMP */
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 6b7f1bf6715d..83471e81501a 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -102,9 +102,9 @@ asmlinkage __visible void dump_stack_lvl(const char *log_lvl)
 	 * Permit this cpu to perform nested stack dumps while serialising
 	 * against other CPUs
 	 */
-	printk_cpu_lock_irqsave(flags);
+	printk_cpu_sync_get_irqsave(flags);
 	__dump_stack(log_lvl);
-	printk_cpu_unlock_irqrestore(flags);
+	printk_cpu_sync_put_irqrestore(flags);
 }
 EXPORT_SYMBOL(dump_stack_lvl);
 
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 199ab201d501..d01aec6ae15c 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -99,7 +99,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 		 * Allow nested NMI backtraces while serializing
 		 * against other CPUs.
 		 */
-		printk_cpu_lock_irqsave(flags);
+		printk_cpu_sync_get_irqsave(flags);
 		if (!READ_ONCE(backtrace_idle) && regs && cpu_in_idle(instruction_pointer(regs))) {
 			pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n",
 				cpu, (void *)instruction_pointer(regs));
@@ -110,7 +110,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 			else
 				dump_stack();
 		}
-		printk_cpu_unlock_irqrestore(flags);
+		printk_cpu_sync_put_irqrestore(flags);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return true;
 	}
-- 
cgit v1.2.3


From f5343321b71ac0a1112adeab0ff90b239bad3a83 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 21 Apr 2022 23:28:37 +0206
Subject: printk: cpu sync always disable interrupts

The CPU sync functions are a NOP for !CONFIG_SMP. But for
!CONFIG_SMP they still need to disable interrupts in order to
preserve context within the CPU sync sections.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20220421212250.565456-3-john.ogness@linutronix.de
---
 include/linux/printk.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/printk.h b/include/linux/printk.h
index 859323a52985..b70a42f94031 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -281,9 +281,16 @@ extern int __printk_cpu_sync_try_get(void);
 extern void __printk_cpu_sync_wait(void);
 extern void __printk_cpu_sync_put(void);
 
+#else
+
+#define __printk_cpu_sync_try_get() true
+#define __printk_cpu_sync_wait()
+#define __printk_cpu_sync_put()
+#endif /* CONFIG_SMP */
+
 /**
- * printk_cpu_sync_get_irqsave() - Acquire the printk cpu-reentrant spinning
- *                                 lock and disable interrupts.
+ * printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk
+ *                                 cpu-reentrant spinning lock.
  * @flags: Stack-allocated storage for saving local interrupt state,
  *         to be passed to printk_cpu_sync_put_irqrestore().
  *
@@ -322,13 +329,6 @@ extern void __printk_cpu_sync_put(void);
 		local_irq_restore(flags);	\
 	} while (0)
 
-#else
-
-#define printk_cpu_sync_get_irqsave(flags) ((void)flags)
-#define printk_cpu_sync_put_irqrestore(flags) ((void)flags)
-
-#endif /* CONFIG_SMP */
-
 extern int kptr_restrict;
 
 /**
-- 
cgit v1.2.3


From a699449bb13b70b8bd10dc03ad7327ea3993221e Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 21 Apr 2022 23:28:44 +0206
Subject: printk: refactor and rework printing logic

Refactor/rework printing logic in order to prepare for moving to
threaded console printing.

- Move @console_seq into struct console so that the current
  "position" of each console can be tracked individually.

- Move @console_dropped into struct console so that the current drop
  count of each console can be tracked individually.

- Modify printing logic so that each console independently loads,
  prepares, and prints its next record.

- Remove exclusive_console logic. Since console positions are
  handled independently, replaying past records occurs naturally.

- Update the comments explaining why preemption is disabled while
  printing from printk() context.

With these changes, there is a change in behavior: the console
replaying the log (formerly exclusive console) will no longer block
other consoles. New messages appear on the other consoles while the
newly added console is still replaying.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20220421212250.565456-10-john.ogness@linutronix.de
---
 include/linux/console.h |   2 +
 kernel/printk/printk.c  | 441 +++++++++++++++++++++++++-----------------------
 2 files changed, 230 insertions(+), 213 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/console.h b/include/linux/console.h
index 7cd758a4f44e..8c1686e2c233 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -151,6 +151,8 @@ struct console {
 	int	cflag;
 	uint	ispeed;
 	uint	ospeed;
+	u64	seq;
+	unsigned long dropped;
 	void	*data;
 	struct	 console *next;
 };
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index e36d3ed41afa..3dea8bbaf402 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -280,11 +280,6 @@ static bool panic_in_progress(void)
  */
 static int console_locked, console_suspended;
 
-/*
- * If exclusive_console is non-NULL then only this console is to be printed to.
- */
-static struct console *exclusive_console;
-
 /*
  *	Array of consoles built from command line options (console=)
  */
@@ -374,12 +369,6 @@ static u64 syslog_seq;
 static size_t syslog_partial;
 static bool syslog_time;
 
-/* All 3 protected by @console_sem. */
-/* the next printk record to write to the console */
-static u64 console_seq;
-static u64 exclusive_console_stop_seq;
-static unsigned long console_dropped;
-
 struct latched_seq {
 	seqcount_latch_t	latch;
 	u64			val[2];
@@ -1933,47 +1922,26 @@ static int console_trylock_spinning(void)
 }
 
 /*
- * Call the console drivers, asking them to write out
- * log_buf[start] to log_buf[end - 1].
- * The console_lock must be held.
+ * Call the specified console driver, asking it to write out the specified
+ * text and length. For non-extended consoles, if any records have been
+ * dropped, a dropped message will be written out first.
  */
-static void call_console_drivers(const char *ext_text, size_t ext_len,
-				 const char *text, size_t len)
+static void call_console_driver(struct console *con, const char *text, size_t len)
 {
 	static char dropped_text[64];
-	size_t dropped_len = 0;
-	struct console *con;
+	size_t dropped_len;
 
 	trace_console_rcuidle(text, len);
 
-	if (!console_drivers)
-		return;
-
-	if (console_dropped) {
+	if (con->dropped && !(con->flags & CON_EXTENDED)) {
 		dropped_len = snprintf(dropped_text, sizeof(dropped_text),
 				       "** %lu printk messages dropped **\n",
-				       console_dropped);
-		console_dropped = 0;
+				       con->dropped);
+		con->dropped = 0;
+		con->write(con, dropped_text, dropped_len);
 	}
 
-	for_each_console(con) {
-		if (exclusive_console && con != exclusive_console)
-			continue;
-		if (!(con->flags & CON_ENABLED))
-			continue;
-		if (!con->write)
-			continue;
-		if (!cpu_online(smp_processor_id()) &&
-		    !(con->flags & CON_ANYTIME))
-			continue;
-		if (con->flags & CON_EXTENDED)
-			con->write(con, ext_text, ext_len);
-		else {
-			if (dropped_len)
-				con->write(con, dropped_text, dropped_len);
-			con->write(con, text, len);
-		}
-	}
+	con->write(con, text, len);
 }
 
 /*
@@ -2283,15 +2251,18 @@ asmlinkage int vprintk_emit(int facility, int level,
 	/* If called from the scheduler, we can not call up(). */
 	if (!in_sched) {
 		/*
-		 * Disable preemption to avoid being preempted while holding
-		 * console_sem which would prevent anyone from printing to
-		 * console
+		 * The caller may be holding system-critical or
+		 * timing-sensitive locks. Disable preemption during
+		 * printing of all remaining records to all consoles so that
+		 * this context can return as soon as possible. Hopefully
+		 * another printk() caller will take over the printing.
 		 */
 		preempt_disable();
 		/*
 		 * Try to acquire and then immediately release the console
-		 * semaphore.  The release will print out buffers and wake up
-		 * /dev/kmsg and syslog() users.
+		 * semaphore. The release will print out buffers. With the
+		 * spinning variant, this context tries to take over the
+		 * printing from another printing context.
 		 */
 		if (console_trylock_spinning())
 			console_unlock();
@@ -2329,11 +2300,9 @@ EXPORT_SYMBOL(_printk);
 
 #define prb_read_valid(rb, seq, r)	false
 #define prb_first_valid_seq(rb)		0
+#define prb_next_seq(rb)		0
 
 static u64 syslog_seq;
-static u64 console_seq;
-static u64 exclusive_console_stop_seq;
-static unsigned long console_dropped;
 
 static size_t record_print_text(const struct printk_record *r,
 				bool syslog, bool time)
@@ -2350,8 +2319,7 @@ static ssize_t msg_print_ext_body(char *buf, size_t size,
 				  struct dev_printk_info *dev_info) { return 0; }
 static void console_lock_spinning_enable(void) { }
 static int console_lock_spinning_disable_and_check(void) { return 0; }
-static void call_console_drivers(const char *ext_text, size_t ext_len,
-				 const char *text, size_t len) {}
+static void call_console_driver(struct console *con, const char *text, size_t len) { }
 static bool suppress_message_printing(int level) { return false; }
 
 #endif /* CONFIG_PRINTK */
@@ -2621,22 +2589,6 @@ int is_console_locked(void)
 }
 EXPORT_SYMBOL(is_console_locked);
 
-/*
- * Check if we have any console that is capable of printing while cpu is
- * booting or shutting down. Requires console_sem.
- */
-static int have_callable_console(void)
-{
-	struct console *con;
-
-	for_each_console(con)
-		if ((con->flags & CON_ENABLED) &&
-				(con->flags & CON_ANYTIME))
-			return 1;
-
-	return 0;
-}
-
 /*
  * Return true when this CPU should unlock console_sem without pushing all
  * messages to the console. This reduces the chance that the console is
@@ -2657,15 +2609,182 @@ static bool abandon_console_lock_in_panic(void)
 }
 
 /*
- * Can we actually use the console at this time on this cpu?
+ * Check if the given console is currently capable and allowed to print
+ * records.
+ *
+ * Requires the console_lock.
+ */
+static inline bool console_is_usable(struct console *con)
+{
+	if (!(con->flags & CON_ENABLED))
+		return false;
+
+	if (!con->write)
+		return false;
+
+	/*
+	 * Console drivers may assume that per-cpu resources have been
+	 * allocated. So unless they're explicitly marked as being able to
+	 * cope (CON_ANYTIME) don't call them until this CPU is officially up.
+	 */
+	if (!cpu_online(raw_smp_processor_id()) &&
+	    !(con->flags & CON_ANYTIME))
+		return false;
+
+	return true;
+}
+
+static void __console_unlock(void)
+{
+	console_locked = 0;
+	up_console_sem();
+}
+
+/*
+ * Print one record for the given console. The record printed is whatever
+ * record is the next available record for the given console.
+ *
+ * @handover will be set to true if a printk waiter has taken over the
+ * console_lock, in which case the caller is no longer holding the
+ * console_lock. Otherwise it is set to false.
+ *
+ * Returns false if the given console has no next record to print, otherwise
+ * true.
  *
- * Console drivers may assume that per-cpu resources have been allocated. So
- * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't
- * call them until this CPU is officially up.
+ * Requires the console_lock.
  */
-static inline int can_use_console(void)
+static bool console_emit_next_record(struct console *con, bool *handover)
 {
-	return cpu_online(raw_smp_processor_id()) || have_callable_console();
+	static char ext_text[CONSOLE_EXT_LOG_MAX];
+	static char text[CONSOLE_LOG_MAX];
+	static int panic_console_dropped;
+	struct printk_info info;
+	struct printk_record r;
+	unsigned long flags;
+	char *write_text;
+	size_t len;
+
+	prb_rec_init_rd(&r, &info, text, sizeof(text));
+
+	*handover = false;
+
+	if (!prb_read_valid(prb, con->seq, &r))
+		return false;
+
+	if (con->seq != r.info->seq) {
+		con->dropped += r.info->seq - con->seq;
+		con->seq = r.info->seq;
+		if (panic_in_progress() && panic_console_dropped++ > 10) {
+			suppress_panic_printk = 1;
+			pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n");
+		}
+	}
+
+	/* Skip record that has level above the console loglevel. */
+	if (suppress_message_printing(r.info->level)) {
+		con->seq++;
+		goto skip;
+	}
+
+	if (con->flags & CON_EXTENDED) {
+		write_text = &ext_text[0];
+		len = info_print_ext_header(ext_text, sizeof(ext_text), r.info);
+		len += msg_print_ext_body(ext_text + len, sizeof(ext_text) - len,
+					  &r.text_buf[0], r.info->text_len, &r.info->dev_info);
+	} else {
+		write_text = &text[0];
+		len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time);
+	}
+
+	/*
+	 * While actively printing out messages, if another printk()
+	 * were to occur on another CPU, it may wait for this one to
+	 * finish. This task can not be preempted if there is a
+	 * waiter waiting to take over.
+	 *
+	 * Interrupts are disabled because the hand over to a waiter
+	 * must not be interrupted until the hand over is completed
+	 * (@console_waiter is cleared).
+	 */
+	printk_safe_enter_irqsave(flags);
+	console_lock_spinning_enable();
+
+	stop_critical_timings();	/* don't trace print latency */
+	call_console_driver(con, write_text, len);
+	start_critical_timings();
+
+	con->seq++;
+
+	*handover = console_lock_spinning_disable_and_check();
+	printk_safe_exit_irqrestore(flags);
+skip:
+	return true;
+}
+
+/*
+ * Print out all remaining records to all consoles.
+ *
+ * @do_cond_resched is set by the caller. It can be true only in schedulable
+ * context.
+ *
+ * @next_seq is set to the sequence number after the last available record.
+ * The value is valid only when this function returns true. It means that all
+ * usable consoles are completely flushed.
+ *
+ * @handover will be set to true if a printk waiter has taken over the
+ * console_lock, in which case the caller is no longer holding the
+ * console_lock. Otherwise it is set to false.
+ *
+ * Returns true when there was at least one usable console and all messages
+ * were flushed to all usable consoles. A returned false informs the caller
+ * that everything was not flushed (either there were no usable consoles or
+ * another context has taken over printing or it is a panic situation and this
+ * is not the panic CPU). Regardless the reason, the caller should assume it
+ * is not useful to immediately try again.
+ *
+ * Requires the console_lock.
+ */
+static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover)
+{
+	bool any_usable = false;
+	struct console *con;
+	bool any_progress;
+
+	*next_seq = 0;
+	*handover = false;
+
+	do {
+		any_progress = false;
+
+		for_each_console(con) {
+			bool progress;
+
+			if (!console_is_usable(con))
+				continue;
+			any_usable = true;
+
+			progress = console_emit_next_record(con, handover);
+			if (*handover)
+				return false;
+
+			/* Track the next of the highest seq flushed. */
+			if (con->seq > *next_seq)
+				*next_seq = con->seq;
+
+			if (!progress)
+				continue;
+			any_progress = true;
+
+			/* Allow panic_cpu to take over the consoles safely. */
+			if (abandon_console_lock_in_panic())
+				return false;
+
+			if (do_cond_resched)
+				cond_resched();
+		}
+	} while (any_progress);
+
+	return any_usable;
 }
 
 /**
@@ -2678,28 +2797,20 @@ static inline int can_use_console(void)
  * by printk().  If this is the case, console_unlock(); emits
  * the output prior to releasing the lock.
  *
- * If there is output waiting, we wake /dev/kmsg and syslog() users.
- *
  * console_unlock(); may be called from any context.
  */
 void console_unlock(void)
 {
-	static char ext_text[CONSOLE_EXT_LOG_MAX];
-	static char text[CONSOLE_LOG_MAX];
-	static int panic_console_dropped;
-	unsigned long flags;
-	bool do_cond_resched, retry;
-	struct printk_info info;
-	struct printk_record r;
-	u64 __maybe_unused next_seq;
+	bool do_cond_resched;
+	bool handover;
+	bool flushed;
+	u64 next_seq;
 
 	if (console_suspended) {
 		up_console_sem();
 		return;
 	}
 
-	prb_rec_init_rd(&r, &info, text, sizeof(text));
-
 	/*
 	 * Console drivers are called with interrupts disabled, so
 	 * @console_may_schedule should be cleared before; however, we may
@@ -2708,125 +2819,34 @@ void console_unlock(void)
 	 * between lines if allowable.  Not doing so can cause a very long
 	 * scheduling stall on a slow console leading to RCU stall and
 	 * softlockup warnings which exacerbate the issue with more
-	 * messages practically incapacitating the system.
-	 *
-	 * console_trylock() is not able to detect the preemptive
-	 * context reliably. Therefore the value must be stored before
-	 * and cleared after the "again" goto label.
+	 * messages practically incapacitating the system. Therefore, create
+	 * a local to use for the printing loop.
 	 */
 	do_cond_resched = console_may_schedule;
-again:
-	console_may_schedule = 0;
-
-	/*
-	 * We released the console_sem lock, so we need to recheck if
-	 * cpu is online and (if not) is there at least one CON_ANYTIME
-	 * console.
-	 */
-	if (!can_use_console()) {
-		console_locked = 0;
-		up_console_sem();
-		return;
-	}
 
-	for (;;) {
-		size_t ext_len = 0;
-		int handover;
-		size_t len;
-
-skip:
-		if (!prb_read_valid(prb, console_seq, &r))
-			break;
-
-		if (console_seq != r.info->seq) {
-			console_dropped += r.info->seq - console_seq;
-			console_seq = r.info->seq;
-			if (panic_in_progress() && panic_console_dropped++ > 10) {
-				suppress_panic_printk = 1;
-				pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n");
-			}
-		}
-
-		if (suppress_message_printing(r.info->level)) {
-			/*
-			 * Skip record we have buffered and already printed
-			 * directly to the console when we received it, and
-			 * record that has level above the console loglevel.
-			 */
-			console_seq++;
-			goto skip;
-		}
+	do {
+		console_may_schedule = 0;
 
-		/* Output to all consoles once old messages replayed. */
-		if (unlikely(exclusive_console &&
-			     console_seq >= exclusive_console_stop_seq)) {
-			exclusive_console = NULL;
-		}
+		flushed = console_flush_all(do_cond_resched, &next_seq, &handover);
+		if (!handover)
+			__console_unlock();
 
 		/*
-		 * Handle extended console text first because later
-		 * record_print_text() will modify the record buffer in-place.
+		 * Abort if there was a failure to flush all messages to all
+		 * usable consoles. Either it is not possible to flush (in
+		 * which case it would be an infinite loop of retrying) or
+		 * another context has taken over printing.
 		 */
-		if (nr_ext_console_drivers) {
-			ext_len = info_print_ext_header(ext_text,
-						sizeof(ext_text),
-						r.info);
-			ext_len += msg_print_ext_body(ext_text + ext_len,
-						sizeof(ext_text) - ext_len,
-						&r.text_buf[0],
-						r.info->text_len,
-						&r.info->dev_info);
-		}
-		len = record_print_text(&r,
-				console_msg_format & MSG_FORMAT_SYSLOG,
-				printk_time);
-		console_seq++;
+		if (!flushed)
+			break;
 
 		/*
-		 * While actively printing out messages, if another printk()
-		 * were to occur on another CPU, it may wait for this one to
-		 * finish. This task can not be preempted if there is a
-		 * waiter waiting to take over.
-		 *
-		 * Interrupts are disabled because the hand over to a waiter
-		 * must not be interrupted until the hand over is completed
-		 * (@console_waiter is cleared).
+		 * Some context may have added new records after
+		 * console_flush_all() but before unlocking the console.
+		 * Re-check if there is a new record to flush. If the trylock
+		 * fails, another context is already handling the printing.
 		 */
-		printk_safe_enter_irqsave(flags);
-		console_lock_spinning_enable();
-
-		stop_critical_timings();	/* don't trace print latency */
-		call_console_drivers(ext_text, ext_len, text, len);
-		start_critical_timings();
-
-		handover = console_lock_spinning_disable_and_check();
-		printk_safe_exit_irqrestore(flags);
-		if (handover)
-			return;
-
-		/* Allow panic_cpu to take over the consoles safely */
-		if (abandon_console_lock_in_panic())
-			break;
-
-		if (do_cond_resched)
-			cond_resched();
-	}
-
-	/* Get consistent value of the next-to-be-used sequence number. */
-	next_seq = console_seq;
-
-	console_locked = 0;
-	up_console_sem();
-
-	/*
-	 * Someone could have filled up the buffer again, so re-check if there's
-	 * something to flush. In case we cannot trylock the console_sem again,
-	 * there's a new owner and the console_unlock() from them will do the
-	 * flush, no worries.
-	 */
-	retry = prb_read_valid(prb, next_seq, NULL);
-	if (retry && !abandon_console_lock_in_panic() && console_trylock())
-		goto again;
+	} while (prb_read_valid(prb, next_seq, NULL) && console_trylock());
 }
 EXPORT_SYMBOL(console_unlock);
 
@@ -2886,8 +2906,14 @@ void console_flush_on_panic(enum con_flush_mode mode)
 	console_trylock();
 	console_may_schedule = 0;
 
-	if (mode == CONSOLE_REPLAY_ALL)
-		console_seq = prb_first_valid_seq(prb);
+	if (mode == CONSOLE_REPLAY_ALL) {
+		struct console *c;
+		u64 seq;
+
+		seq = prb_first_valid_seq(prb);
+		for_each_console(c)
+			c->seq = seq;
+	}
 	console_unlock();
 }
 
@@ -3127,26 +3153,15 @@ void register_console(struct console *newcon)
 	if (newcon->flags & CON_EXTENDED)
 		nr_ext_console_drivers++;
 
+	newcon->dropped = 0;
 	if (newcon->flags & CON_PRINTBUFFER) {
-		/*
-		 * console_unlock(); will print out the buffered messages
-		 * for us.
-		 *
-		 * We're about to replay the log buffer.  Only do this to the
-		 * just-registered console to avoid excessive message spam to
-		 * the already-registered consoles.
-		 *
-		 * Set exclusive_console with disabled interrupts to reduce
-		 * race window with eventual console_flush_on_panic() that
-		 * ignores console_lock.
-		 */
-		exclusive_console = newcon;
-		exclusive_console_stop_seq = console_seq;
-
 		/* Get a consistent copy of @syslog_seq. */
 		mutex_lock(&syslog_lock);
-		console_seq = syslog_seq;
+		newcon->seq = syslog_seq;
 		mutex_unlock(&syslog_lock);
+	} else {
+		/* Begin with next message. */
+		newcon->seq = prb_next_seq(prb);
 	}
 	console_unlock();
 	console_sysfs_notify();
-- 
cgit v1.2.3


From 3b604ca81202eea2a917eb6491e90f610fba0ec7 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 21 Apr 2022 23:28:46 +0206
Subject: printk: add pr_flush()

Provide a might-sleep function to allow waiting for console printers
to catch up to the latest logged message.

Use pr_flush() whenever it is desirable to get buffered messages
printed before continuing: suspend_console(), resume_console(),
console_stop(), console_start(), console_unblank().

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20220421212250.565456-12-john.ogness@linutronix.de
---
 include/linux/printk.h |  7 +++++
 kernel/printk/printk.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 90 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/printk.h b/include/linux/printk.h
index b70a42f94031..091fba7283e1 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -170,6 +170,8 @@ extern void __printk_safe_exit(void);
 #define printk_deferred_enter __printk_safe_enter
 #define printk_deferred_exit __printk_safe_exit
 
+extern bool pr_flush(int timeout_ms, bool reset_on_progress);
+
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
  * with all other unrelated printk_ratelimit() callsites.  Instead use
@@ -220,6 +222,11 @@ static inline void printk_deferred_exit(void)
 {
 }
 
+static inline bool pr_flush(int timeout_ms, bool reset_on_progress)
+{
+	return true;
+}
+
 static inline int printk_ratelimit(void)
 {
 	return 0;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index dec5355c5b5b..a06999d55278 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2296,6 +2296,8 @@ asmlinkage __visible int _printk(const char *fmt, ...)
 }
 EXPORT_SYMBOL(_printk);
 
+static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress);
+
 #else /* CONFIG_PRINTK */
 
 #define CONSOLE_LOG_MAX		0
@@ -2328,6 +2330,7 @@ static void call_console_driver(struct console *con, const char *text, size_t le
 {
 }
 static bool suppress_message_printing(int level) { return false; }
+static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }
 
 #endif /* CONFIG_PRINTK */
 
@@ -2515,6 +2518,7 @@ void suspend_console(void)
 	if (!console_suspend_enabled)
 		return;
 	pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
+	pr_flush(1000, true);
 	console_lock();
 	console_suspended = 1;
 	up_console_sem();
@@ -2527,6 +2531,7 @@ void resume_console(void)
 	down_console_sem();
 	console_suspended = 0;
 	console_unlock();
+	pr_flush(1000, true);
 }
 
 /**
@@ -2912,6 +2917,9 @@ void console_unblank(void)
 		if ((c->flags & CON_ENABLED) && c->unblank)
 			c->unblank();
 	console_unlock();
+
+	if (!oops_in_progress)
+		pr_flush(1000, true);
 }
 
 /**
@@ -2970,6 +2978,7 @@ struct tty_driver *console_device(int *index)
  */
 void console_stop(struct console *console)
 {
+	__pr_flush(console, 1000, true);
 	console_lock();
 	console->flags &= ~CON_ENABLED;
 	console_unlock();
@@ -2981,6 +2990,7 @@ void console_start(struct console *console)
 	console_lock();
 	console->flags |= CON_ENABLED;
 	console_unlock();
+	__pr_flush(console, 1000, true);
 }
 EXPORT_SYMBOL(console_start);
 
@@ -3352,6 +3362,79 @@ static int __init printk_late_init(void)
 late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
+/* If @con is specified, only wait for that console. Otherwise wait for all. */
+static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress)
+{
+	int remaining = timeout_ms;
+	struct console *c;
+	u64 last_diff = 0;
+	u64 printk_seq;
+	u64 diff;
+	u64 seq;
+
+	might_sleep();
+
+	seq = prb_next_seq(prb);
+
+	for (;;) {
+		diff = 0;
+
+		console_lock();
+		for_each_console(c) {
+			if (con && con != c)
+				continue;
+			if (!console_is_usable(c))
+				continue;
+			printk_seq = c->seq;
+			if (printk_seq < seq)
+				diff += seq - printk_seq;
+		}
+		console_unlock();
+
+		if (diff != last_diff && reset_on_progress)
+			remaining = timeout_ms;
+
+		if (diff == 0 || remaining == 0)
+			break;
+
+		if (remaining < 0) {
+			/* no timeout limit */
+			msleep(100);
+		} else if (remaining < 100) {
+			msleep(remaining);
+			remaining = 0;
+		} else {
+			msleep(100);
+			remaining -= 100;
+		}
+
+		last_diff = diff;
+	}
+
+	return (diff == 0);
+}
+
+/**
+ * pr_flush() - Wait for printing threads to catch up.
+ *
+ * @timeout_ms:        The maximum time (in ms) to wait.
+ * @reset_on_progress: Reset the timeout if forward progress is seen.
+ *
+ * A value of 0 for @timeout_ms means no waiting will occur. A value of -1
+ * represents infinite waiting.
+ *
+ * If @reset_on_progress is true, the timeout will be reset whenever any
+ * printer has been seen to make some forward progress.
+ *
+ * Context: Process context. May sleep while acquiring console lock.
+ * Return: true if all enabled printers are caught up.
+ */
+bool pr_flush(int timeout_ms, bool reset_on_progress)
+{
+	return __pr_flush(NULL, timeout_ms, reset_on_progress);
+}
+EXPORT_SYMBOL(pr_flush);
+
 /*
  * Delayed printk version, for scheduler-internal messages:
  */
-- 
cgit v1.2.3


From 2bb2b7b57f81255c13f4395ea911d6bdc70c9fe2 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 21 Apr 2022 23:28:47 +0206
Subject: printk: add functions to prefer direct printing

Once kthread printing is available, console printing will no longer
occur in the context of the printk caller. However, there are some
special contexts where it is desirable for the printk caller to
directly print out kernel messages. Using pr_flush() to wait for
threaded printers is only possible if the caller is in a sleepable
context and the kthreads are active. That is not always the case.

Introduce printk_prefer_direct_enter() and printk_prefer_direct_exit()
functions to explicitly (and globally) activate/deactivate preferred
direct console printing. The term "direct console printing" refers to
printing to all enabled consoles from the context of the printk
caller. The term "prefer" is used because this type of printing is
only best effort. If the console is currently locked or other
printers are already actively printing, the printk caller will need
to rely on the other contexts to handle the printing.

This preferred direct printing is how all printing has been handled
until now (unless it was explicitly deferred).

When kthread printing is introduced, there may be some unanticipated
problems due to kthreads being unable to flush important messages.
In order to minimize such risks, preferred direct printing is
activated for the primary important messages when the system
experiences general types of major errors. These are:

 - emergency reboot/shutdown
 - cpu and rcu stalls
 - hard and soft lockups
 - hung tasks
 - warn
 - sysrq

Note that since kthread printing does not yet exist, no behavior
changes result from this commit. This is only implementing the
counter and marking the various places where preferred direct
printing is active.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org> # for RCU
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20220421212250.565456-13-john.ogness@linutronix.de
---
 drivers/tty/sysrq.c     |  2 ++
 include/linux/printk.h  | 11 +++++++++++
 kernel/hung_task.c      | 11 ++++++++++-
 kernel/panic.c          |  4 ++++
 kernel/printk/printk.c  | 28 ++++++++++++++++++++++++++++
 kernel/rcu/tree_stall.h |  2 ++
 kernel/reboot.c         | 14 +++++++++++++-
 kernel/watchdog.c       |  4 ++++
 kernel/watchdog_hld.c   |  4 ++++
 9 files changed, 78 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index bbfd004449b5..2884cd638d64 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -578,6 +578,7 @@ void __handle_sysrq(int key, bool check_mask)
 
 	rcu_sysrq_start();
 	rcu_read_lock();
+	printk_prefer_direct_enter();
 	/*
 	 * Raise the apparent loglevel to maximum so that the sysrq header
 	 * is shown to provide the user with positive feedback.  We do not
@@ -619,6 +620,7 @@ void __handle_sysrq(int key, bool check_mask)
 		pr_cont("\n");
 		console_loglevel = orig_log_level;
 	}
+	printk_prefer_direct_exit();
 	rcu_read_unlock();
 	rcu_sysrq_end();
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 091fba7283e1..cd26aab0ab2a 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -170,6 +170,9 @@ extern void __printk_safe_exit(void);
 #define printk_deferred_enter __printk_safe_enter
 #define printk_deferred_exit __printk_safe_exit
 
+extern void printk_prefer_direct_enter(void);
+extern void printk_prefer_direct_exit(void);
+
 extern bool pr_flush(int timeout_ms, bool reset_on_progress);
 
 /*
@@ -222,6 +225,14 @@ static inline void printk_deferred_exit(void)
 {
 }
 
+static inline void printk_prefer_direct_enter(void)
+{
+}
+
+static inline void printk_prefer_direct_exit(void)
+{
+}
+
 static inline bool pr_flush(int timeout_ms, bool reset_on_progress)
 {
 	return true;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 52501e5f7655..02a65d554340 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -127,6 +127,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 	 * complain:
 	 */
 	if (sysctl_hung_task_warnings) {
+		printk_prefer_direct_enter();
+
 		if (sysctl_hung_task_warnings > 0)
 			sysctl_hung_task_warnings--;
 		pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n",
@@ -142,6 +144,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 
 		if (sysctl_hung_task_all_cpu_backtrace)
 			hung_task_show_all_bt = true;
+
+		printk_prefer_direct_exit();
 	}
 
 	touch_nmi_watchdog();
@@ -204,12 +208,17 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 	}
  unlock:
 	rcu_read_unlock();
-	if (hung_task_show_lock)
+	if (hung_task_show_lock) {
+		printk_prefer_direct_enter();
 		debug_show_all_locks();
+		printk_prefer_direct_exit();
+	}
 
 	if (hung_task_show_all_bt) {
 		hung_task_show_all_bt = false;
+		printk_prefer_direct_enter();
 		trigger_all_cpu_backtrace();
+		printk_prefer_direct_exit();
 	}
 
 	if (hung_task_call_panic)
diff --git a/kernel/panic.c b/kernel/panic.c
index 55b50e052ec3..7d422597403f 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -560,6 +560,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 {
 	disable_trace_on_warning();
 
+	printk_prefer_direct_enter();
+
 	if (file)
 		pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n",
 			raw_smp_processor_id(), current->pid, file, line,
@@ -597,6 +599,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 
 	/* Just a warning, don't kill lockdep. */
 	add_taint(taint, LOCKDEP_STILL_OK);
+
+	printk_prefer_direct_exit();
 }
 
 #ifndef __WARN_FLAGS
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a06999d55278..ed7f738261cc 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -362,6 +362,34 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
 static DEFINE_MUTEX(syslog_lock);
 
 #ifdef CONFIG_PRINTK
+static atomic_t printk_prefer_direct = ATOMIC_INIT(0);
+
+/**
+ * printk_prefer_direct_enter - cause printk() calls to attempt direct
+ *                              printing to all enabled consoles
+ *
+ * Since it is not possible to call into the console printing code from any
+ * context, there is no guarantee that direct printing will occur.
+ *
+ * This globally effects all printk() callers.
+ *
+ * Context: Any context.
+ */
+void printk_prefer_direct_enter(void)
+{
+	atomic_inc(&printk_prefer_direct);
+}
+
+/**
+ * printk_prefer_direct_exit - restore printk() behavior
+ *
+ * Context: Any context.
+ */
+void printk_prefer_direct_exit(void)
+{
+	WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0);
+}
+
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* All 3 protected by @syslog_lock. */
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 0c5d8516516a..d612707c2ed0 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -619,6 +619,7 @@ static void print_cpu_stall(unsigned long gps)
 	 * See Documentation/RCU/stallwarn.rst for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
+	printk_prefer_direct_enter();
 	trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected"));
 	pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
 	raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
@@ -656,6 +657,7 @@ static void print_cpu_stall(unsigned long gps)
 	 */
 	set_tsk_need_resched(current);
 	set_preempt_need_resched();
+	printk_prefer_direct_exit();
 }
 
 static void check_cpu_stall(struct rcu_data *rdp)
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 6bcc5d6a6572..4177645e74d6 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -447,9 +447,11 @@ static int __orderly_reboot(void)
 	ret = run_cmd(reboot_cmd);
 
 	if (ret) {
+		printk_prefer_direct_enter();
 		pr_warn("Failed to start orderly reboot: forcing the issue\n");
 		emergency_sync();
 		kernel_restart(NULL);
+		printk_prefer_direct_exit();
 	}
 
 	return ret;
@@ -462,6 +464,7 @@ static int __orderly_poweroff(bool force)
 	ret = run_cmd(poweroff_cmd);
 
 	if (ret && force) {
+		printk_prefer_direct_enter();
 		pr_warn("Failed to start orderly shutdown: forcing the issue\n");
 
 		/*
@@ -471,6 +474,7 @@ static int __orderly_poweroff(bool force)
 		 */
 		emergency_sync();
 		kernel_power_off();
+		printk_prefer_direct_exit();
 	}
 
 	return ret;
@@ -528,6 +532,8 @@ EXPORT_SYMBOL_GPL(orderly_reboot);
  */
 static void hw_failure_emergency_poweroff_func(struct work_struct *work)
 {
+	printk_prefer_direct_enter();
+
 	/*
 	 * We have reached here after the emergency shutdown waiting period has
 	 * expired. This means orderly_poweroff has not been able to shut off
@@ -544,6 +550,8 @@ static void hw_failure_emergency_poweroff_func(struct work_struct *work)
 	 */
 	pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n");
 	emergency_restart();
+
+	printk_prefer_direct_exit();
 }
 
 static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work,
@@ -582,11 +590,13 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced)
 {
 	static atomic_t allow_proceed = ATOMIC_INIT(1);
 
+	printk_prefer_direct_enter();
+
 	pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason);
 
 	/* Shutdown should be initiated only once. */
 	if (!atomic_dec_and_test(&allow_proceed))
-		return;
+		goto out;
 
 	/*
 	 * Queue a backup emergency shutdown in the event of
@@ -594,6 +604,8 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced)
 	 */
 	hw_failure_emergency_poweroff(ms_until_forced);
 	orderly_poweroff(true);
+out:
+	printk_prefer_direct_exit();
 }
 EXPORT_SYMBOL_GPL(hw_protection_shutdown);
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 9166220457bc..40024e03d422 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -424,6 +424,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		/* Start period for the next softlockup warning. */
 		update_report_ts();
 
+		printk_prefer_direct_enter();
+
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
@@ -442,6 +444,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
 		if (softlockup_panic)
 			panic("softlockup: hung tasks");
+
+		printk_prefer_direct_exit();
 	}
 
 	return HRTIMER_RESTART;
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 247bf0b1582c..701f35f0e2d4 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -135,6 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event,
 		if (__this_cpu_read(hard_watchdog_warn) == true)
 			return;
 
+		printk_prefer_direct_enter();
+
 		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n",
 			 this_cpu);
 		print_modules();
@@ -155,6 +157,8 @@ static void watchdog_overflow_callback(struct perf_event *event,
 		if (hardlockup_panic)
 			nmi_panic(regs, "Hard LOCKUP");
 
+		printk_prefer_direct_exit();
+
 		__this_cpu_write(hard_watchdog_warn, true);
 		return;
 	}
-- 
cgit v1.2.3


From 09c5ba0aa2fcfdadb17d045c3ee6f86d69270df7 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 21 Apr 2022 23:28:48 +0206
Subject: printk: add kthread console printers

Create a kthread for each console to perform console printing. During
normal operation (@system_state == SYSTEM_RUNNING), the kthread
printers are responsible for all printing on their respective
consoles.

During non-normal operation, console printing is done as it has been:
within the context of the printk caller or within irqwork triggered
by the printk caller, referred to as direct printing.

Since threaded console printers are responsible for all printing
during normal operation, this also includes messages generated via
deferred printk calls. If direct printing is in effect during a
deferred printk call, the queued irqwork will perform the direct
printing. To make it clear that this is the only time that the
irqwork will perform direct printing, rename the flag
PRINTK_PENDING_OUTPUT to PRINTK_PENDING_DIRECT_OUTPUT.

Threaded console printers synchronize against each other and against
console lockers by taking the console lock for each message that is
printed.

Note that the kthread printers do not care about direct printing.
They will always try to print if new records are available. They can
be blocked by direct printing, but will be woken again once direct
printing is finished.

Console unregistration is a bit tricky because the associated
kthread printer cannot be stopped while the console lock is held.
A policy is implemented that states: whichever task clears
con->thread (under the console lock) is responsible for stopping
the kthread. unregister_console() will clear con->thread while
the console lock is held and then stop the kthread after releasing
the console lock.

For consoles that have implemented the exit() callback, the kthread
is stopped before exit() is called.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20220421212250.565456-14-john.ogness@linutronix.de
---
 include/linux/console.h |   2 +
 kernel/printk/printk.c  | 329 ++++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 309 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/console.h b/include/linux/console.h
index 8c1686e2c233..9a251e70c090 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -153,6 +153,8 @@ struct console {
 	uint	ospeed;
 	u64	seq;
 	unsigned long dropped;
+	struct task_struct *thread;
+
 	void	*data;
 	struct	 console *next;
 };
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ed7f738261cc..e4cdc424c826 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -361,6 +361,13 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
 /* syslog_lock protects syslog_* variables and write access to clear_seq. */
 static DEFINE_MUTEX(syslog_lock);
 
+/*
+ * A flag to signify if printk_activate_kthreads() has already started the
+ * kthread printers. If true, any later registered consoles must start their
+ * own kthread directly. The flag is write protected by the console_lock.
+ */
+static bool printk_kthreads_available;
+
 #ifdef CONFIG_PRINTK
 static atomic_t printk_prefer_direct = ATOMIC_INIT(0);
 
@@ -390,6 +397,39 @@ void printk_prefer_direct_exit(void)
 	WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0);
 }
 
+/*
+ * Calling printk() always wakes kthread printers so that they can
+ * flush the new message to their respective consoles. Also, if direct
+ * printing is allowed, printk() tries to flush the messages directly.
+ *
+ * Direct printing is allowed in situations when the kthreads
+ * are not available or the system is in a problematic state.
+ *
+ * See the implementation about possible races.
+ */
+static inline bool allow_direct_printing(void)
+{
+	/*
+	 * Checking kthread availability is a possible race because the
+	 * kthread printers can become permanently disabled during runtime.
+	 * However, doing that requires holding the console_lock, so any
+	 * pending messages will be direct printed by console_unlock().
+	 */
+	if (!printk_kthreads_available)
+		return true;
+
+	/*
+	 * Prefer direct printing when the system is in a problematic state.
+	 * The context that sets this state will always see the updated value.
+	 * The other contexts do not care. Anyway, direct printing is just a
+	 * best effort. The direct output is only possible when console_lock
+	 * is not already taken and no kthread printers are actively printing.
+	 */
+	return (system_state > SYSTEM_RUNNING ||
+		oops_in_progress ||
+		atomic_read(&printk_prefer_direct));
+}
+
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* All 3 protected by @syslog_lock. */
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
@@ -2280,10 +2320,10 @@ asmlinkage int vprintk_emit(int facility, int level,
 	printed_len = vprintk_store(facility, level, dev_info, fmt, args);
 
 	/* If called from the scheduler, we can not call up(). */
-	if (!in_sched) {
+	if (!in_sched && allow_direct_printing()) {
 		/*
 		 * The caller may be holding system-critical or
-		 * timing-sensitive locks. Disable preemption during
+		 * timing-sensitive locks. Disable preemption during direct
 		 * printing of all remaining records to all consoles so that
 		 * this context can return as soon as possible. Hopefully
 		 * another printk() caller will take over the printing.
@@ -2326,6 +2366,8 @@ EXPORT_SYMBOL(_printk);
 
 static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress);
 
+static void printk_start_kthread(struct console *con);
+
 #else /* CONFIG_PRINTK */
 
 #define CONSOLE_LOG_MAX		0
@@ -2359,6 +2401,8 @@ static void call_console_driver(struct console *con, const char *text, size_t le
 }
 static bool suppress_message_printing(int level) { return false; }
 static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }
+static void printk_start_kthread(struct console *con) { }
+static bool allow_direct_printing(void) { return true; }
 
 #endif /* CONFIG_PRINTK */
 
@@ -2559,6 +2603,13 @@ void resume_console(void)
 	down_console_sem();
 	console_suspended = 0;
 	console_unlock();
+
+	/*
+	 * While suspended, new records may have been added to the
+	 * ringbuffer. Wake up the kthread printers to print them.
+	 */
+	wake_up_klogd();
+
 	pr_flush(1000, true);
 }
 
@@ -2577,6 +2628,9 @@ static int console_cpu_notify(unsigned int cpu)
 		/* If trylock fails, someone else is doing the printing */
 		if (console_trylock())
 			console_unlock();
+
+		/* Wake kthread printers. Some may have become usable. */
+		wake_up_klogd();
 	}
 	return 0;
 }
@@ -2648,18 +2702,9 @@ static bool abandon_console_lock_in_panic(void)
 	return atomic_read(&panic_cpu) != raw_smp_processor_id();
 }
 
-/*
- * Check if the given console is currently capable and allowed to print
- * records.
- *
- * Requires the console_lock.
- */
-static inline bool console_is_usable(struct console *con)
+static inline bool __console_is_usable(short flags)
 {
-	if (!(con->flags & CON_ENABLED))
-		return false;
-
-	if (!con->write)
+	if (!(flags & CON_ENABLED))
 		return false;
 
 	/*
@@ -2668,12 +2713,26 @@ static inline bool console_is_usable(struct console *con)
 	 * cope (CON_ANYTIME) don't call them until this CPU is officially up.
 	 */
 	if (!cpu_online(raw_smp_processor_id()) &&
-	    !(con->flags & CON_ANYTIME))
+	    !(flags & CON_ANYTIME))
 		return false;
 
 	return true;
 }
 
+/*
+ * Check if the given console is currently capable and allowed to print
+ * records.
+ *
+ * Requires the console_lock.
+ */
+static inline bool console_is_usable(struct console *con)
+{
+	if (!con->write)
+		return false;
+
+	return __console_is_usable(con->flags);
+}
+
 static void __console_unlock(void)
 {
 	console_locked = 0;
@@ -2786,8 +2845,8 @@ skip:
  * were flushed to all usable consoles. A returned false informs the caller
  * that everything was not flushed (either there were no usable consoles or
  * another context has taken over printing or it is a panic situation and this
- * is not the panic CPU). Regardless the reason, the caller should assume it
- * is not useful to immediately try again.
+ * is not the panic CPU or direct printing is not preferred). Regardless the
+ * reason, the caller should assume it is not useful to immediately try again.
  *
  * Requires the console_lock.
  */
@@ -2804,6 +2863,10 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove
 	*handover = false;
 
 	do {
+		/* Let the kthread printers do the work if they can. */
+		if (!allow_direct_printing())
+			return false;
+
 		any_progress = false;
 
 		for_each_console(con) {
@@ -3018,6 +3081,10 @@ void console_start(struct console *console)
 	console_lock();
 	console->flags |= CON_ENABLED;
 	console_unlock();
+
+	/* Wake the newly enabled kthread printer. */
+	wake_up_klogd();
+
 	__pr_flush(console, 1000, true);
 }
 EXPORT_SYMBOL(console_start);
@@ -3218,6 +3285,8 @@ void register_console(struct console *newcon)
 		nr_ext_console_drivers++;
 
 	newcon->dropped = 0;
+	newcon->thread = NULL;
+
 	if (newcon->flags & CON_PRINTBUFFER) {
 		/* Get a consistent copy of @syslog_seq. */
 		mutex_lock(&syslog_lock);
@@ -3227,6 +3296,10 @@ void register_console(struct console *newcon)
 		/* Begin with next message. */
 		newcon->seq = prb_next_seq(prb);
 	}
+
+	if (printk_kthreads_available)
+		printk_start_kthread(newcon);
+
 	console_unlock();
 	console_sysfs_notify();
 
@@ -3253,6 +3326,7 @@ EXPORT_SYMBOL(register_console);
 
 int unregister_console(struct console *console)
 {
+	struct task_struct *thd;
 	struct console *con;
 	int res;
 
@@ -3293,7 +3367,20 @@ int unregister_console(struct console *console)
 		console_drivers->flags |= CON_CONSDEV;
 
 	console->flags &= ~CON_ENABLED;
+
+	/*
+	 * console->thread can only be cleared under the console lock. But
+	 * stopping the thread must be done without the console lock. The
+	 * task that clears @thread is the task that stops the kthread.
+	 */
+	thd = console->thread;
+	console->thread = NULL;
+
 	console_unlock();
+
+	if (thd)
+		kthread_stop(thd);
+
 	console_sysfs_notify();
 
 	if (console->exit)
@@ -3389,6 +3476,20 @@ static int __init printk_late_init(void)
 }
 late_initcall(printk_late_init);
 
+static int __init printk_activate_kthreads(void)
+{
+	struct console *con;
+
+	console_lock();
+	printk_kthreads_available = true;
+	for_each_console(con)
+		printk_start_kthread(con);
+	console_unlock();
+
+	return 0;
+}
+early_initcall(printk_activate_kthreads);
+
 #if defined CONFIG_PRINTK
 /* If @con is specified, only wait for that console. Otherwise wait for all. */
 static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress)
@@ -3463,11 +3564,180 @@ bool pr_flush(int timeout_ms, bool reset_on_progress)
 }
 EXPORT_SYMBOL(pr_flush);
 
+static void __printk_fallback_preferred_direct(void)
+{
+	printk_prefer_direct_enter();
+	pr_err("falling back to preferred direct printing\n");
+	printk_kthreads_available = false;
+}
+
+/*
+ * Enter preferred direct printing, but never exit. Mark console threads as
+ * unavailable. The system is then forever in preferred direct printing and
+ * any printing threads will exit.
+ *
+ * Must *not* be called under console_lock. Use
+ * __printk_fallback_preferred_direct() if already holding console_lock.
+ */
+static void printk_fallback_preferred_direct(void)
+{
+	console_lock();
+	__printk_fallback_preferred_direct();
+	console_unlock();
+}
+
+static bool printer_should_wake(struct console *con, u64 seq)
+{
+	short flags;
+
+	if (kthread_should_stop() || !printk_kthreads_available)
+		return true;
+
+	if (console_suspended)
+		return false;
+
+	/*
+	 * This is an unsafe read from con->flags, but a false positive is
+	 * not a problem. Worst case it would allow the printer to wake up
+	 * although it is disabled. But the printer will notice that when
+	 * attempting to print and instead go back to sleep.
+	 */
+	flags = data_race(READ_ONCE(con->flags));
+
+	if (!__console_is_usable(flags))
+		return false;
+
+	return prb_read_valid(prb, seq, NULL);
+}
+
+static int printk_kthread_func(void *data)
+{
+	struct console *con = data;
+	char *dropped_text = NULL;
+	char *ext_text = NULL;
+	bool handover;
+	u64 seq = 0;
+	char *text;
+	int error;
+
+	text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL);
+	if (!text) {
+		con_printk(KERN_ERR, con, "failed to allocate text buffer\n");
+		printk_fallback_preferred_direct();
+		goto out;
+	}
+
+	if (con->flags & CON_EXTENDED) {
+		ext_text = kmalloc(CONSOLE_EXT_LOG_MAX, GFP_KERNEL);
+		if (!ext_text) {
+			con_printk(KERN_ERR, con, "failed to allocate ext_text buffer\n");
+			printk_fallback_preferred_direct();
+			goto out;
+		}
+	} else {
+		dropped_text = kmalloc(DROPPED_TEXT_MAX, GFP_KERNEL);
+		if (!dropped_text) {
+			con_printk(KERN_ERR, con, "failed to allocate dropped_text buffer\n");
+			printk_fallback_preferred_direct();
+			goto out;
+		}
+	}
+
+	con_printk(KERN_INFO, con, "printing thread started\n");
+
+	for (;;) {
+		/*
+		 * Guarantee this task is visible on the waitqueue before
+		 * checking the wake condition.
+		 *
+		 * The full memory barrier within set_current_state() of
+		 * prepare_to_wait_event() pairs with the full memory barrier
+		 * within wq_has_sleeper().
+		 *
+		 * This pairs with __wake_up_klogd:A.
+		 */
+		error = wait_event_interruptible(log_wait,
+				printer_should_wake(con, seq)); /* LMM(printk_kthread_func:A) */
+
+		if (kthread_should_stop() || !printk_kthreads_available)
+			break;
+
+		if (error)
+			continue;
+
+		console_lock();
+
+		if (console_suspended) {
+			up_console_sem();
+			continue;
+		}
+
+		if (!console_is_usable(con)) {
+			__console_unlock();
+			continue;
+		}
+
+		/*
+		 * Even though the printk kthread is always preemptible, it is
+		 * still not allowed to call cond_resched() from within
+		 * console drivers. The task may become non-preemptible in the
+		 * console driver call chain. For example, vt_console_print()
+		 * takes a spinlock and then can call into fbcon_redraw(),
+		 * which can conditionally invoke cond_resched().
+		 */
+		console_may_schedule = 0;
+		console_emit_next_record(con, text, ext_text, dropped_text, &handover);
+		if (handover)
+			continue;
+
+		seq = con->seq;
+
+		__console_unlock();
+	}
+
+	con_printk(KERN_INFO, con, "printing thread stopped\n");
+out:
+	kfree(dropped_text);
+	kfree(ext_text);
+	kfree(text);
+
+	console_lock();
+	/*
+	 * If this kthread is being stopped by another task, con->thread will
+	 * already be NULL. That is fine. The important thing is that it is
+	 * NULL after the kthread exits.
+	 */
+	con->thread = NULL;
+	console_unlock();
+
+	return 0;
+}
+
+/* Must be called under console_lock. */
+static void printk_start_kthread(struct console *con)
+{
+	/*
+	 * Do not start a kthread if there is no write() callback. The
+	 * kthreads assume the write() callback exists.
+	 */
+	if (!con->write)
+		return;
+
+	con->thread = kthread_run(printk_kthread_func, con,
+				  "pr/%s%d", con->name, con->index);
+	if (IS_ERR(con->thread)) {
+		con->thread = NULL;
+		con_printk(KERN_ERR, con, "unable to start printing thread\n");
+		__printk_fallback_preferred_direct();
+		return;
+	}
+}
+
 /*
  * Delayed printk version, for scheduler-internal messages:
  */
-#define PRINTK_PENDING_WAKEUP	0x01
-#define PRINTK_PENDING_OUTPUT	0x02
+#define PRINTK_PENDING_WAKEUP		0x01
+#define PRINTK_PENDING_DIRECT_OUTPUT	0x02
 
 static DEFINE_PER_CPU(int, printk_pending);
 
@@ -3475,10 +3745,14 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work)
 {
 	int pending = this_cpu_xchg(printk_pending, 0);
 
-	if (pending & PRINTK_PENDING_OUTPUT) {
+	if (pending & PRINTK_PENDING_DIRECT_OUTPUT) {
+		printk_prefer_direct_enter();
+
 		/* If trylock fails, someone else is doing the printing */
 		if (console_trylock())
 			console_unlock();
+
+		printk_prefer_direct_exit();
 	}
 
 	if (pending & PRINTK_PENDING_WAKEUP)
@@ -3503,10 +3777,11 @@ static void __wake_up_klogd(int val)
 	 * prepare_to_wait_event(), which is called after ___wait_event() adds
 	 * the waiter but before it has checked the wait condition.
 	 *
-	 * This pairs with devkmsg_read:A and syslog_print:A.
+	 * This pairs with devkmsg_read:A, syslog_print:A, and
+	 * printk_kthread_func:A.
 	 */
 	if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */
-	    (val & PRINTK_PENDING_OUTPUT)) {
+	    (val & PRINTK_PENDING_DIRECT_OUTPUT)) {
 		this_cpu_or(printk_pending, val);
 		irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
 	}
@@ -3524,7 +3799,17 @@ void defer_console_output(void)
 	 * New messages may have been added directly to the ringbuffer
 	 * using vprintk_store(), so wake any waiters as well.
 	 */
-	__wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT);
+	int val = PRINTK_PENDING_WAKEUP;
+
+	/*
+	 * Make sure that some context will print the messages when direct
+	 * printing is allowed. This happens in situations when the kthreads
+	 * may not be as reliable or perhaps unusable.
+	 */
+	if (allow_direct_printing())
+		val |= PRINTK_PENDING_DIRECT_OUTPUT;
+
+	__wake_up_klogd(val);
 }
 
 void printk_trigger_flush(void)
-- 
cgit v1.2.3


From 5e7260712b9a76de19c32f15d667f8f93e573978 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Thu, 21 Apr 2022 14:47:26 +0200
Subject: qed: Remove IP services API.

qed_nvmetcp_ip_services.c and its corresponding header file were
introduced in commit 806ee7f81a2b ("qed: Add IP services APIs support")
but there's still no users for any of the functions they declare.
Since these files are effectively unused, let's just drop them.

Found by code inspection. Compile-tested only.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Link: https://lore.kernel.org/r/351ac8c847980e22850eb390553f8cc0e1ccd0ce.1650545051.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qlogic/qed/Makefile           |   3 +-
 .../ethernet/qlogic/qed/qed_nvmetcp_ip_services.c  | 238 ---------------------
 include/linux/qed/qed_nvmetcp_ip_services_if.h     |  29 ---
 3 files changed, 1 insertion(+), 269 deletions(-)
 delete mode 100644 drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c
 delete mode 100644 include/linux/qed/qed_nvmetcp_ip_services_if.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile
index 0d9c2fe0245d..3d2098f21bb7 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -30,8 +30,7 @@ qed-$(CONFIG_QED_OOO) += qed_ooo.o
 
 qed-$(CONFIG_QED_NVMETCP) +=	\
 	qed_nvmetcp.o		\
-	qed_nvmetcp_fw_funcs.o	\
-	qed_nvmetcp_ip_services.o
+	qed_nvmetcp_fw_funcs.o
 
 qed-$(CONFIG_QED_RDMA) +=	\
 	qed_iwarp.o		\
diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c
deleted file mode 100644
index 7e286cddbedb..000000000000
--- a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c
+++ /dev/null
@@ -1,238 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
-/*
- * Copyright 2021 Marvell. All rights reserved.
- */
-
-#include <linux/types.h>
-#include <asm/byteorder.h>
-#include <asm/param.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <linux/dma-mapping.h>
-#include <linux/etherdevice.h>
-#include <linux/kernel.h>
-#include <linux/stddef.h>
-#include <linux/errno.h>
-
-#include <net/tcp.h>
-
-#include <linux/qed/qed_nvmetcp_ip_services_if.h>
-
-#define QED_IP_RESOL_TIMEOUT  4
-
-int qed_route_ipv4(struct sockaddr_storage *local_addr,
-		   struct sockaddr_storage *remote_addr,
-		   struct sockaddr *hardware_address,
-		   struct net_device **ndev)
-{
-	struct neighbour *neigh = NULL;
-	__be32 *loc_ip, *rem_ip;
-	struct rtable *rt;
-	int rc = -ENXIO;
-	int retry;
-
-	loc_ip = &((struct sockaddr_in *)local_addr)->sin_addr.s_addr;
-	rem_ip = &((struct sockaddr_in *)remote_addr)->sin_addr.s_addr;
-	*ndev = NULL;
-	rt = ip_route_output(&init_net, *rem_ip, *loc_ip, 0/*tos*/, 0/*oif*/);
-	if (IS_ERR(rt)) {
-		pr_err("lookup route failed\n");
-		rc = PTR_ERR(rt);
-		goto return_err;
-	}
-
-	neigh = dst_neigh_lookup(&rt->dst, rem_ip);
-	if (!neigh) {
-		rc = -ENOMEM;
-		ip_rt_put(rt);
-		goto return_err;
-	}
-
-	*ndev = rt->dst.dev;
-	ip_rt_put(rt);
-
-	/* If not resolved, kick-off state machine towards resolution */
-	if (!(neigh->nud_state & NUD_VALID))
-		neigh_event_send(neigh, NULL);
-
-	/* query neighbor until resolved or timeout */
-	retry = QED_IP_RESOL_TIMEOUT;
-	while (!(neigh->nud_state & NUD_VALID) && retry > 0) {
-		msleep(1000);
-		retry--;
-	}
-
-	if (neigh->nud_state & NUD_VALID) {
-		/* copy resolved MAC address */
-		neigh_ha_snapshot(hardware_address->sa_data, neigh, *ndev);
-		hardware_address->sa_family = (*ndev)->type;
-		rc = 0;
-	}
-
-	neigh_release(neigh);
-	if (!(*loc_ip)) {
-		*loc_ip = inet_select_addr(*ndev, *rem_ip, RT_SCOPE_UNIVERSE);
-		local_addr->ss_family = AF_INET;
-	}
-
-return_err:
-
-	return rc;
-}
-EXPORT_SYMBOL(qed_route_ipv4);
-
-int qed_route_ipv6(struct sockaddr_storage *local_addr,
-		   struct sockaddr_storage *remote_addr,
-		   struct sockaddr *hardware_address,
-		   struct net_device **ndev)
-{
-	struct neighbour *neigh = NULL;
-	struct dst_entry *dst;
-	struct flowi6 fl6;
-	int rc = -ENXIO;
-	int retry;
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.saddr = ((struct sockaddr_in6 *)local_addr)->sin6_addr;
-	fl6.daddr = ((struct sockaddr_in6 *)remote_addr)->sin6_addr;
-	dst = ip6_route_output(&init_net, NULL, &fl6);
-	if (!dst || dst->error) {
-		if (dst) {
-			dst_release(dst);
-			pr_err("lookup route failed %d\n", dst->error);
-		}
-
-		goto out;
-	}
-
-	neigh = dst_neigh_lookup(dst, &fl6.daddr);
-	if (neigh) {
-		*ndev = ip6_dst_idev(dst)->dev;
-
-		/* If not resolved, kick-off state machine towards resolution */
-		if (!(neigh->nud_state & NUD_VALID))
-			neigh_event_send(neigh, NULL);
-
-		/* query neighbor until resolved or timeout */
-		retry = QED_IP_RESOL_TIMEOUT;
-		while (!(neigh->nud_state & NUD_VALID) && retry > 0) {
-			msleep(1000);
-			retry--;
-		}
-
-		if (neigh->nud_state & NUD_VALID) {
-			neigh_ha_snapshot((u8 *)hardware_address->sa_data,
-					  neigh, *ndev);
-			hardware_address->sa_family = (*ndev)->type;
-			rc = 0;
-		}
-
-		neigh_release(neigh);
-
-		if (ipv6_addr_any(&fl6.saddr)) {
-			if (ipv6_dev_get_saddr(dev_net(*ndev), *ndev,
-					       &fl6.daddr, 0, &fl6.saddr)) {
-				pr_err("Unable to find source IP address\n");
-				goto out;
-			}
-
-			local_addr->ss_family = AF_INET6;
-			((struct sockaddr_in6 *)local_addr)->sin6_addr =
-								fl6.saddr;
-		}
-	}
-
-	dst_release(dst);
-
-out:
-
-	return rc;
-}
-EXPORT_SYMBOL(qed_route_ipv6);
-
-void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id)
-{
-	if (is_vlan_dev(*ndev)) {
-		*vlan_id = vlan_dev_vlan_id(*ndev);
-		*ndev = vlan_dev_real_dev(*ndev);
-	}
-}
-EXPORT_SYMBOL(qed_vlan_get_ndev);
-
-struct pci_dev *qed_validate_ndev(struct net_device *ndev)
-{
-	struct net_device *upper;
-	struct pci_dev *pdev;
-
-	for_each_pci_dev(pdev) {
-		if (pdev->driver &&
-		    !strcmp(pdev->driver->name, "qede")) {
-			upper = pci_get_drvdata(pdev);
-			if (upper->ifindex == ndev->ifindex)
-				return pdev;
-		}
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL(qed_validate_ndev);
-
-__be16 qed_get_in_port(struct sockaddr_storage *sa)
-{
-	return sa->ss_family == AF_INET
-		? ((struct sockaddr_in *)sa)->sin_port
-		: ((struct sockaddr_in6 *)sa)->sin6_port;
-}
-EXPORT_SYMBOL(qed_get_in_port);
-
-int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr,
-		       struct socket **sock, u16 *port)
-{
-	struct sockaddr_storage sa;
-	int rc = 0;
-
-	rc = sock_create(local_ip_addr.ss_family, SOCK_STREAM, IPPROTO_TCP,
-			 sock);
-	if (rc) {
-		pr_warn("failed to create socket: %d\n", rc);
-		goto err;
-	}
-
-	(*sock)->sk->sk_allocation = GFP_KERNEL;
-	sk_set_memalloc((*sock)->sk);
-
-	rc = kernel_bind(*sock, (struct sockaddr *)&local_ip_addr,
-			 sizeof(local_ip_addr));
-
-	if (rc) {
-		pr_warn("failed to bind socket: %d\n", rc);
-		goto err_sock;
-	}
-
-	rc = kernel_getsockname(*sock, (struct sockaddr *)&sa);
-	if (rc < 0) {
-		pr_warn("getsockname() failed: %d\n", rc);
-		goto err_sock;
-	}
-
-	*port = ntohs(qed_get_in_port(&sa));
-
-	return 0;
-
-err_sock:
-	sock_release(*sock);
-	sock = NULL;
-err:
-
-	return rc;
-}
-EXPORT_SYMBOL(qed_fetch_tcp_port);
-
-void qed_return_tcp_port(struct socket *sock)
-{
-	if (sock && sock->sk) {
-		tcp_set_state(sock->sk, TCP_CLOSE);
-		sock_release(sock);
-	}
-}
-EXPORT_SYMBOL(qed_return_tcp_port);
diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h
deleted file mode 100644
index 3604aee53796..000000000000
--- a/include/linux/qed/qed_nvmetcp_ip_services_if.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
-/*
- * Copyright 2021 Marvell. All rights reserved.
- */
-
-#ifndef _QED_IP_SERVICES_IF_H
-#define _QED_IP_SERVICES_IF_H
-
-#include <linux/types.h>
-#include <net/route.h>
-#include <net/ip6_route.h>
-#include <linux/inetdevice.h>
-
-int qed_route_ipv4(struct sockaddr_storage *local_addr,
-		   struct sockaddr_storage *remote_addr,
-		   struct sockaddr *hardware_address,
-		   struct net_device **ndev);
-int qed_route_ipv6(struct sockaddr_storage *local_addr,
-		   struct sockaddr_storage *remote_addr,
-		   struct sockaddr *hardware_address,
-		   struct net_device **ndev);
-void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id);
-struct pci_dev *qed_validate_ndev(struct net_device *ndev);
-void qed_return_tcp_port(struct socket *sock);
-int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr,
-		       struct socket **sock, u16 *port);
-__be16 qed_get_in_port(struct sockaddr_storage *sa);
-
-#endif /* _QED_IP_SERVICES_IF_H */
-- 
cgit v1.2.3


From 9ea4dcf49878bb9546b8fa9319dcbdc9b7ee20f8 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 22 Apr 2022 15:58:11 -0700
Subject: PM: CXL: Disable suspend

The CXL specification claims S3 support at a hardware level, but at a
system software level there are some missing pieces. Section 9.4 (CXL
2.0) rightly claims that "CXL mem adapters may need aux power to retain
memory context across S3", but there is no enumeration mechanism for the
OS to determine if a given adapter has that support. Moreover the save
state and resume image for the system may inadvertantly end up in a CXL
device that needs to be restored before the save state is recoverable.
I.e. a circular dependency that is not resolvable without a third party
save-area.

Arrange for the cxl_mem driver to fail S3 attempts. This still nominaly
allows for suspend, but requires unbinding all CXL memory devices before
the suspend to ensure the typical DRAM flow is taken. The cxl_mem unbind
flow is intended to also tear down all CXL memory regions associated
with a given cxl_memdev.

It is reasonable to assume that any device participating in a System RAM
range published in the EFI memory map is covered by aux power and
save-area outside the device itself. So this restriction can be
minimized in the future once pre-existing region enumeration support
arrives, and perhaps a spec update to clarify if the EFI memory map is
sufficent for determining the range of devices managed by
platform-firmware for S3 support.

Per Rafael, if the CXL configuration prevents suspend then it should
fail early before tasks are frozen, and mem_sleep should stop showing
'mem' as an option [1]. Effectively CXL augments the platform suspend
->valid() op since, for example, the ACPI ops are not aware of the CXL /
PCI dependencies. Given the split role of platform firmware vs OS
provisioned CXL memory it is up to the cxl_mem driver to determine if
the CXL configuration has elements that platform firmware may not be
prepared to restore.

Link: https://lore.kernel.org/r/CAJZ5v0hGVN_=3iU8OLpHY3Ak35T5+JcBM-qs8SbojKrpd0VXsA@mail.gmail.com [1]
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Len Brown <len.brown@intel.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/165066828317.3907920.5690432272182042556.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/Makefile           |  2 +-
 drivers/cxl/Kconfig        |  4 ++++
 drivers/cxl/Makefile       |  2 +-
 drivers/cxl/core/Makefile  |  1 +
 drivers/cxl/core/suspend.c | 24 ++++++++++++++++++++++++
 drivers/cxl/cxlmem.h       | 11 +++++++++++
 drivers/cxl/mem.c          | 22 +++++++++++++++++++++-
 include/linux/pm.h         |  9 +++++++++
 kernel/power/hibernate.c   |  2 +-
 kernel/power/main.c        |  5 ++++-
 kernel/power/suspend.c     |  3 ++-
 11 files changed, 79 insertions(+), 6 deletions(-)
 create mode 100644 drivers/cxl/core/suspend.c

(limited to 'include/linux')

diff --git a/drivers/Makefile b/drivers/Makefile
index 020780b6b4d2..f735c4955143 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -72,9 +72,9 @@ obj-$(CONFIG_PARPORT)		+= parport/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
 obj-$(CONFIG_DAX)		+= dax/
-obj-$(CONFIG_CXL_BUS)		+= cxl/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
+obj-y				+= cxl/
 obj-y				+= macintosh/
 obj-y				+= scsi/
 obj-y				+= nvme/
diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index b88ab956bb7c..f64e3984689f 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -98,4 +98,8 @@ config CXL_PORT
 	default CXL_BUS
 	tristate
 
+config CXL_SUSPEND
+	def_bool y
+	depends on SUSPEND && CXL_MEM
+
 endif
diff --git a/drivers/cxl/Makefile b/drivers/cxl/Makefile
index ce267ef11d93..a78270794150 100644
--- a/drivers/cxl/Makefile
+++ b/drivers/cxl/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_CXL_BUS) += core/
+obj-y += core/
 obj-$(CONFIG_CXL_PCI) += cxl_pci.o
 obj-$(CONFIG_CXL_MEM) += cxl_mem.o
 obj-$(CONFIG_CXL_ACPI) += cxl_acpi.o
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 6d37cd78b151..9d35085d25af 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_CXL_BUS) += cxl_core.o
+obj-$(CONFIG_CXL_SUSPEND) += suspend.o
 
 ccflags-y += -I$(srctree)/drivers/cxl
 cxl_core-y := port.o
diff --git a/drivers/cxl/core/suspend.c b/drivers/cxl/core/suspend.c
new file mode 100644
index 000000000000..a5984d96ea1d
--- /dev/null
+++ b/drivers/cxl/core/suspend.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#include <linux/atomic.h>
+#include <linux/export.h>
+#include "cxlmem.h"
+
+static atomic_t mem_active;
+
+bool cxl_mem_active(void)
+{
+	return atomic_read(&mem_active) != 0;
+}
+
+void cxl_mem_active_inc(void)
+{
+	atomic_inc(&mem_active);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_active_inc, CXL);
+
+void cxl_mem_active_dec(void)
+{
+	atomic_dec(&mem_active);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_active_dec, CXL);
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 243dd86a8b46..7235d2f976e5 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -353,6 +353,17 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds);
 struct cxl_dev_state *cxl_dev_state_create(struct device *dev);
 void set_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
 void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
+#ifdef CONFIG_CXL_SUSPEND
+void cxl_mem_active_inc(void);
+void cxl_mem_active_dec(void);
+#else
+static inline void cxl_mem_active_inc(void)
+{
+}
+static inline void cxl_mem_active_dec(void)
+{
+}
+#endif
 
 struct cxl_hdm {
 	struct cxl_component_regs regs;
diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 43e73d259207..1bd2e0b67f59 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -138,6 +138,11 @@ out:
 	return retval;
 }
 
+static void enable_suspend(void *data)
+{
+	cxl_mem_active_dec();
+}
+
 static int cxl_mem_probe(struct device *dev)
 {
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
@@ -194,7 +199,22 @@ static int cxl_mem_probe(struct device *dev)
 out:
 	cxl_device_unlock(&parent_port->dev);
 	put_device(&parent_port->dev);
-	return rc;
+
+	/*
+	 * The kernel may be operating out of CXL memory on this device,
+	 * there is no spec defined way to determine whether this device
+	 * preserves contents over suspend, and there is no simple way
+	 * to arrange for the suspend image to avoid CXL memory which
+	 * would setup a circular dependency between PCI resume and save
+	 * state restoration.
+	 *
+	 * TODO: support suspend when all the regions this device is
+	 * hosting are locked and covered by the system address map,
+	 * i.e. platform firmware owns restoring the HDM configuration
+	 * that it locked.
+	 */
+	cxl_mem_active_inc();
+	return devm_add_action_or_reset(dev, enable_suspend, NULL);
 }
 
 static struct cxl_driver cxl_mem_driver = {
diff --git a/include/linux/pm.h b/include/linux/pm.h
index e65b3ab28377..7911c4c9a7be 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -36,6 +36,15 @@ static inline void pm_vt_switch_unregister(struct device *dev)
 }
 #endif /* CONFIG_VT_CONSOLE_SLEEP */
 
+#ifdef CONFIG_CXL_SUSPEND
+bool cxl_mem_active(void);
+#else
+static inline bool cxl_mem_active(void)
+{
+	return false;
+}
+#endif
+
 /*
  * Device power management
  */
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 938d5c78b421..20a66bf9f465 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -83,7 +83,7 @@ bool hibernation_available(void)
 {
 	return nohibernate == 0 &&
 		!security_locked_down(LOCKDOWN_HIBERNATION) &&
-		!secretmem_active();
+		!secretmem_active() && !cxl_mem_active();
 }
 
 /**
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7e646079fbeb..3e6be1c33e0b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -127,7 +127,9 @@ static ssize_t mem_sleep_show(struct kobject *kobj, struct kobj_attribute *attr,
 	char *s = buf;
 	suspend_state_t i;
 
-	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) {
+		if (i >= PM_SUSPEND_MEM && cxl_mem_active())
+			continue;
 		if (mem_sleep_states[i]) {
 			const char *label = mem_sleep_states[i];
 
@@ -136,6 +138,7 @@ static ssize_t mem_sleep_show(struct kobject *kobj, struct kobj_attribute *attr,
 			else
 				s += sprintf(s, "%s ", label);
 		}
+	}
 
 	/* Convert the last space to a newline if needed. */
 	if (s != buf)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6fcdee7e87a5..827075944d28 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -236,7 +236,8 @@ EXPORT_SYMBOL_GPL(suspend_valid_only_mem);
 
 static bool sleep_state_supported(suspend_state_t state)
 {
-	return state == PM_SUSPEND_TO_IDLE || valid_state(state);
+	return state == PM_SUSPEND_TO_IDLE ||
+	       (valid_state(state) && !cxl_mem_active());
 }
 
 static int platform_suspend_prepare(suspend_state_t state)
-- 
cgit v1.2.3


From f226041424cf87245d39a1b2dfae304308b36b6b Mon Sep 17 00:00:00 2001
From: Dave Gerlach <d-gerlach@ti.com>
Date: Sat, 9 Apr 2022 14:12:15 -0700
Subject: soc: ti: wkup_m3_ipc: Add support for toggling VTT regulator

Some boards like the AM335x EVM-SK and AM437x GP EVM provide software
control via a GPIO pin to toggle the DDR VTT regulator to reduce power
consumption in low power states.

The VTT regulator should be disabled after enabling self-refresh on
suspend, and should be enabled before disabling self-refresh on resume.
This is to allow proper self-refresh entry/exit commands to be
transmitted to the memory.

The "ti,vtt-gpio-pin" device tree property in the wkup_m3_ipc node
specifies which GPIO pin to use. This property is communicated to the
Wakeup Cortex M3 co-processor where the actual toggling of the GPIO pin
happens in CM3 firmware [1].

Please note that the GPIO pin must be on the GPIO0 module as that module
is in the wakeup power domain.

[1] https://git.ti.com/cgit/processor-firmware/ti-amx3-cm3-pm-firmware/tree/src/pm_services/ddr.c?h=08.02.00.006#n190

Signed-off-by: Dave Gerlach <d-gerlach@ti.com>
Signed-off-by: Keerthy <j-keerthy@ti.com>
[dfustini: remove the unnecessary "ti,needs-vtt-toggle" property]
Signed-off-by: Drew Fustini <dfustini@baylibre.com>
Signed-off-by: Nishanth Menon <nm@ti.com>
Link: https://lore.kernel.org/r/20220409211215.2529387-3-dfustini@baylibre.com
---
 drivers/soc/ti/wkup_m3_ipc.c | 26 ++++++++++++++++++++++++--
 include/linux/wkup_m3_ipc.h  |  1 +
 2 files changed, 25 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index f145e65041fd..48659758228e 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -40,6 +40,13 @@
 #define M3_FW_VERSION_MASK		0xffff
 #define M3_WAKE_SRC_MASK		0xff
 
+#define IPC_MEM_TYPE_SHIFT		(0x0)
+#define IPC_MEM_TYPE_MASK		(0x7 << 0)
+#define IPC_VTT_STAT_SHIFT		(0x3)
+#define IPC_VTT_STAT_MASK		(0x1 << 3)
+#define IPC_VTT_GPIO_PIN_SHIFT		(0x4)
+#define IPC_VTT_GPIO_PIN_MASK		(0x3f << 4)
+
 #define M3_STATE_UNKNOWN		0
 #define M3_STATE_RESET			1
 #define M3_STATE_INITED			2
@@ -215,6 +222,12 @@ static int wkup_m3_is_available(struct wkup_m3_ipc *m3_ipc)
 		(m3_ipc->state != M3_STATE_UNKNOWN));
 }
 
+static void wkup_m3_set_vtt_gpio(struct wkup_m3_ipc *m3_ipc, int gpio)
+{
+	m3_ipc->vtt_conf = (1 << IPC_VTT_STAT_SHIFT) |
+			    (gpio << IPC_VTT_GPIO_PIN_SHIFT);
+}
+
 /* Public functions */
 /**
  * wkup_m3_set_mem_type - Pass wkup_m3 which type of memory is in use
@@ -294,7 +307,8 @@ static int wkup_m3_prepare_low_power(struct wkup_m3_ipc *m3_ipc, int state)
 	/* Program each required IPC register then write defaults to others */
 	wkup_m3_ctrl_ipc_write(m3_ipc, m3_ipc->resume_addr, 0);
 	wkup_m3_ctrl_ipc_write(m3_ipc, m3_power_state, 1);
-	wkup_m3_ctrl_ipc_write(m3_ipc, m3_ipc->mem_type, 4);
+	wkup_m3_ctrl_ipc_write(m3_ipc, m3_ipc->mem_type |
+			       m3_ipc->vtt_conf, 4);
 
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 2);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 3);
@@ -433,12 +447,13 @@ static int wkup_m3_rproc_boot_thread(void *arg)
 static int wkup_m3_ipc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	int irq, ret;
+	int irq, ret, temp;
 	phandle rproc_phandle;
 	struct rproc *m3_rproc;
 	struct resource *res;
 	struct task_struct *task;
 	struct wkup_m3_ipc *m3_ipc;
+	struct device_node *np = dev->of_node;
 
 	m3_ipc = devm_kzalloc(dev, sizeof(*m3_ipc), GFP_KERNEL);
 	if (!m3_ipc)
@@ -494,6 +509,13 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev)
 
 	m3_ipc->ops = &ipc_ops;
 
+	if (!of_property_read_u32(np, "ti,vtt-gpio-pin", &temp)) {
+		if (temp >= 0 && temp <= 31)
+			wkup_m3_set_vtt_gpio(m3_ipc, temp);
+		else
+			dev_warn(dev, "Invalid VTT GPIO(%d) pin\n", temp);
+	}
+
 	/*
 	 * Wait for firmware loading completion in a thread so we
 	 * can boot the wkup_m3 as soon as it's ready without holding
diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h
index 3f496967b538..2bc52c6381d5 100644
--- a/include/linux/wkup_m3_ipc.h
+++ b/include/linux/wkup_m3_ipc.h
@@ -33,6 +33,7 @@ struct wkup_m3_ipc {
 
 	int mem_type;
 	unsigned long resume_addr;
+	int vtt_conf;
 	int state;
 
 	struct completion sync_complete;
-- 
cgit v1.2.3


From 0f08c2e7458e25c967d844170f8ad1aac3b57a02 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Thu, 17 Mar 2022 12:55:06 +0900
Subject: usb: deprecate the third argument of usb_maxpacket()

This is a transitional patch with the ultimate goal of changing the
prototype of usb_maxpacket() from:
| static inline __u16
| usb_maxpacket(struct usb_device *udev, int pipe, int is_out)

into:
| static inline u16 usb_maxpacket(struct usb_device *udev, int pipe)

The third argument of usb_maxpacket(): is_out gets removed because it
can be derived from its second argument: pipe using
usb_pipeout(pipe). Furthermore, in the current version,
ubs_pipeout(pipe) is called regardless in order to sanitize the is_out
parameter.

In order to make a smooth change, we first deprecate the is_out
parameter by simply ignoring it (using a variadic function) and will
remove it later, once all the callers get updated.

The body of the function is reworked accordingly and is_out is
replaced by usb_pipeout(pipe). The WARN_ON() calls become unnecessary
and get removed.

Finally, the return type is changed from __u16 to u16 because this is
not a UAPI function.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20220317035514.6378-2-mailhol.vincent@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index 200b7b79acb5..572e136f6314 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1969,21 +1969,17 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe)
 	return eps[usb_pipeendpoint(pipe)];
 }
 
-/*-------------------------------------------------------------------------*/
-
-static inline __u16
-usb_maxpacket(struct usb_device *udev, int pipe, int is_out)
+static inline u16 usb_maxpacket(struct usb_device *udev, int pipe,
+				/* int is_out deprecated */ ...)
 {
 	struct usb_host_endpoint	*ep;
 	unsigned			epnum = usb_pipeendpoint(pipe);
 
-	if (is_out) {
-		WARN_ON(usb_pipein(pipe));
+	if (usb_pipeout(pipe))
 		ep = udev->ep_out[epnum];
-	} else {
-		WARN_ON(usb_pipeout(pipe));
+	else
 		ep = udev->ep_in[epnum];
-	}
+
 	if (!ep)
 		return 0;
 
@@ -1991,8 +1987,6 @@ usb_maxpacket(struct usb_device *udev, int pipe, int is_out)
 	return usb_endpoint_maxp(&ep->desc);
 }
 
-/* ----------------------------------------------------------------------- */
-
 /* translate USB error codes to codes user space understands */
 static inline int usb_translate_errors(int error_code)
 {
-- 
cgit v1.2.3


From 2ddf7617d568fdcbd3cc454bb4849fa6d3398c86 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Thu, 17 Mar 2022 12:55:13 +0900
Subject: usb: remove third argument of usb_maxpacket()

Now that all users of usb_maxpacket() have been migrated to only use
two arguments, remove the third variadic argument which was introduced
for the transition.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20220317035514.6378-9-mailhol.vincent@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index 572e136f6314..8127782aa7a1 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1969,8 +1969,7 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe)
 	return eps[usb_pipeendpoint(pipe)];
 }
 
-static inline u16 usb_maxpacket(struct usb_device *udev, int pipe,
-				/* int is_out deprecated */ ...)
+static inline u16 usb_maxpacket(struct usb_device *udev, int pipe)
 {
 	struct usb_host_endpoint	*ep;
 	unsigned			epnum = usb_pipeendpoint(pipe);
-- 
cgit v1.2.3


From bdddc253b0938a0063798881d1f6a971ea1d8943 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Thu, 17 Mar 2022 12:55:14 +0900
Subject: usb: rework usb_maxpacket() using usb_pipe_endpoint()

Rework the body of usb_maxpacket() and just rely on the
usb_pipe_endpoint() helper function to retrieve the host endpoint
instead of doing it by hand.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20220317035514.6378-10-mailhol.vincent@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index 8127782aa7a1..60bee864d897 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1971,13 +1971,7 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe)
 
 static inline u16 usb_maxpacket(struct usb_device *udev, int pipe)
 {
-	struct usb_host_endpoint	*ep;
-	unsigned			epnum = usb_pipeendpoint(pipe);
-
-	if (usb_pipeout(pipe))
-		ep = udev->ep_out[epnum];
-	else
-		ep = udev->ep_in[epnum];
+	struct usb_host_endpoint *ep = usb_pipe_endpoint(udev, pipe);
 
 	if (!ep)
 		return 0;
-- 
cgit v1.2.3


From da214a475f8bd1d3e9e7a19ddfeb4d1617551bab Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 12 Apr 2022 14:22:39 -0600
Subject: net: add __sys_socket_file()

This works like __sys_socket(), except instead of allocating and
returning a socket fd, it just returns the file associated with the
socket. No fd is installed into the process file table.

This is similar to do_accept(), and allows io_uring to use this without
instantiating a file descriptor in the process file table.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Acked-by: David S. Miller <davem@davemloft.net>
Link: https://lore.kernel.org/r/20220412202240.234207-2-axboe@kernel.dk
---
 include/linux/socket.h |  1 +
 net/socket.c           | 52 ++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 43 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 6f85f5d957ef..a1882e1e71d2 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -434,6 +434,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags,
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags);
 extern int __sys_socket(int family, int type, int protocol);
+extern struct file *__sys_socket_file(int family, int type, int protocol);
 extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
 extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr,
 			      int addrlen, int file_flags);
diff --git a/net/socket.c b/net/socket.c
index 6887840682bb..bb6a1a12fbde 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -504,7 +504,7 @@ static int sock_map_fd(struct socket *sock, int flags)
 struct socket *sock_from_file(struct file *file)
 {
 	if (file->f_op == &socket_file_ops)
-		return file->private_data;	/* set in sock_map_fd */
+		return file->private_data;	/* set in sock_alloc_file */
 
 	return NULL;
 }
@@ -1538,11 +1538,10 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct
 }
 EXPORT_SYMBOL(sock_create_kern);
 
-int __sys_socket(int family, int type, int protocol)
+static struct socket *__sys_socket_create(int family, int type, int protocol)
 {
-	int retval;
 	struct socket *sock;
-	int flags;
+	int retval;
 
 	/* Check the SOCK_* constants for consistency.  */
 	BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
@@ -1550,17 +1549,50 @@ int __sys_socket(int family, int type, int protocol)
 	BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
 	BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);
 
-	flags = type & ~SOCK_TYPE_MASK;
-	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
-		return -EINVAL;
+	if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
+		return ERR_PTR(-EINVAL);
 	type &= SOCK_TYPE_MASK;
 
+	retval = sock_create(family, type, protocol, &sock);
+	if (retval < 0)
+		return ERR_PTR(retval);
+
+	return sock;
+}
+
+struct file *__sys_socket_file(int family, int type, int protocol)
+{
+	struct socket *sock;
+	struct file *file;
+	int flags;
+
+	sock = __sys_socket_create(family, type, protocol);
+	if (IS_ERR(sock))
+		return ERR_CAST(sock);
+
+	flags = type & ~SOCK_TYPE_MASK;
 	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
 		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
-	retval = sock_create(family, type, protocol, &sock);
-	if (retval < 0)
-		return retval;
+	file = sock_alloc_file(sock, flags, NULL);
+	if (IS_ERR(file))
+		sock_release(sock);
+
+	return file;
+}
+
+int __sys_socket(int family, int type, int protocol)
+{
+	struct socket *sock;
+	int flags;
+
+	sock = __sys_socket_create(family, type, protocol);
+	if (IS_ERR(sock))
+		return PTR_ERR(sock);
+
+	flags = type & ~SOCK_TYPE_MASK;
+	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
+		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
 	return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
 }
-- 
cgit v1.2.3


From da32b5817253697671af961715517bfbb308a592 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Sat, 23 Apr 2022 11:07:49 +0100
Subject: mm: Add fault_in_subpage_writeable() to probe at sub-page granularity

On hardware with features like arm64 MTE or SPARC ADI, an access fault
can be triggered at sub-page granularity. Depending on how the
fault_in_writeable() function is used, the caller can get into a
live-lock by continuously retrying the fault-in on an address different
from the one where the uaccess failed.

In the majority of cases progress is ensured by the following
conditions:

1. copy_to_user_nofault() guarantees at least one byte access if the
   user address is not faulting.

2. The fault_in_writeable() loop is resumed from the first address that
   could not be accessed by copy_to_user_nofault().

If the loop iteration is restarted from an earlier (initial) point, the
loop is repeated with the same conditions and it would live-lock.

Introduce an arch-specific probe_subpage_writeable() and call it from
the newly added fault_in_subpage_writeable() function. The arch code
with sub-page faults will have to implement the specific probing
functionality.

Note that no other fault_in_subpage_*() functions are added since they
have no callers currently susceptible to a live-lock.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/r/20220423100751.1870771-2-catalin.marinas@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/Kconfig            |  7 +++++++
 include/linux/pagemap.h |  1 +
 include/linux/uaccess.h | 22 ++++++++++++++++++++++
 mm/gup.c                | 29 +++++++++++++++++++++++++++++
 4 files changed, 59 insertions(+)

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 29b0167c088b..b34032279926 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -24,6 +24,13 @@ config KEXEC_ELF
 config HAVE_IMA_KEXEC
 	bool
 
+config ARCH_HAS_SUBPAGE_FAULTS
+	bool
+	help
+	  Select if the architecture can check permissions at sub-page
+	  granularity (e.g. arm64 MTE). The probe_user_*() functions
+	  must be implemented.
+
 config HOTPLUG_SMT
 	bool
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 993994cd943a..6165283bdb6f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1046,6 +1046,7 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter);
  * Fault in userspace address range.
  */
 size_t fault_in_writeable(char __user *uaddr, size_t size);
+size_t fault_in_subpage_writeable(char __user *uaddr, size_t size);
 size_t fault_in_safe_writeable(const char __user *uaddr, size_t size);
 size_t fault_in_readable(const char __user *uaddr, size_t size);
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 546179418ffa..5a328cf02b75 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -231,6 +231,28 @@ static inline bool pagefault_disabled(void)
  */
 #define faulthandler_disabled() (pagefault_disabled() || in_atomic())
 
+#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS
+
+/**
+ * probe_subpage_writeable: probe the user range for write faults at sub-page
+ *			    granularity (e.g. arm64 MTE)
+ * @uaddr: start of address range
+ * @size: size of address range
+ *
+ * Returns 0 on success, the number of bytes not probed on fault.
+ *
+ * It is expected that the caller checked for the write permission of each
+ * page in the range either by put_user() or GUP. The architecture port can
+ * implement a more efficient get_user() probing if the same sub-page faults
+ * are triggered by either a read or a write.
+ */
+static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size)
+{
+	return 0;
+}
+
+#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
+
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline __must_check unsigned long
diff --git a/mm/gup.c b/mm/gup.c
index f598a037eb04..501bc150792c 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1648,6 +1648,35 @@ out:
 }
 EXPORT_SYMBOL(fault_in_writeable);
 
+/**
+ * fault_in_subpage_writeable - fault in an address range for writing
+ * @uaddr: start of address range
+ * @size: size of address range
+ *
+ * Fault in a user address range for writing while checking for permissions at
+ * sub-page granularity (e.g. arm64 MTE). This function should be used when
+ * the caller cannot guarantee forward progress of a copy_to_user() loop.
+ *
+ * Returns the number of bytes not faulted in (like copy_to_user() and
+ * copy_from_user()).
+ */
+size_t fault_in_subpage_writeable(char __user *uaddr, size_t size)
+{
+	size_t faulted_in;
+
+	/*
+	 * Attempt faulting in at page granularity first for page table
+	 * permission checking. The arch-specific probe_subpage_writeable()
+	 * functions may not check for this.
+	 */
+	faulted_in = size - fault_in_writeable(uaddr, size);
+	if (faulted_in)
+		faulted_in -= probe_subpage_writeable(uaddr, faulted_in);
+
+	return size - faulted_in;
+}
+EXPORT_SYMBOL(fault_in_subpage_writeable);
+
 /*
  * fault_in_safe_writeable - fault in an address range for writing
  * @uaddr: start of address range
-- 
cgit v1.2.3


From 3c938cc5cebcbd2291fe97f523c0705a2c24c77d Mon Sep 17 00:00:00 2001
From: Schspa Shi <schspa@gmail.com>
Date: Tue, 19 Apr 2022 09:28:10 +0800
Subject: gpio: use raw spinlock for gpio chip shadowed data

In case of PREEMPT_RT, there is a raw_spinlock -> spinlock dependency
as the lockdep report shows.

__irq_set_handler
  irq_get_desc_buslock
    __irq_get_desc_lock
      raw_spin_lock_irqsave(&desc->lock, *flags);  // raw spinlock get here
  __irq_do_set_handler
    mask_ack_irq
      dwapb_irq_ack
        spin_lock_irqsave(&gc->bgpio_lock, flags); // sleep able spinlock
  irq_put_desc_busunlock

Replace with a raw lock to avoid BUGs. This lock is only used to access
registers, and It's safe to replace with the raw lock without bad
influence.

[   15.090359][    T1] =============================
[   15.090365][    T1] [ BUG: Invalid wait context ]
[   15.090373][    T1] 5.10.59-rt52-00983-g186a6841c682-dirty #3 Not tainted
[   15.090386][    T1] -----------------------------
[   15.090392][    T1] swapper/0/1 is trying to lock:
[   15.090402][    T1] 70ff00018507c188 (&gc->bgpio_lock){....}-{3:3}, at: _raw_spin_lock_irqsave+0x1c/0x28
[   15.090470][    T1] other info that might help us debug this:
[   15.090477][    T1] context-{5:5}
[   15.090485][    T1] 3 locks held by swapper/0/1:
[   15.090497][    T1]  #0: c2ff0001816de1a0 (&dev->mutex){....}-{4:4}, at: __device_driver_lock+0x98/0x104
[   15.090553][    T1]  #1: ffff90001485b4b8 (irq_domain_mutex){+.+.}-{4:4}, at: irq_domain_associate+0xbc/0x6d4
[   15.090606][    T1]  #2: 4bff000185d7a8e0 (lock_class){....}-{2:2}, at: _raw_spin_lock_irqsave+0x1c/0x28
[   15.090654][    T1] stack backtrace:
[   15.090661][    T1] CPU: 4 PID: 1 Comm: swapper/0 Not tainted 5.10.59-rt52-00983-g186a6841c682-dirty #3
[   15.090682][    T1] Hardware name: Horizon Robotics Journey 5 DVB (DT)
[   15.090692][    T1] Call trace:
......
[   15.090811][    T1]  _raw_spin_lock_irqsave+0x1c/0x28
[   15.090828][    T1]  dwapb_irq_ack+0xb4/0x300
[   15.090846][    T1]  __irq_do_set_handler+0x494/0xb2c
[   15.090864][    T1]  __irq_set_handler+0x74/0x114
[   15.090881][    T1]  irq_set_chip_and_handler_name+0x44/0x58
[   15.090900][    T1]  gpiochip_irq_map+0x210/0x644

Signed-off-by: Schspa Shi <schspa@gmail.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Doug Berger <opendmb@gmail.com>
Acked-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 drivers/gpio/gpio-amdpt.c                 | 10 ++++-----
 drivers/gpio/gpio-brcmstb.c               | 12 +++++------
 drivers/gpio/gpio-cadence.c               | 12 +++++------
 drivers/gpio/gpio-dwapb.c                 | 36 +++++++++++++++----------------
 drivers/gpio/gpio-grgpio.c                | 30 +++++++++++++-------------
 drivers/gpio/gpio-hlwd.c                  | 18 ++++++++--------
 drivers/gpio/gpio-idt3243x.c              | 12 +++++------
 drivers/gpio/gpio-ixp4xx.c                |  4 ++--
 drivers/gpio/gpio-loongson1.c             |  8 +++----
 drivers/gpio/gpio-menz127.c               |  8 +++----
 drivers/gpio/gpio-mlxbf2.c                | 18 ++++++++--------
 drivers/gpio/gpio-mmio.c                  | 22 +++++++++----------
 drivers/gpio/gpio-sifive.c                | 12 +++++------
 drivers/gpio/gpio-tb10x.c                 |  4 ++--
 drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c |  8 +++----
 include/linux/gpio/driver.h               |  2 +-
 16 files changed, 108 insertions(+), 108 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpio-amdpt.c b/drivers/gpio/gpio-amdpt.c
index 8cfb353c3abb..07c6d090058d 100644
--- a/drivers/gpio/gpio-amdpt.c
+++ b/drivers/gpio/gpio-amdpt.c
@@ -36,19 +36,19 @@ static int pt_gpio_request(struct gpio_chip *gc, unsigned offset)
 
 	dev_dbg(gc->parent, "pt_gpio_request offset=%x\n", offset);
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	using_pins = readl(pt_gpio->reg_base + PT_SYNC_REG);
 	if (using_pins & BIT(offset)) {
 		dev_warn(gc->parent, "PT GPIO pin %x reconfigured\n",
 			 offset);
-		spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+		raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 		return -EINVAL;
 	}
 
 	writel(using_pins | BIT(offset), pt_gpio->reg_base + PT_SYNC_REG);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	return 0;
 }
@@ -59,13 +59,13 @@ static void pt_gpio_free(struct gpio_chip *gc, unsigned offset)
 	unsigned long flags;
 	u32 using_pins;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	using_pins = readl(pt_gpio->reg_base + PT_SYNC_REG);
 	using_pins &= ~BIT(offset);
 	writel(using_pins, pt_gpio->reg_base + PT_SYNC_REG);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	dev_dbg(gc->parent, "pt_gpio_free offset=%x\n", offset);
 }
diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c
index 74ef89248867..6b7439b44690 100644
--- a/drivers/gpio/gpio-brcmstb.c
+++ b/drivers/gpio/gpio-brcmstb.c
@@ -92,9 +92,9 @@ brcmstb_gpio_get_active_irqs(struct brcmstb_gpio_bank *bank)
 	unsigned long status;
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&bank->gc.bgpio_lock, flags);
 	status = __brcmstb_gpio_get_active_irqs(bank);
-	spin_unlock_irqrestore(&bank->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&bank->gc.bgpio_lock, flags);
 
 	return status;
 }
@@ -114,14 +114,14 @@ static void brcmstb_gpio_set_imask(struct brcmstb_gpio_bank *bank,
 	u32 imask;
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	imask = gc->read_reg(priv->reg_base + GIO_MASK(bank->id));
 	if (enable)
 		imask |= mask;
 	else
 		imask &= ~mask;
 	gc->write_reg(priv->reg_base + GIO_MASK(bank->id), imask);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static int brcmstb_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
@@ -204,7 +204,7 @@ static int brcmstb_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&bank->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&bank->gc.bgpio_lock, flags);
 
 	iedge_config = bank->gc.read_reg(priv->reg_base +
 			GIO_EC(bank->id)) & ~mask;
@@ -220,7 +220,7 @@ static int brcmstb_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	bank->gc.write_reg(priv->reg_base + GIO_LEVEL(bank->id),
 			ilevel | level);
 
-	spin_unlock_irqrestore(&bank->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&bank->gc.bgpio_lock, flags);
 	return 0;
 }
 
diff --git a/drivers/gpio/gpio-cadence.c b/drivers/gpio/gpio-cadence.c
index 562f8f7e7d1f..137aea49ba02 100644
--- a/drivers/gpio/gpio-cadence.c
+++ b/drivers/gpio/gpio-cadence.c
@@ -41,12 +41,12 @@ static int cdns_gpio_request(struct gpio_chip *chip, unsigned int offset)
 	struct cdns_gpio_chip *cgpio = gpiochip_get_data(chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&chip->bgpio_lock, flags);
 
 	iowrite32(ioread32(cgpio->regs + CDNS_GPIO_BYPASS_MODE) & ~BIT(offset),
 		  cgpio->regs + CDNS_GPIO_BYPASS_MODE);
 
-	spin_unlock_irqrestore(&chip->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&chip->bgpio_lock, flags);
 	return 0;
 }
 
@@ -55,13 +55,13 @@ static void cdns_gpio_free(struct gpio_chip *chip, unsigned int offset)
 	struct cdns_gpio_chip *cgpio = gpiochip_get_data(chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chip->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&chip->bgpio_lock, flags);
 
 	iowrite32(ioread32(cgpio->regs + CDNS_GPIO_BYPASS_MODE) |
 		  (BIT(offset) & cgpio->bypass_orig),
 		  cgpio->regs + CDNS_GPIO_BYPASS_MODE);
 
-	spin_unlock_irqrestore(&chip->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&chip->bgpio_lock, flags);
 }
 
 static void cdns_gpio_irq_mask(struct irq_data *d)
@@ -90,7 +90,7 @@ static int cdns_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	u32 mask = BIT(d->hwirq);
 	int ret = 0;
 
-	spin_lock_irqsave(&chip->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&chip->bgpio_lock, flags);
 
 	int_value = ioread32(cgpio->regs + CDNS_GPIO_IRQ_VALUE) & ~mask;
 	int_type = ioread32(cgpio->regs + CDNS_GPIO_IRQ_TYPE) & ~mask;
@@ -115,7 +115,7 @@ static int cdns_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	iowrite32(int_type, cgpio->regs + CDNS_GPIO_IRQ_TYPE);
 
 err_irq_type:
-	spin_unlock_irqrestore(&chip->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&chip->bgpio_lock, flags);
 	return ret;
 }
 
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index b0f3aca61974..7130195da48d 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -243,9 +243,9 @@ static void dwapb_irq_ack(struct irq_data *d)
 	u32 val = BIT(irqd_to_hwirq(d));
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	dwapb_write(gpio, GPIO_PORTA_EOI, val);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void dwapb_irq_mask(struct irq_data *d)
@@ -255,10 +255,10 @@ static void dwapb_irq_mask(struct irq_data *d)
 	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	val = dwapb_read(gpio, GPIO_INTMASK) | BIT(irqd_to_hwirq(d));
 	dwapb_write(gpio, GPIO_INTMASK, val);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void dwapb_irq_unmask(struct irq_data *d)
@@ -268,10 +268,10 @@ static void dwapb_irq_unmask(struct irq_data *d)
 	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	val = dwapb_read(gpio, GPIO_INTMASK) & ~BIT(irqd_to_hwirq(d));
 	dwapb_write(gpio, GPIO_INTMASK, val);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void dwapb_irq_enable(struct irq_data *d)
@@ -281,11 +281,11 @@ static void dwapb_irq_enable(struct irq_data *d)
 	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	val = dwapb_read(gpio, GPIO_INTEN);
 	val |= BIT(irqd_to_hwirq(d));
 	dwapb_write(gpio, GPIO_INTEN, val);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void dwapb_irq_disable(struct irq_data *d)
@@ -295,11 +295,11 @@ static void dwapb_irq_disable(struct irq_data *d)
 	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	val = dwapb_read(gpio, GPIO_INTEN);
 	val &= ~BIT(irqd_to_hwirq(d));
 	dwapb_write(gpio, GPIO_INTEN, val);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static int dwapb_irq_set_type(struct irq_data *d, u32 type)
@@ -309,7 +309,7 @@ static int dwapb_irq_set_type(struct irq_data *d, u32 type)
 	irq_hw_number_t bit = irqd_to_hwirq(d);
 	unsigned long level, polarity, flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	level = dwapb_read(gpio, GPIO_INTTYPE_LEVEL);
 	polarity = dwapb_read(gpio, GPIO_INT_POLARITY);
 
@@ -344,7 +344,7 @@ static int dwapb_irq_set_type(struct irq_data *d, u32 type)
 	dwapb_write(gpio, GPIO_INTTYPE_LEVEL, level);
 	if (type != IRQ_TYPE_EDGE_BOTH)
 		dwapb_write(gpio, GPIO_INT_POLARITY, polarity);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	return 0;
 }
@@ -374,7 +374,7 @@ static int dwapb_gpio_set_debounce(struct gpio_chip *gc,
 	unsigned long flags, val_deb;
 	unsigned long mask = BIT(offset);
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	val_deb = dwapb_read(gpio, GPIO_PORTA_DEBOUNCE);
 	if (debounce)
@@ -383,7 +383,7 @@ static int dwapb_gpio_set_debounce(struct gpio_chip *gc,
 		val_deb &= ~mask;
 	dwapb_write(gpio, GPIO_PORTA_DEBOUNCE, val_deb);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	return 0;
 }
@@ -738,7 +738,7 @@ static int dwapb_gpio_suspend(struct device *dev)
 	unsigned long flags;
 	int i;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	for (i = 0; i < gpio->nr_ports; i++) {
 		unsigned int offset;
 		unsigned int idx = gpio->ports[i].idx;
@@ -765,7 +765,7 @@ static int dwapb_gpio_suspend(struct device *dev)
 			dwapb_write(gpio, GPIO_INTMASK, ~ctx->wake_en);
 		}
 	}
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	clk_bulk_disable_unprepare(DWAPB_NR_CLOCKS, gpio->clks);
 
@@ -785,7 +785,7 @@ static int dwapb_gpio_resume(struct device *dev)
 		return err;
 	}
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	for (i = 0; i < gpio->nr_ports; i++) {
 		unsigned int offset;
 		unsigned int idx = gpio->ports[i].idx;
@@ -812,7 +812,7 @@ static int dwapb_gpio_resume(struct device *dev)
 			dwapb_write(gpio, GPIO_PORTA_EOI, 0xffffffff);
 		}
 	}
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	return 0;
 }
diff --git a/drivers/gpio/gpio-grgpio.c b/drivers/gpio/gpio-grgpio.c
index 23d447e17a67..df563616f943 100644
--- a/drivers/gpio/gpio-grgpio.c
+++ b/drivers/gpio/gpio-grgpio.c
@@ -145,7 +145,7 @@ static int grgpio_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
 
 	ipol = priv->gc.read_reg(priv->regs + GRGPIO_IPOL) & ~mask;
 	iedge = priv->gc.read_reg(priv->regs + GRGPIO_IEDGE) & ~mask;
@@ -153,7 +153,7 @@ static int grgpio_irq_set_type(struct irq_data *d, unsigned int type)
 	priv->gc.write_reg(priv->regs + GRGPIO_IPOL, ipol | pol);
 	priv->gc.write_reg(priv->regs + GRGPIO_IEDGE, iedge | edge);
 
-	spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 
 	return 0;
 }
@@ -164,11 +164,11 @@ static void grgpio_irq_mask(struct irq_data *d)
 	int offset = d->hwirq;
 	unsigned long flags;
 
-	spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
 
 	grgpio_set_imask(priv, offset, 0);
 
-	spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 }
 
 static void grgpio_irq_unmask(struct irq_data *d)
@@ -177,11 +177,11 @@ static void grgpio_irq_unmask(struct irq_data *d)
 	int offset = d->hwirq;
 	unsigned long flags;
 
-	spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
 
 	grgpio_set_imask(priv, offset, 1);
 
-	spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 }
 
 static struct irq_chip grgpio_irq_chip = {
@@ -199,7 +199,7 @@ static irqreturn_t grgpio_irq_handler(int irq, void *dev)
 	int i;
 	int match = 0;
 
-	spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
 
 	/*
 	 * For each gpio line, call its interrupt handler if it its underlying
@@ -215,7 +215,7 @@ static irqreturn_t grgpio_irq_handler(int irq, void *dev)
 		}
 	}
 
-	spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 
 	if (!match)
 		dev_warn(priv->dev, "No gpio line matched irq %d\n", irq);
@@ -247,13 +247,13 @@ static int grgpio_irq_map(struct irq_domain *d, unsigned int irq,
 	dev_dbg(priv->dev, "Mapping irq %d for gpio line %d\n",
 		irq, offset);
 
-	spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
 
 	/* Request underlying irq if not already requested */
 	lirq->irq = irq;
 	uirq = &priv->uirqs[lirq->index];
 	if (uirq->refcnt == 0) {
-		spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
+		raw_spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 		ret = request_irq(uirq->uirq, grgpio_irq_handler, 0,
 				  dev_name(priv->dev), priv);
 		if (ret) {
@@ -262,11 +262,11 @@ static int grgpio_irq_map(struct irq_domain *d, unsigned int irq,
 				uirq->uirq);
 			return ret;
 		}
-		spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
+		raw_spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
 	}
 	uirq->refcnt++;
 
-	spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 
 	/* Setup irq  */
 	irq_set_chip_data(irq, priv);
@@ -290,7 +290,7 @@ static void grgpio_irq_unmap(struct irq_domain *d, unsigned int irq)
 	irq_set_chip_and_handler(irq, NULL, NULL);
 	irq_set_chip_data(irq, NULL);
 
-	spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
 
 	/* Free underlying irq if last user unmapped */
 	index = -1;
@@ -309,13 +309,13 @@ static void grgpio_irq_unmap(struct irq_domain *d, unsigned int irq)
 		uirq = &priv->uirqs[lirq->index];
 		uirq->refcnt--;
 		if (uirq->refcnt == 0) {
-			spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
+			raw_spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 			free_irq(uirq->uirq, priv);
 			return;
 		}
 	}
 
-	spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 }
 
 static const struct irq_domain_ops grgpio_irq_domain_ops = {
diff --git a/drivers/gpio/gpio-hlwd.c b/drivers/gpio/gpio-hlwd.c
index 641719a96a1a..4e13e937f832 100644
--- a/drivers/gpio/gpio-hlwd.c
+++ b/drivers/gpio/gpio-hlwd.c
@@ -65,7 +65,7 @@ static void hlwd_gpio_irqhandler(struct irq_desc *desc)
 	int hwirq;
 	u32 emulated_pending;
 
-	spin_lock_irqsave(&hlwd->gpioc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&hlwd->gpioc.bgpio_lock, flags);
 	pending = ioread32be(hlwd->regs + HW_GPIOB_INTFLAG);
 	pending &= ioread32be(hlwd->regs + HW_GPIOB_INTMASK);
 
@@ -93,7 +93,7 @@ static void hlwd_gpio_irqhandler(struct irq_desc *desc)
 		/* Mark emulated interrupts as pending */
 		pending |= rising | falling;
 	}
-	spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
 
 	chained_irq_enter(chip, desc);
 
@@ -118,11 +118,11 @@ static void hlwd_gpio_irq_mask(struct irq_data *data)
 	unsigned long flags;
 	u32 mask;
 
-	spin_lock_irqsave(&hlwd->gpioc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&hlwd->gpioc.bgpio_lock, flags);
 	mask = ioread32be(hlwd->regs + HW_GPIOB_INTMASK);
 	mask &= ~BIT(data->hwirq);
 	iowrite32be(mask, hlwd->regs + HW_GPIOB_INTMASK);
-	spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
 }
 
 static void hlwd_gpio_irq_unmask(struct irq_data *data)
@@ -132,11 +132,11 @@ static void hlwd_gpio_irq_unmask(struct irq_data *data)
 	unsigned long flags;
 	u32 mask;
 
-	spin_lock_irqsave(&hlwd->gpioc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&hlwd->gpioc.bgpio_lock, flags);
 	mask = ioread32be(hlwd->regs + HW_GPIOB_INTMASK);
 	mask |= BIT(data->hwirq);
 	iowrite32be(mask, hlwd->regs + HW_GPIOB_INTMASK);
-	spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
 }
 
 static void hlwd_gpio_irq_enable(struct irq_data *data)
@@ -173,7 +173,7 @@ static int hlwd_gpio_irq_set_type(struct irq_data *data, unsigned int flow_type)
 	unsigned long flags;
 	u32 level;
 
-	spin_lock_irqsave(&hlwd->gpioc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&hlwd->gpioc.bgpio_lock, flags);
 
 	hlwd->edge_emulation &= ~BIT(data->hwirq);
 
@@ -194,11 +194,11 @@ static int hlwd_gpio_irq_set_type(struct irq_data *data, unsigned int flow_type)
 		hlwd_gpio_irq_setup_emulation(hlwd, data->hwirq, flow_type);
 		break;
 	default:
-		spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
+		raw_spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
 		return -EINVAL;
 	}
 
-	spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&hlwd->gpioc.bgpio_lock, flags);
 	return 0;
 }
 
diff --git a/drivers/gpio/gpio-idt3243x.c b/drivers/gpio/gpio-idt3243x.c
index 52b8b72ded77..1cafdf46f875 100644
--- a/drivers/gpio/gpio-idt3243x.c
+++ b/drivers/gpio/gpio-idt3243x.c
@@ -57,7 +57,7 @@ static int idt_gpio_irq_set_type(struct irq_data *d, unsigned int flow_type)
 	if (sense == IRQ_TYPE_NONE || (sense & IRQ_TYPE_EDGE_BOTH))
 		return -EINVAL;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	ilevel = readl(ctrl->gpio + IDT_GPIO_ILEVEL);
 	if (sense & IRQ_TYPE_LEVEL_HIGH)
@@ -68,7 +68,7 @@ static int idt_gpio_irq_set_type(struct irq_data *d, unsigned int flow_type)
 	writel(ilevel, ctrl->gpio + IDT_GPIO_ILEVEL);
 	irq_set_handler_locked(d, handle_level_irq);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 	return 0;
 }
 
@@ -86,12 +86,12 @@ static void idt_gpio_mask(struct irq_data *d)
 	struct idt_gpio_ctrl *ctrl = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	ctrl->mask_cache |= BIT(d->hwirq);
 	writel(ctrl->mask_cache, ctrl->pic + IDT_PIC_IRQ_MASK);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void idt_gpio_unmask(struct irq_data *d)
@@ -100,12 +100,12 @@ static void idt_gpio_unmask(struct irq_data *d)
 	struct idt_gpio_ctrl *ctrl = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	ctrl->mask_cache &= ~BIT(d->hwirq);
 	writel(ctrl->mask_cache, ctrl->pic + IDT_PIC_IRQ_MASK);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static int idt_gpio_irq_init_hw(struct gpio_chip *gc)
diff --git a/drivers/gpio/gpio-ixp4xx.c b/drivers/gpio/gpio-ixp4xx.c
index 1acda980d119..76ab9bd7d84b 100644
--- a/drivers/gpio/gpio-ixp4xx.c
+++ b/drivers/gpio/gpio-ixp4xx.c
@@ -126,7 +126,7 @@ static int ixp4xx_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 		int_reg = IXP4XX_REG_GPIT1;
 	}
 
-	spin_lock_irqsave(&g->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&g->gc.bgpio_lock, flags);
 
 	/* Clear the style for the appropriate pin */
 	val = __raw_readl(g->base + int_reg);
@@ -145,7 +145,7 @@ static int ixp4xx_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	val |= BIT(d->hwirq);
 	__raw_writel(val, g->base + IXP4XX_REG_GPOE);
 
-	spin_unlock_irqrestore(&g->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&g->gc.bgpio_lock, flags);
 
 	/* This parent only accept level high (asserted) */
 	return irq_chip_set_type_parent(d, IRQ_TYPE_LEVEL_HIGH);
diff --git a/drivers/gpio/gpio-loongson1.c b/drivers/gpio/gpio-loongson1.c
index 1b1ee94eeab4..5d90b3bc5a25 100644
--- a/drivers/gpio/gpio-loongson1.c
+++ b/drivers/gpio/gpio-loongson1.c
@@ -25,10 +25,10 @@ static int ls1x_gpio_request(struct gpio_chip *gc, unsigned int offset)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	__raw_writel(__raw_readl(gpio_reg_base + GPIO_CFG) | BIT(offset),
 		     gpio_reg_base + GPIO_CFG);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	return 0;
 }
@@ -37,10 +37,10 @@ static void ls1x_gpio_free(struct gpio_chip *gc, unsigned int offset)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	__raw_writel(__raw_readl(gpio_reg_base + GPIO_CFG) & ~BIT(offset),
 		     gpio_reg_base + GPIO_CFG);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static int ls1x_gpio_probe(struct platform_device *pdev)
diff --git a/drivers/gpio/gpio-menz127.c b/drivers/gpio/gpio-menz127.c
index 1e21c661d79d..a035a9bcb57c 100644
--- a/drivers/gpio/gpio-menz127.c
+++ b/drivers/gpio/gpio-menz127.c
@@ -64,7 +64,7 @@ static int men_z127_debounce(struct gpio_chip *gc, unsigned gpio,
 		debounce /= 50;
 	}
 
-	spin_lock(&gc->bgpio_lock);
+	raw_spin_lock(&gc->bgpio_lock);
 
 	db_en = readl(priv->reg_base + MEN_Z127_DBER);
 
@@ -79,7 +79,7 @@ static int men_z127_debounce(struct gpio_chip *gc, unsigned gpio,
 	writel(db_en, priv->reg_base + MEN_Z127_DBER);
 	writel(db_cnt, priv->reg_base + GPIO_TO_DBCNT_REG(gpio));
 
-	spin_unlock(&gc->bgpio_lock);
+	raw_spin_unlock(&gc->bgpio_lock);
 
 	return 0;
 }
@@ -91,7 +91,7 @@ static int men_z127_set_single_ended(struct gpio_chip *gc,
 	struct men_z127_gpio *priv = gpiochip_get_data(gc);
 	u32 od_en;
 
-	spin_lock(&gc->bgpio_lock);
+	raw_spin_lock(&gc->bgpio_lock);
 	od_en = readl(priv->reg_base + MEN_Z127_ODER);
 
 	if (param == PIN_CONFIG_DRIVE_OPEN_DRAIN)
@@ -101,7 +101,7 @@ static int men_z127_set_single_ended(struct gpio_chip *gc,
 		od_en &= ~BIT(offset);
 
 	writel(od_en, priv->reg_base + MEN_Z127_ODER);
-	spin_unlock(&gc->bgpio_lock);
+	raw_spin_unlock(&gc->bgpio_lock);
 
 	return 0;
 }
diff --git a/drivers/gpio/gpio-mlxbf2.c b/drivers/gpio/gpio-mlxbf2.c
index 3d89912a05b8..64cb060d9d75 100644
--- a/drivers/gpio/gpio-mlxbf2.c
+++ b/drivers/gpio/gpio-mlxbf2.c
@@ -131,7 +131,7 @@ static int mlxbf2_gpio_lock_acquire(struct mlxbf2_gpio_context *gs)
 	u32 arm_gpio_lock_val;
 
 	mutex_lock(yu_arm_gpio_lock_param.lock);
-	spin_lock(&gs->gc.bgpio_lock);
+	raw_spin_lock(&gs->gc.bgpio_lock);
 
 	arm_gpio_lock_val = readl(yu_arm_gpio_lock_param.io);
 
@@ -139,7 +139,7 @@ static int mlxbf2_gpio_lock_acquire(struct mlxbf2_gpio_context *gs)
 	 * When lock active bit[31] is set, ModeX is write enabled
 	 */
 	if (YU_LOCK_ACTIVE_BIT(arm_gpio_lock_val)) {
-		spin_unlock(&gs->gc.bgpio_lock);
+		raw_spin_unlock(&gs->gc.bgpio_lock);
 		mutex_unlock(yu_arm_gpio_lock_param.lock);
 		return -EINVAL;
 	}
@@ -157,7 +157,7 @@ static void mlxbf2_gpio_lock_release(struct mlxbf2_gpio_context *gs)
 	__releases(yu_arm_gpio_lock_param.lock)
 {
 	writel(YU_ARM_GPIO_LOCK_RELEASE, yu_arm_gpio_lock_param.io);
-	spin_unlock(&gs->gc.bgpio_lock);
+	raw_spin_unlock(&gs->gc.bgpio_lock);
 	mutex_unlock(yu_arm_gpio_lock_param.lock);
 }
 
@@ -237,7 +237,7 @@ static void mlxbf2_gpio_irq_enable(struct irq_data *irqd)
 	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&gs->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gs->gc.bgpio_lock, flags);
 	val = readl(gs->gpio_io + YU_GPIO_CAUSE_OR_CLRCAUSE);
 	val |= BIT(offset);
 	writel(val, gs->gpio_io + YU_GPIO_CAUSE_OR_CLRCAUSE);
@@ -245,7 +245,7 @@ static void mlxbf2_gpio_irq_enable(struct irq_data *irqd)
 	val = readl(gs->gpio_io + YU_GPIO_CAUSE_OR_EVTEN0);
 	val |= BIT(offset);
 	writel(val, gs->gpio_io + YU_GPIO_CAUSE_OR_EVTEN0);
-	spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);
 }
 
 static void mlxbf2_gpio_irq_disable(struct irq_data *irqd)
@@ -256,11 +256,11 @@ static void mlxbf2_gpio_irq_disable(struct irq_data *irqd)
 	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&gs->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gs->gc.bgpio_lock, flags);
 	val = readl(gs->gpio_io + YU_GPIO_CAUSE_OR_EVTEN0);
 	val &= ~BIT(offset);
 	writel(val, gs->gpio_io + YU_GPIO_CAUSE_OR_EVTEN0);
-	spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);
 }
 
 static irqreturn_t mlxbf2_gpio_irq_handler(int irq, void *ptr)
@@ -307,7 +307,7 @@ mlxbf2_gpio_irq_set_type(struct irq_data *irqd, unsigned int type)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&gs->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gs->gc.bgpio_lock, flags);
 	if (fall) {
 		val = readl(gs->gpio_io + YU_GPIO_CAUSE_FALL_EN);
 		val |= BIT(offset);
@@ -319,7 +319,7 @@ mlxbf2_gpio_irq_set_type(struct irq_data *irqd, unsigned int type)
 		val |= BIT(offset);
 		writel(val, gs->gpio_io + YU_GPIO_CAUSE_RISE_EN);
 	}
-	spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);
 
 	return 0;
 }
diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c
index c335a0309ba3..d9dff3dc92ae 100644
--- a/drivers/gpio/gpio-mmio.c
+++ b/drivers/gpio/gpio-mmio.c
@@ -220,7 +220,7 @@ static void bgpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 	unsigned long mask = bgpio_line2mask(gc, gpio);
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	if (val)
 		gc->bgpio_data |= mask;
@@ -229,7 +229,7 @@ static void bgpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 
 	gc->write_reg(gc->reg_dat, gc->bgpio_data);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void bgpio_set_with_clear(struct gpio_chip *gc, unsigned int gpio,
@@ -248,7 +248,7 @@ static void bgpio_set_set(struct gpio_chip *gc, unsigned int gpio, int val)
 	unsigned long mask = bgpio_line2mask(gc, gpio);
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	if (val)
 		gc->bgpio_data |= mask;
@@ -257,7 +257,7 @@ static void bgpio_set_set(struct gpio_chip *gc, unsigned int gpio, int val)
 
 	gc->write_reg(gc->reg_set, gc->bgpio_data);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void bgpio_multiple_get_masks(struct gpio_chip *gc,
@@ -286,7 +286,7 @@ static void bgpio_set_multiple_single_reg(struct gpio_chip *gc,
 	unsigned long flags;
 	unsigned long set_mask, clear_mask;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	bgpio_multiple_get_masks(gc, mask, bits, &set_mask, &clear_mask);
 
@@ -295,7 +295,7 @@ static void bgpio_set_multiple_single_reg(struct gpio_chip *gc,
 
 	gc->write_reg(reg, gc->bgpio_data);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void bgpio_set_multiple(struct gpio_chip *gc, unsigned long *mask,
@@ -347,7 +347,7 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
 
@@ -356,7 +356,7 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 	if (gc->reg_dir_out)
 		gc->write_reg(gc->reg_dir_out, gc->bgpio_dir);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	return 0;
 }
@@ -387,7 +387,7 @@ static void bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
 
@@ -396,7 +396,7 @@ static void bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 	if (gc->reg_dir_out)
 		gc->write_reg(gc->reg_dir_out, gc->bgpio_dir);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static int bgpio_dir_out_dir_first(struct gpio_chip *gc, unsigned int gpio,
@@ -610,7 +610,7 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev,
 	if (gc->bgpio_bits > BITS_PER_LONG)
 		return -EINVAL;
 
-	spin_lock_init(&gc->bgpio_lock);
+	raw_spin_lock_init(&gc->bgpio_lock);
 	gc->parent = dev;
 	gc->label = dev_name(dev);
 	gc->base = -1;
diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c
index 7d82388b4ab7..03b8c4de2e91 100644
--- a/drivers/gpio/gpio-sifive.c
+++ b/drivers/gpio/gpio-sifive.c
@@ -44,7 +44,7 @@ static void sifive_gpio_set_ie(struct sifive_gpio *chip, unsigned int offset)
 	unsigned long flags;
 	unsigned int trigger;
 
-	spin_lock_irqsave(&chip->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&chip->gc.bgpio_lock, flags);
 	trigger = (chip->irq_state & BIT(offset)) ? chip->trigger[offset] : 0;
 	regmap_update_bits(chip->regs, SIFIVE_GPIO_RISE_IE, BIT(offset),
 			   (trigger & IRQ_TYPE_EDGE_RISING) ? BIT(offset) : 0);
@@ -54,7 +54,7 @@ static void sifive_gpio_set_ie(struct sifive_gpio *chip, unsigned int offset)
 			   (trigger & IRQ_TYPE_LEVEL_HIGH) ? BIT(offset) : 0);
 	regmap_update_bits(chip->regs, SIFIVE_GPIO_LOW_IE, BIT(offset),
 			   (trigger & IRQ_TYPE_LEVEL_LOW) ? BIT(offset) : 0);
-	spin_unlock_irqrestore(&chip->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&chip->gc.bgpio_lock, flags);
 }
 
 static int sifive_gpio_irq_set_type(struct irq_data *d, unsigned int trigger)
@@ -84,13 +84,13 @@ static void sifive_gpio_irq_enable(struct irq_data *d)
 	/* Switch to input */
 	gc->direction_input(gc, offset);
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	/* Clear any sticky pending interrupts */
 	regmap_write(chip->regs, SIFIVE_GPIO_RISE_IP, bit);
 	regmap_write(chip->regs, SIFIVE_GPIO_FALL_IP, bit);
 	regmap_write(chip->regs, SIFIVE_GPIO_HIGH_IP, bit);
 	regmap_write(chip->regs, SIFIVE_GPIO_LOW_IP, bit);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	/* Enable interrupts */
 	assign_bit(offset, &chip->irq_state, 1);
@@ -116,13 +116,13 @@ static void sifive_gpio_irq_eoi(struct irq_data *d)
 	u32 bit = BIT(offset);
 	unsigned long flags;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 	/* Clear all pending interrupts */
 	regmap_write(chip->regs, SIFIVE_GPIO_RISE_IP, bit);
 	regmap_write(chip->regs, SIFIVE_GPIO_FALL_IP, bit);
 	regmap_write(chip->regs, SIFIVE_GPIO_HIGH_IP, bit);
 	regmap_write(chip->regs, SIFIVE_GPIO_LOW_IP, bit);
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 
 	irq_chip_eoi_parent(d);
 }
diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c
index 718a508d3b2f..de6afa3f9716 100644
--- a/drivers/gpio/gpio-tb10x.c
+++ b/drivers/gpio/gpio-tb10x.c
@@ -62,14 +62,14 @@ static inline void tb10x_set_bits(struct tb10x_gpio *gpio, unsigned int offs,
 	u32 r;
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpio->gc.bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gpio->gc.bgpio_lock, flags);
 
 	r = tb10x_reg_read(gpio, offs);
 	r = (r & ~mask) | (val & mask);
 
 	tb10x_reg_write(gpio, offs, r);
 
-	spin_unlock_irqrestore(&gpio->gc.bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gpio->gc.bgpio_lock, flags);
 }
 
 static int tb10x_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
diff --git a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
index 9557fac5d11c..b2a0f11a658b 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c
@@ -104,12 +104,12 @@ static void npcm_gpio_set(struct gpio_chip *gc, void __iomem *reg,
 	unsigned long flags;
 	unsigned long val;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	val = ioread32(reg) | pinmask;
 	iowrite32(val, reg);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void npcm_gpio_clr(struct gpio_chip *gc, void __iomem *reg,
@@ -118,12 +118,12 @@ static void npcm_gpio_clr(struct gpio_chip *gc, void __iomem *reg,
 	unsigned long flags;
 	unsigned long val;
 
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
+	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
 
 	val = ioread32(reg) & ~pinmask;
 	iowrite32(val, reg);
 
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
+	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
 static void npcmgpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 98c93510640e..991d374dcf71 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -436,7 +436,7 @@ struct gpio_chip {
 	void __iomem *reg_dir_in;
 	bool bgpio_dir_unreadable;
 	int bgpio_bits;
-	spinlock_t bgpio_lock;
+	raw_spinlock_t bgpio_lock;
 	unsigned long bgpio_data;
 	unsigned long bgpio_dir;
 #endif /* CONFIG_GPIO_GENERIC */
-- 
cgit v1.2.3


From 38035c04f5865c4ef9597d6beed6a7178f90f64a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 22 Apr 2022 15:03:13 +0300
Subject: inotify: move control flags from mask to mark flags

The inotify control flags in the mark mask (e.g. FS_IN_ONE_SHOT) are not
relevant to object interest mask, so move them to the mark flags.

This frees up some bits in the object interest mask.

Link: https://lore.kernel.org/r/20220422120327.3459282-3-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fsnotify.c                 |  4 ++--
 fs/notify/inotify/inotify.h          | 11 +++++++++--
 fs/notify/inotify/inotify_fsnotify.c |  2 +-
 fs/notify/inotify/inotify_user.c     | 38 +++++++++++++++++++++++-------------
 include/linux/fsnotify_backend.h     | 16 ++++++++-------
 5 files changed, 45 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 70a8516b78bc..6eee19d15e8c 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -253,7 +253,7 @@ static int fsnotify_handle_inode_event(struct fsnotify_group *group,
 	if (WARN_ON_ONCE(!inode && !dir))
 		return 0;
 
-	if ((inode_mark->mask & FS_EXCL_UNLINK) &&
+	if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) &&
 	    path && d_unlinked(path->dentry))
 		return 0;
 
@@ -581,7 +581,7 @@ static __init int fsnotify_init(void)
 {
 	int ret;
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 25);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23);
 
 	ret = init_srcu_struct(&fsnotify_mark_srcu);
 	if (ret)
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 8f00151eb731..7d5df7a21539 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,11 +27,18 @@ static inline struct inotify_event_info *INOTIFY_E(struct fsnotify_event *fse)
  * userspace.  There is at least one bit (FS_EVENT_ON_CHILD) which is
  * used only internally to the kernel.
  */
-#define INOTIFY_USER_MASK (IN_ALL_EVENTS | IN_ONESHOT | IN_EXCL_UNLINK)
+#define INOTIFY_USER_MASK (IN_ALL_EVENTS)
 
 static inline __u32 inotify_mark_user_mask(struct fsnotify_mark *fsn_mark)
 {
-	return fsn_mark->mask & INOTIFY_USER_MASK;
+	__u32 mask = fsn_mark->mask & INOTIFY_USER_MASK;
+
+	if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK)
+		mask |= IN_EXCL_UNLINK;
+	if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT)
+		mask |= IN_ONESHOT;
+
+	return mask;
 }
 
 extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index d92d7b0adc9a..49cfe2ae6d23 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -122,7 +122,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
 		fsnotify_destroy_event(group, fsn_event);
 	}
 
-	if (inode_mark->mask & IN_ONESHOT)
+	if (inode_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT)
 		fsnotify_destroy_mark(inode_mark, group);
 
 	return 0;
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 3ef57db0ec9d..d8907d32a05b 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -115,6 +115,21 @@ static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg)
 	return mask;
 }
 
+#define INOTIFY_MARK_FLAGS \
+	(FSNOTIFY_MARK_FLAG_EXCL_UNLINK | FSNOTIFY_MARK_FLAG_IN_ONESHOT)
+
+static inline unsigned int inotify_arg_to_flags(u32 arg)
+{
+	unsigned int flags = 0;
+
+	if (arg & IN_EXCL_UNLINK)
+		flags |= FSNOTIFY_MARK_FLAG_EXCL_UNLINK;
+	if (arg & IN_ONESHOT)
+		flags |= FSNOTIFY_MARK_FLAG_IN_ONESHOT;
+
+	return flags;
+}
+
 static inline u32 inotify_mask_to_arg(__u32 mask)
 {
 	return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED |
@@ -526,13 +541,10 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 	struct fsnotify_mark *fsn_mark;
 	struct inotify_inode_mark *i_mark;
 	__u32 old_mask, new_mask;
-	__u32 mask;
-	int add = (arg & IN_MASK_ADD);
+	int replace = !(arg & IN_MASK_ADD);
 	int create = (arg & IN_MASK_CREATE);
 	int ret;
 
-	mask = inotify_arg_to_mask(inode, arg);
-
 	fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
 	if (!fsn_mark)
 		return -ENOENT;
@@ -545,10 +557,12 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 
 	spin_lock(&fsn_mark->lock);
 	old_mask = fsn_mark->mask;
-	if (add)
-		fsn_mark->mask |= mask;
-	else
-		fsn_mark->mask = mask;
+	if (replace) {
+		fsn_mark->mask = 0;
+		fsn_mark->flags &= ~INOTIFY_MARK_FLAGS;
+	}
+	fsn_mark->mask |= inotify_arg_to_mask(inode, arg);
+	fsn_mark->flags |= inotify_arg_to_flags(arg);
 	new_mask = fsn_mark->mask;
 	spin_unlock(&fsn_mark->lock);
 
@@ -579,19 +593,17 @@ static int inotify_new_watch(struct fsnotify_group *group,
 			     u32 arg)
 {
 	struct inotify_inode_mark *tmp_i_mark;
-	__u32 mask;
 	int ret;
 	struct idr *idr = &group->inotify_data.idr;
 	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
 
-	mask = inotify_arg_to_mask(inode, arg);
-
 	tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
 	if (unlikely(!tmp_i_mark))
 		return -ENOMEM;
 
 	fsnotify_init_mark(&tmp_i_mark->fsn_mark, group);
-	tmp_i_mark->fsn_mark.mask = mask;
+	tmp_i_mark->fsn_mark.mask = inotify_arg_to_mask(inode, arg);
+	tmp_i_mark->fsn_mark.flags = inotify_arg_to_flags(arg);
 	tmp_i_mark->wd = -1;
 
 	ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
@@ -845,9 +857,7 @@ static int __init inotify_user_setup(void)
 	BUILD_BUG_ON(IN_UNMOUNT != FS_UNMOUNT);
 	BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW);
 	BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED);
-	BUILD_BUG_ON(IN_EXCL_UNLINK != FS_EXCL_UNLINK);
 	BUILD_BUG_ON(IN_ISDIR != FS_ISDIR);
-	BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT);
 
 	BUILD_BUG_ON(HWEIGHT32(ALL_INOTIFY_BITS) != 22);
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 0805b74cae44..b1c72edd9784 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -55,7 +55,6 @@
 #define FS_ACCESS_PERM		0x00020000	/* access event in a permissions hook */
 #define FS_OPEN_EXEC_PERM	0x00040000	/* open/exec event in a permission hook */
 
-#define FS_EXCL_UNLINK		0x04000000	/* do not send events if object is unlinked */
 /*
  * Set on inode mark that cares about things that happen to its children.
  * Always set for dnotify and inotify.
@@ -66,7 +65,6 @@
 #define FS_RENAME		0x10000000	/* File was renamed */
 #define FS_DN_MULTISHOT		0x20000000	/* dnotify multishot */
 #define FS_ISDIR		0x40000000	/* event occurred against dir */
-#define FS_IN_ONESHOT		0x80000000	/* only send event once */
 
 #define FS_MOVE			(FS_MOVED_FROM | FS_MOVED_TO)
 
@@ -106,8 +104,7 @@
 			     FS_ERROR)
 
 /* Extra flags that may be reported with event or control handling of events */
-#define ALL_FSNOTIFY_FLAGS  (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \
-			     FS_DN_MULTISHOT | FS_EVENT_ON_CHILD)
+#define ALL_FSNOTIFY_FLAGS  (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT)
 
 #define ALL_FSNOTIFY_BITS   (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS)
 
@@ -473,9 +470,14 @@ struct fsnotify_mark {
 	struct fsnotify_mark_connector *connector;
 	/* Events types to ignore [mark->lock, group->mark_mutex] */
 	__u32 ignored_mask;
-#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY	0x01
-#define FSNOTIFY_MARK_FLAG_ALIVE		0x02
-#define FSNOTIFY_MARK_FLAG_ATTACHED		0x04
+	/* General fsnotify mark flags */
+#define FSNOTIFY_MARK_FLAG_ALIVE		0x0001
+#define FSNOTIFY_MARK_FLAG_ATTACHED		0x0002
+	/* inotify mark flags */
+#define FSNOTIFY_MARK_FLAG_EXCL_UNLINK		0x0010
+#define FSNOTIFY_MARK_FLAG_IN_ONESHOT		0x0020
+	/* fanotify mark flags */
+#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY	0x0100
 	unsigned int flags;		/* flags [mark->lock] */
 };
 
-- 
cgit v1.2.3


From 867a448d587e7fa845bceaf4ee1c632448f2a9fa Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 22 Apr 2022 15:03:15 +0300
Subject: fsnotify: pass flags argument to fsnotify_alloc_group()

Add flags argument to fsnotify_alloc_group(), define and use the flag
FSNOTIFY_GROUP_USER in inotify and fanotify instead of the helper
fsnotify_alloc_user_group() to indicate user allocation.

Although the flag FSNOTIFY_GROUP_USER is currently not used after group
allocation, we store the flags argument in the group struct for future
use of other group flags.

Link: https://lore.kernel.org/r/20220422120327.3459282-5-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/nfsd/filecache.c                |  3 ++-
 fs/notify/dnotify/dnotify.c        |  2 +-
 fs/notify/fanotify/fanotify_user.c |  3 ++-
 fs/notify/group.c                  | 21 +++++++++------------
 fs/notify/inotify/inotify_user.c   |  3 ++-
 include/linux/fsnotify_backend.h   |  8 ++++++--
 kernel/audit_fsnotify.c            |  3 ++-
 kernel/audit_tree.c                |  2 +-
 kernel/audit_watch.c               |  2 +-
 9 files changed, 26 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 2c1b027774d4..74ddb828fd75 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -678,7 +678,8 @@ nfsd_file_cache_init(void)
 		goto out_shrinker;
 	}
 
-	nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops);
+	nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops,
+							0);
 	if (IS_ERR(nfsd_file_fsnotify_group)) {
 		pr_err("nfsd: unable to create fsnotify group: %ld\n",
 			PTR_ERR(nfsd_file_fsnotify_group));
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 829dd4a61b66..e4779926edf4 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -401,7 +401,7 @@ static int __init dnotify_init(void)
 					  SLAB_PANIC|SLAB_ACCOUNT);
 	dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT);
 
-	dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops);
+	dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0);
 	if (IS_ERR(dnotify_group))
 		panic("unable to allocate fsnotify group for dnotify\n");
 	dnotify_sysctl_init();
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 9b32b76a9c30..3649c99b3e45 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1355,7 +1355,8 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		f_flags |= O_NONBLOCK;
 
 	/* fsnotify_alloc_group takes a ref.  Dropped in fanotify_release */
-	group = fsnotify_alloc_user_group(&fanotify_fsnotify_ops);
+	group = fsnotify_alloc_group(&fanotify_fsnotify_ops,
+				     FSNOTIFY_GROUP_USER);
 	if (IS_ERR(group)) {
 		return PTR_ERR(group);
 	}
diff --git a/fs/notify/group.c b/fs/notify/group.c
index b7d4d64f87c2..18446b7b0d49 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -112,7 +112,8 @@ void fsnotify_put_group(struct fsnotify_group *group)
 EXPORT_SYMBOL_GPL(fsnotify_put_group);
 
 static struct fsnotify_group *__fsnotify_alloc_group(
-				const struct fsnotify_ops *ops, gfp_t gfp)
+				const struct fsnotify_ops *ops,
+				int flags, gfp_t gfp)
 {
 	struct fsnotify_group *group;
 
@@ -133,6 +134,7 @@ static struct fsnotify_group *__fsnotify_alloc_group(
 	INIT_LIST_HEAD(&group->marks_list);
 
 	group->ops = ops;
+	group->flags = flags;
 
 	return group;
 }
@@ -140,20 +142,15 @@ static struct fsnotify_group *__fsnotify_alloc_group(
 /*
  * Create a new fsnotify_group and hold a reference for the group returned.
  */
-struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
+struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops,
+					    int flags)
 {
-	return __fsnotify_alloc_group(ops, GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(fsnotify_alloc_group);
+	gfp_t gfp = (flags & FSNOTIFY_GROUP_USER) ? GFP_KERNEL_ACCOUNT :
+						    GFP_KERNEL;
 
-/*
- * Create a new fsnotify_group and hold a reference for the group returned.
- */
-struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops)
-{
-	return __fsnotify_alloc_group(ops, GFP_KERNEL_ACCOUNT);
+	return __fsnotify_alloc_group(ops, flags, gfp);
 }
-EXPORT_SYMBOL_GPL(fsnotify_alloc_user_group);
+EXPORT_SYMBOL_GPL(fsnotify_alloc_group);
 
 int fsnotify_fasync(int fd, struct file *file, int on)
 {
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index d8907d32a05b..146890ecd93a 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -656,7 +656,8 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 	struct fsnotify_group *group;
 	struct inotify_event_info *oevent;
 
-	group = fsnotify_alloc_user_group(&inotify_fsnotify_ops);
+	group = fsnotify_alloc_group(&inotify_fsnotify_ops,
+				     FSNOTIFY_GROUP_USER);
 	if (IS_ERR(group))
 		return group;
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index b1c72edd9784..f0bf557af009 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -210,6 +210,9 @@ struct fsnotify_group {
 	unsigned int priority;
 	bool shutdown;		/* group is being shut down, don't queue more events */
 
+#define FSNOTIFY_GROUP_USER	0x01 /* user allocated group */
+	int flags;
+
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
 	struct mutex mark_mutex;	/* protect marks_list */
 	atomic_t user_waits;		/* Number of tasks waiting for user
@@ -543,8 +546,9 @@ static inline void fsnotify_update_flags(struct dentry *dentry)
 /* called from fsnotify listeners, such as fanotify or dnotify */
 
 /* create a new group */
-extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops);
-extern struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops);
+extern struct fsnotify_group *fsnotify_alloc_group(
+				const struct fsnotify_ops *ops,
+				int flags);
 /* get reference to a group */
 extern void fsnotify_get_group(struct fsnotify_group *group);
 /* drop reference on a group from fsnotify_alloc_group */
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 02348b48447c..35fe149586c8 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -181,7 +181,8 @@ static const struct fsnotify_ops audit_mark_fsnotify_ops = {
 
 static int __init audit_fsnotify_init(void)
 {
-	audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops);
+	audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops,
+						    0);
 	if (IS_ERR(audit_fsnotify_group)) {
 		audit_fsnotify_group = NULL;
 		audit_panic("cannot create audit fsnotify group");
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index e7315d487163..b5c02f8573fe 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -1074,7 +1074,7 @@ static int __init audit_tree_init(void)
 
 	audit_tree_mark_cachep = KMEM_CACHE(audit_tree_mark, SLAB_PANIC);
 
-	audit_tree_group = fsnotify_alloc_group(&audit_tree_ops);
+	audit_tree_group = fsnotify_alloc_group(&audit_tree_ops, 0);
 	if (IS_ERR(audit_tree_group))
 		audit_panic("cannot initialize fsnotify group for rectree watches");
 
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 713b256be944..4b0957aa2cd4 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -493,7 +493,7 @@ static const struct fsnotify_ops audit_watch_fsnotify_ops = {
 
 static int __init audit_watch_init(void)
 {
-	audit_watch_group = fsnotify_alloc_group(&audit_watch_fsnotify_ops);
+	audit_watch_group = fsnotify_alloc_group(&audit_watch_fsnotify_ops, 0);
 	if (IS_ERR(audit_watch_group)) {
 		audit_watch_group = NULL;
 		audit_panic("cannot create audit fsnotify group");
-- 
cgit v1.2.3


From f3010343d9e119da35ee864b3a28993bb5c78ed7 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 22 Apr 2022 15:03:16 +0300
Subject: fsnotify: make allow_dups a property of the group

Instead of passing the allow_dups argument to fsnotify_add_mark()
as an argument, define the group flag FSNOTIFY_GROUP_DUPS to express
the allow_dups behavior and set this behavior at group creation time
for all calls of fsnotify_add_mark().

Rename the allow_dups argument to generic add_flags argument for future
use.

Link: https://lore.kernel.org/r/20220422120327.3459282-6-amir73il@gmail.com
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/mark.c                 | 12 ++++++------
 include/linux/fsnotify_backend.h | 13 +++++++------
 kernel/audit_fsnotify.c          |  4 ++--
 3 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index c86982be2d50..1fb246ea6175 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -574,7 +574,7 @@ out:
 static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
 				  fsnotify_connp_t *connp,
 				  unsigned int obj_type,
-				  int allow_dups, __kernel_fsid_t *fsid)
+				  int add_flags, __kernel_fsid_t *fsid)
 {
 	struct fsnotify_mark *lmark, *last = NULL;
 	struct fsnotify_mark_connector *conn;
@@ -633,7 +633,7 @@ restart:
 
 		if ((lmark->group == mark->group) &&
 		    (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) &&
-		    !allow_dups) {
+		    !(mark->group->flags & FSNOTIFY_GROUP_DUPS)) {
 			err = -EEXIST;
 			goto out_err;
 		}
@@ -668,7 +668,7 @@ out_err:
  */
 int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 			     fsnotify_connp_t *connp, unsigned int obj_type,
-			     int allow_dups, __kernel_fsid_t *fsid)
+			     int add_flags, __kernel_fsid_t *fsid)
 {
 	struct fsnotify_group *group = mark->group;
 	int ret = 0;
@@ -688,7 +688,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 	fsnotify_get_mark(mark); /* for g_list */
 	spin_unlock(&mark->lock);
 
-	ret = fsnotify_add_mark_list(mark, connp, obj_type, allow_dups, fsid);
+	ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid);
 	if (ret)
 		goto err;
 
@@ -708,14 +708,14 @@ err:
 }
 
 int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp,
-		      unsigned int obj_type, int allow_dups,
+		      unsigned int obj_type, int add_flags,
 		      __kernel_fsid_t *fsid)
 {
 	int ret;
 	struct fsnotify_group *group = mark->group;
 
 	mutex_lock(&group->mark_mutex);
-	ret = fsnotify_add_mark_locked(mark, connp, obj_type, allow_dups, fsid);
+	ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid);
 	mutex_unlock(&group->mark_mutex);
 	return ret;
 }
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index f0bf557af009..dd440e6ff528 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -211,6 +211,7 @@ struct fsnotify_group {
 	bool shutdown;		/* group is being shut down, don't queue more events */
 
 #define FSNOTIFY_GROUP_USER	0x01 /* user allocated group */
+#define FSNOTIFY_GROUP_DUPS	0x02 /* allow multiple marks per object */
 	int flags;
 
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
@@ -641,26 +642,26 @@ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn,
 /* attach the mark to the object */
 extern int fsnotify_add_mark(struct fsnotify_mark *mark,
 			     fsnotify_connp_t *connp, unsigned int obj_type,
-			     int allow_dups, __kernel_fsid_t *fsid);
+			     int add_flags, __kernel_fsid_t *fsid);
 extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 				    fsnotify_connp_t *connp,
-				    unsigned int obj_type, int allow_dups,
+				    unsigned int obj_type, int add_flags,
 				    __kernel_fsid_t *fsid);
 
 /* attach the mark to the inode */
 static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 					  struct inode *inode,
-					  int allow_dups)
+					  int add_flags)
 {
 	return fsnotify_add_mark(mark, &inode->i_fsnotify_marks,
-				 FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL);
+				 FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL);
 }
 static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark,
 						 struct inode *inode,
-						 int allow_dups)
+						 int add_flags)
 {
 	return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks,
-					FSNOTIFY_OBJ_TYPE_INODE, allow_dups,
+					FSNOTIFY_OBJ_TYPE_INODE, add_flags,
 					NULL);
 }
 
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 35fe149586c8..6432a37ac1c9 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -100,7 +100,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
 	audit_update_mark(audit_mark, dentry->d_inode);
 	audit_mark->rule = krule;
 
-	ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true);
+	ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0);
 	if (ret < 0) {
 		fsnotify_put_mark(&audit_mark->mark);
 		audit_mark = ERR_PTR(ret);
@@ -182,7 +182,7 @@ static const struct fsnotify_ops audit_mark_fsnotify_ops = {
 static int __init audit_fsnotify_init(void)
 {
 	audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops,
-						    0);
+						    FSNOTIFY_GROUP_DUPS);
 	if (IS_ERR(audit_fsnotify_group)) {
 		audit_fsnotify_group = NULL;
 		audit_panic("cannot create audit fsnotify group");
-- 
cgit v1.2.3


From 43b245a788e2d8f1bb742668a9bdace02fcb3e96 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 22 Apr 2022 15:03:17 +0300
Subject: fsnotify: create helpers for group mark_mutex lock

Create helpers to take and release the group mark_mutex lock.

Define a flag FSNOTIFY_GROUP_NOFS in fsnotify_group that determines
if the mark_mutex lock is fs reclaim safe or not.  If not safe, the
lock helpers take the lock and disable direct fs reclaim.

In that case we annotate the mutex with a different lockdep class to
express to lockdep that an allocation of mark of an fs reclaim safe group
may take the group lock of another "NOFS" group to evict inodes.

For now, converted only the callers in common code and no backend
defines the NOFS flag.  It is intended to be set by fanotify for
evictable marks support.

Link: https://lore.kernel.org/r/20220422120327.3459282-7-amir73il@gmail.com
Suggested-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220321112310.vpr7oxro2xkz5llh@quack3.lan/
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fdinfo.c               |  4 ++--
 fs/notify/group.c                | 11 +++++++++++
 fs/notify/mark.c                 | 24 +++++++++++-------------
 include/linux/fsnotify_backend.h | 28 ++++++++++++++++++++++++++++
 4 files changed, 52 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 3451708fd035..1f34c5c29fdb 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -28,13 +28,13 @@ static void show_fdinfo(struct seq_file *m, struct file *f,
 	struct fsnotify_group *group = f->private_data;
 	struct fsnotify_mark *mark;
 
-	mutex_lock(&group->mark_mutex);
+	fsnotify_group_lock(group);
 	list_for_each_entry(mark, &group->marks_list, g_list) {
 		show(m, mark);
 		if (seq_has_overflowed(m))
 			break;
 	}
-	mutex_unlock(&group->mark_mutex);
+	fsnotify_group_unlock(group);
 }
 
 #if defined(CONFIG_EXPORTFS)
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 18446b7b0d49..1de6631a3925 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -115,6 +115,7 @@ static struct fsnotify_group *__fsnotify_alloc_group(
 				const struct fsnotify_ops *ops,
 				int flags, gfp_t gfp)
 {
+	static struct lock_class_key nofs_marks_lock;
 	struct fsnotify_group *group;
 
 	group = kzalloc(sizeof(struct fsnotify_group), gfp);
@@ -135,6 +136,16 @@ static struct fsnotify_group *__fsnotify_alloc_group(
 
 	group->ops = ops;
 	group->flags = flags;
+	/*
+	 * For most backends, eviction of inode with a mark is not expected,
+	 * because marks hold a refcount on the inode against eviction.
+	 *
+	 * Use a different lockdep class for groups that support evictable
+	 * inode marks, because with evictable marks, mark_mutex is NOT
+	 * fs-reclaim safe - the mutex is taken when evicting inodes.
+	 */
+	if (flags & FSNOTIFY_GROUP_NOFS)
+		lockdep_set_class(&group->mark_mutex, &nofs_marks_lock);
 
 	return group;
 }
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 1fb246ea6175..982ca2f20ff5 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -398,9 +398,7 @@ void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info)
  */
 void fsnotify_detach_mark(struct fsnotify_mark *mark)
 {
-	struct fsnotify_group *group = mark->group;
-
-	WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
+	fsnotify_group_assert_locked(mark->group);
 	WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) &&
 		     refcount_read(&mark->refcnt) < 1 +
 			!!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED));
@@ -452,9 +450,9 @@ void fsnotify_free_mark(struct fsnotify_mark *mark)
 void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 			   struct fsnotify_group *group)
 {
-	mutex_lock(&group->mark_mutex);
+	fsnotify_group_lock(group);
 	fsnotify_detach_mark(mark);
-	mutex_unlock(&group->mark_mutex);
+	fsnotify_group_unlock(group);
 	fsnotify_free_mark(mark);
 }
 EXPORT_SYMBOL_GPL(fsnotify_destroy_mark);
@@ -673,7 +671,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 	struct fsnotify_group *group = mark->group;
 	int ret = 0;
 
-	BUG_ON(!mutex_is_locked(&group->mark_mutex));
+	fsnotify_group_assert_locked(group);
 
 	/*
 	 * LOCKING ORDER!!!!
@@ -714,9 +712,9 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp,
 	int ret;
 	struct fsnotify_group *group = mark->group;
 
-	mutex_lock(&group->mark_mutex);
+	fsnotify_group_lock(group);
 	ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid);
-	mutex_unlock(&group->mark_mutex);
+	fsnotify_group_unlock(group);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(fsnotify_add_mark);
@@ -770,24 +768,24 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
 	 * move marks to free to to_free list in one go and then free marks in
 	 * to_free list one by one.
 	 */
-	mutex_lock(&group->mark_mutex);
+	fsnotify_group_lock(group);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
 		if (mark->connector->type == obj_type)
 			list_move(&mark->g_list, &to_free);
 	}
-	mutex_unlock(&group->mark_mutex);
+	fsnotify_group_unlock(group);
 
 clear:
 	while (1) {
-		mutex_lock(&group->mark_mutex);
+		fsnotify_group_lock(group);
 		if (list_empty(head)) {
-			mutex_unlock(&group->mark_mutex);
+			fsnotify_group_unlock(group);
 			break;
 		}
 		mark = list_first_entry(head, struct fsnotify_mark, g_list);
 		fsnotify_get_mark(mark);
 		fsnotify_detach_mark(mark);
-		mutex_unlock(&group->mark_mutex);
+		fsnotify_group_unlock(group);
 		fsnotify_free_mark(mark);
 		fsnotify_put_mark(mark);
 	}
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index dd440e6ff528..d62111e83244 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -20,6 +20,7 @@
 #include <linux/user_namespace.h>
 #include <linux/refcount.h>
 #include <linux/mempool.h>
+#include <linux/sched/mm.h>
 
 /*
  * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily
@@ -212,7 +213,9 @@ struct fsnotify_group {
 
 #define FSNOTIFY_GROUP_USER	0x01 /* user allocated group */
 #define FSNOTIFY_GROUP_DUPS	0x02 /* allow multiple marks per object */
+#define FSNOTIFY_GROUP_NOFS	0x04 /* group lock is not direct reclaim safe */
 	int flags;
+	unsigned int owner_flags;	/* stored flags of mark_mutex owner */
 
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
 	struct mutex mark_mutex;	/* protect marks_list */
@@ -254,6 +257,31 @@ struct fsnotify_group {
 	};
 };
 
+/*
+ * These helpers are used to prevent deadlock when reclaiming inodes with
+ * evictable marks of the same group that is allocating a new mark.
+ */
+static inline void fsnotify_group_lock(struct fsnotify_group *group)
+{
+	mutex_lock(&group->mark_mutex);
+	if (group->flags & FSNOTIFY_GROUP_NOFS)
+		group->owner_flags = memalloc_nofs_save();
+}
+
+static inline void fsnotify_group_unlock(struct fsnotify_group *group)
+{
+	if (group->flags & FSNOTIFY_GROUP_NOFS)
+		memalloc_nofs_restore(group->owner_flags);
+	mutex_unlock(&group->mark_mutex);
+}
+
+static inline void fsnotify_group_assert_locked(struct fsnotify_group *group)
+{
+	WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
+	if (group->flags & FSNOTIFY_GROUP_NOFS)
+		WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
+}
+
 /* When calling fsnotify tell it if the data is a path or inode */
 enum fsnotify_data_type {
 	FSNOTIFY_EVENT_NONE,
-- 
cgit v1.2.3


From c3638b5b13740fa31762d414bbce8b7a694e582a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 22 Apr 2022 15:03:22 +0300
Subject: fsnotify: allow adding an inode mark without pinning inode

fsnotify_add_mark() and variants implicitly take a reference on inode
when attaching a mark to an inode.

Make that behavior opt-out with the mark flag FSNOTIFY_MARK_FLAG_NO_IREF.

Instead of taking the inode reference when attaching connector to inode
and dropping the inode reference when detaching connector from inode,
take the inode reference on attach of the first mark that wants to hold
an inode reference and drop the inode reference on detach of the last
mark that wants to hold an inode reference.

Backends can "upgrade" an existing mark to take an inode reference, but
cannot "downgrade" a mark with inode reference to release the refernce.

This leaves the choice to the backend whether or not to pin the inode
when adding an inode mark.

This is intended to be used when adding a mark with ignored mask that is
used for optimization in cases where group can afford getting unneeded
events and reinstate the mark with ignored mask when inode is accessed
again after being evicted.

Link: https://lore.kernel.org/r/20220422120327.3459282-12-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/mark.c                 | 76 +++++++++++++++++++++++++++++-----------
 include/linux/fsnotify_backend.h |  2 ++
 2 files changed, 58 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 982ca2f20ff5..c74ef947447d 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -116,20 +116,64 @@ __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn)
 	return *fsnotify_conn_mask_p(conn);
 }
 
-static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+static void fsnotify_get_inode_ref(struct inode *inode)
+{
+	ihold(inode);
+	atomic_long_inc(&inode->i_sb->s_fsnotify_connectors);
+}
+
+/*
+ * Grab or drop inode reference for the connector if needed.
+ *
+ * When it's time to drop the reference, we only clear the HAS_IREF flag and
+ * return the inode object. fsnotify_drop_object() will be resonsible for doing
+ * iput() outside of spinlocks. This happens when last mark that wanted iref is
+ * detached.
+ */
+static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn,
+					  bool want_iref)
+{
+	bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF;
+	struct inode *inode = NULL;
+
+	if (conn->type != FSNOTIFY_OBJ_TYPE_INODE ||
+	    want_iref == has_iref)
+		return NULL;
+
+	if (want_iref) {
+		/* Pin inode if any mark wants inode refcount held */
+		fsnotify_get_inode_ref(fsnotify_conn_inode(conn));
+		conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF;
+	} else {
+		/* Unpin inode after detach of last mark that wanted iref */
+		inode = fsnotify_conn_inode(conn);
+		conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF;
+	}
+
+	return inode;
+}
+
+static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
 {
 	u32 new_mask = 0;
+	bool want_iref = false;
 	struct fsnotify_mark *mark;
 
 	assert_spin_locked(&conn->lock);
 	/* We can get detached connector here when inode is getting unlinked. */
 	if (!fsnotify_valid_obj_type(conn->type))
-		return;
+		return NULL;
 	hlist_for_each_entry(mark, &conn->list, obj_list) {
-		if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)
-			new_mask |= fsnotify_calc_mask(mark);
+		if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED))
+			continue;
+		new_mask |= fsnotify_calc_mask(mark);
+		if (conn->type == FSNOTIFY_OBJ_TYPE_INODE &&
+		    !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
+			want_iref = true;
 	}
 	*fsnotify_conn_mask_p(conn) = new_mask;
+
+	return fsnotify_update_iref(conn, want_iref);
 }
 
 /*
@@ -169,12 +213,6 @@ static void fsnotify_connector_destroy_workfn(struct work_struct *work)
 	}
 }
 
-static void fsnotify_get_inode_ref(struct inode *inode)
-{
-	ihold(inode);
-	atomic_long_inc(&inode->i_sb->s_fsnotify_connectors);
-}
-
 static void fsnotify_put_inode_ref(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
@@ -213,6 +251,10 @@ static void *fsnotify_detach_connector_from_object(
 	if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) {
 		inode = fsnotify_conn_inode(conn);
 		inode->i_fsnotify_mask = 0;
+
+		/* Unpin inode when detaching from connector */
+		if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF))
+			inode = NULL;
 	} else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
 		fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0;
 	} else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) {
@@ -274,7 +316,8 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 		objp = fsnotify_detach_connector_from_object(conn, &type);
 		free_conn = true;
 	} else {
-		__fsnotify_recalc_mask(conn);
+		objp = __fsnotify_recalc_mask(conn);
+		type = conn->type;
 	}
 	WRITE_ONCE(mark->connector, NULL);
 	spin_unlock(&conn->lock);
@@ -497,7 +540,6 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
 					       unsigned int obj_type,
 					       __kernel_fsid_t *fsid)
 {
-	struct inode *inode = NULL;
 	struct fsnotify_mark_connector *conn;
 
 	conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL);
@@ -505,6 +547,7 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
 		return -ENOMEM;
 	spin_lock_init(&conn->lock);
 	INIT_HLIST_HEAD(&conn->list);
+	conn->flags = 0;
 	conn->type = obj_type;
 	conn->obj = connp;
 	/* Cache fsid of filesystem containing the object */
@@ -515,10 +558,6 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
 		conn->fsid.val[0] = conn->fsid.val[1] = 0;
 		conn->flags = 0;
 	}
-	if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) {
-		inode = fsnotify_conn_inode(conn);
-		fsnotify_get_inode_ref(inode);
-	}
 	fsnotify_get_sb_connectors(conn);
 
 	/*
@@ -527,8 +566,6 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
 	 */
 	if (cmpxchg(connp, NULL, conn)) {
 		/* Someone else created list structure for us */
-		if (inode)
-			fsnotify_put_inode_ref(inode);
 		fsnotify_put_sb_connectors(conn);
 		kmem_cache_free(fsnotify_mark_connector_cachep, conn);
 	}
@@ -690,8 +727,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 	if (ret)
 		goto err;
 
-	if (mark->mask || mark->ignored_mask)
-		fsnotify_recalc_mask(mark->connector);
+	fsnotify_recalc_mask(mark->connector);
 
 	return ret;
 err:
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index d62111e83244..9a1a9e78f69f 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -456,6 +456,7 @@ struct fsnotify_mark_connector {
 	spinlock_t lock;
 	unsigned short type;	/* Type of object [lock] */
 #define FSNOTIFY_CONN_FLAG_HAS_FSID	0x01
+#define FSNOTIFY_CONN_FLAG_HAS_IREF	0x02
 	unsigned short flags;	/* flags [lock] */
 	__kernel_fsid_t fsid;	/* fsid of filesystem containing object */
 	union {
@@ -510,6 +511,7 @@ struct fsnotify_mark {
 #define FSNOTIFY_MARK_FLAG_IN_ONESHOT		0x0020
 	/* fanotify mark flags */
 #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY	0x0100
+#define FSNOTIFY_MARK_FLAG_NO_IREF		0x0200
 	unsigned int flags;		/* flags [mark->lock] */
 };
 
-- 
cgit v1.2.3


From 5f9d3bd520261fd7a850818c71809fd580e0f30c Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 22 Apr 2022 15:03:27 +0300
Subject: fanotify: enable "evictable" inode marks

Now that the direct reclaim path is handled we can enable evictable
inode marks.

Link: https://lore.kernel.org/r/20220422120327.3459282-17-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify_user.c | 2 +-
 include/linux/fanotify.h           | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 228cf25e9230..edad67d674dc 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1787,7 +1787,7 @@ static int __init fanotify_user_setup(void)
 
 	BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
-	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
+	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 10);
 
 	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
 					 SLAB_PANIC|SLAB_ACCOUNT);
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 419cadcd7ff5..edc28555814c 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -66,6 +66,7 @@
 				 FAN_MARK_ONLYDIR | \
 				 FAN_MARK_IGNORED_MASK | \
 				 FAN_MARK_IGNORED_SURV_MODIFY | \
+				 FAN_MARK_EVICTABLE | \
 				 FAN_MARK_FLUSH)
 
 /*
-- 
cgit v1.2.3


From 430c3500995484962bdbccf358201afef8055535 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 25 Apr 2022 10:51:59 +0100
Subject: firmware: cirrus: cs_dsp: Avoid padding bytes in cs_dsp_coeff_ctl

Change the order of members in struct cs_dsp_coeff_ctl to avoid
the compiler having to insert alignment padding bytes. On a x86_64
build this saves 16 bytes per control.

- Pointers are collected to the top of the struct (with the exception of
  priv, as noted below), so that they are inherently aligned.
- The set and enable bitflags are placed together so they can be merged.
- priv is placed at the end of the struct - it is for use by the
  client so it is helpful to make it stand out, and since the compiler
  will always pad the struct size to an alignment multiple putting a
  pointer last won't introduce any more padding.
- struct cs_dsp_alg_region is placed at the end, right before priv, for
  the same reasoning as priv.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20220425095159.3044527-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/firmware/cirrus/cs_dsp.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h
index 38b4da3ddfe4..30055706cce2 100644
--- a/include/linux/firmware/cirrus/cs_dsp.h
+++ b/include/linux/firmware/cirrus/cs_dsp.h
@@ -68,36 +68,36 @@ struct cs_dsp_alg_region {
 
 /**
  * struct cs_dsp_coeff_ctl - Describes a coefficient control
+ * @list:		List node for internal use
+ * @dsp:		DSP instance associated with this control
+ * @cache:		Cached value of the control
  * @fw_name:		Name of the firmware
  * @subname:		Name of the control parsed from the WMFW
  * @subname_len:	Length of subname
- * @alg_region:		Logical region associated with this control
- * @dsp:		DSP instance associated with this control
- * @enabled:		Flag indicating whether control is enabled
- * @list:		List node for internal use
- * @cache:		Cached value of the control
  * @offset:		Offset of control within alg_region in words
  * @len:		Length of the cached value in bytes
- * @set:		Flag indicating the value has been written by the user
- * @flags:		Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h
  * @type:		One of the WMFW_CTL_TYPE_ control types defined in wmfw.h
+ * @flags:		Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h
+ * @set:		Flag indicating the value has been written by the user
+ * @enabled:		Flag indicating whether control is enabled
+ * @alg_region:		Logical region associated with this control
  * @priv:		For use by the client
  */
 struct cs_dsp_coeff_ctl {
+	struct list_head list;
+	struct cs_dsp *dsp;
+	void *cache;
 	const char *fw_name;
 	/* Subname is needed to match with firmware */
 	const char *subname;
 	unsigned int subname_len;
-	struct cs_dsp_alg_region alg_region;
-	struct cs_dsp *dsp;
-	unsigned int enabled:1;
-	struct list_head list;
-	void *cache;
 	unsigned int offset;
 	size_t len;
-	unsigned int set:1;
-	unsigned int flags;
 	unsigned int type;
+	unsigned int flags;
+	unsigned int set:1;
+	unsigned int enabled:1;
+	struct cs_dsp_alg_region alg_region;
 
 	void *priv;
 };
-- 
cgit v1.2.3


From 66200bbcde697dea7f48071d325ea4dec6f66b11 Mon Sep 17 00:00:00 2001
From: Michael Kelley <mikelley@microsoft.com>
Date: Tue, 12 Apr 2022 19:49:00 -0700
Subject: Drivers: hv: vmbus: Add VMbus IMC device to unsupported list

Hyper-V may offer an Initial Machine Configuration (IMC) synthetic
device to guest VMs. The device may be used by Windows guests to get
specialization information, such as the hostname.  But the device
is not used in Linux and there is no Linux driver, so it is
unsupported.

Currently, the IMC device GUID is not recognized by the VMbus driver,
which results in an "Unknown GUID" error message during boot. Add
the GUID to the list of known but unsupported devices so that the
error message is not generated. Other than avoiding the error message,
there is no change in guest behavior.

Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/1649818140-100953-1-git-send-email-mikelley@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel_mgmt.c |  1 +
 include/linux/hyperv.h    | 12 +++++++++---
 2 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 85a2142c9384..50fea31f019f 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -152,6 +152,7 @@ static const struct {
 	{ HV_AVMA1_GUID },
 	{ HV_AVMA2_GUID },
 	{ HV_RDV_GUID	},
+	{ HV_IMC_GUID	},
 };
 
 /*
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index fe2e0179ed51..2d085d951ee4 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1451,12 +1451,14 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size);
 			  0x80, 0x2e, 0x27, 0xed, 0xe1, 0x9f)
 
 /*
- * Linux doesn't support the 3 devices: the first two are for
- * Automatic Virtual Machine Activation, and the third is for
- * Remote Desktop Virtualization.
+ * Linux doesn't support these 4 devices: the first two are for
+ * Automatic Virtual Machine Activation, the third is for
+ * Remote Desktop Virtualization, and the fourth is Initial
+ * Machine Configuration (IMC) used only by Windows guests.
  * {f8e65716-3cb3-4a06-9a60-1889c5cccab5}
  * {3375baf4-9e15-4b30-b765-67acb10d607b}
  * {276aacf4-ac15-426c-98dd-7521ad3f01fe}
+ * {c376c1c3-d276-48d2-90a9-c04748072c60}
  */
 
 #define HV_AVMA1_GUID \
@@ -1471,6 +1473,10 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size);
 	.guid = GUID_INIT(0x276aacf4, 0xac15, 0x426c, 0x98, 0xdd, \
 			  0x75, 0x21, 0xad, 0x3f, 0x01, 0xfe)
 
+#define HV_IMC_GUID \
+	.guid = GUID_INIT(0xc376c1c3, 0xd276, 0x48d2, 0x90, 0xa9, \
+			  0xc0, 0x47, 0x48, 0x07, 0x2c, 0x60)
+
 /*
  * Common header for Hyper-V ICs
  */
-- 
cgit v1.2.3


From b03afa57c65e1e045e02df49777e953742745f4c Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Tue, 19 Apr 2022 14:23:22 +0200
Subject: Drivers: hv: vmbus: Introduce vmbus_sendpacket_getid()

The function can be used to send a VMbus packet and retrieve the
corresponding transaction ID.  It will be used by hv_pci.

No functional change.

Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20220419122325.10078-4-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c      | 38 ++++++++++++++++++++++++++++++++------
 drivers/hv/hyperv_vmbus.h |  2 +-
 drivers/hv/ring_buffer.c  | 14 +++++++++++---
 include/linux/hyperv.h    |  7 +++++++
 4 files changed, 51 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 20fc8d50a039..585a8084848b 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -1022,11 +1022,13 @@ void vmbus_close(struct vmbus_channel *channel)
 EXPORT_SYMBOL_GPL(vmbus_close);
 
 /**
- * vmbus_sendpacket() - Send the specified buffer on the given channel
+ * vmbus_sendpacket_getid() - Send the specified buffer on the given channel
  * @channel: Pointer to vmbus_channel structure
  * @buffer: Pointer to the buffer you want to send the data from.
  * @bufferlen: Maximum size of what the buffer holds.
  * @requestid: Identifier of the request
+ * @trans_id: Identifier of the transaction associated to this request, if
+ *            the send is successful; undefined, otherwise.
  * @type: Type of packet that is being sent e.g. negotiate, time
  *	  packet etc.
  * @flags: 0 or VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED
@@ -1036,8 +1038,8 @@ EXPORT_SYMBOL_GPL(vmbus_close);
  *
  * Mainly used by Hyper-V drivers.
  */
-int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
-			   u32 bufferlen, u64 requestid,
+int vmbus_sendpacket_getid(struct vmbus_channel *channel, void *buffer,
+			   u32 bufferlen, u64 requestid, u64 *trans_id,
 			   enum vmbus_packet_type type, u32 flags)
 {
 	struct vmpacket_descriptor desc;
@@ -1063,7 +1065,31 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, num_vecs, requestid);
+	return hv_ringbuffer_write(channel, bufferlist, num_vecs, requestid, trans_id);
+}
+EXPORT_SYMBOL(vmbus_sendpacket_getid);
+
+/**
+ * vmbus_sendpacket() - Send the specified buffer on the given channel
+ * @channel: Pointer to vmbus_channel structure
+ * @buffer: Pointer to the buffer you want to send the data from.
+ * @bufferlen: Maximum size of what the buffer holds.
+ * @requestid: Identifier of the request
+ * @type: Type of packet that is being sent e.g. negotiate, time
+ *	  packet etc.
+ * @flags: 0 or VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED
+ *
+ * Sends data in @buffer directly to Hyper-V via the vmbus.
+ * This will send the data unparsed to Hyper-V.
+ *
+ * Mainly used by Hyper-V drivers.
+ */
+int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
+		     u32 bufferlen, u64 requestid,
+		     enum vmbus_packet_type type, u32 flags)
+{
+	return vmbus_sendpacket_getid(channel, buffer, bufferlen,
+				      requestid, NULL, type, flags);
 }
 EXPORT_SYMBOL(vmbus_sendpacket);
 
@@ -1122,7 +1148,7 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, 3, requestid);
+	return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
 
@@ -1160,7 +1186,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, 3, requestid);
+	return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc);
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 6b45c22bb717..4f5b824b16cf 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -181,7 +181,7 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info);
 
 int hv_ringbuffer_write(struct vmbus_channel *channel,
 			const struct kvec *kv_list, u32 kv_count,
-			u64 requestid);
+			u64 requestid, u64 *trans_id);
 
 int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 3d215d9dec43..e101b11f95e5 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -283,7 +283,7 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
 /* Write to the ring buffer. */
 int hv_ringbuffer_write(struct vmbus_channel *channel,
 			const struct kvec *kv_list, u32 kv_count,
-			u64 requestid)
+			u64 requestid, u64 *trans_id)
 {
 	int i;
 	u32 bytes_avail_towrite;
@@ -294,7 +294,7 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 	unsigned long flags;
 	struct hv_ring_buffer_info *outring_info = &channel->outbound;
 	struct vmpacket_descriptor *desc = kv_list[0].iov_base;
-	u64 rqst_id = VMBUS_NO_RQSTOR;
+	u64 __trans_id, rqst_id = VMBUS_NO_RQSTOR;
 
 	if (channel->rescind)
 		return -ENODEV;
@@ -353,7 +353,15 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 		}
 	}
 	desc = hv_get_ring_buffer(outring_info) + old_write;
-	desc->trans_id = (rqst_id == VMBUS_NO_RQSTOR) ? requestid : rqst_id;
+	__trans_id = (rqst_id == VMBUS_NO_RQSTOR) ? requestid : rqst_id;
+	/*
+	 * Ensure the compiler doesn't generate code that reads the value of
+	 * the transaction ID from the ring buffer, which is shared with the
+	 * Hyper-V host and subject to being changed at any time.
+	 */
+	WRITE_ONCE(desc->trans_id, __trans_id);
+	if (trans_id)
+		*trans_id = __trans_id;
 
 	/* Set previous packet start */
 	prev_indices = hv_get_ring_bufferindices(outring_info);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 2d085d951ee4..7cb8718825ee 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1161,6 +1161,13 @@ extern int vmbus_open(struct vmbus_channel *channel,
 
 extern void vmbus_close(struct vmbus_channel *channel);
 
+extern int vmbus_sendpacket_getid(struct vmbus_channel *channel,
+				  void *buffer,
+				  u32 bufferLen,
+				  u64 requestid,
+				  u64 *trans_id,
+				  enum vmbus_packet_type type,
+				  u32 flags);
 extern int vmbus_sendpacket(struct vmbus_channel *channel,
 				  void *buffer,
 				  u32 bufferLen,
-- 
cgit v1.2.3


From 0aadb6a7bb811554cf39318b5d18e8ec50dd9f02 Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Tue, 19 Apr 2022 14:23:23 +0200
Subject: Drivers: hv: vmbus: Introduce vmbus_request_addr_match()

The function can be used to retrieve and clear/remove a transation ID
from a channel requestor, provided the memory address corresponding to
the ID equals a specified address.  The function, and its 'lockless'
variant __vmbus_request_addr_match(), will be used by hv_pci.

Refactor vmbus_request_addr() to reuse the 'newly' introduced code.

No functional change.

Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20220419122325.10078-5-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c   | 65 ++++++++++++++++++++++++++++++++++++--------------
 include/linux/hyperv.h |  5 ++++
 2 files changed, 52 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 585a8084848b..49f10a603a09 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -1279,17 +1279,11 @@ u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr)
 }
 EXPORT_SYMBOL_GPL(vmbus_next_request_id);
 
-/*
- * vmbus_request_addr - Returns the memory address stored at @trans_id
- * in @rqstor. Uses a spin lock to avoid race conditions.
- * @channel: Pointer to the VMbus channel struct
- * @trans_id: Request id sent back from Hyper-V. Becomes the requestor's
- * next request id.
- */
-u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id)
+/* As in vmbus_request_addr_match() but without the requestor lock */
+u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id,
+			       u64 rqst_addr)
 {
 	struct vmbus_requestor *rqstor = &channel->requestor;
-	unsigned long flags;
 	u64 req_addr;
 
 	/* Check rqstor has been initialized */
@@ -1300,25 +1294,60 @@ u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id)
 	if (!trans_id)
 		return VMBUS_RQST_ERROR;
 
-	spin_lock_irqsave(&rqstor->req_lock, flags);
-
 	/* Data corresponding to trans_id is stored at trans_id - 1 */
 	trans_id--;
 
 	/* Invalid trans_id */
-	if (trans_id >= rqstor->size || !test_bit(trans_id, rqstor->req_bitmap)) {
-		spin_unlock_irqrestore(&rqstor->req_lock, flags);
+	if (trans_id >= rqstor->size || !test_bit(trans_id, rqstor->req_bitmap))
 		return VMBUS_RQST_ERROR;
-	}
 
 	req_addr = rqstor->req_arr[trans_id];
-	rqstor->req_arr[trans_id] = rqstor->next_request_id;
-	rqstor->next_request_id = trans_id;
+	if (rqst_addr == VMBUS_RQST_ADDR_ANY || req_addr == rqst_addr) {
+		rqstor->req_arr[trans_id] = rqstor->next_request_id;
+		rqstor->next_request_id = trans_id;
 
-	/* The already held spin lock provides atomicity */
-	bitmap_clear(rqstor->req_bitmap, trans_id, 1);
+		/* The already held spin lock provides atomicity */
+		bitmap_clear(rqstor->req_bitmap, trans_id, 1);
+	}
+
+	return req_addr;
+}
+EXPORT_SYMBOL_GPL(__vmbus_request_addr_match);
+
+/*
+ * vmbus_request_addr_match - Clears/removes @trans_id from the @channel's
+ * requestor, provided the memory address stored at @trans_id equals @rqst_addr
+ * (or provided @rqst_addr matches the sentinel value VMBUS_RQST_ADDR_ANY).
+ *
+ * Returns the memory address stored at @trans_id, or VMBUS_RQST_ERROR if
+ * @trans_id is not contained in the requestor.
+ *
+ * Acquires and releases the requestor spin lock.
+ */
+u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id,
+			     u64 rqst_addr)
+{
+	struct vmbus_requestor *rqstor = &channel->requestor;
+	unsigned long flags;
+	u64 req_addr;
 
+	spin_lock_irqsave(&rqstor->req_lock, flags);
+	req_addr = __vmbus_request_addr_match(channel, trans_id, rqst_addr);
 	spin_unlock_irqrestore(&rqstor->req_lock, flags);
+
 	return req_addr;
 }
+EXPORT_SYMBOL_GPL(vmbus_request_addr_match);
+
+/*
+ * vmbus_request_addr - Returns the memory address stored at @trans_id
+ * in @rqstor. Uses a spin lock to avoid race conditions.
+ * @channel: Pointer to the VMbus channel struct
+ * @trans_id: Request id sent back from Hyper-V. Becomes the requestor's
+ * next request id.
+ */
+u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id)
+{
+	return vmbus_request_addr_match(channel, trans_id, VMBUS_RQST_ADDR_ANY);
+}
 EXPORT_SYMBOL_GPL(vmbus_request_addr);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 7cb8718825ee..2e4962a2fbec 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -788,6 +788,7 @@ struct vmbus_requestor {
 
 #define VMBUS_NO_RQSTOR U64_MAX
 #define VMBUS_RQST_ERROR (U64_MAX - 1)
+#define VMBUS_RQST_ADDR_ANY U64_MAX
 /* NetVSC-specific */
 #define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2)
 /* StorVSC-specific */
@@ -1042,6 +1043,10 @@ struct vmbus_channel {
 };
 
 u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr);
+u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id,
+			       u64 rqst_addr);
+u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id,
+			     u64 rqst_addr);
 u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id);
 
 static inline bool is_hvsock_channel(const struct vmbus_channel *c)
-- 
cgit v1.2.3


From b91eaf7267cf7aec0a4e087decf7770dfb694d78 Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Tue, 19 Apr 2022 14:23:24 +0200
Subject: Drivers: hv: vmbus: Introduce {lock,unlock}_requestor()

To abtract the lock and unlock operations on the requestor spin lock.
The helpers will come in handy in hv_pci.

No functional change.

Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20220419122325.10078-6-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c   | 11 +++++------
 include/linux/hyperv.h | 15 +++++++++++++++
 2 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 49f10a603a09..56f7e06c673e 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -1252,12 +1252,12 @@ u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr)
 	if (!channel->rqstor_size)
 		return VMBUS_NO_RQSTOR;
 
-	spin_lock_irqsave(&rqstor->req_lock, flags);
+	lock_requestor(channel, flags);
 	current_id = rqstor->next_request_id;
 
 	/* Requestor array is full */
 	if (current_id >= rqstor->size) {
-		spin_unlock_irqrestore(&rqstor->req_lock, flags);
+		unlock_requestor(channel, flags);
 		return VMBUS_RQST_ERROR;
 	}
 
@@ -1267,7 +1267,7 @@ u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr)
 	/* The already held spin lock provides atomicity */
 	bitmap_set(rqstor->req_bitmap, current_id, 1);
 
-	spin_unlock_irqrestore(&rqstor->req_lock, flags);
+	unlock_requestor(channel, flags);
 
 	/*
 	 * Cannot return an ID of 0, which is reserved for an unsolicited
@@ -1327,13 +1327,12 @@ EXPORT_SYMBOL_GPL(__vmbus_request_addr_match);
 u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id,
 			     u64 rqst_addr)
 {
-	struct vmbus_requestor *rqstor = &channel->requestor;
 	unsigned long flags;
 	u64 req_addr;
 
-	spin_lock_irqsave(&rqstor->req_lock, flags);
+	lock_requestor(channel, flags);
 	req_addr = __vmbus_request_addr_match(channel, trans_id, rqst_addr);
-	spin_unlock_irqrestore(&rqstor->req_lock, flags);
+	unlock_requestor(channel, flags);
 
 	return req_addr;
 }
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 2e4962a2fbec..460a716f4748 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1042,6 +1042,21 @@ struct vmbus_channel {
 	u32 max_pkt_size;
 };
 
+#define lock_requestor(channel, flags)					\
+do {									\
+	struct vmbus_requestor *rqstor = &(channel)->requestor;		\
+									\
+	spin_lock_irqsave(&rqstor->req_lock, flags);			\
+} while (0)
+
+static __always_inline void unlock_requestor(struct vmbus_channel *channel,
+					     unsigned long flags)
+{
+	struct vmbus_requestor *rqstor = &channel->requestor;
+
+	spin_unlock_irqrestore(&rqstor->req_lock, flags);
+}
+
 u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr);
 u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id,
 			       u64 rqst_addr);
-- 
cgit v1.2.3


From 067c098766c6af667a9002d4e33cf1f3c998abbe Mon Sep 17 00:00:00 2001
From: Frank Rowand <frank.rowand@sony.com>
Date: Wed, 20 Apr 2022 17:25:05 -0500
Subject: of: overlay: rework overlay apply and remove kfree()s

Fix various kfree() issues related to of_overlay_apply().
  - Double kfree() of fdt and tree when init_overlay_changeset()
    returns an error.
  - free_overlay_changeset() free the root of the unflattened
    overlay (variable tree) instead of the memory that contains
    the unflattened overlay.
  - For the case of a failure during applying an overlay, move kfree()
    of new_fdt and overlay_mem into free_overlay_changeset(), which
    is called by the function that allocated them.
  - For the case of removing an overlay, the kfree() of new_fdt and
    overlay_mem remains in free_overlay_changeset().
  - Check return value of of_fdt_unflatten_tree() for error instead
    of checking the returned value of overlay_root.
  - When storing pointers to allocated objects in ovcs, do so as
    near to the allocation as possible instead of in deeply layered
    function.

More clearly document policy related to lifetime of pointers into
overlay memory.

Double kfree()
Reported-by: Slawomir Stepien <slawomir.stepien@nokia.com>

Signed-off-by: Frank Rowand <frank.rowand@sony.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20220420222505.928492-3-frowand.list@gmail.com
---
 Documentation/devicetree/overlay-notes.rst |  30 +++-
 drivers/of/overlay.c                       | 263 ++++++++++++++---------------
 include/linux/of.h                         |   3 +-
 3 files changed, 153 insertions(+), 143 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/overlay-notes.rst b/Documentation/devicetree/overlay-notes.rst
index b2b8db765b8c..e139f22b363e 100644
--- a/Documentation/devicetree/overlay-notes.rst
+++ b/Documentation/devicetree/overlay-notes.rst
@@ -119,10 +119,32 @@ Finally, if you need to remove all overlays in one-go, just call
 of_overlay_remove_all() which will remove every single one in the correct
 order.
 
-In addition, there is the option to register notifiers that get called on
+There is the option to register notifiers that get called on
 overlay operations. See of_overlay_notifier_register/unregister and
 enum of_overlay_notify_action for details.
 
-Note that a notifier callback is not supposed to store pointers to a device
-tree node or its content beyond OF_OVERLAY_POST_REMOVE corresponding to the
-respective node it received.
+A notifier callback for OF_OVERLAY_PRE_APPLY, OF_OVERLAY_POST_APPLY, or
+OF_OVERLAY_PRE_REMOVE may store pointers to a device tree node in the overlay
+or its content but these pointers must not persist past the notifier callback
+for OF_OVERLAY_POST_REMOVE.  The memory containing the overlay will be
+kfree()ed after OF_OVERLAY_POST_REMOVE notifiers are called.  Note that the
+memory will be kfree()ed even if the notifier for OF_OVERLAY_POST_REMOVE
+returns an error.
+
+The changeset notifiers in drivers/of/dynamic.c are a second type of notifier
+that could be triggered by applying or removing an overlay.  These notifiers
+are not allowed to store pointers to a device tree node in the overlay
+or its content.  The overlay code does not protect against such pointers
+remaining active when the memory containing the overlay is freed as a result
+of removing the overlay.
+
+Any other code that retains a pointer to the overlay nodes or data is
+considered to be a bug because after removing the overlay the pointer
+will refer to freed memory.
+
+Users of overlays must be especially aware of the overall operations that
+occur on the system to ensure that other kernel code does not retain any
+pointers to the overlay nodes or data.  Any example of an inadvertent use
+of such pointers is if a driver or subsystem module is loaded after an
+overlay has been applied, and the driver or subsystem scans the entire
+devicetree or a large portion of it, including the overlay nodes.
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 6df9ecdf16cf..bd522da7f76b 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -58,7 +58,9 @@ struct fragment {
  * @id:			changeset identifier
  * @ovcs_list:		list on which we are located
  * @new_fdt:		Memory allocated to hold unflattened aligned FDT
+ * @overlay_mem:	the memory chunk that contains @overlay_root
  * @overlay_root:	expanded device tree that contains the fragment nodes
+ * @notify_state:	most recent notify action used on overlay
  * @count:		count of fragment structures
  * @fragments:		fragment nodes in the overlay expanded device tree
  * @symbols_fragment:	last element of @fragments[] is the  __symbols__ node
@@ -68,7 +70,9 @@ struct overlay_changeset {
 	int id;
 	struct list_head ovcs_list;
 	const void *new_fdt;
+	const void *overlay_mem;
 	struct device_node *overlay_root;
+	enum of_overlay_notify_action notify_state;
 	int count;
 	struct fragment *fragments;
 	bool symbols_fragment;
@@ -115,7 +119,6 @@ void of_overlay_mutex_unlock(void)
 	mutex_unlock(&of_overlay_phandle_mutex);
 }
 
-
 static LIST_HEAD(ovcs_list);
 static DEFINE_IDR(ovcs_idr);
 
@@ -162,6 +165,8 @@ static int overlay_notify(struct overlay_changeset *ovcs,
 	struct of_overlay_notify_data nd;
 	int i, ret;
 
+	ovcs->notify_state = action;
+
 	for (i = 0; i < ovcs->count; i++) {
 		struct fragment *fragment = &ovcs->fragments[i];
 
@@ -717,53 +722,49 @@ static struct device_node *find_target(struct device_node *info_node)
 /**
  * init_overlay_changeset() - initialize overlay changeset from overlay tree
  * @ovcs:		Overlay changeset to build
- * @new_fdt:		Memory allocated to hold unflattened aligned FDT
- * @overlay_root:	Contains the overlay fragments and overlay fixup nodes
  *
  * Initialize @ovcs.  Populate @ovcs->fragments with node information from
  * the top level of @overlay_root.  The relevant top level nodes are the
  * fragment nodes and the __symbols__ node.  Any other top level node will
- * be ignored.
+ * be ignored.  Populate other @ovcs fields.
  *
  * Return: 0 on success, -ENOMEM if memory allocation failure, -EINVAL if error
- * detected in @overlay_root, or -ENOSPC if idr_alloc() error.
+ * detected in @overlay_root.  On error return, the caller of
+ * init_overlay_changeset() must call free_overlay_changeset().
  */
-static int init_overlay_changeset(struct overlay_changeset *ovcs,
-		const void *new_fdt, struct device_node *overlay_root)
+static int init_overlay_changeset(struct overlay_changeset *ovcs)
 {
 	struct device_node *node, *overlay_node;
 	struct fragment *fragment;
 	struct fragment *fragments;
-	int cnt, id, ret;
+	int cnt, ret;
+
+	/*
+	 * None of the resources allocated by this function will be freed in
+	 * the error paths.  Instead the caller of this function is required
+	 * to call free_overlay_changeset() (which will free the resources)
+	 * if error return.
+	 */
 
 	/*
 	 * Warn for some issues.  Can not return -EINVAL for these until
 	 * of_unittest_apply_overlay() is fixed to pass these checks.
 	 */
-	if (!of_node_check_flag(overlay_root, OF_DYNAMIC))
-		pr_debug("%s() overlay_root is not dynamic\n", __func__);
+	if (!of_node_check_flag(ovcs->overlay_root, OF_DYNAMIC))
+		pr_debug("%s() ovcs->overlay_root is not dynamic\n", __func__);
 
-	if (!of_node_check_flag(overlay_root, OF_DETACHED))
-		pr_debug("%s() overlay_root is not detached\n", __func__);
+	if (!of_node_check_flag(ovcs->overlay_root, OF_DETACHED))
+		pr_debug("%s() ovcs->overlay_root is not detached\n", __func__);
 
-	if (!of_node_is_root(overlay_root))
-		pr_debug("%s() overlay_root is not root\n", __func__);
-
-	ovcs->overlay_root = overlay_root;
-	ovcs->new_fdt = new_fdt;
-
-	INIT_LIST_HEAD(&ovcs->ovcs_list);
+	if (!of_node_is_root(ovcs->overlay_root))
+		pr_debug("%s() ovcs->overlay_root is not root\n", __func__);
 
 	of_changeset_init(&ovcs->cset);
 
-	id = idr_alloc(&ovcs_idr, ovcs, 1, 0, GFP_KERNEL);
-	if (id <= 0)
-		return id;
-
 	cnt = 0;
 
 	/* fragment nodes */
-	for_each_child_of_node(overlay_root, node) {
+	for_each_child_of_node(ovcs->overlay_root, node) {
 		overlay_node = of_get_child_by_name(node, "__overlay__");
 		if (overlay_node) {
 			cnt++;
@@ -771,7 +772,7 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs,
 		}
 	}
 
-	node = of_get_child_by_name(overlay_root, "__symbols__");
+	node = of_get_child_by_name(ovcs->overlay_root, "__symbols__");
 	if (node) {
 		cnt++;
 		of_node_put(node);
@@ -780,11 +781,12 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs,
 	fragments = kcalloc(cnt, sizeof(*fragments), GFP_KERNEL);
 	if (!fragments) {
 		ret = -ENOMEM;
-		goto err_free_idr;
+		goto err_out;
 	}
+	ovcs->fragments = fragments;
 
 	cnt = 0;
-	for_each_child_of_node(overlay_root, node) {
+	for_each_child_of_node(ovcs->overlay_root, node) {
 		overlay_node = of_get_child_by_name(node, "__overlay__");
 		if (!overlay_node)
 			continue;
@@ -796,7 +798,7 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs,
 			of_node_put(fragment->overlay);
 			ret = -EINVAL;
 			of_node_put(node);
-			goto err_free_fragments;
+			goto err_out;
 		}
 
 		cnt++;
@@ -806,7 +808,7 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs,
 	 * if there is a symbols fragment in ovcs->fragments[i] it is
 	 * the final element in the array
 	 */
-	node = of_get_child_by_name(overlay_root, "__symbols__");
+	node = of_get_child_by_name(ovcs->overlay_root, "__symbols__");
 	if (node) {
 		ovcs->symbols_fragment = 1;
 		fragment = &fragments[cnt];
@@ -816,7 +818,7 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs,
 		if (!fragment->target) {
 			pr_err("symbols in overlay, but not in live tree\n");
 			ret = -EINVAL;
-			goto err_free_fragments;
+			goto err_out;
 		}
 
 		cnt++;
@@ -825,20 +827,14 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs,
 	if (!cnt) {
 		pr_err("no fragments or symbols in overlay\n");
 		ret = -EINVAL;
-		goto err_free_fragments;
+		goto err_out;
 	}
 
-	ovcs->id = id;
 	ovcs->count = cnt;
-	ovcs->fragments = fragments;
 
 	return 0;
 
-err_free_fragments:
-	kfree(fragments);
-err_free_idr:
-	idr_remove(&ovcs_idr, id);
-
+err_out:
 	pr_err("%s() failed, ret = %d\n", __func__, ret);
 
 	return ret;
@@ -851,21 +847,34 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs)
 	if (ovcs->cset.entries.next)
 		of_changeset_destroy(&ovcs->cset);
 
-	if (ovcs->id)
+	if (ovcs->id) {
 		idr_remove(&ovcs_idr, ovcs->id);
+		list_del(&ovcs->ovcs_list);
+		ovcs->id = 0;
+	}
+
 
 	for (i = 0; i < ovcs->count; i++) {
 		of_node_put(ovcs->fragments[i].target);
 		of_node_put(ovcs->fragments[i].overlay);
 	}
 	kfree(ovcs->fragments);
+
 	/*
-	 * There should be no live pointers into ovcs->overlay_root and
+	 * There should be no live pointers into ovcs->overlay_mem and
 	 * ovcs->new_fdt due to the policy that overlay notifiers are not
-	 * allowed to retain pointers into the overlay devicetree.
+	 * allowed to retain pointers into the overlay devicetree other
+	 * than during the window from OF_OVERLAY_PRE_APPLY overlay
+	 * notifiers until the OF_OVERLAY_POST_REMOVE overlay notifiers.
+	 *
+	 * A memory leak will occur here if within the window.
 	 */
-	kfree(ovcs->overlay_root);
-	kfree(ovcs->new_fdt);
+
+	if (ovcs->notify_state == OF_OVERLAY_INIT ||
+	    ovcs->notify_state == OF_OVERLAY_POST_REMOVE) {
+		kfree(ovcs->overlay_mem);
+		kfree(ovcs->new_fdt);
+	}
 	kfree(ovcs);
 }
 
@@ -873,27 +882,13 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs)
  * internal documentation
  *
  * of_overlay_apply() - Create and apply an overlay changeset
- * @new_fdt:		Memory allocated to hold the aligned FDT
- * @overlay_root:	Expanded overlay device tree
- * @ovcs_id:		Pointer to overlay changeset id
+ * @ovcs:	overlay changeset
  *
  * Creates and applies an overlay changeset.
  *
- * If an error occurs in a pre-apply notifier, then no changes are made
- * to the device tree.
- *
- * A non-zero return value will not have created the changeset if error is from:
- *   - parameter checks
- *   - building the changeset
- *   - overlay changeset pre-apply notifier
- *
  * If an error is returned by an overlay changeset pre-apply notifier
  * then no further overlay changeset pre-apply notifier will be called.
  *
- * A non-zero return value will have created the changeset if error is from:
- *   - overlay changeset entry notifier
- *   - overlay changeset post-apply notifier
- *
  * If an error is returned by an overlay changeset post-apply notifier
  * then no further overlay changeset post-apply notifier will be called.
  *
@@ -907,64 +902,37 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs)
  * following attempt to apply or remove an overlay changeset will be
  * refused.
  *
- * Returns 0 on success, or a negative error number.  Overlay changeset
- * id is returned to *ovcs_id.
+ * Returns 0 on success, or a negative error number.  On error return,
+ * the caller of of_overlay_apply() must call free_overlay_changeset().
  */
 
-static int of_overlay_apply(const void *new_fdt,
-		struct device_node *overlay_root, int *ovcs_id)
+static int of_overlay_apply(struct overlay_changeset *ovcs)
 {
-	struct overlay_changeset *ovcs;
 	int ret = 0, ret_revert, ret_tmp;
 
-	/*
-	 * As of this point, fdt and tree belong to the overlay changeset.
-	 * overlay changeset code is responsible for freeing them.
-	 */
-
 	if (devicetree_corrupt()) {
 		pr_err("devicetree state suspect, refuse to apply overlay\n");
-		kfree(new_fdt);
-		kfree(overlay_root);
 		ret = -EBUSY;
 		goto out;
 	}
 
-	ovcs = kzalloc(sizeof(*ovcs), GFP_KERNEL);
-	if (!ovcs) {
-		kfree(new_fdt);
-		kfree(overlay_root);
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	of_overlay_mutex_lock();
-	mutex_lock(&of_mutex);
-
-	ret = of_resolve_phandles(overlay_root);
+	ret = of_resolve_phandles(ovcs->overlay_root);
 	if (ret)
-		goto err_free_tree;
+		goto out;
 
-	ret = init_overlay_changeset(ovcs, new_fdt, overlay_root);
+	ret = init_overlay_changeset(ovcs);
 	if (ret)
-		goto err_free_tree;
+		goto out;
 
-	/*
-	 * After overlay_notify(), ovcs->overlay_root related pointers may have
-	 * leaked to drivers, so can not kfree() tree, aka ovcs->overlay_tree;
-	 * and can not free memory containing aligned fdt.  The aligned fdt
-	 * is contained within the memory at ovcs->new_fdt, possibly at an
-	 * offset from ovcs->new_fdt.
-	 */
 	ret = overlay_notify(ovcs, OF_OVERLAY_PRE_APPLY);
 	if (ret) {
 		pr_err("overlay changeset pre-apply notify error %d\n", ret);
-		goto err_free_overlay_changeset;
+		goto out;
 	}
 
 	ret = build_changeset(ovcs);
 	if (ret)
-		goto err_free_overlay_changeset;
+		goto out;
 
 	ret_revert = 0;
 	ret = __of_changeset_apply_entries(&ovcs->cset, &ret_revert);
@@ -974,7 +942,7 @@ static int of_overlay_apply(const void *new_fdt,
 				 ret_revert);
 			devicetree_state_flags |= DTSF_APPLY_FAIL;
 		}
-		goto err_free_overlay_changeset;
+		goto out;
 	}
 
 	ret = __of_changeset_apply_notify(&ovcs->cset);
@@ -982,9 +950,6 @@ static int of_overlay_apply(const void *new_fdt,
 		pr_err("overlay apply changeset entry notify error %d\n", ret);
 	/* notify failure is not fatal, continue */
 
-	list_add_tail(&ovcs->ovcs_list, &ovcs_list);
-	*ovcs_id = ovcs->id;
-
 	ret_tmp = overlay_notify(ovcs, OF_OVERLAY_POST_APPLY);
 	if (ret_tmp) {
 		pr_err("overlay changeset post-apply notify error %d\n",
@@ -993,19 +958,6 @@ static int of_overlay_apply(const void *new_fdt,
 			ret = ret_tmp;
 	}
 
-	goto out_unlock;
-
-err_free_tree:
-	kfree(new_fdt);
-	kfree(overlay_root);
-
-err_free_overlay_changeset:
-	free_overlay_changeset(ovcs);
-
-out_unlock:
-	mutex_unlock(&of_mutex);
-	of_overlay_mutex_unlock();
-
 out:
 	pr_debug("%s() err=%d\n", __func__, ret);
 
@@ -1013,15 +965,16 @@ out:
 }
 
 int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
-			 int *ovcs_id)
+			 int *ret_ovcs_id)
 {
 	void *new_fdt;
 	void *new_fdt_align;
+	void *overlay_mem;
 	int ret;
 	u32 size;
-	struct device_node *overlay_root = NULL;
+	struct overlay_changeset *ovcs;
 
-	*ovcs_id = 0;
+	*ret_ovcs_id = 0;
 
 	if (overlay_fdt_size < sizeof(struct fdt_header) ||
 	    fdt_check_header(overlay_fdt)) {
@@ -1033,41 +986,67 @@ int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
 	if (overlay_fdt_size < size)
 		return -EINVAL;
 
+	ovcs = kzalloc(sizeof(*ovcs), GFP_KERNEL);
+	if (!ovcs)
+		return -ENOMEM;
+
+	of_overlay_mutex_lock();
+	mutex_lock(&of_mutex);
+
+	/*
+	 * ovcs->notify_state must be set to OF_OVERLAY_INIT before allocating
+	 * ovcs resources, implicitly set by kzalloc() of ovcs
+	 */
+
+	ovcs->id = idr_alloc(&ovcs_idr, ovcs, 1, 0, GFP_KERNEL);
+	if (ovcs->id <= 0) {
+		ret = ovcs->id;
+		goto err_free_ovcs;
+	}
+
+	INIT_LIST_HEAD(&ovcs->ovcs_list);
+	list_add_tail(&ovcs->ovcs_list, &ovcs_list);
+
 	/*
 	 * Must create permanent copy of FDT because of_fdt_unflatten_tree()
 	 * will create pointers to the passed in FDT in the unflattened tree.
 	 */
 	new_fdt = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL);
-	if (!new_fdt)
-		return -ENOMEM;
+	if (!new_fdt) {
+		ret = -ENOMEM;
+		goto err_free_ovcs;
+	}
+	ovcs->new_fdt = new_fdt;
 
 	new_fdt_align = PTR_ALIGN(new_fdt, FDT_ALIGN_SIZE);
 	memcpy(new_fdt_align, overlay_fdt, size);
 
-	of_fdt_unflatten_tree(new_fdt_align, NULL, &overlay_root);
-	if (!overlay_root) {
+	overlay_mem = of_fdt_unflatten_tree(new_fdt_align, NULL,
+					    &ovcs->overlay_root);
+	if (!overlay_mem) {
 		pr_err("unable to unflatten overlay_fdt\n");
 		ret = -EINVAL;
-		goto out_free_new_fdt;
+		goto err_free_ovcs;
 	}
+	ovcs->overlay_mem = overlay_mem;
 
-	ret = of_overlay_apply(new_fdt, overlay_root, ovcs_id);
-	if (ret < 0) {
-		/*
-		 * new_fdt and overlay_root now belong to the overlay
-		 * changeset.
-		 * overlay changeset code is responsible for freeing them.
-		 */
-		goto out;
-	}
+	ret = of_overlay_apply(ovcs);
+	if (ret < 0)
+		goto err_free_ovcs;
+
+	mutex_unlock(&of_mutex);
+	of_overlay_mutex_unlock();
+
+	*ret_ovcs_id = ovcs->id;
 
 	return 0;
 
+err_free_ovcs:
+	free_overlay_changeset(ovcs);
 
-out_free_new_fdt:
-	kfree(new_fdt);
+	mutex_unlock(&of_mutex);
+	of_overlay_mutex_unlock();
 
-out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(of_overlay_fdt_apply);
@@ -1204,28 +1183,26 @@ int of_overlay_remove(int *ovcs_id)
 	if (!ovcs) {
 		ret = -ENODEV;
 		pr_err("remove: Could not find overlay #%d\n", *ovcs_id);
-		goto out_unlock;
+		goto err_unlock;
 	}
 
 	if (!overlay_removal_is_ok(ovcs)) {
 		ret = -EBUSY;
-		goto out_unlock;
+		goto err_unlock;
 	}
 
 	ret = overlay_notify(ovcs, OF_OVERLAY_PRE_REMOVE);
 	if (ret) {
 		pr_err("overlay changeset pre-remove notify error %d\n", ret);
-		goto out_unlock;
+		goto err_unlock;
 	}
 
-	list_del(&ovcs->ovcs_list);
-
 	ret_apply = 0;
 	ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply);
 	if (ret) {
 		if (ret_apply)
 			devicetree_state_flags |= DTSF_REVERT_FAIL;
-		goto out_unlock;
+		goto err_unlock;
 	}
 
 	ret = __of_changeset_revert_notify(&ovcs->cset);
@@ -1235,6 +1212,11 @@ int of_overlay_remove(int *ovcs_id)
 
 	*ovcs_id = 0;
 
+	/*
+	 * Note that the overlay memory will be kfree()ed by
+	 * free_overlay_changeset() even if the notifier for
+	 * OF_OVERLAY_POST_REMOVE returns an error.
+	 */
 	ret_tmp = overlay_notify(ovcs, OF_OVERLAY_POST_REMOVE);
 	if (ret_tmp) {
 		pr_err("overlay changeset post-remove notify error %d\n",
@@ -1245,7 +1227,12 @@ int of_overlay_remove(int *ovcs_id)
 
 	free_overlay_changeset(ovcs);
 
-out_unlock:
+err_unlock:
+	/*
+	 * If jumped over free_overlay_changeset(), then did not kfree()
+	 * overlay related memory.  This is a memory leak unless a subsequent
+	 * of_overlay_remove() of this overlay is successful.
+	 */
 	mutex_unlock(&of_mutex);
 
 out:
diff --git a/include/linux/of.h b/include/linux/of.h
index 04971e85fbc9..17741eee0ca4 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1543,7 +1543,8 @@ static inline bool of_device_is_system_power_controller(const struct device_node
  */
 
 enum of_overlay_notify_action {
-	OF_OVERLAY_PRE_APPLY = 0,
+	OF_OVERLAY_INIT = 0,	/* kzalloc() of ovcs sets this value */
+	OF_OVERLAY_PRE_APPLY,
 	OF_OVERLAY_POST_APPLY,
 	OF_OVERLAY_PRE_REMOVE,
 	OF_OVERLAY_POST_REMOVE,
-- 
cgit v1.2.3


From 5b0e58542acb3672f42e08cb1cd57784f5e08d6b Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 7 Apr 2022 12:08:54 +0200
Subject: net: ieee802154: Enhance/fix the names of the MLME return codes

Let's keep these definitions as close to the specification as possible
while they are not yet in use. The names get slightly longer, but we
gain the minor cost of being able to search the spec more easily.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20220407100903.1695973-2-miquel.raynal@bootlin.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 include/linux/ieee802154.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 95c831162212..01d945c8b2e1 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -136,16 +136,16 @@ enum {
 	IEEE802154_SUCCESS = 0x0,
 
 	/* The beacon was lost following a synchronization request. */
-	IEEE802154_BEACON_LOSS = 0xe0,
+	IEEE802154_BEACON_LOST = 0xe0,
 	/*
 	 * A transmission could not take place due to activity on the
 	 * channel, i.e., the CSMA-CA mechanism has failed.
 	 */
-	IEEE802154_CHNL_ACCESS_FAIL = 0xe1,
+	IEEE802154_CHANNEL_ACCESS_FAILURE = 0xe1,
 	/* The GTS request has been denied by the PAN coordinator. */
-	IEEE802154_DENINED = 0xe2,
+	IEEE802154_DENIED = 0xe2,
 	/* The attempt to disable the transceiver has failed. */
-	IEEE802154_DISABLE_TRX_FAIL = 0xe3,
+	IEEE802154_DISABLE_TRX_FAILURE = 0xe3,
 	/*
 	 * The received frame induces a failed security check according to
 	 * the security suite.
@@ -185,9 +185,9 @@ enum {
 	 * A PAN identifier conflict has been detected and communicated to the
 	 * PAN coordinator.
 	 */
-	IEEE802154_PANID_CONFLICT = 0xee,
+	IEEE802154_PAN_ID_CONFLICT = 0xee,
 	/* A coordinator realignment command has been received. */
-	IEEE802154_REALIGMENT = 0xef,
+	IEEE802154_REALIGNMENT = 0xef,
 	/* The transaction has expired and its information discarded. */
 	IEEE802154_TRANSACTION_EXPIRED = 0xf0,
 	/* There is no capacity to store the transaction. */
@@ -203,7 +203,7 @@ enum {
 	 * A SET/GET request was issued with the identifier of a PIB attribute
 	 * that is not supported.
 	 */
-	IEEE802154_UNSUPPORTED_ATTR = 0xf4,
+	IEEE802154_UNSUPPORTED_ATTRIBUTE = 0xf4,
 	/*
 	 * A request to perform a scan operation failed because the MLME was
 	 * in the process of performing a previously initiated scan operation.
-- 
cgit v1.2.3


From f06cfc233ac67e26ed137f4e098c047939cf1530 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 7 Apr 2022 12:08:55 +0200
Subject: net: ieee802154: Fill the list of MLME return codes

There are more codes than already listed, let's be a bit more
exhaustive. This will allow to drop device drivers local definitions of
these codes.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/r/20220407100903.1695973-3-miquel.raynal@bootlin.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 include/linux/ieee802154.h | 67 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 66 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 01d945c8b2e1..f1f9412b6ac6 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -134,7 +134,35 @@ enum {
 	 * a successful transmission.
 	 */
 	IEEE802154_SUCCESS = 0x0,
-
+	/* The requested operation failed. */
+	IEEE802154_MAC_ERROR = 0x1,
+	/* The requested operation has been cancelled. */
+	IEEE802154_CANCELLED = 0x2,
+	/*
+	 * Device is ready to poll the coordinator for data in a non beacon
+	 * enabled PAN.
+	 */
+	IEEE802154_READY_FOR_POLL = 0x3,
+	/* Wrong frame counter. */
+	IEEE802154_COUNTER_ERROR = 0xdb,
+	/*
+	 * The frame does not conforms to the incoming key usage policy checking
+	 * procedure.
+	 */
+	IEEE802154_IMPROPER_KEY_TYPE = 0xdc,
+	/*
+	 * The frame does not conforms to the incoming security level usage
+	 * policy checking procedure.
+	 */
+	IEEE802154_IMPROPER_SECURITY_LEVEL = 0xdd,
+	/* Secured frame received with an empty Frame Version field. */
+	IEEE802154_UNSUPPORTED_LEGACY = 0xde,
+	/*
+	 * A secured frame is received or must be sent but security is not
+	 * enabled in the device. Or, the Auxiliary Security Header has security
+	 * level of zero in it.
+	 */
+	IEEE802154_UNSUPPORTED_SECURITY = 0xdf,
 	/* The beacon was lost following a synchronization request. */
 	IEEE802154_BEACON_LOST = 0xe0,
 	/*
@@ -204,11 +232,48 @@ enum {
 	 * that is not supported.
 	 */
 	IEEE802154_UNSUPPORTED_ATTRIBUTE = 0xf4,
+	/* Missing source or destination address or address mode. */
+	IEEE802154_INVALID_ADDRESS = 0xf5,
+	/*
+	 * MLME asked to turn the receiver on, but the on time duration is too
+	 * big compared to the macBeaconOrder.
+	 */
+	IEEE802154_ON_TIME_TOO_LONG = 0xf6,
+	/*
+	 * MLME asaked to turn the receiver on, but the request was delayed for
+	 * too long before getting processed.
+	 */
+	IEEE802154_PAST_TIME = 0xf7,
+	/*
+	 * The StartTime parameter is nonzero, and the MLME is not currently
+	 * tracking the beacon of the coordinator through which it is
+	 * associated.
+	 */
+	IEEE802154_TRACKING_OFF = 0xf8,
+	/*
+	 * The index inside the hierarchical values in PIBAttribute is out of
+	 * range.
+	 */
+	IEEE802154_INVALID_INDEX = 0xf9,
+	/*
+	 * The number of PAN descriptors discovered during a scan has been
+	 * reached.
+	 */
+	IEEE802154_LIMIT_REACHED = 0xfa,
+	/*
+	 * The PIBAttribute parameter specifies an attribute that is a read-only
+	 * attribute.
+	 */
+	IEEE802154_READ_ONLY = 0xfb,
 	/*
 	 * A request to perform a scan operation failed because the MLME was
 	 * in the process of performing a previously initiated scan operation.
 	 */
 	IEEE802154_SCAN_IN_PROGRESS = 0xfc,
+	/* The outgoing superframe overlaps the incoming superframe. */
+	IEEE802154_SUPERFRAME_OVERLAP = 0xfd,
+	/* Any other error situation. */
+	IEEE802154_SYSTEM_ERROR = 0xff,
 };
 
 /* frame control handling */
-- 
cgit v1.2.3


From c83227a5d05ed77b634ce4c2fc5f143ae2a4d6f5 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 21 Apr 2022 22:06:54 +0200
Subject: irq/gpio: ixp4xx: Drop boardfile probe path

The boardfiles for IXP4xx have been deleted. Delete all the
quirks and code dealing with that boot path and rely solely on
device tree boot.

Fix some missing static keywords that the kernel test robot
was complaining about while we're at it.

Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Acked-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 drivers/gpio/Kconfig               |   2 +
 drivers/gpio/gpio-ixp4xx.c         |  40 ++++--------
 drivers/irqchip/irq-ixp4xx.c       | 126 ++-----------------------------------
 include/linux/irqchip/irq-ixp4xx.h |  12 ----
 4 files changed, 17 insertions(+), 163 deletions(-)
 delete mode 100644 include/linux/irqchip/irq-ixp4xx.h

(limited to 'include/linux')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 075a5d0feef7..57426fdba1b6 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -354,6 +354,7 @@ config GPIO_IOP
 config GPIO_IXP4XX
 	bool "Intel IXP4xx GPIO"
 	depends on ARCH_IXP4XX
+	depends on OF
 	select GPIO_GENERIC
 	select GPIOLIB_IRQCHIP
 	select IRQ_DOMAIN_HIERARCHY
@@ -362,6 +363,7 @@ config GPIO_IXP4XX
 	  IXP4xx series of chips.
 
 	  If unsure, say N.
+
 config GPIO_LOGICVC
 	tristate "Xylon LogiCVC GPIO support"
 	depends on MFD_SYSCON && OF
diff --git a/drivers/gpio/gpio-ixp4xx.c b/drivers/gpio/gpio-ixp4xx.c
index 76ab9bd7d84b..312309be0287 100644
--- a/drivers/gpio/gpio-ixp4xx.c
+++ b/drivers/gpio/gpio-ixp4xx.c
@@ -14,8 +14,6 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/bitops.h>
-/* Include that go away with DT transition */
-#include <linux/irqchip/irq-ixp4xx.h>
 
 #define IXP4XX_REG_GPOUT	0x00
 #define IXP4XX_REG_GPOE		0x04
@@ -193,6 +191,7 @@ static int ixp4xx_gpio_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct ixp4xx_gpio *g;
 	struct gpio_irq_chip *girq;
+	struct device_node *irq_parent;
 	int ret;
 
 	g = devm_kzalloc(dev, sizeof(*g), GFP_KERNEL);
@@ -205,34 +204,17 @@ static int ixp4xx_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(g->base))
 		return PTR_ERR(g->base);
 
-	/*
-	 * When we convert to device tree we will simply look up the
-	 * parent irqdomain using irq_find_host(parent) as parent comes
-	 * from IRQCHIP_DECLARE(), then use of_node_to_fwnode() to get
-	 * the fwnode. For now we need this boardfile style code.
-	 */
-	if (np) {
-		struct device_node *irq_parent;
-
-		irq_parent = of_irq_find_parent(np);
-		if (!irq_parent) {
-			dev_err(dev, "no IRQ parent node\n");
-			return -ENODEV;
-		}
-		parent = irq_find_host(irq_parent);
-		if (!parent) {
-			dev_err(dev, "no IRQ parent domain\n");
-			return -ENODEV;
-		}
-		g->fwnode = of_node_to_fwnode(np);
-	} else {
-		parent = ixp4xx_get_irq_domain();
-		g->fwnode = irq_domain_alloc_fwnode(&res->start);
-		if (!g->fwnode) {
-			dev_err(dev, "no domain base\n");
-			return -ENODEV;
-		}
+	irq_parent = of_irq_find_parent(np);
+	if (!irq_parent) {
+		dev_err(dev, "no IRQ parent node\n");
+		return -ENODEV;
+	}
+	parent = irq_find_host(irq_parent);
+	if (!parent) {
+		dev_err(dev, "no IRQ parent domain\n");
+		return -ENODEV;
 	}
+	g->fwnode = of_node_to_fwnode(np);
 
 	/*
 	 * Make sure GPIO 14 and 15 are NOT used as clocks but GPIO on
diff --git a/drivers/irqchip/irq-ixp4xx.c b/drivers/irqchip/irq-ixp4xx.c
index fb68f8c59fbb..5fba907b9052 100644
--- a/drivers/irqchip/irq-ixp4xx.c
+++ b/drivers/irqchip/irq-ixp4xx.c
@@ -13,7 +13,6 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
-#include <linux/irqchip/irq-ixp4xx.h>
 #include <linux/irqdomain.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -106,7 +105,8 @@ static void ixp4xx_irq_unmask(struct irq_data *d)
 	}
 }
 
-asmlinkage void __exception_irq_entry ixp4xx_handle_irq(struct pt_regs *regs)
+static asmlinkage void __exception_irq_entry
+ixp4xx_handle_irq(struct pt_regs *regs)
 {
 	struct ixp4xx_irq *ixi = &ixirq;
 	unsigned long status;
@@ -195,56 +195,6 @@ static const struct irq_domain_ops ixp4xx_irqdomain_ops = {
 	.free = irq_domain_free_irqs_common,
 };
 
-/**
- * ixp4xx_get_irq_domain() - retrieve the ixp4xx irq domain
- *
- * This function will go away when we transition to DT probing.
- */
-struct irq_domain *ixp4xx_get_irq_domain(void)
-{
-	struct ixp4xx_irq *ixi = &ixirq;
-
-	return ixi->domain;
-}
-EXPORT_SYMBOL_GPL(ixp4xx_get_irq_domain);
-
-/*
- * This is the Linux IRQ to hwirq mapping table. This goes away when
- * we have DT support as all IRQ resources are defined in the device
- * tree. It will register all the IRQs that are not used by the hierarchical
- * GPIO IRQ chip. The "holes" inbetween these IRQs will be requested by
- * the GPIO driver using . This is a step-gap solution.
- */
-struct ixp4xx_irq_chunk {
-	int irq;
-	int hwirq;
-	int nr_irqs;
-};
-
-static const struct ixp4xx_irq_chunk ixp4xx_irq_chunks[] = {
-	{
-		.irq = 16,
-		.hwirq = 0,
-		.nr_irqs = 6,
-	},
-	{
-		.irq = 24,
-		.hwirq = 8,
-		.nr_irqs = 11,
-	},
-	{
-		.irq = 46,
-		.hwirq = 30,
-		.nr_irqs = 2,
-	},
-	/* Only on the 436 variants */
-	{
-		.irq = 48,
-		.hwirq = 32,
-		.nr_irqs = 10,
-	},
-};
-
 /**
  * ixp4x_irq_setup() - Common setup code for the IXP4xx interrupt controller
  * @ixi: State container
@@ -298,75 +248,8 @@ static int __init ixp4xx_irq_setup(struct ixp4xx_irq *ixi,
 	return 0;
 }
 
-/**
- * ixp4xx_irq_init() - Function to initialize the irqchip from boardfiles
- * @irqbase: physical base for the irq controller
- * @is_356: if this is an IXP43x, IXP45x or IXP46x SoC variant
- */
-void __init ixp4xx_irq_init(resource_size_t irqbase,
-			    bool is_356)
-{
-	struct ixp4xx_irq *ixi = &ixirq;
-	void __iomem *base;
-	struct fwnode_handle *fwnode;
-	struct irq_fwspec fwspec;
-	int nr_chunks;
-	int ret;
-	int i;
-
-	base = ioremap(irqbase, 0x100);
-	if (!base) {
-		pr_crit("IXP4XX: could not ioremap interrupt controller\n");
-		return;
-	}
-	fwnode = irq_domain_alloc_fwnode(&irqbase);
-	if (!fwnode) {
-		pr_crit("IXP4XX: no domain handle\n");
-		return;
-	}
-	ret = ixp4xx_irq_setup(ixi, base, fwnode, is_356);
-	if (ret) {
-		pr_crit("IXP4XX: failed to set up irqchip\n");
-		irq_domain_free_fwnode(fwnode);
-	}
-
-	nr_chunks = ARRAY_SIZE(ixp4xx_irq_chunks);
-	if (!is_356)
-		nr_chunks--;
-
-	/*
-	 * After adding OF support, this is no longer needed: irqs
-	 * will be allocated for the respective fwnodes.
-	 */
-	for (i = 0; i < nr_chunks; i++) {
-		const struct ixp4xx_irq_chunk *chunk = &ixp4xx_irq_chunks[i];
-
-		pr_info("Allocate Linux IRQs %d..%d HW IRQs %d..%d\n",
-			chunk->irq, chunk->irq + chunk->nr_irqs - 1,
-			chunk->hwirq, chunk->hwirq + chunk->nr_irqs - 1);
-		fwspec.fwnode = fwnode;
-		fwspec.param[0] = chunk->hwirq;
-		fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH;
-		fwspec.param_count = 2;
-		ret = __irq_domain_alloc_irqs(ixi->domain,
-					      chunk->irq,
-					      chunk->nr_irqs,
-					      NUMA_NO_NODE,
-					      &fwspec,
-					      false,
-					      NULL);
-		if (ret < 0) {
-			pr_crit("IXP4XX: can not allocate irqs in hierarchy %d\n",
-				ret);
-			return;
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(ixp4xx_irq_init);
-
-#ifdef CONFIG_OF
-int __init ixp4xx_of_init_irq(struct device_node *np,
-			      struct device_node *parent)
+static int __init ixp4xx_of_init_irq(struct device_node *np,
+				     struct device_node *parent)
 {
 	struct ixp4xx_irq *ixi = &ixirq;
 	void __iomem *base;
@@ -400,4 +283,3 @@ IRQCHIP_DECLARE(ixp45x, "intel,ixp45x-interrupt",
 		ixp4xx_of_init_irq);
 IRQCHIP_DECLARE(ixp46x, "intel,ixp46x-interrupt",
 		ixp4xx_of_init_irq);
-#endif
diff --git a/include/linux/irqchip/irq-ixp4xx.h b/include/linux/irqchip/irq-ixp4xx.h
deleted file mode 100644
index 9395917d6936..000000000000
--- a/include/linux/irqchip/irq-ixp4xx.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __IRQ_IXP4XX_H
-#define __IRQ_IXP4XX_H
-
-#include <linux/ioport.h>
-struct irq_domain;
-
-void ixp4xx_irq_init(resource_size_t irqbase,
-		     bool is_356);
-struct irq_domain *ixp4xx_get_irq_domain(void);
-
-#endif /* __IRQ_IXP4XX_H */
-- 
cgit v1.2.3


From fae74fb5d525f979085b6e70b883d7a7049bf15f Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 25 Apr 2022 19:32:55 +0200
Subject: gpio: pcf857x: Make teardown callback return void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All teardown functions return 0. Also there is little sense in returning
a negative error code from an i2c remove function as this only results in
emitting an error message but the device is removed nevertheless.

This patch is a preparation for making i2c remove callbacks return void.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 arch/arm/mach-davinci/board-da830-evm.c  |  3 +--
 arch/arm/mach-davinci/board-dm644x-evm.c |  9 +++------
 arch/arm/mach-davinci/board-dm646x-evm.c |  4 +---
 drivers/gpio/gpio-pcf857x.c              | 14 +++-----------
 include/linux/platform_data/pcf857x.h    |  2 +-
 5 files changed, 9 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index 823c9cc98f18..52a452eff01c 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -473,11 +473,10 @@ static int __init da830_evm_ui_expander_setup(struct i2c_client *client,
 	return 0;
 }
 
-static int da830_evm_ui_expander_teardown(struct i2c_client *client, int gpio,
+static void da830_evm_ui_expander_teardown(struct i2c_client *client, int gpio,
 		unsigned ngpio, void *context)
 {
 	gpio_free(gpio + 6);
-	return 0;
 }
 
 static struct pcf857x_platform_data __initdata da830_evm_ui_expander_info = {
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index cce3a621eb20..b69fc17d6a8c 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -366,14 +366,13 @@ evm_led_setup(struct i2c_client *client, int gpio, unsigned ngpio, void *c)
 	return status;
 }
 
-static int
+static void
 evm_led_teardown(struct i2c_client *client, int gpio, unsigned ngpio, void *c)
 {
 	if (evm_led_dev) {
 		platform_device_unregister(evm_led_dev);
 		evm_led_dev = NULL;
 	}
-	return 0;
 }
 
 static struct pcf857x_platform_data pcf_data_u2 = {
@@ -428,7 +427,7 @@ evm_u18_setup(struct i2c_client *client, int gpio, unsigned ngpio, void *c)
 	return 0;
 }
 
-static int
+static void
 evm_u18_teardown(struct i2c_client *client, int gpio, unsigned ngpio, void *c)
 {
 	gpio_free(gpio + 1);
@@ -439,7 +438,6 @@ evm_u18_teardown(struct i2c_client *client, int gpio, unsigned ngpio, void *c)
 		device_remove_file(&client->dev, &dev_attr_user_sw);
 		gpio_free(sw_gpio);
 	}
-	return 0;
 }
 
 static struct pcf857x_platform_data pcf_data_u18 = {
@@ -488,7 +486,7 @@ evm_u35_setup(struct i2c_client *client, int gpio, unsigned ngpio, void *c)
 	return 0;
 }
 
-static int
+static void
 evm_u35_teardown(struct i2c_client *client, int gpio, unsigned ngpio, void *c)
 {
 	gpio_free(gpio + 7);
@@ -498,7 +496,6 @@ evm_u35_teardown(struct i2c_client *client, int gpio, unsigned ngpio, void *c)
 	gpio_free(gpio + 2);
 	gpio_free(gpio + 1);
 	gpio_free(gpio + 0);
-	return 0;
 }
 
 static struct pcf857x_platform_data pcf_data_u35 = {
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index ee91d81ebbfd..625d2d626147 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -315,15 +315,13 @@ static int evm_pcf_setup(struct i2c_client *client, int gpio,
 	return evm_led_setup(client, gpio+4, 4, c);
 }
 
-static int evm_pcf_teardown(struct i2c_client *client, int gpio,
+static void evm_pcf_teardown(struct i2c_client *client, int gpio,
 			unsigned int ngpio, void *c)
 {
 	BUG_ON(ngpio < 8);
 
 	evm_sw_teardown(client, gpio, 4, c);
 	evm_led_teardown(client, gpio+4, 4, c);
-
-	return 0;
 }
 
 static struct pcf857x_platform_data pcf_data = {
diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c
index b7568ee33696..e3a53dd5df1e 100644
--- a/drivers/gpio/gpio-pcf857x.c
+++ b/drivers/gpio/gpio-pcf857x.c
@@ -396,20 +396,12 @@ static int pcf857x_remove(struct i2c_client *client)
 {
 	struct pcf857x_platform_data	*pdata = dev_get_platdata(&client->dev);
 	struct pcf857x			*gpio = i2c_get_clientdata(client);
-	int				status = 0;
 
-	if (pdata && pdata->teardown) {
-		status = pdata->teardown(client,
-				gpio->chip.base, gpio->chip.ngpio,
+	if (pdata && pdata->teardown)
+		pdata->teardown(client, gpio->chip.base, gpio->chip.ngpio,
 				pdata->context);
-		if (status < 0) {
-			dev_err(&client->dev, "%s --> %d\n",
-					"teardown", status);
-			return status;
-		}
-	}
 
-	return status;
+	return 0;
 }
 
 static void pcf857x_shutdown(struct i2c_client *client)
diff --git a/include/linux/platform_data/pcf857x.h b/include/linux/platform_data/pcf857x.h
index 11d4ed78c7f4..01d0a3ea3aef 100644
--- a/include/linux/platform_data/pcf857x.h
+++ b/include/linux/platform_data/pcf857x.h
@@ -36,7 +36,7 @@ struct pcf857x_platform_data {
 	int		(*setup)(struct i2c_client *client,
 					int gpio, unsigned ngpio,
 					void *context);
-	int		(*teardown)(struct i2c_client *client,
+	void		(*teardown)(struct i2c_client *client,
 					int gpio, unsigned ngpio,
 					void *context);
 	void		*context;
-- 
cgit v1.2.3


From d9d31cf88702ae071bec033e5c8714048aa71285 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 25 Apr 2022 15:04:48 -0700
Subject: bpf: Use bpf_prog_run_array_cg_flags everywhere

Rename bpf_prog_run_array_cg_flags to bpf_prog_run_array_cg and
use it everywhere. check_return_code already enforces sane
return ranges for all cgroup types. (only egress and bind hooks have
uncanonical return ranges, the rest is using [0, 1])

No functional changes.

v2:
- 'func_ret & 1' under explicit test (Andrii & Martin)

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220425220448.3669032-1-sdf@google.com
---
 include/linux/bpf-cgroup.h |  8 ++----
 kernel/bpf/cgroup.c        | 72 ++++++++++++++++------------------------------
 2 files changed, 26 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 88a51b242adc..669d96d074ad 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -225,24 +225,20 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 
 #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype)				       \
 ({									       \
-	u32 __unused_flags;						       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(atype))					       \
 		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype,     \
-							  NULL,		       \
-							  &__unused_flags);    \
+							  NULL, NULL);	       \
 	__ret;								       \
 })
 
 #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx)		       \
 ({									       \
-	u32 __unused_flags;						       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(atype))	{				       \
 		lock_sock(sk);						       \
 		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype,     \
-							  t_ctx,	       \
-							  &__unused_flags);    \
+							  t_ctx, NULL);	       \
 		release_sock(sk);					       \
 	}								       \
 	__ret;								       \
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 0cb6211fcb58..afb414b26d01 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -25,50 +25,18 @@ EXPORT_SYMBOL(cgroup_bpf_enabled_key);
 /* __always_inline is necessary to prevent indirect call through run_prog
  * function pointer.
  */
-static __always_inline int
-bpf_prog_run_array_cg_flags(const struct cgroup_bpf *cgrp,
-			    enum cgroup_bpf_attach_type atype,
-			    const void *ctx, bpf_prog_run_fn run_prog,
-			    int retval, u32 *ret_flags)
-{
-	const struct bpf_prog_array_item *item;
-	const struct bpf_prog *prog;
-	const struct bpf_prog_array *array;
-	struct bpf_run_ctx *old_run_ctx;
-	struct bpf_cg_run_ctx run_ctx;
-	u32 func_ret;
-
-	run_ctx.retval = retval;
-	migrate_disable();
-	rcu_read_lock();
-	array = rcu_dereference(cgrp->effective[atype]);
-	item = &array->items[0];
-	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
-	while ((prog = READ_ONCE(item->prog))) {
-		run_ctx.prog_item = item;
-		func_ret = run_prog(prog, ctx);
-		if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval))
-			run_ctx.retval = -EPERM;
-		*(ret_flags) |= (func_ret >> 1);
-		item++;
-	}
-	bpf_reset_run_ctx(old_run_ctx);
-	rcu_read_unlock();
-	migrate_enable();
-	return run_ctx.retval;
-}
-
 static __always_inline int
 bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp,
 		      enum cgroup_bpf_attach_type atype,
 		      const void *ctx, bpf_prog_run_fn run_prog,
-		      int retval)
+		      int retval, u32 *ret_flags)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
 	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_cg_run_ctx run_ctx;
+	u32 func_ret;
 
 	run_ctx.retval = retval;
 	migrate_disable();
@@ -78,7 +46,12 @@ bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp,
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	while ((prog = READ_ONCE(item->prog))) {
 		run_ctx.prog_item = item;
-		if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval))
+		func_ret = run_prog(prog, ctx);
+		if (ret_flags) {
+			*(ret_flags) |= (func_ret >> 1);
+			func_ret &= 1;
+		}
+		if (!func_ret && !IS_ERR_VALUE((long)run_ctx.retval))
 			run_ctx.retval = -EPERM;
 		item++;
 	}
@@ -1144,9 +1117,8 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 		u32 flags = 0;
 		bool cn;
 
-		ret = bpf_prog_run_array_cg_flags(
-			&cgrp->bpf, atype,
-			skb, __bpf_prog_run_save_cb, 0, &flags);
+		ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, skb,
+					    __bpf_prog_run_save_cb, 0, &flags);
 
 		/* Return values of CGROUP EGRESS BPF programs are:
 		 *   0: drop packet
@@ -1172,7 +1144,8 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 			ret = (cn ? NET_XMIT_DROP : ret);
 	} else {
 		ret = bpf_prog_run_array_cg(&cgrp->bpf, atype,
-					    skb, __bpf_prog_run_save_cb, 0);
+					    skb, __bpf_prog_run_save_cb, 0,
+					    NULL);
 		if (ret && !IS_ERR_VALUE((long)ret))
 			ret = -EFAULT;
 	}
@@ -1202,7 +1175,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 
-	return bpf_prog_run_array_cg(&cgrp->bpf, atype, sk, bpf_prog_run, 0);
+	return bpf_prog_run_array_cg(&cgrp->bpf, atype, sk, bpf_prog_run, 0,
+				     NULL);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
 
@@ -1247,8 +1221,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 	}
 
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	return bpf_prog_run_array_cg_flags(&cgrp->bpf, atype,
-					   &ctx, bpf_prog_run, 0, flags);
+	return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run,
+				     0, flags);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
 
@@ -1275,7 +1249,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 
 	return bpf_prog_run_array_cg(&cgrp->bpf, atype, sock_ops, bpf_prog_run,
-				     0);
+				     0, NULL);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
 
@@ -1292,7 +1266,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
-	ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0);
+	ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0,
+				    NULL);
 	rcu_read_unlock();
 
 	return ret;
@@ -1457,7 +1432,8 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
-	ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0);
+	ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0,
+				    NULL);
 	rcu_read_unlock();
 
 	kfree(ctx.cur_val);
@@ -1550,7 +1526,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 
 	lock_sock(sk);
 	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_SETSOCKOPT,
-				    &ctx, bpf_prog_run, 0);
+				    &ctx, bpf_prog_run, 0, NULL);
 	release_sock(sk);
 
 	if (ret)
@@ -1650,7 +1626,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 
 	lock_sock(sk);
 	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT,
-				    &ctx, bpf_prog_run, retval);
+				    &ctx, bpf_prog_run, retval, NULL);
 	release_sock(sk);
 
 	if (ret < 0)
@@ -1699,7 +1675,7 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
 	 */
 
 	ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT,
-				    &ctx, bpf_prog_run, retval);
+				    &ctx, bpf_prog_run, retval, NULL);
 	if (ret < 0)
 		return ret;
 
-- 
cgit v1.2.3


From 61df10c7799e27807ad5e459eec9d77cddf8bf45 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:49 +0530
Subject: bpf: Allow storing unreferenced kptr in map

This commit introduces a new pointer type 'kptr' which can be embedded
in a map value to hold a PTR_TO_BTF_ID stored by a BPF program during
its invocation. When storing such a kptr, BPF program's PTR_TO_BTF_ID
register must have the same type as in the map value's BTF, and loading
a kptr marks the destination register as PTR_TO_BTF_ID with the correct
kernel BTF and BTF ID.

Such kptr are unreferenced, i.e. by the time another invocation of the
BPF program loads this pointer, the object which the pointer points to
may not longer exist. Since PTR_TO_BTF_ID loads (using BPF_LDX) are
patched to PROBE_MEM loads by the verifier, it would safe to allow user
to still access such invalid pointer, but passing such pointers into
BPF helpers and kfuncs should not be permitted. A future patch in this
series will close this gap.

The flexibility offered by allowing programs to dereference such invalid
pointers while being safe at runtime frees the verifier from doing
complex lifetime tracking. As long as the user may ensure that the
object remains valid, it can ensure data read by it from the kernel
object is valid.

The user indicates that a certain pointer must be treated as kptr
capable of accepting stores of PTR_TO_BTF_ID of a certain type, by using
a BTF type tag 'kptr' on the pointed to type of the pointer. Then, this
information is recorded in the object BTF which will be passed into the
kernel by way of map's BTF information. The name and kind from the map
value BTF is used to look up the in-kernel type, and the actual BTF and
BTF ID is recorded in the map struct in a new kptr_off_tab member. For
now, only storing pointers to structs is permitted.

An example of this specification is shown below:

	#define __kptr __attribute__((btf_type_tag("kptr")))

	struct map_value {
		...
		struct task_struct __kptr *task;
		...
	};

Then, in a BPF program, user may store PTR_TO_BTF_ID with the type
task_struct into the map, and then load it later.

Note that the destination register is marked PTR_TO_BTF_ID_OR_NULL, as
the verifier cannot know whether the value is NULL or not statically, it
must treat all potential loads at that map value offset as loading a
possibly NULL pointer.

Only BPF_LDX, BPF_STX, and BPF_ST (with insn->imm = 0 to denote NULL)
are allowed instructions that can access such a pointer. On BPF_LDX, the
destination register is updated to be a PTR_TO_BTF_ID, and on BPF_STX,
it is checked whether the source register type is a PTR_TO_BTF_ID with
same BTF type as specified in the map BTF. The access size must always
be BPF_DW.

For the map in map support, the kptr_off_tab for outer map is copied
from the inner map's kptr_off_tab. It was chosen to do a deep copy
instead of introducing a refcount to kptr_off_tab, because the copy only
needs to be done when paramterizing using inner_map_fd in the map in map
case, hence would be unnecessary for all other users.

It is not permitted to use MAP_FREEZE command and mmap for BPF map
having kptrs, similar to the bpf_timer case. A kptr also requires that
BPF program has both read and write access to the map (hence both
BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG are disallowed).

Note that check_map_access must be called from both
check_helper_mem_access and for the BPF instructions, hence the kptr
check must distinguish between ACCESS_DIRECT and ACCESS_HELPER, and
reject ACCESS_HELPER cases. We rename stack_access_src to bpf_access_src
and reuse it for this purpose.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-2-memxor@gmail.com
---
 include/linux/bpf.h     |  31 ++++++++-
 include/linux/btf.h     |   2 +
 kernel/bpf/btf.c        | 167 ++++++++++++++++++++++++++++++++++++++++++------
 kernel/bpf/map_in_map.c |   5 +-
 kernel/bpf/syscall.c    | 103 ++++++++++++++++++++++++++++-
 kernel/bpf/verifier.c   | 161 +++++++++++++++++++++++++++++++++++++++++++---
 6 files changed, 433 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7bf441563ffc..ce12124048c0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -155,6 +155,24 @@ struct bpf_map_ops {
 	const struct bpf_iter_seq_info *iter_seq_info;
 };
 
+enum {
+	/* Support at most 8 pointers in a BPF map value */
+	BPF_MAP_VALUE_OFF_MAX = 8,
+};
+
+struct bpf_map_value_off_desc {
+	u32 offset;
+	struct {
+		struct btf *btf;
+		u32 btf_id;
+	} kptr;
+};
+
+struct bpf_map_value_off {
+	u32 nr_off;
+	struct bpf_map_value_off_desc off[];
+};
+
 struct bpf_map {
 	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
@@ -171,6 +189,7 @@ struct bpf_map {
 	u64 map_extra; /* any per-map-type extra fields */
 	u32 map_flags;
 	int spin_lock_off; /* >=0 valid offset, <0 error */
+	struct bpf_map_value_off *kptr_off_tab;
 	int timer_off; /* >=0 valid offset, <0 error */
 	u32 id;
 	int numa_node;
@@ -184,7 +203,7 @@ struct bpf_map {
 	char name[BPF_OBJ_NAME_LEN];
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
-	/* 14 bytes hole */
+	/* 6 bytes hole */
 
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
@@ -217,6 +236,11 @@ static inline bool map_value_has_timer(const struct bpf_map *map)
 	return map->timer_off >= 0;
 }
 
+static inline bool map_value_has_kptrs(const struct bpf_map *map)
+{
+	return !IS_ERR_OR_NULL(map->kptr_off_tab);
+}
+
 static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
 {
 	if (unlikely(map_value_has_spin_lock(map)))
@@ -1396,6 +1420,11 @@ void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
 void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
 
+struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset);
+void bpf_map_free_kptr_off_tab(struct bpf_map *map);
+struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map);
+bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b);
+
 struct bpf_map *bpf_map_get(u32 ufd);
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 36bc09b8e890..19c297f9a52f 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -123,6 +123,8 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   u32 expected_offset, u32 expected_size);
 int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
 int btf_find_timer(const struct btf *btf, const struct btf_type *t);
+struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
+					  const struct btf_type *t);
 bool btf_type_is_void(const struct btf_type *t);
 s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind);
 const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 0493310d981f..563ac61e6d6b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3166,9 +3166,16 @@ static void btf_struct_log(struct btf_verifier_env *env,
 enum btf_field_type {
 	BTF_FIELD_SPIN_LOCK,
 	BTF_FIELD_TIMER,
+	BTF_FIELD_KPTR,
+};
+
+enum {
+	BTF_FIELD_IGNORE = 0,
+	BTF_FIELD_FOUND  = 1,
 };
 
 struct btf_field_info {
+	u32 type_id;
 	u32 off;
 };
 
@@ -3176,29 +3183,57 @@ static int btf_find_struct(const struct btf *btf, const struct btf_type *t,
 			   u32 off, int sz, struct btf_field_info *info)
 {
 	if (!__btf_type_is_struct(t))
-		return 0;
+		return BTF_FIELD_IGNORE;
 	if (t->size != sz)
-		return 0;
-	if (info->off != -ENOENT)
-		/* only one such field is allowed */
-		return -E2BIG;
+		return BTF_FIELD_IGNORE;
 	info->off = off;
-	return 0;
+	return BTF_FIELD_FOUND;
+}
+
+static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
+			 u32 off, int sz, struct btf_field_info *info)
+{
+	u32 res_id;
+
+	/* For PTR, sz is always == 8 */
+	if (!btf_type_is_ptr(t))
+		return BTF_FIELD_IGNORE;
+	t = btf_type_by_id(btf, t->type);
+
+	if (!btf_type_is_type_tag(t))
+		return BTF_FIELD_IGNORE;
+	/* Reject extra tags */
+	if (btf_type_is_type_tag(btf_type_by_id(btf, t->type)))
+		return -EINVAL;
+	if (strcmp("kptr", __btf_name_by_offset(btf, t->name_off)))
+		return -EINVAL;
+
+	/* Get the base type */
+	t = btf_type_skip_modifiers(btf, t->type, &res_id);
+	/* Only pointer to struct is allowed */
+	if (!__btf_type_is_struct(t))
+		return -EINVAL;
+
+	info->type_id = res_id;
+	info->off = off;
+	return BTF_FIELD_FOUND;
 }
 
 static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t,
 				 const char *name, int sz, int align,
 				 enum btf_field_type field_type,
-				 struct btf_field_info *info)
+				 struct btf_field_info *info, int info_cnt)
 {
 	const struct btf_member *member;
+	struct btf_field_info tmp;
+	int ret, idx = 0;
 	u32 i, off;
 
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								    member->type);
 
-		if (strcmp(__btf_name_by_offset(btf, member_type->name_off), name))
+		if (name && strcmp(__btf_name_by_offset(btf, member_type->name_off), name))
 			continue;
 
 		off = __btf_member_bit_offset(t, member);
@@ -3212,20 +3247,38 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t
 		switch (field_type) {
 		case BTF_FIELD_SPIN_LOCK:
 		case BTF_FIELD_TIMER:
-			return btf_find_struct(btf, member_type, off, sz, info);
+			ret = btf_find_struct(btf, member_type, off, sz,
+					      idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
+		case BTF_FIELD_KPTR:
+			ret = btf_find_kptr(btf, member_type, off, sz,
+					    idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
 		default:
 			return -EFAULT;
 		}
+
+		if (ret == BTF_FIELD_IGNORE)
+			continue;
+		if (idx >= info_cnt)
+			return -E2BIG;
+		++idx;
 	}
-	return 0;
+	return idx;
 }
 
 static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 				const char *name, int sz, int align,
 				enum btf_field_type field_type,
-				struct btf_field_info *info)
+				struct btf_field_info *info, int info_cnt)
 {
 	const struct btf_var_secinfo *vsi;
+	struct btf_field_info tmp;
+	int ret, idx = 0;
 	u32 i, off;
 
 	for_each_vsi(i, t, vsi) {
@@ -3234,7 +3287,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 
 		off = vsi->offset;
 
-		if (strcmp(__btf_name_by_offset(btf, var_type->name_off), name))
+		if (name && strcmp(__btf_name_by_offset(btf, var_type->name_off), name))
 			continue;
 		if (vsi->size != sz)
 			continue;
@@ -3244,17 +3297,33 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 		switch (field_type) {
 		case BTF_FIELD_SPIN_LOCK:
 		case BTF_FIELD_TIMER:
-			return btf_find_struct(btf, var_type, off, sz, info);
+			ret = btf_find_struct(btf, var_type, off, sz,
+					      idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
+		case BTF_FIELD_KPTR:
+			ret = btf_find_kptr(btf, var_type, off, sz,
+					    idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
 		default:
 			return -EFAULT;
 		}
+
+		if (ret == BTF_FIELD_IGNORE)
+			continue;
+		if (idx >= info_cnt)
+			return -E2BIG;
+		++idx;
 	}
-	return 0;
+	return idx;
 }
 
 static int btf_find_field(const struct btf *btf, const struct btf_type *t,
 			  enum btf_field_type field_type,
-			  struct btf_field_info *info)
+			  struct btf_field_info *info, int info_cnt)
 {
 	const char *name;
 	int sz, align;
@@ -3270,14 +3339,19 @@ static int btf_find_field(const struct btf *btf, const struct btf_type *t,
 		sz = sizeof(struct bpf_timer);
 		align = __alignof__(struct bpf_timer);
 		break;
+	case BTF_FIELD_KPTR:
+		name = NULL;
+		sz = sizeof(u64);
+		align = 8;
+		break;
 	default:
 		return -EFAULT;
 	}
 
 	if (__btf_type_is_struct(t))
-		return btf_find_struct_field(btf, t, name, sz, align, field_type, info);
+		return btf_find_struct_field(btf, t, name, sz, align, field_type, info, info_cnt);
 	else if (btf_type_is_datasec(t))
-		return btf_find_datasec_var(btf, t, name, sz, align, field_type, info);
+		return btf_find_datasec_var(btf, t, name, sz, align, field_type, info, info_cnt);
 	return -EINVAL;
 }
 
@@ -3287,26 +3361,77 @@ static int btf_find_field(const struct btf *btf, const struct btf_type *t,
  */
 int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
 {
-	struct btf_field_info info = { .off = -ENOENT };
+	struct btf_field_info info;
 	int ret;
 
-	ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info);
+	ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info, 1);
 	if (ret < 0)
 		return ret;
+	if (!ret)
+		return -ENOENT;
 	return info.off;
 }
 
 int btf_find_timer(const struct btf *btf, const struct btf_type *t)
 {
-	struct btf_field_info info = { .off = -ENOENT };
+	struct btf_field_info info;
 	int ret;
 
-	ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info);
+	ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info, 1);
 	if (ret < 0)
 		return ret;
+	if (!ret)
+		return -ENOENT;
 	return info.off;
 }
 
+struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
+					  const struct btf_type *t)
+{
+	struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX];
+	struct bpf_map_value_off *tab;
+	struct btf *kernel_btf = NULL;
+	int ret, i, nr_off;
+
+	ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr));
+	if (ret < 0)
+		return ERR_PTR(ret);
+	if (!ret)
+		return NULL;
+
+	nr_off = ret;
+	tab = kzalloc(offsetof(struct bpf_map_value_off, off[nr_off]), GFP_KERNEL | __GFP_NOWARN);
+	if (!tab)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < nr_off; i++) {
+		const struct btf_type *t;
+		s32 id;
+
+		/* Find type in map BTF, and use it to look up the matching type
+		 * in vmlinux or module BTFs, by name and kind.
+		 */
+		t = btf_type_by_id(btf, info_arr[i].type_id);
+		id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info),
+				     &kernel_btf);
+		if (id < 0) {
+			ret = id;
+			goto end;
+		}
+
+		tab->off[i].offset = info_arr[i].off;
+		tab->off[i].kptr.btf_id = id;
+		tab->off[i].kptr.btf = kernel_btf;
+	}
+	tab->nr_off = nr_off;
+	return tab;
+end:
+	while (i--)
+		btf_put(tab->off[i].kptr.btf);
+	kfree(tab);
+	return ERR_PTR(ret);
+}
+
 static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
 			      u32 type_id, void *data, u8 bits_offset,
 			      struct btf_show *show)
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 5cd8f5277279..135205d0d560 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -52,6 +52,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 	inner_map_meta->max_entries = inner_map->max_entries;
 	inner_map_meta->spin_lock_off = inner_map->spin_lock_off;
 	inner_map_meta->timer_off = inner_map->timer_off;
+	inner_map_meta->kptr_off_tab = bpf_map_copy_kptr_off_tab(inner_map);
 	if (inner_map->btf) {
 		btf_get(inner_map->btf);
 		inner_map_meta->btf = inner_map->btf;
@@ -71,6 +72,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 
 void bpf_map_meta_free(struct bpf_map *map_meta)
 {
+	bpf_map_free_kptr_off_tab(map_meta);
 	btf_put(map_meta->btf);
 	kfree(map_meta);
 }
@@ -83,7 +85,8 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0,
 		meta0->key_size == meta1->key_size &&
 		meta0->value_size == meta1->value_size &&
 		meta0->timer_off == meta1->timer_off &&
-		meta0->map_flags == meta1->map_flags;
+		meta0->map_flags == meta1->map_flags &&
+		bpf_map_equal_kptr_off_tab(meta0, meta1);
 }
 
 void *bpf_map_fd_get_ptr(struct bpf_map *map,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e9e3e49c0eb7..575b09339360 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -6,6 +6,7 @@
 #include <linux/bpf_trace.h>
 #include <linux/bpf_lirc.h>
 #include <linux/bpf_verifier.h>
+#include <linux/bsearch.h>
 #include <linux/btf.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
@@ -473,12 +474,84 @@ static void bpf_map_release_memcg(struct bpf_map *map)
 }
 #endif
 
+static int bpf_map_kptr_off_cmp(const void *a, const void *b)
+{
+	const struct bpf_map_value_off_desc *off_desc1 = a, *off_desc2 = b;
+
+	if (off_desc1->offset < off_desc2->offset)
+		return -1;
+	else if (off_desc1->offset > off_desc2->offset)
+		return 1;
+	return 0;
+}
+
+struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset)
+{
+	/* Since members are iterated in btf_find_field in increasing order,
+	 * offsets appended to kptr_off_tab are in increasing order, so we can
+	 * do bsearch to find exact match.
+	 */
+	struct bpf_map_value_off *tab;
+
+	if (!map_value_has_kptrs(map))
+		return NULL;
+	tab = map->kptr_off_tab;
+	return bsearch(&offset, tab->off, tab->nr_off, sizeof(tab->off[0]), bpf_map_kptr_off_cmp);
+}
+
+void bpf_map_free_kptr_off_tab(struct bpf_map *map)
+{
+	struct bpf_map_value_off *tab = map->kptr_off_tab;
+	int i;
+
+	if (!map_value_has_kptrs(map))
+		return;
+	for (i = 0; i < tab->nr_off; i++)
+		btf_put(tab->off[i].kptr.btf);
+	kfree(tab);
+	map->kptr_off_tab = NULL;
+}
+
+struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map)
+{
+	struct bpf_map_value_off *tab = map->kptr_off_tab, *new_tab;
+	int size, i;
+
+	if (!map_value_has_kptrs(map))
+		return ERR_PTR(-ENOENT);
+	size = offsetof(struct bpf_map_value_off, off[tab->nr_off]);
+	new_tab = kmemdup(tab, size, GFP_KERNEL | __GFP_NOWARN);
+	if (!new_tab)
+		return ERR_PTR(-ENOMEM);
+	/* Do a deep copy of the kptr_off_tab */
+	for (i = 0; i < tab->nr_off; i++)
+		btf_get(tab->off[i].kptr.btf);
+	return new_tab;
+}
+
+bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b)
+{
+	struct bpf_map_value_off *tab_a = map_a->kptr_off_tab, *tab_b = map_b->kptr_off_tab;
+	bool a_has_kptr = map_value_has_kptrs(map_a), b_has_kptr = map_value_has_kptrs(map_b);
+	int size;
+
+	if (!a_has_kptr && !b_has_kptr)
+		return true;
+	if (a_has_kptr != b_has_kptr)
+		return false;
+	if (tab_a->nr_off != tab_b->nr_off)
+		return false;
+	size = offsetof(struct bpf_map_value_off, off[tab_a->nr_off]);
+	return !memcmp(tab_a, tab_b, size);
+}
+
 /* called from workqueue */
 static void bpf_map_free_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
 
 	security_bpf_map_free(map);
+	bpf_map_free_kptr_off_tab(map);
 	bpf_map_release_memcg(map);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
@@ -640,7 +713,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 	int err;
 
 	if (!map->ops->map_mmap || map_value_has_spin_lock(map) ||
-	    map_value_has_timer(map))
+	    map_value_has_timer(map) || map_value_has_kptrs(map))
 		return -ENOTSUPP;
 
 	if (!(vma->vm_flags & VM_SHARED))
@@ -820,9 +893,33 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 			return -EOPNOTSUPP;
 	}
 
-	if (map->ops->map_check_btf)
+	map->kptr_off_tab = btf_parse_kptrs(btf, value_type);
+	if (map_value_has_kptrs(map)) {
+		if (!bpf_capable()) {
+			ret = -EPERM;
+			goto free_map_tab;
+		}
+		if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) {
+			ret = -EACCES;
+			goto free_map_tab;
+		}
+		if (map->map_type != BPF_MAP_TYPE_HASH &&
+		    map->map_type != BPF_MAP_TYPE_LRU_HASH &&
+		    map->map_type != BPF_MAP_TYPE_ARRAY) {
+			ret = -EOPNOTSUPP;
+			goto free_map_tab;
+		}
+	}
+
+	if (map->ops->map_check_btf) {
 		ret = map->ops->map_check_btf(map, btf, key_type, value_type);
+		if (ret < 0)
+			goto free_map_tab;
+	}
 
+	return ret;
+free_map_tab:
+	bpf_map_free_kptr_off_tab(map);
 	return ret;
 }
 
@@ -1639,7 +1736,7 @@ static int map_freeze(const union bpf_attr *attr)
 		return PTR_ERR(map);
 
 	if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS ||
-	    map_value_has_timer(map)) {
+	    map_value_has_timer(map) || map_value_has_kptrs(map)) {
 		fdput(f);
 		return -ENOTSUPP;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 71827d14724a..17ca586e0585 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3211,7 +3211,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	return 0;
 }
 
-enum stack_access_src {
+enum bpf_access_src {
 	ACCESS_DIRECT = 1,  /* the access is performed by an instruction */
 	ACCESS_HELPER = 2,  /* the access is performed by a helper */
 };
@@ -3219,7 +3219,7 @@ enum stack_access_src {
 static int check_stack_range_initialized(struct bpf_verifier_env *env,
 					 int regno, int off, int access_size,
 					 bool zero_size_allowed,
-					 enum stack_access_src type,
+					 enum bpf_access_src type,
 					 struct bpf_call_arg_meta *meta);
 
 static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
@@ -3507,9 +3507,109 @@ int check_ptr_off_reg(struct bpf_verifier_env *env,
 	return __check_ptr_off_reg(env, reg, regno, false);
 }
 
+static int map_kptr_match_type(struct bpf_verifier_env *env,
+			       struct bpf_map_value_off_desc *off_desc,
+			       struct bpf_reg_state *reg, u32 regno)
+{
+	const char *targ_name = kernel_type_name(off_desc->kptr.btf, off_desc->kptr.btf_id);
+	const char *reg_name = "";
+
+	if (base_type(reg->type) != PTR_TO_BTF_ID || type_flag(reg->type) != PTR_MAYBE_NULL)
+		goto bad_type;
+
+	if (!btf_is_kernel(reg->btf)) {
+		verbose(env, "R%d must point to kernel BTF\n", regno);
+		return -EINVAL;
+	}
+	/* We need to verify reg->type and reg->btf, before accessing reg->btf */
+	reg_name = kernel_type_name(reg->btf, reg->btf_id);
+
+	if (__check_ptr_off_reg(env, reg, regno, true))
+		return -EACCES;
+
+	/* A full type match is needed, as BTF can be vmlinux or module BTF, and
+	 * we also need to take into account the reg->off.
+	 *
+	 * We want to support cases like:
+	 *
+	 * struct foo {
+	 *         struct bar br;
+	 *         struct baz bz;
+	 * };
+	 *
+	 * struct foo *v;
+	 * v = func();	      // PTR_TO_BTF_ID
+	 * val->foo = v;      // reg->off is zero, btf and btf_id match type
+	 * val->bar = &v->br; // reg->off is still zero, but we need to retry with
+	 *                    // first member type of struct after comparison fails
+	 * val->baz = &v->bz; // reg->off is non-zero, so struct needs to be walked
+	 *                    // to match type
+	 *
+	 * In the kptr_ref case, check_func_arg_reg_off already ensures reg->off
+	 * is zero.
+	 */
+	if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
+				  off_desc->kptr.btf, off_desc->kptr.btf_id))
+		goto bad_type;
+	return 0;
+bad_type:
+	verbose(env, "invalid kptr access, R%d type=%s%s ", regno,
+		reg_type_str(env, reg->type), reg_name);
+	verbose(env, "expected=%s%s\n", reg_type_str(env, PTR_TO_BTF_ID), targ_name);
+	return -EINVAL;
+}
+
+static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
+				 int value_regno, int insn_idx,
+				 struct bpf_map_value_off_desc *off_desc)
+{
+	struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
+	int class = BPF_CLASS(insn->code);
+	struct bpf_reg_state *val_reg;
+
+	/* Things we already checked for in check_map_access and caller:
+	 *  - Reject cases where variable offset may touch kptr
+	 *  - size of access (must be BPF_DW)
+	 *  - tnum_is_const(reg->var_off)
+	 *  - off_desc->offset == off + reg->var_off.value
+	 */
+	/* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */
+	if (BPF_MODE(insn->code) != BPF_MEM) {
+		verbose(env, "kptr in map can only be accessed using BPF_MEM instruction mode\n");
+		return -EACCES;
+	}
+
+	if (class == BPF_LDX) {
+		val_reg = reg_state(env, value_regno);
+		/* We can simply mark the value_regno receiving the pointer
+		 * value from map as PTR_TO_BTF_ID, with the correct type.
+		 */
+		mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, off_desc->kptr.btf,
+				off_desc->kptr.btf_id, PTR_MAYBE_NULL);
+		/* For mark_ptr_or_null_reg */
+		val_reg->id = ++env->id_gen;
+	} else if (class == BPF_STX) {
+		val_reg = reg_state(env, value_regno);
+		if (!register_is_null(val_reg) &&
+		    map_kptr_match_type(env, off_desc, val_reg, value_regno))
+			return -EACCES;
+	} else if (class == BPF_ST) {
+		if (insn->imm) {
+			verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n",
+				off_desc->offset);
+			return -EACCES;
+		}
+	} else {
+		verbose(env, "kptr in map can only be accessed using BPF_LDX/BPF_STX/BPF_ST\n");
+		return -EACCES;
+	}
+	return 0;
+}
+
 /* check read/write into a map element with possible variable offset */
 static int check_map_access(struct bpf_verifier_env *env, u32 regno,
-			    int off, int size, bool zero_size_allowed)
+			    int off, int size, bool zero_size_allowed,
+			    enum bpf_access_src src)
 {
 	struct bpf_verifier_state *vstate = env->cur_state;
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
@@ -3545,6 +3645,36 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 			return -EACCES;
 		}
 	}
+	if (map_value_has_kptrs(map)) {
+		struct bpf_map_value_off *tab = map->kptr_off_tab;
+		int i;
+
+		for (i = 0; i < tab->nr_off; i++) {
+			u32 p = tab->off[i].offset;
+
+			if (reg->smin_value + off < p + sizeof(u64) &&
+			    p < reg->umax_value + off + size) {
+				if (src != ACCESS_DIRECT) {
+					verbose(env, "kptr cannot be accessed indirectly by helper\n");
+					return -EACCES;
+				}
+				if (!tnum_is_const(reg->var_off)) {
+					verbose(env, "kptr access cannot have variable offset\n");
+					return -EACCES;
+				}
+				if (p != off + reg->var_off.value) {
+					verbose(env, "kptr access misaligned expected=%u off=%llu\n",
+						p, off + reg->var_off.value);
+					return -EACCES;
+				}
+				if (size != bpf_size_to_bytes(BPF_DW)) {
+					verbose(env, "kptr access size must be BPF_DW\n");
+					return -EACCES;
+				}
+				break;
+			}
+		}
+	}
 	return err;
 }
 
@@ -4316,7 +4446,7 @@ static int check_stack_slot_within_bounds(int off,
 static int check_stack_access_within_bounds(
 		struct bpf_verifier_env *env,
 		int regno, int off, int access_size,
-		enum stack_access_src src, enum bpf_access_type type)
+		enum bpf_access_src src, enum bpf_access_type type)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = regs + regno;
@@ -4412,6 +4542,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else if (reg->type == PTR_TO_MAP_VALUE) {
+		struct bpf_map_value_off_desc *kptr_off_desc = NULL;
+
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
 			verbose(env, "R%d leaks addr into map\n", value_regno);
@@ -4420,8 +4552,16 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		err = check_map_access_type(env, regno, off, size, t);
 		if (err)
 			return err;
-		err = check_map_access(env, regno, off, size, false);
-		if (!err && t == BPF_READ && value_regno >= 0) {
+		err = check_map_access(env, regno, off, size, false, ACCESS_DIRECT);
+		if (err)
+			return err;
+		if (tnum_is_const(reg->var_off))
+			kptr_off_desc = bpf_map_kptr_off_contains(reg->map_ptr,
+								  off + reg->var_off.value);
+		if (kptr_off_desc) {
+			err = check_map_kptr_access(env, regno, value_regno, insn_idx,
+						    kptr_off_desc);
+		} else if (t == BPF_READ && value_regno >= 0) {
 			struct bpf_map *map = reg->map_ptr;
 
 			/* if map is read-only, track its contents as scalars */
@@ -4724,7 +4864,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 static int check_stack_range_initialized(
 		struct bpf_verifier_env *env, int regno, int off,
 		int access_size, bool zero_size_allowed,
-		enum stack_access_src type, struct bpf_call_arg_meta *meta)
+		enum bpf_access_src type, struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *reg = reg_state(env, regno);
 	struct bpf_func_state *state = func(env, reg);
@@ -4874,7 +5014,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 					  BPF_READ))
 			return -EACCES;
 		return check_map_access(env, regno, reg->off, access_size,
-					zero_size_allowed);
+					zero_size_allowed, ACCESS_HELPER);
 	case PTR_TO_MEM:
 		if (type_is_rdonly_mem(reg->type)) {
 			if (meta && meta->raw_mode) {
@@ -5642,7 +5782,8 @@ skip_type_check:
 		}
 
 		err = check_map_access(env, regno, reg->off,
-				       map->value_size - reg->off, false);
+				       map->value_size - reg->off, false,
+				       ACCESS_HELPER);
 		if (err)
 			return err;
 
@@ -7462,7 +7603,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env,
 			return -EACCES;
 		break;
 	case PTR_TO_MAP_VALUE:
-		if (check_map_access(env, dst, dst_reg->off, 1, false)) {
+		if (check_map_access(env, dst, dst_reg->off, 1, false, ACCESS_HELPER)) {
 			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
 				"prohibited for !root\n", dst);
 			return -EACCES;
-- 
cgit v1.2.3


From 8f14852e89113d738c99c375b4c8b8b7e1073df1 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:50 +0530
Subject: bpf: Tag argument to be released in bpf_func_proto

Add a new type flag for bpf_arg_type that when set tells verifier that
for a release function, that argument's register will be the one for
which meta.ref_obj_id will be set, and which will then be released
using release_reference. To capture the regno, introduce a new field
release_regno in bpf_call_arg_meta.

This would be required in the next patch, where we may either pass NULL
or a refcounted pointer as an argument to the release function
bpf_kptr_xchg. Just releasing only when meta.ref_obj_id is set is not
enough, as there is a case where the type of argument needed matches,
but the ref_obj_id is set to 0. Hence, we must enforce that whenever
meta.ref_obj_id is zero, the register that is to be released can only
be NULL for a release function.

Since we now indicate whether an argument is to be released in
bpf_func_proto itself, is_release_function helper has lost its utitlity,
hence refactor code to work without it, and just rely on
meta.release_regno to know when to release state for a ref_obj_id.
Still, the restriction of one release argument and only one ref_obj_id
passed to BPF helper or kfunc remains. This may be lifted in the future.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-3-memxor@gmail.com
---
 include/linux/bpf.h                                |  5 +-
 include/linux/bpf_verifier.h                       |  3 +-
 kernel/bpf/btf.c                                   | 11 ++--
 kernel/bpf/ringbuf.c                               |  4 +-
 kernel/bpf/verifier.c                              | 76 ++++++++++++----------
 net/core/filter.c                                  |  2 +-
 .../testing/selftests/bpf/verifier/ref_tracking.c  |  2 +-
 tools/testing/selftests/bpf/verifier/sock.c        |  6 +-
 8 files changed, 60 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ce12124048c0..492edd2c5713 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -366,7 +366,10 @@ enum bpf_type_flag {
 	 */
 	MEM_PERCPU		= BIT(4 + BPF_BASE_TYPE_BITS),
 
-	__BPF_TYPE_LAST_FLAG	= MEM_PERCPU,
+	/* Indicates that the argument will be released. */
+	OBJ_RELEASE		= BIT(5 + BPF_BASE_TYPE_BITS),
+
+	__BPF_TYPE_LAST_FLAG	= OBJ_RELEASE,
 };
 
 /* Max number of base types. */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3a9d2d7cc6b7..1f1e7f2ea967 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -523,8 +523,7 @@ int check_ptr_off_reg(struct bpf_verifier_env *env,
 		      const struct bpf_reg_state *reg, int regno);
 int check_func_arg_reg_off(struct bpf_verifier_env *env,
 			   const struct bpf_reg_state *reg, int regno,
-			   enum bpf_arg_type arg_type,
-			   bool is_release_func);
+			   enum bpf_arg_type arg_type);
 int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 			     u32 regno);
 int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 563ac61e6d6b..f0287342204f 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6047,6 +6047,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 	 * verifier sees.
 	 */
 	for (i = 0; i < nargs; i++) {
+		enum bpf_arg_type arg_type = ARG_DONTCARE;
 		u32 regno = i + 1;
 		struct bpf_reg_state *reg = &regs[regno];
 
@@ -6067,7 +6068,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 		ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
 		ref_tname = btf_name_by_offset(btf, ref_t->name_off);
 
-		ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE, rel);
+		if (rel && reg->ref_obj_id)
+			arg_type |= OBJ_RELEASE;
+		ret = check_func_arg_reg_off(env, reg, regno, arg_type);
 		if (ret < 0)
 			return ret;
 
@@ -6099,11 +6102,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			if (reg->type == PTR_TO_BTF_ID) {
 				reg_btf = reg->btf;
 				reg_ref_id = reg->btf_id;
-				/* Ensure only one argument is referenced
-				 * PTR_TO_BTF_ID, check_func_arg_reg_off relies
-				 * on only one referenced register being allowed
-				 * for kfuncs.
-				 */
+				/* Ensure only one argument is referenced PTR_TO_BTF_ID */
 				if (reg->ref_obj_id) {
 					if (ref_obj_id) {
 						bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 710ba9de12ce..5173fd37590f 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -404,7 +404,7 @@ BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags)
 const struct bpf_func_proto bpf_ringbuf_submit_proto = {
 	.func		= bpf_ringbuf_submit,
 	.ret_type	= RET_VOID,
-	.arg1_type	= ARG_PTR_TO_ALLOC_MEM,
+	.arg1_type	= ARG_PTR_TO_ALLOC_MEM | OBJ_RELEASE,
 	.arg2_type	= ARG_ANYTHING,
 };
 
@@ -417,7 +417,7 @@ BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags)
 const struct bpf_func_proto bpf_ringbuf_discard_proto = {
 	.func		= bpf_ringbuf_discard,
 	.ret_type	= RET_VOID,
-	.arg1_type	= ARG_PTR_TO_ALLOC_MEM,
+	.arg1_type	= ARG_PTR_TO_ALLOC_MEM | OBJ_RELEASE,
 	.arg2_type	= ARG_ANYTHING,
 };
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 17ca586e0585..5426bab7f02c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -245,6 +245,7 @@ struct bpf_call_arg_meta {
 	struct bpf_map *map_ptr;
 	bool raw_mode;
 	bool pkt_access;
+	u8 release_regno;
 	int regno;
 	int access_size;
 	int mem_size;
@@ -471,17 +472,6 @@ static bool type_may_be_null(u32 type)
 	return type & PTR_MAYBE_NULL;
 }
 
-/* Determine whether the function releases some resources allocated by another
- * function call. The first reference type argument will be assumed to be
- * released by release_reference().
- */
-static bool is_release_function(enum bpf_func_id func_id)
-{
-	return func_id == BPF_FUNC_sk_release ||
-	       func_id == BPF_FUNC_ringbuf_submit ||
-	       func_id == BPF_FUNC_ringbuf_discard;
-}
-
 static bool may_be_acquire_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_lookup_tcp ||
@@ -5326,6 +5316,11 @@ static bool arg_type_is_int_ptr(enum bpf_arg_type type)
 	       type == ARG_PTR_TO_LONG;
 }
 
+static bool arg_type_is_release(enum bpf_arg_type type)
+{
+	return type & OBJ_RELEASE;
+}
+
 static int int_ptr_type_to_size(enum bpf_arg_type type)
 {
 	if (type == ARG_PTR_TO_INT)
@@ -5536,11 +5531,10 @@ found:
 
 int check_func_arg_reg_off(struct bpf_verifier_env *env,
 			   const struct bpf_reg_state *reg, int regno,
-			   enum bpf_arg_type arg_type,
-			   bool is_release_func)
+			   enum bpf_arg_type arg_type)
 {
-	bool fixed_off_ok = false, release_reg;
 	enum bpf_reg_type type = reg->type;
+	bool fixed_off_ok = false;
 
 	switch ((u32)type) {
 	case SCALAR_VALUE:
@@ -5558,7 +5552,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 		/* Some of the argument types nevertheless require a
 		 * zero register offset.
 		 */
-		if (arg_type != ARG_PTR_TO_ALLOC_MEM)
+		if (base_type(arg_type) != ARG_PTR_TO_ALLOC_MEM)
 			return 0;
 		break;
 	/* All the rest must be rejected, except PTR_TO_BTF_ID which allows
@@ -5566,19 +5560,17 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	 */
 	case PTR_TO_BTF_ID:
 		/* When referenced PTR_TO_BTF_ID is passed to release function,
-		 * it's fixed offset must be 0. We rely on the property that
-		 * only one referenced register can be passed to BPF helpers and
-		 * kfuncs. In the other cases, fixed offset can be non-zero.
+		 * it's fixed offset must be 0.	In the other cases, fixed offset
+		 * can be non-zero.
 		 */
-		release_reg = is_release_func && reg->ref_obj_id;
-		if (release_reg && reg->off) {
+		if (arg_type_is_release(arg_type) && reg->off) {
 			verbose(env, "R%d must have zero offset when passed to release func\n",
 				regno);
 			return -EINVAL;
 		}
-		/* For release_reg == true, fixed_off_ok must be false, but we
-		 * already checked and rejected reg->off != 0 above, so set to
-		 * true to allow fixed offset for all other cases.
+		/* For arg is release pointer, fixed_off_ok must be false, but
+		 * we already checked and rejected reg->off != 0 above, so set
+		 * to true to allow fixed offset for all other cases.
 		 */
 		fixed_off_ok = true;
 		break;
@@ -5637,14 +5629,24 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	if (err)
 		return err;
 
-	err = check_func_arg_reg_off(env, reg, regno, arg_type, is_release_function(meta->func_id));
+	err = check_func_arg_reg_off(env, reg, regno, arg_type);
 	if (err)
 		return err;
 
 skip_type_check:
-	/* check_func_arg_reg_off relies on only one referenced register being
-	 * allowed for BPF helpers.
-	 */
+	if (arg_type_is_release(arg_type)) {
+		if (!reg->ref_obj_id && !register_is_null(reg)) {
+			verbose(env, "R%d must be referenced when passed to release function\n",
+				regno);
+			return -EINVAL;
+		}
+		if (meta->release_regno) {
+			verbose(env, "verifier internal error: more than one release argument\n");
+			return -EFAULT;
+		}
+		meta->release_regno = regno;
+	}
+
 	if (reg->ref_obj_id) {
 		if (meta->ref_obj_id) {
 			verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
@@ -6151,7 +6153,8 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 	return true;
 }
 
-static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
+static int check_func_proto(const struct bpf_func_proto *fn, int func_id,
+			    struct bpf_call_arg_meta *meta)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
@@ -6835,7 +6838,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	memset(&meta, 0, sizeof(meta));
 	meta.pkt_access = fn->pkt_access;
 
-	err = check_func_proto(fn, func_id);
+	err = check_func_proto(fn, func_id, &meta);
 	if (err) {
 		verbose(env, "kernel subsystem misconfigured func %s#%d\n",
 			func_id_name(func_id), func_id);
@@ -6868,8 +6871,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			return err;
 	}
 
-	if (is_release_function(func_id)) {
-		err = release_reference(env, meta.ref_obj_id);
+	regs = cur_regs(env);
+
+	if (meta.release_regno) {
+		err = -EINVAL;
+		if (meta.ref_obj_id)
+			err = release_reference(env, meta.ref_obj_id);
+		/* meta.ref_obj_id can only be 0 if register that is meant to be
+		 * released is NULL, which must be > R0.
+		 */
+		else if (register_is_null(&regs[meta.release_regno]))
+			err = 0;
 		if (err) {
 			verbose(env, "func %s#%d reference has not been acquired before\n",
 				func_id_name(func_id), func_id);
@@ -6877,8 +6889,6 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 	}
 
-	regs = cur_regs(env);
-
 	switch (func_id) {
 	case BPF_FUNC_tail_call:
 		err = check_reference_leak(env);
diff --git a/net/core/filter.c b/net/core/filter.c
index 8847316ee20e..da04ad179fda 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6621,7 +6621,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
 	.func		= bpf_sk_release,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON | OBJ_RELEASE,
 };
 
 BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index fbd682520e47..57a83d763ec1 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -796,7 +796,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "reference has not been acquired before",
+	.errstr = "R1 must be referenced when passed to release function",
 },
 {
 	/* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index 86b24cad27a7..d11d0b28be41 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -417,7 +417,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "reference has not been acquired before",
+	.errstr = "R1 must be referenced when passed to release function",
 },
 {
 	"bpf_sk_release(bpf_sk_fullsock(skb->sk))",
@@ -436,7 +436,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "reference has not been acquired before",
+	.errstr = "R1 must be referenced when passed to release function",
 },
 {
 	"bpf_sk_release(bpf_tcp_sock(skb->sk))",
@@ -455,7 +455,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "reference has not been acquired before",
+	.errstr = "R1 must be referenced when passed to release function",
 },
 {
 	"sk_storage_get(map, skb->sk, NULL, 0): value == NULL",
-- 
cgit v1.2.3


From c0a5a21c25f37c9fd7b36072f9968cdff1e4aa13 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:51 +0530
Subject: bpf: Allow storing referenced kptr in map

Extending the code in previous commits, introduce referenced kptr
support, which needs to be tagged using 'kptr_ref' tag instead. Unlike
unreferenced kptr, referenced kptr have a lot more restrictions. In
addition to the type matching, only a newly introduced bpf_kptr_xchg
helper is allowed to modify the map value at that offset. This transfers
the referenced pointer being stored into the map, releasing the
references state for the program, and returning the old value and
creating new reference state for the returned pointer.

Similar to unreferenced pointer case, return value for this case will
also be PTR_TO_BTF_ID_OR_NULL. The reference for the returned pointer
must either be eventually released by calling the corresponding release
function, otherwise it must be transferred into another map.

It is also allowed to call bpf_kptr_xchg with a NULL pointer, to clear
the value, and obtain the old value if any.

BPF_LDX, BPF_STX, and BPF_ST cannot access referenced kptr. A future
commit will permit using BPF_LDX for such pointers, but attempt at
making it safe, since the lifetime of object won't be guaranteed.

There are valid reasons to enforce the restriction of permitting only
bpf_kptr_xchg to operate on referenced kptr. The pointer value must be
consistent in face of concurrent modification, and any prior values
contained in the map must also be released before a new one is moved
into the map. To ensure proper transfer of this ownership, bpf_kptr_xchg
returns the old value, which the verifier would require the user to
either free or move into another map, and releases the reference held
for the pointer being moved in.

In the future, direct BPF_XCHG instruction may also be permitted to work
like bpf_kptr_xchg helper.

Note that process_kptr_func doesn't have to call
check_helper_mem_access, since we already disallow rdonly/wronly flags
for map, which is what check_map_access_type checks, and we already
ensure the PTR_TO_MAP_VALUE refers to kptr by obtaining its off_desc,
so check_map_access is also not required.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-4-memxor@gmail.com
---
 include/linux/bpf.h            |  8 ++++
 include/uapi/linux/bpf.h       | 12 ++++++
 kernel/bpf/btf.c               | 10 ++++-
 kernel/bpf/helpers.c           | 24 +++++++++++
 kernel/bpf/verifier.c          | 98 ++++++++++++++++++++++++++++++++++++------
 tools/include/uapi/linux/bpf.h | 12 ++++++
 6 files changed, 151 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 492edd2c5713..24310837bafc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -160,8 +160,14 @@ enum {
 	BPF_MAP_VALUE_OFF_MAX = 8,
 };
 
+enum bpf_kptr_type {
+	BPF_KPTR_UNREF,
+	BPF_KPTR_REF,
+};
+
 struct bpf_map_value_off_desc {
 	u32 offset;
+	enum bpf_kptr_type type;
 	struct {
 		struct btf *btf;
 		u32 btf_id;
@@ -418,6 +424,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_STACK,	/* pointer to stack */
 	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
 	ARG_PTR_TO_TIMER,	/* pointer to bpf_timer */
+	ARG_PTR_TO_KPTR,	/* pointer to referenced kptr */
 	__BPF_ARG_TYPE_MAX,
 
 	/* Extended arg_types. */
@@ -427,6 +434,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM,
 	ARG_PTR_TO_STACK_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
+	ARG_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d14b10b85e51..444fe6f1cf35 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5143,6 +5143,17 @@ union bpf_attr {
  *		The **hash_algo** is returned on success,
  *		**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
+ *
+ * void *bpf_kptr_xchg(void *map_value, void *ptr)
+ *	Description
+ *		Exchange kptr at pointer *map_value* with *ptr*, and return the
+ *		old value. *ptr* can be NULL, otherwise it must be a referenced
+ *		pointer which will be released when this helper is called.
+ *	Return
+ *		The old value of kptr (which can be NULL). The returned pointer
+ *		if not NULL, is a reference which must be released using its
+ *		corresponding release function, or moved into a BPF map before
+ *		program exit.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5339,6 +5350,7 @@ union bpf_attr {
 	FN(copy_from_user_task),	\
 	FN(skb_set_tstamp),		\
 	FN(ima_file_hash),		\
+	FN(kptr_xchg),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f0287342204f..4138c51728dd 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3177,6 +3177,7 @@ enum {
 struct btf_field_info {
 	u32 type_id;
 	u32 off;
+	enum bpf_kptr_type type;
 };
 
 static int btf_find_struct(const struct btf *btf, const struct btf_type *t,
@@ -3193,6 +3194,7 @@ static int btf_find_struct(const struct btf *btf, const struct btf_type *t,
 static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
 			 u32 off, int sz, struct btf_field_info *info)
 {
+	enum bpf_kptr_type type;
 	u32 res_id;
 
 	/* For PTR, sz is always == 8 */
@@ -3205,7 +3207,11 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
 	/* Reject extra tags */
 	if (btf_type_is_type_tag(btf_type_by_id(btf, t->type)))
 		return -EINVAL;
-	if (strcmp("kptr", __btf_name_by_offset(btf, t->name_off)))
+	if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off)))
+		type = BPF_KPTR_UNREF;
+	else if (!strcmp("kptr_ref", __btf_name_by_offset(btf, t->name_off)))
+		type = BPF_KPTR_REF;
+	else
 		return -EINVAL;
 
 	/* Get the base type */
@@ -3216,6 +3222,7 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
 
 	info->type_id = res_id;
 	info->off = off;
+	info->type = type;
 	return BTF_FIELD_FOUND;
 }
 
@@ -3420,6 +3427,7 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
 		}
 
 		tab->off[i].offset = info_arr[i].off;
+		tab->off[i].type = info_arr[i].type;
 		tab->off[i].kptr.btf_id = id;
 		tab->off[i].kptr.btf = kernel_btf;
 	}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 315053ef6a75..3e709fed5306 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1374,6 +1374,28 @@ out:
 	kfree(t);
 }
 
+BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr)
+{
+	unsigned long *kptr = map_value;
+
+	return xchg(kptr, (unsigned long)ptr);
+}
+
+/* Unlike other PTR_TO_BTF_ID helpers the btf_id in bpf_kptr_xchg()
+ * helper is determined dynamically by the verifier.
+ */
+#define BPF_PTR_POISON ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA))
+
+const struct bpf_func_proto bpf_kptr_xchg_proto = {
+	.func         = bpf_kptr_xchg,
+	.gpl_only     = false,
+	.ret_type     = RET_PTR_TO_BTF_ID_OR_NULL,
+	.ret_btf_id   = BPF_PTR_POISON,
+	.arg1_type    = ARG_PTR_TO_KPTR,
+	.arg2_type    = ARG_PTR_TO_BTF_ID_OR_NULL | OBJ_RELEASE,
+	.arg2_btf_id  = BPF_PTR_POISON,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_get_current_task_btf_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
@@ -1452,6 +1474,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_timer_start_proto;
 	case BPF_FUNC_timer_cancel:
 		return &bpf_timer_cancel_proto;
+	case BPF_FUNC_kptr_xchg:
+		return &bpf_kptr_xchg_proto;
 	default:
 		break;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5426bab7f02c..c9ee44efed89 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -258,6 +258,7 @@ struct bpf_call_arg_meta {
 	struct btf *ret_btf;
 	u32 ret_btf_id;
 	u32 subprogno;
+	struct bpf_map_value_off_desc *kptr_off_desc;
 };
 
 struct btf *btf_vmlinux;
@@ -489,7 +490,8 @@ static bool is_acquire_function(enum bpf_func_id func_id,
 	if (func_id == BPF_FUNC_sk_lookup_tcp ||
 	    func_id == BPF_FUNC_sk_lookup_udp ||
 	    func_id == BPF_FUNC_skc_lookup_tcp ||
-	    func_id == BPF_FUNC_ringbuf_reserve)
+	    func_id == BPF_FUNC_ringbuf_reserve ||
+	    func_id == BPF_FUNC_kptr_xchg)
 		return true;
 
 	if (func_id == BPF_FUNC_map_lookup_elem &&
@@ -3514,6 +3516,12 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
 	/* We need to verify reg->type and reg->btf, before accessing reg->btf */
 	reg_name = kernel_type_name(reg->btf, reg->btf_id);
 
+	/* For ref_ptr case, release function check should ensure we get one
+	 * referenced PTR_TO_BTF_ID, and that its fixed offset is 0. For the
+	 * normal store of unreferenced kptr, we must ensure var_off is zero.
+	 * Since ref_ptr cannot be accessed directly by BPF insns, checks for
+	 * reg->off and reg->ref_obj_id are not needed here.
+	 */
 	if (__check_ptr_off_reg(env, reg, regno, true))
 		return -EACCES;
 
@@ -3569,6 +3577,12 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
 		return -EACCES;
 	}
 
+	/* We cannot directly access kptr_ref */
+	if (off_desc->type == BPF_KPTR_REF) {
+		verbose(env, "accessing referenced kptr disallowed\n");
+		return -EACCES;
+	}
+
 	if (class == BPF_LDX) {
 		val_reg = reg_state(env, value_regno);
 		/* We can simply mark the value_regno receiving the pointer
@@ -5293,6 +5307,53 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
 	return 0;
 }
 
+static int process_kptr_func(struct bpf_verifier_env *env, int regno,
+			     struct bpf_call_arg_meta *meta)
+{
+	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+	struct bpf_map_value_off_desc *off_desc;
+	struct bpf_map *map_ptr = reg->map_ptr;
+	u32 kptr_off;
+	int ret;
+
+	if (!tnum_is_const(reg->var_off)) {
+		verbose(env,
+			"R%d doesn't have constant offset. kptr has to be at the constant offset\n",
+			regno);
+		return -EINVAL;
+	}
+	if (!map_ptr->btf) {
+		verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n",
+			map_ptr->name);
+		return -EINVAL;
+	}
+	if (!map_value_has_kptrs(map_ptr)) {
+		ret = PTR_ERR(map_ptr->kptr_off_tab);
+		if (ret == -E2BIG)
+			verbose(env, "map '%s' has more than %d kptr\n", map_ptr->name,
+				BPF_MAP_VALUE_OFF_MAX);
+		else if (ret == -EEXIST)
+			verbose(env, "map '%s' has repeating kptr BTF tags\n", map_ptr->name);
+		else
+			verbose(env, "map '%s' has no valid kptr\n", map_ptr->name);
+		return -EINVAL;
+	}
+
+	meta->map_ptr = map_ptr;
+	kptr_off = reg->off + reg->var_off.value;
+	off_desc = bpf_map_kptr_off_contains(map_ptr, kptr_off);
+	if (!off_desc) {
+		verbose(env, "off=%d doesn't point to kptr\n", kptr_off);
+		return -EACCES;
+	}
+	if (off_desc->type != BPF_KPTR_REF) {
+		verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off);
+		return -EACCES;
+	}
+	meta->kptr_off_desc = off_desc;
+	return 0;
+}
+
 static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
 {
 	return base_type(type) == ARG_PTR_TO_MEM ||
@@ -5433,6 +5494,7 @@ static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } };
 static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } };
 static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } };
 static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } };
+static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } };
 
 static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
@@ -5460,11 +5522,13 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_STACK]		= &stack_ptr_types,
 	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
 	[ARG_PTR_TO_TIMER]		= &timer_types,
+	[ARG_PTR_TO_KPTR]		= &kptr_types,
 };
 
 static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 			  enum bpf_arg_type arg_type,
-			  const u32 *arg_btf_id)
+			  const u32 *arg_btf_id,
+			  struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	enum bpf_reg_type expected, type = reg->type;
@@ -5517,8 +5581,11 @@ found:
 			arg_btf_id = compatible->btf_id;
 		}
 
-		if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
-					  btf_vmlinux, *arg_btf_id)) {
+		if (meta->func_id == BPF_FUNC_kptr_xchg) {
+			if (map_kptr_match_type(env, meta->kptr_off_desc, reg, regno))
+				return -EACCES;
+		} else if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
+						 btf_vmlinux, *arg_btf_id)) {
 			verbose(env, "R%d is of type %s but %s is expected\n",
 				regno, kernel_type_name(reg->btf, reg->btf_id),
 				kernel_type_name(btf_vmlinux, *arg_btf_id));
@@ -5625,7 +5692,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		 */
 		goto skip_type_check;
 
-	err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg]);
+	err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg], meta);
 	if (err)
 		return err;
 
@@ -5801,6 +5868,9 @@ skip_type_check:
 			verbose(env, "string is not zero-terminated\n");
 			return -EINVAL;
 		}
+	} else if (arg_type == ARG_PTR_TO_KPTR) {
+		if (process_kptr_func(env, regno, meta))
+			return -EACCES;
 	}
 
 	return err;
@@ -6143,10 +6213,10 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
-		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
+		if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
 			return false;
 
-		if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
+		if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
 			return false;
 	}
 
@@ -7012,21 +7082,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
 	} else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) {
+		struct btf *ret_btf;
 		int ret_btf_id;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
-		ret_btf_id = *fn->ret_btf_id;
+		if (func_id == BPF_FUNC_kptr_xchg) {
+			ret_btf = meta.kptr_off_desc->kptr.btf;
+			ret_btf_id = meta.kptr_off_desc->kptr.btf_id;
+		} else {
+			ret_btf = btf_vmlinux;
+			ret_btf_id = *fn->ret_btf_id;
+		}
 		if (ret_btf_id == 0) {
 			verbose(env, "invalid return type %u of func %s#%d\n",
 				base_type(ret_type), func_id_name(func_id),
 				func_id);
 			return -EINVAL;
 		}
-		/* current BPF helper definitions are only coming from
-		 * built-in code with type IDs from  vmlinux BTF
-		 */
-		regs[BPF_REG_0].btf = btf_vmlinux;
+		regs[BPF_REG_0].btf = ret_btf;
 		regs[BPF_REG_0].btf_id = ret_btf_id;
 	} else {
 		verbose(env, "unknown return type %u of func %s#%d\n",
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d14b10b85e51..444fe6f1cf35 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5143,6 +5143,17 @@ union bpf_attr {
  *		The **hash_algo** is returned on success,
  *		**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
+ *
+ * void *bpf_kptr_xchg(void *map_value, void *ptr)
+ *	Description
+ *		Exchange kptr at pointer *map_value* with *ptr*, and return the
+ *		old value. *ptr* can be NULL, otherwise it must be a referenced
+ *		pointer which will be released when this helper is called.
+ *	Return
+ *		The old value of kptr (which can be NULL). The returned pointer
+ *		if not NULL, is a reference which must be released using its
+ *		corresponding release function, or moved into a BPF map before
+ *		program exit.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5339,6 +5350,7 @@ union bpf_attr {
 	FN(copy_from_user_task),	\
 	FN(skb_set_tstamp),		\
 	FN(ima_file_hash),		\
+	FN(kptr_xchg),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 6efe152d4061a83a2c5db6a0e5b58f9345c9742f Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:52 +0530
Subject: bpf: Prevent escaping of kptr loaded from maps

While we can guarantee that even for unreferenced kptr, the object
pointer points to being freed etc. can be handled by the verifier's
exception handling (normal load patching to PROBE_MEM loads), we still
cannot allow the user to pass these pointers to BPF helpers and kfunc,
because the same exception handling won't be done for accesses inside
the kernel. The same is true if a referenced pointer is loaded using
normal load instruction. Since the reference is not guaranteed to be
held while the pointer is used, it must be marked as untrusted.

Hence introduce a new type flag, PTR_UNTRUSTED, which is used to mark
all registers loading unreferenced and referenced kptr from BPF maps,
and ensure they can never escape the BPF program and into the kernel by
way of calling stable/unstable helpers.

In check_ptr_to_btf_access, the !type_may_be_null check to reject type
flags is still correct, as apart from PTR_MAYBE_NULL, only MEM_USER,
MEM_PERCPU, and PTR_UNTRUSTED may be set for PTR_TO_BTF_ID. The first
two are checked inside the function and rejected using a proper error
message, but we still want to allow dereference of untrusted case.

Also, we make sure to inherit PTR_UNTRUSTED when chain of pointers are
walked, so that this flag is never dropped once it has been set on a
PTR_TO_BTF_ID (i.e. trusted to untrusted transition can only be in one
direction).

In convert_ctx_accesses, extend the switch case to consider untrusted
PTR_TO_BTF_ID in addition to normal PTR_TO_BTF_ID for PROBE_MEM
conversion for BPF_LDX.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-5-memxor@gmail.com
---
 include/linux/bpf.h   | 10 +++++++++-
 kernel/bpf/verifier.c | 35 ++++++++++++++++++++++++++++-------
 2 files changed, 37 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 24310837bafc..e13a5cbd4ebb 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -375,7 +375,15 @@ enum bpf_type_flag {
 	/* Indicates that the argument will be released. */
 	OBJ_RELEASE		= BIT(5 + BPF_BASE_TYPE_BITS),
 
-	__BPF_TYPE_LAST_FLAG	= OBJ_RELEASE,
+	/* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark
+	 * unreferenced and referenced kptr loaded from map value using a load
+	 * instruction, so that they can only be dereferenced but not escape the
+	 * BPF program into the kernel (i.e. cannot be passed as arguments to
+	 * kfunc or bpf helpers).
+	 */
+	PTR_UNTRUSTED		= BIT(6 + BPF_BASE_TYPE_BITS),
+
+	__BPF_TYPE_LAST_FLAG	= PTR_UNTRUSTED,
 };
 
 /* Max number of base types. */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c9ee44efed89..955c3125576a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -567,6 +567,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
 		strncpy(prefix, "user_", 32);
 	if (type & MEM_PERCPU)
 		strncpy(prefix, "percpu_", 32);
+	if (type & PTR_UNTRUSTED)
+		strncpy(prefix, "untrusted_", 32);
 
 	snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
 		 prefix, str[base_type(type)], postfix);
@@ -3504,9 +3506,14 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
 			       struct bpf_reg_state *reg, u32 regno)
 {
 	const char *targ_name = kernel_type_name(off_desc->kptr.btf, off_desc->kptr.btf_id);
+	int perm_flags = PTR_MAYBE_NULL;
 	const char *reg_name = "";
 
-	if (base_type(reg->type) != PTR_TO_BTF_ID || type_flag(reg->type) != PTR_MAYBE_NULL)
+	/* Only unreferenced case accepts untrusted pointers */
+	if (off_desc->type == BPF_KPTR_UNREF)
+		perm_flags |= PTR_UNTRUSTED;
+
+	if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags))
 		goto bad_type;
 
 	if (!btf_is_kernel(reg->btf)) {
@@ -3553,7 +3560,12 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
 bad_type:
 	verbose(env, "invalid kptr access, R%d type=%s%s ", regno,
 		reg_type_str(env, reg->type), reg_name);
-	verbose(env, "expected=%s%s\n", reg_type_str(env, PTR_TO_BTF_ID), targ_name);
+	verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name);
+	if (off_desc->type == BPF_KPTR_UNREF)
+		verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED),
+			targ_name);
+	else
+		verbose(env, "\n");
 	return -EINVAL;
 }
 
@@ -3577,9 +3589,11 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
 		return -EACCES;
 	}
 
-	/* We cannot directly access kptr_ref */
-	if (off_desc->type == BPF_KPTR_REF) {
-		verbose(env, "accessing referenced kptr disallowed\n");
+	/* We only allow loading referenced kptr, since it will be marked as
+	 * untrusted, similar to unreferenced kptr.
+	 */
+	if (class != BPF_LDX && off_desc->type == BPF_KPTR_REF) {
+		verbose(env, "store to referenced kptr disallowed\n");
 		return -EACCES;
 	}
 
@@ -3589,7 +3603,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
 		 * value from map as PTR_TO_BTF_ID, with the correct type.
 		 */
 		mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, off_desc->kptr.btf,
-				off_desc->kptr.btf_id, PTR_MAYBE_NULL);
+				off_desc->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED);
 		/* For mark_ptr_or_null_reg */
 		val_reg->id = ++env->id_gen;
 	} else if (class == BPF_STX) {
@@ -4358,6 +4372,12 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	if (ret < 0)
 		return ret;
 
+	/* If this is an untrusted pointer, all pointers formed by walking it
+	 * also inherit the untrusted flag.
+	 */
+	if (type_flag(reg->type) & PTR_UNTRUSTED)
+		flag |= PTR_UNTRUSTED;
+
 	if (atype == BPF_READ && value_regno >= 0)
 		mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag);
 
@@ -13076,7 +13096,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		if (!ctx_access)
 			continue;
 
-		switch (env->insn_aux_data[i + delta].ptr_type) {
+		switch ((int)env->insn_aux_data[i + delta].ptr_type) {
 		case PTR_TO_CTX:
 			if (!ops->convert_ctx_access)
 				continue;
@@ -13093,6 +13113,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			convert_ctx_access = bpf_xdp_sock_convert_ctx_access;
 			break;
 		case PTR_TO_BTF_ID:
+		case PTR_TO_BTF_ID | PTR_UNTRUSTED:
 			if (type == BPF_READ) {
 				insn->code = BPF_LDX | BPF_PROBE_MEM |
 					BPF_SIZE((insn)->code);
-- 
cgit v1.2.3


From 4d7d7f69f4b104b2ddeec6a1e7fcfd2d044ed8c4 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:53 +0530
Subject: bpf: Adapt copy_map_value for multiple offset case

Since now there might be at most 10 offsets that need handling in
copy_map_value, the manual shuffling and special case is no longer going
to work. Hence, let's generalise the copy_map_value function by using
a sorted array of offsets to skip regions that must be avoided while
copying into and out of a map value.

When the map is created, we populate the offset array in struct map,
Then, copy_map_value uses this sorted offset array is used to memcpy
while skipping timer, spin lock, and kptr. The array is allocated as
in most cases none of these special fields would be present in map
value, hence we can save on space for the common case by not embedding
the entire object inside bpf_map struct.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-6-memxor@gmail.com
---
 include/linux/bpf.h  | 56 +++++++++++++++++----------------
 kernel/bpf/syscall.c | 88 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 117 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e13a5cbd4ebb..4e12b27a5de6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -158,6 +158,9 @@ struct bpf_map_ops {
 enum {
 	/* Support at most 8 pointers in a BPF map value */
 	BPF_MAP_VALUE_OFF_MAX = 8,
+	BPF_MAP_OFF_ARR_MAX   = BPF_MAP_VALUE_OFF_MAX +
+				1 + /* for bpf_spin_lock */
+				1,  /* for bpf_timer */
 };
 
 enum bpf_kptr_type {
@@ -179,6 +182,12 @@ struct bpf_map_value_off {
 	struct bpf_map_value_off_desc off[];
 };
 
+struct bpf_map_off_arr {
+	u32 cnt;
+	u32 field_off[BPF_MAP_OFF_ARR_MAX];
+	u8 field_sz[BPF_MAP_OFF_ARR_MAX];
+};
+
 struct bpf_map {
 	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
@@ -207,10 +216,7 @@ struct bpf_map {
 	struct mem_cgroup *memcg;
 #endif
 	char name[BPF_OBJ_NAME_LEN];
-	bool bypass_spec_v1;
-	bool frozen; /* write-once; write-protected by freeze_mutex */
-	/* 6 bytes hole */
-
+	struct bpf_map_off_arr *off_arr;
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
 	 */
@@ -230,6 +236,8 @@ struct bpf_map {
 		bool jited;
 		bool xdp_has_frags;
 	} owner;
+	bool bypass_spec_v1;
+	bool frozen; /* write-once; write-protected by freeze_mutex */
 };
 
 static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -253,37 +261,33 @@ static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
 		memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock));
 	if (unlikely(map_value_has_timer(map)))
 		memset(dst + map->timer_off, 0, sizeof(struct bpf_timer));
+	if (unlikely(map_value_has_kptrs(map))) {
+		struct bpf_map_value_off *tab = map->kptr_off_tab;
+		int i;
+
+		for (i = 0; i < tab->nr_off; i++)
+			*(u64 *)(dst + tab->off[i].offset) = 0;
+	}
 }
 
 /* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */
 static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
 {
-	u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0;
+	u32 curr_off = 0;
+	int i;
 
-	if (unlikely(map_value_has_spin_lock(map))) {
-		s_off = map->spin_lock_off;
-		s_sz = sizeof(struct bpf_spin_lock);
-	}
-	if (unlikely(map_value_has_timer(map))) {
-		t_off = map->timer_off;
-		t_sz = sizeof(struct bpf_timer);
+	if (likely(!map->off_arr)) {
+		memcpy(dst, src, map->value_size);
+		return;
 	}
 
-	if (unlikely(s_sz || t_sz)) {
-		if (s_off < t_off || !s_sz) {
-			swap(s_off, t_off);
-			swap(s_sz, t_sz);
-		}
-		memcpy(dst, src, t_off);
-		memcpy(dst + t_off + t_sz,
-		       src + t_off + t_sz,
-		       s_off - t_off - t_sz);
-		memcpy(dst + s_off + s_sz,
-		       src + s_off + s_sz,
-		       map->value_size - s_off - s_sz);
-	} else {
-		memcpy(dst, src, map->value_size);
+	for (i = 0; i < map->off_arr->cnt; i++) {
+		u32 next_off = map->off_arr->field_off[i];
+
+		memcpy(dst + curr_off, src + curr_off, next_off - curr_off);
+		curr_off += map->off_arr->field_sz[i];
 	}
+	memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off);
 }
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 			   bool lock_src);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 575b09339360..4d419a3effc4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -30,6 +30,7 @@
 #include <linux/pgtable.h>
 #include <linux/bpf_lsm.h>
 #include <linux/poll.h>
+#include <linux/sort.h>
 #include <linux/bpf-netns.h>
 #include <linux/rcupdate_trace.h>
 #include <linux/memcontrol.h>
@@ -551,6 +552,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
 
 	security_bpf_map_free(map);
+	kfree(map->off_arr);
 	bpf_map_free_kptr_off_tab(map);
 	bpf_map_release_memcg(map);
 	/* implementation dependent freeing */
@@ -840,6 +842,84 @@ int map_check_no_btf(const struct bpf_map *map,
 	return -ENOTSUPP;
 }
 
+static int map_off_arr_cmp(const void *_a, const void *_b, const void *priv)
+{
+	const u32 a = *(const u32 *)_a;
+	const u32 b = *(const u32 *)_b;
+
+	if (a < b)
+		return -1;
+	else if (a > b)
+		return 1;
+	return 0;
+}
+
+static void map_off_arr_swap(void *_a, void *_b, int size, const void *priv)
+{
+	struct bpf_map *map = (struct bpf_map *)priv;
+	u32 *off_base = map->off_arr->field_off;
+	u32 *a = _a, *b = _b;
+	u8 *sz_a, *sz_b;
+
+	sz_a = map->off_arr->field_sz + (a - off_base);
+	sz_b = map->off_arr->field_sz + (b - off_base);
+
+	swap(*a, *b);
+	swap(*sz_a, *sz_b);
+}
+
+static int bpf_map_alloc_off_arr(struct bpf_map *map)
+{
+	bool has_spin_lock = map_value_has_spin_lock(map);
+	bool has_timer = map_value_has_timer(map);
+	bool has_kptrs = map_value_has_kptrs(map);
+	struct bpf_map_off_arr *off_arr;
+	u32 i;
+
+	if (!has_spin_lock && !has_timer && !has_kptrs) {
+		map->off_arr = NULL;
+		return 0;
+	}
+
+	off_arr = kmalloc(sizeof(*map->off_arr), GFP_KERNEL | __GFP_NOWARN);
+	if (!off_arr)
+		return -ENOMEM;
+	map->off_arr = off_arr;
+
+	off_arr->cnt = 0;
+	if (has_spin_lock) {
+		i = off_arr->cnt;
+
+		off_arr->field_off[i] = map->spin_lock_off;
+		off_arr->field_sz[i] = sizeof(struct bpf_spin_lock);
+		off_arr->cnt++;
+	}
+	if (has_timer) {
+		i = off_arr->cnt;
+
+		off_arr->field_off[i] = map->timer_off;
+		off_arr->field_sz[i] = sizeof(struct bpf_timer);
+		off_arr->cnt++;
+	}
+	if (has_kptrs) {
+		struct bpf_map_value_off *tab = map->kptr_off_tab;
+		u32 *off = &off_arr->field_off[off_arr->cnt];
+		u8 *sz = &off_arr->field_sz[off_arr->cnt];
+
+		for (i = 0; i < tab->nr_off; i++) {
+			*off++ = tab->off[i].offset;
+			*sz++ = sizeof(u64);
+		}
+		off_arr->cnt += tab->nr_off;
+	}
+
+	if (off_arr->cnt == 1)
+		return 0;
+	sort_r(off_arr->field_off, off_arr->cnt, sizeof(off_arr->field_off[0]),
+	       map_off_arr_cmp, map_off_arr_swap, map);
+	return 0;
+}
+
 static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 			 u32 btf_key_id, u32 btf_value_id)
 {
@@ -1009,10 +1089,14 @@ static int map_create(union bpf_attr *attr)
 			attr->btf_vmlinux_value_type_id;
 	}
 
-	err = security_bpf_map_alloc(map);
+	err = bpf_map_alloc_off_arr(map);
 	if (err)
 		goto free_map;
 
+	err = security_bpf_map_alloc(map);
+	if (err)
+		goto free_map_off_arr;
+
 	err = bpf_map_alloc_id(map);
 	if (err)
 		goto free_map_sec;
@@ -1035,6 +1119,8 @@ static int map_create(union bpf_attr *attr)
 
 free_map_sec:
 	security_bpf_map_free(map);
+free_map_off_arr:
+	kfree(map->off_arr);
 free_map:
 	btf_put(map->btf);
 	map->ops->map_free(map);
-- 
cgit v1.2.3


From 5ce937d613a423ca3102f53d9f3daf4210c1b6e2 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:54 +0530
Subject: bpf: Populate pairs of btf_id and destructor kfunc in btf

To support storing referenced PTR_TO_BTF_ID in maps, we require
associating a specific BTF ID with a 'destructor' kfunc. This is because
we need to release a live referenced pointer at a certain offset in map
value from the map destruction path, otherwise we end up leaking
resources.

Hence, introduce support for passing an array of btf_id, kfunc_btf_id
pairs that denote a BTF ID and its associated release function. Then,
add an accessor 'btf_find_dtor_kfunc' which can be used to look up the
destructor kfunc of a certain BTF ID. If found, we can use it to free
the object from the map free path.

The registration of these pairs also serve as a whitelist of structures
which are allowed as referenced PTR_TO_BTF_ID in a BPF map, because
without finding the destructor kfunc, we will bail and return an error.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-7-memxor@gmail.com
---
 include/linux/btf.h |  17 +++++++++
 kernel/bpf/btf.c    | 108 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 125 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 19c297f9a52f..fea424681d66 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -40,6 +40,11 @@ struct btf_kfunc_id_set {
 	};
 };
 
+struct btf_id_dtor_kfunc {
+	u32 btf_id;
+	u32 kfunc_btf_id;
+};
+
 extern const struct file_operations btf_fops;
 
 void btf_get(struct btf *btf);
@@ -346,6 +351,9 @@ bool btf_kfunc_id_set_contains(const struct btf *btf,
 			       enum btf_kfunc_type type, u32 kfunc_btf_id);
 int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
 			      const struct btf_kfunc_id_set *s);
+s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
+int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
+				struct module *owner);
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
@@ -369,6 +377,15 @@ static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
 {
 	return 0;
 }
+static inline s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id)
+{
+	return -ENOENT;
+}
+static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors,
+					      u32 add_cnt, struct module *owner)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4138c51728dd..a0b1665a4a48 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -207,12 +207,18 @@ enum btf_kfunc_hook {
 
 enum {
 	BTF_KFUNC_SET_MAX_CNT = 32,
+	BTF_DTOR_KFUNC_MAX_CNT = 256,
 };
 
 struct btf_kfunc_set_tab {
 	struct btf_id_set *sets[BTF_KFUNC_HOOK_MAX][BTF_KFUNC_TYPE_MAX];
 };
 
+struct btf_id_dtor_kfunc_tab {
+	u32 cnt;
+	struct btf_id_dtor_kfunc dtors[];
+};
+
 struct btf {
 	void *data;
 	struct btf_type **types;
@@ -228,6 +234,7 @@ struct btf {
 	u32 id;
 	struct rcu_head rcu;
 	struct btf_kfunc_set_tab *kfunc_set_tab;
+	struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab;
 
 	/* split BTF support */
 	struct btf *base_btf;
@@ -1616,8 +1623,19 @@ free_tab:
 	btf->kfunc_set_tab = NULL;
 }
 
+static void btf_free_dtor_kfunc_tab(struct btf *btf)
+{
+	struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab;
+
+	if (!tab)
+		return;
+	kfree(tab);
+	btf->dtor_kfunc_tab = NULL;
+}
+
 static void btf_free(struct btf *btf)
 {
+	btf_free_dtor_kfunc_tab(btf);
 	btf_free_kfunc_set_tab(btf);
 	kvfree(btf->types);
 	kvfree(btf->resolved_sizes);
@@ -7076,6 +7094,96 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
 }
 EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set);
 
+s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id)
+{
+	struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab;
+	struct btf_id_dtor_kfunc *dtor;
+
+	if (!tab)
+		return -ENOENT;
+	/* Even though the size of tab->dtors[0] is > sizeof(u32), we only need
+	 * to compare the first u32 with btf_id, so we can reuse btf_id_cmp_func.
+	 */
+	BUILD_BUG_ON(offsetof(struct btf_id_dtor_kfunc, btf_id) != 0);
+	dtor = bsearch(&btf_id, tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func);
+	if (!dtor)
+		return -ENOENT;
+	return dtor->kfunc_btf_id;
+}
+
+/* This function must be invoked only from initcalls/module init functions */
+int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
+				struct module *owner)
+{
+	struct btf_id_dtor_kfunc_tab *tab;
+	struct btf *btf;
+	u32 tab_cnt;
+	int ret;
+
+	btf = btf_get_module_btf(owner);
+	if (!btf) {
+		if (!owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
+			pr_err("missing vmlinux BTF, cannot register dtor kfuncs\n");
+			return -ENOENT;
+		}
+		if (owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) {
+			pr_err("missing module BTF, cannot register dtor kfuncs\n");
+			return -ENOENT;
+		}
+		return 0;
+	}
+	if (IS_ERR(btf))
+		return PTR_ERR(btf);
+
+	if (add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) {
+		pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT);
+		ret = -E2BIG;
+		goto end;
+	}
+
+	tab = btf->dtor_kfunc_tab;
+	/* Only one call allowed for modules */
+	if (WARN_ON_ONCE(tab && btf_is_module(btf))) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	tab_cnt = tab ? tab->cnt : 0;
+	if (tab_cnt > U32_MAX - add_cnt) {
+		ret = -EOVERFLOW;
+		goto end;
+	}
+	if (tab_cnt + add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) {
+		pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT);
+		ret = -E2BIG;
+		goto end;
+	}
+
+	tab = krealloc(btf->dtor_kfunc_tab,
+		       offsetof(struct btf_id_dtor_kfunc_tab, dtors[tab_cnt + add_cnt]),
+		       GFP_KERNEL | __GFP_NOWARN);
+	if (!tab) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	if (!btf->dtor_kfunc_tab)
+		tab->cnt = 0;
+	btf->dtor_kfunc_tab = tab;
+
+	memcpy(tab->dtors + tab->cnt, dtors, add_cnt * sizeof(tab->dtors[0]));
+	tab->cnt += add_cnt;
+
+	sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL);
+
+	return 0;
+end:
+	btf_free_dtor_kfunc_tab(btf);
+	btf_put(btf);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_btf_id_dtor_kfuncs);
+
 #define MAX_TYPES_ARE_COMPAT_DEPTH 2
 
 static
-- 
cgit v1.2.3


From 14a324f6a67ef6a53e04362a70160a47eb8afffa Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:55 +0530
Subject: bpf: Wire up freeing of referenced kptr

A destructor kfunc can be defined as void func(type *), where type may
be void or any other pointer type as per convenience.

In this patch, we ensure that the type is sane and capture the function
pointer into off_desc of ptr_off_tab for the specific pointer offset,
with the invariant that the dtor pointer is always set when 'kptr_ref'
tag is applied to the pointer's pointee type, which is indicated by the
flag BPF_MAP_VALUE_OFF_F_REF.

Note that only BTF IDs whose destructor kfunc is registered, thus become
the allowed BTF IDs for embedding as referenced kptr. Hence it serves
the purpose of finding dtor kfunc BTF ID, as well acting as a check
against the whitelist of allowed BTF IDs for this purpose.

Finally, wire up the actual freeing of the referenced pointer if any at
all available offsets, so that no references are leaked after the BPF
map goes away and the BPF program previously moved the ownership a
referenced pointer into it.

The behavior is similar to BPF timers, where bpf_map_{update,delete}_elem
will free any existing referenced kptr. The same case is with LRU map's
bpf_lru_push_free/htab_lru_push_free functions, which are extended to
reset unreferenced and free referenced kptr.

Note that unlike BPF timers, kptr is not reset or freed when map uref
drops to zero.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-8-memxor@gmail.com
---
 include/linux/bpf.h   |  4 +++
 include/linux/btf.h   |  2 ++
 kernel/bpf/arraymap.c | 18 +++++++---
 kernel/bpf/btf.c      | 98 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 kernel/bpf/hashtab.c  | 64 ++++++++++++++++++++++++---------
 kernel/bpf/syscall.c  | 49 +++++++++++++++++++++++---
 6 files changed, 210 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4e12b27a5de6..6141564c76c8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
 #include <linux/bpfptr.h>
+#include <linux/btf.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -173,6 +174,8 @@ struct bpf_map_value_off_desc {
 	enum bpf_kptr_type type;
 	struct {
 		struct btf *btf;
+		struct module *module;
+		btf_dtor_kfunc_t dtor;
 		u32 btf_id;
 	} kptr;
 };
@@ -1447,6 +1450,7 @@ struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u3
 void bpf_map_free_kptr_off_tab(struct bpf_map *map);
 struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map);
 bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b);
+void bpf_map_free_kptrs(struct bpf_map *map, void *map_value);
 
 struct bpf_map *bpf_map_get(u32 ufd);
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
diff --git a/include/linux/btf.h b/include/linux/btf.h
index fea424681d66..f70625dd5bb4 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -45,6 +45,8 @@ struct btf_id_dtor_kfunc {
 	u32 kfunc_btf_id;
 };
 
+typedef void (*btf_dtor_kfunc_t)(void *);
+
 extern const struct file_operations btf_fops;
 
 void btf_get(struct btf *btf);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 7f145aefbff8..c3de63ce574e 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -287,10 +287,12 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key
 	return 0;
 }
 
-static void check_and_free_timer_in_array(struct bpf_array *arr, void *val)
+static void check_and_free_fields(struct bpf_array *arr, void *val)
 {
-	if (unlikely(map_value_has_timer(&arr->map)))
+	if (map_value_has_timer(&arr->map))
 		bpf_timer_cancel_and_free(val + arr->map.timer_off);
+	if (map_value_has_kptrs(&arr->map))
+		bpf_map_free_kptrs(&arr->map, val);
 }
 
 /* Called from syscall or from eBPF program */
@@ -327,7 +329,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 			copy_map_value_locked(map, val, value, false);
 		else
 			copy_map_value(map, val, value);
-		check_and_free_timer_in_array(array, val);
+		check_and_free_fields(array, val);
 	}
 	return 0;
 }
@@ -386,7 +388,8 @@ static void array_map_free_timers(struct bpf_map *map)
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
-	if (likely(!map_value_has_timer(map)))
+	/* We don't reset or free kptr on uref dropping to zero. */
+	if (!map_value_has_timer(map))
 		return;
 
 	for (i = 0; i < array->map.max_entries; i++)
@@ -398,6 +401,13 @@ static void array_map_free_timers(struct bpf_map *map)
 static void array_map_free(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	int i;
+
+	if (map_value_has_kptrs(map)) {
+		for (i = 0; i < array->map.max_entries; i++)
+			bpf_map_free_kptrs(map, array->value + array->elem_size * i);
+		bpf_map_free_kptr_off_tab(map);
+	}
 
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		bpf_array_free_percpu(array);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a0b1665a4a48..1f2012fd89fb 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3416,6 +3416,7 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
 	struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX];
 	struct bpf_map_value_off *tab;
 	struct btf *kernel_btf = NULL;
+	struct module *mod = NULL;
 	int ret, i, nr_off;
 
 	ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr));
@@ -3444,16 +3445,69 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
 			goto end;
 		}
 
+		/* Find and stash the function pointer for the destruction function that
+		 * needs to be eventually invoked from the map free path.
+		 */
+		if (info_arr[i].type == BPF_KPTR_REF) {
+			const struct btf_type *dtor_func;
+			const char *dtor_func_name;
+			unsigned long addr;
+			s32 dtor_btf_id;
+
+			/* This call also serves as a whitelist of allowed objects that
+			 * can be used as a referenced pointer and be stored in a map at
+			 * the same time.
+			 */
+			dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id);
+			if (dtor_btf_id < 0) {
+				ret = dtor_btf_id;
+				goto end_btf;
+			}
+
+			dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id);
+			if (!dtor_func) {
+				ret = -ENOENT;
+				goto end_btf;
+			}
+
+			if (btf_is_module(kernel_btf)) {
+				mod = btf_try_get_module(kernel_btf);
+				if (!mod) {
+					ret = -ENXIO;
+					goto end_btf;
+				}
+			}
+
+			/* We already verified dtor_func to be btf_type_is_func
+			 * in register_btf_id_dtor_kfuncs.
+			 */
+			dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off);
+			addr = kallsyms_lookup_name(dtor_func_name);
+			if (!addr) {
+				ret = -EINVAL;
+				goto end_mod;
+			}
+			tab->off[i].kptr.dtor = (void *)addr;
+		}
+
 		tab->off[i].offset = info_arr[i].off;
 		tab->off[i].type = info_arr[i].type;
 		tab->off[i].kptr.btf_id = id;
 		tab->off[i].kptr.btf = kernel_btf;
+		tab->off[i].kptr.module = mod;
 	}
 	tab->nr_off = nr_off;
 	return tab;
+end_mod:
+	module_put(mod);
+end_btf:
+	btf_put(kernel_btf);
 end:
-	while (i--)
+	while (i--) {
 		btf_put(tab->off[i].kptr.btf);
+		if (tab->off[i].kptr.module)
+			module_put(tab->off[i].kptr.module);
+	}
 	kfree(tab);
 	return ERR_PTR(ret);
 }
@@ -7111,6 +7165,43 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id)
 	return dtor->kfunc_btf_id;
 }
 
+static int btf_check_dtor_kfuncs(struct btf *btf, const struct btf_id_dtor_kfunc *dtors, u32 cnt)
+{
+	const struct btf_type *dtor_func, *dtor_func_proto, *t;
+	const struct btf_param *args;
+	s32 dtor_btf_id;
+	u32 nr_args, i;
+
+	for (i = 0; i < cnt; i++) {
+		dtor_btf_id = dtors[i].kfunc_btf_id;
+
+		dtor_func = btf_type_by_id(btf, dtor_btf_id);
+		if (!dtor_func || !btf_type_is_func(dtor_func))
+			return -EINVAL;
+
+		dtor_func_proto = btf_type_by_id(btf, dtor_func->type);
+		if (!dtor_func_proto || !btf_type_is_func_proto(dtor_func_proto))
+			return -EINVAL;
+
+		/* Make sure the prototype of the destructor kfunc is 'void func(type *)' */
+		t = btf_type_by_id(btf, dtor_func_proto->type);
+		if (!t || !btf_type_is_void(t))
+			return -EINVAL;
+
+		nr_args = btf_type_vlen(dtor_func_proto);
+		if (nr_args != 1)
+			return -EINVAL;
+		args = btf_params(dtor_func_proto);
+		t = btf_type_by_id(btf, args[0].type);
+		/* Allow any pointer type, as width on targets Linux supports
+		 * will be same for all pointer types (i.e. sizeof(void *))
+		 */
+		if (!t || !btf_type_is_ptr(t))
+			return -EINVAL;
+	}
+	return 0;
+}
+
 /* This function must be invoked only from initcalls/module init functions */
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner)
@@ -7141,6 +7232,11 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c
 		goto end;
 	}
 
+	/* Ensure that the prototype of dtor kfuncs being registered is sane */
+	ret = btf_check_dtor_kfuncs(btf, dtors, add_cnt);
+	if (ret < 0)
+		goto end;
+
 	tab = btf->dtor_kfunc_tab;
 	/* Only one call allowed for modules */
 	if (WARN_ON_ONCE(tab && btf_is_module(btf))) {
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index c68fbebc8c00..7351e61bd683 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -238,7 +238,7 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab)
 	u32 num_entries = htab->map.max_entries;
 	int i;
 
-	if (likely(!map_value_has_timer(&htab->map)))
+	if (!map_value_has_timer(&htab->map))
 		return;
 	if (htab_has_extra_elems(htab))
 		num_entries += num_possible_cpus();
@@ -254,6 +254,25 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab)
 	}
 }
 
+static void htab_free_prealloced_kptrs(struct bpf_htab *htab)
+{
+	u32 num_entries = htab->map.max_entries;
+	int i;
+
+	if (!map_value_has_kptrs(&htab->map))
+		return;
+	if (htab_has_extra_elems(htab))
+		num_entries += num_possible_cpus();
+
+	for (i = 0; i < num_entries; i++) {
+		struct htab_elem *elem;
+
+		elem = get_htab_elem(htab, i);
+		bpf_map_free_kptrs(&htab->map, elem->key + round_up(htab->map.key_size, 8));
+		cond_resched();
+	}
+}
+
 static void htab_free_elems(struct bpf_htab *htab)
 {
 	int i;
@@ -725,12 +744,15 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map,
 	return insn - insn_buf;
 }
 
-static void check_and_free_timer(struct bpf_htab *htab, struct htab_elem *elem)
+static void check_and_free_fields(struct bpf_htab *htab,
+				  struct htab_elem *elem)
 {
-	if (unlikely(map_value_has_timer(&htab->map)))
-		bpf_timer_cancel_and_free(elem->key +
-					  round_up(htab->map.key_size, 8) +
-					  htab->map.timer_off);
+	void *map_value = elem->key + round_up(htab->map.key_size, 8);
+
+	if (map_value_has_timer(&htab->map))
+		bpf_timer_cancel_and_free(map_value + htab->map.timer_off);
+	if (map_value_has_kptrs(&htab->map))
+		bpf_map_free_kptrs(&htab->map, map_value);
 }
 
 /* It is called from the bpf_lru_list when the LRU needs to delete
@@ -757,7 +779,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l == tgt_l) {
 			hlist_nulls_del_rcu(&l->hash_node);
-			check_and_free_timer(htab, l);
+			check_and_free_fields(htab, l);
 			break;
 		}
 
@@ -829,7 +851,7 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
 {
 	if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
 		free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
-	check_and_free_timer(htab, l);
+	check_and_free_fields(htab, l);
 	kfree(l);
 }
 
@@ -857,7 +879,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 	htab_put_fd_value(htab, l);
 
 	if (htab_is_prealloc(htab)) {
-		check_and_free_timer(htab, l);
+		check_and_free_fields(htab, l);
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
 		atomic_dec(&htab->count);
@@ -1104,7 +1126,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		if (!htab_is_prealloc(htab))
 			free_htab_elem(htab, l_old);
 		else
-			check_and_free_timer(htab, l_old);
+			check_and_free_fields(htab, l_old);
 	}
 	ret = 0;
 err:
@@ -1114,7 +1136,7 @@ err:
 
 static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem)
 {
-	check_and_free_timer(htab, elem);
+	check_and_free_fields(htab, elem);
 	bpf_lru_push_free(&htab->lru, &elem->lru_node);
 }
 
@@ -1419,8 +1441,14 @@ static void htab_free_malloced_timers(struct bpf_htab *htab)
 		struct hlist_nulls_node *n;
 		struct htab_elem *l;
 
-		hlist_nulls_for_each_entry(l, n, head, hash_node)
-			check_and_free_timer(htab, l);
+		hlist_nulls_for_each_entry(l, n, head, hash_node) {
+			/* We don't reset or free kptr on uref dropping to zero,
+			 * hence just free timer.
+			 */
+			bpf_timer_cancel_and_free(l->key +
+						  round_up(htab->map.key_size, 8) +
+						  htab->map.timer_off);
+		}
 		cond_resched_rcu();
 	}
 	rcu_read_unlock();
@@ -1430,7 +1458,8 @@ static void htab_map_free_timers(struct bpf_map *map)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 
-	if (likely(!map_value_has_timer(&htab->map)))
+	/* We don't reset or free kptr on uref dropping to zero. */
+	if (!map_value_has_timer(&htab->map))
 		return;
 	if (!htab_is_prealloc(htab))
 		htab_free_malloced_timers(htab);
@@ -1453,11 +1482,14 @@ static void htab_map_free(struct bpf_map *map)
 	 * not have executed. Wait for them.
 	 */
 	rcu_barrier();
-	if (!htab_is_prealloc(htab))
+	if (!htab_is_prealloc(htab)) {
 		delete_all_elements(htab);
-	else
+	} else {
+		htab_free_prealloced_kptrs(htab);
 		prealloc_destroy(htab);
+	}
 
+	bpf_map_free_kptr_off_tab(map);
 	free_percpu(htab->extra_elems);
 	bpf_map_area_free(htab->buckets);
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4d419a3effc4..e0aead17dff4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -507,8 +507,11 @@ void bpf_map_free_kptr_off_tab(struct bpf_map *map)
 
 	if (!map_value_has_kptrs(map))
 		return;
-	for (i = 0; i < tab->nr_off; i++)
+	for (i = 0; i < tab->nr_off; i++) {
+		if (tab->off[i].kptr.module)
+			module_put(tab->off[i].kptr.module);
 		btf_put(tab->off[i].kptr.btf);
+	}
 	kfree(tab);
 	map->kptr_off_tab = NULL;
 }
@@ -525,8 +528,18 @@ struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map)
 	if (!new_tab)
 		return ERR_PTR(-ENOMEM);
 	/* Do a deep copy of the kptr_off_tab */
-	for (i = 0; i < tab->nr_off; i++)
+	for (i = 0; i < tab->nr_off; i++) {
 		btf_get(tab->off[i].kptr.btf);
+		if (tab->off[i].kptr.module && !try_module_get(tab->off[i].kptr.module)) {
+			while (i--) {
+				if (tab->off[i].kptr.module)
+					module_put(tab->off[i].kptr.module);
+				btf_put(tab->off[i].kptr.btf);
+			}
+			kfree(new_tab);
+			return ERR_PTR(-ENXIO);
+		}
+	}
 	return new_tab;
 }
 
@@ -546,6 +559,33 @@ bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_ma
 	return !memcmp(tab_a, tab_b, size);
 }
 
+/* Caller must ensure map_value_has_kptrs is true. Note that this function can
+ * be called on a map value while the map_value is visible to BPF programs, as
+ * it ensures the correct synchronization, and we already enforce the same using
+ * the bpf_kptr_xchg helper on the BPF program side for referenced kptrs.
+ */
+void bpf_map_free_kptrs(struct bpf_map *map, void *map_value)
+{
+	struct bpf_map_value_off *tab = map->kptr_off_tab;
+	unsigned long *btf_id_ptr;
+	int i;
+
+	for (i = 0; i < tab->nr_off; i++) {
+		struct bpf_map_value_off_desc *off_desc = &tab->off[i];
+		unsigned long old_ptr;
+
+		btf_id_ptr = map_value + off_desc->offset;
+		if (off_desc->type == BPF_KPTR_UNREF) {
+			u64 *p = (u64 *)btf_id_ptr;
+
+			WRITE_ONCE(p, 0);
+			continue;
+		}
+		old_ptr = xchg(btf_id_ptr, 0);
+		off_desc->kptr.dtor((void *)old_ptr);
+	}
+}
+
 /* called from workqueue */
 static void bpf_map_free_deferred(struct work_struct *work)
 {
@@ -553,9 +593,10 @@ static void bpf_map_free_deferred(struct work_struct *work)
 
 	security_bpf_map_free(map);
 	kfree(map->off_arr);
-	bpf_map_free_kptr_off_tab(map);
 	bpf_map_release_memcg(map);
-	/* implementation dependent freeing */
+	/* implementation dependent freeing, map_free callback also does
+	 * bpf_map_free_kptr_off_tab, if needed.
+	 */
 	map->ops->map_free(map);
 }
 
-- 
cgit v1.2.3


From a1ef195996526da45bbc9710849254023df75aea Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:56 +0530
Subject: bpf: Teach verifier about kptr_get kfunc helpers

We introduce a new style of kfunc helpers, namely *_kptr_get, where they
take pointer to the map value which points to a referenced kernel
pointer contained in the map. Since this is referenced, only
bpf_kptr_xchg from BPF side and xchg from kernel side is allowed to
change the current value, and each pointer that resides in that location
would be referenced, and RCU protected (this must be kept in mind while
adding kernel types embeddable as reference kptr in BPF maps).

This means that if do the load of the pointer value in an RCU read
section, and find a live pointer, then as long as we hold RCU read lock,
it won't be freed by a parallel xchg + release operation. This allows us
to implement a safe refcount increment scheme. Hence, enforce that first
argument of all such kfunc is a proper PTR_TO_MAP_VALUE pointing at the
right offset to referenced pointer.

For the rest of the arguments, they are subjected to typical kfunc
argument checks, hence allowing some flexibility in passing more intent
into how the reference should be taken.

For instance, in case of struct nf_conn, it is not freed until RCU grace
period ends, but can still be reused for another tuple once refcount has
dropped to zero. Hence, a bpf_ct_kptr_get helper not only needs to call
refcount_inc_not_zero, but also do a tuple match after incrementing the
reference, and when it fails to match it, put the reference again and
return NULL.

This can be implemented easily if we allow passing additional parameters
to the bpf_ct_kptr_get kfunc, like a struct bpf_sock_tuple * and a
tuple__sz pair.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-9-memxor@gmail.com
---
 include/linux/btf.h |  2 ++
 kernel/bpf/btf.c    | 58 ++++++++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 55 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index f70625dd5bb4..2611cea2c2b6 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -17,6 +17,7 @@ enum btf_kfunc_type {
 	BTF_KFUNC_TYPE_ACQUIRE,
 	BTF_KFUNC_TYPE_RELEASE,
 	BTF_KFUNC_TYPE_RET_NULL,
+	BTF_KFUNC_TYPE_KPTR_ACQUIRE,
 	BTF_KFUNC_TYPE_MAX,
 };
 
@@ -35,6 +36,7 @@ struct btf_kfunc_id_set {
 			struct btf_id_set *acquire_set;
 			struct btf_id_set *release_set;
 			struct btf_id_set *ret_null_set;
+			struct btf_id_set *kptr_acquire_set;
 		};
 		struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX];
 	};
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 1f2012fd89fb..494437fb40b7 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6089,11 +6089,11 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 	struct bpf_verifier_log *log = &env->log;
 	u32 i, nargs, ref_id, ref_obj_id = 0;
 	bool is_kfunc = btf_is_kernel(btf);
+	bool rel = false, kptr_get = false;
 	const char *func_name, *ref_tname;
 	const struct btf_type *t, *ref_t;
 	const struct btf_param *args;
 	int ref_regno = 0, ret;
-	bool rel = false;
 
 	t = btf_type_by_id(btf, func_id);
 	if (!t || !btf_type_is_func(t)) {
@@ -6119,10 +6119,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* Only kfunc can be release func */
-	if (is_kfunc)
+	if (is_kfunc) {
+		/* Only kfunc can be release func */
 		rel = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog),
 						BTF_KFUNC_TYPE_RELEASE, func_id);
+		kptr_get = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog),
+						     BTF_KFUNC_TYPE_KPTR_ACQUIRE, func_id);
+	}
+
 	/* check that BTF function arguments match actual types that the
 	 * verifier sees.
 	 */
@@ -6154,8 +6158,52 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 		if (ret < 0)
 			return ret;
 
-		if (btf_get_prog_ctx_type(log, btf, t,
-					  env->prog->type, i)) {
+		/* kptr_get is only true for kfunc */
+		if (i == 0 && kptr_get) {
+			struct bpf_map_value_off_desc *off_desc;
+
+			if (reg->type != PTR_TO_MAP_VALUE) {
+				bpf_log(log, "arg#0 expected pointer to map value\n");
+				return -EINVAL;
+			}
+
+			/* check_func_arg_reg_off allows var_off for
+			 * PTR_TO_MAP_VALUE, but we need fixed offset to find
+			 * off_desc.
+			 */
+			if (!tnum_is_const(reg->var_off)) {
+				bpf_log(log, "arg#0 must have constant offset\n");
+				return -EINVAL;
+			}
+
+			off_desc = bpf_map_kptr_off_contains(reg->map_ptr, reg->off + reg->var_off.value);
+			if (!off_desc || off_desc->type != BPF_KPTR_REF) {
+				bpf_log(log, "arg#0 no referenced kptr at map value offset=%llu\n",
+					reg->off + reg->var_off.value);
+				return -EINVAL;
+			}
+
+			if (!btf_type_is_ptr(ref_t)) {
+				bpf_log(log, "arg#0 BTF type must be a double pointer\n");
+				return -EINVAL;
+			}
+
+			ref_t = btf_type_skip_modifiers(btf, ref_t->type, &ref_id);
+			ref_tname = btf_name_by_offset(btf, ref_t->name_off);
+
+			if (!btf_type_is_struct(ref_t)) {
+				bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n",
+					func_name, i, btf_type_str(ref_t), ref_tname);
+				return -EINVAL;
+			}
+			if (!btf_struct_ids_match(log, btf, ref_id, 0, off_desc->kptr.btf,
+						  off_desc->kptr.btf_id)) {
+				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n",
+					func_name, i, btf_type_str(ref_t), ref_tname);
+				return -EINVAL;
+			}
+			/* rest of the arguments can be anything, like normal kfunc */
+		} else if (btf_get_prog_ctx_type(log, btf, t, env->prog->type, i)) {
 			/* If function expects ctx type in BTF check that caller
 			 * is passing PTR_TO_CTX.
 			 */
-- 
cgit v1.2.3


From 2ab3b3808eb17f729edfd69e061667ca0a427195 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 25 Apr 2022 03:18:57 +0530
Subject: bpf: Make BTF type match stricter for release arguments

The current of behavior of btf_struct_ids_match for release arguments is
that when type match fails, it retries with first member type again
(recursively). Since the offset is already 0, this is akin to just
casting the pointer in normal C, since if type matches it was just
embedded inside parent sturct as an object. However, we want to reject
cases for release function type matching, be it kfunc or BPF helpers.

An example is the following:

struct foo {
	struct bar b;
};

struct foo *v = acq_foo();
rel_bar(&v->b); // btf_struct_ids_match fails btf_types_are_same, then
		// retries with first member type and succeeds, while
		// it should fail.

Hence, don't walk the struct and only rely on btf_types_are_same for
strict mode. All users of strict mode must be dealing with zero offset
anyway, since otherwise they would want the struct to be walked.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-10-memxor@gmail.com
---
 include/linux/bpf.h   |  3 ++-
 kernel/bpf/btf.c      | 14 ++++++++++----
 kernel/bpf/verifier.c | 18 +++++++++++++++---
 3 files changed, 27 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 6141564c76c8..0af5793ba417 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1748,7 +1748,8 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf,
 		      u32 *next_btf_id, enum bpf_type_flag *flag);
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
 			  const struct btf *btf, u32 id, int off,
-			  const struct btf *need_btf, u32 need_type_id);
+			  const struct btf *need_btf, u32 need_type_id,
+			  bool strict);
 
 int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf *btf,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 494437fb40b7..4cfaf5eebecd 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5746,7 +5746,8 @@ static bool btf_types_are_same(const struct btf *btf1, u32 id1,
 
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
 			  const struct btf *btf, u32 id, int off,
-			  const struct btf *need_btf, u32 need_type_id)
+			  const struct btf *need_btf, u32 need_type_id,
+			  bool strict)
 {
 	const struct btf_type *type;
 	enum bpf_type_flag flag;
@@ -5755,7 +5756,12 @@ bool btf_struct_ids_match(struct bpf_verifier_log *log,
 	/* Are we already done? */
 	if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id))
 		return true;
-
+	/* In case of strict type match, we do not walk struct, the top level
+	 * type match must succeed. When strict is true, off should have already
+	 * been 0.
+	 */
+	if (strict)
+		return false;
 again:
 	type = btf_type_by_id(btf, id);
 	if (!type)
@@ -6197,7 +6203,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 				return -EINVAL;
 			}
 			if (!btf_struct_ids_match(log, btf, ref_id, 0, off_desc->kptr.btf,
-						  off_desc->kptr.btf_id)) {
+						  off_desc->kptr.btf_id, true)) {
 				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n",
 					func_name, i, btf_type_str(ref_t), ref_tname);
 				return -EINVAL;
@@ -6250,7 +6256,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			reg_ref_tname = btf_name_by_offset(reg_btf,
 							   reg_ref_t->name_off);
 			if (!btf_struct_ids_match(log, reg_btf, reg_ref_id,
-						  reg->off, btf, ref_id)) {
+						  reg->off, btf, ref_id, rel && reg->ref_obj_id)) {
 				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n",
 					func_name, i,
 					btf_type_str(ref_t), ref_tname,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 955c3125576a..813f6ee80419 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3551,10 +3551,14 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
 	 *                    // to match type
 	 *
 	 * In the kptr_ref case, check_func_arg_reg_off already ensures reg->off
-	 * is zero.
+	 * is zero. We must also ensure that btf_struct_ids_match does not walk
+	 * the struct to match type against first member of struct, i.e. reject
+	 * second case from above. Hence, when type is BPF_KPTR_REF, we set
+	 * strict mode to true for type match.
 	 */
 	if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
-				  off_desc->kptr.btf, off_desc->kptr.btf_id))
+				  off_desc->kptr.btf, off_desc->kptr.btf_id,
+				  off_desc->type == BPF_KPTR_REF))
 		goto bad_type;
 	return 0;
 bad_type:
@@ -5593,6 +5597,13 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 
 found:
 	if (reg->type == PTR_TO_BTF_ID) {
+		/* For bpf_sk_release, it needs to match against first member
+		 * 'struct sock_common', hence make an exception for it. This
+		 * allows bpf_sk_release to work for multiple socket types.
+		 */
+		bool strict_type_match = arg_type_is_release(arg_type) &&
+					 meta->func_id != BPF_FUNC_sk_release;
+
 		if (!arg_btf_id) {
 			if (!compatible->btf_id) {
 				verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
@@ -5605,7 +5616,8 @@ found:
 			if (map_kptr_match_type(env, meta->kptr_off_desc, reg, regno))
 				return -EACCES;
 		} else if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
-						 btf_vmlinux, *arg_btf_id)) {
+						 btf_vmlinux, *arg_btf_id,
+						 strict_type_match)) {
 			verbose(env, "R%d is of type %s but %s is expected\n",
 				regno, kernel_type_name(reg->btf, reg->btf_id),
 				kernel_type_name(btf_vmlinux, *arg_btf_id));
-- 
cgit v1.2.3


From 66eb6df79aefd6b3f7d2e749da7104e90cedc0ff Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Mon, 25 Apr 2022 09:16:16 -0500
Subject: tee: remove tee_shm_va2pa() and tee_shm_pa2va()

We should not need to index into SHMs based on absolute VA/PA.
These functions are not used and this kind of usage should not be
encouraged anyway. Remove these functions.

Signed-off-by: Andrew Davis <afd@ti.com>
Reviewed-by: Sumit Garg <sumit.garg@linaro.org>
Signed-off-by: Jens Wiklander <jens.wiklander@linaro.org>
---
 drivers/tee/tee_shm.c   | 50 -------------------------------------------------
 include/linux/tee_drv.h | 18 ------------------
 2 files changed, 68 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index f31e29e8f1ca..b0c6d553d3a7 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -414,56 +414,6 @@ void tee_shm_free(struct tee_shm *shm)
 }
 EXPORT_SYMBOL_GPL(tee_shm_free);
 
-/**
- * tee_shm_va2pa() - Get physical address of a virtual address
- * @shm:	Shared memory handle
- * @va:		Virtual address to tranlsate
- * @pa:		Returned physical address
- * @returns 0 on success and < 0 on failure
- */
-int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa)
-{
-	if (!shm->kaddr)
-		return -EINVAL;
-	/* Check that we're in the range of the shm */
-	if ((char *)va < (char *)shm->kaddr)
-		return -EINVAL;
-	if ((char *)va >= ((char *)shm->kaddr + shm->size))
-		return -EINVAL;
-
-	return tee_shm_get_pa(
-			shm, (unsigned long)va - (unsigned long)shm->kaddr, pa);
-}
-EXPORT_SYMBOL_GPL(tee_shm_va2pa);
-
-/**
- * tee_shm_pa2va() - Get virtual address of a physical address
- * @shm:	Shared memory handle
- * @pa:		Physical address to tranlsate
- * @va:		Returned virtual address
- * @returns 0 on success and < 0 on failure
- */
-int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va)
-{
-	if (!shm->kaddr)
-		return -EINVAL;
-	/* Check that we're in the range of the shm */
-	if (pa < shm->paddr)
-		return -EINVAL;
-	if (pa >= (shm->paddr + shm->size))
-		return -EINVAL;
-
-	if (va) {
-		void *v = tee_shm_get_va(shm, pa - shm->paddr);
-
-		if (IS_ERR(v))
-			return PTR_ERR(v);
-		*va = v;
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(tee_shm_pa2va);
-
 /**
  * tee_shm_get_va() - Get virtual address of a shared memory plus an offset
  * @shm:	Shared memory handle
diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h
index 911cad324acc..17eb1c5205d3 100644
--- a/include/linux/tee_drv.h
+++ b/include/linux/tee_drv.h
@@ -298,24 +298,6 @@ void tee_shm_free(struct tee_shm *shm);
  */
 void tee_shm_put(struct tee_shm *shm);
 
-/**
- * tee_shm_va2pa() - Get physical address of a virtual address
- * @shm:	Shared memory handle
- * @va:		Virtual address to tranlsate
- * @pa:		Returned physical address
- * @returns 0 on success and < 0 on failure
- */
-int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa);
-
-/**
- * tee_shm_pa2va() - Get virtual address of a physical address
- * @shm:	Shared memory handle
- * @pa:		Physical address to tranlsate
- * @va:		Returned virtual address
- * @returns 0 on success and < 0 on failure
- */
-int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va);
-
 /**
  * tee_shm_get_va() - Get virtual address of a shared memory plus an offset
  * @shm:	Shared memory handle
-- 
cgit v1.2.3


From 97730bbb242cde22b7140acd202ffd88823886c9 Mon Sep 17 00:00:00 2001
From: Russ Weight <russell.h.weight@intel.com>
Date: Thu, 21 Apr 2022 14:22:00 -0700
Subject: firmware_loader: Add firmware-upload support

Extend the firmware subsystem to support a persistent sysfs interface that
userspace may use to initiate a firmware update. For example, FPGA based
PCIe cards load firmware and FPGA images from local FLASH when the card
boots. The images in FLASH may be updated with new images provided by the
user at his/her convenience.

A device driver may call firmware_upload_register() to expose persistent
"loading" and "data" sysfs files. These files are used in the same way as
the fallback sysfs "loading" and "data" files. When 0 is written to
"loading" to complete the write of firmware data, the data is transferred
to the lower-level driver using pre-registered call-back functions. The
data transfer is done in the context of a kernel worker thread.

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Tianfei zhang <tianfei.zhang@intel.com>
Tested-by: Matthew Gerlach <matthew.gerlach@linux.intel.com>
Signed-off-by: Russ Weight <russell.h.weight@intel.com>
Link: https://lore.kernel.org/r/20220421212204.36052-5-russell.h.weight@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-class-firmware  |  32 +++
 Documentation/driver-api/firmware/fw_upload.rst | 107 +++++++++
 Documentation/driver-api/firmware/index.rst     |   1 +
 drivers/base/firmware_loader/Kconfig            |  14 ++
 drivers/base/firmware_loader/Makefile           |   1 +
 drivers/base/firmware_loader/firmware.h         |   6 +
 drivers/base/firmware_loader/main.c             |  16 +-
 drivers/base/firmware_loader/sysfs.c            |  19 +-
 drivers/base/firmware_loader/sysfs.h            |   4 +
 drivers/base/firmware_loader/sysfs_upload.c     | 276 ++++++++++++++++++++++++
 drivers/base/firmware_loader/sysfs_upload.h     |  49 +++++
 include/linux/firmware.h                        |  82 +++++++
 12 files changed, 595 insertions(+), 12 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-class-firmware
 create mode 100644 Documentation/driver-api/firmware/fw_upload.rst
 create mode 100644 drivers/base/firmware_loader/sysfs_upload.c
 create mode 100644 drivers/base/firmware_loader/sysfs_upload.h

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-firmware b/Documentation/ABI/testing/sysfs-class-firmware
new file mode 100644
index 000000000000..18336c23b70d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-firmware
@@ -0,0 +1,32 @@
+What: 		/sys/class/firmware/.../data
+Date:		July 2022
+KernelVersion:	5.19
+Contact:	Russ Weight <russell.h.weight@intel.com>
+Description:	The data sysfs file is used for firmware-fallback and for
+		firmware uploads. Cat a firmware image to this sysfs file
+		after you echo 1 to the loading sysfs file. When the firmware
+		image write is complete, echo 0 to the loading sysfs file. This
+		sequence will signal the completion of the firmware write and
+		signal the lower-level driver that the firmware data is
+		available.
+
+What: 		/sys/class/firmware/.../loading
+Date:		July 2022
+KernelVersion:	5.19
+Contact:	Russ Weight <russell.h.weight@intel.com>
+Description:	The loading sysfs file is used for both firmware-fallback and
+		for firmware uploads. Echo 1 onto the loading file to indicate
+		you are writing a firmware file to the data sysfs node. Echo
+		-1 onto this file to abort the data write or echo 0 onto this
+		file to indicate that the write is complete. For firmware
+		uploads, the zero value also triggers the transfer of the
+		firmware data to the lower-level device driver.
+
+What: 		/sys/class/firmware/.../timeout
+Date:		July 2022
+KernelVersion:	5.19
+Contact:	Russ Weight <russell.h.weight@intel.com>
+Description:	This file supports the timeout mechanism for firmware
+		fallback.  This file has no affect on firmware uploads. For
+		more information on timeouts please see the documentation
+		for firmware fallback.
diff --git a/Documentation/driver-api/firmware/fw_upload.rst b/Documentation/driver-api/firmware/fw_upload.rst
new file mode 100644
index 000000000000..afbd8baca0d7
--- /dev/null
+++ b/Documentation/driver-api/firmware/fw_upload.rst
@@ -0,0 +1,107 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================
+Firmware Upload API
+===================
+
+A device driver that registers with the firmware loader will expose
+persistent sysfs nodes to enable users to initiate firmware updates for
+that device.  It is the responsibility of the device driver and/or the
+device itself to perform any validation on the data received. Firmware
+upload uses the same *loading* and *data* sysfs files described in the
+documentation for firmware fallback.
+
+Register for firmware upload
+============================
+
+A device driver registers for firmware upload by calling
+firmware_upload_register(). Among the parameter list is a name to
+identify the device under /sys/class/firmware. A user may initiate a
+firmware upload by echoing a 1 to the *loading* sysfs file for the target
+device. Next, the user writes the firmware image to the *data* sysfs
+file. After writing the firmware data, the user echos 0 to the *loading*
+sysfs file to signal completion. Echoing 0 to *loading* also triggers the
+transfer of the firmware to the lower-lever device driver in the context
+of a kernel worker thread.
+
+To use the firmware upload API, write a driver that implements a set of
+ops.  The probe function calls firmware_upload_register() and the remove
+function calls firmware_upload_unregister() such as::
+
+	static const struct fw_upload_ops m10bmc_ops = {
+		.prepare = m10bmc_sec_prepare,
+		.write = m10bmc_sec_write,
+		.poll_complete = m10bmc_sec_poll_complete,
+		.cancel = m10bmc_sec_cancel,
+		.cleanup = m10bmc_sec_cleanup,
+	};
+
+	static int m10bmc_sec_probe(struct platform_device *pdev)
+	{
+		const char *fw_name, *truncate;
+		struct m10bmc_sec *sec;
+		struct fw_upload *fwl;
+		unsigned int len;
+
+		sec = devm_kzalloc(&pdev->dev, sizeof(*sec), GFP_KERNEL);
+		if (!sec)
+			return -ENOMEM;
+
+		sec->dev = &pdev->dev;
+		sec->m10bmc = dev_get_drvdata(pdev->dev.parent);
+		dev_set_drvdata(&pdev->dev, sec);
+
+		fw_name = dev_name(sec->dev);
+		truncate = strstr(fw_name, ".auto");
+		len = (truncate) ? truncate - fw_name : strlen(fw_name);
+		sec->fw_name = kmemdup_nul(fw_name, len, GFP_KERNEL);
+
+		fwl = firmware_upload_register(sec->dev, sec->fw_name, &m10bmc_ops, sec);
+		if (IS_ERR(fwl)) {
+			dev_err(sec->dev, "Firmware Upload driver failed to start\n");
+			kfree(sec->fw_name);
+			return PTR_ERR(fwl);
+		}
+
+		sec->fwl = fwl;
+		return 0;
+	}
+
+	static int m10bmc_sec_remove(struct platform_device *pdev)
+	{
+		struct m10bmc_sec *sec = dev_get_drvdata(&pdev->dev);
+
+		firmware_upload_unregister(sec->fwl);
+		kfree(sec->fw_name);
+		return 0;
+	}
+
+firmware_upload_register
+------------------------
+.. kernel-doc:: drivers/base/firmware_loader/sysfs_upload.c
+   :identifiers: firmware_upload_register
+
+firmware_upload_unregister
+--------------------------
+.. kernel-doc:: drivers/base/firmware_loader/sysfs_upload.c
+   :identifiers: firmware_upload_unregister
+
+Firmware Upload Ops
+-------------------
+.. kernel-doc:: include/linux/firmware.h
+   :identifiers: fw_upload_ops
+
+Firmware Upload Progress Codes
+------------------------------
+The following progress codes are used internally by the firmware loader:
+
+.. kernel-doc:: drivers/base/firmware_loader/sysfs_upload.h
+   :identifiers: fw_upload_prog
+
+Firmware Upload Error Codes
+---------------------------
+The following error codes may be returned by the driver ops in case of
+failure:
+
+.. kernel-doc:: include/linux/firmware.h
+   :identifiers: fw_upload_err
diff --git a/Documentation/driver-api/firmware/index.rst b/Documentation/driver-api/firmware/index.rst
index 57415d657173..9d2c19dc8e36 100644
--- a/Documentation/driver-api/firmware/index.rst
+++ b/Documentation/driver-api/firmware/index.rst
@@ -8,6 +8,7 @@ Linux Firmware API
    core
    efi/index
    request_firmware
+   fw_upload
    other_interfaces
 
 .. only::  subproject and html
diff --git a/drivers/base/firmware_loader/Kconfig b/drivers/base/firmware_loader/Kconfig
index d13e4383ea0c..7e663dd972a7 100644
--- a/drivers/base/firmware_loader/Kconfig
+++ b/drivers/base/firmware_loader/Kconfig
@@ -202,5 +202,19 @@ config FW_CACHE
 
 	  If unsure, say Y.
 
+config FW_UPLOAD
+	bool "Enable users to initiate firmware updates using sysfs"
+	select FW_LOADER_SYSFS
+	select FW_LOADER_PAGED_BUF
+	help
+	  Enabling this option will allow device drivers to expose a persistent
+	  sysfs interface that allows firmware updates to be initiated from
+	  userspace. For example, FPGA based PCIe cards load firmware and FPGA
+	  images from local FLASH when the card boots. The images in FLASH may
+	  be updated with new images provided by the user. Enable this device
+	  to support cards that rely on user-initiated updates for firmware files.
+
+	  If unsure, say N.
+
 endif # FW_LOADER
 endmenu
diff --git a/drivers/base/firmware_loader/Makefile b/drivers/base/firmware_loader/Makefile
index aab213f82288..60d19f9e0ddc 100644
--- a/drivers/base/firmware_loader/Makefile
+++ b/drivers/base/firmware_loader/Makefile
@@ -7,5 +7,6 @@ firmware_class-objs := main.o
 firmware_class-$(CONFIG_FW_LOADER_USER_HELPER) += fallback.o
 firmware_class-$(CONFIG_EFI_EMBEDDED_FIRMWARE) += fallback_platform.o
 firmware_class-$(CONFIG_FW_LOADER_SYSFS) += sysfs.o
+firmware_class-$(CONFIG_FW_UPLOAD) += sysfs_upload.o
 
 obj-y += builtin/
diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h
index d5ff32a1ba2d..fe77e91c38a2 100644
--- a/drivers/base/firmware_loader/firmware.h
+++ b/drivers/base/firmware_loader/firmware.h
@@ -87,6 +87,7 @@ struct fw_priv {
 };
 
 extern struct mutex fw_lock;
+extern struct firmware_cache fw_cache;
 
 static inline bool __fw_state_check(struct fw_priv *fw_priv,
 				    enum fw_status status)
@@ -159,7 +160,12 @@ static inline bool fw_state_is_loading(struct fw_priv *fw_priv)
 	return __fw_state_check(fw_priv, FW_STATUS_LOADING);
 }
 
+int alloc_lookup_fw_priv(const char *fw_name, struct firmware_cache *fwc,
+			 struct fw_priv **fw_priv, void *dbuf, size_t size,
+			 size_t offset, u32 opt_flags);
 int assign_fw(struct firmware *fw, struct device *device);
+void free_fw_priv(struct fw_priv *fw_priv);
+void fw_state_init(struct fw_priv *fw_priv);
 
 #ifdef CONFIG_FW_LOADER
 bool firmware_is_builtin(const struct firmware *fw);
diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 6ac6c7753acc..9a8579e56c26 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -92,9 +92,9 @@ static inline struct fw_priv *to_fw_priv(struct kref *ref)
  * guarding for corner cases a global lock should be OK */
 DEFINE_MUTEX(fw_lock);
 
-static struct firmware_cache fw_cache;
+struct firmware_cache fw_cache;
 
-static void fw_state_init(struct fw_priv *fw_priv)
+void fw_state_init(struct fw_priv *fw_priv)
 {
 	struct fw_state *fw_st = &fw_priv->fw_st;
 
@@ -164,13 +164,9 @@ static struct fw_priv *__lookup_fw_priv(const char *fw_name)
 }
 
 /* Returns 1 for batching firmware requests with the same name */
-static int alloc_lookup_fw_priv(const char *fw_name,
-				struct firmware_cache *fwc,
-				struct fw_priv **fw_priv,
-				void *dbuf,
-				size_t size,
-				size_t offset,
-				u32 opt_flags)
+int alloc_lookup_fw_priv(const char *fw_name, struct firmware_cache *fwc,
+			 struct fw_priv **fw_priv, void *dbuf, size_t size,
+			 size_t offset, u32 opt_flags)
 {
 	struct fw_priv *tmp;
 
@@ -225,7 +221,7 @@ static void __free_fw_priv(struct kref *ref)
 	kfree(fw_priv);
 }
 
-static void free_fw_priv(struct fw_priv *fw_priv)
+void free_fw_priv(struct fw_priv *fw_priv)
 {
 	struct firmware_cache *fwc = fw_priv->fwc;
 	spin_lock(&fwc->lock);
diff --git a/drivers/base/firmware_loader/sysfs.c b/drivers/base/firmware_loader/sysfs.c
index 1509cb6b6e60..4a956cc3b7ea 100644
--- a/drivers/base/firmware_loader/sysfs.c
+++ b/drivers/base/firmware_loader/sysfs.c
@@ -6,8 +6,8 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#include "firmware.h"
 #include "sysfs.h"
+#include "sysfs_upload.h"
 
 /*
  * sysfs support for firmware loader
@@ -94,6 +94,10 @@ static void fw_dev_release(struct device *dev)
 {
 	struct fw_sysfs *fw_sysfs = to_fw_sysfs(dev);
 
+	if (fw_sysfs->fw_upload_priv) {
+		free_fw_priv(fw_sysfs->fw_priv);
+		kfree(fw_sysfs->fw_upload_priv);
+	}
 	kfree(fw_sysfs);
 }
 
@@ -199,6 +203,14 @@ static ssize_t firmware_loading_store(struct device *dev,
 				written = rc;
 			} else {
 				fw_state_done(fw_priv);
+
+				/*
+				 * If this is a user-initiated firmware upload
+				 * then start the upload in a worker thread now.
+				 */
+				rc = fw_upload_start(fw_sysfs);
+				if (rc)
+					written = rc;
 			}
 			break;
 		}
@@ -208,6 +220,9 @@ static ssize_t firmware_loading_store(struct device *dev,
 		fallthrough;
 	case -1:
 		fw_load_abort(fw_sysfs);
+		if (fw_sysfs->fw_upload_priv)
+			fw_state_init(fw_sysfs->fw_priv);
+
 		break;
 	}
 out:
@@ -215,7 +230,7 @@ out:
 	return written;
 }
 
-static DEVICE_ATTR(loading, 0644, firmware_loading_show, firmware_loading_store);
+DEVICE_ATTR(loading, 0644, firmware_loading_show, firmware_loading_store);
 
 static void firmware_rw_data(struct fw_priv *fw_priv, char *buffer,
 			     loff_t offset, size_t count, bool read)
diff --git a/drivers/base/firmware_loader/sysfs.h b/drivers/base/firmware_loader/sysfs.h
index b7b5c1766052..c21bcfe374ff 100644
--- a/drivers/base/firmware_loader/sysfs.h
+++ b/drivers/base/firmware_loader/sysfs.h
@@ -4,9 +4,12 @@
 
 #include <linux/device.h>
 
+#include "firmware.h"
+
 MODULE_IMPORT_NS(FIRMWARE_LOADER_PRIVATE);
 
 extern struct firmware_fallback_config fw_fallback_config;
+extern struct device_attribute dev_attr_loading;
 
 #ifdef CONFIG_FW_LOADER_USER_HELPER
 /**
@@ -73,6 +76,7 @@ struct fw_sysfs {
 	struct device dev;
 	struct fw_priv *fw_priv;
 	struct firmware *fw;
+	void *fw_upload_priv;
 };
 
 static inline struct fw_sysfs *to_fw_sysfs(struct device *dev)
diff --git a/drivers/base/firmware_loader/sysfs_upload.c b/drivers/base/firmware_loader/sysfs_upload.c
new file mode 100644
index 000000000000..0a6450d1974f
--- /dev/null
+++ b/drivers/base/firmware_loader/sysfs_upload.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "sysfs.h"
+#include "sysfs_upload.h"
+
+/*
+ * Support for user-space to initiate a firmware upload to a device.
+ */
+
+static void fw_upload_update_progress(struct fw_upload_priv *fwlp,
+				      enum fw_upload_prog new_progress)
+{
+	mutex_lock(&fwlp->lock);
+	fwlp->progress = new_progress;
+	mutex_unlock(&fwlp->lock);
+}
+
+static void fw_upload_set_error(struct fw_upload_priv *fwlp,
+				enum fw_upload_err err_code)
+{
+	mutex_lock(&fwlp->lock);
+	fwlp->err_progress = fwlp->progress;
+	fwlp->err_code = err_code;
+	mutex_unlock(&fwlp->lock);
+}
+
+static void fw_upload_prog_complete(struct fw_upload_priv *fwlp)
+{
+	mutex_lock(&fwlp->lock);
+	fwlp->progress = FW_UPLOAD_PROG_IDLE;
+	mutex_unlock(&fwlp->lock);
+}
+
+static void fw_upload_main(struct work_struct *work)
+{
+	struct fw_upload_priv *fwlp;
+	struct fw_sysfs *fw_sysfs;
+	u32 written = 0, offset = 0;
+	enum fw_upload_err ret;
+	struct device *fw_dev;
+	struct fw_upload *fwl;
+
+	fwlp = container_of(work, struct fw_upload_priv, work);
+	fwl = fwlp->fw_upload;
+	fw_sysfs = (struct fw_sysfs *)fwl->priv;
+	fw_dev = &fw_sysfs->dev;
+
+	fw_upload_update_progress(fwlp, FW_UPLOAD_PROG_PREPARING);
+	ret = fwlp->ops->prepare(fwl, fwlp->data, fwlp->remaining_size);
+	if (ret != FW_UPLOAD_ERR_NONE) {
+		fw_upload_set_error(fwlp, ret);
+		goto putdev_exit;
+	}
+
+	fw_upload_update_progress(fwlp, FW_UPLOAD_PROG_TRANSFERRING);
+	while (fwlp->remaining_size) {
+		ret = fwlp->ops->write(fwl, fwlp->data, offset,
+					fwlp->remaining_size, &written);
+		if (ret != FW_UPLOAD_ERR_NONE || !written) {
+			if (ret == FW_UPLOAD_ERR_NONE) {
+				dev_warn(fw_dev, "write-op wrote zero data\n");
+				ret = FW_UPLOAD_ERR_RW_ERROR;
+			}
+			fw_upload_set_error(fwlp, ret);
+			goto done;
+		}
+
+		fwlp->remaining_size -= written;
+		offset += written;
+	}
+
+	fw_upload_update_progress(fwlp, FW_UPLOAD_PROG_PROGRAMMING);
+	ret = fwlp->ops->poll_complete(fwl);
+	if (ret != FW_UPLOAD_ERR_NONE)
+		fw_upload_set_error(fwlp, ret);
+
+done:
+	if (fwlp->ops->cleanup)
+		fwlp->ops->cleanup(fwl);
+
+putdev_exit:
+	put_device(fw_dev->parent);
+
+	/*
+	 * Note: fwlp->remaining_size is left unmodified here to provide
+	 * additional information on errors. It will be reinitialized when
+	 * the next firmeware upload begins.
+	 */
+	mutex_lock(&fw_lock);
+	fw_free_paged_buf(fw_sysfs->fw_priv);
+	fw_state_init(fw_sysfs->fw_priv);
+	mutex_unlock(&fw_lock);
+	fwlp->data = NULL;
+	fw_upload_prog_complete(fwlp);
+}
+
+/*
+ * Start a worker thread to upload data to the parent driver.
+ * Must be called with fw_lock held.
+ */
+int fw_upload_start(struct fw_sysfs *fw_sysfs)
+{
+	struct fw_priv *fw_priv = fw_sysfs->fw_priv;
+	struct device *fw_dev = &fw_sysfs->dev;
+	struct fw_upload_priv *fwlp;
+
+	if (!fw_sysfs->fw_upload_priv)
+		return 0;
+
+	if (!fw_priv->size) {
+		fw_free_paged_buf(fw_priv);
+		fw_state_init(fw_sysfs->fw_priv);
+		return 0;
+	}
+
+	fwlp = fw_sysfs->fw_upload_priv;
+	mutex_lock(&fwlp->lock);
+
+	/* Do not interfere with an on-going fw_upload */
+	if (fwlp->progress != FW_UPLOAD_PROG_IDLE) {
+		mutex_unlock(&fwlp->lock);
+		return -EBUSY;
+	}
+
+	get_device(fw_dev->parent); /* released in fw_upload_main */
+
+	fwlp->progress = FW_UPLOAD_PROG_RECEIVING;
+	fwlp->err_code = 0;
+	fwlp->remaining_size = fw_priv->size;
+	fwlp->data = fw_priv->data;
+
+	pr_debug("%s: fw-%s fw_priv=%p data=%p size=%u\n",
+		 __func__, fw_priv->fw_name,
+		 fw_priv, fw_priv->data,
+		 (unsigned int)fw_priv->size);
+
+	queue_work(system_long_wq, &fwlp->work);
+	mutex_unlock(&fwlp->lock);
+
+	return 0;
+}
+
+/**
+ * firmware_upload_register() - register for the firmware upload sysfs API
+ * @parent: parent device instantiating firmware upload
+ * @name: firmware name to be associated with this device
+ * @ops: pointer to structure of firmware upload ops
+ * @dd_handle: pointer to parent driver private data
+ *
+ *	@name must be unique among all users of firmware upload. The firmware
+ *	sysfs files for this device will be found at /sys/class/firmware/@name.
+ *
+ *	Return: struct fw_upload pointer or ERR_PTR()
+ *
+ **/
+struct fw_upload *
+firmware_upload_register(struct module *module, struct device *parent,
+			 const char *name, const struct fw_upload_ops *ops,
+			 void *dd_handle)
+{
+	u32 opt_flags = FW_OPT_NOCACHE;
+	struct fw_upload *fw_upload;
+	struct fw_upload_priv *fw_upload_priv;
+	struct fw_sysfs *fw_sysfs;
+	struct fw_priv *fw_priv;
+	struct device *fw_dev;
+	int ret;
+
+	if (!name || name[0] == '\0')
+		return ERR_PTR(-EINVAL);
+
+	if (!ops || !ops->cancel || !ops->prepare ||
+	    !ops->write || !ops->poll_complete) {
+		dev_err(parent, "Attempt to register without all required ops\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!try_module_get(module))
+		return ERR_PTR(-EFAULT);
+
+	fw_upload = kzalloc(sizeof(*fw_upload), GFP_KERNEL);
+	if (!fw_upload) {
+		ret = -ENOMEM;
+		goto exit_module_put;
+	}
+
+	fw_upload_priv = kzalloc(sizeof(*fw_upload_priv), GFP_KERNEL);
+	if (!fw_upload_priv) {
+		ret = -ENOMEM;
+		goto free_fw_upload;
+	}
+
+	fw_upload_priv->fw_upload = fw_upload;
+	fw_upload_priv->ops = ops;
+	mutex_init(&fw_upload_priv->lock);
+	fw_upload_priv->module = module;
+	fw_upload_priv->name = name;
+	fw_upload_priv->err_code = 0;
+	fw_upload_priv->progress = FW_UPLOAD_PROG_IDLE;
+	INIT_WORK(&fw_upload_priv->work, fw_upload_main);
+	fw_upload->dd_handle = dd_handle;
+
+	fw_sysfs = fw_create_instance(NULL, name, parent, opt_flags);
+	if (IS_ERR(fw_sysfs)) {
+		ret = PTR_ERR(fw_sysfs);
+		goto free_fw_upload_priv;
+	}
+	fw_upload->priv = fw_sysfs;
+	fw_sysfs->fw_upload_priv = fw_upload_priv;
+	fw_dev = &fw_sysfs->dev;
+
+	ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv,  NULL, 0, 0,
+				   FW_OPT_NOCACHE);
+	if (ret != 0) {
+		if (ret > 0)
+			ret = -EINVAL;
+		goto free_fw_sysfs;
+	}
+	fw_priv->is_paged_buf = true;
+	fw_sysfs->fw_priv = fw_priv;
+
+	ret = device_add(fw_dev);
+	if (ret) {
+		dev_err(fw_dev, "%s: device_register failed\n", __func__);
+		put_device(fw_dev);
+		goto exit_module_put;
+	}
+
+	return fw_upload;
+
+free_fw_sysfs:
+	kfree(fw_sysfs);
+
+free_fw_upload_priv:
+	kfree(fw_upload_priv);
+
+free_fw_upload:
+	kfree(fw_upload);
+
+exit_module_put:
+	module_put(module);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(firmware_upload_register);
+
+/**
+ * firmware_upload_unregister() - Unregister firmware upload interface
+ * @fw_upload: pointer to struct fw_upload
+ **/
+void firmware_upload_unregister(struct fw_upload *fw_upload)
+{
+	struct fw_sysfs *fw_sysfs = fw_upload->priv;
+	struct fw_upload_priv *fw_upload_priv = fw_sysfs->fw_upload_priv;
+
+	mutex_lock(&fw_upload_priv->lock);
+	if (fw_upload_priv->progress == FW_UPLOAD_PROG_IDLE) {
+		mutex_unlock(&fw_upload_priv->lock);
+		goto unregister;
+	}
+
+	fw_upload_priv->ops->cancel(fw_upload);
+	mutex_unlock(&fw_upload_priv->lock);
+
+	/* Ensure lower-level device-driver is finished */
+	flush_work(&fw_upload_priv->work);
+
+unregister:
+	device_unregister(&fw_sysfs->dev);
+	module_put(fw_upload_priv->module);
+}
+EXPORT_SYMBOL_GPL(firmware_upload_unregister);
diff --git a/drivers/base/firmware_loader/sysfs_upload.h b/drivers/base/firmware_loader/sysfs_upload.h
new file mode 100644
index 000000000000..18bd4d99f064
--- /dev/null
+++ b/drivers/base/firmware_loader/sysfs_upload.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __FIRMWARE_UPLOAD_H
+#define __FIRMWARE_UPLOAD_H
+
+#include <linux/device.h>
+
+/**
+ * enum fw_upload_prog - firmware upload progress codes
+ * @FW_UPLOAD_PROG_IDLE: there is no firmware upload in progress
+ * @FW_UPLOAD_PROG_RECEIVING: worker thread is receiving firmware data
+ * @FW_UPLOAD_PROG_PREPARING: target device is preparing for firmware upload
+ * @FW_UPLOAD_PROG_TRANSFERRING: data is being copied to the device
+ * @FW_UPLOAD_PROG_PROGRAMMING: device is performing the firmware update
+ * @FW_UPLOAD_PROG_MAX: Maximum progress code marker
+ */
+enum fw_upload_prog {
+	FW_UPLOAD_PROG_IDLE,
+	FW_UPLOAD_PROG_RECEIVING,
+	FW_UPLOAD_PROG_PREPARING,
+	FW_UPLOAD_PROG_TRANSFERRING,
+	FW_UPLOAD_PROG_PROGRAMMING,
+	FW_UPLOAD_PROG_MAX
+};
+
+struct fw_upload_priv {
+	struct fw_upload *fw_upload;
+	struct module *module;
+	const char *name;
+	const struct fw_upload_ops *ops;
+	struct mutex lock;		  /* protect data structure contents */
+	struct work_struct work;
+	const u8 *data;			  /* pointer to update data */
+	u32 remaining_size;		  /* size remaining to transfer */
+	enum fw_upload_prog progress;
+	enum fw_upload_prog err_progress; /* progress at time of failure */
+	enum fw_upload_err err_code;	  /* security manager error code */
+};
+
+#ifdef CONFIG_FW_UPLOAD
+int fw_upload_start(struct fw_sysfs *fw_sysfs);
+umode_t fw_upload_is_visible(struct kobject *kobj, struct attribute *attr, int n);
+#else
+static inline int fw_upload_start(struct fw_sysfs *fw_sysfs)
+{
+	return 0;
+}
+#endif
+
+#endif /* __FIRMWARE_UPLOAD_H */
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index ec2ccfebef65..de7fea3bca51 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -17,6 +17,64 @@ struct firmware {
 	void *priv;
 };
 
+/**
+ * enum fw_upload_err - firmware upload error codes
+ * @FW_UPLOAD_ERR_NONE: returned to indicate success
+ * @FW_UPLOAD_ERR_HW_ERROR: error signalled by hardware, see kernel log
+ * @FW_UPLOAD_ERR_TIMEOUT: SW timed out on handshake with HW/firmware
+ * @FW_UPLOAD_ERR_CANCELED: upload was cancelled by the user
+ * @FW_UPLOAD_ERR_BUSY: there is an upload operation already in progress
+ * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size
+ * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log
+ * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry
+ * @FW_UPLOAD_ERR_MAX: Maximum error code marker
+ */
+enum fw_upload_err {
+	FW_UPLOAD_ERR_NONE,
+	FW_UPLOAD_ERR_HW_ERROR,
+	FW_UPLOAD_ERR_TIMEOUT,
+	FW_UPLOAD_ERR_CANCELED,
+	FW_UPLOAD_ERR_BUSY,
+	FW_UPLOAD_ERR_INVALID_SIZE,
+	FW_UPLOAD_ERR_RW_ERROR,
+	FW_UPLOAD_ERR_WEAROUT,
+	FW_UPLOAD_ERR_MAX
+};
+
+struct fw_upload {
+	void *dd_handle; /* reference to parent driver */
+	void *priv;	 /* firmware loader private fields */
+};
+
+/**
+ * struct fw_upload_ops - device specific operations to support firmware upload
+ * @prepare:		  Required: Prepare secure update
+ * @write:		  Required: The write() op receives the remaining
+ *			  size to be written and must return the actual
+ *			  size written or a negative error code. The write()
+ *			  op will be called repeatedly until all data is
+ *			  written.
+ * @poll_complete:	  Required: Check for the completion of the
+ *			  HW authentication/programming process.
+ * @cancel:		  Required: Request cancellation of update. This op
+ *			  is called from the context of a different kernel
+ *			  thread, so race conditions need to be considered.
+ * @cleanup:		  Optional: Complements the prepare()
+ *			  function and is called at the completion
+ *			  of the update, on success or failure, if the
+ *			  prepare function succeeded.
+ */
+struct fw_upload_ops {
+	enum fw_upload_err (*prepare)(struct fw_upload *fw_upload,
+				      const u8 *data, u32 size);
+	enum fw_upload_err (*write)(struct fw_upload *fw_upload,
+				    const u8 *data, u32 offset,
+				    u32 size, u32 *written);
+	enum fw_upload_err (*poll_complete)(struct fw_upload *fw_upload);
+	void (*cancel)(struct fw_upload *fw_upload);
+	void (*cleanup)(struct fw_upload *fw_upload);
+};
+
 struct module;
 struct device;
 
@@ -112,6 +170,30 @@ static inline int request_partial_firmware_into_buf
 
 #endif
 
+#ifdef CONFIG_FW_UPLOAD
+
+struct fw_upload *
+firmware_upload_register(struct module *module, struct device *parent,
+			 const char *name, const struct fw_upload_ops *ops,
+			 void *dd_handle);
+void firmware_upload_unregister(struct fw_upload *fw_upload);
+
+#else
+
+static inline struct fw_upload *
+firmware_upload_register(struct module *module, struct device *parent,
+			 const char *name, const struct fw_upload_ops *ops,
+			 void *dd_handle)
+{
+		return ERR_PTR(-EINVAL);
+}
+
+static inline void firmware_upload_unregister(struct fw_upload *fw_upload)
+{
+}
+
+#endif
+
 int firmware_request_cache(struct device *device, const char *name);
 
 #endif
-- 
cgit v1.2.3


From d434743e5cac3558381b767f343eef5af246a4dc Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:37 +0530
Subject: bus: mhi: ep: Add support for registering MHI endpoint controllers

This commit adds support for registering MHI endpoint controller drivers
with the MHI endpoint stack. MHI endpoint controller drivers manage
the interaction with the host machines (such as x86). They are also the
MHI endpoint bus master in charge of managing the physical link between
the host and endpoint device. Eventhough the MHI spec is bus agnostic,
the current implementation is entirely based on PCIe bus.

The endpoint controller driver encloses all information about the
underlying physical bus like PCIe. The registration process involves
parsing the channel configuration and allocating an MHI EP device.

Channels used in the endpoint stack follows the perspective of the MHI
host stack. i.e.,

UL - From host to endpoint
DL - From endpoint to host

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-2-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/Kconfig       |   1 +
 drivers/bus/mhi/Makefile      |   3 +
 drivers/bus/mhi/ep/Kconfig    |  10 ++
 drivers/bus/mhi/ep/Makefile   |   2 +
 drivers/bus/mhi/ep/internal.h | 156 ++++++++++++++++++++++++++++
 drivers/bus/mhi/ep/main.c     | 236 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h        | 136 ++++++++++++++++++++++++
 7 files changed, 544 insertions(+)
 create mode 100644 drivers/bus/mhi/ep/Kconfig
 create mode 100644 drivers/bus/mhi/ep/Makefile
 create mode 100644 drivers/bus/mhi/ep/internal.h
 create mode 100644 drivers/bus/mhi/ep/main.c
 create mode 100644 include/linux/mhi_ep.h

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/Kconfig b/drivers/bus/mhi/Kconfig
index 4748df7f9cd5..b39a11e6c624 100644
--- a/drivers/bus/mhi/Kconfig
+++ b/drivers/bus/mhi/Kconfig
@@ -6,3 +6,4 @@
 #
 
 source "drivers/bus/mhi/host/Kconfig"
+source "drivers/bus/mhi/ep/Kconfig"
diff --git a/drivers/bus/mhi/Makefile b/drivers/bus/mhi/Makefile
index 5f5708a249f5..46981331b38f 100644
--- a/drivers/bus/mhi/Makefile
+++ b/drivers/bus/mhi/Makefile
@@ -1,2 +1,5 @@
 # Host MHI stack
 obj-y += host/
+
+# Endpoint MHI stack
+obj-y += ep/
diff --git a/drivers/bus/mhi/ep/Kconfig b/drivers/bus/mhi/ep/Kconfig
new file mode 100644
index 000000000000..90ab3b040672
--- /dev/null
+++ b/drivers/bus/mhi/ep/Kconfig
@@ -0,0 +1,10 @@
+config MHI_BUS_EP
+	tristate "Modem Host Interface (MHI) bus Endpoint implementation"
+	help
+	  Bus driver for MHI protocol. Modem Host Interface (MHI) is a
+	  communication protocol used by a host processor to control
+	  and communicate a modem device over a high speed peripheral
+	  bus or shared memory.
+
+	  MHI_BUS_EP implements the MHI protocol for the endpoint devices,
+	  such as SDX55 modem connected to the host machine over PCIe.
diff --git a/drivers/bus/mhi/ep/Makefile b/drivers/bus/mhi/ep/Makefile
new file mode 100644
index 000000000000..64e29252b608
--- /dev/null
+++ b/drivers/bus/mhi/ep/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_MHI_BUS_EP) += mhi_ep.o
+mhi_ep-y := main.o
diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h
new file mode 100644
index 000000000000..0d3923186a5e
--- /dev/null
+++ b/drivers/bus/mhi/ep/internal.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022, Linaro Ltd.
+ *
+ */
+
+#ifndef _MHI_EP_INTERNAL_
+#define _MHI_EP_INTERNAL_
+
+#include <linux/bitfield.h>
+
+#include "../common.h"
+
+extern struct bus_type mhi_ep_bus_type;
+
+#define MHI_REG_OFFSET				0x100
+#define BHI_REG_OFFSET				0x200
+
+/* MHI registers */
+#define EP_MHIREGLEN				(MHI_REG_OFFSET + MHIREGLEN)
+#define EP_MHIVER				(MHI_REG_OFFSET + MHIVER)
+#define EP_MHICFG				(MHI_REG_OFFSET + MHICFG)
+#define EP_CHDBOFF				(MHI_REG_OFFSET + CHDBOFF)
+#define EP_ERDBOFF				(MHI_REG_OFFSET + ERDBOFF)
+#define EP_BHIOFF				(MHI_REG_OFFSET + BHIOFF)
+#define EP_BHIEOFF				(MHI_REG_OFFSET + BHIEOFF)
+#define EP_DEBUGOFF				(MHI_REG_OFFSET + DEBUGOFF)
+#define EP_MHICTRL				(MHI_REG_OFFSET + MHICTRL)
+#define EP_MHISTATUS				(MHI_REG_OFFSET + MHISTATUS)
+#define EP_CCABAP_LOWER				(MHI_REG_OFFSET + CCABAP_LOWER)
+#define EP_CCABAP_HIGHER			(MHI_REG_OFFSET + CCABAP_HIGHER)
+#define EP_ECABAP_LOWER				(MHI_REG_OFFSET + ECABAP_LOWER)
+#define EP_ECABAP_HIGHER			(MHI_REG_OFFSET + ECABAP_HIGHER)
+#define EP_CRCBAP_LOWER				(MHI_REG_OFFSET + CRCBAP_LOWER)
+#define EP_CRCBAP_HIGHER			(MHI_REG_OFFSET + CRCBAP_HIGHER)
+#define EP_CRDB_LOWER				(MHI_REG_OFFSET + CRDB_LOWER)
+#define EP_CRDB_HIGHER				(MHI_REG_OFFSET + CRDB_HIGHER)
+#define EP_MHICTRLBASE_LOWER			(MHI_REG_OFFSET + MHICTRLBASE_LOWER)
+#define EP_MHICTRLBASE_HIGHER			(MHI_REG_OFFSET + MHICTRLBASE_HIGHER)
+#define EP_MHICTRLLIMIT_LOWER			(MHI_REG_OFFSET + MHICTRLLIMIT_LOWER)
+#define EP_MHICTRLLIMIT_HIGHER			(MHI_REG_OFFSET + MHICTRLLIMIT_HIGHER)
+#define EP_MHIDATABASE_LOWER			(MHI_REG_OFFSET + MHIDATABASE_LOWER)
+#define EP_MHIDATABASE_HIGHER			(MHI_REG_OFFSET + MHIDATABASE_HIGHER)
+#define EP_MHIDATALIMIT_LOWER			(MHI_REG_OFFSET + MHIDATALIMIT_LOWER)
+#define EP_MHIDATALIMIT_HIGHER			(MHI_REG_OFFSET + MHIDATALIMIT_HIGHER)
+
+/* MHI BHI registers */
+#define EP_BHI_INTVEC				(BHI_REG_OFFSET + BHI_INTVEC)
+#define EP_BHI_EXECENV				(BHI_REG_OFFSET + BHI_EXECENV)
+
+/* MHI Doorbell registers */
+#define CHDB_LOWER_n(n)				(0x400 + 0x8 * (n))
+#define CHDB_HIGHER_n(n)			(0x404 + 0x8 * (n))
+#define ERDB_LOWER_n(n)				(0x800 + 0x8 * (n))
+#define ERDB_HIGHER_n(n)			(0x804 + 0x8 * (n))
+
+#define MHI_CTRL_INT_STATUS			0x4
+#define MHI_CTRL_INT_STATUS_MSK			BIT(0)
+#define MHI_CTRL_INT_STATUS_CRDB_MSK		BIT(1)
+#define MHI_CHDB_INT_STATUS_n(n)		(0x28 + 0x4 * (n))
+#define MHI_ERDB_INT_STATUS_n(n)		(0x38 + 0x4 * (n))
+
+#define MHI_CTRL_INT_CLEAR			0x4c
+#define MHI_CTRL_INT_MMIO_WR_CLEAR		BIT(2)
+#define MHI_CTRL_INT_CRDB_CLEAR			BIT(1)
+#define MHI_CTRL_INT_CRDB_MHICTRL_CLEAR		BIT(0)
+
+#define MHI_CHDB_INT_CLEAR_n(n)			(0x70 + 0x4 * (n))
+#define MHI_CHDB_INT_CLEAR_n_CLEAR_ALL		GENMASK(31, 0)
+#define MHI_ERDB_INT_CLEAR_n(n)			(0x80 + 0x4 * (n))
+#define MHI_ERDB_INT_CLEAR_n_CLEAR_ALL		GENMASK(31, 0)
+
+/*
+ * Unlike the usual "masking" convention, writing "1" to a bit in this register
+ * enables the interrupt and writing "0" will disable it..
+ */
+#define MHI_CTRL_INT_MASK			0x94
+#define MHI_CTRL_INT_MASK_MASK			GENMASK(1, 0)
+#define MHI_CTRL_MHICTRL_MASK			BIT(0)
+#define MHI_CTRL_CRDB_MASK			BIT(1)
+
+#define MHI_CHDB_INT_MASK_n(n)			(0xb8 + 0x4 * (n))
+#define MHI_CHDB_INT_MASK_n_EN_ALL		GENMASK(31, 0)
+#define MHI_ERDB_INT_MASK_n(n)			(0xc8 + 0x4 * (n))
+#define MHI_ERDB_INT_MASK_n_EN_ALL		GENMASK(31, 0)
+
+#define NR_OF_CMD_RINGS				1
+#define MHI_MASK_ROWS_CH_DB			4
+#define MHI_MASK_ROWS_EV_DB			4
+#define MHI_MASK_CH_LEN				32
+#define MHI_MASK_EV_LEN				32
+
+/* Generic context */
+struct mhi_generic_ctx {
+	__le32 reserved0;
+	__le32 reserved1;
+	__le32 reserved2;
+
+	__le64 rbase __packed __aligned(4);
+	__le64 rlen __packed __aligned(4);
+	__le64 rp __packed __aligned(4);
+	__le64 wp __packed __aligned(4);
+};
+
+enum mhi_ep_ring_type {
+	RING_TYPE_CMD,
+	RING_TYPE_ER,
+	RING_TYPE_CH,
+};
+
+/* Ring element */
+union mhi_ep_ring_ctx {
+	struct mhi_cmd_ctxt cmd;
+	struct mhi_event_ctxt ev;
+	struct mhi_chan_ctxt ch;
+	struct mhi_generic_ctx generic;
+};
+
+struct mhi_ep_ring {
+	struct mhi_ep_cntrl *mhi_cntrl;
+	union mhi_ep_ring_ctx *ring_ctx;
+	struct mhi_ring_element *ring_cache;
+	enum mhi_ep_ring_type type;
+	u64 rbase;
+	size_t rd_offset;
+	size_t wr_offset;
+	size_t ring_size;
+	u32 db_offset_h;
+	u32 db_offset_l;
+	u32 ch_id;
+};
+
+struct mhi_ep_cmd {
+	struct mhi_ep_ring ring;
+};
+
+struct mhi_ep_event {
+	struct mhi_ep_ring ring;
+};
+
+struct mhi_ep_chan {
+	char *name;
+	struct mhi_ep_device *mhi_dev;
+	struct mhi_ep_ring ring;
+	struct mutex lock;
+	void (*xfer_cb)(struct mhi_ep_device *mhi_dev, struct mhi_result *result);
+	enum mhi_ch_state state;
+	enum dma_data_direction dir;
+	u64 tre_loc;
+	u32 tre_size;
+	u32 tre_bytes_left;
+	u32 chan;
+	bool skip_td;
+};
+
+#endif
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
new file mode 100644
index 000000000000..d932ad01761b
--- /dev/null
+++ b/drivers/bus/mhi/ep/main.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * MHI Endpoint bus stack
+ *
+ * Copyright (C) 2022 Linaro Ltd.
+ * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/dma-direction.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mhi_ep.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include "internal.h"
+
+static DEFINE_IDA(mhi_ep_cntrl_ida);
+
+static void mhi_ep_release_device(struct device *dev)
+{
+	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
+
+	if (mhi_dev->dev_type == MHI_DEVICE_CONTROLLER)
+		mhi_dev->mhi_cntrl->mhi_dev = NULL;
+
+	/*
+	 * We need to set the mhi_chan->mhi_dev to NULL here since the MHI
+	 * devices for the channels will only get created in mhi_ep_create_device()
+	 * if the mhi_dev associated with it is NULL.
+	 */
+	if (mhi_dev->ul_chan)
+		mhi_dev->ul_chan->mhi_dev = NULL;
+
+	if (mhi_dev->dl_chan)
+		mhi_dev->dl_chan->mhi_dev = NULL;
+
+	kfree(mhi_dev);
+}
+
+static struct mhi_ep_device *mhi_ep_alloc_device(struct mhi_ep_cntrl *mhi_cntrl,
+						 enum mhi_device_type dev_type)
+{
+	struct mhi_ep_device *mhi_dev;
+	struct device *dev;
+
+	mhi_dev = kzalloc(sizeof(*mhi_dev), GFP_KERNEL);
+	if (!mhi_dev)
+		return ERR_PTR(-ENOMEM);
+
+	dev = &mhi_dev->dev;
+	device_initialize(dev);
+	dev->bus = &mhi_ep_bus_type;
+	dev->release = mhi_ep_release_device;
+
+	/* Controller device is always allocated first */
+	if (dev_type == MHI_DEVICE_CONTROLLER)
+		/* for MHI controller device, parent is the bus device (e.g. PCI EPF) */
+		dev->parent = mhi_cntrl->cntrl_dev;
+	else
+		/* for MHI client devices, parent is the MHI controller device */
+		dev->parent = &mhi_cntrl->mhi_dev->dev;
+
+	mhi_dev->mhi_cntrl = mhi_cntrl;
+	mhi_dev->dev_type = dev_type;
+
+	return mhi_dev;
+}
+
+static int mhi_ep_chan_init(struct mhi_ep_cntrl *mhi_cntrl,
+			    const struct mhi_ep_cntrl_config *config)
+{
+	const struct mhi_ep_channel_config *ch_cfg;
+	struct device *dev = mhi_cntrl->cntrl_dev;
+	u32 chan, i;
+	int ret = -EINVAL;
+
+	mhi_cntrl->max_chan = config->max_channels;
+
+	/*
+	 * Allocate max_channels supported by the MHI endpoint and populate
+	 * only the defined channels
+	 */
+	mhi_cntrl->mhi_chan = kcalloc(mhi_cntrl->max_chan, sizeof(*mhi_cntrl->mhi_chan),
+				      GFP_KERNEL);
+	if (!mhi_cntrl->mhi_chan)
+		return -ENOMEM;
+
+	for (i = 0; i < config->num_channels; i++) {
+		struct mhi_ep_chan *mhi_chan;
+
+		ch_cfg = &config->ch_cfg[i];
+
+		chan = ch_cfg->num;
+		if (chan >= mhi_cntrl->max_chan) {
+			dev_err(dev, "Channel (%u) exceeds maximum available channels (%u)\n",
+				chan, mhi_cntrl->max_chan);
+			goto error_chan_cfg;
+		}
+
+		/* Bi-directional and direction less channels are not supported */
+		if (ch_cfg->dir == DMA_BIDIRECTIONAL || ch_cfg->dir == DMA_NONE) {
+			dev_err(dev, "Invalid direction (%u) for channel (%u)\n",
+				ch_cfg->dir, chan);
+			goto error_chan_cfg;
+		}
+
+		mhi_chan = &mhi_cntrl->mhi_chan[chan];
+		mhi_chan->name = ch_cfg->name;
+		mhi_chan->chan = chan;
+		mhi_chan->dir = ch_cfg->dir;
+		mutex_init(&mhi_chan->lock);
+	}
+
+	return 0;
+
+error_chan_cfg:
+	kfree(mhi_cntrl->mhi_chan);
+
+	return ret;
+}
+
+/*
+ * Allocate channel and command rings here. Event rings will be allocated
+ * in mhi_ep_power_up() as the config comes from the host.
+ */
+int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
+				const struct mhi_ep_cntrl_config *config)
+{
+	struct mhi_ep_device *mhi_dev;
+	int ret;
+
+	if (!mhi_cntrl || !mhi_cntrl->cntrl_dev)
+		return -EINVAL;
+
+	ret = mhi_ep_chan_init(mhi_cntrl, config);
+	if (ret)
+		return ret;
+
+	mhi_cntrl->mhi_cmd = kcalloc(NR_OF_CMD_RINGS, sizeof(*mhi_cntrl->mhi_cmd), GFP_KERNEL);
+	if (!mhi_cntrl->mhi_cmd) {
+		ret = -ENOMEM;
+		goto err_free_ch;
+	}
+
+	/* Set controller index */
+	ret = ida_alloc(&mhi_ep_cntrl_ida, GFP_KERNEL);
+	if (ret < 0)
+		goto err_free_cmd;
+
+	mhi_cntrl->index = ret;
+
+	/* Allocate the controller device */
+	mhi_dev = mhi_ep_alloc_device(mhi_cntrl, MHI_DEVICE_CONTROLLER);
+	if (IS_ERR(mhi_dev)) {
+		dev_err(mhi_cntrl->cntrl_dev, "Failed to allocate controller device\n");
+		ret = PTR_ERR(mhi_dev);
+		goto err_ida_free;
+	}
+
+	dev_set_name(&mhi_dev->dev, "mhi_ep%u", mhi_cntrl->index);
+	mhi_dev->name = dev_name(&mhi_dev->dev);
+	mhi_cntrl->mhi_dev = mhi_dev;
+
+	ret = device_add(&mhi_dev->dev);
+	if (ret)
+		goto err_put_dev;
+
+	dev_dbg(&mhi_dev->dev, "MHI EP Controller registered\n");
+
+	return 0;
+
+err_put_dev:
+	put_device(&mhi_dev->dev);
+err_ida_free:
+	ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index);
+err_free_cmd:
+	kfree(mhi_cntrl->mhi_cmd);
+err_free_ch:
+	kfree(mhi_cntrl->mhi_chan);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mhi_ep_register_controller);
+
+void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	struct mhi_ep_device *mhi_dev = mhi_cntrl->mhi_dev;
+
+	kfree(mhi_cntrl->mhi_cmd);
+	kfree(mhi_cntrl->mhi_chan);
+
+	device_del(&mhi_dev->dev);
+	put_device(&mhi_dev->dev);
+
+	ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index);
+}
+EXPORT_SYMBOL_GPL(mhi_ep_unregister_controller);
+
+static int mhi_ep_match(struct device *dev, struct device_driver *drv)
+{
+	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
+
+	/*
+	 * If the device is a controller type then there is no client driver
+	 * associated with it
+	 */
+	if (mhi_dev->dev_type == MHI_DEVICE_CONTROLLER)
+		return 0;
+
+	return 0;
+};
+
+struct bus_type mhi_ep_bus_type = {
+	.name = "mhi_ep",
+	.dev_name = "mhi_ep",
+	.match = mhi_ep_match,
+};
+
+static int __init mhi_ep_init(void)
+{
+	return bus_register(&mhi_ep_bus_type);
+}
+
+static void __exit mhi_ep_exit(void)
+{
+	bus_unregister(&mhi_ep_bus_type);
+}
+
+postcore_initcall(mhi_ep_init);
+module_exit(mhi_ep_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("MHI Bus Endpoint stack");
+MODULE_AUTHOR("Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>");
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
new file mode 100644
index 000000000000..891b199a9703
--- /dev/null
+++ b/include/linux/mhi_ep.h
@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022, Linaro Ltd.
+ *
+ */
+#ifndef _MHI_EP_H_
+#define _MHI_EP_H_
+
+#include <linux/dma-direction.h>
+#include <linux/mhi.h>
+
+#define MHI_EP_DEFAULT_MTU 0x8000
+
+/**
+ * struct mhi_ep_channel_config - Channel configuration structure for controller
+ * @name: The name of this channel
+ * @num: The number assigned to this channel
+ * @num_elements: The number of elements that can be queued to this channel
+ * @dir: Direction that data may flow on this channel
+ */
+struct mhi_ep_channel_config {
+	char *name;
+	u32 num;
+	u32 num_elements;
+	enum dma_data_direction dir;
+};
+
+/**
+ * struct mhi_ep_cntrl_config - MHI Endpoint controller configuration
+ * @mhi_version: MHI spec version supported by the controller
+ * @max_channels: Maximum number of channels supported
+ * @num_channels: Number of channels defined in @ch_cfg
+ * @ch_cfg: Array of defined channels
+ */
+struct mhi_ep_cntrl_config {
+	u32 mhi_version;
+	u32 max_channels;
+	u32 num_channels;
+	const struct mhi_ep_channel_config *ch_cfg;
+};
+
+/**
+ * struct mhi_ep_db_info - MHI Endpoint doorbell info
+ * @mask: Mask of the doorbell interrupt
+ * @status: Status of the doorbell interrupt
+ */
+struct mhi_ep_db_info {
+	u32 mask;
+	u32 status;
+};
+
+/**
+ * struct mhi_ep_cntrl - MHI Endpoint controller structure
+ * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
+ *             Endpoint controller
+ * @mhi_dev: MHI Endpoint device instance for the controller
+ * @mmio: MMIO region containing the MHI registers
+ * @mhi_chan: Points to the channel configuration table
+ * @mhi_event: Points to the event ring configurations table
+ * @mhi_cmd: Points to the command ring configurations table
+ * @sm: MHI Endpoint state machine
+ * @raise_irq: CB function for raising IRQ to the host
+ * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
+ * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
+ * @read_from_host: CB function for reading from host memory from endpoint
+ * @write_to_host: CB function for writing to host memory from endpoint
+ * @mhi_state: MHI Endpoint state
+ * @max_chan: Maximum channels supported by the endpoint controller
+ * @mru: MRU (Maximum Receive Unit) value of the endpoint controller
+ * @index: MHI Endpoint controller index
+ */
+struct mhi_ep_cntrl {
+	struct device *cntrl_dev;
+	struct mhi_ep_device *mhi_dev;
+	void __iomem *mmio;
+
+	struct mhi_ep_chan *mhi_chan;
+	struct mhi_ep_event *mhi_event;
+	struct mhi_ep_cmd *mhi_cmd;
+	struct mhi_ep_sm *sm;
+
+	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
+	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
+			 void __iomem **virt, size_t size);
+	void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys,
+			   void __iomem *virt, size_t size);
+	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size);
+	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size);
+
+	enum mhi_state mhi_state;
+
+	u32 max_chan;
+	u32 mru;
+	u32 index;
+};
+
+/**
+ * struct mhi_ep_device - Structure representing an MHI Endpoint device that binds
+ *                     to channels or is associated with controllers
+ * @dev: Driver model device node for the MHI Endpoint device
+ * @mhi_cntrl: Controller the device belongs to
+ * @id: Pointer to MHI Endpoint device ID struct
+ * @name: Name of the associated MHI Endpoint device
+ * @ul_chan: UL channel for the device
+ * @dl_chan: DL channel for the device
+ * @dev_type: MHI device type
+ */
+struct mhi_ep_device {
+	struct device dev;
+	struct mhi_ep_cntrl *mhi_cntrl;
+	const struct mhi_device_id *id;
+	const char *name;
+	struct mhi_ep_chan *ul_chan;
+	struct mhi_ep_chan *dl_chan;
+	enum mhi_device_type dev_type;
+};
+
+#define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev)
+
+/**
+ * mhi_ep_register_controller - Register MHI Endpoint controller
+ * @mhi_cntrl: MHI Endpoint controller to register
+ * @config: Configuration to use for the controller
+ *
+ * Return: 0 if controller registrations succeeds, a negative error code otherwise.
+ */
+int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
+			       const struct mhi_ep_cntrl_config *config);
+
+/**
+ * mhi_ep_unregister_controller - Unregister MHI Endpoint controller
+ * @mhi_cntrl: MHI Endpoint controller to unregister
+ */
+void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl);
+
+#endif
-- 
cgit v1.2.3


From ee0360b20b3fa08e2eee300eacb45e812ae44578 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:38 +0530
Subject: bus: mhi: ep: Add support for registering MHI endpoint client drivers

This commit adds support for registering MHI endpoint client drivers
with the MHI endpoint stack. MHI endpoint client drivers bind to one
or more MHI endpoint devices inorder to send and receive the upper-layer
protocol packets like IP packets, modem control messages, and
diagnostics messages over MHI bus.

Reviewed-by: Hemant Kumar <hemantk@codeaurora.org>
Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-3-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h    | 57 +++++++++++++++++++++++++++++--
 2 files changed, 140 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index d932ad01761b..f7d5f75fc083 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -198,9 +198,88 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
 }
 EXPORT_SYMBOL_GPL(mhi_ep_unregister_controller);
 
+static int mhi_ep_driver_probe(struct device *dev)
+{
+	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
+	struct mhi_ep_driver *mhi_drv = to_mhi_ep_driver(dev->driver);
+	struct mhi_ep_chan *ul_chan = mhi_dev->ul_chan;
+	struct mhi_ep_chan *dl_chan = mhi_dev->dl_chan;
+
+	ul_chan->xfer_cb = mhi_drv->ul_xfer_cb;
+	dl_chan->xfer_cb = mhi_drv->dl_xfer_cb;
+
+	return mhi_drv->probe(mhi_dev, mhi_dev->id);
+}
+
+static int mhi_ep_driver_remove(struct device *dev)
+{
+	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
+	struct mhi_ep_driver *mhi_drv = to_mhi_ep_driver(dev->driver);
+	struct mhi_result result = {};
+	struct mhi_ep_chan *mhi_chan;
+	int dir;
+
+	/* Skip if it is a controller device */
+	if (mhi_dev->dev_type == MHI_DEVICE_CONTROLLER)
+		return 0;
+
+	/* Disconnect the channels associated with the driver */
+	for (dir = 0; dir < 2; dir++) {
+		mhi_chan = dir ? mhi_dev->ul_chan : mhi_dev->dl_chan;
+
+		if (!mhi_chan)
+			continue;
+
+		mutex_lock(&mhi_chan->lock);
+		/* Send channel disconnect status to the client driver */
+		if (mhi_chan->xfer_cb) {
+			result.transaction_status = -ENOTCONN;
+			result.bytes_xferd = 0;
+			mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
+		}
+
+		mhi_chan->state = MHI_CH_STATE_DISABLED;
+		mhi_chan->xfer_cb = NULL;
+		mutex_unlock(&mhi_chan->lock);
+	}
+
+	/* Remove the client driver now */
+	mhi_drv->remove(mhi_dev);
+
+	return 0;
+}
+
+int __mhi_ep_driver_register(struct mhi_ep_driver *mhi_drv, struct module *owner)
+{
+	struct device_driver *driver = &mhi_drv->driver;
+
+	if (!mhi_drv->probe || !mhi_drv->remove)
+		return -EINVAL;
+
+	/* Client drivers should have callbacks defined for both channels */
+	if (!mhi_drv->ul_xfer_cb || !mhi_drv->dl_xfer_cb)
+		return -EINVAL;
+
+	driver->bus = &mhi_ep_bus_type;
+	driver->owner = owner;
+	driver->probe = mhi_ep_driver_probe;
+	driver->remove = mhi_ep_driver_remove;
+
+	return driver_register(driver);
+}
+EXPORT_SYMBOL_GPL(__mhi_ep_driver_register);
+
+void mhi_ep_driver_unregister(struct mhi_ep_driver *mhi_drv)
+{
+	driver_unregister(&mhi_drv->driver);
+}
+EXPORT_SYMBOL_GPL(mhi_ep_driver_unregister);
+
 static int mhi_ep_match(struct device *dev, struct device_driver *drv)
 {
 	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
+	struct mhi_ep_driver *mhi_drv = to_mhi_ep_driver(drv);
+	const struct mhi_device_id *id;
 
 	/*
 	 * If the device is a controller type then there is no client driver
@@ -209,6 +288,12 @@ static int mhi_ep_match(struct device *dev, struct device_driver *drv)
 	if (mhi_dev->dev_type == MHI_DEVICE_CONTROLLER)
 		return 0;
 
+	for (id = mhi_drv->id_table; id->chan[0]; id++)
+		if (!strcmp(mhi_dev->name, id->chan)) {
+			mhi_dev->id = id;
+			return 1;
+		}
+
 	return 0;
 };
 
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 891b199a9703..e2b94f9eb846 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -101,8 +101,8 @@ struct mhi_ep_cntrl {
  * @mhi_cntrl: Controller the device belongs to
  * @id: Pointer to MHI Endpoint device ID struct
  * @name: Name of the associated MHI Endpoint device
- * @ul_chan: UL channel for the device
- * @dl_chan: DL channel for the device
+ * @ul_chan: UL (from host to endpoint) channel for the device
+ * @dl_chan: DL (from endpoint to host) channel for the device
  * @dev_type: MHI device type
  */
 struct mhi_ep_device {
@@ -115,7 +115,60 @@ struct mhi_ep_device {
 	enum mhi_device_type dev_type;
 };
 
+/**
+ * struct mhi_ep_driver - Structure representing a MHI Endpoint client driver
+ * @id_table: Pointer to MHI Endpoint device ID table
+ * @driver: Device driver model driver
+ * @probe: CB function for client driver probe function
+ * @remove: CB function for client driver remove function
+ * @ul_xfer_cb: CB function for UL (from host to endpoint) data transfer
+ * @dl_xfer_cb: CB function for DL (from endpoint to host) data transfer
+ */
+struct mhi_ep_driver {
+	const struct mhi_device_id *id_table;
+	struct device_driver driver;
+	int (*probe)(struct mhi_ep_device *mhi_ep,
+		     const struct mhi_device_id *id);
+	void (*remove)(struct mhi_ep_device *mhi_ep);
+	void (*ul_xfer_cb)(struct mhi_ep_device *mhi_dev,
+			   struct mhi_result *result);
+	void (*dl_xfer_cb)(struct mhi_ep_device *mhi_dev,
+			   struct mhi_result *result);
+};
+
 #define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev)
+#define to_mhi_ep_driver(drv) container_of(drv, struct mhi_ep_driver, driver)
+
+/*
+ * module_mhi_ep_driver() - Helper macro for drivers that don't do
+ * anything special other than using default mhi_ep_driver_register() and
+ * mhi_ep_driver_unregister().  This eliminates a lot of boilerplate.
+ * Each module may only use this macro once.
+ */
+#define module_mhi_ep_driver(mhi_drv) \
+	module_driver(mhi_drv, mhi_ep_driver_register, \
+		      mhi_ep_driver_unregister)
+
+/*
+ * Macro to avoid include chaining to get THIS_MODULE
+ */
+#define mhi_ep_driver_register(mhi_drv) \
+	__mhi_ep_driver_register(mhi_drv, THIS_MODULE)
+
+/**
+ * __mhi_ep_driver_register - Register a driver with MHI Endpoint bus
+ * @mhi_drv: Driver to be associated with the device
+ * @owner: The module owner
+ *
+ * Return: 0 if driver registrations succeeds, a negative error code otherwise.
+ */
+int __mhi_ep_driver_register(struct mhi_ep_driver *mhi_drv, struct module *owner);
+
+/**
+ * mhi_ep_driver_unregister - Unregister a driver from MHI Endpoint bus
+ * @mhi_drv: Driver associated with the device
+ */
+void mhi_ep_driver_unregister(struct mhi_ep_driver *mhi_drv);
 
 /**
  * mhi_ep_register_controller - Register MHI Endpoint controller
-- 
cgit v1.2.3


From e9e4da23cd65ea76ba658346f5c182791bd1cea9 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:40 +0530
Subject: bus: mhi: ep: Add support for managing MMIO registers

Add support for managing the Memory Mapped Input Output (MMIO) registers
of the MHI bus. All MHI operations are carried out using the MMIO registers
by both host and the endpoint device.

The MMIO registers reside inside the endpoint device memory (fixed
location based on the platform) and the address is passed by the MHI EP
controller driver during its registration.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-5-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/Makefile   |   2 +-
 drivers/bus/mhi/ep/internal.h |  26 ++++
 drivers/bus/mhi/ep/main.c     |   6 +-
 drivers/bus/mhi/ep/mmio.c     | 273 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h        |  18 +++
 5 files changed, 323 insertions(+), 2 deletions(-)
 create mode 100644 drivers/bus/mhi/ep/mmio.c

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/Makefile b/drivers/bus/mhi/ep/Makefile
index 64e29252b608..a1555ae287ad 100644
--- a/drivers/bus/mhi/ep/Makefile
+++ b/drivers/bus/mhi/ep/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_MHI_BUS_EP) += mhi_ep.o
-mhi_ep-y := main.o
+mhi_ep-y := main.o mmio.o
diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h
index 0d3923186a5e..475425a30d85 100644
--- a/drivers/bus/mhi/ep/internal.h
+++ b/drivers/bus/mhi/ep/internal.h
@@ -153,4 +153,30 @@ struct mhi_ep_chan {
 	bool skip_td;
 };
 
+/* MMIO related functions */
+u32 mhi_ep_mmio_read(struct mhi_ep_cntrl *mhi_cntrl, u32 offset);
+void mhi_ep_mmio_write(struct mhi_ep_cntrl *mhi_cntrl, u32 offset, u32 val);
+void mhi_ep_mmio_masked_write(struct mhi_ep_cntrl *mhi_cntrl, u32 offset, u32 mask, u32 val);
+u32 mhi_ep_mmio_masked_read(struct mhi_ep_cntrl *dev, u32 offset, u32 mask);
+void mhi_ep_mmio_enable_ctrl_interrupt(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_disable_ctrl_interrupt(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_enable_cmdb_interrupt(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_disable_cmdb_interrupt(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_enable_chdb(struct mhi_ep_cntrl *mhi_cntrl, u32 ch_id);
+void mhi_ep_mmio_disable_chdb(struct mhi_ep_cntrl *mhi_cntrl, u32 ch_id);
+void mhi_ep_mmio_enable_chdb_interrupts(struct mhi_ep_cntrl *mhi_cntrl);
+bool mhi_ep_mmio_read_chdb_status_interrupts(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_mask_interrupts(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_get_chc_base(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_get_erc_base(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_get_crc_base(struct mhi_ep_cntrl *mhi_cntrl);
+u64 mhi_ep_mmio_get_db(struct mhi_ep_ring *ring);
+void mhi_ep_mmio_set_env(struct mhi_ep_cntrl *mhi_cntrl, u32 value);
+void mhi_ep_mmio_clear_reset(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_reset(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_get_mhi_state(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state *state,
+			       bool *mhi_reset);
+void mhi_ep_mmio_init(struct mhi_ep_cntrl *mhi_cntrl);
+void mhi_ep_mmio_update_ner(struct mhi_ep_cntrl *mhi_cntrl);
+
 #endif
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 6c64745e8a06..7dcc784f10d1 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -214,7 +214,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	struct mhi_ep_device *mhi_dev;
 	int ret;
 
-	if (!mhi_cntrl || !mhi_cntrl->cntrl_dev)
+	if (!mhi_cntrl || !mhi_cntrl->cntrl_dev || !mhi_cntrl->mmio)
 		return -EINVAL;
 
 	ret = mhi_ep_chan_init(mhi_cntrl, config);
@@ -227,6 +227,10 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		goto err_free_ch;
 	}
 
+	/* Set MHI version and AMSS EE before enumeration */
+	mhi_ep_mmio_write(mhi_cntrl, EP_MHIVER, config->mhi_version);
+	mhi_ep_mmio_set_env(mhi_cntrl, MHI_EE_AMSS);
+
 	/* Set controller index */
 	ret = ida_alloc(&mhi_ep_cntrl_ida, GFP_KERNEL);
 	if (ret < 0)
diff --git a/drivers/bus/mhi/ep/mmio.c b/drivers/bus/mhi/ep/mmio.c
new file mode 100644
index 000000000000..b5bfd22f2c8e
--- /dev/null
+++ b/drivers/bus/mhi/ep/mmio.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Linaro Ltd.
+ * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/io.h>
+#include <linux/mhi_ep.h>
+
+#include "internal.h"
+
+u32 mhi_ep_mmio_read(struct mhi_ep_cntrl *mhi_cntrl, u32 offset)
+{
+	return readl(mhi_cntrl->mmio + offset);
+}
+
+void mhi_ep_mmio_write(struct mhi_ep_cntrl *mhi_cntrl, u32 offset, u32 val)
+{
+	writel(val, mhi_cntrl->mmio + offset);
+}
+
+void mhi_ep_mmio_masked_write(struct mhi_ep_cntrl *mhi_cntrl, u32 offset, u32 mask, u32 val)
+{
+	u32 regval;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, offset);
+	regval &= ~mask;
+	regval |= (val << __ffs(mask)) & mask;
+	mhi_ep_mmio_write(mhi_cntrl, offset, regval);
+}
+
+u32 mhi_ep_mmio_masked_read(struct mhi_ep_cntrl *dev, u32 offset, u32 mask)
+{
+	u32 regval;
+
+	regval = mhi_ep_mmio_read(dev, offset);
+	regval &= mask;
+	regval >>= __ffs(mask);
+
+	return regval;
+}
+
+void mhi_ep_mmio_get_mhi_state(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state *state,
+				bool *mhi_reset)
+{
+	u32 regval;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_MHICTRL);
+	*state = FIELD_GET(MHICTRL_MHISTATE_MASK, regval);
+	*mhi_reset = !!FIELD_GET(MHICTRL_RESET_MASK, regval);
+}
+
+static void mhi_ep_mmio_set_chdb(struct mhi_ep_cntrl *mhi_cntrl, u32 ch_id, bool enable)
+{
+	u32 chid_mask, chid_shift, chdb_idx, val;
+
+	chid_shift = ch_id % 32;
+	chid_mask = BIT(chid_shift);
+	chdb_idx = ch_id / 32;
+
+	val = enable ? 1 : 0;
+
+	mhi_ep_mmio_masked_write(mhi_cntrl, MHI_CHDB_INT_MASK_n(chdb_idx), chid_mask, val);
+
+	/* Update the local copy of the channel mask */
+	mhi_cntrl->chdb[chdb_idx].mask &= ~chid_mask;
+	mhi_cntrl->chdb[chdb_idx].mask |= val << chid_shift;
+}
+
+void mhi_ep_mmio_enable_chdb(struct mhi_ep_cntrl *mhi_cntrl, u32 ch_id)
+{
+	mhi_ep_mmio_set_chdb(mhi_cntrl, ch_id, true);
+}
+
+void mhi_ep_mmio_disable_chdb(struct mhi_ep_cntrl *mhi_cntrl, u32 ch_id)
+{
+	mhi_ep_mmio_set_chdb(mhi_cntrl, ch_id, false);
+}
+
+static void mhi_ep_mmio_set_chdb_interrupts(struct mhi_ep_cntrl *mhi_cntrl, bool enable)
+{
+	u32 val, i;
+
+	val = enable ? MHI_CHDB_INT_MASK_n_EN_ALL : 0;
+
+	for (i = 0; i < MHI_MASK_ROWS_CH_DB; i++) {
+		mhi_ep_mmio_write(mhi_cntrl, MHI_CHDB_INT_MASK_n(i), val);
+		mhi_cntrl->chdb[i].mask = val;
+	}
+}
+
+void mhi_ep_mmio_enable_chdb_interrupts(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_set_chdb_interrupts(mhi_cntrl, true);
+}
+
+static void mhi_ep_mmio_mask_chdb_interrupts(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_set_chdb_interrupts(mhi_cntrl, false);
+}
+
+bool mhi_ep_mmio_read_chdb_status_interrupts(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	bool chdb = false;
+	u32 i;
+
+	for (i = 0; i < MHI_MASK_ROWS_CH_DB; i++) {
+		mhi_cntrl->chdb[i].status = mhi_ep_mmio_read(mhi_cntrl, MHI_CHDB_INT_STATUS_n(i));
+		if (mhi_cntrl->chdb[i].status)
+			chdb = true;
+	}
+
+	/* Return whether a channel doorbell interrupt occurred or not */
+	return chdb;
+}
+
+static void mhi_ep_mmio_set_erdb_interrupts(struct mhi_ep_cntrl *mhi_cntrl, bool enable)
+{
+	u32 val, i;
+
+	val = enable ? MHI_ERDB_INT_MASK_n_EN_ALL : 0;
+
+	for (i = 0; i < MHI_MASK_ROWS_EV_DB; i++)
+		mhi_ep_mmio_write(mhi_cntrl, MHI_ERDB_INT_MASK_n(i), val);
+}
+
+static void mhi_ep_mmio_mask_erdb_interrupts(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_set_erdb_interrupts(mhi_cntrl, false);
+}
+
+void mhi_ep_mmio_enable_ctrl_interrupt(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_masked_write(mhi_cntrl, MHI_CTRL_INT_MASK,
+				  MHI_CTRL_MHICTRL_MASK, 1);
+}
+
+void mhi_ep_mmio_disable_ctrl_interrupt(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_masked_write(mhi_cntrl, MHI_CTRL_INT_MASK,
+				  MHI_CTRL_MHICTRL_MASK, 0);
+}
+
+void mhi_ep_mmio_enable_cmdb_interrupt(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_masked_write(mhi_cntrl, MHI_CTRL_INT_MASK,
+				  MHI_CTRL_CRDB_MASK, 1);
+}
+
+void mhi_ep_mmio_disable_cmdb_interrupt(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_masked_write(mhi_cntrl, MHI_CTRL_INT_MASK,
+				  MHI_CTRL_CRDB_MASK, 0);
+}
+
+void mhi_ep_mmio_mask_interrupts(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_disable_ctrl_interrupt(mhi_cntrl);
+	mhi_ep_mmio_disable_cmdb_interrupt(mhi_cntrl);
+	mhi_ep_mmio_mask_chdb_interrupts(mhi_cntrl);
+	mhi_ep_mmio_mask_erdb_interrupts(mhi_cntrl);
+}
+
+static void mhi_ep_mmio_clear_interrupts(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	u32 i;
+
+	for (i = 0; i < MHI_MASK_ROWS_CH_DB; i++)
+		mhi_ep_mmio_write(mhi_cntrl, MHI_CHDB_INT_CLEAR_n(i),
+				   MHI_CHDB_INT_CLEAR_n_CLEAR_ALL);
+
+	for (i = 0; i < MHI_MASK_ROWS_EV_DB; i++)
+		mhi_ep_mmio_write(mhi_cntrl, MHI_ERDB_INT_CLEAR_n(i),
+				   MHI_ERDB_INT_CLEAR_n_CLEAR_ALL);
+
+	mhi_ep_mmio_write(mhi_cntrl, MHI_CTRL_INT_CLEAR,
+			   MHI_CTRL_INT_MMIO_WR_CLEAR |
+			   MHI_CTRL_INT_CRDB_CLEAR |
+			   MHI_CTRL_INT_CRDB_MHICTRL_CLEAR);
+}
+
+void mhi_ep_mmio_get_chc_base(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	u32 regval;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_CCABAP_HIGHER);
+	mhi_cntrl->ch_ctx_host_pa = regval;
+	mhi_cntrl->ch_ctx_host_pa <<= 32;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_CCABAP_LOWER);
+	mhi_cntrl->ch_ctx_host_pa |= regval;
+}
+
+void mhi_ep_mmio_get_erc_base(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	u32 regval;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_ECABAP_HIGHER);
+	mhi_cntrl->ev_ctx_host_pa = regval;
+	mhi_cntrl->ev_ctx_host_pa <<= 32;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_ECABAP_LOWER);
+	mhi_cntrl->ev_ctx_host_pa |= regval;
+}
+
+void mhi_ep_mmio_get_crc_base(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	u32 regval;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_CRCBAP_HIGHER);
+	mhi_cntrl->cmd_ctx_host_pa = regval;
+	mhi_cntrl->cmd_ctx_host_pa <<= 32;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_CRCBAP_LOWER);
+	mhi_cntrl->cmd_ctx_host_pa |= regval;
+}
+
+u64 mhi_ep_mmio_get_db(struct mhi_ep_ring *ring)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
+	u64 db_offset;
+	u32 regval;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, ring->db_offset_h);
+	db_offset = regval;
+	db_offset <<= 32;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, ring->db_offset_l);
+	db_offset |= regval;
+
+	return db_offset;
+}
+
+void mhi_ep_mmio_set_env(struct mhi_ep_cntrl *mhi_cntrl, u32 value)
+{
+	mhi_ep_mmio_write(mhi_cntrl, EP_BHI_EXECENV, value);
+}
+
+void mhi_ep_mmio_clear_reset(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_masked_write(mhi_cntrl, EP_MHICTRL, MHICTRL_RESET_MASK, 0);
+}
+
+void mhi_ep_mmio_reset(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	mhi_ep_mmio_write(mhi_cntrl, EP_MHICTRL, 0);
+	mhi_ep_mmio_write(mhi_cntrl, EP_MHISTATUS, 0);
+	mhi_ep_mmio_clear_interrupts(mhi_cntrl);
+}
+
+void mhi_ep_mmio_init(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	u32 regval;
+
+	mhi_cntrl->chdb_offset = mhi_ep_mmio_read(mhi_cntrl, EP_CHDBOFF);
+	mhi_cntrl->erdb_offset = mhi_ep_mmio_read(mhi_cntrl, EP_ERDBOFF);
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_MHICFG);
+	mhi_cntrl->event_rings = FIELD_GET(MHICFG_NER_MASK, regval);
+	mhi_cntrl->hw_event_rings = FIELD_GET(MHICFG_NHWER_MASK, regval);
+
+	mhi_ep_mmio_reset(mhi_cntrl);
+}
+
+void mhi_ep_mmio_update_ner(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	u32 regval;
+
+	regval = mhi_ep_mmio_read(mhi_cntrl, EP_MHICFG);
+	mhi_cntrl->event_rings = FIELD_GET(MHICFG_NER_MASK, regval);
+	mhi_cntrl->hw_event_rings = FIELD_GET(MHICFG_NHWER_MASK, regval);
+}
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index e2b94f9eb846..5db048e258e4 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -59,6 +59,10 @@ struct mhi_ep_db_info {
  * @mhi_event: Points to the event ring configurations table
  * @mhi_cmd: Points to the command ring configurations table
  * @sm: MHI Endpoint state machine
+ * @ch_ctx_host_pa: Physical address of host channel context data structure
+ * @ev_ctx_host_pa: Physical address of host event context data structure
+ * @cmd_ctx_host_pa: Physical address of host command context data structure
+ * @chdb: Array of channel doorbell interrupt info
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
@@ -67,6 +71,10 @@ struct mhi_ep_db_info {
  * @mhi_state: MHI Endpoint state
  * @max_chan: Maximum channels supported by the endpoint controller
  * @mru: MRU (Maximum Receive Unit) value of the endpoint controller
+ * @event_rings: Number of event rings supported by the endpoint controller
+ * @hw_event_rings: Number of hardware event rings supported by the endpoint controller
+ * @chdb_offset: Channel doorbell offset set by the host
+ * @erdb_offset: Event ring doorbell offset set by the host
  * @index: MHI Endpoint controller index
  */
 struct mhi_ep_cntrl {
@@ -79,6 +87,12 @@ struct mhi_ep_cntrl {
 	struct mhi_ep_cmd *mhi_cmd;
 	struct mhi_ep_sm *sm;
 
+	u64 ch_ctx_host_pa;
+	u64 ev_ctx_host_pa;
+	u64 cmd_ctx_host_pa;
+
+	struct mhi_ep_db_info chdb[4];
+
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
 			 void __iomem **virt, size_t size);
@@ -91,6 +105,10 @@ struct mhi_ep_cntrl {
 
 	u32 max_chan;
 	u32 mru;
+	u32 event_rings;
+	u32 hw_event_rings;
+	u32 chdb_offset;
+	u32 erdb_offset;
 	u32 index;
 };
 
-- 
cgit v1.2.3


From 961aeb6892242e0a667f5b8eb62b9b0a6041752c Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:42 +0530
Subject: bus: mhi: ep: Add support for sending events to the host

Add support for sending the events to the host over MHI bus from the
endpoint. Following events are supported:

1. Transfer completion event
2. Command completion event
3. State change event
4. Execution Environment (EE) change event

An event is sent whenever an operation has been completed in the MHI EP
device. Event is sent using the MHI event ring and additionally the host
is notified using an IRQ if required.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-7-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/common.h      | 22 +++++++++++
 drivers/bus/mhi/ep/internal.h |  4 ++
 drivers/bus/mhi/ep/main.c     | 89 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h        |  8 ++++
 4 files changed, 123 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/common.h b/drivers/bus/mhi/common.h
index b4ef9acd3ce7..f794b9c8049e 100644
--- a/drivers/bus/mhi/common.h
+++ b/drivers/bus/mhi/common.h
@@ -165,6 +165,22 @@
 #define MHI_TRE_GET_EV_LINKSPEED(tre)	FIELD_GET(GENMASK(31, 24), (MHI_TRE_GET_DWORD(tre, 1)))
 #define MHI_TRE_GET_EV_LINKWIDTH(tre)	FIELD_GET(GENMASK(7, 0), (MHI_TRE_GET_DWORD(tre, 0)))
 
+/* State change event */
+#define MHI_SC_EV_PTR			0
+#define MHI_SC_EV_DWORD0(state)		cpu_to_le32(FIELD_PREP(GENMASK(31, 24), state))
+#define MHI_SC_EV_DWORD1(type)		cpu_to_le32(FIELD_PREP(GENMASK(23, 16), type))
+
+/* EE event */
+#define MHI_EE_EV_PTR			0
+#define MHI_EE_EV_DWORD0(ee)		cpu_to_le32(FIELD_PREP(GENMASK(31, 24), ee))
+#define MHI_EE_EV_DWORD1(type)		cpu_to_le32(FIELD_PREP(GENMASK(23, 16), type))
+
+
+/* Command Completion event */
+#define MHI_CC_EV_PTR(ptr)		cpu_to_le64(ptr)
+#define MHI_CC_EV_DWORD0(code)		cpu_to_le32(FIELD_PREP(GENMASK(31, 24), code))
+#define MHI_CC_EV_DWORD1(type)		cpu_to_le32(FIELD_PREP(GENMASK(23, 16), type))
+
 /* Transfer descriptor macros */
 #define MHI_TRE_DATA_PTR(ptr)		cpu_to_le64(ptr)
 #define MHI_TRE_DATA_DWORD0(len)	cpu_to_le32(FIELD_PREP(GENMASK(15, 0), len))
@@ -175,6 +191,12 @@
 								FIELD_PREP(BIT(9), ieot) |  \
 								FIELD_PREP(BIT(8), ieob) |  \
 								FIELD_PREP(BIT(0), chain))
+#define MHI_TRE_DATA_GET_PTR(tre)	le64_to_cpu((tre)->ptr)
+#define MHI_TRE_DATA_GET_LEN(tre)	FIELD_GET(GENMASK(15, 0), MHI_TRE_GET_DWORD(tre, 0))
+#define MHI_TRE_DATA_GET_CHAIN(tre)	(!!(FIELD_GET(BIT(0), MHI_TRE_GET_DWORD(tre, 1))))
+#define MHI_TRE_DATA_GET_IEOB(tre)	(!!(FIELD_GET(BIT(8), MHI_TRE_GET_DWORD(tre, 1))))
+#define MHI_TRE_DATA_GET_IEOT(tre)	(!!(FIELD_GET(BIT(9), MHI_TRE_GET_DWORD(tre, 1))))
+#define MHI_TRE_DATA_GET_BEI(tre)	(!!(FIELD_GET(BIT(10), MHI_TRE_GET_DWORD(tre, 1))))
 
 /* RSC transfer descriptor macros */
 #define MHI_RSCTRE_DATA_PTR(ptr, len)	cpu_to_le64(FIELD_PREP(GENMASK(64, 48), len) | ptr)
diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h
index d16b87061ac6..e096d9cb2cb1 100644
--- a/drivers/bus/mhi/ep/internal.h
+++ b/drivers/bus/mhi/ep/internal.h
@@ -197,4 +197,8 @@ void mhi_ep_mmio_get_mhi_state(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state *s
 void mhi_ep_mmio_init(struct mhi_ep_cntrl *mhi_cntrl);
 void mhi_ep_mmio_update_ner(struct mhi_ep_cntrl *mhi_cntrl);
 
+/* MHI EP core functions */
+int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state state);
+int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_env);
+
 #endif
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 7dcc784f10d1..eca1f58ba5fb 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -18,6 +18,93 @@
 
 static DEFINE_IDA(mhi_ep_cntrl_ida);
 
+static int mhi_ep_send_event(struct mhi_ep_cntrl *mhi_cntrl, u32 ring_idx,
+			     struct mhi_ring_element *el, bool bei)
+{
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	union mhi_ep_ring_ctx *ctx;
+	struct mhi_ep_ring *ring;
+	int ret;
+
+	mutex_lock(&mhi_cntrl->event_lock);
+	ring = &mhi_cntrl->mhi_event[ring_idx].ring;
+	ctx = (union mhi_ep_ring_ctx *)&mhi_cntrl->ev_ctx_cache[ring_idx];
+	if (!ring->started) {
+		ret = mhi_ep_ring_start(mhi_cntrl, ring, ctx);
+		if (ret) {
+			dev_err(dev, "Error starting event ring (%u)\n", ring_idx);
+			goto err_unlock;
+		}
+	}
+
+	/* Add element to the event ring */
+	ret = mhi_ep_ring_add_element(ring, el);
+	if (ret) {
+		dev_err(dev, "Error adding element to event ring (%u)\n", ring_idx);
+		goto err_unlock;
+	}
+
+	mutex_unlock(&mhi_cntrl->event_lock);
+
+	/*
+	 * Raise IRQ to host only if the BEI flag is not set in TRE. Host might
+	 * set this flag for interrupt moderation as per MHI protocol.
+	 */
+	if (!bei)
+		mhi_cntrl->raise_irq(mhi_cntrl, ring->irq_vector);
+
+	return 0;
+
+err_unlock:
+	mutex_unlock(&mhi_cntrl->event_lock);
+
+	return ret;
+}
+
+static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
+					struct mhi_ring_element *tre, u32 len, enum mhi_ev_ccs code)
+{
+	struct mhi_ring_element event = {};
+
+	event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre));
+	event.dword[0] = MHI_TRE_EV_DWORD0(code, len);
+	event.dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
+
+	return mhi_ep_send_event(mhi_cntrl, ring->er_index, &event, MHI_TRE_DATA_GET_BEI(tre));
+}
+
+int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state state)
+{
+	struct mhi_ring_element event = {};
+
+	event.dword[0] = MHI_SC_EV_DWORD0(state);
+	event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
+
+	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+}
+
+int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_env)
+{
+	struct mhi_ring_element event = {};
+
+	event.dword[0] = MHI_EE_EV_DWORD0(exec_env);
+	event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
+
+	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+}
+
+static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ev_ccs code)
+{
+	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_cmd->ring;
+	struct mhi_ring_element event = {};
+
+	event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element));
+	event.dword[0] = MHI_CC_EV_DWORD0(code);
+	event.dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
+
+	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+}
+
 static void mhi_ep_release_device(struct device *dev)
 {
 	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
@@ -227,6 +314,8 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		goto err_free_ch;
 	}
 
+	mutex_init(&mhi_cntrl->event_lock);
+
 	/* Set MHI version and AMSS EE before enumeration */
 	mhi_ep_mmio_write(mhi_cntrl, EP_MHIVER, config->mhi_version);
 	mhi_ep_mmio_set_env(mhi_cntrl, MHI_EE_AMSS);
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 5db048e258e4..46236ffb528a 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -59,10 +59,14 @@ struct mhi_ep_db_info {
  * @mhi_event: Points to the event ring configurations table
  * @mhi_cmd: Points to the command ring configurations table
  * @sm: MHI Endpoint state machine
+ * @ch_ctx_cache: Cache of host channel context data structure
+ * @ev_ctx_cache: Cache of host event context data structure
+ * @cmd_ctx_cache: Cache of host command context data structure
  * @ch_ctx_host_pa: Physical address of host channel context data structure
  * @ev_ctx_host_pa: Physical address of host event context data structure
  * @cmd_ctx_host_pa: Physical address of host command context data structure
  * @chdb: Array of channel doorbell interrupt info
+ * @event_lock: Lock for protecting event rings
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
@@ -87,11 +91,15 @@ struct mhi_ep_cntrl {
 	struct mhi_ep_cmd *mhi_cmd;
 	struct mhi_ep_sm *sm;
 
+	struct mhi_chan_ctxt *ch_ctx_cache;
+	struct mhi_event_ctxt *ev_ctx_cache;
+	struct mhi_cmd_ctxt *cmd_ctx_cache;
 	u64 ch_ctx_host_pa;
 	u64 ev_ctx_host_pa;
 	u64 cmd_ctx_host_pa;
 
 	struct mhi_ep_db_info chdb[4];
+	struct mutex event_lock;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
-- 
cgit v1.2.3


From f9baa4f737950523ca648866dfa345ac378e4487 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:43 +0530
Subject: bus: mhi: ep: Add support for managing MHI state machine

Add support for managing the MHI state machine by controlling the state
transitions. Only the following MHI state transitions are supported:

1. Ready state
2. M0 state
3. M3 state
4. SYS_ERR state

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-8-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/Makefile   |   2 +-
 drivers/bus/mhi/ep/internal.h |  11 ++++
 drivers/bus/mhi/ep/main.c     |  54 ++++++++++++++++-
 drivers/bus/mhi/ep/sm.c       | 136 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h        |  12 ++++
 5 files changed, 213 insertions(+), 2 deletions(-)
 create mode 100644 drivers/bus/mhi/ep/sm.c

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/Makefile b/drivers/bus/mhi/ep/Makefile
index 7ba0e04801eb..aad85f180b70 100644
--- a/drivers/bus/mhi/ep/Makefile
+++ b/drivers/bus/mhi/ep/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_MHI_BUS_EP) += mhi_ep.o
-mhi_ep-y := main.o mmio.o ring.o
+mhi_ep-y := main.o mmio.o ring.o sm.o
diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h
index e096d9cb2cb1..4f2e26841702 100644
--- a/drivers/bus/mhi/ep/internal.h
+++ b/drivers/bus/mhi/ep/internal.h
@@ -146,6 +146,11 @@ struct mhi_ep_event {
 	struct mhi_ep_ring ring;
 };
 
+struct mhi_ep_state_transition {
+	struct list_head node;
+	enum mhi_state state;
+};
+
 struct mhi_ep_chan {
 	char *name;
 	struct mhi_ep_device *mhi_dev;
@@ -200,5 +205,11 @@ void mhi_ep_mmio_update_ner(struct mhi_ep_cntrl *mhi_cntrl);
 /* MHI EP core functions */
 int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state state);
 int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_env);
+bool mhi_ep_check_mhi_state(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state cur_mhi_state,
+			    enum mhi_state mhi_state);
+int mhi_ep_set_mhi_state(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state mhi_state);
+int mhi_ep_set_m0_state(struct mhi_ep_cntrl *mhi_cntrl);
+int mhi_ep_set_m3_state(struct mhi_ep_cntrl *mhi_cntrl);
+int mhi_ep_set_ready_state(struct mhi_ep_cntrl *mhi_cntrl);
 
 #endif
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index eca1f58ba5fb..c912daf6dc65 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -105,6 +105,43 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
 }
 
+static void mhi_ep_state_worker(struct work_struct *work)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, state_work);
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	struct mhi_ep_state_transition *itr, *tmp;
+	unsigned long flags;
+	LIST_HEAD(head);
+	int ret;
+
+	spin_lock_irqsave(&mhi_cntrl->list_lock, flags);
+	list_splice_tail_init(&mhi_cntrl->st_transition_list, &head);
+	spin_unlock_irqrestore(&mhi_cntrl->list_lock, flags);
+
+	list_for_each_entry_safe(itr, tmp, &head, node) {
+		list_del(&itr->node);
+		dev_dbg(dev, "Handling MHI state transition to %s\n",
+			 mhi_state_str(itr->state));
+
+		switch (itr->state) {
+		case MHI_STATE_M0:
+			ret = mhi_ep_set_m0_state(mhi_cntrl);
+			if (ret)
+				dev_err(dev, "Failed to transition to M0 state\n");
+			break;
+		case MHI_STATE_M3:
+			ret = mhi_ep_set_m3_state(mhi_cntrl);
+			if (ret)
+				dev_err(dev, "Failed to transition to M3 state\n");
+			break;
+		default:
+			dev_err(dev, "Invalid MHI state transition: %d\n", itr->state);
+			break;
+		}
+		kfree(itr);
+	}
+}
+
 static void mhi_ep_release_device(struct device *dev)
 {
 	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
@@ -314,6 +351,17 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		goto err_free_ch;
 	}
 
+	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
+
+	mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0);
+	if (!mhi_cntrl->wq) {
+		ret = -ENOMEM;
+		goto err_free_cmd;
+	}
+
+	INIT_LIST_HEAD(&mhi_cntrl->st_transition_list);
+	spin_lock_init(&mhi_cntrl->state_lock);
+	spin_lock_init(&mhi_cntrl->list_lock);
 	mutex_init(&mhi_cntrl->event_lock);
 
 	/* Set MHI version and AMSS EE before enumeration */
@@ -323,7 +371,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	/* Set controller index */
 	ret = ida_alloc(&mhi_ep_cntrl_ida, GFP_KERNEL);
 	if (ret < 0)
-		goto err_free_cmd;
+		goto err_destroy_wq;
 
 	mhi_cntrl->index = ret;
 
@@ -351,6 +399,8 @@ err_put_dev:
 	put_device(&mhi_dev->dev);
 err_ida_free:
 	ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index);
+err_destroy_wq:
+	destroy_workqueue(mhi_cntrl->wq);
 err_free_cmd:
 	kfree(mhi_cntrl->mhi_cmd);
 err_free_ch:
@@ -364,6 +414,8 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
 {
 	struct mhi_ep_device *mhi_dev = mhi_cntrl->mhi_dev;
 
+	destroy_workqueue(mhi_cntrl->wq);
+
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_chan);
 
diff --git a/drivers/bus/mhi/ep/sm.c b/drivers/bus/mhi/ep/sm.c
new file mode 100644
index 000000000000..ffc02f5d0a0d
--- /dev/null
+++ b/drivers/bus/mhi/ep/sm.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Linaro Ltd.
+ * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+ */
+
+#include <linux/errno.h>
+#include <linux/mhi_ep.h>
+#include "internal.h"
+
+bool __must_check mhi_ep_check_mhi_state(struct mhi_ep_cntrl *mhi_cntrl,
+					 enum mhi_state cur_mhi_state,
+					 enum mhi_state mhi_state)
+{
+	if (mhi_state == MHI_STATE_SYS_ERR)
+		return true;    /* Allowed in any state */
+
+	if (mhi_state == MHI_STATE_READY)
+		return cur_mhi_state == MHI_STATE_RESET;
+
+	if (mhi_state == MHI_STATE_M0)
+		return cur_mhi_state == MHI_STATE_M3 || cur_mhi_state == MHI_STATE_READY;
+
+	if (mhi_state == MHI_STATE_M3)
+		return cur_mhi_state == MHI_STATE_M0;
+
+	return false;
+}
+
+int mhi_ep_set_mhi_state(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state mhi_state)
+{
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+
+	if (!mhi_ep_check_mhi_state(mhi_cntrl, mhi_cntrl->mhi_state, mhi_state)) {
+		dev_err(dev, "MHI state change to %s from %s is not allowed!\n",
+			mhi_state_str(mhi_state),
+			mhi_state_str(mhi_cntrl->mhi_state));
+		return -EACCES;
+	}
+
+	/* TODO: Add support for M1 and M2 states */
+	if (mhi_state == MHI_STATE_M1 || mhi_state == MHI_STATE_M2) {
+		dev_err(dev, "MHI state (%s) not supported\n", mhi_state_str(mhi_state));
+		return -EOPNOTSUPP;
+	}
+
+	mhi_ep_mmio_masked_write(mhi_cntrl, EP_MHISTATUS, MHISTATUS_MHISTATE_MASK, mhi_state);
+	mhi_cntrl->mhi_state = mhi_state;
+
+	if (mhi_state == MHI_STATE_READY)
+		mhi_ep_mmio_masked_write(mhi_cntrl, EP_MHISTATUS, MHISTATUS_READY_MASK, 1);
+
+	if (mhi_state == MHI_STATE_SYS_ERR)
+		mhi_ep_mmio_masked_write(mhi_cntrl, EP_MHISTATUS, MHISTATUS_SYSERR_MASK, 1);
+
+	return 0;
+}
+
+int mhi_ep_set_m0_state(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	enum mhi_state old_state;
+	int ret;
+
+	spin_lock_bh(&mhi_cntrl->state_lock);
+	old_state = mhi_cntrl->mhi_state;
+
+	ret = mhi_ep_set_mhi_state(mhi_cntrl, MHI_STATE_M0);
+	spin_unlock_bh(&mhi_cntrl->state_lock);
+
+	if (ret)
+		return ret;
+
+	/* Signal host that the device moved to M0 */
+	ret = mhi_ep_send_state_change_event(mhi_cntrl, MHI_STATE_M0);
+	if (ret) {
+		dev_err(dev, "Failed sending M0 state change event\n");
+		return ret;
+	}
+
+	if (old_state == MHI_STATE_READY) {
+		/* Send AMSS EE event to host */
+		ret = mhi_ep_send_ee_event(mhi_cntrl, MHI_EE_AMSS);
+		if (ret) {
+			dev_err(dev, "Failed sending AMSS EE event\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+int mhi_ep_set_m3_state(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	int ret;
+
+	spin_lock_bh(&mhi_cntrl->state_lock);
+	ret = mhi_ep_set_mhi_state(mhi_cntrl, MHI_STATE_M3);
+	spin_unlock_bh(&mhi_cntrl->state_lock);
+
+	if (ret)
+		return ret;
+
+	/* Signal host that the device moved to M3 */
+	ret = mhi_ep_send_state_change_event(mhi_cntrl, MHI_STATE_M3);
+	if (ret) {
+		dev_err(dev, "Failed sending M3 state change event\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+int mhi_ep_set_ready_state(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	enum mhi_state mhi_state;
+	int ret, is_ready;
+
+	spin_lock_bh(&mhi_cntrl->state_lock);
+	/* Ensure that the MHISTATUS is set to RESET by host */
+	mhi_state = mhi_ep_mmio_masked_read(mhi_cntrl, EP_MHISTATUS, MHISTATUS_MHISTATE_MASK);
+	is_ready = mhi_ep_mmio_masked_read(mhi_cntrl, EP_MHISTATUS, MHISTATUS_READY_MASK);
+
+	if (mhi_state != MHI_STATE_RESET || is_ready) {
+		dev_err(dev, "READY state transition failed. MHI host not in RESET state\n");
+		spin_unlock_bh(&mhi_cntrl->state_lock);
+		return -EIO;
+	}
+
+	ret = mhi_ep_set_mhi_state(mhi_cntrl, MHI_STATE_READY);
+	spin_unlock_bh(&mhi_cntrl->state_lock);
+
+	return ret;
+}
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 46236ffb528a..2880d2aa88b8 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -67,6 +67,11 @@ struct mhi_ep_db_info {
  * @cmd_ctx_host_pa: Physical address of host command context data structure
  * @chdb: Array of channel doorbell interrupt info
  * @event_lock: Lock for protecting event rings
+ * @list_lock: Lock for protecting state transition and channel doorbell lists
+ * @state_lock: Lock for protecting state transitions
+ * @st_transition_list: List of state transitions
+ * @wq: Dedicated workqueue for handling rings and state changes
+ * @state_work: State transition worker
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
@@ -100,6 +105,13 @@ struct mhi_ep_cntrl {
 
 	struct mhi_ep_db_info chdb[4];
 	struct mutex event_lock;
+	spinlock_t list_lock;
+	spinlock_t state_lock;
+
+	struct list_head st_transition_list;
+
+	struct workqueue_struct *wq;
+	struct work_struct state_work;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
-- 
cgit v1.2.3


From 4799e71b082615445dc40ba0bbb86cbb76c24724 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:44 +0530
Subject: bus: mhi: ep: Add support for processing MHI endpoint interrupts

Add support for processing MHI endpoint interrupts such as control
interrupt, command interrupt and channel interrupt from the host.

The interrupts will be generated in the endpoint device whenever host
writes to the corresponding doorbell registers. The doorbell logic
is handled inside the hardware internally.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-9-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 124 +++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/mhi_ep.h    |   4 ++
 2 files changed, 126 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index c912daf6dc65..4e82006bd83b 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -11,6 +11,7 @@
 #include <linux/dma-direction.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/mhi_ep.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
@@ -142,6 +143,112 @@ static void mhi_ep_state_worker(struct work_struct *work)
 	}
 }
 
+static void mhi_ep_queue_channel_db(struct mhi_ep_cntrl *mhi_cntrl, unsigned long ch_int,
+				    u32 ch_idx)
+{
+	struct mhi_ep_ring_item *item;
+	struct mhi_ep_ring *ring;
+	bool work = !!ch_int;
+	LIST_HEAD(head);
+	u32 i;
+
+	/* First add the ring items to a local list */
+	for_each_set_bit(i, &ch_int, 32) {
+		/* Channel index varies for each register: 0, 32, 64, 96 */
+		u32 ch_id = ch_idx + i;
+
+		ring = &mhi_cntrl->mhi_chan[ch_id].ring;
+		item = kzalloc(sizeof(*item), GFP_ATOMIC);
+		if (!item)
+			return;
+
+		item->ring = ring;
+		list_add_tail(&item->node, &head);
+	}
+
+	/* Now, splice the local list into ch_db_list and queue the work item */
+	if (work) {
+		spin_lock(&mhi_cntrl->list_lock);
+		list_splice_tail_init(&head, &mhi_cntrl->ch_db_list);
+		spin_unlock(&mhi_cntrl->list_lock);
+	}
+}
+
+/*
+ * Channel interrupt statuses are contained in 4 registers each of 32bit length.
+ * For checking all interrupts, we need to loop through each registers and then
+ * check for bits set.
+ */
+static void mhi_ep_check_channel_interrupt(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	u32 ch_int, ch_idx, i;
+
+	/* Bail out if there is no channel doorbell interrupt */
+	if (!mhi_ep_mmio_read_chdb_status_interrupts(mhi_cntrl))
+		return;
+
+	for (i = 0; i < MHI_MASK_ROWS_CH_DB; i++) {
+		ch_idx = i * MHI_MASK_CH_LEN;
+
+		/* Only process channel interrupt if the mask is enabled */
+		ch_int = mhi_cntrl->chdb[i].status & mhi_cntrl->chdb[i].mask;
+		if (ch_int) {
+			mhi_ep_queue_channel_db(mhi_cntrl, ch_int, ch_idx);
+			mhi_ep_mmio_write(mhi_cntrl, MHI_CHDB_INT_CLEAR_n(i),
+							mhi_cntrl->chdb[i].status);
+		}
+	}
+}
+
+static void mhi_ep_process_ctrl_interrupt(struct mhi_ep_cntrl *mhi_cntrl,
+					 enum mhi_state state)
+{
+	struct mhi_ep_state_transition *item;
+
+	item = kzalloc(sizeof(*item), GFP_ATOMIC);
+	if (!item)
+		return;
+
+	item->state = state;
+	spin_lock(&mhi_cntrl->list_lock);
+	list_add_tail(&item->node, &mhi_cntrl->st_transition_list);
+	spin_unlock(&mhi_cntrl->list_lock);
+
+	queue_work(mhi_cntrl->wq, &mhi_cntrl->state_work);
+}
+
+/*
+ * Interrupt handler that services interrupts raised by the host writing to
+ * MHICTRL and Command ring doorbell (CRDB) registers for state change and
+ * channel interrupts.
+ */
+static irqreturn_t mhi_ep_irq(int irq, void *data)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = data;
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	enum mhi_state state;
+	u32 int_value;
+
+	/* Acknowledge the ctrl interrupt */
+	int_value = mhi_ep_mmio_read(mhi_cntrl, MHI_CTRL_INT_STATUS);
+	mhi_ep_mmio_write(mhi_cntrl, MHI_CTRL_INT_CLEAR, int_value);
+
+	/* Check for ctrl interrupt */
+	if (FIELD_GET(MHI_CTRL_INT_STATUS_MSK, int_value)) {
+		dev_dbg(dev, "Processing ctrl interrupt\n");
+		mhi_ep_process_ctrl_interrupt(mhi_cntrl, state);
+	}
+
+	/* Check for command doorbell interrupt */
+	if (FIELD_GET(MHI_CTRL_INT_STATUS_CRDB_MSK, int_value))
+		dev_dbg(dev, "Processing command doorbell interrupt\n");
+
+	/* Check for channel interrupts */
+	mhi_ep_check_channel_interrupt(mhi_cntrl);
+
+	return IRQ_HANDLED;
+}
+
 static void mhi_ep_release_device(struct device *dev)
 {
 	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
@@ -338,7 +445,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	struct mhi_ep_device *mhi_dev;
 	int ret;
 
-	if (!mhi_cntrl || !mhi_cntrl->cntrl_dev || !mhi_cntrl->mmio)
+	if (!mhi_cntrl || !mhi_cntrl->cntrl_dev || !mhi_cntrl->mmio || !mhi_cntrl->irq)
 		return -EINVAL;
 
 	ret = mhi_ep_chan_init(mhi_cntrl, config);
@@ -360,6 +467,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	}
 
 	INIT_LIST_HEAD(&mhi_cntrl->st_transition_list);
+	INIT_LIST_HEAD(&mhi_cntrl->ch_db_list);
 	spin_lock_init(&mhi_cntrl->state_lock);
 	spin_lock_init(&mhi_cntrl->list_lock);
 	mutex_init(&mhi_cntrl->event_lock);
@@ -375,12 +483,20 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 
 	mhi_cntrl->index = ret;
 
+	irq_set_status_flags(mhi_cntrl->irq, IRQ_NOAUTOEN);
+	ret = request_irq(mhi_cntrl->irq, mhi_ep_irq, IRQF_TRIGGER_HIGH,
+			  "doorbell_irq", mhi_cntrl);
+	if (ret) {
+		dev_err(mhi_cntrl->cntrl_dev, "Failed to request Doorbell IRQ\n");
+		goto err_ida_free;
+	}
+
 	/* Allocate the controller device */
 	mhi_dev = mhi_ep_alloc_device(mhi_cntrl, MHI_DEVICE_CONTROLLER);
 	if (IS_ERR(mhi_dev)) {
 		dev_err(mhi_cntrl->cntrl_dev, "Failed to allocate controller device\n");
 		ret = PTR_ERR(mhi_dev);
-		goto err_ida_free;
+		goto err_free_irq;
 	}
 
 	dev_set_name(&mhi_dev->dev, "mhi_ep%u", mhi_cntrl->index);
@@ -397,6 +513,8 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 
 err_put_dev:
 	put_device(&mhi_dev->dev);
+err_free_irq:
+	free_irq(mhi_cntrl->irq, mhi_cntrl);
 err_ida_free:
 	ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index);
 err_destroy_wq:
@@ -416,6 +534,8 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
 
 	destroy_workqueue(mhi_cntrl->wq);
 
+	free_irq(mhi_cntrl->irq, mhi_cntrl);
+
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_chan);
 
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 2880d2aa88b8..137bd3ee2e43 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -70,6 +70,7 @@ struct mhi_ep_db_info {
  * @list_lock: Lock for protecting state transition and channel doorbell lists
  * @state_lock: Lock for protecting state transitions
  * @st_transition_list: List of state transitions
+ * @ch_db_list: List of queued channel doorbells
  * @wq: Dedicated workqueue for handling rings and state changes
  * @state_work: State transition worker
  * @raise_irq: CB function for raising IRQ to the host
@@ -85,6 +86,7 @@ struct mhi_ep_db_info {
  * @chdb_offset: Channel doorbell offset set by the host
  * @erdb_offset: Event ring doorbell offset set by the host
  * @index: MHI Endpoint controller index
+ * @irq: IRQ used by the endpoint controller
  */
 struct mhi_ep_cntrl {
 	struct device *cntrl_dev;
@@ -109,6 +111,7 @@ struct mhi_ep_cntrl {
 	spinlock_t state_lock;
 
 	struct list_head st_transition_list;
+	struct list_head ch_db_list;
 
 	struct workqueue_struct *wq;
 	struct work_struct state_work;
@@ -130,6 +133,7 @@ struct mhi_ep_cntrl {
 	u32 chdb_offset;
 	u32 erdb_offset;
 	u32 index;
+	int irq;
 };
 
 /**
-- 
cgit v1.2.3


From fb3a26b7e8aff11e44d582604f61c38f63bd507c Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:45 +0530
Subject: bus: mhi: ep: Add support for powering up the MHI endpoint stack

Add support for MHI endpoint power_up that includes initializing the MMIO
and rings, caching the host MHI registers, and setting the MHI state to M0.
After registering the MHI EP controller, the stack has to be powered up
for usage.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-10-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 205 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h    |  16 ++++
 2 files changed, 221 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 4e82006bd83b..20d579733486 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -17,6 +17,9 @@
 #include <linux/module.h>
 #include "internal.h"
 
+#define M0_WAIT_DELAY_MS	100
+#define M0_WAIT_COUNT		100
+
 static DEFINE_IDA(mhi_ep_cntrl_ida);
 
 static int mhi_ep_send_event(struct mhi_ep_cntrl *mhi_cntrl, u32 ring_idx,
@@ -106,6 +109,154 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
 }
 
+static int mhi_ep_cache_host_cfg(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	size_t cmd_ctx_host_size, ch_ctx_host_size, ev_ctx_host_size;
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	int ret;
+
+	/* Update the number of event rings (NER) programmed by the host */
+	mhi_ep_mmio_update_ner(mhi_cntrl);
+
+	dev_dbg(dev, "Number of Event rings: %u, HW Event rings: %u\n",
+		 mhi_cntrl->event_rings, mhi_cntrl->hw_event_rings);
+
+	ch_ctx_host_size = sizeof(struct mhi_chan_ctxt) * mhi_cntrl->max_chan;
+	ev_ctx_host_size = sizeof(struct mhi_event_ctxt) * mhi_cntrl->event_rings;
+	cmd_ctx_host_size = sizeof(struct mhi_cmd_ctxt) * NR_OF_CMD_RINGS;
+
+	/* Get the channel context base pointer from host */
+	mhi_ep_mmio_get_chc_base(mhi_cntrl);
+
+	/* Allocate and map memory for caching host channel context */
+	ret = mhi_cntrl->alloc_map(mhi_cntrl, mhi_cntrl->ch_ctx_host_pa,
+				   &mhi_cntrl->ch_ctx_cache_phys,
+				   (void __iomem **) &mhi_cntrl->ch_ctx_cache,
+				   ch_ctx_host_size);
+	if (ret) {
+		dev_err(dev, "Failed to allocate and map ch_ctx_cache\n");
+		return ret;
+	}
+
+	/* Get the event context base pointer from host */
+	mhi_ep_mmio_get_erc_base(mhi_cntrl);
+
+	/* Allocate and map memory for caching host event context */
+	ret = mhi_cntrl->alloc_map(mhi_cntrl, mhi_cntrl->ev_ctx_host_pa,
+				   &mhi_cntrl->ev_ctx_cache_phys,
+				   (void __iomem **) &mhi_cntrl->ev_ctx_cache,
+				   ev_ctx_host_size);
+	if (ret) {
+		dev_err(dev, "Failed to allocate and map ev_ctx_cache\n");
+		goto err_ch_ctx;
+	}
+
+	/* Get the command context base pointer from host */
+	mhi_ep_mmio_get_crc_base(mhi_cntrl);
+
+	/* Allocate and map memory for caching host command context */
+	ret = mhi_cntrl->alloc_map(mhi_cntrl, mhi_cntrl->cmd_ctx_host_pa,
+				   &mhi_cntrl->cmd_ctx_cache_phys,
+				   (void __iomem **) &mhi_cntrl->cmd_ctx_cache,
+				   cmd_ctx_host_size);
+	if (ret) {
+		dev_err(dev, "Failed to allocate and map cmd_ctx_cache\n");
+		goto err_ev_ctx;
+	}
+
+	/* Initialize command ring */
+	ret = mhi_ep_ring_start(mhi_cntrl, &mhi_cntrl->mhi_cmd->ring,
+				(union mhi_ep_ring_ctx *)mhi_cntrl->cmd_ctx_cache);
+	if (ret) {
+		dev_err(dev, "Failed to start the command ring\n");
+		goto err_cmd_ctx;
+	}
+
+	return ret;
+
+err_cmd_ctx:
+	mhi_cntrl->unmap_free(mhi_cntrl, mhi_cntrl->cmd_ctx_host_pa, mhi_cntrl->cmd_ctx_cache_phys,
+			      (void __iomem *) mhi_cntrl->cmd_ctx_cache, cmd_ctx_host_size);
+
+err_ev_ctx:
+	mhi_cntrl->unmap_free(mhi_cntrl, mhi_cntrl->ev_ctx_host_pa, mhi_cntrl->ev_ctx_cache_phys,
+			      (void __iomem *) mhi_cntrl->ev_ctx_cache, ev_ctx_host_size);
+
+err_ch_ctx:
+	mhi_cntrl->unmap_free(mhi_cntrl, mhi_cntrl->ch_ctx_host_pa, mhi_cntrl->ch_ctx_cache_phys,
+			      (void __iomem *) mhi_cntrl->ch_ctx_cache, ch_ctx_host_size);
+
+	return ret;
+}
+
+static void mhi_ep_free_host_cfg(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	size_t cmd_ctx_host_size, ch_ctx_host_size, ev_ctx_host_size;
+
+	ch_ctx_host_size = sizeof(struct mhi_chan_ctxt) * mhi_cntrl->max_chan;
+	ev_ctx_host_size = sizeof(struct mhi_event_ctxt) * mhi_cntrl->event_rings;
+	cmd_ctx_host_size = sizeof(struct mhi_cmd_ctxt) * NR_OF_CMD_RINGS;
+
+	mhi_cntrl->unmap_free(mhi_cntrl, mhi_cntrl->cmd_ctx_host_pa, mhi_cntrl->cmd_ctx_cache_phys,
+			      (void __iomem *) mhi_cntrl->cmd_ctx_cache, cmd_ctx_host_size);
+
+	mhi_cntrl->unmap_free(mhi_cntrl, mhi_cntrl->ev_ctx_host_pa, mhi_cntrl->ev_ctx_cache_phys,
+			      (void __iomem *) mhi_cntrl->ev_ctx_cache, ev_ctx_host_size);
+
+	mhi_cntrl->unmap_free(mhi_cntrl, mhi_cntrl->ch_ctx_host_pa, mhi_cntrl->ch_ctx_cache_phys,
+			      (void __iomem *) mhi_cntrl->ch_ctx_cache, ch_ctx_host_size);
+}
+
+static void mhi_ep_enable_int(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	/*
+	 * Doorbell interrupts are enabled when the corresponding channel gets started.
+	 * Enabling all interrupts here triggers spurious irqs as some of the interrupts
+	 * associated with hw channels always get triggered.
+	 */
+	mhi_ep_mmio_enable_ctrl_interrupt(mhi_cntrl);
+	mhi_ep_mmio_enable_cmdb_interrupt(mhi_cntrl);
+}
+
+static int mhi_ep_enable(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	enum mhi_state state;
+	bool mhi_reset;
+	u32 count = 0;
+	int ret;
+
+	/* Wait for Host to set the M0 state */
+	do {
+		msleep(M0_WAIT_DELAY_MS);
+		mhi_ep_mmio_get_mhi_state(mhi_cntrl, &state, &mhi_reset);
+		if (mhi_reset) {
+			/* Clear the MHI reset if host is in reset state */
+			mhi_ep_mmio_clear_reset(mhi_cntrl);
+			dev_info(dev, "Detected Host reset while waiting for M0\n");
+		}
+		count++;
+	} while (state != MHI_STATE_M0 && count < M0_WAIT_COUNT);
+
+	if (state != MHI_STATE_M0) {
+		dev_err(dev, "Host failed to enter M0\n");
+		return -ETIMEDOUT;
+	}
+
+	ret = mhi_ep_cache_host_cfg(mhi_cntrl);
+	if (ret) {
+		dev_err(dev, "Failed to cache host config\n");
+		return ret;
+	}
+
+	mhi_ep_mmio_set_env(mhi_cntrl, MHI_EE_AMSS);
+
+	/* Enable all interrupts now */
+	mhi_ep_enable_int(mhi_cntrl);
+
+	return 0;
+}
+
 static void mhi_ep_state_worker(struct work_struct *work)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, state_work);
@@ -249,6 +400,60 @@ static irqreturn_t mhi_ep_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	int ret, i;
+
+	/*
+	 * Mask all interrupts until the state machine is ready. Interrupts will
+	 * be enabled later with mhi_ep_enable().
+	 */
+	mhi_ep_mmio_mask_interrupts(mhi_cntrl);
+	mhi_ep_mmio_init(mhi_cntrl);
+
+	mhi_cntrl->mhi_event = kzalloc(mhi_cntrl->event_rings * (sizeof(*mhi_cntrl->mhi_event)),
+					GFP_KERNEL);
+	if (!mhi_cntrl->mhi_event)
+		return -ENOMEM;
+
+	/* Initialize command, channel and event rings */
+	mhi_ep_ring_init(&mhi_cntrl->mhi_cmd->ring, RING_TYPE_CMD, 0);
+	for (i = 0; i < mhi_cntrl->max_chan; i++)
+		mhi_ep_ring_init(&mhi_cntrl->mhi_chan[i].ring, RING_TYPE_CH, i);
+	for (i = 0; i < mhi_cntrl->event_rings; i++)
+		mhi_ep_ring_init(&mhi_cntrl->mhi_event[i].ring, RING_TYPE_ER, i);
+
+	mhi_cntrl->mhi_state = MHI_STATE_RESET;
+
+	/* Set AMSS EE before signaling ready state */
+	mhi_ep_mmio_set_env(mhi_cntrl, MHI_EE_AMSS);
+
+	/* All set, notify the host that we are ready */
+	ret = mhi_ep_set_ready_state(mhi_cntrl);
+	if (ret)
+		goto err_free_event;
+
+	dev_dbg(dev, "READY state notification sent to the host\n");
+
+	ret = mhi_ep_enable(mhi_cntrl);
+	if (ret) {
+		dev_err(dev, "Failed to enable MHI endpoint\n");
+		goto err_free_event;
+	}
+
+	enable_irq(mhi_cntrl->irq);
+	mhi_cntrl->enabled = true;
+
+	return 0;
+
+err_free_event:
+	kfree(mhi_cntrl->mhi_event);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mhi_ep_power_up);
+
 static void mhi_ep_release_device(struct device *dev)
 {
 	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 137bd3ee2e43..3b065f82fbeb 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -65,6 +65,9 @@ struct mhi_ep_db_info {
  * @ch_ctx_host_pa: Physical address of host channel context data structure
  * @ev_ctx_host_pa: Physical address of host event context data structure
  * @cmd_ctx_host_pa: Physical address of host command context data structure
+ * @ch_ctx_cache_phys: Physical address of the host channel context cache
+ * @ev_ctx_cache_phys: Physical address of the host event context cache
+ * @cmd_ctx_cache_phys: Physical address of the host command context cache
  * @chdb: Array of channel doorbell interrupt info
  * @event_lock: Lock for protecting event rings
  * @list_lock: Lock for protecting state transition and channel doorbell lists
@@ -87,6 +90,7 @@ struct mhi_ep_db_info {
  * @erdb_offset: Event ring doorbell offset set by the host
  * @index: MHI Endpoint controller index
  * @irq: IRQ used by the endpoint controller
+ * @enabled: Check if the endpoint controller is enabled or not
  */
 struct mhi_ep_cntrl {
 	struct device *cntrl_dev;
@@ -104,6 +108,9 @@ struct mhi_ep_cntrl {
 	u64 ch_ctx_host_pa;
 	u64 ev_ctx_host_pa;
 	u64 cmd_ctx_host_pa;
+	phys_addr_t ch_ctx_cache_phys;
+	phys_addr_t ev_ctx_cache_phys;
+	phys_addr_t cmd_ctx_cache_phys;
 
 	struct mhi_ep_db_info chdb[4];
 	struct mutex event_lock;
@@ -134,6 +141,7 @@ struct mhi_ep_cntrl {
 	u32 erdb_offset;
 	u32 index;
 	int irq;
+	bool enabled;
 };
 
 /**
@@ -228,4 +236,12 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
  */
 void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl);
 
+/**
+ * mhi_ep_power_up - Power up the MHI endpoint stack
+ * @mhi_cntrl: MHI Endpoint controller
+ *
+ * Return: 0 if power up succeeds, a negative error code otherwise.
+ */
+int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl);
+
 #endif
-- 
cgit v1.2.3


From 5d507ee04894e166f8c5a29f05c6b06ce91d5833 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:46 +0530
Subject: bus: mhi: ep: Add support for powering down the MHI endpoint stack

Add support for MHI endpoint power_down that includes stopping all
available channels, destroying the channels, resetting the event and
transfer rings and freeing the host cache.

The stack will be powered down whenever the physical bus link goes down.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-11-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h    |  6 ++++
 2 files changed, 84 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 20d579733486..968025e4d3ac 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -22,6 +22,8 @@
 
 static DEFINE_IDA(mhi_ep_cntrl_ida);
 
+static int mhi_ep_destroy_device(struct device *dev, void *data);
+
 static int mhi_ep_send_event(struct mhi_ep_cntrl *mhi_cntrl, u32 ring_idx,
 			     struct mhi_ring_element *el, bool bei)
 {
@@ -400,6 +402,68 @@ static irqreturn_t mhi_ep_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static void mhi_ep_abort_transfer(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	struct mhi_ep_ring *ch_ring, *ev_ring;
+	struct mhi_result result = {};
+	struct mhi_ep_chan *mhi_chan;
+	int i;
+
+	/* Stop all the channels */
+	for (i = 0; i < mhi_cntrl->max_chan; i++) {
+		mhi_chan = &mhi_cntrl->mhi_chan[i];
+		if (!mhi_chan->ring.started)
+			continue;
+
+		mutex_lock(&mhi_chan->lock);
+		/* Send channel disconnect status to client drivers */
+		if (mhi_chan->xfer_cb) {
+			result.transaction_status = -ENOTCONN;
+			result.bytes_xferd = 0;
+			mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
+		}
+
+		mhi_chan->state = MHI_CH_STATE_DISABLED;
+		mutex_unlock(&mhi_chan->lock);
+	}
+
+	flush_workqueue(mhi_cntrl->wq);
+
+	/* Destroy devices associated with all channels */
+	device_for_each_child(&mhi_cntrl->mhi_dev->dev, NULL, mhi_ep_destroy_device);
+
+	/* Stop and reset the transfer rings */
+	for (i = 0; i < mhi_cntrl->max_chan; i++) {
+		mhi_chan = &mhi_cntrl->mhi_chan[i];
+		if (!mhi_chan->ring.started)
+			continue;
+
+		ch_ring = &mhi_cntrl->mhi_chan[i].ring;
+		mutex_lock(&mhi_chan->lock);
+		mhi_ep_ring_reset(mhi_cntrl, ch_ring);
+		mutex_unlock(&mhi_chan->lock);
+	}
+
+	/* Stop and reset the event rings */
+	for (i = 0; i < mhi_cntrl->event_rings; i++) {
+		ev_ring = &mhi_cntrl->mhi_event[i].ring;
+		if (!ev_ring->started)
+			continue;
+
+		mutex_lock(&mhi_cntrl->event_lock);
+		mhi_ep_ring_reset(mhi_cntrl, ev_ring);
+		mutex_unlock(&mhi_cntrl->event_lock);
+	}
+
+	/* Stop and reset the command ring */
+	mhi_ep_ring_reset(mhi_cntrl, &mhi_cntrl->mhi_cmd->ring);
+
+	mhi_ep_free_host_cfg(mhi_cntrl);
+	mhi_ep_mmio_mask_interrupts(mhi_cntrl);
+
+	mhi_cntrl->enabled = false;
+}
+
 int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl)
 {
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
@@ -454,6 +518,16 @@ err_free_event:
 }
 EXPORT_SYMBOL_GPL(mhi_ep_power_up);
 
+void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl)
+{
+	if (mhi_cntrl->enabled)
+		mhi_ep_abort_transfer(mhi_cntrl);
+
+	kfree(mhi_cntrl->mhi_event);
+	disable_irq(mhi_cntrl->irq);
+}
+EXPORT_SYMBOL_GPL(mhi_ep_power_down);
+
 static void mhi_ep_release_device(struct device *dev)
 {
 	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
@@ -733,6 +807,10 @@ err_free_ch:
 }
 EXPORT_SYMBOL_GPL(mhi_ep_register_controller);
 
+/*
+ * It is expected that the controller drivers will power down the MHI EP stack
+ * using "mhi_ep_power_down()" before calling this function to unregister themselves.
+ */
 void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
 {
 	struct mhi_ep_device *mhi_dev = mhi_cntrl->mhi_dev;
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 3b065f82fbeb..9da683e8302c 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -244,4 +244,10 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl);
  */
 int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl);
 
+/**
+ * mhi_ep_power_down - Power down the MHI endpoint stack
+ * @mhi_cntrl: MHI controller
+ */
+void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl);
+
 #endif
-- 
cgit v1.2.3


From 7a97b6b47353c60dd1b53ada6180741437e377f2 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:47 +0530
Subject: bus: mhi: ep: Add support for handling MHI_RESET

Add support for handling MHI_RESET in MHI endpoint stack. MHI_RESET will
be issued by the host during shutdown and during error scenario so that
it can recover the endpoint device without restarting the whole device.

MHI_RESET handling involves resetting the internal MHI registers, data
structures, state machines, resetting all channels/rings and setting
MHICTRL.RESET bit to 0. Additionally the device will also move to READY
state if the reset was due to SYS_ERR.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-12-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h    |  2 ++
 2 files changed, 55 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 968025e4d3ac..d36708d43eb6 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -381,6 +381,7 @@ static irqreturn_t mhi_ep_irq(int irq, void *data)
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	enum mhi_state state;
 	u32 int_value;
+	bool mhi_reset;
 
 	/* Acknowledge the ctrl interrupt */
 	int_value = mhi_ep_mmio_read(mhi_cntrl, MHI_CTRL_INT_STATUS);
@@ -389,6 +390,14 @@ static irqreturn_t mhi_ep_irq(int irq, void *data)
 	/* Check for ctrl interrupt */
 	if (FIELD_GET(MHI_CTRL_INT_STATUS_MSK, int_value)) {
 		dev_dbg(dev, "Processing ctrl interrupt\n");
+		mhi_ep_mmio_get_mhi_state(mhi_cntrl, &state, &mhi_reset);
+		if (mhi_reset) {
+			dev_info(dev, "Host triggered MHI reset!\n");
+			disable_irq_nosync(mhi_cntrl->irq);
+			schedule_work(&mhi_cntrl->reset_work);
+			return IRQ_HANDLED;
+		}
+
 		mhi_ep_process_ctrl_interrupt(mhi_cntrl, state);
 	}
 
@@ -464,6 +473,49 @@ static void mhi_ep_abort_transfer(struct mhi_ep_cntrl *mhi_cntrl)
 	mhi_cntrl->enabled = false;
 }
 
+static void mhi_ep_reset_worker(struct work_struct *work)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, reset_work);
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	enum mhi_state cur_state;
+	int ret;
+
+	mhi_ep_abort_transfer(mhi_cntrl);
+
+	spin_lock_bh(&mhi_cntrl->state_lock);
+	/* Reset MMIO to signal host that the MHI_RESET is completed in endpoint */
+	mhi_ep_mmio_reset(mhi_cntrl);
+	cur_state = mhi_cntrl->mhi_state;
+	spin_unlock_bh(&mhi_cntrl->state_lock);
+
+	/*
+	 * Only proceed further if the reset is due to SYS_ERR. The host will
+	 * issue reset during shutdown also and we don't need to do re-init in
+	 * that case.
+	 */
+	if (cur_state == MHI_STATE_SYS_ERR) {
+		mhi_ep_mmio_init(mhi_cntrl);
+
+		/* Set AMSS EE before signaling ready state */
+		mhi_ep_mmio_set_env(mhi_cntrl, MHI_EE_AMSS);
+
+		/* All set, notify the host that we are ready */
+		ret = mhi_ep_set_ready_state(mhi_cntrl);
+		if (ret)
+			return;
+
+		dev_dbg(dev, "READY state notification sent to the host\n");
+
+		ret = mhi_ep_enable(mhi_cntrl);
+		if (ret) {
+			dev_err(dev, "Failed to enable MHI endpoint: %d\n", ret);
+			return;
+		}
+
+		enable_irq(mhi_cntrl->irq);
+	}
+}
+
 int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl)
 {
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
@@ -738,6 +790,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	}
 
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
+	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 
 	mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0);
 	if (!mhi_cntrl->wq) {
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 9da683e8302c..2f31a54c205f 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -76,6 +76,7 @@ struct mhi_ep_db_info {
  * @ch_db_list: List of queued channel doorbells
  * @wq: Dedicated workqueue for handling rings and state changes
  * @state_work: State transition worker
+ * @reset_work: Worker for MHI Endpoint reset
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
@@ -122,6 +123,7 @@ struct mhi_ep_cntrl {
 
 	struct workqueue_struct *wq;
 	struct work_struct state_work;
+	struct work_struct reset_work;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
-- 
cgit v1.2.3


From e827569062a804c67b51930ce83a4cb886113cb7 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:49 +0530
Subject: bus: mhi: ep: Add support for processing command rings

Add support for processing the command rings. Command ring is used by the
host to issue channel specific commands to the ep device. Following
commands are supported:

1. Start channel
2. Stop channel
3. Reset channel

Once the device receives the command doorbell interrupt from host, it
executes the command and generates a command completion event to the
host in the primary event ring.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-14-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 190 +++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/mhi_ep.h    |   2 +
 2 files changed, 191 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 706473ea4918..32ac567e0f67 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -22,6 +22,7 @@
 
 static DEFINE_IDA(mhi_ep_cntrl_ida);
 
+static int mhi_ep_create_device(struct mhi_ep_cntrl *mhi_cntrl, u32 ch_id);
 static int mhi_ep_destroy_device(struct device *dev, void *data);
 
 static int mhi_ep_send_event(struct mhi_ep_cntrl *mhi_cntrl, u32 ring_idx,
@@ -111,6 +112,156 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
 }
 
+static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	struct mhi_result result = {};
+	struct mhi_ep_chan *mhi_chan;
+	struct mhi_ep_ring *ch_ring;
+	u32 tmp, ch_id;
+	int ret;
+
+	ch_id = MHI_TRE_GET_CMD_CHID(el);
+	mhi_chan = &mhi_cntrl->mhi_chan[ch_id];
+	ch_ring = &mhi_cntrl->mhi_chan[ch_id].ring;
+
+	switch (MHI_TRE_GET_CMD_TYPE(el)) {
+	case MHI_PKT_TYPE_START_CHAN_CMD:
+		dev_dbg(dev, "Received START command for channel (%u)\n", ch_id);
+
+		mutex_lock(&mhi_chan->lock);
+		/* Initialize and configure the corresponding channel ring */
+		if (!ch_ring->started) {
+			ret = mhi_ep_ring_start(mhi_cntrl, ch_ring,
+				(union mhi_ep_ring_ctx *)&mhi_cntrl->ch_ctx_cache[ch_id]);
+			if (ret) {
+				dev_err(dev, "Failed to start ring for channel (%u)\n", ch_id);
+				ret = mhi_ep_send_cmd_comp_event(mhi_cntrl,
+							MHI_EV_CC_UNDEFINED_ERR);
+				if (ret)
+					dev_err(dev, "Error sending completion event: %d\n", ret);
+
+				goto err_unlock;
+			}
+		}
+
+		/* Set channel state to RUNNING */
+		mhi_chan->state = MHI_CH_STATE_RUNNING;
+		tmp = le32_to_cpu(mhi_cntrl->ch_ctx_cache[ch_id].chcfg);
+		tmp &= ~CHAN_CTX_CHSTATE_MASK;
+		tmp |= FIELD_PREP(CHAN_CTX_CHSTATE_MASK, MHI_CH_STATE_RUNNING);
+		mhi_cntrl->ch_ctx_cache[ch_id].chcfg = cpu_to_le32(tmp);
+
+		ret = mhi_ep_send_cmd_comp_event(mhi_cntrl, MHI_EV_CC_SUCCESS);
+		if (ret) {
+			dev_err(dev, "Error sending command completion event (%u)\n",
+				MHI_EV_CC_SUCCESS);
+			goto err_unlock;
+		}
+
+		mutex_unlock(&mhi_chan->lock);
+
+		/*
+		 * Create MHI device only during UL channel start. Since the MHI
+		 * channels operate in a pair, we'll associate both UL and DL
+		 * channels to the same device.
+		 *
+		 * We also need to check for mhi_dev != NULL because, the host
+		 * will issue START_CHAN command during resume and we don't
+		 * destroy the device during suspend.
+		 */
+		if (!(ch_id % 2) && !mhi_chan->mhi_dev) {
+			ret = mhi_ep_create_device(mhi_cntrl, ch_id);
+			if (ret) {
+				dev_err(dev, "Error creating device for channel (%u)\n", ch_id);
+				mhi_ep_handle_syserr(mhi_cntrl);
+				return ret;
+			}
+		}
+
+		/* Finally, enable DB for the channel */
+		mhi_ep_mmio_enable_chdb(mhi_cntrl, ch_id);
+
+		break;
+	case MHI_PKT_TYPE_STOP_CHAN_CMD:
+		dev_dbg(dev, "Received STOP command for channel (%u)\n", ch_id);
+		if (!ch_ring->started) {
+			dev_err(dev, "Channel (%u) not opened\n", ch_id);
+			return -ENODEV;
+		}
+
+		mutex_lock(&mhi_chan->lock);
+		/* Disable DB for the channel */
+		mhi_ep_mmio_disable_chdb(mhi_cntrl, ch_id);
+
+		/* Send channel disconnect status to client drivers */
+		result.transaction_status = -ENOTCONN;
+		result.bytes_xferd = 0;
+		mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
+
+		/* Set channel state to STOP */
+		mhi_chan->state = MHI_CH_STATE_STOP;
+		tmp = le32_to_cpu(mhi_cntrl->ch_ctx_cache[ch_id].chcfg);
+		tmp &= ~CHAN_CTX_CHSTATE_MASK;
+		tmp |= FIELD_PREP(CHAN_CTX_CHSTATE_MASK, MHI_CH_STATE_STOP);
+		mhi_cntrl->ch_ctx_cache[ch_id].chcfg = cpu_to_le32(tmp);
+
+		ret = mhi_ep_send_cmd_comp_event(mhi_cntrl, MHI_EV_CC_SUCCESS);
+		if (ret) {
+			dev_err(dev, "Error sending command completion event (%u)\n",
+				MHI_EV_CC_SUCCESS);
+			goto err_unlock;
+		}
+
+		mutex_unlock(&mhi_chan->lock);
+		break;
+	case MHI_PKT_TYPE_RESET_CHAN_CMD:
+		dev_dbg(dev, "Received STOP command for channel (%u)\n", ch_id);
+		if (!ch_ring->started) {
+			dev_err(dev, "Channel (%u) not opened\n", ch_id);
+			return -ENODEV;
+		}
+
+		mutex_lock(&mhi_chan->lock);
+		/* Stop and reset the transfer ring */
+		mhi_ep_ring_reset(mhi_cntrl, ch_ring);
+
+		/* Send channel disconnect status to client driver */
+		result.transaction_status = -ENOTCONN;
+		result.bytes_xferd = 0;
+		mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
+
+		/* Set channel state to DISABLED */
+		mhi_chan->state = MHI_CH_STATE_DISABLED;
+		tmp = le32_to_cpu(mhi_cntrl->ch_ctx_cache[ch_id].chcfg);
+		tmp &= ~CHAN_CTX_CHSTATE_MASK;
+		tmp |= FIELD_PREP(CHAN_CTX_CHSTATE_MASK, MHI_CH_STATE_DISABLED);
+		mhi_cntrl->ch_ctx_cache[ch_id].chcfg = cpu_to_le32(tmp);
+
+		ret = mhi_ep_send_cmd_comp_event(mhi_cntrl, MHI_EV_CC_SUCCESS);
+		if (ret) {
+			dev_err(dev, "Error sending command completion event (%u)\n",
+				MHI_EV_CC_SUCCESS);
+			goto err_unlock;
+		}
+
+		mutex_unlock(&mhi_chan->lock);
+		break;
+	default:
+		dev_err(dev, "Invalid command received: %lu for channel (%u)\n",
+			MHI_TRE_GET_CMD_TYPE(el), ch_id);
+		return -EINVAL;
+	}
+
+	return 0;
+
+err_unlock:
+	mutex_unlock(&mhi_chan->lock);
+
+	return ret;
+}
+
 static int mhi_ep_cache_host_cfg(struct mhi_ep_cntrl *mhi_cntrl)
 {
 	size_t cmd_ctx_host_size, ch_ctx_host_size, ev_ctx_host_size;
@@ -259,6 +410,40 @@ static int mhi_ep_enable(struct mhi_ep_cntrl *mhi_cntrl)
 	return 0;
 }
 
+static void mhi_ep_cmd_ring_worker(struct work_struct *work)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, cmd_ring_work);
+	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_cmd->ring;
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	struct mhi_ring_element *el;
+	int ret;
+
+	/* Update the write offset for the ring */
+	ret = mhi_ep_update_wr_offset(ring);
+	if (ret) {
+		dev_err(dev, "Error updating write offset for ring\n");
+		return;
+	}
+
+	/* Sanity check to make sure there are elements in the ring */
+	if (ring->rd_offset == ring->wr_offset)
+		return;
+
+	/*
+	 * Process command ring element till write offset. In case of an error, just try to
+	 * process next element.
+	 */
+	while (ring->rd_offset != ring->wr_offset) {
+		el = &ring->ring_cache[ring->rd_offset];
+
+		ret = mhi_ep_process_cmd_ring(ring, el);
+		if (ret)
+			dev_err(dev, "Error processing cmd ring element: %zu\n", ring->rd_offset);
+
+		mhi_ep_ring_inc_index(ring);
+	}
+}
+
 static void mhi_ep_state_worker(struct work_struct *work)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, state_work);
@@ -402,8 +587,10 @@ static irqreturn_t mhi_ep_irq(int irq, void *data)
 	}
 
 	/* Check for command doorbell interrupt */
-	if (FIELD_GET(MHI_CTRL_INT_STATUS_CRDB_MSK, int_value))
+	if (FIELD_GET(MHI_CTRL_INT_STATUS_CRDB_MSK, int_value)) {
 		dev_dbg(dev, "Processing command doorbell interrupt\n");
+		queue_work(mhi_cntrl->wq, &mhi_cntrl->cmd_ring_work);
+	}
 
 	/* Check for channel interrupts */
 	mhi_ep_check_channel_interrupt(mhi_cntrl);
@@ -811,6 +998,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
+	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
 
 	mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0);
 	if (!mhi_cntrl->wq) {
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 2f31a54c205f..8c6406d9c51f 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -77,6 +77,7 @@ struct mhi_ep_db_info {
  * @wq: Dedicated workqueue for handling rings and state changes
  * @state_work: State transition worker
  * @reset_work: Worker for MHI Endpoint reset
+ * @cmd_ring_work: Worker for processing command rings
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
@@ -124,6 +125,7 @@ struct mhi_ep_cntrl {
 	struct workqueue_struct *wq;
 	struct work_struct state_work;
 	struct work_struct reset_work;
+	struct work_struct cmd_ring_work;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
-- 
cgit v1.2.3


From 530125889977365cb6db32d7d0bd84c9f54c8aab Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:50 +0530
Subject: bus: mhi: ep: Add support for reading from the host

Data transfer between host and the ep device happens over the transfer
ring associated with each bi-directional channel pair. Host defines the
transfer ring by allocating memory for it. The read and write pointer
addresses of the transfer ring are stored in the channel context.

Once host places the elements in the transfer ring, it increments the
write pointer and rings the channel doorbell. Device will receive the
doorbell interrupt and will process the transfer ring elements.

This commit adds support for reading the transfer ring elements from
the transfer ring till write pointer, incrementing the read pointer and
finally sending the completion event to the host through corresponding
event ring.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-15-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 121 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h    |   9 ++++
 2 files changed, 130 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 32ac567e0f67..1e24eae4b446 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -262,6 +262,127 @@ err_unlock:
 	return ret;
 }
 
+bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_direction dir)
+{
+	struct mhi_ep_chan *mhi_chan = (dir == DMA_FROM_DEVICE) ? mhi_dev->dl_chan :
+								mhi_dev->ul_chan;
+	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
+
+	return !!(ring->rd_offset == ring->wr_offset);
+}
+EXPORT_SYMBOL_GPL(mhi_ep_queue_is_empty);
+
+static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
+				struct mhi_ep_ring *ring,
+				struct mhi_result *result,
+				u32 len)
+{
+	struct mhi_ep_chan *mhi_chan = &mhi_cntrl->mhi_chan[ring->ch_id];
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	size_t tr_len, read_offset, write_offset;
+	struct mhi_ring_element *el;
+	bool tr_done = false;
+	void *write_addr;
+	u64 read_addr;
+	u32 buf_left;
+	int ret;
+
+	buf_left = len;
+
+	do {
+		/* Don't process the transfer ring if the channel is not in RUNNING state */
+		if (mhi_chan->state != MHI_CH_STATE_RUNNING) {
+			dev_err(dev, "Channel not available\n");
+			return -ENODEV;
+		}
+
+		el = &ring->ring_cache[ring->rd_offset];
+
+		/* Check if there is data pending to be read from previous read operation */
+		if (mhi_chan->tre_bytes_left) {
+			dev_dbg(dev, "TRE bytes remaining: %u\n", mhi_chan->tre_bytes_left);
+			tr_len = min(buf_left, mhi_chan->tre_bytes_left);
+		} else {
+			mhi_chan->tre_loc = MHI_TRE_DATA_GET_PTR(el);
+			mhi_chan->tre_size = MHI_TRE_DATA_GET_LEN(el);
+			mhi_chan->tre_bytes_left = mhi_chan->tre_size;
+
+			tr_len = min(buf_left, mhi_chan->tre_size);
+		}
+
+		read_offset = mhi_chan->tre_size - mhi_chan->tre_bytes_left;
+		write_offset = len - buf_left;
+		read_addr = mhi_chan->tre_loc + read_offset;
+		write_addr = result->buf_addr + write_offset;
+
+		dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id);
+		ret = mhi_cntrl->read_from_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		if (ret < 0) {
+			dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n");
+			return ret;
+		}
+
+		buf_left -= tr_len;
+		mhi_chan->tre_bytes_left -= tr_len;
+
+		/*
+		 * Once the TRE (Transfer Ring Element) of a TD (Transfer Descriptor) has been
+		 * read completely:
+		 *
+		 * 1. Send completion event to the host based on the flags set in TRE.
+		 * 2. Increment the local read offset of the transfer ring.
+		 */
+		if (!mhi_chan->tre_bytes_left) {
+			/*
+			 * The host will split the data packet into multiple TREs if it can't fit
+			 * the packet in a single TRE. In that case, CHAIN flag will be set by the
+			 * host for all TREs except the last one.
+			 */
+			if (MHI_TRE_DATA_GET_CHAIN(el)) {
+				/*
+				 * IEOB (Interrupt on End of Block) flag will be set by the host if
+				 * it expects the completion event for all TREs of a TD.
+				 */
+				if (MHI_TRE_DATA_GET_IEOB(el)) {
+					ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
+								     MHI_TRE_DATA_GET_LEN(el),
+								     MHI_EV_CC_EOB);
+					if (ret < 0) {
+						dev_err(&mhi_chan->mhi_dev->dev,
+							"Error sending transfer compl. event\n");
+						return ret;
+					}
+				}
+			} else {
+				/*
+				 * IEOT (Interrupt on End of Transfer) flag will be set by the host
+				 * for the last TRE of the TD and expects the completion event for
+				 * the same.
+				 */
+				if (MHI_TRE_DATA_GET_IEOT(el)) {
+					ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el,
+								     MHI_TRE_DATA_GET_LEN(el),
+								     MHI_EV_CC_EOT);
+					if (ret < 0) {
+						dev_err(&mhi_chan->mhi_dev->dev,
+							"Error sending transfer compl. event\n");
+						return ret;
+					}
+				}
+
+				tr_done = true;
+			}
+
+			mhi_ep_ring_inc_index(ring);
+		}
+
+		result->bytes_xferd += tr_len;
+	} while (buf_left && !tr_done);
+
+	return 0;
+}
+
 static int mhi_ep_cache_host_cfg(struct mhi_ep_cntrl *mhi_cntrl)
 {
 	size_t cmd_ctx_host_size, ch_ctx_host_size, ev_ctx_host_size;
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 8c6406d9c51f..fc7d197413eb 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -254,4 +254,13 @@ int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl);
  */
 void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl);
 
+/**
+ * mhi_ep_queue_is_empty - Determine whether the transfer queue is empty
+ * @mhi_dev: Device associated with the channels
+ * @dir: DMA direction for the channel
+ *
+ * Return: true if the queue is empty, false otherwise.
+ */
+bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_direction dir);
+
 #endif
-- 
cgit v1.2.3


From 03c0bb8ec983f993a704417d73cc0a3511453d3e Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:51 +0530
Subject: bus: mhi: ep: Add support for processing channel rings

Add support for processing the channel rings from host. For the channel
ring associated with DL channel, the xfer callback will simply invoked.
For the case of UL channel, the ring elements will be read in a buffer
till the write pointer and later passed to the client driver using the
xfer callback.

The client drivers should provide the callbacks for both UL and DL
channels during registration.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-16-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 108 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h    |   2 +
 2 files changed, 110 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 1e24eae4b446..e2ed10b4a9d2 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -383,6 +383,57 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 	return 0;
 }
 
+static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
+	struct mhi_result result = {};
+	u32 len = MHI_EP_DEFAULT_MTU;
+	struct mhi_ep_chan *mhi_chan;
+	int ret;
+
+	mhi_chan = &mhi_cntrl->mhi_chan[ring->ch_id];
+
+	/*
+	 * Bail out if transfer callback is not registered for the channel.
+	 * This is most likely due to the client driver not loaded at this point.
+	 */
+	if (!mhi_chan->xfer_cb) {
+		dev_err(&mhi_chan->mhi_dev->dev, "Client driver not available\n");
+		return -ENODEV;
+	}
+
+	if (ring->ch_id % 2) {
+		/* DL channel */
+		result.dir = mhi_chan->dir;
+		mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
+	} else {
+		/* UL channel */
+		result.buf_addr = kzalloc(len, GFP_KERNEL);
+		if (!result.buf_addr)
+			return -ENOMEM;
+
+		do {
+			ret = mhi_ep_read_channel(mhi_cntrl, ring, &result, len);
+			if (ret < 0) {
+				dev_err(&mhi_chan->mhi_dev->dev, "Failed to read channel\n");
+				kfree(result.buf_addr);
+				return ret;
+			}
+
+			result.dir = mhi_chan->dir;
+			mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
+			result.bytes_xferd = 0;
+			memset(result.buf_addr, 0, len);
+
+			/* Read until the ring becomes empty */
+		} while (!mhi_ep_queue_is_empty(mhi_chan->mhi_dev, DMA_TO_DEVICE));
+
+		kfree(result.buf_addr);
+	}
+
+	return 0;
+}
+
 static int mhi_ep_cache_host_cfg(struct mhi_ep_cntrl *mhi_cntrl)
 {
 	size_t cmd_ctx_host_size, ch_ctx_host_size, ev_ctx_host_size;
@@ -565,6 +616,60 @@ static void mhi_ep_cmd_ring_worker(struct work_struct *work)
 	}
 }
 
+static void mhi_ep_ch_ring_worker(struct work_struct *work)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, ch_ring_work);
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	struct mhi_ep_ring_item *itr, *tmp;
+	struct mhi_ring_element *el;
+	struct mhi_ep_ring *ring;
+	struct mhi_ep_chan *chan;
+	unsigned long flags;
+	LIST_HEAD(head);
+	int ret;
+
+	spin_lock_irqsave(&mhi_cntrl->list_lock, flags);
+	list_splice_tail_init(&mhi_cntrl->ch_db_list, &head);
+	spin_unlock_irqrestore(&mhi_cntrl->list_lock, flags);
+
+	/* Process each queued channel ring. In case of an error, just process next element. */
+	list_for_each_entry_safe(itr, tmp, &head, node) {
+		list_del(&itr->node);
+		ring = itr->ring;
+
+		/* Update the write offset for the ring */
+		ret = mhi_ep_update_wr_offset(ring);
+		if (ret) {
+			dev_err(dev, "Error updating write offset for ring\n");
+			kfree(itr);
+			continue;
+		}
+
+		/* Sanity check to make sure there are elements in the ring */
+		if (ring->rd_offset == ring->wr_offset) {
+			kfree(itr);
+			continue;
+		}
+
+		el = &ring->ring_cache[ring->rd_offset];
+		chan = &mhi_cntrl->mhi_chan[ring->ch_id];
+
+		mutex_lock(&chan->lock);
+		dev_dbg(dev, "Processing the ring for channel (%u)\n", ring->ch_id);
+		ret = mhi_ep_process_ch_ring(ring, el);
+		if (ret) {
+			dev_err(dev, "Error processing ring for channel (%u): %d\n",
+				ring->ch_id, ret);
+			mutex_unlock(&chan->lock);
+			kfree(itr);
+			continue;
+		}
+
+		mutex_unlock(&chan->lock);
+		kfree(itr);
+	}
+}
+
 static void mhi_ep_state_worker(struct work_struct *work)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = container_of(work, struct mhi_ep_cntrl, state_work);
@@ -630,6 +735,8 @@ static void mhi_ep_queue_channel_db(struct mhi_ep_cntrl *mhi_cntrl, unsigned lon
 		spin_lock(&mhi_cntrl->list_lock);
 		list_splice_tail_init(&head, &mhi_cntrl->ch_db_list);
 		spin_unlock(&mhi_cntrl->list_lock);
+
+		queue_work(mhi_cntrl->wq, &mhi_cntrl->ch_ring_work);
 	}
 }
 
@@ -1120,6 +1227,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
+	INIT_WORK(&mhi_cntrl->ch_ring_work, mhi_ep_ch_ring_worker);
 
 	mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0);
 	if (!mhi_cntrl->wq) {
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index fc7d197413eb..eecc8f35d630 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -78,6 +78,7 @@ struct mhi_ep_db_info {
  * @state_work: State transition worker
  * @reset_work: Worker for MHI Endpoint reset
  * @cmd_ring_work: Worker for processing command rings
+ * @ch_ring_work: Worker for processing channel rings
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
@@ -126,6 +127,7 @@ struct mhi_ep_cntrl {
 	struct work_struct state_work;
 	struct work_struct reset_work;
 	struct work_struct cmd_ring_work;
+	struct work_struct ch_ring_work;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
-- 
cgit v1.2.3


From 2d945a394d9c1c59d88397cb383b11216d018a6b Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:52 +0530
Subject: bus: mhi: ep: Add support for queueing SKBs to the host

Add support for queueing SKBs to the host over the transfer ring of the
relevant channel. The mhi_ep_queue_skb() API will be used by the client
networking drivers to queue the SKBs to the host over MHI bus.

The host will add ring elements to the transfer ring periodically for
the device and the device will write SKBs to the ring elements. If a
single SKB doesn't fit in a ring element (TRE), it will be placed in
multiple ring elements and the overflow event will be sent for all ring
elements except the last one. For the last ring element, the EOT event
will be sent indicating the packet boundary.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-17-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mhi_ep.h    |  9 ++++++
 2 files changed, 91 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index e2ed10b4a9d2..660d1e9791d3 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -434,6 +434,88 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 	return 0;
 }
 
+/* TODO: Handle partially formed TDs */
+int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
+{
+	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan;
+	struct device *dev = &mhi_chan->mhi_dev->dev;
+	struct mhi_ring_element *el;
+	u32 buf_left, read_offset;
+	struct mhi_ep_ring *ring;
+	enum mhi_ev_ccs code;
+	void *read_addr;
+	u64 write_addr;
+	size_t tr_len;
+	u32 tre_len;
+	int ret;
+
+	buf_left = skb->len;
+	ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
+
+	mutex_lock(&mhi_chan->lock);
+
+	do {
+		/* Don't process the transfer ring if the channel is not in RUNNING state */
+		if (mhi_chan->state != MHI_CH_STATE_RUNNING) {
+			dev_err(dev, "Channel not available\n");
+			ret = -ENODEV;
+			goto err_exit;
+		}
+
+		if (mhi_ep_queue_is_empty(mhi_dev, DMA_FROM_DEVICE)) {
+			dev_err(dev, "TRE not available!\n");
+			ret = -ENOSPC;
+			goto err_exit;
+		}
+
+		el = &ring->ring_cache[ring->rd_offset];
+		tre_len = MHI_TRE_DATA_GET_LEN(el);
+
+		tr_len = min(buf_left, tre_len);
+		read_offset = skb->len - buf_left;
+		read_addr = skb->data + read_offset;
+		write_addr = MHI_TRE_DATA_GET_PTR(el);
+
+		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
+		ret = mhi_cntrl->write_to_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		if (ret < 0) {
+			dev_err(dev, "Error writing to the channel\n");
+			goto err_exit;
+		}
+
+		buf_left -= tr_len;
+		/*
+		 * For all TREs queued by the host for DL channel, only the EOT flag will be set.
+		 * If the packet doesn't fit into a single TRE, send the OVERFLOW event to
+		 * the host so that the host can adjust the packet boundary to next TREs. Else send
+		 * the EOT event to the host indicating the packet boundary.
+		 */
+		if (buf_left)
+			code = MHI_EV_CC_OVERFLOW;
+		else
+			code = MHI_EV_CC_EOT;
+
+		ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, tr_len, code);
+		if (ret) {
+			dev_err(dev, "Error sending transfer completion event\n");
+			goto err_exit;
+		}
+
+		mhi_ep_ring_inc_index(ring);
+	} while (buf_left);
+
+	mutex_unlock(&mhi_chan->lock);
+
+	return 0;
+
+err_exit:
+	mutex_unlock(&mhi_chan->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mhi_ep_queue_skb);
+
 static int mhi_ep_cache_host_cfg(struct mhi_ep_cntrl *mhi_cntrl)
 {
 	size_t cmd_ctx_host_size, ch_ctx_host_size, ev_ctx_host_size;
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index eecc8f35d630..478aece17046 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -265,4 +265,13 @@ void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl);
  */
 bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_direction dir);
 
+/**
+ * mhi_ep_queue_skb - Send SKBs to host over MHI Endpoint
+ * @mhi_dev: Device associated with the DL channel
+ * @skb: SKBs to be queued
+ *
+ * Return: 0 if the SKBs has been sent successfully, a negative error code otherwise.
+ */
+int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb);
+
 #endif
-- 
cgit v1.2.3


From c268c0a8a33047cd957fecc1349d09a68eb6ad9e Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 5 Apr 2022 19:27:54 +0530
Subject: bus: mhi: ep: Add uevent support for module autoloading

Add uevent support to MHI endpoint bus so that the client drivers can be
autoloaded by udev when the MHI endpoint devices gets created. The client
drivers are expected to provide MODULE_DEVICE_TABLE with the MHI id_table
struct so that the alias can be exported.

The MHI endpoint reused the mhi_device_id structure of the MHI bus.

Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20220405135754.6622-19-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/ep/main.c       |  9 +++++++++
 include/linux/mod_devicetable.h |  2 ++
 scripts/mod/file2alias.c        | 10 ++++++++++
 3 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index bae5f40ec15e..40109a79017a 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -1536,6 +1536,14 @@ void mhi_ep_driver_unregister(struct mhi_ep_driver *mhi_drv)
 }
 EXPORT_SYMBOL_GPL(mhi_ep_driver_unregister);
 
+static int mhi_ep_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
+
+	return add_uevent_var(env, "MODALIAS=" MHI_EP_DEVICE_MODALIAS_FMT,
+					mhi_dev->name);
+}
+
 static int mhi_ep_match(struct device *dev, struct device_driver *drv)
 {
 	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
@@ -1562,6 +1570,7 @@ struct bus_type mhi_ep_bus_type = {
 	.name = "mhi_ep",
 	.dev_name = "mhi_ep",
 	.match = mhi_ep_match,
+	.uevent = mhi_ep_uevent,
 };
 
 static int __init mhi_ep_init(void)
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 5da5d990ff58..549590e9c644 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -835,6 +835,8 @@ struct wmi_device_id {
 #define MHI_DEVICE_MODALIAS_FMT "mhi:%s"
 #define MHI_NAME_SIZE 32
 
+#define MHI_EP_DEVICE_MODALIAS_FMT "mhi_ep:%s"
+
 /**
  * struct mhi_device_id - MHI device identification
  * @chan: MHI channel name
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 5258247d78ac..d9d6a31446ea 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1391,6 +1391,15 @@ static int do_mhi_entry(const char *filename, void *symval, char *alias)
 	return 1;
 }
 
+/* Looks like: mhi_ep:S */
+static int do_mhi_ep_entry(const char *filename, void *symval, char *alias)
+{
+	DEF_FIELD_ADDR(symval, mhi_device_id, chan);
+	sprintf(alias, MHI_EP_DEVICE_MODALIAS_FMT, *chan);
+
+	return 1;
+}
+
 /* Looks like: ishtp:{guid} */
 static int do_ishtp_entry(const char *filename, void *symval, char *alias)
 {
@@ -1519,6 +1528,7 @@ static const struct devtable devtable[] = {
 	{"tee", SIZE_tee_client_device_id, do_tee_entry},
 	{"wmi", SIZE_wmi_device_id, do_wmi_entry},
 	{"mhi", SIZE_mhi_device_id, do_mhi_entry},
+	{"mhi_ep", SIZE_mhi_device_id, do_mhi_ep_entry},
 	{"auxiliary", SIZE_auxiliary_device_id, do_auxiliary_entry},
 	{"ssam", SIZE_ssam_device_id, do_ssam_entry},
 	{"dfl", SIZE_dfl_device_id, do_dfl_entry},
-- 
cgit v1.2.3


From 31f6bd7fad3b149a1eb6f67fc2e742e4df369b3d Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Mon, 25 Apr 2022 17:33:58 +0300
Subject: serial: Store character timing information to uart_port
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Struct uart_port currently stores FIFO timeout. Having character timing
information readily available is useful. Even serial core itself
determines char_time from port->timeout using inverse calculation.

Store frame_time directly into uart_port. Character time is stored in
nanoseconds to have reasonable precision with high rates. To avoid
overflow, 64-bit math is necessary.

It might be possible to determine timeout from frame_time by
multiplying it with fifosize as needed but only part of the users seem
to be protected by a lock. Thus, this patch does not pursue storing
only frame_time in uart_port.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20220425143410.12703-2-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 14 ++++++++------
 include/linux/serial_core.h      |  1 +
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 01823ce87801..82a1770dd808 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -24,6 +24,7 @@
 #include <linux/sysrq.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
+#include <linux/math64.h>
 #include <linux/security.h>
 
 #include <linux/irq.h>
@@ -338,15 +339,18 @@ void
 uart_update_timeout(struct uart_port *port, unsigned int cflag,
 		    unsigned int baud)
 {
-	unsigned int size;
+	unsigned int size = tty_get_frame_size(cflag);
+	u64 frame_time;
 
-	size = tty_get_frame_size(cflag) * port->fifosize;
+	frame_time = (u64)size * NSEC_PER_SEC;
+	size *= port->fifosize;
 
 	/*
 	 * Figure the timeout to send the above number of bits.
 	 * Add .02 seconds of slop
 	 */
 	port->timeout = (HZ * size) / baud + HZ/50;
+	port->frame_time = DIV64_U64_ROUND_UP(frame_time, baud);
 }
 EXPORT_SYMBOL(uart_update_timeout);
 
@@ -1643,10 +1647,8 @@ static void uart_wait_until_sent(struct tty_struct *tty, int timeout)
 	 * Note: we have to use pretty tight timings here to satisfy
 	 * the NIST-PCTS.
 	 */
-	char_time = (port->timeout - HZ/50) / port->fifosize;
-	char_time = char_time / 5;
-	if (char_time == 0)
-		char_time = 1;
+	char_time = max(nsecs_to_jiffies(port->frame_time / 5), 1UL);
+
 	if (timeout && timeout < char_time)
 		char_time = timeout;
 
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index d4828e69087a..cbd5070bc87f 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -232,6 +232,7 @@ struct uart_port {
 	int			hw_stopped;		/* sw-assisted CTS flow state */
 	unsigned int		mctrl;			/* current modem ctrl settings */
 	unsigned int		timeout;		/* character-based timeout */
+	unsigned int		frame_time;		/* frame timing in ns */
 	unsigned int		type;			/* port type */
 	const struct uart_ops	*ops;
 	unsigned int		custom_divisor;
-- 
cgit v1.2.3


From 7a20917d30fb627bebff6bacbe860ad4eb3a04d6 Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@linaro.org>
Date: Fri, 22 Apr 2022 15:23:45 -0700
Subject: device property: Add helper to match multiple connections

In some cases multiple connections with the same connection id
needs to be resolved from a fwnode graph.

One such example is when separate hardware is used for performing muxing
and/or orientation switching of the SuperSpeed and SBU lines in a USB
Type-C connector. In this case the connector needs to belong to a graph
with multiple matching remote endpoints, and the Type-C controller needs
to be able to resolve them both.

Add a new API that allows this kind of lookup.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Link: https://lore.kernel.org/r/20220422222351.1297276-2-bjorn.andersson@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/property.c  | 109 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/property.h |   5 +++
 2 files changed, 114 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index c0e94cce9c29..08da5ca49e9c 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1218,6 +1218,40 @@ fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 	return NULL;
 }
 
+static unsigned int fwnode_graph_devcon_matches(struct fwnode_handle *fwnode,
+						const char *con_id, void *data,
+						devcon_match_fn_t match,
+						void **matches,
+						unsigned int matches_len)
+{
+	struct fwnode_handle *node;
+	struct fwnode_handle *ep;
+	unsigned int count = 0;
+	void *ret;
+
+	fwnode_graph_for_each_endpoint(fwnode, ep) {
+		if (matches && count >= matches_len) {
+			fwnode_handle_put(ep);
+			break;
+		}
+
+		node = fwnode_graph_get_remote_port_parent(ep);
+		if (!fwnode_device_is_available(node)) {
+			fwnode_handle_put(node);
+			continue;
+		}
+
+		ret = match(node, con_id, data);
+		fwnode_handle_put(node);
+		if (ret) {
+			if (matches)
+				matches[count] = ret;
+			count++;
+		}
+	}
+	return count;
+}
+
 static void *
 fwnode_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 		    void *data, devcon_match_fn_t match)
@@ -1240,6 +1274,37 @@ fwnode_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 	return NULL;
 }
 
+static unsigned int fwnode_devcon_matches(struct fwnode_handle *fwnode,
+					  const char *con_id, void *data,
+					  devcon_match_fn_t match,
+					  void **matches,
+					  unsigned int matches_len)
+{
+	struct fwnode_handle *node;
+	unsigned int count = 0;
+	unsigned int i;
+	void *ret;
+
+	for (i = 0; ; i++) {
+		if (matches && count >= matches_len)
+			break;
+
+		node = fwnode_find_reference(fwnode, con_id, i);
+		if (IS_ERR(node))
+			break;
+
+		ret = match(node, NULL, data);
+		fwnode_handle_put(node);
+		if (ret) {
+			if (matches)
+				matches[count] = ret;
+			count++;
+		}
+	}
+
+	return count;
+}
+
 /**
  * fwnode_connection_find_match - Find connection from a device node
  * @fwnode: Device node with the connection
@@ -1267,3 +1332,47 @@ void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
 	return fwnode_devcon_match(fwnode, con_id, data, match);
 }
 EXPORT_SYMBOL_GPL(fwnode_connection_find_match);
+
+/**
+ * fwnode_connection_find_matches - Find connections from a device node
+ * @fwnode: Device node with the connection
+ * @con_id: Identifier for the connection
+ * @data: Data for the match function
+ * @match: Function to check and convert the connection description
+ * @matches: (Optional) array of pointers to fill with matches
+ * @matches_len: Length of @matches
+ *
+ * Find up to @matches_len connections with unique identifier @con_id between
+ * @fwnode and other device nodes. @match will be used to convert the
+ * connection description to data the caller is expecting to be returned
+ * through the @matches array.
+ * If @matches is NULL @matches_len is ignored and the total number of resolved
+ * matches is returned.
+ *
+ * Return: Number of matches resolved, or negative errno.
+ */
+int fwnode_connection_find_matches(struct fwnode_handle *fwnode,
+				   const char *con_id, void *data,
+				   devcon_match_fn_t match,
+				   void **matches, unsigned int matches_len)
+{
+	unsigned int count_graph;
+	unsigned int count_ref;
+
+	if (!fwnode || !match)
+		return -EINVAL;
+
+	count_graph = fwnode_graph_devcon_matches(fwnode, con_id, data, match,
+						  matches, matches_len);
+
+	if (matches) {
+		matches += count_graph;
+		matches_len -= count_graph;
+	}
+
+	count_ref = fwnode_devcon_matches(fwnode, con_id, data, match,
+					  matches, matches_len);
+
+	return count_graph + count_ref;
+}
+EXPORT_SYMBOL_GPL(fwnode_connection_find_matches);
diff --git a/include/linux/property.h b/include/linux/property.h
index 4cd4b326941f..de7ff336d2c8 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -447,6 +447,11 @@ static inline void *device_connection_find_match(struct device *dev,
 	return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match);
 }
 
+int fwnode_connection_find_matches(struct fwnode_handle *fwnode,
+				   const char *con_id, void *data,
+				   devcon_match_fn_t match,
+				   void **matches, unsigned int matches_len);
+
 /* -------------------------------------------------------------------------- */
 /* Software fwnode support - when HW description is incomplete or missing */
 
-- 
cgit v1.2.3


From 713fd49b430c37263c6cae2c82954f4e1cbcd90d Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@linaro.org>
Date: Fri, 22 Apr 2022 15:23:48 -0700
Subject: usb: typec: mux: Introduce indirection

Rather than directly exposing the implementation's representation of the
typec muxes to the controller/clients, introduce an indirection object.

This enables the introduction of turning this relationship into a
one-to-many in the following patch.

Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Link: https://lore.kernel.org/r/20220422222351.1297276-5-bjorn.andersson@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/bus.c               |   2 +-
 drivers/usb/typec/mux.c               | 193 +++++++++++++++++++++-------------
 drivers/usb/typec/mux.h               |  12 +--
 drivers/usb/typec/mux/intel_pmc_mux.c |   8 +-
 drivers/usb/typec/mux/pi3usb30532.c   |   8 +-
 include/linux/usb/typec_mux.h         |  22 ++--
 6 files changed, 148 insertions(+), 97 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c
index 78e0e78954f2..26ea2fdec17d 100644
--- a/drivers/usb/typec/bus.c
+++ b/drivers/usb/typec/bus.c
@@ -24,7 +24,7 @@ typec_altmode_set_mux(struct altmode *alt, unsigned long conf, void *data)
 	state.mode = conf;
 	state.data = data;
 
-	return alt->mux->set(alt->mux, &state);
+	return typec_mux_set(alt->mux, &state);
 }
 
 static int typec_altmode_set_state(struct typec_altmode *adev,
diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c
index d2aaf294b649..bb6c095b4af9 100644
--- a/drivers/usb/typec/mux.c
+++ b/drivers/usb/typec/mux.c
@@ -17,9 +17,13 @@
 #include "class.h"
 #include "mux.h"
 
+struct typec_switch {
+	struct typec_switch_dev *sw_dev;
+};
+
 static int switch_fwnode_match(struct device *dev, const void *fwnode)
 {
-	if (!is_typec_switch(dev))
+	if (!is_typec_switch_dev(dev))
 		return 0;
 
 	return dev_fwnode(dev) == fwnode;
@@ -49,7 +53,7 @@ static void *typec_switch_match(struct fwnode_handle *fwnode, const char *id,
 	dev = class_find_device(&typec_mux_class, NULL, fwnode,
 				switch_fwnode_match);
 
-	return dev ? to_typec_switch(dev) : ERR_PTR(-EPROBE_DEFER);
+	return dev ? to_typec_switch_dev(dev) : ERR_PTR(-EPROBE_DEFER);
 }
 
 /**
@@ -63,12 +67,23 @@ static void *typec_switch_match(struct fwnode_handle *fwnode, const char *id,
  */
 struct typec_switch *fwnode_typec_switch_get(struct fwnode_handle *fwnode)
 {
+	struct typec_switch_dev *sw_dev;
 	struct typec_switch *sw;
 
-	sw = fwnode_connection_find_match(fwnode, "orientation-switch", NULL,
-					  typec_switch_match);
-	if (!IS_ERR_OR_NULL(sw))
-		WARN_ON(!try_module_get(sw->dev.parent->driver->owner));
+	sw = kzalloc(sizeof(*sw), GFP_KERNEL);
+	if (!sw)
+		return ERR_PTR(-ENOMEM);
+
+	sw_dev = fwnode_connection_find_match(fwnode, "orientation-switch", NULL,
+					      typec_switch_match);
+	if (IS_ERR_OR_NULL(sw_dev)) {
+		kfree(sw);
+		return ERR_CAST(sw_dev);
+	}
+
+	WARN_ON(!try_module_get(sw_dev->dev.parent->driver->owner));
+
+	sw->sw_dev = sw_dev;
 
 	return sw;
 }
@@ -82,16 +97,22 @@ EXPORT_SYMBOL_GPL(fwnode_typec_switch_get);
  */
 void typec_switch_put(struct typec_switch *sw)
 {
-	if (!IS_ERR_OR_NULL(sw)) {
-		module_put(sw->dev.parent->driver->owner);
-		put_device(&sw->dev);
-	}
+	struct typec_switch_dev *sw_dev;
+
+	if (IS_ERR_OR_NULL(sw))
+		return;
+
+	sw_dev = sw->sw_dev;
+
+	module_put(sw_dev->dev.parent->driver->owner);
+	put_device(&sw_dev->dev);
+	kfree(sw);
 }
 EXPORT_SYMBOL_GPL(typec_switch_put);
 
 static void typec_switch_release(struct device *dev)
 {
-	kfree(to_typec_switch(dev));
+	kfree(to_typec_switch_dev(dev));
 }
 
 const struct device_type typec_switch_dev_type = {
@@ -109,85 +130,93 @@ const struct device_type typec_switch_dev_type = {
  * connector to the USB controllers. USB Type-C plugs can be inserted
  * right-side-up or upside-down.
  */
-struct typec_switch *
+struct typec_switch_dev *
 typec_switch_register(struct device *parent,
 		      const struct typec_switch_desc *desc)
 {
-	struct typec_switch *sw;
+	struct typec_switch_dev *sw_dev;
 	int ret;
 
 	if (!desc || !desc->set)
 		return ERR_PTR(-EINVAL);
 
-	sw = kzalloc(sizeof(*sw), GFP_KERNEL);
-	if (!sw)
+	sw_dev = kzalloc(sizeof(*sw_dev), GFP_KERNEL);
+	if (!sw_dev)
 		return ERR_PTR(-ENOMEM);
 
-	sw->set = desc->set;
+	sw_dev->set = desc->set;
 
-	device_initialize(&sw->dev);
-	sw->dev.parent = parent;
-	sw->dev.fwnode = desc->fwnode;
-	sw->dev.class = &typec_mux_class;
-	sw->dev.type = &typec_switch_dev_type;
-	sw->dev.driver_data = desc->drvdata;
-	ret = dev_set_name(&sw->dev, "%s-switch", desc->name ? desc->name : dev_name(parent));
+	device_initialize(&sw_dev->dev);
+	sw_dev->dev.parent = parent;
+	sw_dev->dev.fwnode = desc->fwnode;
+	sw_dev->dev.class = &typec_mux_class;
+	sw_dev->dev.type = &typec_switch_dev_type;
+	sw_dev->dev.driver_data = desc->drvdata;
+	ret = dev_set_name(&sw_dev->dev, "%s-switch", desc->name ? desc->name : dev_name(parent));
 	if (ret) {
-		put_device(&sw->dev);
+		put_device(&sw_dev->dev);
 		return ERR_PTR(ret);
 	}
 
-	ret = device_add(&sw->dev);
+	ret = device_add(&sw_dev->dev);
 	if (ret) {
 		dev_err(parent, "failed to register switch (%d)\n", ret);
-		put_device(&sw->dev);
+		put_device(&sw_dev->dev);
 		return ERR_PTR(ret);
 	}
 
-	return sw;
+	return sw_dev;
 }
 EXPORT_SYMBOL_GPL(typec_switch_register);
 
 int typec_switch_set(struct typec_switch *sw,
 		     enum typec_orientation orientation)
 {
+	struct typec_switch_dev *sw_dev;
+
 	if (IS_ERR_OR_NULL(sw))
 		return 0;
 
-	return sw->set(sw, orientation);
+	sw_dev = sw->sw_dev;
+
+	return sw_dev->set(sw_dev, orientation);
 }
 EXPORT_SYMBOL_GPL(typec_switch_set);
 
 /**
  * typec_switch_unregister - Unregister USB Type-C orientation switch
- * @sw: USB Type-C orientation switch
+ * @sw_dev: USB Type-C orientation switch
  *
  * Unregister switch that was registered with typec_switch_register().
  */
-void typec_switch_unregister(struct typec_switch *sw)
+void typec_switch_unregister(struct typec_switch_dev *sw_dev)
 {
-	if (!IS_ERR_OR_NULL(sw))
-		device_unregister(&sw->dev);
+	if (!IS_ERR_OR_NULL(sw_dev))
+		device_unregister(&sw_dev->dev);
 }
 EXPORT_SYMBOL_GPL(typec_switch_unregister);
 
-void typec_switch_set_drvdata(struct typec_switch *sw, void *data)
+void typec_switch_set_drvdata(struct typec_switch_dev *sw_dev, void *data)
 {
-	dev_set_drvdata(&sw->dev, data);
+	dev_set_drvdata(&sw_dev->dev, data);
 }
 EXPORT_SYMBOL_GPL(typec_switch_set_drvdata);
 
-void *typec_switch_get_drvdata(struct typec_switch *sw)
+void *typec_switch_get_drvdata(struct typec_switch_dev *sw_dev)
 {
-	return dev_get_drvdata(&sw->dev);
+	return dev_get_drvdata(&sw_dev->dev);
 }
 EXPORT_SYMBOL_GPL(typec_switch_get_drvdata);
 
 /* ------------------------------------------------------------------------- */
 
+struct typec_mux {
+	struct typec_mux_dev *mux_dev;
+};
+
 static int mux_fwnode_match(struct device *dev, const void *fwnode)
 {
-	if (!is_typec_mux(dev))
+	if (!is_typec_mux_dev(dev))
 		return 0;
 
 	return dev_fwnode(dev) == fwnode;
@@ -249,7 +278,7 @@ find_mux:
 	dev = class_find_device(&typec_mux_class, NULL, fwnode,
 				mux_fwnode_match);
 
-	return dev ? to_typec_mux(dev) : ERR_PTR(-EPROBE_DEFER);
+	return dev ? to_typec_mux_dev(dev) : ERR_PTR(-EPROBE_DEFER);
 }
 
 /**
@@ -265,12 +294,23 @@ find_mux:
 struct typec_mux *fwnode_typec_mux_get(struct fwnode_handle *fwnode,
 				       const struct typec_altmode_desc *desc)
 {
+	struct typec_mux_dev *mux_dev;
 	struct typec_mux *mux;
 
-	mux = fwnode_connection_find_match(fwnode, "mode-switch", (void *)desc,
-					   typec_mux_match);
-	if (!IS_ERR_OR_NULL(mux))
-		WARN_ON(!try_module_get(mux->dev.parent->driver->owner));
+	mux = kzalloc(sizeof(*mux), GFP_KERNEL);
+	if (!mux)
+		return ERR_PTR(-ENOMEM);
+
+	mux_dev = fwnode_connection_find_match(fwnode, "mode-switch", (void *)desc,
+					       typec_mux_match);
+	if (IS_ERR_OR_NULL(mux_dev)) {
+		kfree(mux);
+		return ERR_CAST(mux_dev);
+	}
+
+	WARN_ON(!try_module_get(mux_dev->dev.parent->driver->owner));
+
+	mux->mux_dev = mux_dev;
 
 	return mux;
 }
@@ -284,25 +324,34 @@ EXPORT_SYMBOL_GPL(fwnode_typec_mux_get);
  */
 void typec_mux_put(struct typec_mux *mux)
 {
-	if (!IS_ERR_OR_NULL(mux)) {
-		module_put(mux->dev.parent->driver->owner);
-		put_device(&mux->dev);
-	}
+	struct typec_mux_dev *mux_dev;
+
+	if (IS_ERR_OR_NULL(mux))
+		return;
+
+	mux_dev = mux->mux_dev;
+	module_put(mux_dev->dev.parent->driver->owner);
+	put_device(&mux_dev->dev);
+	kfree(mux);
 }
 EXPORT_SYMBOL_GPL(typec_mux_put);
 
 int typec_mux_set(struct typec_mux *mux, struct typec_mux_state *state)
 {
+	struct typec_mux_dev *mux_dev;
+
 	if (IS_ERR_OR_NULL(mux))
 		return 0;
 
-	return mux->set(mux, state);
+	mux_dev = mux->mux_dev;
+
+	return mux_dev->set(mux_dev, state);
 }
 EXPORT_SYMBOL_GPL(typec_mux_set);
 
 static void typec_mux_release(struct device *dev)
 {
-	kfree(to_typec_mux(dev));
+	kfree(to_typec_mux_dev(dev));
 }
 
 const struct device_type typec_mux_dev_type = {
@@ -320,66 +369,66 @@ const struct device_type typec_mux_dev_type = {
  * the pins on the connector need to be reconfigured. This function registers
  * multiplexer switches routing the pins on the connector.
  */
-struct typec_mux *
+struct typec_mux_dev *
 typec_mux_register(struct device *parent, const struct typec_mux_desc *desc)
 {
-	struct typec_mux *mux;
+	struct typec_mux_dev *mux_dev;
 	int ret;
 
 	if (!desc || !desc->set)
 		return ERR_PTR(-EINVAL);
 
-	mux = kzalloc(sizeof(*mux), GFP_KERNEL);
-	if (!mux)
+	mux_dev = kzalloc(sizeof(*mux_dev), GFP_KERNEL);
+	if (!mux_dev)
 		return ERR_PTR(-ENOMEM);
 
-	mux->set = desc->set;
+	mux_dev->set = desc->set;
 
-	device_initialize(&mux->dev);
-	mux->dev.parent = parent;
-	mux->dev.fwnode = desc->fwnode;
-	mux->dev.class = &typec_mux_class;
-	mux->dev.type = &typec_mux_dev_type;
-	mux->dev.driver_data = desc->drvdata;
-	ret = dev_set_name(&mux->dev, "%s-mux", desc->name ? desc->name : dev_name(parent));
+	device_initialize(&mux_dev->dev);
+	mux_dev->dev.parent = parent;
+	mux_dev->dev.fwnode = desc->fwnode;
+	mux_dev->dev.class = &typec_mux_class;
+	mux_dev->dev.type = &typec_mux_dev_type;
+	mux_dev->dev.driver_data = desc->drvdata;
+	ret = dev_set_name(&mux_dev->dev, "%s-mux", desc->name ? desc->name : dev_name(parent));
 	if (ret) {
-		put_device(&mux->dev);
+		put_device(&mux_dev->dev);
 		return ERR_PTR(ret);
 	}
 
-	ret = device_add(&mux->dev);
+	ret = device_add(&mux_dev->dev);
 	if (ret) {
 		dev_err(parent, "failed to register mux (%d)\n", ret);
-		put_device(&mux->dev);
+		put_device(&mux_dev->dev);
 		return ERR_PTR(ret);
 	}
 
-	return mux;
+	return mux_dev;
 }
 EXPORT_SYMBOL_GPL(typec_mux_register);
 
 /**
  * typec_mux_unregister - Unregister Multiplexer Switch
- * @mux: USB Type-C Connector Multiplexer/DeMultiplexer
+ * @mux_dev: USB Type-C Connector Multiplexer/DeMultiplexer
  *
  * Unregister mux that was registered with typec_mux_register().
  */
-void typec_mux_unregister(struct typec_mux *mux)
+void typec_mux_unregister(struct typec_mux_dev *mux_dev)
 {
-	if (!IS_ERR_OR_NULL(mux))
-		device_unregister(&mux->dev);
+	if (!IS_ERR_OR_NULL(mux_dev))
+		device_unregister(&mux_dev->dev);
 }
 EXPORT_SYMBOL_GPL(typec_mux_unregister);
 
-void typec_mux_set_drvdata(struct typec_mux *mux, void *data)
+void typec_mux_set_drvdata(struct typec_mux_dev *mux_dev, void *data)
 {
-	dev_set_drvdata(&mux->dev, data);
+	dev_set_drvdata(&mux_dev->dev, data);
 }
 EXPORT_SYMBOL_GPL(typec_mux_set_drvdata);
 
-void *typec_mux_get_drvdata(struct typec_mux *mux)
+void *typec_mux_get_drvdata(struct typec_mux_dev *mux_dev)
 {
-	return dev_get_drvdata(&mux->dev);
+	return dev_get_drvdata(&mux_dev->dev);
 }
 EXPORT_SYMBOL_GPL(typec_mux_get_drvdata);
 
diff --git a/drivers/usb/typec/mux.h b/drivers/usb/typec/mux.h
index b1d6e837cb74..58f0f28b6dc8 100644
--- a/drivers/usb/typec/mux.h
+++ b/drivers/usb/typec/mux.h
@@ -5,23 +5,23 @@
 
 #include <linux/usb/typec_mux.h>
 
-struct typec_switch {
+struct typec_switch_dev {
 	struct device dev;
 	typec_switch_set_fn_t set;
 };
 
-struct typec_mux {
+struct typec_mux_dev {
 	struct device dev;
 	typec_mux_set_fn_t set;
 };
 
-#define to_typec_switch(_dev_) container_of(_dev_, struct typec_switch, dev)
-#define to_typec_mux(_dev_) container_of(_dev_, struct typec_mux, dev)
+#define to_typec_switch_dev(_dev_) container_of(_dev_, struct typec_switch_dev, dev)
+#define to_typec_mux_dev(_dev_) container_of(_dev_, struct typec_mux_dev, dev)
 
 extern const struct device_type typec_switch_dev_type;
 extern const struct device_type typec_mux_dev_type;
 
-#define is_typec_switch(dev) ((dev)->type == &typec_switch_dev_type)
-#define is_typec_mux(dev) ((dev)->type == &typec_mux_dev_type)
+#define is_typec_switch_dev(dev) ((dev)->type == &typec_switch_dev_type)
+#define is_typec_mux_dev(dev) ((dev)->type == &typec_mux_dev_type)
 
 #endif /* __USB_TYPEC_MUX__ */
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index da6b381ddf00..47b733f78fb0 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -121,8 +121,8 @@ struct pmc_usb_port {
 	int num;
 	u32 iom_status;
 	struct pmc_usb *pmc;
-	struct typec_mux *typec_mux;
-	struct typec_switch *typec_sw;
+	struct typec_mux_dev *typec_mux;
+	struct typec_switch_dev *typec_sw;
 	struct usb_role_switch *usb_sw;
 
 	enum typec_orientation orientation;
@@ -433,7 +433,7 @@ static int pmc_usb_connect(struct pmc_usb_port *port, enum usb_role role)
 }
 
 static int
-pmc_usb_mux_set(struct typec_mux *mux, struct typec_mux_state *state)
+pmc_usb_mux_set(struct typec_mux_dev *mux, struct typec_mux_state *state)
 {
 	struct pmc_usb_port *port = typec_mux_get_drvdata(mux);
 
@@ -469,7 +469,7 @@ pmc_usb_mux_set(struct typec_mux *mux, struct typec_mux_state *state)
 	return -EOPNOTSUPP;
 }
 
-static int pmc_usb_set_orientation(struct typec_switch *sw,
+static int pmc_usb_set_orientation(struct typec_switch_dev *sw,
 				   enum typec_orientation orientation)
 {
 	struct pmc_usb_port *port = typec_switch_get_drvdata(sw);
diff --git a/drivers/usb/typec/mux/pi3usb30532.c b/drivers/usb/typec/mux/pi3usb30532.c
index 7afe275b17d0..6ce9f282594e 100644
--- a/drivers/usb/typec/mux/pi3usb30532.c
+++ b/drivers/usb/typec/mux/pi3usb30532.c
@@ -23,8 +23,8 @@
 struct pi3usb30532 {
 	struct i2c_client *client;
 	struct mutex lock; /* protects the cached conf register */
-	struct typec_switch *sw;
-	struct typec_mux *mux;
+	struct typec_switch_dev *sw;
+	struct typec_mux_dev *mux;
 	u8 conf;
 };
 
@@ -45,7 +45,7 @@ static int pi3usb30532_set_conf(struct pi3usb30532 *pi, u8 new_conf)
 	return 0;
 }
 
-static int pi3usb30532_sw_set(struct typec_switch *sw,
+static int pi3usb30532_sw_set(struct typec_switch_dev *sw,
 			      enum typec_orientation orientation)
 {
 	struct pi3usb30532 *pi = typec_switch_get_drvdata(sw);
@@ -74,7 +74,7 @@ static int pi3usb30532_sw_set(struct typec_switch *sw,
 }
 
 static int
-pi3usb30532_mux_set(struct typec_mux *mux, struct typec_mux_state *state)
+pi3usb30532_mux_set(struct typec_mux_dev *mux, struct typec_mux_state *state)
 {
 	struct pi3usb30532 *pi = typec_mux_get_drvdata(mux);
 	u8 new_conf;
diff --git a/include/linux/usb/typec_mux.h b/include/linux/usb/typec_mux.h
index a9d9957933dc..ee57781dcf28 100644
--- a/include/linux/usb/typec_mux.h
+++ b/include/linux/usb/typec_mux.h
@@ -8,11 +8,13 @@
 
 struct device;
 struct typec_mux;
+struct typec_mux_dev;
 struct typec_switch;
+struct typec_switch_dev;
 struct typec_altmode;
 struct fwnode_handle;
 
-typedef int (*typec_switch_set_fn_t)(struct typec_switch *sw,
+typedef int (*typec_switch_set_fn_t)(struct typec_switch_dev *sw,
 				     enum typec_orientation orientation);
 
 struct typec_switch_desc {
@@ -32,13 +34,13 @@ static inline struct typec_switch *typec_switch_get(struct device *dev)
 	return fwnode_typec_switch_get(dev_fwnode(dev));
 }
 
-struct typec_switch *
+struct typec_switch_dev *
 typec_switch_register(struct device *parent,
 		      const struct typec_switch_desc *desc);
-void typec_switch_unregister(struct typec_switch *sw);
+void typec_switch_unregister(struct typec_switch_dev *sw);
 
-void typec_switch_set_drvdata(struct typec_switch *sw, void *data);
-void *typec_switch_get_drvdata(struct typec_switch *sw);
+void typec_switch_set_drvdata(struct typec_switch_dev *sw, void *data);
+void *typec_switch_get_drvdata(struct typec_switch_dev *sw);
 
 struct typec_mux_state {
 	struct typec_altmode *alt;
@@ -46,7 +48,7 @@ struct typec_mux_state {
 	void *data;
 };
 
-typedef int (*typec_mux_set_fn_t)(struct typec_mux *mux,
+typedef int (*typec_mux_set_fn_t)(struct typec_mux_dev *mux,
 				  struct typec_mux_state *state);
 
 struct typec_mux_desc {
@@ -67,11 +69,11 @@ typec_mux_get(struct device *dev, const struct typec_altmode_desc *desc)
 	return fwnode_typec_mux_get(dev_fwnode(dev), desc);
 }
 
-struct typec_mux *
+struct typec_mux_dev *
 typec_mux_register(struct device *parent, const struct typec_mux_desc *desc);
-void typec_mux_unregister(struct typec_mux *mux);
+void typec_mux_unregister(struct typec_mux_dev *mux);
 
-void typec_mux_set_drvdata(struct typec_mux *mux, void *data);
-void *typec_mux_get_drvdata(struct typec_mux *mux);
+void typec_mux_set_drvdata(struct typec_mux_dev *mux, void *data);
+void *typec_mux_get_drvdata(struct typec_mux_dev *mux);
 
 #endif /* __USB_TYPEC_MUX */
-- 
cgit v1.2.3


From af1969a2d734d6272c0640b50c3ed31e59e203a9 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Sat, 23 Apr 2022 20:42:03 -0400
Subject: USB: gadget: Rename usb_gadget_probe_driver()

In preparation for adding a "gadget" bus, this patch renames
usb_gadget_probe_driver() to usb_gadget_register_driver().  The new
name will be more accurate, since gadget drivers will be registered on
the gadget bus and the probing will be done by the driver core, not
the UDC core.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/YmSc29YZvxgT5fEJ@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/composite.c         | 2 +-
 drivers/usb/gadget/configfs.c          | 2 +-
 drivers/usb/gadget/legacy/dbgp.c       | 2 +-
 drivers/usb/gadget/legacy/inode.c      | 2 +-
 drivers/usb/gadget/legacy/raw_gadget.c | 4 ++--
 drivers/usb/gadget/udc/core.c          | 4 ++--
 include/linux/usb/gadget.h             | 4 ++--
 7 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 2eaeaae96759..403563c06477 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2505,7 +2505,7 @@ int usb_composite_probe(struct usb_composite_driver *driver)
 	gadget_driver->driver.name = driver->name;
 	gadget_driver->max_speed = driver->max_speed;
 
-	return usb_gadget_probe_driver(gadget_driver);
+	return usb_gadget_register_driver(gadget_driver);
 }
 EXPORT_SYMBOL_GPL(usb_composite_probe);
 
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 1fb837d9271e..4141206bb0ed 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -284,7 +284,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item,
 			goto err;
 		}
 		gi->composite.gadget_driver.udc_name = name;
-		ret = usb_gadget_probe_driver(&gi->composite.gadget_driver);
+		ret = usb_gadget_register_driver(&gi->composite.gadget_driver);
 		if (ret) {
 			gi->composite.gadget_driver.udc_name = NULL;
 			goto err;
diff --git a/drivers/usb/gadget/legacy/dbgp.c b/drivers/usb/gadget/legacy/dbgp.c
index 6bcbad382580..b62e45235e8e 100644
--- a/drivers/usb/gadget/legacy/dbgp.c
+++ b/drivers/usb/gadget/legacy/dbgp.c
@@ -422,7 +422,7 @@ static struct usb_gadget_driver dbgp_driver = {
 
 static int __init dbgp_init(void)
 {
-	return usb_gadget_probe_driver(&dbgp_driver);
+	return usb_gadget_register_driver(&dbgp_driver);
 }
 
 static void __exit dbgp_exit(void)
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 0c01e749f9ea..79990597c39f 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -1873,7 +1873,7 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 	else
 		gadgetfs_driver.max_speed = USB_SPEED_FULL;
 
-	value = usb_gadget_probe_driver(&gadgetfs_driver);
+	value = usb_gadget_register_driver(&gadgetfs_driver);
 	if (value != 0) {
 		spin_lock_irq(&dev->lock);
 		goto fail;
diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c
index 8d40a1f2ec57..b3be8db1ff63 100644
--- a/drivers/usb/gadget/legacy/raw_gadget.c
+++ b/drivers/usb/gadget/legacy/raw_gadget.c
@@ -510,12 +510,12 @@ static int raw_ioctl_run(struct raw_dev *dev, unsigned long value)
 	}
 	spin_unlock_irqrestore(&dev->lock, flags);
 
-	ret = usb_gadget_probe_driver(&dev->driver);
+	ret = usb_gadget_register_driver(&dev->driver);
 
 	spin_lock_irqsave(&dev->lock, flags);
 	if (ret) {
 		dev_err(dev->dev,
-			"fail, usb_gadget_probe_driver returned %d\n", ret);
+			"fail, usb_gadget_register_driver returned %d\n", ret);
 		dev->state = STATE_DEV_FAILED;
 		goto out_unlock;
 	}
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 85b194011a16..f0cce482b74a 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1523,7 +1523,7 @@ err1:
 	return ret;
 }
 
-int usb_gadget_probe_driver(struct usb_gadget_driver *driver)
+int usb_gadget_register_driver(struct usb_gadget_driver *driver)
 {
 	struct usb_udc		*udc = NULL, *iter;
 	int			ret = -ENODEV;
@@ -1572,7 +1572,7 @@ found:
 	mutex_unlock(&udc_lock);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(usb_gadget_probe_driver);
+EXPORT_SYMBOL_GPL(usb_gadget_register_driver);
 
 int usb_gadget_unregister_driver(struct usb_gadget_driver *driver)
 {
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 10fe57cf40be..5830b8a903da 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -745,7 +745,7 @@ struct usb_gadget_driver {
  */
 
 /**
- * usb_gadget_probe_driver - probe a gadget driver
+ * usb_gadget_register_driver - register a gadget driver
  * @driver: the driver being registered
  * Context: can sleep
  *
@@ -755,7 +755,7 @@ struct usb_gadget_driver {
  * registration call returns.  It's expected that the @bind() function will
  * be in init sections.
  */
-int usb_gadget_probe_driver(struct usb_gadget_driver *driver);
+int usb_gadget_register_driver(struct usb_gadget_driver *driver);
 
 /**
  * usb_gadget_unregister_driver - unregister a gadget driver
-- 
cgit v1.2.3


From fc274c1e997314bf47f6a62c79b5d7e554ed59c4 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Sat, 23 Apr 2022 21:35:51 -0400
Subject: USB: gadget: Add a new bus for gadgets

This patch adds a "gadget" bus and uses it for registering gadgets and
their drivers.  From now on, bindings will be managed by the driver
core rather than through ad-hoc manipulations in the UDC core.

As part of this change, the driver_pending_list is removed.  The UDC
core won't need to keep track of unbound drivers for later binding,
because the driver core handles all of that for us.

However, we do need one new feature: a way to prevent gadget drivers
from being bound to more than one gadget at a time.  The existing code
does this automatically, but the driver core doesn't -- it's perfectly
happy to bind a single driver to all the matching devices on the bus.
The patch adds a new bitflag to the usb_gadget_driver structure for
this purpose.

A nice side effect of this change is a reduction in the total lines of
code, since now the driver core will do part of the work that the UDC
used to do.

A possible future patch could add udc devices to the gadget bus, say
as a separate device type.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/YmSpdxaDNeC2BBOf@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/core.c | 256 ++++++++++++++++++++----------------------
 include/linux/usb/gadget.h    |  26 +++--
 2 files changed, 139 insertions(+), 143 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index a878e7afacdd..61790592b2c8 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -23,6 +23,8 @@
 
 #include "trace.h"
 
+static struct bus_type gadget_bus_type;
+
 /**
  * struct usb_udc - describes one usb device controller
  * @driver: the gadget driver pointer. For use by the class code
@@ -47,11 +49,9 @@ struct usb_udc {
 
 static struct class *udc_class;
 static LIST_HEAD(udc_list);
-static LIST_HEAD(gadget_driver_pending_list);
-static DEFINE_MUTEX(udc_lock);
 
-static int udc_bind_to_driver(struct usb_udc *udc,
-		struct usb_gadget_driver *driver);
+/* Protects udc_list, udc->driver, driver->is_bound, and related calls */
+static DEFINE_MUTEX(udc_lock);
 
 /* ------------------------------------------------------------------------- */
 
@@ -1238,24 +1238,6 @@ static void usb_udc_nop_release(struct device *dev)
 	dev_vdbg(dev, "%s\n", __func__);
 }
 
-/* should be called with udc_lock held */
-static int check_pending_gadget_drivers(struct usb_udc *udc)
-{
-	struct usb_gadget_driver *driver;
-	int ret = 0;
-
-	list_for_each_entry(driver, &gadget_driver_pending_list, pending)
-		if (!driver->udc_name || strcmp(driver->udc_name,
-						dev_name(&udc->dev)) == 0) {
-			ret = udc_bind_to_driver(udc, driver);
-			if (ret != -EPROBE_DEFER)
-				list_del_init(&driver->pending);
-			break;
-		}
-
-	return ret;
-}
-
 /**
  * usb_initialize_gadget - initialize a gadget and its embedded struct device
  * @parent: the parent device to this udc. Usually the controller driver's
@@ -1276,6 +1258,7 @@ void usb_initialize_gadget(struct device *parent, struct usb_gadget *gadget,
 		gadget->dev.release = usb_udc_nop_release;
 
 	device_initialize(&gadget->dev);
+	gadget->dev.bus = &gadget_bus_type;
 }
 EXPORT_SYMBOL_GPL(usb_initialize_gadget);
 
@@ -1312,6 +1295,7 @@ int usb_add_gadget(struct usb_gadget *gadget)
 
 	mutex_lock(&udc_lock);
 	list_add_tail(&udc->list, &udc_list);
+	mutex_unlock(&udc_lock);
 
 	ret = device_add(&udc->dev);
 	if (ret)
@@ -1324,23 +1308,14 @@ int usb_add_gadget(struct usb_gadget *gadget)
 	if (ret)
 		goto err_del_udc;
 
-	/* pick up one of pending gadget drivers */
-	ret = check_pending_gadget_drivers(udc);
-	if (ret)
-		goto err_del_gadget;
-
-	mutex_unlock(&udc_lock);
-
 	return 0;
 
- err_del_gadget:
-	device_del(&gadget->dev);
-
  err_del_udc:
 	flush_work(&gadget->work);
 	device_del(&udc->dev);
 
  err_unlist_udc:
+	mutex_lock(&udc_lock);
 	list_del(&udc->list);
 	mutex_unlock(&udc_lock);
 
@@ -1419,24 +1394,6 @@ int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget)
 }
 EXPORT_SYMBOL_GPL(usb_add_gadget_udc);
 
-static void usb_gadget_remove_driver(struct usb_udc *udc)
-{
-	dev_dbg(&udc->dev, "unregistering UDC driver [%s]\n",
-			udc->driver->function);
-
-	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
-
-	usb_gadget_disconnect(udc->gadget);
-	usb_gadget_disable_async_callbacks(udc);
-	if (udc->gadget->irq)
-		synchronize_irq(udc->gadget->irq);
-	udc->driver->unbind(udc->gadget);
-	usb_gadget_udc_stop(udc);
-
-	udc->driver = NULL;
-	udc->gadget->dev.driver = NULL;
-}
-
 /**
  * usb_del_gadget - deletes a gadget and unregisters its udc
  * @gadget: the gadget to be deleted.
@@ -1455,13 +1412,6 @@ void usb_del_gadget(struct usb_gadget *gadget)
 
 	mutex_lock(&udc_lock);
 	list_del(&udc->list);
-
-	if (udc->driver) {
-		struct usb_gadget_driver *driver = udc->driver;
-
-		usb_gadget_remove_driver(udc);
-		list_add(&driver->pending, &gadget_driver_pending_list);
-	}
 	mutex_unlock(&udc_lock);
 
 	kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE);
@@ -1486,123 +1436,147 @@ EXPORT_SYMBOL_GPL(usb_del_gadget_udc);
 
 /* ------------------------------------------------------------------------- */
 
-static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *driver)
+static int gadget_match_driver(struct device *dev, struct device_driver *drv)
 {
-	int ret;
+	struct usb_gadget *gadget = dev_to_usb_gadget(dev);
+	struct usb_udc *udc = gadget->udc;
+	struct usb_gadget_driver *driver = container_of(drv,
+			struct usb_gadget_driver, driver);
+
+	/* If the driver specifies a udc_name, it must match the UDC's name */
+	if (driver->udc_name &&
+			strcmp(driver->udc_name, dev_name(&udc->dev)) != 0)
+		return 0;
+
+	/* If the driver is already bound to a gadget, it doesn't match */
+	if (driver->is_bound)
+		return 0;
+
+	/* Otherwise any gadget driver matches any UDC */
+	return 1;
+}
 
-	dev_dbg(&udc->dev, "registering UDC driver [%s]\n",
-			driver->function);
+static int gadget_bind_driver(struct device *dev)
+{
+	struct usb_gadget *gadget = dev_to_usb_gadget(dev);
+	struct usb_udc *udc = gadget->udc;
+	struct usb_gadget_driver *driver = container_of(dev->driver,
+			struct usb_gadget_driver, driver);
+	int ret = 0;
 
+	mutex_lock(&udc_lock);
+	if (driver->is_bound) {
+		mutex_unlock(&udc_lock);
+		return -ENXIO;		/* Driver binds to only one gadget */
+	}
+	driver->is_bound = true;
 	udc->driver = driver;
-	udc->gadget->dev.driver = &driver->driver;
+	mutex_unlock(&udc_lock);
+
+	dev_dbg(&udc->dev, "binding gadget driver [%s]\n", driver->function);
 
 	usb_gadget_udc_set_speed(udc, driver->max_speed);
 
+	mutex_lock(&udc_lock);
 	ret = driver->bind(udc->gadget, driver);
 	if (ret)
-		goto err1;
+		goto err_bind;
+
 	ret = usb_gadget_udc_start(udc);
-	if (ret) {
-		driver->unbind(udc->gadget);
-		goto err1;
-	}
+	if (ret)
+		goto err_start;
 	usb_gadget_enable_async_callbacks(udc);
 	usb_udc_connect_control(udc);
+	mutex_unlock(&udc_lock);
 
 	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
 	return 0;
-err1:
+
+ err_start:
+	driver->unbind(udc->gadget);
+
+ err_bind:
 	if (ret != -EISNAM)
 		dev_err(&udc->dev, "failed to start %s: %d\n",
-			udc->driver->function, ret);
+			driver->function, ret);
+
 	udc->driver = NULL;
-	udc->gadget->dev.driver = NULL;
+	driver->is_bound = false;
+	mutex_unlock(&udc_lock);
+
 	return ret;
 }
 
-int usb_gadget_register_driver(struct usb_gadget_driver *driver)
+static void gadget_unbind_driver(struct device *dev)
+{
+	struct usb_gadget *gadget = dev_to_usb_gadget(dev);
+	struct usb_udc *udc = gadget->udc;
+	struct usb_gadget_driver *driver = udc->driver;
+
+	dev_dbg(&udc->dev, "unbinding gadget driver [%s]\n", driver->function);
+
+	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
+
+	mutex_lock(&udc_lock);
+	usb_gadget_disconnect(gadget);
+	usb_gadget_disable_async_callbacks(udc);
+	if (gadget->irq)
+		synchronize_irq(gadget->irq);
+	udc->driver->unbind(gadget);
+	usb_gadget_udc_stop(udc);
+
+	driver->is_bound = false;
+	udc->driver = NULL;
+	mutex_unlock(&udc_lock);
+}
+
+/* ------------------------------------------------------------------------- */
+
+int usb_gadget_register_driver_owner(struct usb_gadget_driver *driver,
+		struct module *owner, const char *mod_name)
 {
-	struct usb_udc		*udc = NULL, *iter;
-	int			ret = -ENODEV;
+	int ret;
 
 	if (!driver || !driver->bind || !driver->setup)
 		return -EINVAL;
 
+	driver->driver.bus = &gadget_bus_type;
+	driver->driver.owner = owner;
+	driver->driver.mod_name = mod_name;
+	ret = driver_register(&driver->driver);
+	if (ret) {
+		pr_warn("%s: driver registration failed: %d\n",
+				driver->function, ret);
+		return ret;
+	}
+
 	mutex_lock(&udc_lock);
-	if (driver->udc_name) {
-		list_for_each_entry(iter, &udc_list, list) {
-			ret = strcmp(driver->udc_name, dev_name(&iter->dev));
-			if (ret)
-				continue;
-			udc = iter;
-			break;
-		}
-		if (ret)
-			ret = -ENODEV;
-		else if (udc->driver)
+	if (!driver->is_bound) {
+		if (driver->match_existing_only) {
+			pr_warn("%s: couldn't find an available UDC or it's busy\n",
+					driver->function);
 			ret = -EBUSY;
-		else
-			goto found;
-	} else {
-		list_for_each_entry(iter, &udc_list, list) {
-			/* For now we take the first one */
-			if (iter->driver)
-				continue;
-			udc = iter;
-			goto found;
+		} else {
+			pr_info("%s: couldn't find an available UDC\n",
+					driver->function);
 		}
-	}
-
-	if (!driver->match_existing_only) {
-		list_add_tail(&driver->pending, &gadget_driver_pending_list);
-		pr_info("couldn't find an available UDC - added [%s] to list of pending drivers\n",
-			driver->function);
 		ret = 0;
 	}
-
 	mutex_unlock(&udc_lock);
+
 	if (ret)
-		pr_warn("couldn't find an available UDC or it's busy: %d\n", ret);
-	return ret;
-found:
-	ret = udc_bind_to_driver(udc, driver);
-	mutex_unlock(&udc_lock);
+		driver_unregister(&driver->driver);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(usb_gadget_register_driver);
+EXPORT_SYMBOL_GPL(usb_gadget_register_driver_owner);
 
 int usb_gadget_unregister_driver(struct usb_gadget_driver *driver)
 {
-	struct usb_udc		*udc = NULL;
-	int			ret = -ENODEV;
-
 	if (!driver || !driver->unbind)
 		return -EINVAL;
 
-	mutex_lock(&udc_lock);
-	list_for_each_entry(udc, &udc_list, list) {
-		if (udc->driver == driver) {
-			usb_gadget_remove_driver(udc);
-			usb_gadget_set_state(udc->gadget,
-					     USB_STATE_NOTATTACHED);
-
-			/* Maybe there is someone waiting for this UDC? */
-			check_pending_gadget_drivers(udc);
-			/*
-			 * For now we ignore bind errors as probably it's
-			 * not a valid reason to fail other's gadget unbind
-			 */
-			ret = 0;
-			break;
-		}
-	}
-
-	if (ret) {
-		list_del(&driver->pending);
-		ret = 0;
-	}
-	mutex_unlock(&udc_lock);
-	return ret;
+	driver_unregister(&driver->driver);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(usb_gadget_unregister_driver);
 
@@ -1754,8 +1728,17 @@ static int usb_udc_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
+static struct bus_type gadget_bus_type = {
+	.name = "gadget",
+	.probe = gadget_bind_driver,
+	.remove = gadget_unbind_driver,
+	.match = gadget_match_driver,
+};
+
 static int __init usb_udc_init(void)
 {
+	int rc;
+
 	udc_class = class_create(THIS_MODULE, "udc");
 	if (IS_ERR(udc_class)) {
 		pr_err("failed to create udc class --> %ld\n",
@@ -1764,12 +1747,17 @@ static int __init usb_udc_init(void)
 	}
 
 	udc_class->dev_uevent = usb_udc_uevent;
-	return 0;
+
+	rc = bus_register(&gadget_bus_type);
+	if (rc)
+		class_destroy(udc_class);
+	return rc;
 }
 subsys_initcall(usb_udc_init);
 
 static void __exit usb_udc_exit(void)
 {
+	bus_unregister(&gadget_bus_type);
 	class_destroy(udc_class);
 }
 module_exit(usb_udc_exit);
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 5830b8a903da..cf7af8a0a6e9 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -664,9 +664,9 @@ static inline int usb_gadget_check_config(struct usb_gadget *gadget)
  * @driver: Driver model state for this driver.
  * @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL,
  *	this driver will be bound to any available UDC.
- * @pending: UDC core private data used for deferred probe of this driver.
- * @match_existing_only: If udc is not found, return an error and don't add this
- *      gadget driver to list of pending driver
+ * @match_existing_only: If udc is not found, return an error and fail
+ *	the driver registration
+ * @is_bound: Allow a driver to be bound to only one gadget
  *
  * Devices are disabled till a gadget driver successfully bind()s, which
  * means the driver will handle setup() requests needed to enumerate (and
@@ -729,8 +729,8 @@ struct usb_gadget_driver {
 	struct device_driver	driver;
 
 	char			*udc_name;
-	struct list_head	pending;
 	unsigned                match_existing_only:1;
+	bool			is_bound:1;
 };
 
 
@@ -740,22 +740,30 @@ struct usb_gadget_driver {
 /* driver modules register and unregister, as usual.
  * these calls must be made in a context that can sleep.
  *
- * these will usually be implemented directly by the hardware-dependent
- * usb bus interface driver, which will only support a single driver.
+ * A gadget driver can be bound to only one gadget at a time.
  */
 
 /**
- * usb_gadget_register_driver - register a gadget driver
+ * usb_gadget_register_driver_owner - register a gadget driver
  * @driver: the driver being registered
+ * @owner: the driver module
+ * @mod_name: the driver module's build name
  * Context: can sleep
  *
  * Call this in your gadget driver's module initialization function,
- * to tell the underlying usb controller driver about your driver.
+ * to tell the underlying UDC controller driver about your driver.
  * The @bind() function will be called to bind it to a gadget before this
  * registration call returns.  It's expected that the @bind() function will
  * be in init sections.
+ *
+ * Use the macro defined below instead of calling this directly.
  */
-int usb_gadget_register_driver(struct usb_gadget_driver *driver);
+int usb_gadget_register_driver_owner(struct usb_gadget_driver *driver,
+		struct module *owner, const char *mod_name);
+
+/* use a define to avoid include chaining to get THIS_MODULE & friends */
+#define usb_gadget_register_driver(driver) \
+	usb_gadget_register_driver_owner(driver, THIS_MODULE, KBUILD_MODNAME)
 
 /**
  * usb_gadget_unregister_driver - unregister a gadget driver
-- 
cgit v1.2.3


From 8e8b11956486e3fe8cacf54a1d492ebdd8cc1fb2 Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Thu, 17 Feb 2022 10:42:52 -0800
Subject: of/platform: Add stubs for of_platform_device_create/destroy()

Code for platform_device_create() and of_platform_device_destroy() is
only generated if CONFIG_OF_ADDRESS=y. Add stubs to avoid unresolved
symbols when CONFIG_OF_ADDRESS is not set.

Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/20220217104219.v21.1.I08fd2e1c775af04f663730e9fb4d00e6bbb38541@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/of_platform.h | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index 84a966623e78..d15b6cd5e1c3 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -61,16 +61,18 @@ static inline struct platform_device *of_find_device_by_node(struct device_node
 }
 #endif
 
+extern int of_platform_bus_probe(struct device_node *root,
+				 const struct of_device_id *matches,
+				 struct device *parent);
+
+#ifdef CONFIG_OF_ADDRESS
 /* Platform devices and busses creation */
 extern struct platform_device *of_platform_device_create(struct device_node *np,
 						   const char *bus_id,
 						   struct device *parent);
 
 extern int of_platform_device_destroy(struct device *dev, void *data);
-extern int of_platform_bus_probe(struct device_node *root,
-				 const struct of_device_id *matches,
-				 struct device *parent);
-#ifdef CONFIG_OF_ADDRESS
+
 extern int of_platform_populate(struct device_node *root,
 				const struct of_device_id *matches,
 				const struct of_dev_auxdata *lookup,
@@ -84,6 +86,18 @@ extern int devm_of_platform_populate(struct device *dev);
 
 extern void devm_of_platform_depopulate(struct device *dev);
 #else
+/* Platform devices and busses creation */
+static inline struct platform_device *of_platform_device_create(struct device_node *np,
+								const char *bus_id,
+								struct device *parent)
+{
+	return NULL;
+}
+static inline int of_platform_device_destroy(struct device *dev, void *data)
+{
+	return -ENODEV;
+}
+
 static inline int of_platform_populate(struct device_node *root,
 					const struct of_device_id *matches,
 					const struct of_dev_auxdata *lookup,
-- 
cgit v1.2.3


From 0298b4b95cb373c21e6323c905589f8dac42c5b4 Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Thu, 17 Feb 2022 10:42:53 -0800
Subject: usb: misc: Add onboard_usb_hub driver

The main issue this driver addresses is that a USB hub needs to be
powered before it can be discovered. For discrete onboard hubs (an
example for such a hub is the Realtek RTS5411) this is often solved
by supplying the hub with an 'always-on' regulator, which is kind
of a hack. Some onboard hubs may require further initialization
steps, like changing the state of a GPIO or enabling a clock, which
requires even more hacks. This driver creates a platform device
representing the hub which performs the necessary initialization.
Currently it only supports switching on a single regulator, support
for multiple regulators or other actions can be added as needed.
Different initialization sequences can be supported based on the
compatible string.

Besides performing the initialization the driver can be configured
to power the hub off during system suspend. This can help to extend
battery life on battery powered devices which have no requirements
to keep the hub powered during suspend. The driver can also be
configured to leave the hub powered when a wakeup capable USB device
is connected when suspending, and power it off otherwise.

Technically the driver consists of two drivers, the platform driver
described above and a very thin USB driver that subclasses the
generic driver. The purpose of this driver is to provide the platform
driver with the USB devices corresponding to the hub(s) (a hub
controller may provide multiple 'logical' hubs, e.g. one to support
USB 2.0 and another for USB 3.x).

Note: the current series only supports hubs connected directly to
a root hub, support for other configurations could be added if
needed.

Co-developed-by: Ravi Chandra Sadineni <ravisadineni@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Ravi Chandra Sadineni <ravisadineni@chromium.org>
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/20220217104219.v21.2.I7c9a1f1d6ced41dd8310e8a03da666a32364e790@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../ABI/testing/sysfs-bus-platform-onboard-usb-hub |   8 +
 MAINTAINERS                                        |   7 +
 drivers/usb/misc/Kconfig                           |  23 +
 drivers/usb/misc/Makefile                          |   1 +
 drivers/usb/misc/onboard_usb_hub.c                 | 510 +++++++++++++++++++++
 include/linux/usb/onboard_hub.h                    |  18 +
 6 files changed, 567 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub
 create mode 100644 drivers/usb/misc/onboard_usb_hub.c
 create mode 100644 include/linux/usb/onboard_hub.h

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub b/Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub
new file mode 100644
index 000000000000..af818d9d90c1
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub
@@ -0,0 +1,8 @@
+What:		/sys/bus/platform/devices/<dev>/always_powered_in_suspend
+Date:		February 2022
+KernelVersion:	5.18
+Contact:	Matthias Kaehlcke <matthias@kaehlcke.net>
+		linux-usb@vger.kernel.org
+Description:
+		(RW) Controls whether the USB hub remains always powered
+		during system suspend or not.
\ No newline at end of file
diff --git a/MAINTAINERS b/MAINTAINERS
index fd768d43e048..38d82f592b4f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14622,6 +14622,13 @@ S:	Maintained
 T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/i2c/ov9734.c
 
+ONBOARD USB HUB DRIVER
+M:	Matthias Kaehlcke <mka@chromium.org>
+L:	linux-usb@vger.kernel.org
+S:	Maintained
+F:	Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub
+F:	drivers/usb/misc/onboard_usb_hub.c
+
 ONENAND FLASH DRIVER
 M:	Kyungmin Park <kyungmin.park@samsung.com>
 L:	linux-mtd@lists.infradead.org
diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig
index 4c5ddbd75b7e..993d07d2ffe5 100644
--- a/drivers/usb/misc/Kconfig
+++ b/drivers/usb/misc/Kconfig
@@ -295,3 +295,26 @@ config BRCM_USB_PINMAP
 	  This option enables support for remapping some USB external
 	  signals, which are typically on dedicated pins on the chip,
 	  to any gpio.
+
+config USB_ONBOARD_HUB
+	bool "Onboard USB hub support"
+	depends on OF || COMPILE_TEST
+	help
+	  Say Y here if you want to support discrete onboard USB hubs that
+	  don't require an additional control bus for initialization, but
+	  need some non-trivial form of initialization, such as enabling a
+	  power regulator. An example for such a hub is the Realtek
+	  RTS5411.
+
+	  This driver can be used as a module but its state (module vs
+	  builtin) must match the state of the USB subsystem. Enabling
+	  this config will enable the driver and it will automatically
+	  match the state of the USB subsystem. If this driver is a
+	  module it will be called onboard_usb_hub.
+
+if USB_ONBOARD_HUB
+config USB_ONBOARD_HUB_ACTUAL
+	tristate
+	default m if USB=m
+	default y if USB=y
+endif
diff --git a/drivers/usb/misc/Makefile b/drivers/usb/misc/Makefile
index 35bdb4b6c3b6..ea65e202a055 100644
--- a/drivers/usb/misc/Makefile
+++ b/drivers/usb/misc/Makefile
@@ -33,3 +33,4 @@ obj-$(CONFIG_USB_CHAOSKEY)		+= chaoskey.o
 obj-$(CONFIG_USB_SISUSBVGA)		+= sisusbvga/
 obj-$(CONFIG_USB_LINK_LAYER_TEST)	+= lvstest.o
 obj-$(CONFIG_BRCM_USB_PINMAP)		+= brcmstb-usb-pinmap.o
+obj-$(CONFIG_USB_ONBOARD_HUB_ACTUAL)	+= onboard_usb_hub.o
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
new file mode 100644
index 000000000000..34f7e4885b2e
--- /dev/null
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -0,0 +1,510 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Driver for onboard USB hubs
+ *
+ * Copyright (c) 2022, Google LLC
+ */
+
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/suspend.h>
+#include <linux/sysfs.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+#include <linux/usb/of.h>
+#include <linux/usb/onboard_hub.h>
+
+static struct usb_device_driver onboard_hub_usbdev_driver;
+
+/************************** Platform driver **************************/
+
+struct usbdev_node {
+	struct usb_device *udev;
+	struct list_head list;
+};
+
+struct onboard_hub {
+	struct regulator *vdd;
+	struct device *dev;
+	bool always_powered_in_suspend;
+	bool is_powered_on;
+	bool going_away;
+	struct list_head udev_list;
+	struct mutex lock;
+};
+
+static int onboard_hub_power_on(struct onboard_hub *hub)
+{
+	int err;
+
+	err = regulator_enable(hub->vdd);
+	if (err) {
+		dev_err(hub->dev, "failed to enable regulator: %d\n", err);
+		return err;
+	}
+
+	hub->is_powered_on = true;
+
+	return 0;
+}
+
+static int onboard_hub_power_off(struct onboard_hub *hub)
+{
+	int err;
+
+	err = regulator_disable(hub->vdd);
+	if (err) {
+		dev_err(hub->dev, "failed to disable regulator: %d\n", err);
+		return err;
+	}
+
+	hub->is_powered_on = false;
+
+	return 0;
+}
+
+static int __maybe_unused onboard_hub_suspend(struct device *dev)
+{
+	struct onboard_hub *hub = dev_get_drvdata(dev);
+	struct usbdev_node *node;
+	bool power_off = true;
+
+	if (hub->always_powered_in_suspend)
+		return 0;
+
+	mutex_lock(&hub->lock);
+
+	list_for_each_entry(node, &hub->udev_list, list) {
+		if (!device_may_wakeup(node->udev->bus->controller))
+			continue;
+
+		if (usb_wakeup_enabled_descendants(node->udev)) {
+			power_off = false;
+			break;
+		}
+	}
+
+	mutex_unlock(&hub->lock);
+
+	if (!power_off)
+		return 0;
+
+	return onboard_hub_power_off(hub);
+}
+
+static int __maybe_unused onboard_hub_resume(struct device *dev)
+{
+	struct onboard_hub *hub = dev_get_drvdata(dev);
+
+	if (hub->is_powered_on)
+		return 0;
+
+	return onboard_hub_power_on(hub);
+}
+
+static inline void get_udev_link_name(const struct usb_device *udev, char *buf, size_t size)
+{
+	snprintf(buf, size, "usb_dev.%s", dev_name(&udev->dev));
+}
+
+static int onboard_hub_add_usbdev(struct onboard_hub *hub, struct usb_device *udev)
+{
+	struct usbdev_node *node;
+	char link_name[64];
+	int err;
+
+	mutex_lock(&hub->lock);
+
+	if (hub->going_away) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (!node) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	node->udev = udev;
+
+	list_add(&node->list, &hub->udev_list);
+
+	mutex_unlock(&hub->lock);
+
+	get_udev_link_name(udev, link_name, sizeof(link_name));
+	WARN_ON(sysfs_create_link(&hub->dev->kobj, &udev->dev.kobj, link_name));
+
+	return 0;
+
+error:
+	mutex_unlock(&hub->lock);
+
+	return err;
+}
+
+static void onboard_hub_remove_usbdev(struct onboard_hub *hub, const struct usb_device *udev)
+{
+	struct usbdev_node *node;
+	char link_name[64];
+
+	get_udev_link_name(udev, link_name, sizeof(link_name));
+	sysfs_remove_link(&hub->dev->kobj, link_name);
+
+	mutex_lock(&hub->lock);
+
+	list_for_each_entry(node, &hub->udev_list, list) {
+		if (node->udev == udev) {
+			list_del(&node->list);
+			kfree(node);
+			break;
+		}
+	}
+
+	mutex_unlock(&hub->lock);
+}
+
+static ssize_t always_powered_in_suspend_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	const struct onboard_hub *hub = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n", hub->always_powered_in_suspend);
+}
+
+static ssize_t always_powered_in_suspend_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct onboard_hub *hub = dev_get_drvdata(dev);
+	bool val;
+	int ret;
+
+	ret = kstrtobool(buf, &val);
+	if (ret < 0)
+		return ret;
+
+	hub->always_powered_in_suspend = val;
+
+	return count;
+}
+static DEVICE_ATTR_RW(always_powered_in_suspend);
+
+static struct attribute *onboard_hub_attrs[] = {
+	&dev_attr_always_powered_in_suspend.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(onboard_hub);
+
+static int onboard_hub_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct onboard_hub *hub;
+	int err;
+
+	hub = devm_kzalloc(dev, sizeof(*hub), GFP_KERNEL);
+	if (!hub)
+		return -ENOMEM;
+
+	hub->vdd = devm_regulator_get(dev, "vdd");
+	if (IS_ERR(hub->vdd))
+		return PTR_ERR(hub->vdd);
+
+	hub->dev = dev;
+	mutex_init(&hub->lock);
+	INIT_LIST_HEAD(&hub->udev_list);
+
+	dev_set_drvdata(dev, hub);
+
+	err = onboard_hub_power_on(hub);
+	if (err)
+		return err;
+
+	/*
+	 * The USB driver might have been detached from the USB devices by
+	 * onboard_hub_remove(), make sure to re-attach it if needed.
+	 */
+	err = driver_attach(&onboard_hub_usbdev_driver.drvwrap.driver);
+	if (err) {
+		onboard_hub_power_off(hub);
+		return err;
+	}
+
+	return 0;
+}
+
+static int onboard_hub_remove(struct platform_device *pdev)
+{
+	struct onboard_hub *hub = dev_get_drvdata(&pdev->dev);
+	struct usbdev_node *node;
+	struct usb_device *udev;
+
+	hub->going_away = true;
+
+	mutex_lock(&hub->lock);
+
+	/* unbind the USB devices to avoid dangling references to this device */
+	while (!list_empty(&hub->udev_list)) {
+		node = list_first_entry(&hub->udev_list, struct usbdev_node, list);
+		udev = node->udev;
+
+		/*
+		 * Unbinding the driver will call onboard_hub_remove_usbdev(),
+		 * which acquires hub->lock.  We must release the lock first.
+		 */
+		get_device(&udev->dev);
+		mutex_unlock(&hub->lock);
+		device_release_driver(&udev->dev);
+		put_device(&udev->dev);
+		mutex_lock(&hub->lock);
+	}
+
+	mutex_unlock(&hub->lock);
+
+	return onboard_hub_power_off(hub);
+}
+
+static const struct of_device_id onboard_hub_match[] = {
+	{ .compatible = "usbbda,411" },
+	{ .compatible = "usbbda,5411" },
+	{ .compatible = "usbbda,414" },
+	{ .compatible = "usbbda,5414" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, onboard_hub_match);
+
+static bool of_is_onboard_usb_hub(const struct device_node *np)
+{
+	return !!of_match_node(onboard_hub_match, np);
+}
+
+static const struct dev_pm_ops __maybe_unused onboard_hub_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(onboard_hub_suspend, onboard_hub_resume)
+};
+
+static struct platform_driver onboard_hub_driver = {
+	.probe = onboard_hub_probe,
+	.remove = onboard_hub_remove,
+
+	.driver = {
+		.name = "onboard-usb-hub",
+		.of_match_table = onboard_hub_match,
+		.pm = pm_ptr(&onboard_hub_pm_ops),
+		.dev_groups = onboard_hub_groups,
+	},
+};
+
+/************************** USB driver **************************/
+
+#define VENDOR_ID_REALTEK	0x0bda
+
+/*
+ * Returns the onboard_hub platform device that is associated with the USB
+ * device passed as parameter.
+ */
+static struct onboard_hub *_find_onboard_hub(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct device_node *np;
+	struct onboard_hub *hub;
+
+	pdev = of_find_device_by_node(dev->of_node);
+	if (!pdev) {
+		np = of_parse_phandle(dev->of_node, "companion-hub", 0);
+		if (!np) {
+			dev_err(dev, "failed to find device node for companion hub\n");
+			return ERR_PTR(-EINVAL);
+		}
+
+		pdev = of_find_device_by_node(np);
+		of_node_put(np);
+
+		if (!pdev)
+			return ERR_PTR(-ENODEV);
+	}
+
+	hub = dev_get_drvdata(&pdev->dev);
+	put_device(&pdev->dev);
+
+	/*
+	 * The presence of drvdata ('hub') indicates that the platform driver
+	 * finished probing. This handles the case where (conceivably) we could
+	 * be running at the exact same time as the platform driver's probe. If
+	 * we detect the race we request probe deferral and we'll come back and
+	 * try again.
+	 */
+	if (!hub)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	return hub;
+}
+
+static int onboard_hub_usbdev_probe(struct usb_device *udev)
+{
+	struct device *dev = &udev->dev;
+	struct onboard_hub *hub;
+	int err;
+
+	/* ignore supported hubs without device tree node */
+	if (!dev->of_node)
+		return -ENODEV;
+
+	hub = _find_onboard_hub(dev);
+	if (IS_ERR(hub))
+		return PTR_ERR(hub);
+
+	dev_set_drvdata(dev, hub);
+
+	err = onboard_hub_add_usbdev(hub, udev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void onboard_hub_usbdev_disconnect(struct usb_device *udev)
+{
+	struct onboard_hub *hub = dev_get_drvdata(&udev->dev);
+
+	onboard_hub_remove_usbdev(hub, udev);
+}
+
+static const struct usb_device_id onboard_hub_id_table[] = {
+	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x0411) }, /* RTS5411 USB 3.1 */
+	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x5411) }, /* RTS5411 USB 2.1 */
+	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x0414) }, /* RTS5414 USB 3.2 */
+	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x5414) }, /* RTS5414 USB 2.1 */
+	{}
+};
+MODULE_DEVICE_TABLE(usb, onboard_hub_id_table);
+
+static struct usb_device_driver onboard_hub_usbdev_driver = {
+	.name = "onboard-usb-hub",
+	.probe = onboard_hub_usbdev_probe,
+	.disconnect = onboard_hub_usbdev_disconnect,
+	.generic_subclass = 1,
+	.supports_autosuspend =	1,
+	.id_table = onboard_hub_id_table,
+};
+
+/*** Helpers for creating/destroying platform devices for onboard hubs ***/
+
+struct pdev_list_entry {
+	struct platform_device *pdev;
+	struct list_head node;
+};
+
+/**
+ * onboard_hub_create_pdevs -- create platform devices for onboard USB hubs
+ * @parent_hub	: parent hub to scan for connected onboard hubs
+ * @pdev_list	: list of onboard hub platform devices owned by the parent hub
+ *
+ * Creates a platform device for each supported onboard hub that is connected to
+ * the given parent hub. To keep track of the platform devices they are added to
+ * a list that is owned by the parent hub.
+ */
+void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list)
+{
+	int i;
+	struct device_node *np, *npc;
+	struct platform_device *pdev = NULL;
+	struct pdev_list_entry *pdle;
+
+	INIT_LIST_HEAD(pdev_list);
+
+	for (i = 1; i <= parent_hub->maxchild; i++) {
+		np = usb_of_get_device_node(parent_hub, i);
+		if (!np)
+			continue;
+
+		if (!of_is_onboard_usb_hub(np))
+			goto node_put;
+
+		npc = of_parse_phandle(np, "companion-hub", 0);
+		if (npc) {
+			pdev = of_find_device_by_node(npc);
+			of_node_put(npc);
+		}
+
+		if (pdev) {
+			/* the companion hub already has a platform device, nothing to do here */
+			put_device(&pdev->dev);
+			goto node_put;
+		}
+
+		pdev = of_platform_device_create(np, NULL, &parent_hub->dev);
+		if (!pdev) {
+			dev_err(&parent_hub->dev,
+				"failed to create platform device for onboard hub '%pOF'\n", np);
+			goto node_put;
+		}
+
+		pdle = devm_kzalloc(&pdev->dev, sizeof(*pdle), GFP_KERNEL);
+		if (!pdle) {
+			of_platform_device_destroy(&pdev->dev, NULL);
+			goto node_put;
+		}
+
+		pdle->pdev = pdev;
+		list_add(&pdle->node, pdev_list);
+
+node_put:
+		of_node_put(np);
+	}
+}
+EXPORT_SYMBOL_GPL(onboard_hub_create_pdevs);
+
+/**
+ * onboard_hub_destroy_pdevs -- free resources of onboard hub platform devices
+ * @pdev_list	: list of onboard hub platform devices
+ *
+ * Destroys the platform devices in the given list and frees the memory associated
+ * with the list entry.
+ */
+void onboard_hub_destroy_pdevs(struct list_head *pdev_list)
+{
+	struct pdev_list_entry *pdle, *tmp;
+
+	list_for_each_entry_safe(pdle, tmp, pdev_list, node) {
+		list_del(&pdle->node);
+		of_platform_device_destroy(&pdle->pdev->dev, NULL);
+	}
+}
+EXPORT_SYMBOL_GPL(onboard_hub_destroy_pdevs);
+
+/************************** Driver (de)registration **************************/
+
+static int __init onboard_hub_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&onboard_hub_driver);
+	if (ret)
+		return ret;
+
+	ret = usb_register_device_driver(&onboard_hub_usbdev_driver, THIS_MODULE);
+	if (ret)
+		platform_driver_unregister(&onboard_hub_driver);
+
+	return ret;
+}
+module_init(onboard_hub_init);
+
+static void __exit onboard_hub_exit(void)
+{
+	usb_deregister_device_driver(&onboard_hub_usbdev_driver);
+	platform_driver_unregister(&onboard_hub_driver);
+}
+module_exit(onboard_hub_exit);
+
+MODULE_AUTHOR("Matthias Kaehlcke <mka@chromium.org>");
+MODULE_DESCRIPTION("Driver for discrete onboard USB hubs");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h
new file mode 100644
index 000000000000..d9373230556e
--- /dev/null
+++ b/include/linux/usb/onboard_hub.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __LINUX_USB_ONBOARD_HUB_H
+#define __LINUX_USB_ONBOARD_HUB_H
+
+struct usb_device;
+struct list_head;
+
+#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB)
+void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list);
+void onboard_hub_destroy_pdevs(struct list_head *pdev_list);
+#else
+static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub,
+					    struct list_head *pdev_list) {}
+static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {}
+#endif
+
+#endif /* __LINUX_USB_ONBOARD_HUB_H */
-- 
cgit v1.2.3


From c40b62216c1aecc0dc00faf33d71bd71cb440337 Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Thu, 17 Feb 2022 10:42:54 -0800
Subject: usb: core: hcd: Create platform devices for onboard hubs in probe()

Call onboard_hub_create/destroy_pdevs() from usb_add/remove_hcd()
for primary HCDs to create/destroy platform devices for onboard
USB hubs that may be connected to the root hub of the controller.
These functions are a NOP unless CONFIG_USB_ONBOARD_HUB=y/m.

Also add a field to struct usb_hcd to keep track of the onboard hub
platform devices that are owned by the HCD.

Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/20220217104219.v21.3.I7a3a7d9d2126c34079b1cab87aa0b2ec3030f9b7@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c  | 6 ++++++
 include/linux/usb/hcd.h | 1 +
 2 files changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index d9712c2602af..81785072fafb 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -36,6 +36,7 @@
 #include <linux/phy/phy.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
+#include <linux/usb/onboard_hub.h>
 #include <linux/usb/otg.h>
 
 #include "usb.h"
@@ -2984,6 +2985,9 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	if (hcd->uses_new_polling && HCD_POLL_RH(hcd))
 		usb_hcd_poll_rh_status(hcd);
 
+	if (usb_hcd_is_primary_hcd(hcd))
+		onboard_hub_create_pdevs(hcd->self.root_hub, &hcd->onboard_hub_devs);
+
 	return retval;
 
 err_register_root_hub:
@@ -3062,6 +3066,8 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	if (usb_hcd_is_primary_hcd(hcd)) {
 		if (hcd->irq > 0)
 			free_irq(hcd->irq, hcd);
+
+		onboard_hub_destroy_pdevs(&hcd->onboard_hub_devs);
 	}
 
 	usb_deregister_bus(&hcd->self);
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 548a028f2dab..4ebc91c09182 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -198,6 +198,7 @@ struct usb_hcd {
 	struct usb_hcd		*shared_hcd;
 	struct usb_hcd		*primary_hcd;
 
+	struct list_head	onboard_hub_devs;
 
 #define HCD_BUFFER_POOLS	4
 	struct dma_pool		*pool[HCD_BUFFER_POOLS];
-- 
cgit v1.2.3


From 9723f69d1de37ca25474372ad1753ea39bb0dce1 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Fri, 8 Apr 2022 10:00:43 +0200
Subject: mmc: core: improve API to make clear that mmc_sw_reset is for cards

To make it unambiguous that mmc_sw_reset() is for cards and not for
controllers, we make the function argument mmc_card instead of mmc_host.
There are no users to convert currently.

Suggested-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://lore.kernel.org/r/20220408080045.6497-3-wsa+renesas@sang-engineering.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/core.c  | 3 ++-
 include/linux/mmc/core.h | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index c6ae16d40766..06a9bc97be2a 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2017,8 +2017,9 @@ int mmc_hw_reset(struct mmc_card *card)
 }
 EXPORT_SYMBOL(mmc_hw_reset);
 
-int mmc_sw_reset(struct mmc_host *host)
+int mmc_sw_reset(struct mmc_card *card)
 {
+	struct mmc_host *host = card->host;
 	int ret;
 
 	if (!host->bus_ops->sw_reset)
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index de5c64bbdb72..6efec0b9820c 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -176,7 +176,7 @@ int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd,
 		int retries);
 
 int mmc_hw_reset(struct mmc_card *card);
-int mmc_sw_reset(struct mmc_host *host);
+int mmc_sw_reset(struct mmc_card *card);
 void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card);
 
 #endif /* LINUX_MMC_CORE_H */
-- 
cgit v1.2.3


From 32f18e596141f40dbc5d8700b2730371ffd3055f Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Fri, 8 Apr 2022 10:00:44 +0200
Subject: mmc: improve API to make clear hw_reset callback is for cards

To make it unambiguous that the hw_reset callback is for cards and not
for controllers, we add 'card' to the callback name and convert all
users in one go. We keep the argument as mmc_host, though, because the
callback is used very early when mmc_card is not yet populated.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://lore.kernel.org/r/20220408080045.6497-4-wsa+renesas@sang-engineering.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/core.c              | 4 ++--
 drivers/mmc/core/mmc.c               | 4 ++--
 drivers/mmc/host/bcm2835.c           | 2 +-
 drivers/mmc/host/dw_mmc.c            | 2 +-
 drivers/mmc/host/meson-mx-sdhc-mmc.c | 2 +-
 drivers/mmc/host/mtk-sd.c            | 2 +-
 drivers/mmc/host/sdhci.c             | 2 +-
 drivers/mmc/host/sunxi-mmc.c         | 2 +-
 drivers/mmc/host/uniphier-sd.c       | 2 +-
 include/linux/mmc/host.h             | 2 +-
 10 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 06a9bc97be2a..4b70cbfc6d5d 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -1988,9 +1988,9 @@ static void mmc_hw_reset_for_init(struct mmc_host *host)
 {
 	mmc_pwrseq_reset(host);
 
-	if (!(host->caps & MMC_CAP_HW_RESET) || !host->ops->hw_reset)
+	if (!(host->caps & MMC_CAP_HW_RESET) || !host->ops->card_hw_reset)
 		return;
-	host->ops->hw_reset(host);
+	host->ops->card_hw_reset(host);
 }
 
 /**
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index e7ea45386c22..5d8d9f72476f 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -2225,11 +2225,11 @@ static int _mmc_hw_reset(struct mmc_host *host)
 	 */
 	_mmc_flush_cache(host);
 
-	if ((host->caps & MMC_CAP_HW_RESET) && host->ops->hw_reset &&
+	if ((host->caps & MMC_CAP_HW_RESET) && host->ops->card_hw_reset &&
 	     mmc_can_reset(card)) {
 		/* If the card accept RST_n signal, send it. */
 		mmc_set_clock(host, host->f_init);
-		host->ops->hw_reset(host);
+		host->ops->card_hw_reset(host);
 		/* Set initial state and call mmc_set_ios */
 		mmc_set_initial_state(host);
 	} else {
diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c
index 463b707d9e99..641ab4f42125 100644
--- a/drivers/mmc/host/bcm2835.c
+++ b/drivers/mmc/host/bcm2835.c
@@ -1259,7 +1259,7 @@ static void bcm2835_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 static const struct mmc_host_ops bcm2835_ops = {
 	.request = bcm2835_request,
 	.set_ios = bcm2835_set_ios,
-	.hw_reset = bcm2835_reset,
+	.card_hw_reset = bcm2835_reset,
 };
 
 static int bcm2835_add_host(struct bcm2835_host *host)
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 06dc56cbada8..581614196a84 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -1812,7 +1812,7 @@ static const struct mmc_host_ops dw_mci_ops = {
 	.set_ios		= dw_mci_set_ios,
 	.get_ro			= dw_mci_get_ro,
 	.get_cd			= dw_mci_get_cd,
-	.hw_reset               = dw_mci_hw_reset,
+	.card_hw_reset          = dw_mci_hw_reset,
 	.enable_sdio_irq	= dw_mci_enable_sdio_irq,
 	.ack_sdio_irq		= dw_mci_ack_sdio_irq,
 	.execute_tuning		= dw_mci_execute_tuning,
diff --git a/drivers/mmc/host/meson-mx-sdhc-mmc.c b/drivers/mmc/host/meson-mx-sdhc-mmc.c
index 28aa78aa08f3..e92e63cb5641 100644
--- a/drivers/mmc/host/meson-mx-sdhc-mmc.c
+++ b/drivers/mmc/host/meson-mx-sdhc-mmc.c
@@ -511,7 +511,7 @@ static int meson_mx_sdhc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 }
 
 static const struct mmc_host_ops meson_mx_sdhc_ops = {
-	.hw_reset			= meson_mx_sdhc_hw_reset,
+	.card_hw_reset			= meson_mx_sdhc_hw_reset,
 	.request			= meson_mx_sdhc_request,
 	.set_ios			= meson_mx_sdhc_set_ios,
 	.card_busy			= meson_mx_sdhc_card_busy,
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index e61b0b98065a..195dc897188b 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -2458,7 +2458,7 @@ static const struct mmc_host_ops mt_msdc_ops = {
 	.execute_tuning = msdc_execute_tuning,
 	.prepare_hs400_tuning = msdc_prepare_hs400_tuning,
 	.execute_hs400_tuning = msdc_execute_hs400_tuning,
-	.hw_reset = msdc_hw_reset,
+	.card_hw_reset = msdc_hw_reset,
 };
 
 static const struct cqhci_host_ops msdc_cmdq_ops = {
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 07c6da1f2f0f..22152029e14c 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2999,7 +2999,7 @@ static const struct mmc_host_ops sdhci_ops = {
 	.set_ios	= sdhci_set_ios,
 	.get_cd		= sdhci_get_cd,
 	.get_ro		= sdhci_get_ro,
-	.hw_reset	= sdhci_hw_reset,
+	.card_hw_reset	= sdhci_hw_reset,
 	.enable_sdio_irq = sdhci_enable_sdio_irq,
 	.ack_sdio_irq    = sdhci_ack_sdio_irq,
 	.start_signal_voltage_switch	= sdhci_start_signal_voltage_switch,
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index c62afd212692..0e8fbf4957d8 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -1115,7 +1115,7 @@ static const struct mmc_host_ops sunxi_mmc_ops = {
 	.get_cd		 = mmc_gpio_get_cd,
 	.enable_sdio_irq = sunxi_mmc_enable_sdio_irq,
 	.start_signal_voltage_switch = sunxi_mmc_volt_switch,
-	.hw_reset	 = sunxi_mmc_hw_reset,
+	.card_hw_reset	 = sunxi_mmc_hw_reset,
 	.card_busy	 = sunxi_mmc_card_busy,
 };
 
diff --git a/drivers/mmc/host/uniphier-sd.c b/drivers/mmc/host/uniphier-sd.c
index ccbf9885a52b..3a8defdcca77 100644
--- a/drivers/mmc/host/uniphier-sd.c
+++ b/drivers/mmc/host/uniphier-sd.c
@@ -597,7 +597,7 @@ static int uniphier_sd_probe(struct platform_device *pdev)
 			ret = PTR_ERR(priv->rst_hw);
 			goto free_host;
 		}
-		host->ops.hw_reset = uniphier_sd_hw_reset;
+		host->ops.card_hw_reset = uniphier_sd_hw_reset;
 	}
 
 	if (host->mmc->caps & MMC_CAP_UHS) {
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 7afb57cab00b..c193c50ccd78 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -181,7 +181,7 @@ struct mmc_host_ops {
 					 unsigned int max_dtr, int host_drv,
 					 int card_drv, int *drv_type);
 	/* Reset the eMMC card via RST_n */
-	void	(*hw_reset)(struct mmc_host *host);
+	void	(*card_hw_reset)(struct mmc_host *host);
 	void	(*card_event)(struct mmc_host *host);
 
 	/*
-- 
cgit v1.2.3


From 13acb62ce1ee7377ef03034fbbad6f5499464b86 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Tue, 12 Apr 2022 11:31:02 +0200
Subject: mmc: sh_mmcif: move platform_data header to proper location

We have a dedicated directory for platform_data meanwhile, don't spoil
the MMC directory with it.

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://lore.kernel.org/r/20220412093102.3428-1-wsa+renesas@sang-engineering.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 arch/sh/boards/board-sh7757lcr.c       |   2 +-
 arch/sh/boards/mach-ecovec24/setup.c   |   2 +-
 arch/sh/boot/romimage/mmcif-sh7724.c   |   2 +-
 drivers/mmc/host/sh_mmcif.c            |   2 +-
 include/linux/mmc/sh_mmcif.h           | 209 ---------------------------------
 include/linux/platform_data/sh_mmcif.h | 207 ++++++++++++++++++++++++++++++++
 6 files changed, 211 insertions(+), 213 deletions(-)
 delete mode 100644 include/linux/mmc/sh_mmcif.h
 create mode 100644 include/linux/platform_data/sh_mmcif.h

(limited to 'include/linux')

diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c
index c32b4c6229d3..f39c8196efdf 100644
--- a/arch/sh/boards/board-sh7757lcr.c
+++ b/arch/sh/boards/board-sh7757lcr.c
@@ -16,7 +16,7 @@
 #include <linux/io.h>
 #include <linux/mfd/tmio.h>
 #include <linux/mmc/host.h>
-#include <linux/mmc/sh_mmcif.h>
+#include <linux/platform_data/sh_mmcif.h>
 #include <linux/sh_eth.h>
 #include <linux/sh_intc.h>
 #include <linux/usb/renesas_usbhs.h>
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 4c9522dd351f..674da7ebd8b7 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -19,7 +19,7 @@
 #include <linux/memblock.h>
 #include <linux/mfd/tmio.h>
 #include <linux/mmc/host.h>
-#include <linux/mmc/sh_mmcif.h>
+#include <linux/platform_data/sh_mmcif.h>
 #include <linux/mtd/physmap.h>
 #include <linux/gpio.h>
 #include <linux/gpio/machine.h>
diff --git a/arch/sh/boot/romimage/mmcif-sh7724.c b/arch/sh/boot/romimage/mmcif-sh7724.c
index 6595b6b45bf1..d30123d859e0 100644
--- a/arch/sh/boot/romimage/mmcif-sh7724.c
+++ b/arch/sh/boot/romimage/mmcif-sh7724.c
@@ -8,7 +8,7 @@
  * for more details.
  */
 
-#include <linux/mmc/sh_mmcif.h>
+#include <linux/platform_data/sh_mmcif.h>
 #include <mach/romimage.h>
 
 #define MMCIF_BASE      (void __iomem *)0xa4ca0000
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 5f9ebf045b1c..0fd4c9d644dd 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -43,12 +43,12 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
 #include <linux/mmc/sdio.h>
-#include <linux/mmc/sh_mmcif.h>
 #include <linux/mmc/slot-gpio.h>
 #include <linux/mod_devicetable.h>
 #include <linux/mutex.h>
 #include <linux/of_device.h>
 #include <linux/pagemap.h>
+#include <linux/platform_data/sh_mmcif.h>
 #include <linux/platform_device.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h
deleted file mode 100644
index e25533b95d9f..000000000000
--- a/include/linux/mmc/sh_mmcif.h
+++ /dev/null
@@ -1,209 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * include/linux/mmc/sh_mmcif.h
- *
- * platform data for eMMC driver
- *
- * Copyright (C) 2010 Renesas Solutions Corp.
- */
-
-#ifndef LINUX_MMC_SH_MMCIF_H
-#define LINUX_MMC_SH_MMCIF_H
-
-#include <linux/io.h>
-#include <linux/platform_device.h>
-
-/*
- * MMCIF : CE_CLK_CTRL [19:16]
- * 1000 : Peripheral clock / 512
- * 0111 : Peripheral clock / 256
- * 0110 : Peripheral clock / 128
- * 0101 : Peripheral clock / 64
- * 0100 : Peripheral clock / 32
- * 0011 : Peripheral clock / 16
- * 0010 : Peripheral clock / 8
- * 0001 : Peripheral clock / 4
- * 0000 : Peripheral clock / 2
- * 1111 : Peripheral clock (sup_pclk set '1')
- */
-
-struct sh_mmcif_plat_data {
-	unsigned int		slave_id_tx;	/* embedded slave_id_[tr]x */
-	unsigned int		slave_id_rx;
-	u8			sup_pclk;	/* 1 :SH7757, 0: SH7724/SH7372 */
-	unsigned long		caps;
-	u32			ocr;
-};
-
-#define MMCIF_CE_CMD_SET	0x00000000
-#define MMCIF_CE_ARG		0x00000008
-#define MMCIF_CE_ARG_CMD12	0x0000000C
-#define MMCIF_CE_CMD_CTRL	0x00000010
-#define MMCIF_CE_BLOCK_SET	0x00000014
-#define MMCIF_CE_CLK_CTRL	0x00000018
-#define MMCIF_CE_BUF_ACC	0x0000001C
-#define MMCIF_CE_RESP3		0x00000020
-#define MMCIF_CE_RESP2		0x00000024
-#define MMCIF_CE_RESP1		0x00000028
-#define MMCIF_CE_RESP0		0x0000002C
-#define MMCIF_CE_RESP_CMD12	0x00000030
-#define MMCIF_CE_DATA		0x00000034
-#define MMCIF_CE_INT		0x00000040
-#define MMCIF_CE_INT_MASK	0x00000044
-#define MMCIF_CE_HOST_STS1	0x00000048
-#define MMCIF_CE_HOST_STS2	0x0000004C
-#define MMCIF_CE_CLK_CTRL2	0x00000070
-#define MMCIF_CE_VERSION	0x0000007C
-
-/* CE_BUF_ACC */
-#define BUF_ACC_DMAWEN		(1 << 25)
-#define BUF_ACC_DMAREN		(1 << 24)
-#define BUF_ACC_BUSW_32		(0 << 17)
-#define BUF_ACC_BUSW_16		(1 << 17)
-#define BUF_ACC_ATYP		(1 << 16)
-
-/* CE_CLK_CTRL */
-#define CLK_ENABLE		(1 << 24) /* 1: output mmc clock */
-#define CLK_CLEAR		(0xf << 16)
-#define CLK_SUP_PCLK		(0xf << 16)
-#define CLKDIV_4		(1 << 16) /* mmc clock frequency.
-					   * n: bus clock/(2^(n+1)) */
-#define CLKDIV_256		(7 << 16) /* mmc clock frequency. (see above) */
-#define SRSPTO_256		(2 << 12) /* resp timeout */
-#define SRBSYTO_29		(0xf << 8) /* resp busy timeout */
-#define SRWDTO_29		(0xf << 4) /* read/write timeout */
-#define SCCSTO_29		(0xf << 0) /* ccs timeout */
-
-/* CE_VERSION */
-#define SOFT_RST_ON		(1 << 31)
-#define SOFT_RST_OFF		0
-
-static inline u32 sh_mmcif_readl(void __iomem *addr, int reg)
-{
-	return __raw_readl(addr + reg);
-}
-
-static inline void sh_mmcif_writel(void __iomem *addr, int reg, u32 val)
-{
-	__raw_writel(val, addr + reg);
-}
-
-#define SH_MMCIF_BBS 512 /* boot block size */
-
-static inline void sh_mmcif_boot_cmd_send(void __iomem *base,
-					  unsigned long cmd, unsigned long arg)
-{
-	sh_mmcif_writel(base, MMCIF_CE_INT, 0);
-	sh_mmcif_writel(base, MMCIF_CE_ARG, arg);
-	sh_mmcif_writel(base, MMCIF_CE_CMD_SET, cmd);
-}
-
-static inline int sh_mmcif_boot_cmd_poll(void __iomem *base, unsigned long mask)
-{
-	unsigned long tmp;
-	int cnt;
-
-	for (cnt = 0; cnt < 1000000; cnt++) {
-		tmp = sh_mmcif_readl(base, MMCIF_CE_INT);
-		if (tmp & mask) {
-			sh_mmcif_writel(base, MMCIF_CE_INT, tmp & ~mask);
-			return 0;
-		}
-	}
-
-	return -1;
-}
-
-static inline int sh_mmcif_boot_cmd(void __iomem *base,
-				    unsigned long cmd, unsigned long arg)
-{
-	sh_mmcif_boot_cmd_send(base, cmd, arg);
-	return sh_mmcif_boot_cmd_poll(base, 0x00010000);
-}
-
-static inline int sh_mmcif_boot_do_read_single(void __iomem *base,
-					       unsigned int block_nr,
-					       unsigned long *buf)
-{
-	int k;
-
-	/* CMD13 - Status */
-	sh_mmcif_boot_cmd(base, 0x0d400000, 0x00010000);
-
-	if (sh_mmcif_readl(base, MMCIF_CE_RESP0) != 0x0900)
-		return -1;
-
-	/* CMD17 - Read */
-	sh_mmcif_boot_cmd(base, 0x11480000, block_nr * SH_MMCIF_BBS);
-	if (sh_mmcif_boot_cmd_poll(base, 0x00100000) < 0)
-		return -1;
-
-	for (k = 0; k < (SH_MMCIF_BBS / 4); k++)
-		buf[k] = sh_mmcif_readl(base, MMCIF_CE_DATA);
-
-	return 0;
-}
-
-static inline int sh_mmcif_boot_do_read(void __iomem *base,
-					unsigned long first_block,
-					unsigned long nr_blocks,
-					void *buf)
-{
-	unsigned long k;
-	int ret = 0;
-
-	/* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */
-	sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL,
-			CLK_ENABLE | CLKDIV_4 | SRSPTO_256 |
-			SRBSYTO_29 | SRWDTO_29 | SCCSTO_29);
-
-	/* CMD9 - Get CSD */
-	sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000);
-
-	/* CMD7 - Select the card */
-	sh_mmcif_boot_cmd(base, 0x07400000, 0x00010000);
-
-	/* CMD16 - Set the block size */
-	sh_mmcif_boot_cmd(base, 0x10400000, SH_MMCIF_BBS);
-
-	for (k = 0; !ret && k < nr_blocks; k++)
-		ret = sh_mmcif_boot_do_read_single(base, first_block + k,
-						   buf + (k * SH_MMCIF_BBS));
-
-	return ret;
-}
-
-static inline void sh_mmcif_boot_init(void __iomem *base)
-{
-	/* reset */
-	sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_ON);
-	sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_OFF);
-
-	/* byte swap */
-	sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, BUF_ACC_ATYP);
-
-	/* Set block size in MMCIF hardware */
-	sh_mmcif_writel(base, MMCIF_CE_BLOCK_SET, SH_MMCIF_BBS);
-
-	/* Enable the clock, set it to Bus clock/256 (about 325Khz). */
-	sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL,
-			CLK_ENABLE | CLKDIV_256 | SRSPTO_256 |
-			SRBSYTO_29 | SRWDTO_29 | SCCSTO_29);
-
-	/* CMD0 */
-	sh_mmcif_boot_cmd(base, 0x00000040, 0);
-
-	/* CMD1 - Get OCR */
-	do {
-		sh_mmcif_boot_cmd(base, 0x01405040, 0x40300000); /* CMD1 */
-	} while ((sh_mmcif_readl(base, MMCIF_CE_RESP0) & 0x80000000)
-		 != 0x80000000);
-
-	/* CMD2 - Get CID */
-	sh_mmcif_boot_cmd(base, 0x02806040, 0);
-
-	/* CMD3 - Set card relative address */
-	sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000);
-}
-
-#endif /* LINUX_MMC_SH_MMCIF_H */
diff --git a/include/linux/platform_data/sh_mmcif.h b/include/linux/platform_data/sh_mmcif.h
new file mode 100644
index 000000000000..6eb914f958f9
--- /dev/null
+++ b/include/linux/platform_data/sh_mmcif.h
@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * platform data for eMMC driver
+ *
+ * Copyright (C) 2010 Renesas Solutions Corp.
+ */
+
+#ifndef LINUX_MMC_SH_MMCIF_H
+#define LINUX_MMC_SH_MMCIF_H
+
+#include <linux/io.h>
+#include <linux/platform_device.h>
+
+/*
+ * MMCIF : CE_CLK_CTRL [19:16]
+ * 1000 : Peripheral clock / 512
+ * 0111 : Peripheral clock / 256
+ * 0110 : Peripheral clock / 128
+ * 0101 : Peripheral clock / 64
+ * 0100 : Peripheral clock / 32
+ * 0011 : Peripheral clock / 16
+ * 0010 : Peripheral clock / 8
+ * 0001 : Peripheral clock / 4
+ * 0000 : Peripheral clock / 2
+ * 1111 : Peripheral clock (sup_pclk set '1')
+ */
+
+struct sh_mmcif_plat_data {
+	unsigned int		slave_id_tx;	/* embedded slave_id_[tr]x */
+	unsigned int		slave_id_rx;
+	u8			sup_pclk;	/* 1 :SH7757, 0: SH7724/SH7372 */
+	unsigned long		caps;
+	u32			ocr;
+};
+
+#define MMCIF_CE_CMD_SET	0x00000000
+#define MMCIF_CE_ARG		0x00000008
+#define MMCIF_CE_ARG_CMD12	0x0000000C
+#define MMCIF_CE_CMD_CTRL	0x00000010
+#define MMCIF_CE_BLOCK_SET	0x00000014
+#define MMCIF_CE_CLK_CTRL	0x00000018
+#define MMCIF_CE_BUF_ACC	0x0000001C
+#define MMCIF_CE_RESP3		0x00000020
+#define MMCIF_CE_RESP2		0x00000024
+#define MMCIF_CE_RESP1		0x00000028
+#define MMCIF_CE_RESP0		0x0000002C
+#define MMCIF_CE_RESP_CMD12	0x00000030
+#define MMCIF_CE_DATA		0x00000034
+#define MMCIF_CE_INT		0x00000040
+#define MMCIF_CE_INT_MASK	0x00000044
+#define MMCIF_CE_HOST_STS1	0x00000048
+#define MMCIF_CE_HOST_STS2	0x0000004C
+#define MMCIF_CE_CLK_CTRL2	0x00000070
+#define MMCIF_CE_VERSION	0x0000007C
+
+/* CE_BUF_ACC */
+#define BUF_ACC_DMAWEN		(1 << 25)
+#define BUF_ACC_DMAREN		(1 << 24)
+#define BUF_ACC_BUSW_32		(0 << 17)
+#define BUF_ACC_BUSW_16		(1 << 17)
+#define BUF_ACC_ATYP		(1 << 16)
+
+/* CE_CLK_CTRL */
+#define CLK_ENABLE		(1 << 24) /* 1: output mmc clock */
+#define CLK_CLEAR		(0xf << 16)
+#define CLK_SUP_PCLK		(0xf << 16)
+#define CLKDIV_4		(1 << 16) /* mmc clock frequency.
+					   * n: bus clock/(2^(n+1)) */
+#define CLKDIV_256		(7 << 16) /* mmc clock frequency. (see above) */
+#define SRSPTO_256		(2 << 12) /* resp timeout */
+#define SRBSYTO_29		(0xf << 8) /* resp busy timeout */
+#define SRWDTO_29		(0xf << 4) /* read/write timeout */
+#define SCCSTO_29		(0xf << 0) /* ccs timeout */
+
+/* CE_VERSION */
+#define SOFT_RST_ON		(1 << 31)
+#define SOFT_RST_OFF		0
+
+static inline u32 sh_mmcif_readl(void __iomem *addr, int reg)
+{
+	return __raw_readl(addr + reg);
+}
+
+static inline void sh_mmcif_writel(void __iomem *addr, int reg, u32 val)
+{
+	__raw_writel(val, addr + reg);
+}
+
+#define SH_MMCIF_BBS 512 /* boot block size */
+
+static inline void sh_mmcif_boot_cmd_send(void __iomem *base,
+					  unsigned long cmd, unsigned long arg)
+{
+	sh_mmcif_writel(base, MMCIF_CE_INT, 0);
+	sh_mmcif_writel(base, MMCIF_CE_ARG, arg);
+	sh_mmcif_writel(base, MMCIF_CE_CMD_SET, cmd);
+}
+
+static inline int sh_mmcif_boot_cmd_poll(void __iomem *base, unsigned long mask)
+{
+	unsigned long tmp;
+	int cnt;
+
+	for (cnt = 0; cnt < 1000000; cnt++) {
+		tmp = sh_mmcif_readl(base, MMCIF_CE_INT);
+		if (tmp & mask) {
+			sh_mmcif_writel(base, MMCIF_CE_INT, tmp & ~mask);
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+static inline int sh_mmcif_boot_cmd(void __iomem *base,
+				    unsigned long cmd, unsigned long arg)
+{
+	sh_mmcif_boot_cmd_send(base, cmd, arg);
+	return sh_mmcif_boot_cmd_poll(base, 0x00010000);
+}
+
+static inline int sh_mmcif_boot_do_read_single(void __iomem *base,
+					       unsigned int block_nr,
+					       unsigned long *buf)
+{
+	int k;
+
+	/* CMD13 - Status */
+	sh_mmcif_boot_cmd(base, 0x0d400000, 0x00010000);
+
+	if (sh_mmcif_readl(base, MMCIF_CE_RESP0) != 0x0900)
+		return -1;
+
+	/* CMD17 - Read */
+	sh_mmcif_boot_cmd(base, 0x11480000, block_nr * SH_MMCIF_BBS);
+	if (sh_mmcif_boot_cmd_poll(base, 0x00100000) < 0)
+		return -1;
+
+	for (k = 0; k < (SH_MMCIF_BBS / 4); k++)
+		buf[k] = sh_mmcif_readl(base, MMCIF_CE_DATA);
+
+	return 0;
+}
+
+static inline int sh_mmcif_boot_do_read(void __iomem *base,
+					unsigned long first_block,
+					unsigned long nr_blocks,
+					void *buf)
+{
+	unsigned long k;
+	int ret = 0;
+
+	/* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */
+	sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL,
+			CLK_ENABLE | CLKDIV_4 | SRSPTO_256 |
+			SRBSYTO_29 | SRWDTO_29 | SCCSTO_29);
+
+	/* CMD9 - Get CSD */
+	sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000);
+
+	/* CMD7 - Select the card */
+	sh_mmcif_boot_cmd(base, 0x07400000, 0x00010000);
+
+	/* CMD16 - Set the block size */
+	sh_mmcif_boot_cmd(base, 0x10400000, SH_MMCIF_BBS);
+
+	for (k = 0; !ret && k < nr_blocks; k++)
+		ret = sh_mmcif_boot_do_read_single(base, first_block + k,
+						   buf + (k * SH_MMCIF_BBS));
+
+	return ret;
+}
+
+static inline void sh_mmcif_boot_init(void __iomem *base)
+{
+	/* reset */
+	sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_ON);
+	sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_OFF);
+
+	/* byte swap */
+	sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, BUF_ACC_ATYP);
+
+	/* Set block size in MMCIF hardware */
+	sh_mmcif_writel(base, MMCIF_CE_BLOCK_SET, SH_MMCIF_BBS);
+
+	/* Enable the clock, set it to Bus clock/256 (about 325Khz). */
+	sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL,
+			CLK_ENABLE | CLKDIV_256 | SRSPTO_256 |
+			SRBSYTO_29 | SRWDTO_29 | SCCSTO_29);
+
+	/* CMD0 */
+	sh_mmcif_boot_cmd(base, 0x00000040, 0);
+
+	/* CMD1 - Get OCR */
+	do {
+		sh_mmcif_boot_cmd(base, 0x01405040, 0x40300000); /* CMD1 */
+	} while ((sh_mmcif_readl(base, MMCIF_CE_RESP0) & 0x80000000)
+		 != 0x80000000);
+
+	/* CMD2 - Get CID */
+	sh_mmcif_boot_cmd(base, 0x02806040, 0);
+
+	/* CMD3 - Set card relative address */
+	sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000);
+}
+
+#endif /* LINUX_MMC_SH_MMCIF_H */
-- 
cgit v1.2.3


From 8e274732115f63c1d09136284431b3555bd5cc56 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Mon, 25 Apr 2022 23:04:28 +0206
Subject: printk: extend console_lock for per-console locking

Currently threaded console printers synchronize against each
other using console_lock(). However, different console drivers
are unrelated and do not require any synchronization between
each other. Removing the synchronization between the threaded
console printers will allow each console to print at its own
speed.

But the threaded consoles printers do still need to synchronize
against console_lock() callers. Introduce a per-console mutex
and a new console boolean field @blocked to provide this
synchronization.

console_lock() is modified so that it must acquire the mutex
of each console in order to set the @blocked field. Console
printing threads will acquire their mutex while printing a
record. If @blocked was set, the thread will go back to sleep
instead of printing.

The reason for the @blocked boolean field is so that
console_lock() callers do not need to acquire multiple console
mutexes simultaneously, which would introduce unnecessary
complexity due to nested mutex locking. Also, a new field
was chosen instead of adding a new @flags value so that the
blocked status could be checked without concern of reading
inconsistent values due to @flags updates from other contexts.

Threaded console printers also need to synchronize against
console_trylock() callers. Since console_trylock() may be
called from any context, the per-console mutex cannot be used
for this synchronization. (mutex_trylock() cannot be called
from atomic contexts.) Introduce a global atomic counter to
identify if any threaded printers are active. The threaded
printers will also check the atomic counter to identify if the
console has been locked by another task via console_trylock().

Note that @console_sem is still used to provide synchronization
between console_lock() and console_trylock() callers.

A locking overview for console_lock(), console_trylock(), and the
threaded printers is as follows (pseudo code):

console_lock()
{
        down(&console_sem);
        for_each_console(con) {
                mutex_lock(&con->lock);
                con->blocked = true;
                mutex_unlock(&con->lock);
        }
        /* console_lock acquired */
}

console_trylock()
{
        if (down_trylock(&console_sem) == 0) {
                if (atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0) {
                        /* console_lock acquired */
                }
        }
}

threaded_printer()
{
        mutex_lock(&con->lock);
        if (!con->blocked) {
		/* console_lock() callers blocked */

                if (atomic_inc_unless_negative(&console_kthreads_active)) {
                        /* console_trylock() callers blocked */

                        con->write();

                        atomic_dec(&console_lock_count);
                }
        }
        mutex_unlock(&con->lock);
}

The console owner and waiter logic now only applies between contexts
that have taken the console_lock via console_trylock(). Threaded
printers never take the console_lock, so they do not have a
console_lock to handover. Tasks that have used console_lock() will
block the threaded printers using a mutex and if the console_lock
is handed over to an atomic context, it would be unable to unblock
the threaded printers. However, the console_trylock() case is
really the only scenario that is interesting for handovers anyway.

@panic_console_dropped must change to atomic_t since it is no longer
protected exclusively by the console_lock.

Since threaded printers remain asleep if they see that the console
is locked, they now must be explicitly woken in __console_unlock().
This means wake_up_klogd() calls following a console_unlock() are
no longer necessary and are removed.

Also note that threaded printers no longer need to check
@console_suspended. The check for the @blocked field implicitly
covers the suspended console case.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/878rrs6ft7.fsf@jogness.linutronix.de
---
 include/linux/console.h |  15 +++
 kernel/printk/printk.c  | 261 +++++++++++++++++++++++++++++++++++++-----------
 2 files changed, 220 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/console.h b/include/linux/console.h
index 9a251e70c090..143653090c48 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -16,6 +16,7 @@
 
 #include <linux/atomic.h>
 #include <linux/types.h>
+#include <linux/mutex.h>
 
 struct vc_data;
 struct console_font_op;
@@ -154,6 +155,20 @@ struct console {
 	u64	seq;
 	unsigned long dropped;
 	struct task_struct *thread;
+	bool	blocked;
+
+	/*
+	 * The per-console lock is used by printing kthreads to synchronize
+	 * this console with callers of console_lock(). This is necessary in
+	 * order to allow printing kthreads to run in parallel to each other,
+	 * while each safely accessing the @blocked field and synchronizing
+	 * against direct printing via console_lock/console_unlock.
+	 *
+	 * Note: For synchronizing against direct printing via
+	 *       console_trylock/console_unlock, see the static global
+	 *       variable @console_kthreads_active.
+	 */
+	struct mutex lock;
 
 	void	*data;
 	struct	 console *next;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index e4cdc424c826..750d1229cc11 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -223,6 +223,33 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
 /* Number of registered extended console drivers. */
 static int nr_ext_console_drivers;
 
+/*
+ * Used to synchronize printing kthreads against direct printing via
+ * console_trylock/console_unlock.
+ *
+ * Values:
+ * -1 = console kthreads atomically blocked (via global trylock)
+ *  0 = no kthread printing, console not locked (via trylock)
+ * >0 = kthread(s) actively printing
+ *
+ * Note: For synchronizing against direct printing via
+ *       console_lock/console_unlock, see the @lock variable in
+ *       struct console.
+ */
+static atomic_t console_kthreads_active = ATOMIC_INIT(0);
+
+#define console_kthreads_atomic_tryblock() \
+	(atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0)
+#define console_kthreads_atomic_unblock() \
+	atomic_cmpxchg(&console_kthreads_active, -1, 0)
+#define console_kthreads_atomically_blocked() \
+	(atomic_read(&console_kthreads_active) == -1)
+
+#define console_kthread_printing_tryenter() \
+	atomic_inc_unless_negative(&console_kthreads_active)
+#define console_kthread_printing_exit() \
+	atomic_dec(&console_kthreads_active)
+
 /*
  * Helper macros to handle lockdep when locking/unlocking console_sem. We use
  * macros instead of functions so that _RET_IP_ contains useful information.
@@ -270,6 +297,49 @@ static bool panic_in_progress(void)
 	return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID);
 }
 
+/*
+ * Tracks whether kthread printers are all blocked. A value of true implies
+ * that the console is locked via console_lock() or the console is suspended.
+ * Writing to this variable requires holding @console_sem.
+ */
+static bool console_kthreads_blocked;
+
+/*
+ * Block all kthread printers from a schedulable context.
+ *
+ * Requires holding @console_sem.
+ */
+static void console_kthreads_block(void)
+{
+	struct console *con;
+
+	for_each_console(con) {
+		mutex_lock(&con->lock);
+		con->blocked = true;
+		mutex_unlock(&con->lock);
+	}
+
+	console_kthreads_blocked = true;
+}
+
+/*
+ * Unblock all kthread printers from a schedulable context.
+ *
+ * Requires holding @console_sem.
+ */
+static void console_kthreads_unblock(void)
+{
+	struct console *con;
+
+	for_each_console(con) {
+		mutex_lock(&con->lock);
+		con->blocked = false;
+		mutex_unlock(&con->lock);
+	}
+
+	console_kthreads_blocked = false;
+}
+
 /*
  * This is used for debugging the mess that is the VT code by
  * keeping track if we have the console semaphore held. It's
@@ -2603,13 +2673,6 @@ void resume_console(void)
 	down_console_sem();
 	console_suspended = 0;
 	console_unlock();
-
-	/*
-	 * While suspended, new records may have been added to the
-	 * ringbuffer. Wake up the kthread printers to print them.
-	 */
-	wake_up_klogd();
-
 	pr_flush(1000, true);
 }
 
@@ -2628,9 +2691,14 @@ static int console_cpu_notify(unsigned int cpu)
 		/* If trylock fails, someone else is doing the printing */
 		if (console_trylock())
 			console_unlock();
-
-		/* Wake kthread printers. Some may have become usable. */
-		wake_up_klogd();
+		else {
+			/*
+			 * If a new CPU comes online, the conditions for
+			 * printer_should_wake() may have changed for some
+			 * kthread printer with !CON_ANYTIME.
+			 */
+			wake_up_klogd();
+		}
 	}
 	return 0;
 }
@@ -2650,6 +2718,7 @@ void console_lock(void)
 	down_console_sem();
 	if (console_suspended)
 		return;
+	console_kthreads_block();
 	console_locked = 1;
 	console_may_schedule = 1;
 }
@@ -2671,6 +2740,10 @@ int console_trylock(void)
 		up_console_sem();
 		return 0;
 	}
+	if (!console_kthreads_atomic_tryblock()) {
+		up_console_sem();
+		return 0;
+	}
 	console_locked = 1;
 	console_may_schedule = 0;
 	return 1;
@@ -2679,7 +2752,7 @@ EXPORT_SYMBOL(console_trylock);
 
 int is_console_locked(void)
 {
-	return console_locked;
+	return (console_locked || atomic_read(&console_kthreads_active));
 }
 EXPORT_SYMBOL(is_console_locked);
 
@@ -2723,7 +2796,7 @@ static inline bool __console_is_usable(short flags)
  * Check if the given console is currently capable and allowed to print
  * records.
  *
- * Requires the console_lock.
+ * Requires holding the console_lock.
  */
 static inline bool console_is_usable(struct console *con)
 {
@@ -2736,6 +2809,22 @@ static inline bool console_is_usable(struct console *con)
 static void __console_unlock(void)
 {
 	console_locked = 0;
+
+	/*
+	 * Depending on whether console_lock() or console_trylock() was used,
+	 * appropriately allow the kthread printers to continue.
+	 */
+	if (console_kthreads_blocked)
+		console_kthreads_unblock();
+	else
+		console_kthreads_atomic_unblock();
+
+	/*
+	 * New records may have arrived while the console was locked.
+	 * Wake the kthread printers to print them.
+	 */
+	wake_up_klogd();
+
 	up_console_sem();
 }
 
@@ -2753,17 +2842,19 @@ static void __console_unlock(void)
  *
  * @handover will be set to true if a printk waiter has taken over the
  * console_lock, in which case the caller is no longer holding the
- * console_lock. Otherwise it is set to false.
+ * console_lock. Otherwise it is set to false. A NULL pointer may be provided
+ * to disable allowing the console_lock to be taken over by a printk waiter.
  *
  * Returns false if the given console has no next record to print, otherwise
  * true.
  *
- * Requires the console_lock.
+ * Requires the console_lock if @handover is non-NULL.
+ * Requires con->lock otherwise.
  */
-static bool console_emit_next_record(struct console *con, char *text, char *ext_text,
-				     char *dropped_text, bool *handover)
+static bool __console_emit_next_record(struct console *con, char *text, char *ext_text,
+				       char *dropped_text, bool *handover)
 {
-	static int panic_console_dropped;
+	static atomic_t panic_console_dropped = ATOMIC_INIT(0);
 	struct printk_info info;
 	struct printk_record r;
 	unsigned long flags;
@@ -2772,7 +2863,8 @@ static bool console_emit_next_record(struct console *con, char *text, char *ext_
 
 	prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);
 
-	*handover = false;
+	if (handover)
+		*handover = false;
 
 	if (!prb_read_valid(prb, con->seq, &r))
 		return false;
@@ -2780,7 +2872,8 @@ static bool console_emit_next_record(struct console *con, char *text, char *ext_
 	if (con->seq != r.info->seq) {
 		con->dropped += r.info->seq - con->seq;
 		con->seq = r.info->seq;
-		if (panic_in_progress() && panic_console_dropped++ > 10) {
+		if (panic_in_progress() &&
+		    atomic_fetch_inc_relaxed(&panic_console_dropped) > 10) {
 			suppress_panic_printk = 1;
 			pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n");
 		}
@@ -2802,31 +2895,61 @@ static bool console_emit_next_record(struct console *con, char *text, char *ext_
 		len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time);
 	}
 
-	/*
-	 * While actively printing out messages, if another printk()
-	 * were to occur on another CPU, it may wait for this one to
-	 * finish. This task can not be preempted if there is a
-	 * waiter waiting to take over.
-	 *
-	 * Interrupts are disabled because the hand over to a waiter
-	 * must not be interrupted until the hand over is completed
-	 * (@console_waiter is cleared).
-	 */
-	printk_safe_enter_irqsave(flags);
-	console_lock_spinning_enable();
+	if (handover) {
+		/*
+		 * While actively printing out messages, if another printk()
+		 * were to occur on another CPU, it may wait for this one to
+		 * finish. This task can not be preempted if there is a
+		 * waiter waiting to take over.
+		 *
+		 * Interrupts are disabled because the hand over to a waiter
+		 * must not be interrupted until the hand over is completed
+		 * (@console_waiter is cleared).
+		 */
+		printk_safe_enter_irqsave(flags);
+		console_lock_spinning_enable();
+
+		/* don't trace irqsoff print latency */
+		stop_critical_timings();
+	}
 
-	stop_critical_timings();	/* don't trace print latency */
 	call_console_driver(con, write_text, len, dropped_text);
-	start_critical_timings();
 
 	con->seq++;
 
-	*handover = console_lock_spinning_disable_and_check();
-	printk_safe_exit_irqrestore(flags);
+	if (handover) {
+		start_critical_timings();
+		*handover = console_lock_spinning_disable_and_check();
+		printk_safe_exit_irqrestore(flags);
+	}
 skip:
 	return true;
 }
 
+/*
+ * Print a record for a given console, but allow another printk() caller to
+ * take over the console_lock and continue printing.
+ *
+ * Requires the console_lock, but depending on @handover after the call, the
+ * caller may no longer have the console_lock.
+ *
+ * See __console_emit_next_record() for argument and return details.
+ */
+static bool console_emit_next_record_transferable(struct console *con, char *text, char *ext_text,
+						  char *dropped_text, bool *handover)
+{
+	/*
+	 * Handovers are only supported if threaded printers are atomically
+	 * blocked. The context taking over the console_lock may be atomic.
+	 */
+	if (!console_kthreads_atomically_blocked()) {
+		*handover = false;
+		handover = NULL;
+	}
+
+	return __console_emit_next_record(con, text, ext_text, dropped_text, handover);
+}
+
 /*
  * Print out all remaining records to all consoles.
  *
@@ -2878,13 +3001,11 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove
 
 			if (con->flags & CON_EXTENDED) {
 				/* Extended consoles do not print "dropped messages". */
-				progress = console_emit_next_record(con, &text[0],
-								    &ext_text[0], NULL,
-								    handover);
+				progress = console_emit_next_record_transferable(con, &text[0],
+								&ext_text[0], NULL, handover);
 			} else {
-				progress = console_emit_next_record(con, &text[0],
-								    NULL, &dropped_text[0],
-								    handover);
+				progress = console_emit_next_record_transferable(con, &text[0],
+								NULL, &dropped_text[0], handover);
 			}
 			if (*handover)
 				return false;
@@ -2999,6 +3120,10 @@ void console_unblank(void)
 	if (oops_in_progress) {
 		if (down_trylock_console_sem() != 0)
 			return;
+		if (!console_kthreads_atomic_tryblock()) {
+			up_console_sem();
+			return;
+		}
 	} else
 		console_lock();
 
@@ -3081,10 +3206,6 @@ void console_start(struct console *console)
 	console_lock();
 	console->flags |= CON_ENABLED;
 	console_unlock();
-
-	/* Wake the newly enabled kthread printer. */
-	wake_up_klogd();
-
 	__pr_flush(console, 1000, true);
 }
 EXPORT_SYMBOL(console_start);
@@ -3286,6 +3407,8 @@ void register_console(struct console *newcon)
 
 	newcon->dropped = 0;
 	newcon->thread = NULL;
+	newcon->blocked = true;
+	mutex_init(&newcon->lock);
 
 	if (newcon->flags & CON_PRINTBUFFER) {
 		/* Get a consistent copy of @syslog_seq. */
@@ -3586,6 +3709,19 @@ static void printk_fallback_preferred_direct(void)
 	console_unlock();
 }
 
+/*
+ * Print a record for a given console, not allowing another printk() caller
+ * to take over. This is appropriate for contexts that do not have the
+ * console_lock.
+ *
+ * See __console_emit_next_record() for argument and return details.
+ */
+static bool console_emit_next_record(struct console *con, char *text, char *ext_text,
+				     char *dropped_text)
+{
+	return __console_emit_next_record(con, text, ext_text, dropped_text, NULL);
+}
+
 static bool printer_should_wake(struct console *con, u64 seq)
 {
 	short flags;
@@ -3593,8 +3729,10 @@ static bool printer_should_wake(struct console *con, u64 seq)
 	if (kthread_should_stop() || !printk_kthreads_available)
 		return true;
 
-	if (console_suspended)
+	if (con->blocked ||
+	    console_kthreads_atomically_blocked()) {
 		return false;
+	}
 
 	/*
 	 * This is an unsafe read from con->flags, but a false positive is
@@ -3615,7 +3753,6 @@ static int printk_kthread_func(void *data)
 	struct console *con = data;
 	char *dropped_text = NULL;
 	char *ext_text = NULL;
-	bool handover;
 	u64 seq = 0;
 	char *text;
 	int error;
@@ -3665,15 +3802,27 @@ static int printk_kthread_func(void *data)
 		if (error)
 			continue;
 
-		console_lock();
+		error = mutex_lock_interruptible(&con->lock);
+		if (error)
+			continue;
 
-		if (console_suspended) {
-			up_console_sem();
+		if (con->blocked ||
+		    !console_kthread_printing_tryenter()) {
+			/* Another context has locked the console_lock. */
+			mutex_unlock(&con->lock);
 			continue;
 		}
 
-		if (!console_is_usable(con)) {
-			__console_unlock();
+		/*
+		 * Although this context has not locked the console_lock, it
+		 * is known that the console_lock is not locked and it is not
+		 * possible for any other context to lock the console_lock.
+		 * Therefore it is safe to read con->flags.
+		 */
+
+		if (!__console_is_usable(con->flags)) {
+			console_kthread_printing_exit();
+			mutex_unlock(&con->lock);
 			continue;
 		}
 
@@ -3686,13 +3835,13 @@ static int printk_kthread_func(void *data)
 		 * which can conditionally invoke cond_resched().
 		 */
 		console_may_schedule = 0;
-		console_emit_next_record(con, text, ext_text, dropped_text, &handover);
-		if (handover)
-			continue;
+		console_emit_next_record(con, text, ext_text, dropped_text);
 
 		seq = con->seq;
 
-		__console_unlock();
+		console_kthread_printing_exit();
+
+		mutex_unlock(&con->lock);
 	}
 
 	con_printk(KERN_INFO, con, "printing thread stopped\n");
-- 
cgit v1.2.3


From 33337d03f04f9ea3a50ac2d3490a5d7a3ba9be82 Mon Sep 17 00:00:00 2001
From: Dylan Yudaken <dylany@fb.com>
Date: Tue, 26 Apr 2022 01:29:05 -0700
Subject: io_uring: add io_uring_get_opcode

In some debug scenarios it is useful to have the text representation of
the opcode. Add this function in preparation.

Signed-off-by: Dylan Yudaken <dylany@fb.com>
Link: https://lore.kernel.org/r/20220426082907.3600028-3-dylany@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 101 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/io_uring.h |   5 +++
 2 files changed, 106 insertions(+)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index bf95ef9240e5..dfebbf3a272a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1285,6 +1285,107 @@ static struct kmem_cache *req_cachep;
 
 static const struct file_operations io_uring_fops;
 
+const char *io_uring_get_opcode(u8 opcode)
+{
+	switch ((enum io_uring_op)opcode) {
+	case IORING_OP_NOP:
+		return "NOP";
+	case IORING_OP_READV:
+		return "READV";
+	case IORING_OP_WRITEV:
+		return "WRITEV";
+	case IORING_OP_FSYNC:
+		return "FSYNC";
+	case IORING_OP_READ_FIXED:
+		return "READ_FIXED";
+	case IORING_OP_WRITE_FIXED:
+		return "WRITE_FIXED";
+	case IORING_OP_POLL_ADD:
+		return "POLL_ADD";
+	case IORING_OP_POLL_REMOVE:
+		return "POLL_REMOVE";
+	case IORING_OP_SYNC_FILE_RANGE:
+		return "SYNC_FILE_RANGE";
+	case IORING_OP_SENDMSG:
+		return "SENDMSG";
+	case IORING_OP_RECVMSG:
+		return "RECVMSG";
+	case IORING_OP_TIMEOUT:
+		return "TIMEOUT";
+	case IORING_OP_TIMEOUT_REMOVE:
+		return "TIMEOUT_REMOVE";
+	case IORING_OP_ACCEPT:
+		return "ACCEPT";
+	case IORING_OP_ASYNC_CANCEL:
+		return "ASYNC_CANCEL";
+	case IORING_OP_LINK_TIMEOUT:
+		return "LINK_TIMEOUT";
+	case IORING_OP_CONNECT:
+		return "CONNECT";
+	case IORING_OP_FALLOCATE:
+		return "FALLOCATE";
+	case IORING_OP_OPENAT:
+		return "OPENAT";
+	case IORING_OP_CLOSE:
+		return "CLOSE";
+	case IORING_OP_FILES_UPDATE:
+		return "FILES_UPDATE";
+	case IORING_OP_STATX:
+		return "STATX";
+	case IORING_OP_READ:
+		return "READ";
+	case IORING_OP_WRITE:
+		return "WRITE";
+	case IORING_OP_FADVISE:
+		return "FADVISE";
+	case IORING_OP_MADVISE:
+		return "MADVISE";
+	case IORING_OP_SEND:
+		return "SEND";
+	case IORING_OP_RECV:
+		return "RECV";
+	case IORING_OP_OPENAT2:
+		return "OPENAT2";
+	case IORING_OP_EPOLL_CTL:
+		return "EPOLL_CTL";
+	case IORING_OP_SPLICE:
+		return "SPLICE";
+	case IORING_OP_PROVIDE_BUFFERS:
+		return "PROVIDE_BUFFERS";
+	case IORING_OP_REMOVE_BUFFERS:
+		return "REMOVE_BUFFERS";
+	case IORING_OP_TEE:
+		return "TEE";
+	case IORING_OP_SHUTDOWN:
+		return "SHUTDOWN";
+	case IORING_OP_RENAMEAT:
+		return "RENAMEAT";
+	case IORING_OP_UNLINKAT:
+		return "UNLINKAT";
+	case IORING_OP_MKDIRAT:
+		return "MKDIRAT";
+	case IORING_OP_SYMLINKAT:
+		return "SYMLINKAT";
+	case IORING_OP_LINKAT:
+		return "LINKAT";
+	case IORING_OP_MSG_RING:
+		return "MSG_RING";
+	case IORING_OP_FSETXATTR:
+		return "FSETXATTR";
+	case IORING_OP_SETXATTR:
+		return "SETXATTR";
+	case IORING_OP_FGETXATTR:
+		return "FGETXATTR";
+	case IORING_OP_GETXATTR:
+		return "GETXATTR";
+	case IORING_OP_SOCKET:
+		return "SOCKET";
+	case IORING_OP_LAST:
+		return "INVALID";
+	}
+	return "INVALID";
+}
+
 struct sock *io_uring_get_socket(struct file *file)
 {
 #if defined(CONFIG_UNIX)
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 1814e698d861..24651c229ed2 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -10,6 +10,7 @@ struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 void io_uring_unreg_ringfd(void);
+const char *io_uring_get_opcode(u8 opcode);
 
 static inline void io_uring_files_cancel(void)
 {
@@ -42,6 +43,10 @@ static inline void io_uring_files_cancel(void)
 static inline void io_uring_free(struct task_struct *tsk)
 {
 }
+static inline const char *io_uring_get_opcode(u8 opcode)
+{
+	return "";
+}
 #endif
 
 #endif
-- 
cgit v1.2.3


From 54c861f930180e096483a6e1744c9c4b76e20da5 Mon Sep 17 00:00:00 2001
From: Daniel Ammann <daniel.ammann@bytesatwork.ch>
Date: Tue, 5 Apr 2022 14:54:25 +0200
Subject: mfd: tps65218: Fix trivial typo in comment

The driver is for TPS65218, not TPS65219.

Signed-off-by: Daniel Ammann <daniel.ammann@bytesatwork.ch>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Link: https://lore.kernel.org/r/20220405125426.28016-1-daniel.ammann@bytesatwork.ch
---
 include/linux/mfd/tps65218.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h
index f4ca367e3473..122e24ddbd4b 100644
--- a/include/linux/mfd/tps65218.h
+++ b/include/linux/mfd/tps65218.h
@@ -1,7 +1,7 @@
 /*
  * linux/mfd/tps65218.h
  *
- * Functions to access TPS65219 power management chip.
+ * Functions to access TPS65218 power management chip.
  *
  * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com/
  *
-- 
cgit v1.2.3


From 7f5aaa4a0ae6948eace6cf30f40a3ec27ece8441 Mon Sep 17 00:00:00 2001
From: Maíra Canal <maira.canal@usp.br>
Date: Wed, 6 Apr 2022 11:40:41 -0300
Subject: mfd: hi655x-pmic: Replace legacy gpio interface for gpiod interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Considering the current transition of the GPIO subsystem, remove all
dependencies of the legacy GPIO interface (linux/gpio.h and linux
/of_gpio.h) and replace it with the descriptor-based GPIO approach.

Signed-off-by: Maíra Canal <maira.canal@usp.br>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Link: https://lore.kernel.org/r/Yk2maZuf+5FGL+eg@fedora
---
 drivers/mfd/hi655x-pmic.c       | 27 ++++++++-------------------
 include/linux/mfd/hi655x-pmic.h |  4 +++-
 2 files changed, 11 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/hi655x-pmic.c b/drivers/mfd/hi655x-pmic.c
index 6909d075d017..a58e42ddcd0c 100644
--- a/drivers/mfd/hi655x-pmic.c
+++ b/drivers/mfd/hi655x-pmic.c
@@ -9,14 +9,13 @@
  * Fei  Wang <w.f@huawei.com>
  */
 
-#include <linux/gpio.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/hi655x-pmic.h>
 #include <linux/module.h>
-#include <linux/of_gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
@@ -94,7 +93,6 @@ static int hi655x_pmic_probe(struct platform_device *pdev)
 	int ret;
 	struct hi655x_pmic *pmic;
 	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
 	void __iomem *base;
 
 	pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
@@ -120,21 +118,12 @@ static int hi655x_pmic_probe(struct platform_device *pdev)
 
 	hi655x_local_irq_clear(pmic->regmap);
 
-	pmic->gpio = of_get_named_gpio(np, "pmic-gpios", 0);
-	if (!gpio_is_valid(pmic->gpio)) {
-		dev_err(dev, "Failed to get the pmic-gpios\n");
-		return -ENODEV;
-	}
-
-	ret = devm_gpio_request_one(dev, pmic->gpio, GPIOF_IN,
-				    "hi655x_pmic_irq");
-	if (ret < 0) {
-		dev_err(dev, "Failed to request gpio %d  ret = %d\n",
-			pmic->gpio, ret);
-		return ret;
-	}
+	pmic->gpio = devm_gpiod_get_optional(dev, "pmic", GPIOD_IN);
+	if (IS_ERR(pmic->gpio))
+		return dev_err_probe(dev, PTR_ERR(pmic->gpio),
+				"Failed to request hi655x pmic-gpio");
 
-	ret = regmap_add_irq_chip(pmic->regmap, gpio_to_irq(pmic->gpio),
+	ret = regmap_add_irq_chip(pmic->regmap, gpiod_to_irq(pmic->gpio),
 				  IRQF_TRIGGER_LOW | IRQF_NO_SUSPEND, 0,
 				  &hi655x_irq_chip, &pmic->irq_data);
 	if (ret) {
@@ -149,7 +138,7 @@ static int hi655x_pmic_probe(struct platform_device *pdev)
 			      regmap_irq_get_domain(pmic->irq_data));
 	if (ret) {
 		dev_err(dev, "Failed to register device %d\n", ret);
-		regmap_del_irq_chip(gpio_to_irq(pmic->gpio), pmic->irq_data);
+		regmap_del_irq_chip(gpiod_to_irq(pmic->gpio), pmic->irq_data);
 		return ret;
 	}
 
@@ -160,7 +149,7 @@ static int hi655x_pmic_remove(struct platform_device *pdev)
 {
 	struct hi655x_pmic *pmic = platform_get_drvdata(pdev);
 
-	regmap_del_irq_chip(gpio_to_irq(pmic->gpio), pmic->irq_data);
+	regmap_del_irq_chip(gpiod_to_irq(pmic->gpio), pmic->irq_data);
 	mfd_remove_devices(&pdev->dev);
 	return 0;
 }
diff --git a/include/linux/mfd/hi655x-pmic.h b/include/linux/mfd/hi655x-pmic.h
index af5d97239c0d..6a012784dd1b 100644
--- a/include/linux/mfd/hi655x-pmic.h
+++ b/include/linux/mfd/hi655x-pmic.h
@@ -12,6 +12,8 @@
 #ifndef __HI655X_PMIC_H
 #define __HI655X_PMIC_H
 
+#include <linux/gpio/consumer.h>
+
 /* Hi655x registers are mapped to memory bus in 4 bytes stride */
 #define HI655X_STRIDE                   4
 #define HI655X_BUS_ADDR(x)              ((x) << 2)
@@ -53,7 +55,7 @@ struct hi655x_pmic {
 	struct resource *res;
 	struct device *dev;
 	struct regmap *regmap;
-	int gpio;
+	struct gpio_desc *gpio;
 	unsigned int ver;
 	struct regmap_irq_chip_data *irq_data;
 };
-- 
cgit v1.2.3


From 82028ba4d590c4e9eb3c93326019db7c26d02e35 Mon Sep 17 00:00:00 2001
From: Fabien Parent <fparent@baylibre.com>
Date: Fri, 15 Apr 2022 17:36:24 +0200
Subject: mfd: mt6359: Add missing defines necessary for mtk-pmic-keys support

Add 2 missing MT6359 registers that are needed to implement
the keyboard driver.

Signed-off-by: Fabien Parent <fparent@baylibre.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Link: https://lore.kernel.org/r/20220415153629.1817202-3-fparent@baylibre.com
---
 include/linux/mfd/mt6359/registers.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mfd/mt6359/registers.h b/include/linux/mfd/mt6359/registers.h
index 2135c9695918..2a4394a27b1c 100644
--- a/include/linux/mfd/mt6359/registers.h
+++ b/include/linux/mfd/mt6359/registers.h
@@ -8,6 +8,8 @@
 
 /* PMIC Registers */
 #define MT6359_SWCID                         0xa
+#define MT6359_TOPSTATUS                     0x2a
+#define MT6359_TOP_RST_MISC                  0x14c
 #define MT6359_MISC_TOP_INT_CON0             0x188
 #define MT6359_MISC_TOP_INT_STATUS0          0x194
 #define MT6359_TOP_INT_STATUS0               0x19e
-- 
cgit v1.2.3


From c317ab71facc2cd0a94145973318a4c914e11acc Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Mon, 25 Apr 2022 21:32:47 +0800
Subject: bpf: Compute map_btf_id during build time

For now, the field 'map_btf_id' in 'struct bpf_map_ops' for all map
types are computed during vmlinux-btf init:

  btf_parse_vmlinux() -> btf_vmlinux_map_ids_init()

It will lookup the btf_type according to the 'map_btf_name' field in
'struct bpf_map_ops'. This process can be done during build time,
thanks to Jiri's resolve_btfids.

selftest of map_ptr has passed:

  $96 map_ptr:OK
  Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            |  3 +--
 kernel/bpf/arraymap.c          | 26 ++++++++------------------
 kernel/bpf/bloom_filter.c      |  6 +++---
 kernel/bpf/bpf_inode_storage.c |  6 +++---
 kernel/bpf/bpf_struct_ops.c    |  6 +++---
 kernel/bpf/bpf_task_storage.c  |  5 ++---
 kernel/bpf/btf.c               | 40 ----------------------------------------
 kernel/bpf/cpumap.c            |  6 +++---
 kernel/bpf/devmap.c            | 10 ++++------
 kernel/bpf/hashtab.c           | 22 +++++++---------------
 kernel/bpf/local_storage.c     |  7 ++++---
 kernel/bpf/lpm_trie.c          |  6 +++---
 kernel/bpf/queue_stack_maps.c  | 10 ++++------
 kernel/bpf/reuseport_array.c   |  6 +++---
 kernel/bpf/ringbuf.c           |  6 +++---
 kernel/bpf/stackmap.c          |  5 ++---
 net/core/bpf_sk_storage.c      |  5 ++---
 net/core/sock_map.c            | 10 ++++------
 net/xdp/xskmap.c               |  6 +++---
 19 files changed, 62 insertions(+), 129 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0af5793ba417..be94833d390a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -148,8 +148,7 @@ struct bpf_map_ops {
 				     bpf_callback_t callback_fn,
 				     void *callback_ctx, u64 flags);
 
-	/* BTF name and id of struct allocated by map_alloc */
-	const char * const map_btf_name;
+	/* BTF id of struct allocated by map_alloc */
 	int *map_btf_id;
 
 	/* bpf_iter info used to open a seq_file */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index c3de63ce574e..b3bf31fd9458 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -11,6 +11,7 @@
 #include <linux/perf_event.h>
 #include <uapi/linux/btf.h>
 #include <linux/rcupdate_trace.h>
+#include <linux/btf_ids.h>
 
 #include "map_in_map.h"
 
@@ -690,7 +691,7 @@ static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_
 	return num_elems;
 }
 
-static int array_map_btf_id;
+BTF_ID_LIST_SINGLE(array_map_btf_ids, struct, bpf_array)
 const struct bpf_map_ops array_map_ops = {
 	.map_meta_equal = array_map_meta_equal,
 	.map_alloc_check = array_map_alloc_check,
@@ -711,12 +712,10 @@ const struct bpf_map_ops array_map_ops = {
 	.map_update_batch = generic_map_update_batch,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_array_elem,
-	.map_btf_name = "bpf_array",
-	.map_btf_id = &array_map_btf_id,
+	.map_btf_id = &array_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
-static int percpu_array_map_btf_id;
 const struct bpf_map_ops percpu_array_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = array_map_alloc_check,
@@ -732,8 +731,7 @@ const struct bpf_map_ops percpu_array_map_ops = {
 	.map_update_batch = generic_map_update_batch,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_array_elem,
-	.map_btf_name = "bpf_array",
-	.map_btf_id = &percpu_array_map_btf_id,
+	.map_btf_id = &array_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
@@ -1112,7 +1110,6 @@ static void prog_array_map_free(struct bpf_map *map)
  * Thus, prog_array_map cannot be used as an inner_map
  * and map_meta_equal is not implemented.
  */
-static int prog_array_map_btf_id;
 const struct bpf_map_ops prog_array_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = prog_array_map_alloc,
@@ -1128,8 +1125,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
 	.map_release_uref = prog_array_map_clear,
 	.map_seq_show_elem = prog_array_map_seq_show_elem,
-	.map_btf_name = "bpf_array",
-	.map_btf_id = &prog_array_map_btf_id,
+	.map_btf_id = &array_map_btf_ids[0],
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
@@ -1218,7 +1214,6 @@ static void perf_event_fd_array_map_free(struct bpf_map *map)
 	fd_array_map_free(map);
 }
 
-static int perf_event_array_map_btf_id;
 const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = fd_array_map_alloc_check,
@@ -1231,8 +1226,7 @@ const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
 	.map_release = perf_event_fd_array_release,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_array",
-	.map_btf_id = &perf_event_array_map_btf_id,
+	.map_btf_id = &array_map_btf_ids[0],
 };
 
 #ifdef CONFIG_CGROUPS
@@ -1255,7 +1249,6 @@ static void cgroup_fd_array_free(struct bpf_map *map)
 	fd_array_map_free(map);
 }
 
-static int cgroup_array_map_btf_id;
 const struct bpf_map_ops cgroup_array_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = fd_array_map_alloc_check,
@@ -1267,8 +1260,7 @@ const struct bpf_map_ops cgroup_array_map_ops = {
 	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
 	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_array",
-	.map_btf_id = &cgroup_array_map_btf_id,
+	.map_btf_id = &array_map_btf_ids[0],
 };
 #endif
 
@@ -1342,7 +1334,6 @@ static int array_of_map_gen_lookup(struct bpf_map *map,
 	return insn - insn_buf;
 }
 
-static int array_of_maps_map_btf_id;
 const struct bpf_map_ops array_of_maps_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_of_map_alloc,
@@ -1355,6 +1346,5 @@ const struct bpf_map_ops array_of_maps_map_ops = {
 	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
 	.map_gen_lookup = array_of_map_gen_lookup,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_array",
-	.map_btf_id = &array_of_maps_map_btf_id,
+	.map_btf_id = &array_map_btf_ids[0],
 };
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
index b141a1346f72..b9ea539a5561 100644
--- a/kernel/bpf/bloom_filter.c
+++ b/kernel/bpf/bloom_filter.c
@@ -7,6 +7,7 @@
 #include <linux/err.h>
 #include <linux/jhash.h>
 #include <linux/random.h>
+#include <linux/btf_ids.h>
 
 #define BLOOM_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK)
@@ -192,7 +193,7 @@ static int bloom_map_check_btf(const struct bpf_map *map,
 	return btf_type_is_void(key_type) ? 0 : -EINVAL;
 }
 
-static int bpf_bloom_map_btf_id;
+BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter)
 const struct bpf_map_ops bloom_filter_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = bloom_map_alloc,
@@ -205,6 +206,5 @@ const struct bpf_map_ops bloom_filter_map_ops = {
 	.map_update_elem = bloom_map_update_elem,
 	.map_delete_elem = bloom_map_delete_elem,
 	.map_check_btf = bloom_map_check_btf,
-	.map_btf_name = "bpf_bloom_filter",
-	.map_btf_id = &bpf_bloom_map_btf_id,
+	.map_btf_id = &bpf_bloom_map_btf_ids[0],
 };
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 10424a1cda51..5f7683b19199 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -245,7 +245,8 @@ static void inode_storage_map_free(struct bpf_map *map)
 	bpf_local_storage_map_free(smap, NULL);
 }
 
-static int inode_storage_map_btf_id;
+BTF_ID_LIST_SINGLE(inode_storage_map_btf_ids, struct,
+		   bpf_local_storage_map)
 const struct bpf_map_ops inode_storage_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = bpf_local_storage_map_alloc_check,
@@ -256,8 +257,7 @@ const struct bpf_map_ops inode_storage_map_ops = {
 	.map_update_elem = bpf_fd_inode_storage_update_elem,
 	.map_delete_elem = bpf_fd_inode_storage_delete_elem,
 	.map_check_btf = bpf_local_storage_map_check_btf,
-	.map_btf_name = "bpf_local_storage_map",
-	.map_btf_id = &inode_storage_map_btf_id,
+	.map_btf_id = &inode_storage_map_btf_ids[0],
 	.map_owner_storage_ptr = inode_storage_ptr,
 };
 
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index de01d37c2d3b..3a0103ad97bc 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -10,6 +10,7 @@
 #include <linux/seq_file.h>
 #include <linux/refcount.h>
 #include <linux/mutex.h>
+#include <linux/btf_ids.h>
 
 enum bpf_struct_ops_state {
 	BPF_STRUCT_OPS_STATE_INIT,
@@ -612,7 +613,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	return map;
 }
 
-static int bpf_struct_ops_map_btf_id;
+BTF_ID_LIST_SINGLE(bpf_struct_ops_map_btf_ids, struct, bpf_struct_ops_map)
 const struct bpf_map_ops bpf_struct_ops_map_ops = {
 	.map_alloc_check = bpf_struct_ops_map_alloc_check,
 	.map_alloc = bpf_struct_ops_map_alloc,
@@ -622,8 +623,7 @@ const struct bpf_map_ops bpf_struct_ops_map_ops = {
 	.map_delete_elem = bpf_struct_ops_map_delete_elem,
 	.map_update_elem = bpf_struct_ops_map_update_elem,
 	.map_seq_show_elem = bpf_struct_ops_map_seq_show_elem,
-	.map_btf_name = "bpf_struct_ops_map",
-	.map_btf_id = &bpf_struct_ops_map_btf_id,
+	.map_btf_id = &bpf_struct_ops_map_btf_ids[0],
 };
 
 /* "const void *" because some subsystem is
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index 57904263a710..e9014dc62682 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -307,7 +307,7 @@ static void task_storage_map_free(struct bpf_map *map)
 	bpf_local_storage_map_free(smap, &bpf_task_storage_busy);
 }
 
-static int task_storage_map_btf_id;
+BTF_ID_LIST_SINGLE(task_storage_map_btf_ids, struct, bpf_local_storage_map)
 const struct bpf_map_ops task_storage_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = bpf_local_storage_map_alloc_check,
@@ -318,8 +318,7 @@ const struct bpf_map_ops task_storage_map_ops = {
 	.map_update_elem = bpf_pid_task_storage_update_elem,
 	.map_delete_elem = bpf_pid_task_storage_delete_elem,
 	.map_check_btf = bpf_local_storage_map_check_btf,
-	.map_btf_name = "bpf_local_storage_map",
-	.map_btf_id = &task_storage_map_btf_id,
+	.map_btf_id = &task_storage_map_btf_ids[0],
 	.map_owner_storage_ptr = task_storage_ptr,
 };
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4cfaf5eebecd..2f0b0440131c 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5025,41 +5025,6 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 	return ctx_type;
 }
 
-static const struct bpf_map_ops * const btf_vmlinux_map_ops[] = {
-#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
-#define BPF_LINK_TYPE(_id, _name)
-#define BPF_MAP_TYPE(_id, _ops) \
-	[_id] = &_ops,
-#include <linux/bpf_types.h>
-#undef BPF_PROG_TYPE
-#undef BPF_LINK_TYPE
-#undef BPF_MAP_TYPE
-};
-
-static int btf_vmlinux_map_ids_init(const struct btf *btf,
-				    struct bpf_verifier_log *log)
-{
-	const struct bpf_map_ops *ops;
-	int i, btf_id;
-
-	for (i = 0; i < ARRAY_SIZE(btf_vmlinux_map_ops); ++i) {
-		ops = btf_vmlinux_map_ops[i];
-		if (!ops || (!ops->map_btf_name && !ops->map_btf_id))
-			continue;
-		if (!ops->map_btf_name || !ops->map_btf_id) {
-			bpf_log(log, "map type %d is misconfigured\n", i);
-			return -EINVAL;
-		}
-		btf_id = btf_find_by_name_kind(btf, ops->map_btf_name,
-					       BTF_KIND_STRUCT);
-		if (btf_id < 0)
-			return btf_id;
-		*ops->map_btf_id = btf_id;
-	}
-
-	return 0;
-}
-
 static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 				     struct btf *btf,
 				     const struct btf_type *t,
@@ -5125,11 +5090,6 @@ struct btf *btf_parse_vmlinux(void)
 	/* btf_parse_vmlinux() runs under bpf_verifier_lock */
 	bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]);
 
-	/* find bpf map structs for map_ptr access checking */
-	err = btf_vmlinux_map_ids_init(btf, log);
-	if (err < 0)
-		goto errout;
-
 	bpf_struct_ops_init(btf, log);
 
 	refcount_set(&btf->refcnt, 1);
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 650e5d21f90d..f4860ac756cd 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -27,6 +27,7 @@
 #include <linux/kthread.h>
 #include <linux/capability.h>
 #include <trace/events/xdp.h>
+#include <linux/btf_ids.h>
 
 #include <linux/netdevice.h>   /* netif_receive_skb_list */
 #include <linux/etherdevice.h> /* eth_type_trans */
@@ -673,7 +674,7 @@ static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 				      __cpu_map_lookup_elem);
 }
 
-static int cpu_map_btf_id;
+BTF_ID_LIST_SINGLE(cpu_map_btf_ids, struct, bpf_cpu_map)
 const struct bpf_map_ops cpu_map_ops = {
 	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= cpu_map_alloc,
@@ -683,8 +684,7 @@ const struct bpf_map_ops cpu_map_ops = {
 	.map_lookup_elem	= cpu_map_lookup_elem,
 	.map_get_next_key	= cpu_map_get_next_key,
 	.map_check_btf		= map_check_no_btf,
-	.map_btf_name		= "bpf_cpu_map",
-	.map_btf_id		= &cpu_map_btf_id,
+	.map_btf_id		= &cpu_map_btf_ids[0],
 	.map_redirect		= cpu_map_redirect,
 };
 
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 038f6d7a83e4..c2867068e5bd 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -48,6 +48,7 @@
 #include <net/xdp.h>
 #include <linux/filter.h>
 #include <trace/events/xdp.h>
+#include <linux/btf_ids.h>
 
 #define DEV_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
@@ -1005,7 +1006,7 @@ static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 				      __dev_map_hash_lookup_elem);
 }
 
-static int dev_map_btf_id;
+BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab)
 const struct bpf_map_ops dev_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = dev_map_alloc,
@@ -1015,12 +1016,10 @@ const struct bpf_map_ops dev_map_ops = {
 	.map_update_elem = dev_map_update_elem,
 	.map_delete_elem = dev_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_dtab",
-	.map_btf_id = &dev_map_btf_id,
+	.map_btf_id = &dev_map_btf_ids[0],
 	.map_redirect = dev_map_redirect,
 };
 
-static int dev_map_hash_map_btf_id;
 const struct bpf_map_ops dev_map_hash_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = dev_map_alloc,
@@ -1030,8 +1029,7 @@ const struct bpf_map_ops dev_map_hash_ops = {
 	.map_update_elem = dev_map_hash_update_elem,
 	.map_delete_elem = dev_map_hash_delete_elem,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_dtab",
-	.map_btf_id = &dev_map_hash_map_btf_id,
+	.map_btf_id = &dev_map_btf_ids[0],
 	.map_redirect = dev_hash_map_redirect,
 };
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 7351e61bd683..3e00e62b2218 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -10,6 +10,7 @@
 #include <linux/random.h>
 #include <uapi/linux/btf.h>
 #include <linux/rcupdate_trace.h>
+#include <linux/btf_ids.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
@@ -2137,7 +2138,7 @@ out:
 	return num_elems;
 }
 
-static int htab_map_btf_id;
+BTF_ID_LIST_SINGLE(htab_map_btf_ids, struct, bpf_htab)
 const struct bpf_map_ops htab_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
@@ -2154,12 +2155,10 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab),
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
-static int htab_lru_map_btf_id;
 const struct bpf_map_ops htab_lru_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
@@ -2177,8 +2176,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_lru),
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_lru_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
@@ -2284,7 +2282,6 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
-static int htab_percpu_map_btf_id;
 const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
@@ -2299,12 +2296,10 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_percpu),
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_percpu_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
-static int htab_lru_percpu_map_btf_id;
 const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
@@ -2319,8 +2314,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_lru_percpu),
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_lru_percpu_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
@@ -2444,7 +2438,6 @@ static void htab_of_map_free(struct bpf_map *map)
 	fd_htab_map_free(map);
 }
 
-static int htab_of_maps_map_btf_id;
 const struct bpf_map_ops htab_of_maps_map_ops = {
 	.map_alloc_check = fd_htab_map_alloc_check,
 	.map_alloc = htab_of_map_alloc,
@@ -2457,6 +2450,5 @@ const struct bpf_map_ops htab_of_maps_map_ops = {
 	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
 	.map_gen_lookup = htab_of_map_gen_lookup,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_of_maps_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 };
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 497916060ac7..8654fc97f5fe 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -9,6 +9,7 @@
 #include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <uapi/linux/btf.h>
+#include <linux/btf_ids.h>
 
 #ifdef CONFIG_CGROUP_BPF
 
@@ -446,7 +447,8 @@ static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
-static int cgroup_storage_map_btf_id;
+BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct,
+		   bpf_cgroup_storage_map)
 const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_alloc = cgroup_storage_map_alloc,
 	.map_free = cgroup_storage_map_free,
@@ -456,8 +458,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_delete_elem = cgroup_storage_delete_elem,
 	.map_check_btf = cgroup_storage_check_btf,
 	.map_seq_show_elem = cgroup_storage_seq_show_elem,
-	.map_btf_name = "bpf_cgroup_storage_map",
-	.map_btf_id = &cgroup_storage_map_btf_id,
+	.map_btf_id = &cgroup_storage_map_btf_ids[0],
 };
 
 int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 5763cc7ac4f1..f0d05a3cc4b9 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -14,6 +14,7 @@
 #include <linux/vmalloc.h>
 #include <net/ipv6.h>
 #include <uapi/linux/btf.h>
+#include <linux/btf_ids.h>
 
 /* Intermediate node */
 #define LPM_TREE_NODE_FLAG_IM BIT(0)
@@ -719,7 +720,7 @@ static int trie_check_btf(const struct bpf_map *map,
 	       -EINVAL : 0;
 }
 
-static int trie_map_btf_id;
+BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie)
 const struct bpf_map_ops trie_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = trie_alloc,
@@ -732,6 +733,5 @@ const struct bpf_map_ops trie_map_ops = {
 	.map_update_batch = generic_map_update_batch,
 	.map_delete_batch = generic_map_delete_batch,
 	.map_check_btf = trie_check_btf,
-	.map_btf_name = "lpm_trie",
-	.map_btf_id = &trie_map_btf_id,
+	.map_btf_id = &trie_map_btf_ids[0],
 };
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index f9c734aaa990..a1c0794ae49d 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -8,6 +8,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/capability.h>
+#include <linux/btf_ids.h>
 #include "percpu_freelist.h"
 
 #define QUEUE_STACK_CREATE_FLAG_MASK \
@@ -247,7 +248,7 @@ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key,
 	return -EINVAL;
 }
 
-static int queue_map_btf_id;
+BTF_ID_LIST_SINGLE(queue_map_btf_ids, struct, bpf_queue_stack)
 const struct bpf_map_ops queue_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = queue_stack_map_alloc_check,
@@ -260,11 +261,9 @@ const struct bpf_map_ops queue_map_ops = {
 	.map_pop_elem = queue_map_pop_elem,
 	.map_peek_elem = queue_map_peek_elem,
 	.map_get_next_key = queue_stack_map_get_next_key,
-	.map_btf_name = "bpf_queue_stack",
-	.map_btf_id = &queue_map_btf_id,
+	.map_btf_id = &queue_map_btf_ids[0],
 };
 
-static int stack_map_btf_id;
 const struct bpf_map_ops stack_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = queue_stack_map_alloc_check,
@@ -277,6 +276,5 @@ const struct bpf_map_ops stack_map_ops = {
 	.map_pop_elem = stack_map_pop_elem,
 	.map_peek_elem = stack_map_peek_elem,
 	.map_get_next_key = queue_stack_map_get_next_key,
-	.map_btf_name = "bpf_queue_stack",
-	.map_btf_id = &stack_map_btf_id,
+	.map_btf_id = &queue_map_btf_ids[0],
 };
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 8251243022a2..e2618fb5870e 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -6,6 +6,7 @@
 #include <linux/err.h>
 #include <linux/sock_diag.h>
 #include <net/sock_reuseport.h>
+#include <linux/btf_ids.h>
 
 struct reuseport_array {
 	struct bpf_map map;
@@ -337,7 +338,7 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
 	return 0;
 }
 
-static int reuseport_array_map_btf_id;
+BTF_ID_LIST_SINGLE(reuseport_array_map_btf_ids, struct, reuseport_array)
 const struct bpf_map_ops reuseport_array_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = reuseport_array_alloc_check,
@@ -346,6 +347,5 @@ const struct bpf_map_ops reuseport_array_ops = {
 	.map_lookup_elem = reuseport_array_lookup_elem,
 	.map_get_next_key = reuseport_array_get_next_key,
 	.map_delete_elem = reuseport_array_delete_elem,
-	.map_btf_name = "reuseport_array",
-	.map_btf_id = &reuseport_array_map_btf_id,
+	.map_btf_id = &reuseport_array_map_btf_ids[0],
 };
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 5173fd37590f..311264ab80c4 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -10,6 +10,7 @@
 #include <linux/poll.h>
 #include <linux/kmemleak.h>
 #include <uapi/linux/btf.h>
+#include <linux/btf_ids.h>
 
 #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE)
 
@@ -263,7 +264,7 @@ static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp,
 	return 0;
 }
 
-static int ringbuf_map_btf_id;
+BTF_ID_LIST_SINGLE(ringbuf_map_btf_ids, struct, bpf_ringbuf_map)
 const struct bpf_map_ops ringbuf_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = ringbuf_map_alloc,
@@ -274,8 +275,7 @@ const struct bpf_map_ops ringbuf_map_ops = {
 	.map_update_elem = ringbuf_map_update_elem,
 	.map_delete_elem = ringbuf_map_delete_elem,
 	.map_get_next_key = ringbuf_map_get_next_key,
-	.map_btf_name = "bpf_ringbuf_map",
-	.map_btf_id = &ringbuf_map_btf_id,
+	.map_btf_id = &ringbuf_map_btf_ids[0],
 };
 
 /* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself,
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 1dd5266fbebb..1adbe67cdb95 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -654,7 +654,7 @@ static void stack_map_free(struct bpf_map *map)
 	put_callchain_buffers();
 }
 
-static int stack_trace_map_btf_id;
+BTF_ID_LIST_SINGLE(stack_trace_map_btf_ids, struct, bpf_stack_map)
 const struct bpf_map_ops stack_trace_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = stack_map_alloc,
@@ -664,6 +664,5 @@ const struct bpf_map_ops stack_trace_map_ops = {
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_stack_map",
-	.map_btf_id = &stack_trace_map_btf_id,
+	.map_btf_id = &stack_trace_map_btf_ids[0],
 };
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 83d7641ef67b..a25ec93729b9 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -338,7 +338,7 @@ bpf_sk_storage_ptr(void *owner)
 	return &sk->sk_bpf_storage;
 }
 
-static int sk_storage_map_btf_id;
+BTF_ID_LIST_SINGLE(sk_storage_map_btf_ids, struct, bpf_local_storage_map)
 const struct bpf_map_ops sk_storage_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = bpf_local_storage_map_alloc_check,
@@ -349,8 +349,7 @@ const struct bpf_map_ops sk_storage_map_ops = {
 	.map_update_elem = bpf_fd_sk_storage_update_elem,
 	.map_delete_elem = bpf_fd_sk_storage_delete_elem,
 	.map_check_btf = bpf_local_storage_map_check_btf,
-	.map_btf_name = "bpf_local_storage_map",
-	.map_btf_id = &sk_storage_map_btf_id,
+	.map_btf_id = &sk_storage_map_btf_ids[0],
 	.map_local_storage_charge = bpf_sk_storage_charge,
 	.map_local_storage_uncharge = bpf_sk_storage_uncharge,
 	.map_owner_storage_ptr = bpf_sk_storage_ptr,
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 2d213c4011db..81d4b4756a02 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -793,7 +793,7 @@ static const struct bpf_iter_seq_info sock_map_iter_seq_info = {
 	.seq_priv_size		= sizeof(struct sock_map_seq_info),
 };
 
-static int sock_map_btf_id;
+BTF_ID_LIST_SINGLE(sock_map_btf_ids, struct, bpf_stab)
 const struct bpf_map_ops sock_map_ops = {
 	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= sock_map_alloc,
@@ -805,8 +805,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_lookup_elem	= sock_map_lookup,
 	.map_release_uref	= sock_map_release_progs,
 	.map_check_btf		= map_check_no_btf,
-	.map_btf_name		= "bpf_stab",
-	.map_btf_id		= &sock_map_btf_id,
+	.map_btf_id		= &sock_map_btf_ids[0],
 	.iter_seq_info		= &sock_map_iter_seq_info,
 };
 
@@ -1385,7 +1384,7 @@ static const struct bpf_iter_seq_info sock_hash_iter_seq_info = {
 	.seq_priv_size		= sizeof(struct sock_hash_seq_info),
 };
 
-static int sock_hash_map_btf_id;
+BTF_ID_LIST_SINGLE(sock_hash_map_btf_ids, struct, bpf_shtab)
 const struct bpf_map_ops sock_hash_ops = {
 	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= sock_hash_alloc,
@@ -1397,8 +1396,7 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_lookup_elem_sys_only = sock_hash_lookup_sys,
 	.map_release_uref	= sock_hash_release_progs,
 	.map_check_btf		= map_check_no_btf,
-	.map_btf_name		= "bpf_shtab",
-	.map_btf_id		= &sock_hash_map_btf_id,
+	.map_btf_id		= &sock_hash_map_btf_ids[0],
 	.iter_seq_info		= &sock_hash_iter_seq_info,
 };
 
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 65b53fb3de13..acc8e52a4f5f 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -9,6 +9,7 @@
 #include <net/xdp_sock.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/btf_ids.h>
 
 #include "xsk.h"
 
@@ -254,7 +255,7 @@ static bool xsk_map_meta_equal(const struct bpf_map *meta0,
 		bpf_map_meta_equal(meta0, meta1);
 }
 
-static int xsk_map_btf_id;
+BTF_ID_LIST_SINGLE(xsk_map_btf_ids, struct, xsk_map)
 const struct bpf_map_ops xsk_map_ops = {
 	.map_meta_equal = xsk_map_meta_equal,
 	.map_alloc = xsk_map_alloc,
@@ -266,7 +267,6 @@ const struct bpf_map_ops xsk_map_ops = {
 	.map_update_elem = xsk_map_update_elem,
 	.map_delete_elem = xsk_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "xsk_map",
-	.map_btf_id = &xsk_map_btf_id,
+	.map_btf_id = &xsk_map_btf_ids[0],
 	.map_redirect = xsk_map_redirect,
 };
-- 
cgit v1.2.3


From 3ce0f2373f7073f04715b1ffd7b1812d3183f79a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 5 Apr 2022 15:12:57 +0800
Subject: compat: consolidate the compat_flock{,64} definition

Provide a single common definition for the compat_flock and
compat_flock64 structures using the same tricks as for the native
variants.  Another extra define is added for the packing required on
x86.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Helge Deller <deller@gmx.de>  # parisc
Link: https://lore.kernel.org/r/20220405071314.3225832-4-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/arm64/include/asm/compat.h   | 16 ----------------
 arch/mips/include/asm/compat.h    | 19 ++-----------------
 arch/parisc/include/asm/compat.h  | 16 ----------------
 arch/powerpc/include/asm/compat.h | 16 ----------------
 arch/s390/include/asm/compat.h    | 16 ----------------
 arch/sparc/include/asm/compat.h   | 18 +-----------------
 arch/x86/include/asm/compat.h     | 20 +++-----------------
 include/linux/compat.h            | 31 +++++++++++++++++++++++++++++++
 8 files changed, 37 insertions(+), 115 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 276328765408..e0faec1984a1 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -65,22 +65,6 @@ struct compat_stat {
 	compat_ulong_t	__unused4[2];
 };
 
-struct compat_flock {
-	short		l_type;
-	short		l_whence;
-	compat_off_t	l_start;
-	compat_off_t	l_len;
-	compat_pid_t	l_pid;
-};
-
-struct compat_flock64 {
-	short		l_type;
-	short		l_whence;
-	compat_loff_t	l_start;
-	compat_loff_t	l_len;
-	compat_pid_t	l_pid;
-};
-
 struct compat_statfs {
 	int		f_type;
 	int		f_bsize;
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 6a350c1f70d7..6d6e5a451f4d 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -55,23 +55,8 @@ struct compat_stat {
 	s32		st_pad4[14];
 };
 
-struct compat_flock {
-	short		l_type;
-	short		l_whence;
-	compat_off_t	l_start;
-	compat_off_t	l_len;
-	s32		l_sysid;
-	compat_pid_t	l_pid;
-	s32		pad[4];
-};
-
-struct compat_flock64 {
-	short		l_type;
-	short		l_whence;
-	compat_loff_t	l_start;
-	compat_loff_t	l_len;
-	compat_pid_t	l_pid;
-};
+#define __ARCH_COMPAT_FLOCK_EXTRA_SYSID		s32 l_sysid;
+#define __ARCH_COMPAT_FLOCK_PAD			s32 pad[4];
 
 struct compat_statfs {
 	int		f_type;
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index c04f5a637c39..a1e4534d8050 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -53,22 +53,6 @@ struct compat_stat {
 	u32			st_spare4[3];
 };
 
-struct compat_flock {
-	short			l_type;
-	short			l_whence;
-	compat_off_t		l_start;
-	compat_off_t		l_len;
-	compat_pid_t		l_pid;
-};
-
-struct compat_flock64 {
-	short			l_type;
-	short			l_whence;
-	compat_loff_t		l_start;
-	compat_loff_t		l_len;
-	compat_pid_t		l_pid;
-};
-
 struct compat_statfs {
 	s32		f_type;
 	s32		f_bsize;
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 83d8f70779cb..5ef3c7c83c34 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -44,22 +44,6 @@ struct compat_stat {
 	u32		__unused4[2];
 };
 
-struct compat_flock {
-	short		l_type;
-	short		l_whence;
-	compat_off_t	l_start;
-	compat_off_t	l_len;
-	compat_pid_t	l_pid;
-};
-
-struct compat_flock64 {
-	short		l_type;
-	short		l_whence;
-	compat_loff_t	l_start;
-	compat_loff_t	l_len;
-	compat_pid_t	l_pid;
-};
-
 struct compat_statfs {
 	int		f_type;
 	int		f_bsize;
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 0f14b3188b1b..07f04d37068b 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -102,22 +102,6 @@ struct compat_stat {
 	u32		__unused5;
 };
 
-struct compat_flock {
-	short		l_type;
-	short		l_whence;
-	compat_off_t	l_start;
-	compat_off_t	l_len;
-	compat_pid_t	l_pid;
-};
-
-struct compat_flock64 {
-	short		l_type;
-	short		l_whence;
-	compat_loff_t	l_start;
-	compat_loff_t	l_len;
-	compat_pid_t	l_pid;
-};
-
 struct compat_statfs {
 	u32		f_type;
 	u32		f_bsize;
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index 108078751bb5..d78fb44942e0 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -75,23 +75,7 @@ struct compat_stat64 {
 	unsigned int	__unused5;
 };
 
-struct compat_flock {
-	short		l_type;
-	short		l_whence;
-	compat_off_t	l_start;
-	compat_off_t	l_len;
-	compat_pid_t	l_pid;
-	short		__unused;
-};
-
-struct compat_flock64 {
-	short		l_type;
-	short		l_whence;
-	compat_loff_t	l_start;
-	compat_loff_t	l_len;
-	compat_pid_t	l_pid;
-	short		__unused;
-};
+#define __ARCH_COMPAT_FLOCK_PAD		short __unused;
 
 struct compat_statfs {
 	int		f_type;
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 8d19a212f4f2..de794d895866 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -50,25 +50,11 @@ struct compat_stat {
 	u32		__unused5;
 };
 
-struct compat_flock {
-	short		l_type;
-	short		l_whence;
-	compat_off_t	l_start;
-	compat_off_t	l_len;
-	compat_pid_t	l_pid;
-};
-
 /*
- * IA32 uses 4 byte alignment for 64 bit quantities,
- * so we need to pack this structure.
+ * IA32 uses 4 byte alignment for 64 bit quantities, so we need to pack the
+ * compat flock64 structure.
  */
-struct compat_flock64 {
-	short		l_type;
-	short		l_whence;
-	compat_loff_t	l_start;
-	compat_loff_t	l_len;
-	compat_pid_t	l_pid;
-} __attribute__((packed));
+#define __ARCH_NEED_COMPAT_FLOCK64_PACKED
 
 struct compat_statfs {
 	int		f_type;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 1c758b0e0359..a0481fe6c5d5 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -258,6 +258,37 @@ struct compat_rlimit {
 	compat_ulong_t	rlim_max;
 };
 
+#ifdef __ARCH_NEED_COMPAT_FLOCK64_PACKED
+#define __ARCH_COMPAT_FLOCK64_PACK	__attribute__((packed))
+#else
+#define __ARCH_COMPAT_FLOCK64_PACK
+#endif
+
+struct compat_flock {
+	short			l_type;
+	short			l_whence;
+	compat_off_t		l_start;
+	compat_off_t		l_len;
+#ifdef __ARCH_COMPAT_FLOCK_EXTRA_SYSID
+	__ARCH_COMPAT_FLOCK_EXTRA_SYSID
+#endif
+	compat_pid_t		l_pid;
+#ifdef __ARCH_COMPAT_FLOCK_PAD
+	__ARCH_COMPAT_FLOCK_PAD
+#endif
+};
+
+struct compat_flock64 {
+	short		l_type;
+	short		l_whence;
+	compat_loff_t	l_start;
+	compat_loff_t	l_len;
+	compat_pid_t	l_pid;
+#ifdef __ARCH_COMPAT_FLOCK64_PAD
+	__ARCH_COMPAT_FLOCK64_PAD
+#endif
+} __ARCH_COMPAT_FLOCK64_PACK;
+
 struct compat_rusage {
 	struct old_timeval32 ru_utime;
 	struct old_timeval32 ru_stime;
-- 
cgit v1.2.3


From 59c10c52f573faca862cda5ebcdd43831608eb5a Mon Sep 17 00:00:00 2001
From: Guo Ren <guoren@linux.alibaba.com>
Date: Tue, 5 Apr 2022 15:13:05 +0800
Subject: riscv: compat: syscall: Add compat_sys_call_table implementation

Implement compat sys_call_table and some system call functions:
truncate64, ftruncate64, fallocate, pread64, pwrite64,
sync_file_range, readahead, fadvise64_64 which need argument
translation.

Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20220405071314.3225832-12-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/syscall.h         |  1 +
 arch/riscv/include/asm/unistd.h          | 11 ++++++++++
 arch/riscv/include/uapi/asm/unistd.h     |  2 +-
 arch/riscv/kernel/Makefile               |  1 +
 arch/riscv/kernel/compat_syscall_table.c | 19 ++++++++++++++++
 arch/riscv/kernel/sys_riscv.c            |  6 ++++--
 fs/open.c                                | 24 +++++++++++++++++++++
 fs/read_write.c                          | 16 ++++++++++++++
 fs/sync.c                                |  9 ++++++++
 include/asm-generic/compat.h             |  7 ++++++
 include/linux/compat.h                   | 37 ++++++++++++++++++++++++++++++++
 mm/fadvise.c                             | 11 ++++++++++
 mm/readahead.c                           |  7 ++++++
 13 files changed, 148 insertions(+), 3 deletions(-)
 create mode 100644 arch/riscv/kernel/compat_syscall_table.c

(limited to 'include/linux')

diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index 7ac6a0e275f2..384a63b86420 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -16,6 +16,7 @@
 
 /* The array of function pointers for syscalls. */
 extern void * const sys_call_table[];
+extern void * const compat_sys_call_table[];
 
 /*
  * Only the low 32 bits of orig_r0 are meaningful, so we return int.
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
index 6c316093a1e5..5ddac412b578 100644
--- a/arch/riscv/include/asm/unistd.h
+++ b/arch/riscv/include/asm/unistd.h
@@ -11,6 +11,17 @@
 #define __ARCH_WANT_SYS_CLONE
 #define __ARCH_WANT_MEMFD_SECRET
 
+#ifdef CONFIG_COMPAT
+#define __ARCH_WANT_COMPAT_TRUNCATE64
+#define __ARCH_WANT_COMPAT_FTRUNCATE64
+#define __ARCH_WANT_COMPAT_FALLOCATE
+#define __ARCH_WANT_COMPAT_PREAD64
+#define __ARCH_WANT_COMPAT_PWRITE64
+#define __ARCH_WANT_COMPAT_SYNC_FILE_RANGE
+#define __ARCH_WANT_COMPAT_READAHEAD
+#define __ARCH_WANT_COMPAT_FADVISE64_64
+#endif
+
 #include <uapi/asm/unistd.h>
 
 #define NR_syscalls (__NR_syscalls)
diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
index 8062996c2dfd..c9e50eed14aa 100644
--- a/arch/riscv/include/uapi/asm/unistd.h
+++ b/arch/riscv/include/uapi/asm/unistd.h
@@ -15,7 +15,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-#ifdef __LP64__
+#if defined(__LP64__) && !defined(__SYSCALL_COMPAT)
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SET_GET_RLIMIT
 #endif /* __LP64__ */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 87adbe47bc15..2fa06d6572bb 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -69,3 +69,4 @@ obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 
 obj-$(CONFIG_EFI)		+= efi.o
+obj-$(CONFIG_COMPAT)		+= compat_syscall_table.o
diff --git a/arch/riscv/kernel/compat_syscall_table.c b/arch/riscv/kernel/compat_syscall_table.c
new file mode 100644
index 000000000000..651f2b009c28
--- /dev/null
+++ b/arch/riscv/kernel/compat_syscall_table.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define __SYSCALL_COMPAT
+
+#include <linux/compat.h>
+#include <linux/syscalls.h>
+#include <asm-generic/mman-common.h>
+#include <asm-generic/syscalls.h>
+#include <asm/syscall.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call)      [nr] = (call),
+
+asmlinkage long compat_sys_rt_sigreturn(void);
+
+void * const compat_sys_call_table[__NR_syscalls] = {
+	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+#include <asm/unistd.h>
+};
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 12f8a7fce78b..9c0194f176fc 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -33,7 +33,9 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 {
 	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0);
 }
-#else
+#endif
+
+#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
 SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 	unsigned long, prot, unsigned long, flags,
 	unsigned long, fd, off_t, offset)
@@ -44,7 +46,7 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 	 */
 	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12);
 }
-#endif /* !CONFIG_64BIT */
+#endif
 
 /*
  * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
diff --git a/fs/open.c b/fs/open.c
index 1315253e0247..0573eebb68a6 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -224,6 +224,21 @@ SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length)
 }
 #endif /* BITS_PER_LONG == 32 */
 
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_TRUNCATE64)
+COMPAT_SYSCALL_DEFINE3(truncate64, const char __user *, pathname,
+		       compat_arg_u64_dual(length))
+{
+	return ksys_truncate(pathname, compat_arg_u64_glue(length));
+}
+#endif
+
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FTRUNCATE64)
+COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd,
+		       compat_arg_u64_dual(length))
+{
+	return ksys_ftruncate(fd, compat_arg_u64_glue(length));
+}
+#endif
 
 int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
@@ -339,6 +354,15 @@ SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
 	return ksys_fallocate(fd, mode, offset, len);
 }
 
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FALLOCATE)
+COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode, compat_arg_u64_dual(offset),
+		       compat_arg_u64_dual(len))
+{
+	return ksys_fallocate(fd, mode, compat_arg_u64_glue(offset),
+			      compat_arg_u64_glue(len));
+}
+#endif
+
 /*
  * access() needs to use the real uid/gid, not the effective uid/gid.
  * We do this by temporarily clearing all FS-related capabilities and
diff --git a/fs/read_write.c b/fs/read_write.c
index e643aec2b0ef..b1b1cdfee9d3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -682,6 +682,14 @@ SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf,
 	return ksys_pread64(fd, buf, count, pos);
 }
 
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64)
+COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf,
+		       size_t, count, compat_arg_u64_dual(pos))
+{
+	return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos));
+}
+#endif
+
 ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf,
 		      size_t count, loff_t pos)
 {
@@ -708,6 +716,14 @@ SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf,
 	return ksys_pwrite64(fd, buf, count, pos);
 }
 
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64)
+COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf,
+		       size_t, count, compat_arg_u64_dual(pos))
+{
+	return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos));
+}
+#endif
+
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 		loff_t *ppos, int type, rwf_t flags)
 {
diff --git a/fs/sync.c b/fs/sync.c
index c7690016453e..dc725914e1ed 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -373,6 +373,15 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
 	return ksys_sync_file_range(fd, offset, nbytes, flags);
 }
 
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_SYNC_FILE_RANGE)
+COMPAT_SYSCALL_DEFINE6(sync_file_range, int, fd, compat_arg_u64_dual(offset),
+		       compat_arg_u64_dual(nbytes), unsigned int, flags)
+{
+	return ksys_sync_file_range(fd, compat_arg_u64_glue(offset),
+				    compat_arg_u64_glue(nbytes), flags);
+}
+#endif
+
 /* It would be nice if people remember that not all the world's an i386
    when they introduce new system calls */
 SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags,
diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h
index 11653d6846cc..d06308a2a7a8 100644
--- a/include/asm-generic/compat.h
+++ b/include/asm-generic/compat.h
@@ -14,6 +14,13 @@
 #define COMPAT_OFF_T_MAX	0x7fffffff
 #endif
 
+#if !defined(compat_arg_u64) && !defined(CONFIG_CPU_BIG_ENDIAN)
+#define compat_arg_u64(name)		u32  name##_lo, u32  name##_hi
+#define compat_arg_u64_dual(name)	u32, name##_lo, u32, name##_hi
+#define compat_arg_u64_glue(name)	(((u64)name##_lo & 0xffffffffUL) | \
+					 ((u64)name##_hi << 32))
+#endif
+
 /* These types are common across all compat ABIs */
 typedef u32 compat_size_t;
 typedef s32 compat_ssize_t;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index a0481fe6c5d5..ce6cd9b30d27 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -926,6 +926,43 @@ asmlinkage long compat_sys_sigaction(int sig,
 /* obsolete: net/socket.c */
 asmlinkage long compat_sys_socketcall(int call, u32 __user *args);
 
+#ifdef __ARCH_WANT_COMPAT_TRUNCATE64
+asmlinkage long compat_sys_truncate64(const char __user *pathname, compat_arg_u64(len));
+#endif
+
+#ifdef __ARCH_WANT_COMPAT_FTRUNCATE64
+asmlinkage long compat_sys_ftruncate64(unsigned int fd, compat_arg_u64(len));
+#endif
+
+#ifdef __ARCH_WANT_COMPAT_FALLOCATE
+asmlinkage long compat_sys_fallocate(int fd, int mode, compat_arg_u64(offset),
+				     compat_arg_u64(len));
+#endif
+
+#ifdef __ARCH_WANT_COMPAT_PREAD64
+asmlinkage long compat_sys_pread64(unsigned int fd, char __user *buf, size_t count,
+				   compat_arg_u64(pos));
+#endif
+
+#ifdef __ARCH_WANT_COMPAT_PWRITE64
+asmlinkage long compat_sys_pwrite64(unsigned int fd, const char __user *buf, size_t count,
+				    compat_arg_u64(pos));
+#endif
+
+#ifdef __ARCH_WANT_COMPAT_SYNC_FILE_RANGE
+asmlinkage long compat_sys_sync_file_range(int fd, compat_arg_u64(pos),
+					   compat_arg_u64(nbytes), unsigned int flags);
+#endif
+
+#ifdef __ARCH_WANT_COMPAT_FADVISE64_64
+asmlinkage long compat_sys_fadvise64_64(int fd, compat_arg_u64(pos),
+					compat_arg_u64(len), int advice);
+#endif
+
+#ifdef __ARCH_WANT_COMPAT_READAHEAD
+asmlinkage long compat_sys_readahead(int fd, compat_arg_u64(offset), size_t count);
+#endif
+
 #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
 
 /**
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 338f16022012..c76ee665355a 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -214,5 +214,16 @@ SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
 	return ksys_fadvise64_64(fd, offset, len, advice);
 }
 
+#endif
+
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FADVISE64_64)
+
+COMPAT_SYSCALL_DEFINE6(fadvise64_64, int, fd, compat_arg_u64_dual(offset),
+		       compat_arg_u64_dual(len), int, advice)
+{
+	return ksys_fadvise64_64(fd, compat_arg_u64_glue(offset),
+				 compat_arg_u64_glue(len), advice);
+}
+
 #endif
 #endif
diff --git a/mm/readahead.c b/mm/readahead.c
index 8e3775829513..a9ba3bb19ad0 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -746,6 +746,13 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
 	return ksys_readahead(fd, offset, count);
 }
 
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD)
+COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count)
+{
+	return ksys_readahead(fd, compat_arg_u64_glue(offset), count);
+}
+#endif
+
 /**
  * readahead_expand - Expand a readahead request
  * @ractl: The request to be expanded
-- 
cgit v1.2.3


From a2a9d67a26ec94a99ed29efbd61cf5be0a575678 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 6 Apr 2022 11:31:19 +0900
Subject: bootconfig: Support embedding a bootconfig file in kernel

This allows kernel developer to embed a default bootconfig file in
the kernel instead of embedding it in the initrd. This will be good
for who are using the kernel without initrd, or who needs a default
bootconfigs.
This needs to set two kconfigs: CONFIG_BOOT_CONFIG_EMBED=y and set
the file path to CONFIG_BOOT_CONFIG_EMBED_FILE.

Note that you still need 'bootconfig' command line option to load the
embedded bootconfig. Also if you boot using an initrd with a different
bootconfig, the kernel will use the bootconfig in the initrd, instead
of the default bootconfig.

Link: https://lkml.kernel.org/r/164921227943.1090670.14035119557571329218.stgit@devnote2

Cc: Padmanabha Srinivasaiah <treasure4paddy@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Linux Kbuild mailing list <linux-kbuild@vger.kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 MAINTAINERS                |  1 +
 include/linux/bootconfig.h | 10 ++++++++++
 init/Kconfig               | 21 ++++++++++++++++++++-
 init/main.c                | 22 ++++++++++++----------
 lib/.gitignore             |  1 +
 lib/Makefile               |  8 ++++++++
 lib/bootconfig-data.S      | 10 ++++++++++
 lib/bootconfig.c           | 13 +++++++++++++
 8 files changed, 75 insertions(+), 11 deletions(-)
 create mode 100644 lib/bootconfig-data.S

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index b90535d923a0..abc8e6fee21e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7457,6 +7457,7 @@ S:	Maintained
 F:	Documentation/admin-guide/bootconfig.rst
 F:	fs/proc/bootconfig.c
 F:	include/linux/bootconfig.h
+F:	lib/bootconfig-data.S
 F:	lib/bootconfig.c
 F:	tools/bootconfig/*
 F:	tools/bootconfig/scripts/*
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index a4665c7ab07c..1611f9db878e 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -289,4 +289,14 @@ int __init xbc_get_info(int *node_size, size_t *data_size);
 /* XBC cleanup data structures */
 void __init xbc_exit(void);
 
+/* XBC embedded bootconfig data in kernel */
+#ifdef CONFIG_BOOT_CONFIG_EMBED
+const char * __init xbc_get_embedded_bootconfig(size_t *size);
+#else
+static inline const char *xbc_get_embedded_bootconfig(size_t *size)
+{
+	return NULL;
+}
+#endif
+
 #endif
diff --git a/init/Kconfig b/init/Kconfig
index ddcbefe535e9..2462d4ae2dc8 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1351,7 +1351,7 @@ endif
 
 config BOOT_CONFIG
 	bool "Boot config support"
-	select BLK_DEV_INITRD
+	select BLK_DEV_INITRD if !BOOT_CONFIG_EMBED
 	help
 	  Extra boot config allows system admin to pass a config file as
 	  complemental extension of kernel cmdline when booting.
@@ -1361,6 +1361,25 @@ config BOOT_CONFIG
 
 	  If unsure, say Y.
 
+config BOOT_CONFIG_EMBED
+	bool "Embed bootconfig file in the kernel"
+	depends on BOOT_CONFIG
+	help
+	  Embed a bootconfig file given by BOOT_CONFIG_EMBED_FILE in the
+	  kernel. Usually, the bootconfig file is loaded with the initrd
+	  image. But if the system doesn't support initrd, this option will
+	  help you by embedding a bootconfig file while building the kernel.
+
+	  If unsure, say N.
+
+config BOOT_CONFIG_EMBED_FILE
+	string "Embedded bootconfig file path"
+	depends on BOOT_CONFIG_EMBED
+	help
+	  Specify a bootconfig file which will be embedded to the kernel.
+	  This bootconfig will be used if there is no initrd or no other
+	  bootconfig in the initrd.
+
 choice
 	prompt "Compiler optimization level"
 	default CC_OPTIMIZE_FOR_PERFORMANCE
diff --git a/init/main.c b/init/main.c
index 266d61bc67b0..f7fe7cbb1df8 100644
--- a/init/main.c
+++ b/init/main.c
@@ -266,7 +266,7 @@ static int __init loglevel(char *str)
 early_param("loglevel", loglevel);
 
 #ifdef CONFIG_BLK_DEV_INITRD
-static void * __init get_boot_config_from_initrd(u32 *_size)
+static void * __init get_boot_config_from_initrd(size_t *_size)
 {
 	u32 size, csum;
 	char *data;
@@ -313,7 +313,7 @@ found:
 	return data;
 }
 #else
-static void * __init get_boot_config_from_initrd(u32 *_size)
+static void * __init get_boot_config_from_initrd(size_t *_size)
 {
 	return NULL;
 }
@@ -410,14 +410,16 @@ static int __init warn_bootconfig(char *str)
 static void __init setup_boot_config(void)
 {
 	static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
-	const char *msg;
-	int pos;
-	u32 size;
-	char *data, *err;
-	int ret;
+	const char *msg, *data;
+	int pos, ret;
+	size_t size;
+	char *err;
 
 	/* Cut out the bootconfig data even if we have no bootconfig option */
 	data = get_boot_config_from_initrd(&size);
+	/* If there is no bootconfig in initrd, try embedded one. */
+	if (!data)
+		data = xbc_get_embedded_bootconfig(&size);
 
 	strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
 	err = parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
@@ -436,8 +438,8 @@ static void __init setup_boot_config(void)
 	}
 
 	if (size >= XBC_DATA_MAX) {
-		pr_err("bootconfig size %d greater than max size %d\n",
-			size, XBC_DATA_MAX);
+		pr_err("bootconfig size %ld greater than max size %d\n",
+			(long)size, XBC_DATA_MAX);
 		return;
 	}
 
@@ -450,7 +452,7 @@ static void __init setup_boot_config(void)
 				msg, pos);
 	} else {
 		xbc_get_info(&ret, NULL);
-		pr_info("Load bootconfig: %d bytes %d nodes\n", size, ret);
+		pr_info("Load bootconfig: %ld bytes %d nodes\n", (long)size, ret);
 		/* keys starting with "kernel." are passed via cmdline */
 		extra_command_line = xbc_make_cmdline("kernel");
 		/* Also, "init." keys are init arguments */
diff --git a/lib/.gitignore b/lib/.gitignore
index e5e217b8307b..54596b634ecb 100644
--- a/lib/.gitignore
+++ b/lib/.gitignore
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /crc32table.h
 /crc64table.h
+/default.bconf
 /gen_crc32table
 /gen_crc64table
 /oid_registry_data.c
diff --git a/lib/Makefile b/lib/Makefile
index 08053df16c7c..95268d6c75b7 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -280,6 +280,14 @@ $(foreach file, $(libfdt_files), \
 lib-$(CONFIG_LIBFDT) += $(libfdt_files)
 
 obj-$(CONFIG_BOOT_CONFIG) += bootconfig.o
+obj-$(CONFIG_BOOT_CONFIG_EMBED) += bootconfig-data.o
+
+$(obj)/bootconfig-data.o: $(obj)/default.bconf
+
+targets += default.bconf
+filechk_defbconf = cat $(or $(real-prereqs), /dev/null)
+$(obj)/default.bconf: $(CONFIG_BOOT_CONFIG_EMBED_FILE) FORCE
+	$(call filechk,defbconf)
 
 obj-$(CONFIG_RBTREE_TEST) += rbtree_test.o
 obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o
diff --git a/lib/bootconfig-data.S b/lib/bootconfig-data.S
new file mode 100644
index 000000000000..ef85ba1a82f4
--- /dev/null
+++ b/lib/bootconfig-data.S
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Embed default bootconfig in the kernel.
+ */
+	.section .init.rodata, "aw"
+	.global embedded_bootconfig_data
+embedded_bootconfig_data:
+	.incbin "lib/default.bconf"
+	.global embedded_bootconfig_data_end
+embedded_bootconfig_data_end:
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 74f3201ab8e5..c59d26068a64 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -12,6 +12,19 @@
 #include <linux/kernel.h>
 #include <linux/memblock.h>
 #include <linux/string.h>
+
+#ifdef CONFIG_BOOT_CONFIG_EMBED
+/* embedded_bootconfig_data is defined in bootconfig-data.S */
+extern __visible const char embedded_bootconfig_data[];
+extern __visible const char embedded_bootconfig_data_end[];
+
+const char * __init xbc_get_embedded_bootconfig(size_t *size)
+{
+	*size = embedded_bootconfig_data_end - embedded_bootconfig_data;
+	return (*size) ? embedded_bootconfig_data : NULL;
+}
+#endif
+
 #else /* !__KERNEL__ */
 /*
  * NOTE: This is only for tools/bootconfig, because tools/bootconfig will
-- 
cgit v1.2.3


From 68822bdf76f10c3dc80609d4e2cdc1e847429086 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Apr 2022 13:12:37 -0700
Subject: net: generalize skb freeing deferral to per-cpu lists

Logic added in commit f35f821935d8 ("tcp: defer skb freeing after socket
lock is released") helped bulk TCP flows to move the cost of skbs
frees outside of critical section where socket lock was held.

But for RPC traffic, or hosts with RFS enabled, the solution is far from
being ideal.

For RPC traffic, recvmsg() has to return to user space right after
skb payload has been consumed, meaning that BH handler has no chance
to pick the skb before recvmsg() thread. This issue is more visible
with BIG TCP, as more RPC fit one skb.

For RFS, even if BH handler picks the skbs, they are still picked
from the cpu on which user thread is running.

Ideally, it is better to free the skbs (and associated page frags)
on the cpu that originally allocated them.

This patch removes the per socket anchor (sk->defer_list) and
instead uses a per-cpu list, which will hold more skbs per round.

This new per-cpu list is drained at the end of net_action_rx(),
after incoming packets have been processed, to lower latencies.

In normal conditions, skbs are added to the per-cpu list with
no further action. In the (unlikely) cases where the cpu does not
run net_action_rx() handler fast enough, we use an IPI to raise
NET_RX_SOFTIRQ on the remote cpu.

Also, we do not bother draining the per-cpu list from dev_cpu_dead()
This is because skbs in this list have no requirement on how fast
they should be freed.

Note that we can add in the future a small per-cpu cache
if we see any contention on sd->defer_lock.

Tested on a pair of hosts with 100Gbit NIC, RFS enabled,
and /proc/sys/net/ipv4/tcp_rmem[2] tuned to 16MB to work around
page recycling strategy used by NIC driver (its page pool capacity
being too small compared to number of skbs/pages held in sockets
receive queues)

Note that this tuning was only done to demonstrate worse
conditions for skb freeing for this particular test.
These conditions can happen in more general production workload.

10 runs of one TCP_STREAM flow

Before:
Average throughput: 49685 Mbit.

Kernel profiles on cpu running user thread recvmsg() show high cost for
skb freeing related functions (*)

    57.81%  [kernel]       [k] copy_user_enhanced_fast_string
(*) 12.87%  [kernel]       [k] skb_release_data
(*)  4.25%  [kernel]       [k] __free_one_page
(*)  3.57%  [kernel]       [k] __list_del_entry_valid
     1.85%  [kernel]       [k] __netif_receive_skb_core
     1.60%  [kernel]       [k] __skb_datagram_iter
(*)  1.59%  [kernel]       [k] free_unref_page_commit
(*)  1.16%  [kernel]       [k] __slab_free
     1.16%  [kernel]       [k] _copy_to_iter
(*)  1.01%  [kernel]       [k] kfree
(*)  0.88%  [kernel]       [k] free_unref_page
     0.57%  [kernel]       [k] ip6_rcv_core
     0.55%  [kernel]       [k] ip6t_do_table
     0.54%  [kernel]       [k] flush_smp_call_function_queue
(*)  0.54%  [kernel]       [k] free_pcppages_bulk
     0.51%  [kernel]       [k] llist_reverse_order
     0.38%  [kernel]       [k] process_backlog
(*)  0.38%  [kernel]       [k] free_pcp_prepare
     0.37%  [kernel]       [k] tcp_recvmsg_locked
(*)  0.37%  [kernel]       [k] __list_add_valid
     0.34%  [kernel]       [k] sock_rfree
     0.34%  [kernel]       [k] _raw_spin_lock_irq
(*)  0.33%  [kernel]       [k] __page_cache_release
     0.33%  [kernel]       [k] tcp_v6_rcv
(*)  0.33%  [kernel]       [k] __put_page
(*)  0.29%  [kernel]       [k] __mod_zone_page_state
     0.27%  [kernel]       [k] _raw_spin_lock

After patch:
Average throughput: 73076 Mbit.

Kernel profiles on cpu running user thread recvmsg() looks better:

    81.35%  [kernel]       [k] copy_user_enhanced_fast_string
     1.95%  [kernel]       [k] _copy_to_iter
     1.95%  [kernel]       [k] __skb_datagram_iter
     1.27%  [kernel]       [k] __netif_receive_skb_core
     1.03%  [kernel]       [k] ip6t_do_table
     0.60%  [kernel]       [k] sock_rfree
     0.50%  [kernel]       [k] tcp_v6_rcv
     0.47%  [kernel]       [k] ip6_rcv_core
     0.45%  [kernel]       [k] read_tsc
     0.44%  [kernel]       [k] _raw_spin_lock_irqsave
     0.37%  [kernel]       [k] _raw_spin_lock
     0.37%  [kernel]       [k] native_irq_return_iret
     0.33%  [kernel]       [k] __inet6_lookup_established
     0.31%  [kernel]       [k] ip6_protocol_deliver_rcu
     0.29%  [kernel]       [k] tcp_rcv_established
     0.29%  [kernel]       [k] llist_reverse_order

v2: kdoc issue (kernel bots)
    do not defer if (alloc_cpu == smp_processor_id()) (Paolo)
    replace the sk_buff_head with a single-linked list (Jakub)
    add a READ_ONCE()/WRITE_ONCE() for the lockless read of sd->defer_list

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20220422201237.416238-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  5 +++++
 include/linux/skbuff.h    |  3 +++
 include/net/sock.h        |  2 --
 include/net/tcp.h         | 12 -----------
 net/core/dev.c            | 31 ++++++++++++++++++++++++++++
 net/core/skbuff.c         | 51 ++++++++++++++++++++++++++++++++++++++++++++++-
 net/core/sock.c           |  3 ---
 net/ipv4/tcp.c            | 25 +----------------------
 net/ipv4/tcp_ipv4.c       |  1 -
 net/ipv6/tcp_ipv6.c       |  1 -
 net/tls/tls_sw.c          |  2 --
 11 files changed, 90 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7dccbfd1bf56..ac8a5f71220a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3081,6 +3081,11 @@ struct softnet_data {
 	struct sk_buff_head	input_pkt_queue;
 	struct napi_struct	backlog;
 
+	/* Another possibly contended cache line */
+	spinlock_t		defer_lock ____cacheline_aligned_in_smp;
+	int			defer_count;
+	struct sk_buff		*defer_list;
+	call_single_data_t	defer_csd;
 };
 
 static inline void input_queue_head_incr(struct softnet_data *sd)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 84d78df60453..5cbc184ca685 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -888,6 +888,7 @@ typedef unsigned char *sk_buff_data_t;
  *		delivery_time at egress.
  *	@napi_id: id of the NAPI struct this skb came from
  *	@sender_cpu: (aka @napi_id) source CPU in XPS
+ *	@alloc_cpu: CPU which did the skb allocation.
  *	@secmark: security marking
  *	@mark: Generic packet mark
  *	@reserved_tailroom: (aka @mark) number of bytes of free space available
@@ -1080,6 +1081,7 @@ struct sk_buff {
 		unsigned int	sender_cpu;
 	};
 #endif
+	u16			alloc_cpu;
 #ifdef CONFIG_NETWORK_SECMARK
 	__u32		secmark;
 #endif
@@ -1321,6 +1323,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb_around(struct sk_buff *skb,
 				 void *data, unsigned int frag_size);
+void skb_attempt_defer_free(struct sk_buff *skb);
 
 struct sk_buff *napi_build_skb(void *data, unsigned int frag_size);
 
diff --git a/include/net/sock.h b/include/net/sock.h
index a01d6c421aa2..f9f8ecae0f8d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -292,7 +292,6 @@ struct sk_filter;
   *	@sk_pacing_shift: scaling factor for TCP Small Queues
   *	@sk_lingertime: %SO_LINGER l_linger setting
   *	@sk_backlog: always used with the per-socket spinlock held
-  *	@defer_list: head of llist storing skbs to be freed
   *	@sk_callback_lock: used with the callbacks in the end of this struct
   *	@sk_error_queue: rarely used
   *	@sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
@@ -417,7 +416,6 @@ struct sock {
 		struct sk_buff	*head;
 		struct sk_buff	*tail;
 	} sk_backlog;
-	struct llist_head defer_list;
 
 #define sk_rmem_alloc sk_backlog.rmem_alloc
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 679b1964d494..94a52ad1101c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1375,18 +1375,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 		     enum skb_drop_reason *reason);
 
-#ifdef CONFIG_INET
-void __sk_defer_free_flush(struct sock *sk);
-
-static inline void sk_defer_free_flush(struct sock *sk)
-{
-	if (llist_empty(&sk->defer_list))
-		return;
-	__sk_defer_free_flush(sk);
-}
-#else
-static inline void sk_defer_free_flush(struct sock *sk) {}
-#endif
 
 int tcp_filter(struct sock *sk, struct sk_buff *skb);
 void tcp_set_state(struct sock *sk, int state);
diff --git a/net/core/dev.c b/net/core/dev.c
index 4a77ebda4fb1..611bd7197064 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4545,6 +4545,12 @@ static void rps_trigger_softirq(void *data)
 
 #endif /* CONFIG_RPS */
 
+/* Called from hardirq (IPI) context */
+static void trigger_rx_softirq(void *data __always_unused)
+{
+	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+}
+
 /*
  * Check if this softnet_data structure is another cpu one
  * If yes, queue it to our IPI list and return 1
@@ -6571,6 +6577,28 @@ static int napi_threaded_poll(void *data)
 	return 0;
 }
 
+static void skb_defer_free_flush(struct softnet_data *sd)
+{
+	struct sk_buff *skb, *next;
+	unsigned long flags;
+
+	/* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
+	if (!READ_ONCE(sd->defer_list))
+		return;
+
+	spin_lock_irqsave(&sd->defer_lock, flags);
+	skb = sd->defer_list;
+	sd->defer_list = NULL;
+	sd->defer_count = 0;
+	spin_unlock_irqrestore(&sd->defer_lock, flags);
+
+	while (skb != NULL) {
+		next = skb->next;
+		__kfree_skb(skb);
+		skb = next;
+	}
+}
+
 static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -6616,6 +6644,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
 
 	net_rps_action_and_irq_enable(sd);
+	skb_defer_free_flush(sd);
 }
 
 struct netdev_adjacent {
@@ -11326,6 +11355,8 @@ static int __init net_dev_init(void)
 		INIT_CSD(&sd->csd, rps_trigger_softirq, sd);
 		sd->cpu = i;
 #endif
+		INIT_CSD(&sd->defer_csd, trigger_rx_softirq, NULL);
+		spin_lock_init(&sd->defer_lock);
 
 		init_gro_hash(&sd->backlog);
 		sd->backlog.poll = process_backlog;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 30b523fa4ad2..028a280fbabd 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -204,7 +204,7 @@ static void __build_skb_around(struct sk_buff *skb, void *data,
 	skb_set_end_offset(skb, size);
 	skb->mac_header = (typeof(skb->mac_header))~0U;
 	skb->transport_header = (typeof(skb->transport_header))~0U;
-
+	skb->alloc_cpu = raw_smp_processor_id();
 	/* make sure we initialize shinfo sequentially */
 	shinfo = skb_shinfo(skb);
 	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
@@ -1037,6 +1037,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	CHECK_SKB_FIELD(napi_id);
 #endif
+	CHECK_SKB_FIELD(alloc_cpu);
 #ifdef CONFIG_XPS
 	CHECK_SKB_FIELD(sender_cpu);
 #endif
@@ -6486,3 +6487,51 @@ free_now:
 }
 EXPORT_SYMBOL(__skb_ext_put);
 #endif /* CONFIG_SKB_EXTENSIONS */
+
+/**
+ * skb_attempt_defer_free - queue skb for remote freeing
+ * @skb: buffer
+ *
+ * Put @skb in a per-cpu list, using the cpu which
+ * allocated the skb/pages to reduce false sharing
+ * and memory zone spinlock contention.
+ */
+void skb_attempt_defer_free(struct sk_buff *skb)
+{
+	int cpu = skb->alloc_cpu;
+	struct softnet_data *sd;
+	unsigned long flags;
+	bool kick;
+
+	if (WARN_ON_ONCE(cpu >= nr_cpu_ids) ||
+	    !cpu_online(cpu) ||
+	    cpu == raw_smp_processor_id()) {
+		__kfree_skb(skb);
+		return;
+	}
+
+	sd = &per_cpu(softnet_data, cpu);
+	/* We do not send an IPI or any signal.
+	 * Remote cpu will eventually call skb_defer_free_flush()
+	 */
+	spin_lock_irqsave(&sd->defer_lock, flags);
+	skb->next = sd->defer_list;
+	/* Paired with READ_ONCE() in skb_defer_free_flush() */
+	WRITE_ONCE(sd->defer_list, skb);
+	sd->defer_count++;
+
+	/* kick every time queue length reaches 128.
+	 * This should avoid blocking in smp_call_function_single_async().
+	 * This condition should hardly be bit under normal conditions,
+	 * unless cpu suddenly stopped to receive NIC interrupts.
+	 */
+	kick = sd->defer_count == 128;
+
+	spin_unlock_irqrestore(&sd->defer_lock, flags);
+
+	/* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU
+	 * if we are unlucky enough (this seems very unlikely).
+	 */
+	if (unlikely(kick))
+		smp_call_function_single_async(cpu, &sd->defer_csd);
+}
diff --git a/net/core/sock.c b/net/core/sock.c
index 29abec3eabd8..a0f3989de3d6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2082,9 +2082,6 @@ void sk_destruct(struct sock *sk)
 {
 	bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
 
-	WARN_ON_ONCE(!llist_empty(&sk->defer_list));
-	sk_defer_free_flush(sk);
-
 	if (rcu_access_pointer(sk->sk_reuseport_cb)) {
 		reuseport_detach_sock(sk);
 		use_call_rcu = true;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e20b87b3bf90..db55af9eb37b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -843,7 +843,6 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 	}
 
 	release_sock(sk);
-	sk_defer_free_flush(sk);
 
 	if (spliced)
 		return spliced;
@@ -1589,20 +1588,6 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 		tcp_send_ack(sk);
 }
 
-void __sk_defer_free_flush(struct sock *sk)
-{
-	struct llist_node *head;
-	struct sk_buff *skb, *n;
-
-	head = llist_del_all(&sk->defer_list);
-	llist_for_each_entry_safe(skb, n, head, ll_node) {
-		prefetch(n);
-		skb_mark_not_on_list(skb);
-		__kfree_skb(skb);
-	}
-}
-EXPORT_SYMBOL(__sk_defer_free_flush);
-
 static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
@@ -1610,11 +1595,7 @@ static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 		sock_rfree(skb);
 		skb->destructor = NULL;
 		skb->sk = NULL;
-		if (!skb_queue_empty(&sk->sk_receive_queue) ||
-		    !llist_empty(&sk->defer_list)) {
-			llist_add(&skb->ll_node, &sk->defer_list);
-			return;
-		}
+		return skb_attempt_defer_free(skb);
 	}
 	__kfree_skb(skb);
 }
@@ -2453,7 +2434,6 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			__sk_flush_backlog(sk);
 		} else {
 			tcp_cleanup_rbuf(sk, copied);
-			sk_defer_free_flush(sk);
 			sk_wait_data(sk, &timeo, last);
 		}
 
@@ -2571,7 +2551,6 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 	lock_sock(sk);
 	ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags);
 	release_sock(sk);
-	sk_defer_free_flush(sk);
 
 	if (cmsg_flags && ret >= 0) {
 		if (cmsg_flags & TCP_CMSG_TS)
@@ -3096,7 +3075,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 		sk->sk_frag.page = NULL;
 		sk->sk_frag.offset = 0;
 	}
-	sk_defer_free_flush(sk);
 	sk_error_report(sk);
 	return 0;
 }
@@ -4225,7 +4203,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
 							  &zc, &len, err);
 		release_sock(sk);
-		sk_defer_free_flush(sk);
 		if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags))
 			goto zerocopy_rcv_cmsg;
 		switch (len) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2c2d42142555..918816ec5dd4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2065,7 +2065,6 @@ process:
 
 	sk_incoming_cpu_update(sk);
 
-	sk_defer_free_flush(sk);
 	bh_lock_sock_nested(sk);
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 54277de7474b..60bdec257ba7 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1728,7 +1728,6 @@ process:
 
 	sk_incoming_cpu_update(sk);
 
-	sk_defer_free_flush(sk);
 	bh_lock_sock_nested(sk);
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index ddbe05ec5489..bc54f6c5b1a4 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1911,7 +1911,6 @@ recv_end:
 
 end:
 	release_sock(sk);
-	sk_defer_free_flush(sk);
 	if (psock)
 		sk_psock_put(sk, psock);
 	return copied ? : err;
@@ -1983,7 +1982,6 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 
 splice_read_end:
 	release_sock(sk);
-	sk_defer_free_flush(sk);
 	return copied ? : err;
 }
 
-- 
cgit v1.2.3


From 6423d2951087231706246f81851067f7f0593d4a Mon Sep 17 00:00:00 2001
From: Won Chung <wonchung@google.com>
Date: Mon, 14 Mar 2022 19:54:58 +0000
Subject: driver core: Add sysfs support for physical location of a device

When ACPI table includes _PLD fields for a device, create a new
directory (physical_location) in sysfs to share _PLD fields.

Currently without PLD information, when there are multiple of same
devices, it is hard to distinguish which device corresponds to which
physical device at which location. For example, when there are two Type
C connectors, it is hard to find out which connector corresponds to the
Type C port on the left panel versus the Type C port on the right panel.
With PLD information provided, we can determine which specific device at
which location is doing what.

_PLD output includes much more fields, but only generic fields are added
and exposed to sysfs, so that non-ACPI devices can also support it in
the future. The minimal generic fields needed for locating a device are
the following.
- panel
- vertical_position
- horizontal_position
- dock
- lid

Signed-off-by: Won Chung <wonchung@google.com>
Link: https://lore.kernel.org/r/20220314195458.271430-1-wonchung@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../ABI/testing/sysfs-devices-physical_location    |  42 +++++++
 drivers/base/Makefile                              |   1 +
 drivers/base/core.c                                |  15 +++
 drivers/base/physical_location.c                   | 137 +++++++++++++++++++++
 drivers/base/physical_location.h                   |  16 +++
 include/linux/device.h                             |  73 +++++++++++
 6 files changed, 284 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-devices-physical_location
 create mode 100644 drivers/base/physical_location.c
 create mode 100644 drivers/base/physical_location.h

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-devices-physical_location b/Documentation/ABI/testing/sysfs-devices-physical_location
new file mode 100644
index 000000000000..202324b87083
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-physical_location
@@ -0,0 +1,42 @@
+What:		/sys/devices/.../physical_location
+Date:		March 2022
+Contact:	Won Chung <wonchung@google.com>
+Description:
+		This directory contains information on physical location of
+		the device connection point with respect to the system's
+		housing.
+
+What:		/sys/devices/.../physical_location/panel
+Date:		March 2022
+Contact:	Won Chung <wonchung@google.com>
+Description:
+		Describes which panel surface of the system’s housing the
+		device connection point resides on.
+
+What:		/sys/devices/.../physical_location/vertical_position
+Date:		March 2022
+Contact:	Won Chung <wonchung@google.com>
+Description:
+		Describes vertical position of the device connection point on
+		the panel surface.
+
+What:		/sys/devices/.../physical_location/horizontal_position
+Date:		March 2022
+Contact:	Won Chung <wonchung@google.com>
+Description:
+		Describes horizontal position of the device connection point on
+		the panel surface.
+
+What:		/sys/devices/.../physical_location/dock
+Date:		March 2022
+Contact:	Won Chung <wonchung@google.com>
+Description:
+		"Yes" if the device connection point resides in a docking
+		station or a port replicator. "No" otherwise.
+
+What:		/sys/devices/.../physical_location/lid
+Date:		March 2022
+Contact:	Won Chung <wonchung@google.com>
+Description:
+		"Yes" if the device connection point resides on the lid of
+		laptop system. "No" otherwise.
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 02f7f1358e86..83217d243c25 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o
 obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o
 obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += arch_topology.o
 obj-$(CONFIG_GENERIC_ARCH_NUMA) += arch_numa.o
+obj-$(CONFIG_ACPI) += physical_location.o
 
 obj-y			+= test/
 
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 3d6430eb0c6a..50f9aa3fb92b 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -32,6 +32,7 @@
 #include <linux/dma-map-ops.h> /* for dma_default_coherent */
 
 #include "base.h"
+#include "physical_location.h"
 #include "power/power.h"
 
 #ifdef CONFIG_SYSFS_DEPRECATED
@@ -2649,8 +2650,17 @@ static int device_add_attrs(struct device *dev)
 			goto err_remove_dev_waiting_for_supplier;
 	}
 
+	if (dev_add_physical_location(dev)) {
+		error = device_add_group(dev,
+			&dev_attr_physical_location_group);
+		if (error)
+			goto err_remove_dev_removable;
+	}
+
 	return 0;
 
+ err_remove_dev_removable:
+	device_remove_file(dev, &dev_attr_removable);
  err_remove_dev_waiting_for_supplier:
 	device_remove_file(dev, &dev_attr_waiting_for_supplier);
  err_remove_dev_online:
@@ -2672,6 +2682,11 @@ static void device_remove_attrs(struct device *dev)
 	struct class *class = dev->class;
 	const struct device_type *type = dev->type;
 
+	if (dev->physical_location) {
+		device_remove_group(dev, &dev_attr_physical_location_group);
+		kfree(dev->physical_location);
+	}
+
 	device_remove_file(dev, &dev_attr_removable);
 	device_remove_file(dev, &dev_attr_waiting_for_supplier);
 	device_remove_file(dev, &dev_attr_online);
diff --git a/drivers/base/physical_location.c b/drivers/base/physical_location.c
new file mode 100644
index 000000000000..4c1a52ecd7f6
--- /dev/null
+++ b/drivers/base/physical_location.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Device physical location support
+ *
+ * Author: Won Chung <wonchung@google.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/sysfs.h>
+
+#include "physical_location.h"
+
+bool dev_add_physical_location(struct device *dev)
+{
+	struct acpi_pld_info *pld;
+	acpi_status status;
+
+	if (!has_acpi_companion(dev))
+		return false;
+
+	status = acpi_get_physical_device_location(ACPI_HANDLE(dev), &pld);
+	if (ACPI_FAILURE(status))
+		return false;
+
+	dev->physical_location =
+		kzalloc(sizeof(*dev->physical_location), GFP_KERNEL);
+	dev->physical_location->panel = pld->panel;
+	dev->physical_location->vertical_position = pld->vertical_position;
+	dev->physical_location->horizontal_position = pld->horizontal_position;
+	dev->physical_location->dock = pld->dock;
+	dev->physical_location->lid = pld->lid;
+
+	return true;
+}
+
+static ssize_t panel_show(struct device *dev, struct device_attribute *attr,
+	char *buf)
+{
+	const char *panel;
+
+	switch (dev->physical_location->panel) {
+	case DEVICE_PANEL_TOP:
+		panel = "top";
+		break;
+	case DEVICE_PANEL_BOTTOM:
+		panel = "bottom";
+		break;
+	case DEVICE_PANEL_LEFT:
+		panel = "left";
+		break;
+	case DEVICE_PANEL_RIGHT:
+		panel = "right";
+		break;
+	case DEVICE_PANEL_FRONT:
+		panel = "front";
+		break;
+	default:
+		panel = "unknown";
+	}
+	return sysfs_emit(buf, "%s\n", panel);
+}
+static DEVICE_ATTR_RO(panel);
+
+static ssize_t vertical_position_show(struct device *dev,
+	struct device_attribute *attr, char *buf)
+{
+	const char *vertical_position;
+
+	switch (dev->physical_location->vertical_position) {
+	case DEVICE_VERT_POS_UPPER:
+		vertical_position = "upper";
+		break;
+	case DEVICE_VERT_POS_CENTER:
+		vertical_position = "center";
+		break;
+	case DEVICE_VERT_POS_LOWER:
+		vertical_position = "lower";
+		break;
+	default:
+		vertical_position = "unknown";
+	}
+	return sysfs_emit(buf, "%s\n", vertical_position);
+}
+static DEVICE_ATTR_RO(vertical_position);
+
+static ssize_t horizontal_position_show(struct device *dev,
+	struct device_attribute *attr, char *buf)
+{
+	const char *horizontal_position;
+
+	switch (dev->physical_location->horizontal_position) {
+	case DEVICE_HORI_POS_LEFT:
+		horizontal_position = "left";
+		break;
+	case DEVICE_HORI_POS_CENTER:
+		horizontal_position = "center";
+		break;
+	case DEVICE_HORI_POS_RIGHT:
+		horizontal_position = "right";
+		break;
+	default:
+		horizontal_position = "unknown";
+	}
+	return sysfs_emit(buf, "%s\n", horizontal_position);
+}
+static DEVICE_ATTR_RO(horizontal_position);
+
+static ssize_t dock_show(struct device *dev, struct device_attribute *attr,
+	char *buf)
+{
+	return sysfs_emit(buf, "%s\n",
+		dev->physical_location->dock ? "yes" : "no");
+}
+static DEVICE_ATTR_RO(dock);
+
+static ssize_t lid_show(struct device *dev, struct device_attribute *attr,
+	char *buf)
+{
+	return sysfs_emit(buf, "%s\n",
+		dev->physical_location->lid ? "yes" : "no");
+}
+static DEVICE_ATTR_RO(lid);
+
+static struct attribute *dev_attr_physical_location[] = {
+	&dev_attr_panel.attr,
+	&dev_attr_vertical_position.attr,
+	&dev_attr_horizontal_position.attr,
+	&dev_attr_dock.attr,
+	&dev_attr_lid.attr,
+	NULL,
+};
+
+const struct attribute_group dev_attr_physical_location_group = {
+	.name = "physical_location",
+	.attrs = dev_attr_physical_location,
+};
+
diff --git a/drivers/base/physical_location.h b/drivers/base/physical_location.h
new file mode 100644
index 000000000000..82cde9f1b161
--- /dev/null
+++ b/drivers/base/physical_location.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Device physical location support
+ *
+ * Author: Won Chung <wonchung@google.com>
+ */
+
+#include <linux/device.h>
+
+#ifdef CONFIG_ACPI
+extern bool dev_add_physical_location(struct device *dev);
+extern const struct attribute_group dev_attr_physical_location_group;
+#else
+static inline bool dev_add_physical_location(struct device *dev) { return false; };
+static const struct attribute_group dev_attr_physical_location_group = {};
+#endif
diff --git a/include/linux/device.h b/include/linux/device.h
index 93459724dcde..766fbea6ca83 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -386,6 +386,75 @@ struct dev_msi_info {
 #endif
 };
 
+/**
+ * enum device_physical_location_panel - Describes which panel surface of the
+ * system's housing the device connection point resides on.
+ * @DEVICE_PANEL_TOP: Device connection point is on the top panel.
+ * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel.
+ * @DEVICE_PANEL_LEFT: Device connection point is on the left panel.
+ * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel.
+ * @DEVICE_PANEL_FRONT: Device connection point is on the front panel.
+ * @DEVICE_PANEL_BACK: Device connection point is on the back panel.
+ * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown.
+ */
+enum device_physical_location_panel {
+	DEVICE_PANEL_TOP,
+	DEVICE_PANEL_BOTTOM,
+	DEVICE_PANEL_LEFT,
+	DEVICE_PANEL_RIGHT,
+	DEVICE_PANEL_FRONT,
+	DEVICE_PANEL_BACK,
+	DEVICE_PANEL_UNKNOWN,
+};
+
+/**
+ * enum device_physical_location_vertical_position - Describes vertical
+ * position of the device connection point on the panel surface.
+ * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel.
+ * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel.
+ * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel.
+ */
+enum device_physical_location_vertical_position {
+	DEVICE_VERT_POS_UPPER,
+	DEVICE_VERT_POS_CENTER,
+	DEVICE_VERT_POS_LOWER,
+};
+
+/**
+ * enum device_physical_location_horizontal_position - Describes horizontal
+ * position of the device connection point on the panel surface.
+ * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel.
+ * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel.
+ * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel.
+ */
+enum device_physical_location_horizontal_position {
+	DEVICE_HORI_POS_LEFT,
+	DEVICE_HORI_POS_CENTER,
+	DEVICE_HORI_POS_RIGHT,
+};
+
+/**
+ * struct device_physical_location - Device data related to physical location
+ * of the device connection point.
+ * @panel: Panel surface of the system's housing that the device connection
+ *         point resides on.
+ * @vertical_position: Vertical position of the device connection point within
+ *                     the panel.
+ * @horizontal_position: Horizontal position of the device connection point
+ *                       within the panel.
+ * @dock: Set if the device connection point resides in a docking station or
+ *        port replicator.
+ * @lid: Set if this device connection point resides on the lid of laptop
+ *       system.
+ */
+struct device_physical_location {
+	enum device_physical_location_panel panel;
+	enum device_physical_location_vertical_position vertical_position;
+	enum device_physical_location_horizontal_position horizontal_position;
+	bool dock;
+	bool lid;
+};
+
 /**
  * struct device - The basic device structure
  * @parent:	The device's "parent" device, the device to which it is attached.
@@ -453,6 +522,8 @@ struct dev_msi_info {
  * 		device (i.e. the bus driver that discovered the device).
  * @iommu_group: IOMMU group the device belongs to.
  * @iommu:	Per device generic IOMMU runtime data
+ * @physical_location: Describes physical location of the device connection
+ *		point in the system housing.
  * @removable:  Whether the device can be removed from the system. This
  *              should be set by the subsystem / bus driver that discovered
  *              the device.
@@ -567,6 +638,8 @@ struct device {
 	struct iommu_group	*iommu_group;
 	struct dev_iommu	*iommu;
 
+	struct device_physical_location *physical_location;
+
 	enum device_removable	removable;
 
 	bool			offline_disabled:1;
-- 
cgit v1.2.3


From b041b525dab95352fbd666b14dc73ab898df465f Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Thu, 10 Mar 2022 12:48:53 -0800
Subject: x86/split_lock: Make life miserable for split lockers

In https://lore.kernel.org/all/87y22uujkm.ffs@tglx/ Thomas
said:

  Its's simply wishful thinking that stuff gets fixed because of a
  WARN_ONCE(). This has never worked. The only thing which works is to
  make stuff fail hard or slow it down in a way which makes it annoying
  enough to users to complain.

He was talking about WBINVD. But it made me think about how we use the
split lock detection feature in Linux.

Existing code has three options for applications:

 1) Don't enable split lock detection (allow arbitrary split locks)
 2) Warn once when a process uses split lock, but let the process
    keep running with split lock detection disabled
 3) Kill process that use split locks

Option 2 falls into the "wishful thinking" territory that Thomas warns does
nothing. But option 3 might not be viable in a situation with legacy
applications that need to run.

Hence make option 2 much stricter to "slow it down in a way which makes
it annoying".

Primary reason for this change is to provide better quality of service to
the rest of the applications running on the system. Internal testing shows
that even with many processes splitting locks, performance for the rest of
the system is much more responsive.

The new "warn" mode operates like this.  When an application tries to
execute a bus lock the #AC handler.

 1) Delays (interruptibly) 10 ms before moving to next step.

 2) Blocks (interruptibly) until it can get the semaphore
	If interrupted, just return. Assume the signal will either
	kill the task, or direct execution away from the instruction
	that is trying to get the bus lock.
 3) Disables split lock detection for the current core
 4) Schedules a work queue to re-enable split lock detect in 2 jiffies
 5) Returns

The work queue that re-enables split lock detection also releases the
semaphore.

There is a corner case where a CPU may be taken offline while split lock
detection is disabled. A CPU hotplug handler handles this case.

Old behaviour was to only print the split lock warning on the first
occurrence of a split lock from a task. Preserve that by adding a flag to
the task structure that suppresses subsequent split lock messages from that
task.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20220310204854.31752-2-tony.luck@intel.com
---
 arch/x86/kernel/cpu/intel.c | 63 ++++++++++++++++++++++++++++++++++++++-------
 include/linux/sched.h       |  3 +++
 kernel/fork.c               |  5 ++++
 3 files changed, 61 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f7a5370a9b3b..be2a0bdb9527 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -7,10 +7,13 @@
 #include <linux/smp.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/semaphore.h>
 #include <linux/thread_info.h>
 #include <linux/init.h>
 #include <linux/uaccess.h>
+#include <linux/workqueue.h>
 #include <linux/delay.h>
+#include <linux/cpuhotplug.h>
 
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
@@ -999,6 +1002,8 @@ static const struct {
 
 static struct ratelimit_state bld_ratelimit;
 
+static DEFINE_SEMAPHORE(buslock_sem);
+
 static inline bool match_option(const char *arg, int arglen, const char *opt)
 {
 	int len = strlen(opt), ratelimit;
@@ -1109,18 +1114,52 @@ static void split_lock_init(void)
 		split_lock_verify_msr(sld_state != sld_off);
 }
 
+static void __split_lock_reenable(struct work_struct *work)
+{
+	sld_update_msr(true);
+	up(&buslock_sem);
+}
+
+/*
+ * If a CPU goes offline with pending delayed work to re-enable split lock
+ * detection then the delayed work will be executed on some other CPU. That
+ * handles releasing the buslock_sem, but because it executes on a
+ * different CPU probably won't re-enable split lock detection. This is a
+ * problem on HT systems since the sibling CPU on the same core may then be
+ * left running with split lock detection disabled.
+ *
+ * Unconditionally re-enable detection here.
+ */
+static int splitlock_cpu_offline(unsigned int cpu)
+{
+	sld_update_msr(true);
+
+	return 0;
+}
+
+static DECLARE_DELAYED_WORK(split_lock_reenable, __split_lock_reenable);
+
 static void split_lock_warn(unsigned long ip)
 {
-	pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n",
-			    current->comm, current->pid, ip);
+	int cpu;
 
-	/*
-	 * Disable the split lock detection for this task so it can make
-	 * progress and set TIF_SLD so the detection is re-enabled via
-	 * switch_to_sld() when the task is scheduled out.
-	 */
+	if (!current->reported_split_lock)
+		pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n",
+				    current->comm, current->pid, ip);
+	current->reported_split_lock = 1;
+
+	/* misery factor #1, sleep 10ms before trying to execute split lock */
+	if (msleep_interruptible(10) > 0)
+		return;
+	/* Misery factor #2, only allow one buslocked disabled core at a time */
+	if (down_interruptible(&buslock_sem) == -EINTR)
+		return;
+	cpu = get_cpu();
+	schedule_delayed_work_on(cpu, &split_lock_reenable, 2);
+
+	/* Disable split lock detection on this CPU to make progress */
 	sld_update_msr(false);
-	set_tsk_thread_flag(current, TIF_SLD);
+	put_cpu();
 }
 
 bool handle_guest_split_lock(unsigned long ip)
@@ -1274,10 +1313,14 @@ static void sld_state_show(void)
 		pr_info("disabled\n");
 		break;
 	case sld_warn:
-		if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT))
+		if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) {
 			pr_info("#AC: crashing the kernel on kernel split_locks and warning on user-space split_locks\n");
-		else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
+			if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+					      "x86/splitlock", NULL, splitlock_cpu_offline) < 0)
+				pr_warn("No splitlock CPU offline handler\n");
+		} else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) {
 			pr_info("#DB: warning on user-space bus_locks\n");
+		}
 		break;
 	case sld_fatal:
 		if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a8911b1f35aa..23e03c7824c4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -941,6 +941,9 @@ struct task_struct {
 #ifdef CONFIG_IOMMU_SVA
 	unsigned			pasid_activated:1;
 #endif
+#ifdef	CONFIG_CPU_SUP_INTEL
+	unsigned			reported_split_lock:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 9796897560ab..f39795f372c2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1045,6 +1045,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #ifdef CONFIG_MEMCG
 	tsk->active_memcg = NULL;
 #endif
+
+#ifdef CONFIG_CPU_SUP_INTEL
+	tsk->reported_split_lock = 0;
+#endif
+
 	return tsk;
 
 free_stack:
-- 
cgit v1.2.3


From 4fd62f15afa0d0da4823f429a2fb4c3492a84edf Mon Sep 17 00:00:00 2001
From: Chuanhong Guo <gch981213@gmail.com>
Date: Sun, 24 Apr 2022 11:25:23 +0800
Subject: mtd: nand: make mtk_ecc.c a separated module

this code will be used in mediatek snfi spi-mem controller with
pipelined ECC engine.

Signed-off-by: Chuanhong Guo <gch981213@gmail.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20220424032527.673605-2-gch981213@gmail.com
---
 drivers/mtd/nand/Kconfig         |   7 +
 drivers/mtd/nand/Makefile        |   1 +
 drivers/mtd/nand/ecc-mtk.c       | 592 ++++++++++++++++++++++++++++++++++++++
 drivers/mtd/nand/raw/Kconfig     |   1 +
 drivers/mtd/nand/raw/Makefile    |   2 +-
 drivers/mtd/nand/raw/mtk_ecc.c   | 593 ---------------------------------------
 drivers/mtd/nand/raw/mtk_ecc.h   |  47 ----
 drivers/mtd/nand/raw/mtk_nand.c  |   2 +-
 include/linux/mtd/nand-ecc-mtk.h |  47 ++++
 9 files changed, 650 insertions(+), 642 deletions(-)
 create mode 100644 drivers/mtd/nand/ecc-mtk.c
 delete mode 100644 drivers/mtd/nand/raw/mtk_ecc.c
 delete mode 100644 drivers/mtd/nand/raw/mtk_ecc.h
 create mode 100644 include/linux/mtd/nand-ecc-mtk.h

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 9b249826ef93..2f3e02ab72ed 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -53,6 +53,13 @@ config MTD_NAND_ECC_MXIC
 	help
 	  This enables support for the hardware ECC engine from Macronix.
 
+config MTD_NAND_ECC_MEDIATEK
+	tristate "Mediatek hardware ECC engine"
+	depends on HAS_IOMEM
+	select MTD_NAND_ECC
+	help
+	  This enables support for the hardware ECC engine from Mediatek.
+
 endmenu
 
 endmenu
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index a4e6b7ae0614..19e1291ac4d5 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -2,6 +2,7 @@
 
 nandcore-objs := core.o bbt.o
 obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o
+obj-$(CONFIG_MTD_NAND_ECC_MEDIATEK) += ecc-mtk.o
 
 obj-y	+= onenand/
 obj-y	+= raw/
diff --git a/drivers/mtd/nand/ecc-mtk.c b/drivers/mtd/nand/ecc-mtk.c
new file mode 100644
index 000000000000..491c2d66f815
--- /dev/null
+++ b/drivers/mtd/nand/ecc-mtk.c
@@ -0,0 +1,592 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * MTK ECC controller driver.
+ * Copyright (C) 2016  MediaTek Inc.
+ * Authors:	Xiaolei Li		<xiaolei.li@mediatek.com>
+ *		Jorge Ramirez-Ortiz	<jorge.ramirez-ortiz@linaro.org>
+ */
+
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/iopoll.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/mutex.h>
+#include <linux/mtd/nand-ecc-mtk.h>
+
+#define ECC_IDLE_MASK		BIT(0)
+#define ECC_IRQ_EN		BIT(0)
+#define ECC_PG_IRQ_SEL		BIT(1)
+#define ECC_OP_ENABLE		(1)
+#define ECC_OP_DISABLE		(0)
+
+#define ECC_ENCCON		(0x00)
+#define ECC_ENCCNFG		(0x04)
+#define		ECC_MS_SHIFT		(16)
+#define ECC_ENCDIADDR		(0x08)
+#define ECC_ENCIDLE		(0x0C)
+#define ECC_DECCON		(0x100)
+#define ECC_DECCNFG		(0x104)
+#define		DEC_EMPTY_EN		BIT(31)
+#define		DEC_CNFG_CORRECT	(0x3 << 12)
+#define ECC_DECIDLE		(0x10C)
+#define ECC_DECENUM0		(0x114)
+
+#define ECC_TIMEOUT		(500000)
+
+#define ECC_IDLE_REG(op)	((op) == ECC_ENCODE ? ECC_ENCIDLE : ECC_DECIDLE)
+#define ECC_CTL_REG(op)		((op) == ECC_ENCODE ? ECC_ENCCON : ECC_DECCON)
+
+struct mtk_ecc_caps {
+	u32 err_mask;
+	const u8 *ecc_strength;
+	const u32 *ecc_regs;
+	u8 num_ecc_strength;
+	u8 ecc_mode_shift;
+	u32 parity_bits;
+	int pg_irq_sel;
+};
+
+struct mtk_ecc {
+	struct device *dev;
+	const struct mtk_ecc_caps *caps;
+	void __iomem *regs;
+	struct clk *clk;
+
+	struct completion done;
+	struct mutex lock;
+	u32 sectors;
+
+	u8 *eccdata;
+};
+
+/* ecc strength that each IP supports */
+static const u8 ecc_strength_mt2701[] = {
+	4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36,
+	40, 44, 48, 52, 56, 60
+};
+
+static const u8 ecc_strength_mt2712[] = {
+	4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36,
+	40, 44, 48, 52, 56, 60, 68, 72, 80
+};
+
+static const u8 ecc_strength_mt7622[] = {
+	4, 6, 8, 10, 12, 14, 16
+};
+
+enum mtk_ecc_regs {
+	ECC_ENCPAR00,
+	ECC_ENCIRQ_EN,
+	ECC_ENCIRQ_STA,
+	ECC_DECDONE,
+	ECC_DECIRQ_EN,
+	ECC_DECIRQ_STA,
+};
+
+static int mt2701_ecc_regs[] = {
+	[ECC_ENCPAR00] =        0x10,
+	[ECC_ENCIRQ_EN] =       0x80,
+	[ECC_ENCIRQ_STA] =      0x84,
+	[ECC_DECDONE] =         0x124,
+	[ECC_DECIRQ_EN] =       0x200,
+	[ECC_DECIRQ_STA] =      0x204,
+};
+
+static int mt2712_ecc_regs[] = {
+	[ECC_ENCPAR00] =        0x300,
+	[ECC_ENCIRQ_EN] =       0x80,
+	[ECC_ENCIRQ_STA] =      0x84,
+	[ECC_DECDONE] =         0x124,
+	[ECC_DECIRQ_EN] =       0x200,
+	[ECC_DECIRQ_STA] =      0x204,
+};
+
+static int mt7622_ecc_regs[] = {
+	[ECC_ENCPAR00] =        0x10,
+	[ECC_ENCIRQ_EN] =       0x30,
+	[ECC_ENCIRQ_STA] =      0x34,
+	[ECC_DECDONE] =         0x11c,
+	[ECC_DECIRQ_EN] =       0x140,
+	[ECC_DECIRQ_STA] =      0x144,
+};
+
+static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc,
+				     enum mtk_ecc_operation op)
+{
+	struct device *dev = ecc->dev;
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout_atomic(ecc->regs + ECC_IDLE_REG(op), val,
+					val & ECC_IDLE_MASK,
+					10, ECC_TIMEOUT);
+	if (ret)
+		dev_warn(dev, "%s NOT idle\n",
+			 op == ECC_ENCODE ? "encoder" : "decoder");
+}
+
+static irqreturn_t mtk_ecc_irq(int irq, void *id)
+{
+	struct mtk_ecc *ecc = id;
+	u32 dec, enc;
+
+	dec = readw(ecc->regs + ecc->caps->ecc_regs[ECC_DECIRQ_STA])
+		    & ECC_IRQ_EN;
+	if (dec) {
+		dec = readw(ecc->regs + ecc->caps->ecc_regs[ECC_DECDONE]);
+		if (dec & ecc->sectors) {
+			/*
+			 * Clear decode IRQ status once again to ensure that
+			 * there will be no extra IRQ.
+			 */
+			readw(ecc->regs + ecc->caps->ecc_regs[ECC_DECIRQ_STA]);
+			ecc->sectors = 0;
+			complete(&ecc->done);
+		} else {
+			return IRQ_HANDLED;
+		}
+	} else {
+		enc = readl(ecc->regs + ecc->caps->ecc_regs[ECC_ENCIRQ_STA])
+		      & ECC_IRQ_EN;
+		if (enc)
+			complete(&ecc->done);
+		else
+			return IRQ_NONE;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
+{
+	u32 ecc_bit, dec_sz, enc_sz;
+	u32 reg, i;
+
+	for (i = 0; i < ecc->caps->num_ecc_strength; i++) {
+		if (ecc->caps->ecc_strength[i] == config->strength)
+			break;
+	}
+
+	if (i == ecc->caps->num_ecc_strength) {
+		dev_err(ecc->dev, "invalid ecc strength %d\n",
+			config->strength);
+		return -EINVAL;
+	}
+
+	ecc_bit = i;
+
+	if (config->op == ECC_ENCODE) {
+		/* configure ECC encoder (in bits) */
+		enc_sz = config->len << 3;
+
+		reg = ecc_bit | (config->mode << ecc->caps->ecc_mode_shift);
+		reg |= (enc_sz << ECC_MS_SHIFT);
+		writel(reg, ecc->regs + ECC_ENCCNFG);
+
+		if (config->mode != ECC_NFI_MODE)
+			writel(lower_32_bits(config->addr),
+			       ecc->regs + ECC_ENCDIADDR);
+
+	} else {
+		/* configure ECC decoder (in bits) */
+		dec_sz = (config->len << 3) +
+			 config->strength * ecc->caps->parity_bits;
+
+		reg = ecc_bit | (config->mode << ecc->caps->ecc_mode_shift);
+		reg |= (dec_sz << ECC_MS_SHIFT) | DEC_CNFG_CORRECT;
+		reg |= DEC_EMPTY_EN;
+		writel(reg, ecc->regs + ECC_DECCNFG);
+
+		if (config->sectors)
+			ecc->sectors = 1 << (config->sectors - 1);
+	}
+
+	return 0;
+}
+
+void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats,
+		       int sectors)
+{
+	u32 offset, i, err;
+	u32 bitflips = 0;
+
+	stats->corrected = 0;
+	stats->failed = 0;
+
+	for (i = 0; i < sectors; i++) {
+		offset = (i >> 2) << 2;
+		err = readl(ecc->regs + ECC_DECENUM0 + offset);
+		err = err >> ((i % 4) * 8);
+		err &= ecc->caps->err_mask;
+		if (err == ecc->caps->err_mask) {
+			/* uncorrectable errors */
+			stats->failed++;
+			continue;
+		}
+
+		stats->corrected += err;
+		bitflips = max_t(u32, bitflips, err);
+	}
+
+	stats->bitflips = bitflips;
+}
+EXPORT_SYMBOL(mtk_ecc_get_stats);
+
+void mtk_ecc_release(struct mtk_ecc *ecc)
+{
+	clk_disable_unprepare(ecc->clk);
+	put_device(ecc->dev);
+}
+EXPORT_SYMBOL(mtk_ecc_release);
+
+static void mtk_ecc_hw_init(struct mtk_ecc *ecc)
+{
+	mtk_ecc_wait_idle(ecc, ECC_ENCODE);
+	writew(ECC_OP_DISABLE, ecc->regs + ECC_ENCCON);
+
+	mtk_ecc_wait_idle(ecc, ECC_DECODE);
+	writel(ECC_OP_DISABLE, ecc->regs + ECC_DECCON);
+}
+
+static struct mtk_ecc *mtk_ecc_get(struct device_node *np)
+{
+	struct platform_device *pdev;
+	struct mtk_ecc *ecc;
+
+	pdev = of_find_device_by_node(np);
+	if (!pdev)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	ecc = platform_get_drvdata(pdev);
+	if (!ecc) {
+		put_device(&pdev->dev);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	clk_prepare_enable(ecc->clk);
+	mtk_ecc_hw_init(ecc);
+
+	return ecc;
+}
+
+struct mtk_ecc *of_mtk_ecc_get(struct device_node *of_node)
+{
+	struct mtk_ecc *ecc = NULL;
+	struct device_node *np;
+
+	np = of_parse_phandle(of_node, "ecc-engine", 0);
+	if (np) {
+		ecc = mtk_ecc_get(np);
+		of_node_put(np);
+	}
+
+	return ecc;
+}
+EXPORT_SYMBOL(of_mtk_ecc_get);
+
+int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
+{
+	enum mtk_ecc_operation op = config->op;
+	u16 reg_val;
+	int ret;
+
+	ret = mutex_lock_interruptible(&ecc->lock);
+	if (ret) {
+		dev_err(ecc->dev, "interrupted when attempting to lock\n");
+		return ret;
+	}
+
+	mtk_ecc_wait_idle(ecc, op);
+
+	ret = mtk_ecc_config(ecc, config);
+	if (ret) {
+		mutex_unlock(&ecc->lock);
+		return ret;
+	}
+
+	if (config->mode != ECC_NFI_MODE || op != ECC_ENCODE) {
+		init_completion(&ecc->done);
+		reg_val = ECC_IRQ_EN;
+		/*
+		 * For ECC_NFI_MODE, if ecc->caps->pg_irq_sel is 1, then it
+		 * means this chip can only generate one ecc irq during page
+		 * read / write. If is 0, generate one ecc irq each ecc step.
+		 */
+		if (ecc->caps->pg_irq_sel && config->mode == ECC_NFI_MODE)
+			reg_val |= ECC_PG_IRQ_SEL;
+		if (op == ECC_ENCODE)
+			writew(reg_val, ecc->regs +
+			       ecc->caps->ecc_regs[ECC_ENCIRQ_EN]);
+		else
+			writew(reg_val, ecc->regs +
+			       ecc->caps->ecc_regs[ECC_DECIRQ_EN]);
+	}
+
+	writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op));
+
+	return 0;
+}
+EXPORT_SYMBOL(mtk_ecc_enable);
+
+void mtk_ecc_disable(struct mtk_ecc *ecc)
+{
+	enum mtk_ecc_operation op = ECC_ENCODE;
+
+	/* find out the running operation */
+	if (readw(ecc->regs + ECC_CTL_REG(op)) != ECC_OP_ENABLE)
+		op = ECC_DECODE;
+
+	/* disable it */
+	mtk_ecc_wait_idle(ecc, op);
+	if (op == ECC_DECODE) {
+		/*
+		 * Clear decode IRQ status in case there is a timeout to wait
+		 * decode IRQ.
+		 */
+		readw(ecc->regs + ecc->caps->ecc_regs[ECC_DECDONE]);
+		writew(0, ecc->regs + ecc->caps->ecc_regs[ECC_DECIRQ_EN]);
+	} else {
+		writew(0, ecc->regs + ecc->caps->ecc_regs[ECC_ENCIRQ_EN]);
+	}
+
+	writew(ECC_OP_DISABLE, ecc->regs + ECC_CTL_REG(op));
+
+	mutex_unlock(&ecc->lock);
+}
+EXPORT_SYMBOL(mtk_ecc_disable);
+
+int mtk_ecc_wait_done(struct mtk_ecc *ecc, enum mtk_ecc_operation op)
+{
+	int ret;
+
+	ret = wait_for_completion_timeout(&ecc->done, msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ecc->dev, "%s timeout - interrupt did not arrive)\n",
+			(op == ECC_ENCODE) ? "encoder" : "decoder");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mtk_ecc_wait_done);
+
+int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config,
+		   u8 *data, u32 bytes)
+{
+	dma_addr_t addr;
+	u32 len;
+	int ret;
+
+	addr = dma_map_single(ecc->dev, data, bytes, DMA_TO_DEVICE);
+	ret = dma_mapping_error(ecc->dev, addr);
+	if (ret) {
+		dev_err(ecc->dev, "dma mapping error\n");
+		return -EINVAL;
+	}
+
+	config->op = ECC_ENCODE;
+	config->addr = addr;
+	ret = mtk_ecc_enable(ecc, config);
+	if (ret) {
+		dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
+		return ret;
+	}
+
+	ret = mtk_ecc_wait_done(ecc, ECC_ENCODE);
+	if (ret)
+		goto timeout;
+
+	mtk_ecc_wait_idle(ecc, ECC_ENCODE);
+
+	/* Program ECC bytes to OOB: per sector oob = FDM + ECC + SPARE */
+	len = (config->strength * ecc->caps->parity_bits + 7) >> 3;
+
+	/* write the parity bytes generated by the ECC back to temp buffer */
+	__ioread32_copy(ecc->eccdata,
+			ecc->regs + ecc->caps->ecc_regs[ECC_ENCPAR00],
+			round_up(len, 4));
+
+	/* copy into possibly unaligned OOB region with actual length */
+	memcpy(data + bytes, ecc->eccdata, len);
+timeout:
+
+	dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
+	mtk_ecc_disable(ecc);
+
+	return ret;
+}
+EXPORT_SYMBOL(mtk_ecc_encode);
+
+void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p)
+{
+	const u8 *ecc_strength = ecc->caps->ecc_strength;
+	int i;
+
+	for (i = 0; i < ecc->caps->num_ecc_strength; i++) {
+		if (*p <= ecc_strength[i]) {
+			if (!i)
+				*p = ecc_strength[i];
+			else if (*p != ecc_strength[i])
+				*p = ecc_strength[i - 1];
+			return;
+		}
+	}
+
+	*p = ecc_strength[ecc->caps->num_ecc_strength - 1];
+}
+EXPORT_SYMBOL(mtk_ecc_adjust_strength);
+
+unsigned int mtk_ecc_get_parity_bits(struct mtk_ecc *ecc)
+{
+	return ecc->caps->parity_bits;
+}
+EXPORT_SYMBOL(mtk_ecc_get_parity_bits);
+
+static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = {
+	.err_mask = 0x3f,
+	.ecc_strength = ecc_strength_mt2701,
+	.ecc_regs = mt2701_ecc_regs,
+	.num_ecc_strength = 20,
+	.ecc_mode_shift = 5,
+	.parity_bits = 14,
+	.pg_irq_sel = 0,
+};
+
+static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = {
+	.err_mask = 0x7f,
+	.ecc_strength = ecc_strength_mt2712,
+	.ecc_regs = mt2712_ecc_regs,
+	.num_ecc_strength = 23,
+	.ecc_mode_shift = 5,
+	.parity_bits = 14,
+	.pg_irq_sel = 1,
+};
+
+static const struct mtk_ecc_caps mtk_ecc_caps_mt7622 = {
+	.err_mask = 0x3f,
+	.ecc_strength = ecc_strength_mt7622,
+	.ecc_regs = mt7622_ecc_regs,
+	.num_ecc_strength = 7,
+	.ecc_mode_shift = 4,
+	.parity_bits = 13,
+	.pg_irq_sel = 0,
+};
+
+static const struct of_device_id mtk_ecc_dt_match[] = {
+	{
+		.compatible = "mediatek,mt2701-ecc",
+		.data = &mtk_ecc_caps_mt2701,
+	}, {
+		.compatible = "mediatek,mt2712-ecc",
+		.data = &mtk_ecc_caps_mt2712,
+	}, {
+		.compatible = "mediatek,mt7622-ecc",
+		.data = &mtk_ecc_caps_mt7622,
+	},
+	{},
+};
+
+static int mtk_ecc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mtk_ecc *ecc;
+	u32 max_eccdata_size;
+	int irq, ret;
+
+	ecc = devm_kzalloc(dev, sizeof(*ecc), GFP_KERNEL);
+	if (!ecc)
+		return -ENOMEM;
+
+	ecc->caps = of_device_get_match_data(dev);
+
+	max_eccdata_size = ecc->caps->num_ecc_strength - 1;
+	max_eccdata_size = ecc->caps->ecc_strength[max_eccdata_size];
+	max_eccdata_size = (max_eccdata_size * ecc->caps->parity_bits + 7) >> 3;
+	max_eccdata_size = round_up(max_eccdata_size, 4);
+	ecc->eccdata = devm_kzalloc(dev, max_eccdata_size, GFP_KERNEL);
+	if (!ecc->eccdata)
+		return -ENOMEM;
+
+	ecc->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ecc->regs))
+		return PTR_ERR(ecc->regs);
+
+	ecc->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(ecc->clk)) {
+		dev_err(dev, "failed to get clock: %ld\n", PTR_ERR(ecc->clk));
+		return PTR_ERR(ecc->clk);
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(dev, "failed to set DMA mask\n");
+		return ret;
+	}
+
+	ret = devm_request_irq(dev, irq, mtk_ecc_irq, 0x0, "mtk-ecc", ecc);
+	if (ret) {
+		dev_err(dev, "failed to request irq\n");
+		return -EINVAL;
+	}
+
+	ecc->dev = dev;
+	mutex_init(&ecc->lock);
+	platform_set_drvdata(pdev, ecc);
+	dev_info(dev, "probed\n");
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mtk_ecc_suspend(struct device *dev)
+{
+	struct mtk_ecc *ecc = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(ecc->clk);
+
+	return 0;
+}
+
+static int mtk_ecc_resume(struct device *dev)
+{
+	struct mtk_ecc *ecc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(ecc->clk);
+	if (ret) {
+		dev_err(dev, "failed to enable clk\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(mtk_ecc_pm_ops, mtk_ecc_suspend, mtk_ecc_resume);
+#endif
+
+MODULE_DEVICE_TABLE(of, mtk_ecc_dt_match);
+
+static struct platform_driver mtk_ecc_driver = {
+	.probe  = mtk_ecc_probe,
+	.driver = {
+		.name  = "mtk-ecc",
+		.of_match_table = mtk_ecc_dt_match,
+#ifdef CONFIG_PM_SLEEP
+		.pm = &mtk_ecc_pm_ops,
+#endif
+	},
+};
+
+module_platform_driver(mtk_ecc_driver);
+
+MODULE_AUTHOR("Xiaolei Li <xiaolei.li@mediatek.com>");
+MODULE_DESCRIPTION("MTK Nand ECC Driver");
+MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 9b078e78f3fa..8b6d7a515445 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -374,6 +374,7 @@ config MTD_NAND_QCOM
 
 config MTD_NAND_MTK
 	tristate "MTK NAND controller"
+	depends on MTD_NAND_ECC_MEDIATEK
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index 88a566513c56..fa1d00120310 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -48,7 +48,7 @@ obj-$(CONFIG_MTD_NAND_SUNXI)		+= sunxi_nand.o
 obj-$(CONFIG_MTD_NAND_HISI504)	        += hisi504_nand.o
 obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmnand/
 obj-$(CONFIG_MTD_NAND_QCOM)		+= qcom_nandc.o
-obj-$(CONFIG_MTD_NAND_MTK)		+= mtk_ecc.o mtk_nand.o
+obj-$(CONFIG_MTD_NAND_MTK)		+= mtk_nand.o
 obj-$(CONFIG_MTD_NAND_MXIC)		+= mxic_nand.o
 obj-$(CONFIG_MTD_NAND_TEGRA)		+= tegra_nand.o
 obj-$(CONFIG_MTD_NAND_STM32_FMC2)	+= stm32_fmc2_nand.o
diff --git a/drivers/mtd/nand/raw/mtk_ecc.c b/drivers/mtd/nand/raw/mtk_ecc.c
deleted file mode 100644
index e7df3dac705e..000000000000
--- a/drivers/mtd/nand/raw/mtk_ecc.c
+++ /dev/null
@@ -1,593 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
-/*
- * MTK ECC controller driver.
- * Copyright (C) 2016  MediaTek Inc.
- * Authors:	Xiaolei Li		<xiaolei.li@mediatek.com>
- *		Jorge Ramirez-Ortiz	<jorge.ramirez-ortiz@linaro.org>
- */
-
-#include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/interrupt.h>
-#include <linux/clk.h>
-#include <linux/module.h>
-#include <linux/iopoll.h>
-#include <linux/of.h>
-#include <linux/of_platform.h>
-#include <linux/mutex.h>
-
-#include "mtk_ecc.h"
-
-#define ECC_IDLE_MASK		BIT(0)
-#define ECC_IRQ_EN		BIT(0)
-#define ECC_PG_IRQ_SEL		BIT(1)
-#define ECC_OP_ENABLE		(1)
-#define ECC_OP_DISABLE		(0)
-
-#define ECC_ENCCON		(0x00)
-#define ECC_ENCCNFG		(0x04)
-#define		ECC_MS_SHIFT		(16)
-#define ECC_ENCDIADDR		(0x08)
-#define ECC_ENCIDLE		(0x0C)
-#define ECC_DECCON		(0x100)
-#define ECC_DECCNFG		(0x104)
-#define		DEC_EMPTY_EN		BIT(31)
-#define		DEC_CNFG_CORRECT	(0x3 << 12)
-#define ECC_DECIDLE		(0x10C)
-#define ECC_DECENUM0		(0x114)
-
-#define ECC_TIMEOUT		(500000)
-
-#define ECC_IDLE_REG(op)	((op) == ECC_ENCODE ? ECC_ENCIDLE : ECC_DECIDLE)
-#define ECC_CTL_REG(op)		((op) == ECC_ENCODE ? ECC_ENCCON : ECC_DECCON)
-
-struct mtk_ecc_caps {
-	u32 err_mask;
-	const u8 *ecc_strength;
-	const u32 *ecc_regs;
-	u8 num_ecc_strength;
-	u8 ecc_mode_shift;
-	u32 parity_bits;
-	int pg_irq_sel;
-};
-
-struct mtk_ecc {
-	struct device *dev;
-	const struct mtk_ecc_caps *caps;
-	void __iomem *regs;
-	struct clk *clk;
-
-	struct completion done;
-	struct mutex lock;
-	u32 sectors;
-
-	u8 *eccdata;
-};
-
-/* ecc strength that each IP supports */
-static const u8 ecc_strength_mt2701[] = {
-	4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36,
-	40, 44, 48, 52, 56, 60
-};
-
-static const u8 ecc_strength_mt2712[] = {
-	4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36,
-	40, 44, 48, 52, 56, 60, 68, 72, 80
-};
-
-static const u8 ecc_strength_mt7622[] = {
-	4, 6, 8, 10, 12, 14, 16
-};
-
-enum mtk_ecc_regs {
-	ECC_ENCPAR00,
-	ECC_ENCIRQ_EN,
-	ECC_ENCIRQ_STA,
-	ECC_DECDONE,
-	ECC_DECIRQ_EN,
-	ECC_DECIRQ_STA,
-};
-
-static int mt2701_ecc_regs[] = {
-	[ECC_ENCPAR00] =        0x10,
-	[ECC_ENCIRQ_EN] =       0x80,
-	[ECC_ENCIRQ_STA] =      0x84,
-	[ECC_DECDONE] =         0x124,
-	[ECC_DECIRQ_EN] =       0x200,
-	[ECC_DECIRQ_STA] =      0x204,
-};
-
-static int mt2712_ecc_regs[] = {
-	[ECC_ENCPAR00] =        0x300,
-	[ECC_ENCIRQ_EN] =       0x80,
-	[ECC_ENCIRQ_STA] =      0x84,
-	[ECC_DECDONE] =         0x124,
-	[ECC_DECIRQ_EN] =       0x200,
-	[ECC_DECIRQ_STA] =      0x204,
-};
-
-static int mt7622_ecc_regs[] = {
-	[ECC_ENCPAR00] =        0x10,
-	[ECC_ENCIRQ_EN] =       0x30,
-	[ECC_ENCIRQ_STA] =      0x34,
-	[ECC_DECDONE] =         0x11c,
-	[ECC_DECIRQ_EN] =       0x140,
-	[ECC_DECIRQ_STA] =      0x144,
-};
-
-static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc,
-				     enum mtk_ecc_operation op)
-{
-	struct device *dev = ecc->dev;
-	u32 val;
-	int ret;
-
-	ret = readl_poll_timeout_atomic(ecc->regs + ECC_IDLE_REG(op), val,
-					val & ECC_IDLE_MASK,
-					10, ECC_TIMEOUT);
-	if (ret)
-		dev_warn(dev, "%s NOT idle\n",
-			 op == ECC_ENCODE ? "encoder" : "decoder");
-}
-
-static irqreturn_t mtk_ecc_irq(int irq, void *id)
-{
-	struct mtk_ecc *ecc = id;
-	u32 dec, enc;
-
-	dec = readw(ecc->regs + ecc->caps->ecc_regs[ECC_DECIRQ_STA])
-		    & ECC_IRQ_EN;
-	if (dec) {
-		dec = readw(ecc->regs + ecc->caps->ecc_regs[ECC_DECDONE]);
-		if (dec & ecc->sectors) {
-			/*
-			 * Clear decode IRQ status once again to ensure that
-			 * there will be no extra IRQ.
-			 */
-			readw(ecc->regs + ecc->caps->ecc_regs[ECC_DECIRQ_STA]);
-			ecc->sectors = 0;
-			complete(&ecc->done);
-		} else {
-			return IRQ_HANDLED;
-		}
-	} else {
-		enc = readl(ecc->regs + ecc->caps->ecc_regs[ECC_ENCIRQ_STA])
-		      & ECC_IRQ_EN;
-		if (enc)
-			complete(&ecc->done);
-		else
-			return IRQ_NONE;
-	}
-
-	return IRQ_HANDLED;
-}
-
-static int mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
-{
-	u32 ecc_bit, dec_sz, enc_sz;
-	u32 reg, i;
-
-	for (i = 0; i < ecc->caps->num_ecc_strength; i++) {
-		if (ecc->caps->ecc_strength[i] == config->strength)
-			break;
-	}
-
-	if (i == ecc->caps->num_ecc_strength) {
-		dev_err(ecc->dev, "invalid ecc strength %d\n",
-			config->strength);
-		return -EINVAL;
-	}
-
-	ecc_bit = i;
-
-	if (config->op == ECC_ENCODE) {
-		/* configure ECC encoder (in bits) */
-		enc_sz = config->len << 3;
-
-		reg = ecc_bit | (config->mode << ecc->caps->ecc_mode_shift);
-		reg |= (enc_sz << ECC_MS_SHIFT);
-		writel(reg, ecc->regs + ECC_ENCCNFG);
-
-		if (config->mode != ECC_NFI_MODE)
-			writel(lower_32_bits(config->addr),
-			       ecc->regs + ECC_ENCDIADDR);
-
-	} else {
-		/* configure ECC decoder (in bits) */
-		dec_sz = (config->len << 3) +
-			 config->strength * ecc->caps->parity_bits;
-
-		reg = ecc_bit | (config->mode << ecc->caps->ecc_mode_shift);
-		reg |= (dec_sz << ECC_MS_SHIFT) | DEC_CNFG_CORRECT;
-		reg |= DEC_EMPTY_EN;
-		writel(reg, ecc->regs + ECC_DECCNFG);
-
-		if (config->sectors)
-			ecc->sectors = 1 << (config->sectors - 1);
-	}
-
-	return 0;
-}
-
-void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats,
-		       int sectors)
-{
-	u32 offset, i, err;
-	u32 bitflips = 0;
-
-	stats->corrected = 0;
-	stats->failed = 0;
-
-	for (i = 0; i < sectors; i++) {
-		offset = (i >> 2) << 2;
-		err = readl(ecc->regs + ECC_DECENUM0 + offset);
-		err = err >> ((i % 4) * 8);
-		err &= ecc->caps->err_mask;
-		if (err == ecc->caps->err_mask) {
-			/* uncorrectable errors */
-			stats->failed++;
-			continue;
-		}
-
-		stats->corrected += err;
-		bitflips = max_t(u32, bitflips, err);
-	}
-
-	stats->bitflips = bitflips;
-}
-EXPORT_SYMBOL(mtk_ecc_get_stats);
-
-void mtk_ecc_release(struct mtk_ecc *ecc)
-{
-	clk_disable_unprepare(ecc->clk);
-	put_device(ecc->dev);
-}
-EXPORT_SYMBOL(mtk_ecc_release);
-
-static void mtk_ecc_hw_init(struct mtk_ecc *ecc)
-{
-	mtk_ecc_wait_idle(ecc, ECC_ENCODE);
-	writew(ECC_OP_DISABLE, ecc->regs + ECC_ENCCON);
-
-	mtk_ecc_wait_idle(ecc, ECC_DECODE);
-	writel(ECC_OP_DISABLE, ecc->regs + ECC_DECCON);
-}
-
-static struct mtk_ecc *mtk_ecc_get(struct device_node *np)
-{
-	struct platform_device *pdev;
-	struct mtk_ecc *ecc;
-
-	pdev = of_find_device_by_node(np);
-	if (!pdev)
-		return ERR_PTR(-EPROBE_DEFER);
-
-	ecc = platform_get_drvdata(pdev);
-	if (!ecc) {
-		put_device(&pdev->dev);
-		return ERR_PTR(-EPROBE_DEFER);
-	}
-
-	clk_prepare_enable(ecc->clk);
-	mtk_ecc_hw_init(ecc);
-
-	return ecc;
-}
-
-struct mtk_ecc *of_mtk_ecc_get(struct device_node *of_node)
-{
-	struct mtk_ecc *ecc = NULL;
-	struct device_node *np;
-
-	np = of_parse_phandle(of_node, "ecc-engine", 0);
-	if (np) {
-		ecc = mtk_ecc_get(np);
-		of_node_put(np);
-	}
-
-	return ecc;
-}
-EXPORT_SYMBOL(of_mtk_ecc_get);
-
-int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
-{
-	enum mtk_ecc_operation op = config->op;
-	u16 reg_val;
-	int ret;
-
-	ret = mutex_lock_interruptible(&ecc->lock);
-	if (ret) {
-		dev_err(ecc->dev, "interrupted when attempting to lock\n");
-		return ret;
-	}
-
-	mtk_ecc_wait_idle(ecc, op);
-
-	ret = mtk_ecc_config(ecc, config);
-	if (ret) {
-		mutex_unlock(&ecc->lock);
-		return ret;
-	}
-
-	if (config->mode != ECC_NFI_MODE || op != ECC_ENCODE) {
-		init_completion(&ecc->done);
-		reg_val = ECC_IRQ_EN;
-		/*
-		 * For ECC_NFI_MODE, if ecc->caps->pg_irq_sel is 1, then it
-		 * means this chip can only generate one ecc irq during page
-		 * read / write. If is 0, generate one ecc irq each ecc step.
-		 */
-		if (ecc->caps->pg_irq_sel && config->mode == ECC_NFI_MODE)
-			reg_val |= ECC_PG_IRQ_SEL;
-		if (op == ECC_ENCODE)
-			writew(reg_val, ecc->regs +
-			       ecc->caps->ecc_regs[ECC_ENCIRQ_EN]);
-		else
-			writew(reg_val, ecc->regs +
-			       ecc->caps->ecc_regs[ECC_DECIRQ_EN]);
-	}
-
-	writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op));
-
-	return 0;
-}
-EXPORT_SYMBOL(mtk_ecc_enable);
-
-void mtk_ecc_disable(struct mtk_ecc *ecc)
-{
-	enum mtk_ecc_operation op = ECC_ENCODE;
-
-	/* find out the running operation */
-	if (readw(ecc->regs + ECC_CTL_REG(op)) != ECC_OP_ENABLE)
-		op = ECC_DECODE;
-
-	/* disable it */
-	mtk_ecc_wait_idle(ecc, op);
-	if (op == ECC_DECODE) {
-		/*
-		 * Clear decode IRQ status in case there is a timeout to wait
-		 * decode IRQ.
-		 */
-		readw(ecc->regs + ecc->caps->ecc_regs[ECC_DECDONE]);
-		writew(0, ecc->regs + ecc->caps->ecc_regs[ECC_DECIRQ_EN]);
-	} else {
-		writew(0, ecc->regs + ecc->caps->ecc_regs[ECC_ENCIRQ_EN]);
-	}
-
-	writew(ECC_OP_DISABLE, ecc->regs + ECC_CTL_REG(op));
-
-	mutex_unlock(&ecc->lock);
-}
-EXPORT_SYMBOL(mtk_ecc_disable);
-
-int mtk_ecc_wait_done(struct mtk_ecc *ecc, enum mtk_ecc_operation op)
-{
-	int ret;
-
-	ret = wait_for_completion_timeout(&ecc->done, msecs_to_jiffies(500));
-	if (!ret) {
-		dev_err(ecc->dev, "%s timeout - interrupt did not arrive)\n",
-			(op == ECC_ENCODE) ? "encoder" : "decoder");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(mtk_ecc_wait_done);
-
-int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config,
-		   u8 *data, u32 bytes)
-{
-	dma_addr_t addr;
-	u32 len;
-	int ret;
-
-	addr = dma_map_single(ecc->dev, data, bytes, DMA_TO_DEVICE);
-	ret = dma_mapping_error(ecc->dev, addr);
-	if (ret) {
-		dev_err(ecc->dev, "dma mapping error\n");
-		return -EINVAL;
-	}
-
-	config->op = ECC_ENCODE;
-	config->addr = addr;
-	ret = mtk_ecc_enable(ecc, config);
-	if (ret) {
-		dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
-		return ret;
-	}
-
-	ret = mtk_ecc_wait_done(ecc, ECC_ENCODE);
-	if (ret)
-		goto timeout;
-
-	mtk_ecc_wait_idle(ecc, ECC_ENCODE);
-
-	/* Program ECC bytes to OOB: per sector oob = FDM + ECC + SPARE */
-	len = (config->strength * ecc->caps->parity_bits + 7) >> 3;
-
-	/* write the parity bytes generated by the ECC back to temp buffer */
-	__ioread32_copy(ecc->eccdata,
-			ecc->regs + ecc->caps->ecc_regs[ECC_ENCPAR00],
-			round_up(len, 4));
-
-	/* copy into possibly unaligned OOB region with actual length */
-	memcpy(data + bytes, ecc->eccdata, len);
-timeout:
-
-	dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
-	mtk_ecc_disable(ecc);
-
-	return ret;
-}
-EXPORT_SYMBOL(mtk_ecc_encode);
-
-void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p)
-{
-	const u8 *ecc_strength = ecc->caps->ecc_strength;
-	int i;
-
-	for (i = 0; i < ecc->caps->num_ecc_strength; i++) {
-		if (*p <= ecc_strength[i]) {
-			if (!i)
-				*p = ecc_strength[i];
-			else if (*p != ecc_strength[i])
-				*p = ecc_strength[i - 1];
-			return;
-		}
-	}
-
-	*p = ecc_strength[ecc->caps->num_ecc_strength - 1];
-}
-EXPORT_SYMBOL(mtk_ecc_adjust_strength);
-
-unsigned int mtk_ecc_get_parity_bits(struct mtk_ecc *ecc)
-{
-	return ecc->caps->parity_bits;
-}
-EXPORT_SYMBOL(mtk_ecc_get_parity_bits);
-
-static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = {
-	.err_mask = 0x3f,
-	.ecc_strength = ecc_strength_mt2701,
-	.ecc_regs = mt2701_ecc_regs,
-	.num_ecc_strength = 20,
-	.ecc_mode_shift = 5,
-	.parity_bits = 14,
-	.pg_irq_sel = 0,
-};
-
-static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = {
-	.err_mask = 0x7f,
-	.ecc_strength = ecc_strength_mt2712,
-	.ecc_regs = mt2712_ecc_regs,
-	.num_ecc_strength = 23,
-	.ecc_mode_shift = 5,
-	.parity_bits = 14,
-	.pg_irq_sel = 1,
-};
-
-static const struct mtk_ecc_caps mtk_ecc_caps_mt7622 = {
-	.err_mask = 0x3f,
-	.ecc_strength = ecc_strength_mt7622,
-	.ecc_regs = mt7622_ecc_regs,
-	.num_ecc_strength = 7,
-	.ecc_mode_shift = 4,
-	.parity_bits = 13,
-	.pg_irq_sel = 0,
-};
-
-static const struct of_device_id mtk_ecc_dt_match[] = {
-	{
-		.compatible = "mediatek,mt2701-ecc",
-		.data = &mtk_ecc_caps_mt2701,
-	}, {
-		.compatible = "mediatek,mt2712-ecc",
-		.data = &mtk_ecc_caps_mt2712,
-	}, {
-		.compatible = "mediatek,mt7622-ecc",
-		.data = &mtk_ecc_caps_mt7622,
-	},
-	{},
-};
-
-static int mtk_ecc_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct mtk_ecc *ecc;
-	u32 max_eccdata_size;
-	int irq, ret;
-
-	ecc = devm_kzalloc(dev, sizeof(*ecc), GFP_KERNEL);
-	if (!ecc)
-		return -ENOMEM;
-
-	ecc->caps = of_device_get_match_data(dev);
-
-	max_eccdata_size = ecc->caps->num_ecc_strength - 1;
-	max_eccdata_size = ecc->caps->ecc_strength[max_eccdata_size];
-	max_eccdata_size = (max_eccdata_size * ecc->caps->parity_bits + 7) >> 3;
-	max_eccdata_size = round_up(max_eccdata_size, 4);
-	ecc->eccdata = devm_kzalloc(dev, max_eccdata_size, GFP_KERNEL);
-	if (!ecc->eccdata)
-		return -ENOMEM;
-
-	ecc->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(ecc->regs))
-		return PTR_ERR(ecc->regs);
-
-	ecc->clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(ecc->clk)) {
-		dev_err(dev, "failed to get clock: %ld\n", PTR_ERR(ecc->clk));
-		return PTR_ERR(ecc->clk);
-	}
-
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
-
-	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
-	if (ret) {
-		dev_err(dev, "failed to set DMA mask\n");
-		return ret;
-	}
-
-	ret = devm_request_irq(dev, irq, mtk_ecc_irq, 0x0, "mtk-ecc", ecc);
-	if (ret) {
-		dev_err(dev, "failed to request irq\n");
-		return -EINVAL;
-	}
-
-	ecc->dev = dev;
-	mutex_init(&ecc->lock);
-	platform_set_drvdata(pdev, ecc);
-	dev_info(dev, "probed\n");
-
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int mtk_ecc_suspend(struct device *dev)
-{
-	struct mtk_ecc *ecc = dev_get_drvdata(dev);
-
-	clk_disable_unprepare(ecc->clk);
-
-	return 0;
-}
-
-static int mtk_ecc_resume(struct device *dev)
-{
-	struct mtk_ecc *ecc = dev_get_drvdata(dev);
-	int ret;
-
-	ret = clk_prepare_enable(ecc->clk);
-	if (ret) {
-		dev_err(dev, "failed to enable clk\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-static SIMPLE_DEV_PM_OPS(mtk_ecc_pm_ops, mtk_ecc_suspend, mtk_ecc_resume);
-#endif
-
-MODULE_DEVICE_TABLE(of, mtk_ecc_dt_match);
-
-static struct platform_driver mtk_ecc_driver = {
-	.probe  = mtk_ecc_probe,
-	.driver = {
-		.name  = "mtk-ecc",
-		.of_match_table = mtk_ecc_dt_match,
-#ifdef CONFIG_PM_SLEEP
-		.pm = &mtk_ecc_pm_ops,
-#endif
-	},
-};
-
-module_platform_driver(mtk_ecc_driver);
-
-MODULE_AUTHOR("Xiaolei Li <xiaolei.li@mediatek.com>");
-MODULE_DESCRIPTION("MTK Nand ECC Driver");
-MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/mtd/nand/raw/mtk_ecc.h b/drivers/mtd/nand/raw/mtk_ecc.h
deleted file mode 100644
index 0e48c36e6ca0..000000000000
--- a/drivers/mtd/nand/raw/mtk_ecc.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
-/*
- * MTK SDG1 ECC controller
- *
- * Copyright (c) 2016 Mediatek
- * Authors:	Xiaolei Li		<xiaolei.li@mediatek.com>
- *		Jorge Ramirez-Ortiz	<jorge.ramirez-ortiz@linaro.org>
- */
-
-#ifndef __DRIVERS_MTD_NAND_MTK_ECC_H__
-#define __DRIVERS_MTD_NAND_MTK_ECC_H__
-
-#include <linux/types.h>
-
-enum mtk_ecc_mode {ECC_DMA_MODE = 0, ECC_NFI_MODE = 1};
-enum mtk_ecc_operation {ECC_ENCODE, ECC_DECODE};
-
-struct device_node;
-struct mtk_ecc;
-
-struct mtk_ecc_stats {
-	u32 corrected;
-	u32 bitflips;
-	u32 failed;
-};
-
-struct mtk_ecc_config {
-	enum mtk_ecc_operation op;
-	enum mtk_ecc_mode mode;
-	dma_addr_t addr;
-	u32 strength;
-	u32 sectors;
-	u32 len;
-};
-
-int mtk_ecc_encode(struct mtk_ecc *, struct mtk_ecc_config *, u8 *, u32);
-void mtk_ecc_get_stats(struct mtk_ecc *, struct mtk_ecc_stats *, int);
-int mtk_ecc_wait_done(struct mtk_ecc *, enum mtk_ecc_operation);
-int mtk_ecc_enable(struct mtk_ecc *, struct mtk_ecc_config *);
-void mtk_ecc_disable(struct mtk_ecc *);
-void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p);
-unsigned int mtk_ecc_get_parity_bits(struct mtk_ecc *ecc);
-
-struct mtk_ecc *of_mtk_ecc_get(struct device_node *);
-void mtk_ecc_release(struct mtk_ecc *);
-
-#endif
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 66f04c693c87..d540454cbbdf 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -17,7 +17,7 @@
 #include <linux/iopoll.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include "mtk_ecc.h"
+#include <linux/mtd/nand-ecc-mtk.h>
 
 /* NAND controller register definition */
 #define NFI_CNFG		(0x00)
diff --git a/include/linux/mtd/nand-ecc-mtk.h b/include/linux/mtd/nand-ecc-mtk.h
new file mode 100644
index 000000000000..0e48c36e6ca0
--- /dev/null
+++ b/include/linux/mtd/nand-ecc-mtk.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * MTK SDG1 ECC controller
+ *
+ * Copyright (c) 2016 Mediatek
+ * Authors:	Xiaolei Li		<xiaolei.li@mediatek.com>
+ *		Jorge Ramirez-Ortiz	<jorge.ramirez-ortiz@linaro.org>
+ */
+
+#ifndef __DRIVERS_MTD_NAND_MTK_ECC_H__
+#define __DRIVERS_MTD_NAND_MTK_ECC_H__
+
+#include <linux/types.h>
+
+enum mtk_ecc_mode {ECC_DMA_MODE = 0, ECC_NFI_MODE = 1};
+enum mtk_ecc_operation {ECC_ENCODE, ECC_DECODE};
+
+struct device_node;
+struct mtk_ecc;
+
+struct mtk_ecc_stats {
+	u32 corrected;
+	u32 bitflips;
+	u32 failed;
+};
+
+struct mtk_ecc_config {
+	enum mtk_ecc_operation op;
+	enum mtk_ecc_mode mode;
+	dma_addr_t addr;
+	u32 strength;
+	u32 sectors;
+	u32 len;
+};
+
+int mtk_ecc_encode(struct mtk_ecc *, struct mtk_ecc_config *, u8 *, u32);
+void mtk_ecc_get_stats(struct mtk_ecc *, struct mtk_ecc_stats *, int);
+int mtk_ecc_wait_done(struct mtk_ecc *, enum mtk_ecc_operation);
+int mtk_ecc_enable(struct mtk_ecc *, struct mtk_ecc_config *);
+void mtk_ecc_disable(struct mtk_ecc *);
+void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p);
+unsigned int mtk_ecc_get_parity_bits(struct mtk_ecc *ecc);
+
+struct mtk_ecc *of_mtk_ecc_get(struct device_node *);
+void mtk_ecc_release(struct mtk_ecc *);
+
+#endif
-- 
cgit v1.2.3


From 7d84c1ebf9ddafca27b481e6da7d24a023dacaa2 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 15 Apr 2022 21:20:02 +0200
Subject: x86/aperfmperf: Replace aperfmperf_get_khz()

The frequency invariance infrastructure provides the APERF/MPERF samples
already. Utilize them for the cpu frequency display in /proc/cpuinfo.

The sample is considered valid for 20ms. So for idle or isolated NOHZ full
CPUs the function returns 0, which is matching the previous behaviour.

This gets rid of the mass IPIs and a delay of 20ms for stabilizing observed
by Eric when reading /proc/cpuinfo.

Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/r/20220415161206.875029458@linutronix.de
---
 arch/x86/kernel/cpu/aperfmperf.c | 77 ++++++++++++++++++----------------------
 fs/proc/cpuinfo.c                |  6 +---
 include/linux/cpufreq.h          |  1 -
 3 files changed, 35 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 963c0697a92b..e9d2da7effc9 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -101,49 +101,6 @@ static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait)
 	return time_delta <= APERFMPERF_STALE_THRESHOLD_MS;
 }
 
-unsigned int aperfmperf_get_khz(int cpu)
-{
-	if (!cpu_khz)
-		return 0;
-
-	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return 0;
-
-	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
-		return 0;
-
-	if (rcu_is_idle_cpu(cpu))
-		return 0; /* Idle CPUs are completely uninteresting. */
-
-	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
-	return per_cpu(samples.khz, cpu);
-}
-
-void arch_freq_prepare_all(void)
-{
-	ktime_t now = ktime_get();
-	bool wait = false;
-	int cpu;
-
-	if (!cpu_khz)
-		return;
-
-	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return;
-
-	for_each_online_cpu(cpu) {
-		if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
-			continue;
-		if (rcu_is_idle_cpu(cpu))
-			continue; /* Idle CPUs are completely uninteresting. */
-		if (!aperfmperf_snapshot_cpu(cpu, now, false))
-			wait = true;
-	}
-
-	if (wait)
-		msleep(APERFMPERF_REFRESH_DELAY_MS);
-}
-
 unsigned int arch_freq_get_on_cpu(int cpu)
 {
 	struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu);
@@ -530,6 +487,40 @@ void arch_scale_freq_tick(void)
 	scale_freq_tick(acnt, mcnt);
 }
 
+/*
+ * Discard samples older than the define maximum sample age of 20ms. There
+ * is no point in sending IPIs in such a case. If the scheduler tick was
+ * not running then the CPU is either idle or isolated.
+ */
+#define MAX_SAMPLE_AGE	((unsigned long)HZ / 50)
+
+unsigned int aperfmperf_get_khz(int cpu)
+{
+	struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu);
+	unsigned long last;
+	unsigned int seq;
+	u64 acnt, mcnt;
+
+	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+		return 0;
+
+	do {
+		seq = raw_read_seqcount_begin(&s->seq);
+		last = s->last_update;
+		acnt = s->acnt;
+		mcnt = s->mcnt;
+	} while (read_seqcount_retry(&s->seq, seq));
+
+	/*
+	 * Bail on invalid count and when the last update was too long ago,
+	 * which covers idle and NOHZ full CPUs.
+	 */
+	if (!mcnt || (jiffies - last) > MAX_SAMPLE_AGE)
+		return 0;
+
+	return div64_u64((cpu_khz * acnt), mcnt);
+}
+
 static int __init bp_init_aperfmperf(void)
 {
 	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c
index 419760fd77bd..f38bda5b83ec 100644
--- a/fs/proc/cpuinfo.c
+++ b/fs/proc/cpuinfo.c
@@ -5,14 +5,10 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
-__weak void arch_freq_prepare_all(void)
-{
-}
-
 extern const struct seq_operations cpuinfo_op;
+
 static int cpuinfo_open(struct inode *inode, struct file *file)
 {
-	arch_freq_prepare_all();
 	return seq_open(file, &cpuinfo_op);
 }
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 35c7d6db4139..d5595d57f4e5 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1199,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
 			struct cpufreq_governor *old_gov) { }
 #endif
 
-extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
 #ifndef arch_set_freq_scale
-- 
cgit v1.2.3


From b941820ec938d175fd6e4e7ba5b4a6ca9d092afd Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Mon, 25 Apr 2022 14:45:44 +0300
Subject: ACPI: OSL: Remove the helper for deactivating memory region

There are no more users for acpi_release_memory().

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/osl.c   | 86 ----------------------------------------------------
 include/linux/acpi.h |  3 --
 2 files changed, 89 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 7a70c4bfc23c..3269a888fb7a 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -36,7 +36,6 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "acpica/accommon.h"
-#include "acpica/acnamesp.h"
 #include "internal.h"
 
 /* Definitions for ACPI_DEBUG_PRINT() */
@@ -1496,91 +1495,6 @@ int acpi_check_region(resource_size_t start, resource_size_t n,
 }
 EXPORT_SYMBOL(acpi_check_region);
 
-static acpi_status acpi_deactivate_mem_region(acpi_handle handle, u32 level,
-					      void *_res, void **return_value)
-{
-	struct acpi_mem_space_context **mem_ctx;
-	union acpi_operand_object *handler_obj;
-	union acpi_operand_object *region_obj2;
-	union acpi_operand_object *region_obj;
-	struct resource *res = _res;
-	acpi_status status;
-
-	region_obj = acpi_ns_get_attached_object(handle);
-	if (!region_obj)
-		return AE_OK;
-
-	handler_obj = region_obj->region.handler;
-	if (!handler_obj)
-		return AE_OK;
-
-	if (region_obj->region.space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY)
-		return AE_OK;
-
-	if (!(region_obj->region.flags & AOPOBJ_SETUP_COMPLETE))
-		return AE_OK;
-
-	region_obj2 = acpi_ns_get_secondary_object(region_obj);
-	if (!region_obj2)
-		return AE_OK;
-
-	mem_ctx = (void *)&region_obj2->extra.region_context;
-
-	if (!(mem_ctx[0]->address >= res->start &&
-	      mem_ctx[0]->address < res->end))
-		return AE_OK;
-
-	status = handler_obj->address_space.setup(region_obj,
-						  ACPI_REGION_DEACTIVATE,
-						  NULL, (void **)mem_ctx);
-	if (ACPI_SUCCESS(status))
-		region_obj->region.flags &= ~(AOPOBJ_SETUP_COMPLETE);
-
-	return status;
-}
-
-/**
- * acpi_release_memory - Release any mappings done to a memory region
- * @handle: Handle to namespace node
- * @res: Memory resource
- * @level: A level that terminates the search
- *
- * Walks through @handle and unmaps all SystemMemory Operation Regions that
- * overlap with @res and that have already been activated (mapped).
- *
- * This is a helper that allows drivers to place special requirements on memory
- * region that may overlap with operation regions, primarily allowing them to
- * safely map the region as non-cached memory.
- *
- * The unmapped Operation Regions will be automatically remapped next time they
- * are called, so the drivers do not need to do anything else.
- */
-acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
-				u32 level)
-{
-	acpi_status status;
-
-	if (!(res->flags & IORESOURCE_MEM))
-		return AE_TYPE;
-
-	status = acpi_walk_namespace(ACPI_TYPE_REGION, handle, level,
-				     acpi_deactivate_mem_region, NULL,
-				     res, NULL);
-	if (ACPI_FAILURE(status))
-		return status;
-
-	/*
-	 * Wait for all of the mappings queued up for removal by
-	 * acpi_deactivate_mem_region() to actually go away.
-	 */
-	synchronize_rcu();
-	rcu_barrier();
-	flush_scheduled_work();
-
-	return AE_OK;
-}
-EXPORT_SYMBOL_GPL(acpi_release_memory);
-
 /*
  * Let drivers know whether the resource checks are effective
  */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d7136d13aa44..fadda404bcc9 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -520,9 +520,6 @@ int acpi_check_resource_conflict(const struct resource *res);
 int acpi_check_region(resource_size_t start, resource_size_t n,
 		      const char *name);
 
-acpi_status acpi_release_memory(acpi_handle handle, struct resource *res,
-				u32 level);
-
 int acpi_resources_are_enforced(void);
 
 #ifdef CONFIG_HIBERNATION
-- 
cgit v1.2.3


From 0a8e98305f63deaf0a799d5cf5532cc83af035d1 Mon Sep 17 00:00:00 2001
From: Tokunori Ikegami <ikegami.t@gmail.com>
Date: Thu, 24 Mar 2022 02:04:56 +0900
Subject: mtd: cfi_cmdset_0002: Use chip_ready() for write on S29GL064N

Since commit dfeae1073583("mtd: cfi_cmdset_0002: Change write buffer to
check correct value") buffered writes fail on S29GL064N. This is
because, on S29GL064N, reads return 0xFF at the end of DQ polling for
write completion, where as, chip_good() check expects actual data
written to the last location to be returned post DQ polling completion.
Fix is to revert to using chip_good() for S29GL064N which only checks
for DQ lines to settle down to determine write completion.

Link: https://lore.kernel.org/r/b687c259-6413-26c9-d4c9-b3afa69ea124@pengutronix.de/
Fixes: dfeae1073583("mtd: cfi_cmdset_0002: Change write buffer to check correct value")
Cc: stable@vger.kernel.org
Signed-off-by: Tokunori Ikegami <ikegami.t@gmail.com>
Acked-by: Vignesh Raghavendra <vigneshr@ti.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20220323170458.5608-3-ikegami.t@gmail.com
---
 drivers/mtd/chips/cfi_cmdset_0002.c | 42 ++++++++++++++++++++++++++++++-------
 include/linux/mtd/cfi.h             |  1 +
 2 files changed, 35 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 9ccde90dc180..59334530dd46 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -59,6 +59,10 @@
 #define CFI_SR_WBASB		BIT(3)
 #define CFI_SR_SLSB		BIT(1)
 
+enum cfi_quirks {
+	CFI_QUIRK_DQ_TRUE_DATA = BIT(0),
+};
+
 static int cfi_amdstd_read (struct mtd_info *, loff_t, size_t, size_t *, u_char *);
 static int cfi_amdstd_write_words(struct mtd_info *, loff_t, size_t, size_t *, const u_char *);
 #if !FORCE_WORD_WRITE
@@ -436,6 +440,15 @@ static void fixup_s29ns512p_sectors(struct mtd_info *mtd)
 		mtd->name);
 }
 
+static void fixup_quirks(struct mtd_info *mtd)
+{
+	struct map_info *map = mtd->priv;
+	struct cfi_private *cfi = map->fldrv_priv;
+
+	if (cfi->mfr == CFI_MFR_AMD && cfi->id == 0x0c01)
+		cfi->quirks |= CFI_QUIRK_DQ_TRUE_DATA;
+}
+
 /* Used to fix CFI-Tables of chips without Extended Query Tables */
 static struct cfi_fixup cfi_nopri_fixup_table[] = {
 	{ CFI_MFR_SST, 0x234a, fixup_sst39vf }, /* SST39VF1602 */
@@ -474,6 +487,7 @@ static struct cfi_fixup cfi_fixup_table[] = {
 #if !FORCE_WORD_WRITE
 	{ CFI_MFR_ANY, CFI_ID_ANY, fixup_use_write_buffers },
 #endif
+	{ CFI_MFR_ANY, CFI_ID_ANY, fixup_quirks },
 	{ 0, 0, NULL }
 };
 static struct cfi_fixup jedec_fixup_table[] = {
@@ -846,6 +860,18 @@ static int __xipram chip_ready(struct map_info *map, struct flchip *chip,
 	return map_word_equal(map, t, *expected);
 }
 
+static int __xipram chip_good(struct map_info *map, struct flchip *chip,
+			      unsigned long addr, map_word *expected)
+{
+	struct cfi_private *cfi = map->fldrv_priv;
+	map_word *datum = expected;
+
+	if (cfi->quirks & CFI_QUIRK_DQ_TRUE_DATA)
+		datum = NULL;
+
+	return chip_ready(map, chip, addr, datum);
+}
+
 static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr, int mode)
 {
 	DECLARE_WAITQUEUE(wait, current);
@@ -1662,11 +1688,11 @@ static int __xipram do_write_oneword_once(struct map_info *map,
 		}
 
 		/*
-		 * We check "time_after" and "!chip_ready" before checking
-		 * "chip_ready" to avoid the failure due to scheduling.
+		 * We check "time_after" and "!chip_good" before checking
+		 * "chip_good" to avoid the failure due to scheduling.
 		 */
 		if (time_after(jiffies, timeo) &&
-		    !chip_ready(map, chip, adr, &datum)) {
+		    !chip_good(map, chip, adr, &datum)) {
 			xip_enable(map, chip, adr);
 			printk(KERN_WARNING "MTD %s(): software timeout\n", __func__);
 			xip_disable(map, chip, adr);
@@ -1674,7 +1700,7 @@ static int __xipram do_write_oneword_once(struct map_info *map,
 			break;
 		}
 
-		if (chip_ready(map, chip, adr, &datum)) {
+		if (chip_good(map, chip, adr, &datum)) {
 			if (cfi_check_err_status(map, chip, adr))
 				ret = -EIO;
 			break;
@@ -1942,18 +1968,18 @@ static int __xipram do_write_buffer_wait(struct map_info *map,
 		}
 
 		/*
-		 * We check "time_after" and "!chip_ready" before checking
-		 * "chip_ready" to avoid the failure due to scheduling.
+		 * We check "time_after" and "!chip_good" before checking
+		 * "chip_good" to avoid the failure due to scheduling.
 		 */
 		if (time_after(jiffies, timeo) &&
-		    !chip_ready(map, chip, adr, &datum)) {
+		    !chip_good(map, chip, adr, &datum)) {
 			pr_err("MTD %s(): software timeout, address:0x%.8lx.\n",
 			       __func__, adr);
 			ret = -EIO;
 			break;
 		}
 
-		if (chip_ready(map, chip, adr, &datum)) {
+		if (chip_good(map, chip, adr, &datum)) {
 			if (cfi_check_err_status(map, chip, adr))
 				ret = -EIO;
 			break;
diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h
index fd1ecb821106..d88bb56c18e2 100644
--- a/include/linux/mtd/cfi.h
+++ b/include/linux/mtd/cfi.h
@@ -286,6 +286,7 @@ struct cfi_private {
 	map_word sector_erase_cmd;
 	unsigned long chipshift; /* Because they're of the same type */
 	const char *im_name;	 /* inter_module name for cmdset_setup */
+	unsigned long quirks;
 	struct flchip chips[];  /* per-chip data structure for each chip */
 };
 
-- 
cgit v1.2.3


From ed36d04e8f8d7b00db451b0fa56a54e8e02ec43e Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 25 Apr 2022 13:42:02 +0100
Subject: iommu: Introduce device_iommu_capable()

iommu_capable() only really works for systems where all IOMMU instances
are completely homogeneous, and all devices are IOMMU-mapped. Implement
the new variant which will be able to give a more accurate answer for
whichever device the caller is actually interested in, and even more so
once all the external users have been converted and we can reliably pass
the device pointer through the internal driver interface too.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/8407eb9586677995b7a9fd70d0fd82d85929a9bb.1650878781.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 23 +++++++++++++++++++++++
 include/linux/iommu.h |  6 ++++++
 2 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index f2c45b85b9fc..780c11734979 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1906,6 +1906,29 @@ bool iommu_present(struct bus_type *bus)
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
+/**
+ * device_iommu_capable() - check for a general IOMMU capability
+ * @dev: device to which the capability would be relevant, if available
+ * @cap: IOMMU capability
+ *
+ * Return: true if an IOMMU is present and supports the given capability
+ * for the given device, otherwise false.
+ */
+bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	const struct iommu_ops *ops;
+
+	if (!dev->iommu || !dev->iommu->iommu_dev)
+		return false;
+
+	ops = dev_iommu_ops(dev);
+	if (!ops->capable)
+		return false;
+
+	return ops->capable(cap);
+}
+EXPORT_SYMBOL_GPL(device_iommu_capable);
+
 bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
 {
 	if (!bus->iommu_ops || !bus->iommu_ops->capable)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 9208eca4b0d1..e26cf84e5d82 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -417,6 +417,7 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
 extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops);
 extern int bus_iommu_probe(struct bus_type *bus);
 extern bool iommu_present(struct bus_type *bus);
+extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap);
 extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap);
 extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus);
 extern struct iommu_group *iommu_group_get_by_id(int id);
@@ -689,6 +690,11 @@ static inline bool iommu_present(struct bus_type *bus)
 	return false;
 }
 
+static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+	return false;
+}
+
 static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
 {
 	return false;
-- 
cgit v1.2.3


From d0be55fbeb6ac694d15af5d1aad19cdec8cd64e5 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 25 Apr 2022 13:42:03 +0100
Subject: iommu: Add capability for pre-boot DMA protection

VT-d's dmar_platform_optin() actually represents a combination of
properties fairly well standardised by Microsoft as "Pre-boot DMA
Protection" and "Kernel DMA Protection"[1]. As such, we can provide
interested consumers with an abstracted capability rather than
driver-specific interfaces that won't scale. We name it for the former
aspect since that's what external callers are most likely to be
interested in; the latter is for the IOMMU layer to handle itself.

[1] https://docs.microsoft.com/en-us/windows-hardware/design/device-experiences/oem-kernel-dma-protection

Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/d6218dff2702472da80db6aec2c9589010684551.1650878781.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 2 ++
 include/linux/iommu.h       | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index df5c62ecf942..0edf6084dc14 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4551,6 +4551,8 @@ static bool intel_iommu_capable(enum iommu_cap cap)
 		return domain_update_iommu_snooping(NULL);
 	if (cap == IOMMU_CAP_INTR_REMAP)
 		return irq_remapping_enabled == 1;
+	if (cap == IOMMU_CAP_PRE_BOOT_PROTECTION)
+		return dmar_platform_optin();
 
 	return false;
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e26cf84e5d82..4123693ae319 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -107,6 +107,8 @@ enum iommu_cap {
 					   transactions */
 	IOMMU_CAP_INTR_REMAP,		/* IOMMU supports interrupt isolation */
 	IOMMU_CAP_NOEXEC,		/* IOMMU_NOEXEC flag */
+	IOMMU_CAP_PRE_BOOT_PROTECTION,	/* Firmware says it used the IOMMU for
+					   DMA protection and we should too */
 };
 
 /* These are the possible reserved region types */
-- 
cgit v1.2.3


From 86eaf4a5b4312bea8676fb79399d9e08b53d8e71 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 25 Apr 2022 13:42:04 +0100
Subject: thunderbolt: Make iommu_dma_protection more accurate

Between me trying to get rid of iommu_present() and Mario wanting to
support the AMD equivalent of DMAR_PLATFORM_OPT_IN, scrutiny has shown
that the iommu_dma_protection attribute is being far too optimistic.
Even if an IOMMU might be present for some PCI segment in the system,
that doesn't necessarily mean it provides translation for the device(s)
we care about. Furthermore, all that DMAR_PLATFORM_OPT_IN really does
is tell us that memory was protected before the kernel was loaded, and
prevent the user from disabling the intel-iommu driver entirely. While
that lets us assume kernel integrity, what matters for actual runtime
DMA protection is whether we trust individual devices, based on the
"external facing" property that we expect firmware to describe for
Thunderbolt ports.

It's proven challenging to determine the appropriate ports accurately
given the variety of possible topologies, so while still not getting a
perfect answer, by putting enough faith in firmware we can at least get
a good bit closer. If we can see that any device near a Thunderbolt NHI
has all the requisites for Kernel DMA Protection, chances are that it
*is* a relevant port, but moreover that implies that firmware is playing
the game overall, so we'll use that to assume that all Thunderbolt ports
should be correctly marked and thus will end up fully protected.

CC: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/b153f208bc9eafab5105bad0358b77366509d2d4.1650878781.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/thunderbolt/domain.c | 12 +++---------
 drivers/thunderbolt/nhi.c    | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/thunderbolt.h  |  2 ++
 3 files changed, 49 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index 7018d959f775..2889a214dadc 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -7,9 +7,7 @@
  */
 
 #include <linux/device.h>
-#include <linux/dmar.h>
 #include <linux/idr.h>
-#include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -257,13 +255,9 @@ static ssize_t iommu_dma_protection_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	/*
-	 * Kernel DMA protection is a feature where Thunderbolt security is
-	 * handled natively using IOMMU. It is enabled when IOMMU is
-	 * enabled and ACPI DMAR table has DMAR_PLATFORM_OPT_IN set.
-	 */
-	return sprintf(buf, "%d\n",
-		       iommu_present(&pci_bus_type) && dmar_platform_optin());
+	struct tb *tb = container_of(dev, struct tb, dev);
+
+	return sysfs_emit(buf, "%d\n", tb->nhi->iommu_dma_protection);
 }
 static DEVICE_ATTR_RO(iommu_dma_protection);
 
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 4a582183f675..4bc87b0f003a 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -15,9 +15,11 @@
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
+#include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/property.h>
+#include <linux/string_helpers.h>
 
 #include "nhi.h"
 #include "nhi_regs.h"
@@ -1103,6 +1105,47 @@ static void nhi_check_quirks(struct tb_nhi *nhi)
 		nhi->quirks |= QUIRK_AUTO_CLEAR_INT;
 }
 
+static int nhi_check_iommu_pdev(struct pci_dev *pdev, void *data)
+{
+	if (!pdev->external_facing ||
+	    !device_iommu_capable(&pdev->dev, IOMMU_CAP_PRE_BOOT_PROTECTION))
+		return 0;
+	*(bool *)data = true;
+	return 1; /* Stop walking */
+}
+
+static void nhi_check_iommu(struct tb_nhi *nhi)
+{
+	struct pci_bus *bus = nhi->pdev->bus;
+	bool port_ok = false;
+
+	/*
+	 * Ideally what we'd do here is grab every PCI device that
+	 * represents a tunnelling adapter for this NHI and check their
+	 * status directly, but unfortunately USB4 seems to make it
+	 * obnoxiously difficult to reliably make any correlation.
+	 *
+	 * So for now we'll have to bodge it... Hoping that the system
+	 * is at least sane enough that an adapter is in the same PCI
+	 * segment as its NHI, if we can find *something* on that segment
+	 * which meets the requirements for Kernel DMA Protection, we'll
+	 * take that to imply that firmware is aware and has (hopefully)
+	 * done the right thing in general. We need to know that the PCI
+	 * layer has seen the ExternalFacingPort property which will then
+	 * inform the IOMMU layer to enforce the complete "untrusted DMA"
+	 * flow, but also that the IOMMU driver itself can be trusted not
+	 * to have been subverted by a pre-boot DMA attack.
+	 */
+	while (bus->parent)
+		bus = bus->parent;
+
+	pci_walk_bus(bus, nhi_check_iommu_pdev, &port_ok);
+
+	nhi->iommu_dma_protection = port_ok;
+	dev_dbg(&nhi->pdev->dev, "IOMMU DMA protection is %s\n",
+		str_enabled_disabled(port_ok));
+}
+
 static int nhi_init_msi(struct tb_nhi *nhi)
 {
 	struct pci_dev *pdev = nhi->pdev;
@@ -1220,6 +1263,7 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	nhi_check_quirks(nhi);
+	nhi_check_iommu(nhi);
 
 	res = nhi_init_msi(nhi);
 	if (res) {
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index 124e13cb1469..7a8ad984e651 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -465,6 +465,7 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc)
  * @msix_ida: Used to allocate MSI-X vectors for rings
  * @going_away: The host controller device is about to disappear so when
  *		this flag is set, avoid touching the hardware anymore.
+ * @iommu_dma_protection: An IOMMU will isolate external-facing ports.
  * @interrupt_work: Work scheduled to handle ring interrupt when no
  *		    MSI-X is used.
  * @hop_count: Number of rings (end point hops) supported by NHI.
@@ -479,6 +480,7 @@ struct tb_nhi {
 	struct tb_ring **rx_rings;
 	struct ida msix_ida;
 	bool going_away;
+	bool iommu_dma_protection;
 	struct work_struct interrupt_work;
 	u32 hop_count;
 	unsigned long quirks;
-- 
cgit v1.2.3


From 2147c438fde135d6c145a96e373d9348e7076f7f Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Mon, 25 Apr 2022 16:40:02 -0700
Subject: x86/speculation: Add missing prototype for unpriv_ebpf_notify()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following warnings seen with "make W=1":

  kernel/sysctl.c:183:13: warning: no previous prototype for ‘unpriv_ebpf_notify’ [-Wmissing-prototypes]
    183 | void __weak unpriv_ebpf_notify(int new_state)
        |             ^~~~~~~~~~~~~~~~~~

  arch/x86/kernel/cpu/bugs.c:659:6: warning: no previous prototype for ‘unpriv_ebpf_notify’ [-Wmissing-prototypes]
    659 | void unpriv_ebpf_notify(int new_state)
        |      ^~~~~~~~~~~~~~~~~~

Fixes: 44a3918c8245 ("x86/speculation: Include unprivileged eBPF status in Spectre v2 mitigation reporting")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/5689d065f739602ececaee1e05e68b8644009608.1650930000.git.jpoimboe@redhat.com
---
 include/linux/bpf.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bdb5298735ce..ecc3d3ec41cf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2085,6 +2085,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
 				       struct net_device *netdev);
 bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev);
 
+void unpriv_ebpf_notify(int new_state);
+
 #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
 int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
 
-- 
cgit v1.2.3


From 1ea2a07a532b0e22aabe7e8483f935c672b9e7ed Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Apr 2022 08:49:50 +0800
Subject: iommu: Add DMA ownership management interfaces

Multiple devices may be placed in the same IOMMU group because they
cannot be isolated from each other. These devices must either be
entirely under kernel control or userspace control, never a mixture.

This adds dma ownership management in iommu core and exposes several
interfaces for the device drivers and the device userspace assignment
framework (i.e. VFIO), so that any conflict between user and kernel
controlled dma could be detected at the beginning.

The device driver oriented interfaces are,

	int iommu_device_use_default_domain(struct device *dev);
	void iommu_device_unuse_default_domain(struct device *dev);

By calling iommu_device_use_default_domain(), the device driver tells
the iommu layer that the device dma is handled through the kernel DMA
APIs. The iommu layer will manage the IOVA and use the default domain
for DMA address translation.

The device user-space assignment framework oriented interfaces are,

	int iommu_group_claim_dma_owner(struct iommu_group *group,
					void *owner);
	void iommu_group_release_dma_owner(struct iommu_group *group);
	bool iommu_group_dma_owner_claimed(struct iommu_group *group);

The device userspace assignment must be disallowed if the DMA owner
claiming interface returns failure.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20220418005000.897664-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 153 +++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/iommu.h |  31 ++++++++++
 2 files changed, 181 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index f2c45b85b9fc..eba8e8ccf19d 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -48,6 +48,8 @@ struct iommu_group {
 	struct iommu_domain *default_domain;
 	struct iommu_domain *domain;
 	struct list_head entry;
+	unsigned int owner_cnt;
+	void *owner;
 };
 
 struct group_device {
@@ -294,7 +296,11 @@ int iommu_probe_device(struct device *dev)
 	mutex_lock(&group->mutex);
 	iommu_alloc_default_domain(group, dev);
 
-	if (group->default_domain) {
+	/*
+	 * If device joined an existing group which has been claimed, don't
+	 * attach the default domain.
+	 */
+	if (group->default_domain && !group->owner) {
 		ret = __iommu_attach_device(group->default_domain, dev);
 		if (ret) {
 			mutex_unlock(&group->mutex);
@@ -2109,7 +2115,7 @@ static int __iommu_attach_group(struct iommu_domain *domain,
 {
 	int ret;
 
-	if (group->default_domain && group->domain != group->default_domain)
+	if (group->domain && group->domain != group->default_domain)
 		return -EBUSY;
 
 	ret = __iommu_group_for_each_dev(group, domain,
@@ -2146,7 +2152,11 @@ static void __iommu_detach_group(struct iommu_domain *domain,
 {
 	int ret;
 
-	if (!group->default_domain) {
+	/*
+	 * If the group has been claimed already, do not re-attach the default
+	 * domain.
+	 */
+	if (!group->default_domain || group->owner) {
 		__iommu_group_for_each_dev(group, domain,
 					   iommu_group_do_detach_device);
 		group->domain = NULL;
@@ -3095,3 +3105,140 @@ out:
 
 	return ret;
 }
+
+/**
+ * iommu_device_use_default_domain() - Device driver wants to handle device
+ *                                     DMA through the kernel DMA API.
+ * @dev: The device.
+ *
+ * The device driver about to bind @dev wants to do DMA through the kernel
+ * DMA API. Return 0 if it is allowed, otherwise an error.
+ */
+int iommu_device_use_default_domain(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+	int ret = 0;
+
+	if (!group)
+		return 0;
+
+	mutex_lock(&group->mutex);
+	if (group->owner_cnt) {
+		if (group->domain != group->default_domain ||
+		    group->owner) {
+			ret = -EBUSY;
+			goto unlock_out;
+		}
+	}
+
+	group->owner_cnt++;
+
+unlock_out:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
+
+/**
+ * iommu_device_unuse_default_domain() - Device driver stops handling device
+ *                                       DMA through the kernel DMA API.
+ * @dev: The device.
+ *
+ * The device driver doesn't want to do DMA through kernel DMA API anymore.
+ * It must be called after iommu_device_use_default_domain().
+ */
+void iommu_device_unuse_default_domain(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	if (!group)
+		return;
+
+	mutex_lock(&group->mutex);
+	if (!WARN_ON(!group->owner_cnt))
+		group->owner_cnt--;
+
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+}
+
+/**
+ * iommu_group_claim_dma_owner() - Set DMA ownership of a group
+ * @group: The group.
+ * @owner: Caller specified pointer. Used for exclusive ownership.
+ *
+ * This is to support backward compatibility for vfio which manages
+ * the dma ownership in iommu_group level. New invocations on this
+ * interface should be prohibited.
+ */
+int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner)
+{
+	int ret = 0;
+
+	mutex_lock(&group->mutex);
+	if (group->owner_cnt) {
+		ret = -EPERM;
+		goto unlock_out;
+	} else {
+		if (group->domain && group->domain != group->default_domain) {
+			ret = -EBUSY;
+			goto unlock_out;
+		}
+
+		group->owner = owner;
+		if (group->domain)
+			__iommu_detach_group(group->domain, group);
+	}
+
+	group->owner_cnt++;
+unlock_out:
+	mutex_unlock(&group->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner);
+
+/**
+ * iommu_group_release_dma_owner() - Release DMA ownership of a group
+ * @group: The group.
+ *
+ * Release the DMA ownership claimed by iommu_group_claim_dma_owner().
+ */
+void iommu_group_release_dma_owner(struct iommu_group *group)
+{
+	mutex_lock(&group->mutex);
+	if (WARN_ON(!group->owner_cnt || !group->owner))
+		goto unlock_out;
+
+	group->owner_cnt = 0;
+	/*
+	 * The UNMANAGED domain should be detached before all USER
+	 * owners have been released.
+	 */
+	if (!WARN_ON(group->domain) && group->default_domain)
+		__iommu_attach_group(group->default_domain, group);
+	group->owner = NULL;
+unlock_out:
+	mutex_unlock(&group->mutex);
+}
+EXPORT_SYMBOL_GPL(iommu_group_release_dma_owner);
+
+/**
+ * iommu_group_dma_owner_claimed() - Query group dma ownership status
+ * @group: The group.
+ *
+ * This provides status query on a given group. It is racy and only for
+ * non-binding status reporting.
+ */
+bool iommu_group_dma_owner_claimed(struct iommu_group *group)
+{
+	unsigned int user;
+
+	mutex_lock(&group->mutex);
+	user = group->owner_cnt;
+	mutex_unlock(&group->mutex);
+
+	return user;
+}
+EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 9208eca4b0d1..77972ef978b5 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -675,6 +675,13 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 void iommu_sva_unbind_device(struct iommu_sva *handle);
 u32 iommu_sva_get_pasid(struct iommu_sva *handle);
 
+int iommu_device_use_default_domain(struct device *dev);
+void iommu_device_unuse_default_domain(struct device *dev);
+
+int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner);
+void iommu_group_release_dma_owner(struct iommu_group *group);
+bool iommu_group_dma_owner_claimed(struct iommu_group *group);
+
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -1031,6 +1038,30 @@ static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev)
 {
 	return NULL;
 }
+
+static inline int iommu_device_use_default_domain(struct device *dev)
+{
+	return 0;
+}
+
+static inline void iommu_device_unuse_default_domain(struct device *dev)
+{
+}
+
+static inline int
+iommu_group_claim_dma_owner(struct iommu_group *group, void *owner)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_group_release_dma_owner(struct iommu_group *group)
+{
+}
+
+static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group)
+{
+	return false;
+}
 #endif /* CONFIG_IOMMU_API */
 
 /**
-- 
cgit v1.2.3


From 25f3bcfc54bcf7b0e45d140ec8bfbbf10ba11869 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Apr 2022 08:49:51 +0800
Subject: driver core: Add dma_cleanup callback in bus_type

The bus_type structure defines dma_configure() callback for bus drivers
to configure DMA on the devices. This adds the paired dma_cleanup()
callback and calls it during driver unbinding so that bus drivers can do
some cleanup work.

One use case for this paired DMA callbacks is for the bus driver to check
for DMA ownership conflicts during driver binding, where multiple devices
belonging to a same IOMMU group (the minimum granularity of isolation and
protection) may be assigned to kernel drivers or user space respectively.

Without this change, for example, the vfio driver has to listen to a bus
BOUND_DRIVER event and then BUG_ON() in case of dma ownership conflict.
This leads to bad user experience since careless driver binding operation
may crash the system if the admin overlooks the group restriction. Aside
from bad design, this leads to a security problem as a root user, even with
lockdown=integrity, can force the kernel to BUG.

With this change, the bus driver could check and set the DMA ownership in
driver binding process and fail on ownership conflicts. The DMA ownership
should be released during driver unbinding.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20220418005000.897664-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/base/dd.c          | 5 +++++
 include/linux/device/bus.h | 3 +++
 2 files changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 3fc3b5940bb3..94b7ac9bf459 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -671,6 +671,8 @@ sysfs_failed:
 	if (dev->bus)
 		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
 					     BUS_NOTIFY_DRIVER_NOT_BOUND, dev);
+	if (dev->bus && dev->bus->dma_cleanup)
+		dev->bus->dma_cleanup(dev);
 pinctrl_bind_failed:
 	device_links_no_driver(dev);
 	device_unbind_cleanup(dev);
@@ -1199,6 +1201,9 @@ static void __device_release_driver(struct device *dev, struct device *parent)
 
 		device_remove(dev);
 
+		if (dev->bus && dev->bus->dma_cleanup)
+			dev->bus->dma_cleanup(dev);
+
 		device_links_driver_cleanup(dev);
 		device_unbind_cleanup(dev);
 
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index a039ab809753..d8b29ccd07e5 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -59,6 +59,8 @@ struct fwnode_handle;
  *		bus supports.
  * @dma_configure:	Called to setup DMA configuration on a device on
  *			this bus.
+ * @dma_cleanup:	Called to cleanup DMA configuration on a device on
+ *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
  * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
@@ -103,6 +105,7 @@ struct bus_type {
 	int (*num_vf)(struct device *dev);
 
 	int (*dma_configure)(struct device *dev);
+	void (*dma_cleanup)(struct device *dev);
 
 	const struct dev_pm_ops *pm;
 
-- 
cgit v1.2.3


From 4a6d9dd564d0e7339fc15ecc5ce66db4ad842be2 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Apr 2022 08:49:52 +0800
Subject: amba: Stop sharing platform_dma_configure()

Stop sharing platform_dma_configure() helper as they are about to have
their own bus dma_configure callbacks.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20220418005000.897664-4-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/amba/bus.c              | 19 ++++++++++++++++++-
 drivers/base/platform.c         |  3 +--
 include/linux/platform_device.h |  2 --
 3 files changed, 19 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index d3bd14aaabf6..76b52bd2c2a4 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -20,6 +20,8 @@
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/of_irq.h>
+#include <linux/of_device.h>
+#include <linux/acpi.h>
 
 #define to_amba_driver(d)	container_of(d, struct amba_driver, drv)
 
@@ -273,6 +275,21 @@ static void amba_shutdown(struct device *dev)
 		drv->shutdown(to_amba_device(dev));
 }
 
+static int amba_dma_configure(struct device *dev)
+{
+	enum dev_dma_attr attr;
+	int ret = 0;
+
+	if (dev->of_node) {
+		ret = of_dma_configure(dev, dev->of_node, true);
+	} else if (has_acpi_companion(dev)) {
+		attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode));
+		ret = acpi_dma_configure(dev, attr);
+	}
+
+	return ret;
+}
+
 #ifdef CONFIG_PM
 /*
  * Hooks to provide runtime PM of the pclk (bus clock).  It is safe to
@@ -341,7 +358,7 @@ struct bus_type amba_bustype = {
 	.probe		= amba_probe,
 	.remove		= amba_remove,
 	.shutdown	= amba_shutdown,
-	.dma_configure	= platform_dma_configure,
+	.dma_configure	= amba_dma_configure,
 	.pm		= &amba_pm,
 };
 EXPORT_SYMBOL_GPL(amba_bustype);
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 8cc272fd5c99..d7915734d931 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1454,8 +1454,7 @@ static void platform_shutdown(struct device *_dev)
 		drv->shutdown(dev);
 }
 
-
-int platform_dma_configure(struct device *dev)
+static int platform_dma_configure(struct device *dev)
 {
 	enum dev_dma_attr attr;
 	int ret = 0;
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 7c96f169d274..17fde717df68 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -328,8 +328,6 @@ extern int platform_pm_restore(struct device *dev);
 #define platform_pm_restore		NULL
 #endif
 
-extern int platform_dma_configure(struct device *dev);
-
 #ifdef CONFIG_PM_SLEEP
 #define USE_PLATFORM_PM_SLEEP_OPS \
 	.suspend = platform_pm_suspend, \
-- 
cgit v1.2.3


From 512881eacfa72c2136b27b9934b7b27504a9efc2 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Apr 2022 08:49:53 +0800
Subject: bus: platform,amba,fsl-mc,PCI: Add device DMA ownership management

The devices on platform/amba/fsl-mc/PCI buses could be bound to drivers
with the device DMA managed by kernel drivers or user-space applications.
Unfortunately, multiple devices may be placed in the same IOMMU group
because they cannot be isolated from each other. The DMA on these devices
must either be entirely under kernel control or userspace control, never
a mixture. Otherwise the driver integrity is not guaranteed because they
could access each other through the peer-to-peer accesses which by-pass
the IOMMU protection.

This checks and sets the default DMA mode during driver binding, and
cleanups during driver unbinding. In the default mode, the device DMA is
managed by the device driver which handles DMA operations through the
kernel DMA APIs (see Documentation/core-api/dma-api.rst).

For cases where the devices are assigned for userspace control through the
userspace driver framework(i.e. VFIO), the drivers(for example, vfio_pci/
vfio_platfrom etc.) may set a new flag (driver_managed_dma) to skip this
default setting in the assumption that the drivers know what they are
doing with the device DMA.

Calling iommu_device_use_default_domain() before {of,acpi}_dma_configure
is currently a problem. As things stand, the IOMMU driver ignored the
initial iommu_probe_device() call when the device was added, since at
that point it had no fwspec yet. In this situation,
{of,acpi}_iommu_configure() are retriggering iommu_probe_device() after
the IOMMU driver has seen the firmware data via .of_xlate to learn that
it actually responsible for the given device. As the result, before
that gets fixed, iommu_use_default_domain() goes at the end, and calls
arch_teardown_dma_ops() if it fails.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Stuart Yoder <stuyoder@gmail.com>
Cc: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20220418005000.897664-5-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/amba/bus.c              | 18 ++++++++++++++++++
 drivers/base/platform.c         | 18 ++++++++++++++++++
 drivers/bus/fsl-mc/fsl-mc-bus.c | 24 ++++++++++++++++++++++--
 drivers/pci/pci-driver.c        | 18 ++++++++++++++++++
 include/linux/amba/bus.h        |  8 ++++++++
 include/linux/fsl/mc.h          |  8 ++++++++
 include/linux/pci.h             |  8 ++++++++
 include/linux/platform_device.h |  8 ++++++++
 8 files changed, 108 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 76b52bd2c2a4..a0ec61232b6c 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -22,6 +22,8 @@
 #include <linux/of_irq.h>
 #include <linux/of_device.h>
 #include <linux/acpi.h>
+#include <linux/iommu.h>
+#include <linux/dma-map-ops.h>
 
 #define to_amba_driver(d)	container_of(d, struct amba_driver, drv)
 
@@ -277,6 +279,7 @@ static void amba_shutdown(struct device *dev)
 
 static int amba_dma_configure(struct device *dev)
 {
+	struct amba_driver *drv = to_amba_driver(dev->driver);
 	enum dev_dma_attr attr;
 	int ret = 0;
 
@@ -287,9 +290,23 @@ static int amba_dma_configure(struct device *dev)
 		ret = acpi_dma_configure(dev, attr);
 	}
 
+	if (!ret && !drv->driver_managed_dma) {
+		ret = iommu_device_use_default_domain(dev);
+		if (ret)
+			arch_teardown_dma_ops(dev);
+	}
+
 	return ret;
 }
 
+static void amba_dma_cleanup(struct device *dev)
+{
+	struct amba_driver *drv = to_amba_driver(dev->driver);
+
+	if (!drv->driver_managed_dma)
+		iommu_device_unuse_default_domain(dev);
+}
+
 #ifdef CONFIG_PM
 /*
  * Hooks to provide runtime PM of the pclk (bus clock).  It is safe to
@@ -359,6 +376,7 @@ struct bus_type amba_bustype = {
 	.remove		= amba_remove,
 	.shutdown	= amba_shutdown,
 	.dma_configure	= amba_dma_configure,
+	.dma_cleanup	= amba_dma_cleanup,
 	.pm		= &amba_pm,
 };
 EXPORT_SYMBOL_GPL(amba_bustype);
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index d7915734d931..70bc30cf575c 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -30,6 +30,8 @@
 #include <linux/property.h>
 #include <linux/kmemleak.h>
 #include <linux/types.h>
+#include <linux/iommu.h>
+#include <linux/dma-map-ops.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -1456,6 +1458,7 @@ static void platform_shutdown(struct device *_dev)
 
 static int platform_dma_configure(struct device *dev)
 {
+	struct platform_driver *drv = to_platform_driver(dev->driver);
 	enum dev_dma_attr attr;
 	int ret = 0;
 
@@ -1466,9 +1469,23 @@ static int platform_dma_configure(struct device *dev)
 		ret = acpi_dma_configure(dev, attr);
 	}
 
+	if (!ret && !drv->driver_managed_dma) {
+		ret = iommu_device_use_default_domain(dev);
+		if (ret)
+			arch_teardown_dma_ops(dev);
+	}
+
 	return ret;
 }
 
+static void platform_dma_cleanup(struct device *dev)
+{
+	struct platform_driver *drv = to_platform_driver(dev->driver);
+
+	if (!drv->driver_managed_dma)
+		iommu_device_unuse_default_domain(dev);
+}
+
 static const struct dev_pm_ops platform_dev_pm_ops = {
 	SET_RUNTIME_PM_OPS(pm_generic_runtime_suspend, pm_generic_runtime_resume, NULL)
 	USE_PLATFORM_PM_SLEEP_OPS
@@ -1483,6 +1500,7 @@ struct bus_type platform_bus_type = {
 	.remove		= platform_remove,
 	.shutdown	= platform_shutdown,
 	.dma_configure	= platform_dma_configure,
+	.dma_cleanup	= platform_dma_cleanup,
 	.pm		= &platform_dev_pm_ops,
 };
 EXPORT_SYMBOL_GPL(platform_bus_type);
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 8fd4a356a86e..76648c4fdaf4 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -21,6 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/acpi.h>
 #include <linux/iommu.h>
+#include <linux/dma-map-ops.h>
 
 #include "fsl-mc-private.h"
 
@@ -140,15 +141,33 @@ static int fsl_mc_dma_configure(struct device *dev)
 {
 	struct device *dma_dev = dev;
 	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+	struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(dev->driver);
 	u32 input_id = mc_dev->icid;
+	int ret;
 
 	while (dev_is_fsl_mc(dma_dev))
 		dma_dev = dma_dev->parent;
 
 	if (dev_of_node(dma_dev))
-		return of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id);
+		ret = of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id);
+	else
+		ret = acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id);
+
+	if (!ret && !mc_drv->driver_managed_dma) {
+		ret = iommu_device_use_default_domain(dev);
+		if (ret)
+			arch_teardown_dma_ops(dev);
+	}
+
+	return ret;
+}
+
+static void fsl_mc_dma_cleanup(struct device *dev)
+{
+	struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(dev->driver);
 
-	return acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id);
+	if (!mc_drv->driver_managed_dma)
+		iommu_device_unuse_default_domain(dev);
 }
 
 static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
@@ -312,6 +331,7 @@ struct bus_type fsl_mc_bus_type = {
 	.match = fsl_mc_bus_match,
 	.uevent = fsl_mc_bus_uevent,
 	.dma_configure  = fsl_mc_dma_configure,
+	.dma_cleanup = fsl_mc_dma_cleanup,
 	.dev_groups = fsl_mc_dev_groups,
 	.bus_groups = fsl_mc_bus_groups,
 };
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 4ceeb75fc899..f83f7fbac68f 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -20,6 +20,7 @@
 #include <linux/of_device.h>
 #include <linux/acpi.h>
 #include <linux/dma-map-ops.h>
+#include <linux/iommu.h>
 #include "pci.h"
 #include "pcie/portdrv.h"
 
@@ -1601,6 +1602,7 @@ static int pci_bus_num_vf(struct device *dev)
  */
 static int pci_dma_configure(struct device *dev)
 {
+	struct pci_driver *driver = to_pci_driver(dev->driver);
 	struct device *bridge;
 	int ret = 0;
 
@@ -1616,9 +1618,24 @@ static int pci_dma_configure(struct device *dev)
 	}
 
 	pci_put_host_bridge_device(bridge);
+
+	if (!ret && !driver->driver_managed_dma) {
+		ret = iommu_device_use_default_domain(dev);
+		if (ret)
+			arch_teardown_dma_ops(dev);
+	}
+
 	return ret;
 }
 
+static void pci_dma_cleanup(struct device *dev)
+{
+	struct pci_driver *driver = to_pci_driver(dev->driver);
+
+	if (!driver->driver_managed_dma)
+		iommu_device_unuse_default_domain(dev);
+}
+
 struct bus_type pci_bus_type = {
 	.name		= "pci",
 	.match		= pci_bus_match,
@@ -1632,6 +1649,7 @@ struct bus_type pci_bus_type = {
 	.pm		= PCI_PM_OPS_PTR,
 	.num_vf		= pci_bus_num_vf,
 	.dma_configure	= pci_dma_configure,
+	.dma_cleanup	= pci_dma_cleanup,
 };
 EXPORT_SYMBOL(pci_bus_type);
 
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 6562f543c3e0..2ddce9bcd00e 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -79,6 +79,14 @@ struct amba_driver {
 	void			(*remove)(struct amba_device *);
 	void			(*shutdown)(struct amba_device *);
 	const struct amba_id	*id_table;
+	/*
+	 * For most device drivers, no need to care about this flag as long as
+	 * all DMAs are handled through the kernel DMA API. For some special
+	 * ones, for example VFIO drivers, they know how to manage the DMA
+	 * themselves and set this flag so that the IOMMU layer will allow them
+	 * to setup and manage their own I/O address space.
+	 */
+	bool driver_managed_dma;
 };
 
 /*
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 7b6c42bfb660..27efef8affb1 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -32,6 +32,13 @@ struct fsl_mc_io;
  * @shutdown: Function called at shutdown time to quiesce the device
  * @suspend: Function called when a device is stopped
  * @resume: Function called when a device is resumed
+ * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA.
+ *		For most device drivers, no need to care about this flag
+ *		as long as all DMAs are handled through the kernel DMA API.
+ *		For some special ones, for example VFIO drivers, they know
+ *		how to manage the DMA themselves and set this flag so that
+ *		the IOMMU layer will allow them to setup and manage their
+ *		own I/O address space.
  *
  * Generic DPAA device driver object for device drivers that are registered
  * with a DPRC bus. This structure is to be embedded in each device-specific
@@ -45,6 +52,7 @@ struct fsl_mc_driver {
 	void (*shutdown)(struct fsl_mc_device *dev);
 	int (*suspend)(struct fsl_mc_device *dev, pm_message_t state);
 	int (*resume)(struct fsl_mc_device *dev);
+	bool driver_managed_dma;
 };
 
 #define to_fsl_mc_driver(_drv) \
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60adf42460ab..b933d2b08d4d 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -895,6 +895,13 @@ struct module;
  *              created once it is bound to the driver.
  * @driver:	Driver model structure.
  * @dynids:	List of dynamically added device IDs.
+ * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA.
+ *		For most device drivers, no need to care about this flag
+ *		as long as all DMAs are handled through the kernel DMA API.
+ *		For some special ones, for example VFIO drivers, they know
+ *		how to manage the DMA themselves and set this flag so that
+ *		the IOMMU layer will allow them to setup and manage their
+ *		own I/O address space.
  */
 struct pci_driver {
 	struct list_head	node;
@@ -913,6 +920,7 @@ struct pci_driver {
 	const struct attribute_group **dev_groups;
 	struct device_driver	driver;
 	struct pci_dynids	dynids;
+	bool driver_managed_dma;
 };
 
 static inline struct pci_driver *to_pci_driver(struct device_driver *drv)
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 17fde717df68..b3d9c744f1e5 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -210,6 +210,14 @@ struct platform_driver {
 	struct device_driver driver;
 	const struct platform_device_id *id_table;
 	bool prevent_deferred_probe;
+	/*
+	 * For most device drivers, no need to care about this flag as long as
+	 * all DMAs are handled through the kernel DMA API. For some special
+	 * ones, for example VFIO drivers, they know how to manage the DMA
+	 * themselves and set this flag so that the IOMMU layer will allow them
+	 * to setup and manage their own I/O address space.
+	 */
+	bool driver_managed_dma;
 };
 
 #define to_platform_driver(drv)	(container_of((drv), struct platform_driver, \
-- 
cgit v1.2.3


From a5f1bd1afacd7b1e088f93f66af5453df0d8be9a Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 18 Apr 2022 08:50:00 +0800
Subject: iommu: Remove iommu group changes notifier

The iommu group changes notifer is not referenced in the tree. Remove it
to avoid dead code.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20220418005000.897664-12-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 75 ---------------------------------------------------
 include/linux/iommu.h | 23 ----------------
 2 files changed, 98 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index eba8e8ccf19d..0c42ece25854 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -18,7 +18,6 @@
 #include <linux/errno.h>
 #include <linux/iommu.h>
 #include <linux/idr.h>
-#include <linux/notifier.h>
 #include <linux/err.h>
 #include <linux/pci.h>
 #include <linux/bitops.h>
@@ -40,7 +39,6 @@ struct iommu_group {
 	struct kobject *devices_kobj;
 	struct list_head devices;
 	struct mutex mutex;
-	struct blocking_notifier_head notifier;
 	void *iommu_data;
 	void (*iommu_data_release)(void *iommu_data);
 	char *name;
@@ -632,7 +630,6 @@ struct iommu_group *iommu_group_alloc(void)
 	mutex_init(&group->mutex);
 	INIT_LIST_HEAD(&group->devices);
 	INIT_LIST_HEAD(&group->entry);
-	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
 
 	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
@@ -905,10 +902,6 @@ rename:
 	if (ret)
 		goto err_put_group;
 
-	/* Notify any listeners about change to group. */
-	blocking_notifier_call_chain(&group->notifier,
-				     IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);
-
 	trace_add_device_to_group(group->id, dev);
 
 	dev_info(dev, "Adding to iommu group %d\n", group->id);
@@ -950,10 +943,6 @@ void iommu_group_remove_device(struct device *dev)
 
 	dev_info(dev, "Removing from iommu group %d\n", group->id);
 
-	/* Pre-notify listeners that a device is being removed. */
-	blocking_notifier_call_chain(&group->notifier,
-				     IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev);
-
 	mutex_lock(&group->mutex);
 	list_for_each_entry(tmp_device, &group->devices, list) {
 		if (tmp_device->dev == dev) {
@@ -1075,36 +1064,6 @@ void iommu_group_put(struct iommu_group *group)
 }
 EXPORT_SYMBOL_GPL(iommu_group_put);
 
-/**
- * iommu_group_register_notifier - Register a notifier for group changes
- * @group: the group to watch
- * @nb: notifier block to signal
- *
- * This function allows iommu group users to track changes in a group.
- * See include/linux/iommu.h for actions sent via this notifier.  Caller
- * should hold a reference to the group throughout notifier registration.
- */
-int iommu_group_register_notifier(struct iommu_group *group,
-				  struct notifier_block *nb)
-{
-	return blocking_notifier_chain_register(&group->notifier, nb);
-}
-EXPORT_SYMBOL_GPL(iommu_group_register_notifier);
-
-/**
- * iommu_group_unregister_notifier - Unregister a notifier
- * @group: the group to watch
- * @nb: notifier block to signal
- *
- * Unregister a previously registered group notifier block.
- */
-int iommu_group_unregister_notifier(struct iommu_group *group,
-				    struct notifier_block *nb)
-{
-	return blocking_notifier_chain_unregister(&group->notifier, nb);
-}
-EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier);
-
 /**
  * iommu_register_device_fault_handler() - Register a device fault handler
  * @dev: the device
@@ -1650,14 +1609,8 @@ static int remove_iommu_group(struct device *dev, void *data)
 static int iommu_bus_notifier(struct notifier_block *nb,
 			      unsigned long action, void *data)
 {
-	unsigned long group_action = 0;
 	struct device *dev = data;
-	struct iommu_group *group;
 
-	/*
-	 * ADD/DEL call into iommu driver ops if provided, which may
-	 * result in ADD/DEL notifiers to group->notifier
-	 */
 	if (action == BUS_NOTIFY_ADD_DEVICE) {
 		int ret;
 
@@ -1668,34 +1621,6 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 		return NOTIFY_OK;
 	}
 
-	/*
-	 * Remaining BUS_NOTIFYs get filtered and republished to the
-	 * group, if anyone is listening
-	 */
-	group = iommu_group_get(dev);
-	if (!group)
-		return 0;
-
-	switch (action) {
-	case BUS_NOTIFY_BIND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER;
-		break;
-	case BUS_NOTIFY_BOUND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER;
-		break;
-	case BUS_NOTIFY_UNBIND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER;
-		break;
-	case BUS_NOTIFY_UNBOUND_DRIVER:
-		group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER;
-		break;
-	}
-
-	if (group_action)
-		blocking_notifier_call_chain(&group->notifier,
-					     group_action, dev);
-
-	iommu_group_put(group);
 	return 0;
 }
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 77972ef978b5..6ef2df258673 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -407,13 +407,6 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
 	return dev->iommu->iommu_dev->ops;
 }
 
-#define IOMMU_GROUP_NOTIFY_ADD_DEVICE		1 /* Device added */
-#define IOMMU_GROUP_NOTIFY_DEL_DEVICE		2 /* Pre Device removed */
-#define IOMMU_GROUP_NOTIFY_BIND_DRIVER		3 /* Pre Driver bind */
-#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER		4 /* Post Driver bind */
-#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER	5 /* Pre Driver unbind */
-#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER	6 /* Post Driver unbind */
-
 extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops);
 extern int bus_iommu_probe(struct bus_type *bus);
 extern bool iommu_present(struct bus_type *bus);
@@ -478,10 +471,6 @@ extern int iommu_group_for_each_dev(struct iommu_group *group, void *data,
 extern struct iommu_group *iommu_group_get(struct device *dev);
 extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group);
 extern void iommu_group_put(struct iommu_group *group);
-extern int iommu_group_register_notifier(struct iommu_group *group,
-					 struct notifier_block *nb);
-extern int iommu_group_unregister_notifier(struct iommu_group *group,
-					   struct notifier_block *nb);
 extern int iommu_register_device_fault_handler(struct device *dev,
 					iommu_dev_fault_handler_t handler,
 					void *data);
@@ -878,18 +867,6 @@ static inline void iommu_group_put(struct iommu_group *group)
 {
 }
 
-static inline int iommu_group_register_notifier(struct iommu_group *group,
-						struct notifier_block *nb)
-{
-	return -ENODEV;
-}
-
-static inline int iommu_group_unregister_notifier(struct iommu_group *group,
-						  struct notifier_block *nb)
-{
-	return 0;
-}
-
 static inline
 int iommu_register_device_fault_handler(struct device *dev,
 					iommu_dev_fault_handler_t handler,
-- 
cgit v1.2.3


From 00675017e0aeba5305665c52ded4ddce6a4c0231 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 4 Apr 2022 12:51:40 +0200
Subject: fs: add two trivial lookup helpers

Similar to the addition of lookup_one() add a version of
lookup_one_unlocked() and lookup_one_positive_unlocked() that take
idmapped mounts into account. This is required to port overlay to
support idmapped base layers.

Cc: <linux-fsdevel@vger.kernel.org>
Tested-by: Giuseppe Scrivano <gscrivan@redhat.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/namei.c            | 70 +++++++++++++++++++++++++++++++++++++++++++--------
 include/linux/namei.h |  6 +++++
 2 files changed, 66 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/namei.c b/fs/namei.c
index 3f1829b3ab5b..5f91d526a86e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2768,7 +2768,8 @@ struct dentry *lookup_one(struct user_namespace *mnt_userns, const char *name,
 EXPORT_SYMBOL(lookup_one);
 
 /**
- * lookup_one_len_unlocked - filesystem helper to lookup single pathname component
+ * lookup_one_unlocked - filesystem helper to lookup single pathname component
+ * @mnt_userns:	idmapping of the mount the lookup is performed from
  * @name:	pathname component to lookup
  * @base:	base directory to lookup from
  * @len:	maximum length @len should be interpreted to
@@ -2779,14 +2780,15 @@ EXPORT_SYMBOL(lookup_one);
  * Unlike lookup_one_len, it should be called without the parent
  * i_mutex held, and will take the i_mutex itself if necessary.
  */
-struct dentry *lookup_one_len_unlocked(const char *name,
-				       struct dentry *base, int len)
+struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns,
+				   const char *name, struct dentry *base,
+				   int len)
 {
 	struct qstr this;
 	int err;
 	struct dentry *ret;
 
-	err = lookup_one_common(&init_user_ns, name, base, len, &this);
+	err = lookup_one_common(mnt_userns, name, base, len, &this);
 	if (err)
 		return ERR_PTR(err);
 
@@ -2795,6 +2797,59 @@ struct dentry *lookup_one_len_unlocked(const char *name,
 		ret = lookup_slow(&this, base, 0);
 	return ret;
 }
+EXPORT_SYMBOL(lookup_one_unlocked);
+
+/**
+ * lookup_one_positive_unlocked - filesystem helper to lookup single
+ *				  pathname component
+ * @mnt_userns:	idmapping of the mount the lookup is performed from
+ * @name:	pathname component to lookup
+ * @base:	base directory to lookup from
+ * @len:	maximum length @len should be interpreted to
+ *
+ * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns
+ * known positive or ERR_PTR(). This is what most of the users want.
+ *
+ * Note that pinned negative with unlocked parent _can_ become positive at any
+ * time, so callers of lookup_one_unlocked() need to be very careful; pinned
+ * positives have >d_inode stable, so this one avoids such problems.
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * The helper should be called without i_mutex held.
+ */
+struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns,
+					    const char *name,
+					    struct dentry *base, int len)
+{
+	struct dentry *ret = lookup_one_unlocked(mnt_userns, name, base, len);
+
+	if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) {
+		dput(ret);
+		ret = ERR_PTR(-ENOENT);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(lookup_one_positive_unlocked);
+
+/**
+ * lookup_one_len_unlocked - filesystem helper to lookup single pathname component
+ * @name:	pathname component to lookup
+ * @base:	base directory to lookup from
+ * @len:	maximum length @len should be interpreted to
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * Unlike lookup_one_len, it should be called without the parent
+ * i_mutex held, and will take the i_mutex itself if necessary.
+ */
+struct dentry *lookup_one_len_unlocked(const char *name,
+				       struct dentry *base, int len)
+{
+	return lookup_one_unlocked(&init_user_ns, name, base, len);
+}
 EXPORT_SYMBOL(lookup_one_len_unlocked);
 
 /*
@@ -2808,12 +2863,7 @@ EXPORT_SYMBOL(lookup_one_len_unlocked);
 struct dentry *lookup_positive_unlocked(const char *name,
 				       struct dentry *base, int len)
 {
-	struct dentry *ret = lookup_one_len_unlocked(name, base, len);
-	if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) {
-		dput(ret);
-		ret = ERR_PTR(-ENOENT);
-	}
-	return ret;
+	return lookup_one_positive_unlocked(&init_user_ns, name, base, len);
 }
 EXPORT_SYMBOL(lookup_positive_unlocked);
 
diff --git a/include/linux/namei.h b/include/linux/namei.h
index e89329bb3134..caeb08a98536 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -69,6 +69,12 @@ extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
 extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int);
 extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int);
 struct dentry *lookup_one(struct user_namespace *, const char *, struct dentry *, int);
+struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns,
+				   const char *name, struct dentry *base,
+				   int len);
+struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns,
+					    const char *name,
+					    struct dentry *base, int len);
 
 extern int follow_down_one(struct path *);
 extern int follow_down(struct path *);
-- 
cgit v1.2.3


From dbde6d0c7a5a462a1767a07c28eadd2c3dd08fb2 Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Thu, 28 Apr 2022 16:51:05 +0200
Subject: hv_sock: Add validation for untrusted Hyper-V values

For additional robustness in the face of Hyper-V errors or malicious
behavior, validate all values that originate from packets that Hyper-V
has sent to the guest in the host-to-guest ring buffer.  Ensure that
invalid values cannot cause data being copied out of the bounds of the
source buffer in hvs_stream_dequeue().

Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/r/20220428145107.7878-4-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 include/linux/hyperv.h           |  5 +++++
 net/vmw_vsock/hyperv_transport.c | 10 ++++++++--
 2 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 460a716f4748..a01c9fd0a334 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1696,6 +1696,11 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc)
 	return (desc->len8 << 3) - (desc->offset8 << 3);
 }
 
+/* Get packet length associated with descriptor */
+static inline u32 hv_pkt_len(const struct vmpacket_descriptor *desc)
+{
+	return desc->len8 << 3;
+}
 
 struct vmpacket_descriptor *
 hv_pkt_iter_first_raw(struct vmbus_channel *channel);
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 8c37d07017fc..fd98229e3db3 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -577,12 +577,18 @@ static bool hvs_dgram_allow(u32 cid, u32 port)
 static int hvs_update_recv_data(struct hvsock *hvs)
 {
 	struct hvs_recv_buf *recv_buf;
-	u32 payload_len;
+	u32 pkt_len, payload_len;
+
+	pkt_len = hv_pkt_len(hvs->recv_desc);
+
+	if (pkt_len < HVS_HEADER_LEN)
+		return -EIO;
 
 	recv_buf = (struct hvs_recv_buf *)(hvs->recv_desc + 1);
 	payload_len = recv_buf->hdr.data_size;
 
-	if (payload_len > HVS_MTU_SIZE)
+	if (payload_len > pkt_len - HVS_HEADER_LEN ||
+	    payload_len > HVS_MTU_SIZE)
 		return -EIO;
 
 	if (payload_len == 0)
-- 
cgit v1.2.3


From da795eb239d9e9496812e22cb582d38a71e0789a Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Thu, 28 Apr 2022 16:51:06 +0200
Subject: Drivers: hv: vmbus: Accept hv_sock offers in isolated guests

So that isolated guests can communicate with the host via hv_sock
channels.

Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20220428145107.7878-5-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel_mgmt.c | 8 ++++++--
 include/linux/hyperv.h    | 8 ++++++--
 2 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 50fea31f019f..0db1b775e013 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -976,13 +976,17 @@ find_primary_channel_by_offer(const struct vmbus_channel_offer_channel *offer)
 	return channel;
 }
 
-static bool vmbus_is_valid_device(const guid_t *guid)
+static bool vmbus_is_valid_offer(const struct vmbus_channel_offer_channel *offer)
 {
+	const guid_t *guid = &offer->offer.if_type;
 	u16 i;
 
 	if (!hv_is_isolation_supported())
 		return true;
 
+	if (is_hvsock_offer(offer))
+		return true;
+
 	for (i = 0; i < ARRAY_SIZE(vmbus_devs); i++) {
 		if (guid_equal(guid, &vmbus_devs[i].guid))
 			return vmbus_devs[i].allowed_in_isolated;
@@ -1004,7 +1008,7 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 
 	trace_vmbus_onoffer(offer);
 
-	if (!vmbus_is_valid_device(&offer->offer.if_type)) {
+	if (!vmbus_is_valid_offer(offer)) {
 		pr_err_ratelimited("Invalid offer %d from the host supporting isolation\n",
 				   offer->child_relid);
 		atomic_dec(&vmbus_connection.offer_in_progress);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index a01c9fd0a334..b028905d8334 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1064,10 +1064,14 @@ u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id,
 			     u64 rqst_addr);
 u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id);
 
+static inline bool is_hvsock_offer(const struct vmbus_channel_offer_channel *o)
+{
+	return !!(o->offer.chn_flags & VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER);
+}
+
 static inline bool is_hvsock_channel(const struct vmbus_channel *c)
 {
-	return !!(c->offermsg.offer.chn_flags &
-		  VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER);
+	return is_hvsock_offer(&c->offermsg);
 }
 
 static inline bool is_sub_channel(const struct vmbus_channel *c)
-- 
cgit v1.2.3


From 1c9de08f7f952b4101f092802581344033d84429 Mon Sep 17 00:00:00 2001
From: "Andrea Parri (Microsoft)" <parri.andrea@gmail.com>
Date: Thu, 28 Apr 2022 16:51:07 +0200
Subject: Drivers: hv: vmbus: Refactor the ring-buffer iterator functions

With no users of hv_pkt_iter_next_raw() and no "external" users of
hv_pkt_iter_first_raw(), the iterator functions can be refactored
and simplified to remove some indirection/code.

Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20220428145107.7878-6-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/ring_buffer.c | 32 +++++++++-----------------------
 include/linux/hyperv.h   | 35 ++++-------------------------------
 2 files changed, 13 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index e101b11f95e5..59a4aa86d1f3 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -429,7 +429,7 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 	memcpy(buffer, (const char *)desc + offset, packetlen);
 
 	/* Advance ring index to next packet descriptor */
-	__hv_pkt_iter_next(channel, desc, true);
+	__hv_pkt_iter_next(channel, desc);
 
 	/* Notify host of update */
 	hv_pkt_iter_close(channel);
@@ -464,22 +464,6 @@ static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
 		return (rbi->ring_datasize - priv_read_loc) + write_loc;
 }
 
-/*
- * Get first vmbus packet without copying it out of the ring buffer
- */
-struct vmpacket_descriptor *hv_pkt_iter_first_raw(struct vmbus_channel *channel)
-{
-	struct hv_ring_buffer_info *rbi = &channel->inbound;
-
-	hv_debug_delay_test(channel, MESSAGE_DELAY);
-
-	if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
-		return NULL;
-
-	return (struct vmpacket_descriptor *)(hv_get_ring_buffer(rbi) + rbi->priv_read_index);
-}
-EXPORT_SYMBOL_GPL(hv_pkt_iter_first_raw);
-
 /*
  * Get first vmbus packet from ring buffer after read_index
  *
@@ -491,11 +475,14 @@ struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel)
 	struct vmpacket_descriptor *desc, *desc_copy;
 	u32 bytes_avail, pkt_len, pkt_offset;
 
-	desc = hv_pkt_iter_first_raw(channel);
-	if (!desc)
+	hv_debug_delay_test(channel, MESSAGE_DELAY);
+
+	bytes_avail = hv_pkt_iter_avail(rbi);
+	if (bytes_avail < sizeof(struct vmpacket_descriptor))
 		return NULL;
+	bytes_avail = min(rbi->pkt_buffer_size, bytes_avail);
 
-	bytes_avail = min(rbi->pkt_buffer_size, hv_pkt_iter_avail(rbi));
+	desc = (struct vmpacket_descriptor *)(hv_get_ring_buffer(rbi) + rbi->priv_read_index);
 
 	/*
 	 * Ensure the compiler does not use references to incoming Hyper-V values (which
@@ -542,8 +529,7 @@ EXPORT_SYMBOL_GPL(hv_pkt_iter_first);
  */
 struct vmpacket_descriptor *
 __hv_pkt_iter_next(struct vmbus_channel *channel,
-		   const struct vmpacket_descriptor *desc,
-		   bool copy)
+		   const struct vmpacket_descriptor *desc)
 {
 	struct hv_ring_buffer_info *rbi = &channel->inbound;
 	u32 packetlen = desc->len8 << 3;
@@ -556,7 +542,7 @@ __hv_pkt_iter_next(struct vmbus_channel *channel,
 		rbi->priv_read_index -= dsize;
 
 	/* more data? */
-	return copy ? hv_pkt_iter_first(channel) : hv_pkt_iter_first_raw(channel);
+	return hv_pkt_iter_first(channel);
 }
 EXPORT_SYMBOL_GPL(__hv_pkt_iter_next);
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index b028905d8334..c440c45887c2 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1706,55 +1706,28 @@ static inline u32 hv_pkt_len(const struct vmpacket_descriptor *desc)
 	return desc->len8 << 3;
 }
 
-struct vmpacket_descriptor *
-hv_pkt_iter_first_raw(struct vmbus_channel *channel);
-
 struct vmpacket_descriptor *
 hv_pkt_iter_first(struct vmbus_channel *channel);
 
 struct vmpacket_descriptor *
 __hv_pkt_iter_next(struct vmbus_channel *channel,
-		   const struct vmpacket_descriptor *pkt,
-		   bool copy);
+		   const struct vmpacket_descriptor *pkt);
 
 void hv_pkt_iter_close(struct vmbus_channel *channel);
 
 static inline struct vmpacket_descriptor *
-hv_pkt_iter_next_pkt(struct vmbus_channel *channel,
-		     const struct vmpacket_descriptor *pkt,
-		     bool copy)
+hv_pkt_iter_next(struct vmbus_channel *channel,
+		 const struct vmpacket_descriptor *pkt)
 {
 	struct vmpacket_descriptor *nxt;
 
-	nxt = __hv_pkt_iter_next(channel, pkt, copy);
+	nxt = __hv_pkt_iter_next(channel, pkt);
 	if (!nxt)
 		hv_pkt_iter_close(channel);
 
 	return nxt;
 }
 
-/*
- * Get next packet descriptor without copying it out of the ring buffer
- * If at end of list, return NULL and update host.
- */
-static inline struct vmpacket_descriptor *
-hv_pkt_iter_next_raw(struct vmbus_channel *channel,
-		     const struct vmpacket_descriptor *pkt)
-{
-	return hv_pkt_iter_next_pkt(channel, pkt, false);
-}
-
-/*
- * Get next packet descriptor from iterator
- * If at end of list, return NULL and update host.
- */
-static inline struct vmpacket_descriptor *
-hv_pkt_iter_next(struct vmbus_channel *channel,
-		 const struct vmpacket_descriptor *pkt)
-{
-	return hv_pkt_iter_next_pkt(channel, pkt, true);
-}
-
 #define foreach_vmbus_pkt(pkt, channel) \
 	for (pkt = hv_pkt_iter_first(channel); pkt; \
 	    pkt = hv_pkt_iter_next(channel, pkt))
-- 
cgit v1.2.3


From 6043257b1de069fbb5a2a52d7211c0275bc8c0e0 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 11 Apr 2022 12:16:05 -0300
Subject: iommu: Introduce the domain op enforce_cache_coherency()

This new mechanism will replace using IOMMU_CAP_CACHE_COHERENCY and
IOMMU_CACHE to control the no-snoop blocking behavior of the IOMMU.

Currently only Intel and AMD IOMMUs are known to support this
feature. They both implement it as an IOPTE bit, that when set, will cause
PCIe TLPs to that IOVA with the no-snoop bit set to be treated as though
the no-snoop bit was clear.

The new API is triggered by calling enforce_cache_coherency() before
mapping any IOVA to the domain which globally switches on no-snoop
blocking. This allows other implementations that might block no-snoop
globally and outside the IOPTE - AMD also documents such a HW capability.

Leave AMD out of sync with Intel and have it block no-snoop even for
in-kernel users. This can be trivially resolved in a follow up patch.

Only VFIO needs to call this API because it does not have detailed control
over the device to avoid requesting no-snoop behavior at the device
level. Other places using domains with real kernel drivers should simply
avoid asking their devices to set the no-snoop bit.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c   |  7 +++++++
 drivers/iommu/intel/iommu.c | 14 +++++++++++++-
 include/linux/intel-iommu.h |  1 +
 include/linux/iommu.h       |  4 ++++
 4 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 038e104b922c..840831d5d2ad 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2266,6 +2266,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	return 0;
 }
 
+static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	/* IOMMU_PTE_FC is always set */
+	return true;
+}
+
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -2288,6 +2294,7 @@ const struct iommu_ops amd_iommu_ops = {
 		.flush_iotlb_all = amd_iommu_flush_iotlb_all,
 		.iotlb_sync	= amd_iommu_iotlb_sync,
 		.free		= amd_iommu_domain_free,
+		.enforce_cache_coherency = amd_iommu_enforce_cache_coherency,
 	}
 };
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 0edf6084dc14..161199f62270 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4422,7 +4422,8 @@ static int intel_iommu_map(struct iommu_domain *domain,
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= DMA_PTE_WRITE;
-	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
+	if (((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) ||
+	    dmar_domain->force_snooping)
 		prot |= DMA_PTE_SNP;
 
 	max_addr = iova + size;
@@ -4545,6 +4546,16 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
+static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (!dmar_domain->iommu_snooping)
+		return false;
+	dmar_domain->force_snooping = true;
+	return true;
+}
+
 static bool intel_iommu_capable(enum iommu_cap cap)
 {
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
@@ -4900,6 +4911,7 @@ const struct iommu_ops intel_iommu_ops = {
 		.iotlb_sync		= intel_iommu_tlb_sync,
 		.iova_to_phys		= intel_iommu_iova_to_phys,
 		.free			= intel_iommu_domain_free,
+		.enforce_cache_coherency = intel_iommu_enforce_cache_coherency,
 	}
 };
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 2f9891cb3d00..4c2baf2446c2 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -540,6 +540,7 @@ struct dmar_domain {
 	u8 has_iotlb_device: 1;
 	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
 	u8 iommu_snooping: 1;		/* indicate snooping control feature */
+	u8 force_snooping : 1;		/* Create IOPTEs with snoop control */
 
 	struct list_head devices;	/* all devices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 4123693ae319..c7ad6b10e261 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -274,6 +274,9 @@ struct iommu_ops {
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
  * @iova_to_phys: translate iova to physical address
+ * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE,
+ *                           including no-snoop TLPs on PCIe or other platform
+ *                           specific mechanisms.
  * @enable_nesting: Enable nesting
  * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*)
  * @free: Release the domain after use.
@@ -302,6 +305,7 @@ struct iommu_domain_ops {
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    dma_addr_t iova);
 
+	bool (*enforce_cache_coherency)(struct iommu_domain *domain);
 	int (*enable_nesting)(struct iommu_domain *domain);
 	int (*set_pgtable_quirks)(struct iommu_domain *domain,
 				  unsigned long quirks);
-- 
cgit v1.2.3


From 71cfafda9c9bd9812cdb62ddb94daf65a1af12c1 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 11 Apr 2022 12:16:06 -0300
Subject: vfio: Move the Intel no-snoop control off of IOMMU_CACHE

IOMMU_CACHE means "normal DMA to this iommu_domain's IOVA should be cache
coherent" and is used by the DMA API. The definition allows for special
non-coherent DMA to exist - ie processing of the no-snoop flag in PCIe
TLPs - so long as this behavior is opt-in by the device driver.

The flag is mainly used by the DMA API to synchronize the IOMMU setting
with the expected cache behavior of the DMA master. eg based on
dev_is_dma_coherent() in some case.

For Intel IOMMU IOMMU_CACHE was redefined to mean 'force all DMA to be
cache coherent' which has the practical effect of causing the IOMMU to
ignore the no-snoop bit in a PCIe TLP.

x86 platforms are always IOMMU_CACHE, so Intel should ignore this flag.

Instead use the new domain op enforce_cache_coherency() which causes every
IOPTE created in the domain to have the no-snoop blocking behavior.

Reconfigure VFIO to always use IOMMU_CACHE and call
enforce_cache_coherency() to operate the special Intel behavior.

Remove the IOMMU_CACHE test from Intel IOMMU.

Ultimately VFIO plumbs the result of enforce_cache_coherency() back into
the x86 platform code through kvm_arch_register_noncoherent_dma() which
controls if the WBINVD instruction is available in the guest.  No other
archs implement kvm_arch_register_noncoherent_dma() nor are there any
other known consumers of VFIO_DMA_CC_IOMMU that might be affected by the
user visible result change on non-x86 archs.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/2-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c     |  7 ++-----
 drivers/vfio/vfio_iommu_type1.c | 30 +++++++++++++++++++-----------
 include/linux/intel-iommu.h     |  1 -
 3 files changed, 21 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 161199f62270..38441cb06c8c 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -641,7 +641,6 @@ static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
-	domain->iommu_snooping = domain_update_iommu_snooping(NULL);
 	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
 
 	/*
@@ -4283,7 +4282,6 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	domain->agaw = width_to_agaw(adjust_width);
 
 	domain->iommu_coherency = false;
-	domain->iommu_snooping = false;
 	domain->iommu_superpage = 0;
 	domain->max_addr = 0;
 
@@ -4422,8 +4420,7 @@ static int intel_iommu_map(struct iommu_domain *domain,
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= DMA_PTE_WRITE;
-	if (((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) ||
-	    dmar_domain->force_snooping)
+	if (dmar_domain->force_snooping)
 		prot |= DMA_PTE_SNP;
 
 	max_addr = iova + size;
@@ -4550,7 +4547,7 @@ static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 
-	if (!dmar_domain->iommu_snooping)
+	if (!domain_update_iommu_snooping(NULL))
 		return false;
 	dmar_domain->force_snooping = true;
 	return true;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 9394aa9444c1..c13b9290e357 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -84,8 +84,8 @@ struct vfio_domain {
 	struct iommu_domain	*domain;
 	struct list_head	next;
 	struct list_head	group_list;
-	int			prot;		/* IOMMU_CACHE */
-	bool			fgsp;		/* Fine-grained super pages */
+	bool			fgsp : 1;	/* Fine-grained super pages */
+	bool			enforce_cache_coherency : 1;
 };
 
 struct vfio_dma {
@@ -1461,7 +1461,7 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
 
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT,
-				npage << PAGE_SHIFT, prot | d->prot);
+				npage << PAGE_SHIFT, prot | IOMMU_CACHE);
 		if (ret)
 			goto unwind;
 
@@ -1771,7 +1771,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			}
 
 			ret = iommu_map(domain->domain, iova, phys,
-					size, dma->prot | domain->prot);
+					size, dma->prot | IOMMU_CACHE);
 			if (ret) {
 				if (!dma->iommu_mapped) {
 					vfio_unpin_pages_remote(dma, iova,
@@ -1859,7 +1859,7 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain)
 		return;
 
 	ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2,
-			IOMMU_READ | IOMMU_WRITE | domain->prot);
+			IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
 	if (!ret) {
 		size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE);
 
@@ -2267,8 +2267,15 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 		goto out_detach;
 	}
 
-	if (iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY))
-		domain->prot |= IOMMU_CACHE;
+	/*
+	 * If the IOMMU can block non-coherent operations (ie PCIe TLPs with
+	 * no-snoop set) then VFIO always turns this feature on because on Intel
+	 * platforms it optimizes KVM to disable wbinvd emulation.
+	 */
+	if (domain->domain->ops->enforce_cache_coherency)
+		domain->enforce_cache_coherency =
+			domain->domain->ops->enforce_cache_coherency(
+				domain->domain);
 
 	/*
 	 * Try to match an existing compatible domain.  We don't want to
@@ -2279,7 +2286,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	 */
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		if (d->domain->ops == domain->domain->ops &&
-		    d->prot == domain->prot) {
+		    d->enforce_cache_coherency ==
+			    domain->enforce_cache_coherency) {
 			iommu_detach_group(domain->domain, group->iommu_group);
 			if (!iommu_attach_group(d->domain,
 						group->iommu_group)) {
@@ -2611,14 +2619,14 @@ static void vfio_iommu_type1_release(void *iommu_data)
 	kfree(iommu);
 }
 
-static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)
+static int vfio_domains_have_enforce_cache_coherency(struct vfio_iommu *iommu)
 {
 	struct vfio_domain *domain;
 	int ret = 1;
 
 	mutex_lock(&iommu->lock);
 	list_for_each_entry(domain, &iommu->domain_list, next) {
-		if (!(domain->prot & IOMMU_CACHE)) {
+		if (!(domain->enforce_cache_coherency)) {
 			ret = 0;
 			break;
 		}
@@ -2641,7 +2649,7 @@ static int vfio_iommu_type1_check_extension(struct vfio_iommu *iommu,
 	case VFIO_DMA_CC_IOMMU:
 		if (!iommu)
 			return 0;
-		return vfio_domains_have_iommu_cache(iommu);
+		return vfio_domains_have_enforce_cache_coherency(iommu);
 	default:
 		return 0;
 	}
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 4c2baf2446c2..72e5d7900e71 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -539,7 +539,6 @@ struct dmar_domain {
 
 	u8 has_iotlb_device: 1;
 	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
-	u8 iommu_snooping: 1;		/* indicate snooping control feature */
 	u8 force_snooping : 1;		/* Create IOPTEs with snoop control */
 
 	struct list_head devices;	/* all devices' list */
-- 
cgit v1.2.3


From f78dc1dad829e505d83e33dc0879887f074c52e1 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 11 Apr 2022 12:16:07 -0300
Subject: iommu: Redefine IOMMU_CAP_CACHE_COHERENCY as the cap flag for
 IOMMU_CACHE

While the comment was correct that this flag was intended to convey the
block no-snoop support in the IOMMU, it has become widely implemented and
used to mean the IOMMU supports IOMMU_CACHE as a map flag. Only the Intel
driver was different.

Now that the Intel driver is using enforce_cache_coherency() update the
comment to make it clear that IOMMU_CAP_CACHE_COHERENCY is only about
IOMMU_CACHE.  Fix the Intel driver to return true since IOMMU_CACHE always
works.

The two places that test this flag, usnic and vdpa, are both assigning
userspace pages to a driver controlled iommu_domain and require
IOMMU_CACHE behavior as they offer no way for userspace to synchronize
caches.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/3-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 2 +-
 include/linux/iommu.h       | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 38441cb06c8c..efcecfa5952a 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4556,7 +4556,7 @@ static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 static bool intel_iommu_capable(enum iommu_cap cap)
 {
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
-		return domain_update_iommu_snooping(NULL);
+		return true;
 	if (cap == IOMMU_CAP_INTR_REMAP)
 		return irq_remapping_enabled == 1;
 	if (cap == IOMMU_CAP_PRE_BOOT_PROTECTION)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index c7ad6b10e261..575ab27ede5b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -103,8 +103,7 @@ static inline bool iommu_is_dma_domain(struct iommu_domain *domain)
 }
 
 enum iommu_cap {
-	IOMMU_CAP_CACHE_COHERENCY,	/* IOMMU can enforce cache coherent DMA
-					   transactions */
+	IOMMU_CAP_CACHE_COHERENCY,	/* IOMMU_CACHE is supported */
 	IOMMU_CAP_INTR_REMAP,		/* IOMMU supports interrupt isolation */
 	IOMMU_CAP_NOEXEC,		/* IOMMU_NOEXEC flag */
 	IOMMU_CAP_PRE_BOOT_PROTECTION,	/* Firmware says it used the IOMMU for
-- 
cgit v1.2.3


From 992be5d3c818fcc277db246cb409659ca82abdbe Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 30 Mar 2022 16:05:35 +0100
Subject: firmware: arm_scmi: Make name_get operations return a const

A few protocol operations are available that returns a pointer to an
internal character array representing resource name. Make those functions
return a const pointer to such array.

Link: https://lore.kernel.org/r/20220330150551.2573938-7-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/power.c | 5 +++--
 drivers/firmware/arm_scmi/reset.c | 4 ++--
 include/linux/scmi_protocol.h     | 6 ++++--
 3 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/power.c b/drivers/firmware/arm_scmi/power.c
index 0f0b94f0b624..5c04d63e7ff1 100644
--- a/drivers/firmware/arm_scmi/power.c
+++ b/drivers/firmware/arm_scmi/power.c
@@ -174,8 +174,9 @@ static int scmi_power_num_domains_get(const struct scmi_protocol_handle *ph)
 	return pi->num_domains;
 }
 
-static char *scmi_power_name_get(const struct scmi_protocol_handle *ph,
-				 u32 domain)
+static const char *
+scmi_power_name_get(const struct scmi_protocol_handle *ph,
+		    u32 domain)
 {
 	struct scmi_power_info *pi = ph->get_priv(ph);
 	struct power_dom_info *dom = pi->dom_info + domain;
diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c
index 9cdbd133db10..b823a9f64af9 100644
--- a/drivers/firmware/arm_scmi/reset.c
+++ b/drivers/firmware/arm_scmi/reset.c
@@ -126,8 +126,8 @@ static int scmi_reset_num_domains_get(const struct scmi_protocol_handle *ph)
 	return pi->num_domains;
 }
 
-static char *scmi_reset_name_get(const struct scmi_protocol_handle *ph,
-				 u32 domain)
+static const char *
+scmi_reset_name_get(const struct scmi_protocol_handle *ph, u32 domain)
 {
 	struct scmi_reset_info *pi = ph->get_priv(ph);
 
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index b87551f41f9f..ced37d1de1fe 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -146,7 +146,8 @@ struct scmi_perf_proto_ops {
  */
 struct scmi_power_proto_ops {
 	int (*num_domains_get)(const struct scmi_protocol_handle *ph);
-	char *(*name_get)(const struct scmi_protocol_handle *ph, u32 domain);
+	const char *(*name_get)(const struct scmi_protocol_handle *ph,
+				u32 domain);
 #define SCMI_POWER_STATE_TYPE_SHIFT	30
 #define SCMI_POWER_STATE_ID_MASK	(BIT(28) - 1)
 #define SCMI_POWER_STATE_PARAM(type, id) \
@@ -484,7 +485,8 @@ struct scmi_sensor_proto_ops {
  */
 struct scmi_reset_proto_ops {
 	int (*num_domains_get)(const struct scmi_protocol_handle *ph);
-	char *(*name_get)(const struct scmi_protocol_handle *ph, u32 domain);
+	const char *(*name_get)(const struct scmi_protocol_handle *ph,
+				u32 domain);
 	int (*latency_get)(const struct scmi_protocol_handle *ph, u32 domain);
 	int (*reset)(const struct scmi_protocol_handle *ph, u32 domain);
 	int (*assert)(const struct scmi_protocol_handle *ph, u32 domain);
-- 
cgit v1.2.3


From b260fccaebdc2c838e62aaef24fedf497f181d10 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 30 Mar 2022 16:05:40 +0100
Subject: firmware: arm_scmi: Add SCMI v3.1 protocol extended names support

Using the common protocol helper implementation add support for all new
SCMIv3.1 extended names commands related to all protocols with the
exception of SENSOR_AXIS_GET_NAME.

Link: https://lore.kernel.org/r/20220330150551.2573938-12-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/clock.c     | 21 ++++++++++++++++++---
 drivers/firmware/arm_scmi/perf.c      | 22 ++++++++++++++++++----
 drivers/firmware/arm_scmi/power.c     | 25 ++++++++++++++++++++-----
 drivers/firmware/arm_scmi/protocols.h |  2 ++
 drivers/firmware/arm_scmi/reset.c     | 22 ++++++++++++++++++----
 drivers/firmware/arm_scmi/sensors.c   | 15 ++++++++++++++-
 drivers/firmware/arm_scmi/voltage.c   | 14 +++++++++++++-
 include/linux/scmi_protocol.h         |  2 +-
 8 files changed, 104 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index 40a6364e5578..7a031afff389 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -16,6 +16,7 @@ enum scmi_clock_protocol_cmd {
 	CLOCK_RATE_SET = 0x5,
 	CLOCK_RATE_GET = 0x6,
 	CLOCK_CONFIG_SET = 0x7,
+	CLOCK_NAME_GET = 0x8,
 };
 
 struct scmi_msg_resp_clock_protocol_attributes {
@@ -27,7 +28,8 @@ struct scmi_msg_resp_clock_protocol_attributes {
 struct scmi_msg_resp_clock_attributes {
 	__le32 attributes;
 #define	CLOCK_ENABLE	BIT(0)
-	u8 name[SCMI_MAX_STR_SIZE];
+#define SUPPORTS_EXTENDED_NAMES(x)	((x) & BIT(29))
+	u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 	__le32 clock_enable_latency;
 };
 
@@ -108,9 +110,11 @@ scmi_clock_protocol_attributes_get(const struct scmi_protocol_handle *ph,
 }
 
 static int scmi_clock_attributes_get(const struct scmi_protocol_handle *ph,
-				     u32 clk_id, struct scmi_clock_info *clk)
+				     u32 clk_id, struct scmi_clock_info *clk,
+				     u32 version)
 {
 	int ret;
+	u32 attributes;
 	struct scmi_xfer *t;
 	struct scmi_msg_resp_clock_attributes *attr;
 
@@ -124,6 +128,7 @@ static int scmi_clock_attributes_get(const struct scmi_protocol_handle *ph,
 
 	ret = ph->xops->do_xfer(ph, t);
 	if (!ret) {
+		attributes = le32_to_cpu(attr->attributes);
 		strlcpy(clk->name, attr->name, SCMI_MAX_STR_SIZE);
 		/* Is optional field clock_enable_latency provided ? */
 		if (t->rx.len == sizeof(*attr))
@@ -132,6 +137,16 @@ static int scmi_clock_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	/*
+	 * If supported overwrite short name with the extended one;
+	 * on error just carry on and use already provided short name.
+	 */
+	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x2 &&
+	    SUPPORTS_EXTENDED_NAMES(attributes))
+		ph->hops->extended_name_get(ph, CLOCK_NAME_GET, clk_id,
+					    clk->name, SCMI_MAX_STR_SIZE);
+
 	return ret;
 }
 
@@ -400,7 +415,7 @@ static int scmi_clock_protocol_init(const struct scmi_protocol_handle *ph)
 	for (clkid = 0; clkid < cinfo->num_clocks; clkid++) {
 		struct scmi_clock_info *clk = cinfo->clk + clkid;
 
-		ret = scmi_clock_attributes_get(ph, clkid, clk);
+		ret = scmi_clock_attributes_get(ph, clkid, clk, version);
 		if (!ret)
 			scmi_clock_describe_rates_get(ph, clkid, clk);
 	}
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index 0e9703310758..9e046fd121b9 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -32,6 +32,7 @@ enum scmi_performance_protocol_cmd {
 	PERF_NOTIFY_LIMITS = 0x9,
 	PERF_NOTIFY_LEVEL = 0xa,
 	PERF_DESCRIBE_FASTCHANNEL = 0xb,
+	PERF_DOMAIN_NAME_GET = 0xc,
 };
 
 struct scmi_opp {
@@ -56,10 +57,11 @@ struct scmi_msg_resp_perf_domain_attributes {
 #define SUPPORTS_PERF_LIMIT_NOTIFY(x)	((x) & BIT(29))
 #define SUPPORTS_PERF_LEVEL_NOTIFY(x)	((x) & BIT(28))
 #define SUPPORTS_PERF_FASTCHANNELS(x)	((x) & BIT(27))
+#define SUPPORTS_EXTENDED_NAMES(x)	((x) & BIT(26))
 	__le32 rate_limit_us;
 	__le32 sustained_freq_khz;
 	__le32 sustained_perf_level;
-	    u8 name[SCMI_MAX_STR_SIZE];
+	    u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 };
 
 struct scmi_msg_perf_describe_levels {
@@ -209,9 +211,11 @@ static int scmi_perf_attributes_get(const struct scmi_protocol_handle *ph,
 
 static int
 scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
-				u32 domain, struct perf_dom_info *dom_info)
+				u32 domain, struct perf_dom_info *dom_info,
+				u32 version)
 {
 	int ret;
+	u32 flags;
 	struct scmi_xfer *t;
 	struct scmi_msg_resp_perf_domain_attributes *attr;
 
@@ -225,7 +229,7 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 
 	ret = ph->xops->do_xfer(ph, t);
 	if (!ret) {
-		u32 flags = le32_to_cpu(attr->flags);
+		flags = le32_to_cpu(attr->flags);
 
 		dom_info->set_limits = SUPPORTS_SET_LIMITS(flags);
 		dom_info->set_perf = SUPPORTS_SET_PERF_LVL(flags);
@@ -248,6 +252,16 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	/*
+	 * If supported overwrite short name with the extended one;
+	 * on error just carry on and use already provided short name.
+	 */
+	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x3 &&
+	    SUPPORTS_EXTENDED_NAMES(flags))
+		ph->hops->extended_name_get(ph, PERF_DOMAIN_NAME_GET, domain,
+					    dom_info->name, SCMI_MAX_STR_SIZE);
+
 	return ret;
 }
 
@@ -902,7 +916,7 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph)
 	for (domain = 0; domain < pinfo->num_domains; domain++) {
 		struct perf_dom_info *dom = pinfo->dom_info + domain;
 
-		scmi_perf_domain_attributes_get(ph, domain, dom);
+		scmi_perf_domain_attributes_get(ph, domain, dom, version);
 		scmi_perf_describe_levels_get(ph, domain, dom);
 
 		if (dom->perf_fastchannels)
diff --git a/drivers/firmware/arm_scmi/power.c b/drivers/firmware/arm_scmi/power.c
index e378a3eb0d07..964882cc8747 100644
--- a/drivers/firmware/arm_scmi/power.c
+++ b/drivers/firmware/arm_scmi/power.c
@@ -18,6 +18,7 @@ enum scmi_power_protocol_cmd {
 	POWER_STATE_SET = 0x4,
 	POWER_STATE_GET = 0x5,
 	POWER_STATE_NOTIFY = 0x6,
+	POWER_DOMAIN_NAME_GET = 0x8,
 };
 
 struct scmi_msg_resp_power_attributes {
@@ -33,7 +34,8 @@ struct scmi_msg_resp_power_domain_attributes {
 #define SUPPORTS_STATE_SET_NOTIFY(x)	((x) & BIT(31))
 #define SUPPORTS_STATE_SET_ASYNC(x)	((x) & BIT(30))
 #define SUPPORTS_STATE_SET_SYNC(x)	((x) & BIT(29))
-	    u8 name[SCMI_MAX_STR_SIZE];
+#define SUPPORTS_EXTENDED_NAMES(x)	((x) & BIT(27))
+	    u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 };
 
 struct scmi_power_set_state {
@@ -97,9 +99,11 @@ static int scmi_power_attributes_get(const struct scmi_protocol_handle *ph,
 
 static int
 scmi_power_domain_attributes_get(const struct scmi_protocol_handle *ph,
-				 u32 domain, struct power_dom_info *dom_info)
+				 u32 domain, struct power_dom_info *dom_info,
+				 u32 version)
 {
 	int ret;
+	u32 flags;
 	struct scmi_xfer *t;
 	struct scmi_msg_resp_power_domain_attributes *attr;
 
@@ -113,15 +117,26 @@ scmi_power_domain_attributes_get(const struct scmi_protocol_handle *ph,
 
 	ret = ph->xops->do_xfer(ph, t);
 	if (!ret) {
-		u32 flags = le32_to_cpu(attr->flags);
+		flags = le32_to_cpu(attr->flags);
 
 		dom_info->state_set_notify = SUPPORTS_STATE_SET_NOTIFY(flags);
 		dom_info->state_set_async = SUPPORTS_STATE_SET_ASYNC(flags);
 		dom_info->state_set_sync = SUPPORTS_STATE_SET_SYNC(flags);
 		strlcpy(dom_info->name, attr->name, SCMI_MAX_STR_SIZE);
 	}
-
 	ph->xops->xfer_put(ph, t);
+
+	/*
+	 * If supported overwrite short name with the extended one;
+	 * on error just carry on and use already provided short name.
+	 */
+	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x3 &&
+	    SUPPORTS_EXTENDED_NAMES(flags)) {
+		ph->hops->extended_name_get(ph, POWER_DOMAIN_NAME_GET,
+					    domain, dom_info->name,
+					    SCMI_MAX_STR_SIZE);
+	}
+
 	return ret;
 }
 
@@ -308,7 +323,7 @@ static int scmi_power_protocol_init(const struct scmi_protocol_handle *ph)
 	for (domain = 0; domain < pinfo->num_domains; domain++) {
 		struct power_dom_info *dom = pinfo->dom_info + domain;
 
-		scmi_power_domain_attributes_get(ph, domain, dom);
+		scmi_power_domain_attributes_get(ph, domain, dom, version);
 	}
 
 	pinfo->version = version;
diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h
index 5461fa333152..60ea880b3855 100644
--- a/drivers/firmware/arm_scmi/protocols.h
+++ b/drivers/firmware/arm_scmi/protocols.h
@@ -24,6 +24,8 @@
 
 #include <asm/unaligned.h>
 
+#define SCMI_SHORT_NAME_MAX_SIZE	16
+
 #define PROTOCOL_REV_MINOR_MASK	GENMASK(15, 0)
 #define PROTOCOL_REV_MAJOR_MASK	GENMASK(31, 16)
 #define PROTOCOL_REV_MAJOR(x)	((u16)(FIELD_GET(PROTOCOL_REV_MAJOR_MASK, (x))))
diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c
index cc465632aa1a..a420a9102094 100644
--- a/drivers/firmware/arm_scmi/reset.c
+++ b/drivers/firmware/arm_scmi/reset.c
@@ -17,6 +17,7 @@ enum scmi_reset_protocol_cmd {
 	RESET_DOMAIN_ATTRIBUTES = 0x3,
 	RESET = 0x4,
 	RESET_NOTIFY = 0x5,
+	RESET_DOMAIN_NAME_GET = 0x6,
 };
 
 #define NUM_RESET_DOMAIN_MASK	0xffff
@@ -26,8 +27,9 @@ struct scmi_msg_resp_reset_domain_attributes {
 	__le32 attributes;
 #define SUPPORTS_ASYNC_RESET(x)		((x) & BIT(31))
 #define SUPPORTS_NOTIFY_RESET(x)	((x) & BIT(30))
+#define SUPPORTS_EXTENDED_NAMES(x)	((x) & BIT(29))
 	__le32 latency;
-	    u8 name[SCMI_MAX_STR_SIZE];
+	u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 };
 
 struct scmi_msg_reset_domain_reset {
@@ -89,9 +91,11 @@ static int scmi_reset_attributes_get(const struct scmi_protocol_handle *ph,
 
 static int
 scmi_reset_domain_attributes_get(const struct scmi_protocol_handle *ph,
-				 u32 domain, struct reset_dom_info *dom_info)
+				 u32 domain, struct reset_dom_info *dom_info,
+				 u32 version)
 {
 	int ret;
+	u32 attributes;
 	struct scmi_xfer *t;
 	struct scmi_msg_resp_reset_domain_attributes *attr;
 
@@ -105,7 +109,7 @@ scmi_reset_domain_attributes_get(const struct scmi_protocol_handle *ph,
 
 	ret = ph->xops->do_xfer(ph, t);
 	if (!ret) {
-		u32 attributes = le32_to_cpu(attr->attributes);
+		attributes = le32_to_cpu(attr->attributes);
 
 		dom_info->async_reset = SUPPORTS_ASYNC_RESET(attributes);
 		dom_info->reset_notify = SUPPORTS_NOTIFY_RESET(attributes);
@@ -116,6 +120,16 @@ scmi_reset_domain_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	/*
+	 * If supported overwrite short name with the extended one;
+	 * on error just carry on and use already provided short name.
+	 */
+	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x3 &&
+	    SUPPORTS_EXTENDED_NAMES(attributes))
+		ph->hops->extended_name_get(ph, RESET_DOMAIN_NAME_GET, domain,
+					    dom_info->name, SCMI_MAX_STR_SIZE);
+
 	return ret;
 }
 
@@ -320,7 +334,7 @@ static int scmi_reset_protocol_init(const struct scmi_protocol_handle *ph)
 	for (domain = 0; domain < pinfo->num_domains; domain++) {
 		struct reset_dom_info *dom = pinfo->dom_info + domain;
 
-		scmi_reset_domain_attributes_get(ph, domain, dom);
+		scmi_reset_domain_attributes_get(ph, domain, dom, version);
 	}
 
 	pinfo->version = version;
diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 07c28e249f0c..6fd8b3a874ea 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -27,6 +27,7 @@ enum scmi_sensor_protocol_cmd {
 	SENSOR_CONFIG_GET = 0x9,
 	SENSOR_CONFIG_SET = 0xA,
 	SENSOR_CONTINUOUS_UPDATE_NOTIFY = 0xB,
+	SENSOR_NAME_GET = 0xC,
 };
 
 struct scmi_msg_resp_sensor_attributes {
@@ -71,6 +72,7 @@ struct scmi_msg_resp_sensor_description {
 		__le32 attributes_low;
 /* Common attributes_low macros */
 #define SUPPORTS_ASYNC_READ(x)		FIELD_GET(BIT(31), (x))
+#define SUPPORTS_EXTENDED_NAMES(x)	FIELD_GET(BIT(29), (x))
 #define NUM_TRIP_POINTS(x)		FIELD_GET(GENMASK(7, 0), (x))
 		__le32 attributes_high;
 /* Common attributes_high macros */
@@ -78,7 +80,7 @@ struct scmi_msg_resp_sensor_description {
 #define SENSOR_SCALE_SIGN		BIT(4)
 #define SENSOR_SCALE_EXTEND		GENMASK(31, 5)
 #define SENSOR_TYPE(x)			FIELD_GET(GENMASK(7, 0), (x))
-		u8 name[SCMI_MAX_STR_SIZE];
+		u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 		/* only for version > 2.0 */
 		__le32 power;
 		__le32 resolution;
@@ -519,6 +521,17 @@ static int scmi_sensor_description_get(const struct scmi_protocol_handle *ph,
 					    SCMI_MAX_NUM_SENSOR_AXIS);
 			strlcpy(s->name, sdesc->name, SCMI_MAX_STR_SIZE);
 
+			/*
+			 * If supported overwrite short name with the extended
+			 * one; on error just carry on and use already provided
+			 * short name.
+			 */
+			if (PROTOCOL_REV_MAJOR(si->version) >= 0x3 &&
+			    SUPPORTS_EXTENDED_NAMES(attrl))
+				ph->hops->extended_name_get(ph, SENSOR_NAME_GET,
+							    s->id, s->name,
+							    SCMI_MAX_STR_SIZE);
+
 			if (s->extended_scalar_attrs) {
 				s->sensor_power = le32_to_cpu(sdesc->power);
 				dsize += sizeof(sdesc->power);
diff --git a/drivers/firmware/arm_scmi/voltage.c b/drivers/firmware/arm_scmi/voltage.c
index 7aa887a7cbd2..5d58ba724eeb 100644
--- a/drivers/firmware/arm_scmi/voltage.c
+++ b/drivers/firmware/arm_scmi/voltage.c
@@ -21,13 +21,15 @@ enum scmi_voltage_protocol_cmd {
 	VOLTAGE_CONFIG_GET = 0x6,
 	VOLTAGE_LEVEL_SET = 0x7,
 	VOLTAGE_LEVEL_GET = 0x8,
+	VOLTAGE_DOMAIN_NAME_GET = 0x09,
 };
 
 #define NUM_VOLTAGE_DOMAINS(x)	((u16)(FIELD_GET(VOLTAGE_DOMS_NUM_MASK, (x))))
 
 struct scmi_msg_resp_domain_attributes {
 	__le32 attr;
-	u8 name[SCMI_MAX_STR_SIZE];
+#define SUPPORTS_EXTENDED_NAMES(x)	((x) & BIT(30))
+	u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 };
 
 struct scmi_msg_cmd_describe_levels {
@@ -149,6 +151,16 @@ static int scmi_voltage_descriptors_get(const struct scmi_protocol_handle *ph,
 		v->attributes = le32_to_cpu(resp_dom->attr);
 		strlcpy(v->name, resp_dom->name, SCMI_MAX_STR_SIZE);
 
+		/*
+		 * If supported overwrite short name with the extended one;
+		 * on error just carry on and use already provided short name.
+		 */
+		if (PROTOCOL_REV_MAJOR(vinfo->version) >= 0x2 &&
+		    SUPPORTS_EXTENDED_NAMES(v->attributes))
+			ph->hops->extended_name_get(ph, VOLTAGE_DOMAIN_NAME_GET,
+						    v->id, v->name,
+						    SCMI_MAX_STR_SIZE);
+
 		cmd = tl->tx.buf;
 		/* ...then retrieve domain levels descriptions */
 		do {
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index ced37d1de1fe..56e6f13355b8 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -13,7 +13,7 @@
 #include <linux/notifier.h>
 #include <linux/types.h>
 
-#define SCMI_MAX_STR_SIZE	16
+#define SCMI_MAX_STR_SIZE	64
 #define SCMI_MAX_NUM_RATES	16
 
 /**
-- 
cgit v1.2.3


From 7aa75496ea1f38dfd99b93c66f8d9bc525d11efc Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 30 Mar 2022 16:05:48 +0100
Subject: firmware: arm_scmi: Add SCMI v3.1 clock notifications

Add SCMI v3.1 clock pre and post notifications.

Link: https://lore.kernel.org/r/20220330150551.2573938-20-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/clock.c | 136 ++++++++++++++++++++++++++++++++++++--
 include/linux/scmi_protocol.h     |  11 +++
 2 files changed, 142 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index 5af14b0c8049..4d36a9a133d1 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -10,6 +10,7 @@
 #include <linux/sort.h>
 
 #include "protocols.h"
+#include "notify.h"
 
 enum scmi_clock_protocol_cmd {
 	CLOCK_ATTRIBUTES = 0x3,
@@ -18,6 +19,8 @@ enum scmi_clock_protocol_cmd {
 	CLOCK_RATE_GET = 0x6,
 	CLOCK_CONFIG_SET = 0x7,
 	CLOCK_NAME_GET = 0x8,
+	CLOCK_RATE_NOTIFY = 0x9,
+	CLOCK_RATE_CHANGE_REQUESTED_NOTIFY = 0xA,
 };
 
 struct scmi_msg_resp_clock_protocol_attributes {
@@ -29,7 +32,9 @@ struct scmi_msg_resp_clock_protocol_attributes {
 struct scmi_msg_resp_clock_attributes {
 	__le32 attributes;
 #define	CLOCK_ENABLE	BIT(0)
-#define SUPPORTS_EXTENDED_NAMES(x)	((x) & BIT(29))
+#define SUPPORTS_RATE_CHANGED_NOTIF(x)		((x) & BIT(31))
+#define SUPPORTS_RATE_CHANGE_REQUESTED_NOTIF(x)	((x) & BIT(30))
+#define SUPPORTS_EXTENDED_NAMES(x)		((x) & BIT(29))
 	u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 	__le32 clock_enable_latency;
 };
@@ -77,6 +82,18 @@ struct scmi_msg_resp_set_rate_complete {
 	__le32 rate_high;
 };
 
+struct scmi_msg_clock_rate_notify {
+	__le32 clk_id;
+	__le32 notify_enable;
+};
+
+struct scmi_clock_rate_notify_payld {
+	__le32 agent_id;
+	__le32 clock_id;
+	__le32 rate_low;
+	__le32 rate_high;
+};
+
 struct clock_info {
 	u32 version;
 	int num_clocks;
@@ -85,6 +102,11 @@ struct clock_info {
 	struct scmi_clock_info *clk;
 };
 
+static enum scmi_clock_protocol_cmd evt_2_cmd[] = {
+	CLOCK_RATE_NOTIFY,
+	CLOCK_RATE_CHANGE_REQUESTED_NOTIFY,
+};
+
 static int
 scmi_clock_protocol_attributes_get(const struct scmi_protocol_handle *ph,
 				   struct clock_info *ci)
@@ -144,10 +166,17 @@ static int scmi_clock_attributes_get(const struct scmi_protocol_handle *ph,
 	 * If supported overwrite short name with the extended one;
 	 * on error just carry on and use already provided short name.
 	 */
-	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x2 &&
-	    SUPPORTS_EXTENDED_NAMES(attributes))
-		ph->hops->extended_name_get(ph, CLOCK_NAME_GET, clk_id,
-					    clk->name, SCMI_MAX_STR_SIZE);
+	if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x2) {
+		if (SUPPORTS_EXTENDED_NAMES(attributes))
+			ph->hops->extended_name_get(ph, CLOCK_NAME_GET, clk_id,
+						    clk->name,
+						    SCMI_MAX_STR_SIZE);
+
+		if (SUPPORTS_RATE_CHANGED_NOTIF(attributes))
+			clk->rate_changed_notifications = true;
+		if (SUPPORTS_RATE_CHANGE_REQUESTED_NOTIF(attributes))
+			clk->rate_change_requested_notifications = true;
+	}
 
 	return ret;
 }
@@ -418,6 +447,102 @@ static const struct scmi_clk_proto_ops clk_proto_ops = {
 	.disable_atomic = scmi_clock_disable_atomic,
 };
 
+static int scmi_clk_rate_notify(const struct scmi_protocol_handle *ph,
+				u32 clk_id, int message_id, bool enable)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct scmi_msg_clock_rate_notify *notify;
+
+	ret = ph->xops->xfer_get_init(ph, message_id, sizeof(*notify), 0, &t);
+	if (ret)
+		return ret;
+
+	notify = t->tx.buf;
+	notify->clk_id = cpu_to_le32(clk_id);
+	notify->notify_enable = enable ? cpu_to_le32(BIT(0)) : 0;
+
+	ret = ph->xops->do_xfer(ph, t);
+
+	ph->xops->xfer_put(ph, t);
+	return ret;
+}
+
+static int scmi_clk_set_notify_enabled(const struct scmi_protocol_handle *ph,
+				       u8 evt_id, u32 src_id, bool enable)
+{
+	int ret, cmd_id;
+
+	if (evt_id >= ARRAY_SIZE(evt_2_cmd))
+		return -EINVAL;
+
+	cmd_id = evt_2_cmd[evt_id];
+	ret = scmi_clk_rate_notify(ph, src_id, cmd_id, enable);
+	if (ret)
+		pr_debug("FAIL_ENABLED - evt[%X] dom[%d] - ret:%d\n",
+			 evt_id, src_id, ret);
+
+	return ret;
+}
+
+static void *scmi_clk_fill_custom_report(const struct scmi_protocol_handle *ph,
+					 u8 evt_id, ktime_t timestamp,
+					 const void *payld, size_t payld_sz,
+					 void *report, u32 *src_id)
+{
+	const struct scmi_clock_rate_notify_payld *p = payld;
+	struct scmi_clock_rate_notif_report *r = report;
+
+	if (sizeof(*p) != payld_sz ||
+	    (evt_id != SCMI_EVENT_CLOCK_RATE_CHANGED &&
+	     evt_id != SCMI_EVENT_CLOCK_RATE_CHANGE_REQUESTED))
+		return NULL;
+
+	r->timestamp = timestamp;
+	r->agent_id = le32_to_cpu(p->agent_id);
+	r->clock_id = le32_to_cpu(p->clock_id);
+	r->rate = get_unaligned_le64(&p->rate_low);
+	*src_id = r->clock_id;
+
+	return r;
+}
+
+static int scmi_clk_get_num_sources(const struct scmi_protocol_handle *ph)
+{
+	struct clock_info *ci = ph->get_priv(ph);
+
+	if (!ci)
+		return -EINVAL;
+
+	return ci->num_clocks;
+}
+
+static const struct scmi_event clk_events[] = {
+	{
+		.id = SCMI_EVENT_CLOCK_RATE_CHANGED,
+		.max_payld_sz = sizeof(struct scmi_clock_rate_notify_payld),
+		.max_report_sz = sizeof(struct scmi_clock_rate_notif_report),
+	},
+	{
+		.id = SCMI_EVENT_CLOCK_RATE_CHANGE_REQUESTED,
+		.max_payld_sz = sizeof(struct scmi_clock_rate_notify_payld),
+		.max_report_sz = sizeof(struct scmi_clock_rate_notif_report),
+	},
+};
+
+static const struct scmi_event_ops clk_event_ops = {
+	.get_num_sources = scmi_clk_get_num_sources,
+	.set_notify_enabled = scmi_clk_set_notify_enabled,
+	.fill_custom_report = scmi_clk_fill_custom_report,
+};
+
+static const struct scmi_protocol_events clk_protocol_events = {
+	.queue_sz = SCMI_PROTO_QUEUE_SZ,
+	.ops = &clk_event_ops,
+	.evts = clk_events,
+	.num_events = ARRAY_SIZE(clk_events),
+};
+
 static int scmi_clock_protocol_init(const struct scmi_protocol_handle *ph)
 {
 	u32 version;
@@ -461,6 +586,7 @@ static const struct scmi_protocol scmi_clock = {
 	.owner = THIS_MODULE,
 	.instance_init = &scmi_clock_protocol_init,
 	.ops = &clk_proto_ops,
+	.events = &clk_protocol_events,
 };
 
 DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(clock, scmi_clock)
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 56e6f13355b8..0e20acc80d50 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -44,6 +44,8 @@ struct scmi_clock_info {
 	char name[SCMI_MAX_STR_SIZE];
 	unsigned int enable_latency;
 	bool rate_discrete;
+	bool rate_changed_notifications;
+	bool rate_change_requested_notifications;
 	union {
 		struct {
 			int num_rates;
@@ -744,6 +746,8 @@ void scmi_protocol_unregister(const struct scmi_protocol *proto);
 /* SCMI Notification API - Custom Event Reports */
 enum scmi_notification_events {
 	SCMI_EVENT_POWER_STATE_CHANGED = 0x0,
+	SCMI_EVENT_CLOCK_RATE_CHANGED = 0x0,
+	SCMI_EVENT_CLOCK_RATE_CHANGE_REQUESTED = 0x1,
 	SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0,
 	SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1,
 	SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0,
@@ -760,6 +764,13 @@ struct scmi_power_state_changed_report {
 	unsigned int	power_state;
 };
 
+struct scmi_clock_rate_notif_report {
+	ktime_t			timestamp;
+	unsigned int		agent_id;
+	unsigned int		clock_id;
+	unsigned long long	rate;
+};
+
 struct scmi_system_power_state_notifier_report {
 	ktime_t		timestamp;
 	unsigned int	agent_id;
-- 
cgit v1.2.3


From 4c74701b1eb7636eb0cdd66b488b42920105122a Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Wed, 30 Mar 2022 16:05:49 +0100
Subject: firmware: arm_scmi: Add SCMI v3.1 VOLTAGE_LEVEL_SET_COMPLETE

Add SCMI v3.1 voltage protocol support for asynchronous VOLTAGE_LEVEL_SET
command.

Note that, if a voltage domain is advertised to support the asynchronous
version of VOLTAGE_LEVEL_SET, the command will be issued asynchronously
unless explicitly requested to use the synchronous version by setting the
mode to SCMI_VOLTAGE_LEVEL_SET_SYNC when calling voltage_ops->level_set.

The SCMI regulator driver level_set invocation has been left unchanged
so that it will transparently use the asynchronous version if available.

Link: https://lore.kernel.org/r/20220330150551.2573938-21-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/voltage.c | 51 ++++++++++++++++++++++++++++++-------
 include/linux/scmi_protocol.h       | 12 ++++++---
 2 files changed, 51 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/voltage.c b/drivers/firmware/arm_scmi/voltage.c
index e1bdce573c4f..9d195d8719ab 100644
--- a/drivers/firmware/arm_scmi/voltage.c
+++ b/drivers/firmware/arm_scmi/voltage.c
@@ -28,6 +28,7 @@ enum scmi_voltage_protocol_cmd {
 
 struct scmi_msg_resp_domain_attributes {
 	__le32 attr;
+#define SUPPORTS_ASYNC_LEVEL_SET(x)	((x) & BIT(31))
 #define SUPPORTS_EXTENDED_NAMES(x)	((x) & BIT(30))
 	u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 };
@@ -56,6 +57,11 @@ struct scmi_msg_cmd_level_set {
 	__le32 voltage_level;
 };
 
+struct scmi_resp_voltage_level_set_complete {
+	__le32 domain_id;
+	__le32 voltage_level;
+};
+
 struct voltage_info {
 	unsigned int version;
 	unsigned int num_domains;
@@ -214,6 +220,7 @@ static int scmi_voltage_descriptors_get(const struct scmi_protocol_handle *ph,
 	resp_dom = td->rx.buf;
 
 	for (dom = 0; dom < vinfo->num_domains; dom++) {
+		u32 attributes;
 		struct scmi_voltage_info *v;
 
 		/* Retrieve domain attributes at first ... */
@@ -225,18 +232,22 @@ static int scmi_voltage_descriptors_get(const struct scmi_protocol_handle *ph,
 
 		v = vinfo->domains + dom;
 		v->id = dom;
-		v->attributes = le32_to_cpu(resp_dom->attr);
+		attributes = le32_to_cpu(resp_dom->attr);
 		strlcpy(v->name, resp_dom->name, SCMI_MAX_STR_SIZE);
 
 		/*
 		 * If supported overwrite short name with the extended one;
 		 * on error just carry on and use already provided short name.
 		 */
-		if (PROTOCOL_REV_MAJOR(vinfo->version) >= 0x2 &&
-		    SUPPORTS_EXTENDED_NAMES(v->attributes))
-			ph->hops->extended_name_get(ph, VOLTAGE_DOMAIN_NAME_GET,
-						    v->id, v->name,
-						    SCMI_MAX_STR_SIZE);
+		if (PROTOCOL_REV_MAJOR(vinfo->version) >= 0x2) {
+			if (SUPPORTS_EXTENDED_NAMES(attributes))
+				ph->hops->extended_name_get(ph,
+							VOLTAGE_DOMAIN_NAME_GET,
+							v->id, v->name,
+							SCMI_MAX_STR_SIZE);
+			if (SUPPORTS_ASYNC_LEVEL_SET(attributes))
+				v->async_level_set = true;
+		}
 
 		ret = scmi_voltage_levels_get(ph, v);
 		/* Skip invalid voltage descriptors */
@@ -308,12 +319,15 @@ static int scmi_voltage_config_get(const struct scmi_protocol_handle *ph,
 }
 
 static int scmi_voltage_level_set(const struct scmi_protocol_handle *ph,
-				  u32 domain_id, u32 flags, s32 volt_uV)
+				  u32 domain_id,
+				  enum scmi_voltage_level_mode mode,
+				  s32 volt_uV)
 {
 	int ret;
 	struct scmi_xfer *t;
 	struct voltage_info *vinfo = ph->get_priv(ph);
 	struct scmi_msg_cmd_level_set *cmd;
+	struct scmi_voltage_info *v;
 
 	if (domain_id >= vinfo->num_domains)
 		return -EINVAL;
@@ -323,12 +337,31 @@ static int scmi_voltage_level_set(const struct scmi_protocol_handle *ph,
 	if (ret)
 		return ret;
 
+	v = vinfo->domains + domain_id;
+
 	cmd = t->tx.buf;
 	cmd->domain_id = cpu_to_le32(domain_id);
-	cmd->flags = cpu_to_le32(flags);
 	cmd->voltage_level = cpu_to_le32(volt_uV);
 
-	ret = ph->xops->do_xfer(ph, t);
+	if (!v->async_level_set || mode != SCMI_VOLTAGE_LEVEL_SET_AUTO) {
+		cmd->flags = cpu_to_le32(0x0);
+		ret = ph->xops->do_xfer(ph, t);
+	} else {
+		cmd->flags = cpu_to_le32(0x1);
+		ret = ph->xops->do_xfer_with_response(ph, t);
+		if (!ret) {
+			struct scmi_resp_voltage_level_set_complete *resp;
+
+			resp = t->rx.buf;
+			if (le32_to_cpu(resp->domain_id) == domain_id)
+				dev_dbg(ph->dev,
+					"Voltage domain %d set async to %d\n",
+					v->id,
+					le32_to_cpu(resp->voltage_level));
+			else
+				ret = -EPROTO;
+		}
+	}
 
 	ph->xops->xfer_put(ph, t);
 	return ret;
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 0e20acc80d50..1c58646ba381 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -495,6 +495,11 @@ struct scmi_reset_proto_ops {
 	int (*deassert)(const struct scmi_protocol_handle *ph, u32 domain);
 };
 
+enum scmi_voltage_level_mode {
+	SCMI_VOLTAGE_LEVEL_SET_AUTO,
+	SCMI_VOLTAGE_LEVEL_SET_SYNC,
+};
+
 /**
  * struct scmi_voltage_info - describe one available SCMI Voltage Domain
  *
@@ -507,7 +512,8 @@ struct scmi_reset_proto_ops {
  *	         supported voltage level
  * @negative_volts_allowed: True if any of the entries of @levels_uv represent
  *			    a negative voltage.
- * @attributes: represents Voltage Domain advertised attributes
+ * @async_level_set: True when the voltage domain supports asynchronous level
+ *		     set commands.
  * @name: name assigned to the Voltage Domain by platform
  * @num_levels: number of total entries in @levels_uv.
  * @levels_uv: array of entries describing the available voltage levels for
@@ -517,7 +523,7 @@ struct scmi_voltage_info {
 	unsigned int id;
 	bool segmented;
 	bool negative_volts_allowed;
-	unsigned int attributes;
+	bool async_level_set;
 	char name[SCMI_MAX_STR_SIZE];
 	unsigned int num_levels;
 #define SCMI_VOLTAGE_SEGMENT_LOW	0
@@ -548,7 +554,7 @@ struct scmi_voltage_proto_ops {
 	int (*config_get)(const struct scmi_protocol_handle *ph, u32 domain_id,
 			  u32 *config);
 	int (*level_set)(const struct scmi_protocol_handle *ph, u32 domain_id,
-			 u32 flags, s32 volt_uV);
+			 enum scmi_voltage_level_mode mode, s32 volt_uV);
 	int (*level_get)(const struct scmi_protocol_handle *ph, u32 domain_id,
 			 s32 *volt_uV);
 };
-- 
cgit v1.2.3


From ac3e62f51b3fbda78a44fff62ece8f11d8f08a25 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 7 Feb 2022 15:38:40 +0100
Subject: iio: core: Clarify the modes

As part of a previous discussion with Jonathan Cameron [1], it appeared
necessary to clarify the meaning of each mode so that new developers
could understand better what they should use or not use and when.

The idea of renaming these modes as been let aside because naming is a
big deal and requires a lot of thinking. So for now let's focus on
correctly explaining what each mode implies.

[1] https://lore.kernel.org/linux-iio/20210930165510.2295e6c4@jic23-huawei/

Suggested-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20220207143840.707510-14-miquel.raynal@bootlin.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 85cb924debd9..233d2e6b7721 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -315,7 +315,54 @@ static inline bool iio_channel_has_available(const struct iio_chan_spec *chan,
 s64 iio_get_time_ns(const struct iio_dev *indio_dev);
 unsigned int iio_get_time_res(const struct iio_dev *indio_dev);
 
-/* Device operating modes */
+/*
+ * Device operating modes
+ * @INDIO_DIRECT_MODE: There is an access to either:
+ * a) The last single value available for devices that do not provide
+ *    on-demand reads.
+ * b) A new value after performing an on-demand read otherwise.
+ * On most devices, this is a single-shot read. On some devices with data
+ * streams without an 'on-demand' function, this might also be the 'last value'
+ * feature. Above all, this mode internally means that we are not in any of the
+ * other modes, and sysfs reads should work.
+ * Device drivers should inform the core if they support this mode.
+ * @INDIO_BUFFER_TRIGGERED: Common mode when dealing with kfifo buffers.
+ * It indicates that an explicit trigger is required. This requests the core to
+ * attach a poll function when enabling the buffer, which is indicated by the
+ * _TRIGGERED suffix.
+ * The core will ensure this mode is set when registering a triggered buffer
+ * with iio_triggered_buffer_setup().
+ * @INDIO_BUFFER_SOFTWARE: Another kfifo buffer mode, but not event triggered.
+ * No poll function can be attached because there is no triggered infrastructure
+ * we can use to cause capture. There is a kfifo that the driver will fill, but
+ * not "only one scan at a time". Typically, hardware will have a buffer that
+ * can hold multiple scans. Software may read one or more scans at a single time
+ * and push the available data to a Kfifo. This means the core will not attach
+ * any poll function when enabling the buffer.
+ * The core will ensure this mode is set when registering a simple kfifo buffer
+ * with devm_iio_kfifo_buffer_setup().
+ * @INDIO_BUFFER_HARDWARE: For specific hardware, if unsure do not use this mode.
+ * Same as above but this time the buffer is not a kfifo where we have direct
+ * access to the data. Instead, the consumer driver must access the data through
+ * non software visible channels (or DMA when there is no demux possible in
+ * software)
+ * The core will ensure this mode is set when registering a dmaengine buffer
+ * with devm_iio_dmaengine_buffer_setup().
+ * @INDIO_EVENT_TRIGGERED: Very unusual mode.
+ * Triggers usually refer to an external event which will start data capture.
+ * Here it is kind of the opposite as, a particular state of the data might
+ * produce an event which can be considered as an event. We don't necessarily
+ * have access to the data itself, but to the event produced. For example, this
+ * can be a threshold detector. The internal path of this mode is very close to
+ * the INDIO_BUFFER_TRIGGERED mode.
+ * The core will ensure this mode is set when registering a triggered event.
+ * @INDIO_HARDWARE_TRIGGERED: Very unusual mode.
+ * Here, triggers can result in data capture and can be routed to multiple
+ * hardware components, which make them close to regular triggers in the way
+ * they must be managed by the core, but without the entire interrupts/poll
+ * functions burden. Interrupts are irrelevant as the data flow is hardware
+ * mediated and distributed.
+ */
 #define INDIO_DIRECT_MODE		0x01
 #define INDIO_BUFFER_TRIGGERED		0x02
 #define INDIO_BUFFER_SOFTWARE		0x04
-- 
cgit v1.2.3


From cc10eee95204579fcd66fd5965073fdcbf629676 Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Wed, 13 Apr 2022 01:36:16 -0600
Subject: PCI/ACPI: add a helper for retrieving _OSC Control DWORDs

During _OSC negotiation, when the 'Control' DWORD is needed from the
result buffer after running _OSC, a couple of places performed manual
pointer arithmetic to offset into the right spot in the raw buffer.
Add a acpi_osc_ctx_get_pci_control() helper to use the #define'd
DWORD offsets to fetch the DWORDs needed from @acpi_osc_context, and
replace the above instances of the open-coded arithmetic.

Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Suggested-by: Davidlohr Bueso <dave@stgolabs.net>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed by: Adam Manzanares <a.manzanares@samsung.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lore.kernel.org/r/20220413073618.291335-2-vishal.l.verma@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/bus.c      |  2 +-
 drivers/acpi/pci_root.c |  2 +-
 include/linux/acpi.h    | 13 +++++++++++++
 3 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 3e58b613a2c4..7658acbbb2bd 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -425,7 +425,7 @@ static void acpi_bus_osc_negotiate_usb_control(void)
 	}
 
 	osc_sb_native_usb4_control =
-		control & ((u32 *)context.ret.pointer)[OSC_CONTROL_DWORD];
+		control &  acpi_osc_ctx_get_pci_control(&context);
 
 	acpi_bus_decode_usb_osc("USB4 _OSC: OS supports", control);
 	acpi_bus_decode_usb_osc("USB4 _OSC: OS controls",
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 6f9e75d14808..57be89cb3966 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -183,7 +183,7 @@ static acpi_status acpi_pci_run_osc(acpi_handle handle,
 
 	status = acpi_run_osc(handle, &context);
 	if (ACPI_SUCCESS(status)) {
-		*retval = *((u32 *)(context.ret.pointer + 8));
+		*retval = acpi_osc_ctx_get_pci_control(&context);
 		kfree(context.ret.pointer);
 	}
 	return status;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d7136d13aa44..04e5a038dd57 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -608,6 +608,13 @@ extern u32 osc_sb_native_usb4_control;
 #define OSC_PCI_EXPRESS_LTR_CONTROL		0x00000020
 #define OSC_PCI_EXPRESS_DPC_CONTROL		0x00000080
 
+static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
+{
+	u32 *ret = context->ret.pointer;
+
+	return ret[OSC_CONTROL_DWORD];
+}
+
 #define ACPI_GSB_ACCESS_ATTRIB_QUICK		0x00000002
 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV         0x00000004
 #define ACPI_GSB_ACCESS_ATTRIB_BYTE		0x00000006
@@ -1004,6 +1011,12 @@ static inline int acpi_register_wakeup_handler(int wake_irq,
 static inline void acpi_unregister_wakeup_handler(
 	bool (*wakeup)(void *context), void *context) { }
 
+struct acpi_osc_context;
+static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
+{
+	return 0;
+}
+
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
-- 
cgit v1.2.3


From 241d26bc26add2e2867c546f7474902406d37c60 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 13 Apr 2022 01:36:17 -0600
Subject: PCI/ACPI: Prefer CXL _OSC instead of PCIe _OSC for CXL host bridges

OB In preparation for negotiating OS control of CXL _OSC features, do the
minimal enabling to use CXL _OSC to handle the base PCIe feature
negotiation. Recall that CXL _OSC is a super-set of PCIe _OSC and the
CXL 2.0 specification mandates: "If a CXL Host Bridge device exposes CXL
_OSC, CXL aware OSPM shall evaluate CXL _OSC and not evaluate PCIe
_OSC."

Rather than pass a boolean flag alongside @root to all the helper
functions that need to consider PCIe specifics, add is_pcie() and
is_cxl() helper functions to check the flavor of @root. This also
allows for dynamic fallback to PCIe _OSC in cases where an attempt to
use CXL _OXC fails. This can happen on CXL 1.1 platforms that publish
ACPI0016 devices to indicate CXL host bridges, but do not publish the
optional CXL _OSC method. CXL _OSC is mandatory for CXL 2.0 hosts.

Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Robert Moore <robert.moore@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lore.kernel.org/r/20220413073618.291335-3-vishal.l.verma@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/pci_root.c | 67 ++++++++++++++++++++++++++++++++++++++-----------
 include/acpi/acpi_bus.h |  6 +++++
 include/linux/acpi.h    |  4 +++
 3 files changed, 63 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 57be89cb3966..1e683c115ee0 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -168,20 +168,45 @@ static void decode_osc_control(struct acpi_pci_root *root, char *msg, u32 word)
 			ARRAY_SIZE(pci_osc_control_bit));
 }
 
+static inline bool is_pcie(struct acpi_pci_root *root)
+{
+	return root->bridge_type == ACPI_BRIDGE_TYPE_PCIE;
+}
+
+static inline bool is_cxl(struct acpi_pci_root *root)
+{
+	return root->bridge_type == ACPI_BRIDGE_TYPE_CXL;
+}
+
 static u8 pci_osc_uuid_str[] = "33DB4D5B-1FF7-401C-9657-7441C03DD766";
+static u8 cxl_osc_uuid_str[] = "68F2D50B-C469-4d8A-BD3D-941A103FD3FC";
+
+static char *to_uuid(struct acpi_pci_root *root)
+{
+	if (is_cxl(root))
+		return cxl_osc_uuid_str;
+	return pci_osc_uuid_str;
+}
+
+static int cap_length(struct acpi_pci_root *root)
+{
+	if (is_cxl(root))
+		return sizeof(u32) * OSC_CXL_CAPABILITY_DWORDS;
+	return sizeof(u32) * OSC_PCI_CAPABILITY_DWORDS;
+}
 
-static acpi_status acpi_pci_run_osc(acpi_handle handle,
+static acpi_status acpi_pci_run_osc(struct acpi_pci_root *root,
 				    const u32 *capbuf, u32 *retval)
 {
 	struct acpi_osc_context context = {
-		.uuid_str = pci_osc_uuid_str,
+		.uuid_str = to_uuid(root),
 		.rev = 1,
-		.cap.length = 12,
+		.cap.length = cap_length(root),
 		.cap.pointer = (void *)capbuf,
 	};
 	acpi_status status;
 
-	status = acpi_run_osc(handle, &context);
+	status = acpi_run_osc(root->device->handle, &context);
 	if (ACPI_SUCCESS(status)) {
 		*retval = acpi_osc_ctx_get_pci_control(&context);
 		kfree(context.ret.pointer);
@@ -194,7 +219,7 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
 					u32 *control)
 {
 	acpi_status status;
-	u32 result, capbuf[3];
+	u32 result, capbuf[OSC_CXL_CAPABILITY_DWORDS];
 
 	support |= root->osc_support_set;
 
@@ -202,10 +227,18 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
 	capbuf[OSC_SUPPORT_DWORD] = support;
 	capbuf[OSC_CONTROL_DWORD] = *control | root->osc_control_set;
 
-	status = acpi_pci_run_osc(root->device->handle, capbuf, &result);
+retry:
+	status = acpi_pci_run_osc(root, capbuf, &result);
 	if (ACPI_SUCCESS(status)) {
 		root->osc_support_set = support;
 		*control = result;
+	} else if (is_cxl(root)) {
+		/*
+		 * CXL _OSC is optional on CXL 1.1 hosts. Fall back to PCIe _OSC
+		 * upon any failure using CXL _OSC.
+		 */
+		root->bridge_type = ACPI_BRIDGE_TYPE_PCIE;
+		goto retry;
 	}
 	return status;
 }
@@ -336,7 +369,7 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 s
 	u32 req = OSC_PCI_EXPRESS_CAPABILITY_CONTROL;
 	struct acpi_pci_root *root;
 	acpi_status status;
-	u32 ctrl, capbuf[3];
+	u32 ctrl, capbuf[OSC_CXL_CAPABILITY_DWORDS];
 
 	if (!mask)
 		return AE_BAD_PARAMETER;
@@ -373,7 +406,7 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 s
 	capbuf[OSC_QUERY_DWORD] = 0;
 	capbuf[OSC_SUPPORT_DWORD] = root->osc_support_set;
 	capbuf[OSC_CONTROL_DWORD] = ctrl;
-	status = acpi_pci_run_osc(handle, capbuf, mask);
+	status = acpi_pci_run_osc(root, capbuf, mask);
 	if (ACPI_FAILURE(status))
 		return status;
 
@@ -452,8 +485,7 @@ static bool os_control_query_checks(struct acpi_pci_root *root, u32 support)
 	return true;
 }
 
-static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm,
-				 bool is_pcie)
+static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm)
 {
 	u32 support, control = 0, requested = 0;
 	acpi_status status;
@@ -504,7 +536,7 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm,
 		*no_aspm = 1;
 
 		/* _OSC is optional for PCI host bridges */
-		if ((status == AE_NOT_FOUND) && !is_pcie)
+		if (status == AE_NOT_FOUND && !is_pcie(root))
 			return;
 
 		if (control) {
@@ -527,7 +559,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	acpi_handle handle = device->handle;
 	int no_aspm = 0;
 	bool hotadd = system_state == SYSTEM_RUNNING;
-	bool is_pcie;
+	const char *acpi_hid;
 
 	root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL);
 	if (!root)
@@ -585,8 +617,15 @@ static int acpi_pci_root_add(struct acpi_device *device,
 
 	root->mcfg_addr = acpi_pci_root_get_mcfg_addr(handle);
 
-	is_pcie = strcmp(acpi_device_hid(device), "PNP0A08") == 0;
-	negotiate_os_control(root, &no_aspm, is_pcie);
+	acpi_hid = acpi_device_hid(root->device);
+	if (strcmp(acpi_hid, "PNP0A08") == 0)
+		root->bridge_type = ACPI_BRIDGE_TYPE_PCIE;
+	else if (strcmp(acpi_hid, "ACPI0016") == 0)
+		root->bridge_type = ACPI_BRIDGE_TYPE_CXL;
+	else
+		dev_dbg(&device->dev, "Assuming non-PCIe host bridge\n");
+
+	negotiate_os_control(root, &no_aspm);
 
 	/*
 	 * TBD: Need PCI interface for enumeration/configuration of roots.
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index c4b78c21d793..305ebf2a3fa7 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -582,10 +582,16 @@ int unregister_acpi_bus_type(struct acpi_bus_type *);
 int acpi_bind_one(struct device *dev, struct acpi_device *adev);
 int acpi_unbind_one(struct device *dev);
 
+enum acpi_bridge_type {
+	ACPI_BRIDGE_TYPE_PCIE = 1,
+	ACPI_BRIDGE_TYPE_CXL,
+};
+
 struct acpi_pci_root {
 	struct acpi_device * device;
 	struct pci_bus *bus;
 	u16 segment;
+	int bridge_type;
 	struct resource secondary;	/* downstream bus range */
 
 	u32 osc_support_set;	/* _OSC state of support bits */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 04e5a038dd57..82d91d9ccce5 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -550,6 +550,10 @@ struct acpi_osc_context {
 
 acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 
+/* Number of _OSC capability DWORDS depends on bridge type */
+#define OSC_PCI_CAPABILITY_DWORDS		3
+#define OSC_CXL_CAPABILITY_DWORDS		5
+
 /* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */
 #define OSC_QUERY_DWORD				0	/* DWORD 1 */
 #define OSC_SUPPORT_DWORD			1	/* DWORD 2 */
-- 
cgit v1.2.3


From 56368029d93bbb3246ee2e03268fa6dd9754be05 Mon Sep 17 00:00:00 2001
From: Vishal Verma <vishal.l.verma@intel.com>
Date: Wed, 13 Apr 2022 01:36:18 -0600
Subject: PCI/ACPI: negotiate CXL _OSC

Add full support for negotiating _OSC as defined in the CXL 2.0 spec, as
applicable to CXL-enabled platforms. Advertise support for the CXL
features we support - 'CXL 2.0 port/device register access', 'Protocol
Error Reporting', and 'CXL Native Hot Plug'. Request control for 'CXL
Memory Error Reporting'. The requests are dependent on CONFIG_* based
prerequisites, and prior PCI enabling, similar to how the standard PCI
_OSC bits are determined.

The CXL specification does not define any additional constraints on
the hotplug flow beyond PCIe native hotplug, so a kernel that supports
native PCIe hotplug, supports CXL hotplug. For error handling protocol
and link errors just use PCIe AER. There is nascent support for
amending AER events with CXL specific status [1], but there's
otherwise no additional OS responsibility for CXL errors beyond PCIe
AER. CXL Memory Errors behave the same as typical memory errors so
CONFIG_MEMORY_FAILURE is sufficient to indicate support to platform
firmware.

[1]: https://lore.kernel.org/linux-cxl/164740402242.3912056.8303625392871313860.stgit@dwillia2-desk3.amr.corp.intel.com/

Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Robert Moore <robert.moore@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lore.kernel.org/r/20220413073618.291335-4-vishal.l.verma@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/pci_root.c | 179 +++++++++++++++++++++++++++++++++++++++++++-----
 include/acpi/acpi_bus.h |   6 +-
 include/linux/acpi.h    |  25 ++++++-
 3 files changed, 188 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 1e683c115ee0..c82ad63fffed 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -140,6 +140,17 @@ static struct pci_osc_bit_struct pci_osc_control_bit[] = {
 	{ OSC_PCI_EXPRESS_DPC_CONTROL, "DPC" },
 };
 
+static struct pci_osc_bit_struct cxl_osc_support_bit[] = {
+	{ OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT, "CXL11PortRegAccess" },
+	{ OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT, "CXL20PortDevRegAccess" },
+	{ OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT, "CXLProtocolErrorReporting" },
+	{ OSC_CXL_NATIVE_HP_SUPPORT, "CXLNativeHotPlug" },
+};
+
+static struct pci_osc_bit_struct cxl_osc_control_bit[] = {
+	{ OSC_CXL_ERROR_REPORTING_CONTROL, "CXLMemErrorReporting" },
+};
+
 static void decode_osc_bits(struct acpi_pci_root *root, char *msg, u32 word,
 			    struct pci_osc_bit_struct *table, int size)
 {
@@ -168,6 +179,18 @@ static void decode_osc_control(struct acpi_pci_root *root, char *msg, u32 word)
 			ARRAY_SIZE(pci_osc_control_bit));
 }
 
+static void decode_cxl_osc_support(struct acpi_pci_root *root, char *msg, u32 word)
+{
+	decode_osc_bits(root, msg, word, cxl_osc_support_bit,
+			ARRAY_SIZE(cxl_osc_support_bit));
+}
+
+static void decode_cxl_osc_control(struct acpi_pci_root *root, char *msg, u32 word)
+{
+	decode_osc_bits(root, msg, word, cxl_osc_control_bit,
+			ARRAY_SIZE(cxl_osc_control_bit));
+}
+
 static inline bool is_pcie(struct acpi_pci_root *root)
 {
 	return root->bridge_type == ACPI_BRIDGE_TYPE_PCIE;
@@ -196,7 +219,8 @@ static int cap_length(struct acpi_pci_root *root)
 }
 
 static acpi_status acpi_pci_run_osc(struct acpi_pci_root *root,
-				    const u32 *capbuf, u32 *retval)
+				    const u32 *capbuf, u32 *pci_control,
+				    u32 *cxl_control)
 {
 	struct acpi_osc_context context = {
 		.uuid_str = to_uuid(root),
@@ -208,18 +232,20 @@ static acpi_status acpi_pci_run_osc(struct acpi_pci_root *root,
 
 	status = acpi_run_osc(root->device->handle, &context);
 	if (ACPI_SUCCESS(status)) {
-		*retval = acpi_osc_ctx_get_pci_control(&context);
+		*pci_control = acpi_osc_ctx_get_pci_control(&context);
+		if (is_cxl(root))
+			*cxl_control = acpi_osc_ctx_get_cxl_control(&context);
 		kfree(context.ret.pointer);
 	}
 	return status;
 }
 
-static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
-					u32 support,
-					u32 *control)
+static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root, u32 support,
+				      u32 *control, u32 cxl_support,
+				      u32 *cxl_control)
 {
 	acpi_status status;
-	u32 result, capbuf[OSC_CXL_CAPABILITY_DWORDS];
+	u32 pci_result, cxl_result, capbuf[OSC_CXL_CAPABILITY_DWORDS];
 
 	support |= root->osc_support_set;
 
@@ -227,11 +253,21 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
 	capbuf[OSC_SUPPORT_DWORD] = support;
 	capbuf[OSC_CONTROL_DWORD] = *control | root->osc_control_set;
 
+	if (is_cxl(root)) {
+		cxl_support |= root->osc_ext_support_set;
+		capbuf[OSC_EXT_SUPPORT_DWORD] = cxl_support;
+		capbuf[OSC_EXT_CONTROL_DWORD] = *cxl_control | root->osc_ext_control_set;
+	}
+
 retry:
-	status = acpi_pci_run_osc(root, capbuf, &result);
+	status = acpi_pci_run_osc(root, capbuf, &pci_result, &cxl_result);
 	if (ACPI_SUCCESS(status)) {
 		root->osc_support_set = support;
-		*control = result;
+		*control = pci_result;
+		if (is_cxl(root)) {
+			root->osc_ext_support_set = cxl_support;
+			*cxl_control = cxl_result;
+		}
 	} else if (is_cxl(root)) {
 		/*
 		 * CXL _OSC is optional on CXL 1.1 hosts. Fall back to PCIe _OSC
@@ -354,6 +390,8 @@ EXPORT_SYMBOL_GPL(acpi_get_pci_dev);
  * @handle: ACPI handle of a PCI root bridge (or PCIe Root Complex).
  * @mask: Mask of _OSC bits to request control of, place to store control mask.
  * @support: _OSC supported capability.
+ * @cxl_mask: Mask of CXL _OSC control bits, place to store control mask.
+ * @cxl_support: CXL _OSC supported capability.
  *
  * Run _OSC query for @mask and if that is successful, compare the returned
  * mask of control bits with @req.  If all of the @req bits are set in the
@@ -364,12 +402,14 @@ EXPORT_SYMBOL_GPL(acpi_get_pci_dev);
  * _OSC bits the BIOS has granted control of, but its contents are meaningless
  * on failure.
  **/
-static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 support)
+static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask,
+					    u32 support, u32 *cxl_mask,
+					    u32 cxl_support)
 {
 	u32 req = OSC_PCI_EXPRESS_CAPABILITY_CONTROL;
 	struct acpi_pci_root *root;
 	acpi_status status;
-	u32 ctrl, capbuf[OSC_CXL_CAPABILITY_DWORDS];
+	u32 ctrl, cxl_ctrl = 0, capbuf[OSC_CXL_CAPABILITY_DWORDS];
 
 	if (!mask)
 		return AE_BAD_PARAMETER;
@@ -381,20 +421,42 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 s
 	ctrl   = *mask;
 	*mask |= root->osc_control_set;
 
+	if (is_cxl(root)) {
+		cxl_ctrl = *cxl_mask;
+		*cxl_mask |= root->osc_ext_control_set;
+	}
+
 	/* Need to check the available controls bits before requesting them. */
 	do {
-		status = acpi_pci_query_osc(root, support, mask);
+		u32 pci_missing = 0, cxl_missing = 0;
+
+		status = acpi_pci_query_osc(root, support, mask, cxl_support,
+					    cxl_mask);
 		if (ACPI_FAILURE(status))
 			return status;
-		if (ctrl == *mask)
-			break;
-		decode_osc_control(root, "platform does not support",
-				   ctrl & ~(*mask));
+		if (is_cxl(root)) {
+			if (ctrl == *mask && cxl_ctrl == *cxl_mask)
+				break;
+			pci_missing = ctrl & ~(*mask);
+			cxl_missing = cxl_ctrl & ~(*cxl_mask);
+		} else {
+			if (ctrl == *mask)
+				break;
+			pci_missing = ctrl & ~(*mask);
+		}
+		if (pci_missing)
+			decode_osc_control(root, "platform does not support",
+					   pci_missing);
+		if (cxl_missing)
+			decode_cxl_osc_control(root, "CXL platform does not support",
+					   cxl_missing);
 		ctrl = *mask;
-	} while (*mask);
+		cxl_ctrl = *cxl_mask;
+	} while (*mask || *cxl_mask);
 
 	/* No need to request _OSC if the control was already granted. */
-	if ((root->osc_control_set & ctrl) == ctrl)
+	if ((root->osc_control_set & ctrl) == ctrl &&
+	    (root->osc_ext_control_set & cxl_ctrl) == cxl_ctrl)
 		return AE_OK;
 
 	if ((ctrl & req) != req) {
@@ -406,11 +468,17 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 s
 	capbuf[OSC_QUERY_DWORD] = 0;
 	capbuf[OSC_SUPPORT_DWORD] = root->osc_support_set;
 	capbuf[OSC_CONTROL_DWORD] = ctrl;
-	status = acpi_pci_run_osc(root, capbuf, mask);
+	if (is_cxl(root)) {
+		capbuf[OSC_EXT_SUPPORT_DWORD] = root->osc_ext_support_set;
+		capbuf[OSC_EXT_CONTROL_DWORD] = cxl_ctrl;
+	}
+
+	status = acpi_pci_run_osc(root, capbuf, mask, cxl_mask);
 	if (ACPI_FAILURE(status))
 		return status;
 
 	root->osc_control_set = *mask;
+	root->osc_ext_control_set = *cxl_mask;
 	return AE_OK;
 }
 
@@ -436,6 +504,53 @@ static u32 calculate_support(void)
 	return support;
 }
 
+/*
+ * Background on hotplug support, and making it depend on only
+ * CONFIG_HOTPLUG_PCI_PCIE vs. also considering CONFIG_MEMORY_HOTPLUG:
+ *
+ * CONFIG_ACPI_HOTPLUG_MEMORY does depend on CONFIG_MEMORY_HOTPLUG, but
+ * there is no existing _OSC for memory hotplug support. The reason is that
+ * ACPI memory hotplug requires the OS to acknowledge / coordinate with
+ * memory plug events via a scan handler. On the CXL side the equivalent
+ * would be if Linux supported the Mechanical Retention Lock [1], or
+ * otherwise had some coordination for the driver of a PCI device
+ * undergoing hotplug to be consulted on whether the hotplug should
+ * proceed or not.
+ *
+ * The concern is that if Linux says no to supporting CXL hotplug then
+ * the BIOS may say no to giving the OS hotplug control of any other PCIe
+ * device. So the question here is not whether hotplug is enabled, it's
+ * whether it is handled natively by the at all OS, and if
+ * CONFIG_HOTPLUG_PCI_PCIE is enabled then the answer is "yes".
+ *
+ * Otherwise, the plan for CXL coordinated remove, since the kernel does
+ * not support blocking hotplug, is to require the memory device to be
+ * disabled before hotplug is attempted. When CONFIG_MEMORY_HOTPLUG is
+ * disabled that step will fail and the remove attempt cancelled by the
+ * user. If that is not honored and the card is removed anyway then it
+ * does not matter if CONFIG_MEMORY_HOTPLUG is enabled or not, it will
+ * cause a crash and other badness.
+ *
+ * Therefore, just say yes to CXL hotplug and require removal to
+ * be coordinated by userspace unless and until the kernel grows better
+ * mechanisms for doing "managed" removal of devices in consultation with
+ * the driver.
+ *
+ * [1]: https://lore.kernel.org/all/20201122014203.4706-1-ashok.raj@intel.com/
+ */
+static u32 calculate_cxl_support(void)
+{
+	u32 support;
+
+	support = OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT;
+	if (pci_aer_available())
+		support |= OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT;
+	if (IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE))
+		support |= OSC_CXL_NATIVE_HP_SUPPORT;
+
+	return support;
+}
+
 static u32 calculate_control(void)
 {
 	u32 control;
@@ -467,6 +582,16 @@ static u32 calculate_control(void)
 	return control;
 }
 
+static u32 calculate_cxl_control(void)
+{
+	u32 control = 0;
+
+	if (IS_ENABLED(CONFIG_MEMORY_FAILURE))
+		control |= OSC_CXL_ERROR_REPORTING_CONTROL;
+
+	return control;
+}
+
 static bool os_control_query_checks(struct acpi_pci_root *root, u32 support)
 {
 	struct acpi_device *device = root->device;
@@ -488,6 +613,7 @@ static bool os_control_query_checks(struct acpi_pci_root *root, u32 support)
 static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm)
 {
 	u32 support, control = 0, requested = 0;
+	u32 cxl_support = 0, cxl_control = 0, cxl_requested = 0;
 	acpi_status status;
 	struct acpi_device *device = root->device;
 	acpi_handle handle = device->handle;
@@ -511,10 +637,20 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm)
 	if (os_control_query_checks(root, support))
 		requested = control = calculate_control();
 
-	status = acpi_pci_osc_control_set(handle, &control, support);
+	if (is_cxl(root)) {
+		cxl_support = calculate_cxl_support();
+		decode_cxl_osc_support(root, "OS supports", cxl_support);
+		cxl_requested = cxl_control = calculate_cxl_control();
+	}
+
+	status = acpi_pci_osc_control_set(handle, &control, support,
+					  &cxl_control, cxl_support);
 	if (ACPI_SUCCESS(status)) {
 		if (control)
 			decode_osc_control(root, "OS now controls", control);
+		if (cxl_control)
+			decode_cxl_osc_control(root, "OS now controls",
+					   cxl_control);
 
 		if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) {
 			/*
@@ -543,6 +679,11 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm)
 			decode_osc_control(root, "OS requested", requested);
 			decode_osc_control(root, "platform willing to grant", control);
 		}
+		if (cxl_control) {
+			decode_cxl_osc_control(root, "OS requested", cxl_requested);
+			decode_cxl_osc_control(root, "platform willing to grant",
+					   cxl_control);
+		}
 
 		dev_info(&device->dev, "_OSC: platform retains control of PCIe features (%s)\n",
 			 acpi_format_exception(status));
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 305ebf2a3fa7..4c463ae2777b 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -594,8 +594,10 @@ struct acpi_pci_root {
 	int bridge_type;
 	struct resource secondary;	/* downstream bus range */
 
-	u32 osc_support_set;	/* _OSC state of support bits */
-	u32 osc_control_set;	/* _OSC state of control bits */
+	u32 osc_support_set;		/* _OSC state of support bits */
+	u32 osc_control_set;		/* _OSC state of control bits */
+	u32 osc_ext_support_set;	/* _OSC state of extended support bits */
+	u32 osc_ext_control_set;	/* _OSC state of extended control bits */
 	phys_addr_t mcfg_addr;
 };
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 82d91d9ccce5..378a431666b3 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -554,10 +554,12 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 #define OSC_PCI_CAPABILITY_DWORDS		3
 #define OSC_CXL_CAPABILITY_DWORDS		5
 
-/* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */
+/* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */
 #define OSC_QUERY_DWORD				0	/* DWORD 1 */
 #define OSC_SUPPORT_DWORD			1	/* DWORD 2 */
 #define OSC_CONTROL_DWORD			2	/* DWORD 3 */
+#define OSC_EXT_SUPPORT_DWORD			3	/* DWORD 4 */
+#define OSC_EXT_CONTROL_DWORD			4	/* DWORD 5 */
 
 /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */
 #define OSC_QUERY_ENABLE			0x00000001  /* input */
@@ -612,6 +614,15 @@ extern u32 osc_sb_native_usb4_control;
 #define OSC_PCI_EXPRESS_LTR_CONTROL		0x00000020
 #define OSC_PCI_EXPRESS_DPC_CONTROL		0x00000080
 
+/* CXL _OSC: Capabilities DWORD 4: Support Field */
+#define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT	0x00000001
+#define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT	0x00000002
+#define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT	0x00000004
+#define OSC_CXL_NATIVE_HP_SUPPORT		0x00000008
+
+/* CXL _OSC: Capabilities DWORD 5: Control Field */
+#define OSC_CXL_ERROR_REPORTING_CONTROL		0x00000001
+
 static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
 {
 	u32 *ret = context->ret.pointer;
@@ -619,6 +630,13 @@ static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
 	return ret[OSC_CONTROL_DWORD];
 }
 
+static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context)
+{
+	u32 *ret = context->ret.pointer;
+
+	return ret[OSC_EXT_CONTROL_DWORD];
+}
+
 #define ACPI_GSB_ACCESS_ATTRIB_QUICK		0x00000002
 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV         0x00000004
 #define ACPI_GSB_ACCESS_ATTRIB_BYTE		0x00000006
@@ -1021,6 +1039,11 @@ static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
 	return 0;
 }
 
+static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context)
+{
+	return 0;
+}
+
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
-- 
cgit v1.2.3


From d864b8ea6468cf1dce614a58eec92a23d8e07fec Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 26 Apr 2022 12:22:44 -0700
Subject: cxl/acpi: Add root device lockdep validation

The CXL "root" device, ACPI0017, is an attach point for coordinating
platform level CXL resources and is the parent device for a CXL port
topology tree. As such it has distinct locking rules relative to other
CXL subsystem objects, but because it is an ACPI device the lock class
is established well before it is given to the cxl_acpi driver.

However, the lockdep API does support changing the lock class "live" for
situations like this. Add a device_lock_set_class() helper that a driver
can use in ->probe() to set a custom lock class, and
device_lock_reset_class() to return to the default "no validate" class
before the custom lock class key goes out of scope after ->remove().

Note the helpers are all macros to support dead code elimination in the
CONFIG_PROVE_LOCKING=n case, however device_set_lock_class() still needs
#ifdef CONFIG_PROVE_LOCKING since lockdep_match_class() explicitly does
not have a helper in the CONFIG_PROVE_LOCKING=n case (see comment in
lockdep.h). The lockdep API needs 2 small tweaks to prevent "unused"
warnings for the @key argument to lock_set_class(), and a new
lock_set_novalidate_class() is added to supplement
lockdep_set_novalidate_class() in the cases where the lock class is
converted while the lock is held.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Alison Schofield <alison.schofield@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Ben Widawsky <ben.widawsky@intel.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/165100081305.1528964.11138612430659737238.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/acpi.c      | 13 +++++++++++++
 include/linux/device.h  | 43 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/lockdep.h |  6 +++++-
 3 files changed, 61 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index d15a6aec0331..40286f5df812 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -275,6 +275,13 @@ static int add_root_nvdimm_bridge(struct device *match, void *data)
 	return 1;
 }
 
+static struct lock_class_key cxl_root_key;
+
+static void cxl_acpi_lock_reset_class(void *dev)
+{
+	device_lock_reset_class(dev);
+}
+
 static int cxl_acpi_probe(struct platform_device *pdev)
 {
 	int rc;
@@ -283,6 +290,12 @@ static int cxl_acpi_probe(struct platform_device *pdev)
 	struct acpi_device *adev = ACPI_COMPANION(host);
 	struct cxl_cfmws_context ctx;
 
+	device_lock_set_class(&pdev->dev, &cxl_root_key);
+	rc = devm_add_action_or_reset(&pdev->dev, cxl_acpi_lock_reset_class,
+				      &pdev->dev);
+	if (rc)
+		return rc;
+
 	root_port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL);
 	if (IS_ERR(root_port))
 		return PTR_ERR(root_port);
diff --git a/include/linux/device.h b/include/linux/device.h
index 93459724dcde..833b0b3b0193 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -850,6 +850,49 @@ static inline bool device_supports_offline(struct device *dev)
 	return dev->bus && dev->bus->offline && dev->bus->online;
 }
 
+#define __device_lock_set_class(dev, name, key)                        \
+do {                                                                   \
+	struct device *__d2 __maybe_unused = dev;                      \
+	lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \
+} while (0)
+
+/**
+ * device_lock_set_class - Specify a temporary lock class while a device
+ *			   is attached to a driver
+ * @dev: device to modify
+ * @key: lock class key data
+ *
+ * This must be called with the device_lock() already held, for example
+ * from driver ->probe(). Take care to only override the default
+ * lockdep_no_validate class.
+ */
+#ifdef CONFIG_LOCKDEP
+#define device_lock_set_class(dev, key)                                    \
+do {                                                                       \
+	struct device *__d = dev;                                          \
+	dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex,               \
+						&__lockdep_no_validate__), \
+		 "overriding existing custom lock class\n");               \
+	__device_lock_set_class(__d, #key, key);                           \
+} while (0)
+#else
+#define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key)
+#endif
+
+/**
+ * device_lock_reset_class - Return a device to the default lockdep novalidate state
+ * @dev: device to modify
+ *
+ * This must be called with the device_lock() already held, for example
+ * from driver ->remove().
+ */
+#define device_lock_reset_class(dev) \
+do { \
+	struct device *__d __maybe_unused = dev;                       \
+	lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex",  \
+				  _THIS_IP_);                          \
+} while (0)
+
 void lock_device_hotplug(void);
 void unlock_device_hotplug(void);
 int lock_device_hotplug_sysfs(void);
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 467b94257105..43b0dc6a0b21 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -290,6 +290,9 @@ extern void lock_set_class(struct lockdep_map *lock, const char *name,
 			   struct lock_class_key *key, unsigned int subclass,
 			   unsigned long ip);
 
+#define lock_set_novalidate_class(l, n, i) \
+	lock_set_class(l, n, &__lockdep_no_validate__, 0, i)
+
 static inline void lock_set_subclass(struct lockdep_map *lock,
 		unsigned int subclass, unsigned long ip)
 {
@@ -357,7 +360,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
 # define lock_acquire(l, s, t, r, c, n, i)	do { } while (0)
 # define lock_release(l, i)			do { } while (0)
 # define lock_downgrade(l, i)			do { } while (0)
-# define lock_set_class(l, n, k, s, i)		do { } while (0)
+# define lock_set_class(l, n, key, s, i)	do { (void)(key); } while (0)
+# define lock_set_novalidate_class(l, n, i)	do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
 # define lockdep_init()				do { } while (0)
 # define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \
-- 
cgit v1.2.3


From fd3abd2cafa46955846d731b9a6ded2c19ab73d8 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 21 Apr 2022 08:33:45 -0700
Subject: device-core: Kill the lockdep_mutex

Per Peter [1], the lockdep API has native support for all the use cases
lockdep_mutex was attempting to enable. Now that all lockdep_mutex users
have been converted to those APIs, drop this lock.

Link: https://lore.kernel.org/r/Ylf0dewci8myLvoW@hirez.programming.kicks-ass.net [1]
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/165055522548.3745911.14298368286915484086.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/base/core.c    | 3 ---
 include/linux/device.h | 5 -----
 2 files changed, 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 3d6430eb0c6a..2eede2ec3d64 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2864,9 +2864,6 @@ void device_initialize(struct device *dev)
 	kobject_init(&dev->kobj, &device_ktype);
 	INIT_LIST_HEAD(&dev->dma_pools);
 	mutex_init(&dev->mutex);
-#ifdef CONFIG_PROVE_LOCKING
-	mutex_init(&dev->lockdep_mutex);
-#endif
 	lockdep_set_novalidate_class(&dev->mutex);
 	spin_lock_init(&dev->devres_lock);
 	INIT_LIST_HEAD(&dev->devres_head);
diff --git a/include/linux/device.h b/include/linux/device.h
index 833b0b3b0193..073f1b0126ac 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -400,8 +400,6 @@ struct dev_msi_info {
  * 		This identifies the device type and carries type-specific
  * 		information.
  * @mutex:	Mutex to synchronize calls to its driver.
- * @lockdep_mutex: An optional debug lock that a subsystem can use as a
- * 		peer lock to gain localized lockdep coverage of the device_lock.
  * @bus:	Type of bus device is on.
  * @driver:	Which driver has allocated this
  * @platform_data: Platform data specific to the device.
@@ -499,9 +497,6 @@ struct device {
 					   core doesn't touch it */
 	void		*driver_data;	/* Driver data, set and get with
 					   dev_set_drvdata/dev_get_drvdata */
-#ifdef CONFIG_PROVE_LOCKING
-	struct mutex		lockdep_mutex;
-#endif
 	struct mutex		mutex;	/* mutex to synchronize calls to
 					 * its driver.
 					 */
-- 
cgit v1.2.3


From 9096bbe951ddd3f9dc813e73b5bde6d5715d1cdb Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 28 Apr 2022 23:15:58 -0700
Subject: mm: shmem: make shmem_init return void

The return value of shmem_init is never used.  So we can make it return
void now.

[akpm@linux-foundation.org: remove `return;' from void-returning function, per Muchun Song]
Link: https://lkml.kernel.org/r/20220328112707.22217-1-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/shmem_fs.h | 2 +-
 mm/shmem.c               | 9 +++------
 2 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index ab51d3cd39bd..3e915cc550bc 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -56,7 +56,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode)
  * Functions in mm/shmem.c called directly from elsewhere:
  */
 extern const struct fs_parameter_spec shmem_fs_parameters[];
-extern int shmem_init(void);
+extern void shmem_init(void);
 extern int shmem_init_fs_context(struct fs_context *fc);
 extern struct file *shmem_file_setup(const char *name,
 					loff_t size, unsigned long flags);
diff --git a/mm/shmem.c b/mm/shmem.c
index 4b2fea33158e..e504d734177b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3888,7 +3888,7 @@ static struct file_system_type shmem_fs_type = {
 	.fs_flags	= FS_USERNS_MOUNT,
 };
 
-int __init shmem_init(void)
+void __init shmem_init(void)
 {
 	int error;
 
@@ -3913,14 +3913,13 @@ int __init shmem_init(void)
 	else
 		shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */
 #endif
-	return 0;
+	return;
 
 out1:
 	unregister_filesystem(&shmem_fs_type);
 out2:
 	shmem_destroy_inodecache();
 	shm_mnt = ERR_PTR(error);
-	return error;
 }
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS)
@@ -3998,14 +3997,12 @@ static struct file_system_type shmem_fs_type = {
 	.fs_flags	= FS_USERNS_MOUNT,
 };
 
-int __init shmem_init(void)
+void __init shmem_init(void)
 {
 	BUG_ON(register_filesystem(&shmem_fs_type) != 0);
 
 	shm_mnt = kern_mount(&shmem_fs_type);
 	BUG_ON(IS_ERR(shm_mnt));
-
-	return 0;
 }
 
 int shmem_unuse(unsigned int type)
-- 
cgit v1.2.3


From ef7a4ffc4c7f969d61e297c53cb2de1d6f012a11 Mon Sep 17 00:00:00 2001
From: Lu Jialin <lujialin4@huawei.com>
Date: Thu, 28 Apr 2022 23:16:00 -0700
Subject: mm/memcontrol.c: make cgroup_memory_noswap static

cgroup_memory_noswap is only used in mm/memcontrol.c, therefore just make
it static, and remove export in include/linux/memcontrol.h

Link: https://lkml.kernel.org/r/20220421124736.62180-1-lujialin4@huawei.com
Signed-off-by: Lu Jialin <lujialin4@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h | 4 ----
 mm/memcontrol.c            | 2 +-
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 89b14729d59f..fe580cb96683 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -937,10 +937,6 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
 					    struct mem_cgroup *oom_domain);
 void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
 
-#ifdef CONFIG_MEMCG_SWAP
-extern bool cgroup_memory_noswap;
-#endif
-
 void folio_memcg_lock(struct folio *folio);
 void folio_memcg_unlock(struct folio *folio);
 void lock_page_memcg(struct page *page);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b2d5c6618c8a..5cf5e32de313 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -89,7 +89,7 @@ static bool cgroup_memory_nokmem __ro_after_init;
 
 /* Whether the swap controller is active */
 #ifdef CONFIG_MEMCG_SWAP
-bool cgroup_memory_noswap __ro_after_init;
+static bool cgroup_memory_noswap __ro_after_init;
 #else
 #define cgroup_memory_noswap		1
 #endif
-- 
cgit v1.2.3


From 2ba2b008a8bf5fd268a43d03ba79e0ad464d6836 Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Date: Thu, 28 Apr 2022 23:16:02 -0700
Subject: Revert "mm/memory-failure.c: fix race with changing page compound
 again"

Reverts commit 888af2701db7 ("mm/memory-failure.c: fix race with changing
page compound again") because now we fetch the page refcount under
hugetlb_lock in try_memory_failure_hugetlb() so that the race check is no
longer necessary.

Link: https://lkml.kernel.org/r/20220408135323.1559401-4-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Suggested-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h      |  1 -
 include/ras/ras_event.h |  1 -
 mm/memory-failure.c     | 11 -----------
 3 files changed, 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9f44254af8ce..d446e834a3e5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3251,7 +3251,6 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_DAX,
 	MF_MSG_UNSPLIT_THP,
-	MF_MSG_DIFFERENT_PAGE_SIZE,
 	MF_MSG_UNKNOWN,
 };
 
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 1e694fd239b9..d0337a41141c 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -374,7 +374,6 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_BUDDY, "free buddy page" )				\
 	EM ( MF_MSG_DAX, "dax page" )					\
 	EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" )			\
-	EM ( MF_MSG_DIFFERENT_PAGE_SIZE, "different page size" )	\
 	EMe ( MF_MSG_UNKNOWN, "unknown page" )
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 44510efd0829..8af37f76e7ba 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -733,7 +733,6 @@ static const char * const action_page_types[] = {
 	[MF_MSG_BUDDY]			= "free buddy page",
 	[MF_MSG_DAX]			= "dax page",
 	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
-	[MF_MSG_DIFFERENT_PAGE_SIZE]	= "different page size",
 	[MF_MSG_UNKNOWN]		= "unknown page",
 };
 
@@ -1605,16 +1604,6 @@ retry:
 		return res == MF_RECOVERED ? 0 : -EBUSY;
 	}
 
-	/*
-	 * The page could have changed compound pages due to race window.
-	 * If this happens just bail out.
-	 */
-	if (!PageHuge(p) || compound_head(p) != head) {
-		action_result(pfn, MF_MSG_DIFFERENT_PAGE_SIZE, MF_IGNORED);
-		res = -EBUSY;
-		goto out;
-	}
-
 	page_flags = head->flags;
 
 	/*
-- 
cgit v1.2.3


From 7d6e2d96384556a4f30547803be1f606eb805a62 Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 28 Apr 2022 23:16:09 -0700
Subject: mm: untangle config dependencies for demote-on-reclaim

At the time demote-on-reclaim was introduced, it was tied to
CONFIG_HOTPLUG_CPU + CONFIG_MIGRATE, but that is not really accurate.

The only two things we need to depend on are CONFIG_NUMA + CONFIG_MIGRATE,
so clean this up.  Furthermore, we only register the hotplug memory
notifier when the system has CONFIG_MEMORY_HOTPLUG.

Link: https://lkml.kernel.org/r/20220322224016.4574-1-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Suggested-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/migrate.h | 34 +++++++++++++++-------------------
 mm/migrate.c            | 11 ++++++-----
 mm/vmstat.c             |  2 --
 3 files changed, 21 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 90e75d5a54d6..2707bfd43a0d 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -47,17 +47,8 @@ void folio_migrate_copy(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);
 
-extern bool numa_demotion_enabled;
-extern void migrate_on_reclaim_init(void);
-#ifdef CONFIG_HOTPLUG_CPU
-extern void set_migration_target_nodes(void);
-#else
-static inline void set_migration_target_nodes(void) {}
-#endif
 #else
 
-static inline void set_migration_target_nodes(void) {}
-
 static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t new,
 		free_page_t free, unsigned long private, enum migrate_mode mode,
@@ -82,9 +73,23 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 	return -ENOSYS;
 }
 
-#define numa_demotion_enabled	false
 #endif /* CONFIG_MIGRATION */
 
+#if defined(CONFIG_MIGRATION) && defined(CONFIG_NUMA)
+extern void set_migration_target_nodes(void);
+extern void migrate_on_reclaim_init(void);
+extern bool numa_demotion_enabled;
+extern int next_demotion_node(int node);
+#else
+static inline void set_migration_target_nodes(void) {}
+static inline void migrate_on_reclaim_init(void) {}
+static inline int next_demotion_node(int node)
+{
+        return NUMA_NO_NODE;
+}
+#define numa_demotion_enabled  false
+#endif
+
 #ifdef CONFIG_COMPACTION
 extern int PageMovable(struct page *page);
 extern void __SetPageMovable(struct page *page, struct address_space *mapping);
@@ -172,15 +177,6 @@ struct migrate_vma {
 int migrate_vma_setup(struct migrate_vma *args);
 void migrate_vma_pages(struct migrate_vma *migrate);
 void migrate_vma_finalize(struct migrate_vma *migrate);
-int next_demotion_node(int node);
-
-#else /* CONFIG_MIGRATION disabled: */
-
-static inline int next_demotion_node(int node)
-{
-	return NUMA_NO_NODE;
-}
-
 #endif /* CONFIG_MIGRATION */
 
 #endif /* _LINUX_MIGRATE_H */
diff --git a/mm/migrate.c b/mm/migrate.c
index f97d724b8fc0..77592288fbc0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2104,7 +2104,6 @@ out:
 	return 0;
 }
 #endif /* CONFIG_NUMA_BALANCING */
-#endif /* CONFIG_NUMA */
 
 /*
  * node_demotion[] example:
@@ -2238,7 +2237,6 @@ out:
 	return target;
 }
 
-#if defined(CONFIG_HOTPLUG_CPU)
 /* Disable reclaim-based migration. */
 static void __disable_all_migrate_targets(void)
 {
@@ -2431,6 +2429,7 @@ void set_migration_target_nodes(void)
  * __set_migration_target_nodes() can be used as opposed to
  * set_migration_target_nodes().
  */
+#ifdef CONFIG_MEMORY_HOTPLUG
 static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
 						 unsigned long action, void *_arg)
 {
@@ -2476,6 +2475,7 @@ static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
 
 	return notifier_from_errno(0);
 }
+#endif
 
 void __init migrate_on_reclaim_init(void)
 {
@@ -2483,8 +2483,9 @@ void __init migrate_on_reclaim_init(void)
 				sizeof(struct demotion_nodes),
 				GFP_KERNEL);
 	WARN_ON(!node_demotion);
-
+#ifdef CONFIG_MEMORY_HOTPLUG
 	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
+#endif
 	/*
 	 * At this point, all numa nodes with memory/CPus have their state
 	 * properly set, so we can build the demotion order now.
@@ -2495,7 +2496,6 @@ void __init migrate_on_reclaim_init(void)
 	set_migration_target_nodes();
 	cpus_read_unlock();
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 bool numa_demotion_enabled = false;
 
@@ -2556,4 +2556,5 @@ delete_obj:
 	return err;
 }
 subsys_initcall(numa_init_sysfs);
-#endif
+#endif /* CONFIG_SYSFS */
+#endif /* CONFIG_NUMA */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b75b1a64b54c..f2d0dec1062d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2111,9 +2111,7 @@ void __init init_mm_internals(void)
 
 	start_shepherd_timer();
 #endif
-#if defined(CONFIG_MIGRATION) && defined(CONFIG_HOTPLUG_CPU)
 	migrate_on_reclaim_init();
-#endif
 #ifdef CONFIG_PROC_FS
 	proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
 	proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op);
-- 
cgit v1.2.3


From 6a8e0596f00469c15ec556b9f3624acd2e9a04f9 Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Thu, 28 Apr 2022 23:16:10 -0700
Subject: mm: rmap: introduce pfn_mkclean_range() to cleans PTEs

The page_mkclean_one() is supposed to be used with the pfn that has a
associated struct page, but not all the pfns (e.g.  DAX) have a struct
page.  Introduce a new function pfn_mkclean_range() to cleans the PTEs
(including PMDs) mapped with range of pfns which has no struct page
associated with them.  This helper will be used by DAX device in the next
patch to make pfns clean.

Link: https://lkml.kernel.org/r/20220403053957.10770-4-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |  3 +++
 mm/internal.h        | 26 +++++++++++++--------
 mm/rmap.c            | 65 +++++++++++++++++++++++++++++++++++++++++++---------
 3 files changed, 74 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 17230c458341..8573aae50d96 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -261,6 +261,9 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
  */
 int folio_mkclean(struct folio *);
 
+int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
+		      struct vm_area_struct *vma);
+
 void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked);
 
 /*
diff --git a/mm/internal.h b/mm/internal.h
index 6293468fd7b7..69a5eabe0943 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -525,26 +525,22 @@ void mlock_page_drain_remote(int cpu);
 extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
 
 /*
- * At what user virtual address is page expected in vma?
- * Returns -EFAULT if all of the page is outside the range of vma.
- * If page is a compound head, the entire compound page is considered.
+ * Return the start of user virtual address at the specific offset within
+ * a vma.
  */
 static inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
+vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages,
+		  struct vm_area_struct *vma)
 {
-	pgoff_t pgoff;
 	unsigned long address;
 
-	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
-	pgoff = page_to_pgoff(page);
 	if (pgoff >= vma->vm_pgoff) {
 		address = vma->vm_start +
 			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
 		/* Check for address beyond vma (or wrapped through 0?) */
 		if (address < vma->vm_start || address >= vma->vm_end)
 			address = -EFAULT;
-	} else if (PageHead(page) &&
-		   pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
+	} else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) {
 		/* Test above avoids possibility of wrap to 0 on 32-bit */
 		address = vma->vm_start;
 	} else {
@@ -553,6 +549,18 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 	return address;
 }
 
+/*
+ * Return the start of user virtual address of a page within a vma.
+ * Returns -EFAULT if all of the page is outside the range of vma.
+ * If page is a compound head, the entire compound page is considered.
+ */
+static inline unsigned long
+vma_address(struct page *page, struct vm_area_struct *vma)
+{
+	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
+	return vma_pgoff_address(page_to_pgoff(page), compound_nr(page), vma);
+}
+
 /*
  * Then at what user virtual address will none of the range be found in vma?
  * Assumes that vma_address() already returned a good starting address.
diff --git a/mm/rmap.c b/mm/rmap.c
index c194ec913c68..ad509b3a89ee 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -929,12 +929,12 @@ int folio_referenced(struct folio *folio, int is_locked,
 	return pra.referenced;
 }
 
-static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
-			    unsigned long address, void *arg)
+static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
 {
-	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
+	int cleaned = 0;
+	struct vm_area_struct *vma = pvmw->vma;
 	struct mmu_notifier_range range;
-	int *cleaned = arg;
+	unsigned long address = pvmw->address;
 
 	/*
 	 * We have to assume the worse case ie pmd for invalidation. Note that
@@ -942,16 +942,16 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 	 */
 	mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
 				0, vma, vma->vm_mm, address,
-				vma_address_end(&pvmw));
+				vma_address_end(pvmw));
 	mmu_notifier_invalidate_range_start(&range);
 
-	while (page_vma_mapped_walk(&pvmw)) {
+	while (page_vma_mapped_walk(pvmw)) {
 		int ret = 0;
 
-		address = pvmw.address;
-		if (pvmw.pte) {
+		address = pvmw->address;
+		if (pvmw->pte) {
 			pte_t entry;
-			pte_t *pte = pvmw.pte;
+			pte_t *pte = pvmw->pte;
 
 			if (!pte_dirty(*pte) && !pte_write(*pte))
 				continue;
@@ -964,7 +964,7 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 			ret = 1;
 		} else {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			pmd_t *pmd = pvmw.pmd;
+			pmd_t *pmd = pvmw->pmd;
 			pmd_t entry;
 
 			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
@@ -991,11 +991,22 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 		 * See Documentation/vm/mmu_notifier.rst
 		 */
 		if (ret)
-			(*cleaned)++;
+			cleaned++;
 	}
 
 	mmu_notifier_invalidate_range_end(&range);
 
+	return cleaned;
+}
+
+static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
+			     unsigned long address, void *arg)
+{
+	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
+	int *cleaned = arg;
+
+	*cleaned += page_vma_mkclean_one(&pvmw);
+
 	return true;
 }
 
@@ -1032,6 +1043,38 @@ int folio_mkclean(struct folio *folio)
 }
 EXPORT_SYMBOL_GPL(folio_mkclean);
 
+/**
+ * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of
+ *                     [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff)
+ *                     within the @vma of shared mappings. And since clean PTEs
+ *                     should also be readonly, write protects them too.
+ * @pfn: start pfn.
+ * @nr_pages: number of physically contiguous pages srarting with @pfn.
+ * @pgoff: page offset that the @pfn mapped with.
+ * @vma: vma that @pfn mapped within.
+ *
+ * Returns the number of cleaned PTEs (including PMDs).
+ */
+int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
+		      struct vm_area_struct *vma)
+{
+	struct page_vma_mapped_walk pvmw = {
+		.pfn		= pfn,
+		.nr_pages	= nr_pages,
+		.pgoff		= pgoff,
+		.vma		= vma,
+		.flags		= PVMW_SYNC,
+	};
+
+	if (invalid_mkclean_vma(vma, NULL))
+		return 0;
+
+	pvmw.address = vma_pgoff_address(pgoff, nr_pages, vma);
+	VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma);
+
+	return page_vma_mkclean_one(&pvmw);
+}
+
 /**
  * page_move_anon_rmap - move a page to our anon_vma
  * @page:	the page to move to our anon_vma
-- 
cgit v1.2.3


From 0e5e64c0b0d7bb33a5e971ad17e771cf6e0a1127 Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Thu, 28 Apr 2022 23:16:10 -0700
Subject: mm: simplify follow_invalidate_pte()

The only user (DAX) of range and pmdpp parameters of
follow_invalidate_pte() is gone, it is safe to remove them and make it
static to simlify the code.  This is revertant of the following commits:

  097963959594 ("mm: add follow_pte_pmd()")
  a4d1a8852513 ("dax: update to new mmu_notifier semantic")

There is only one caller of the follow_invalidate_pte().  So just fold it
into follow_pte() and remove it.

Link: https://lkml.kernel.org/r/20220403053957.10770-7-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h |  3 --
 mm/memory.c        | 81 ++++++++++++++++--------------------------------------
 2 files changed, 23 insertions(+), 61 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d446e834a3e5..16d6b46d2d3e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1845,9 +1845,6 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
-int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
-			  struct mmu_notifier_range *range, pte_t **ptepp,
-			  pmd_t **pmdpp, spinlock_t **ptlp);
 int follow_pte(struct mm_struct *mm, unsigned long address,
 	       pte_t **ptepp, spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
diff --git a/mm/memory.c b/mm/memory.c
index 76e3af9639d9..8895dd2f2255 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4949,9 +4949,29 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
-			  struct mmu_notifier_range *range, pte_t **ptepp,
-			  pmd_t **pmdpp, spinlock_t **ptlp)
+/**
+ * follow_pte - look up PTE at a user virtual address
+ * @mm: the mm_struct of the target address space
+ * @address: user virtual address
+ * @ptepp: location to store found PTE
+ * @ptlp: location to store the lock for the PTE
+ *
+ * On a successful return, the pointer to the PTE is stored in @ptepp;
+ * the corresponding lock is taken and its location is stored in @ptlp.
+ * The contents of the PTE are only stable until @ptlp is released;
+ * any further use, if any, must be protected against invalidation
+ * with MMU notifiers.
+ *
+ * Only IO mappings and raw PFN mappings are allowed.  The mmap semaphore
+ * should be taken for read.
+ *
+ * KVM uses this function.  While it is arguably less bad than ``follow_pfn``,
+ * it is not a good general-purpose API.
+ *
+ * Return: zero on success, -ve otherwise.
+ */
+int follow_pte(struct mm_struct *mm, unsigned long address,
+	       pte_t **ptepp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -4974,35 +4994,9 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
 	pmd = pmd_offset(pud, address);
 	VM_BUG_ON(pmd_trans_huge(*pmd));
 
-	if (pmd_huge(*pmd)) {
-		if (!pmdpp)
-			goto out;
-
-		if (range) {
-			mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0,
-						NULL, mm, address & PMD_MASK,
-						(address & PMD_MASK) + PMD_SIZE);
-			mmu_notifier_invalidate_range_start(range);
-		}
-		*ptlp = pmd_lock(mm, pmd);
-		if (pmd_huge(*pmd)) {
-			*pmdpp = pmd;
-			return 0;
-		}
-		spin_unlock(*ptlp);
-		if (range)
-			mmu_notifier_invalidate_range_end(range);
-	}
-
 	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto out;
 
-	if (range) {
-		mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm,
-					address & PAGE_MASK,
-					(address & PAGE_MASK) + PAGE_SIZE);
-		mmu_notifier_invalidate_range_start(range);
-	}
 	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
 	if (!pte_present(*ptep))
 		goto unlock;
@@ -5010,38 +5004,9 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
 	return 0;
 unlock:
 	pte_unmap_unlock(ptep, *ptlp);
-	if (range)
-		mmu_notifier_invalidate_range_end(range);
 out:
 	return -EINVAL;
 }
-
-/**
- * follow_pte - look up PTE at a user virtual address
- * @mm: the mm_struct of the target address space
- * @address: user virtual address
- * @ptepp: location to store found PTE
- * @ptlp: location to store the lock for the PTE
- *
- * On a successful return, the pointer to the PTE is stored in @ptepp;
- * the corresponding lock is taken and its location is stored in @ptlp.
- * The contents of the PTE are only stable until @ptlp is released;
- * any further use, if any, must be protected against invalidation
- * with MMU notifiers.
- *
- * Only IO mappings and raw PFN mappings are allowed.  The mmap semaphore
- * should be taken for read.
- *
- * KVM uses this function.  While it is arguably less bad than ``follow_pfn``,
- * it is not a good general-purpose API.
- *
- * Return: zero on success, -ve otherwise.
- */
-int follow_pte(struct mm_struct *mm, unsigned long address,
-	       pte_t **ptepp, spinlock_t **ptlp)
-{
-	return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp);
-}
 EXPORT_SYMBOL_GPL(follow_pte);
 
 /**
-- 
cgit v1.2.3


From 3afa793082e624f7bd83533010ff4a676451d4ee Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Thu, 28 Apr 2022 23:16:14 -0700
Subject: mm/mmap: drop arch_vm_get_page_pgprot()

There are no platforms left which use arch_vm_get_page_prot(). Just drop
generic arch_vm_get_page_prot().

Link: https://lkml.kernel.org/r/20220414062125.609297-8-anshuman.khandual@arm.com
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mman.h | 4 ----
 mm/mmap.c            | 4 +---
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mman.h b/include/linux/mman.h
index b66e91b8176c..58b3abd457a3 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -93,10 +93,6 @@ static inline void vm_unacct_memory(long pages)
 #define arch_calc_vm_flag_bits(flags) 0
 #endif
 
-#ifndef arch_vm_get_page_prot
-#define arch_vm_get_page_prot(vm_flags) __pgprot(0)
-#endif
-
 #ifndef arch_validate_prot
 /*
  * This is called from mprotect().  PROT_GROWSDOWN and PROT_GROWSUP have
diff --git a/mm/mmap.c b/mm/mmap.c
index defc5af46973..d7e120ad5825 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -123,9 +123,7 @@ pgprot_t protection_map[16] __ro_after_init = {
 #ifndef CONFIG_ARCH_HAS_VM_GET_PAGE_PROT
 pgprot_t vm_get_page_prot(unsigned long vm_flags)
 {
-	return __pgprot(pgprot_val(protection_map[vm_flags &
-			(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
-			pgprot_val(arch_vm_get_page_prot(vm_flags)));
+	return protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)];
 }
 EXPORT_SYMBOL(vm_get_page_prot);
 #endif	/* CONFIG_ARCH_HAS_VM_GET_PAGE_PROT */
-- 
cgit v1.2.3


From 5981611d0a006472d367d7a8e6ead8afaecf17c7 Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Thu, 28 Apr 2022 23:16:14 -0700
Subject: mm: hugetlb_vmemmap: cleanup hugetlb_vmemmap related functions

Patch series "cleanup hugetlb_vmemmap".

The word of "free" is not expressive enough to express the feature of
optimizing vmemmap pages associated with each HugeTLB, rename this keywork
to "optimize" is more clear.  In this series, cheanup related codes to
make it more clear and expressive.  This is suggested by David.


This patch (of 3):

The word of "free" is not expressive enough to express the feature of
optimizing vmemmap pages associated with each HugeTLB, rename this keywork
to "optimize".  And some function names are prefixed with "huge_page"
instead of "hugetlb", it is easily to be confused with THP.  In this
patch, cheanup related functions to make code more clear and expressive.

Link: https://lkml.kernel.org/r/20220404074652.68024-1-songmuchun@bytedance.com
Link: https://lkml.kernel.org/r/20220404074652.68024-2-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h |  2 +-
 mm/hugetlb.c            | 10 +++++-----
 mm/hugetlb_vmemmap.c    | 42 ++++++++++++++++++++----------------------
 mm/hugetlb_vmemmap.h    | 20 ++++++++++----------
 4 files changed, 36 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ac2a1d758a80..189bddb8eca4 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -624,7 +624,7 @@ struct hstate {
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
-	unsigned int nr_free_vmemmap_pages;
+	unsigned int optimize_vmemmap_pages;
 #endif
 #ifdef CONFIG_CGROUP_HUGETLB
 	/* cgroup control files */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 34efd507a68d..87ba50b270a3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1540,7 +1540,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page)
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
-	if (alloc_huge_page_vmemmap(h, page)) {
+	if (hugetlb_vmemmap_alloc(h, page)) {
 		spin_lock_irq(&hugetlb_lock);
 		/*
 		 * If we cannot allocate vmemmap pages, just refuse to free the
@@ -1617,7 +1617,7 @@ static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
 
 static inline void flush_free_hpage_work(struct hstate *h)
 {
-	if (free_vmemmap_pages_per_hpage(h))
+	if (hugetlb_optimize_vmemmap_pages(h))
 		flush_work(&free_hpage_work);
 }
 
@@ -1737,7 +1737,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid)
 
 static void __prep_new_huge_page(struct hstate *h, struct page *page)
 {
-	free_huge_page_vmemmap(h, page);
+	hugetlb_vmemmap_free(h, page);
 	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
 	hugetlb_set_page_subpool(page, NULL);
@@ -2110,7 +2110,7 @@ retry:
 		 * Attempt to allocate vmemmmap here so that we can take
 		 * appropriate action on failure.
 		 */
-		rc = alloc_huge_page_vmemmap(h, head);
+		rc = hugetlb_vmemmap_alloc(h, head);
 		if (!rc) {
 			/*
 			 * Move PageHWPoison flag from head page to the raw
@@ -3425,7 +3425,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page)
 	remove_hugetlb_page_for_demote(h, page, false);
 	spin_unlock_irq(&hugetlb_lock);
 
-	rc = alloc_huge_page_vmemmap(h, page);
+	rc = hugetlb_vmemmap_alloc(h, page);
 	if (rc) {
 		/* Allocation of vmemmmap failed, we can not demote page */
 		spin_lock_irq(&hugetlb_lock);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 791626983c2e..91b79b9d9e25 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Free some vmemmap pages of HugeTLB
+ * Optimize vmemmap pages associated with HugeTLB
  *
  * Copyright (c) 2020, Bytedance. All rights reserved.
  *
@@ -192,7 +192,7 @@ DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
 			hugetlb_free_vmemmap_enabled_key);
 EXPORT_SYMBOL(hugetlb_free_vmemmap_enabled_key);
 
-static int __init early_hugetlb_free_vmemmap_param(char *buf)
+static int __init hugetlb_vmemmap_early_param(char *buf)
 {
 	/* We cannot optimize if a "struct page" crosses page boundaries. */
 	if (!is_power_of_2(sizeof(struct page))) {
@@ -212,29 +212,26 @@ static int __init early_hugetlb_free_vmemmap_param(char *buf)
 
 	return 0;
 }
-early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param);
-
-static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h)
-{
-	return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
-}
+early_param("hugetlb_free_vmemmap", hugetlb_vmemmap_early_param);
 
 /*
  * Previously discarded vmemmap pages will be allocated and remapping
  * after this function returns zero.
  */
-int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
 {
 	int ret;
 	unsigned long vmemmap_addr = (unsigned long)head;
-	unsigned long vmemmap_end, vmemmap_reuse;
+	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
 
 	if (!HPageVmemmapOptimized(head))
 		return 0;
 
-	vmemmap_addr += RESERVE_VMEMMAP_SIZE;
-	vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h);
-	vmemmap_reuse = vmemmap_addr - PAGE_SIZE;
+	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
+	vmemmap_pages	= hugetlb_optimize_vmemmap_pages(h);
+	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
+	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;
+
 	/*
 	 * The pages which the vmemmap virtual address range [@vmemmap_addr,
 	 * @vmemmap_end) are mapped to are freed to the buddy allocator, and
@@ -250,17 +247,18 @@ int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 	return ret;
 }
 
-void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
 {
 	unsigned long vmemmap_addr = (unsigned long)head;
-	unsigned long vmemmap_end, vmemmap_reuse;
+	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
 
-	if (!free_vmemmap_pages_per_hpage(h))
+	vmemmap_pages = hugetlb_optimize_vmemmap_pages(h);
+	if (!vmemmap_pages)
 		return;
 
-	vmemmap_addr += RESERVE_VMEMMAP_SIZE;
-	vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h);
-	vmemmap_reuse = vmemmap_addr - PAGE_SIZE;
+	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
+	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
+	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;
 
 	/*
 	 * Remap the vmemmap virtual address range [@vmemmap_addr, @vmemmap_end)
@@ -297,8 +295,8 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	 * hugetlbpage.rst for more details.
 	 */
 	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
-		h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+		h->optimize_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
 
-	pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
-		h->name);
+	pr_info("can optimize %d vmemmap pages for %s\n",
+		h->optimize_vmemmap_pages, h->name);
 }
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index cb2bef8f9e73..9760537849b5 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Free some vmemmap pages of HugeTLB
+ * Optimize vmemmap pages associated with HugeTLB
  *
  * Copyright (c) 2020, Bytedance. All rights reserved.
  *
@@ -11,25 +11,25 @@
 #include <linux/hugetlb.h>
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
-int alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
-void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head);
+void hugetlb_vmemmap_free(struct hstate *h, struct page *head);
 void hugetlb_vmemmap_init(struct hstate *h);
 
 /*
- * How many vmemmap pages associated with a HugeTLB page that can be freed
- * to the buddy allocator.
+ * How many vmemmap pages associated with a HugeTLB page that can be
+ * optimized and freed to the buddy allocator.
  */
-static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+static inline unsigned int hugetlb_optimize_vmemmap_pages(struct hstate *h)
 {
-	return h->nr_free_vmemmap_pages;
+	return h->optimize_vmemmap_pages;
 }
 #else
-static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+static inline int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
 {
 	return 0;
 }
 
-static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+static inline void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
 {
 }
 
@@ -37,7 +37,7 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
 }
 
-static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+static inline unsigned int hugetlb_optimize_vmemmap_pages(struct hstate *h)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From f10f1442c309ccef7a80ba3dc4abde0978e86fb4 Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Thu, 28 Apr 2022 23:16:15 -0700
Subject: mm: hugetlb_vmemmap: cleanup hugetlb_free_vmemmap_enabled*

The word of "free" is not expressive enough to express the feature of
optimizing vmemmap pages associated with each HugeTLB, rename this keywork
to "optimize".  In this patch , cheanup the static key and
hugetlb_free_vmemmap_enabled() to make code more expressive.

Link: https://lkml.kernel.org/r/20220404074652.68024-3-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm64/mm/flush.c      |  2 +-
 include/linux/page-flags.h | 12 ++++++------
 mm/hugetlb_vmemmap.c       | 10 +++++-----
 mm/memory_hotplug.c        |  2 +-
 4 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 840d998879ad..bbb2640f4f54 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -86,7 +86,7 @@ void flush_dcache_page(struct page *page)
 	 * is reused (more details can refer to the comments above
 	 * page_fixed_fake_head()).
 	 */
-	if (hugetlb_free_vmemmap_enabled() && PageHuge(page))
+	if (hugetlb_optimize_vmemmap_enabled() && PageHuge(page))
 		page = compound_head(page);
 
 	if (test_bit(PG_dcache_clean, &page->flags))
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 9d8eeaa67d05..573f499d5a2d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -192,16 +192,16 @@ enum pageflags {
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
-			 hugetlb_free_vmemmap_enabled_key);
+			 hugetlb_optimize_vmemmap_key);
 
-static __always_inline bool hugetlb_free_vmemmap_enabled(void)
+static __always_inline bool hugetlb_optimize_vmemmap_enabled(void)
 {
 	return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
-				   &hugetlb_free_vmemmap_enabled_key);
+				   &hugetlb_optimize_vmemmap_key);
 }
 
 /*
- * If the feature of freeing some vmemmap pages associated with each HugeTLB
+ * If the feature of optimizing vmemmap pages associated with each HugeTLB
  * page is enabled, the head vmemmap page frame is reused and all of the tail
  * vmemmap addresses map to the head vmemmap page frame (furture details can
  * refer to the figure at the head of the mm/hugetlb_vmemmap.c).  In other
@@ -218,7 +218,7 @@ static __always_inline bool hugetlb_free_vmemmap_enabled(void)
  */
 static __always_inline const struct page *page_fixed_fake_head(const struct page *page)
 {
-	if (!hugetlb_free_vmemmap_enabled())
+	if (!hugetlb_optimize_vmemmap_enabled())
 		return page;
 
 	/*
@@ -247,7 +247,7 @@ static inline const struct page *page_fixed_fake_head(const struct page *page)
 	return page;
 }
 
-static inline bool hugetlb_free_vmemmap_enabled(void)
+static inline bool hugetlb_optimize_vmemmap_enabled(void)
 {
 	return false;
 }
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 91b79b9d9e25..f25294973398 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -189,8 +189,8 @@
 #define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
 
 DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
-			hugetlb_free_vmemmap_enabled_key);
-EXPORT_SYMBOL(hugetlb_free_vmemmap_enabled_key);
+			hugetlb_optimize_vmemmap_key);
+EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key);
 
 static int __init hugetlb_vmemmap_early_param(char *buf)
 {
@@ -204,9 +204,9 @@ static int __init hugetlb_vmemmap_early_param(char *buf)
 		return -EINVAL;
 
 	if (!strcmp(buf, "on"))
-		static_branch_enable(&hugetlb_free_vmemmap_enabled_key);
+		static_branch_enable(&hugetlb_optimize_vmemmap_key);
 	else if (!strcmp(buf, "off"))
-		static_branch_disable(&hugetlb_free_vmemmap_enabled_key);
+		static_branch_disable(&hugetlb_optimize_vmemmap_key);
 	else
 		return -EINVAL;
 
@@ -282,7 +282,7 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	BUILD_BUG_ON(__NR_USED_SUBPAGE >=
 		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));
 
-	if (!hugetlb_free_vmemmap_enabled())
+	if (!hugetlb_optimize_vmemmap_enabled())
 		return;
 
 	vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 416b38ca8def..678a449ec0f7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1289,7 +1289,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size)
 	 *       populate a single PMD.
 	 */
 	return memmap_on_memory &&
-	       !hugetlb_free_vmemmap_enabled() &&
+	       !hugetlb_optimize_vmemmap_enabled() &&
 	       IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) &&
 	       size == memory_block_size_bytes() &&
 	       IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
-- 
cgit v1.2.3


From 47010c040dec8af6347ec6259104fc13f7e7e30a Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Thu, 28 Apr 2022 23:16:15 -0700
Subject: mm: hugetlb_vmemmap: cleanup CONFIG_HUGETLB_PAGE_FREE_VMEMMAP*

The word of "free" is not expressive enough to express the feature of
optimizing vmemmap pages associated with each HugeTLB, rename this keywork
to "optimize".  In this patch , cheanup configs to make code more
expressive.

Link: https://lkml.kernel.org/r/20220404074652.68024-4-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  4 ++--
 Documentation/admin-guide/mm/hugetlbpage.rst    |  2 +-
 arch/arm64/Kconfig                              |  2 +-
 arch/arm64/mm/flush.c                           |  2 +-
 arch/x86/Kconfig                                |  2 +-
 arch/x86/mm/init_64.c                           |  2 +-
 fs/Kconfig                                      | 16 ++++++++--------
 include/linux/hugetlb.h                         |  2 +-
 include/linux/mm.h                              |  2 +-
 include/linux/page-flags.h                      |  6 +++---
 mm/Makefile                                     |  2 +-
 mm/hugetlb_vmemmap.c                            |  4 ++--
 mm/hugetlb_vmemmap.h                            |  4 ++--
 mm/sparse-vmemmap.c                             |  4 ++--
 14 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 3f1cc5e317ed..d9b577db6e19 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1660,7 +1660,7 @@
 			Format: size[KMG]
 
 	hugetlb_free_vmemmap=
-			[KNL] Reguires CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+			[KNL] Reguires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 			enabled.
 			Allows heavy hugetlb users to free up some more
 			memory (7 * PAGE_SIZE for each 2MB hugetlb page).
@@ -1669,7 +1669,7 @@
 			on:  enable the feature
 			off: disable the feature
 
-			Built with CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON=y,
+			Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y,
 			the default is on.
 
 			This is not compatible with memory_hotplug.memmap_on_memory.
diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst
index 0166f9de3428..a90330d0a837 100644
--- a/Documentation/admin-guide/mm/hugetlbpage.rst
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -164,7 +164,7 @@ default_hugepagesz
 	will all result in 256 2M huge pages being allocated.  Valid default
 	huge page size is architecture dependent.
 hugetlb_free_vmemmap
-	When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set, this enables freeing
+	When CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is set, this enables optimizing
 	unused vmemmap pages associated with each HugeTLB page.
 
 When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8da1f65ae398..cc0498652bae 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -97,7 +97,7 @@ config ARM64
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
-	select ARCH_WANT_HUGETLB_PAGE_FREE_VMEMMAP
+	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index bbb2640f4f54..fc4f710e9820 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -78,7 +78,7 @@ void flush_dcache_page(struct page *page)
 	/*
 	 * Only the head page's flags of HugeTLB can be cleared since the tail
 	 * vmemmap pages associated with each HugeTLB page are mapped with
-	 * read-only when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is enabled (more
+	 * read-only when CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is enabled (more
 	 * details can refer to vmemmap_remap_pte()).  Although
 	 * __sync_icache_dcache() only set PG_dcache_clean flag on the head
 	 * page struct, there is more than one page struct with PG_dcache_clean
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5b77b4301d36..da07c8087e5a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -121,7 +121,7 @@ config X86
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_HUGE_PMD_SHARE
-	select ARCH_WANT_HUGETLB_PAGE_FREE_VMEMMAP	if X86_64
+	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP	if X86_64
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_THP_SWAP		if X86_64
 	select ARCH_HAS_PARANOID_L1D_FLUSH
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 96d34ebb20a9..af34dd1510d6 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1269,7 +1269,7 @@ static struct kcore_list kcore_vsyscall;
 
 static void __init register_page_bootmem_info(void)
 {
-#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)
+#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP)
 	int i;
 
 	for_each_online_node(i)
diff --git a/fs/Kconfig b/fs/Kconfig
index 8f6ab1cf5115..5976eb33535f 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -250,22 +250,22 @@ config HUGETLB_PAGE
 # to enable the feature of minimizing overhead of struct page associated with
 # each HugeTLB page.
 #
-config ARCH_WANT_HUGETLB_PAGE_FREE_VMEMMAP
+config ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	bool
 
-config HUGETLB_PAGE_FREE_VMEMMAP
+config HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	def_bool HUGETLB_PAGE
-	depends on ARCH_WANT_HUGETLB_PAGE_FREE_VMEMMAP
+	depends on ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	depends on SPARSEMEM_VMEMMAP
 
-config HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON
-	bool "Default freeing vmemmap pages of HugeTLB to on"
+config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON
+	bool "Default optimizing vmemmap pages of HugeTLB to on"
 	default n
-	depends on HUGETLB_PAGE_FREE_VMEMMAP
+	depends on HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	help
-	  When using HUGETLB_PAGE_FREE_VMEMMAP, the freeing unused vmemmap
+	  When using HUGETLB_PAGE_OPTIMIZE_VMEMMAP, the optimizing unused vmemmap
 	  pages associated with each HugeTLB page is default off. Say Y here
-	  to enable freeing vmemmap pages of HugeTLB by default. It can then
+	  to enable optimizing vmemmap pages of HugeTLB by default. It can then
 	  be disabled on the command line via hugetlb_free_vmemmap=off.
 
 config MEMFD_CREATE
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 189bddb8eca4..ac2ece9e9c79 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -623,7 +623,7 @@ struct hstate {
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	unsigned int optimize_vmemmap_pages;
 #endif
 #ifdef CONFIG_CGROUP_HUGETLB
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 16d6b46d2d3e..a8f4c7e96ad5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3145,7 +3145,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
 }
 #endif
 
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 int vmemmap_remap_free(unsigned long start, unsigned long end,
 		       unsigned long reuse);
 int vmemmap_remap_alloc(unsigned long start, unsigned long end,
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 573f499d5a2d..1ea896887ee4 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -190,13 +190,13 @@ enum pageflags {
 
 #ifndef __GENERATING_BOUNDS_H
 
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
-DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON,
 			 hugetlb_optimize_vmemmap_key);
 
 static __always_inline bool hugetlb_optimize_vmemmap_enabled(void)
 {
-	return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
+	return static_branch_maybe(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON,
 				   &hugetlb_optimize_vmemmap_key);
 }
 
diff --git a/mm/Makefile b/mm/Makefile
index 4cc13f3179a5..6f9ffa968a1a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -77,7 +77,7 @@ obj-$(CONFIG_FRONTSWAP)	+= frontswap.o
 obj-$(CONFIG_ZSWAP)	+= zswap.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
-obj-$(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)	+= hugetlb_vmemmap.o
+obj-$(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP)	+= hugetlb_vmemmap.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index f25294973398..2655434a946b 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -188,7 +188,7 @@
 #define RESERVE_VMEMMAP_NR		1U
 #define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
 
-DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
+DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON,
 			hugetlb_optimize_vmemmap_key);
 EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key);
 
@@ -276,7 +276,7 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 
 	/*
 	 * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
-	 * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP,
+	 * page structs that can be used when CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP,
 	 * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.
 	 */
 	BUILD_BUG_ON(__NR_USED_SUBPAGE >=
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 9760537849b5..109b0a53b6fe 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -10,7 +10,7 @@
 #define _LINUX_HUGETLB_VMEMMAP_H
 #include <linux/hugetlb.h>
 
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head);
 void hugetlb_vmemmap_free(struct hstate *h, struct page *head);
 void hugetlb_vmemmap_init(struct hstate *h);
@@ -41,5 +41,5 @@ static inline unsigned int hugetlb_optimize_vmemmap_pages(struct hstate *h)
 {
 	return 0;
 }
-#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
+#endif /* CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP */
 #endif /* _LINUX_HUGETLB_VMEMMAP_H */
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 8aecd6b3896c..52f36527bab3 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -34,7 +34,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 /**
  * struct vmemmap_remap_walk - walk vmemmap page table
  *
@@ -420,7 +420,7 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end,
 
 	return 0;
 }
-#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
+#endif /* CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP */
 
 /*
  * Allocate a block of memory to be used to back the virtual memory map
-- 
cgit v1.2.3


From e3246d8f52173a798710314a42fea83223036fc8 Mon Sep 17 00:00:00 2001
From: Joao Martins <joao.m.martins@oracle.com>
Date: Thu, 28 Apr 2022 23:16:15 -0700
Subject: mm/sparse-vmemmap: add a pgmap argument to section activation

Patch series "sparse-vmemmap: memory savings for compound devmaps (device-dax)", v9.

This series minimizes 'struct page' overhead by pursuing a similar
approach as Muchun Song series "Free some vmemmap pages of hugetlb page"
(now merged since v5.14), but applied to devmap with @vmemmap_shift
(device-dax).

The vmemmap dedpulication original idea (already used in HugeTLB) is to
reuse/deduplicate tail page vmemmap areas, particular the area which only
describes tail pages.  So a vmemmap page describes 64 struct pages, and
the first page for a given ZONE_DEVICE vmemmap would contain the head page
and 63 tail pages.  The second vmemmap page would contain only tail pages,
and that's what gets reused across the rest of the subsection/section.
The bigger the page size, the bigger the savings (2M hpage -> save 6
vmemmap pages; 1G hpage -> save 4094 vmemmap pages).

This is done for PMEM /specifically only/ on device-dax configured
namespaces, not fsdax.  In other words, a devmap with a @vmemmap_shift.

In terms of savings, per 1Tb of memory, the struct page cost would go down
with compound devmap:

* with 2M pages we lose 4G instead of 16G (0.39% instead of 1.5% of
  total memory)

* with 1G pages we lose 40MB instead of 16G (0.0014% instead of 1.5% of
  total memory)

The series is mostly summed up by patch 4, and to summarize what the
series does:

Patches 1 - 3: Minor cleanups in preparation for patch 4.  Move the very
nice docs of hugetlb_vmemmap.c into a Documentation/vm/ entry.

Patch 4: Patch 4 is the one that takes care of the struct page savings
(also referred to here as tail-page/vmemmap deduplication).  Much like
Muchun series, we reuse the second PTE tail page vmemmap areas across a
given @vmemmap_shift On important difference though, is that contrary to
the hugetlbfs series, there's no vmemmap for the area because we are
late-populating it as opposed to remapping a system-ram range.  IOW no
freeing of pages of already initialized vmemmap like the case for
hugetlbfs, which greatly simplifies the logic (besides not being
arch-specific).  altmap case unchanged and still goes via the
vmemmap_populate().  Also adjust the newly added docs to the device-dax
case.

[Note that device-dax is still a little behind HugeTLB in terms of
savings.  I have an additional simple patch that reuses the head vmemmap
page too, as a follow-up.  That will double the savings and namespaces
initialization.]

Patch 5: Initialize fewer struct pages depending on the page size with
DRAM backed struct pages -- because fewer pages are unique and most tail
pages (with bigger vmemmap_shift).

    NVDIMM namespace bootstrap improves from ~268-358 ms to
    ~80-110/<1ms on 128G NVDIMMs with 2M and 1G respectivally.  And struct
    page needed capacity will be 3.8x / 1071x smaller for 2M and 1G
    respectivelly.  Tested on x86 with 1.5Tb of pmem (including pinning,
    and RDMA registration/deregistration scalability with 2M MRs)


This patch (of 5):

In support of using compound pages for devmap mappings, plumb the pgmap
down to the vmemmap_populate implementation.  Note that while altmap is
retrievable from pgmap the memory hotplug code passes altmap without
pgmap[*], so both need to be independently plumbed.

So in addition to @altmap, pass @pgmap to sparse section populate
functions namely:

	sparse_add_section
	  section_activate
	    populate_section_memmap
   	      __populate_section_memmap

Passing @pgmap allows __populate_section_memmap() to both fetch the
vmemmap_shift in which memmap metadata is created for and also to let
sparse-vmemmap fetch pgmap ranges to co-relate to a given section and pick
whether to just reuse tail pages from past onlined sections.

While at it, fix the kdoc for @altmap for sparse_add_section().

[*] https://lore.kernel.org/linux-mm/20210319092635.6214-1-osalvador@suse.de/

Link: https://lkml.kernel.org/r/20220420155310.9712-1-joao.m.martins@oracle.com
Link: https://lkml.kernel.org/r/20220420155310.9712-2-joao.m.martins@oracle.com
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memory_hotplug.h |  5 ++++-
 include/linux/mm.h             |  3 ++-
 mm/memory_hotplug.c            |  3 ++-
 mm/sparse-vmemmap.c            |  3 ++-
 mm/sparse.c                    | 26 ++++++++++++++++----------
 5 files changed, 26 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 1ce6f8044f1e..e0b2209ab71c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -15,6 +15,7 @@ struct memory_block;
 struct memory_group;
 struct resource;
 struct vmem_altmap;
+struct dev_pagemap;
 
 #ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
 /*
@@ -122,6 +123,7 @@ typedef int __bitwise mhp_t;
 struct mhp_params {
 	struct vmem_altmap *altmap;
 	pgprot_t pgprot;
+	struct dev_pagemap *pgmap;
 };
 
 bool mhp_range_allowed(u64 start, u64 size, bool need_mapping);
@@ -333,7 +335,8 @@ extern void remove_pfn_range_from_zone(struct zone *zone,
 				       unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern int sparse_add_section(int nid, unsigned long pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap);
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap);
 extern void sparse_remove_section(struct mem_section *ms,
 		unsigned long pfn, unsigned long nr_pages,
 		unsigned long map_offset, struct vmem_altmap *altmap);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a8f4c7e96ad5..80bba49387e9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3154,7 +3154,8 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end,
 
 void *sparse_buffer_alloc(unsigned long size);
 struct page * __populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap);
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 678a449ec0f7..19a6beb9d4b6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -328,7 +328,8 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 		/* Select all remaining pages up to the next section boundary */
 		cur_nr_pages = min(end_pfn - pfn,
 				   SECTION_ALIGN_UP(pfn + 1) - pfn);
-		err = sparse_add_section(nid, pfn, cur_nr_pages, altmap);
+		err = sparse_add_section(nid, pfn, cur_nr_pages, altmap,
+					 params->pgmap);
 		if (err)
 			break;
 		cond_resched();
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 52f36527bab3..fb68e7764ba2 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -641,7 +641,8 @@ int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
 }
 
 struct page * __meminit __populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	unsigned long start = (unsigned long) pfn_to_page(pfn);
 	unsigned long end = start + nr_pages * sizeof(struct page);
diff --git a/mm/sparse.c b/mm/sparse.c
index 952f06d8f373..d2d76d158b39 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -427,7 +427,8 @@ static unsigned long __init section_map_size(void)
 }
 
 struct page __init *__populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	unsigned long size = section_map_size();
 	struct page *map = sparse_buffer_alloc(size);
@@ -524,7 +525,7 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
 			break;
 
 		map = __populate_section_memmap(pfn, PAGES_PER_SECTION,
-				nid, NULL);
+				nid, NULL, NULL);
 		if (!map) {
 			pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.",
 			       __func__, nid);
@@ -629,9 +630,10 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 static struct page * __meminit populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
-	return __populate_section_memmap(pfn, nr_pages, nid, altmap);
+	return __populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
 }
 
 static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
@@ -700,7 +702,8 @@ static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
 }
 #else
 struct page * __meminit populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	return kvmalloc_node(array_size(sizeof(struct page),
 					PAGES_PER_SECTION), GFP_KERNEL, nid);
@@ -823,7 +826,8 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 }
 
 static struct page * __meminit section_activate(int nid, unsigned long pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap)
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	struct mem_section *ms = __pfn_to_section(pfn);
 	struct mem_section_usage *usage = NULL;
@@ -855,7 +859,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
 	if (nr_pages < PAGES_PER_SECTION && early_section(ms))
 		return pfn_to_page(pfn);
 
-	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap);
+	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
 	if (!memmap) {
 		section_deactivate(pfn, nr_pages, altmap);
 		return ERR_PTR(-ENOMEM);
@@ -869,7 +873,8 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
  * @nid: The node to add section on
  * @start_pfn: start pfn of the memory range
  * @nr_pages: number of pfns to add in the section
- * @altmap: device page map
+ * @altmap: alternate pfns to allocate the memmap backing store
+ * @pgmap: alternate compound page geometry for devmap mappings
  *
  * This is only intended for hotplug.
  *
@@ -883,7 +888,8 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
  * * -ENOMEM	- Out of memory.
  */
 int __meminit sparse_add_section(int nid, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap)
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
 	struct mem_section *ms;
@@ -894,7 +900,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 	if (ret < 0)
 		return ret;
 
-	memmap = section_activate(nid, start_pfn, nr_pages, altmap);
+	memmap = section_activate(nid, start_pfn, nr_pages, altmap, pgmap);
 	if (IS_ERR(memmap))
 		return PTR_ERR(memmap);
 
-- 
cgit v1.2.3


From 4917f55b4ef963e2d2288fe4eb651728be8db406 Mon Sep 17 00:00:00 2001
From: Joao Martins <joao.m.martins@oracle.com>
Date: Thu, 28 Apr 2022 23:16:16 -0700
Subject: mm/sparse-vmemmap: improve memory savings for compound devmaps

A compound devmap is a dev_pagemap with @vmemmap_shift > 0 and it means
that pages are mapped at a given huge page alignment and utilize uses
compound pages as opposed to order-0 pages.

Take advantage of the fact that most tail pages look the same (except the
first two) to minimize struct page overhead.  Allocate a separate page for
the vmemmap area which contains the head page and separate for the next 64
pages.  The rest of the subsections then reuse this tail vmemmap page to
initialize the rest of the tail pages.

Sections are arch-dependent (e.g.  on x86 it's 64M, 128M or 512M) and when
initializing compound devmap with big enough @vmemmap_shift (e.g.  1G PUD)
it may cross multiple sections.  The vmemmap code needs to consult @pgmap
so that multiple sections that all map the same tail data can refer back
to the first copy of that data for a given gigantic page.

On compound devmaps with 2M align, this mechanism lets 6 pages be saved
out of the 8 necessary PFNs necessary to set the subsection's 512 struct
pages being mapped.  On a 1G compound devmap it saves 4094 pages.

Altmap isn't supported yet, given various restrictions in altmap pfn
allocator, thus fallback to the already in use vmemmap_populate().  It is
worth noting that altmap for devmap mappings was there to relieve the
pressure of inordinate amounts of memmap space to map terabytes of pmem.
With compound pages the motivation for altmaps for pmem gets reduced.

Link: https://lkml.kernel.org/r/20220420155310.9712-5-joao.m.martins@oracle.com
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/vm/vmemmap_dedup.rst |  56 +++++++++++++++-
 include/linux/mm.h                 |   2 +-
 mm/memremap.c                      |   1 +
 mm/sparse-vmemmap.c                | 132 ++++++++++++++++++++++++++++++++++---
 4 files changed, 177 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/vm/vmemmap_dedup.rst b/Documentation/vm/vmemmap_dedup.rst
index 485ccf4f7b10..c9c495f62d12 100644
--- a/Documentation/vm/vmemmap_dedup.rst
+++ b/Documentation/vm/vmemmap_dedup.rst
@@ -1,8 +1,11 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-==================================
-Free some vmemmap pages of HugeTLB
-==================================
+=========================================
+A vmemmap diet for HugeTLB and Device DAX
+=========================================
+
+HugeTLB
+=======
 
 The struct page structures (page structs) are used to describe a physical
 page frame. By default, there is a one-to-one mapping from a page frame to
@@ -171,3 +174,50 @@ tail vmemmap pages are mapped to the head vmemmap page frame. So we can see
 more than one struct page struct with PG_head (e.g. 8 per 2 MB HugeTLB page)
 associated with each HugeTLB page. The compound_head() can handle this
 correctly (more details refer to the comment above compound_head()).
+
+Device DAX
+==========
+
+The device-dax interface uses the same tail deduplication technique explained
+in the previous chapter, except when used with the vmemmap in
+the device (altmap).
+
+The following page sizes are supported in DAX: PAGE_SIZE (4K on x86_64),
+PMD_SIZE (2M on x86_64) and PUD_SIZE (1G on x86_64).
+
+The differences with HugeTLB are relatively minor.
+
+It only use 3 page structs for storing all information as opposed
+to 4 on HugeTLB pages.
+
+There's no remapping of vmemmap given that device-dax memory is not part of
+System RAM ranges initialized at boot. Thus the tail page deduplication
+happens at a later stage when we populate the sections. HugeTLB reuses the
+the head vmemmap page representing, whereas device-dax reuses the tail
+vmemmap page. This results in only half of the savings compared to HugeTLB.
+
+Deduplicated tail pages are not mapped read-only.
+
+Here's how things look like on device-dax after the sections are populated::
+
+ +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ |           |                     |     0     | -------------> |     0     |
+ |           |                     +-----------+                +-----------+
+ |           |                     |     1     | -------------> |     1     |
+ |           |                     +-----------+                +-----------+
+ |           |                     |     2     | ----------------^ ^ ^ ^ ^ ^
+ |           |                     +-----------+                   | | | | |
+ |           |                     |     3     | ------------------+ | | | |
+ |           |                     +-----------+                     | | | |
+ |           |                     |     4     | --------------------+ | | |
+ |    PMD    |                     +-----------+                       | | |
+ |   level   |                     |     5     | ----------------------+ | |
+ |  mapping  |                     +-----------+                         | |
+ |           |                     |     6     | ------------------------+ |
+ |           |                     +-----------+                           |
+ |           |                     |     7     | --------------------------+
+ |           |                     +-----------+
+ |           |
+ |           |
+ |           |
+ +-----------+
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80bba49387e9..b9316b2c11ce 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3161,7 +3161,7 @@ p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
-			    struct vmem_altmap *altmap);
+			    struct vmem_altmap *altmap, struct page *reuse);
 void *vmemmap_alloc_block(unsigned long size, int node);
 struct vmem_altmap;
 void *vmemmap_alloc_block_buf(unsigned long size, int node,
diff --git a/mm/memremap.c b/mm/memremap.c
index af0223605e69..c33bcd0398c9 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -287,6 +287,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 {
 	struct mhp_params params = {
 		.altmap = pgmap_altmap(pgmap),
+		.pgmap = pgmap,
 		.pgprot = PAGE_KERNEL,
 	};
 	const int nr_range = pgmap->nr_range;
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index ef15664c6b6c..f4fa61dbbee3 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -533,16 +533,31 @@ void __meminit vmemmap_verify(pte_t *pte, int node,
 }
 
 pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
-				       struct vmem_altmap *altmap)
+				       struct vmem_altmap *altmap,
+				       struct page *reuse)
 {
 	pte_t *pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte)) {
 		pte_t entry;
 		void *p;
 
-		p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
-		if (!p)
-			return NULL;
+		if (!reuse) {
+			p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
+			if (!p)
+				return NULL;
+		} else {
+			/*
+			 * When a PTE/PMD entry is freed from the init_mm
+			 * there's a a free_pages() call to this page allocated
+			 * above. Thus this get_page() is paired with the
+			 * put_page_testzero() on the freeing path.
+			 * This can only called by certain ZONE_DEVICE path,
+			 * and through vmemmap_populate_compound_pages() when
+			 * slab is available.
+			 */
+			get_page(reuse);
+			p = page_to_virt(reuse);
+		}
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
 	}
@@ -609,7 +624,8 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 }
 
 static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
-					      struct vmem_altmap *altmap)
+					      struct vmem_altmap *altmap,
+					      struct page *reuse)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -629,7 +645,7 @@ static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
 	pmd = vmemmap_pmd_populate(pud, addr, node);
 	if (!pmd)
 		return NULL;
-	pte = vmemmap_pte_populate(pmd, addr, node, altmap);
+	pte = vmemmap_pte_populate(pmd, addr, node, altmap, reuse);
 	if (!pte)
 		return NULL;
 	vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
@@ -639,13 +655,14 @@ static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
 
 static int __meminit vmemmap_populate_range(unsigned long start,
 					    unsigned long end, int node,
-					    struct vmem_altmap *altmap)
+					    struct vmem_altmap *altmap,
+					    struct page *reuse)
 {
 	unsigned long addr = start;
 	pte_t *pte;
 
 	for (; addr < end; addr += PAGE_SIZE) {
-		pte = vmemmap_populate_address(addr, node, altmap);
+		pte = vmemmap_populate_address(addr, node, altmap, reuse);
 		if (!pte)
 			return -ENOMEM;
 	}
@@ -656,7 +673,95 @@ static int __meminit vmemmap_populate_range(unsigned long start,
 int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
 					 int node, struct vmem_altmap *altmap)
 {
-	return vmemmap_populate_range(start, end, node, altmap);
+	return vmemmap_populate_range(start, end, node, altmap, NULL);
+}
+
+/*
+ * For compound pages bigger than section size (e.g. x86 1G compound
+ * pages with 2M subsection size) fill the rest of sections as tail
+ * pages.
+ *
+ * Note that memremap_pages() resets @nr_range value and will increment
+ * it after each range successful onlining. Thus the value or @nr_range
+ * at section memmap populate corresponds to the in-progress range
+ * being onlined here.
+ */
+static bool __meminit reuse_compound_section(unsigned long start_pfn,
+					     struct dev_pagemap *pgmap)
+{
+	unsigned long nr_pages = pgmap_vmemmap_nr(pgmap);
+	unsigned long offset = start_pfn -
+		PHYS_PFN(pgmap->ranges[pgmap->nr_range].start);
+
+	return !IS_ALIGNED(offset, nr_pages) && nr_pages > PAGES_PER_SUBSECTION;
+}
+
+static pte_t * __meminit compound_section_tail_page(unsigned long addr)
+{
+	pte_t *pte;
+
+	addr -= PAGE_SIZE;
+
+	/*
+	 * Assuming sections are populated sequentially, the previous section's
+	 * page data can be reused.
+	 */
+	pte = pte_offset_kernel(pmd_off_k(addr), addr);
+	if (!pte)
+		return NULL;
+
+	return pte;
+}
+
+static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
+						     unsigned long start,
+						     unsigned long end, int node,
+						     struct dev_pagemap *pgmap)
+{
+	unsigned long size, addr;
+	pte_t *pte;
+	int rc;
+
+	if (reuse_compound_section(start_pfn, pgmap)) {
+		pte = compound_section_tail_page(start);
+		if (!pte)
+			return -ENOMEM;
+
+		/*
+		 * Reuse the page that was populated in the prior iteration
+		 * with just tail struct pages.
+		 */
+		return vmemmap_populate_range(start, end, node, NULL,
+					      pte_page(*pte));
+	}
+
+	size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page));
+	for (addr = start; addr < end; addr += size) {
+		unsigned long next = addr, last = addr + size;
+
+		/* Populate the head page vmemmap page */
+		pte = vmemmap_populate_address(addr, node, NULL, NULL);
+		if (!pte)
+			return -ENOMEM;
+
+		/* Populate the tail pages vmemmap page */
+		next = addr + PAGE_SIZE;
+		pte = vmemmap_populate_address(next, node, NULL, NULL);
+		if (!pte)
+			return -ENOMEM;
+
+		/*
+		 * Reuse the previous page for the rest of tail pages
+		 * See layout diagram in Documentation/vm/vmemmap_dedup.rst
+		 */
+		next += PAGE_SIZE;
+		rc = vmemmap_populate_range(next, last, node, NULL,
+					    pte_page(*pte));
+		if (rc)
+			return -ENOMEM;
+	}
+
+	return 0;
 }
 
 struct page * __meminit __populate_section_memmap(unsigned long pfn,
@@ -665,12 +770,19 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
 {
 	unsigned long start = (unsigned long) pfn_to_page(pfn);
 	unsigned long end = start + nr_pages * sizeof(struct page);
+	int r;
 
 	if (WARN_ON_ONCE(!IS_ALIGNED(pfn, PAGES_PER_SUBSECTION) ||
 		!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
 		return NULL;
 
-	if (vmemmap_populate(start, end, nid, altmap))
+	if (is_power_of_2(sizeof(struct page)) &&
+	    pgmap && pgmap_vmemmap_nr(pgmap) > 1 && !altmap)
+		r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
+	else
+		r = vmemmap_populate(start, end, nid, altmap);
+
+	if (r < 0)
 		return NULL;
 
 	return pfn_to_page(pfn);
-- 
cgit v1.2.3


From ba91fb7dd03c4f463453f28af24851097a6547fb Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 28 Apr 2022 23:16:16 -0700
Subject: include/linux/swapops.h: remove stub for non_swap_entry()

The stub for non_swap_entry() may not help much, because MAX_SWAPFILES has
already contained all the information to decide whether a swap entry is
real swap entry or pesudo ones (migrations, ...).

There can be some performance influences on non_swap_entry() with below
conditions all met:

  !CONFIG_MIGRATION && !CONFIG_MEMORY_FAILURE && !CONFIG_DEVICE_PRIVATE

But that's definitely not the major config most machines will use, at the
meantime it's already in a slow path of swap entry (being parsed from a
swap pte), so IMHO it shouldn't be a major issue.  Also according to the
analysis from Alistair, somehow the stub didn't do the job right [1].

To make the code cleaner, let's drop the stub.

[1] https://lore.kernel.org/lkml/8735ihbw6g.fsf@nvdebian.thelocal/

Note: the uffd-wp shmem & hugetlbfs series will need this patch to make
sure swap entries work as expected with below config as spotted by
Alistair:

  !CONFIG_MIGRATION &&
  !CONFIG_MEMORY_FAILURE &&
  !CONFIG_DEVICE_PRIVATE &&
  CONFIG_PTE_MARKER

(PS: this config should mostly never gonna happen, though, afaict..)

Link: https://lkml.kernel.org/r/20220413191147.66645-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swapops.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index d356ab4047f7..5af852b68805 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -387,18 +387,10 @@ static inline void num_poisoned_pages_inc(void)
 }
 #endif
 
-#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \
-    defined(CONFIG_DEVICE_PRIVATE)
 static inline int non_swap_entry(swp_entry_t entry)
 {
 	return swp_type(entry) >= MAX_SWAPFILES;
 }
-#else
-static inline int non_swap_entry(swp_entry_t entry)
-{
-	return 0;
-}
-#endif
 
 #endif /* CONFIG_MMU */
 #endif /* _LINUX_SWAPOPS_H */
-- 
cgit v1.2.3


From 7609385337a4feb6236e42dcd0df2185683ce839 Mon Sep 17 00:00:00 2001
From: xu xin <xu.xin16@zte.com.cn>
Date: Thu, 28 Apr 2022 23:16:16 -0700
Subject: ksm: count ksm merging pages for each process

Some applications or containers want to use KSM by calling madvise() to
advise areas of address space to be MERGEABLE.  But they may not know
which applications are more likely to cause real merges in the
deployment.  If this patch is applied, it helps them know their
corresponding number of merged pages, and then optimize their app code.

As current KSM only counts the number of KSM merging pages(e.g.
ksm_pages_sharing and ksm_pages_shared) of the whole system, we cannot see
the more fine-grained KSM merging, for the upper application optimization,
the merging area cannot be set easily according to the KSM page merging
probability of each process.  Therefore, it is necessary to add extra
statistical means so that the upper level users can know the detailed KSM
merging information of each process.

We add a new proc file named as ksm_merging_pages under /proc/<pid>/ to
indicate the involved ksm merging pages of this process.

[akpm@linux-foundation.org: fix comment typo, remove BUG_ON()s]
Link: https://lkml.kernel.org/r/20220325082318.2352853-1-xu.xin16@zte.com.cn
Signed-off-by: xu xin <xu.xin16@zte.com.cn>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Yang Yang <yang.yang29@zte.com.cn>
Reviewed-by: Ran Xiaokai <ran.xiaokai@zte.com.cn>
Reported-by: Zeal Robot <zealci@zte.com.cn>
Cc: Kees Cook <keescook@chromium.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Ohhoon Kwon <ohoono.kwon@samsung.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Yang Yang <yang.yang29@zte.com.cn>
Cc: Ran Xiaokai <ran.xiaokai@zte.com.cn>
Cc: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/base.c           | 22 ++++++++++++++++++++++
 include/linux/mm_types.h |  7 +++++++
 mm/ksm.c                 |  8 ++++++++
 3 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index c1031843cc6a..8dfa36a99c74 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3154,6 +3154,22 @@ static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns,
 }
 #endif /* CONFIG_LIVEPATCH */
 
+#ifdef CONFIG_KSM
+static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task)
+{
+	struct mm_struct *mm;
+
+	mm = get_task_mm(task);
+	if (mm) {
+		seq_printf(m, "%lu\n", mm->ksm_merging_pages);
+		mmput(mm);
+	}
+
+	return 0;
+}
+#endif /* CONFIG_KSM */
+
 #ifdef CONFIG_STACKLEAK_METRICS
 static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task)
@@ -3285,6 +3301,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_SECCOMP_CACHE_DEBUG
 	ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache),
 #endif
+#ifdef CONFIG_KSM
+	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3618,6 +3637,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_SECCOMP_CACHE_DEBUG
 	ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache),
 #endif
+#ifdef CONFIG_KSM
+	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8834e38c06a4..87eddd509de2 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -654,6 +654,13 @@ struct mm_struct {
 
 #ifdef CONFIG_IOMMU_SVA
 		u32 pasid;
+#endif
+#ifdef CONFIG_KSM
+		/*
+		 * Represent how many pages of this process are involved in KSM
+		 * merging.
+		 */
+		unsigned long ksm_merging_pages;
 #endif
 	} __randomize_layout;
 
diff --git a/mm/ksm.c b/mm/ksm.c
index 063a48eeb5ee..94bb0f049806 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -638,6 +638,9 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node)
 			ksm_pages_sharing--;
 		else
 			ksm_pages_shared--;
+
+		rmap_item->mm->ksm_merging_pages--;
+
 		VM_BUG_ON(stable_node->rmap_hlist_len <= 0);
 		stable_node->rmap_hlist_len--;
 		put_anon_vma(rmap_item->anon_vma);
@@ -785,6 +788,9 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item)
 			ksm_pages_sharing--;
 		else
 			ksm_pages_shared--;
+
+		rmap_item->mm->ksm_merging_pages--;
+
 		VM_BUG_ON(stable_node->rmap_hlist_len <= 0);
 		stable_node->rmap_hlist_len--;
 
@@ -2007,6 +2013,8 @@ static void stable_tree_append(struct rmap_item *rmap_item,
 		ksm_pages_sharing++;
 	else
 		ksm_pages_shared++;
+
+	rmap_item->mm->ksm_merging_pages++;
 }
 
 /*
-- 
cgit v1.2.3


From 94bfe85bde18a99612bb5d0ce348643c2d352836 Mon Sep 17 00:00:00 2001
From: Yang Yang <yang.yang29@zte.com.cn>
Date: Thu, 28 Apr 2022 23:16:16 -0700
Subject: mm/vmstat: add events for ksm cow

Users may use ksm by calling madvise(, , MADV_MERGEABLE) when they want to
save memory, it's a tradeoff by suffering delay on ksm cow.  Users can get
to know how much memory ksm saved by reading
/sys/kernel/mm/ksm/pages_sharing, but they don't know what's the costs of
ksm cow, and this is important of some delay sensitive tasks.

So add ksm cow events to help users evaluate whether or how to use ksm.
Also update Documentation/admin-guide/mm/ksm.rst with new added events.

Link: https://lkml.kernel.org/r/20220331035616.2390805-1-yang.yang29@zte.com.cn
Signed-off-by: Yang Yang <yang.yang29@zte.com.cn>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: xu xin <xu.xin16@zte.com.cn>
Reviewed-by: Ran Xiaokai <ran.xiaokai@zte.com.cn>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Saravanan D <saravanand@fb.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/mm/ksm.rst | 18 ++++++++++++++++++
 include/linux/vm_event_item.h        |  3 +++
 mm/memory.c                          |  4 ++++
 mm/vmstat.c                          |  3 +++
 4 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst
index 97d816791aca..b244f0202a03 100644
--- a/Documentation/admin-guide/mm/ksm.rst
+++ b/Documentation/admin-guide/mm/ksm.rst
@@ -184,6 +184,24 @@ The maximum possible ``pages_sharing/pages_shared`` ratio is limited by the
 ``max_page_sharing`` tunable. To increase the ratio ``max_page_sharing`` must
 be increased accordingly.
 
+Monitoring KSM events
+=====================
+
+There are some counters in /proc/vmstat that may be used to monitor KSM events.
+KSM might help save memory, it's a tradeoff by may suffering delay on KSM COW
+or on swapping in copy. Those events could help users evaluate whether or how
+to use KSM. For example, if cow_ksm increases too fast, user may decrease the
+range of madvise(, , MADV_MERGEABLE).
+
+cow_ksm
+	is incremented every time a KSM page triggers copy on write (COW)
+	when users try to write to a KSM page, we have to make a copy.
+
+ksm_swpin_copy
+	is incremented every time a KSM page is copied when swapping in
+	note that KSM page might be copied when swapping in because do_swap_page()
+	cannot do all the locking needed to reconstitute a cross-anon_vma KSM page.
+
 --
 Izik Eidus,
 Hugh Dickins, 17 Nov 2009
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 16a0a4fd000b..e83967e4c20e 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -133,6 +133,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		KSM_SWPIN_COPY,
 #endif
 #endif
+#ifdef CONFIG_KSM
+		COW_KSM,
+#endif
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
 		DIRECT_MAP_LEVEL3_SPLIT,
diff --git a/mm/memory.c b/mm/memory.c
index 8895dd2f2255..e873a6143181 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3331,6 +3331,10 @@ copy:
 	get_page(vmf->page);
 
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
+#ifdef CONFIG_KSM
+	if (PageKsm(vmf->page))
+		count_vm_event(COW_KSM);
+#endif
 	return wp_page_copy(vmf);
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f2d0dec1062d..b94a2e4723ff 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1393,6 +1393,9 @@ const char * const vmstat_text[] = {
 	"ksm_swpin_copy",
 #endif
 #endif
+#ifdef CONFIG_KSM
+	"cow_ksm",
+#endif
 #ifdef CONFIG_X86
 	"direct_map_level2_splits",
 	"direct_map_level3_splits",
-- 
cgit v1.2.3


From 024c61eaff17f6a8c73cb8b25137251f0c3ef039 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 28 Apr 2022 23:16:17 -0700
Subject: mm: compaction: remove unneeded return value of kcompactd_run

Patch series "A few cleanup and fixup patches for compaction".

This series contains a few patches to clean up some obsolete comment,
remove unneeded return value and so on.  Also we fix the possible NULL
pointer dereference.  More details can be found in the respective
changelogs.


This patch (of 12):

The return value of kcompactd_run() is unused now.  Clean it up.

Link: https://lkml.kernel.org/r/20220418141253.24298-1-linmiaohe@huawei.com
Link: https://lkml.kernel.org/r/20220418141253.24298-2-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Cc; Mel Gorman <mgorman@techsingularity.net>
Cc: David Hildenbrand <david@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Pintu Kumar <pintu@codeaurora.org>
Cc: Charan Teja Kalla <charante@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/compaction.h | 5 ++---
 mm/compaction.c            | 7 ++-----
 2 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 34bce35c808d..52a9ff65faee 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -177,7 +177,7 @@ static inline bool compaction_withdrawn(enum compact_result result)
 bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 					int alloc_flags);
 
-extern int kcompactd_run(int nid);
+extern void kcompactd_run(int nid);
 extern void kcompactd_stop(int nid);
 extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx);
 
@@ -212,9 +212,8 @@ static inline bool compaction_withdrawn(enum compact_result result)
 	return true;
 }
 
-static inline int kcompactd_run(int nid)
+static inline void kcompactd_run(int nid)
 {
-	return 0;
 }
 static inline void kcompactd_stop(int nid)
 {
diff --git a/mm/compaction.c b/mm/compaction.c
index baf654b5e073..2e838992b324 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -3016,21 +3016,18 @@ static int kcompactd(void *p)
  * This kcompactd start function will be called by init and node-hot-add.
  * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added.
  */
-int kcompactd_run(int nid)
+void kcompactd_run(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
-	int ret = 0;
 
 	if (pgdat->kcompactd)
-		return 0;
+		return;
 
 	pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid);
 	if (IS_ERR(pgdat->kcompactd)) {
 		pr_err("Failed to start kcompactd on node %d\n", nid);
-		ret = PTR_ERR(pgdat->kcompactd);
 		pgdat->kcompactd = NULL;
 	}
-	return ret;
 }
 
 /*
-- 
cgit v1.2.3


From 766475cb526b2fc5ca21374b5810d6d8557870fc Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 28 Apr 2022 12:28:59 +0200
Subject: ARM: omap1: add back omap_set_dma_priority() stub

One of my multiplatform patches went a little too far and removed
a declaration that is needed for compile-testing the omapfb
driver on non-OMAP1 platforms:

  arm-linux-gnueabi-ld: drivers/video/fbdev/omap/omapfb_main.o: in function `omapfb_do_probe':
  omapfb_main.c:(.text+0x41ec): undefined reference to `omap_set_dma_priority'

Add back the inline stub, and in turn hide the definition when
omapfb is disabled, like we do for the usb specific bits.

Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Fixes: 52ef8efcb75e ("dma: omap: hide legacy interface")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-omap1/omap-dma.c | 18 ++----------------
 include/linux/omap-dma.h       |  7 +++++++
 2 files changed, 9 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/omap-dma.c b/arch/arm/mach-omap1/omap-dma.c
index e504f65cdc1b..f7e62de427f3 100644
--- a/arch/arm/mach-omap1/omap-dma.c
+++ b/arch/arm/mach-omap1/omap-dma.c
@@ -99,7 +99,7 @@ static inline void set_gdma_dev(int req, int dev)
 	omap_writel(l, reg);
 }
 
-#ifdef CONFIG_ARCH_OMAP1
+#if IS_ENABLED(CONFIG_FB_OMAP)
 void omap_set_dma_priority(int lch, int dst_port, int priority)
 {
 	unsigned long reg;
@@ -129,22 +129,8 @@ void omap_set_dma_priority(int lch, int dst_port, int priority)
 		omap_writel(l, reg);
 	}
 }
-#endif
-
-#ifdef CONFIG_ARCH_OMAP2PLUS
-void omap_set_dma_priority(int lch, int dst_port, int priority)
-{
-	u32 ccr;
-
-	ccr = p->dma_read(CCR, lch);
-	if (priority)
-		ccr |= (1 << 6);
-	else
-		ccr &= ~(1 << 6);
-	p->dma_write(ccr, CCR, lch);
-}
-#endif
 EXPORT_SYMBOL(omap_set_dma_priority);
+#endif
 
 #if IS_ENABLED(CONFIG_USB_OMAP)
 #ifdef CONFIG_ARCH_OMAP15XX
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 254b4e10511b..6f6c31e3fb93 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -294,7 +294,14 @@ struct omap_system_dma_plat_info {
 
 extern struct omap_system_dma_plat_info *omap_get_plat_info(void);
 
+#if defined(CONFIG_ARCH_OMAP1)
 extern void omap_set_dma_priority(int lch, int dst_port, int priority);
+#else
+static inline void omap_set_dma_priority(int lch, int dst_port, int priority)
+{
+}
+#endif
+
 extern int omap_request_dma(int dev_id, const char *dev_name,
 			void (*callback)(int lch, u16 ch_status, void *data),
 			void *data, int *dma_ch);
-- 
cgit v1.2.3


From 50e7b416d2ab10b9771bd00a4d85df90ad2e4b37 Mon Sep 17 00:00:00 2001
From: Dietmar Eggemann <dietmar.eggemann@arm.com>
Date: Thu, 28 Apr 2022 15:43:37 +0100
Subject: sched/fair: Remove sched_trace_*() helper functions

We no longer need them as we can use DWARF debug info or BTF + pahole to
re-generate the required structs to compile against them for a given
kernel.

This moves the burden of maintaining these helper functions to the
module.

	https://github.com/qais-yousef/sched_tp

Note that pahole v1.15 is required at least for using DWARF. And for BTF
v1.23 which is not yet released will be required. There's alignment
problem that will lead to crashes in earlier versions when used with
BTF.

We should have enough infrastructure to make these helper functions now
obsolete, so remove them.

[Rewrote commit message to reflect the new alternative]
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220428144338.479094-2-qais.yousef@arm.com
---
 include/linux/sched.h | 14 --------
 kernel/sched/fair.c   | 98 ---------------------------------------------------
 2 files changed, 112 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 67f06f72c50e..fc74ea2578b7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2378,20 +2378,6 @@ static inline void rseq_syscall(struct pt_regs *regs)
 
 #endif
 
-const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq);
-char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len);
-int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq);
-
-const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq);
-const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
-const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
-
-int sched_trace_rq_cpu(struct rq *rq);
-int sched_trace_rq_cpu_capacity(struct rq *rq);
-int sched_trace_rq_nr_running(struct rq *rq);
-
-const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
-
 #ifdef CONFIG_SCHED_CORE
 extern void sched_core_free(struct task_struct *tsk);
 extern void sched_core_fork(struct task_struct *p);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7d38728ebe97..19803e1c9138 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11839,101 +11839,3 @@ __init void init_sched_fair_class(void)
 #endif /* SMP */
 
 }
-
-/*
- * Helper functions to facilitate extracting info from tracepoints.
- */
-
-const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq)
-{
-#ifdef CONFIG_SMP
-	return cfs_rq ? &cfs_rq->avg : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_avg);
-
-char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len)
-{
-	if (!cfs_rq) {
-		if (str)
-			strlcpy(str, "(null)", len);
-		else
-			return NULL;
-	}
-
-	cfs_rq_tg_path(cfs_rq, str, len);
-	return str;
-}
-EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_path);
-
-int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq)
-{
-	return cfs_rq ? cpu_of(rq_of(cfs_rq)) : -1;
-}
-EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_cpu);
-
-const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq)
-{
-#ifdef CONFIG_SMP
-	return rq ? &rq->avg_rt : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_avg_rt);
-
-const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq)
-{
-#ifdef CONFIG_SMP
-	return rq ? &rq->avg_dl : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_avg_dl);
-
-const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq)
-{
-#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_SCHED_AVG_IRQ)
-	return rq ? &rq->avg_irq : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_avg_irq);
-
-int sched_trace_rq_cpu(struct rq *rq)
-{
-	return rq ? cpu_of(rq) : -1;
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_cpu);
-
-int sched_trace_rq_cpu_capacity(struct rq *rq)
-{
-	return rq ?
-#ifdef CONFIG_SMP
-		rq->cpu_capacity
-#else
-		SCHED_CAPACITY_SCALE
-#endif
-		: -1;
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_cpu_capacity);
-
-const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
-{
-#ifdef CONFIG_SMP
-	return rd ? rd->span : NULL;
-#else
-	return NULL;
-#endif
-}
-EXPORT_SYMBOL_GPL(sched_trace_rd_span);
-
-int sched_trace_rq_nr_running(struct rq *rq)
-{
-        return rq ? rq->nr_running : -1;
-}
-EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running);
-- 
cgit v1.2.3


From 498af8d1678ae2351218337b47bbf3cb0fc16821 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 29 Apr 2022 12:39:45 +0100
Subject: firmware: arm_ffa: Add ffa_dev_get_drvdata helper function

Add a helper function to fetch ffa_dev's driver_data using
dev_get_drvdata. At the same time move existing ffa_dev_set_drvdata
to use dev_set_drvdata.

Link: https://lore.kernel.org/r/20220429113946.2087145-3-sudeep.holla@arm.com
Suggested-by: Arunachalam Ganapathy <arunachalam.ganapathy@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 include/linux/arm_ffa.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 85651e41ded8..e5c76c1ef9ed 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -38,7 +38,12 @@ struct ffa_driver {
 
 static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data)
 {
-	fdev->dev.driver_data = data;
+	dev_set_drvdata(&fdev->dev, data);
+}
+
+static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev)
+{
+	return dev_get_drvdata(&fdev->dev);
 }
 
 #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT)
-- 
cgit v1.2.3


From 892de36fd4a98fab3298d417c051d9099af5448d Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 29 Apr 2022 12:22:10 -0400
Subject: SUNRPC: Ensure gss-proxy connects on setup

For reasons best known to the author, gss-proxy does not implement a
NULL procedure, and returns RPC_PROC_UNAVAIL. However we still want to
ensure that we connect to the service at setup time.
So add a quirk-flag specially for this case.

Fixes: 1d658336b05f ("SUNRPC: Add RPC based upcall mechanism for RPCGSS auth")
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/clnt.h          | 1 +
 net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +-
 net/sunrpc/clnt.c                    | 3 +++
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 267b7aeaf1a6..db5149567305 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -160,6 +160,7 @@ struct rpc_add_xprt_test {
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 #define RPC_CLNT_CREATE_SOFTERR		(1UL << 10)
 #define RPC_CLNT_CREATE_REUSEPORT	(1UL << 11)
+#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index 61c276bddaf2..8ca1d809b78d 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -97,7 +97,7 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt)
 		 * timeout, which would result in reconnections being
 		 * done without the correct namespace:
 		 */
-		.flags		= RPC_CLNT_CREATE_NOPING |
+		.flags		= RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL |
 				  RPC_CLNT_CREATE_NO_IDLE_TIMEOUT
 	};
 	struct rpc_clnt *clnt;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 98133aa54f19..22c28cf43eba 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -479,6 +479,9 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 
 	if (!(args->flags & RPC_CLNT_CREATE_NOPING)) {
 		int err = rpc_ping(clnt);
+		if ((args->flags & RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL) &&
+		    err == -EOPNOTSUPP)
+			err = 0;
 		if (err != 0) {
 			rpc_shutdown_client(clnt);
 			return ERR_PTR(err);
-- 
cgit v1.2.3


From ec2a0f9c8b50865a11720651c9c536f20c578def Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Fri, 29 Apr 2022 14:36:58 -0700
Subject: kasan: mark KASAN_VMALLOC flags as kasan_vmalloc_flags_t

Fix sparse warning:

mm/kasan/shadow.c:496:15: warning: restricted kasan_vmalloc_flags_t degrades to integer

Link: https://lkml.kernel.org/r/52d8fccdd3a48d4bdfd0ff522553bac2a13f1579.1649351254.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index ceebcb9de7bf..b092277bf48d 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -23,10 +23,10 @@ struct task_struct;
 
 typedef unsigned int __bitwise kasan_vmalloc_flags_t;
 
-#define KASAN_VMALLOC_NONE		0x00u
-#define KASAN_VMALLOC_INIT		0x01u
-#define KASAN_VMALLOC_VM_ALLOC		0x02u
-#define KASAN_VMALLOC_PROT_NORMAL	0x04u
+#define KASAN_VMALLOC_NONE		((__force kasan_vmalloc_flags_t)0x00u)
+#define KASAN_VMALLOC_INIT		((__force kasan_vmalloc_flags_t)0x01u)
+#define KASAN_VMALLOC_VM_ALLOC		((__force kasan_vmalloc_flags_t)0x02u)
+#define KASAN_VMALLOC_PROT_NORMAL	((__force kasan_vmalloc_flags_t)0x04u)
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
-- 
cgit v1.2.3


From 5d8de293c224896a4da99763fce4f9794308caf4 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 14:37:59 -0700
Subject: vmcore: convert copy_oldmem_page() to take an iov_iter

Patch series "Convert vmcore to use an iov_iter", v5.

For some reason several people have been sending bad patches to fix
compiler warnings in vmcore recently.  Here's how it should be done.
Compile-tested only on x86.  As noted in the first patch, s390 should take
this conversion a bit further, but I'm not inclined to do that work
myself.


This patch (of 3):

Instead of passing in a 'buf' and 'userbuf' argument, pass in an iov_iter.
s390 needs more work to pass the iov_iter down further, or refactor, but
I'd be more comfortable if someone who can test on s390 did that work.

It's more convenient to convert the whole of read_from_oldmem() to take an
iov_iter at the same time, so rename it to read_from_oldmem_iter() and add
a temporary read_from_oldmem() wrapper that creates an iov_iter.

Link: https://lkml.kernel.org/r/20220408090636.560886-1-bhe@redhat.com
Link: https://lkml.kernel.org/r/20220408090636.560886-2-bhe@redhat.com
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Baoquan He <bhe@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm/kernel/crash_dump.c     | 27 +++-----------------
 arch/arm64/kernel/crash_dump.c   | 29 +++------------------
 arch/ia64/kernel/crash_dump.c    | 32 +++---------------------
 arch/mips/kernel/crash_dump.c    | 27 +++-----------------
 arch/powerpc/kernel/crash_dump.c | 35 ++++----------------------
 arch/riscv/kernel/crash_dump.c   | 26 +++----------------
 arch/s390/kernel/crash_dump.c    | 13 ++++++----
 arch/sh/kernel/crash_dump.c      | 29 ++++-----------------
 arch/x86/kernel/crash_dump_32.c  | 29 +++------------------
 arch/x86/kernel/crash_dump_64.c  | 41 ++++++++----------------------
 fs/proc/vmcore.c                 | 54 +++++++++++++++++++++++++---------------
 include/linux/crash_dump.h       |  9 +++----
 12 files changed, 91 insertions(+), 260 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/crash_dump.c b/arch/arm/kernel/crash_dump.c
index 53cb92435392..938bd932df9a 100644
--- a/arch/arm/kernel/crash_dump.c
+++ b/arch/arm/kernel/crash_dump.c
@@ -14,22 +14,10 @@
 #include <linux/crash_dump.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/uio.h>
 
-/**
- * copy_oldmem_page() - copy one page from old kernel memory
- * @pfn: page frame number to be copied
- * @buf: buffer where the copied page is placed
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page
- * @userbuf: if set, @buf is int he user address space
- *
- * This function copies one page from old kernel memory into buffer pointed by
- * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes
- * copied or negative error in case of failure.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-			 size_t csize, unsigned long offset,
-			 int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			 size_t csize, unsigned long offset)
 {
 	void *vaddr;
 
@@ -40,14 +28,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!vaddr)
 		return -ENOMEM;
 
-	if (userbuf) {
-		if (copy_to_user(buf, vaddr + offset, csize)) {
-			iounmap(vaddr);
-			return -EFAULT;
-		}
-	} else {
-		memcpy(buf, vaddr + offset, csize);
-	}
+	csize = copy_to_iter(vaddr + offset, csize, iter);
 
 	iounmap(vaddr);
 	return csize;
diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c
index 58303a9ec32c..670e4ce81822 100644
--- a/arch/arm64/kernel/crash_dump.c
+++ b/arch/arm64/kernel/crash_dump.c
@@ -9,25 +9,11 @@
 #include <linux/crash_dump.h>
 #include <linux/errno.h>
 #include <linux/io.h>
-#include <linux/memblock.h>
-#include <linux/uaccess.h>
+#include <linux/uio.h>
 #include <asm/memory.h>
 
-/**
- * copy_oldmem_page() - copy one page from old kernel memory
- * @pfn: page frame number to be copied
- * @buf: buffer where the copied page is placed
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page
- * @userbuf: if set, @buf is in a user address space
- *
- * This function copies one page from old kernel memory into buffer pointed by
- * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes
- * copied or negative error in case of failure.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-			 size_t csize, unsigned long offset,
-			 int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			 size_t csize, unsigned long offset)
 {
 	void *vaddr;
 
@@ -38,14 +24,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!vaddr)
 		return -ENOMEM;
 
-	if (userbuf) {
-		if (copy_to_user((char __user *)buf, vaddr + offset, csize)) {
-			memunmap(vaddr);
-			return -EFAULT;
-		}
-	} else {
-		memcpy(buf, vaddr + offset, csize);
-	}
+	csize = copy_to_iter(vaddr + offset, csize, iter);
 
 	memunmap(vaddr);
 
diff --git a/arch/ia64/kernel/crash_dump.c b/arch/ia64/kernel/crash_dump.c
index 0ed3c3dee4cd..4ef68e2aa757 100644
--- a/arch/ia64/kernel/crash_dump.c
+++ b/arch/ia64/kernel/crash_dump.c
@@ -10,42 +10,18 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/crash_dump.h>
-
+#include <linux/uio.h>
 #include <asm/page.h>
-#include <linux/uaccess.h>
 
-/**
- * copy_oldmem_page - copy one page from "oldmem"
- * @pfn: page frame number to be copied
- * @buf: target memory address for the copy; this can be in kernel address
- *	space or user address space (see @userbuf)
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page (based on pfn) to begin the copy
- * @userbuf: if set, @buf is in user address space, use copy_to_user(),
- *	otherwise @buf is in kernel address space, use memcpy().
- *
- * Copy a page from "oldmem". For this page, there is no pte mapped
- * in the current kernel. We stitch up a pte, similar to kmap_atomic.
- *
- * Calling copy_to_user() in atomic context is not desirable. Hence first
- * copying the data to a pre-allocated kernel page and then copying to user
- * space in non-atomic context.
- */
-ssize_t
-copy_oldmem_page(unsigned long pfn, char *buf,
-		size_t csize, unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+		size_t csize, unsigned long offset)
 {
 	void  *vaddr;
 
 	if (!csize)
 		return 0;
 	vaddr = __va(pfn<<PAGE_SHIFT);
-	if (userbuf) {
-		if (copy_to_user(buf, (vaddr + offset), csize)) {
-			return -EFAULT;
-		}
-	} else
-		memcpy(buf, (vaddr + offset), csize);
+	csize = copy_to_iter(vaddr + offset, csize, iter);
 	return csize;
 }
 
diff --git a/arch/mips/kernel/crash_dump.c b/arch/mips/kernel/crash_dump.c
index 2e50f55185a6..6e50f4902409 100644
--- a/arch/mips/kernel/crash_dump.c
+++ b/arch/mips/kernel/crash_dump.c
@@ -1,22 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/highmem.h>
 #include <linux/crash_dump.h>
+#include <linux/uio.h>
 
-/**
- * copy_oldmem_page - copy one page from "oldmem"
- * @pfn: page frame number to be copied
- * @buf: target memory address for the copy; this can be in kernel address
- *	space or user address space (see @userbuf)
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page (based on pfn) to begin the copy
- * @userbuf: if set, @buf is in user address space, use copy_to_user(),
- *	otherwise @buf is in kernel address space, use memcpy().
- *
- * Copy a page from "oldmem". For this page, there is no pte mapped
- * in the current kernel.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-			 size_t csize, unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			 size_t csize, unsigned long offset)
 {
 	void  *vaddr;
 
@@ -24,14 +12,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 		return 0;
 
 	vaddr = kmap_local_pfn(pfn);
-
-	if (!userbuf) {
-		memcpy(buf, vaddr + offset, csize);
-	} else {
-		if (copy_to_user(buf, vaddr + offset, csize))
-			csize = -EFAULT;
-	}
-
+	csize = copy_to_iter(vaddr + offset, csize, iter);
 	kunmap_local(vaddr);
 
 	return csize;
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 5693e1c67c2b..32b4a97f1b79 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -16,7 +16,7 @@
 #include <asm/kdump.h>
 #include <asm/prom.h>
 #include <asm/firmware.h>
-#include <linux/uaccess.h>
+#include <linux/uio.h>
 #include <asm/rtas.h>
 #include <asm/inst.h>
 
@@ -68,33 +68,8 @@ void __init setup_kdump_trampoline(void)
 }
 #endif /* CONFIG_NONSTATIC_KERNEL */
 
-static size_t copy_oldmem_vaddr(void *vaddr, char *buf, size_t csize,
-                               unsigned long offset, int userbuf)
-{
-	if (userbuf) {
-		if (copy_to_user((char __user *)buf, (vaddr + offset), csize))
-			return -EFAULT;
-	} else
-		memcpy(buf, (vaddr + offset), csize);
-
-	return csize;
-}
-
-/**
- * copy_oldmem_page - copy one page from "oldmem"
- * @pfn: page frame number to be copied
- * @buf: target memory address for the copy; this can be in kernel address
- *      space or user address space (see @userbuf)
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page (based on pfn) to begin the copy
- * @userbuf: if set, @buf is in user address space, use copy_to_user(),
- *      otherwise @buf is in kernel address space, use memcpy().
- *
- * Copy a page from "oldmem". For this page, there is no pte mapped
- * in the current kernel. We stitch up a pte, similar to kmap_atomic.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-			size_t csize, unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			size_t csize, unsigned long offset)
 {
 	void  *vaddr;
 	phys_addr_t paddr;
@@ -107,10 +82,10 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 
 	if (memblock_is_region_memory(paddr, csize)) {
 		vaddr = __va(paddr);
-		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
+		csize = copy_to_iter(vaddr + offset, csize, iter);
 	} else {
 		vaddr = ioremap_cache(paddr, PAGE_SIZE);
-		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
+		csize = copy_to_iter(vaddr + offset, csize, iter);
 		iounmap(vaddr);
 	}
 
diff --git a/arch/riscv/kernel/crash_dump.c b/arch/riscv/kernel/crash_dump.c
index 86cc0ada5752..ea2158cee97b 100644
--- a/arch/riscv/kernel/crash_dump.c
+++ b/arch/riscv/kernel/crash_dump.c
@@ -7,22 +7,10 @@
 
 #include <linux/crash_dump.h>
 #include <linux/io.h>
+#include <linux/uio.h>
 
-/**
- * copy_oldmem_page() - copy one page from old kernel memory
- * @pfn: page frame number to be copied
- * @buf: buffer where the copied page is placed
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page
- * @userbuf: if set, @buf is in a user address space
- *
- * This function copies one page from old kernel memory into buffer pointed by
- * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes
- * copied or negative error in case of failure.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-			 size_t csize, unsigned long offset,
-			 int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			 size_t csize, unsigned long offset)
 {
 	void *vaddr;
 
@@ -33,13 +21,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!vaddr)
 		return -ENOMEM;
 
-	if (userbuf) {
-		if (copy_to_user((char __user *)buf, vaddr + offset, csize)) {
-			memunmap(vaddr);
-			return -EFAULT;
-		}
-	} else
-		memcpy(buf, vaddr + offset, csize);
+	csize = copy_to_iter(vaddr + offset, csize, iter);
 
 	memunmap(vaddr);
 	return csize;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 69819b765250..a2c1c55daec0 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/memblock.h>
 #include <linux/elf.h>
+#include <linux/uio.h>
 #include <asm/asm-offsets.h>
 #include <asm/os_info.h>
 #include <asm/elf.h>
@@ -212,8 +213,8 @@ static int copy_oldmem_user(void __user *dst, unsigned long src, size_t count)
 /*
  * Copy one page from "oldmem"
  */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
-			 unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, size_t csize,
+			 unsigned long offset)
 {
 	unsigned long src;
 	int rc;
@@ -221,10 +222,12 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
 	if (!csize)
 		return 0;
 	src = pfn_to_phys(pfn) + offset;
-	if (userbuf)
-		rc = copy_oldmem_user((void __force __user *) buf, src, csize);
+
+	/* XXX: pass the iov_iter down to a common function */
+	if (iter_is_iovec(iter))
+		rc = copy_oldmem_user(iter->iov->iov_base, src, csize);
 	else
-		rc = copy_oldmem_kernel((void *) buf, src, csize);
+		rc = copy_oldmem_kernel(iter->kvec->iov_base, src, csize);
 	return rc;
 }
 
diff --git a/arch/sh/kernel/crash_dump.c b/arch/sh/kernel/crash_dump.c
index 5b41b59698c1..19ce6a950aac 100644
--- a/arch/sh/kernel/crash_dump.c
+++ b/arch/sh/kernel/crash_dump.c
@@ -8,23 +8,11 @@
 #include <linux/errno.h>
 #include <linux/crash_dump.h>
 #include <linux/io.h>
+#include <linux/uio.h>
 #include <linux/uaccess.h>
 
-/**
- * copy_oldmem_page - copy one page from "oldmem"
- * @pfn: page frame number to be copied
- * @buf: target memory address for the copy; this can be in kernel address
- *	space or user address space (see @userbuf)
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page (based on pfn) to begin the copy
- * @userbuf: if set, @buf is in user address space, use copy_to_user(),
- *	otherwise @buf is in kernel address space, use memcpy().
- *
- * Copy a page from "oldmem". For this page, there is no pte mapped
- * in the current kernel. We stitch up a pte, similar to kmap_atomic.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-                               size_t csize, unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			 size_t csize, unsigned long offset)
 {
 	void  __iomem *vaddr;
 
@@ -32,15 +20,8 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 		return 0;
 
 	vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
-
-	if (userbuf) {
-		if (copy_to_user((void __user *)buf, (vaddr + offset), csize)) {
-			iounmap(vaddr);
-			return -EFAULT;
-		}
-	} else
-	memcpy(buf, (vaddr + offset), csize);
-
+	csize = copy_to_iter(vaddr + offset, csize, iter);
 	iounmap(vaddr);
+
 	return csize;
 }
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index 5fcac46aaf6b..5f4ae5476e19 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -10,8 +10,7 @@
 #include <linux/errno.h>
 #include <linux/highmem.h>
 #include <linux/crash_dump.h>
-
-#include <linux/uaccess.h>
+#include <linux/uio.h>
 
 static inline bool is_crashed_pfn_valid(unsigned long pfn)
 {
@@ -29,21 +28,8 @@ static inline bool is_crashed_pfn_valid(unsigned long pfn)
 #endif
 }
 
-/**
- * copy_oldmem_page - copy one page from "oldmem"
- * @pfn: page frame number to be copied
- * @buf: target memory address for the copy; this can be in kernel address
- *	space or user address space (see @userbuf)
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page (based on pfn) to begin the copy
- * @userbuf: if set, @buf is in user address space, use copy_to_user(),
- *	otherwise @buf is in kernel address space, use memcpy().
- *
- * Copy a page from "oldmem". For this page, there might be no pte mapped
- * in the current kernel.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
-			 unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, size_t csize,
+			 unsigned long offset)
 {
 	void  *vaddr;
 
@@ -54,14 +40,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
 		return -EFAULT;
 
 	vaddr = kmap_local_pfn(pfn);
-
-	if (!userbuf) {
-		memcpy(buf, vaddr + offset, csize);
-	} else {
-		if (copy_to_user(buf, vaddr + offset, csize))
-			csize = -EFAULT;
-	}
-
+	csize = copy_to_iter(vaddr + offset, csize, iter);
 	kunmap_local(vaddr);
 
 	return csize;
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 97529552dd24..94fe4aff9694 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -8,12 +8,12 @@
 
 #include <linux/errno.h>
 #include <linux/crash_dump.h>
-#include <linux/uaccess.h>
+#include <linux/uio.h>
 #include <linux/io.h>
 #include <linux/cc_platform.h>
 
-static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
-				  unsigned long offset, int userbuf,
+static ssize_t __copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+				  size_t csize, unsigned long offset,
 				  bool encrypted)
 {
 	void  *vaddr;
@@ -29,46 +29,27 @@ static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
 	if (!vaddr)
 		return -ENOMEM;
 
-	if (userbuf) {
-		if (copy_to_user((void __user *)buf, vaddr + offset, csize)) {
-			iounmap((void __iomem *)vaddr);
-			return -EFAULT;
-		}
-	} else
-		memcpy(buf, vaddr + offset, csize);
+	csize = copy_to_iter(vaddr + offset, csize, iter);
 
 	iounmap((void __iomem *)vaddr);
 	return csize;
 }
 
-/**
- * copy_oldmem_page - copy one page of memory
- * @pfn: page frame number to be copied
- * @buf: target memory address for the copy; this can be in kernel address
- *	space or user address space (see @userbuf)
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page (based on pfn) to begin the copy
- * @userbuf: if set, @buf is in user address space, use copy_to_user(),
- *	otherwise @buf is in kernel address space, use memcpy().
- *
- * Copy a page from the old kernel's memory. For this page, there is no pte
- * mapped in the current kernel. We stitch up a pte, similar to kmap_atomic.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
-			 unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, size_t csize,
+			 unsigned long offset)
 {
-	return __copy_oldmem_page(pfn, buf, csize, offset, userbuf, false);
+	return __copy_oldmem_page(iter, pfn, csize, offset, false);
 }
 
-/**
+/*
  * copy_oldmem_page_encrypted - same as copy_oldmem_page() above but ioremap the
  * memory with the encryption mask set to accommodate kdump on SME-enabled
  * machines.
  */
-ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize,
-				   unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn,
+				   size_t csize, unsigned long offset)
 {
-	return __copy_oldmem_page(pfn, buf, csize, offset, userbuf, true);
+	return __copy_oldmem_page(iter, pfn, csize, offset, true);
 }
 
 ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 6f1b8ddc6f7a..54dda2e19ed1 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -26,6 +26,7 @@
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
 #include <linux/uaccess.h>
+#include <linux/uio.h>
 #include <linux/cc_platform.h>
 #include <asm/io.h>
 #include "internal.h"
@@ -128,9 +129,8 @@ static int open_vmcore(struct inode *inode, struct file *file)
 }
 
 /* Reads a page from the oldmem device from given offset. */
-ssize_t read_from_oldmem(char *buf, size_t count,
-			 u64 *ppos, int userbuf,
-			 bool encrypted)
+static ssize_t read_from_oldmem_iter(struct iov_iter *iter, size_t count,
+			 u64 *ppos, bool encrypted)
 {
 	unsigned long pfn, offset;
 	size_t nr_bytes;
@@ -152,29 +152,23 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 
 		/* If pfn is not ram, return zeros for sparse dump files */
 		if (!pfn_is_ram(pfn)) {
-			tmp = 0;
-			if (!userbuf)
-				memset(buf, 0, nr_bytes);
-			else if (clear_user(buf, nr_bytes))
-				tmp = -EFAULT;
+			tmp = iov_iter_zero(nr_bytes, iter);
 		} else {
 			if (encrypted)
-				tmp = copy_oldmem_page_encrypted(pfn, buf,
+				tmp = copy_oldmem_page_encrypted(iter, pfn,
 								 nr_bytes,
-								 offset,
-								 userbuf);
+								 offset);
 			else
-				tmp = copy_oldmem_page(pfn, buf, nr_bytes,
-						       offset, userbuf);
+				tmp = copy_oldmem_page(iter, pfn, nr_bytes,
+						       offset);
 		}
-		if (tmp < 0) {
+		if (tmp < nr_bytes) {
 			srcu_read_unlock(&vmcore_cb_srcu, idx);
-			return tmp;
+			return -EFAULT;
 		}
 
 		*ppos += nr_bytes;
 		count -= nr_bytes;
-		buf += nr_bytes;
 		read += nr_bytes;
 		++pfn;
 		offset = 0;
@@ -184,6 +178,27 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 	return read;
 }
 
+ssize_t read_from_oldmem(char *buf, size_t count,
+			 u64 *ppos, int userbuf,
+			 bool encrypted)
+{
+	struct iov_iter iter;
+	struct iovec iov;
+	struct kvec kvec;
+
+	if (userbuf) {
+		iov.iov_base = (__force void __user *)buf;
+		iov.iov_len = count;
+		iov_iter_init(&iter, READ, &iov, 1, count);
+	} else {
+		kvec.iov_base = buf;
+		kvec.iov_len = count;
+		iov_iter_kvec(&iter, READ, &kvec, 1, count);
+	}
+
+	return read_from_oldmem_iter(&iter, count, ppos, encrypted);
+}
+
 /*
  * Architectures may override this function to allocate ELF header in 2nd kernel
  */
@@ -228,11 +243,10 @@ int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
 /*
  * Architectures which support memory encryption override this.
  */
-ssize_t __weak
-copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize,
-			   unsigned long offset, int userbuf)
+ssize_t __weak copy_oldmem_page_encrypted(struct iov_iter *iter,
+		unsigned long pfn, size_t csize, unsigned long offset)
 {
-	return copy_oldmem_page(pfn, buf, csize, offset, userbuf);
+	return copy_oldmem_page(iter, pfn, csize, offset);
 }
 
 /*
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 620821549b23..a1cf7d5c03c7 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -24,11 +24,10 @@ extern int remap_oldmem_pfn_range(struct vm_area_struct *vma,
 				  unsigned long from, unsigned long pfn,
 				  unsigned long size, pgprot_t prot);
 
-extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
-						unsigned long, int);
-extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf,
-					  size_t csize, unsigned long offset,
-					  int userbuf);
+ssize_t copy_oldmem_page(struct iov_iter *i, unsigned long pfn, size_t csize,
+		unsigned long offset);
+ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn,
+				   size_t csize, unsigned long offset);
 
 void vmcore_cleanup(void);
 
-- 
cgit v1.2.3


From e0690479917cbce740eef51fa3de92c69647a5ad Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 14:37:59 -0700
Subject: vmcore: convert read_from_oldmem() to take an iov_iter

Remove the read_from_oldmem() wrapper introduced earlier and convert all
the remaining callers to pass an iov_iter.

Link: https://lkml.kernel.org/r/20220408090636.560886-4-bhe@redhat.com
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Baoquan He <bhe@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Amit Daniel Kachhap <amit.kachhap@arm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/kernel/crash_dump_64.c |  7 ++++++-
 fs/proc/vmcore.c                | 40 +++++++++++++++-------------------------
 include/linux/crash_dump.h      | 10 ++++------
 3 files changed, 25 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 94fe4aff9694..e75bc2f217ff 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -54,6 +54,11 @@ ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn,
 
 ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
 {
-	return read_from_oldmem(buf, count, ppos, 0,
+	struct kvec kvec = { .iov_base = buf, .iov_len = count };
+	struct iov_iter iter;
+
+	iov_iter_kvec(&iter, READ, &kvec, 1, count);
+
+	return read_from_oldmem(&iter, count, ppos,
 				cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT));
 }
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 4a721865b5cd..4eaeb645e759 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -129,7 +129,7 @@ static int open_vmcore(struct inode *inode, struct file *file)
 }
 
 /* Reads a page from the oldmem device from given offset. */
-static ssize_t read_from_oldmem_iter(struct iov_iter *iter, size_t count,
+ssize_t read_from_oldmem(struct iov_iter *iter, size_t count,
 			 u64 *ppos, bool encrypted)
 {
 	unsigned long pfn, offset;
@@ -178,27 +178,6 @@ static ssize_t read_from_oldmem_iter(struct iov_iter *iter, size_t count,
 	return read;
 }
 
-ssize_t read_from_oldmem(char *buf, size_t count,
-			 u64 *ppos, int userbuf,
-			 bool encrypted)
-{
-	struct iov_iter iter;
-	struct iovec iov;
-	struct kvec kvec;
-
-	if (userbuf) {
-		iov.iov_base = (__force void __user *)buf;
-		iov.iov_len = count;
-		iov_iter_init(&iter, READ, &iov, 1, count);
-	} else {
-		kvec.iov_base = buf;
-		kvec.iov_len = count;
-		iov_iter_kvec(&iter, READ, &kvec, 1, count);
-	}
-
-	return read_from_oldmem_iter(&iter, count, ppos, encrypted);
-}
-
 /*
  * Architectures may override this function to allocate ELF header in 2nd kernel
  */
@@ -218,7 +197,12 @@ void __weak elfcorehdr_free(unsigned long long addr)
  */
 ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
 {
-	return read_from_oldmem(buf, count, ppos, 0, false);
+	struct kvec kvec = { .iov_base = buf, .iov_len = count };
+	struct iov_iter iter;
+
+	iov_iter_kvec(&iter, READ, &kvec, 1, count);
+
+	return read_from_oldmem(&iter, count, ppos, false);
 }
 
 /*
@@ -226,7 +210,13 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
  */
 ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
 {
-	return read_from_oldmem(buf, count, ppos, 0, cc_platform_has(CC_ATTR_MEM_ENCRYPT));
+	struct kvec kvec = { .iov_base = buf, .iov_len = count };
+	struct iov_iter iter;
+
+	iov_iter_kvec(&iter, READ, &kvec, 1, count);
+
+	return read_from_oldmem(&iter, count, ppos,
+			cc_platform_has(CC_ATTR_MEM_ENCRYPT));
 }
 
 /*
@@ -402,7 +392,7 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos)
 					    m->offset + m->size - *fpos,
 					    iov_iter_count(iter));
 			start = m->paddr + *fpos - m->offset;
-			tmp = read_from_oldmem_iter(iter, tsz, &start,
+			tmp = read_from_oldmem(iter, tsz, &start,
 					cc_platform_has(CC_ATTR_MEM_ENCRYPT));
 			if (tmp < 0)
 				return tmp;
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index a1cf7d5c03c7..0f3a656293b0 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -134,13 +134,11 @@ static inline int vmcore_add_device_dump(struct vmcoredd_data *data)
 #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
 
 #ifdef CONFIG_PROC_VMCORE
-ssize_t read_from_oldmem(char *buf, size_t count,
-			 u64 *ppos, int userbuf,
-			 bool encrypted);
+ssize_t read_from_oldmem(struct iov_iter *iter, size_t count,
+			 u64 *ppos, bool encrypted);
 #else
-static inline ssize_t read_from_oldmem(char *buf, size_t count,
-				       u64 *ppos, int userbuf,
-				       bool encrypted)
+static inline ssize_t read_from_oldmem(struct iov_iter *iter, size_t count,
+				       u64 *ppos, bool encrypted)
 {
 	return -EOPNOTSUPP;
 }
-- 
cgit v1.2.3


From f485922d8fe4e44f6d52a5bb95a603b7c65554bb Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Date: Fri, 29 Apr 2022 14:38:01 -0700
Subject: pipe: make poll_usage boolean and annotate its access

Patch series "Fix data-races around epoll reported by KCSAN."

This series suppresses a false positive KCSAN's message and fixes a real
data-race.


This patch (of 2):

pipe_poll() runs locklessly and assigns 1 to poll_usage.  Once poll_usage
is set to 1, it never changes in other places.  However, concurrent writes
of a value trigger KCSAN, so let's make KCSAN happy.

BUG: KCSAN: data-race in pipe_poll / pipe_poll

write to 0xffff8880042f6678 of 4 bytes by task 174 on cpu 3:
 pipe_poll (fs/pipe.c:656)
 ep_item_poll.isra.0 (./include/linux/poll.h:88 fs/eventpoll.c:853)
 do_epoll_wait (fs/eventpoll.c:1692 fs/eventpoll.c:1806 fs/eventpoll.c:2234)
 __x64_sys_epoll_wait (fs/eventpoll.c:2246 fs/eventpoll.c:2241 fs/eventpoll.c:2241)
 do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80)
 entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:113)

write to 0xffff8880042f6678 of 4 bytes by task 177 on cpu 1:
 pipe_poll (fs/pipe.c:656)
 ep_item_poll.isra.0 (./include/linux/poll.h:88 fs/eventpoll.c:853)
 do_epoll_wait (fs/eventpoll.c:1692 fs/eventpoll.c:1806 fs/eventpoll.c:2234)
 __x64_sys_epoll_wait (fs/eventpoll.c:2246 fs/eventpoll.c:2241 fs/eventpoll.c:2241)
 do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80)
 entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:113)

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 177 Comm: epoll_race Not tainted 5.17.0-58927-gf443e374ae13 #6
Hardware name: Red Hat KVM, BIOS 1.11.0-2.amzn2 04/01/2014

Link: https://lkml.kernel.org/r/20220322002653.33865-1-kuniyu@amazon.co.jp
Link: https://lkml.kernel.org/r/20220322002653.33865-2-kuniyu@amazon.co.jp
Fixes: 3b844826b6c6 ("pipe: avoid unnecessary EPOLLET wakeups under normal loads")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Kuniyuki Iwashima <kuni1840@gmail.com>
Cc: "Soheil Hassas Yeganeh" <soheil@google.com>
Cc: "Sridhar Samudrala" <sridhar.samudrala@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/pipe.c                 | 2 +-
 include/linux/pipe_fs_i.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/pipe.c b/fs/pipe.c
index e140ea150bbb..d04c3fce28a6 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -653,7 +653,7 @@ pipe_poll(struct file *filp, poll_table *wait)
 	unsigned int head, tail;
 
 	/* Epoll has some historical nasty semantics, this enables them */
-	pipe->poll_usage = 1;
+	WRITE_ONCE(pipe->poll_usage, true);
 
 	/*
 	 * Reading pipe state only -- no need for acquiring the semaphore.
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index c00c618ef290..cb0fd633a610 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -71,7 +71,7 @@ struct pipe_inode_info {
 	unsigned int files;
 	unsigned int r_counter;
 	unsigned int w_counter;
-	unsigned int poll_usage;
+	bool poll_usage;
 	struct page *tmp_page;
 	struct fasync_struct *fasync_readers;
 	struct fasync_struct *fasync_writers;
-- 
cgit v1.2.3


From d679ae94fdd5d3ab00c35078f5af5f37e068b03d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Date: Fri, 29 Apr 2022 14:38:01 -0700
Subject: list: fix a data-race around ep->rdllist

ep_poll() first calls ep_events_available() with no lock held and checks
if ep->rdllist is empty by list_empty_careful(), which reads
rdllist->prev.  Thus all accesses to it need some protection to avoid
store/load-tearing.

Note INIT_LIST_HEAD_RCU() already has the annotation for both prev
and next.

Commit bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket
fds.") added the first lockless ep_events_available(), and commit
c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()")
made some ep_events_available() calls lockless and added single call under
a lock, finally commit e59d3c64cba6 ("epoll: eliminate unnecessary lock
for zero timeout") made the last ep_events_available() lockless.

BUG: KCSAN: data-race in do_epoll_wait / do_epoll_wait

write to 0xffff88810480c7d8 of 8 bytes by task 1802 on cpu 0:
 INIT_LIST_HEAD include/linux/list.h:38 [inline]
 list_splice_init include/linux/list.h:492 [inline]
 ep_start_scan fs/eventpoll.c:622 [inline]
 ep_send_events fs/eventpoll.c:1656 [inline]
 ep_poll fs/eventpoll.c:1806 [inline]
 do_epoll_wait+0x4eb/0xf40 fs/eventpoll.c:2234
 do_epoll_pwait fs/eventpoll.c:2268 [inline]
 __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline]
 __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275
 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff88810480c7d8 of 8 bytes by task 1799 on cpu 1:
 list_empty_careful include/linux/list.h:329 [inline]
 ep_events_available fs/eventpoll.c:381 [inline]
 ep_poll fs/eventpoll.c:1797 [inline]
 do_epoll_wait+0x279/0xf40 fs/eventpoll.c:2234
 do_epoll_pwait fs/eventpoll.c:2268 [inline]
 __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline]
 __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275
 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0xffff88810480c7d0 -> 0xffff888103c15098

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 1799 Comm: syz-fuzzer Tainted: G        W         5.17.0-rc7-syzkaller-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Link: https://lkml.kernel.org/r/20220322002653.33865-3-kuniyu@amazon.co.jp
Fixes: e59d3c64cba6 ("epoll: eliminate unnecessary lock for zero timeout")
Fixes: c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()")
Fixes: bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Reported-by: syzbot+bdd6e38a1ed5ee58d8bd@syzkaller.appspotmail.com
Cc: Al Viro <viro@zeniv.linux.org.uk>, Andrew Morton <akpm@linux-foundation.org>
Cc: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Cc: Kuniyuki Iwashima <kuni1840@gmail.com>
Cc: "Soheil Hassas Yeganeh" <soheil@google.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "Sridhar Samudrala" <sridhar.samudrala@intel.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/list.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/list.h b/include/linux/list.h
index dd6c2041d09c..d7d2bfa1a365 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -35,7 +35,7 @@
 static inline void INIT_LIST_HEAD(struct list_head *list)
 {
 	WRITE_ONCE(list->next, list);
-	list->prev = list;
+	WRITE_ONCE(list->prev, list);
 }
 
 #ifdef CONFIG_DEBUG_LIST
@@ -306,7 +306,7 @@ static inline int list_empty(const struct list_head *head)
 static inline void list_del_init_careful(struct list_head *entry)
 {
 	__list_del_entry(entry);
-	entry->prev = entry;
+	WRITE_ONCE(entry->prev, entry);
 	smp_store_release(&entry->next, entry);
 }
 
@@ -326,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry)
 static inline int list_empty_careful(const struct list_head *head)
 {
 	struct list_head *next = smp_load_acquire(&head->next);
-	return list_is_head(next, head) && (next == head->prev);
+	return list_is_head(next, head) && (next == READ_ONCE(head->prev));
 }
 
 /**
-- 
cgit v1.2.3


From a9866bef5171c859cfabc1155c594d28f194aa23 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Fri, 29 Apr 2022 14:38:02 -0700
Subject: ptrace: fix wrong comment of PT_DTRACE

PT_DTRACE is only used on um now, fix the wrong comment.

Link: https://lkml.kernel.org/r/1649240981-11024-3-git-send-email-yangtiezhu@loongson.cn
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/ptrace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 15b3d176b6b4..db4509587d2c 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -30,7 +30,7 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 
 #define PT_SEIZED	0x00010000	/* SEIZE used, enable new behavior */
 #define PT_PTRACED	0x00000001
-#define PT_DTRACE	0x00000002	/* delayed trace (used on m68k, i386) */
+#define PT_DTRACE	0x00000002	/* delayed trace (used on um) */
 
 #define PT_OPT_FLAG_SHIFT	3
 /* PT_TRACE_* event enable flags */
-- 
cgit v1.2.3


From f94fd25cb0aaf77fd7453f31c5d394a1a68ecf60 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 28 Apr 2022 18:45:06 -0600
Subject: tcp: pass back data left in socket after receive

This is currently done for CMSG_INQ, add an ability to do so via struct
msghdr as well and have CMSG_INQ use that too. If the caller sets
msghdr->msg_get_inq, then we'll pass back the hint in msghdr->msg_inq.

Rearrange struct msghdr a bit so we can add this member while shrinking
it at the same time. On a 64-bit build, it was 96 bytes before this
change and 88 bytes afterwards.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Link: https://lore.kernel.org/r/650c22ca-cffc-0255-9a05-2413a1e20826@kernel.dk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/socket.h |  6 +++++-
 net/ipv4/tcp.c         | 16 ++++++++++------
 2 files changed, 15 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 6f85f5d957ef..12085c9a8544 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -50,6 +50,9 @@ struct linger {
 struct msghdr {
 	void		*msg_name;	/* ptr to socket address structure */
 	int		msg_namelen;	/* size of socket address structure */
+
+	int		msg_inq;	/* output, data left in socket */
+
 	struct iov_iter	msg_iter;	/* data */
 
 	/*
@@ -62,8 +65,9 @@ struct msghdr {
 		void __user	*msg_control_user;
 	};
 	bool		msg_control_is_user : 1;
-	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
+	bool		msg_get_inq : 1;/* return INQ after receive */
 	unsigned int	msg_flags;	/* flags on received message */
+	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cf18fbcbf123..bb7ef45408e1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2335,8 +2335,10 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
 
-	if (tp->recvmsg_inq)
+	if (tp->recvmsg_inq) {
 		*cmsg_flags = TCP_CMSG_INQ;
+		msg->msg_get_inq = 1;
+	}
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	/* Urgent data needs to be handled specially. */
@@ -2559,7 +2561,7 @@ recv_sndq:
 int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		int flags, int *addr_len)
 {
-	int cmsg_flags = 0, ret, inq;
+	int cmsg_flags = 0, ret;
 	struct scm_timestamping_internal tss;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
@@ -2576,12 +2578,14 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	release_sock(sk);
 	sk_defer_free_flush(sk);
 
-	if (cmsg_flags && ret >= 0) {
+	if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) {
 		if (cmsg_flags & TCP_CMSG_TS)
 			tcp_recv_timestamp(msg, sk, &tss);
-		if (cmsg_flags & TCP_CMSG_INQ) {
-			inq = tcp_inq_hint(sk);
-			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
+		if (msg->msg_get_inq) {
+			msg->msg_inq = tcp_inq_hint(sk);
+			if (cmsg_flags & TCP_CMSG_INQ)
+				put_cmsg(msg, SOL_TCP, TCP_CM_INQ,
+					 sizeof(msg->msg_inq), &msg->msg_inq);
 		}
 	}
 	return ret;
-- 
cgit v1.2.3


From 657dd5f97b2ed16cdaa6339f42f9130240af1c04 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 28 Apr 2022 11:58:45 +0100
Subject: net: inline skb_zerocopy_iter_dgram

skb_zerocopy_iter_dgram() is a small proxy function, inline it. For
that, move __zerocopy_sg_from_iter into linux/skbuff.h

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 36 ++++++++++++++++++++++--------------
 net/core/datagram.c    |  2 --
 net/core/datagram.h    | 15 ---------------
 net/core/skbuff.c      |  7 -------
 4 files changed, 22 insertions(+), 38 deletions(-)
 delete mode 100644 net/core/datagram.h

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index dc4b3e1cf21b..3270cb72e4d8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -684,20 +684,6 @@ struct ubuf_info {
 int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
 void mm_unaccount_pinned_pages(struct mmpin *mmp);
 
-struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size);
-struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
-				       struct ubuf_info *uarg);
-
-void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
-
-void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
-			   bool success);
-
-int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len);
-int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
-			     struct msghdr *msg, int len,
-			     struct ubuf_info *uarg);
-
 /* This data is invariant across clones and lives at
  * the end of the header data, ie. at skb->end.
  */
@@ -1679,6 +1665,28 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 }
 #endif
 
+struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size);
+struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
+				       struct ubuf_info *uarg);
+
+void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
+
+void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
+			   bool success);
+
+int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
+			    struct iov_iter *from, size_t length);
+
+static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
+					  struct msghdr *msg, int len)
+{
+	return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
+}
+
+int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
+			     struct msghdr *msg, int len,
+			     struct ubuf_info *uarg);
+
 /* Internal */
 #define skb_shinfo(SKB)	((struct skb_shared_info *)(skb_end_pointer(SKB)))
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 70126d15ca6e..50f4faeea76c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -62,8 +62,6 @@
 #include <trace/events/skb.h>
 #include <net/busy_poll.h>
 
-#include "datagram.h"
-
 /*
  *	Is a socket 'connection oriented' ?
  */
diff --git a/net/core/datagram.h b/net/core/datagram.h
deleted file mode 100644
index bcfb75bfa3b2..000000000000
--- a/net/core/datagram.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef _NET_CORE_DATAGRAM_H_
-#define _NET_CORE_DATAGRAM_H_
-
-#include <linux/types.h>
-
-struct sock;
-struct sk_buff;
-struct iov_iter;
-
-int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
-			    struct iov_iter *from, size_t length);
-
-#endif /* _NET_CORE_DATAGRAM_H_ */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 00980e62415b..b92e93dcaa91 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -80,7 +80,6 @@
 #include <linux/user_namespace.h>
 #include <linux/indirect_call_wrapper.h>
 
-#include "datagram.h"
 #include "sock_destructor.h"
 
 struct kmem_cache *skbuff_head_cache __ro_after_init;
@@ -1340,12 +1339,6 @@ void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref)
 }
 EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort);
 
-int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len)
-{
-	return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
-}
-EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram);
-
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			     struct msghdr *msg, int len,
 			     struct ubuf_info *uarg)
-- 
cgit v1.2.3


From c526fd8f9f4f21cb83c0b1c9a1ee9c0ac9be9e2e Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 28 Apr 2022 11:58:46 +0100
Subject: net: inline dev_queue_xmit()

Inline dev_queue_xmit() and dev_queue_xmit_accel(), they both are small
proxy functions doing nothing but redirecting the control flow to
__dev_queue_xmit().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 14 ++++++++++++--
 net/core/dev.c            | 15 ++-------------
 2 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b75ca2d095ae..4aba92a4042a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2940,10 +2940,20 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
 		       struct net_device *sb_dev);
 
-int dev_queue_xmit(struct sk_buff *skb);
-int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
+int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev);
 int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
 
+static inline int dev_queue_xmit(struct sk_buff *skb)
+{
+	return __dev_queue_xmit(skb, NULL);
+}
+
+static inline int dev_queue_xmit_accel(struct sk_buff *skb,
+				       struct net_device *sb_dev)
+{
+	return __dev_queue_xmit(skb, sb_dev);
+}
+
 static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 {
 	int ret;
diff --git a/net/core/dev.c b/net/core/dev.c
index 7a61690d3137..d127164771f2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4111,7 +4111,7 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
  *      the BH enable code must have IRQs enabled so that it will not deadlock.
  *          --BLG
  */
-static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
+int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 {
 	struct net_device *dev = skb->dev;
 	struct netdev_queue *txq = NULL;
@@ -4235,18 +4235,7 @@ out:
 	rcu_read_unlock_bh();
 	return rc;
 }
-
-int dev_queue_xmit(struct sk_buff *skb)
-{
-	return __dev_queue_xmit(skb, NULL);
-}
-EXPORT_SYMBOL(dev_queue_xmit);
-
-int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
-{
-	return __dev_queue_xmit(skb, sb_dev);
-}
-EXPORT_SYMBOL(dev_queue_xmit_accel);
+EXPORT_SYMBOL(__dev_queue_xmit);
 
 int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 {
-- 
cgit v1.2.3


From 48cec73a891cca087fbc7791c4753784180991a9 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Fri, 29 Apr 2022 09:19:53 +0200
Subject: net: lan966x: Fix compilation error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Starting from the blamed commit, the lan966x build fails with the
following compilation error:

drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c:342:9: error: implicit declaration of function ‘ptp_find_pin_unlocked’ [-Werror=implicit-function-declaration]
  342 |   pin = ptp_find_pin_unlocked(phc->clock, PTP_PF_EXTTS, 0);

The issue is that there is no stub function for ptp_find_pin_unlocked
in case CONFIG_PTP_1588_CLOCK is not selected. Therefore add one.

Reported-by: kernel test robot <lkp@intel.com>
Fixes: f3d8e0a9c28ba0 ("net: lan966x: Add support for PTP_PF_EXTTS")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptp_clock_kernel.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 554454cb8693..e8cc8b6bbf50 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -321,6 +321,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp)
 static inline int ptp_find_pin(struct ptp_clock *ptp,
 			       enum ptp_pin_function func, unsigned int chan)
 { return -1; }
+static inline int ptp_find_pin_unlocked(struct ptp_clock *ptp,
+					enum ptp_pin_function func,
+					unsigned int chan)
+{ return -1; }
 static inline int ptp_schedule_worker(struct ptp_clock *ptp,
 				      unsigned long delay)
 { return -EOPNOTSUPP; }
-- 
cgit v1.2.3


From e788be95a57a9bebe446878ce9bf2750f6fe4974 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 28 Apr 2022 17:25:16 -0600
Subject: task_work: allow TWA_SIGNAL without a rescheduling IPI

Some use cases don't always need an IPI when sending a TWA_SIGNAL
notification. Add TWA_SIGNAL_NO_IPI, which is just like TWA_SIGNAL, except
it doesn't send an IPI to the target task. It merely sets
TIF_NOTIFY_SIGNAL and wakes up the task.

This can be useful in avoiding a forceful transition to the kernel if the
task is running in userspace. Depending on the task_work in question, it
may be quite fine waiting for the next reschedule or kernel enter anyway,
or the use case may even have other mechanisms for hinting to the task
that a transition may be useful. This can drive more cooperative
scheduling of task_work.

Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/821f42b6-7d91-8074-8212-d34998097de4@kernel.dk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/sched/signal.h | 13 +++++++++++--
 include/linux/task_work.h    |  1 +
 kernel/task_work.c           | 25 +++++++++++++++++++------
 3 files changed, 31 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 3c8b34876744..66b689f6cfcb 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -355,14 +355,23 @@ static inline void clear_notify_signal(void)
 	smp_mb__after_atomic();
 }
 
+/*
+ * Returns 'true' if kick_process() is needed to force a transition from
+ * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work.
+ */
+static inline bool __set_notify_signal(struct task_struct *task)
+{
+	return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) &&
+	       !wake_up_state(task, TASK_INTERRUPTIBLE);
+}
+
 /*
  * Called to break out of interruptible wait loops, and enter the
  * exit_to_user_mode_loop().
  */
 static inline void set_notify_signal(struct task_struct *task)
 {
-	if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) &&
-	    !wake_up_state(task, TASK_INTERRUPTIBLE))
+	if (__set_notify_signal(task))
 		kick_process(task);
 }
 
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
index 897494b597ba..795ef5a68429 100644
--- a/include/linux/task_work.h
+++ b/include/linux/task_work.h
@@ -17,6 +17,7 @@ enum task_work_notify_mode {
 	TWA_NONE,
 	TWA_RESUME,
 	TWA_SIGNAL,
+	TWA_SIGNAL_NO_IPI,
 };
 
 static inline bool task_work_pending(struct task_struct *task)
diff --git a/kernel/task_work.c b/kernel/task_work.c
index c59e1a49bc40..dff75bcde151 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -12,12 +12,22 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * @notify: how to notify the targeted task
  *
  * Queue @work for task_work_run() below and notify the @task if @notify
- * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the
- * it will interrupt the targeted task and run the task_work. @TWA_RESUME
- * work is run only when the task exits the kernel and returns to user mode,
- * or before entering guest mode. Fails if the @task is exiting/exited and thus
- * it can't process this @work. Otherwise @work->func() will be called when the
- * @task goes through one of the aforementioned transitions, or exits.
+ * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI.
+ *
+ * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted
+ * task and run the task_work, regardless of whether the task is currently
+ * running in the kernel or userspace.
+ * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a
+ * reschedule IPI to force the targeted task to reschedule and run task_work.
+ * This can be advantageous if there's no strict requirement that the
+ * task_work be run as soon as possible, just whenever the task enters the
+ * kernel anyway.
+ * @TWA_RESUME work is run only when the task exits the kernel and returns to
+ * user mode, or before entering guest mode.
+ *
+ * Fails if the @task is exiting/exited and thus it can't process this @work.
+ * Otherwise @work->func() will be called when the @task goes through one of
+ * the aforementioned transitions, or exits.
  *
  * If the targeted task is exiting, then an error is returned and the work item
  * is not queued. It's up to the caller to arrange for an alternative mechanism
@@ -53,6 +63,9 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 	case TWA_SIGNAL:
 		set_notify_signal(task);
 		break;
+	case TWA_SIGNAL_NO_IPI:
+		__set_notify_signal(task);
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;
-- 
cgit v1.2.3


From d664e399128bd78b905ff480917e2c2d4949e101 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 13 Apr 2022 15:31:02 +0200
Subject: sched: Fix missing prototype warnings

A W=1 build emits more than a dozen missing prototype warnings related to
scheduler and scheduler specific includes.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220413133024.249118058@linutronix.de
---
 include/linux/sched.h        | 2 ++
 kernel/sched/build_policy.c  | 2 ++
 kernel/sched/build_utility.c | 1 +
 kernel/sched/core.c          | 3 +++
 kernel/sched/deadline.c      | 2 --
 kernel/sched/fair.c          | 1 +
 kernel/sched/sched.h         | 8 ++------
 kernel/sched/smp.h           | 6 ++++++
 kernel/stop_machine.c        | 2 --
 9 files changed, 17 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index fc74ea2578b7..a27316f5f737 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2388,4 +2388,6 @@ static inline void sched_core_free(struct task_struct *tsk) { }
 static inline void sched_core_fork(struct task_struct *p) { }
 #endif
 
+extern void sched_set_stop_task(int cpu, struct task_struct *stop);
+
 #endif
diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
index e0104b45029a..d9dc9ab3773f 100644
--- a/kernel/sched/build_policy.c
+++ b/kernel/sched/build_policy.c
@@ -15,6 +15,7 @@
 /* Headers: */
 #include <linux/sched/clock.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/hotplug.h>
 #include <linux/sched/posix-timers.h>
 #include <linux/sched/rt.h>
 
@@ -31,6 +32,7 @@
 #include <uapi/linux/sched/types.h>
 
 #include "sched.h"
+#include "smp.h"
 
 #include "autogroup.h"
 #include "stats.h"
diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
index eec0849b2aae..99bdd96f454f 100644
--- a/kernel/sched/build_utility.c
+++ b/kernel/sched/build_utility.c
@@ -14,6 +14,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/nohz.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/rseq_api.h>
 #include <linux/sched/task_stack.h>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 068c088e9584..e644578bc871 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -26,7 +26,10 @@
 #include <linux/topology.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/cond_resched.h>
+#include <linux/sched/cputime.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/hotplug.h>
+#include <linux/sched/init.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/mm.h>
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fb4255ae0b2c..6ae423627a7a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1220,8 +1220,6 @@ int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 	return (dl_se->runtime <= 0);
 }
 
-extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
-
 /*
  * This function implements the GRUB accounting rule:
  * according to the GRUB reclaiming algorithm, the runtime is
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6ca054b11a16..bc9f6e94c84e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -36,6 +36,7 @@
 #include <linux/sched/cond_resched.h>
 #include <linux/sched/cputime.h>
 #include <linux/sched/isolation.h>
+#include <linux/sched/nohz.h>
 
 #include <linux/cpuidle.h>
 #include <linux/interrupt.h>
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 762be73972bd..4784898e8f83 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1833,12 +1833,7 @@ static inline void dirty_sched_domain_sysctl(int cpu)
 #endif
 
 extern int sched_update_scaling(void);
-
-extern void flush_smp_call_function_from_idle(void);
-
-#else /* !CONFIG_SMP: */
-static inline void flush_smp_call_function_from_idle(void) { }
-#endif
+#endif /* CONFIG_SMP */
 
 #include "stats.h"
 
@@ -2315,6 +2310,7 @@ extern void resched_cpu(int cpu);
 
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
 
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
diff --git a/kernel/sched/smp.h b/kernel/sched/smp.h
index 9620e323162c..5719bf9280e9 100644
--- a/kernel/sched/smp.h
+++ b/kernel/sched/smp.h
@@ -7,3 +7,9 @@
 extern void sched_ttwu_pending(void *arg);
 
 extern void send_call_function_single_ipi(int cpu);
+
+#ifdef CONFIG_SMP
+extern void flush_smp_call_function_from_idle(void);
+#else
+static inline void flush_smp_call_function_from_idle(void) { }
+#endif
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index cbc30271ea4d..6da7b91af353 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -535,8 +535,6 @@ void stop_machine_park(int cpu)
 	kthread_park(stopper->thread);
 }
 
-extern void sched_set_stop_task(int cpu, struct task_struct *stop);
-
 static void cpu_stop_create(unsigned int cpu)
 {
 	sched_set_stop_task(cpu, per_cpu(cpu_stopper.thread, cpu));
-- 
cgit v1.2.3


From 1a90bfd220201fbe050dfc15deaac20ca5f15638 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 13 Apr 2022 15:31:05 +0200
Subject: smp: Make softirq handling RT safe in flush_smp_call_function_queue()

flush_smp_call_function_queue() invokes do_softirq() which is not available
on PREEMPT_RT. flush_smp_call_function_queue() is invoked from the idle
task and the migration task with preemption or interrupts disabled.

So RT kernels cannot process soft interrupts in that context as that has to
acquire 'sleeping spinlocks' which is not possible with preemption or
interrupts disabled and forbidden from the idle task anyway.

The currently known SMP function call which raises a soft interrupt is in
the block layer, but this functionality is not enabled on RT kernels due to
latency and performance reasons.

RT could wake up ksoftirqd unconditionally, but this wants to be avoided if
there were soft interrupts pending already when this is invoked in the
context of the migration task. The migration task might have preempted a
threaded interrupt handler which raised a soft interrupt, but did not reach
the local_bh_enable() to process it. The "running" ksoftirqd might prevent
the handling in the interrupt thread context which is causing latency
issues.

Add a new function which handles this case explicitely for RT and falls
back to do_softirq() on !RT kernels. In the RT case this warns when one of
the flushed SMP function calls raised a soft interrupt so this can be
investigated.

[ tglx: Moved the RT part out of SMP code ]

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/YgKgL6aPj8aBES6G@linutronix.de
Link: https://lore.kernel.org/r/20220413133024.356509586@linutronix.de
---
 include/linux/interrupt.h |  9 +++++++++
 kernel/smp.c              |  5 ++++-
 kernel/softirq.c          | 13 +++++++++++++
 3 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index f40754caaefa..a49fe8d88676 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -607,6 +607,15 @@ struct softirq_action
 asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
 
+#ifdef CONFIG_PREEMPT_RT
+extern void do_softirq_post_smp_call_flush(unsigned int was_pending);
+#else
+static inline void do_softirq_post_smp_call_flush(unsigned int unused)
+{
+	do_softirq();
+}
+#endif
+
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
 extern void __raise_softirq_irqoff(unsigned int nr);
diff --git a/kernel/smp.c b/kernel/smp.c
index 8e85f22ed538..d54c2fe51ada 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -696,6 +696,7 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline)
  */
 void flush_smp_call_function_queue(void)
 {
+	unsigned int was_pending;
 	unsigned long flags;
 
 	if (llist_empty(this_cpu_ptr(&call_single_queue)))
@@ -704,9 +705,11 @@ void flush_smp_call_function_queue(void)
 	cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->idle, CFD_SEQ_NOCPU,
 		      smp_processor_id(), CFD_SEQ_IDLE);
 	local_irq_save(flags);
+	/* Get the already pending soft interrupts for RT enabled kernels */
+	was_pending = local_softirq_pending();
 	__flush_smp_call_function_queue(true);
 	if (local_softirq_pending())
-		do_softirq();
+		do_softirq_post_smp_call_flush(was_pending);
 
 	local_irq_restore(flags);
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index fac801815554..9f0aef8aa9ff 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -294,6 +294,19 @@ static inline void invoke_softirq(void)
 		wakeup_softirqd();
 }
 
+/*
+ * flush_smp_call_function_queue() can raise a soft interrupt in a function
+ * call. On RT kernels this is undesired and the only known functionality
+ * in the block layer which does this is disabled on RT. If soft interrupts
+ * get raised which haven't been raised before the flush, warn so it can be
+ * investigated.
+ */
+void do_softirq_post_smp_call_flush(unsigned int was_pending)
+{
+	if (WARN_ON_ONCE(was_pending != local_softirq_pending()))
+		invoke_softirq();
+}
+
 #else /* CONFIG_PREEMPT_RT */
 
 /*
-- 
cgit v1.2.3


From 47f753c1108e287edb3e27fad8a7511a9d55578e Mon Sep 17 00:00:00 2001
From: Tan Tee Min <tee.min.tan@linux.intel.com>
Date: Fri, 29 Apr 2022 19:58:07 +0800
Subject: net: stmmac: disable Split Header (SPH) for Intel platforms

Based on DesignWare Ethernet QoS datasheet, we are seeing the limitation
of Split Header (SPH) feature is not supported for Ipv4 fragmented packet.
This SPH limitation will cause ping failure when the packets size exceed
the MTU size. For example, the issue happens once the basic ping packet
size is larger than the configured MTU size and the data is lost inside
the fragmented packet, replaced by zeros/corrupted values, and leads to
ping fail.

So, disable the Split Header for Intel platforms.

v2: Add fixes tag in commit message.

Fixes: 67afd6d1cfdf("net: stmmac: Add Split Header support and enable it in XGMAC cores")
Cc: <stable@vger.kernel.org> # 5.10.x
Suggested-by: Ong, Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Mohammad Athari Bin Ismail <mohammad.athari.ismail@intel.com>
Signed-off-by: Wong Vee Khee <vee.khee.wong@linux.intel.com>
Signed-off-by: Tan Tee Min <tee.min.tan@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 1 +
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +-
 include/linux/stmmac.h                            | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 63754a9c4ba7..0b0be0898ac5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -454,6 +454,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->has_gmac4 = 1;
 	plat->force_sf_dma_mode = 0;
 	plat->tso_en = 1;
+	plat->sph_disable = 1;
 
 	/* Multiplying factor to the clk_eee_i clock time
 	 * period to make it closer to 100 ns. This value
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4a4b3651ab3e..2525a80353b7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7021,7 +7021,7 @@ int stmmac_dvr_probe(struct device *device,
 		dev_info(priv->device, "TSO feature enabled\n");
 	}
 
-	if (priv->dma_cap.sphen) {
+	if (priv->dma_cap.sphen && !priv->plat->sph_disable) {
 		ndev->hw_features |= NETIF_F_GRO;
 		priv->sph_cap = true;
 		priv->sph = priv->sph_cap;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 24eea1b05ca2..29917850f079 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -270,5 +270,6 @@ struct plat_stmmacenet_data {
 	int msi_rx_base_vec;
 	int msi_tx_base_vec;
 	bool use_phy_wol;
+	bool sph_disable;
 };
 #endif
-- 
cgit v1.2.3


From 9bd1d9a0d8bb1a549831fd98fcc3105960f7068b Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@svenpeter.dev>
Date: Sun, 1 May 2022 16:55:06 +0200
Subject: soc: apple: Add RTKit IPC library

Apple SoCs such as the M1 come with multiple embedded co-processors
running proprietary firmware. Communication with those is established
over a simple mailbox using the RTKit IPC protocol.

This cannot be implemented inside the mailbox subsystem since on top
of communication over channels we also need support for starting,
hibernating and resetting these co-processors. We also need to
handle shared memory allocations differently depending on the
co-processor and don't want to split that across multiple drivers.

Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sven Peter <sven@svenpeter.dev>
---
 drivers/soc/apple/Kconfig          |  13 +
 drivers/soc/apple/Makefile         |   3 +
 drivers/soc/apple/rtkit-crashlog.c | 154 ++++++
 drivers/soc/apple/rtkit-internal.h |  62 +++
 drivers/soc/apple/rtkit.c          | 958 +++++++++++++++++++++++++++++++++++++
 include/linux/soc/apple/rtkit.h    | 155 ++++++
 6 files changed, 1345 insertions(+)
 create mode 100644 drivers/soc/apple/rtkit-crashlog.c
 create mode 100644 drivers/soc/apple/rtkit-internal.h
 create mode 100644 drivers/soc/apple/rtkit.c
 create mode 100644 include/linux/soc/apple/rtkit.h

(limited to 'include/linux')

diff --git a/drivers/soc/apple/Kconfig b/drivers/soc/apple/Kconfig
index 9b8de31d6a8f..1b09037584a0 100644
--- a/drivers/soc/apple/Kconfig
+++ b/drivers/soc/apple/Kconfig
@@ -17,6 +17,19 @@ config APPLE_PMGR_PWRSTATE
 	  controls for SoC devices. This driver manages them through the
 	  generic power domain framework, and also provides reset support.
 
+config APPLE_RTKIT
+	tristate "Apple RTKit co-processor IPC protocol"
+	depends on MAILBOX
+	depends on ARCH_APPLE || COMPILE_TEST
+	default ARCH_APPLE
+	help
+	  Apple SoCs such as the M1 come with various co-processors running
+	  their proprietary RTKit operating system. This option enables support
+	  for the protocol library used to communicate with those. It is used
+	  by various client drivers.
+
+	  Say 'y' here if you have an Apple SoC.
+
 endmenu
 
 endif
diff --git a/drivers/soc/apple/Makefile b/drivers/soc/apple/Makefile
index c114e84667e4..8aca79fca0dd 100644
--- a/drivers/soc/apple/Makefile
+++ b/drivers/soc/apple/Makefile
@@ -1,2 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_APPLE_PMGR_PWRSTATE)	+= apple-pmgr-pwrstate.o
+
+obj-$(CONFIG_APPLE_RTKIT) += apple-rtkit.o
+apple-rtkit-y = rtkit.o rtkit-crashlog.o
diff --git a/drivers/soc/apple/rtkit-crashlog.c b/drivers/soc/apple/rtkit-crashlog.c
new file mode 100644
index 000000000000..732deed64660
--- /dev/null
+++ b/drivers/soc/apple/rtkit-crashlog.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Apple RTKit IPC library
+ * Copyright (C) The Asahi Linux Contributors
+ */
+#include "rtkit-internal.h"
+
+#define FOURCC(a, b, c, d) \
+	(((u32)(a) << 24) | ((u32)(b) << 16) | ((u32)(c) << 8) | ((u32)(d)))
+
+#define APPLE_RTKIT_CRASHLOG_HEADER FOURCC('C', 'L', 'H', 'E')
+#define APPLE_RTKIT_CRASHLOG_STR FOURCC('C', 's', 't', 'r')
+#define APPLE_RTKIT_CRASHLOG_VERSION FOURCC('C', 'v', 'e', 'r')
+#define APPLE_RTKIT_CRASHLOG_MBOX FOURCC('C', 'm', 'b', 'x')
+#define APPLE_RTKIT_CRASHLOG_TIME FOURCC('C', 't', 'i', 'm')
+
+struct apple_rtkit_crashlog_header {
+	u32 fourcc;
+	u32 version;
+	u32 size;
+	u32 flags;
+	u8 _unk[16];
+};
+static_assert(sizeof(struct apple_rtkit_crashlog_header) == 0x20);
+
+struct apple_rtkit_crashlog_mbox_entry {
+	u64 msg0;
+	u64 msg1;
+	u32 timestamp;
+	u8 _unk[4];
+};
+static_assert(sizeof(struct apple_rtkit_crashlog_mbox_entry) == 0x18);
+
+static void apple_rtkit_crashlog_dump_str(struct apple_rtkit *rtk, u8 *bfr,
+					  size_t size)
+{
+	u32 idx;
+	u8 *ptr, *end;
+
+	memcpy(&idx, bfr, 4);
+
+	ptr = bfr + 4;
+	end = bfr + size;
+	while (ptr < end) {
+		u8 *newline = memchr(ptr, '\n', end - ptr);
+
+		if (newline) {
+			u8 tmp = *newline;
+			*newline = '\0';
+			dev_warn(rtk->dev, "RTKit: Message (id=%x): %s\n", idx,
+				 ptr);
+			*newline = tmp;
+			ptr = newline + 1;
+		} else {
+			dev_warn(rtk->dev, "RTKit: Message (id=%x): %s", idx,
+				 ptr);
+			break;
+		}
+	}
+}
+
+static void apple_rtkit_crashlog_dump_version(struct apple_rtkit *rtk, u8 *bfr,
+					      size_t size)
+{
+	dev_warn(rtk->dev, "RTKit: Version: %s", bfr + 16);
+}
+
+static void apple_rtkit_crashlog_dump_time(struct apple_rtkit *rtk, u8 *bfr,
+					   size_t size)
+{
+	u64 crash_time;
+
+	memcpy(&crash_time, bfr, 8);
+	dev_warn(rtk->dev, "RTKit: Crash time: %lld", crash_time);
+}
+
+static void apple_rtkit_crashlog_dump_mailbox(struct apple_rtkit *rtk, u8 *bfr,
+					      size_t size)
+{
+	u32 type, index, i;
+	size_t n_messages;
+	struct apple_rtkit_crashlog_mbox_entry entry;
+
+	memcpy(&type, bfr + 16, 4);
+	memcpy(&index, bfr + 24, 4);
+	n_messages = (size - 28) / sizeof(entry);
+
+	dev_warn(rtk->dev, "RTKit: Mailbox history (type = %d, index = %d)",
+		 type, index);
+	for (i = 0; i < n_messages; ++i) {
+		memcpy(&entry, bfr + 28 + i * sizeof(entry), sizeof(entry));
+		dev_warn(rtk->dev, "RTKit:  #%03d@%08x: %016llx %016llx", i,
+			 entry.timestamp, entry.msg0, entry.msg1);
+	}
+}
+
+void apple_rtkit_crashlog_dump(struct apple_rtkit *rtk, u8 *bfr, size_t size)
+{
+	size_t offset;
+	u32 section_fourcc, section_size;
+	struct apple_rtkit_crashlog_header header;
+
+	memcpy(&header, bfr, sizeof(header));
+	if (header.fourcc != APPLE_RTKIT_CRASHLOG_HEADER) {
+		dev_warn(rtk->dev, "RTKit: Expected crashlog header but got %x",
+			 header.fourcc);
+		return;
+	}
+
+	if (header.size > size) {
+		dev_warn(rtk->dev, "RTKit: Crashlog size (%x) is too large",
+			 header.size);
+		return;
+	}
+
+	size = header.size;
+	offset = sizeof(header);
+
+	while (offset < size) {
+		memcpy(&section_fourcc, bfr + offset, 4);
+		memcpy(&section_size, bfr + offset + 12, 4);
+
+		switch (section_fourcc) {
+		case APPLE_RTKIT_CRASHLOG_HEADER:
+			dev_dbg(rtk->dev, "RTKit: End of crashlog reached");
+			return;
+		case APPLE_RTKIT_CRASHLOG_STR:
+			apple_rtkit_crashlog_dump_str(rtk, bfr + offset + 16,
+						      section_size);
+			break;
+		case APPLE_RTKIT_CRASHLOG_VERSION:
+			apple_rtkit_crashlog_dump_version(
+				rtk, bfr + offset + 16, section_size);
+			break;
+		case APPLE_RTKIT_CRASHLOG_MBOX:
+			apple_rtkit_crashlog_dump_mailbox(
+				rtk, bfr + offset + 16, section_size);
+			break;
+		case APPLE_RTKIT_CRASHLOG_TIME:
+			apple_rtkit_crashlog_dump_time(rtk, bfr + offset + 16,
+						       section_size);
+			break;
+		default:
+			dev_warn(rtk->dev,
+				 "RTKit: Unknown crashlog section: %x",
+				 section_fourcc);
+		}
+
+		offset += section_size;
+	}
+
+	dev_warn(rtk->dev,
+		 "RTKit: End of crashlog reached but no footer present");
+}
diff --git a/drivers/soc/apple/rtkit-internal.h b/drivers/soc/apple/rtkit-internal.h
new file mode 100644
index 000000000000..24bd619ec5e4
--- /dev/null
+++ b/drivers/soc/apple/rtkit-internal.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+/*
+ * Apple RTKit IPC library
+ * Copyright (C) The Asahi Linux Contributors
+ */
+
+#ifndef _APPLE_RTKIT_INTERAL_H
+#define _APPLE_RTKIT_INTERAL_H
+
+#include <linux/apple-mailbox.h>
+#include <linux/bitfield.h>
+#include <linux/bitmap.h>
+#include <linux/completion.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_client.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/soc/apple/rtkit.h>
+#include <linux/workqueue.h>
+
+#define APPLE_RTKIT_APP_ENDPOINT_START 0x20
+#define APPLE_RTKIT_MAX_ENDPOINTS 0x100
+
+struct apple_rtkit {
+	void *cookie;
+	const struct apple_rtkit_ops *ops;
+	struct device *dev;
+
+	const char *mbox_name;
+	int mbox_idx;
+	struct mbox_client mbox_cl;
+	struct mbox_chan *mbox_chan;
+
+	struct completion epmap_completion;
+	struct completion iop_pwr_ack_completion;
+	struct completion ap_pwr_ack_completion;
+
+	int boot_result;
+	int version;
+
+	unsigned int iop_power_state;
+	unsigned int ap_power_state;
+	bool crashed;
+
+	DECLARE_BITMAP(endpoints, APPLE_RTKIT_MAX_ENDPOINTS);
+
+	struct apple_rtkit_shmem ioreport_buffer;
+	struct apple_rtkit_shmem crashlog_buffer;
+
+	struct apple_rtkit_shmem syslog_buffer;
+	char *syslog_msg_buffer;
+	size_t syslog_n_entries;
+	size_t syslog_msg_size;
+
+	struct workqueue_struct *wq;
+};
+
+void apple_rtkit_crashlog_dump(struct apple_rtkit *rtk, u8 *bfr, size_t size);
+
+#endif
diff --git a/drivers/soc/apple/rtkit.c b/drivers/soc/apple/rtkit.c
new file mode 100644
index 000000000000..cf1129e9f76b
--- /dev/null
+++ b/drivers/soc/apple/rtkit.c
@@ -0,0 +1,958 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Apple RTKit IPC library
+ * Copyright (C) The Asahi Linux Contributors
+ */
+
+#include "rtkit-internal.h"
+
+enum {
+	APPLE_RTKIT_PWR_STATE_OFF = 0x00, /* power off, cannot be restarted */
+	APPLE_RTKIT_PWR_STATE_SLEEP = 0x01, /* sleeping, can be restarted */
+	APPLE_RTKIT_PWR_STATE_QUIESCED = 0x10, /* running but no communication */
+	APPLE_RTKIT_PWR_STATE_ON = 0x20, /* normal operating state */
+};
+
+enum {
+	APPLE_RTKIT_EP_MGMT = 0,
+	APPLE_RTKIT_EP_CRASHLOG = 1,
+	APPLE_RTKIT_EP_SYSLOG = 2,
+	APPLE_RTKIT_EP_DEBUG = 3,
+	APPLE_RTKIT_EP_IOREPORT = 4,
+	APPLE_RTKIT_EP_OSLOG = 8,
+};
+
+#define APPLE_RTKIT_MGMT_TYPE GENMASK_ULL(59, 52)
+
+enum {
+	APPLE_RTKIT_MGMT_HELLO = 1,
+	APPLE_RTKIT_MGMT_HELLO_REPLY = 2,
+	APPLE_RTKIT_MGMT_STARTEP = 5,
+	APPLE_RTKIT_MGMT_SET_IOP_PWR_STATE = 6,
+	APPLE_RTKIT_MGMT_SET_IOP_PWR_STATE_ACK = 7,
+	APPLE_RTKIT_MGMT_EPMAP = 8,
+	APPLE_RTKIT_MGMT_EPMAP_REPLY = 8,
+	APPLE_RTKIT_MGMT_SET_AP_PWR_STATE = 0xb,
+	APPLE_RTKIT_MGMT_SET_AP_PWR_STATE_ACK = 0xb,
+};
+
+#define APPLE_RTKIT_MGMT_HELLO_MINVER GENMASK_ULL(15, 0)
+#define APPLE_RTKIT_MGMT_HELLO_MAXVER GENMASK_ULL(31, 16)
+
+#define APPLE_RTKIT_MGMT_EPMAP_LAST   BIT_ULL(51)
+#define APPLE_RTKIT_MGMT_EPMAP_BASE   GENMASK_ULL(34, 32)
+#define APPLE_RTKIT_MGMT_EPMAP_BITMAP GENMASK_ULL(31, 0)
+
+#define APPLE_RTKIT_MGMT_EPMAP_REPLY_MORE BIT_ULL(0)
+
+#define APPLE_RTKIT_MGMT_STARTEP_EP   GENMASK_ULL(39, 32)
+#define APPLE_RTKIT_MGMT_STARTEP_FLAG BIT_ULL(1)
+
+#define APPLE_RTKIT_MGMT_PWR_STATE GENMASK_ULL(15, 0)
+
+#define APPLE_RTKIT_CRASHLOG_CRASH 1
+
+#define APPLE_RTKIT_BUFFER_REQUEST	1
+#define APPLE_RTKIT_BUFFER_REQUEST_SIZE GENMASK_ULL(51, 44)
+#define APPLE_RTKIT_BUFFER_REQUEST_IOVA GENMASK_ULL(41, 0)
+
+#define APPLE_RTKIT_SYSLOG_TYPE GENMASK_ULL(59, 52)
+
+#define APPLE_RTKIT_SYSLOG_LOG 5
+
+#define APPLE_RTKIT_SYSLOG_INIT	     8
+#define APPLE_RTKIT_SYSLOG_N_ENTRIES GENMASK_ULL(7, 0)
+#define APPLE_RTKIT_SYSLOG_MSG_SIZE  GENMASK_ULL(31, 24)
+
+#define APPLE_RTKIT_OSLOG_TYPE GENMASK_ULL(63, 56)
+#define APPLE_RTKIT_OSLOG_INIT	1
+#define APPLE_RTKIT_OSLOG_ACK	3
+
+#define APPLE_RTKIT_MIN_SUPPORTED_VERSION 11
+#define APPLE_RTKIT_MAX_SUPPORTED_VERSION 12
+
+struct apple_rtkit_msg {
+	struct completion *completion;
+	struct apple_mbox_msg mbox_msg;
+};
+
+struct apple_rtkit_rx_work {
+	struct apple_rtkit *rtk;
+	u8 ep;
+	u64 msg;
+	struct work_struct work;
+};
+
+bool apple_rtkit_is_running(struct apple_rtkit *rtk)
+{
+	if (rtk->crashed)
+		return false;
+	if ((rtk->iop_power_state & 0xff) != APPLE_RTKIT_PWR_STATE_ON)
+		return false;
+	if ((rtk->ap_power_state & 0xff) != APPLE_RTKIT_PWR_STATE_ON)
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_is_running);
+
+bool apple_rtkit_is_crashed(struct apple_rtkit *rtk)
+{
+	return rtk->crashed;
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_is_crashed);
+
+static void apple_rtkit_management_send(struct apple_rtkit *rtk, u8 type,
+					u64 msg)
+{
+	msg &= ~APPLE_RTKIT_MGMT_TYPE;
+	msg |= FIELD_PREP(APPLE_RTKIT_MGMT_TYPE, type);
+	apple_rtkit_send_message(rtk, APPLE_RTKIT_EP_MGMT, msg, NULL, false);
+}
+
+static void apple_rtkit_management_rx_hello(struct apple_rtkit *rtk, u64 msg)
+{
+	u64 reply;
+
+	int min_ver = FIELD_GET(APPLE_RTKIT_MGMT_HELLO_MINVER, msg);
+	int max_ver = FIELD_GET(APPLE_RTKIT_MGMT_HELLO_MAXVER, msg);
+	int want_ver = min(APPLE_RTKIT_MAX_SUPPORTED_VERSION, max_ver);
+
+	dev_dbg(rtk->dev, "RTKit: Min ver %d, max ver %d\n", min_ver, max_ver);
+
+	if (min_ver > APPLE_RTKIT_MAX_SUPPORTED_VERSION) {
+		dev_err(rtk->dev, "RTKit: Firmware min version %d is too new\n",
+			min_ver);
+		goto abort_boot;
+	}
+
+	if (max_ver < APPLE_RTKIT_MIN_SUPPORTED_VERSION) {
+		dev_err(rtk->dev, "RTKit: Firmware max version %d is too old\n",
+			max_ver);
+		goto abort_boot;
+	}
+
+	dev_info(rtk->dev, "RTKit: Initializing (protocol version %d)\n",
+		 want_ver);
+	rtk->version = want_ver;
+
+	reply = FIELD_PREP(APPLE_RTKIT_MGMT_HELLO_MINVER, want_ver);
+	reply |= FIELD_PREP(APPLE_RTKIT_MGMT_HELLO_MAXVER, want_ver);
+	apple_rtkit_management_send(rtk, APPLE_RTKIT_MGMT_HELLO_REPLY, reply);
+
+	return;
+
+abort_boot:
+	rtk->boot_result = -EINVAL;
+	complete_all(&rtk->epmap_completion);
+}
+
+static void apple_rtkit_management_rx_epmap(struct apple_rtkit *rtk, u64 msg)
+{
+	int i, ep;
+	u64 reply;
+	unsigned long bitmap = FIELD_GET(APPLE_RTKIT_MGMT_EPMAP_BITMAP, msg);
+	u32 base = FIELD_GET(APPLE_RTKIT_MGMT_EPMAP_BASE, msg);
+
+	dev_dbg(rtk->dev,
+		"RTKit: received endpoint bitmap 0x%lx with base 0x%x\n",
+		bitmap, base);
+
+	for_each_set_bit(i, &bitmap, 32) {
+		ep = 32 * base + i;
+		dev_dbg(rtk->dev, "RTKit: Discovered endpoint 0x%02x\n", ep);
+		set_bit(ep, rtk->endpoints);
+	}
+
+	reply = FIELD_PREP(APPLE_RTKIT_MGMT_EPMAP_BASE, base);
+	if (msg & APPLE_RTKIT_MGMT_EPMAP_LAST)
+		reply |= APPLE_RTKIT_MGMT_EPMAP_LAST;
+	else
+		reply |= APPLE_RTKIT_MGMT_EPMAP_REPLY_MORE;
+
+	apple_rtkit_management_send(rtk, APPLE_RTKIT_MGMT_EPMAP_REPLY, reply);
+
+	if (!(msg & APPLE_RTKIT_MGMT_EPMAP_LAST))
+		return;
+
+	for_each_set_bit(ep, rtk->endpoints, APPLE_RTKIT_APP_ENDPOINT_START) {
+		switch (ep) {
+		/* the management endpoint is started by default */
+		case APPLE_RTKIT_EP_MGMT:
+			break;
+
+		/* without starting these RTKit refuses to boot */
+		case APPLE_RTKIT_EP_SYSLOG:
+		case APPLE_RTKIT_EP_CRASHLOG:
+		case APPLE_RTKIT_EP_DEBUG:
+		case APPLE_RTKIT_EP_IOREPORT:
+		case APPLE_RTKIT_EP_OSLOG:
+			dev_dbg(rtk->dev,
+				"RTKit: Starting system endpoint 0x%02x\n", ep);
+			apple_rtkit_start_ep(rtk, ep);
+			break;
+
+		default:
+			dev_warn(rtk->dev,
+				 "RTKit: Unknown system endpoint: 0x%02x\n",
+				 ep);
+		}
+	}
+
+	rtk->boot_result = 0;
+	complete_all(&rtk->epmap_completion);
+}
+
+static void apple_rtkit_management_rx_iop_pwr_ack(struct apple_rtkit *rtk,
+						  u64 msg)
+{
+	unsigned int new_state = FIELD_GET(APPLE_RTKIT_MGMT_PWR_STATE, msg);
+
+	dev_dbg(rtk->dev, "RTKit: IOP power state transition: 0x%x -> 0x%x\n",
+		rtk->iop_power_state, new_state);
+	rtk->iop_power_state = new_state;
+
+	complete_all(&rtk->iop_pwr_ack_completion);
+}
+
+static void apple_rtkit_management_rx_ap_pwr_ack(struct apple_rtkit *rtk,
+						 u64 msg)
+{
+	unsigned int new_state = FIELD_GET(APPLE_RTKIT_MGMT_PWR_STATE, msg);
+
+	dev_dbg(rtk->dev, "RTKit: AP power state transition: 0x%x -> 0x%x\n",
+		rtk->ap_power_state, new_state);
+	rtk->ap_power_state = new_state;
+
+	complete_all(&rtk->ap_pwr_ack_completion);
+}
+
+static void apple_rtkit_management_rx(struct apple_rtkit *rtk, u64 msg)
+{
+	u8 type = FIELD_GET(APPLE_RTKIT_MGMT_TYPE, msg);
+
+	switch (type) {
+	case APPLE_RTKIT_MGMT_HELLO:
+		apple_rtkit_management_rx_hello(rtk, msg);
+		break;
+	case APPLE_RTKIT_MGMT_EPMAP:
+		apple_rtkit_management_rx_epmap(rtk, msg);
+		break;
+	case APPLE_RTKIT_MGMT_SET_IOP_PWR_STATE_ACK:
+		apple_rtkit_management_rx_iop_pwr_ack(rtk, msg);
+		break;
+	case APPLE_RTKIT_MGMT_SET_AP_PWR_STATE_ACK:
+		apple_rtkit_management_rx_ap_pwr_ack(rtk, msg);
+		break;
+	default:
+		dev_warn(
+			rtk->dev,
+			"RTKit: unknown management message: 0x%llx (type: 0x%02x)\n",
+			msg, type);
+	}
+}
+
+static int apple_rtkit_common_rx_get_buffer(struct apple_rtkit *rtk,
+					    struct apple_rtkit_shmem *buffer,
+					    u8 ep, u64 msg)
+{
+	size_t n_4kpages = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_SIZE, msg);
+	u64 reply;
+	int err;
+
+	buffer->buffer = NULL;
+	buffer->iomem = NULL;
+	buffer->is_mapped = false;
+	buffer->iova = FIELD_GET(APPLE_RTKIT_BUFFER_REQUEST_IOVA, msg);
+	buffer->size = n_4kpages << 12;
+
+	dev_dbg(rtk->dev, "RTKit: buffer request for 0x%zx bytes at %pad\n",
+		buffer->size, &buffer->iova);
+
+	if (buffer->iova &&
+	    (!rtk->ops->shmem_setup || !rtk->ops->shmem_destroy)) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	if (rtk->ops->shmem_setup) {
+		err = rtk->ops->shmem_setup(rtk->cookie, buffer);
+		if (err)
+			goto error;
+	} else {
+		buffer->buffer = dma_alloc_coherent(rtk->dev, buffer->size,
+						    &buffer->iova, GFP_KERNEL);
+		if (!buffer->buffer) {
+			err = -ENOMEM;
+			goto error;
+		}
+	}
+
+	if (!buffer->is_mapped) {
+		reply = FIELD_PREP(APPLE_RTKIT_SYSLOG_TYPE,
+				   APPLE_RTKIT_BUFFER_REQUEST);
+		reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_SIZE, n_4kpages);
+		reply |= FIELD_PREP(APPLE_RTKIT_BUFFER_REQUEST_IOVA,
+				    buffer->iova);
+		apple_rtkit_send_message(rtk, ep, reply, NULL, false);
+	}
+
+	return 0;
+
+error:
+	buffer->buffer = NULL;
+	buffer->iomem = NULL;
+	buffer->iova = 0;
+	buffer->size = 0;
+	buffer->is_mapped = false;
+	return err;
+}
+
+static void apple_rtkit_free_buffer(struct apple_rtkit *rtk,
+				    struct apple_rtkit_shmem *bfr)
+{
+	if (bfr->size == 0)
+		return;
+
+	if (rtk->ops->shmem_destroy)
+		rtk->ops->shmem_destroy(rtk->cookie, bfr);
+	else if (bfr->buffer)
+		dma_free_coherent(rtk->dev, bfr->size, bfr->buffer, bfr->iova);
+
+	bfr->buffer = NULL;
+	bfr->iomem = NULL;
+	bfr->iova = 0;
+	bfr->size = 0;
+	bfr->is_mapped = false;
+}
+
+static void apple_rtkit_memcpy(struct apple_rtkit *rtk, void *dst,
+			       struct apple_rtkit_shmem *bfr, size_t offset,
+			       size_t len)
+{
+	if (bfr->iomem)
+		memcpy_fromio(dst, bfr->iomem + offset, len);
+	else
+		memcpy(dst, bfr->buffer + offset, len);
+}
+
+static void apple_rtkit_crashlog_rx(struct apple_rtkit *rtk, u64 msg)
+{
+	u8 type = FIELD_GET(APPLE_RTKIT_SYSLOG_TYPE, msg);
+	u8 *bfr;
+
+	if (type != APPLE_RTKIT_CRASHLOG_CRASH) {
+		dev_warn(rtk->dev, "RTKit: Unknown crashlog message: %llx\n",
+			 msg);
+		return;
+	}
+
+	if (!rtk->crashlog_buffer.size) {
+		apple_rtkit_common_rx_get_buffer(rtk, &rtk->crashlog_buffer,
+						 APPLE_RTKIT_EP_CRASHLOG, msg);
+		return;
+	}
+
+	dev_err(rtk->dev, "RTKit: co-processor has crashed\n");
+
+	/*
+	 * create a shadow copy here to make sure the co-processor isn't able
+	 * to change the log while we're dumping it. this also ensures
+	 * the buffer is in normal memory and not iomem for e.g. the SMC
+	 */
+	bfr = kzalloc(rtk->crashlog_buffer.size, GFP_KERNEL);
+	if (bfr) {
+		apple_rtkit_memcpy(rtk, bfr, &rtk->crashlog_buffer, 0,
+				   rtk->crashlog_buffer.size);
+		apple_rtkit_crashlog_dump(rtk, bfr, rtk->crashlog_buffer.size);
+		kfree(bfr);
+	} else {
+		dev_err(rtk->dev,
+			"RTKit: Couldn't allocate crashlog shadow buffer\n");
+	}
+
+	rtk->crashed = true;
+	if (rtk->ops->crashed)
+		rtk->ops->crashed(rtk->cookie);
+}
+
+static void apple_rtkit_ioreport_rx(struct apple_rtkit *rtk, u64 msg)
+{
+	u8 type = FIELD_GET(APPLE_RTKIT_SYSLOG_TYPE, msg);
+
+	switch (type) {
+	case APPLE_RTKIT_BUFFER_REQUEST:
+		apple_rtkit_common_rx_get_buffer(rtk, &rtk->ioreport_buffer,
+						 APPLE_RTKIT_EP_IOREPORT, msg);
+		break;
+	/* unknown, must be ACKed or the co-processor will hang */
+	case 0x8:
+	case 0xc:
+		apple_rtkit_send_message(rtk, APPLE_RTKIT_EP_IOREPORT, msg,
+					 NULL, false);
+		break;
+	default:
+		dev_warn(rtk->dev, "RTKit: Unknown ioreport message: %llx\n",
+			 msg);
+	}
+}
+
+static void apple_rtkit_syslog_rx_init(struct apple_rtkit *rtk, u64 msg)
+{
+	rtk->syslog_n_entries = FIELD_GET(APPLE_RTKIT_SYSLOG_N_ENTRIES, msg);
+	rtk->syslog_msg_size = FIELD_GET(APPLE_RTKIT_SYSLOG_MSG_SIZE, msg);
+
+	rtk->syslog_msg_buffer = kzalloc(rtk->syslog_msg_size, GFP_KERNEL);
+
+	dev_dbg(rtk->dev,
+		"RTKit: syslog initialized: entries: %zd, msg_size: %zd\n",
+		rtk->syslog_n_entries, rtk->syslog_msg_size);
+}
+
+static void apple_rtkit_syslog_rx_log(struct apple_rtkit *rtk, u64 msg)
+{
+	u8 idx = msg & 0xff;
+	char log_context[24];
+	size_t entry_size = 0x20 + rtk->syslog_msg_size;
+
+	if (!rtk->syslog_msg_buffer) {
+		dev_warn(
+			rtk->dev,
+			"RTKit: received syslog message but no syslog_msg_buffer\n");
+		goto done;
+	}
+	if (!rtk->syslog_buffer.size) {
+		dev_warn(
+			rtk->dev,
+			"RTKit: received syslog message but syslog_buffer.size is zero\n");
+		goto done;
+	}
+	if (!rtk->syslog_buffer.buffer && !rtk->syslog_buffer.iomem) {
+		dev_warn(
+			rtk->dev,
+			"RTKit: received syslog message but no syslog_buffer.buffer or syslog_buffer.iomem\n");
+		goto done;
+	}
+	if (idx > rtk->syslog_n_entries) {
+		dev_warn(rtk->dev, "RTKit: syslog index %d out of range\n",
+			 idx);
+		goto done;
+	}
+
+	apple_rtkit_memcpy(rtk, log_context, &rtk->syslog_buffer,
+			   idx * entry_size + 8, sizeof(log_context));
+	apple_rtkit_memcpy(rtk, rtk->syslog_msg_buffer, &rtk->syslog_buffer,
+			   idx * entry_size + 8 + sizeof(log_context),
+			   rtk->syslog_msg_size);
+
+	log_context[sizeof(log_context) - 1] = 0;
+	rtk->syslog_msg_buffer[rtk->syslog_msg_size - 1] = 0;
+	dev_info(rtk->dev, "RTKit: syslog message: %s: %s\n", log_context,
+		 rtk->syslog_msg_buffer);
+
+done:
+	apple_rtkit_send_message(rtk, APPLE_RTKIT_EP_SYSLOG, msg, NULL, false);
+}
+
+static void apple_rtkit_syslog_rx(struct apple_rtkit *rtk, u64 msg)
+{
+	u8 type = FIELD_GET(APPLE_RTKIT_SYSLOG_TYPE, msg);
+
+	switch (type) {
+	case APPLE_RTKIT_BUFFER_REQUEST:
+		apple_rtkit_common_rx_get_buffer(rtk, &rtk->syslog_buffer,
+						 APPLE_RTKIT_EP_SYSLOG, msg);
+		break;
+	case APPLE_RTKIT_SYSLOG_INIT:
+		apple_rtkit_syslog_rx_init(rtk, msg);
+		break;
+	case APPLE_RTKIT_SYSLOG_LOG:
+		apple_rtkit_syslog_rx_log(rtk, msg);
+		break;
+	default:
+		dev_warn(rtk->dev, "RTKit: Unknown syslog message: %llx\n",
+			 msg);
+	}
+}
+
+static void apple_rtkit_oslog_rx_init(struct apple_rtkit *rtk, u64 msg)
+{
+	u64 ack;
+
+	dev_dbg(rtk->dev, "RTKit: oslog init: msg: 0x%llx\n", msg);
+	ack = FIELD_PREP(APPLE_RTKIT_OSLOG_TYPE, APPLE_RTKIT_OSLOG_ACK);
+	apple_rtkit_send_message(rtk, APPLE_RTKIT_EP_OSLOG, ack, NULL, false);
+}
+
+static void apple_rtkit_oslog_rx(struct apple_rtkit *rtk, u64 msg)
+{
+	u8 type = FIELD_GET(APPLE_RTKIT_OSLOG_TYPE, msg);
+
+	switch (type) {
+	case APPLE_RTKIT_OSLOG_INIT:
+		apple_rtkit_oslog_rx_init(rtk, msg);
+		break;
+	default:
+		dev_warn(rtk->dev, "RTKit: Unknown oslog message: %llx\n", msg);
+	}
+}
+
+static void apple_rtkit_rx_work(struct work_struct *work)
+{
+	struct apple_rtkit_rx_work *rtk_work =
+		container_of(work, struct apple_rtkit_rx_work, work);
+	struct apple_rtkit *rtk = rtk_work->rtk;
+
+	switch (rtk_work->ep) {
+	case APPLE_RTKIT_EP_MGMT:
+		apple_rtkit_management_rx(rtk, rtk_work->msg);
+		break;
+	case APPLE_RTKIT_EP_CRASHLOG:
+		apple_rtkit_crashlog_rx(rtk, rtk_work->msg);
+		break;
+	case APPLE_RTKIT_EP_SYSLOG:
+		apple_rtkit_syslog_rx(rtk, rtk_work->msg);
+		break;
+	case APPLE_RTKIT_EP_IOREPORT:
+		apple_rtkit_ioreport_rx(rtk, rtk_work->msg);
+		break;
+	case APPLE_RTKIT_EP_OSLOG:
+		apple_rtkit_oslog_rx(rtk, rtk_work->msg);
+		break;
+	case APPLE_RTKIT_APP_ENDPOINT_START ... 0xff:
+		if (rtk->ops->recv_message)
+			rtk->ops->recv_message(rtk->cookie, rtk_work->ep,
+					       rtk_work->msg);
+		else
+			dev_warn(
+				rtk->dev,
+				"Received unexpected message to EP%02d: %llx\n",
+				rtk_work->ep, rtk_work->msg);
+		break;
+	default:
+		dev_warn(rtk->dev,
+			 "RTKit: message to unknown endpoint %02x: %llx\n",
+			 rtk_work->ep, rtk_work->msg);
+	}
+
+	kfree(rtk_work);
+}
+
+static void apple_rtkit_rx(struct mbox_client *cl, void *mssg)
+{
+	struct apple_rtkit *rtk = container_of(cl, struct apple_rtkit, mbox_cl);
+	struct apple_mbox_msg *msg = mssg;
+	struct apple_rtkit_rx_work *work;
+	u8 ep = msg->msg1;
+
+	/*
+	 * The message was read from a MMIO FIFO and we have to make
+	 * sure all reads from buffers sent with that message happen
+	 * afterwards.
+	 */
+	dma_rmb();
+
+	if (!test_bit(ep, rtk->endpoints))
+		dev_warn(rtk->dev,
+			 "RTKit: Message to undiscovered endpoint 0x%02x\n",
+			 ep);
+
+	if (ep >= APPLE_RTKIT_APP_ENDPOINT_START &&
+	    rtk->ops->recv_message_early &&
+	    rtk->ops->recv_message_early(rtk->cookie, ep, msg->msg0))
+		return;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return;
+
+	work->rtk = rtk;
+	work->ep = ep;
+	work->msg = msg->msg0;
+	INIT_WORK(&work->work, apple_rtkit_rx_work);
+	queue_work(rtk->wq, &work->work);
+}
+
+static void apple_rtkit_tx_done(struct mbox_client *cl, void *mssg, int r)
+{
+	struct apple_rtkit_msg *msg =
+		container_of(mssg, struct apple_rtkit_msg, mbox_msg);
+
+	if (r == -ETIME)
+		return;
+
+	if (msg->completion)
+		complete(msg->completion);
+	kfree(msg);
+}
+
+int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message,
+			     struct completion *completion, bool atomic)
+{
+	struct apple_rtkit_msg *msg;
+	int ret;
+	gfp_t flags;
+
+	if (rtk->crashed)
+		return -EINVAL;
+	if (ep >= APPLE_RTKIT_APP_ENDPOINT_START &&
+	    !apple_rtkit_is_running(rtk))
+		return -EINVAL;
+
+	if (atomic)
+		flags = GFP_ATOMIC;
+	else
+		flags = GFP_KERNEL;
+
+	msg = kzalloc(sizeof(*msg), flags);
+	if (!msg)
+		return -ENOMEM;
+
+	msg->mbox_msg.msg0 = message;
+	msg->mbox_msg.msg1 = ep;
+	msg->completion = completion;
+
+	/*
+	 * The message will be sent with a MMIO write. We need the barrier
+	 * here to ensure any previous writes to buffers are visible to the
+	 * device before that MMIO write happens.
+	 */
+	dma_wmb();
+
+	ret = mbox_send_message(rtk->mbox_chan, &msg->mbox_msg);
+	if (ret < 0) {
+		kfree(msg);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_send_message);
+
+int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message,
+				  unsigned long timeout, bool atomic)
+{
+	DECLARE_COMPLETION_ONSTACK(completion);
+	int ret;
+	long t;
+
+	ret = apple_rtkit_send_message(rtk, ep, message, &completion, atomic);
+	if (ret < 0)
+		return ret;
+
+	if (atomic) {
+		ret = mbox_flush(rtk->mbox_chan, timeout);
+		if (ret < 0)
+			return ret;
+
+		if (try_wait_for_completion(&completion))
+			return 0;
+
+		return -ETIME;
+	} else {
+		t = wait_for_completion_interruptible_timeout(
+			&completion, msecs_to_jiffies(timeout));
+		if (t < 0)
+			return t;
+		else if (t == 0)
+			return -ETIME;
+		return 0;
+	}
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_send_message_wait);
+
+int apple_rtkit_start_ep(struct apple_rtkit *rtk, u8 endpoint)
+{
+	u64 msg;
+
+	if (!test_bit(endpoint, rtk->endpoints))
+		return -EINVAL;
+	if (endpoint >= APPLE_RTKIT_APP_ENDPOINT_START &&
+	    !apple_rtkit_is_running(rtk))
+		return -EINVAL;
+
+	msg = FIELD_PREP(APPLE_RTKIT_MGMT_STARTEP_EP, endpoint);
+	msg |= APPLE_RTKIT_MGMT_STARTEP_FLAG;
+	apple_rtkit_management_send(rtk, APPLE_RTKIT_MGMT_STARTEP, msg);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_start_ep);
+
+static int apple_rtkit_request_mbox_chan(struct apple_rtkit *rtk)
+{
+	if (rtk->mbox_name)
+		rtk->mbox_chan = mbox_request_channel_byname(&rtk->mbox_cl,
+							     rtk->mbox_name);
+	else
+		rtk->mbox_chan =
+			mbox_request_channel(&rtk->mbox_cl, rtk->mbox_idx);
+
+	if (IS_ERR(rtk->mbox_chan))
+		return PTR_ERR(rtk->mbox_chan);
+	return 0;
+}
+
+static struct apple_rtkit *apple_rtkit_init(struct device *dev, void *cookie,
+					    const char *mbox_name, int mbox_idx,
+					    const struct apple_rtkit_ops *ops)
+{
+	struct apple_rtkit *rtk;
+	int ret;
+
+	if (!ops)
+		return ERR_PTR(-EINVAL);
+
+	rtk = kzalloc(sizeof(*rtk), GFP_KERNEL);
+	if (!rtk)
+		return ERR_PTR(-ENOMEM);
+
+	rtk->dev = dev;
+	rtk->cookie = cookie;
+	rtk->ops = ops;
+
+	init_completion(&rtk->epmap_completion);
+	init_completion(&rtk->iop_pwr_ack_completion);
+	init_completion(&rtk->ap_pwr_ack_completion);
+
+	bitmap_zero(rtk->endpoints, APPLE_RTKIT_MAX_ENDPOINTS);
+	set_bit(APPLE_RTKIT_EP_MGMT, rtk->endpoints);
+
+	rtk->mbox_name = mbox_name;
+	rtk->mbox_idx = mbox_idx;
+	rtk->mbox_cl.dev = dev;
+	rtk->mbox_cl.tx_block = false;
+	rtk->mbox_cl.knows_txdone = false;
+	rtk->mbox_cl.rx_callback = &apple_rtkit_rx;
+	rtk->mbox_cl.tx_done = &apple_rtkit_tx_done;
+
+	rtk->wq = alloc_ordered_workqueue("rtkit-%s", WQ_MEM_RECLAIM,
+					  dev_name(rtk->dev));
+	if (!rtk->wq) {
+		ret = -ENOMEM;
+		goto free_rtk;
+	}
+
+	ret = apple_rtkit_request_mbox_chan(rtk);
+	if (ret)
+		goto destroy_wq;
+
+	return rtk;
+
+destroy_wq:
+	destroy_workqueue(rtk->wq);
+free_rtk:
+	kfree(rtk);
+	return ERR_PTR(ret);
+}
+
+static int apple_rtkit_wait_for_completion(struct completion *c)
+{
+	long t;
+
+	t = wait_for_completion_interruptible_timeout(c,
+						      msecs_to_jiffies(1000));
+	if (t < 0)
+		return t;
+	else if (t == 0)
+		return -ETIME;
+	else
+		return 0;
+}
+
+int apple_rtkit_reinit(struct apple_rtkit *rtk)
+{
+	/* make sure we don't handle any messages while reinitializing */
+	mbox_free_channel(rtk->mbox_chan);
+	flush_workqueue(rtk->wq);
+
+	apple_rtkit_free_buffer(rtk, &rtk->ioreport_buffer);
+	apple_rtkit_free_buffer(rtk, &rtk->crashlog_buffer);
+	apple_rtkit_free_buffer(rtk, &rtk->syslog_buffer);
+
+	kfree(rtk->syslog_msg_buffer);
+
+	rtk->syslog_msg_buffer = NULL;
+	rtk->syslog_n_entries = 0;
+	rtk->syslog_msg_size = 0;
+
+	bitmap_zero(rtk->endpoints, APPLE_RTKIT_MAX_ENDPOINTS);
+	set_bit(APPLE_RTKIT_EP_MGMT, rtk->endpoints);
+
+	reinit_completion(&rtk->epmap_completion);
+	reinit_completion(&rtk->iop_pwr_ack_completion);
+	reinit_completion(&rtk->ap_pwr_ack_completion);
+
+	rtk->crashed = false;
+	rtk->iop_power_state = APPLE_RTKIT_PWR_STATE_OFF;
+	rtk->ap_power_state = APPLE_RTKIT_PWR_STATE_OFF;
+
+	return apple_rtkit_request_mbox_chan(rtk);
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_reinit);
+
+static int apple_rtkit_set_ap_power_state(struct apple_rtkit *rtk,
+					  unsigned int state)
+{
+	u64 msg;
+	int ret;
+
+	reinit_completion(&rtk->ap_pwr_ack_completion);
+
+	msg = FIELD_PREP(APPLE_RTKIT_MGMT_PWR_STATE, state);
+	apple_rtkit_management_send(rtk, APPLE_RTKIT_MGMT_SET_AP_PWR_STATE,
+				    msg);
+
+	ret = apple_rtkit_wait_for_completion(&rtk->ap_pwr_ack_completion);
+	if (ret)
+		return ret;
+
+	if (rtk->ap_power_state != state)
+		return -EINVAL;
+	return 0;
+}
+
+static int apple_rtkit_set_iop_power_state(struct apple_rtkit *rtk,
+					   unsigned int state)
+{
+	u64 msg;
+	int ret;
+
+	reinit_completion(&rtk->iop_pwr_ack_completion);
+
+	msg = FIELD_PREP(APPLE_RTKIT_MGMT_PWR_STATE, state);
+	apple_rtkit_management_send(rtk, APPLE_RTKIT_MGMT_SET_IOP_PWR_STATE,
+				    msg);
+
+	ret = apple_rtkit_wait_for_completion(&rtk->iop_pwr_ack_completion);
+	if (ret)
+		return ret;
+
+	if (rtk->iop_power_state != state)
+		return -EINVAL;
+	return 0;
+}
+
+int apple_rtkit_boot(struct apple_rtkit *rtk)
+{
+	int ret;
+
+	if (apple_rtkit_is_running(rtk))
+		return 0;
+	if (rtk->crashed)
+		return -EINVAL;
+
+	dev_dbg(rtk->dev, "RTKit: waiting for boot to finish\n");
+	ret = apple_rtkit_wait_for_completion(&rtk->epmap_completion);
+	if (ret)
+		return ret;
+	if (rtk->boot_result)
+		return rtk->boot_result;
+
+	dev_dbg(rtk->dev, "RTKit: waiting for IOP power state ACK\n");
+	ret = apple_rtkit_wait_for_completion(&rtk->iop_pwr_ack_completion);
+	if (ret)
+		return ret;
+
+	return apple_rtkit_set_ap_power_state(rtk, APPLE_RTKIT_PWR_STATE_ON);
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_boot);
+
+int apple_rtkit_shutdown(struct apple_rtkit *rtk)
+{
+	int ret;
+
+	/* if OFF is used here the co-processor will not wake up again */
+	ret = apple_rtkit_set_ap_power_state(rtk,
+					     APPLE_RTKIT_PWR_STATE_QUIESCED);
+	if (ret)
+		return ret;
+
+	ret = apple_rtkit_set_iop_power_state(rtk, APPLE_RTKIT_PWR_STATE_SLEEP);
+	if (ret)
+		return ret;
+
+	return apple_rtkit_reinit(rtk);
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_shutdown);
+
+int apple_rtkit_quiesce(struct apple_rtkit *rtk)
+{
+	int ret;
+
+	ret = apple_rtkit_set_ap_power_state(rtk,
+					     APPLE_RTKIT_PWR_STATE_QUIESCED);
+	if (ret)
+		return ret;
+
+	ret = apple_rtkit_set_iop_power_state(rtk,
+					      APPLE_RTKIT_PWR_STATE_QUIESCED);
+	if (ret)
+		return ret;
+
+	ret = apple_rtkit_reinit(rtk);
+	if (ret)
+		return ret;
+
+	rtk->iop_power_state = APPLE_RTKIT_PWR_STATE_QUIESCED;
+	rtk->ap_power_state = APPLE_RTKIT_PWR_STATE_QUIESCED;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_quiesce);
+
+int apple_rtkit_wake(struct apple_rtkit *rtk)
+{
+	u64 msg;
+
+	if (apple_rtkit_is_running(rtk))
+		return -EINVAL;
+
+	reinit_completion(&rtk->iop_pwr_ack_completion);
+
+	/*
+	 * Use open-coded apple_rtkit_set_iop_power_state since apple_rtkit_boot
+	 * will wait for the completion anyway.
+	 */
+	msg = FIELD_PREP(APPLE_RTKIT_MGMT_PWR_STATE, APPLE_RTKIT_PWR_STATE_ON);
+	apple_rtkit_management_send(rtk, APPLE_RTKIT_MGMT_SET_IOP_PWR_STATE,
+				    msg);
+
+	return apple_rtkit_boot(rtk);
+}
+EXPORT_SYMBOL_GPL(apple_rtkit_wake);
+
+static void apple_rtkit_free(struct apple_rtkit *rtk)
+{
+	mbox_free_channel(rtk->mbox_chan);
+	destroy_workqueue(rtk->wq);
+
+	apple_rtkit_free_buffer(rtk, &rtk->ioreport_buffer);
+	apple_rtkit_free_buffer(rtk, &rtk->crashlog_buffer);
+	apple_rtkit_free_buffer(rtk, &rtk->syslog_buffer);
+
+	kfree(rtk->syslog_msg_buffer);
+	kfree(rtk);
+}
+
+struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie,
+					  const char *mbox_name, int mbox_idx,
+					  const struct apple_rtkit_ops *ops)
+{
+	struct apple_rtkit *rtk;
+	int ret;
+
+	rtk = apple_rtkit_init(dev, cookie, mbox_name, mbox_idx, ops);
+	if (IS_ERR(rtk))
+		return rtk;
+
+	ret = devm_add_action_or_reset(dev, (void (*)(void *))apple_rtkit_free,
+				       rtk);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return rtk;
+}
+EXPORT_SYMBOL_GPL(devm_apple_rtkit_init);
+
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
+MODULE_DESCRIPTION("Apple RTKit driver");
diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h
new file mode 100644
index 000000000000..88eb832eac7b
--- /dev/null
+++ b/include/linux/soc/apple/rtkit.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+/*
+ * Apple RTKit IPC Library
+ * Copyright (C) The Asahi Linux Contributors
+ *
+ * Apple's SoCs come with various co-processors running their RTKit operating
+ * system. This protocol library is used by client drivers to use the
+ * features provided by them.
+ */
+#ifndef _LINUX_APPLE_RTKIT_H_
+#define _LINUX_APPLE_RTKIT_H_
+
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/mailbox_client.h>
+
+/*
+ * Struct to represent implementation-specific RTKit operations.
+ *
+ * @buffer:    Shared memory buffer allocated inside normal RAM.
+ * @iomem:     Shared memory buffer controlled by the co-processors.
+ * @size:      Size of the shared memory buffer.
+ * @iova:      Device VA of shared memory buffer.
+ * @is_mapped: Shared memory buffer is managed by the co-processor.
+ */
+
+struct apple_rtkit_shmem {
+	void *buffer;
+	void __iomem *iomem;
+	size_t size;
+	dma_addr_t iova;
+	bool is_mapped;
+};
+
+/*
+ * Struct to represent implementation-specific RTKit operations.
+ *
+ * @crashed:       Called when the co-processor has crashed. Runs in process
+ *                 context.
+ * @recv_message:  Function called when a message from RTKit is received
+ *                 on a non-system endpoint. Called from a worker thread.
+ * @recv_message_early:
+ *                 Like recv_message, but called from atomic context. It
+ *                 should return true if it handled the message. If it
+ *                 returns false, the message will be passed on to the
+ *                 worker thread.
+ * @shmem_setup:   Setup shared memory buffer. If bfr.is_iomem is true the
+ *                 buffer is managed by the co-processor and needs to be mapped.
+ *                 Otherwise the buffer is managed by Linux and needs to be
+ *                 allocated. If not specified dma_alloc_coherent is used.
+ *                 Called in process context.
+ * @shmem_destroy: Undo the shared memory buffer setup in shmem_setup. If not
+ *                 specified dma_free_coherent is used. Called in process
+ *                 context.
+ */
+struct apple_rtkit_ops {
+	void (*crashed)(void *cookie);
+	void (*recv_message)(void *cookie, u8 endpoint, u64 message);
+	bool (*recv_message_early)(void *cookie, u8 endpoint, u64 message);
+	int (*shmem_setup)(void *cookie, struct apple_rtkit_shmem *bfr);
+	void (*shmem_destroy)(void *cookie, struct apple_rtkit_shmem *bfr);
+};
+
+struct apple_rtkit;
+
+/*
+ * Initializes the internal state required to handle RTKit. This
+ * should usually be called within _probe.
+ *
+ * @dev:         Pointer to the device node this coprocessor is assocated with
+ * @cookie:      opaque cookie passed to all functions defined in rtkit_ops
+ * @mbox_name:   mailbox name used to communicate with the co-processor
+ * @mbox_idx:    mailbox index to be used if mbox_name is NULL
+ * @ops:         pointer to rtkit_ops to be used for this co-processor
+ */
+struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie,
+					  const char *mbox_name, int mbox_idx,
+					  const struct apple_rtkit_ops *ops);
+
+/*
+ * Reinitialize internal structures. Must only be called with the co-processor
+ * is held in reset.
+ */
+int apple_rtkit_reinit(struct apple_rtkit *rtk);
+
+/*
+ * Handle RTKit's boot process. Should be called after the CPU of the
+ * co-processor has been started.
+ */
+int apple_rtkit_boot(struct apple_rtkit *rtk);
+
+/*
+ * Quiesce the co-processor.
+ */
+int apple_rtkit_quiesce(struct apple_rtkit *rtk);
+
+/*
+ * Wake the co-processor up from hibernation mode.
+ */
+int apple_rtkit_wake(struct apple_rtkit *rtk);
+
+/*
+ * Shutdown the co-processor
+ */
+int apple_rtkit_shutdown(struct apple_rtkit *rtk);
+
+/*
+ * Checks if RTKit is running and ready to handle messages.
+ */
+bool apple_rtkit_is_running(struct apple_rtkit *rtk);
+
+/*
+ * Checks if RTKit has crashed.
+ */
+bool apple_rtkit_is_crashed(struct apple_rtkit *rtk);
+
+/*
+ * Starts an endpoint. Must be called after boot but before any messages can be
+ * sent or received from that endpoint.
+ */
+int apple_rtkit_start_ep(struct apple_rtkit *rtk, u8 endpoint);
+
+/*
+ * Send a message to the given endpoint.
+ *
+ * @rtk:            RTKit reference
+ * @ep:             target endpoint
+ * @message:        message to be sent
+ * @completeion:    will be completed once the message has been submitted
+ *                  to the hardware FIFO. Can be NULL.
+ * @atomic:         if set to true this function can be called from atomic
+ *                  context.
+ */
+int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message,
+			     struct completion *completion, bool atomic);
+
+/*
+ * Send a message to the given endpoint and wait until it has been submitted
+ * to the hardware FIFO.
+ * Will return zero on success and a negative error code on failure
+ * (e.g. -ETIME when the message couldn't be written within the given
+ * timeout)
+ *
+ * @rtk:            RTKit reference
+ * @ep:             target endpoint
+ * @message:        message to be sent
+ * @timeout:        timeout in milliseconds to allow the message transmission
+ *                  to be completed
+ * @atomic:         if set to true this function can be called from atomic
+ *                  context.
+ */
+int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message,
+				  unsigned long timeout, bool atomic);
+
+#endif /* _LINUX_APPLE_RTKIT_H_ */
-- 
cgit v1.2.3


From 3254e0b9eb5649ffaa48717ebc9c593adc4ee6a9 Mon Sep 17 00:00:00 2001
From: Alexandru Tachici <alexandru.tachici@analog.com>
Date: Fri, 29 Apr 2022 18:34:31 +0300
Subject: ethtool: Add 10base-T1L link mode entry

Add entry for the 10base-T1L full duplex mode.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Alexandru Tachici <alexandru.tachici@analog.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-core.c   | 3 ++-
 drivers/net/phy/phy_device.c | 3 ++-
 drivers/net/phy/phylink.c    | 4 +++-
 include/linux/phy.h          | 2 +-
 include/uapi/linux/ethtool.h | 1 +
 net/ethtool/common.c         | 3 +++
 6 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 2001f3329133..1f2531a1a876 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -13,7 +13,7 @@
  */
 const char *phy_speed_to_str(int speed)
 {
-	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 92,
+	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 93,
 		"Enum ethtool_link_mode_bit_indices and phylib are out of sync. "
 		"If a speed or mode has been added please update phy_speed_to_str "
 		"and the PHY settings array.\n");
@@ -176,6 +176,7 @@ static const struct phy_setting settings[] = {
 	/* 10M */
 	PHY_SETTING(     10, FULL,     10baseT_Full		),
 	PHY_SETTING(     10, HALF,     10baseT_Half		),
+	PHY_SETTING(     10, FULL,     10baseT1L_Full		),
 };
 #undef PHY_SETTING
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index f867042b2eb4..1369daeded14 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -90,8 +90,9 @@ const int phy_10_100_features_array[4] = {
 };
 EXPORT_SYMBOL_GPL(phy_10_100_features_array);
 
-const int phy_basic_t1_features_array[2] = {
+const int phy_basic_t1_features_array[3] = {
 	ETHTOOL_LINK_MODE_TP_BIT,
+	ETHTOOL_LINK_MODE_10baseT1L_Full_BIT,
 	ETHTOOL_LINK_MODE_100baseT1_Full_BIT,
 };
 EXPORT_SYMBOL_GPL(phy_basic_t1_features_array);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 33c285252584..d707604d1d5a 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -168,8 +168,10 @@ static void phylink_caps_to_linkmodes(unsigned long *linkmodes,
 	if (caps & MAC_10HD)
 		__set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, linkmodes);
 
-	if (caps & MAC_10FD)
+	if (caps & MAC_10FD) {
 		__set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, linkmodes);
+		__set_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, linkmodes);
+	}
 
 	if (caps & MAC_100HD) {
 		__set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, linkmodes);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 36ca2b5c2253..b12af9e2f389 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -65,7 +65,7 @@ extern const int phy_basic_ports_array[3];
 extern const int phy_fibre_port_array[1];
 extern const int phy_all_ports_features_array[7];
 extern const int phy_10_100_features_array[4];
-extern const int phy_basic_t1_features_array[2];
+extern const int phy_basic_t1_features_array[3];
 extern const int phy_gbit_features_array[2];
 extern const int phy_10gbit_features_array[1];
 
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 7bc4b8def12c..e0f0ee9bc89e 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1691,6 +1691,7 @@ enum ethtool_link_mode_bit_indices {
 	ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT	 = 89,
 	ETHTOOL_LINK_MODE_100baseFX_Half_BIT		 = 90,
 	ETHTOOL_LINK_MODE_100baseFX_Full_BIT		 = 91,
+	ETHTOOL_LINK_MODE_10baseT1L_Full_BIT		 = 92,
 	/* must be last entry */
 	__ETHTOOL_LINK_MODE_MASK_NBITS
 };
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 0c5210015911..566adf85e658 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -201,6 +201,7 @@ const char link_mode_names[][ETH_GSTRING_LEN] = {
 	__DEFINE_LINK_MODE_NAME(400000, CR4, Full),
 	__DEFINE_LINK_MODE_NAME(100, FX, Half),
 	__DEFINE_LINK_MODE_NAME(100, FX, Full),
+	__DEFINE_LINK_MODE_NAME(10, T1L, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 
@@ -236,6 +237,7 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 #define __LINK_MODE_LANES_T1		1
 #define __LINK_MODE_LANES_X		1
 #define __LINK_MODE_LANES_FX		1
+#define __LINK_MODE_LANES_T1L		1
 
 #define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex)	\
 	[ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = {		\
@@ -349,6 +351,7 @@ const struct link_mode_info link_mode_params[] = {
 	__DEFINE_LINK_MODE_PARAMS(400000, CR4, Full),
 	__DEFINE_LINK_MODE_PARAMS(100, FX, Half),
 	__DEFINE_LINK_MODE_PARAMS(100, FX, Full),
+	__DEFINE_LINK_MODE_PARAMS(10, T1L, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 
-- 
cgit v1.2.3


From 3da8ffd8545f62fec85a48a3c637b2f427974f11 Mon Sep 17 00:00:00 2001
From: Alexandru Tachici <alexandru.tachici@analog.com>
Date: Fri, 29 Apr 2022 18:34:34 +0300
Subject: net: phy: Add 10BASE-T1L support in phy-c45

This patch is needed because the BASE-T1 uses different registers
for status, control and advertisement to those already
employed in the existing phy-c45 functions.

Where required, genphy_c45 functions will now check whether
the device supports BASE-T1 and use the specific registers
instead: 45.2.7.19 BASE-T1 AN control register,
45.2.7.20 BASE-T1 AN status, 45.2.7.21 BASE-T1 AN
advertisement register, 45.2.7.22 BASE-T1 AN LP Base
Page ability register, 45.2.1.185 BASE-T1 PMA/PMD control
register.

Tested-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Alexandru Tachici <alexandru.tachici@analog.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-c45.c    | 257 ++++++++++++++++++++++++++++++++++++++++++-
 drivers/net/phy/phy_device.c |   1 +
 include/linux/mdio.h         |  70 ++++++++++++
 include/linux/phy.h          |   3 +
 include/uapi/linux/mdio.h    |  10 ++
 5 files changed, 336 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index db709d30bf84..eefdd67d5556 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -8,6 +8,25 @@
 #include <linux/mii.h>
 #include <linux/phy.h>
 
+/**
+ * genphy_c45_baset1_able - checks if the PMA has BASE-T1 extended abilities
+ * @phydev: target phy_device struct
+ */
+static bool genphy_c45_baset1_able(struct phy_device *phydev)
+{
+	int val;
+
+	if (phydev->pma_extable == -ENODATA) {
+		val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE);
+		if (val < 0)
+			return false;
+
+		phydev->pma_extable = val;
+	}
+
+	return !!(phydev->pma_extable & MDIO_PMA_EXTABLE_BT1);
+}
+
 /**
  * genphy_c45_pma_can_sleep - checks if the PMA have sleep support
  * @phydev: target phy_device struct
@@ -80,7 +99,10 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev)
 
 	switch (phydev->speed) {
 	case SPEED_10:
-		ctrl2 |= MDIO_PMA_CTRL2_10BT;
+		if (genphy_c45_baset1_able(phydev))
+			ctrl2 |= MDIO_PMA_CTRL2_BASET1;
+		else
+			ctrl2 |= MDIO_PMA_CTRL2_10BT;
 		break;
 	case SPEED_100:
 		ctrl1 |= MDIO_PMA_CTRL1_SPEED100;
@@ -118,10 +140,95 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
+	if (genphy_c45_baset1_able(phydev)) {
+		int ctl = 0;
+
+		switch (phydev->master_slave_set) {
+		case MASTER_SLAVE_CFG_MASTER_PREFERRED:
+		case MASTER_SLAVE_CFG_MASTER_FORCE:
+			ctl = MDIO_PMA_PMD_BT1_CTRL_CFG_MST;
+			break;
+		case MASTER_SLAVE_CFG_SLAVE_FORCE:
+		case MASTER_SLAVE_CFG_SLAVE_PREFERRED:
+		case MASTER_SLAVE_CFG_UNKNOWN:
+		case MASTER_SLAVE_CFG_UNSUPPORTED:
+			break;
+		default:
+			phydev_warn(phydev, "Unsupported Master/Slave mode\n");
+			return -EOPNOTSUPP;
+		}
+
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1_CTRL,
+				     MDIO_PMA_PMD_BT1_CTRL_CFG_MST, ctl);
+		if (ret < 0)
+			return ret;
+	}
+
 	return genphy_c45_an_disable_aneg(phydev);
 }
 EXPORT_SYMBOL_GPL(genphy_c45_pma_setup_forced);
 
+/* Sets master/slave preference and supported technologies.
+ * The preference is set in the BIT(4) of BASE-T1 AN
+ * advertisement register 7.515 and whether the status
+ * is forced or not, it is set in the BIT(12) of BASE-T1
+ * AN advertisement register 7.514.
+ * Sets 10BASE-T1L Ability BIT(14) in BASE-T1 autonegotiation
+ * advertisement register [31:16] if supported.
+ */
+static int genphy_c45_baset1_an_config_aneg(struct phy_device *phydev)
+{
+	int changed = 0;
+	u16 adv_l = 0;
+	u16 adv_m = 0;
+	int ret;
+
+	switch (phydev->master_slave_set) {
+	case MASTER_SLAVE_CFG_MASTER_FORCE:
+	case MASTER_SLAVE_CFG_SLAVE_FORCE:
+		adv_l |= MDIO_AN_T1_ADV_L_FORCE_MS;
+		break;
+	case MASTER_SLAVE_CFG_MASTER_PREFERRED:
+	case MASTER_SLAVE_CFG_SLAVE_PREFERRED:
+		break;
+	default:
+		break;
+	}
+
+	switch (phydev->master_slave_set) {
+	case MASTER_SLAVE_CFG_MASTER_FORCE:
+	case MASTER_SLAVE_CFG_MASTER_PREFERRED:
+		adv_m |= MDIO_AN_T1_ADV_M_MST;
+		break;
+	case MASTER_SLAVE_CFG_SLAVE_FORCE:
+	case MASTER_SLAVE_CFG_SLAVE_PREFERRED:
+		break;
+	default:
+		break;
+	}
+
+	adv_l |= linkmode_adv_to_mii_t1_adv_l_t(phydev->advertising);
+
+	ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_T1_ADV_L,
+				     (MDIO_AN_T1_ADV_L_FORCE_MS | MDIO_AN_T1_ADV_L_PAUSE_CAP
+				     | MDIO_AN_T1_ADV_L_PAUSE_ASYM), adv_l);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = 1;
+
+	adv_m |= linkmode_adv_to_mii_t1_adv_m_t(phydev->advertising);
+
+	ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_T1_ADV_M,
+				     MDIO_AN_T1_ADV_M_MST | MDIO_AN_T1_ADV_M_B10L, adv_m);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = 1;
+
+	return changed;
+}
+
 /**
  * genphy_c45_an_config_aneg - configure advertisement registers
  * @phydev: target phy_device struct
@@ -141,6 +248,9 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev)
 
 	changed = genphy_config_eee_advert(phydev);
 
+	if (genphy_c45_baset1_able(phydev))
+		return genphy_c45_baset1_an_config_aneg(phydev);
+
 	adv = linkmode_adv_to_mii_adv_t(phydev->advertising);
 
 	ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE,
@@ -178,8 +288,12 @@ EXPORT_SYMBOL_GPL(genphy_c45_an_config_aneg);
  */
 int genphy_c45_an_disable_aneg(struct phy_device *phydev)
 {
+	u16 reg = MDIO_CTRL1;
 
-	return phy_clear_bits_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1,
+	if (genphy_c45_baset1_able(phydev))
+		reg = MDIO_AN_T1_CTRL;
+
+	return phy_clear_bits_mmd(phydev, MDIO_MMD_AN, reg,
 				  MDIO_AN_CTRL1_ENABLE | MDIO_AN_CTRL1_RESTART);
 }
 EXPORT_SYMBOL_GPL(genphy_c45_an_disable_aneg);
@@ -194,7 +308,12 @@ EXPORT_SYMBOL_GPL(genphy_c45_an_disable_aneg);
  */
 int genphy_c45_restart_aneg(struct phy_device *phydev)
 {
-	return phy_set_bits_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1,
+	u16 reg = MDIO_CTRL1;
+
+	if (genphy_c45_baset1_able(phydev))
+		reg = MDIO_AN_T1_CTRL;
+
+	return phy_set_bits_mmd(phydev, MDIO_MMD_AN, reg,
 				MDIO_AN_CTRL1_ENABLE | MDIO_AN_CTRL1_RESTART);
 }
 EXPORT_SYMBOL_GPL(genphy_c45_restart_aneg);
@@ -210,11 +329,15 @@ EXPORT_SYMBOL_GPL(genphy_c45_restart_aneg);
  */
 int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart)
 {
+	u16 reg = MDIO_CTRL1;
 	int ret;
 
+	if (genphy_c45_baset1_able(phydev))
+		reg = MDIO_AN_T1_CTRL;
+
 	if (!restart) {
 		/* Configure and restart aneg if it wasn't set before */
-		ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1);
+		ret = phy_read_mmd(phydev, MDIO_MMD_AN, reg);
 		if (ret < 0)
 			return ret;
 
@@ -242,7 +365,13 @@ EXPORT_SYMBOL_GPL(genphy_c45_check_and_restart_aneg);
  */
 int genphy_c45_aneg_done(struct phy_device *phydev)
 {
-	int val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
+	int reg = MDIO_STAT1;
+	int val;
+
+	if (genphy_c45_baset1_able(phydev))
+		reg = MDIO_AN_T1_STAT;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, reg);
 
 	return val < 0 ? val : val & MDIO_AN_STAT1_COMPLETE ? 1 : 0;
 }
@@ -307,6 +436,49 @@ int genphy_c45_read_link(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(genphy_c45_read_link);
 
+/* Read the Clause 45 defined BASE-T1 AN (7.513) status register to check
+ * if autoneg is complete. If so read the BASE-T1 Autonegotiation
+ * Advertisement registers filling in the link partner advertisement,
+ * pause and asym_pause members in phydev.
+ */
+static int genphy_c45_baset1_read_lpa(struct phy_device *phydev)
+{
+	int val;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_STAT);
+	if (val < 0)
+		return val;
+
+	if (!(val & MDIO_AN_STAT1_COMPLETE)) {
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->lp_advertising);
+		mii_t1_adv_l_mod_linkmode_t(phydev->lp_advertising, 0);
+		mii_t1_adv_m_mod_linkmode_t(phydev->lp_advertising, 0);
+
+		phydev->pause = 0;
+		phydev->asym_pause = 0;
+
+		return 0;
+	}
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->lp_advertising, 1);
+
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_LP_L);
+	if (val < 0)
+		return val;
+
+	mii_t1_adv_l_mod_linkmode_t(phydev->lp_advertising, val);
+	phydev->pause = val & MDIO_AN_T1_ADV_L_PAUSE_CAP ? 1 : 0;
+	phydev->asym_pause = val & MDIO_AN_T1_ADV_L_PAUSE_ASYM ? 1 : 0;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_LP_M);
+	if (val < 0)
+		return val;
+
+	mii_t1_adv_m_mod_linkmode_t(phydev->lp_advertising, val);
+
+	return 0;
+}
+
 /**
  * genphy_c45_read_lpa - read the link partner advertisement and pause
  * @phydev: target phy_device struct
@@ -321,6 +493,9 @@ int genphy_c45_read_lpa(struct phy_device *phydev)
 {
 	int val;
 
+	if (genphy_c45_baset1_able(phydev))
+		return genphy_c45_baset1_read_lpa(phydev);
+
 	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
 	if (val < 0)
 		return val;
@@ -399,6 +574,17 @@ int genphy_c45_read_pma(struct phy_device *phydev)
 
 	phydev->duplex = DUPLEX_FULL;
 
+	if (genphy_c45_baset1_able(phydev)) {
+		val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1_CTRL);
+		if (val < 0)
+			return val;
+
+		if (MDIO_PMA_PMD_BT1_CTRL_CFG_MST)
+			phydev->master_slave_state = MASTER_SLAVE_STATE_MASTER;
+		else
+			phydev->master_slave_state = MASTER_SLAVE_STATE_SLAVE;
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(genphy_c45_read_pma);
@@ -530,12 +716,67 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev)
 					 phydev->supported,
 					 val & MDIO_PMA_NG_EXTABLE_5GBT);
 		}
+
+		if (val & MDIO_PMA_EXTABLE_BT1) {
+			val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1);
+			if (val < 0)
+				return val;
+
+			linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT,
+					 phydev->supported,
+					 val & MDIO_PMA_PMD_BT1_B10L_ABLE);
+
+			val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_STAT);
+			if (val < 0)
+				return val;
+
+			linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+					 phydev->supported,
+					 val & MDIO_AN_STAT1_ABLE);
+		}
 	}
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(genphy_c45_pma_read_abilities);
 
+/* Read master/slave preference from registers.
+ * The preference is read from the BIT(4) of BASE-T1 AN
+ * advertisement register 7.515 and whether the preference
+ * is forced or not, it is read from BASE-T1 AN advertisement
+ * register 7.514.
+ */
+static int genphy_c45_baset1_read_status(struct phy_device *phydev)
+{
+	int ret;
+	int cfg;
+
+	phydev->master_slave_get = MASTER_SLAVE_CFG_UNKNOWN;
+	phydev->master_slave_state = MASTER_SLAVE_STATE_UNKNOWN;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_ADV_L);
+	if (ret < 0)
+		return ret;
+
+	cfg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_ADV_M);
+	if (cfg < 0)
+		return cfg;
+
+	if (ret & MDIO_AN_T1_ADV_L_FORCE_MS) {
+		if (cfg & MDIO_AN_T1_ADV_M_MST)
+			phydev->master_slave_get = MASTER_SLAVE_CFG_MASTER_FORCE;
+		else
+			phydev->master_slave_get = MASTER_SLAVE_CFG_SLAVE_FORCE;
+	} else {
+		if (cfg & MDIO_AN_T1_ADV_M_MST)
+			phydev->master_slave_get = MASTER_SLAVE_CFG_MASTER_PREFERRED;
+		else
+			phydev->master_slave_get = MASTER_SLAVE_CFG_SLAVE_PREFERRED;
+	}
+
+	return 0;
+}
+
 /**
  * genphy_c45_read_status - read PHY status
  * @phydev: target phy_device struct
@@ -560,6 +801,12 @@ int genphy_c45_read_status(struct phy_device *phydev)
 		if (ret)
 			return ret;
 
+		if (genphy_c45_baset1_able(phydev)) {
+			ret = genphy_c45_baset1_read_status(phydev);
+			if (ret < 0)
+				return ret;
+		}
+
 		phy_resolve_aneg_linkmode(phydev);
 	} else {
 		ret = genphy_c45_read_pma(phydev);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 1369daeded14..431a8719c635 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -600,6 +600,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 
 	dev->autoneg = AUTONEG_ENABLE;
 
+	dev->pma_extable = -ENODATA;
 	dev->is_c45 = is_c45;
 	dev->phy_id = phy_id;
 	if (c45_ids)
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index ecac96d52e01..00177567cfef 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -340,6 +340,76 @@ static inline void mii_10gbt_stat_mod_linkmode_lpa_t(unsigned long *advertising,
 			 advertising, lpa & MDIO_AN_10GBT_STAT_LP10G);
 }
 
+/**
+ * mii_t1_adv_l_mod_linkmode_t
+ * @advertising: target the linkmode advertisement settings
+ * @lpa: value of the BASE-T1 Autonegotiation Advertisement [15:0] Register
+ *
+ * A small helper function that translates BASE-T1 Autonegotiation
+ * Advertisement [15:0] Register bits to linkmode advertisement settings.
+ * Other bits in advertising aren't changed.
+ */
+static inline void mii_t1_adv_l_mod_linkmode_t(unsigned long *advertising, u32 lpa)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising,
+			 lpa & MDIO_AN_T1_ADV_L_PAUSE_CAP);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising,
+			 lpa & MDIO_AN_T1_ADV_L_PAUSE_ASYM);
+}
+
+/**
+ * mii_t1_adv_m_mod_linkmode_t
+ * @advertising: target the linkmode advertisement settings
+ * @lpa: value of the BASE-T1 Autonegotiation Advertisement [31:16] Register
+ *
+ * A small helper function that translates BASE-T1 Autonegotiation
+ * Advertisement [31:16] Register bits to linkmode advertisement settings.
+ * Other bits in advertising aren't changed.
+ */
+static inline void mii_t1_adv_m_mod_linkmode_t(unsigned long *advertising, u32 lpa)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT,
+			 advertising, lpa & MDIO_AN_T1_ADV_M_B10L);
+}
+
+/**
+ * linkmode_adv_to_mii_t1_adv_l_t
+ * @advertising: the linkmode advertisement settings
+ *
+ * A small helper function that translates linkmode advertisement
+ * settings to phy autonegotiation advertisements for the
+ * BASE-T1 Autonegotiation Advertisement [15:0] Register.
+ */
+static inline u32 linkmode_adv_to_mii_t1_adv_l_t(unsigned long *advertising)
+{
+	u32 result = 0;
+
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising))
+		result |= MDIO_AN_T1_ADV_L_PAUSE_CAP;
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising))
+		result |= MDIO_AN_T1_ADV_L_PAUSE_ASYM;
+
+	return result;
+}
+
+/**
+ * linkmode_adv_to_mii_t1_adv_m_t
+ * @advertising: the linkmode advertisement settings
+ *
+ * A small helper function that translates linkmode advertisement
+ * settings to phy autonegotiation advertisements for the
+ * BASE-T1 Autonegotiation Advertisement [31:16] Register.
+ */
+static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising)
+{
+	u32 result = 0;
+
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, advertising))
+		result |= MDIO_AN_T1_ADV_M_B10L;
+
+	return result;
+}
+
 int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum);
 int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val);
 int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index b12af9e2f389..2d12054932ba 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -570,6 +570,7 @@ struct macsec_ops;
  * @autoneg_complete: Flag auto negotiation of the link has completed
  * @mdix: Current crossover
  * @mdix_ctrl: User setting of crossover
+ * @pma_extable: Cached value of PMA/PMD Extended Abilities Register
  * @interrupts: Flag interrupts have been enabled
  * @interface: enum phy_interface_t value
  * @skb: Netlink message for cable diagnostics
@@ -698,6 +699,8 @@ struct phy_device {
 	u8 mdix;
 	u8 mdix_ctrl;
 
+	int pma_extable;
+
 	void (*phy_link_change)(struct phy_device *phydev, bool up);
 	void (*adjust_link)(struct net_device *dev);
 
diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h
index fa3515257f54..75b7257a51e1 100644
--- a/include/uapi/linux/mdio.h
+++ b/include/uapi/linux/mdio.h
@@ -70,6 +70,7 @@
 #define MDIO_B10L_PMA_CTRL	2294	/* 10BASE-T1L PMA control */
 #define MDIO_PMA_10T1L_STAT	2295	/* 10BASE-T1L PMA status */
 #define MDIO_PCS_10T1L_CTRL	2278	/* 10BASE-T1L PCS control */
+#define MDIO_PMA_PMD_BT1	18	/* BASE-T1 PMA/PMD extended ability */
 #define MDIO_AN_T1_CTRL		512	/* BASE-T1 AN control */
 #define MDIO_AN_T1_STAT		513	/* BASE-T1 AN status */
 #define MDIO_AN_T1_ADV_L	514	/* BASE-T1 AN advertisement register [15:0] */
@@ -78,6 +79,7 @@
 #define MDIO_AN_T1_LP_L		517	/* BASE-T1 AN LP Base Page ability register [15:0] */
 #define MDIO_AN_T1_LP_M		518	/* BASE-T1 AN LP Base Page ability register [31:16] */
 #define MDIO_AN_T1_LP_H		519	/* BASE-T1 AN LP Base Page ability register [47:32] */
+#define MDIO_PMA_PMD_BT1_CTRL	2100	/* BASE-T1 PMA/PMD control register */
 
 /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */
 #define MDIO_PMA_LASI_RXCTRL	0x9000	/* RX_ALARM control */
@@ -170,6 +172,7 @@
 #define MDIO_PMA_CTRL2_10BT		0x000f	/* 10BASE-T type */
 #define MDIO_PMA_CTRL2_2_5GBT		0x0030  /* 2.5GBaseT type */
 #define MDIO_PMA_CTRL2_5GBT		0x0031  /* 5GBaseT type */
+#define MDIO_PMA_CTRL2_BASET1		0x003D  /* BASE-T1 type */
 #define MDIO_PCS_CTRL2_TYPE		0x0003	/* PCS type selection */
 #define MDIO_PCS_CTRL2_10GBR		0x0000	/* 10GBASE-R type */
 #define MDIO_PCS_CTRL2_10GBX		0x0001	/* 10GBASE-X type */
@@ -223,6 +226,7 @@
 #define MDIO_PMA_EXTABLE_1000BKX	0x0040	/* 1000BASE-KX ability */
 #define MDIO_PMA_EXTABLE_100BTX		0x0080	/* 100BASE-TX ability */
 #define MDIO_PMA_EXTABLE_10BT		0x0100	/* 10BASE-T ability */
+#define MDIO_PMA_EXTABLE_BT1		0x0800	/* BASE-T1 ability */
 #define MDIO_PMA_EXTABLE_NBT		0x4000  /* 2.5/5GBASE-T ability */
 
 /* PHY XGXS lane state register. */
@@ -301,6 +305,9 @@
 #define MDIO_PCS_10T1L_CTRL_LB		0x4000	/* Enable PCS level loopback mode */
 #define MDIO_PCS_10T1L_CTRL_RESET	0x8000	/* PCS reset */
 
+/* BASE-T1 PMA/PMD extended ability register. */
+#define MDIO_PMA_PMD_BT1_B10L_ABLE	0x0004	/* 10BASE-T1L Ability */
+
 /* BASE-T1 auto-negotiation advertisement register [15:0] */
 #define MDIO_AN_T1_ADV_L_PAUSE_CAP	ADVERTISE_PAUSE_CAP
 #define MDIO_AN_T1_ADV_L_PAUSE_ASYM	ADVERTISE_PAUSE_ASYM
@@ -333,6 +340,9 @@
 #define MDIO_AN_T1_LP_H_10L_TX_HI_REQ	0x1000	/* 10BASE-T1L High Level LP Transmit Request */
 #define MDIO_AN_T1_LP_H_10L_TX_HI	0x2000	/* 10BASE-T1L High Level LP Transmit Ability */
 
+/* BASE-T1 PMA/PMD control register */
+#define MDIO_PMA_PMD_BT1_CTRL_CFG_MST	0x4000 /* MASTER-SLAVE config value */
+
 /* EEE Supported/Advertisement/LP Advertisement registers.
  *
  * EEE capability Register (3.20), Advertisement (7.60) and
-- 
cgit v1.2.3


From 246d921646c071b878480997c294db6c83215b06 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.ibm.com>
Date: Tue, 23 Nov 2021 13:37:52 -0500
Subject: fs-verity: define a function to return the integrity protected file
 digest

Define a function named fsverity_get_digest() to return the verity file
digest and the associated hash algorithm (enum hash_algo).

This assumes that before calling fsverity_get_digest() the file must have
been opened, which is even true for the IMA measure/appraise on file
open policy rule use case (func=FILE_CHECK).  do_open() calls vfs_open()
immediately prior to ima_file_check().

Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 fs/verity/Kconfig            |  1 +
 fs/verity/fsverity_private.h |  7 -------
 fs/verity/measure.c          | 43 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/fsverity.h     | 18 ++++++++++++++++++
 4 files changed, 62 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig
index 24d1b54de807..54598cd80145 100644
--- a/fs/verity/Kconfig
+++ b/fs/verity/Kconfig
@@ -3,6 +3,7 @@
 config FS_VERITY
 	bool "FS Verity (read-only file-based authenticity protection)"
 	select CRYPTO
+	select CRYPTO_HASH_INFO
 	# SHA-256 is implied as it's intended to be the default hash algorithm.
 	# To avoid bloat, other wanted algorithms must be selected explicitly.
 	# Note that CRYPTO_SHA256 denotes the generic C implementation, but
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index a7920434bae5..c6fb62e0ef1a 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -14,7 +14,6 @@
 
 #define pr_fmt(fmt) "fs-verity: " fmt
 
-#include <crypto/sha2.h>
 #include <linux/fsverity.h>
 #include <linux/mempool.h>
 
@@ -26,12 +25,6 @@ struct ahash_request;
  */
 #define FS_VERITY_MAX_LEVELS		8
 
-/*
- * Largest digest size among all hash algorithms supported by fs-verity.
- * Currently assumed to be <= size of fsverity_descriptor::root_hash.
- */
-#define FS_VERITY_MAX_DIGEST_SIZE	SHA512_DIGEST_SIZE
-
 /* A hash algorithm supported by fs-verity */
 struct fsverity_hash_alg {
 	struct crypto_ahash *tfm; /* hash tfm, allocated on demand */
diff --git a/fs/verity/measure.c b/fs/verity/measure.c
index f0d7b30c62db..e99c00350c28 100644
--- a/fs/verity/measure.c
+++ b/fs/verity/measure.c
@@ -57,3 +57,46 @@ int fsverity_ioctl_measure(struct file *filp, void __user *_uarg)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fsverity_ioctl_measure);
+
+/**
+ * fsverity_get_digest() - get a verity file's digest
+ * @inode: inode to get digest of
+ * @digest: (out) pointer to the digest
+ * @alg: (out) pointer to the hash algorithm enumeration
+ *
+ * Return the file hash algorithm and digest of an fsverity protected file.
+ * Assumption: before calling fsverity_get_digest(), the file must have been
+ * opened.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fsverity_get_digest(struct inode *inode,
+			u8 digest[FS_VERITY_MAX_DIGEST_SIZE],
+			enum hash_algo *alg)
+{
+	const struct fsverity_info *vi;
+	const struct fsverity_hash_alg *hash_alg;
+	int i;
+
+	vi = fsverity_get_info(inode);
+	if (!vi)
+		return -ENODATA; /* not a verity file */
+
+	hash_alg = vi->tree_params.hash_alg;
+	memset(digest, 0, FS_VERITY_MAX_DIGEST_SIZE);
+
+	/* convert the verity hash algorithm name to a hash_algo_name enum */
+	i = match_string(hash_algo_name, HASH_ALGO__LAST, hash_alg->name);
+	if (i < 0)
+		return -EINVAL;
+	*alg = i;
+
+	if (WARN_ON_ONCE(hash_alg->digest_size != hash_digest_size[*alg]))
+		return -EINVAL;
+	memcpy(digest, vi->file_digest, hash_alg->digest_size);
+
+	pr_debug("file digest %s:%*phN\n", hash_algo_name[*alg],
+		 hash_digest_size[*alg], digest);
+
+	return 0;
+}
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index a7afc800bd8d..7af030fa3c36 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -12,8 +12,16 @@
 #define _LINUX_FSVERITY_H
 
 #include <linux/fs.h>
+#include <crypto/hash_info.h>
+#include <crypto/sha2.h>
 #include <uapi/linux/fsverity.h>
 
+/*
+ * Largest digest size among all hash algorithms supported by fs-verity.
+ * Currently assumed to be <= size of fsverity_descriptor::root_hash.
+ */
+#define FS_VERITY_MAX_DIGEST_SIZE	SHA512_DIGEST_SIZE
+
 /* Verity operations for filesystems */
 struct fsverity_operations {
 
@@ -131,6 +139,9 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *arg);
 /* measure.c */
 
 int fsverity_ioctl_measure(struct file *filp, void __user *arg);
+int fsverity_get_digest(struct inode *inode,
+			u8 digest[FS_VERITY_MAX_DIGEST_SIZE],
+			enum hash_algo *alg);
 
 /* open.c */
 
@@ -170,6 +181,13 @@ static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg)
 	return -EOPNOTSUPP;
 }
 
+static inline int fsverity_get_digest(struct inode *inode,
+				      u8 digest[FS_VERITY_MAX_DIGEST_SIZE],
+				      enum hash_algo *alg)
+{
+	return -EOPNOTSUPP;
+}
+
 /* open.c */
 
 static inline int fsverity_file_open(struct inode *inode, struct file *filp)
-- 
cgit v1.2.3


From 8cf9e1210adf49cd83d11e2b1984540cf0e0be71 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Thu, 28 Apr 2022 17:59:39 +0200
Subject: mm: slab: fix comment for ARCH_KMALLOC_MINALIGN

The comment next to the ARCH_KMALLOC_MINALIGN definition says that
ARCH_KMALLOC_MINALIGN can be defined in arch headers. This is incorrect:
it's actually ARCH_DMA_MINALIGN that can be defined there.

Fix the comment.

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/fe1ca7a25a054b61d1038686d07569416e287e7b.1651161548.git.andreyknvl@google.com
---
 include/linux/slab.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 11ceddcae9f4..8c090599fc21 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -197,7 +197,7 @@ void kmem_dump_obj(void *object);
 /*
  * Some archs want to perform DMA into kmalloc caches and need a guaranteed
  * alignment larger than the alignment of a 64-bit integer.
- * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that.
+ * Setting ARCH_DMA_MINALIGN in arch headers allows that.
  */
 #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8
 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN
-- 
cgit v1.2.3


From 154036a3b3f39cb17fc65511011f4c4024846e91 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Thu, 28 Apr 2022 17:59:40 +0200
Subject: mm: slab: fix comment for __assume_kmalloc_alignment

The comment next to the __assume_kmalloc_alignment definition is not
precise: kmalloc relies on kmem_cache_alloc, so kmalloc technically returns
pointers aligned to both ARCH_KMALLOC_MINALIGN and ARCH_SLAB_MINALIGN,
not only to ARCH_KMALLOC_MINALIGN.

(See create_kmalloc_cache()->create_boot_cache()->calculate_alignment()
 for SLAB and SLUB and __do_kmalloc_node() for SLOB.)

Clarify the comment.

The assumption specified by __assume_kmalloc_alignment is still correct,
although it can be made stronger. I'll leave this to a separate patch.

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/84d8142747230f2015eaf9705ee7c2e1a9f56596.1651161548.git.andreyknvl@google.com
---
 include/linux/slab.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 8c090599fc21..58bb9392775d 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -217,9 +217,9 @@ void kmem_dump_obj(void *object);
 #endif
 
 /*
- * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned
- * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN
- * aligned pointers.
+ * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN.
+ * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN
+ * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment.
  */
 #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN)
 #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN)
-- 
cgit v1.2.3


From 23587f7c5daa936524ede26201253a089666b5d9 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Fri, 29 Apr 2022 17:05:45 +0800
Subject: mm/slub: remove unused kmem_cache_order_objects max

max field holds the largest slab order that was ever used for a slab cache.
But it's unused now. Remove it.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/20220429090545.33413-1-linmiaohe@huawei.com
---
 include/linux/slub_def.h | 1 -
 mm/slub.c                | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 33c5c0e3bd8d..f9c68a9dac04 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -105,7 +105,6 @@ struct kmem_cache {
 	struct kmem_cache_order_objects oo;
 
 	/* Allocation and freeing of slabs */
-	struct kmem_cache_order_objects max;
 	struct kmem_cache_order_objects min;
 	gfp_t allocflags;	/* gfp flags to use on each alloc */
 	int refcount;		/* Refcount for slab cache destroy */
diff --git a/mm/slub.c b/mm/slub.c
index 74d92aa4a3a2..547b5168c938 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4165,8 +4165,6 @@ static int calculate_sizes(struct kmem_cache *s)
 	 */
 	s->oo = oo_make(order, size);
 	s->min = oo_make(get_order(size), size);
-	if (oo_objects(s->oo) > oo_objects(s->max))
-		s->max = s->oo;
 
 	return !!oo_objects(s->oo);
 }
-- 
cgit v1.2.3


From 94f697c5384bd7f9632acca483ba1ef9dd99ea97 Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Fri, 29 Apr 2022 12:01:53 +0200
Subject: mtd: spi-nor: move spi_nor_write_ear() to winbond module

The "Extended Address Register" is winbond specific. If the flash is
larger than 16MiB and is used in 3 byte address mode, it is used to set
the remaining address bits. Move the write_ear() function, the opcode
macros and the spimem op template into the winbond module and rename
them accordingly.

Signed-off-by: Michael Walle <michael@walle.cc>
Signed-off-by: Pratyush Yadav <p.yadav@ti.com>
Reviewed-by: Pratyush Yadav <p.yadav@ti.com>
Link: https://lore.kernel.org/r/20220429100153.2338501-1-michael@walle.cc
---
 drivers/mtd/spi-nor/core.c    | 30 ------------------------------
 drivers/mtd/spi-nor/core.h    |  7 -------
 drivers/mtd/spi-nor/winbond.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/mtd/spi-nor.h   |  2 --
 4 files changed, 41 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 6bf3921541b5..94f9847858bd 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -570,36 +570,6 @@ static int spansion_set_4byte_addr_mode(struct spi_nor *nor, bool enable)
 	return ret;
 }
 
-/**
- * spi_nor_write_ear() - Write Extended Address Register.
- * @nor:	pointer to 'struct spi_nor'.
- * @ear:	value to write to the Extended Address Register.
- *
- * Return: 0 on success, -errno otherwise.
- */
-int spi_nor_write_ear(struct spi_nor *nor, u8 ear)
-{
-	int ret;
-
-	nor->bouncebuf[0] = ear;
-
-	if (nor->spimem) {
-		struct spi_mem_op op = SPI_NOR_WREAR_OP(nor->bouncebuf);
-
-		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
-
-		ret = spi_mem_exec_op(nor->spimem, &op);
-	} else {
-		ret = spi_nor_controller_ops_write_reg(nor, SPINOR_OP_WREAR,
-						       nor->bouncebuf, 1);
-	}
-
-	if (ret)
-		dev_dbg(nor->dev, "error %d writing EAR\n", ret);
-
-	return ret;
-}
-
 /**
  * spi_nor_sr_ready() - Query the Status Register to see if the flash is ready
  * for new commands.
diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h
index 80d4831a4f34..296bfa57f7c1 100644
--- a/drivers/mtd/spi-nor/core.h
+++ b/drivers/mtd/spi-nor/core.h
@@ -72,12 +72,6 @@
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_DATA_OUT(1, buf, 0))
 
-#define SPI_NOR_WREAR_OP(buf)						\
-	SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREAR, 0),			\
-		   SPI_MEM_OP_NO_ADDR,					\
-		   SPI_MEM_OP_NO_DUMMY,					\
-		   SPI_MEM_OP_DATA_OUT(1, buf, 0))
-
 #define SPI_NOR_GBULK_OP						\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_GBULK, 0),			\
 		   SPI_MEM_OP_NO_ADDR,					\
@@ -636,7 +630,6 @@ void spi_nor_spimem_setup_op(const struct spi_nor *nor,
 int spi_nor_write_enable(struct spi_nor *nor);
 int spi_nor_write_disable(struct spi_nor *nor);
 int spi_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable);
-int spi_nor_write_ear(struct spi_nor *nor, u8 ear);
 int spi_nor_wait_till_ready(struct spi_nor *nor);
 int spi_nor_global_block_unlock(struct spi_nor *nor);
 int spi_nor_lock_and_prep(struct spi_nor *nor);
diff --git a/drivers/mtd/spi-nor/winbond.c b/drivers/mtd/spi-nor/winbond.c
index fe80dffc2e70..5a60468d897d 100644
--- a/drivers/mtd/spi-nor/winbond.c
+++ b/drivers/mtd/spi-nor/winbond.c
@@ -8,6 +8,15 @@
 
 #include "core.h"
 
+#define WINBOND_NOR_OP_RDEAR	0xc8	/* Read Extended Address Register */
+#define WINBOND_NOR_OP_WREAR	0xc5	/* Write Extended Address Register */
+
+#define WINBOND_NOR_WREAR_OP(buf)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(WINBOND_NOR_OP_WREAR, 0),		\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(1, buf, 0))
+
 static int
 w25q256_post_bfpt_fixups(struct spi_nor *nor,
 			 const struct sfdp_parameter_header *bfpt_header,
@@ -129,6 +138,37 @@ static const struct flash_info winbond_nor_parts[] = {
 			      SPI_NOR_QUAD_READ) },
 };
 
+/**
+ * winbond_nor_write_ear() - Write Extended Address Register.
+ * @nor:	pointer to 'struct spi_nor'.
+ * @ear:	value to write to the Extended Address Register.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int winbond_nor_write_ear(struct spi_nor *nor, u8 ear)
+{
+	int ret;
+
+	nor->bouncebuf[0] = ear;
+
+	if (nor->spimem) {
+		struct spi_mem_op op = WINBOND_NOR_WREAR_OP(nor->bouncebuf);
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
+		ret = spi_mem_exec_op(nor->spimem, &op);
+	} else {
+		ret = spi_nor_controller_ops_write_reg(nor,
+						       WINBOND_NOR_OP_WREAR,
+						       nor->bouncebuf, 1);
+	}
+
+	if (ret)
+		dev_dbg(nor->dev, "error %d writing EAR\n", ret);
+
+	return ret;
+}
+
 /**
  * winbond_nor_set_4byte_addr_mode() - Set 4-byte address mode for Winbond
  * flashes.
@@ -155,7 +195,7 @@ static int winbond_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable)
 	if (ret)
 		return ret;
 
-	ret = spi_nor_write_ear(nor, 0);
+	ret = winbond_nor_write_ear(nor, 0);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 5e25a7b75ae2..e505c4a5c530 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -47,8 +47,6 @@
 #define SPINOR_OP_RDID		0x9f	/* Read JEDEC ID */
 #define SPINOR_OP_RDSFDP	0x5a	/* Read SFDP */
 #define SPINOR_OP_RDCR		0x35	/* Read configuration register */
-#define SPINOR_OP_RDEAR		0xc8	/* Read Extended Address Register */
-#define SPINOR_OP_WREAR		0xc5	/* Write Extended Address Register */
 #define SPINOR_OP_SRSTEN	0x66	/* Software Reset Enable */
 #define SPINOR_OP_SRST		0x99	/* Software Reset */
 #define SPINOR_OP_GBULK		0x98    /* Global Block Unlock */
-- 
cgit v1.2.3


From b170143ae1113882731666aec9b9105356f1fc17 Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@svenpeter.dev>
Date: Sun, 1 May 2022 16:55:08 +0200
Subject: soc: apple: Add SART driver

The NVMe co-processor on the Apple M1 uses a DMA address filter called
SART for some DMA transactions. This adds a simple driver used to
configure the memory regions from which DMA transactions are allowed.

Unlike a real IOMMU, SART does not support any pagetables and can't be
implemented inside the IOMMU subsystem using iommu_ops.

It also can't be implemented using dma_map_ops since not all DMA
transactions of the NVMe controller are filtered by SART.
Instead, most buffers have to be registered using the integrated NVMe
IOMMU and we can't have two separate dma_map_ops implementations for a
single device.

Co-developed-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Sven Peter <sven@svenpeter.dev>
---
 MAINTAINERS                    |   1 +
 drivers/soc/apple/Kconfig      |  11 ++
 drivers/soc/apple/Makefile     |   3 +
 drivers/soc/apple/sart.c       | 328 +++++++++++++++++++++++++++++++++++++++++
 include/linux/soc/apple/sart.h |  53 +++++++
 5 files changed, 396 insertions(+)
 create mode 100644 drivers/soc/apple/sart.c
 create mode 100644 include/linux/soc/apple/sart.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 4961da640e82..8dad61c380c3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1854,6 +1854,7 @@ F:	drivers/watchdog/apple_wdt.c
 F:	include/dt-bindings/interrupt-controller/apple-aic.h
 F:	include/dt-bindings/pinctrl/apple.h
 F:	include/linux/apple-mailbox.h
+F:	include/linux/soc/apple/*
 
 ARM/ARTPEC MACHINE SUPPORT
 M:	Jesper Nilsson <jesper.nilsson@axis.com>
diff --git a/drivers/soc/apple/Kconfig b/drivers/soc/apple/Kconfig
index 1b09037584a0..a1596fefacff 100644
--- a/drivers/soc/apple/Kconfig
+++ b/drivers/soc/apple/Kconfig
@@ -30,6 +30,17 @@ config APPLE_RTKIT
 
 	  Say 'y' here if you have an Apple SoC.
 
+config APPLE_SART
+	tristate "Apple SART DMA address filter"
+	depends on ARCH_APPLE || COMPILE_TEST
+	default ARCH_APPLE
+	help
+	  Apple SART is a simple DMA address filter used on Apple SoCs such
+	  as the M1. It is usually required for the NVMe coprocessor which does
+	  not use a proper IOMMU.
+
+	  Say 'y' here if you have an Apple SoC.
+
 endmenu
 
 endif
diff --git a/drivers/soc/apple/Makefile b/drivers/soc/apple/Makefile
index 8aca79fca0dd..e293770cf66d 100644
--- a/drivers/soc/apple/Makefile
+++ b/drivers/soc/apple/Makefile
@@ -3,3 +3,6 @@ obj-$(CONFIG_APPLE_PMGR_PWRSTATE)	+= apple-pmgr-pwrstate.o
 
 obj-$(CONFIG_APPLE_RTKIT) += apple-rtkit.o
 apple-rtkit-y = rtkit.o rtkit-crashlog.o
+
+obj-$(CONFIG_APPLE_SART) += apple-sart.o
+apple-sart-y = sart.o
diff --git a/drivers/soc/apple/sart.c b/drivers/soc/apple/sart.c
new file mode 100644
index 000000000000..83804b16ad03
--- /dev/null
+++ b/drivers/soc/apple/sart.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Apple SART device driver
+ * Copyright (C) The Asahi Linux Contributors
+ *
+ * Apple SART is a simple address filter for some DMA transactions.
+ * Regions of physical memory must be added to the SART's allow
+ * list before any DMA can target these. Unlike a proper
+ * IOMMU no remapping can be done and special support in the
+ * consumer driver is required since not all DMA transactions of
+ * a single device are subject to SART filtering.
+ */
+
+#include <linux/soc/apple/sart.h>
+#include <linux/atomic.h>
+#include <linux/bits.h>
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#define APPLE_SART_MAX_ENTRIES 16
+
+/* This is probably a bitfield but the exact meaning of each bit is unknown. */
+#define APPLE_SART_FLAGS_ALLOW 0xff
+
+/* SARTv2 registers */
+#define APPLE_SART2_CONFIG(idx)	      (0x00 + 4 * (idx))
+#define APPLE_SART2_CONFIG_FLAGS      GENMASK(31, 24)
+#define APPLE_SART2_CONFIG_SIZE	      GENMASK(23, 0)
+#define APPLE_SART2_CONFIG_SIZE_SHIFT 12
+#define APPLE_SART2_CONFIG_SIZE_MAX   GENMASK(23, 0)
+
+#define APPLE_SART2_PADDR(idx)	(0x40 + 4 * (idx))
+#define APPLE_SART2_PADDR_SHIFT 12
+
+/* SARTv3 registers */
+#define APPLE_SART3_CONFIG(idx) (0x00 + 4 * (idx))
+
+#define APPLE_SART3_PADDR(idx)	(0x40 + 4 * (idx))
+#define APPLE_SART3_PADDR_SHIFT 12
+
+#define APPLE_SART3_SIZE(idx)  (0x80 + 4 * (idx))
+#define APPLE_SART3_SIZE_SHIFT 12
+#define APPLE_SART3_SIZE_MAX   GENMASK(29, 0)
+
+struct apple_sart_ops {
+	void (*get_entry)(struct apple_sart *sart, int index, u8 *flags,
+			  phys_addr_t *paddr, size_t *size);
+	void (*set_entry)(struct apple_sart *sart, int index, u8 flags,
+			  phys_addr_t paddr_shifted, size_t size_shifted);
+	unsigned int size_shift;
+	unsigned int paddr_shift;
+	size_t size_max;
+};
+
+struct apple_sart {
+	struct device *dev;
+	void __iomem *regs;
+
+	const struct apple_sart_ops *ops;
+
+	unsigned long protected_entries;
+	unsigned long used_entries;
+};
+
+static void sart2_get_entry(struct apple_sart *sart, int index, u8 *flags,
+			    phys_addr_t *paddr, size_t *size)
+{
+	u32 cfg = readl(sart->regs + APPLE_SART2_CONFIG(index));
+	phys_addr_t paddr_ = readl(sart->regs + APPLE_SART2_PADDR(index));
+	size_t size_ = FIELD_GET(APPLE_SART2_CONFIG_SIZE, cfg);
+
+	*flags = FIELD_GET(APPLE_SART2_CONFIG_FLAGS, cfg);
+	*size = size_ << APPLE_SART2_CONFIG_SIZE_SHIFT;
+	*paddr = paddr_ << APPLE_SART2_PADDR_SHIFT;
+}
+
+static void sart2_set_entry(struct apple_sart *sart, int index, u8 flags,
+			    phys_addr_t paddr_shifted, size_t size_shifted)
+{
+	u32 cfg;
+
+	cfg = FIELD_PREP(APPLE_SART2_CONFIG_FLAGS, flags);
+	cfg |= FIELD_PREP(APPLE_SART2_CONFIG_SIZE, size_shifted);
+
+	writel(paddr_shifted, sart->regs + APPLE_SART2_PADDR(index));
+	writel(cfg, sart->regs + APPLE_SART2_CONFIG(index));
+}
+
+static struct apple_sart_ops sart_ops_v2 = {
+	.get_entry = sart2_get_entry,
+	.set_entry = sart2_set_entry,
+	.size_shift = APPLE_SART2_CONFIG_SIZE_SHIFT,
+	.paddr_shift = APPLE_SART2_PADDR_SHIFT,
+	.size_max = APPLE_SART2_CONFIG_SIZE_MAX,
+};
+
+static void sart3_get_entry(struct apple_sart *sart, int index, u8 *flags,
+			    phys_addr_t *paddr, size_t *size)
+{
+	phys_addr_t paddr_ = readl(sart->regs + APPLE_SART3_PADDR(index));
+	size_t size_ = readl(sart->regs + APPLE_SART3_SIZE(index));
+
+	*flags = readl(sart->regs + APPLE_SART3_CONFIG(index));
+	*size = size_ << APPLE_SART3_SIZE_SHIFT;
+	*paddr = paddr_ << APPLE_SART3_PADDR_SHIFT;
+}
+
+static void sart3_set_entry(struct apple_sart *sart, int index, u8 flags,
+			    phys_addr_t paddr_shifted, size_t size_shifted)
+{
+	writel(paddr_shifted, sart->regs + APPLE_SART3_PADDR(index));
+	writel(size_shifted, sart->regs + APPLE_SART3_SIZE(index));
+	writel(flags, sart->regs + APPLE_SART3_CONFIG(index));
+}
+
+static struct apple_sart_ops sart_ops_v3 = {
+	.get_entry = sart3_get_entry,
+	.set_entry = sart3_set_entry,
+	.size_shift = APPLE_SART3_SIZE_SHIFT,
+	.paddr_shift = APPLE_SART3_PADDR_SHIFT,
+	.size_max = APPLE_SART3_SIZE_MAX,
+};
+
+static int apple_sart_probe(struct platform_device *pdev)
+{
+	int i;
+	struct apple_sart *sart;
+	struct device *dev = &pdev->dev;
+
+	sart = devm_kzalloc(dev, sizeof(*sart), GFP_KERNEL);
+	if (!sart)
+		return -ENOMEM;
+
+	sart->dev = dev;
+	sart->ops = of_device_get_match_data(dev);
+
+	sart->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(sart->regs))
+		return PTR_ERR(sart->regs);
+
+	for (i = 0; i < APPLE_SART_MAX_ENTRIES; ++i) {
+		u8 flags;
+		size_t size;
+		phys_addr_t paddr;
+
+		sart->ops->get_entry(sart, i, &flags, &paddr, &size);
+
+		if (!flags)
+			continue;
+
+		dev_dbg(sart->dev,
+			"SART bootloader entry: index %02d; flags: 0x%02x; paddr: %pa; size: 0x%zx\n",
+			i, flags, &paddr, size);
+		set_bit(i, &sart->protected_entries);
+	}
+
+	platform_set_drvdata(pdev, sart);
+	return 0;
+}
+
+struct apple_sart *devm_apple_sart_get(struct device *dev)
+{
+	struct device_node *sart_node;
+	struct platform_device *sart_pdev;
+	struct apple_sart *sart;
+	int ret;
+
+	sart_node = of_parse_phandle(dev->of_node, "apple,sart", 0);
+	if (!sart_node)
+		return ERR_PTR(-ENODEV);
+
+	sart_pdev = of_find_device_by_node(sart_node);
+	of_node_put(sart_node);
+
+	if (!sart_pdev)
+		return ERR_PTR(-ENODEV);
+
+	sart = dev_get_drvdata(&sart_pdev->dev);
+	if (!sart) {
+		put_device(&sart_pdev->dev);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	ret = devm_add_action_or_reset(dev, (void (*)(void *))put_device,
+				       &sart_pdev->dev);
+	if (ret)
+		return ERR_PTR(ret);
+
+	device_link_add(dev, &sart_pdev->dev,
+			DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_SUPPLIER);
+
+	return sart;
+}
+EXPORT_SYMBOL_GPL(devm_apple_sart_get);
+
+static int sart_set_entry(struct apple_sart *sart, int index, u8 flags,
+			  phys_addr_t paddr, size_t size)
+{
+	if (size & ((1 << sart->ops->size_shift) - 1))
+		return -EINVAL;
+	if (paddr & ((1 << sart->ops->paddr_shift) - 1))
+		return -EINVAL;
+
+	paddr >>= sart->ops->size_shift;
+	size >>= sart->ops->paddr_shift;
+
+	if (size > sart->ops->size_max)
+		return -EINVAL;
+
+	sart->ops->set_entry(sart, index, flags, paddr, size);
+	return 0;
+}
+
+int apple_sart_add_allowed_region(struct apple_sart *sart, phys_addr_t paddr,
+				  size_t size)
+{
+	int i, ret;
+
+	for (i = 0; i < APPLE_SART_MAX_ENTRIES; ++i) {
+		if (test_bit(i, &sart->protected_entries))
+			continue;
+		if (test_and_set_bit(i, &sart->used_entries))
+			continue;
+
+		ret = sart_set_entry(sart, i, APPLE_SART_FLAGS_ALLOW, paddr,
+				     size);
+		if (ret) {
+			dev_dbg(sart->dev,
+				"unable to set entry %d to [%pa, 0x%zx]\n",
+				i, &paddr, size);
+			clear_bit(i, &sart->used_entries);
+			return ret;
+		}
+
+		dev_dbg(sart->dev, "wrote [%pa, 0x%zx] to %d\n", &paddr, size,
+			i);
+		return 0;
+	}
+
+	dev_warn(sart->dev,
+		 "no free entries left to add [paddr: 0x%pa, size: 0x%zx]\n",
+		 &paddr, size);
+
+	return -EBUSY;
+}
+EXPORT_SYMBOL_GPL(apple_sart_add_allowed_region);
+
+int apple_sart_remove_allowed_region(struct apple_sart *sart, phys_addr_t paddr,
+				     size_t size)
+{
+	int i;
+
+	dev_dbg(sart->dev,
+		"will remove [paddr: %pa, size: 0x%zx] from allowed regions\n",
+		&paddr, size);
+
+	for (i = 0; i < APPLE_SART_MAX_ENTRIES; ++i) {
+		u8 eflags;
+		size_t esize;
+		phys_addr_t epaddr;
+
+		if (test_bit(i, &sart->protected_entries))
+			continue;
+
+		sart->ops->get_entry(sart, i, &eflags, &epaddr, &esize);
+
+		if (epaddr != paddr || esize != size)
+			continue;
+
+		sart->ops->set_entry(sart, i, 0, 0, 0);
+
+		clear_bit(i, &sart->used_entries);
+		dev_dbg(sart->dev, "cleared entry %d\n", i);
+		return 0;
+	}
+
+	dev_warn(sart->dev, "entry [paddr: 0x%pa, size: 0x%zx] not found\n",
+		 &paddr, size);
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(apple_sart_remove_allowed_region);
+
+static void apple_sart_shutdown(struct platform_device *pdev)
+{
+	struct apple_sart *sart = dev_get_drvdata(&pdev->dev);
+	int i;
+
+	for (i = 0; i < APPLE_SART_MAX_ENTRIES; ++i) {
+		if (test_bit(i, &sart->protected_entries))
+			continue;
+
+		sart->ops->set_entry(sart, i, 0, 0, 0);
+	}
+}
+
+static const struct of_device_id apple_sart_of_match[] = {
+	{
+		.compatible = "apple,t6000-sart",
+		.data = &sart_ops_v3,
+	},
+	{
+		.compatible = "apple,t8103-sart",
+		.data = &sart_ops_v2,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, apple_sart_of_match);
+
+static struct platform_driver apple_sart_driver = {
+	.driver = {
+		.name = "apple-sart",
+		.of_match_table = apple_sart_of_match,
+	},
+	.probe = apple_sart_probe,
+	.shutdown = apple_sart_shutdown,
+};
+module_platform_driver(apple_sart_driver);
+
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
+MODULE_DESCRIPTION("Apple SART driver");
diff --git a/include/linux/soc/apple/sart.h b/include/linux/soc/apple/sart.h
new file mode 100644
index 000000000000..2249bf6cde09
--- /dev/null
+++ b/include/linux/soc/apple/sart.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+/*
+ * Apple SART device driver
+ * Copyright (C) The Asahi Linux Contributors
+ *
+ * Apple SART is a simple address filter for DMA transactions.
+ * Regions of physical memory must be added to the SART's allow
+ * list before any DMA can target these. Unlike a proper
+ * IOMMU no remapping can be done.
+ */
+
+#ifndef _LINUX_SOC_APPLE_SART_H_
+#define _LINUX_SOC_APPLE_SART_H_
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/types.h>
+
+struct apple_sart;
+
+/*
+ * Get a reference to the SART attached to dev.
+ *
+ * Looks for the phandle reference in apple,sart and returns a pointer
+ * to the corresponding apple_sart struct to be used with
+ * apple_sart_add_allowed_region and apple_sart_remove_allowed_region.
+ */
+struct apple_sart *devm_apple_sart_get(struct device *dev);
+
+/*
+ * Adds the region [paddr, paddr+size] to the DMA allow list.
+ *
+ * @sart: SART reference
+ * @paddr: Start address of the region to be used for DMA
+ * @size: Size of the region to be used for DMA.
+ */
+int apple_sart_add_allowed_region(struct apple_sart *sart, phys_addr_t paddr,
+				  size_t size);
+
+/*
+ * Removes the region [paddr, paddr+size] from the DMA allow list.
+ *
+ * Note that exact same paddr and size used for apple_sart_add_allowed_region
+ * have to be passed.
+ *
+ * @sart: SART reference
+ * @paddr: Start address of the region no longer used for DMA
+ * @size: Size of the region no longer used for DMA.
+ */
+int apple_sart_remove_allowed_region(struct apple_sart *sart, phys_addr_t paddr,
+				     size_t size);
+
+#endif /* _LINUX_SOC_APPLE_SART_H_ */
-- 
cgit v1.2.3


From f502cc568de95e5ed9cc9e6133fa454fbe0c5c01 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Fri, 4 Mar 2022 11:48:38 -0800
Subject: KVM: Add max_vcpus field in common 'struct kvm'

For TDX guests, the maximum number of vcpus needs to be specified when the
TDX guest VM is initialized (creating the TDX data corresponding to TDX
guest) before creating vcpu.  It needs to record the maximum number of
vcpus on VM creation (KVM_CREATE_VM) and return error if the number of
vcpus exceeds it

Because there is already max_vcpu member in arm64 struct kvm_arch, move it
to common struct kvm and initialize it to KVM_MAX_VCPUS before
kvm_arch_init_vm() instead of adding it to x86 struct kvm_arch.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Message-Id: <e53234cdee6a92357d06c80c03d77c19cdefb804.1646422845.git.isaku.yamahata@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/include/asm/kvm_host.h | 3 ---
 arch/arm64/kvm/arm.c              | 6 +++---
 arch/arm64/kvm/vgic/vgic-init.c   | 6 +++---
 include/linux/kvm_host.h          | 1 +
 virt/kvm/kvm_main.c               | 3 ++-
 5 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 94a27a7520f4..27ebb2929e0c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -107,9 +107,6 @@ struct kvm_arch {
 	/* VTCR_EL2 value for this VM */
 	u64    vtcr;
 
-	/* The maximum number of vCPUs depends on the used GIC model */
-	int max_vcpus;
-
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 523bc934fe2f..7fceb855fa71 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -153,7 +153,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm_vgic_early_init(kvm);
 
 	/* The maximum number of VCPUs is limited by the host's GIC model */
-	kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
+	kvm->max_vcpus = kvm_arm_default_max_vcpus();
 
 	set_default_spectre(kvm);
 
@@ -230,7 +230,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 	case KVM_CAP_MAX_VCPU_ID:
 		if (kvm)
-			r = kvm->arch.max_vcpus;
+			r = kvm->max_vcpus;
 		else
 			r = kvm_arm_default_max_vcpus();
 		break;
@@ -306,7 +306,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
 		return -EBUSY;
 
-	if (id >= kvm->arch.max_vcpus)
+	if (id >= kvm->max_vcpus)
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index fc00304fe7d8..77feafd5c0e3 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -98,11 +98,11 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	ret = 0;
 
 	if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
-		kvm->arch.max_vcpus = VGIC_V2_MAX_CPUS;
+		kvm->max_vcpus = VGIC_V2_MAX_CPUS;
 	else
-		kvm->arch.max_vcpus = VGIC_V3_MAX_CPUS;
+		kvm->max_vcpus = VGIC_V3_MAX_CPUS;
 
-	if (atomic_read(&kvm->online_vcpus) > kvm->arch.max_vcpus) {
+	if (atomic_read(&kvm->online_vcpus) > kvm->max_vcpus) {
 		ret = -E2BIG;
 		goto out_unlock;
 	}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 252ee4a61b58..f94f72bbd2d3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -725,6 +725,7 @@ struct kvm {
 	 * and is accessed atomically.
 	 */
 	atomic_t online_vcpus;
+	int max_vcpus;
 	int created_vcpus;
 	int last_boosted_vcpu;
 	struct list_head vm_list;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ac57fc2c935f..655365b2cbe8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1078,6 +1078,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	spin_lock_init(&kvm->gpc_lock);
 
 	INIT_LIST_HEAD(&kvm->devices);
+	kvm->max_vcpus = KVM_MAX_VCPUS;
 
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
@@ -3732,7 +3733,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 		return -EINVAL;
 
 	mutex_lock(&kvm->lock);
-	if (kvm->created_vcpus == KVM_MAX_VCPUS) {
+	if (kvm->created_vcpus >= kvm->max_vcpus) {
 		mutex_unlock(&kvm->lock);
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From db05628435aa761d30b4eae481a82befe7a8492a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:12 +0200
Subject: blk-cgroup: move blkcg_{get,set}_fc_appid out of line

No need to have these helpers inline.  Also remove the stubs and just use
an IS_ENABLED for the get side (the set side already is only built
conditionlly).

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Makefile                |  1 +
 block/blk-cgroup-fc-appid.c   | 57 ++++++++++++++++++++++++++++++++++++++++++
 drivers/scsi/lpfc/lpfc_scsi.c |  4 ++-
 include/linux/blk-cgroup.h    | 58 ++-----------------------------------------
 4 files changed, 63 insertions(+), 57 deletions(-)
 create mode 100644 block/blk-cgroup-fc-appid.c

(limited to 'include/linux')

diff --git a/block/Makefile b/block/Makefile
index 3950ecbc5c26..4e01bb71ad6e 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_CGROUP_RWSTAT)	+= blk-cgroup-rwstat.o
+obj-$(CONFIG_BLK_CGROUP_FC_APPID) += blk-cgroup-fc-appid.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_BLK_CGROUP_IOPRIO)	+= blk-ioprio.o
 obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
diff --git a/block/blk-cgroup-fc-appid.c b/block/blk-cgroup-fc-appid.c
new file mode 100644
index 000000000000..760a2e1878dd
--- /dev/null
+++ b/block/blk-cgroup-fc-appid.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "blk-cgroup.h"
+
+/**
+ * blkcg_set_fc_appid - set the fc_app_id field associted to blkcg
+ * @app_id: application identifier
+ * @cgrp_id: cgroup id
+ * @app_id_len: size of application identifier
+ */
+int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len)
+{
+	struct cgroup *cgrp;
+	struct cgroup_subsys_state *css;
+	struct blkcg *blkcg;
+	int ret  = 0;
+
+	if (app_id_len > FC_APPID_LEN)
+		return -EINVAL;
+
+	cgrp = cgroup_get_from_id(cgrp_id);
+	if (!cgrp)
+		return -ENOENT;
+	css = cgroup_get_e_css(cgrp, &io_cgrp_subsys);
+	if (!css) {
+		ret = -ENOENT;
+		goto out_cgrp_put;
+	}
+	blkcg = css_to_blkcg(css);
+	/*
+	 * There is a slight race condition on setting the appid.
+	 * Worst case an I/O may not find the right id.
+	 * This is no different from the I/O we let pass while obtaining
+	 * the vmid from the fabric.
+	 * Adding the overhead of a lock is not necessary.
+	 */
+	strlcpy(blkcg->fc_app_id, app_id, app_id_len);
+	css_put(css);
+out_cgrp_put:
+	cgroup_put(cgrp);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkcg_set_fc_appid);
+
+/**
+ * blkcg_get_fc_appid - get the fc app identifier associated with a bio
+ * @bio: target bio
+ *
+ * On success return the fc_app_id, on failure return NULL
+ */
+char *blkcg_get_fc_appid(struct bio *bio)
+{
+	if (!bio->bi_blkg || bio->bi_blkg->blkcg->fc_app_id[0] == '\0')
+		return NULL;
+	return bio->bi_blkg->blkcg->fc_app_id;
+}
+EXPORT_SYMBOL_GPL(blkcg_get_fc_appid);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index ba9dbb51b75f..f6b83853f7ee 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5528,7 +5528,9 @@ static char *lpfc_is_command_vm_io(struct scsi_cmnd *cmd)
 {
 	struct bio *bio = scsi_cmd_to_rq(cmd)->bio;
 
-	return bio ? blkcg_get_fc_appid(bio) : NULL;
+	if (!IS_ENABLED(CONFIG_BLK_CGROUP_FC_APPID) || !bio)
+		return NULL;
+	return blkcg_get_fc_appid(bio);
 }
 
 /**
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 652cd05b0924..7a2f7de30173 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -218,61 +218,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
 
 #endif	/* CONFIG_BLK_CGROUP */
 
-#ifdef CONFIG_BLK_CGROUP_FC_APPID
-/*
- * Sets the fc_app_id field associted to blkcg
- * @app_id: application identifier
- * @cgrp_id: cgroup id
- * @app_id_len: size of application identifier
- */
-static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len)
-{
-	struct cgroup *cgrp;
-	struct cgroup_subsys_state *css;
-	struct blkcg *blkcg;
-	int ret  = 0;
-
-	if (app_id_len > FC_APPID_LEN)
-		return -EINVAL;
-
-	cgrp = cgroup_get_from_id(cgrp_id);
-	if (!cgrp)
-		return -ENOENT;
-	css = cgroup_get_e_css(cgrp, &io_cgrp_subsys);
-	if (!css) {
-		ret = -ENOENT;
-		goto out_cgrp_put;
-	}
-	blkcg = css_to_blkcg(css);
-	/*
-	 * There is a slight race condition on setting the appid.
-	 * Worst case an I/O may not find the right id.
-	 * This is no different from the I/O we let pass while obtaining
-	 * the vmid from the fabric.
-	 * Adding the overhead of a lock is not necessary.
-	 */
-	strlcpy(blkcg->fc_app_id, app_id, app_id_len);
-	css_put(css);
-out_cgrp_put:
-	cgroup_put(cgrp);
-	return ret;
-}
+int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len);
+char *blkcg_get_fc_appid(struct bio *bio);
 
-/**
- * blkcg_get_fc_appid - get the fc app identifier associated with a bio
- * @bio: target bio
- *
- * On success return the fc_app_id, on failure return NULL
- */
-static inline char *blkcg_get_fc_appid(struct bio *bio)
-{
-	if (bio && bio->bi_blkg &&
-		(bio->bi_blkg->blkcg->fc_app_id[0] != '\0'))
-		return bio->bi_blkg->blkcg->fc_app_id;
-	return NULL;
-}
-#else
-static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; }
-static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; }
-#endif /*CONFIG_BLK_CGROUP_FC_APPID*/
 #endif	/* _BLK_CGROUP_H */
-- 
cgit v1.2.3


From 216889aad362b5b7e998a5371348b5e95d485dd1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:13 +0200
Subject: blk-cgroup: move blk_cgroup_congested out line

There is no urgent need to inline this function, so move it out of line.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-6-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c         | 20 ++++++++++++++++++++
 include/linux/blk-cgroup.h | 20 +-------------------
 2 files changed, 21 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 8dfe62786cd5..97266ebde975 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1950,6 +1950,26 @@ void blk_cgroup_bio_start(struct bio *bio)
 	put_cpu();
 }
 
+bool blk_cgroup_congested(void)
+{
+	struct cgroup_subsys_state *css;
+	bool ret = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (!css)
+		css = task_css(current, io_cgrp_id);
+	while (css) {
+		if (atomic_read(&css->cgroup->congestion_count)) {
+			ret = true;
+			break;
+		}
+		css = css->parent;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
 static int __init blkcg_init(void)
 {
 	blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio",
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 7a2f7de30173..988965c1c27b 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -135,25 +135,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 	return NULL;
 }
 
-static inline bool blk_cgroup_congested(void)
-{
-	struct cgroup_subsys_state *css;
-	bool ret = false;
-
-	rcu_read_lock();
-	css = kthread_blkcg();
-	if (!css)
-		css = task_css(current, io_cgrp_id);
-	while (css) {
-		if (atomic_read(&css->cgroup->congestion_count)) {
-			ret = true;
-			break;
-		}
-		css = css->parent;
-	}
-	rcu_read_unlock();
-	return ret;
-}
+bool blk_cgroup_congested(void);
 
 /**
  * blkcg_parent - get the parent of a blkcg
-- 
cgit v1.2.3


From 397c9f46ee4d99024c64954b007c1b5762d01cb4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:14 +0200
Subject: blk-cgroup: move blkcg_{pin,unpin}_online out of line

Move these two functions out of line as there is no good reason
to inline them.  Also switch to passing a cgroup_subsys_state
instead of doing the conversion in the caller to prepare for making
the blkcg structure private to blk-cgroup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-7-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c         | 88 ++++++++++++++++++++++++++++++++++------------
 include/linux/blk-cgroup.h | 46 ++----------------------
 mm/backing-dev.c           |  5 ++-
 3 files changed, 69 insertions(+), 70 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 97266ebde975..3af0d4a61955 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -155,6 +155,17 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 		blk_finish_plug(&plug);
 }
 
+/**
+ * blkcg_parent - get the parent of a blkcg
+ * @blkcg: blkcg of interest
+ *
+ * Return the parent blkcg of @blkcg.  Can be called anytime.
+ */
+static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
+{
+	return css_to_blkcg(blkcg->css.parent);
+}
+
 /**
  * blkg_alloc - allocate a blkg
  * @blkcg: block cgroup the new blkg is associated with
@@ -1015,25 +1026,6 @@ static struct cftype blkcg_legacy_files[] = {
  *    This finally frees the blkcg.
  */
 
-/**
- * blkcg_css_offline - cgroup css_offline callback
- * @css: css of interest
- *
- * This function is called when @css is about to go away.  Here the cgwbs are
- * offlined first and only once writeback associated with the blkcg has
- * finished do we start step 2 (see above).
- */
-static void blkcg_css_offline(struct cgroup_subsys_state *css)
-{
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	/* this prevents anyone from attaching or migrating to this blkcg */
-	wb_blkcg_offline(blkcg);
-
-	/* put the base online pin allowing step 2 to be triggered */
-	blkcg_unpin_online(blkcg);
-}
-
 /**
  * blkcg_destroy_blkgs - responsible for shooting down blkgs
  * @blkcg: blkcg of interest
@@ -1045,7 +1037,7 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css)
  *
  * This is the blkcg counterpart of ioc_release_fn().
  */
-void blkcg_destroy_blkgs(struct blkcg *blkcg)
+static void blkcg_destroy_blkgs(struct blkcg *blkcg)
 {
 	might_sleep();
 
@@ -1075,6 +1067,57 @@ void blkcg_destroy_blkgs(struct blkcg *blkcg)
 	spin_unlock_irq(&blkcg->lock);
 }
 
+/**
+ * blkcg_pin_online - pin online state
+ * @blkcg_css: blkcg of interest
+ *
+ * While pinned, a blkcg is kept online.  This is primarily used to
+ * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline
+ * while an associated cgwb is still active.
+ */
+void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css)
+{
+	refcount_inc(&css_to_blkcg(blkcg_css)->online_pin);
+}
+
+/**
+ * blkcg_unpin_online - unpin online state
+ * @blkcg_css: blkcg of interest
+ *
+ * This is primarily used to impedance-match blkg and cgwb lifetimes so
+ * that blkg doesn't go offline while an associated cgwb is still active.
+ * When this count goes to zero, all active cgwbs have finished so the
+ * blkcg can continue destruction by calling blkcg_destroy_blkgs().
+ */
+void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css)
+{
+	struct blkcg *blkcg = css_to_blkcg(blkcg_css);
+
+	do {
+		if (!refcount_dec_and_test(&blkcg->online_pin))
+			break;
+		blkcg_destroy_blkgs(blkcg);
+		blkcg = blkcg_parent(blkcg);
+	} while (blkcg);
+}
+
+/**
+ * blkcg_css_offline - cgroup css_offline callback
+ * @css: css of interest
+ *
+ * This function is called when @css is about to go away.  Here the cgwbs are
+ * offlined first and only once writeback associated with the blkcg has
+ * finished do we start step 2 (see above).
+ */
+static void blkcg_css_offline(struct cgroup_subsys_state *css)
+{
+	/* this prevents anyone from attaching or migrating to this blkcg */
+	wb_blkcg_offline(css_to_blkcg(css));
+
+	/* put the base online pin allowing step 2 to be triggered */
+	blkcg_unpin_online(css);
+}
+
 static void blkcg_css_free(struct cgroup_subsys_state *css)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
@@ -1163,8 +1206,7 @@ unlock:
 
 static int blkcg_css_online(struct cgroup_subsys_state *css)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-	struct blkcg *parent = blkcg_parent(blkcg);
+	struct blkcg *parent = blkcg_parent(css_to_blkcg(css));
 
 	/*
 	 * blkcg_pin_online() is used to delay blkcg offline so that blkgs
@@ -1172,7 +1214,7 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
 	 * parent so that offline always happens towards the root.
 	 */
 	if (parent)
-		blkcg_pin_online(parent);
+		blkcg_pin_online(css);
 	return 0;
 }
 
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 988965c1c27b..0fb7459096e9 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -111,7 +111,6 @@ struct blkcg_gq {
 
 extern struct cgroup_subsys_state * const blkcg_root_css;
 
-void blkcg_destroy_blkgs(struct blkcg *blkcg);
 void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
 void blkcg_maybe_throttle_current(void);
 
@@ -136,49 +135,8 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 }
 
 bool blk_cgroup_congested(void);
-
-/**
- * blkcg_parent - get the parent of a blkcg
- * @blkcg: blkcg of interest
- *
- * Return the parent blkcg of @blkcg.  Can be called anytime.
- */
-static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
-{
-	return css_to_blkcg(blkcg->css.parent);
-}
-
-/**
- * blkcg_pin_online - pin online state
- * @blkcg: blkcg of interest
- *
- * While pinned, a blkcg is kept online.  This is primarily used to
- * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline
- * while an associated cgwb is still active.
- */
-static inline void blkcg_pin_online(struct blkcg *blkcg)
-{
-	refcount_inc(&blkcg->online_pin);
-}
-
-/**
- * blkcg_unpin_online - unpin online state
- * @blkcg: blkcg of interest
- *
- * This is primarily used to impedance-match blkg and cgwb lifetimes so
- * that blkg doesn't go offline while an associated cgwb is still active.
- * When this count goes to zero, all active cgwbs have finished so the
- * blkcg can continue destruction by calling blkcg_destroy_blkgs().
- */
-static inline void blkcg_unpin_online(struct blkcg *blkcg)
-{
-	do {
-		if (!refcount_dec_and_test(&blkcg->online_pin))
-			break;
-		blkcg_destroy_blkgs(blkcg);
-		blkcg = blkcg_parent(blkcg);
-	} while (blkcg);
-}
+void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css);
+void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css);
 
 #else	/* CONFIG_BLK_CGROUP */
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7176af65b103..93cddbcd4eb8 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -390,7 +390,6 @@ static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
 						release_work);
-	struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css);
 	struct backing_dev_info *bdi = wb->bdi;
 
 	mutex_lock(&wb->bdi->cgwb_release_mutex);
@@ -401,7 +400,7 @@ static void cgwb_release_workfn(struct work_struct *work)
 	mutex_unlock(&wb->bdi->cgwb_release_mutex);
 
 	/* triggers blkg destruction if no online users left */
-	blkcg_unpin_online(blkcg);
+	blkcg_unpin_online(wb->blkcg_css);
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 
@@ -511,7 +510,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 			list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list);
 			list_add(&wb->memcg_node, memcg_cgwb_list);
 			list_add(&wb->blkcg_node, blkcg_cgwb_list);
-			blkcg_pin_online(blkcg);
+			blkcg_pin_online(blkcg_css);
 			css_get(memcg_css);
 			css_get(blkcg_css);
 		}
-- 
cgit v1.2.3


From dec223c92a4688f6c9642d640cfe15a99d289dd4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:15 +0200
Subject: blk-cgroup: move struct blkcg to block/blk-cgroup.h

There is no real need to expose the blkcg structure to the whole kernel.
Move it to the private header an expose a helper to let the writeback
code access the cgwb_list member.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-8-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c          |  9 ++++++++-
 block/blk-cgroup.h          | 28 ++++++++++++++++++++++++++++
 include/linux/backing-dev.h |  6 ++----
 include/linux/blk-cgroup.h  | 32 +-------------------------------
 mm/backing-dev.c            | 13 ++++++-------
 5 files changed, 45 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 3af0d4a61955..bb52797c02bd 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1005,6 +1005,13 @@ static struct cftype blkcg_legacy_files[] = {
 	{ }	/* terminate */
 };
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css)
+{
+	return &css_to_blkcg(css)->cgwb_list;
+}
+#endif
+
 /*
  * blkcg destruction is a three-stage process.
  *
@@ -1112,7 +1119,7 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css)
 static void blkcg_css_offline(struct cgroup_subsys_state *css)
 {
 	/* this prevents anyone from attaching or migrating to this blkcg */
-	wb_blkcg_offline(css_to_blkcg(css));
+	wb_blkcg_offline(css);
 
 	/* put the base online pin allowing step 2 to be triggered */
 	blkcg_unpin_online(css);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 49e88fc9cc39..b00fb1169e7c 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -17,10 +17,38 @@
 #include <linux/blk-cgroup.h>
 #include <linux/blk-mq.h>
 
+struct blkcg_gq;
+struct blkg_policy_data;
+
+
 /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */
 #define BLKG_STAT_CPU_BATCH	(INT_MAX / 2)
 
 #ifdef CONFIG_BLK_CGROUP
+struct blkcg {
+	struct cgroup_subsys_state	css;
+	spinlock_t			lock;
+	refcount_t			online_pin;
+
+	struct radix_tree_root		blkg_tree;
+	struct blkcg_gq	__rcu		*blkg_hint;
+	struct hlist_head		blkg_list;
+
+	struct blkcg_policy_data	*cpd[BLKCG_MAX_POLS];
+
+	struct list_head		all_blkcgs_node;
+#ifdef CONFIG_BLK_CGROUP_FC_APPID
+	char                            fc_app_id[FC_APPID_LEN];
+#endif
+#ifdef CONFIG_CGROUP_WRITEBACK
+	struct list_head		cgwb_list;
+#endif
+};
+
+static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct blkcg, css) : NULL;
+}
 
 /*
  * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 87ce24d238f3..2bd073fa6bb5 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -17,8 +17,6 @@
 #include <linux/backing-dev-defs.h>
 #include <linux/slab.h>
 
-struct blkcg;
-
 static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
 {
 	kref_get(&bdi->refcnt);
@@ -154,7 +152,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
 				    struct cgroup_subsys_state *memcg_css,
 				    gfp_t gfp);
 void wb_memcg_offline(struct mem_cgroup *memcg);
-void wb_blkcg_offline(struct blkcg *blkcg);
+void wb_blkcg_offline(struct cgroup_subsys_state *css);
 
 /**
  * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
@@ -378,7 +376,7 @@ static inline void wb_memcg_offline(struct mem_cgroup *memcg)
 {
 }
 
-static inline void wb_blkcg_offline(struct blkcg *blkcg)
+static inline void wb_blkcg_offline(struct cgroup_subsys_state *css)
 {
 }
 
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 0fb7459096e9..d7b188095040 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -37,29 +37,6 @@ enum blkg_iostat_type {
 	BLKG_IOSTAT_NR,
 };
 
-struct blkcg_gq;
-struct blkg_policy_data;
-
-struct blkcg {
-	struct cgroup_subsys_state	css;
-	spinlock_t			lock;
-	refcount_t			online_pin;
-
-	struct radix_tree_root		blkg_tree;
-	struct blkcg_gq	__rcu		*blkg_hint;
-	struct hlist_head		blkg_list;
-
-	struct blkcg_policy_data	*cpd[BLKCG_MAX_POLS];
-
-	struct list_head		all_blkcgs_node;
-#ifdef CONFIG_BLK_CGROUP_FC_APPID
-	char                            fc_app_id[FC_APPID_LEN];
-#endif
-#ifdef CONFIG_CGROUP_WRITEBACK
-	struct list_head		cgwb_list;
-#endif
-};
-
 struct blkg_iostat {
 	u64				bytes[BLKG_IOSTAT_NR];
 	u64				ios[BLKG_IOSTAT_NR];
@@ -114,11 +91,6 @@ extern struct cgroup_subsys_state * const blkcg_root_css;
 void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
 void blkcg_maybe_throttle_current(void);
 
-static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
-{
-	return css ? container_of(css, struct blkcg, css) : NULL;
-}
-
 /**
  * bio_blkcg - grab the blkcg associated with a bio
  * @bio: target bio
@@ -137,12 +109,10 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 bool blk_cgroup_congested(void);
 void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css);
 void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css);
+struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css);
 
 #else	/* CONFIG_BLK_CGROUP */
 
-struct blkcg {
-};
-
 struct blkcg_gq {
 };
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 93cddbcd4eb8..98f8f62e52ca 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -445,7 +445,6 @@ static int cgwb_create(struct backing_dev_info *bdi,
 {
 	struct mem_cgroup *memcg;
 	struct cgroup_subsys_state *blkcg_css;
-	struct blkcg *blkcg;
 	struct list_head *memcg_cgwb_list, *blkcg_cgwb_list;
 	struct bdi_writeback *wb;
 	unsigned long flags;
@@ -453,9 +452,8 @@ static int cgwb_create(struct backing_dev_info *bdi,
 
 	memcg = mem_cgroup_from_css(memcg_css);
 	blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys);
-	blkcg = css_to_blkcg(blkcg_css);
 	memcg_cgwb_list = &memcg->cgwb_list;
-	blkcg_cgwb_list = &blkcg->cgwb_list;
+	blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css);
 
 	/* look up again under lock and discard on blkcg mismatch */
 	spin_lock_irqsave(&cgwb_lock, flags);
@@ -723,18 +721,19 @@ void wb_memcg_offline(struct mem_cgroup *memcg)
 
 /**
  * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined
- * @blkcg: blkcg being offlined
+ * @css: blkcg being offlined
  *
  * Also prevents creation of any new wb's associated with @blkcg.
  */
-void wb_blkcg_offline(struct blkcg *blkcg)
+void wb_blkcg_offline(struct cgroup_subsys_state *css)
 {
 	struct bdi_writeback *wb, *next;
+	struct list_head *list = blkcg_get_cgwb_list(css);
 
 	spin_lock_irq(&cgwb_lock);
-	list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node)
+	list_for_each_entry_safe(wb, next, list, blkcg_node)
 		cgwb_kill(wb);
-	blkcg->cgwb_list.next = NULL;	/* prevent new wb's */
+	list->next = NULL;	/* prevent new wb's */
 	spin_unlock_irq(&cgwb_lock);
 }
 
-- 
cgit v1.2.3


From f4a6a61cb6d40d9ae63e47743d33200f3efe3fe7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:16 +0200
Subject: blktrace: cleanup the __trace_note_message interface

Pass the cgroup_subsys_state instead of a the blkg so that blktrace
doesn't need to poke into blk-cgroup internals, and give the name a
blk prefix as the current name is way too generic for a public
interface.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-9-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.h          |  4 ++--
 block/blk-throttle.c         |  2 +-
 include/linux/blktrace_api.h | 10 ++++------
 kernel/trace/blktrace.c      | 20 ++++++++++----------
 4 files changed, 17 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 978ef5d6fe6a..b18d6c31c225 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -1102,13 +1102,13 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 		break;							\
 	bfq_bfqq_name((bfqq), pid_str, MAX_BFQQ_NAME_LENGTH);		\
 	blk_add_cgroup_trace_msg((bfqd)->queue,				\
-			bfqg_to_blkg(bfqq_group(bfqq))->blkcg,		\
+			&bfqg_to_blkg(bfqq_group(bfqq))->blkcg->css,	\
 			"%s " fmt, pid_str, ##args);			\
 } while (0)
 
 #define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
 	blk_add_cgroup_trace_msg((bfqd)->queue,				\
-		bfqg_to_blkg(bfqg)->blkcg, fmt, ##args);		\
+		&bfqg_to_blkg(bfqg)->blkcg->css, fmt, ##args);		\
 } while (0)
 
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 469c483719be..447e1b8722f7 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -227,7 +227,7 @@ static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
 		break;							\
 	if ((__tg)) {							\
 		blk_add_cgroup_trace_msg(__td->queue,			\
-			tg_to_blkg(__tg)->blkcg, "throtl " fmt, ##args);\
+			&tg_to_blkg(__tg)->blkcg->css, "throtl " fmt, ##args);\
 	} else {							\
 		blk_add_trace_msg(__td->queue, "throtl " fmt, ##args);	\
 	}								\
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 22501a293fa5..623e22492afa 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -27,12 +27,10 @@ struct blk_trace {
 	atomic_t dropped;
 };
 
-struct blkcg;
-
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
-extern __printf(3, 4)
-void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...);
+__printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt,
+		struct cgroup_subsys_state *css, const char *fmt, ...);
 
 /**
  * blk_add_trace_msg - Add a (simple) message to the blktrace stream
@@ -47,14 +45,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f
  *     NOTE: Can not use 'static inline' due to presence of var args...
  *
  **/
-#define blk_add_cgroup_trace_msg(q, cg, fmt, ...)			\
+#define blk_add_cgroup_trace_msg(q, css, fmt, ...)			\
 	do {								\
 		struct blk_trace *bt;					\
 									\
 		rcu_read_lock();					\
 		bt = rcu_dereference((q)->blk_trace);			\
 		if (unlikely(bt))					\
-			__trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\
+			__blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\
 		rcu_read_unlock();					\
 	} while (0)
 #define blk_add_trace_msg(q, fmt, ...)					\
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 4d5629196d01..9ef349ac49c0 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -145,13 +145,14 @@ static void trace_note_time(struct blk_trace *bt)
 	local_irq_restore(flags);
 }
 
-void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
-	const char *fmt, ...)
+void __blk_trace_note_message(struct blk_trace *bt,
+		struct cgroup_subsys_state *css, const char *fmt, ...)
 {
 	int n;
 	va_list args;
 	unsigned long flags;
 	char *buf;
+	u64 cgid = 0;
 
 	if (unlikely(bt->trace_state != Blktrace_running &&
 		     !blk_tracer_enabled))
@@ -170,17 +171,16 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
 	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
 	va_end(args);
 
-	if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
-		blkcg = NULL;
 #ifdef CONFIG_BLK_CGROUP
-	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n,
-		   blkcg ? cgroup_id(blkcg->css.cgroup) : 1);
-#else
-	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0);
+	if (css && (blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
+		cgid = cgroup_id(css->cgroup);
+	else
+		cgid = 1;
 #endif
+	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, cgid);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(__trace_note_message);
+EXPORT_SYMBOL_GPL(__blk_trace_note_message);
 
 static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 			 pid_t pid)
@@ -411,7 +411,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
 		return PTR_ERR(msg);
 
 	bt = filp->private_data;
-	__trace_note_message(bt, NULL, "%s", msg);
+	__blk_trace_note_message(bt, NULL, "%s", msg);
 	kfree(msg);
 
 	return count;
-- 
cgit v1.2.3


From bbb1ebe7a909db4de49777fb7676d5bf293f34c9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:17 +0200
Subject: blk-cgroup: replace bio_blkcg with bio_blkcg_css

All callers of bio_blkcg actually want the CSS, so replace it with an
interface that does return the CSS.  This now allows to move
struct blkcg_gq to block/blk-cgroup.h instead of exposing it in a
public header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-10-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c         | 18 +++++++++-
 block/blk-cgroup.h         | 67 +++++++++++++++++++++++++++++++++++--
 drivers/block/loop.c       | 12 ++++---
 include/linux/blk-cgroup.h | 83 +++-------------------------------------------
 kernel/trace/blktrace.c    |  6 ++--
 5 files changed, 97 insertions(+), 89 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index bb52797c02bd..8e32cc494808 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -155,6 +155,22 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 		blk_finish_plug(&plug);
 }
 
+/**
+ * bio_blkcg_css - return the blkcg CSS associated with a bio
+ * @bio: target bio
+ *
+ * This returns the CSS for the blkcg associated with a bio, or %NULL if not
+ * associated. Callers are expected to either handle %NULL or know association
+ * has been done prior to calling this.
+ */
+struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio)
+{
+	if (!bio || !bio->bi_blkg)
+		return NULL;
+	return &bio->bi_blkg->blkcg->css;
+}
+EXPORT_SYMBOL_GPL(bio_blkcg_css);
+
 /**
  * blkcg_parent - get the parent of a blkcg
  * @blkcg: blkcg of interest
@@ -1938,7 +1954,7 @@ void bio_associate_blkg(struct bio *bio)
 	rcu_read_lock();
 
 	if (bio->bi_blkg)
-		css = &bio_blkcg(bio)->css;
+		css = bio_blkcg_css(bio);
 	else
 		css = blkcg_css();
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index b00fb1169e7c..03405ddf2a7b 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -25,6 +25,64 @@ struct blkg_policy_data;
 #define BLKG_STAT_CPU_BATCH	(INT_MAX / 2)
 
 #ifdef CONFIG_BLK_CGROUP
+
+enum blkg_iostat_type {
+	BLKG_IOSTAT_READ,
+	BLKG_IOSTAT_WRITE,
+	BLKG_IOSTAT_DISCARD,
+
+	BLKG_IOSTAT_NR,
+};
+
+struct blkg_iostat {
+	u64				bytes[BLKG_IOSTAT_NR];
+	u64				ios[BLKG_IOSTAT_NR];
+};
+
+struct blkg_iostat_set {
+	struct u64_stats_sync		sync;
+	struct blkg_iostat		cur;
+	struct blkg_iostat		last;
+};
+
+/* association between a blk cgroup and a request queue */
+struct blkcg_gq {
+	/* Pointer to the associated request_queue */
+	struct request_queue		*q;
+	struct list_head		q_node;
+	struct hlist_node		blkcg_node;
+	struct blkcg			*blkcg;
+
+	/* all non-root blkcg_gq's are guaranteed to have access to parent */
+	struct blkcg_gq			*parent;
+
+	/* reference count */
+	struct percpu_ref		refcnt;
+
+	/* is this blkg online? protected by both blkcg and q locks */
+	bool				online;
+
+	struct blkg_iostat_set __percpu	*iostat_cpu;
+	struct blkg_iostat_set		iostat;
+
+	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
+
+	spinlock_t			async_bio_lock;
+	struct bio_list			async_bios;
+	union {
+		struct work_struct	async_bio_work;
+		struct work_struct	free_work;
+	};
+
+	atomic_t			use_delay;
+	atomic64_t			delay_nsec;
+	atomic64_t			delay_start;
+	u64				last_delay;
+	int				last_use;
+
+	struct rcu_head			rcu_head;
+};
+
 struct blkcg {
 	struct cgroup_subsys_state	css;
 	spinlock_t			lock;
@@ -173,9 +231,9 @@ static inline struct cgroup_subsys_state *blkcg_css(void)
  *
  * In order to avoid priority inversions we sometimes need to issue a bio as if
  * it were attached to the root blkg, and then backcharge to the actual owning
- * blkg.  The idea is we do bio_blkcg() to look up the actual context for the
- * bio and attach the appropriate blkg to the bio.  Then we call this helper and
- * if it is true run with the root blkg for that queue and then do any
+ * blkg.  The idea is we do bio_blkcg_css() to look up the actual context for
+ * the bio and attach the appropriate blkg to the bio.  Then we call this helper
+ * and if it is true run with the root blkg for that queue and then do any
  * backcharging to the originating cgroup once the io is complete.
  */
 static inline bool bio_issue_as_root_blkg(struct bio *bio)
@@ -464,6 +522,9 @@ struct blkcg_policy_data {
 struct blkcg_policy {
 };
 
+struct blkcg {
+};
+
 #ifdef CONFIG_BLOCK
 
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 976cf987b392..fabcf647306a 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1829,12 +1829,14 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	cmd->blkcg_css = NULL;
 	cmd->memcg_css = NULL;
 #ifdef CONFIG_BLK_CGROUP
-	if (rq->bio && rq->bio->bi_blkg) {
-		cmd->blkcg_css = &bio_blkcg(rq->bio)->css;
+	if (rq->bio) {
+		cmd->blkcg_css = bio_blkcg_css(rq->bio);
 #ifdef CONFIG_MEMCG
-		cmd->memcg_css =
-			cgroup_get_e_css(cmd->blkcg_css->cgroup,
-					&memory_cgrp_subsys);
+		if (cmd->blkcg_css) {
+			cmd->memcg_css =
+				cgroup_get_e_css(cmd->blkcg_css->cgroup,
+						&memory_cgrp_subsys);
+		}
 #endif
 	}
 #endif
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index d7b188095040..97c7968e3204 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -28,94 +28,18 @@
 #define FC_APPID_LEN              129
 
 #ifdef CONFIG_BLK_CGROUP
-
-enum blkg_iostat_type {
-	BLKG_IOSTAT_READ,
-	BLKG_IOSTAT_WRITE,
-	BLKG_IOSTAT_DISCARD,
-
-	BLKG_IOSTAT_NR,
-};
-
-struct blkg_iostat {
-	u64				bytes[BLKG_IOSTAT_NR];
-	u64				ios[BLKG_IOSTAT_NR];
-};
-
-struct blkg_iostat_set {
-	struct u64_stats_sync		sync;
-	struct blkg_iostat		cur;
-	struct blkg_iostat		last;
-};
-
-/* association between a blk cgroup and a request queue */
-struct blkcg_gq {
-	/* Pointer to the associated request_queue */
-	struct request_queue		*q;
-	struct list_head		q_node;
-	struct hlist_node		blkcg_node;
-	struct blkcg			*blkcg;
-
-	/* all non-root blkcg_gq's are guaranteed to have access to parent */
-	struct blkcg_gq			*parent;
-
-	/* reference count */
-	struct percpu_ref		refcnt;
-
-	/* is this blkg online? protected by both blkcg and q locks */
-	bool				online;
-
-	struct blkg_iostat_set __percpu	*iostat_cpu;
-	struct blkg_iostat_set		iostat;
-
-	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
-
-	spinlock_t			async_bio_lock;
-	struct bio_list			async_bios;
-	union {
-		struct work_struct	async_bio_work;
-		struct work_struct	free_work;
-	};
-
-	atomic_t			use_delay;
-	atomic64_t			delay_nsec;
-	atomic64_t			delay_start;
-	u64				last_delay;
-	int				last_use;
-
-	struct rcu_head			rcu_head;
-};
-
 extern struct cgroup_subsys_state * const blkcg_root_css;
 
 void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
 void blkcg_maybe_throttle_current(void);
-
-/**
- * bio_blkcg - grab the blkcg associated with a bio
- * @bio: target bio
- *
- * This returns the blkcg associated with a bio, %NULL if not associated.
- * Callers are expected to either handle %NULL or know association has been
- * done prior to calling this.
- */
-static inline struct blkcg *bio_blkcg(struct bio *bio)
-{
-	if (bio && bio->bi_blkg)
-		return bio->bi_blkg->blkcg;
-	return NULL;
-}
-
 bool blk_cgroup_congested(void);
 void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css);
 void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css);
 struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio);
 
 #else	/* CONFIG_BLK_CGROUP */
 
-struct blkcg_gq {
-};
-
 #define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
 
 static inline void blkcg_maybe_throttle_current(void) { }
@@ -123,7 +47,10 @@ static inline bool blk_cgroup_congested(void) { return false; }
 
 #ifdef CONFIG_BLOCK
 static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
-static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
+static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio)
+{
+	return NULL;
+}
 #endif /* CONFIG_BLOCK */
 
 #endif	/* CONFIG_BLK_CGROUP */
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 9ef349ac49c0..10a32b0f2deb 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -783,6 +783,7 @@ void blk_trace_shutdown(struct request_queue *q)
 #ifdef CONFIG_BLK_CGROUP
 static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 {
+	struct cgroup_subsys_state *blkcg_css;
 	struct blk_trace *bt;
 
 	/* We don't use the 'bt' value here except as an optimization... */
@@ -790,9 +791,10 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 	if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
 		return 0;
 
-	if (!bio->bi_blkg)
+	blkcg_css = bio_blkcg_css(bio);
+	if (!blkcg_css)
 		return 0;
-	return cgroup_id(bio_blkcg(bio)->css.cgroup);
+	return cgroup_id(blkcg_css->cgroup);
 }
 #else
 static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
-- 
cgit v1.2.3


From 7f20ba7c42fd899557cef7d001f48711c3066ba5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:18 +0200
Subject: blk-cgroup: remove pointless CONFIG_BLOCK ifdefs

No need to make BLK_CGROUP stubs conditional on CONFIG_BLOCK as they
can't be used without that.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-11-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.h         | 3 ---
 include/linux/blk-cgroup.h | 4 ----
 2 files changed, 7 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 03405ddf2a7b..a948f4eb0bff 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -525,8 +525,6 @@ struct blkcg_policy {
 struct blkcg {
 };
 
-#ifdef CONFIG_BLOCK
-
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
 static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
 { return NULL; }
@@ -554,7 +552,6 @@ static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { r
 #define blk_queue_for_each_rl(rl, q)	\
 	for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)
 
-#endif	/* CONFIG_BLOCK */
 #endif	/* CONFIG_BLK_CGROUP */
 
 #endif /* _BLK_CGROUP_PRIVATE_H */
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 97c7968e3204..abbfa97d6d46 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -44,15 +44,11 @@ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio);
 
 static inline void blkcg_maybe_throttle_current(void) { }
 static inline bool blk_cgroup_congested(void) { return false; }
-
-#ifdef CONFIG_BLOCK
 static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
 static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio)
 {
 	return NULL;
 }
-#endif /* CONFIG_BLOCK */
-
 #endif	/* CONFIG_BLK_CGROUP */
 
 int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len);
-- 
cgit v1.2.3


From c97ab271576dec2170e7b804cb05f7617b30fed9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:19 +0200
Subject: blk-cgroup: remove unneeded includes from <linux/blk-cgroup.h>

Remove all the includes that aren't actually needed from
<linux/blk-cgroup.h> and push them to the actual source files where
needed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-12-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.h         |  2 ++
 include/linux/blk-cgroup.h | 15 +++++----------
 mm/backing-dev.c           |  1 +
 mm/readahead.c             |  1 +
 mm/swapfile.c              |  1 +
 5 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index a948f4eb0bff..62ed8ed50b6e 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -15,6 +15,8 @@
  */
 
 #include <linux/blk-cgroup.h>
+#include <linux/cgroup.h>
+#include <linux/kthread.h>
 #include <linux/blk-mq.h>
 
 struct blkcg_gq;
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index abbfa97d6d46..9f40dbc65f82 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -14,16 +14,11 @@
  * 	              Nauman Rafique <nauman@google.com>
  */
 
-#include <linux/cgroup.h>
-#include <linux/percpu.h>
-#include <linux/percpu_counter.h>
-#include <linux/u64_stats_sync.h>
-#include <linux/seq_file.h>
-#include <linux/radix-tree.h>
-#include <linux/blkdev.h>
-#include <linux/atomic.h>
-#include <linux/kthread.h>
-#include <linux/fs.h>
+#include <linux/types.h>
+
+struct bio;
+struct cgroup_subsys_state;
+struct request_queue;
 
 #define FC_APPID_LEN              129
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 98f8f62e52ca..ff60bd7d74e0 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <linux/blkdev.h>
 #include <linux/wait.h>
 #include <linux/rbtree.h>
 #include <linux/kthread.h>
diff --git a/mm/readahead.c b/mm/readahead.c
index 8e3775829513..c93671a2bf0f 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -113,6 +113,7 @@
  * ->readpage() which may be less efficient.
  */
 
+#include <linux/blkdev.h>
 #include <linux/kernel.h>
 #include <linux/dax.h>
 #include <linux/gfp.h>
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a2b31fea0c42..981a6e85c88e 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -6,6 +6,7 @@
  *  Swap reorganised 29.12.95, Stephen Tweedie
  */
 
+#include <linux/blkdev.h>
 #include <linux/mm.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/task.h>
-- 
cgit v1.2.3


From f624506f98b198e65b44da303f44974590fb16c0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Apr 2022 06:27:23 +0200
Subject: kthread: unexport kthread_blkcg

kthread_blkcg is only used by the built-in blk-cgroup code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-16-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/kthread.h | 4 ----
 kernel/kthread.c        | 1 -
 2 files changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index de5d75bafd66..30e5bec81d2b 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -222,9 +222,5 @@ void kthread_associate_blkcg(struct cgroup_subsys_state *css);
 struct cgroup_subsys_state *kthread_blkcg(void);
 #else
 static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { }
-static inline struct cgroup_subsys_state *kthread_blkcg(void)
-{
-	return NULL;
-}
 #endif
 #endif /* _LINUX_KTHREAD_H */
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 50265f69a135..544fd4097406 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1522,5 +1522,4 @@ struct cgroup_subsys_state *kthread_blkcg(void)
 	}
 	return NULL;
 }
-EXPORT_SYMBOL(kthread_blkcg);
 #endif
-- 
cgit v1.2.3


From d639af621600dc52dd9ed0dcf62b22595f2f5b52 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 22 Mar 2022 09:16:39 +0000
Subject: net/mlx5: fs, split software and IFC flow destination definitions

Separate flow destinations between software and IFC.
Flow destination type passed by callers was used as the input in
firmware commands and over the years software only types were added
which resulted in mixing between the two.

Create an IFC enum that contains only the flow destinations defined
when talking to the firmware.

Now that there is a proper software only enum for flow destinations
the hardcoded values can be removed as the values are no longer used
in firmware commands.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c         | 13 ++++++++++---
 .../net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c    | 16 ++++++++++++----
 include/linux/mlx5/fs.h                                  | 11 +++++++++++
 include/linux/mlx5/mlx5_ifc.h                            | 16 ++++++----------
 4 files changed, 39 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 33e9f86cf7d4..a5662cb46660 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -571,7 +571,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 		int list_size = 0;
 
 		list_for_each_entry(dst, &fte->node.children, node.list) {
-			unsigned int id, type = dst->dest_attr.type;
+			enum mlx5_flow_destination_type type = dst->dest_attr.type;
+			enum mlx5_ifc_flow_destination_type ifc_type;
+			unsigned int id;
 
 			if (type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
 				continue;
@@ -579,10 +581,11 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			switch (type) {
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
 				id = dst->dest_attr.ft_num;
-				type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 				break;
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
 				id = dst->dest_attr.ft->id;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 				break;
 			case MLX5_FLOW_DESTINATION_TYPE_UPLINK:
 			case MLX5_FLOW_DESTINATION_TYPE_VPORT:
@@ -596,8 +599,10 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				if (type == MLX5_FLOW_DESTINATION_TYPE_UPLINK) {
 					/* destination_id is reserved */
 					id = 0;
+					ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK;
 					break;
 				}
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT;
 				id = dst->dest_attr.vport.num;
 				if (extended_dest &&
 				    dst->dest_attr.vport.pkt_reformat) {
@@ -612,13 +617,15 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				break;
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
 				id = dst->dest_attr.sampler_id;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
 				break;
 			default:
 				id = dst->dest_attr.tir_num;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_TIR;
 			}
 
 			MLX5_SET(dest_format_struct, in_dests, destination_type,
-				 type);
+				 ifc_type);
 			MLX5_SET(dest_format_struct, in_dests, destination_id, id);
 			in_dests += dst_cnt_size;
 			list_size++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
index 4dd619d238cc..728ccb950fec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -311,7 +311,7 @@ int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev,
 
 	in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination);
 	MLX5_SET(dest_format_struct, in_dests, destination_type,
-		 MLX5_FLOW_DESTINATION_TYPE_VPORT);
+		 MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT);
 	MLX5_SET(dest_format_struct, in_dests, destination_id, vport);
 
 	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
@@ -719,7 +719,9 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
 		int list_size = 0;
 
 		for (i = 0; i < fte->dests_size; i++) {
-			unsigned int id, type = fte->dest_arr[i].type;
+			enum mlx5_flow_destination_type type = fte->dest_arr[i].type;
+			enum mlx5_ifc_flow_destination_type ifc_type;
+			unsigned int id;
 
 			if (type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
 				continue;
@@ -727,10 +729,12 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
 			switch (type) {
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
 				id = fte->dest_arr[i].ft_num;
-				type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 				break;
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
 				id = fte->dest_arr[i].ft_id;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+
 				break;
 			case MLX5_FLOW_DESTINATION_TYPE_UPLINK:
 			case MLX5_FLOW_DESTINATION_TYPE_VPORT:
@@ -740,8 +744,10 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
 						 destination_eswitch_owner_vhca_id_valid,
 						 !!(fte->dest_arr[i].vport.flags &
 						    MLX5_FLOW_DEST_VPORT_VHCA_ID));
+					ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT;
 				} else {
 					id = 0;
+					ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK;
 					MLX5_SET(dest_format_struct, in_dests,
 						 destination_eswitch_owner_vhca_id_valid, 1);
 				}
@@ -761,13 +767,15 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
 				break;
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
 				id = fte->dest_arr[i].sampler_id;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
 				break;
 			default:
 				id = fte->dest_arr[i].tir_num;
+				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_TIR;
 			}
 
 			MLX5_SET(dest_format_struct, in_dests, destination_type,
-				 type);
+				 ifc_type);
 			MLX5_SET(dest_format_struct, in_dests, destination_id, id);
 			in_dests += dst_cnt_size;
 			list_size++;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index e3bfed68b08a..9da9df9ae751 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -40,6 +40,17 @@
 
 #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
 
+enum mlx5_flow_destination_type {
+	MLX5_FLOW_DESTINATION_TYPE_VPORT,
+	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE,
+	MLX5_FLOW_DESTINATION_TYPE_TIR,
+	MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER,
+	MLX5_FLOW_DESTINATION_TYPE_UPLINK,
+	MLX5_FLOW_DESTINATION_TYPE_PORT,
+	MLX5_FLOW_DESTINATION_TYPE_COUNTER,
+	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM,
+};
+
 enum {
 	MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO	= 1 << 16,
 	MLX5_FLOW_CONTEXT_ACTION_ENCRYPT	= 1 << 17,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 7d2d0ba82144..7f4ec9faa180 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1806,16 +1806,12 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_c0[0x740];
 };
 
-enum mlx5_flow_destination_type {
-	MLX5_FLOW_DESTINATION_TYPE_VPORT        = 0x0,
-	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE   = 0x1,
-	MLX5_FLOW_DESTINATION_TYPE_TIR          = 0x2,
-	MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
-	MLX5_FLOW_DESTINATION_TYPE_UPLINK       = 0x8,
-
-	MLX5_FLOW_DESTINATION_TYPE_PORT         = 0x99,
-	MLX5_FLOW_DESTINATION_TYPE_COUNTER      = 0x100,
-	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101,
+enum mlx5_ifc_flow_destination_type {
+	MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT        = 0x0,
+	MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE   = 0x1,
+	MLX5_IFC_FLOW_DESTINATION_TYPE_TIR          = 0x2,
+	MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
+	MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK       = 0x8,
 };
 
 enum mlx5_flow_table_miss_action {
-- 
cgit v1.2.3


From 6510bc0d7cb4119ebe10f9ab43aca6fd0e5f3e73 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 15 Mar 2022 14:08:23 +0000
Subject: net/mlx5: fs, add unused destination type

When the caller doesn't pass a destination fs_core will create a unused
rule just so a context can be returned. This unused rule
is zeroed out and its type is 0 which can be mixed up with
MLX5_FLOW_DESTINATION_TYPE_VPORT.

Create a dedicated type to differentiate between the two
named MLX5_FLOW_DESTINATION_TYPE_NONE.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c             | 5 ++++-
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c            | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c    | 5 ++++-
 include/linux/mlx5/fs.h                                      | 1 +
 5 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
index 7841ef6c193c..c5bb79a4fa57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
@@ -259,6 +259,9 @@ const char *parse_fs_dst(struct trace_seq *p,
 	case MLX5_FLOW_DESTINATION_TYPE_PORT:
 		trace_seq_printf(p, "port\n");
 		break;
+	case MLX5_FLOW_DESTINATION_TYPE_NONE:
+		trace_seq_printf(p, "none\n");
+		break;
 	}
 
 	trace_seq_putc(p, 0);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index a5662cb46660..2ccf7bef9b05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -455,7 +455,8 @@ static int mlx5_set_extended_dest(struct mlx5_core_dev *dev,
 		return 0;
 
 	list_for_each_entry(dst, &fte->node.children, node.list) {
-		if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+		if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER ||
+		    dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_NONE)
 			continue;
 		if ((dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_VPORT ||
 		     dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_UPLINK) &&
@@ -579,6 +580,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				continue;
 
 			switch (type) {
+			case MLX5_FLOW_DESTINATION_TYPE_NONE:
+				continue;
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
 				id = dst->dest_attr.ft_num;
 				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index e282d80f1fd2..f9d6ddd865e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1289,6 +1289,8 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest)
 	rule->node.type = FS_TYPE_FLOW_DEST;
 	if (dest)
 		memcpy(&rule->dest_attr, dest, sizeof(*dest));
+	else
+		rule->dest_attr.type = MLX5_FLOW_DESTINATION_TYPE_NONE;
 
 	return rule;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
index 728ccb950fec..223c8741b7ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -604,7 +604,8 @@ static int mlx5dr_cmd_set_extended_dest(struct mlx5_core_dev *dev,
 	if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
 		return 0;
 	for (i = 0; i < fte->dests_size; i++) {
-		if (fte->dest_arr[i].type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+		if (fte->dest_arr[i].type == MLX5_FLOW_DESTINATION_TYPE_COUNTER ||
+		    fte->dest_arr[i].type == MLX5_FLOW_DESTINATION_TYPE_NONE)
 			continue;
 		if ((fte->dest_arr[i].type == MLX5_FLOW_DESTINATION_TYPE_VPORT ||
 		     fte->dest_arr[i].type == MLX5_FLOW_DESTINATION_TYPE_UPLINK) &&
@@ -727,6 +728,8 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev,
 				continue;
 
 			switch (type) {
+			case MLX5_FLOW_DESTINATION_TYPE_NONE:
+				continue;
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
 				id = fte->dest_arr[i].ft_num;
 				ifc_type = MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 9da9df9ae751..8135713b0d2d 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -41,6 +41,7 @@
 #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
 
 enum mlx5_flow_destination_type {
+	MLX5_FLOW_DESTINATION_TYPE_NONE,
 	MLX5_FLOW_DESTINATION_TYPE_VPORT,
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE,
 	MLX5_FLOW_DESTINATION_TYPE_TIR,
-- 
cgit v1.2.3


From c9bc1a0ef9f613a7bc1adfff4c67dc5e5d7d1709 Mon Sep 17 00:00:00 2001
From: "Dustin L. Howett" <dustin@howett.net>
Date: Thu, 17 Feb 2022 10:59:30 -0600
Subject: platform/chrome: cros_ec_lpcs: reserve the MEC LPC I/O ports first

Some ChromeOS EC devices (such as the Framework Laptop) only map I/O
ports 0x800-0x807. Making the larger reservation required by the non-MEC
LPC (the 0xFF ports for the memory map, and the 0xFF ports for the
parameter region) is non-viable on these devices.

Since we probe the MEC EC first, we can get away with a smaller
reservation that covers the MEC EC ports. If we fall back to classic
LPC, we can grow the reservation to cover the memory map and the
parameter region.

cros_ec_lpc_probe also interacted with I/O ports 0x800-0x807 without a
reservation. Restructuring the code to request the MEC LPC region first
obviates the need to do so.

Signed-off-by: Dustin L. Howett <dustin@howett.net>
Signed-off-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20220217165930.15081-3-dustin@howett.net
---
 drivers/platform/chrome/cros_ec_lpc.c          | 39 +++++++++++++++++---------
 include/linux/platform_data/cros_ec_commands.h | 10 +++++--
 2 files changed, 33 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
index 1ec12d19c779..8eeef85a96b1 100644
--- a/drivers/platform/chrome/cros_ec_lpc.c
+++ b/drivers/platform/chrome/cros_ec_lpc.c
@@ -341,9 +341,14 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
 	u8 buf[2];
 	int irq, ret;
 
-	if (!devm_request_region(dev, EC_LPC_ADDR_MEMMAP, EC_MEMMAP_SIZE,
-				 dev_name(dev))) {
-		dev_err(dev, "couldn't reserve memmap region\n");
+	/*
+	 * The Framework Laptop (and possibly other non-ChromeOS devices)
+	 * only exposes the eight I/O ports that are required for the Microchip EC.
+	 * Requesting a larger reservation will fail.
+	 */
+	if (!devm_request_region(dev, EC_HOST_CMD_REGION0,
+				 EC_HOST_CMD_MEC_REGION_SIZE, dev_name(dev))) {
+		dev_err(dev, "couldn't reserve MEC region\n");
 		return -EBUSY;
 	}
 
@@ -357,6 +362,12 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
 	cros_ec_lpc_ops.write = cros_ec_lpc_mec_write_bytes;
 	cros_ec_lpc_ops.read(EC_LPC_ADDR_MEMMAP + EC_MEMMAP_ID, 2, buf);
 	if (buf[0] != 'E' || buf[1] != 'C') {
+		if (!devm_request_region(dev, EC_LPC_ADDR_MEMMAP, EC_MEMMAP_SIZE,
+					 dev_name(dev))) {
+			dev_err(dev, "couldn't reserve memmap region\n");
+			return -EBUSY;
+		}
+
 		/* Re-assign read/write operations for the non MEC variant */
 		cros_ec_lpc_ops.read = cros_ec_lpc_read_bytes;
 		cros_ec_lpc_ops.write = cros_ec_lpc_write_bytes;
@@ -366,17 +377,19 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
 			dev_err(dev, "EC ID not detected\n");
 			return -ENODEV;
 		}
-	}
 
-	if (!devm_request_region(dev, EC_HOST_CMD_REGION0,
-				 EC_HOST_CMD_REGION_SIZE, dev_name(dev))) {
-		dev_err(dev, "couldn't reserve region0\n");
-		return -EBUSY;
-	}
-	if (!devm_request_region(dev, EC_HOST_CMD_REGION1,
-				 EC_HOST_CMD_REGION_SIZE, dev_name(dev))) {
-		dev_err(dev, "couldn't reserve region1\n");
-		return -EBUSY;
+		/* Reserve the remaining I/O ports required by the non-MEC protocol. */
+		if (!devm_request_region(dev, EC_HOST_CMD_REGION0 + EC_HOST_CMD_MEC_REGION_SIZE,
+					 EC_HOST_CMD_REGION_SIZE - EC_HOST_CMD_MEC_REGION_SIZE,
+					 dev_name(dev))) {
+			dev_err(dev, "couldn't reserve remainder of region0\n");
+			return -EBUSY;
+		}
+		if (!devm_request_region(dev, EC_HOST_CMD_REGION1,
+					 EC_HOST_CMD_REGION_SIZE, dev_name(dev))) {
+			dev_err(dev, "couldn't reserve region1\n");
+			return -EBUSY;
+		}
 	}
 
 	ec_dev = devm_kzalloc(dev, sizeof(*ec_dev), GFP_KERNEL);
diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index c23554531961..8cfa8cfca77e 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -51,10 +51,14 @@
 /*
  * The actual block is 0x800-0x8ff, but some BIOSes think it's 0x880-0x8ff
  * and they tell the kernel that so we have to think of it as two parts.
+ *
+ * Other BIOSes report only the I/O port region spanned by the Microchip
+ * MEC series EC; an attempt to address a larger region may fail.
  */
-#define EC_HOST_CMD_REGION0    0x800
-#define EC_HOST_CMD_REGION1    0x880
-#define EC_HOST_CMD_REGION_SIZE 0x80
+#define EC_HOST_CMD_REGION0       0x800
+#define EC_HOST_CMD_REGION1       0x880
+#define EC_HOST_CMD_REGION_SIZE    0x80
+#define EC_HOST_CMD_MEC_REGION_SIZE 0x8
 
 /* EC command register bit functions */
 #define EC_LPC_CMDR_DATA	BIT(0)  /* Data ready for host to read */
-- 
cgit v1.2.3


From 4c7f24f857c7cd0381dd92495db476066d1c6aec Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Sun, 1 May 2022 11:55:23 +0800
Subject: net: sysctl: introduce sysctl SYSCTL_THREE

This patch introdues the SYSCTL_THREE.

KUnit:
[00:10:14] ================ sysctl_test (10 subtests) =================
[00:10:14] [PASSED] sysctl_test_api_dointvec_null_tbl_data
[00:10:14] [PASSED] sysctl_test_api_dointvec_table_maxlen_unset
[00:10:14] [PASSED] sysctl_test_api_dointvec_table_len_is_zero
[00:10:14] [PASSED] sysctl_test_api_dointvec_table_read_but_position_set
[00:10:14] [PASSED] sysctl_test_dointvec_read_happy_single_positive
[00:10:14] [PASSED] sysctl_test_dointvec_read_happy_single_negative
[00:10:14] [PASSED] sysctl_test_dointvec_write_happy_single_positive
[00:10:14] [PASSED] sysctl_test_dointvec_write_happy_single_negative
[00:10:14] [PASSED] sysctl_test_api_dointvec_write_single_less_int_min
[00:10:14] [PASSED] sysctl_test_api_dointvec_write_single_greater_int_max
[00:10:14] =================== [PASSED] sysctl_test ===================

./run_kselftest.sh -c sysctl
...
ok 1 selftests: sysctl: sysctl.sh

Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: David Ahern <dsahern@kernel.org>
Cc: Simon Horman <horms@verge.net.au>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Jozsef Kadlecsik <kadlec@netfilter.org>
Cc: Florian Westphal <fw@strlen.de>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Lorenz Bauer <lmb@cloudflare.com>
Cc: Akhmat Karakotov <hmukos@yandex-team.ru>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 fs/proc/proc_sysctl.c          | 2 +-
 include/linux/sysctl.h         | 9 +++++----
 net/core/sysctl_net_core.c     | 3 +--
 net/ipv4/sysctl_net_ipv4.c     | 3 +--
 net/ipv6/sysctl_net_ipv6.c     | 3 +--
 net/netfilter/ipvs/ip_vs_ctl.c | 4 +---
 6 files changed, 10 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 7d9cfc730bd4..5851c2a92c0d 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -26,7 +26,7 @@ static const struct file_operations proc_sys_dir_file_operations;
 static const struct inode_operations proc_sys_dir_operations;
 
 /* shared constants to be used in various sysctls */
-const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX, 65535 };
+const int sysctl_vals[] = { 0, 1, 2, 3, 4, 100, 200, 1000, 3000, INT_MAX, 65535, -1 };
 EXPORT_SYMBOL(sysctl_vals);
 
 const unsigned long sysctl_long_vals[] = { 0, 1, LONG_MAX };
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 6353d6db69b2..80263f7cdb77 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -38,10 +38,10 @@ struct ctl_table_header;
 struct ctl_dir;
 
 /* Keep the same order as in fs/proc/proc_sysctl.c */
-#define SYSCTL_NEG_ONE			((void *)&sysctl_vals[0])
-#define SYSCTL_ZERO			((void *)&sysctl_vals[1])
-#define SYSCTL_ONE			((void *)&sysctl_vals[2])
-#define SYSCTL_TWO			((void *)&sysctl_vals[3])
+#define SYSCTL_ZERO			((void *)&sysctl_vals[0])
+#define SYSCTL_ONE			((void *)&sysctl_vals[1])
+#define SYSCTL_TWO			((void *)&sysctl_vals[2])
+#define SYSCTL_THREE			((void *)&sysctl_vals[3])
 #define SYSCTL_FOUR			((void *)&sysctl_vals[4])
 #define SYSCTL_ONE_HUNDRED		((void *)&sysctl_vals[5])
 #define SYSCTL_TWO_HUNDRED		((void *)&sysctl_vals[6])
@@ -51,6 +51,7 @@ struct ctl_dir;
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 #define SYSCTL_MAXOLDUID		((void *)&sysctl_vals[10])
+#define SYSCTL_NEG_ONE			((void *)&sysctl_vals[11])
 
 extern const int sysctl_vals[];
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 3a0ce309ffcd..195ca5c28771 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -25,7 +25,6 @@
 
 #include "dev.h"
 
-static int three = 3;
 static int int_3600 = 3600;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
@@ -553,7 +552,7 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &three,
+		.extra2		= SYSCTL_THREE,
 	},
 	{
 		.procname	= "high_order_alloc_disable",
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9ff60a389cd0..cd448cdd3b38 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -20,7 +20,6 @@
 #include <net/protocol.h>
 #include <net/netevent.h>
 
-static int three __maybe_unused = 3;
 static int tcp_retr1_max = 255;
 static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
@@ -1056,7 +1055,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_fib_multipath_hash_policy,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &three,
+		.extra2		= SYSCTL_THREE,
 	},
 	{
 		.procname	= "fib_multipath_hash_fields",
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 560c48d0ddb7..94a0a294c6a1 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -23,7 +23,6 @@
 #endif
 #include <linux/ioam6.h>
 
-static int three = 3;
 static int flowlabel_reflect_max = 0x7;
 static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
 static u32 rt6_multipath_hash_fields_all_mask =
@@ -171,7 +170,7 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler   = proc_rt6_multipath_hash_policy,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &three,
+		.extra2		= SYSCTL_THREE,
 	},
 	{
 		.procname	= "fib_multipath_hash_fields",
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 7f645328b47f..efab2b06d373 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1767,8 +1767,6 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs)
 
 #ifdef CONFIG_SYSCTL
 
-static int three = 3;
-
 static int
 proc_do_defense_mode(struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos)
@@ -1977,7 +1975,7 @@ static struct ctl_table vs_vars[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &three,
+		.extra2		= SYSCTL_THREE,
 	},
 	{
 		.procname	= "nat_icmp_send",
-- 
cgit v1.2.3


From 62139f52b7e588d565aa9df81ea0a0548a68b823 Mon Sep 17 00:00:00 2001
From: Per-Daniel Olsson <perdo@axis.com>
Date: Fri, 29 Apr 2022 09:22:08 +0200
Subject: regulator: pca9450: Make I2C Level Translator configurable

Make the I2C Level Translator included in PCA9450 configurable from
devicetree. The reset state is off. By setting nxp,i2c-lt-enable, the
I2C Level Translator will be enabled while in STANDBY or RUN state.

Signed-off-by: Per-Daniel Olsson <perdo@axis.com>
Signed-off-by: Rickard x Andersson <rickaran@axis.com>
Link: https://lore.kernel.org/r/20220429072211.24957-2-rickaran@axis.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pca9450-regulator.c | 11 +++++++++++
 include/linux/regulator/pca9450.h     |  7 +++++++
 2 files changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index 64e5f5f0cc84..87b4e6e29ba1 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -810,6 +810,17 @@ static int pca9450_i2c_probe(struct i2c_client *i2c,
 		return ret;
 	}
 
+	if (of_property_read_bool(i2c->dev.of_node, "nxp,i2c-lt-enable")) {
+		/* Enable I2C Level Translator */
+		ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_CONFIG2,
+					 I2C_LT_MASK, I2C_LT_ON_STANDBY_RUN);
+		if (ret) {
+			dev_err(&i2c->dev,
+				"Failed to enable I2C level translator\n");
+			return ret;
+		}
+	}
+
 	/*
 	 * The driver uses the LDO5CTRL_H register to control the LDO5 regulator.
 	 * This is only valid if the SD_VSEL input of the PMIC is high. Let's
diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h
index 71902f41c919..3c01c2bf84f5 100644
--- a/include/linux/regulator/pca9450.h
+++ b/include/linux/regulator/pca9450.h
@@ -226,4 +226,11 @@ enum {
 #define WDOG_B_CFG_COLD_LDO12		0x80
 #define WDOG_B_CFG_COLD			0xC0
 
+/* PCA9450_REG_CONFIG2 bits */
+#define I2C_LT_MASK			0x03
+#define I2C_LT_FORCE_DISABLE		0x00
+#define I2C_LT_ON_STANDBY_RUN		0x01
+#define I2C_LT_ON_RUN			0x02
+#define I2C_LT_FORCE_ENABLE		0x03
+
 #endif /* __LINUX_REG_PCA9450_H__ */
-- 
cgit v1.2.3


From 1dcbae86ee669bdb0338954cd0136863f5c96c0a Mon Sep 17 00:00:00 2001
From: Dave Gerlach <d-gerlach@ti.com>
Date: Thu, 14 Apr 2022 12:27:24 -0700
Subject: soc: ti: wkup_m3_ipc: Add support for IO Isolation

AM43xx support isolation of the IOs so that control is taken
from the peripheral they are connected to and overridden by values
present in the CTRL_CONF_* registers for the pad in the control module.

The actual toggling happens from the wkup_m3, so use a DT property from
the wkup_m3_ipc node to allow the PM code to communicate the necessity
for placing the IOs into isolation to the firmware.

Signed-off-by: Dave Gerlach <d-gerlach@ti.com>
Signed-off-by: Keerthy <j-keerthy@ti.com>
Signed-off-by: Drew Fustini <dfustini@baylibre.com>
Signed-off-by: Nishanth Menon <nm@ti.com>
Link: https://lore.kernel.org/r/20220414192722.2978837-3-dfustini@baylibre.com
---
 drivers/soc/ti/wkup_m3_ipc.c | 14 ++++++++++++--
 include/linux/wkup_m3_ipc.h  |  1 +
 2 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index 48659758228e..2f2a0ab32aff 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -46,6 +46,8 @@
 #define IPC_VTT_STAT_MASK		(0x1 << 3)
 #define IPC_VTT_GPIO_PIN_SHIFT		(0x4)
 #define IPC_VTT_GPIO_PIN_MASK		(0x3f << 4)
+#define IPC_IO_ISOLATION_STAT_SHIFT	(10)
+#define IPC_IO_ISOLATION_STAT_MASK	(0x1 << 10)
 
 #define M3_STATE_UNKNOWN		0
 #define M3_STATE_RESET			1
@@ -228,6 +230,11 @@ static void wkup_m3_set_vtt_gpio(struct wkup_m3_ipc *m3_ipc, int gpio)
 			    (gpio << IPC_VTT_GPIO_PIN_SHIFT);
 }
 
+static void wkup_m3_set_io_isolation(struct wkup_m3_ipc *m3_ipc)
+{
+	m3_ipc->isolation_conf = (1 << IPC_IO_ISOLATION_STAT_SHIFT);
+}
+
 /* Public functions */
 /**
  * wkup_m3_set_mem_type - Pass wkup_m3 which type of memory is in use
@@ -308,8 +315,8 @@ static int wkup_m3_prepare_low_power(struct wkup_m3_ipc *m3_ipc, int state)
 	wkup_m3_ctrl_ipc_write(m3_ipc, m3_ipc->resume_addr, 0);
 	wkup_m3_ctrl_ipc_write(m3_ipc, m3_power_state, 1);
 	wkup_m3_ctrl_ipc_write(m3_ipc, m3_ipc->mem_type |
-			       m3_ipc->vtt_conf, 4);
-
+			       m3_ipc->vtt_conf |
+			       m3_ipc->isolation_conf, 4);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 2);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 3);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 5);
@@ -516,6 +523,9 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev)
 			dev_warn(dev, "Invalid VTT GPIO(%d) pin\n", temp);
 	}
 
+	if (of_find_property(np, "ti,set-io-isolation", NULL))
+		wkup_m3_set_io_isolation(m3_ipc);
+
 	/*
 	 * Wait for firmware loading completion in a thread so we
 	 * can boot the wkup_m3 as soon as it's ready without holding
diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h
index 2bc52c6381d5..b706eac58f92 100644
--- a/include/linux/wkup_m3_ipc.h
+++ b/include/linux/wkup_m3_ipc.h
@@ -34,6 +34,7 @@ struct wkup_m3_ipc {
 	int mem_type;
 	unsigned long resume_addr;
 	int vtt_conf;
+	int isolation_conf;
 	int state;
 
 	struct completion sync_complete;
-- 
cgit v1.2.3


From ea082040fe071d2ba1f8f73792743d7ca9fb218e Mon Sep 17 00:00:00 2001
From: Dave Gerlach <d-gerlach@ti.com>
Date: Tue, 26 Apr 2022 13:07:44 -0700
Subject: soc: ti: wkup_m3_ipc: Add support for i2c voltage scaling

Allow loading of a binary containing i2c scaling sequences to be
provided to the wkup_m3 firmware in order to properly scale voltage
rails on the PMIC during low power modes like DeepSleep0. Proper binary
format is determined by the FW in use.

Code expects firmware to have 0x0C57 present as the first two bytes
followed by one byte defining offset to sleep sequence followed by one
byte defining offset to wake sequence and then lastly both sequences.
Each sequence is a series of I2C transfers in the form:

u8 length | u8 chip address | u8 byte0/reg address | u8 byte1 | u8 byteN
..

The length indicates the number of bytes to transfer, including the
register address. The length of each transfer is limited by the I2C
buffer size of 32 bytes.

Based on previous work by Russ Dill.

[dfustini: replace FW_ACTION_HOTPLUG with FW_ACTION_UEVENT]

Signed-off-by: Dave Gerlach <d-gerlach@ti.com>
Signed-off-by: Keerthy <j-keerthy@ti.com>
[dfustini: add NULL argument to rproc_da_to_va() call]
Signed-off-by: Drew Fustini <dfustini@baylibre.com>
Signed-off-by: Nishanth Menon <nm@ti.com>
Link: https://lore.kernel.org/r/20220426200741.712842-3-dfustini@baylibre.com
---
 drivers/soc/ti/wkup_m3_ipc.c | 93 +++++++++++++++++++++++++++++++++++++++++++-
 include/linux/wkup_m3_ipc.h  |  9 +++++
 2 files changed, 101 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index 2f2a0ab32aff..84e9534056f8 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/err.h>
+#include <linux/firmware.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
 #include <linux/interrupt.h>
@@ -55,6 +56,12 @@
 #define M3_STATE_MSG_FOR_LP		3
 #define M3_STATE_MSG_FOR_RESET		4
 
+#define WKUP_M3_SD_FW_MAGIC		0x570C
+
+#define WKUP_M3_DMEM_START		0x80000
+#define WKUP_M3_AUXDATA_OFFSET		0x1000
+#define WKUP_M3_AUXDATA_SIZE		0xFF
+
 static struct wkup_m3_ipc *m3_ipc_state;
 
 static const struct wkup_m3_wakeup_src wakeups[] = {
@@ -75,6 +82,81 @@ static const struct wkup_m3_wakeup_src wakeups[] = {
 	{.irq_nr = 0,	.src = "Unknown"},
 };
 
+/**
+ * wkup_m3_copy_aux_data - Copy auxiliary data to special region of m3 dmem
+ * @data - pointer to data
+ * @sz - size of data to copy (limit 256 bytes)
+ *
+ * Copies any additional blob of data to the wkup_m3 dmem to be used by the
+ * firmware
+ */
+static unsigned long wkup_m3_copy_aux_data(struct wkup_m3_ipc *m3_ipc,
+					   const void *data, int sz)
+{
+	unsigned long aux_data_dev_addr;
+	void *aux_data_addr;
+
+	aux_data_dev_addr = WKUP_M3_DMEM_START + WKUP_M3_AUXDATA_OFFSET;
+	aux_data_addr = rproc_da_to_va(m3_ipc->rproc,
+				       aux_data_dev_addr,
+				       WKUP_M3_AUXDATA_SIZE,
+				       NULL);
+	memcpy(aux_data_addr, data, sz);
+
+	return WKUP_M3_AUXDATA_OFFSET;
+}
+
+static void wkup_m3_scale_data_fw_cb(const struct firmware *fw, void *context)
+{
+	unsigned long val, aux_base;
+	struct wkup_m3_scale_data_header hdr;
+	struct wkup_m3_ipc *m3_ipc = context;
+	struct device *dev = m3_ipc->dev;
+
+	if (!fw) {
+		dev_err(dev, "Voltage scale fw name given but file missing.\n");
+		return;
+	}
+
+	memcpy(&hdr, fw->data, sizeof(hdr));
+
+	if (hdr.magic != WKUP_M3_SD_FW_MAGIC) {
+		dev_err(dev, "PM: Voltage Scale Data binary does not appear valid.\n");
+		goto release_sd_fw;
+	}
+
+	aux_base = wkup_m3_copy_aux_data(m3_ipc, fw->data + sizeof(hdr),
+					 fw->size - sizeof(hdr));
+
+	val = (aux_base + hdr.sleep_offset);
+	val |= ((aux_base + hdr.wake_offset) << 16);
+
+	m3_ipc->volt_scale_offsets = val;
+
+release_sd_fw:
+	release_firmware(fw);
+};
+
+static int wkup_m3_init_scale_data(struct wkup_m3_ipc *m3_ipc,
+				   struct device *dev)
+{
+	int ret = 0;
+
+	/*
+	 * If no name is provided, user has already been warned, pm will
+	 * still work so return 0
+	 */
+
+	if (!m3_ipc->sd_fw_name)
+		return ret;
+
+	ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT,
+				      m3_ipc->sd_fw_name, dev, GFP_ATOMIC,
+				      m3_ipc, wkup_m3_scale_data_fw_cb);
+
+	return ret;
+}
+
 static void am33xx_txev_eoi(struct wkup_m3_ipc *m3_ipc)
 {
 	writel(AM33XX_M3_TXEV_ACK,
@@ -139,6 +221,7 @@ static irqreturn_t wkup_m3_txev_handler(int irq, void *ipc_data)
 		}
 
 		m3_ipc->state = M3_STATE_INITED;
+		wkup_m3_init_scale_data(m3_ipc, dev);
 		complete(&m3_ipc->sync_complete);
 		break;
 	case M3_STATE_MSG_FOR_RESET:
@@ -300,12 +383,15 @@ static int wkup_m3_prepare_low_power(struct wkup_m3_ipc *m3_ipc, int state)
 	switch (state) {
 	case WKUP_M3_DEEPSLEEP:
 		m3_power_state = IPC_CMD_DS0;
+		wkup_m3_ctrl_ipc_write(m3_ipc, m3_ipc->volt_scale_offsets, 5);
 		break;
 	case WKUP_M3_STANDBY:
 		m3_power_state = IPC_CMD_STANDBY;
+		wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 5);
 		break;
 	case WKUP_M3_IDLE:
 		m3_power_state = IPC_CMD_IDLE;
+		wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 5);
 		break;
 	default:
 		return 1;
@@ -319,7 +405,6 @@ static int wkup_m3_prepare_low_power(struct wkup_m3_ipc *m3_ipc, int state)
 			       m3_ipc->isolation_conf, 4);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 2);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 3);
-	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 5);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 6);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 7);
 
@@ -526,6 +611,12 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev)
 	if (of_find_property(np, "ti,set-io-isolation", NULL))
 		wkup_m3_set_io_isolation(m3_ipc);
 
+	ret = of_property_read_string(np, "firmware-name",
+				      &m3_ipc->sd_fw_name);
+	if (ret) {
+		dev_dbg(dev, "Voltage scaling data blob not provided from DT.\n");
+	};
+
 	/*
 	 * Wait for firmware loading completion in a thread so we
 	 * can boot the wkup_m3 as soon as it's ready without holding
diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h
index b706eac58f92..fef0fac60f8c 100644
--- a/include/linux/wkup_m3_ipc.h
+++ b/include/linux/wkup_m3_ipc.h
@@ -37,6 +37,9 @@ struct wkup_m3_ipc {
 	int isolation_conf;
 	int state;
 
+	unsigned long volt_scale_offsets;
+	const char *sd_fw_name;
+
 	struct completion sync_complete;
 	struct mbox_client mbox_client;
 	struct mbox_chan *mbox;
@@ -50,6 +53,12 @@ struct wkup_m3_wakeup_src {
 	char src[10];
 };
 
+struct wkup_m3_scale_data_header {
+	u16 magic;
+	u8 sleep_offset;
+	u8 wake_offset;
+} __packed;
+
 struct wkup_m3_ipc_ops {
 	void (*set_mem_type)(struct wkup_m3_ipc *m3_ipc, int mem_type);
 	void (*set_resume_address)(struct wkup_m3_ipc *m3_ipc, void *addr);
-- 
cgit v1.2.3


From 2a21f9e6d9a408dbd09a01caf5fff42c2f70fa82 Mon Sep 17 00:00:00 2001
From: Dave Gerlach <d-gerlach@ti.com>
Date: Sun, 1 May 2022 20:32:12 -0700
Subject: soc: ti: wkup_m3_ipc: Add debug option to halt m3 in suspend

Add a debugfs option to allow configurable halting of the wkup_m3
during suspend at the last possible point before low power mode entry.
This condition can only be resolved through JTAG and advancing beyond
the while loop in a8_lp_ds0_handler [1]. Although this hangs the system
it forces the system to remain active once it has been entirely
configured for low power mode entry, allowing for register inspection
through JTAG to help in debugging transition errors.

Halt mode can be set using the enable_off_mode entry under wkup_m3_ipc
in the debugfs.

[1] https://git.ti.com/cgit/processor-firmware/ti-amx3-cm3-pm-firmware/tree/src/pm_services/pm_handlers.c?h=08.02.00.006#n141

Suggested-by: Brad Griffis <bgriffis@ti.com>
Signed-off-by: Dave Gerlach <d-gerlach@ti.com>
[dfustini: add link for a8_lp_ds0_handler() in ti-amx3-cm3-pm-firmware]
Signed-off-by: Drew Fustini <dfustini@baylibre.com>
Signed-off-by: Nishanth Menon <nm@ti.com>
Link: https://lore.kernel.org/r/20220502033211.1383158-1-dfustini@baylibre.com
---
 drivers/soc/ti/wkup_m3_ipc.c | 79 +++++++++++++++++++++++++++++++++++++++++++-
 include/linux/wkup_m3_ipc.h  |  2 ++
 2 files changed, 80 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index 84e9534056f8..0076d467ff6b 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -7,6 +7,7 @@
  * Dave Gerlach <d-gerlach@ti.com>
  */
 
+#include <linux/debugfs.h>
 #include <linux/err.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
@@ -50,6 +51,9 @@
 #define IPC_IO_ISOLATION_STAT_SHIFT	(10)
 #define IPC_IO_ISOLATION_STAT_MASK	(0x1 << 10)
 
+#define IPC_DBG_HALT_SHIFT		(11)
+#define IPC_DBG_HALT_MASK		(0x1 << 11)
+
 #define M3_STATE_UNKNOWN		0
 #define M3_STATE_RESET			1
 #define M3_STATE_INITED			2
@@ -157,6 +161,73 @@ static int wkup_m3_init_scale_data(struct wkup_m3_ipc *m3_ipc,
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_FS
+static void wkup_m3_set_halt_late(bool enabled)
+{
+	if (enabled)
+		m3_ipc_state->halt = (1 << IPC_DBG_HALT_SHIFT);
+	else
+		m3_ipc_state->halt = 0;
+}
+
+static int option_get(void *data, u64 *val)
+{
+	u32 *option = data;
+
+	*val = *option;
+
+	return 0;
+}
+
+static int option_set(void *data, u64 val)
+{
+	u32 *option = data;
+
+	*option = val;
+
+	if (option == &m3_ipc_state->halt) {
+		if (val)
+			wkup_m3_set_halt_late(true);
+		else
+			wkup_m3_set_halt_late(false);
+	}
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(wkup_m3_ipc_option_fops, option_get, option_set,
+			"%llu\n");
+
+static int wkup_m3_ipc_dbg_init(struct wkup_m3_ipc *m3_ipc)
+{
+	m3_ipc->dbg_path = debugfs_create_dir("wkup_m3_ipc", NULL);
+
+	if (!m3_ipc->dbg_path)
+		return -EINVAL;
+
+	(void)debugfs_create_file("enable_late_halt", 0644,
+				  m3_ipc->dbg_path,
+				  &m3_ipc->halt,
+				  &wkup_m3_ipc_option_fops);
+
+	return 0;
+}
+
+static inline void wkup_m3_ipc_dbg_destroy(struct wkup_m3_ipc *m3_ipc)
+{
+	debugfs_remove_recursive(m3_ipc->dbg_path);
+}
+#else
+static inline int wkup_m3_ipc_dbg_init(struct wkup_m3_ipc *m3_ipc)
+{
+	return 0;
+}
+
+static inline void wkup_m3_ipc_dbg_destroy(struct wkup_m3_ipc *m3_ipc)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
 static void am33xx_txev_eoi(struct wkup_m3_ipc *m3_ipc)
 {
 	writel(AM33XX_M3_TXEV_ACK,
@@ -402,7 +473,9 @@ static int wkup_m3_prepare_low_power(struct wkup_m3_ipc *m3_ipc, int state)
 	wkup_m3_ctrl_ipc_write(m3_ipc, m3_power_state, 1);
 	wkup_m3_ctrl_ipc_write(m3_ipc, m3_ipc->mem_type |
 			       m3_ipc->vtt_conf |
-			       m3_ipc->isolation_conf, 4);
+			       m3_ipc->isolation_conf |
+			       m3_ipc->halt, 4);
+
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 2);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 3);
 	wkup_m3_ctrl_ipc_write(m3_ipc, DS_IPC_DEFAULT, 6);
@@ -631,6 +704,8 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev)
 		goto err_put_rproc;
 	}
 
+	wkup_m3_ipc_dbg_init(m3_ipc);
+
 	return 0;
 
 err_put_rproc:
@@ -642,6 +717,8 @@ err_free_mbox:
 
 static int wkup_m3_ipc_remove(struct platform_device *pdev)
 {
+	wkup_m3_ipc_dbg_destroy(m3_ipc_state);
+
 	mbox_free_channel(m3_ipc_state->mbox);
 
 	rproc_shutdown(m3_ipc_state->rproc);
diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h
index fef0fac60f8c..26d1eb058fa3 100644
--- a/include/linux/wkup_m3_ipc.h
+++ b/include/linux/wkup_m3_ipc.h
@@ -36,6 +36,7 @@ struct wkup_m3_ipc {
 	int vtt_conf;
 	int isolation_conf;
 	int state;
+	u32 halt;
 
 	unsigned long volt_scale_offsets;
 	const char *sd_fw_name;
@@ -46,6 +47,7 @@ struct wkup_m3_ipc {
 
 	struct wkup_m3_ipc_ops *ops;
 	int is_rtc_only;
+	struct dentry *dbg_path;
 };
 
 struct wkup_m3_wakeup_src {
-- 
cgit v1.2.3


From 3ba75c1316390b2bc39c19cb8f0f85922ab3f9ed Mon Sep 17 00:00:00 2001
From: Baskov Evgeniy <baskov@ispras.ru>
Date: Thu, 3 Mar 2022 17:21:19 +0300
Subject: efi: libstub: declare DXE services table

UEFI DXE services are not yet used in kernel code
but are required to manipulate page table memory
protection flags.

Add required declarations to use DXE services functions.

Signed-off-by: Baskov Evgeniy <baskov@ispras.ru>
Link: https://lore.kernel.org/r/20220303142120.1975-2-baskov@ispras.ru
[ardb: ignore absent DXE table but warn if the signature check fails]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/include/asm/efi.h              |  5 +++
 drivers/firmware/efi/libstub/efistub.h  | 74 +++++++++++++++++++++++++++++++++
 drivers/firmware/efi/libstub/x86-stub.c |  9 +++-
 include/linux/efi.h                     |  2 +
 4 files changed, 89 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 98938a68251c..bed74a0f2932 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -357,6 +357,11 @@ static inline u32 efi64_convert_status(efi_status_t status)
 						   runtime),		\
 				    func, __VA_ARGS__))
 
+#define efi_dxe_call(func, ...)						\
+	(efi_is_native()						\
+		? efi_dxe_table->func(__VA_ARGS__)			\
+		: __efi64_thunk_map(efi_dxe_table, func, __VA_ARGS__))
+
 #else /* CONFIG_EFI_MIXED */
 
 static inline bool efi_is_64bit(void)
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index edb77b0621ea..2dc24776899a 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -36,6 +36,9 @@ extern bool efi_novamap;
 
 extern const efi_system_table_t *efi_system_table;
 
+typedef union efi_dxe_services_table efi_dxe_services_table_t;
+extern const efi_dxe_services_table_t *efi_dxe_table;
+
 efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 				   efi_system_table_t *sys_table_arg);
 
@@ -44,6 +47,7 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 #define efi_is_native()		(true)
 #define efi_bs_call(func, ...)	efi_system_table->boottime->func(__VA_ARGS__)
 #define efi_rt_call(func, ...)	efi_system_table->runtime->func(__VA_ARGS__)
+#define efi_dxe_call(func, ...)	efi_dxe_table->func(__VA_ARGS__)
 #define efi_table_attr(inst, attr)	(inst->attr)
 #define efi_call_proto(inst, func, ...) inst->func(inst, ##__VA_ARGS__)
 
@@ -329,6 +333,76 @@ union efi_boot_services {
 	} mixed_mode;
 };
 
+typedef enum {
+	EfiGcdMemoryTypeNonExistent,
+	EfiGcdMemoryTypeReserved,
+	EfiGcdMemoryTypeSystemMemory,
+	EfiGcdMemoryTypeMemoryMappedIo,
+	EfiGcdMemoryTypePersistent,
+	EfiGcdMemoryTypeMoreReliable,
+	EfiGcdMemoryTypeMaximum
+} efi_gcd_memory_type_t;
+
+typedef struct {
+	efi_physical_addr_t base_address;
+	u64 length;
+	u64 capabilities;
+	u64 attributes;
+	efi_gcd_memory_type_t gcd_memory_type;
+	void *image_handle;
+	void *device_handle;
+} efi_gcd_memory_space_desc_t;
+
+/*
+ * EFI DXE Services table
+ */
+union efi_dxe_services_table {
+	struct {
+		efi_table_hdr_t hdr;
+		void *add_memory_space;
+		void *allocate_memory_space;
+		void *free_memory_space;
+		void *remove_memory_space;
+		efi_status_t (__efiapi *get_memory_space_descriptor)(efi_physical_addr_t,
+								     efi_gcd_memory_space_desc_t *);
+		efi_status_t (__efiapi *set_memory_space_attributes)(efi_physical_addr_t,
+								     u64, u64);
+		void *get_memory_space_map;
+		void *add_io_space;
+		void *allocate_io_space;
+		void *free_io_space;
+		void *remove_io_space;
+		void *get_io_space_descriptor;
+		void *get_io_space_map;
+		void *dispatch;
+		void *schedule;
+		void *trust;
+		void *process_firmware_volume;
+		void *set_memory_space_capabilities;
+	};
+	struct {
+		efi_table_hdr_t hdr;
+		u32 add_memory_space;
+		u32 allocate_memory_space;
+		u32 free_memory_space;
+		u32 remove_memory_space;
+		u32 get_memory_space_descriptor;
+		u32 set_memory_space_attributes;
+		u32 get_memory_space_map;
+		u32 add_io_space;
+		u32 allocate_io_space;
+		u32 free_io_space;
+		u32 remove_io_space;
+		u32 get_io_space_descriptor;
+		u32 get_io_space_map;
+		u32 dispatch;
+		u32 schedule;
+		u32 trust;
+		u32 process_firmware_volume;
+		u32 set_memory_space_capabilities;
+	} mixed_mode;
+};
+
 typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t;
 
 union efi_uga_draw_protocol {
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 01ddd4502e28..cda60aba2f12 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -22,6 +22,7 @@
 #define MAXMEM_X86_64_4LEVEL (1ull << 46)
 
 const efi_system_table_t *efi_system_table;
+const efi_dxe_services_table_t *efi_dxe_table;
 extern u32 image_offset;
 static efi_loaded_image_t *image = NULL;
 
@@ -677,11 +678,17 @@ unsigned long efi_main(efi_handle_t handle,
 	efi_status_t status;
 
 	efi_system_table = sys_table_arg;
-
 	/* Check if we were booted by the EFI firmware */
 	if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		efi_exit(handle, EFI_INVALID_PARAMETER);
 
+	efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID);
+	if (efi_dxe_table &&
+	    efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) {
+		efi_warn("Ignoring DXE services table: invalid signature\n");
+		efi_dxe_table = NULL;
+	}
+
 	/*
 	 * If the kernel isn't already loaded at a suitable address,
 	 * relocate it.
diff --git a/include/linux/efi.h b/include/linux/efi.h
index fd266198f9d8..b1f7c6a3e5bf 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -385,6 +385,7 @@ void efi_native_runtime_setup(void);
 #define EFI_LOAD_FILE_PROTOCOL_GUID		EFI_GUID(0x56ec3091, 0x954c, 0x11d2,  0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b)
 #define EFI_LOAD_FILE2_PROTOCOL_GUID		EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e,  0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d)
 #define EFI_RT_PROPERTIES_TABLE_GUID		EFI_GUID(0xeb66918a, 0x7eef, 0x402a,  0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9)
+#define EFI_DXE_SERVICES_TABLE_GUID		EFI_GUID(0x05ad34ba, 0x6f02, 0x4214,  0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9)
 
 #define EFI_IMAGE_SECURITY_DATABASE_GUID	EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596,  0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f)
 #define EFI_SHIM_LOCK_GUID			EFI_GUID(0x605dab50, 0xe046, 0x4300,  0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23)
@@ -438,6 +439,7 @@ typedef struct {
 } efi_config_table_type_t;
 
 #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL)
+#define EFI_DXE_SERVICES_TABLE_SIGNATURE ((u64)0x565245535f455844ULL)
 
 #define EFI_2_30_SYSTEM_TABLE_REVISION  ((2 << 16) | (30))
 #define EFI_2_20_SYSTEM_TABLE_REVISION  ((2 << 16) | (20))
-- 
cgit v1.2.3


From 07768c55f9c2ad64ccae3ed82447a87d8af8a687 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Sat, 19 Mar 2022 19:00:20 +0100
Subject: efi/arm64: libstub: run image in place if randomized by the loader

If the loader has already placed the EFI kernel image randomly in
physical memory, and indicates having done so by installing the 'fixed
placement' protocol onto the image handle, don't bother randomizing the
placement again in the EFI stub.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/arm64-stub.c | 12 +++++++++---
 include/linux/efi.h                       | 11 +++++++++++
 2 files changed, 20 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index 00c91a3807ea..577173ee1f83 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -101,7 +101,15 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	u64 min_kimg_align = efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN;
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
-		if (!efi_nokaslr) {
+		efi_guid_t li_fixed_proto = LINUX_EFI_LOADED_IMAGE_FIXED_GUID;
+		void *p;
+
+		if (efi_nokaslr) {
+			efi_info("KASLR disabled on kernel command line\n");
+		} else if (efi_bs_call(handle_protocol, image_handle,
+				       &li_fixed_proto, &p) == EFI_SUCCESS) {
+			efi_info("Image placement fixed by loader\n");
+		} else {
 			status = efi_get_random_bytes(sizeof(phys_seed),
 						      (u8 *)&phys_seed);
 			if (status == EFI_NOT_FOUND) {
@@ -112,8 +120,6 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 					status);
 				efi_nokaslr = true;
 			}
-		} else {
-			efi_info("KASLR disabled on kernel command line\n");
 		}
 	}
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index b1f7c6a3e5bf..580ce607d6f5 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -410,6 +410,17 @@ void efi_native_runtime_setup(void);
 #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID	EFI_GUID(0xc451ed2b, 0x9694, 0x45d3,  0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89)
 #define LINUX_EFI_COCO_SECRET_AREA_GUID		EFI_GUID(0xadf956ad, 0xe98c, 0x484c,  0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47)
 
+/*
+ * This GUID may be installed onto the kernel image's handle as a NULL protocol
+ * to signal to the stub that the placement of the image should be respected,
+ * and moving the image in physical memory is undesirable. To ensure
+ * compatibility with 64k pages kernels with virtually mapped stacks, and to
+ * avoid defeating physical randomization, this protocol should only be
+ * installed if the image was placed at a randomized 128k aligned address in
+ * memory.
+ */
+#define LINUX_EFI_LOADED_IMAGE_FIXED_GUID	EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5,  0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a)
+
 /* OEM GUIDs */
 #define DELLEMC_EFI_RCI2_TABLE_GUID		EFI_GUID(0x2d9f28a2, 0xa886, 0x456a,  0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
 #define AMD_SEV_MEM_ENCRYPT_GUID		EFI_GUID(0x0cf29b71, 0x9e51, 0x433a,  0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75)
-- 
cgit v1.2.3


From f2b6e79c7378542e03e42fd47c0c8bf00a2fcf6b Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 3 May 2022 16:44:02 +0200
Subject: Revert "usb: core: hcd: Create platform devices for onboard hubs in
 probe()"

This reverts commit c40b62216c1aecc0dc00faf33d71bd71cb440337.

The series still has built errors as reported in linux-next, so revert
it for now.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au
Cc: Stephen Boyd <swboyd@chromium.org>
Cc: Douglas Anderson <dianders@chromium.org>
Cc: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c  | 6 ------
 include/linux/usb/hcd.h | 1 -
 2 files changed, 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 81785072fafb..d9712c2602af 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -36,7 +36,6 @@
 #include <linux/phy/phy.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
-#include <linux/usb/onboard_hub.h>
 #include <linux/usb/otg.h>
 
 #include "usb.h"
@@ -2985,9 +2984,6 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	if (hcd->uses_new_polling && HCD_POLL_RH(hcd))
 		usb_hcd_poll_rh_status(hcd);
 
-	if (usb_hcd_is_primary_hcd(hcd))
-		onboard_hub_create_pdevs(hcd->self.root_hub, &hcd->onboard_hub_devs);
-
 	return retval;
 
 err_register_root_hub:
@@ -3066,8 +3062,6 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	if (usb_hcd_is_primary_hcd(hcd)) {
 		if (hcd->irq > 0)
 			free_irq(hcd->irq, hcd);
-
-		onboard_hub_destroy_pdevs(&hcd->onboard_hub_devs);
 	}
 
 	usb_deregister_bus(&hcd->self);
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 4ebc91c09182..548a028f2dab 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -198,7 +198,6 @@ struct usb_hcd {
 	struct usb_hcd		*shared_hcd;
 	struct usb_hcd		*primary_hcd;
 
-	struct list_head	onboard_hub_devs;
 
 #define HCD_BUFFER_POOLS	4
 	struct dma_pool		*pool[HCD_BUFFER_POOLS];
-- 
cgit v1.2.3


From 67a7570ad31f2a7f02550153e774bf4c630f0fef Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 3 May 2022 16:44:11 +0200
Subject: Revert "usb: misc: Add onboard_usb_hub driver"

This reverts commit 0298b4b95cb373c21e6323c905589f8dac42c5b4.

The series still has built errors as reported in linux-next, so revert
it for now.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Douglas Anderson <dianders@chromium.org>
Cc: Matthias Kaehlcke <mka@chromium.org>
Cc: Ravi Chandra Sadineni <ravisadineni@chromium.org>
Cc: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../ABI/testing/sysfs-bus-platform-onboard-usb-hub |   8 -
 MAINTAINERS                                        |   7 -
 drivers/usb/misc/Kconfig                           |  23 -
 drivers/usb/misc/Makefile                          |   1 -
 drivers/usb/misc/onboard_usb_hub.c                 | 510 ---------------------
 include/linux/usb/onboard_hub.h                    |  18 -
 6 files changed, 567 deletions(-)
 delete mode 100644 Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub
 delete mode 100644 drivers/usb/misc/onboard_usb_hub.c
 delete mode 100644 include/linux/usb/onboard_hub.h

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub b/Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub
deleted file mode 100644
index af818d9d90c1..000000000000
--- a/Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub
+++ /dev/null
@@ -1,8 +0,0 @@
-What:		/sys/bus/platform/devices/<dev>/always_powered_in_suspend
-Date:		February 2022
-KernelVersion:	5.18
-Contact:	Matthias Kaehlcke <matthias@kaehlcke.net>
-		linux-usb@vger.kernel.org
-Description:
-		(RW) Controls whether the USB hub remains always powered
-		during system suspend or not.
\ No newline at end of file
diff --git a/MAINTAINERS b/MAINTAINERS
index 4ed0456ec129..edc96cdb85e8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14631,13 +14631,6 @@ S:	Maintained
 T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/i2c/ov9734.c
 
-ONBOARD USB HUB DRIVER
-M:	Matthias Kaehlcke <mka@chromium.org>
-L:	linux-usb@vger.kernel.org
-S:	Maintained
-F:	Documentation/ABI/testing/sysfs-bus-platform-onboard-usb-hub
-F:	drivers/usb/misc/onboard_usb_hub.c
-
 ONENAND FLASH DRIVER
 M:	Kyungmin Park <kyungmin.park@samsung.com>
 L:	linux-mtd@lists.infradead.org
diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig
index 993d07d2ffe5..4c5ddbd75b7e 100644
--- a/drivers/usb/misc/Kconfig
+++ b/drivers/usb/misc/Kconfig
@@ -295,26 +295,3 @@ config BRCM_USB_PINMAP
 	  This option enables support for remapping some USB external
 	  signals, which are typically on dedicated pins on the chip,
 	  to any gpio.
-
-config USB_ONBOARD_HUB
-	bool "Onboard USB hub support"
-	depends on OF || COMPILE_TEST
-	help
-	  Say Y here if you want to support discrete onboard USB hubs that
-	  don't require an additional control bus for initialization, but
-	  need some non-trivial form of initialization, such as enabling a
-	  power regulator. An example for such a hub is the Realtek
-	  RTS5411.
-
-	  This driver can be used as a module but its state (module vs
-	  builtin) must match the state of the USB subsystem. Enabling
-	  this config will enable the driver and it will automatically
-	  match the state of the USB subsystem. If this driver is a
-	  module it will be called onboard_usb_hub.
-
-if USB_ONBOARD_HUB
-config USB_ONBOARD_HUB_ACTUAL
-	tristate
-	default m if USB=m
-	default y if USB=y
-endif
diff --git a/drivers/usb/misc/Makefile b/drivers/usb/misc/Makefile
index ea65e202a055..35bdb4b6c3b6 100644
--- a/drivers/usb/misc/Makefile
+++ b/drivers/usb/misc/Makefile
@@ -33,4 +33,3 @@ obj-$(CONFIG_USB_CHAOSKEY)		+= chaoskey.o
 obj-$(CONFIG_USB_SISUSBVGA)		+= sisusbvga/
 obj-$(CONFIG_USB_LINK_LAYER_TEST)	+= lvstest.o
 obj-$(CONFIG_BRCM_USB_PINMAP)		+= brcmstb-usb-pinmap.o
-obj-$(CONFIG_USB_ONBOARD_HUB_ACTUAL)	+= onboard_usb_hub.o
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
deleted file mode 100644
index 34f7e4885b2e..000000000000
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ /dev/null
@@ -1,510 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Driver for onboard USB hubs
- *
- * Copyright (c) 2022, Google LLC
- */
-
-#include <linux/device.h>
-#include <linux/export.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/of.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-#include <linux/regulator/consumer.h>
-#include <linux/suspend.h>
-#include <linux/sysfs.h>
-#include <linux/usb.h>
-#include <linux/usb/hcd.h>
-#include <linux/usb/of.h>
-#include <linux/usb/onboard_hub.h>
-
-static struct usb_device_driver onboard_hub_usbdev_driver;
-
-/************************** Platform driver **************************/
-
-struct usbdev_node {
-	struct usb_device *udev;
-	struct list_head list;
-};
-
-struct onboard_hub {
-	struct regulator *vdd;
-	struct device *dev;
-	bool always_powered_in_suspend;
-	bool is_powered_on;
-	bool going_away;
-	struct list_head udev_list;
-	struct mutex lock;
-};
-
-static int onboard_hub_power_on(struct onboard_hub *hub)
-{
-	int err;
-
-	err = regulator_enable(hub->vdd);
-	if (err) {
-		dev_err(hub->dev, "failed to enable regulator: %d\n", err);
-		return err;
-	}
-
-	hub->is_powered_on = true;
-
-	return 0;
-}
-
-static int onboard_hub_power_off(struct onboard_hub *hub)
-{
-	int err;
-
-	err = regulator_disable(hub->vdd);
-	if (err) {
-		dev_err(hub->dev, "failed to disable regulator: %d\n", err);
-		return err;
-	}
-
-	hub->is_powered_on = false;
-
-	return 0;
-}
-
-static int __maybe_unused onboard_hub_suspend(struct device *dev)
-{
-	struct onboard_hub *hub = dev_get_drvdata(dev);
-	struct usbdev_node *node;
-	bool power_off = true;
-
-	if (hub->always_powered_in_suspend)
-		return 0;
-
-	mutex_lock(&hub->lock);
-
-	list_for_each_entry(node, &hub->udev_list, list) {
-		if (!device_may_wakeup(node->udev->bus->controller))
-			continue;
-
-		if (usb_wakeup_enabled_descendants(node->udev)) {
-			power_off = false;
-			break;
-		}
-	}
-
-	mutex_unlock(&hub->lock);
-
-	if (!power_off)
-		return 0;
-
-	return onboard_hub_power_off(hub);
-}
-
-static int __maybe_unused onboard_hub_resume(struct device *dev)
-{
-	struct onboard_hub *hub = dev_get_drvdata(dev);
-
-	if (hub->is_powered_on)
-		return 0;
-
-	return onboard_hub_power_on(hub);
-}
-
-static inline void get_udev_link_name(const struct usb_device *udev, char *buf, size_t size)
-{
-	snprintf(buf, size, "usb_dev.%s", dev_name(&udev->dev));
-}
-
-static int onboard_hub_add_usbdev(struct onboard_hub *hub, struct usb_device *udev)
-{
-	struct usbdev_node *node;
-	char link_name[64];
-	int err;
-
-	mutex_lock(&hub->lock);
-
-	if (hub->going_away) {
-		err = -EINVAL;
-		goto error;
-	}
-
-	node = kzalloc(sizeof(*node), GFP_KERNEL);
-	if (!node) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	node->udev = udev;
-
-	list_add(&node->list, &hub->udev_list);
-
-	mutex_unlock(&hub->lock);
-
-	get_udev_link_name(udev, link_name, sizeof(link_name));
-	WARN_ON(sysfs_create_link(&hub->dev->kobj, &udev->dev.kobj, link_name));
-
-	return 0;
-
-error:
-	mutex_unlock(&hub->lock);
-
-	return err;
-}
-
-static void onboard_hub_remove_usbdev(struct onboard_hub *hub, const struct usb_device *udev)
-{
-	struct usbdev_node *node;
-	char link_name[64];
-
-	get_udev_link_name(udev, link_name, sizeof(link_name));
-	sysfs_remove_link(&hub->dev->kobj, link_name);
-
-	mutex_lock(&hub->lock);
-
-	list_for_each_entry(node, &hub->udev_list, list) {
-		if (node->udev == udev) {
-			list_del(&node->list);
-			kfree(node);
-			break;
-		}
-	}
-
-	mutex_unlock(&hub->lock);
-}
-
-static ssize_t always_powered_in_suspend_show(struct device *dev, struct device_attribute *attr,
-			   char *buf)
-{
-	const struct onboard_hub *hub = dev_get_drvdata(dev);
-
-	return sysfs_emit(buf, "%d\n", hub->always_powered_in_suspend);
-}
-
-static ssize_t always_powered_in_suspend_store(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
-{
-	struct onboard_hub *hub = dev_get_drvdata(dev);
-	bool val;
-	int ret;
-
-	ret = kstrtobool(buf, &val);
-	if (ret < 0)
-		return ret;
-
-	hub->always_powered_in_suspend = val;
-
-	return count;
-}
-static DEVICE_ATTR_RW(always_powered_in_suspend);
-
-static struct attribute *onboard_hub_attrs[] = {
-	&dev_attr_always_powered_in_suspend.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(onboard_hub);
-
-static int onboard_hub_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct onboard_hub *hub;
-	int err;
-
-	hub = devm_kzalloc(dev, sizeof(*hub), GFP_KERNEL);
-	if (!hub)
-		return -ENOMEM;
-
-	hub->vdd = devm_regulator_get(dev, "vdd");
-	if (IS_ERR(hub->vdd))
-		return PTR_ERR(hub->vdd);
-
-	hub->dev = dev;
-	mutex_init(&hub->lock);
-	INIT_LIST_HEAD(&hub->udev_list);
-
-	dev_set_drvdata(dev, hub);
-
-	err = onboard_hub_power_on(hub);
-	if (err)
-		return err;
-
-	/*
-	 * The USB driver might have been detached from the USB devices by
-	 * onboard_hub_remove(), make sure to re-attach it if needed.
-	 */
-	err = driver_attach(&onboard_hub_usbdev_driver.drvwrap.driver);
-	if (err) {
-		onboard_hub_power_off(hub);
-		return err;
-	}
-
-	return 0;
-}
-
-static int onboard_hub_remove(struct platform_device *pdev)
-{
-	struct onboard_hub *hub = dev_get_drvdata(&pdev->dev);
-	struct usbdev_node *node;
-	struct usb_device *udev;
-
-	hub->going_away = true;
-
-	mutex_lock(&hub->lock);
-
-	/* unbind the USB devices to avoid dangling references to this device */
-	while (!list_empty(&hub->udev_list)) {
-		node = list_first_entry(&hub->udev_list, struct usbdev_node, list);
-		udev = node->udev;
-
-		/*
-		 * Unbinding the driver will call onboard_hub_remove_usbdev(),
-		 * which acquires hub->lock.  We must release the lock first.
-		 */
-		get_device(&udev->dev);
-		mutex_unlock(&hub->lock);
-		device_release_driver(&udev->dev);
-		put_device(&udev->dev);
-		mutex_lock(&hub->lock);
-	}
-
-	mutex_unlock(&hub->lock);
-
-	return onboard_hub_power_off(hub);
-}
-
-static const struct of_device_id onboard_hub_match[] = {
-	{ .compatible = "usbbda,411" },
-	{ .compatible = "usbbda,5411" },
-	{ .compatible = "usbbda,414" },
-	{ .compatible = "usbbda,5414" },
-	{}
-};
-MODULE_DEVICE_TABLE(of, onboard_hub_match);
-
-static bool of_is_onboard_usb_hub(const struct device_node *np)
-{
-	return !!of_match_node(onboard_hub_match, np);
-}
-
-static const struct dev_pm_ops __maybe_unused onboard_hub_pm_ops = {
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(onboard_hub_suspend, onboard_hub_resume)
-};
-
-static struct platform_driver onboard_hub_driver = {
-	.probe = onboard_hub_probe,
-	.remove = onboard_hub_remove,
-
-	.driver = {
-		.name = "onboard-usb-hub",
-		.of_match_table = onboard_hub_match,
-		.pm = pm_ptr(&onboard_hub_pm_ops),
-		.dev_groups = onboard_hub_groups,
-	},
-};
-
-/************************** USB driver **************************/
-
-#define VENDOR_ID_REALTEK	0x0bda
-
-/*
- * Returns the onboard_hub platform device that is associated with the USB
- * device passed as parameter.
- */
-static struct onboard_hub *_find_onboard_hub(struct device *dev)
-{
-	struct platform_device *pdev;
-	struct device_node *np;
-	struct onboard_hub *hub;
-
-	pdev = of_find_device_by_node(dev->of_node);
-	if (!pdev) {
-		np = of_parse_phandle(dev->of_node, "companion-hub", 0);
-		if (!np) {
-			dev_err(dev, "failed to find device node for companion hub\n");
-			return ERR_PTR(-EINVAL);
-		}
-
-		pdev = of_find_device_by_node(np);
-		of_node_put(np);
-
-		if (!pdev)
-			return ERR_PTR(-ENODEV);
-	}
-
-	hub = dev_get_drvdata(&pdev->dev);
-	put_device(&pdev->dev);
-
-	/*
-	 * The presence of drvdata ('hub') indicates that the platform driver
-	 * finished probing. This handles the case where (conceivably) we could
-	 * be running at the exact same time as the platform driver's probe. If
-	 * we detect the race we request probe deferral and we'll come back and
-	 * try again.
-	 */
-	if (!hub)
-		return ERR_PTR(-EPROBE_DEFER);
-
-	return hub;
-}
-
-static int onboard_hub_usbdev_probe(struct usb_device *udev)
-{
-	struct device *dev = &udev->dev;
-	struct onboard_hub *hub;
-	int err;
-
-	/* ignore supported hubs without device tree node */
-	if (!dev->of_node)
-		return -ENODEV;
-
-	hub = _find_onboard_hub(dev);
-	if (IS_ERR(hub))
-		return PTR_ERR(hub);
-
-	dev_set_drvdata(dev, hub);
-
-	err = onboard_hub_add_usbdev(hub, udev);
-	if (err)
-		return err;
-
-	return 0;
-}
-
-static void onboard_hub_usbdev_disconnect(struct usb_device *udev)
-{
-	struct onboard_hub *hub = dev_get_drvdata(&udev->dev);
-
-	onboard_hub_remove_usbdev(hub, udev);
-}
-
-static const struct usb_device_id onboard_hub_id_table[] = {
-	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x0411) }, /* RTS5411 USB 3.1 */
-	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x5411) }, /* RTS5411 USB 2.1 */
-	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x0414) }, /* RTS5414 USB 3.2 */
-	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x5414) }, /* RTS5414 USB 2.1 */
-	{}
-};
-MODULE_DEVICE_TABLE(usb, onboard_hub_id_table);
-
-static struct usb_device_driver onboard_hub_usbdev_driver = {
-	.name = "onboard-usb-hub",
-	.probe = onboard_hub_usbdev_probe,
-	.disconnect = onboard_hub_usbdev_disconnect,
-	.generic_subclass = 1,
-	.supports_autosuspend =	1,
-	.id_table = onboard_hub_id_table,
-};
-
-/*** Helpers for creating/destroying platform devices for onboard hubs ***/
-
-struct pdev_list_entry {
-	struct platform_device *pdev;
-	struct list_head node;
-};
-
-/**
- * onboard_hub_create_pdevs -- create platform devices for onboard USB hubs
- * @parent_hub	: parent hub to scan for connected onboard hubs
- * @pdev_list	: list of onboard hub platform devices owned by the parent hub
- *
- * Creates a platform device for each supported onboard hub that is connected to
- * the given parent hub. To keep track of the platform devices they are added to
- * a list that is owned by the parent hub.
- */
-void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list)
-{
-	int i;
-	struct device_node *np, *npc;
-	struct platform_device *pdev = NULL;
-	struct pdev_list_entry *pdle;
-
-	INIT_LIST_HEAD(pdev_list);
-
-	for (i = 1; i <= parent_hub->maxchild; i++) {
-		np = usb_of_get_device_node(parent_hub, i);
-		if (!np)
-			continue;
-
-		if (!of_is_onboard_usb_hub(np))
-			goto node_put;
-
-		npc = of_parse_phandle(np, "companion-hub", 0);
-		if (npc) {
-			pdev = of_find_device_by_node(npc);
-			of_node_put(npc);
-		}
-
-		if (pdev) {
-			/* the companion hub already has a platform device, nothing to do here */
-			put_device(&pdev->dev);
-			goto node_put;
-		}
-
-		pdev = of_platform_device_create(np, NULL, &parent_hub->dev);
-		if (!pdev) {
-			dev_err(&parent_hub->dev,
-				"failed to create platform device for onboard hub '%pOF'\n", np);
-			goto node_put;
-		}
-
-		pdle = devm_kzalloc(&pdev->dev, sizeof(*pdle), GFP_KERNEL);
-		if (!pdle) {
-			of_platform_device_destroy(&pdev->dev, NULL);
-			goto node_put;
-		}
-
-		pdle->pdev = pdev;
-		list_add(&pdle->node, pdev_list);
-
-node_put:
-		of_node_put(np);
-	}
-}
-EXPORT_SYMBOL_GPL(onboard_hub_create_pdevs);
-
-/**
- * onboard_hub_destroy_pdevs -- free resources of onboard hub platform devices
- * @pdev_list	: list of onboard hub platform devices
- *
- * Destroys the platform devices in the given list and frees the memory associated
- * with the list entry.
- */
-void onboard_hub_destroy_pdevs(struct list_head *pdev_list)
-{
-	struct pdev_list_entry *pdle, *tmp;
-
-	list_for_each_entry_safe(pdle, tmp, pdev_list, node) {
-		list_del(&pdle->node);
-		of_platform_device_destroy(&pdle->pdev->dev, NULL);
-	}
-}
-EXPORT_SYMBOL_GPL(onboard_hub_destroy_pdevs);
-
-/************************** Driver (de)registration **************************/
-
-static int __init onboard_hub_init(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&onboard_hub_driver);
-	if (ret)
-		return ret;
-
-	ret = usb_register_device_driver(&onboard_hub_usbdev_driver, THIS_MODULE);
-	if (ret)
-		platform_driver_unregister(&onboard_hub_driver);
-
-	return ret;
-}
-module_init(onboard_hub_init);
-
-static void __exit onboard_hub_exit(void)
-{
-	usb_deregister_device_driver(&onboard_hub_usbdev_driver);
-	platform_driver_unregister(&onboard_hub_driver);
-}
-module_exit(onboard_hub_exit);
-
-MODULE_AUTHOR("Matthias Kaehlcke <mka@chromium.org>");
-MODULE_DESCRIPTION("Driver for discrete onboard USB hubs");
-MODULE_LICENSE("GPL v2");
diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h
deleted file mode 100644
index d9373230556e..000000000000
--- a/include/linux/usb/onboard_hub.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef __LINUX_USB_ONBOARD_HUB_H
-#define __LINUX_USB_ONBOARD_HUB_H
-
-struct usb_device;
-struct list_head;
-
-#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB)
-void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list);
-void onboard_hub_destroy_pdevs(struct list_head *pdev_list);
-#else
-static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub,
-					    struct list_head *pdev_list) {}
-static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {}
-#endif
-
-#endif /* __LINUX_USB_ONBOARD_HUB_H */
-- 
cgit v1.2.3


From 1a9517a0a43040b77b5ef64d9053df214ba33d17 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 3 May 2022 16:44:24 +0200
Subject: Revert "of/platform: Add stubs for
 of_platform_device_create/destroy()"

This reverts commit 8e8b11956486e3fe8cacf54a1d492ebdd8cc1fb2.

The series still has built errors as reported in linux-next, so revert
it for now.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au
Cc: Stephen Boyd <swboyd@chromium.org>
Cc: Douglas Anderson <dianders@chromium.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/of_platform.h | 22 ++++------------------
 1 file changed, 4 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index d15b6cd5e1c3..84a966623e78 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -61,18 +61,16 @@ static inline struct platform_device *of_find_device_by_node(struct device_node
 }
 #endif
 
-extern int of_platform_bus_probe(struct device_node *root,
-				 const struct of_device_id *matches,
-				 struct device *parent);
-
-#ifdef CONFIG_OF_ADDRESS
 /* Platform devices and busses creation */
 extern struct platform_device *of_platform_device_create(struct device_node *np,
 						   const char *bus_id,
 						   struct device *parent);
 
 extern int of_platform_device_destroy(struct device *dev, void *data);
-
+extern int of_platform_bus_probe(struct device_node *root,
+				 const struct of_device_id *matches,
+				 struct device *parent);
+#ifdef CONFIG_OF_ADDRESS
 extern int of_platform_populate(struct device_node *root,
 				const struct of_device_id *matches,
 				const struct of_dev_auxdata *lookup,
@@ -86,18 +84,6 @@ extern int devm_of_platform_populate(struct device *dev);
 
 extern void devm_of_platform_depopulate(struct device *dev);
 #else
-/* Platform devices and busses creation */
-static inline struct platform_device *of_platform_device_create(struct device_node *np,
-								const char *bus_id,
-								struct device *parent)
-{
-	return NULL;
-}
-static inline int of_platform_device_destroy(struct device *dev, void *data)
-{
-	return -ENODEV;
-}
-
 static inline int of_platform_populate(struct device_node *root,
 					const struct of_device_id *matches,
 					const struct of_dev_auxdata *lookup,
-- 
cgit v1.2.3


From 1ac17586c950a2c129393f8a92901a2b357acf24 Mon Sep 17 00:00:00 2001
From: Frank Rowand <frank.rowand@sony.com>
Date: Mon, 2 May 2022 13:17:40 -0500
Subject: of: overlay: add entry to of_overlay_action_name[]

The values of enum of_overlay_notify_action are used to index into
array of_overlay_action_name.  Add an entry to of_overlay_action_name
for the value recently added to of_overlay_notify_action.

Array of_overlay_action_name[] is moved into include/linux/of.h
adjacent to enum of_overlay_notify_action to make the connection
between the two more obvious if either is modified in the future.

The only use of of_overlay_action_name is for error reporting in
overlay_notify().  All callers of overlay_notify() report the same
error, but with fewer details.  Remove the redundant error reports
in the callers.

Fixes: 067c098766c6 ("of: overlay: rework overlay apply and remove kfree()s")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20220502181742.1402826-2-frowand.list@gmail.com
---
 drivers/of/overlay.c | 27 +++++----------------------
 include/linux/of.h   | 13 +++++++++++++
 2 files changed, 18 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index bd522da7f76b..ae5ea5b1079b 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -152,13 +152,6 @@ int of_overlay_notifier_unregister(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(of_overlay_notifier_unregister);
 
-static char *of_overlay_action_name[] = {
-	"pre-apply",
-	"post-apply",
-	"pre-remove",
-	"post-remove",
-};
-
 static int overlay_notify(struct overlay_changeset *ovcs,
 		enum of_overlay_notify_action action)
 {
@@ -178,7 +171,7 @@ static int overlay_notify(struct overlay_changeset *ovcs,
 		if (notifier_to_errno(ret)) {
 			ret = notifier_to_errno(ret);
 			pr_err("overlay changeset %s notifier error %d, target: %pOF\n",
-			       of_overlay_action_name[action], ret, nd.target);
+			       of_overlay_action_name(action), ret, nd.target);
 			return ret;
 		}
 	}
@@ -925,10 +918,8 @@ static int of_overlay_apply(struct overlay_changeset *ovcs)
 		goto out;
 
 	ret = overlay_notify(ovcs, OF_OVERLAY_PRE_APPLY);
-	if (ret) {
-		pr_err("overlay changeset pre-apply notify error %d\n", ret);
+	if (ret)
 		goto out;
-	}
 
 	ret = build_changeset(ovcs);
 	if (ret)
@@ -951,12 +942,9 @@ static int of_overlay_apply(struct overlay_changeset *ovcs)
 	/* notify failure is not fatal, continue */
 
 	ret_tmp = overlay_notify(ovcs, OF_OVERLAY_POST_APPLY);
-	if (ret_tmp) {
-		pr_err("overlay changeset post-apply notify error %d\n",
-		       ret_tmp);
+	if (ret_tmp)
 		if (!ret)
 			ret = ret_tmp;
-	}
 
 out:
 	pr_debug("%s() err=%d\n", __func__, ret);
@@ -1192,10 +1180,8 @@ int of_overlay_remove(int *ovcs_id)
 	}
 
 	ret = overlay_notify(ovcs, OF_OVERLAY_PRE_REMOVE);
-	if (ret) {
-		pr_err("overlay changeset pre-remove notify error %d\n", ret);
+	if (ret)
 		goto err_unlock;
-	}
 
 	ret_apply = 0;
 	ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply);
@@ -1218,12 +1204,9 @@ int of_overlay_remove(int *ovcs_id)
 	 * OF_OVERLAY_POST_REMOVE returns an error.
 	 */
 	ret_tmp = overlay_notify(ovcs, OF_OVERLAY_POST_REMOVE);
-	if (ret_tmp) {
-		pr_err("overlay changeset post-remove notify error %d\n",
-		       ret_tmp);
+	if (ret_tmp)
 		if (!ret)
 			ret = ret_tmp;
-	}
 
 	free_overlay_changeset(ovcs);
 
diff --git a/include/linux/of.h b/include/linux/of.h
index 17741eee0ca4..f0a5d6b10c5a 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1550,6 +1550,19 @@ enum of_overlay_notify_action {
 	OF_OVERLAY_POST_REMOVE,
 };
 
+static inline char *of_overlay_action_name(enum of_overlay_notify_action action)
+{
+	static char *of_overlay_action_name[] = {
+		"init",
+		"pre-apply",
+		"post-apply",
+		"pre-remove",
+		"post-remove",
+	};
+
+	return of_overlay_action_name[action];
+}
+
 struct of_overlay_notify_data {
 	struct device_node *overlay;
 	struct device_node *target;
-- 
cgit v1.2.3


From 282d8998e9979c2186af7f7d22366f2fc3149838 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 8 Mar 2022 15:45:33 -0800
Subject: srcu: Prevent expedited GPs and blocking readers from consuming CPU

If an SRCU reader blocks while a synchronize_srcu_expedited() waits for
that same reader, then that grace period will spawn an endless series of
workqueue handlers, consuming a full CPU.  This quickly gets pointless
because consuming more CPU isn't going to make that reader get done
faster, especially if it is blocked waiting for an external event.

This commit therefore spawns at most one pair of back-to-back workqueue
handlers per expedited grace period phase, instead inserting increasing
delays as that grace period phase grows older, but capped at 10 jiffies.
In any case, if there have been at least 100 back-to-back workqueue
handlers within a single jiffy, regardless of grace period or grace-period
phase, then a one-jiffy delay is inserted.

[ paulmck:  Apply feedback from kernel test robot. ]

Cc: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Reported-by: Song Liu <song@kernel.org>
Tested-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/srcutree.h |  4 ++++
 kernel/rcu/srcutree.c    | 44 ++++++++++++++++++++++++++++++++++++++------
 2 files changed, 42 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 1b9ff4ed37e4..e3014319d1ad 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -71,9 +71,11 @@ struct srcu_struct {
 	unsigned long srcu_gp_seq;		/* Grace-period seq #. */
 	unsigned long srcu_gp_seq_needed;	/* Latest gp_seq needed. */
 	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
+	unsigned long srcu_gp_start;		/* Last GP start timestamp (jiffies) */
 	unsigned long srcu_last_gp_end;		/* Last GP end timestamp (ns) */
 	unsigned long srcu_size_jiffies;	/* Current contention-measurement interval. */
 	unsigned long srcu_n_lock_retries;	/* Contention events in current interval. */
+	unsigned long srcu_n_exp_nodelay;	/* # expedited no-delays in current GP phase. */
 	struct srcu_data __percpu *sda;		/* Per-CPU srcu_data array. */
 	bool sda_is_static;			/* May ->sda be passed to free_percpu()? */
 	unsigned long srcu_barrier_seq;		/* srcu_barrier seq #. */
@@ -83,6 +85,8 @@ struct srcu_struct {
 	atomic_t srcu_barrier_cpu_cnt;		/* # CPUs not yet posting a */
 						/*  callback for the barrier */
 						/*  operation. */
+	unsigned long reschedule_jiffies;
+	unsigned long reschedule_count;
 	struct delayed_work work;
 	struct lockdep_map dep_map;
 };
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 862008c147b0..6dd44e759f12 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -511,7 +511,10 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
 	return sum;
 }
 
-#define SRCU_INTERVAL		1
+#define SRCU_INTERVAL		1	// Base delay if no expedited GPs pending.
+#define SRCU_MAX_INTERVAL	10	// Maximum incremental delay from slow readers.
+#define SRCU_MAX_NODELAY_PHASE	1	// Maximum per-GP-phase consecutive no-delay instances.
+#define SRCU_MAX_NODELAY	100	// Maximum consecutive no-delay instances.
 
 /*
  * Return grace-period delay, zero if there are expedited grace
@@ -519,9 +522,18 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
  */
 static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 {
+	unsigned long jbase = SRCU_INTERVAL;
+
 	if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
-		return 0;
-	return SRCU_INTERVAL;
+		jbase = 0;
+	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)))
+		jbase += jiffies - READ_ONCE(ssp->srcu_gp_start);
+	if (!jbase) {
+		WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1);
+		if (READ_ONCE(ssp->srcu_n_exp_nodelay) > SRCU_MAX_NODELAY_PHASE)
+			jbase = 1;
+	}
+	return jbase > SRCU_MAX_INTERVAL ? SRCU_MAX_INTERVAL : jbase;
 }
 
 /**
@@ -623,6 +635,8 @@ static void srcu_gp_start(struct srcu_struct *ssp)
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
 				       rcu_seq_snap(&ssp->srcu_gp_seq));
 	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
+	WRITE_ONCE(ssp->srcu_gp_start, jiffies);
+	WRITE_ONCE(ssp->srcu_n_exp_nodelay, 0);
 	smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
 	rcu_seq_start(&ssp->srcu_gp_seq);
 	state = rcu_seq_state(ssp->srcu_gp_seq);
@@ -706,7 +720,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	spin_lock_irq_rcu_node(ssp);
 	idx = rcu_seq_state(ssp->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
-	cbdelay = srcu_get_delay(ssp);
+	cbdelay = !!srcu_get_delay(ssp);
 	WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns());
 	rcu_seq_end(&ssp->srcu_gp_seq);
 	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
@@ -893,7 +907,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		// the one boot CPU running with interrupts still disabled.
 		if (likely(srcu_init_done))
 			queue_delayed_work(rcu_gp_wq, &ssp->work,
-					   srcu_get_delay(ssp));
+					   !!srcu_get_delay(ssp));
 		else if (list_empty(&ssp->work.work.entry))
 			list_add(&ssp->work.work.entry, &srcu_boot_list);
 	}
@@ -1448,6 +1462,7 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 		srcu_flip(ssp);
 		spin_lock_irq_rcu_node(ssp);
 		rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2);
+		ssp->srcu_n_exp_nodelay = 0;
 		spin_unlock_irq_rcu_node(ssp);
 	}
 
@@ -1462,6 +1477,7 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 			mutex_unlock(&ssp->srcu_gp_mutex);
 			return; /* readers present, retry later. */
 		}
+		ssp->srcu_n_exp_nodelay = 0;
 		srcu_gp_end(ssp);  /* Releases ->srcu_gp_mutex. */
 	}
 }
@@ -1552,12 +1568,28 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay)
  */
 static void process_srcu(struct work_struct *work)
 {
+	unsigned long curdelay;
+	unsigned long j;
 	struct srcu_struct *ssp;
 
 	ssp = container_of(work, struct srcu_struct, work.work);
 
 	srcu_advance_state(ssp);
-	srcu_reschedule(ssp, srcu_get_delay(ssp));
+	curdelay = srcu_get_delay(ssp);
+	if (curdelay) {
+		WRITE_ONCE(ssp->reschedule_count, 0);
+	} else {
+		j = jiffies;
+		if (READ_ONCE(ssp->reschedule_jiffies) == j) {
+			WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1);
+			if (READ_ONCE(ssp->reschedule_count) > SRCU_MAX_NODELAY)
+				curdelay = 1;
+		} else {
+			WRITE_ONCE(ssp->reschedule_count, 1);
+			WRITE_ONCE(ssp->reschedule_jiffies, j);
+		}
+	}
+	srcu_reschedule(ssp, curdelay);
 }
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
-- 
cgit v1.2.3


From c29722fad4aabbf6bb841b8f058f858ec911df56 Mon Sep 17 00:00:00 2001
From: Christian Göttsche <cgzones@googlemail.com>
Date: Tue, 8 Mar 2022 18:09:26 +0100
Subject: selinux: log anon inode class name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Log the anonymous inode class name in the security hook
inode_init_security_anon.  This name is the key for name based type
transitions on the anon_inode security class on creation.  Example:

    type=AVC msg=audit(02/16/22 22:02:50.585:216) : avc:  granted \
        { create } for  pid=2136 comm=mariadbd anonclass=[io_uring] \
        scontext=system_u:system_r:mysqld_t:s0 \
        tcontext=system_u:system_r:mysqld_iouring_t:s0 tclass=anon_inode

Add a new LSM audit data type holding the inode and the class name.

Signed-off-by: Christian Göttsche <cgzones@googlemail.com>
[PM: adjusted 'anonclass' to be a trusted string, cgzones approved]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/lsm_audit.h | 2 ++
 security/lsm_audit.c      | 3 +++
 security/selinux/hooks.c  | 4 ++--
 3 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 17d02eda9538..97a8b21eb033 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -76,6 +76,7 @@ struct common_audit_data {
 #define LSM_AUDIT_DATA_IBENDPORT 14
 #define LSM_AUDIT_DATA_LOCKDOWN 15
 #define LSM_AUDIT_DATA_NOTIFICATION 16
+#define LSM_AUDIT_DATA_ANONINODE	17
 	union 	{
 		struct path path;
 		struct dentry *dentry;
@@ -96,6 +97,7 @@ struct common_audit_data {
 		struct lsm_ibpkey_audit *ibpkey;
 		struct lsm_ibendport_audit *ibendport;
 		int reason;
+		const char *anonclass;
 	} u;
 	/* this union contains LSM specific data */
 	union {
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 1897cbf6fc69..78a278f28e49 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -433,6 +433,9 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		audit_log_format(ab, " lockdown_reason=\"%s\"",
 				 lockdown_reasons[a->u.reason]);
 		break;
+	case LSM_AUDIT_DATA_ANONINODE:
+		audit_log_format(ab, " anonclass=%s", a->u.anonclass);
+		break;
 	} /* switch (a->type) */
 }
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index f1ee1bfc11de..beceb89f68d9 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2964,8 +2964,8 @@ static int selinux_inode_init_security_anon(struct inode *inode,
 	 * allowed to actually create this type of anonymous inode.
 	 */
 
-	ad.type = LSM_AUDIT_DATA_INODE;
-	ad.u.inode = inode;
+	ad.type = LSM_AUDIT_DATA_ANONINODE;
+	ad.u.anonclass = name ? (const char *)name->name : "?";
 
 	return avc_has_perm(&selinux_state,
 			    tsec->sid,
-- 
cgit v1.2.3


From c2aa2dfef243efe213a480a1ee8566507a5152f4 Mon Sep 17 00:00:00 2001
From: Sargun Dhillon <sargun@sargun.me>
Date: Tue, 3 May 2022 01:09:56 -0700
Subject: seccomp: Add wait_killable semantic to seccomp user notifier

This introduces a per-filter flag (SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV)
that makes it so that when notifications are received by the supervisor the
notifying process will transition to wait killable semantics. Although wait
killable isn't a set of semantics formally exposed to userspace, the
concept is searchable. If the notifying process is signaled prior to the
notification being received by the userspace agent, it will be handled as
normal.

One quirk about how this is handled is that the notifying process
only switches to TASK_KILLABLE if it receives a wakeup from either
an addfd or a signal. This is to avoid an unnecessary wakeup of
the notifying task.

The reasons behind switching into wait_killable only after userspace
receives the notification are:
* Avoiding unncessary work - Often, workloads will perform work that they
  may abort (request racing comes to mind). This allows for syscalls to be
  aborted safely prior to the notification being received by the
  supervisor. In this, the supervisor doesn't end up doing work that the
  workload does not want to complete anyways.
* Avoiding side effects - We don't want the syscall to be interruptible
  once the supervisor starts doing work because it may not be trivial
  to reverse the operation. For example, unmounting a file system may
  take a long time, and it's hard to rollback, or treat that as
  reentrant.
* Avoid breaking runtimes - Various runtimes do not GC when they are
  during a syscall (or while running native code that subsequently
  calls a syscall). If many notifications are blocked, and not picked
  up by the supervisor, this can get the application into a bad state.

Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220503080958.20220-2-sargun@sargun.me
---
 Documentation/userspace-api/seccomp_filter.rst | 10 ++++++
 include/linux/seccomp.h                        |  3 +-
 include/uapi/linux/seccomp.h                   |  2 ++
 kernel/seccomp.c                               | 42 ++++++++++++++++++++++++--
 4 files changed, 54 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst
index 539e9d4a4860..d1e2b9193f09 100644
--- a/Documentation/userspace-api/seccomp_filter.rst
+++ b/Documentation/userspace-api/seccomp_filter.rst
@@ -271,6 +271,16 @@ notifying process it will be replaced. The supervisor can also add an FD, and
 respond atomically by using the ``SECCOMP_ADDFD_FLAG_SEND`` flag and the return
 value will be the injected file descriptor number.
 
+The notifying process can be preempted, resulting in the notification being
+aborted. This can be problematic when trying to take actions on behalf of the
+notifying process that are long-running and typically retryable (mounting a
+filesytem). Alternatively, at filter installation time, the
+``SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV`` flag can be set. This flag makes it
+such that when a user notification is received by the supervisor, the notifying
+process will ignore non-fatal signals until the response is sent. Signals that
+are sent prior to the notification being received by userspace are handled
+normally.
+
 It is worth noting that ``struct seccomp_data`` contains the values of register
 arguments to the syscall, but does not contain pointers to memory. The task's
 memory is accessible to suitably privileged traces via ``ptrace()`` or
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 0c564e5d40ff..d31d76be4982 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -8,7 +8,8 @@
 					 SECCOMP_FILTER_FLAG_LOG | \
 					 SECCOMP_FILTER_FLAG_SPEC_ALLOW | \
 					 SECCOMP_FILTER_FLAG_NEW_LISTENER | \
-					 SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
+					 SECCOMP_FILTER_FLAG_TSYNC_ESRCH | \
+					 SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV)
 
 /* sizeof() the first published struct seccomp_notif_addfd */
 #define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 78074254ab98..0fdc6ef02b94 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -23,6 +23,8 @@
 #define SECCOMP_FILTER_FLAG_SPEC_ALLOW		(1UL << 2)
 #define SECCOMP_FILTER_FLAG_NEW_LISTENER	(1UL << 3)
 #define SECCOMP_FILTER_FLAG_TSYNC_ESRCH		(1UL << 4)
+/* Received notifications wait in killable state (only respond to fatal signals) */
+#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV	(1UL << 5)
 
 /*
  * All BPF programs must return a 32-bit value.
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 3caa0fe85235..e9852d1b4a5e 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -200,6 +200,8 @@ static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter)
  *	   the filter can be freed.
  * @cache: cache of arch/syscall mappings to actions
  * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
+ * @wait_killable_recv: Put notifying process in killable state once the
+ *			notification is received by the userspace listener.
  * @prev: points to a previously installed, or inherited, filter
  * @prog: the BPF program to evaluate
  * @notif: the struct that holds all notification related information
@@ -220,6 +222,7 @@ struct seccomp_filter {
 	refcount_t refs;
 	refcount_t users;
 	bool log;
+	bool wait_killable_recv;
 	struct action_cache cache;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
@@ -893,6 +896,10 @@ static long seccomp_attach_filter(unsigned int flags,
 	if (flags & SECCOMP_FILTER_FLAG_LOG)
 		filter->log = true;
 
+	/* Set wait killable flag, if present. */
+	if (flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV)
+		filter->wait_killable_recv = true;
+
 	/*
 	 * If there is an existing filter, make it the prev and don't drop its
 	 * task reference.
@@ -1080,6 +1087,12 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn
 	complete(&addfd->completion);
 }
 
+static bool should_sleep_killable(struct seccomp_filter *match,
+				  struct seccomp_knotif *n)
+{
+	return match->wait_killable_recv && n->state == SECCOMP_NOTIFY_SENT;
+}
+
 static int seccomp_do_user_notification(int this_syscall,
 					struct seccomp_filter *match,
 					const struct seccomp_data *sd)
@@ -1110,11 +1123,25 @@ static int seccomp_do_user_notification(int this_syscall,
 	 * This is where we wait for a reply from userspace.
 	 */
 	do {
+		bool wait_killable = should_sleep_killable(match, &n);
+
 		mutex_unlock(&match->notify_lock);
-		err = wait_for_completion_interruptible(&n.ready);
+		if (wait_killable)
+			err = wait_for_completion_killable(&n.ready);
+		else
+			err = wait_for_completion_interruptible(&n.ready);
 		mutex_lock(&match->notify_lock);
-		if (err != 0)
+
+		if (err != 0) {
+			/*
+			 * Check to see if the notifcation got picked up and
+			 * whether we should switch to wait killable.
+			 */
+			if (!wait_killable && should_sleep_killable(match, &n))
+				continue;
+
 			goto interrupted;
+		}
 
 		addfd = list_first_entry_or_null(&n.addfd,
 						 struct seccomp_kaddfd, list);
@@ -1484,6 +1511,9 @@ out:
 		mutex_lock(&filter->notify_lock);
 		knotif = find_notification(filter, unotif.id);
 		if (knotif) {
+			/* Reset the process to make sure it's not stuck */
+			if (should_sleep_killable(filter, knotif))
+				complete(&knotif->ready);
 			knotif->state = SECCOMP_NOTIFY_INIT;
 			up(&filter->notif->request);
 		}
@@ -1829,6 +1859,14 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	    ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0))
 		return -EINVAL;
 
+	/*
+	 * The SECCOMP_FILTER_FLAG_WAIT_KILLABLE_SENT flag doesn't make sense
+	 * without the SECCOMP_FILTER_FLAG_NEW_LISTENER flag.
+	 */
+	if ((flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) &&
+	    ((flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) == 0))
+		return -EINVAL;
+
 	/* Prepare the new filter before holding any locks. */
 	prepared = seccomp_prepare_user_filter(filter);
 	if (IS_ERR(prepared))
-- 
cgit v1.2.3


From 58caed3dacb4354a25a1aa8d2febc3e9648ba1f4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 May 2022 16:27:03 -0700
Subject: netdev: reshuffle netif_napi_add() APIs to allow dropping weight

Most drivers should not have to worry about selecting the right
weight for their NAPI instances and pass NAPI_POLL_WEIGHT.
It'd be best if we didn't require the argument at all and selected
the default internally.

This change prepares the ground for such reshuffling, allowing
for a smooth transition. The following API should remain after
the next release cycle:
  netif_napi_add()
  netif_napi_add_weight()
  netif_napi_add_tx()
  netif_napi_add_tx_weight()
Where the _weight() variants take an explicit weight argument.
I opted for a _weight() suffix rather than a __ prefix, because
we use __ in places to mean that caller needs to also issue a
synchronize_net() call.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20220502232703.396351-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 50 +++++++++++++++++++++++++++++++----------------
 net/core/dev.c            |  6 +++---
 2 files changed, 36 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4aba92a4042a..eaf66e57d891 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2499,37 +2499,53 @@ static inline void *netdev_priv(const struct net_device *dev)
  */
 #define NAPI_POLL_WEIGHT 64
 
+void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
+			   int (*poll)(struct napi_struct *, int), int weight);
+
 /**
- *	netif_napi_add - initialize a NAPI context
- *	@dev:  network device
- *	@napi: NAPI context
- *	@poll: polling function
- *	@weight: default weight
+ * netif_napi_add() - initialize a NAPI context
+ * @dev:  network device
+ * @napi: NAPI context
+ * @poll: polling function
+ * @weight: default weight
  *
  * netif_napi_add() must be used to initialize a NAPI context prior to calling
  * *any* of the other NAPI-related functions.
  */
-void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
-		    int (*poll)(struct napi_struct *, int), int weight);
+static inline void
+netif_napi_add(struct net_device *dev, struct napi_struct *napi,
+	       int (*poll)(struct napi_struct *, int), int weight)
+{
+	netif_napi_add_weight(dev, napi, poll, weight);
+}
+
+static inline void
+netif_napi_add_tx_weight(struct net_device *dev,
+			 struct napi_struct *napi,
+			 int (*poll)(struct napi_struct *, int),
+			 int weight)
+{
+	set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state);
+	netif_napi_add_weight(dev, napi, poll, weight);
+}
+
+#define netif_tx_napi_add netif_napi_add_tx_weight
 
 /**
- *	netif_tx_napi_add - initialize a NAPI context
- *	@dev:  network device
- *	@napi: NAPI context
- *	@poll: polling function
- *	@weight: default weight
+ * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only
+ * @dev:  network device
+ * @napi: NAPI context
+ * @poll: polling function
  *
  * This variant of netif_napi_add() should be used from drivers using NAPI
  * to exclusively poll a TX queue.
  * This will avoid we add it into napi_hash[], thus polluting this hash table.
  */
-static inline void netif_tx_napi_add(struct net_device *dev,
+static inline void netif_napi_add_tx(struct net_device *dev,
 				     struct napi_struct *napi,
-				     int (*poll)(struct napi_struct *, int),
-				     int weight)
+				     int (*poll)(struct napi_struct *, int))
 {
-	set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state);
-	netif_napi_add(dev, napi, poll, weight);
+	netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT);
 }
 
 /**
diff --git a/net/core/dev.c b/net/core/dev.c
index d127164771f2..c2d73595a7c3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6303,8 +6303,8 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 }
 EXPORT_SYMBOL(dev_set_threaded);
 
-void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
-		    int (*poll)(struct napi_struct *, int), int weight)
+void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
+			   int (*poll)(struct napi_struct *, int), int weight)
 {
 	if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state)))
 		return;
@@ -6337,7 +6337,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 	if (dev->threaded && napi_kthread_create(napi))
 		dev->threaded = 0;
 }
-EXPORT_SYMBOL(netif_napi_add);
+EXPORT_SYMBOL(netif_napi_add_weight);
 
 void napi_disable(struct napi_struct *n)
 {
-- 
cgit v1.2.3


From c674df973ad8af2074c834788e167332d81309fa Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 8 Mar 2022 20:36:15 +0200
Subject: net/mlx5: Store IPsec ESN update work in XFRM state

mlx5 IPsec code updated ESN through workqueue with allocation calls
in the data path, which can be saved easily if the work is created
during XFRM state initialization routine.

The locking used later in the work didn't protect from anything because
change of HW context is possible during XFRM state add or delete only,
which can cancel work and make sure that it is not running.

Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c   | 49 +++++++---------------
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h   |  7 +++-
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c    | 39 +++--------------
 include/linux/mlx5/accel.h                         | 10 +++--
 4 files changed, 33 insertions(+), 72 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 251178e6e82b..8283cf273a63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -271,6 +271,16 @@ static inline int mlx5e_xfrm_validate_state(struct xfrm_state *x)
 	return 0;
 }
 
+static void _update_xfrm_state(struct work_struct *work)
+{
+	struct mlx5e_ipsec_modify_state_work *modify_work =
+		container_of(work, struct mlx5e_ipsec_modify_state_work, work);
+	struct mlx5e_ipsec_sa_entry *sa_entry = container_of(
+		modify_work, struct mlx5e_ipsec_sa_entry, modify_work);
+
+	mlx5_accel_esp_modify_xfrm(sa_entry->xfrm, &modify_work->attrs);
+}
+
 static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = NULL;
@@ -334,6 +344,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 				mlx5e_ipsec_set_iv_esn : mlx5e_ipsec_set_iv;
 	}
 
+	INIT_WORK(&sa_entry->modify_work.work, _update_xfrm_state);
 	x->xso.offload_handle = (unsigned long)sa_entry;
 	goto out;
 
@@ -365,7 +376,7 @@ static void mlx5e_xfrm_free_state(struct xfrm_state *x)
 	struct mlx5e_priv *priv = netdev_priv(x->xso.dev);
 
 	if (sa_entry->hw_context) {
-		flush_workqueue(sa_entry->ipsec->wq);
+		cancel_work_sync(&sa_entry->modify_work.work);
 		mlx5e_accel_ipsec_fs_del_rule(priv, &sa_entry->xfrm->attrs,
 					      &sa_entry->ipsec_rule);
 		mlx5_accel_esp_free_hw_context(sa_entry->xfrm->mdev, sa_entry->hw_context);
@@ -392,7 +403,6 @@ int mlx5e_ipsec_init(struct mlx5e_priv *priv)
 	hash_init(ipsec->sadb_rx);
 	spin_lock_init(&ipsec->sadb_rx_lock);
 	ipsec->mdev = priv->mdev;
-	ipsec->en_priv = priv;
 	ipsec->wq = alloc_ordered_workqueue("mlx5e_ipsec: %s", 0,
 					    priv->netdev->name);
 	if (!ipsec->wq) {
@@ -424,7 +434,6 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv)
 
 	mlx5e_accel_ipsec_fs_cleanup(ipsec);
 	destroy_workqueue(ipsec->wq);
-
 	kfree(ipsec);
 	priv->ipsec = NULL;
 }
@@ -444,47 +453,19 @@ static bool mlx5e_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 	return true;
 }
 
-struct mlx5e_ipsec_modify_state_work {
-	struct work_struct		work;
-	struct mlx5_accel_esp_xfrm_attrs attrs;
-	struct mlx5e_ipsec_sa_entry	*sa_entry;
-};
-
-static void _update_xfrm_state(struct work_struct *work)
-{
-	int ret;
-	struct mlx5e_ipsec_modify_state_work *modify_work =
-		container_of(work, struct mlx5e_ipsec_modify_state_work, work);
-	struct mlx5e_ipsec_sa_entry *sa_entry = modify_work->sa_entry;
-
-	ret = mlx5_accel_esp_modify_xfrm(sa_entry->xfrm,
-					 &modify_work->attrs);
-	if (ret)
-		netdev_warn(sa_entry->ipsec->en_priv->netdev,
-			    "Not an IPSec offload device\n");
-
-	kfree(modify_work);
-}
-
 static void mlx5e_xfrm_advance_esn_state(struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
-	struct mlx5e_ipsec_modify_state_work *modify_work;
+	struct mlx5e_ipsec_modify_state_work *modify_work =
+		&sa_entry->modify_work;
 	bool need_update;
 
 	need_update = mlx5e_ipsec_update_esn_state(sa_entry);
 	if (!need_update)
 		return;
 
-	modify_work = kzalloc(sizeof(*modify_work), GFP_ATOMIC);
-	if (!modify_work)
-		return;
-
 	mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &modify_work->attrs);
-	modify_work->sa_entry = sa_entry;
-
-	INIT_WORK(&modify_work->work, _update_xfrm_state);
-	WARN_ON(!queue_work(sa_entry->ipsec->wq, &modify_work->work));
+	queue_work(sa_entry->ipsec->wq, &modify_work->work);
 }
 
 static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index bbf48d4616f9..35a751faeb33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -62,7 +62,6 @@ struct mlx5e_ipsec_tx;
 
 struct mlx5e_ipsec {
 	struct mlx5_core_dev *mdev;
-	struct mlx5e_priv *en_priv;
 	DECLARE_HASHTABLE(sadb_rx, MLX5E_IPSEC_SADB_RX_BITS);
 	spinlock_t sadb_rx_lock; /* Protects sadb_rx */
 	struct mlx5e_ipsec_sw_stats sw_stats;
@@ -82,6 +81,11 @@ struct mlx5e_ipsec_rule {
 	struct mlx5_modify_hdr *set_modify_hdr;
 };
 
+struct mlx5e_ipsec_modify_state_work {
+	struct work_struct		work;
+	struct mlx5_accel_esp_xfrm_attrs attrs;
+};
+
 struct mlx5e_ipsec_sa_entry {
 	struct hlist_node hlist; /* Item in SADB_RX hashtable */
 	struct mlx5e_ipsec_esn_state esn_state;
@@ -94,6 +98,7 @@ struct mlx5e_ipsec_sa_entry {
 			  struct xfrm_offload *xo);
 	u32 ipsec_obj_id;
 	struct mlx5e_ipsec_rule ipsec_rule;
+	struct mlx5e_ipsec_modify_state_work modify_work;
 };
 
 int mlx5e_ipsec_init(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 37c9880719cf..bbfb6643ed80 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -18,7 +18,6 @@ struct mlx5_ipsec_sa_ctx {
 struct mlx5_ipsec_esp_xfrm {
 	/* reference counter of SA ctx */
 	struct mlx5_ipsec_sa_ctx *sa_ctx;
-	struct mutex lock; /* protects mlx5_ipsec_esp_xfrm */
 	struct mlx5_accel_esp_xfrm accel_xfrm;
 };
 
@@ -117,7 +116,6 @@ mlx5_ipsec_offload_esp_create_xfrm(struct mlx5_core_dev *mdev,
 	if (!mxfrm)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_init(&mxfrm->lock);
 	memcpy(&mxfrm->accel_xfrm.attrs, attrs,
 	       sizeof(mxfrm->accel_xfrm.attrs));
 
@@ -129,8 +127,6 @@ static void mlx5_ipsec_offload_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm
 	struct mlx5_ipsec_esp_xfrm *mxfrm = container_of(xfrm, struct mlx5_ipsec_esp_xfrm,
 							 accel_xfrm);
 
-	/* assuming no sa_ctx are connected to this xfrm_ctx */
-	WARN_ON(mxfrm->sa_ctx);
 	kfree(mxfrm);
 }
 
@@ -232,7 +228,6 @@ static void *mlx5_ipsec_offload_create_sa_ctx(struct mlx5_core_dev *mdev,
 	sa_ctx->dev = mdev;
 
 	mxfrm = container_of(accel_xfrm, struct mlx5_ipsec_esp_xfrm, accel_xfrm);
-	mutex_lock(&mxfrm->lock);
 	sa_ctx->mxfrm = mxfrm;
 
 	/* key */
@@ -258,14 +253,12 @@ static void *mlx5_ipsec_offload_create_sa_ctx(struct mlx5_core_dev *mdev,
 
 	*hw_handle = sa_ctx->ipsec_obj_id;
 	mxfrm->sa_ctx = sa_ctx;
-	mutex_unlock(&mxfrm->lock);
 
 	return sa_ctx;
 
 err_enc_key:
 	mlx5_destroy_encryption_key(mdev, sa_ctx->enc_key_id);
 err_sa_ctx:
-	mutex_unlock(&mxfrm->lock);
 	kfree(sa_ctx);
 	return ERR_PTR(err);
 }
@@ -273,14 +266,10 @@ err_sa_ctx:
 static void mlx5_ipsec_offload_delete_sa_ctx(void *context)
 {
 	struct mlx5_ipsec_sa_ctx *sa_ctx = (struct mlx5_ipsec_sa_ctx *)context;
-	struct mlx5_ipsec_esp_xfrm *mxfrm = sa_ctx->mxfrm;
 
-	mutex_lock(&mxfrm->lock);
 	mlx5_destroy_ipsec_obj(sa_ctx->dev, sa_ctx->ipsec_obj_id);
 	mlx5_destroy_encryption_key(sa_ctx->dev, sa_ctx->enc_key_id);
 	kfree(sa_ctx);
-	mxfrm->sa_ctx = NULL;
-	mutex_unlock(&mxfrm->lock);
 }
 
 static int mlx5_modify_ipsec_obj(struct mlx5_core_dev *mdev,
@@ -331,29 +320,17 @@ static int mlx5_modify_ipsec_obj(struct mlx5_core_dev *mdev,
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
 
-static int mlx5_ipsec_offload_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-					      const struct mlx5_accel_esp_xfrm_attrs *attrs)
+static void mlx5_ipsec_offload_esp_modify_xfrm(
+	struct mlx5_accel_esp_xfrm *xfrm,
+	const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_ipsec_obj_attrs ipsec_attrs = {};
 	struct mlx5_core_dev *mdev = xfrm->mdev;
 	struct mlx5_ipsec_esp_xfrm *mxfrm;
-
 	int err = 0;
 
-	if (!memcmp(&xfrm->attrs, attrs, sizeof(xfrm->attrs)))
-		return 0;
-
-	if (mlx5_ipsec_offload_esp_validate_xfrm_attrs(mdev, attrs))
-		return -EOPNOTSUPP;
-
 	mxfrm = container_of(xfrm, struct mlx5_ipsec_esp_xfrm, accel_xfrm);
 
-	mutex_lock(&mxfrm->lock);
-
-	if (!mxfrm->sa_ctx)
-		/* Not bound xfrm, change only sw attrs */
-		goto change_sw_xfrm_attrs;
-
 	/* need to add find and replace in ipsec_rhash_sa the sa_ctx */
 	/* modify device with new hw_sa */
 	ipsec_attrs.accel_flags = attrs->flags;
@@ -362,12 +339,8 @@ static int mlx5_ipsec_offload_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 				    &ipsec_attrs,
 				    mxfrm->sa_ctx->ipsec_obj_id);
 
-change_sw_xfrm_attrs:
 	if (!err)
 		memcpy(&xfrm->attrs, attrs, sizeof(xfrm->attrs));
-
-	mutex_unlock(&mxfrm->lock);
-	return err;
 }
 
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
@@ -413,8 +386,8 @@ void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
 	mlx5_ipsec_offload_esp_destroy_xfrm(xfrm);
 }
 
-int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-			       const struct mlx5_accel_esp_xfrm_attrs *attrs)
+void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
+				const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	return mlx5_ipsec_offload_esp_modify_xfrm(xfrm, attrs);
+	mlx5_ipsec_offload_esp_modify_xfrm(xfrm, attrs);
 }
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index 0f2596297f6a..a2720ebbb9fd 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -127,8 +127,8 @@ struct mlx5_accel_esp_xfrm *
 mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
 			   const struct mlx5_accel_esp_xfrm_attrs *attrs);
 void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm);
-int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-			       const struct mlx5_accel_esp_xfrm_attrs *attrs);
+void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
+				const struct mlx5_accel_esp_xfrm_attrs *attrs);
 
 #else
 
@@ -145,9 +145,11 @@ mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
 }
 static inline void
 mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {}
-static inline int
+static inline void
 mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-			   const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; }
+			   const struct mlx5_accel_esp_xfrm_attrs *attrs)
+{
+}
 
 #endif /* CONFIG_MLX5_EN_IPSEC */
 #endif /* __MLX5_ACCEL_H__ */
-- 
cgit v1.2.3


From 2ea36e2e4ad2b77bd5d45142a529b72eb5ca9156 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 8 Mar 2022 20:55:00 +0200
Subject: net/mlx5: Remove useless validity check

All callers build xfrm attributes with help of mlx5e_ipsec_build_accel_xfrm_attrs()
function that ensure validity of attributes. There is no need to recheck
them again.

Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c    | 44 ----------------------
 include/linux/mlx5/accel.h                         | 10 -----
 2 files changed, 54 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index bbfb6643ed80..9d2932cf12f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -62,55 +62,11 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 }
 EXPORT_SYMBOL_GPL(mlx5_ipsec_device_caps);
 
-static int
-mlx5_ipsec_offload_esp_validate_xfrm_attrs(struct mlx5_core_dev *mdev,
-					   const struct mlx5_accel_esp_xfrm_attrs *attrs)
-{
-	if (attrs->replay_type != MLX5_ACCEL_ESP_REPLAY_NONE) {
-		mlx5_core_err(mdev, "Cannot offload xfrm states with anti replay (replay_type = %d)\n",
-			      attrs->replay_type);
-		return -EOPNOTSUPP;
-	}
-
-	if (attrs->keymat_type != MLX5_ACCEL_ESP_KEYMAT_AES_GCM) {
-		mlx5_core_err(mdev, "Only aes gcm keymat is supported (keymat_type = %d)\n",
-			      attrs->keymat_type);
-		return -EOPNOTSUPP;
-	}
-
-	if (attrs->keymat.aes_gcm.iv_algo !=
-	    MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ) {
-		mlx5_core_err(mdev, "Only iv sequence algo is supported (iv_algo = %d)\n",
-			      attrs->keymat.aes_gcm.iv_algo);
-		return -EOPNOTSUPP;
-	}
-
-	if (attrs->keymat.aes_gcm.key_len != 128 &&
-	    attrs->keymat.aes_gcm.key_len != 256) {
-		mlx5_core_err(mdev, "Cannot offload xfrm states with key length other than 128/256 bit (key length = %d)\n",
-			      attrs->keymat.aes_gcm.key_len);
-		return -EOPNOTSUPP;
-	}
-
-	if ((attrs->flags & MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED) &&
-	    !MLX5_CAP_IPSEC(mdev, ipsec_esn)) {
-		mlx5_core_err(mdev, "Cannot offload xfrm states with ESN triggered\n");
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
 static struct mlx5_accel_esp_xfrm *
 mlx5_ipsec_offload_esp_create_xfrm(struct mlx5_core_dev *mdev,
 				   const struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_ipsec_esp_xfrm *mxfrm;
-	int err = 0;
-
-	err = mlx5_ipsec_offload_esp_validate_xfrm_attrs(mdev, attrs);
-	if (err)
-		return ERR_PTR(err);
 
 	mxfrm = kzalloc(sizeof(*mxfrm), GFP_KERNEL);
 	if (!mxfrm)
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index a2720ebbb9fd..9c511d466e55 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -36,10 +36,6 @@
 
 #include <linux/mlx5/driver.h>
 
-enum mlx5_accel_esp_aes_gcm_keymat_iv_algo {
-	MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ,
-};
-
 enum mlx5_accel_esp_flags {
 	MLX5_ACCEL_ESP_FLAGS_TUNNEL            = 0,    /* Default */
 	MLX5_ACCEL_ESP_FLAGS_TRANSPORT         = 1UL << 0,
@@ -57,14 +53,9 @@ enum mlx5_accel_esp_keymats {
 	MLX5_ACCEL_ESP_KEYMAT_AES_GCM,
 };
 
-enum mlx5_accel_esp_replay {
-	MLX5_ACCEL_ESP_REPLAY_NONE,
-	MLX5_ACCEL_ESP_REPLAY_BMP,
-};
 
 struct aes_gcm_keymat {
 	u64   seq_iv;
-	enum mlx5_accel_esp_aes_gcm_keymat_iv_algo iv_algo;
 
 	u32   salt;
 	u32   icv_len;
@@ -81,7 +72,6 @@ struct mlx5_accel_esp_xfrm_attrs {
 	u32   tfc_pad;
 	u32   flags;
 	u32   sa_handle;
-	enum mlx5_accel_esp_replay replay_type;
 	union {
 		struct {
 			u32 size;
-- 
cgit v1.2.3


From c6e3b421c7079af67201351c9faff62613e06f40 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 9 Mar 2022 10:35:05 +0200
Subject: net/mlx5: Merge various control path IPsec headers into one file

The mlx5 IPsec code has logical separation between code that operates
with XFRM objects (ipsec.c), HW objects (ipsec_offload.c), flow steering
logic (ipsec_fs.c) and data path (ipsec_rxtx.c).

Such separation makes sense for C-files, but isn't needed at all for
H-files as they are included in batch anyway.

Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/params.c    |   2 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c   |   5 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h   | 101 +++++++++++++-
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         |  17 +--
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c    |   3 +-
 .../mellanox/mlx5/core/en_accel/ipsec_offload.h    |  14 --
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.c       |   5 +-
 .../mellanox/mlx5/core/en_accel/ipsec_stats.c      |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |   1 -
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   2 +-
 include/linux/mlx5/accel.h                         | 145 ---------------------
 12 files changed, 117 insertions(+), 184 deletions(-)
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
 delete mode 100644 include/linux/mlx5/accel.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 1e8700957280..3c1edfa33aa7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -5,7 +5,7 @@
 #include "en/txrx.h"
 #include "en/port.h"
 #include "en_accel/en_accel.h"
-#include "en_accel/ipsec_offload.h"
+#include "en_accel/ipsec.h"
 
 static bool mlx5e_rx_is_xdp(struct mlx5e_params *params,
 			    struct mlx5e_xsk_param *xsk)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 8283cf273a63..0daf9350471f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -37,9 +37,8 @@
 #include <linux/netdevice.h>
 
 #include "en.h"
-#include "en_accel/ipsec.h"
-#include "en_accel/ipsec_rxtx.h"
-#include "en_accel/ipsec_fs.h"
+#include "ipsec.h"
+#include "ipsec_rxtx.h"
 
 static struct mlx5e_ipsec_sa_entry *to_ipsec_sa_entry(struct xfrm_state *x)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 35a751faeb33..b438b0358c36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -40,11 +40,81 @@
 #include <net/xfrm.h>
 #include <linux/idr.h>
 
-#include "ipsec_offload.h"
-
 #define MLX5E_IPSEC_SADB_RX_BITS 10
 #define MLX5E_IPSEC_ESN_SCOPE_MID 0x80000000L
 
+enum mlx5_accel_esp_flags {
+	MLX5_ACCEL_ESP_FLAGS_TUNNEL            = 0,    /* Default */
+	MLX5_ACCEL_ESP_FLAGS_TRANSPORT         = 1UL << 0,
+	MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED     = 1UL << 1,
+	MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP = 1UL << 2,
+};
+
+enum mlx5_accel_esp_action {
+	MLX5_ACCEL_ESP_ACTION_DECRYPT,
+	MLX5_ACCEL_ESP_ACTION_ENCRYPT,
+};
+
+enum mlx5_accel_esp_keymats {
+	MLX5_ACCEL_ESP_KEYMAT_AES_NONE,
+	MLX5_ACCEL_ESP_KEYMAT_AES_GCM,
+};
+
+struct aes_gcm_keymat {
+	u64   seq_iv;
+
+	u32   salt;
+	u32   icv_len;
+
+	u32   key_len;
+	u32   aes_key[256 / 32];
+};
+
+struct mlx5_accel_esp_xfrm_attrs {
+	enum mlx5_accel_esp_action action;
+	u32   esn;
+	__be32 spi;
+	u32   seq;
+	u32   tfc_pad;
+	u32   flags;
+	u32   sa_handle;
+	union {
+		struct {
+			u32 size;
+
+		} bmp;
+	} replay;
+	enum mlx5_accel_esp_keymats keymat_type;
+	union {
+		struct aes_gcm_keymat aes_gcm;
+	} keymat;
+
+	union {
+		__be32 a4;
+		__be32 a6[4];
+	} saddr;
+
+	union {
+		__be32 a4;
+		__be32 a6[4];
+	} daddr;
+
+	u8 is_ipv6;
+};
+
+struct mlx5_accel_esp_xfrm {
+	struct mlx5_core_dev  *mdev;
+	struct mlx5_accel_esp_xfrm_attrs attrs;
+};
+
+enum mlx5_accel_ipsec_cap {
+	MLX5_ACCEL_IPSEC_CAP_DEVICE		= 1 << 0,
+	MLX5_ACCEL_IPSEC_CAP_ESP		= 1 << 1,
+	MLX5_ACCEL_IPSEC_CAP_IPV6		= 1 << 2,
+	MLX5_ACCEL_IPSEC_CAP_LSO		= 1 << 3,
+	MLX5_ACCEL_IPSEC_CAP_ESN		= 1 << 4,
+};
+
 struct mlx5e_priv;
 
 struct mlx5e_ipsec_sw_stats {
@@ -108,6 +178,29 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv);
 struct xfrm_state *mlx5e_ipsec_sadb_rx_lookup(struct mlx5e_ipsec *dev,
 					      unsigned int handle);
 
+void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec);
+int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec);
+int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv,
+				  struct mlx5_accel_esp_xfrm_attrs *attrs,
+				  u32 ipsec_obj_id,
+				  struct mlx5e_ipsec_rule *ipsec_rule);
+void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv,
+				   struct mlx5_accel_esp_xfrm_attrs *attrs,
+				   struct mlx5e_ipsec_rule *ipsec_rule);
+
+void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
+				       struct mlx5_accel_esp_xfrm *xfrm,
+				       u32 *sa_handle);
+void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context);
+
+u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev);
+
+struct mlx5_accel_esp_xfrm *
+mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
+			   const struct mlx5_accel_esp_xfrm_attrs *attrs);
+void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm);
+void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
+				const struct mlx5_accel_esp_xfrm_attrs *attrs);
 #else
 static inline int mlx5e_ipsec_init(struct mlx5e_priv *priv)
 {
@@ -122,6 +215,10 @@ static inline void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv)
 {
 }
 
+static inline u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
+{
+	return 0;
+}
 #endif
 
 #endif	/* __MLX5E_IPSEC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index bffad18a59d6..96ab2e9d6f9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -2,8 +2,9 @@
 /* Copyright (c) 2020, Mellanox Technologies inc. All rights reserved. */
 
 #include <linux/netdevice.h>
-#include "ipsec_offload.h"
-#include "ipsec_fs.h"
+#include "en.h"
+#include "en/fs.h"
+#include "ipsec.h"
 #include "fs_core.h"
 
 #define NUM_IPSEC_FTE BIT(15)
@@ -565,7 +566,7 @@ static int tx_add_rule(struct mlx5e_priv *priv,
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		netdev_err(priv->netdev, "fail to add ipsec rule attrs->action=0x%x, err=%d\n",
-			   attrs->action, err);
+				attrs->action, err);
 		goto out;
 	}
 
@@ -579,8 +580,8 @@ out:
 }
 
 static void rx_del_rule(struct mlx5e_priv *priv,
-			struct mlx5_accel_esp_xfrm_attrs *attrs,
-			struct mlx5e_ipsec_rule *ipsec_rule)
+		struct mlx5_accel_esp_xfrm_attrs *attrs,
+		struct mlx5e_ipsec_rule *ipsec_rule)
 {
 	mlx5_del_flow_rules(ipsec_rule->rule);
 	ipsec_rule->rule = NULL;
@@ -592,7 +593,7 @@ static void rx_del_rule(struct mlx5e_priv *priv,
 }
 
 static void tx_del_rule(struct mlx5e_priv *priv,
-			struct mlx5e_ipsec_rule *ipsec_rule)
+		struct mlx5e_ipsec_rule *ipsec_rule)
 {
 	mlx5_del_flow_rules(ipsec_rule->rule);
 	ipsec_rule->rule = NULL;
@@ -612,8 +613,8 @@ int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv,
 }
 
 void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv,
-			     struct mlx5_accel_esp_xfrm_attrs *attrs,
-			     struct mlx5e_ipsec_rule *ipsec_rule)
+		struct mlx5_accel_esp_xfrm_attrs *attrs,
+		struct mlx5e_ipsec_rule *ipsec_rule)
 {
 	if (attrs->action == MLX5_ACCEL_ESP_ACTION_DECRYPT)
 		rx_del_rule(priv, attrs, ipsec_rule);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 9d2932cf12f1..6c03ce8aba92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -2,9 +2,8 @@
 /* Copyright (c) 2017, Mellanox Technologies inc. All rights reserved. */
 
 #include "mlx5_core.h"
-#include "ipsec_offload.h"
+#include "ipsec.h"
 #include "lib/mlx5.h"
-#include "en_accel/ipsec_fs.h"
 
 struct mlx5_ipsec_sa_ctx {
 	struct rhash_head hash;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
deleted file mode 100644
index 7dac104e6ef1..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2020, Mellanox Technologies inc. All rights reserved. */
-
-#ifndef __MLX5_IPSEC_OFFLOAD_H__
-#define __MLX5_IPSEC_OFFLOAD_H__
-
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/accel.h>
-
-void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				       struct mlx5_accel_esp_xfrm *xfrm,
-				       u32 *sa_handle);
-void mlx5_accel_esp_free_hw_context(struct mlx5_core_dev *mdev, void *context);
-#endif /* __MLX5_IPSEC_OFFLOAD_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 9b65c765cbd9..d30922e1b60f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -34,9 +34,8 @@
 #include <crypto/aead.h>
 #include <net/xfrm.h>
 #include <net/esp.h>
-#include "ipsec_offload.h"
-#include "en_accel/ipsec_rxtx.h"
-#include "en_accel/ipsec.h"
+#include "ipsec.h"
+#include "ipsec_rxtx.h"
 #include "en.h"
 
 enum {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
index 3aace1c2a763..9de84821dafb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
@@ -35,9 +35,7 @@
 #include <net/sock.h>
 
 #include "en.h"
-#include "ipsec_offload.h"
-#include "fpga/sdk.h"
-#include "en_accel/ipsec.h"
+#include "ipsec.h"
 
 static const struct counter_desc mlx5e_ipsec_sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_sp_alloc) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 12b72a0bcb1a..d27986869b8b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -48,7 +48,6 @@
 #include "en_accel/ipsec.h"
 #include "en_accel/en_accel.h"
 #include "en_accel/ktls.h"
-#include "en_accel/ipsec_offload.h"
 #include "lib/vxlan.h"
 #include "lib/clock.h"
 #include "en/port.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 2dea9e4649a6..fb11081001a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -48,7 +48,7 @@
 #include "en_rep.h"
 #include "en/rep/tc.h"
 #include "ipoib/ipoib.h"
-#include "en_accel/ipsec_offload.h"
+#include "en_accel/ipsec.h"
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/ktls_txrx.h"
 #include "en/xdp.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 95d7712c2d9a..35e48ef04845 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -62,7 +62,7 @@
 #include "lib/mlx5.h"
 #include "lib/tout.h"
 #include "fpga/core.h"
-#include "en_accel/ipsec_offload.h"
+#include "en_accel/ipsec.h"
 #include "lib/clock.h"
 #include "lib/vxlan.h"
 #include "lib/geneve.h"
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
deleted file mode 100644
index 9c511d466e55..000000000000
--- a/include/linux/mlx5/accel.h
+++ /dev/null
@@ -1,145 +0,0 @@
-/*
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#ifndef __MLX5_ACCEL_H__
-#define __MLX5_ACCEL_H__
-
-#include <linux/mlx5/driver.h>
-
-enum mlx5_accel_esp_flags {
-	MLX5_ACCEL_ESP_FLAGS_TUNNEL            = 0,    /* Default */
-	MLX5_ACCEL_ESP_FLAGS_TRANSPORT         = 1UL << 0,
-	MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED     = 1UL << 1,
-	MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP = 1UL << 2,
-};
-
-enum mlx5_accel_esp_action {
-	MLX5_ACCEL_ESP_ACTION_DECRYPT,
-	MLX5_ACCEL_ESP_ACTION_ENCRYPT,
-};
-
-enum mlx5_accel_esp_keymats {
-	MLX5_ACCEL_ESP_KEYMAT_AES_NONE,
-	MLX5_ACCEL_ESP_KEYMAT_AES_GCM,
-};
-
-
-struct aes_gcm_keymat {
-	u64   seq_iv;
-
-	u32   salt;
-	u32   icv_len;
-
-	u32   key_len;
-	u32   aes_key[256 / 32];
-};
-
-struct mlx5_accel_esp_xfrm_attrs {
-	enum mlx5_accel_esp_action action;
-	u32   esn;
-	__be32 spi;
-	u32   seq;
-	u32   tfc_pad;
-	u32   flags;
-	u32   sa_handle;
-	union {
-		struct {
-			u32 size;
-
-		} bmp;
-	} replay;
-	enum mlx5_accel_esp_keymats keymat_type;
-	union {
-		struct aes_gcm_keymat aes_gcm;
-	} keymat;
-
-	union {
-		__be32 a4;
-		__be32 a6[4];
-	} saddr;
-
-	union {
-		__be32 a4;
-		__be32 a6[4];
-	} daddr;
-
-	u8 is_ipv6;
-};
-
-struct mlx5_accel_esp_xfrm {
-	struct mlx5_core_dev  *mdev;
-	struct mlx5_accel_esp_xfrm_attrs attrs;
-};
-
-enum mlx5_accel_ipsec_cap {
-	MLX5_ACCEL_IPSEC_CAP_DEVICE		= 1 << 0,
-	MLX5_ACCEL_IPSEC_CAP_ESP		= 1 << 1,
-	MLX5_ACCEL_IPSEC_CAP_IPV6		= 1 << 2,
-	MLX5_ACCEL_IPSEC_CAP_LSO		= 1 << 3,
-	MLX5_ACCEL_IPSEC_CAP_ESN		= 1 << 4,
-};
-
-#ifdef CONFIG_MLX5_EN_IPSEC
-
-u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev);
-
-struct mlx5_accel_esp_xfrm *
-mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
-			   const struct mlx5_accel_esp_xfrm_attrs *attrs);
-void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm);
-void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-				const struct mlx5_accel_esp_xfrm_attrs *attrs);
-
-#else
-
-static inline u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
-{
-	return 0;
-}
-
-static inline struct mlx5_accel_esp_xfrm *
-mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
-			   const struct mlx5_accel_esp_xfrm_attrs *attrs)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-static inline void
-mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {}
-static inline void
-mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-			   const struct mlx5_accel_esp_xfrm_attrs *attrs)
-{
-}
-
-#endif /* CONFIG_MLX5_EN_IPSEC */
-#endif /* __MLX5_ACCEL_H__ */
-- 
cgit v1.2.3


From 1c4a59b9fa98c222bd6a8fa82bff942312165c1a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 27 Mar 2022 19:23:19 +0300
Subject: net/mlx5: Remove not-supported ICV length

mlx5 doesn't allow to configure any AEAD ICV length other than 128,
so remove the logic that configures other unsupported values.

Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c         | 17 +----------------
 include/linux/mlx5/mlx5_ifc.h                           |  2 --
 2 files changed, 1 insertion(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index b44bce3f4ef1..91ec8b8bf1ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -62,22 +62,7 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry)
 	salt_p = MLX5_ADDR_OF(ipsec_obj, obj, salt);
 	memcpy(salt_p, &aes_gcm->salt, sizeof(aes_gcm->salt));
 
-	switch (aes_gcm->icv_len) {
-	case 64:
-		MLX5_SET(ipsec_obj, obj, icv_length,
-			 MLX5_IPSEC_OBJECT_ICV_LEN_8B);
-		break;
-	case 96:
-		MLX5_SET(ipsec_obj, obj, icv_length,
-			 MLX5_IPSEC_OBJECT_ICV_LEN_12B);
-		break;
-	case 128:
-		MLX5_SET(ipsec_obj, obj, icv_length,
-			 MLX5_IPSEC_OBJECT_ICV_LEN_16B);
-		break;
-	default:
-		return -EINVAL;
-	}
+	MLX5_SET(ipsec_obj, obj, icv_length, MLX5_IPSEC_OBJECT_ICV_LEN_16B);
 	salt_iv_p = MLX5_ADDR_OF(ipsec_obj, obj, implicit_iv);
 	memcpy(salt_iv_p, &aes_gcm->seq_iv, sizeof(aes_gcm->seq_iv));
 	/* esn */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 7f4ec9faa180..7bab3e51c61e 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -11379,8 +11379,6 @@ enum {
 
 enum {
 	MLX5_IPSEC_OBJECT_ICV_LEN_16B,
-	MLX5_IPSEC_OBJECT_ICV_LEN_12B,
-	MLX5_IPSEC_OBJECT_ICV_LEN_8B,
 };
 
 struct mlx5_ifc_ipsec_obj_bits {
-- 
cgit v1.2.3


From 31ab09b4218879bc394c9faa6da983a82a694600 Mon Sep 17 00:00:00 2001
From: Dipen Patel <dipenp@nvidia.com>
Date: Fri, 22 Apr 2022 13:52:13 -0700
Subject: drivers: Add hardware timestamp engine (HTE) subsystem

Some devices can timestamp system lines/signals/Buses in real-time
using the hardware counter or other hardware means which can give
finer granularity and help avoid jitter introduced by software
timestamping. To utilize such functionality, this patchset creates
HTE subsystem where devices can register themselves as providers so
that the consumers devices can request specific line from the
providers. The patch also adds compilation support in Makefile and
menu options in Kconfig.

The provider does following:
- Registers chip with the framework.
- Provides translation hook to convert logical line id.
- Provides enable/disable, request/release callbacks.
- Pushes timestamp data to HTE subsystem.

The consumer does following:
- Initializes line attribute.
- Gets HTE timestamp descriptor.
- Requests timestamp functionality.
- Puts HTE timestamp descriptor.

Signed-off-by: Dipen Patel <dipenp@nvidia.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/Kconfig      |   2 +
 drivers/Makefile     |   1 +
 drivers/hte/Kconfig  |  14 +
 drivers/hte/Makefile |   2 +
 drivers/hte/hte.c    | 947 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/hte.h  | 271 +++++++++++++++
 6 files changed, 1237 insertions(+)
 create mode 100644 drivers/hte/Kconfig
 create mode 100644 drivers/hte/Makefile
 create mode 100644 drivers/hte/hte.c
 create mode 100644 include/linux/hte.h

(limited to 'include/linux')

diff --git a/drivers/Kconfig b/drivers/Kconfig
index 8d6cd5d08722..a5a7768f95d2 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -239,4 +239,6 @@ source "drivers/most/Kconfig"
 
 source "drivers/peci/Kconfig"
 
+source "drivers/hte/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 020780b6b4d2..368a09b6020a 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -188,3 +188,4 @@ obj-$(CONFIG_INTERCONNECT)	+= interconnect/
 obj-$(CONFIG_COUNTER)		+= counter/
 obj-$(CONFIG_MOST)		+= most/
 obj-$(CONFIG_PECI)		+= peci/
+obj-$(CONFIG_HTE)		+= hte/
diff --git a/drivers/hte/Kconfig b/drivers/hte/Kconfig
new file mode 100644
index 000000000000..478a80a2f384
--- /dev/null
+++ b/drivers/hte/Kconfig
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menuconfig HTE
+	bool "Hardware Timestamping Engine (HTE) Support"
+	help
+	  Hardware Timestamping Engine (HTE) Support.
+
+	  Some devices provide a hardware timestamping engine which can
+	  timestamp certain device lines/signals in realtime. It comes with a
+	  benefit for the applications needing accurate timestamping event with
+	  less jitter. This framework provides a generic interface to such HTE
+	  providers and consumer devices.
+
+	  If unsure, say no.
+
diff --git a/drivers/hte/Makefile b/drivers/hte/Makefile
new file mode 100644
index 000000000000..fc03bdf44427
--- /dev/null
+++ b/drivers/hte/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_HTE)		+= hte.o
+
diff --git a/drivers/hte/hte.c b/drivers/hte/hte.c
new file mode 100644
index 000000000000..891b98ad609e
--- /dev/null
+++ b/drivers/hte/hte.c
@@ -0,0 +1,947 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021-2022 NVIDIA Corporation
+ *
+ * Author: Dipen Patel <dipenp@nvidia.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/mutex.h>
+#include <linux/uaccess.h>
+#include <linux/hte.h>
+#include <linux/delay.h>
+#include <linux/debugfs.h>
+
+#define HTE_TS_NAME_LEN		10
+
+/* Global list of the HTE devices */
+static DEFINE_SPINLOCK(hte_lock);
+static LIST_HEAD(hte_devices);
+
+enum {
+	HTE_TS_REGISTERED,
+	HTE_TS_REQ,
+	HTE_TS_DISABLE,
+	HTE_TS_QUEUE_WK,
+};
+
+/**
+ * struct hte_ts_info - Information related to requested timestamp.
+ *
+ * @xlated_id: Timestamp ID as understood between HTE subsys and HTE provider,
+ * See xlate callback API.
+ * @flags: Flags holding state information.
+ * @hte_cb_flags: Callback related flags.
+ * @seq: Timestamp sequence counter.
+ * @line_name: HTE allocated line name.
+ * @free_attr_name: If set, free the attr name.
+ * @cb: A nonsleeping callback function provided by clients.
+ * @tcb: A secondary sleeping callback function provided by clients.
+ * @dropped_ts: Dropped timestamps.
+ * @slock: Spin lock to synchronize between disable/enable,
+ * request/release APIs.
+ * @cb_work: callback workqueue, used when tcb is specified.
+ * @req_mlock: Lock during timestamp request/release APIs.
+ * @ts_dbg_root: Root for the debug fs.
+ * @gdev: HTE abstract device that this timestamp information belongs to.
+ * @cl_data: Client specific data.
+ */
+struct hte_ts_info {
+	u32 xlated_id;
+	unsigned long flags;
+	unsigned long hte_cb_flags;
+	u64 seq;
+	char *line_name;
+	bool free_attr_name;
+	hte_ts_cb_t cb;
+	hte_ts_sec_cb_t tcb;
+	atomic_t dropped_ts;
+	spinlock_t slock;
+	struct work_struct cb_work;
+	struct mutex req_mlock;
+	struct dentry *ts_dbg_root;
+	struct hte_device *gdev;
+	void *cl_data;
+};
+
+/**
+ * struct hte_device - HTE abstract device
+ * @nlines: Number of entities this device supports.
+ * @ts_req: Total number of entities requested.
+ * @sdev: Device used at various debug prints.
+ * @dbg_root: Root directory for debug fs.
+ * @list: List node to store hte_device for each provider.
+ * @chip: HTE chip providing this HTE device.
+ * @owner: helps prevent removal of modules when in use.
+ * @ei: Timestamp information.
+ */
+struct hte_device {
+	u32 nlines;
+	atomic_t ts_req;
+	struct device *sdev;
+	struct dentry *dbg_root;
+	struct list_head list;
+	struct hte_chip *chip;
+	struct module *owner;
+	struct hte_ts_info ei[];
+};
+
+#ifdef CONFIG_DEBUG_FS
+
+static struct dentry *hte_root;
+
+static int __init hte_subsys_dbgfs_init(void)
+{
+	/* creates /sys/kernel/debug/hte/ */
+	hte_root = debugfs_create_dir("hte", NULL);
+
+	return 0;
+}
+subsys_initcall(hte_subsys_dbgfs_init);
+
+static void hte_chip_dbgfs_init(struct hte_device *gdev)
+{
+	const struct hte_chip *chip = gdev->chip;
+	const char *name = chip->name ? chip->name : dev_name(chip->dev);
+
+	gdev->dbg_root = debugfs_create_dir(name, hte_root);
+
+	debugfs_create_atomic_t("ts_requested", 0444, gdev->dbg_root,
+				&gdev->ts_req);
+	debugfs_create_u32("total_ts", 0444, gdev->dbg_root,
+			   &gdev->nlines);
+}
+
+static void hte_ts_dbgfs_init(const char *name, struct hte_ts_info *ei)
+{
+	if (!ei->gdev->dbg_root || !name)
+		return;
+
+	ei->ts_dbg_root = debugfs_create_dir(name, ei->gdev->dbg_root);
+
+	debugfs_create_atomic_t("dropped_timestamps", 0444, ei->ts_dbg_root,
+				&ei->dropped_ts);
+}
+
+#else
+
+static void hte_chip_dbgfs_init(struct hte_device *gdev)
+{
+}
+
+static void hte_ts_dbgfs_init(const char *name, struct hte_ts_info *ei)
+{
+}
+
+#endif
+
+/**
+ * hte_ts_put() - Release and disable timestamp for the given desc.
+ *
+ * @desc: timestamp descriptor.
+ *
+ * Context: debugfs_remove_recursive() function call may use sleeping locks,
+ *	    not suitable from atomic context.
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int hte_ts_put(struct hte_ts_desc *desc)
+{
+	int ret = 0;
+	unsigned long flag;
+	struct hte_device *gdev;
+	struct hte_ts_info *ei;
+
+	if (!desc)
+		return -EINVAL;
+
+	ei = desc->hte_data;
+
+	if (!ei || !ei->gdev)
+		return -EINVAL;
+
+	gdev = ei->gdev;
+
+	mutex_lock(&ei->req_mlock);
+
+	if (unlikely(!test_bit(HTE_TS_REQ, &ei->flags) &&
+	    !test_bit(HTE_TS_REGISTERED, &ei->flags))) {
+		dev_info(gdev->sdev, "id:%d is not requested\n",
+			 desc->attr.line_id);
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (unlikely(!test_bit(HTE_TS_REQ, &ei->flags) &&
+	    test_bit(HTE_TS_REGISTERED, &ei->flags))) {
+		dev_info(gdev->sdev, "id:%d is registered but not requested\n",
+			 desc->attr.line_id);
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (test_bit(HTE_TS_REQ, &ei->flags) &&
+	    !test_bit(HTE_TS_REGISTERED, &ei->flags)) {
+		clear_bit(HTE_TS_REQ, &ei->flags);
+		desc->hte_data = NULL;
+		ret = 0;
+		goto mod_put;
+	}
+
+	ret = gdev->chip->ops->release(gdev->chip, desc, ei->xlated_id);
+	if (ret) {
+		dev_err(gdev->sdev, "id: %d free failed\n",
+			desc->attr.line_id);
+		goto unlock;
+	}
+
+	kfree(ei->line_name);
+	if (ei->free_attr_name)
+		kfree_const(desc->attr.name);
+
+	debugfs_remove_recursive(ei->ts_dbg_root);
+
+	spin_lock_irqsave(&ei->slock, flag);
+
+	if (test_bit(HTE_TS_QUEUE_WK, &ei->flags)) {
+		spin_unlock_irqrestore(&ei->slock, flag);
+		flush_work(&ei->cb_work);
+		spin_lock_irqsave(&ei->slock, flag);
+	}
+
+	atomic_dec(&gdev->ts_req);
+	atomic_set(&ei->dropped_ts, 0);
+
+	ei->seq = 1;
+	ei->flags = 0;
+	desc->hte_data = NULL;
+
+	spin_unlock_irqrestore(&ei->slock, flag);
+
+	ei->cb = NULL;
+	ei->tcb = NULL;
+	ei->cl_data = NULL;
+
+mod_put:
+	module_put(gdev->owner);
+unlock:
+	mutex_unlock(&ei->req_mlock);
+	dev_dbg(gdev->sdev, "release id: %d\n", desc->attr.line_id);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hte_ts_put);
+
+static int hte_ts_dis_en_common(struct hte_ts_desc *desc, bool en)
+{
+	u32 ts_id;
+	struct hte_device *gdev;
+	struct hte_ts_info *ei;
+	int ret;
+	unsigned long flag;
+
+	if (!desc)
+		return -EINVAL;
+
+	ei = desc->hte_data;
+
+	if (!ei || !ei->gdev)
+		return -EINVAL;
+
+	gdev = ei->gdev;
+	ts_id = desc->attr.line_id;
+
+	mutex_lock(&ei->req_mlock);
+
+	if (!test_bit(HTE_TS_REGISTERED, &ei->flags)) {
+		dev_dbg(gdev->sdev, "id:%d is not registered", ts_id);
+		ret = -EUSERS;
+		goto out;
+	}
+
+	spin_lock_irqsave(&ei->slock, flag);
+
+	if (en) {
+		if (!test_bit(HTE_TS_DISABLE, &ei->flags)) {
+			ret = 0;
+			goto out_unlock;
+		}
+
+		spin_unlock_irqrestore(&ei->slock, flag);
+		ret = gdev->chip->ops->enable(gdev->chip, ei->xlated_id);
+		if (ret) {
+			dev_warn(gdev->sdev, "id: %d enable failed\n",
+				 ts_id);
+			goto out;
+		}
+
+		spin_lock_irqsave(&ei->slock, flag);
+		clear_bit(HTE_TS_DISABLE, &ei->flags);
+	} else {
+		if (test_bit(HTE_TS_DISABLE, &ei->flags)) {
+			ret = 0;
+			goto out_unlock;
+		}
+
+		spin_unlock_irqrestore(&ei->slock, flag);
+		ret = gdev->chip->ops->disable(gdev->chip, ei->xlated_id);
+		if (ret) {
+			dev_warn(gdev->sdev, "id: %d disable failed\n",
+				 ts_id);
+			goto out;
+		}
+
+		spin_lock_irqsave(&ei->slock, flag);
+		set_bit(HTE_TS_DISABLE, &ei->flags);
+	}
+
+out_unlock:
+	spin_unlock_irqrestore(&ei->slock, flag);
+out:
+	mutex_unlock(&ei->req_mlock);
+	return ret;
+}
+
+/**
+ * hte_disable_ts() - Disable timestamp on given descriptor.
+ *
+ * The API does not release any resources associated with desc.
+ *
+ * @desc: ts descriptor, this is the same as returned by the request API.
+ *
+ * Context: Holds mutex lock, not suitable from atomic context.
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int hte_disable_ts(struct hte_ts_desc *desc)
+{
+	return hte_ts_dis_en_common(desc, false);
+}
+EXPORT_SYMBOL_GPL(hte_disable_ts);
+
+/**
+ * hte_enable_ts() - Enable timestamp on given descriptor.
+ *
+ * @desc: ts descriptor, this is the same as returned by the request API.
+ *
+ * Context: Holds mutex lock, not suitable from atomic context.
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int hte_enable_ts(struct hte_ts_desc *desc)
+{
+	return hte_ts_dis_en_common(desc, true);
+}
+EXPORT_SYMBOL_GPL(hte_enable_ts);
+
+static void hte_do_cb_work(struct work_struct *w)
+{
+	unsigned long flag;
+	struct hte_ts_info *ei = container_of(w, struct hte_ts_info, cb_work);
+
+	if (unlikely(!ei->tcb))
+		return;
+
+	ei->tcb(ei->cl_data);
+
+	spin_lock_irqsave(&ei->slock, flag);
+	clear_bit(HTE_TS_QUEUE_WK, &ei->flags);
+	spin_unlock_irqrestore(&ei->slock, flag);
+}
+
+static int __hte_req_ts(struct hte_ts_desc *desc, hte_ts_cb_t cb,
+			hte_ts_sec_cb_t tcb, void *data)
+{
+	int ret;
+	struct hte_device *gdev;
+	struct hte_ts_info *ei = desc->hte_data;
+
+	gdev = ei->gdev;
+	/*
+	 * There is a chance that multiple consumers requesting same entity,
+	 * lock here.
+	 */
+	mutex_lock(&ei->req_mlock);
+
+	if (test_bit(HTE_TS_REGISTERED, &ei->flags) ||
+	    !test_bit(HTE_TS_REQ, &ei->flags)) {
+		dev_dbg(gdev->chip->dev, "id:%u req failed\n",
+			desc->attr.line_id);
+		ret = -EUSERS;
+		goto unlock;
+	}
+
+	ei->cb = cb;
+	ei->tcb = tcb;
+	if (tcb)
+		INIT_WORK(&ei->cb_work, hte_do_cb_work);
+
+	ret = gdev->chip->ops->request(gdev->chip, desc, ei->xlated_id);
+	if (ret < 0) {
+		dev_err(gdev->chip->dev, "ts request failed\n");
+		goto unlock;
+	}
+
+	ei->cl_data = data;
+	ei->seq = 1;
+
+	atomic_inc(&gdev->ts_req);
+
+	ei->line_name = NULL;
+	if (!desc->attr.name) {
+		ei->line_name = kzalloc(HTE_TS_NAME_LEN, GFP_KERNEL);
+		if (ei->line_name)
+			scnprintf(ei->line_name, HTE_TS_NAME_LEN, "ts_%u",
+				  desc->attr.line_id);
+	}
+
+	hte_ts_dbgfs_init(desc->attr.name == NULL ?
+			  ei->line_name : desc->attr.name, ei);
+	set_bit(HTE_TS_REGISTERED, &ei->flags);
+
+	dev_dbg(gdev->chip->dev, "id: %u, xlated id:%u",
+		desc->attr.line_id, ei->xlated_id);
+
+	ret = 0;
+
+unlock:
+	mutex_unlock(&ei->req_mlock);
+
+	return ret;
+}
+
+static int hte_bind_ts_info_locked(struct hte_ts_info *ei,
+				   struct hte_ts_desc *desc, u32 x_id)
+{
+	int ret = 0;
+
+	mutex_lock(&ei->req_mlock);
+
+	if (test_bit(HTE_TS_REQ, &ei->flags)) {
+		dev_dbg(ei->gdev->chip->dev, "id:%u is already requested\n",
+			desc->attr.line_id);
+		ret = -EUSERS;
+		goto out;
+	}
+
+	set_bit(HTE_TS_REQ, &ei->flags);
+	desc->hte_data = ei;
+	ei->xlated_id = x_id;
+
+out:
+	mutex_unlock(&ei->req_mlock);
+
+	return ret;
+}
+
+static struct hte_device *of_node_to_htedevice(struct device_node *np)
+{
+	struct hte_device *gdev;
+
+	spin_lock(&hte_lock);
+
+	list_for_each_entry(gdev, &hte_devices, list)
+		if (gdev->chip && gdev->chip->dev &&
+		    gdev->chip->dev->of_node == np) {
+			spin_unlock(&hte_lock);
+			return gdev;
+		}
+
+	spin_unlock(&hte_lock);
+
+	return ERR_PTR(-ENODEV);
+}
+
+static struct hte_device *hte_find_dev_from_linedata(struct hte_ts_desc *desc)
+{
+	struct hte_device *gdev;
+
+	spin_lock(&hte_lock);
+
+	list_for_each_entry(gdev, &hte_devices, list)
+		if (gdev->chip && gdev->chip->match_from_linedata) {
+			if (!gdev->chip->match_from_linedata(gdev->chip, desc))
+				continue;
+			spin_unlock(&hte_lock);
+			return gdev;
+		}
+
+	spin_unlock(&hte_lock);
+
+	return ERR_PTR(-ENODEV);
+}
+
+/**
+ * of_hte_req_count - Return the number of entities to timestamp.
+ *
+ * The function returns the total count of the requested entities to timestamp
+ * by parsing device tree.
+ *
+ * @dev: The HTE consumer.
+ *
+ * Returns: Positive number on success, -ENOENT if no entries,
+ * -EINVAL for other errors.
+ */
+int of_hte_req_count(struct device *dev)
+{
+	int count;
+
+	if (!dev || !dev->of_node)
+		return -EINVAL;
+
+	count = of_count_phandle_with_args(dev->of_node, "timestamps",
+					   "#timestamp-cells");
+
+	return count ? count : -ENOENT;
+}
+EXPORT_SYMBOL_GPL(of_hte_req_count);
+
+static inline struct hte_device *hte_get_dev(struct hte_ts_desc *desc)
+{
+	return hte_find_dev_from_linedata(desc);
+}
+
+static struct hte_device *hte_of_get_dev(struct device *dev,
+					 struct hte_ts_desc *desc,
+					 int index,
+					 struct of_phandle_args *args,
+					 bool *free_name)
+{
+	int ret;
+	struct device_node *np;
+	char *temp;
+
+	if (!dev->of_node)
+		return ERR_PTR(-EINVAL);
+
+	np = dev->of_node;
+
+	if (!of_find_property(np, "timestamp-names", NULL)) {
+		/* Let hte core construct it during request time */
+		desc->attr.name = NULL;
+	} else {
+		ret = of_property_read_string_index(np, "timestamp-names",
+						    index, &desc->attr.name);
+		if (ret) {
+			pr_err("can't parse \"timestamp-names\" property\n");
+			return ERR_PTR(ret);
+		}
+		*free_name = false;
+		if (desc->attr.name) {
+			temp = skip_spaces(desc->attr.name);
+			if (!*temp)
+				desc->attr.name = NULL;
+		}
+	}
+
+	ret = of_parse_phandle_with_args(np, "timestamps", "#timestamp-cells",
+					 index, args);
+	if (ret) {
+		pr_err("%s(): can't parse \"timestamps\" property\n",
+		       __func__);
+		return ERR_PTR(ret);
+	}
+
+	of_node_put(args->np);
+
+	return of_node_to_htedevice(args->np);
+}
+
+/**
+ * hte_ts_get() - The function to initialize and obtain HTE desc.
+ *
+ * The function initializes the consumer provided HTE descriptor. If consumer
+ * has device tree node, index is used to parse the line id and other details.
+ * The function needs to be called before using any request APIs.
+ *
+ * @dev: HTE consumer/client device, used in case of parsing device tree node.
+ * @desc: Pre-allocated timestamp descriptor.
+ * @index: The index will be used as an index to parse line_id from the
+ * device tree node if node is present.
+ *
+ * Context: Holds mutex lock.
+ * Returns: Returns 0 on success or negative error code on failure.
+ */
+int hte_ts_get(struct device *dev, struct hte_ts_desc *desc, int index)
+{
+	struct hte_device *gdev;
+	struct hte_ts_info *ei;
+	const struct fwnode_handle *fwnode;
+	struct of_phandle_args args;
+	u32 xlated_id;
+	int ret;
+	bool free_name;
+
+	if (!desc)
+		return -EINVAL;
+
+	fwnode = dev ? dev_fwnode(dev) : NULL;
+
+	if (is_of_node(fwnode))
+		gdev = hte_of_get_dev(dev, desc, index, &args, &free_name);
+	else
+		gdev = hte_get_dev(desc);
+
+	if (IS_ERR(gdev)) {
+		pr_err("%s() no hte dev found\n", __func__);
+		return PTR_ERR(gdev);
+	}
+
+	if (!try_module_get(gdev->owner))
+		return -ENODEV;
+
+	if (!gdev->chip) {
+		pr_err("%s(): requested id does not have provider\n",
+		       __func__);
+		ret = -ENODEV;
+		goto put;
+	}
+
+	if (is_of_node(fwnode)) {
+		if (!gdev->chip->xlate_of)
+			ret = -EINVAL;
+		else
+			ret = gdev->chip->xlate_of(gdev->chip, &args,
+						   desc, &xlated_id);
+	} else {
+		if (!gdev->chip->xlate_plat)
+			ret = -EINVAL;
+		else
+			ret = gdev->chip->xlate_plat(gdev->chip, desc,
+						     &xlated_id);
+	}
+
+	if (ret < 0)
+		goto put;
+
+	ei = &gdev->ei[xlated_id];
+
+	ret = hte_bind_ts_info_locked(ei, desc, xlated_id);
+	if (ret)
+		goto put;
+
+	ei->free_attr_name = free_name;
+
+	return 0;
+
+put:
+	module_put(gdev->owner);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hte_ts_get);
+
+static void __devm_hte_release_ts(void *res)
+{
+	hte_ts_put(res);
+}
+
+/**
+ * hte_request_ts_ns() - The API to request and enable hardware timestamp in
+ * nanoseconds.
+ *
+ * The entity is provider specific for example, GPIO lines, signals, buses
+ * etc...The API allocates necessary resources and enables the timestamp.
+ *
+ * @desc: Pre-allocated and initialized timestamp descriptor.
+ * @cb: Callback to push the timestamp data to consumer.
+ * @tcb: Optional callback. If its provided, subsystem initializes
+ * workqueue. It is called when cb returns HTE_RUN_SECOND_CB.
+ * @data: Client data, used during cb and tcb callbacks.
+ *
+ * Context: Holds mutex lock.
+ * Returns: Returns 0 on success or negative error code on failure.
+ */
+int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb,
+		      hte_ts_sec_cb_t tcb, void *data)
+{
+	int ret;
+	struct hte_ts_info *ei;
+
+	if (!desc || !desc->hte_data || !cb)
+		return -EINVAL;
+
+	ei = desc->hte_data;
+	if (!ei || !ei->gdev)
+		return -EINVAL;
+
+	ret = __hte_req_ts(desc, cb, tcb, data);
+	if (ret < 0) {
+		dev_err(ei->gdev->chip->dev,
+			"failed to request id: %d\n", desc->attr.line_id);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hte_request_ts_ns);
+
+/**
+ * devm_hte_request_ts_ns() - Resource managed API to request and enable
+ * hardware timestamp in nanoseconds.
+ *
+ * The entity is provider specific for example, GPIO lines, signals, buses
+ * etc...The API allocates necessary resources and enables the timestamp. It
+ * deallocates and disables automatically when the consumer exits.
+ *
+ * @dev: HTE consumer/client device.
+ * @desc: Pre-allocated and initialized timestamp descriptor.
+ * @cb: Callback to push the timestamp data to consumer.
+ * @tcb: Optional callback. If its provided, subsystem initializes
+ * workqueue. It is called when cb returns HTE_RUN_SECOND_CB.
+ * @data: Client data, used during cb and tcb callbacks.
+ *
+ * Context: Holds mutex lock.
+ * Returns: Returns 0 on success or negative error code on failure.
+ */
+int devm_hte_request_ts_ns(struct device *dev, struct hte_ts_desc *desc,
+			   hte_ts_cb_t cb, hte_ts_sec_cb_t tcb,
+			   void *data)
+{
+	int err;
+
+	if (!dev)
+		return -EINVAL;
+
+	err = hte_request_ts_ns(desc, cb, tcb, data);
+	if (err)
+		return err;
+
+	err = devm_add_action_or_reset(dev, __devm_hte_release_ts, desc);
+	if (err)
+		return err;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_hte_request_ts_ns);
+
+/**
+ * hte_init_line_attr() - Initialize line attributes.
+ *
+ * Zeroes out line attributes and initializes with provided arguments.
+ * The function needs to be called before calling any consumer facing
+ * functions.
+ *
+ * @desc: Pre-allocated timestamp descriptor.
+ * @line_id: line id.
+ * @edge_flags: edge flags related to line_id.
+ * @name: name of the line.
+ * @data: line data related to line_id.
+ *
+ * Context: Any.
+ * Returns: 0 on success or negative error code for the failure.
+ */
+int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id,
+		       unsigned long edge_flags, const char *name, void *data)
+{
+	if (!desc)
+		return -EINVAL;
+
+	memset(&desc->attr, 0, sizeof(desc->attr));
+
+	desc->attr.edge_flags = edge_flags;
+	desc->attr.line_id = line_id;
+	desc->attr.line_data = data;
+	if (name) {
+		name =  kstrdup_const(name, GFP_KERNEL);
+		if (!name)
+			return -ENOMEM;
+	}
+
+	desc->attr.name = name;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hte_init_line_attr);
+
+/**
+ * hte_get_clk_src_info() - Get the clock source information for a ts
+ * descriptor.
+ *
+ * @desc: ts descriptor, same as returned from request API.
+ * @ci: The API fills this structure with the clock information data.
+ *
+ * Context: Any context.
+ * Returns: 0 on success else negative error code on failure.
+ */
+int hte_get_clk_src_info(const struct hte_ts_desc *desc,
+			 struct hte_clk_info *ci)
+{
+	struct hte_chip *chip;
+	struct hte_ts_info *ei;
+
+	if (!desc || !desc->hte_data || !ci) {
+		pr_debug("%s:%d\n", __func__, __LINE__);
+		return -EINVAL;
+	}
+
+	ei = desc->hte_data;
+	if (!ei->gdev || !ei->gdev->chip)
+		return -EINVAL;
+
+	chip = ei->gdev->chip;
+	if (!chip->ops->get_clk_src_info)
+		return -EOPNOTSUPP;
+
+	return chip->ops->get_clk_src_info(chip, ci);
+}
+EXPORT_SYMBOL_GPL(hte_get_clk_src_info);
+
+/**
+ * hte_push_ts_ns() - Push timestamp data in nanoseconds.
+ *
+ * It is used by the provider to push timestamp data.
+ *
+ * @chip: The HTE chip, used during the registration.
+ * @xlated_id: entity id understood by both subsystem and provider, this is
+ * obtained from xlate callback during request API.
+ * @data: timestamp data.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int hte_push_ts_ns(const struct hte_chip *chip, u32 xlated_id,
+		   struct hte_ts_data *data)
+{
+	enum hte_return ret;
+	int st = 0;
+	struct hte_ts_info *ei;
+	unsigned long flag;
+
+	if (!chip || !data || !chip->gdev)
+		return -EINVAL;
+
+	if (xlated_id > chip->nlines)
+		return -EINVAL;
+
+	ei = &chip->gdev->ei[xlated_id];
+
+	spin_lock_irqsave(&ei->slock, flag);
+
+	/* timestamp sequence counter */
+	data->seq = ei->seq++;
+
+	if (!test_bit(HTE_TS_REGISTERED, &ei->flags) ||
+	    test_bit(HTE_TS_DISABLE, &ei->flags)) {
+		dev_dbg(chip->dev, "Unknown timestamp push\n");
+		atomic_inc(&ei->dropped_ts);
+		st = -EINVAL;
+		goto unlock;
+	}
+
+	ret = ei->cb(data, ei->cl_data);
+	if (ret == HTE_RUN_SECOND_CB && ei->tcb) {
+		queue_work(system_unbound_wq, &ei->cb_work);
+		set_bit(HTE_TS_QUEUE_WK, &ei->flags);
+	}
+
+unlock:
+	spin_unlock_irqrestore(&ei->slock, flag);
+
+	return st;
+}
+EXPORT_SYMBOL_GPL(hte_push_ts_ns);
+
+static int hte_register_chip(struct hte_chip *chip)
+{
+	struct hte_device *gdev;
+	u32 i;
+
+	if (!chip || !chip->dev || !chip->dev->of_node)
+		return -EINVAL;
+
+	if (!chip->ops || !chip->ops->request || !chip->ops->release) {
+		dev_err(chip->dev, "Driver needs to provide ops\n");
+		return -EINVAL;
+	}
+
+	gdev = kzalloc(struct_size(gdev, ei, chip->nlines), GFP_KERNEL);
+	if (!gdev)
+		return -ENOMEM;
+
+	gdev->chip = chip;
+	chip->gdev = gdev;
+	gdev->nlines = chip->nlines;
+	gdev->sdev = chip->dev;
+
+	for (i = 0; i < chip->nlines; i++) {
+		gdev->ei[i].gdev = gdev;
+		mutex_init(&gdev->ei[i].req_mlock);
+		spin_lock_init(&gdev->ei[i].slock);
+	}
+
+	if (chip->dev->driver)
+		gdev->owner = chip->dev->driver->owner;
+	else
+		gdev->owner = THIS_MODULE;
+
+	of_node_get(chip->dev->of_node);
+
+	INIT_LIST_HEAD(&gdev->list);
+
+	spin_lock(&hte_lock);
+	list_add_tail(&gdev->list, &hte_devices);
+	spin_unlock(&hte_lock);
+
+	hte_chip_dbgfs_init(gdev);
+
+	dev_dbg(chip->dev, "Added hte chip\n");
+
+	return 0;
+}
+
+static int hte_unregister_chip(struct hte_chip *chip)
+{
+	struct hte_device *gdev;
+
+	if (!chip)
+		return -EINVAL;
+
+	gdev = chip->gdev;
+
+	spin_lock(&hte_lock);
+	list_del(&gdev->list);
+	spin_unlock(&hte_lock);
+
+	gdev->chip = NULL;
+
+	of_node_put(chip->dev->of_node);
+	debugfs_remove_recursive(gdev->dbg_root);
+	kfree(gdev);
+
+	dev_dbg(chip->dev, "Removed hte chip\n");
+
+	return 0;
+}
+
+static void _hte_devm_unregister_chip(void *chip)
+{
+	hte_unregister_chip(chip);
+}
+
+/**
+ * devm_hte_register_chip() - Resource managed API to register HTE chip.
+ *
+ * It is used by the provider to register itself with the HTE subsystem.
+ * The unregistration is done automatically when the provider exits.
+ *
+ * @chip: the HTE chip to add to subsystem.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+int devm_hte_register_chip(struct hte_chip *chip)
+{
+	int err;
+
+	err = hte_register_chip(chip);
+	if (err)
+		return err;
+
+	err = devm_add_action_or_reset(chip->dev, _hte_devm_unregister_chip,
+				       chip);
+	if (err)
+		return err;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_hte_register_chip);
diff --git a/include/linux/hte.h b/include/linux/hte.h
new file mode 100644
index 000000000000..8289055061ab
--- /dev/null
+++ b/include/linux/hte.h
@@ -0,0 +1,271 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __LINUX_HTE_H
+#define __LINUX_HTE_H
+
+#include <linux/errno.h>
+
+struct hte_chip;
+struct hte_device;
+struct of_phandle_args;
+
+/**
+ * enum hte_edge - HTE line edge flags.
+ *
+ * @HTE_EDGE_NO_SETUP: No edge setup. In this case consumer will setup edges,
+ * for example during request irq call.
+ * @HTE_RISING_EDGE_TS: Rising edge.
+ * @HTE_FALLING_EDGE_TS: Falling edge.
+ *
+ */
+enum hte_edge {
+	HTE_EDGE_NO_SETUP = 1U << 0,
+	HTE_RISING_EDGE_TS = 1U << 1,
+	HTE_FALLING_EDGE_TS = 1U << 2,
+};
+
+/**
+ * enum hte_return - HTE subsystem return values used during callback.
+ *
+ * @HTE_CB_HANDLED: The consumer handled the data.
+ * @HTE_RUN_SECOND_CB: The consumer needs further processing, in that case
+ * HTE subsystem calls secondary callback provided by the consumer where it
+ * is allowed to sleep.
+ */
+enum hte_return {
+	HTE_CB_HANDLED,
+	HTE_RUN_SECOND_CB,
+};
+
+/**
+ * struct hte_ts_data - HTE timestamp data.
+ *
+ * @tsc: Timestamp value.
+ * @seq: Sequence counter of the timestamps.
+ * @raw_level: Level of the line at the timestamp if provider supports it,
+ * -1 otherwise.
+ */
+struct hte_ts_data {
+	u64 tsc;
+	u64 seq;
+	int raw_level;
+};
+
+/**
+ * struct hte_clk_info - Clock source info that HTE provider uses to timestamp.
+ *
+ * @hz: Supported clock rate in HZ, for example 1KHz clock = 1000.
+ * @type: Supported clock type.
+ */
+struct hte_clk_info {
+	u64 hz;
+	clockid_t type;
+};
+
+/**
+ * typedef hte_ts_cb_t - HTE timestamp data processing primary callback.
+ *
+ * The callback is used to push timestamp data to the client and it is
+ * not allowed to sleep.
+ *
+ * @ts: HW timestamp data.
+ * @data: Client supplied data.
+ */
+typedef enum hte_return (*hte_ts_cb_t)(struct hte_ts_data *ts, void *data);
+
+/**
+ * typedef hte_ts_sec_cb_t - HTE timestamp data processing secondary callback.
+ *
+ * This is used when the client needs further processing where it is
+ * allowed to sleep.
+ *
+ * @data: Client supplied data.
+ *
+ */
+typedef enum hte_return (*hte_ts_sec_cb_t)(void *data);
+
+/**
+ * struct hte_line_attr - Line attributes.
+ *
+ * @line_id: The logical ID understood by the consumers and providers.
+ * @line_data: Line data related to line_id.
+ * @edge_flags: Edge setup flags.
+ * @name: Descriptive name of the entity that is being monitored for the
+ * hardware timestamping. If null, HTE core will construct the name.
+ *
+ */
+struct hte_line_attr {
+	u32 line_id;
+	void *line_data;
+	unsigned long edge_flags;
+	const char *name;
+};
+
+/**
+ * struct hte_ts_desc - HTE timestamp descriptor.
+ *
+ * This structure is a communication token between consumers to subsystem
+ * and subsystem to providers.
+ *
+ * @attr: The line attributes.
+ * @hte_data: Subsystem's private data, set by HTE subsystem.
+ */
+struct hte_ts_desc {
+	struct hte_line_attr attr;
+	void *hte_data;
+};
+
+/**
+ * struct hte_ops - HTE operations set by providers.
+ *
+ * @request: Hook for requesting a HTE timestamp. Returns 0 on success,
+ * non-zero for failures.
+ * @release: Hook for releasing a HTE timestamp. Returns 0 on success,
+ * non-zero for failures.
+ * @enable: Hook to enable the specified timestamp. Returns 0 on success,
+ * non-zero for failures.
+ * @disable: Hook to disable specified timestamp. Returns 0 on success,
+ * non-zero for failures.
+ * @get_clk_src_info: Hook to get the clock information the provider uses
+ * to timestamp. Returns 0 for success and negative error code for failure. On
+ * success HTE subsystem fills up provided struct hte_clk_info.
+ *
+ * xlated_id parameter is used to communicate between HTE subsystem and the
+ * providers and is translated by the provider.
+ */
+struct hte_ops {
+	int (*request)(struct hte_chip *chip, struct hte_ts_desc *desc,
+		       u32 xlated_id);
+	int (*release)(struct hte_chip *chip, struct hte_ts_desc *desc,
+		       u32 xlated_id);
+	int (*enable)(struct hte_chip *chip, u32 xlated_id);
+	int (*disable)(struct hte_chip *chip, u32 xlated_id);
+	int (*get_clk_src_info)(struct hte_chip *chip,
+				struct hte_clk_info *ci);
+};
+
+/**
+ * struct hte_chip - Abstract HTE chip.
+ *
+ * @name: functional name of the HTE IP block.
+ * @dev: device providing the HTE.
+ * @ops: callbacks for this HTE.
+ * @nlines: number of lines/signals supported by this chip.
+ * @xlate_of: Callback which translates consumer supplied logical ids to
+ * physical ids, return 0 for the success and negative for the failures.
+ * It stores (between 0 to @nlines) in xlated_id parameter for the success.
+ * @xlate_plat: Same as above but for the consumers with no DT node.
+ * @match_from_linedata: Match HTE device using the line_data.
+ * @of_hte_n_cells: Number of cells used to form the HTE specifier.
+ * @gdev: HTE subsystem abstract device, internal to the HTE subsystem.
+ * @data: chip specific private data.
+ */
+struct hte_chip {
+	const char *name;
+	struct device *dev;
+	const struct hte_ops *ops;
+	u32 nlines;
+	int (*xlate_of)(struct hte_chip *gc,
+			const struct of_phandle_args *args,
+			struct hte_ts_desc *desc, u32 *xlated_id);
+	int (*xlate_plat)(struct hte_chip *gc, struct hte_ts_desc *desc,
+			 u32 *xlated_id);
+	bool (*match_from_linedata)(const struct hte_chip *chip,
+				    const struct hte_ts_desc *hdesc);
+	u8 of_hte_n_cells;
+
+	struct hte_device *gdev;
+	void *data;
+};
+
+#if IS_ENABLED(CONFIG_HTE)
+/* HTE APIs for the providers */
+int devm_hte_register_chip(struct hte_chip *chip);
+int hte_push_ts_ns(const struct hte_chip *chip, u32 xlated_id,
+		   struct hte_ts_data *data);
+
+/* HTE APIs for the consumers */
+int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id,
+		       unsigned long edge_flags, const char *name,
+		       void *data);
+int hte_ts_get(struct device *dev, struct hte_ts_desc *desc, int index);
+int hte_ts_put(struct hte_ts_desc *desc);
+int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb,
+		      hte_ts_sec_cb_t tcb, void *data);
+int devm_hte_request_ts_ns(struct device *dev, struct hte_ts_desc *desc,
+			   hte_ts_cb_t cb, hte_ts_sec_cb_t tcb, void *data);
+int of_hte_req_count(struct device *dev);
+int hte_enable_ts(struct hte_ts_desc *desc);
+int hte_disable_ts(struct hte_ts_desc *desc);
+int hte_get_clk_src_info(const struct hte_ts_desc *desc,
+			 struct hte_clk_info *ci);
+
+#else /* !CONFIG_HTE */
+static inline int devm_hte_register_chip(struct hte_chip *chip)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int hte_push_ts_ns(const struct hte_chip *chip,
+				 u32 xlated_id,
+				 const struct hte_ts_data *data)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id,
+				     unsigned long edge_flags,
+				     const char *name, void *data)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int hte_ts_get(struct device *dev, struct hte_ts_desc *desc,
+			     int index)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int hte_ts_put(struct hte_ts_desc *desc)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb,
+				    hte_ts_sec_cb_t tcb, void *data)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int devm_hte_request_ts_ns(struct device *dev,
+					 struct hte_ts_desc *desc,
+					 hte_ts_cb_t cb,
+					 hte_ts_sec_cb_t tcb,
+					 void *data)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int of_hte_req_count(struct device *dev)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int hte_enable_ts(struct hte_ts_desc *desc)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int hte_disable_ts(struct hte_ts_desc *desc)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int hte_get_clk_src_info(const struct hte_ts_desc *desc,
+				       struct hte_clk_info *ci)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* !CONFIG_HTE */
+
+#endif
-- 
cgit v1.2.3


From 42112dd77b74220e6a1f4a71bb51ca3f583d3842 Mon Sep 17 00:00:00 2001
From: Dipen Patel <dipenp@nvidia.com>
Date: Fri, 22 Apr 2022 13:52:16 -0700
Subject: gpiolib: Add HTE support

Some GPIO chip can provide hardware timestamp support on its GPIO lines
, in order to support that, additional API needs to be added which
can talk to both GPIO chip and HTE (hardware timestamping engine)
providers if there is any dependencies. This patch introduces optional
hooks to enable and disable hardware timestamping related features
in the GPIO controller chip.

Signed-off-by: Dipen Patel <dipenp@nvidia.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpio/gpiolib.c        | 58 +++++++++++++++++++++++++++++++++++++++++++
 drivers/gpio/gpiolib.h        |  1 +
 include/linux/gpio/consumer.h | 16 ++++++++++--
 include/linux/gpio/driver.h   | 10 ++++++++
 4 files changed, 83 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index e59884cc12a7..60cd7cc33647 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2434,6 +2434,64 @@ set_output_flag:
 }
 EXPORT_SYMBOL_GPL(gpiod_direction_output);
 
+/**
+ * gpiod_enable_hw_timestamp_ns - Enable hardware timestamp in nanoseconds.
+ *
+ * @desc: GPIO to enable.
+ * @flags: Flags related to GPIO edge.
+ *
+ * Return 0 in case of success, else negative error code.
+ */
+int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags)
+{
+	int ret = 0;
+	struct gpio_chip *gc;
+
+	VALIDATE_DESC(desc);
+
+	gc = desc->gdev->chip;
+	if (!gc->en_hw_timestamp) {
+		gpiod_warn(desc, "%s: hw ts not supported\n", __func__);
+		return -ENOTSUPP;
+	}
+
+	ret = gc->en_hw_timestamp(gc, gpio_chip_hwgpio(desc), flags);
+	if (ret)
+		gpiod_warn(desc, "%s: hw ts request failed\n", __func__);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gpiod_enable_hw_timestamp_ns);
+
+/**
+ * gpiod_disable_hw_timestamp_ns - Disable hardware timestamp.
+ *
+ * @desc: GPIO to disable.
+ * @flags: Flags related to GPIO edge, same value as used during enable call.
+ *
+ * Return 0 in case of success, else negative error code.
+ */
+int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags)
+{
+	int ret = 0;
+	struct gpio_chip *gc;
+
+	VALIDATE_DESC(desc);
+
+	gc = desc->gdev->chip;
+	if (!gc->dis_hw_timestamp) {
+		gpiod_warn(desc, "%s: hw ts not supported\n", __func__);
+		return -ENOTSUPP;
+	}
+
+	ret = gc->dis_hw_timestamp(gc, gpio_chip_hwgpio(desc), flags);
+	if (ret)
+		gpiod_warn(desc, "%s: hw ts release failed\n", __func__);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gpiod_disable_hw_timestamp_ns);
+
 /**
  * gpiod_set_config - sets @config for a GPIO
  * @desc: descriptor of the GPIO for which to set the configuration
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 06f3faa9fbef..29a7d39062b3 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -158,6 +158,7 @@ struct gpio_desc {
 #define FLAG_EDGE_RISING     16	/* GPIO CDEV detects rising edge events */
 #define FLAG_EDGE_FALLING    17	/* GPIO CDEV detects falling edge events */
 #define FLAG_EVENT_CLOCK_REALTIME	18 /* GPIO CDEV reports REALTIME timestamps in events */
+#define FLAG_EVENT_CLOCK_HTE		19 /* GPIO CDEV reports hardware timestamps in events */
 
 	/* Connection label */
 	const char		*label;
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index c3aa8b330e1c..7eaec081ae6c 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -109,6 +109,8 @@ int gpiod_get_direction(struct gpio_desc *desc);
 int gpiod_direction_input(struct gpio_desc *desc);
 int gpiod_direction_output(struct gpio_desc *desc, int value);
 int gpiod_direction_output_raw(struct gpio_desc *desc, int value);
+int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags);
+int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags);
 
 /* Value get/set from non-sleeping context */
 int gpiod_get_value(const struct gpio_desc *desc);
@@ -350,8 +352,18 @@ static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value)
 	WARN_ON(desc);
 	return -ENOSYS;
 }
-
-
+static inline int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc,
+					       unsigned long flags)
+{
+	WARN_ON(desc);
+	return -ENOSYS;
+}
+static inline int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc,
+						unsigned long flags)
+{
+	WARN_ON(desc);
+	return -ENOSYS;
+}
 static inline int gpiod_get_value(const struct gpio_desc *desc)
 {
 	/* GPIO can never have been requested */
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 98c93510640e..0ce96ebdaa36 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -323,6 +323,10 @@ struct gpio_irq_chip {
  * @add_pin_ranges: optional routine to initialize pin ranges, to be used when
  *	requires special mapping of the pins that provides GPIO functionality.
  *	It is called after adding GPIO chip and before adding IRQ chip.
+ * @en_hw_timestamp: Dependent on GPIO chip, an optional routine to
+ *	enable hardware timestamp.
+ * @dis_hw_timestamp: Dependent on GPIO chip, an optional routine to
+ *	disable hardware timestamp.
  * @base: identifies the first GPIO number handled by this chip;
  *	or, if negative during registration, requests dynamic ID allocation.
  *	DEPRECATION: providing anything non-negative and nailing the base
@@ -419,6 +423,12 @@ struct gpio_chip {
 
 	int			(*add_pin_ranges)(struct gpio_chip *gc);
 
+	int			(*en_hw_timestamp)(struct gpio_chip *gc,
+						   u32 offset,
+						   unsigned long flags);
+	int			(*dis_hw_timestamp)(struct gpio_chip *gc,
+						    u32 offset,
+						    unsigned long flags);
 	int			base;
 	u16			ngpio;
 	u16			offset;
-- 
cgit v1.2.3


From 3ae2722c93c916b47bfe47a4326e88cc4abb9bf4 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Apr 2022 14:55:57 +0200
Subject: mmc: mmci: Remove custom ios handler

The custom boardfile ios handler isn't used anywhere in the
kernel. Delete it.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20220427125557.1608825-1-linus.walleij@linaro.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/mmci.c   | 4 ----
 include/linux/amba/mmci.h | 6 ------
 2 files changed, 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index f3cf3152a397..01159eaf8694 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1748,10 +1748,6 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	unsigned long flags;
 	int ret;
 
-	if (host->plat->ios_handler &&
-		host->plat->ios_handler(mmc_dev(mmc), ios))
-			dev_err(mmc_dev(mmc), "platform ios_handler failed\n");
-
 	switch (ios->power_mode) {
 	case MMC_POWER_OFF:
 		if (!IS_ERR(mmc->supply.vmmc))
diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h
index c92ebc39fc1f..6f96dc2209c0 100644
--- a/include/linux/amba/mmci.h
+++ b/include/linux/amba/mmci.h
@@ -13,17 +13,11 @@
  * @ocr_mask: available voltages on the 4 pins from the block, this
  * is ignored if a regulator is used, see the MMC_VDD_* masks in
  * mmc/host.h
- * @ios_handler: a callback function to act on specfic ios changes,
- * used for example to control a levelshifter
- * mask into a value to be binary (or set some other custom bits
- * in MMCIPWR) or:ed and written into the MMCIPWR register of the
- * block.  May also control external power based on the power_mode.
  * @status: if no GPIO line was given to the block in this function will
  * be called to determine whether a card is present in the MMC slot or not
  */
 struct mmci_platform_data {
 	unsigned int ocr_mask;
-	int (*ios_handler)(struct device *, struct mmc_ios *);
 	unsigned int (*status)(struct device *);
 };
 
-- 
cgit v1.2.3


From 00ce3873f730fb24c657854ec04374358e711838 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 4 May 2022 10:17:32 +0200
Subject: opp: Add apis to retrieve opps with interconnect bandwidth

Add dev_pm_opp_find_bw_ceil and dev_pm_opp_find_bw_floor to retrieve opps
based on interconnect associated with the opp and bandwidth. The index
variable is the index of the interconnect as specified in the opp table
in Devicetree.

Co-developed-by: Thara Gopinath <thara.gopinath@linaro.org>
Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/core.c     | 120 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pm_opp.h |  19 ++++++++
 2 files changed, 139 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 6725ff27c35e..48606f52759d 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -729,6 +729,126 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil_by_volt);
 
+/**
+ * dev_pm_opp_find_bw_ceil() - Search for a rounded ceil bandwidth
+ * @dev:	device for which we do this operation
+ * @freq:	start bandwidth
+ * @index:	which bandwidth to compare, in case of OPPs with several values
+ *
+ * Search for the matching floor *available* OPP from a starting bandwidth
+ * for a device.
+ *
+ * Return: matching *opp and refreshes *bw accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR. Error return
+ * values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev,
+					   unsigned int *bw, int index)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	if (!dev || !bw) {
+		dev_err(dev, "%s: Invalid argument bw=%p\n", __func__, bw);
+		return ERR_PTR(-EINVAL);
+	}
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
+
+	if (index >= opp_table->path_count)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->bandwidth) {
+			if (temp_opp->bandwidth[index].peak >= *bw) {
+				opp = temp_opp;
+				*bw = opp->bandwidth[index].peak;
+
+				/* Increment the reference count of OPP */
+				dev_pm_opp_get(opp);
+				break;
+			}
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_bw_ceil);
+
+/**
+ * dev_pm_opp_find_bw_floor() - Search for a rounded floor bandwidth
+ * @dev:	device for which we do this operation
+ * @freq:	start bandwidth
+ * @index:	which bandwidth to compare, in case of OPPs with several values
+ *
+ * Search for the matching floor *available* OPP from a starting bandwidth
+ * for a device.
+ *
+ * Return: matching *opp and refreshes *bw accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR. Error return
+ * values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev,
+					    unsigned int *bw, int index)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	if (!dev || !bw) {
+		dev_err(dev, "%s: Invalid argument bw=%p\n", __func__, bw);
+		return ERR_PTR(-EINVAL);
+	}
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
+
+	if (index >= opp_table->path_count)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->bandwidth) {
+			/* go to the next node, before choosing prev */
+			if (temp_opp->bandwidth[index].peak > *bw)
+				break;
+			opp = temp_opp;
+		}
+	}
+
+	/* Increment the reference count of OPP */
+	if (!IS_ERR(opp))
+		dev_pm_opp_get(opp);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	if (!IS_ERR(opp))
+		*bw = opp->bandwidth[index].peak;
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_bw_floor);
+
 static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 			    struct dev_pm_opp_supply *supply)
 {
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 0d85a63a1f78..dcea178868c9 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -129,6 +129,13 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
 
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq);
+
+struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev,
+					   unsigned int *bw, int index);
+
+struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev,
+					   unsigned int *bw, int index);
+
 void dev_pm_opp_put(struct dev_pm_opp *opp);
 
 int dev_pm_opp_add(struct device *dev, unsigned long freq,
@@ -279,6 +286,18 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev,
+					unsigned int *bw, int index)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev,
+					unsigned int *bw, int index)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {}
 
 static inline int dev_pm_opp_add(struct device *dev, unsigned long freq,
-- 
cgit v1.2.3


From 22079af7df5a5dfef1c4d160abfd43035211759e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 4 May 2022 15:40:22 +0530
Subject: opp: Reorder definition of ceil/floor helpers

Reorder the helpers to keep all freq specific ones, followed by level
and bw.

No functional change.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/core.c     | 194 ++++++++++++++++++++++++-------------------------
 include/linux/pm_opp.h |  22 +++---
 2 files changed, 108 insertions(+), 108 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 48606f52759d..84063eaebb91 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -456,103 +456,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
 
-/**
- * dev_pm_opp_find_level_exact() - search for an exact level
- * @dev:		device for which we do this operation
- * @level:		level to search for
- *
- * Return: Searches for exact match in the opp table and returns pointer to the
- * matching opp if found, else returns ERR_PTR in case of error and should
- * be handled using IS_ERR. Error return values can be:
- * EINVAL:	for bad pointer
- * ERANGE:	no match found for search
- * ENODEV:	if device not found in list of registered devices
- *
- * The callers are required to call dev_pm_opp_put() for the returned OPP after
- * use.
- */
-struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev,
-					       unsigned int level)
-{
-	struct opp_table *opp_table;
-	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		int r = PTR_ERR(opp_table);
-
-		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
-		return ERR_PTR(r);
-	}
-
-	mutex_lock(&opp_table->lock);
-
-	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
-		if (temp_opp->level == level) {
-			opp = temp_opp;
-
-			/* Increment the reference count of OPP */
-			dev_pm_opp_get(opp);
-			break;
-		}
-	}
-
-	mutex_unlock(&opp_table->lock);
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return opp;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_exact);
-
-/**
- * dev_pm_opp_find_level_ceil() - search for an rounded up level
- * @dev:		device for which we do this operation
- * @level:		level to search for
- *
- * Return: Searches for rounded up match in the opp table and returns pointer
- * to the  matching opp if found, else returns ERR_PTR in case of error and
- * should be handled using IS_ERR. Error return values can be:
- * EINVAL:	for bad pointer
- * ERANGE:	no match found for search
- * ENODEV:	if device not found in list of registered devices
- *
- * The callers are required to call dev_pm_opp_put() for the returned OPP after
- * use.
- */
-struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
-					      unsigned int *level)
-{
-	struct opp_table *opp_table;
-	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		int r = PTR_ERR(opp_table);
-
-		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
-		return ERR_PTR(r);
-	}
-
-	mutex_lock(&opp_table->lock);
-
-	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
-		if (temp_opp->available && temp_opp->level >= *level) {
-			opp = temp_opp;
-			*level = opp->level;
-
-			/* Increment the reference count of OPP */
-			dev_pm_opp_get(opp);
-			break;
-		}
-	}
-
-	mutex_unlock(&opp_table->lock);
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return opp;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_ceil);
-
 static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 						   unsigned long *freq)
 {
@@ -729,6 +632,103 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil_by_volt);
 
+/**
+ * dev_pm_opp_find_level_exact() - search for an exact level
+ * @dev:		device for which we do this operation
+ * @level:		level to search for
+ *
+ * Return: Searches for exact match in the opp table and returns pointer to the
+ * matching opp if found, else returns ERR_PTR in case of error and should
+ * be handled using IS_ERR. Error return values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev,
+					       unsigned int level)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		int r = PTR_ERR(opp_table);
+
+		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
+		return ERR_PTR(r);
+	}
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->level == level) {
+			opp = temp_opp;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
+			break;
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_exact);
+
+/**
+ * dev_pm_opp_find_level_ceil() - search for an rounded up level
+ * @dev:		device for which we do this operation
+ * @level:		level to search for
+ *
+ * Return: Searches for rounded up match in the opp table and returns pointer
+ * to the  matching opp if found, else returns ERR_PTR in case of error and
+ * should be handled using IS_ERR. Error return values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
+					      unsigned int *level)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		int r = PTR_ERR(opp_table);
+
+		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
+		return ERR_PTR(r);
+	}
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->level >= *level) {
+			opp = temp_opp;
+			*level = opp->level;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
+			break;
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_ceil);
+
 /**
  * dev_pm_opp_find_bw_ceil() - Search for a rounded ceil bandwidth
  * @dev:	device for which we do this operation
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index dcea178868c9..6708b4ec244d 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -117,16 +117,16 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev);
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
 					      bool available);
-struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev,
-					       unsigned int level);
-struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
-					      unsigned int *level);
-
 struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					      unsigned long *freq);
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
 						     unsigned long u_volt);
 
+struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev,
+					       unsigned int level);
+struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
+					      unsigned int *level);
+
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq);
 
@@ -250,12 +250,6 @@ static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 	return 0;
 }
 
-static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
-					unsigned long freq, bool available)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
 static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev,
 					unsigned int level)
 {
@@ -268,6 +262,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
+					unsigned long freq, bool available)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					unsigned long *freq)
 {
-- 
cgit v1.2.3


From 34453c2e9f799d02f5f379519495208bbd96a935 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 5 Apr 2022 19:23:24 +0100
Subject: irqchip/gic-v3: Exposes bit values for GICR_CTLR.{IR, CES}

As we're about to expose GICR_CTLR.{IR,CES} to guests, populate
the include file with the architectural values.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Oliver Upton <oupton@google.com>
Link: https://lore.kernel.org/r/20220405182327.205520-2-maz@kernel.org
---
 include/linux/irqchip/arm-gic-v3.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 12d91f0dedf9..728691365464 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -127,6 +127,8 @@
 #define GICR_PIDR2			GICD_PIDR2
 
 #define GICR_CTLR_ENABLE_LPIS		(1UL << 0)
+#define GICR_CTLR_CES			(1UL << 1)
+#define GICR_CTLR_IR			(1UL << 2)
 #define GICR_CTLR_RWP			(1UL << 3)
 
 #define GICR_TYPER_CPU_NUMBER(r)	(((r) >> 8) & 0xffff)
-- 
cgit v1.2.3


From ec69dfbdc426f22a9557e5c5408d7902fe0e0144 Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@linaro.org>
Date: Mon, 2 May 2022 14:54:06 -0700
Subject: soc: qcom: llcc: Add sc8180x and sc8280xp configurations

Add LLCC configuration data for the SC8180X and SC8280XP platforms,
based on the downstream tables.

Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Sai Prakash Ranjan <quic_saipraka@quicinc.com>
Link: https://lore.kernel.org/r/20220502215406.612967-3-bjorn.andersson@linaro.org
---
 drivers/soc/qcom/llcc-qcom.c       | 60 ++++++++++++++++++++++++++++++++++++++
 include/linux/soc/qcom/llcc-qcom.h |  2 ++
 2 files changed, 62 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c
index 85ba8209b182..4b143cf7b4ce 100644
--- a/drivers/soc/qcom/llcc-qcom.c
+++ b/drivers/soc/qcom/llcc-qcom.c
@@ -130,6 +130,50 @@ static const struct llcc_slice_config sc7280_data[] =  {
 	{ LLCC_MODPE,    29, 64,  1, 1, 0x3f, 0x0, 0, 0, 0, 1, 0, 0},
 };
 
+static const struct llcc_slice_config sc8180x_data[] = {
+	{ LLCC_CPUSS,    1, 6144,  1, 1, 0xfff, 0x0,   0, 0, 0, 1, 1 },
+	{ LLCC_VIDSC0,   2, 512,   2, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_VIDSC1,   3, 512,   2, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_AUDIO,    6, 1024,  1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_MDMHPGRW, 7, 3072,  1, 1, 0x3ff, 0xc00, 0, 0, 0, 1, 0 },
+	{ LLCC_MDM,      8, 3072,  1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_MODHW,    9, 1024,  1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_CMPT,     10, 6144, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_GPUHTW,   11, 1024, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_GPU,      12, 5120, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_MMUHWT,   13, 1024, 1, 1, 0xfff, 0x0,   0, 0, 0, 0, 1 },
+	{ LLCC_CMPTDMA,  15, 6144, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_DISP,     16, 6144, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_VIDFW,    17, 1024, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_MDMHPFX,  20, 1024, 2, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_MDMPNG,   21, 1024, 0, 1, 0xc,   0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_AUDHW,    22, 1024, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_NPU,      23, 6144, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_WLHW,     24, 6144, 1, 1, 0xfff, 0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_MODPE,    29, 512,  1, 1, 0xc,   0x0,   0, 0, 0, 1, 0 },
+	{ LLCC_APTCM,    30, 512,  3, 1, 0x0,   0x1,   1, 0, 0, 1, 0 },
+	{ LLCC_WRCACHE,  31, 128,  1, 1, 0xfff, 0x0,   0, 0, 0, 0, 0 },
+};
+
+static const struct llcc_slice_config sc8280xp_data[] = {
+	{ LLCC_CPUSS,    1,  6144, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 1, 0 },
+	{ LLCC_VIDSC0,   2,  512,  3, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0 },
+	{ LLCC_AUDIO,    6,  1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 0, 0 },
+	{ LLCC_CMPT,     10, 6144, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 0, 0 },
+	{ LLCC_GPUHTW,   11, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0 },
+	{ LLCC_GPU,      12, 4096, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 1 },
+	{ LLCC_MMUHWT,   13, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 },
+	{ LLCC_DISP,     16, 6144, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0 },
+	{ LLCC_AUDHW,    22, 2048, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0 },
+	{ LLCC_DRE,      26, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0 },
+	{ LLCC_CVP,      28, 512,  3, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0 },
+	{ LLCC_APTCM,    30, 1024, 3, 1, 0x0,   0x1, 1, 0, 0, 1, 0, 0 },
+	{ LLCC_WRCACHE,  31, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 },
+	{ LLCC_CVPFW,    32, 512,  1, 0, 0xfff, 0x0, 0, 0, 0, 1, 0, 0 },
+	{ LLCC_CPUSS1,   33, 2048, 1, 1, 0xfff, 0x0, 0, 0, 0, 1, 0, 0 },
+	{ LLCC_CPUHWT,   36, 512,  1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 },
+};
+
 static const struct llcc_slice_config sdm845_data[] =  {
 	{ LLCC_CPUSS,    1,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 1 },
 	{ LLCC_VIDSC0,   2,  512,  2, 1, 0x0,   0x0f0, 0, 0, 1, 1, 0 },
@@ -276,6 +320,20 @@ static const struct qcom_llcc_config sc7280_cfg = {
 	.reg_offset	= llcc_v1_2_reg_offset,
 };
 
+static const struct qcom_llcc_config sc8180x_cfg = {
+	.sct_data	= sc8180x_data,
+	.size		= ARRAY_SIZE(sc8180x_data),
+	.need_llcc_cfg	= true,
+	.reg_offset	= llcc_v1_2_reg_offset,
+};
+
+static const struct qcom_llcc_config sc8280xp_cfg = {
+	.sct_data	= sc8280xp_data,
+	.size		= ARRAY_SIZE(sc8280xp_data),
+	.need_llcc_cfg	= true,
+	.reg_offset	= llcc_v1_2_reg_offset,
+};
+
 static const struct qcom_llcc_config sdm845_cfg = {
 	.sct_data	= sdm845_data,
 	.size		= ARRAY_SIZE(sdm845_data),
@@ -741,6 +799,8 @@ err:
 static const struct of_device_id qcom_llcc_of_match[] = {
 	{ .compatible = "qcom,sc7180-llcc", .data = &sc7180_cfg },
 	{ .compatible = "qcom,sc7280-llcc", .data = &sc7280_cfg },
+	{ .compatible = "qcom,sc8180x-llcc", .data = &sc8180x_cfg },
+	{ .compatible = "qcom,sc8280xp-llcc", .data = &sc8280xp_cfg },
 	{ .compatible = "qcom,sdm845-llcc", .data = &sdm845_cfg },
 	{ .compatible = "qcom,sm6350-llcc", .data = &sm6350_cfg },
 	{ .compatible = "qcom,sm8150-llcc", .data = &sm8150_cfg },
diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h
index 0bc21ee58fac..9ed5384c5ca1 100644
--- a/include/linux/soc/qcom/llcc-qcom.h
+++ b/include/linux/soc/qcom/llcc-qcom.h
@@ -29,6 +29,8 @@
 #define LLCC_AUDHW       22
 #define LLCC_NPU         23
 #define LLCC_WLHW        24
+#define LLCC_PIMEM       25
+#define LLCC_DRE         26
 #define LLCC_CVP         28
 #define LLCC_MODPE       29
 #define LLCC_APTCM       30
-- 
cgit v1.2.3


From 170f37d6aa6ad4582eefd7459015de79e244536e Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 3 May 2022 00:09:31 -0400
Subject: block: Do not call folio_next() on an unreferenced folio

It is unsafe to call folio_next() on a folio unless you hold a reference
on it that prevents it from being split or freed.  After returning
from the iterator, iomap calls folio_end_writeback() which may drop
the last reference to the page, or allow the page to be split.  If that
happens, the iterator will not advance far enough through the bio_vec,
leading to assertion failures like the BUG() in folio_end_writeback()
that checks we're not trying to end writeback on a page not currently
under writeback.  Other assertion failures were also seen, but they're
all explained by this one bug.

Fix the bug by remembering where the next folio starts before returning
from the iterator.  There are other ways of fixing this bug, but this
seems the simplest.

Reported-by: Darrick J. Wong <djwong@kernel.org>
Tested-by: Darrick J. Wong <djwong@kernel.org>
Reported-by: Brian Foster <bfoster@redhat.com>
Tested-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/bio.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 278cc81cc1e7..00450fd86bb4 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -269,6 +269,7 @@ struct folio_iter {
 	size_t offset;
 	size_t length;
 	/* private: for use by the iterator */
+	struct folio *_next;
 	size_t _seg_count;
 	int _i;
 };
@@ -283,6 +284,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
 			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
 	fi->_seg_count = bvec->bv_len;
 	fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count);
+	fi->_next = folio_next(fi->folio);
 	fi->_i = i;
 }
 
@@ -290,9 +292,10 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio)
 {
 	fi->_seg_count -= fi->length;
 	if (fi->_seg_count) {
-		fi->folio = folio_next(fi->folio);
+		fi->folio = fi->_next;
 		fi->offset = 0;
 		fi->length = min(folio_size(fi->folio), fi->_seg_count);
+		fi->_next = folio_next(fi->folio);
 	} else if (fi->_i + 1 < bio->bi_vcnt) {
 		bio_first_folio(fi, bio, fi->_i + 1);
 	} else {
-- 
cgit v1.2.3


From 8e1de7042596abb7cb277ea751fc13a4c2b65aea Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Sun, 13 Feb 2022 16:44:45 +0200
Subject: thunderbolt: Add support for XDomain lane bonding

The USB4 Inter-Domain Service specification defines a protocol that can
be used to establish lane bonding between two USB4 domains (hosts). So
far we have not implemented it because the host controller DMA was not
fast enough to be able to go over 20 Gbits/s even if lanes were bonded.
However, starting from Intel Alder Lake CPUs the DMA can go over
20 Gbits/s so now it makes more sense to add this support to the driver.

Because both ends need to negotiate the bonding we add a simple state
machine that tracks the connection state and does the necessary steps
described by the USB4 Inter-Domain Service specification. We only
establish lane bonding when both sides of the link support it. Otherwise
we default to use the single lane. Also this is only done when software
connection manager is used. On systems with firmware based connection
manager, it handles the high-speed tunneling so bonding lanes is
specific to the implementation (Intel firmware based connection manager
does not support lane bonding).

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tb.c      |   6 -
 drivers/thunderbolt/tb_msgs.h |  39 +++
 drivers/thunderbolt/tb_regs.h |   5 +
 drivers/thunderbolt/xdomain.c | 609 +++++++++++++++++++++++++++++++++++++-----
 include/linux/thunderbolt.h   |  19 +-
 5 files changed, 595 insertions(+), 83 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 44d04b651a8b..9a3214fb5038 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -169,12 +169,6 @@ static void tb_discover_tunnels(struct tb *tb)
 
 static int tb_port_configure_xdomain(struct tb_port *port)
 {
-	/*
-	 * XDomain paths currently only support single lane so we must
-	 * disable the other lane according to USB4 spec.
-	 */
-	tb_port_disable(port->dual_link_port);
-
 	if (tb_switch_is_usb4(port->sw))
 		return usb4_port_configure_xdomain(port);
 	return tb_lc_configure_xdomain(port);
diff --git a/drivers/thunderbolt/tb_msgs.h b/drivers/thunderbolt/tb_msgs.h
index fe1afa44c56d..33c4c7aed56d 100644
--- a/drivers/thunderbolt/tb_msgs.h
+++ b/drivers/thunderbolt/tb_msgs.h
@@ -527,6 +527,10 @@ enum tb_xdp_type {
 	PROPERTIES_CHANGED_RESPONSE,
 	ERROR_RESPONSE,
 	UUID_REQUEST = 12,
+	LINK_STATE_STATUS_REQUEST = 15,
+	LINK_STATE_STATUS_RESPONSE,
+	LINK_STATE_CHANGE_REQUEST,
+	LINK_STATE_CHANGE_RESPONSE,
 };
 
 struct tb_xdp_header {
@@ -540,6 +544,41 @@ struct tb_xdp_error_response {
 	u32 error;
 };
 
+struct tb_xdp_link_state_status {
+	struct tb_xdp_header hdr;
+};
+
+struct tb_xdp_link_state_status_response {
+	union {
+		struct tb_xdp_error_response err;
+		struct {
+			struct tb_xdp_header hdr;
+			u32 status;
+			u8 slw;
+			u8 tlw;
+			u8 sls;
+			u8 tls;
+		};
+	};
+};
+
+struct tb_xdp_link_state_change {
+	struct tb_xdp_header hdr;
+	u8 tlw;
+	u8 tls;
+	u16 reserved;
+};
+
+struct tb_xdp_link_state_change_response {
+	union {
+		struct tb_xdp_error_response err;
+		struct {
+			struct tb_xdp_header hdr;
+			u32 status;
+		};
+	};
+};
+
 struct tb_xdp_uuid {
 	struct tb_xdp_header hdr;
 };
diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h
index b301eeb0c89b..6a16f61a72a1 100644
--- a/drivers/thunderbolt/tb_regs.h
+++ b/drivers/thunderbolt/tb_regs.h
@@ -311,11 +311,16 @@ struct tb_regs_port_header {
 
 /* Lane adapter registers */
 #define LANE_ADP_CS_0				0x00
+#define LANE_ADP_CS_0_SUPPORTED_SPEED_MASK	GENMASK(19, 16)
+#define LANE_ADP_CS_0_SUPPORTED_SPEED_SHIFT	16
 #define LANE_ADP_CS_0_SUPPORTED_WIDTH_MASK	GENMASK(25, 20)
 #define LANE_ADP_CS_0_SUPPORTED_WIDTH_SHIFT	20
+#define LANE_ADP_CS_0_SUPPORTED_WIDTH_DUAL	0x2
 #define LANE_ADP_CS_0_CL0S_SUPPORT		BIT(26)
 #define LANE_ADP_CS_0_CL1_SUPPORT		BIT(27)
 #define LANE_ADP_CS_1				0x01
+#define LANE_ADP_CS_1_TARGET_SPEED_MASK		GENMASK(3, 0)
+#define LANE_ADP_CS_1_TARGET_SPEED_GEN3		0xc
 #define LANE_ADP_CS_1_TARGET_WIDTH_MASK		GENMASK(9, 4)
 #define LANE_ADP_CS_1_TARGET_WIDTH_SHIFT	4
 #define LANE_ADP_CS_1_TARGET_WIDTH_SINGLE	0x1
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 01d6b724ca51..c31c0d94d8b3 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -19,13 +19,38 @@
 
 #include "tb.h"
 
-#define XDOMAIN_DEFAULT_TIMEOUT			1000 /* ms */
-#define XDOMAIN_UUID_RETRIES			10
-#define XDOMAIN_PROPERTIES_RETRIES		10
-#define XDOMAIN_PROPERTIES_CHANGED_RETRIES	10
-#define XDOMAIN_BONDING_WAIT			100  /* ms */
+#define XDOMAIN_SHORT_TIMEOUT			100	/* ms */
+#define XDOMAIN_DEFAULT_TIMEOUT			1000	/* ms */
+#define XDOMAIN_BONDING_TIMEOUT			10000	/* ms */
+#define XDOMAIN_RETRIES				10
 #define XDOMAIN_DEFAULT_MAX_HOPID		15
 
+enum {
+	XDOMAIN_STATE_INIT,
+	XDOMAIN_STATE_UUID,
+	XDOMAIN_STATE_LINK_STATUS,
+	XDOMAIN_STATE_LINK_STATE_CHANGE,
+	XDOMAIN_STATE_LINK_STATUS2,
+	XDOMAIN_STATE_BONDING_UUID_LOW,
+	XDOMAIN_STATE_BONDING_UUID_HIGH,
+	XDOMAIN_STATE_PROPERTIES,
+	XDOMAIN_STATE_ENUMERATED,
+	XDOMAIN_STATE_ERROR,
+};
+
+static const char * const state_names[] = {
+	[XDOMAIN_STATE_INIT] = "INIT",
+	[XDOMAIN_STATE_UUID] = "UUID",
+	[XDOMAIN_STATE_LINK_STATUS] = "LINK_STATUS",
+	[XDOMAIN_STATE_LINK_STATE_CHANGE] = "LINK_STATE_CHANGE",
+	[XDOMAIN_STATE_LINK_STATUS2] = "LINK_STATUS2",
+	[XDOMAIN_STATE_BONDING_UUID_LOW] = "BONDING_UUID_LOW",
+	[XDOMAIN_STATE_BONDING_UUID_HIGH] = "BONDING_UUID_HIGH",
+	[XDOMAIN_STATE_PROPERTIES] = "PROPERTIES",
+	[XDOMAIN_STATE_ENUMERATED] = "ENUMERATED",
+	[XDOMAIN_STATE_ERROR] = "ERROR",
+};
+
 struct xdomain_request_work {
 	struct work_struct work;
 	struct tb_xdp_header *pkg;
@@ -235,7 +260,7 @@ static int tb_xdp_handle_error(const struct tb_xdp_error_response *res)
 }
 
 static int tb_xdp_uuid_request(struct tb_ctl *ctl, u64 route, int retry,
-			       uuid_t *uuid)
+			       uuid_t *uuid, u64 *remote_route)
 {
 	struct tb_xdp_uuid_response res;
 	struct tb_xdp_uuid req;
@@ -258,6 +283,8 @@ static int tb_xdp_uuid_request(struct tb_ctl *ctl, u64 route, int retry,
 		return ret;
 
 	uuid_copy(uuid, &res.src_uuid);
+	*remote_route = (u64)res.src_route_hi << 32 | res.src_route_lo;
+
 	return 0;
 }
 
@@ -473,6 +500,112 @@ tb_xdp_properties_changed_response(struct tb_ctl *ctl, u64 route, u8 sequence)
 				     TB_CFG_PKG_XDOMAIN_RESP);
 }
 
+static int tb_xdp_link_state_status_request(struct tb_ctl *ctl, u64 route,
+					    u8 sequence, u8 *slw, u8 *tlw,
+					    u8 *sls, u8 *tls)
+{
+	struct tb_xdp_link_state_status_response res;
+	struct tb_xdp_link_state_status req;
+	int ret;
+
+	memset(&req, 0, sizeof(req));
+	tb_xdp_fill_header(&req.hdr, route, sequence, LINK_STATE_STATUS_REQUEST,
+			   sizeof(req));
+
+	memset(&res, 0, sizeof(res));
+	ret = __tb_xdomain_request(ctl, &req, sizeof(req), TB_CFG_PKG_XDOMAIN_REQ,
+				   &res, sizeof(res), TB_CFG_PKG_XDOMAIN_RESP,
+				   XDOMAIN_DEFAULT_TIMEOUT);
+	if (ret)
+		return ret;
+
+	ret = tb_xdp_handle_error(&res.err);
+	if (ret)
+		return ret;
+
+	if (res.status != 0)
+		return -EREMOTEIO;
+
+	*slw = res.slw;
+	*tlw = res.tlw;
+	*sls = res.sls;
+	*tls = res.tls;
+
+	return 0;
+}
+
+static int tb_xdp_link_state_status_response(struct tb *tb, struct tb_ctl *ctl,
+					     struct tb_xdomain *xd, u8 sequence)
+{
+	struct tb_switch *sw = tb_to_switch(xd->dev.parent);
+	struct tb_xdp_link_state_status_response res;
+	struct tb_port *port = tb_port_at(xd->route, sw);
+	u32 val[2];
+	int ret;
+
+	memset(&res, 0, sizeof(res));
+	tb_xdp_fill_header(&res.hdr, xd->route, sequence,
+			   LINK_STATE_STATUS_RESPONSE, sizeof(res));
+
+	ret = tb_port_read(port, val, TB_CFG_PORT,
+			   port->cap_phy + LANE_ADP_CS_0, ARRAY_SIZE(val));
+	if (ret)
+		return ret;
+
+	res.slw = (val[0] & LANE_ADP_CS_0_SUPPORTED_WIDTH_MASK) >>
+			LANE_ADP_CS_0_SUPPORTED_WIDTH_SHIFT;
+	res.sls = (val[0] & LANE_ADP_CS_0_SUPPORTED_SPEED_MASK) >>
+			LANE_ADP_CS_0_SUPPORTED_SPEED_SHIFT;
+	res.tls = val[1] & LANE_ADP_CS_1_TARGET_SPEED_MASK;
+	res.tlw = (val[1] & LANE_ADP_CS_1_TARGET_WIDTH_MASK) >>
+			LANE_ADP_CS_1_TARGET_WIDTH_SHIFT;
+
+	return __tb_xdomain_response(ctl, &res, sizeof(res),
+				     TB_CFG_PKG_XDOMAIN_RESP);
+}
+
+static int tb_xdp_link_state_change_request(struct tb_ctl *ctl, u64 route,
+					    u8 sequence, u8 tlw, u8 tls)
+{
+	struct tb_xdp_link_state_change_response res;
+	struct tb_xdp_link_state_change req;
+	int ret;
+
+	memset(&req, 0, sizeof(req));
+	tb_xdp_fill_header(&req.hdr, route, sequence, LINK_STATE_CHANGE_REQUEST,
+			   sizeof(req));
+	req.tlw = tlw;
+	req.tls = tls;
+
+	memset(&res, 0, sizeof(res));
+	ret = __tb_xdomain_request(ctl, &req, sizeof(req), TB_CFG_PKG_XDOMAIN_REQ,
+				   &res, sizeof(res), TB_CFG_PKG_XDOMAIN_RESP,
+				   XDOMAIN_DEFAULT_TIMEOUT);
+	if (ret)
+		return ret;
+
+	ret = tb_xdp_handle_error(&res.err);
+	if (ret)
+		return ret;
+
+	return res.status != 0 ? -EREMOTEIO : 0;
+}
+
+static int tb_xdp_link_state_change_response(struct tb_ctl *ctl, u64 route,
+					     u8 sequence, u32 status)
+{
+	struct tb_xdp_link_state_change_response res;
+
+	memset(&res, 0, sizeof(res));
+	tb_xdp_fill_header(&res.hdr, route, sequence, LINK_STATE_CHANGE_RESPONSE,
+			   sizeof(res));
+
+	res.status = status;
+
+	return __tb_xdomain_response(ctl, &res, sizeof(res),
+				     TB_CFG_PKG_XDOMAIN_RESP);
+}
+
 /**
  * tb_register_protocol_handler() - Register protocol handler
  * @handler: Handler to register
@@ -600,14 +733,13 @@ static void tb_xdp_handle_request(struct work_struct *work)
 		goto out;
 	}
 
-	tb_dbg(tb, "%llx: received XDomain request %#x\n", route, pkg->type);
-
 	xd = tb_xdomain_find_by_route_locked(tb, route);
 	if (xd)
 		update_property_block(xd);
 
 	switch (pkg->type) {
 	case PROPERTIES_REQUEST:
+		tb_dbg(tb, "%llx: received XDomain properties request\n", route);
 		if (xd) {
 			ret = tb_xdp_properties_response(tb, ctl, xd, sequence,
 				(const struct tb_xdp_properties *)pkg);
@@ -615,6 +747,9 @@ static void tb_xdp_handle_request(struct work_struct *work)
 		break;
 
 	case PROPERTIES_CHANGED_REQUEST:
+		tb_dbg(tb, "%llx: received XDomain properties changed request\n",
+		       route);
+
 		ret = tb_xdp_properties_changed_response(ctl, route, sequence);
 
 		/*
@@ -622,18 +757,51 @@ static void tb_xdp_handle_request(struct work_struct *work)
 		 * the xdomain related to this connection as well in
 		 * case there is a change in services it offers.
 		 */
-		if (xd && device_is_registered(&xd->dev)) {
-			queue_delayed_work(tb->wq, &xd->get_properties_work,
-					   msecs_to_jiffies(50));
-		}
+		if (xd && device_is_registered(&xd->dev))
+			queue_delayed_work(tb->wq, &xd->state_work,
+					   msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT));
 		break;
 
 	case UUID_REQUEST_OLD:
 	case UUID_REQUEST:
+		tb_dbg(tb, "%llx: received XDomain UUID request\n", route);
 		ret = tb_xdp_uuid_response(ctl, route, sequence, uuid);
 		break;
 
+	case LINK_STATE_STATUS_REQUEST:
+		tb_dbg(tb, "%llx: received XDomain link state status request\n",
+		       route);
+
+		if (xd) {
+			ret = tb_xdp_link_state_status_response(tb, ctl, xd,
+								sequence);
+		} else {
+			tb_xdp_error_response(ctl, route, sequence,
+					      ERROR_NOT_READY);
+		}
+		break;
+
+	case LINK_STATE_CHANGE_REQUEST:
+		tb_dbg(tb, "%llx: received XDomain link state change request\n",
+		       route);
+
+		if (xd && xd->state == XDOMAIN_STATE_BONDING_UUID_HIGH) {
+			const struct tb_xdp_link_state_change *lsc =
+				(const struct tb_xdp_link_state_change *)pkg;
+
+			ret = tb_xdp_link_state_change_response(ctl, route,
+								sequence, 0);
+			xd->target_link_width = lsc->tlw;
+			queue_delayed_work(tb->wq, &xd->state_work,
+					   msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT));
+		} else {
+			tb_xdp_error_response(ctl, route, sequence,
+					      ERROR_NOT_READY);
+		}
+		break;
+
 	default:
+		tb_dbg(tb, "%llx: unknown XDomain request %#x\n", route, pkg->type);
 		tb_xdp_error_response(ctl, route, sequence,
 				      ERROR_NOT_SUPPORTED);
 		break;
@@ -1000,32 +1168,38 @@ static int tb_xdomain_update_link_attributes(struct tb_xdomain *xd)
 	return 0;
 }
 
-static void tb_xdomain_get_uuid(struct work_struct *work)
+static int tb_xdomain_get_uuid(struct tb_xdomain *xd)
 {
-	struct tb_xdomain *xd = container_of(work, typeof(*xd),
-					     get_uuid_work.work);
 	struct tb *tb = xd->tb;
 	uuid_t uuid;
+	u64 route;
 	int ret;
 
 	dev_dbg(&xd->dev, "requesting remote UUID\n");
 
-	ret = tb_xdp_uuid_request(tb->ctl, xd->route, xd->uuid_retries, &uuid);
+	ret = tb_xdp_uuid_request(tb->ctl, xd->route, xd->state_retries, &uuid,
+				  &route);
 	if (ret < 0) {
-		if (xd->uuid_retries-- > 0) {
+		if (xd->state_retries-- > 0) {
 			dev_dbg(&xd->dev, "failed to request UUID, retrying\n");
-			queue_delayed_work(xd->tb->wq, &xd->get_uuid_work,
-					   msecs_to_jiffies(100));
+			return -EAGAIN;
 		} else {
 			dev_dbg(&xd->dev, "failed to read remote UUID\n");
 		}
-		return;
+		return ret;
 	}
 
 	dev_dbg(&xd->dev, "got remote UUID %pUb\n", &uuid);
 
-	if (uuid_equal(&uuid, xd->local_uuid))
-		dev_dbg(&xd->dev, "intra-domain loop detected\n");
+	if (uuid_equal(&uuid, xd->local_uuid)) {
+		if (route == xd->route)
+			dev_dbg(&xd->dev, "loop back detected\n");
+		else
+			dev_dbg(&xd->dev, "intra-domain loop detected\n");
+
+		/* Don't bond lanes automatically for loops */
+		xd->bonding_possible = false;
+	}
 
 	/*
 	 * If the UUID is different, there is another domain connected
@@ -1035,27 +1209,152 @@ static void tb_xdomain_get_uuid(struct work_struct *work)
 	if (xd->remote_uuid && !uuid_equal(&uuid, xd->remote_uuid)) {
 		dev_dbg(&xd->dev, "remote UUID is different, unplugging\n");
 		xd->is_unplugged = true;
-		return;
+		return -ENODEV;
 	}
 
 	/* First time fill in the missing UUID */
 	if (!xd->remote_uuid) {
 		xd->remote_uuid = kmemdup(&uuid, sizeof(uuid_t), GFP_KERNEL);
 		if (!xd->remote_uuid)
-			return;
+			return -ENOMEM;
 	}
 
-	/* Now we can start the normal properties exchange */
-	queue_delayed_work(xd->tb->wq, &xd->properties_changed_work,
-			   msecs_to_jiffies(100));
-	queue_delayed_work(xd->tb->wq, &xd->get_properties_work,
-			   msecs_to_jiffies(1000));
+	return 0;
 }
 
-static void tb_xdomain_get_properties(struct work_struct *work)
+static int tb_xdomain_get_link_status(struct tb_xdomain *xd)
+{
+	struct tb *tb = xd->tb;
+	u8 slw, tlw, sls, tls;
+	int ret;
+
+	dev_dbg(&xd->dev, "sending link state status request to %pUb\n",
+		xd->remote_uuid);
+
+	ret = tb_xdp_link_state_status_request(tb->ctl, xd->route,
+					       xd->state_retries, &slw, &tlw, &sls,
+					       &tls);
+	if (ret) {
+		if (ret != -EOPNOTSUPP && xd->state_retries-- > 0) {
+			dev_dbg(&xd->dev,
+				"failed to request remote link status, retrying\n");
+			return -EAGAIN;
+		}
+		dev_dbg(&xd->dev, "failed to receive remote link status\n");
+		return ret;
+	}
+
+	dev_dbg(&xd->dev, "remote link supports width %#x speed %#x\n", slw, sls);
+
+	if (slw < LANE_ADP_CS_0_SUPPORTED_WIDTH_DUAL) {
+		dev_dbg(&xd->dev, "remote adapter is single lane only\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int tb_xdomain_link_state_change(struct tb_xdomain *xd,
+					unsigned int width)
+{
+	struct tb_switch *sw = tb_to_switch(xd->dev.parent);
+	struct tb_port *port = tb_port_at(xd->route, sw);
+	struct tb *tb = xd->tb;
+	u8 tlw, tls;
+	u32 val;
+	int ret;
+
+	if (width == 2)
+		tlw = LANE_ADP_CS_1_TARGET_WIDTH_DUAL;
+	else if (width == 1)
+		tlw = LANE_ADP_CS_1_TARGET_WIDTH_SINGLE;
+	else
+		return -EINVAL;
+
+	/* Use the current target speed */
+	ret = tb_port_read(port, &val, TB_CFG_PORT, port->cap_phy + LANE_ADP_CS_1, 1);
+	if (ret)
+		return ret;
+	tls = val & LANE_ADP_CS_1_TARGET_SPEED_MASK;
+
+	dev_dbg(&xd->dev, "sending link state change request with width %#x speed %#x\n",
+		tlw, tls);
+
+	ret = tb_xdp_link_state_change_request(tb->ctl, xd->route,
+					       xd->state_retries, tlw, tls);
+	if (ret) {
+		if (ret != -EOPNOTSUPP && xd->state_retries-- > 0) {
+			dev_dbg(&xd->dev,
+				"failed to change remote link state, retrying\n");
+			return -EAGAIN;
+		}
+		dev_err(&xd->dev, "failed request link state change, aborting\n");
+		return ret;
+	}
+
+	dev_dbg(&xd->dev, "received link state change response\n");
+	return 0;
+}
+
+static int tb_xdomain_bond_lanes_uuid_high(struct tb_xdomain *xd)
+{
+	struct tb_port *port;
+	int ret, width;
+
+	if (xd->target_link_width == LANE_ADP_CS_1_TARGET_WIDTH_SINGLE) {
+		width = 1;
+	} else if (xd->target_link_width == LANE_ADP_CS_1_TARGET_WIDTH_DUAL) {
+		width = 2;
+	} else {
+		if (xd->state_retries-- > 0) {
+			dev_dbg(&xd->dev,
+				"link state change request not received yet, retrying\n");
+			return -EAGAIN;
+		}
+		dev_dbg(&xd->dev, "timeout waiting for link change request\n");
+		return -ETIMEDOUT;
+	}
+
+	port = tb_port_at(xd->route, tb_xdomain_parent(xd));
+
+	/*
+	 * We can't use tb_xdomain_lane_bonding_enable() here because it
+	 * is the other side that initiates lane bonding. So here we
+	 * just set the width to both lane adapters and wait for the
+	 * link to transition bonded.
+	 */
+	ret = tb_port_set_link_width(port->dual_link_port, width);
+	if (ret) {
+		tb_port_warn(port->dual_link_port,
+			     "failed to set link width to %d\n", width);
+		return ret;
+	}
+
+	ret = tb_port_set_link_width(port, width);
+	if (ret) {
+		tb_port_warn(port, "failed to set link width to %d\n", width);
+		return ret;
+	}
+
+	ret = tb_port_wait_for_link_width(port, width, XDOMAIN_BONDING_TIMEOUT);
+	if (ret) {
+		dev_warn(&xd->dev, "error waiting for link width to become %d\n",
+			 width);
+		return ret;
+	}
+
+	port->bonded = width == 2;
+	port->dual_link_port->bonded = width == 2;
+
+	tb_port_update_credits(port);
+	tb_xdomain_update_link_attributes(xd);
+
+	dev_dbg(&xd->dev, "lane bonding %sabled\n", width == 2 ? "en" : "dis");
+	return 0;
+}
+
+static int tb_xdomain_get_properties(struct tb_xdomain *xd)
 {
-	struct tb_xdomain *xd = container_of(work, typeof(*xd),
-					     get_properties_work.work);
 	struct tb_property_dir *dir;
 	struct tb *tb = xd->tb;
 	bool update = false;
@@ -1066,34 +1365,35 @@ static void tb_xdomain_get_properties(struct work_struct *work)
 	dev_dbg(&xd->dev, "requesting remote properties\n");
 
 	ret = tb_xdp_properties_request(tb->ctl, xd->route, xd->local_uuid,
-					xd->remote_uuid, xd->properties_retries,
+					xd->remote_uuid, xd->state_retries,
 					&block, &gen);
 	if (ret < 0) {
-		if (xd->properties_retries-- > 0) {
+		if (xd->state_retries-- > 0) {
 			dev_dbg(&xd->dev,
 				"failed to request remote properties, retrying\n");
-			queue_delayed_work(xd->tb->wq, &xd->get_properties_work,
-					   msecs_to_jiffies(1000));
+			return -EAGAIN;
 		} else {
 			/* Give up now */
 			dev_err(&xd->dev,
 				"failed read XDomain properties from %pUb\n",
 				xd->remote_uuid);
 		}
-		return;
-	}
 
-	xd->properties_retries = XDOMAIN_PROPERTIES_RETRIES;
+		return ret;
+	}
 
 	mutex_lock(&xd->lock);
 
 	/* Only accept newer generation properties */
-	if (xd->remote_properties && gen <= xd->remote_property_block_gen)
+	if (xd->remote_properties && gen <= xd->remote_property_block_gen) {
+		ret = 0;
 		goto err_free_block;
+	}
 
 	dir = tb_property_parse_dir(block, ret);
 	if (!dir) {
 		dev_err(&xd->dev, "failed to parse XDomain properties\n");
+		ret = -ENOMEM;
 		goto err_free_block;
 	}
 
@@ -1124,9 +1424,16 @@ static void tb_xdomain_get_properties(struct work_struct *work)
 	 * registered, we notify the userspace that it has changed.
 	 */
 	if (!update) {
+		struct tb_port *port;
+
+		/* Now disable lane 1 if bonding was not enabled */
+		port = tb_port_at(xd->route, tb_xdomain_parent(xd));
+		if (!port->bonded)
+			tb_port_disable(port->dual_link_port);
+
 		if (device_add(&xd->dev)) {
 			dev_err(&xd->dev, "failed to add XDomain device\n");
-			return;
+			return -ENODEV;
 		}
 		dev_info(&xd->dev, "new host found, vendor=%#x device=%#x\n",
 			 xd->vendor, xd->device);
@@ -1138,13 +1445,193 @@ static void tb_xdomain_get_properties(struct work_struct *work)
 	}
 
 	enumerate_services(xd);
-	return;
+	return 0;
 
 err_free_dir:
 	tb_property_free_dir(dir);
 err_free_block:
 	kfree(block);
 	mutex_unlock(&xd->lock);
+
+	return ret;
+}
+
+static void tb_xdomain_queue_uuid(struct tb_xdomain *xd)
+{
+	xd->state = XDOMAIN_STATE_UUID;
+	xd->state_retries = XDOMAIN_RETRIES;
+	queue_delayed_work(xd->tb->wq, &xd->state_work,
+			   msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT));
+}
+
+static void tb_xdomain_queue_link_status(struct tb_xdomain *xd)
+{
+	xd->state = XDOMAIN_STATE_LINK_STATUS;
+	xd->state_retries = XDOMAIN_RETRIES;
+	queue_delayed_work(xd->tb->wq, &xd->state_work,
+			   msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT));
+}
+
+static void tb_xdomain_queue_link_status2(struct tb_xdomain *xd)
+{
+	xd->state = XDOMAIN_STATE_LINK_STATUS2;
+	xd->state_retries = XDOMAIN_RETRIES;
+	queue_delayed_work(xd->tb->wq, &xd->state_work,
+			   msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT));
+}
+
+static void tb_xdomain_queue_bonding(struct tb_xdomain *xd)
+{
+	if (memcmp(xd->local_uuid, xd->remote_uuid, UUID_SIZE) > 0) {
+		dev_dbg(&xd->dev, "we have higher UUID, other side bonds the lanes\n");
+		xd->state = XDOMAIN_STATE_BONDING_UUID_HIGH;
+	} else {
+		dev_dbg(&xd->dev, "we have lower UUID, bonding lanes\n");
+		xd->state = XDOMAIN_STATE_LINK_STATE_CHANGE;
+	}
+
+	xd->state_retries = XDOMAIN_RETRIES;
+	queue_delayed_work(xd->tb->wq, &xd->state_work,
+			   msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT));
+}
+
+static void tb_xdomain_queue_bonding_uuid_low(struct tb_xdomain *xd)
+{
+	xd->state = XDOMAIN_STATE_BONDING_UUID_LOW;
+	xd->state_retries = XDOMAIN_RETRIES;
+	queue_delayed_work(xd->tb->wq, &xd->state_work,
+			   msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT));
+}
+
+static void tb_xdomain_queue_properties(struct tb_xdomain *xd)
+{
+	xd->state = XDOMAIN_STATE_PROPERTIES;
+	xd->state_retries = XDOMAIN_RETRIES;
+	queue_delayed_work(xd->tb->wq, &xd->state_work,
+			   msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT));
+}
+
+static void tb_xdomain_queue_properties_changed(struct tb_xdomain *xd)
+{
+	xd->properties_changed_retries = XDOMAIN_RETRIES;
+	queue_delayed_work(xd->tb->wq, &xd->properties_changed_work,
+			   msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT));
+}
+
+static void tb_xdomain_state_work(struct work_struct *work)
+{
+	struct tb_xdomain *xd = container_of(work, typeof(*xd), state_work.work);
+	int ret, state = xd->state;
+
+	if (WARN_ON_ONCE(state < XDOMAIN_STATE_INIT ||
+			 state > XDOMAIN_STATE_ERROR))
+		return;
+
+	dev_dbg(&xd->dev, "running state %s\n", state_names[state]);
+
+	switch (state) {
+	case XDOMAIN_STATE_INIT:
+		if (xd->needs_uuid) {
+			tb_xdomain_queue_uuid(xd);
+		} else {
+			tb_xdomain_queue_properties_changed(xd);
+			tb_xdomain_queue_properties(xd);
+		}
+		break;
+
+	case XDOMAIN_STATE_UUID:
+		ret = tb_xdomain_get_uuid(xd);
+		if (ret) {
+			if (ret == -EAGAIN)
+				goto retry_state;
+			xd->state = XDOMAIN_STATE_ERROR;
+		} else {
+			tb_xdomain_queue_properties_changed(xd);
+			if (xd->bonding_possible)
+				tb_xdomain_queue_link_status(xd);
+			else
+				tb_xdomain_queue_properties(xd);
+		}
+		break;
+
+	case XDOMAIN_STATE_LINK_STATUS:
+		ret = tb_xdomain_get_link_status(xd);
+		if (ret) {
+			if (ret == -EAGAIN)
+				goto retry_state;
+
+			/*
+			 * If any of the lane bonding states fail we skip
+			 * bonding completely and try to continue from
+			 * reading properties.
+			 */
+			tb_xdomain_queue_properties(xd);
+		} else {
+			tb_xdomain_queue_bonding(xd);
+		}
+		break;
+
+	case XDOMAIN_STATE_LINK_STATE_CHANGE:
+		ret = tb_xdomain_link_state_change(xd, 2);
+		if (ret) {
+			if (ret == -EAGAIN)
+				goto retry_state;
+			tb_xdomain_queue_properties(xd);
+		} else {
+			tb_xdomain_queue_link_status2(xd);
+		}
+		break;
+
+	case XDOMAIN_STATE_LINK_STATUS2:
+		ret = tb_xdomain_get_link_status(xd);
+		if (ret) {
+			if (ret == -EAGAIN)
+				goto retry_state;
+			tb_xdomain_queue_properties(xd);
+		} else {
+			tb_xdomain_queue_bonding_uuid_low(xd);
+		}
+		break;
+
+	case XDOMAIN_STATE_BONDING_UUID_LOW:
+		tb_xdomain_lane_bonding_enable(xd);
+		tb_xdomain_queue_properties(xd);
+		break;
+
+	case XDOMAIN_STATE_BONDING_UUID_HIGH:
+		if (tb_xdomain_bond_lanes_uuid_high(xd) == -EAGAIN)
+			goto retry_state;
+		tb_xdomain_queue_properties(xd);
+		break;
+
+	case XDOMAIN_STATE_PROPERTIES:
+		ret = tb_xdomain_get_properties(xd);
+		if (ret) {
+			if (ret == -EAGAIN)
+				goto retry_state;
+			xd->state = XDOMAIN_STATE_ERROR;
+		} else {
+			xd->state = XDOMAIN_STATE_ENUMERATED;
+		}
+		break;
+
+	case XDOMAIN_STATE_ENUMERATED:
+		tb_xdomain_queue_properties(xd);
+		break;
+
+	case XDOMAIN_STATE_ERROR:
+		break;
+
+	default:
+		dev_warn(&xd->dev, "unexpected state %d\n", state);
+		break;
+	}
+
+	return;
+
+retry_state:
+	queue_delayed_work(xd->tb->wq, &xd->state_work,
+			   msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT));
 }
 
 static void tb_xdomain_properties_changed(struct work_struct *work)
@@ -1163,13 +1650,13 @@ static void tb_xdomain_properties_changed(struct work_struct *work)
 				"failed to send properties changed notification, retrying\n");
 			queue_delayed_work(xd->tb->wq,
 					   &xd->properties_changed_work,
-					   msecs_to_jiffies(1000));
+					   msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT));
 		}
 		dev_err(&xd->dev, "failed to send properties changed notification\n");
 		return;
 	}
 
-	xd->properties_changed_retries = XDOMAIN_PROPERTIES_CHANGED_RETRIES;
+	xd->properties_changed_retries = XDOMAIN_RETRIES;
 }
 
 static ssize_t device_show(struct device *dev, struct device_attribute *attr,
@@ -1304,31 +1791,17 @@ static void tb_xdomain_release(struct device *dev)
 
 static void start_handshake(struct tb_xdomain *xd)
 {
-	xd->uuid_retries = XDOMAIN_UUID_RETRIES;
-	xd->properties_retries = XDOMAIN_PROPERTIES_RETRIES;
-	xd->properties_changed_retries = XDOMAIN_PROPERTIES_CHANGED_RETRIES;
-
-	if (xd->needs_uuid) {
-		queue_delayed_work(xd->tb->wq, &xd->get_uuid_work,
-				   msecs_to_jiffies(100));
-	} else {
-		/* Start exchanging properties with the other host */
-		queue_delayed_work(xd->tb->wq, &xd->properties_changed_work,
-				   msecs_to_jiffies(100));
-		queue_delayed_work(xd->tb->wq, &xd->get_properties_work,
-				   msecs_to_jiffies(1000));
-	}
+	xd->state = XDOMAIN_STATE_INIT;
+	queue_delayed_work(xd->tb->wq, &xd->state_work,
+			   msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT));
 }
 
 static void stop_handshake(struct tb_xdomain *xd)
 {
-	xd->uuid_retries = 0;
-	xd->properties_retries = 0;
-	xd->properties_changed_retries = 0;
-
-	cancel_delayed_work_sync(&xd->get_uuid_work);
-	cancel_delayed_work_sync(&xd->get_properties_work);
 	cancel_delayed_work_sync(&xd->properties_changed_work);
+	cancel_delayed_work_sync(&xd->state_work);
+	xd->properties_changed_retries = 0;
+	xd->state_retries = 0;
 }
 
 static int __maybe_unused tb_xdomain_suspend(struct device *dev)
@@ -1389,8 +1862,7 @@ struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent,
 	ida_init(&xd->in_hopids);
 	ida_init(&xd->out_hopids);
 	mutex_init(&xd->lock);
-	INIT_DELAYED_WORK(&xd->get_uuid_work, tb_xdomain_get_uuid);
-	INIT_DELAYED_WORK(&xd->get_properties_work, tb_xdomain_get_properties);
+	INIT_DELAYED_WORK(&xd->state_work, tb_xdomain_state_work);
 	INIT_DELAYED_WORK(&xd->properties_changed_work,
 			  tb_xdomain_properties_changed);
 
@@ -1405,6 +1877,7 @@ struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent,
 			goto err_free_local_uuid;
 	} else {
 		xd->needs_uuid = true;
+		xd->bonding_possible = !!down->dual_link_port;
 	}
 
 	device_initialize(&xd->dev);
@@ -1523,9 +1996,9 @@ int tb_xdomain_lane_bonding_enable(struct tb_xdomain *xd)
 		return ret;
 	}
 
-	ret = tb_port_wait_for_link_width(port, 2, 100);
+	ret = tb_port_wait_for_link_width(port, 2, XDOMAIN_BONDING_TIMEOUT);
 	if (ret) {
-		tb_port_warn(port, "timeout enabling lane bonding\n");
+		tb_port_warn(port, "failed to enable lane bonding\n");
 		return ret;
 	}
 
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index 124e13cb1469..e13fe15e6a51 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -198,15 +198,15 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir);
  * @local_property_block_len: Length of the @local_property_block in dwords
  * @remote_properties: Properties exported by the remote domain
  * @remote_property_block_gen: Generation of @remote_properties
- * @get_uuid_work: Work used to retrieve @remote_uuid
- * @uuid_retries: Number of times left @remote_uuid is requested before
- *		  giving up
- * @get_properties_work: Work used to get remote domain properties
- * @properties_retries: Number of times left to read properties
+ * @state: Next XDomain discovery state to run
+ * @state_work: Work used to run the next state
+ * @state_retries: Number of retries remain for the state
  * @properties_changed_work: Work used to notify the remote domain that
  *			     our properties have changed
  * @properties_changed_retries: Number of times left to send properties
  *				changed notification
+ * @bonding_possible: True if lane bonding is possible on local side
+ * @target_link_width: Target link width from the remote host
  * @link: Root switch link the remote domain is connected (ICM only)
  * @depth: Depth in the chain the remote domain is connected (ICM only)
  *
@@ -244,12 +244,13 @@ struct tb_xdomain {
 	u32 local_property_block_len;
 	struct tb_property_dir *remote_properties;
 	u32 remote_property_block_gen;
-	struct delayed_work get_uuid_work;
-	int uuid_retries;
-	struct delayed_work get_properties_work;
-	int properties_retries;
+	int state;
+	struct delayed_work state_work;
+	int state_retries;
 	struct delayed_work properties_changed_work;
 	int properties_changed_retries;
+	bool bonding_possible;
+	u8 target_link_width;
 	u8 link;
 	u8 depth;
 };
-- 
cgit v1.2.3


From 4b439e25e29ec336c0e71ef1d1b212c412526518 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Sat, 9 Apr 2022 19:17:27 +0200
Subject: mm, hugetlbfs: Allow an arch to always use generic versions of
 get_unmapped_area functions

Unlike most architectures, powerpc can only define at runtime
if it is going to use the generic arch_get_unmapped_area() or not.

Today, powerpc has a copy of the generic arch_get_unmapped_area()
because when selection HAVE_ARCH_UNMAPPED_AREA the generic
arch_get_unmapped_area() is not available.

Rename it generic_get_unmapped_area() and make it independent of
HAVE_ARCH_UNMAPPED_AREA.

Do the same for arch_get_unmapped_area_topdown() versus
HAVE_ARCH_UNMAPPED_AREA_TOPDOWN.

Do the same for hugetlb_get_unmapped_area() versus
HAVE_ARCH_HUGETLB_UNMAPPED_AREA.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/77f9d3e592f1c8511df9381aa1c4e754651da4d1.1649523076.git.christophe.leroy@csgroup.eu
---
 fs/hugetlbfs/inode.c     | 17 +++++++++++++----
 include/linux/hugetlb.h  |  5 +++++
 include/linux/sched/mm.h |  9 +++++++++
 mm/mmap.c                | 31 ++++++++++++++++++++++++-------
 4 files changed, 51 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index dd3a088db11d..ec611c7de9e3 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -195,7 +195,6 @@ out:
  * Called under mmap_write_lock(mm).
  */
 
-#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 static unsigned long
 hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
@@ -244,9 +243,10 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
 	return addr;
 }
 
-static unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
+unsigned long
+generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+				  unsigned long len, unsigned long pgoff,
+				  unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
@@ -283,6 +283,15 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	return hugetlb_get_unmapped_area_bottomup(file, addr, len,
 			pgoff, flags);
 }
+
+#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+static unsigned long
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+			  unsigned long len, unsigned long pgoff,
+			  unsigned long flags)
+{
+	return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
+}
 #endif
 
 static size_t
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ac2a1d758a80..bc97c8458df6 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -519,6 +519,11 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long flags);
 #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
 
+unsigned long
+generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+				  unsigned long len, unsigned long pgoff,
+				  unsigned long flags);
+
 /*
  * huegtlb page specific state flags.  These flags are located in page.private
  * of the hugetlb head page.  Functions created via the below macros should be
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 1ad1f4bfa025..da3a32d05b34 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -153,6 +153,15 @@ extern unsigned long
 arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 			  unsigned long len, unsigned long pgoff,
 			  unsigned long flags);
+
+unsigned long
+generic_get_unmapped_area(struct file *filp, unsigned long addr,
+			  unsigned long len, unsigned long pgoff,
+			  unsigned long flags);
+unsigned long
+generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+				  unsigned long len, unsigned long pgoff,
+				  unsigned long flags);
 #else
 static inline void arch_pick_mmap_layout(struct mm_struct *mm,
 					 struct rlimit *rlim_stack) {}
diff --git a/mm/mmap.c b/mm/mmap.c
index 313b57d55a63..d2b6c3fbfb8c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2128,10 +2128,10 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info)
  *
  * This function "knows" that -ENOMEM has the bits set.
  */
-#ifndef HAVE_ARCH_UNMAPPED_AREA
 unsigned long
-arch_get_unmapped_area(struct file *filp, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
+generic_get_unmapped_area(struct file *filp, unsigned long addr,
+			  unsigned long len, unsigned long pgoff,
+			  unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
@@ -2161,17 +2161,25 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.align_offset = 0;
 	return vm_unmapped_area(&info);
 }
+
+#ifndef HAVE_ARCH_UNMAPPED_AREA
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+		       unsigned long len, unsigned long pgoff,
+		       unsigned long flags)
+{
+	return generic_get_unmapped_area(filp, addr, len, pgoff, flags);
+}
 #endif
 
 /*
  * This mmap-allocator allocates new areas top-down from below the
  * stack's low limit (the base):
  */
-#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 unsigned long
-arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
-			  unsigned long len, unsigned long pgoff,
-			  unsigned long flags)
+generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+				  unsigned long len, unsigned long pgoff,
+				  unsigned long flags)
 {
 	struct vm_area_struct *vma, *prev;
 	struct mm_struct *mm = current->mm;
@@ -2219,6 +2227,15 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 
 	return addr;
 }
+
+#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+			       unsigned long len, unsigned long pgoff,
+			       unsigned long flags)
+{
+	return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags);
+}
 #endif
 
 unsigned long
-- 
cgit v1.2.3


From 2cb4de085f383cb9289083d1bedbaad046f640eb Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Sat, 9 Apr 2022 19:17:28 +0200
Subject: mm: Add len and flags parameters to arch_get_mmap_end()

Powerpc needs flags and len to make decision on arch_get_mmap_end().

So add them as parameters to arch_get_mmap_end().

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/b556daabe7d2bdb2361c4d6130280da7c1ba2c14.1649523076.git.christophe.leroy@csgroup.eu
---
 arch/arm64/include/asm/processor.h | 4 ++--
 fs/hugetlbfs/inode.c               | 6 +++---
 include/linux/sched/mm.h           | 2 +-
 mm/mmap.c                          | 4 ++--
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 73e38d9a540c..bd22d94e844d 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -92,8 +92,8 @@
 #endif /* CONFIG_COMPAT */
 
 #ifndef CONFIG_ARM64_FORCE_52BIT
-#define arch_get_mmap_end(addr) ((addr > DEFAULT_MAP_WINDOW) ? TASK_SIZE :\
-				DEFAULT_MAP_WINDOW)
+#define arch_get_mmap_end(addr, len, flags) \
+		(((addr) > DEFAULT_MAP_WINDOW) ? TASK_SIZE : DEFAULT_MAP_WINDOW)
 
 #define arch_get_mmap_base(addr, base) ((addr > DEFAULT_MAP_WINDOW) ? \
 					base + TASK_SIZE - DEFAULT_MAP_WINDOW :\
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ec611c7de9e3..6f863497bd69 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -205,7 +205,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr,
 	info.flags = 0;
 	info.length = len;
 	info.low_limit = current->mm->mmap_base;
-	info.high_limit = arch_get_mmap_end(addr);
+	info.high_limit = arch_get_mmap_end(addr, len, flags);
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	return vm_unmapped_area(&info);
@@ -236,7 +236,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
 		VM_BUG_ON(addr != -ENOMEM);
 		info.flags = 0;
 		info.low_limit = current->mm->mmap_base;
-		info.high_limit = arch_get_mmap_end(addr);
+		info.high_limit = arch_get_mmap_end(addr, len, flags);
 		addr = vm_unmapped_area(&info);
 	}
 
@@ -251,7 +251,7 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	struct hstate *h = hstate_file(file);
-	const unsigned long mmap_end = arch_get_mmap_end(addr);
+	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index da3a32d05b34..8cd975a8bfeb 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -137,7 +137,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 
 #ifdef CONFIG_MMU
 #ifndef arch_get_mmap_end
-#define arch_get_mmap_end(addr)	(TASK_SIZE)
+#define arch_get_mmap_end(addr, len, flags)	(TASK_SIZE)
 #endif
 
 #ifndef arch_get_mmap_base
diff --git a/mm/mmap.c b/mm/mmap.c
index d2b6c3fbfb8c..e9b7d74e58bc 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2136,7 +2136,7 @@ generic_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
 	struct vm_unmapped_area_info info;
-	const unsigned long mmap_end = arch_get_mmap_end(addr);
+	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
 
 	if (len > mmap_end - mmap_min_addr)
 		return -ENOMEM;
@@ -2184,7 +2184,7 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 	struct vm_area_struct *vma, *prev;
 	struct mm_struct *mm = current->mm;
 	struct vm_unmapped_area_info info;
-	const unsigned long mmap_end = arch_get_mmap_end(addr);
+	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
 
 	/* requested length too big for entire address space */
 	if (len > mmap_end - mmap_min_addr)
-- 
cgit v1.2.3


From d77e745613680c54708470402e2b623dcd769681 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Sat, 30 Apr 2022 04:51:44 +0200
Subject: regmap: Add bulk read/write callbacks into regmap_config

Currently the regmap_config structure only allows the user to implement
single element register read/write using .reg_read/.reg_write callbacks.
The regmap_bus already implements bulk counterparts of both, and is being
misused as a workaround for the missing bulk read/write callbacks in
regmap_config by a couple of drivers. To stop this misuse, add the bulk
read/write callbacks to regmap_config and call them from the regmap core
code.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Jagan Teki <jagan@amarulasolutions.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Maxime Ripard <maxime@cerno.tech>
Cc: Robert Foss <robert.foss@linaro.org>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
To: dri-devel@lists.freedesktop.org
Link: https://lore.kernel.org/r/20220430025145.640305-1-marex@denx.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/internal.h |  4 +++
 drivers/base/regmap/regmap.c   | 76 ++++++++++++++++++++++--------------------
 include/linux/regmap.h         | 12 +++++++
 3 files changed, 56 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index b4df36c7b17d..da8996e7a1f1 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -110,6 +110,10 @@ struct regmap {
 	int (*reg_write)(void *context, unsigned int reg, unsigned int val);
 	int (*reg_update_bits)(void *context, unsigned int reg,
 			       unsigned int mask, unsigned int val);
+	/* Bulk read/write */
+	int (*read)(void *context, const void *reg_buf, size_t reg_size,
+		    void *val_buf, size_t val_size);
+	int (*write)(void *context, const void *data, size_t count);
 
 	bool defer_caching;
 
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 5e12f7cb5147..879a87a6461b 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -838,12 +838,15 @@ struct regmap *__regmap_init(struct device *dev,
 		map->reg_stride_order = ilog2(map->reg_stride);
 	else
 		map->reg_stride_order = -1;
-	map->use_single_read = config->use_single_read || !bus || !bus->read;
-	map->use_single_write = config->use_single_write || !bus || !bus->write;
-	map->can_multi_write = config->can_multi_write && bus && bus->write;
+	map->use_single_read = config->use_single_read || !(config->read || (bus && bus->read));
+	map->use_single_write = config->use_single_write || !(config->write || (bus && bus->write));
+	map->can_multi_write = config->can_multi_write && (config->write || (bus && bus->write));
 	if (bus) {
 		map->max_raw_read = bus->max_raw_read;
 		map->max_raw_write = bus->max_raw_write;
+	} else if (config->max_raw_read && config->max_raw_write) {
+		map->max_raw_read = config->max_raw_read;
+		map->max_raw_write = config->max_raw_write;
 	}
 	map->dev = dev;
 	map->bus = bus;
@@ -877,7 +880,16 @@ struct regmap *__regmap_init(struct device *dev,
 		map->read_flag_mask = bus->read_flag_mask;
 	}
 
-	if (!bus) {
+	if (config && config->read && config->write) {
+		map->reg_read  = _regmap_bus_read;
+
+		/* Bulk read/write */
+		map->read = config->read;
+		map->write = config->write;
+
+		reg_endian = REGMAP_ENDIAN_NATIVE;
+		val_endian = REGMAP_ENDIAN_NATIVE;
+	} else if (!bus) {
 		map->reg_read  = config->reg_read;
 		map->reg_write = config->reg_write;
 		map->reg_update_bits = config->reg_update_bits;
@@ -894,10 +906,13 @@ struct regmap *__regmap_init(struct device *dev,
 	} else {
 		map->reg_read  = _regmap_bus_read;
 		map->reg_update_bits = bus->reg_update_bits;
-	}
+		/* Bulk read/write */
+		map->read = bus->read;
+		map->write = bus->write;
 
-	reg_endian = regmap_get_reg_endian(bus, config);
-	val_endian = regmap_get_val_endian(dev, bus, config);
+		reg_endian = regmap_get_reg_endian(bus, config);
+		val_endian = regmap_get_val_endian(dev, bus, config);
+	}
 
 	switch (config->reg_bits + map->reg_shift) {
 	case 2:
@@ -1671,8 +1686,6 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
 	size_t len;
 	int i;
 
-	WARN_ON(!map->bus);
-
 	/* Check for unwritable or noinc registers in range
 	 * before we start
 	 */
@@ -1754,7 +1767,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
 		val = work_val;
 	}
 
-	if (map->async && map->bus->async_write) {
+	if (map->async && map->bus && map->bus->async_write) {
 		struct regmap_async *async;
 
 		trace_regmap_async_write_start(map, reg, val_len);
@@ -1822,10 +1835,10 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
 	 * write.
 	 */
 	if (val == work_val)
-		ret = map->bus->write(map->bus_context, map->work_buf,
-				      map->format.reg_bytes +
-				      map->format.pad_bytes +
-				      val_len);
+		ret = map->write(map->bus_context, map->work_buf,
+				 map->format.reg_bytes +
+				 map->format.pad_bytes +
+				 val_len);
 	else if (map->bus->gather_write)
 		ret = map->bus->gather_write(map->bus_context, map->work_buf,
 					     map->format.reg_bytes +
@@ -1844,7 +1857,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
 		memcpy(buf, map->work_buf, map->format.reg_bytes);
 		memcpy(buf + map->format.reg_bytes + map->format.pad_bytes,
 		       val, val_len);
-		ret = map->bus->write(map->bus_context, buf, len);
+		ret = map->write(map->bus_context, buf, len);
 
 		kfree(buf);
 	} else if (ret != 0 && !map->cache_bypass && map->format.parse_val) {
@@ -1901,7 +1914,7 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg,
 	struct regmap_range_node *range;
 	struct regmap *map = context;
 
-	WARN_ON(!map->bus || !map->format.format_write);
+	WARN_ON(!map->format.format_write);
 
 	range = _regmap_range_lookup(map, reg);
 	if (range) {
@@ -1916,8 +1929,7 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg,
 
 	trace_regmap_hw_write_start(map, reg, 1);
 
-	ret = map->bus->write(map->bus_context, map->work_buf,
-			      map->format.buf_size);
+	ret = map->write(map->bus_context, map->work_buf, map->format.buf_size);
 
 	trace_regmap_hw_write_done(map, reg, 1);
 
@@ -1937,7 +1949,7 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg,
 {
 	struct regmap *map = context;
 
-	WARN_ON(!map->bus || !map->format.format_val);
+	WARN_ON(!map->format.format_val);
 
 	map->format.format_val(map->work_buf + map->format.reg_bytes
 			       + map->format.pad_bytes, val, 0);
@@ -1951,7 +1963,7 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg,
 
 static inline void *_regmap_map_get_context(struct regmap *map)
 {
-	return (map->bus) ? map : map->bus_context;
+	return (map->bus || (!map->bus && map->read)) ? map : map->bus_context;
 }
 
 int _regmap_write(struct regmap *map, unsigned int reg,
@@ -2363,7 +2375,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map,
 	u8 = buf;
 	*u8 |= map->write_flag_mask;
 
-	ret = map->bus->write(map->bus_context, buf, len);
+	ret = map->write(map->bus_context, buf, len);
 
 	kfree(buf);
 
@@ -2669,9 +2681,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 	struct regmap_range_node *range;
 	int ret;
 
-	WARN_ON(!map->bus);
-
-	if (!map->bus || !map->bus->read)
+	if (!map->read)
 		return -EINVAL;
 
 	range = _regmap_range_lookup(map, reg);
@@ -2689,9 +2699,9 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 				      map->read_flag_mask);
 	trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes);
 
-	ret = map->bus->read(map->bus_context, map->work_buf,
-			     map->format.reg_bytes + map->format.pad_bytes,
-			     val, val_len);
+	ret = map->read(map->bus_context, map->work_buf,
+			map->format.reg_bytes + map->format.pad_bytes,
+			val, val_len);
 
 	trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes);
 
@@ -2802,8 +2812,6 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 	unsigned int v;
 	int ret, i;
 
-	if (!map->bus)
-		return -EINVAL;
 	if (val_len % map->format.val_bytes)
 		return -EINVAL;
 	if (!IS_ALIGNED(reg, map->reg_stride))
@@ -2818,7 +2826,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 		size_t chunk_count, chunk_bytes;
 		size_t chunk_regs = val_count;
 
-		if (!map->bus->read) {
+		if (!map->read) {
 			ret = -ENOTSUPP;
 			goto out;
 		}
@@ -2878,7 +2886,7 @@ EXPORT_SYMBOL_GPL(regmap_raw_read);
  * @val: Pointer to data buffer
  * @val_len: Length of output buffer in bytes.
  *
- * The regmap API usually assumes that bulk bus read operations will read a
+ * The regmap API usually assumes that bulk read operations will read a
  * range of registers. Some devices have certain registers for which a read
  * operation read will read from an internal FIFO.
  *
@@ -2896,10 +2904,6 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg,
 	size_t read_len;
 	int ret;
 
-	if (!map->bus)
-		return -EINVAL;
-	if (!map->bus->read)
-		return -ENOTSUPP;
 	if (val_len % map->format.val_bytes)
 		return -EINVAL;
 	if (!IS_ALIGNED(reg, map->reg_stride))
@@ -3013,7 +3017,7 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val,
 	if (val_count == 0)
 		return -EINVAL;
 
-	if (map->bus && map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) {
+	if (map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) {
 		ret = regmap_raw_read(map, reg, val, val_bytes * val_count);
 		if (ret != 0)
 			return ret;
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index de81a94d7b30..8952fa3d0d59 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -299,6 +299,12 @@ typedef void (*regmap_unlock)(void *);
  *		     if the function require special handling with lock and reg
  *		     handling and the operation cannot be represented as a simple
  *		     update_bits operation on a bus such as SPI, I2C, etc.
+ * @read: Optional callback that if filled will be used to perform all the
+ *        bulk reads from the registers. Data is returned in the buffer used
+ *        to transmit data.
+ * @write: Same as above for writing.
+ * @max_raw_read: Max raw read size that can be used on the device.
+ * @max_raw_write: Max raw write size that can be used on the device.
  * @fast_io:	  Register IO is fast. Use a spinlock instead of a mutex
  *	     	  to perform locking. This field is ignored if custom lock/unlock
  *	     	  functions are used (see fields lock/unlock of struct regmap_config).
@@ -385,6 +391,12 @@ struct regmap_config {
 	int (*reg_write)(void *context, unsigned int reg, unsigned int val);
 	int (*reg_update_bits)(void *context, unsigned int reg,
 			       unsigned int mask, unsigned int val);
+	/* Bulk read/write */
+	int (*read)(void *context, const void *reg_buf, size_t reg_size,
+		    void *val_buf, size_t val_size);
+	int (*write)(void *context, const void *data, size_t count);
+	size_t max_raw_read;
+	size_t max_raw_write;
 
 	bool fast_io;
 
-- 
cgit v1.2.3


From 6d5f2207447b28dc73c25b3907e7ee32ee66bdbd Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 May 2022 19:08:27 +0200
Subject: gpio: max732x: Drop unused support for irq and setup code via
 platform data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only user of max732x_platform_data is arch/arm/mach-pxa/littleton.c
and it only uses .gpio_base. So drop the other members from the data struct
and simplify the driver accordingly.

The motivating side effect of this change is that the .remove() callback
cannot return a nonzero error code any more which prepares making i2c
remove callbacks return void.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 drivers/gpio/gpio-max732x.c           | 37 ++---------------------------------
 include/linux/platform_data/max732x.h | 12 ------------
 2 files changed, 2 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index 238cbe926b9f..da6972117030 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -496,17 +496,13 @@ static int max732x_irq_setup(struct max732x_chip *chip,
 			     const struct i2c_device_id *id)
 {
 	struct i2c_client *client = chip->client;
-	struct max732x_platform_data *pdata = dev_get_platdata(&client->dev);
 	int has_irq = max732x_features[id->driver_data] >> 32;
 	int irq_base = 0;
 	int ret;
 
-	if (((pdata && pdata->irq_base) || client->irq)
-			&& has_irq != INT_NONE) {
+	if (client->irq && has_irq != INT_NONE) {
 		struct gpio_irq_chip *girq;
 
-		if (pdata)
-			irq_base = pdata->irq_base;
 		chip->irq_features = has_irq;
 		mutex_init(&chip->irq_lock);
 
@@ -540,10 +536,9 @@ static int max732x_irq_setup(struct max732x_chip *chip,
 			     const struct i2c_device_id *id)
 {
 	struct i2c_client *client = chip->client;
-	struct max732x_platform_data *pdata = dev_get_platdata(&client->dev);
 	int has_irq = max732x_features[id->driver_data] >> 32;
 
-	if (((pdata && pdata->irq_base) || client->irq) && has_irq != INT_NONE)
+	if (client->irq && has_irq != INT_NONE)
 		dev_warn(&client->dev, "interrupt support not compiled in\n");
 
 	return 0;
@@ -703,44 +698,16 @@ static int max732x_probe(struct i2c_client *client,
 	if (ret)
 		return ret;
 
-	if (pdata->setup) {
-		ret = pdata->setup(client, chip->gpio_chip.base,
-				chip->gpio_chip.ngpio, pdata->context);
-		if (ret < 0)
-			dev_warn(&client->dev, "setup failed, %d\n", ret);
-	}
-
 	i2c_set_clientdata(client, chip);
 	return 0;
 }
 
-static int max732x_remove(struct i2c_client *client)
-{
-	struct max732x_platform_data *pdata = dev_get_platdata(&client->dev);
-	struct max732x_chip *chip = i2c_get_clientdata(client);
-
-	if (pdata && pdata->teardown) {
-		int ret;
-
-		ret = pdata->teardown(client, chip->gpio_chip.base,
-				chip->gpio_chip.ngpio, pdata->context);
-		if (ret < 0) {
-			dev_err(&client->dev, "%s failed, %d\n",
-					"teardown", ret);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
 static struct i2c_driver max732x_driver = {
 	.driver = {
 		.name		= "max732x",
 		.of_match_table	= of_match_ptr(max732x_of_table),
 	},
 	.probe		= max732x_probe,
-	.remove		= max732x_remove,
 	.id_table	= max732x_id,
 };
 
diff --git a/include/linux/platform_data/max732x.h b/include/linux/platform_data/max732x.h
index f231c635faec..423999207cd5 100644
--- a/include/linux/platform_data/max732x.h
+++ b/include/linux/platform_data/max732x.h
@@ -7,17 +7,5 @@
 struct max732x_platform_data {
 	/* number of the first GPIO */
 	unsigned	gpio_base;
-
-	/* interrupt base */
-	int		irq_base;
-
-	void		*context;	/* param to setup/teardown */
-
-	int		(*setup)(struct i2c_client *client,
-				unsigned gpio, unsigned ngpio,
-				void *context);
-	int		(*teardown)(struct i2c_client *client,
-				unsigned gpio, unsigned ngpio,
-				void *context);
 };
 #endif /* __LINUX_I2C_MAX732X_H */
-- 
cgit v1.2.3


From 8221ecd4e4620cf2f0e942cafcdecac1685f8f16 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 14 Apr 2022 15:04:27 +0200
Subject: PCI/PM: Drop the runtime_d3cold device flag

The runtime_d3cold flag is not needed any more, so drop it.

Link: https://lore.kernel.org/r/8077784.T7Z3S40VBb@kreacher
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pci/pci-driver.c | 2 --
 drivers/pci/pci.c        | 3 ---
 include/linux/pci.h      | 4 ----
 3 files changed, 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index ee5868810a5b..d76fab66a9c9 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1342,8 +1342,6 @@ static int pci_pm_runtime_resume(struct device *dev)
 	if (pm && pm->runtime_resume)
 		error = pm->runtime_resume(dev);
 
-	pci_dev->runtime_d3cold = false;
-
 	return error;
 }
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e6c7f48e8b07..992417646128 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2703,8 +2703,6 @@ int pci_finish_runtime_suspend(struct pci_dev *dev)
 	if (target_state == PCI_POWER_ERROR)
 		return -EIO;
 
-	dev->runtime_d3cold = target_state == PCI_D3cold;
-
 	/*
 	 * There are systems (for example, Intel mobile chips since Coffee
 	 * Lake) where the power drawn while suspended can be significantly
@@ -2722,7 +2720,6 @@ int pci_finish_runtime_suspend(struct pci_dev *dev)
 	if (error) {
 		pci_enable_wake(dev, target_state, false);
 		pci_restore_ptm_state(dev);
-		dev->runtime_d3cold = false;
 	}
 
 	return error;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60adf42460ab..3266ac08f8ec 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -379,10 +379,6 @@ struct pci_dev {
 	unsigned int	mmio_always_on:1;	/* Disallow turning off io/mem
 						   decoding during BAR sizing */
 	unsigned int	wakeup_prepared:1;
-	unsigned int	runtime_d3cold:1;	/* Whether go through runtime
-						   D3cold, not set for devices
-						   powered on/off by the
-						   corresponding bridge */
 	unsigned int	skip_bus_pm:1;	/* Internal: Skip bus-level PM */
 	unsigned int	ignore_hotplug:1;	/* Ignore hotplug events */
 	unsigned int	hotplug_user_indicators:1; /* SlotCtl indicators
-- 
cgit v1.2.3


From 26817fb7b066b21c66cd41d75ed2137e046045be Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 4 May 2022 09:27:10 -0400
Subject: Revert "fbdev: fbmem: add a helper to determine if an aperture is
 used by a fw fb"

This reverts commit 9a45ac2320d0a6ae01880a30d4b86025fce4061b.

This was added a helper for amdgpu to workaround a runtime pm regression
caused by a runtime pm fix in efifb.  We now have a better workaround
in amdgpu in
commit f95af4a9236695 ("drm/amdgpu: don't runtime suspend if there are displays attached (v3)")
so this workaround is no longer necessary.  Since amdgpu was the only
user of this interface, we can remove it.

Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/video/fbdev/core/fbmem.c | 47 ----------------------------------------
 include/linux/fb.h               |  1 -
 2 files changed, 48 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index ad9aac06427a..700ac4a83329 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -1783,53 +1783,6 @@ int remove_conflicting_framebuffers(struct apertures_struct *a,
 }
 EXPORT_SYMBOL(remove_conflicting_framebuffers);
 
-/**
- * is_firmware_framebuffer - detect if firmware-configured framebuffer matches
- * @a: memory range, users of which are to be checked
- *
- * This function checks framebuffer devices (initialized by firmware/bootloader)
- * which use memory range described by @a. If @a matchesm the function returns
- * true, otherwise false.
- */
-bool is_firmware_framebuffer(struct apertures_struct *a)
-{
-	bool do_free = false;
-	bool found = false;
-	int i;
-
-	if (!a) {
-		a = alloc_apertures(1);
-		if (!a)
-			return false;
-
-		a->ranges[0].base = 0;
-		a->ranges[0].size = ~0;
-		do_free = true;
-	}
-
-	mutex_lock(&registration_lock);
-	/* check all firmware fbs and kick off if the base addr overlaps */
-	for_each_registered_fb(i) {
-		struct apertures_struct *gen_aper;
-
-		if (!(registered_fb[i]->flags & FBINFO_MISC_FIRMWARE))
-			continue;
-
-		gen_aper = registered_fb[i]->apertures;
-		if (fb_do_apertures_overlap(gen_aper, a)) {
-			found = true;
-			break;
-		}
-	}
-	mutex_unlock(&registration_lock);
-
-	if (do_free)
-		kfree(a);
-
-	return found;
-}
-EXPORT_SYMBOL(is_firmware_framebuffer);
-
 /**
  * remove_conflicting_pci_framebuffers - remove firmware-configured framebuffers for PCI devices
  * @pdev: PCI device
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 9a77ab615c36..147d582dab41 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -612,7 +612,6 @@ extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev,
 					       const char *name);
 extern int remove_conflicting_framebuffers(struct apertures_struct *a,
 					   const char *name, bool primary);
-extern bool is_firmware_framebuffer(struct apertures_struct *a);
 extern int fb_prepare_logo(struct fb_info *fb_info, int rotate);
 extern int fb_show_logo(struct fb_info *fb_info, int rotate);
 extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size);
-- 
cgit v1.2.3


From c67b627e99affe4865b13557d68152ad4c35515c Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Wed, 4 May 2022 10:09:47 -0700
Subject: net: Make msg_zerocopy_alloc static

msg_zerocopy_alloc is only used by msg_zerocopy_realloc; remove the
export and make static in skbuff.c

Signed-off-by: David Ahern <dsahern@kernel.org>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Link: https://lore.kernel.org/r/20220504170947.18773-1-dsahern@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 1 -
 net/core/skbuff.c      | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3270cb72e4d8..5c2599e3fe7d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1665,7 +1665,6 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 }
 #endif
 
-struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size);
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 				       struct ubuf_info *uarg);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 475183f37891..15f7b6f99a8f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1165,7 +1165,7 @@ void mm_unaccount_pinned_pages(struct mmpin *mmp)
 }
 EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages);
 
-struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
+static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
 {
 	struct ubuf_info *uarg;
 	struct sk_buff *skb;
@@ -1196,7 +1196,6 @@ struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
 
 	return uarg;
 }
-EXPORT_SYMBOL_GPL(msg_zerocopy_alloc);
 
 static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg)
 {
-- 
cgit v1.2.3


From 85db6352fc8a158a893151baa1716463d34a20d0 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Wed, 4 May 2022 11:09:14 +0300
Subject: net: Fix features skip in for_each_netdev_feature()

The find_next_netdev_feature() macro gets the "remaining length",
not bit index.
Passing "bit - 1" for the following iteration is wrong as it skips
the adjacent bit. Pass "bit" instead.

Fixes: 3b89ea9c5902 ("net: Fix for_each_netdev_feature on Big endian")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Link: https://lore.kernel.org/r/20220504080914.1918-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdev_features.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 2c6b9e416225..7c2d77d75a88 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -169,7 +169,7 @@ enum {
 #define NETIF_F_HW_HSR_FWD	__NETIF_F(HW_HSR_FWD)
 #define NETIF_F_HW_HSR_DUP	__NETIF_F(HW_HSR_DUP)
 
-/* Finds the next feature with the highest number of the range of start till 0.
+/* Finds the next feature with the highest number of the range of start-1 till 0.
  */
 static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 {
@@ -188,7 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 	for ((bit) = find_next_netdev_feature((mask_addr),		\
 					      NETDEV_FEATURE_COUNT);	\
 	     (bit) >= 0;						\
-	     (bit) = find_next_netdev_feature((mask_addr), (bit) - 1))
+	     (bit) = find_next_netdev_feature((mask_addr), (bit)))
 
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
-- 
cgit v1.2.3


From bb17d110cbf270d5247a6e261c5ad50e362d1675 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 29 Apr 2022 21:59:45 +0200
Subject: rpmsg: Fix calling device_lock() on non-initialized device

driver_set_override() helper uses device_lock() so it should not be
called before rpmsg_register_device() (which calls device_register()).
Effect can be seen with CONFIG_DEBUG_MUTEXES:

  DEBUG_LOCKS_WARN_ON(lock->magic != lock)
  WARNING: CPU: 3 PID: 57 at kernel/locking/mutex.c:582 __mutex_lock+0x1ec/0x430
  ...
  Call trace:
   __mutex_lock+0x1ec/0x430
   mutex_lock_nested+0x44/0x50
   driver_set_override+0x124/0x150
   qcom_glink_native_probe+0x30c/0x3b0
   glink_rpm_probe+0x274/0x350
   platform_probe+0x6c/0xe0
   really_probe+0x17c/0x3d0
   __driver_probe_device+0x114/0x190
   driver_probe_device+0x3c/0xf0
   ...

Refactor the rpmsg_register_device() function to use two-step device
registering (initialization + add) and call driver_set_override() in
proper moment.

This moves the code around, so while at it also NULL-ify the
rpdev->driver_override in error path to be sure it won't be kfree()
second time.

Fixes: 42cd402b8fd4 ("rpmsg: Fix kfree() of static memory on setting driver_override")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20220429195946.1061725-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/rpmsg/rpmsg_core.c     | 33 ++++++++++++++++++++++++++++++---
 drivers/rpmsg/rpmsg_internal.h | 14 +-------------
 drivers/rpmsg/rpmsg_ns.c       | 14 +-------------
 include/linux/rpmsg.h          |  8 ++++++++
 4 files changed, 40 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index 95fc283f6af7..4938fc4eff00 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -593,24 +593,51 @@ static struct bus_type rpmsg_bus = {
 	.remove		= rpmsg_dev_remove,
 };
 
-int rpmsg_register_device(struct rpmsg_device *rpdev)
+/*
+ * A helper for registering rpmsg device with driver override and name.
+ * Drivers should not be using it, but instead rpmsg_register_device().
+ */
+int rpmsg_register_device_override(struct rpmsg_device *rpdev,
+				   const char *driver_override)
 {
 	struct device *dev = &rpdev->dev;
 	int ret;
 
+	if (driver_override)
+		strcpy(rpdev->id.name, driver_override);
+
 	dev_set_name(&rpdev->dev, "%s.%s.%d.%d", dev_name(dev->parent),
 		     rpdev->id.name, rpdev->src, rpdev->dst);
 
 	rpdev->dev.bus = &rpmsg_bus;
 
-	ret = device_register(&rpdev->dev);
+	device_initialize(dev);
+	if (driver_override) {
+		ret = driver_set_override(dev, &rpdev->driver_override,
+					  driver_override,
+					  strlen(driver_override));
+		if (ret) {
+			dev_err(dev, "device_set_override failed: %d\n", ret);
+			return ret;
+		}
+	}
+
+	ret = device_add(dev);
 	if (ret) {
-		dev_err(dev, "device_register failed: %d\n", ret);
+		dev_err(dev, "device_add failed: %d\n", ret);
+		kfree(rpdev->driver_override);
+		rpdev->driver_override = NULL;
 		put_device(&rpdev->dev);
 	}
 
 	return ret;
 }
+EXPORT_SYMBOL(rpmsg_register_device_override);
+
+int rpmsg_register_device(struct rpmsg_device *rpdev)
+{
+	return rpmsg_register_device_override(rpdev, NULL);
+}
 EXPORT_SYMBOL(rpmsg_register_device);
 
 /*
diff --git a/drivers/rpmsg/rpmsg_internal.h b/drivers/rpmsg/rpmsg_internal.h
index 3e81642238d2..a22cd4abe7d1 100644
--- a/drivers/rpmsg/rpmsg_internal.h
+++ b/drivers/rpmsg/rpmsg_internal.h
@@ -94,19 +94,7 @@ int rpmsg_release_channel(struct rpmsg_device *rpdev,
  */
 static inline int rpmsg_ctrldev_register_device(struct rpmsg_device *rpdev)
 {
-	int ret;
-
-	strcpy(rpdev->id.name, "rpmsg_ctrl");
-	ret = driver_set_override(&rpdev->dev, &rpdev->driver_override,
-				  rpdev->id.name, strlen(rpdev->id.name));
-	if (ret)
-		return ret;
-
-	ret = rpmsg_register_device(rpdev);
-	if (ret)
-		kfree(rpdev->driver_override);
-
-	return ret;
+	return rpmsg_register_device_override(rpdev, "rpmsg_ctrl");
 }
 
 #endif
diff --git a/drivers/rpmsg/rpmsg_ns.c b/drivers/rpmsg/rpmsg_ns.c
index 8eb8f328237e..c70ad03ff2e9 100644
--- a/drivers/rpmsg/rpmsg_ns.c
+++ b/drivers/rpmsg/rpmsg_ns.c
@@ -20,22 +20,10 @@
  */
 int rpmsg_ns_register_device(struct rpmsg_device *rpdev)
 {
-	int ret;
-
-	strcpy(rpdev->id.name, "rpmsg_ns");
-	ret = driver_set_override(&rpdev->dev, &rpdev->driver_override,
-				  rpdev->id.name, strlen(rpdev->id.name));
-	if (ret)
-		return ret;
-
 	rpdev->src = RPMSG_NS_ADDR;
 	rpdev->dst = RPMSG_NS_ADDR;
 
-	ret = rpmsg_register_device(rpdev);
-	if (ret)
-		kfree(rpdev->driver_override);
-
-	return ret;
+	return rpmsg_register_device_override(rpdev, "rpmsg_ns");
 }
 EXPORT_SYMBOL(rpmsg_ns_register_device);
 
diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h
index 20c8cd1cde21..523c98b96cb4 100644
--- a/include/linux/rpmsg.h
+++ b/include/linux/rpmsg.h
@@ -165,6 +165,8 @@ static inline __rpmsg64 cpu_to_rpmsg64(struct rpmsg_device *rpdev, u64 val)
 
 #if IS_ENABLED(CONFIG_RPMSG)
 
+int rpmsg_register_device_override(struct rpmsg_device *rpdev,
+				   const char *driver_override);
 int rpmsg_register_device(struct rpmsg_device *rpdev);
 int rpmsg_unregister_device(struct device *parent,
 			    struct rpmsg_channel_info *chinfo);
@@ -192,6 +194,12 @@ ssize_t rpmsg_get_mtu(struct rpmsg_endpoint *ept);
 
 #else
 
+static inline int rpmsg_register_device_override(struct rpmsg_device *rpdev,
+						 const char *driver_override)
+{
+	return -ENXIO;
+}
+
 static inline int rpmsg_register_device(struct rpmsg_device *rpdev)
 {
 	return -ENXIO;
-- 
cgit v1.2.3


From d143b9db8069f0e2a0fa34484e806a55a0dd4855 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 27 Apr 2022 11:04:42 +0200
Subject: export: fix string handling of namespace in EXPORT_SYMBOL_NS

Commit c3a6cf19e695 ("export: avoid code duplication in
include/linux/export.h") broke the ability for a defined string to be
used as a namespace value.  Fix this up by using stringify to properly
encode the namespace name.

Fixes: c3a6cf19e695 ("export: avoid code duplication in include/linux/export.h")
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Emil Velikov <emil.l.velikov@gmail.com>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Cc: Matthias Maennich <maennich@google.com>
Reviewed-by: Masahiro Yamada <masahiroy@kernel.org>
Link: https://lore.kernel.org/r/20220427090442.2105905-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/export.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/export.h b/include/linux/export.h
index 27d848712b90..5910ccb66ca2 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_EXPORT_H
 #define _LINUX_EXPORT_H
 
+#include <linux/stringify.h>
+
 /*
  * Export symbols from the kernel to modules.  Forked from module.h
  * to reduce the amount of pointless cruft we feed to gcc when only
@@ -154,7 +156,6 @@ struct kernel_symbol {
 #endif /* CONFIG_MODULES */
 
 #ifdef DEFAULT_SYMBOL_NAMESPACE
-#include <linux/stringify.h>
 #define _EXPORT_SYMBOL(sym, sec)	__EXPORT_SYMBOL(sym, sec, __stringify(DEFAULT_SYMBOL_NAMESPACE))
 #else
 #define _EXPORT_SYMBOL(sym, sec)	__EXPORT_SYMBOL(sym, sec, "")
@@ -162,8 +163,8 @@ struct kernel_symbol {
 
 #define EXPORT_SYMBOL(sym)		_EXPORT_SYMBOL(sym, "")
 #define EXPORT_SYMBOL_GPL(sym)		_EXPORT_SYMBOL(sym, "_gpl")
-#define EXPORT_SYMBOL_NS(sym, ns)	__EXPORT_SYMBOL(sym, "", #ns)
-#define EXPORT_SYMBOL_NS_GPL(sym, ns)	__EXPORT_SYMBOL(sym, "_gpl", #ns)
+#define EXPORT_SYMBOL_NS(sym, ns)	__EXPORT_SYMBOL(sym, "", __stringify(ns))
+#define EXPORT_SYMBOL_NS_GPL(sym, ns)	__EXPORT_SYMBOL(sym, "_gpl", __stringify(ns))
 
 #endif /* !__ASSEMBLY__ */
 
-- 
cgit v1.2.3


From 6de4d4eca9a2d0195f802bc97b0e9aeeaff05900 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Thu, 28 Apr 2022 02:24:27 -0400
Subject: platform/x86: pmc_atom: remove unused pmc_atom_write()

This function isn't used anywhere in the driver or anywhere in tree.
So remove it.  It can always be re-added if/when a use arises.

Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Aubrey Li <aubrey.li@linux.intel.com>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Mark Gross <markgross@kernel.org>
Cc: platform-driver-x86@vger.kernel.org
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Link: https://lore.kernel.org/r/20220428062430.31010-2-paul.gortmaker@windriver.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/pmc_atom.c            | 12 ------------
 include/linux/platform_data/x86/pmc_atom.h |  1 -
 2 files changed, 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c
index a40fae6edc84..31cf25d25d66 100644
--- a/drivers/platform/x86/pmc_atom.c
+++ b/drivers/platform/x86/pmc_atom.c
@@ -223,18 +223,6 @@ int pmc_atom_read(int offset, u32 *value)
 }
 EXPORT_SYMBOL_GPL(pmc_atom_read);
 
-int pmc_atom_write(int offset, u32 value)
-{
-	struct pmc_dev *pmc = &pmc_device;
-
-	if (!pmc->init)
-		return -ENODEV;
-
-	pmc_reg_write(pmc, offset, value);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pmc_atom_write);
-
 static void pmc_power_off(void)
 {
 	u16	pm1_cnt_port;
diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h
index 022bcea9edec..6807839c718b 100644
--- a/include/linux/platform_data/x86/pmc_atom.h
+++ b/include/linux/platform_data/x86/pmc_atom.h
@@ -144,6 +144,5 @@
 #define	SLEEP_ENABLE		0x2000
 
 extern int pmc_atom_read(int offset, u32 *value);
-extern int pmc_atom_write(int offset, u32 value);
 
 #endif /* PMC_ATOM_H */
-- 
cgit v1.2.3


From 6df6398f7c8b481ce83f28143bc08a5231616deb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 5 May 2022 19:51:31 -0700
Subject: net: add netif_inherit_tso_max()

To make later patches smaller create a helper for inheriting
the TSO limitations of a lower device. The TSO in the name
is not an accident, subsequent patches will replace GSO
with TSO in more names.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c |  3 +--
 drivers/net/ipvlan/ipvlan_main.c                  |  6 ++----
 drivers/net/macvlan.c                             |  6 ++----
 drivers/net/veth.c                                |  3 +--
 drivers/net/vxlan/vxlan_core.c                    |  3 +--
 include/linux/netdevice.h                         |  3 +++
 net/8021q/vlan.c                                  |  3 +--
 net/8021q/vlan_dev.c                              |  3 +--
 net/core/dev.c                                    | 12 ++++++++++++
 9 files changed, 24 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index ba3fa7eac98d..790e1d5e4b4a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -286,8 +286,7 @@ nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower)
 	if (repr->dst->u.port_info.lower_dev != lower)
 		return;
 
-	netif_set_gso_max_size(netdev, lower->gso_max_size);
-	netif_set_gso_max_segs(netdev, lower->gso_max_segs);
+	netif_inherit_tso_max(netdev, lower);
 
 	netdev_update_features(netdev);
 }
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 696e245f6d00..aa28a29e228c 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -139,8 +139,7 @@ static int ipvlan_init(struct net_device *dev)
 	dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES;
 	dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS;
 	dev->hw_enc_features |= dev->features;
-	netif_set_gso_max_size(dev, phy_dev->gso_max_size);
-	netif_set_gso_max_segs(dev, phy_dev->gso_max_segs);
+	netif_inherit_tso_max(dev, phy_dev);
 	dev->hard_header_len = phy_dev->hard_header_len;
 
 	netdev_lockdep_set_classes(dev);
@@ -762,8 +761,7 @@ static int ipvlan_device_event(struct notifier_block *unused,
 
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			netif_set_gso_max_size(ipvlan->dev, dev->gso_max_size);
-			netif_set_gso_max_segs(ipvlan->dev, dev->gso_max_segs);
+			netif_inherit_tso_max(ipvlan->dev, dev);
 			netdev_update_features(ipvlan->dev);
 		}
 		break;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index b00bc8173abe..0017bd0fe3bb 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -904,8 +904,7 @@ static int macvlan_init(struct net_device *dev)
 	dev->vlan_features	= lowerdev->vlan_features & MACVLAN_FEATURES;
 	dev->vlan_features	|= ALWAYS_ON_OFFLOADS;
 	dev->hw_enc_features    |= dev->features;
-	netif_set_gso_max_size(dev, lowerdev->gso_max_size);
-	netif_set_gso_max_segs(dev, lowerdev->gso_max_segs);
+	netif_inherit_tso_max(dev, lowerdev);
 	dev->hard_header_len	= lowerdev->hard_header_len;
 	macvlan_set_lockdep_class(dev);
 
@@ -1763,8 +1762,7 @@ static int macvlan_device_event(struct notifier_block *unused,
 		break;
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(vlan, &port->vlans, list) {
-			netif_set_gso_max_size(vlan->dev, dev->gso_max_size);
-			netif_set_gso_max_segs(vlan->dev, dev->gso_max_segs);
+			netif_inherit_tso_max(vlan->dev, dev);
 			netdev_update_features(vlan->dev);
 		}
 		break;
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 3592014e50cc..f474e79a7745 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1758,8 +1758,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	if (ifmp && (dev->ifindex != 0))
 		peer->ifindex = ifmp->ifi_index;
 
-	netif_set_gso_max_size(peer, dev->gso_max_size);
-	netif_set_gso_max_segs(peer, dev->gso_max_segs);
+	netif_inherit_tso_max(peer, dev);
 
 	err = register_netdevice(peer);
 	put_net(net);
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 8a5e3a6d32d7..2bda692f70c5 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -3683,8 +3683,7 @@ static void vxlan_config_apply(struct net_device *dev,
 	if (lowerdev) {
 		dst->remote_ifindex = conf->remote_ifindex;
 
-		netif_set_gso_max_size(dev, lowerdev->gso_max_size);
-		netif_set_gso_max_segs(dev, lowerdev->gso_max_segs);
+		netif_inherit_tso_max(dev, lowerdev);
 
 		needed_headroom = lowerdev->hard_header_len;
 		needed_headroom += lowerdev->needed_headroom;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index eaf66e57d891..006bb5c0e413 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4895,6 +4895,9 @@ static inline void netif_set_gro_max_size(struct net_device *dev,
 	WRITE_ONCE(dev->gro_max_size, size);
 }
 
+void netif_inherit_tso_max(struct net_device *to,
+			   const struct net_device *from);
+
 static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
 					int pulled_hlen, u16 mac_offset,
 					int mac_len)
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 788076b002b3..e40aa3e3641c 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -319,8 +319,7 @@ static void vlan_transfer_features(struct net_device *dev,
 {
 	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 
-	netif_set_gso_max_size(vlandev, dev->gso_max_size);
-	netif_set_gso_max_segs(vlandev, dev->gso_max_segs);
+	netif_inherit_tso_max(vlandev, dev);
 
 	if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
 		vlandev->hard_header_len = dev->hard_header_len;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e5d23e75572a..839f2020b015 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -573,8 +573,7 @@ static int vlan_dev_init(struct net_device *dev)
 			   NETIF_F_ALL_FCOE;
 
 	dev->features |= dev->hw_features | NETIF_F_LLTX;
-	netif_set_gso_max_size(dev, real_dev->gso_max_size);
-	netif_set_gso_max_segs(dev, real_dev->gso_max_segs);
+	netif_inherit_tso_max(dev, real_dev);
 	if (dev->features & NETIF_F_VLAN_FEATURES)
 		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
 
diff --git a/net/core/dev.c b/net/core/dev.c
index c2d73595a7c3..eef1d19b130f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2992,6 +2992,18 @@ undo_rx:
 }
 EXPORT_SYMBOL(netif_set_real_num_queues);
 
+/**
+ * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper
+ * @to:		netdev to update
+ * @from:	netdev from which to copy the limits
+ */
+void netif_inherit_tso_max(struct net_device *to, const struct net_device *from)
+{
+	netif_set_gso_max_size(to, from->gso_max_size);
+	netif_set_gso_max_segs(to, from->gso_max_segs);
+}
+EXPORT_SYMBOL(netif_inherit_tso_max);
+
 /**
  * netif_get_num_default_rss_queues - default number of RSS queues
  *
-- 
cgit v1.2.3


From 14d7b8122fd591693a2388b98563707ba72c6780 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 5 May 2022 19:51:32 -0700
Subject: net: don't allow user space to lift the device limits

Up until commit 46e6b992c250 ("rtnetlink: allow GSO maximums to
be set on device creation") the gso_max_segs and gso_max_size
of a device were not controlled from user space.

The quoted commit added the ability to control them because of
the following setup:

 netns A  |  netns B
     veth<->veth   eth0

If eth0 has TSO limitations and user wants to efficiently forward
traffic between eth0 and the veths they should copy the TSO
limitations of eth0 onto the veths. This would happen automatically
for macvlans or ipvlan but veth users are not so lucky (given the
loose coupling).

Unfortunately the commit in question allowed users to also override
the limits on real HW devices.

It may be useful to control the max GSO size and someone may be using
that ability (not that I know of any user), so create a separate set
of knobs to reliably record the TSO limitations. Validate the user
requests.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  9 +++++++++
 net/core/dev.c            | 35 +++++++++++++++++++++++++++++++++++
 net/core/rtnetlink.c      |  4 ++--
 3 files changed, 46 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 006bb5c0e413..e12f7de6d6ae 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1917,8 +1917,10 @@ enum netdev_ml_priv_type {
  *	@rtnl_link_ops:	Rtnl_link_ops
  *
  *	@gso_max_size:	Maximum size of generic segmentation offload
+ *	@tso_max_size:	Device (as in HW) limit on the max TSO request size
  *	@gso_max_segs:	Maximum number of segments that can be passed to the
  *			NIC for GSO
+ *	@tso_max_segs:	Device (as in HW) limit on the max TSO segment count
  *
  *	@dcbnl_ops:	Data Center Bridging netlink ops
  *	@num_tc:	Number of traffic classes in the net device
@@ -2262,8 +2264,13 @@ struct net_device {
 	/* for setting kernel sock attribute on TCP connection setup */
 #define GSO_MAX_SIZE		65536
 	unsigned int		gso_max_size;
+#define TSO_LEGACY_MAX_SIZE	65536
+#define TSO_MAX_SIZE		UINT_MAX
+	unsigned int		tso_max_size;
 #define GSO_MAX_SEGS		65535
 	u16			gso_max_segs;
+#define TSO_MAX_SEGS		U16_MAX
+	u16			tso_max_segs;
 
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
@@ -4895,6 +4902,8 @@ static inline void netif_set_gro_max_size(struct net_device *dev,
 	WRITE_ONCE(dev->gro_max_size, size);
 }
 
+void netif_set_tso_max_size(struct net_device *dev, unsigned int size);
+void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs);
 void netif_inherit_tso_max(struct net_device *to,
 			   const struct net_device *from);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index eef1d19b130f..6ae085b11373 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2992,6 +2992,39 @@ undo_rx:
 }
 EXPORT_SYMBOL(netif_set_real_num_queues);
 
+/**
+ * netif_set_tso_max_size() - set the max size of TSO frames supported
+ * @dev:	netdev to update
+ * @size:	max skb->len of a TSO frame
+ *
+ * Set the limit on the size of TSO super-frames the device can handle.
+ * Unless explicitly set the stack will assume the value of %GSO_MAX_SIZE.
+ */
+void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
+{
+	dev->tso_max_size = size;
+	if (size < READ_ONCE(dev->gso_max_size))
+		netif_set_gso_max_size(dev, size);
+}
+EXPORT_SYMBOL(netif_set_tso_max_size);
+
+/**
+ * netif_set_tso_max_segs() - set the max number of segs supported for TSO
+ * @dev:	netdev to update
+ * @segs:	max number of TCP segments
+ *
+ * Set the limit on the number of TCP segments the device can generate from
+ * a single TSO super-frame.
+ * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS.
+ */
+void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs)
+{
+	dev->tso_max_segs = segs;
+	if (segs < READ_ONCE(dev->gso_max_segs))
+		netif_set_gso_max_segs(dev, segs);
+}
+EXPORT_SYMBOL(netif_set_tso_max_segs);
+
 /**
  * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper
  * @to:		netdev to update
@@ -10572,6 +10605,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
 	dev->gro_max_size = GRO_MAX_SIZE;
+	dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
+	dev->tso_max_segs = TSO_MAX_SEGS;
 	dev->upper_level = 1;
 	dev->lower_level = 1;
 #ifdef CONFIG_LOCKDEP
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index eea5ed09e1bb..e6d4b9272995 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2803,7 +2803,7 @@ static int do_setlink(const struct sk_buff *skb,
 	if (tb[IFLA_GSO_MAX_SIZE]) {
 		u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);
 
-		if (max_size > GSO_MAX_SIZE) {
+		if (max_size > GSO_MAX_SIZE || max_size > dev->tso_max_size) {
 			err = -EINVAL;
 			goto errout;
 		}
@@ -2817,7 +2817,7 @@ static int do_setlink(const struct sk_buff *skb,
 	if (tb[IFLA_GSO_MAX_SEGS]) {
 		u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);
 
-		if (max_segs > GSO_MAX_SEGS) {
+		if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) {
 			err = -EINVAL;
 			goto errout;
 		}
-- 
cgit v1.2.3


From 744d49daf8bd3b17b345c836f2e6f97d49fa6ae8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 5 May 2022 19:51:34 -0700
Subject: net: move netif_set_gso_max helpers

These are now internal to the core, no need to expose them.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 21 ---------------------
 net/core/dev.h            | 21 +++++++++++++++++++++
 2 files changed, 21 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e12f7de6d6ae..8cf0ac616cb9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4881,27 +4881,6 @@ static inline bool netif_needs_gso(struct sk_buff *skb,
 			 (skb->ip_summed != CHECKSUM_UNNECESSARY)));
 }
 
-static inline void netif_set_gso_max_size(struct net_device *dev,
-					  unsigned int size)
-{
-	/* dev->gso_max_size is read locklessly from sk_setup_caps() */
-	WRITE_ONCE(dev->gso_max_size, size);
-}
-
-static inline void netif_set_gso_max_segs(struct net_device *dev,
-					  unsigned int segs)
-{
-	/* dev->gso_max_segs is read locklessly from sk_setup_caps() */
-	WRITE_ONCE(dev->gso_max_segs, segs);
-}
-
-static inline void netif_set_gro_max_size(struct net_device *dev,
-					  unsigned int size)
-{
-	/* This pairs with the READ_ONCE() in skb_gro_receive() */
-	WRITE_ONCE(dev->gro_max_size, size);
-}
-
 void netif_set_tso_max_size(struct net_device *dev, unsigned int size);
 void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs);
 void netif_inherit_tso_max(struct net_device *to,
diff --git a/net/core/dev.h b/net/core/dev.h
index 27923df00637..328b37af90ba 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -88,4 +88,25 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier);
 
 void __dev_set_rx_mode(struct net_device *dev);
 
+static inline void netif_set_gso_max_size(struct net_device *dev,
+					  unsigned int size)
+{
+	/* dev->gso_max_size is read locklessly from sk_setup_caps() */
+	WRITE_ONCE(dev->gso_max_size, size);
+}
+
+static inline void netif_set_gso_max_segs(struct net_device *dev,
+					  unsigned int segs)
+{
+	/* dev->gso_max_segs is read locklessly from sk_setup_caps() */
+	WRITE_ONCE(dev->gso_max_segs, segs);
+}
+
+static inline void netif_set_gro_max_size(struct net_device *dev,
+					  unsigned int size)
+{
+	/* This pairs with the READ_ONCE() in skb_gro_receive() */
+	WRITE_ONCE(dev->gro_max_size, size);
+}
+
 #endif
-- 
cgit v1.2.3


From 3ff5f7840979aa36d47a6a00694826c78d63bf3c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 6 May 2022 14:14:36 +0200
Subject: linkage: Fix issue with missing symbol size

Occasionally, typically when a function doesn't end with 'ret', an
alias on that function will have 0 size.

The difference between what GCC generates and our linkage magic, is
that GCC doesn't appear to provide .size for the alias'ed symbol at
all. And indeed, removing this directive cures the issue.

Additionally, GCC also doesn't emit .type for alias symbols either, so
also omit that.

Fixes: e0891269a8c2 ("linkage: add SYM_FUNC_ALIAS{,_LOCAL,_WEAK}()")
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/20220506121631.437480085@infradead.org
---
 include/linux/linkage.h | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index acb1ad2356f1..1feab6136b5b 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -171,12 +171,9 @@
 
 /* SYM_ALIAS -- use only if you have to */
 #ifndef SYM_ALIAS
-#define SYM_ALIAS(alias, name, sym_type, linkage)			\
-	linkage(alias) ASM_NL						\
-	.set alias, name ASM_NL						\
-	.type alias sym_type ASM_NL					\
-	.set .L__sym_size_##alias, .L__sym_size_##name ASM_NL		\
-	.size alias, .L__sym_size_##alias
+#define SYM_ALIAS(alias, name, linkage)			\
+	linkage(alias) ASM_NL				\
+	.set alias, name ASM_NL
 #endif
 
 /* === code annotations === */
@@ -261,7 +258,7 @@
  */
 #ifndef SYM_FUNC_ALIAS
 #define SYM_FUNC_ALIAS(alias, name)					\
-	SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL)
+	SYM_ALIAS(alias, name, SYM_L_GLOBAL)
 #endif
 
 /*
@@ -269,7 +266,7 @@
  */
 #ifndef SYM_FUNC_ALIAS_LOCAL
 #define SYM_FUNC_ALIAS_LOCAL(alias, name)				\
-	SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL)
+	SYM_ALIAS(alias, name, SYM_L_LOCAL)
 #endif
 
 /*
@@ -277,7 +274,7 @@
  */
 #ifndef SYM_FUNC_ALIAS_WEAK
 #define SYM_FUNC_ALIAS_WEAK(alias, name)				\
-	SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK)
+	SYM_ALIAS(alias, name, SYM_L_WEAK)
 #endif
 
 /* SYM_CODE_START -- use for non-C (special) functions */
-- 
cgit v1.2.3


From 6b79738b6ed91a2d0fe958819469eeedac3bca81 Mon Sep 17 00:00:00 2001
From: Qi Liu <liuqi115@huawei.com>
Date: Fri, 15 Apr 2022 18:23:52 +0800
Subject: drivers/perf: hisi: Add Support for CPA PMU

On HiSilicon Hip09 platform, there is a CPA (Coherency Protocol Agent) on
each SICL (Super IO Cluster) which implements packet format translation,
route parsing and traffic statistics.

CPA PMU has 8 PMU counters and interrupt is supported to handle counter
overflow. Let's support its driver under the framework of HiSilicon PMU
driver.

Signed-off-by: Qi Liu <liuqi115@huawei.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Reviewed-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Link: https://lore.kernel.org/r/20220415102352.6665-3-liuqi115@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/hisilicon/Makefile              |   2 +-
 drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c | 409 +++++++++++++++++++++++++++
 include/linux/cpuhotplug.h                   |   1 +
 3 files changed, 411 insertions(+), 1 deletion(-)
 create mode 100644 drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c

(limited to 'include/linux')

diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile
index 506ed39e3266..6be83517acaa 100644
--- a/drivers/perf/hisilicon/Makefile
+++ b/drivers/perf/hisilicon/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \
 			  hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o hisi_uncore_sllc_pmu.o \
-			  hisi_uncore_pa_pmu.o
+			  hisi_uncore_pa_pmu.o hisi_uncore_cpa_pmu.o
 
 obj-$(CONFIG_HISI_PCIE_PMU) += hisi_pcie_pmu.o
diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
new file mode 100644
index 000000000000..a9bb73f76be4
--- /dev/null
+++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HiSilicon SoC CPA(Coherency Protocol Agent) hardware event counters support
+ *
+ * Copyright (C) 2022 HiSilicon Limited
+ * Author: Qi Liu <liuqi115@huawei.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ */
+
+#define pr_fmt(fmt) "cpa pmu: " fmt
+#include <linux/acpi.h>
+#include <linux/bug.h>
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/smp.h>
+
+#include "hisi_uncore_pmu.h"
+
+/* CPA register definition */
+#define CPA_PERF_CTRL		0x1c00
+#define CPA_EVENT_CTRL		0x1c04
+#define CPA_INT_MASK		0x1c70
+#define CPA_INT_STATUS		0x1c78
+#define CPA_INT_CLEAR		0x1c7c
+#define CPA_EVENT_TYPE0		0x1c80
+#define CPA_VERSION		0x1cf0
+#define CPA_CNT0_LOWER		0x1d00
+#define CPA_CFG_REG		0x0534
+
+/* CPA operation command */
+#define CPA_PERF_CTRL_EN	BIT_ULL(0)
+#define CPA_EVTYPE_MASK		0xffUL
+#define CPA_PM_CTRL		BIT_ULL(9)
+
+/* CPA has 8-counters */
+#define CPA_NR_COUNTERS		0x8
+#define CPA_COUNTER_BITS	64
+#define CPA_NR_EVENTS		0xff
+#define CPA_REG_OFFSET		0x8
+
+static u32 hisi_cpa_pmu_get_counter_offset(int idx)
+{
+	return (CPA_CNT0_LOWER + idx * CPA_REG_OFFSET);
+}
+
+static u64 hisi_cpa_pmu_read_counter(struct hisi_pmu *cpa_pmu,
+				     struct hw_perf_event *hwc)
+{
+	return readq(cpa_pmu->base + hisi_cpa_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_cpa_pmu_write_counter(struct hisi_pmu *cpa_pmu,
+				       struct hw_perf_event *hwc, u64 val)
+{
+	writeq(val, cpa_pmu->base + hisi_cpa_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_cpa_pmu_write_evtype(struct hisi_pmu *cpa_pmu, int idx,
+				      u32 type)
+{
+	u32 reg, reg_idx, shift, val;
+
+	/*
+	 * Select the appropriate event select register(CPA_EVENT_TYPE0/1).
+	 * There are 2 event select registers for the 8 hardware counters.
+	 * Event code is 8-bits and for the former 4 hardware counters,
+	 * CPA_EVENT_TYPE0 is chosen. For the latter 4 hardware counters,
+	 * CPA_EVENT_TYPE1 is chosen.
+	 */
+	reg = CPA_EVENT_TYPE0 + (idx / 4) * 4;
+	reg_idx = idx % 4;
+	shift = CPA_REG_OFFSET * reg_idx;
+
+	/* Write event code to CPA_EVENT_TYPEx Register */
+	val = readl(cpa_pmu->base + reg);
+	val &= ~(CPA_EVTYPE_MASK << shift);
+	val |= type << shift;
+	writel(val, cpa_pmu->base + reg);
+}
+
+static void hisi_cpa_pmu_start_counters(struct hisi_pmu *cpa_pmu)
+{
+	u32 val;
+
+	val = readl(cpa_pmu->base + CPA_PERF_CTRL);
+	val |= CPA_PERF_CTRL_EN;
+	writel(val, cpa_pmu->base + CPA_PERF_CTRL);
+}
+
+static void hisi_cpa_pmu_stop_counters(struct hisi_pmu *cpa_pmu)
+{
+	u32 val;
+
+	val = readl(cpa_pmu->base + CPA_PERF_CTRL);
+	val &= ~(CPA_PERF_CTRL_EN);
+	writel(val, cpa_pmu->base + CPA_PERF_CTRL);
+}
+
+static void hisi_cpa_pmu_disable_pm(struct hisi_pmu *cpa_pmu)
+{
+	u32 val;
+
+	val = readl(cpa_pmu->base + CPA_CFG_REG);
+	val |= CPA_PM_CTRL;
+	writel(val, cpa_pmu->base + CPA_CFG_REG);
+}
+
+static void hisi_cpa_pmu_enable_pm(struct hisi_pmu *cpa_pmu)
+{
+	u32 val;
+
+	val = readl(cpa_pmu->base + CPA_CFG_REG);
+	val &= ~(CPA_PM_CTRL);
+	writel(val, cpa_pmu->base + CPA_CFG_REG);
+}
+
+static void hisi_cpa_pmu_enable_counter(struct hisi_pmu *cpa_pmu,
+					struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Enable counter index in CPA_EVENT_CTRL register */
+	val = readl(cpa_pmu->base + CPA_EVENT_CTRL);
+	val |= 1 << hwc->idx;
+	writel(val, cpa_pmu->base + CPA_EVENT_CTRL);
+}
+
+static void hisi_cpa_pmu_disable_counter(struct hisi_pmu *cpa_pmu,
+					 struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Clear counter index in CPA_EVENT_CTRL register */
+	val = readl(cpa_pmu->base + CPA_EVENT_CTRL);
+	val &= ~(1UL << hwc->idx);
+	writel(val, cpa_pmu->base + CPA_EVENT_CTRL);
+}
+
+static void hisi_cpa_pmu_enable_counter_int(struct hisi_pmu *cpa_pmu,
+					    struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Write 0 to enable interrupt */
+	val = readl(cpa_pmu->base + CPA_INT_MASK);
+	val &= ~(1UL << hwc->idx);
+	writel(val, cpa_pmu->base + CPA_INT_MASK);
+}
+
+static void hisi_cpa_pmu_disable_counter_int(struct hisi_pmu *cpa_pmu,
+					     struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Write 1 to mask interrupt */
+	val = readl(cpa_pmu->base + CPA_INT_MASK);
+	val |= 1 << hwc->idx;
+	writel(val, cpa_pmu->base + CPA_INT_MASK);
+}
+
+static u32 hisi_cpa_pmu_get_int_status(struct hisi_pmu *cpa_pmu)
+{
+	return readl(cpa_pmu->base + CPA_INT_STATUS);
+}
+
+static void hisi_cpa_pmu_clear_int_status(struct hisi_pmu *cpa_pmu, int idx)
+{
+	writel(1 << idx, cpa_pmu->base + CPA_INT_CLEAR);
+}
+
+static const struct acpi_device_id hisi_cpa_pmu_acpi_match[] = {
+	{ "HISI0281", },
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, hisi_cpa_pmu_acpi_match);
+
+static int hisi_cpa_pmu_init_data(struct platform_device *pdev,
+				  struct hisi_pmu *cpa_pmu)
+{
+	if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id",
+				     &cpa_pmu->sicl_id)) {
+		dev_err(&pdev->dev, "Can not read sicl-id\n");
+		return -EINVAL;
+	}
+
+	if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id",
+				     &cpa_pmu->index_id)) {
+		dev_err(&pdev->dev, "Cannot read idx-id\n");
+		return -EINVAL;
+	}
+
+	cpa_pmu->ccl_id = -1;
+	cpa_pmu->sccl_id = -1;
+	cpa_pmu->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(cpa_pmu->base))
+		return PTR_ERR(cpa_pmu->base);
+
+	cpa_pmu->identifier = readl(cpa_pmu->base + CPA_VERSION);
+
+	return 0;
+}
+
+static struct attribute *hisi_cpa_pmu_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-15"),
+	NULL
+};
+
+static const struct attribute_group hisi_cpa_pmu_format_group = {
+	.name = "format",
+	.attrs = hisi_cpa_pmu_format_attr,
+};
+
+static struct attribute *hisi_cpa_pmu_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(cpa_cycles,		0x00),
+	HISI_PMU_EVENT_ATTR(cpa_p1_wr_dat,	0x61),
+	HISI_PMU_EVENT_ATTR(cpa_p1_rd_dat,	0x62),
+	HISI_PMU_EVENT_ATTR(cpa_p0_wr_dat,	0xE1),
+	HISI_PMU_EVENT_ATTR(cpa_p0_rd_dat,	0xE2),
+	NULL
+};
+
+static const struct attribute_group hisi_cpa_pmu_events_group = {
+	.name = "events",
+	.attrs = hisi_cpa_pmu_events_attr,
+};
+
+static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
+
+static struct attribute *hisi_cpa_pmu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL
+};
+
+static const struct attribute_group hisi_cpa_pmu_cpumask_attr_group = {
+	.attrs = hisi_cpa_pmu_cpumask_attrs,
+};
+
+static struct device_attribute hisi_cpa_pmu_identifier_attr =
+	__ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL);
+
+static struct attribute *hisi_cpa_pmu_identifier_attrs[] = {
+	&hisi_cpa_pmu_identifier_attr.attr,
+	NULL
+};
+
+static const struct attribute_group hisi_cpa_pmu_identifier_group = {
+	.attrs = hisi_cpa_pmu_identifier_attrs,
+};
+
+static const struct attribute_group *hisi_cpa_pmu_attr_groups[] = {
+	&hisi_cpa_pmu_format_group,
+	&hisi_cpa_pmu_events_group,
+	&hisi_cpa_pmu_cpumask_attr_group,
+	&hisi_cpa_pmu_identifier_group,
+	NULL
+};
+
+static const struct hisi_uncore_ops hisi_uncore_cpa_pmu_ops = {
+	.write_evtype           = hisi_cpa_pmu_write_evtype,
+	.get_event_idx		= hisi_uncore_pmu_get_event_idx,
+	.start_counters		= hisi_cpa_pmu_start_counters,
+	.stop_counters		= hisi_cpa_pmu_stop_counters,
+	.enable_counter		= hisi_cpa_pmu_enable_counter,
+	.disable_counter	= hisi_cpa_pmu_disable_counter,
+	.enable_counter_int	= hisi_cpa_pmu_enable_counter_int,
+	.disable_counter_int	= hisi_cpa_pmu_disable_counter_int,
+	.write_counter		= hisi_cpa_pmu_write_counter,
+	.read_counter		= hisi_cpa_pmu_read_counter,
+	.get_int_status		= hisi_cpa_pmu_get_int_status,
+	.clear_int_status	= hisi_cpa_pmu_clear_int_status,
+};
+
+static int hisi_cpa_pmu_dev_probe(struct platform_device *pdev,
+				  struct hisi_pmu *cpa_pmu)
+{
+	int ret;
+
+	ret = hisi_cpa_pmu_init_data(pdev, cpa_pmu);
+	if (ret)
+		return ret;
+
+	ret = hisi_uncore_pmu_init_irq(cpa_pmu, pdev);
+	if (ret)
+		return ret;
+
+	cpa_pmu->counter_bits = CPA_COUNTER_BITS;
+	cpa_pmu->check_event = CPA_NR_EVENTS;
+	cpa_pmu->pmu_events.attr_groups = hisi_cpa_pmu_attr_groups;
+	cpa_pmu->ops = &hisi_uncore_cpa_pmu_ops;
+	cpa_pmu->num_counters = CPA_NR_COUNTERS;
+	cpa_pmu->dev = &pdev->dev;
+	cpa_pmu->on_cpu = -1;
+
+	return 0;
+}
+
+static int hisi_cpa_pmu_probe(struct platform_device *pdev)
+{
+	struct hisi_pmu *cpa_pmu;
+	char *name;
+	int ret;
+
+	cpa_pmu = devm_kzalloc(&pdev->dev, sizeof(*cpa_pmu), GFP_KERNEL);
+	if (!cpa_pmu)
+		return -ENOMEM;
+
+	ret = hisi_cpa_pmu_dev_probe(pdev, cpa_pmu);
+	if (ret)
+		return ret;
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_cpa%u",
+			      cpa_pmu->sicl_id, cpa_pmu->index_id);
+	if (!name)
+		return -ENOMEM;
+
+	cpa_pmu->pmu = (struct pmu) {
+		.name		= name,
+		.module		= THIS_MODULE,
+		.task_ctx_nr	= perf_invalid_context,
+		.event_init	= hisi_uncore_pmu_event_init,
+		.pmu_enable	= hisi_uncore_pmu_enable,
+		.pmu_disable	= hisi_uncore_pmu_disable,
+		.add		= hisi_uncore_pmu_add,
+		.del		= hisi_uncore_pmu_del,
+		.start		= hisi_uncore_pmu_start,
+		.stop		= hisi_uncore_pmu_stop,
+		.read		= hisi_uncore_pmu_read,
+		.attr_groups	= cpa_pmu->pmu_events.attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	};
+
+	/* Power Management should be disabled before using CPA PMU. */
+	hisi_cpa_pmu_disable_pm(cpa_pmu);
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE,
+				       &cpa_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+		hisi_cpa_pmu_enable_pm(cpa_pmu);
+		return ret;
+	}
+
+	ret = perf_pmu_register(&cpa_pmu->pmu, name, -1);
+	if (ret) {
+		dev_err(cpa_pmu->dev, "PMU register failed\n");
+		cpuhp_state_remove_instance_nocalls(
+			CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, &cpa_pmu->node);
+		hisi_cpa_pmu_enable_pm(cpa_pmu);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, cpa_pmu);
+	return ret;
+}
+
+static int hisi_cpa_pmu_remove(struct platform_device *pdev)
+{
+	struct hisi_pmu *cpa_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&cpa_pmu->pmu);
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE,
+					    &cpa_pmu->node);
+	hisi_cpa_pmu_enable_pm(cpa_pmu);
+	return 0;
+}
+
+static struct platform_driver hisi_cpa_pmu_driver = {
+	.driver = {
+		.name = "hisi_cpa_pmu",
+		.acpi_match_table = ACPI_PTR(hisi_cpa_pmu_acpi_match),
+		.suppress_bind_attrs = true,
+	},
+	.probe = hisi_cpa_pmu_probe,
+	.remove = hisi_cpa_pmu_remove,
+};
+
+static int __init hisi_cpa_pmu_module_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE,
+				      "AP_PERF_ARM_HISI_CPA_ONLINE",
+				      hisi_uncore_pmu_online_cpu,
+				      hisi_uncore_pmu_offline_cpu);
+	if (ret) {
+		pr_err("setup hotplug failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = platform_driver_register(&hisi_cpa_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE);
+
+	return ret;
+}
+module_init(hisi_cpa_pmu_module_init);
+
+static void __exit hisi_cpa_pmu_module_exit(void)
+{
+	platform_driver_unregister(&hisi_cpa_pmu_driver);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE);
+}
+module_exit(hisi_cpa_pmu_module_exit);
+
+MODULE_DESCRIPTION("HiSilicon SoC CPA PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Qi Liu <liuqi115@huawei.com>");
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 82e33137f917..b66c5f389159 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -222,6 +222,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,
 	CPUHP_AP_PERF_ARM_CCN_ONLINE,
+	CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE,
 	CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
 	CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
 	CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
-- 
cgit v1.2.3


From 343f4c49f2438d8920f1f76fa823ee59b91f02e4 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 11 Apr 2022 11:40:14 -0500
Subject: kthread: Don't allocate kthread_struct for init and umh
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If kthread_is_per_cpu runs concurrently with free_kthread_struct the
kthread_struct that was just freed may be read from.

This bug was introduced by commit 40966e316f86 ("kthread: Ensure
struct kthread is present for all kthreads").  When kthread_struct
started to be allocated for all tasks that have PF_KTHREAD set.  This
in turn required the kthread_struct to be freed in kernel_execve and
violated the assumption that kthread_struct will have the same
lifetime as the task.

Looking a bit deeper this only applies to callers of kernel_execve
which is just the init process and the user mode helper processes.
These processes really don't want to be kernel threads but are for
historical reasons.  Mostly that copy_thread does not know how to take
a kernel mode function to the process with for processes without
PF_KTHREAD or PF_IO_WORKER set.

Solve this by not allocating kthread_struct for the init process and
the user mode helper processes.

This is done by adding a kthread member to struct kernel_clone_args.
Setting kthread in fork_idle and kernel_thread.  Adding
user_mode_thread that works like kernel_thread except it does not set
kthread.  In fork only allocating the kthread_struct if .kthread is set.

I have looked at kernel/kthread.c and since commit 40966e316f86
("kthread: Ensure struct kthread is present for all kthreads") there
have been no assumptions added that to_kthread or __to_kthread will
not return NULL.

There are a few callers of to_kthread or __to_kthread that assume a
non-NULL struct kthread pointer will be returned.  These functions are
kthread_data(), kthread_parmme(), kthread_exit(), kthread(),
kthread_park(), kthread_unpark(), kthread_stop().  All of those functions
can reasonably expected to be called when it is know that a task is a
kthread so that assumption seems reasonable.

Cc: stable@vger.kernel.org
Fixes: 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads")
Reported-by: Максим Кутявин <maximkabox13@gmail.com>
Link: https://lkml.kernel.org/r/20220506141512.516114-1-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/exec.c                  |  6 ++++--
 include/linux/sched/task.h |  2 ++
 init/main.c                |  2 +-
 kernel/fork.c              | 22 ++++++++++++++++++++--
 kernel/umh.c               |  6 +++---
 5 files changed, 30 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index e3e55d5e0be1..75eb6e0ee7b2 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1308,8 +1308,6 @@ int begin_new_exec(struct linux_binprm * bprm)
 	if (retval)
 		goto out_unlock;
 
-	if (me->flags & PF_KTHREAD)
-		free_kthread_struct(me);
 	me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
 					PF_NOFREEZE | PF_NO_SETAFFINITY);
 	flush_thread();
@@ -1955,6 +1953,10 @@ int kernel_execve(const char *kernel_filename,
 	int fd = AT_FDCWD;
 	int retval;
 
+	if (WARN_ON_ONCE((current->flags & PF_KTHREAD) &&
+			(current->worker_private)))
+		return -EINVAL;
+
 	filename = getname_kernel(kernel_filename);
 	if (IS_ERR(filename))
 		return PTR_ERR(filename);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 719c9a6cac8d..4492266935dd 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -32,6 +32,7 @@ struct kernel_clone_args {
 	size_t set_tid_size;
 	int cgroup;
 	int io_thread;
+	int kthread;
 	struct cgroup *cgrp;
 	struct css_set *cset;
 };
@@ -89,6 +90,7 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
+extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 int kernel_wait(pid_t pid, int *stat);
 
diff --git a/init/main.c b/init/main.c
index 98182c3c2c4b..39baac0211c6 100644
--- a/init/main.c
+++ b/init/main.c
@@ -688,7 +688,7 @@ noinline void __ref rest_init(void)
 	 * the init task will end up wanting to create kthreads, which, if
 	 * we schedule it before we create kthreadd, will OOPS.
 	 */
-	pid = kernel_thread(kernel_init, NULL, CLONE_FS);
+	pid = user_mode_thread(kernel_init, NULL, CLONE_FS);
 	/*
 	 * Pin init on the boot CPU. Task migration is not properly working
 	 * until sched_init_smp() has been run. It will set the allowed
diff --git a/kernel/fork.c b/kernel/fork.c
index 9796897560ab..27c5203750b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2157,7 +2157,7 @@ static __latent_entropy struct task_struct *copy_process(
 	p->io_context = NULL;
 	audit_set_context(p, NULL);
 	cgroup_fork(p);
-	if (p->flags & PF_KTHREAD) {
+	if (args->kthread) {
 		if (!set_kthread_struct(p))
 			goto bad_fork_cleanup_delayacct;
 	}
@@ -2548,7 +2548,8 @@ struct task_struct * __init fork_idle(int cpu)
 {
 	struct task_struct *task;
 	struct kernel_clone_args args = {
-		.flags = CLONE_VM,
+		.flags		= CLONE_VM,
+		.kthread	= 1,
 	};
 
 	task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args);
@@ -2679,6 +2680,23 @@ pid_t kernel_clone(struct kernel_clone_args *args)
  * Create a kernel thread.
  */
 pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
+{
+	struct kernel_clone_args args = {
+		.flags		= ((lower_32_bits(flags) | CLONE_VM |
+				    CLONE_UNTRACED) & ~CSIGNAL),
+		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
+		.stack		= (unsigned long)fn,
+		.stack_size	= (unsigned long)arg,
+		.kthread	= 1,
+	};
+
+	return kernel_clone(&args);
+}
+
+/*
+ * Create a user mode thread.
+ */
+pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags)
 {
 	struct kernel_clone_args args = {
 		.flags		= ((lower_32_bits(flags) | CLONE_VM |
diff --git a/kernel/umh.c b/kernel/umh.c
index 36c123360ab8..b989736e8707 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -132,7 +132,7 @@ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info)
 
 	/* If SIGCLD is ignored do_wait won't populate the status. */
 	kernel_sigaction(SIGCHLD, SIG_DFL);
-	pid = kernel_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
+	pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
 	if (pid < 0)
 		sub_info->retval = pid;
 	else
@@ -171,8 +171,8 @@ static void call_usermodehelper_exec_work(struct work_struct *work)
 		 * want to pollute current->children, and we need a parent
 		 * that always ignores SIGCHLD to ensure auto-reaping.
 		 */
-		pid = kernel_thread(call_usermodehelper_exec_async, sub_info,
-				    CLONE_PARENT | SIGCHLD);
+		pid = user_mode_thread(call_usermodehelper_exec_async, sub_info,
+				       CLONE_PARENT | SIGCHLD);
 		if (pid < 0) {
 			sub_info->retval = pid;
 			umh_complete(sub_info);
-- 
cgit v1.2.3


From e2ef115813c34ea5380ac5b4879f515070150210 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 6 May 2022 14:14:37 +0200
Subject: objtool: Fix STACK_FRAME_NON_STANDARD reloc type

STACK_FRAME_NON_STANDARD results in inconsistent relocation types
depending on .c or .S usage:

  Relocation section '.rela.discard.func_stack_frame_non_standard' at offset 0x3c01090 contains 5 entries:
  Offset             Info             Type               Symbol's Value  Symbol's Name + Addend
  0000000000000000  00020c2200000002 R_X86_64_PC32          0000000000047b40 do_suspend_lowlevel + 0
  0000000000000008  0002461e00000001 R_X86_64_64            00000000000480a0 machine_real_restart + 0
  0000000000000010  0000001400000001 R_X86_64_64            0000000000000000 .rodata + b3d4
  0000000000000018  0002444600000002 R_X86_64_PC32          00000000000678a0 __efi64_thunk + 0
  0000000000000020  0002659d00000001 R_X86_64_64            0000000000113160 __crash_kexec + 0

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20220506121631.508692613@infradead.org
---
 include/linux/objtool.h       | 4 +++-
 tools/include/linux/objtool.h | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 586d35720f13..b9c1474a571e 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -40,6 +40,8 @@ struct unwind_hint {
 
 #ifdef CONFIG_STACK_VALIDATION
 
+#include <asm/asm.h>
+
 #ifndef __ASSEMBLY__
 
 #define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
@@ -137,7 +139,7 @@ struct unwind_hint {
 
 .macro STACK_FRAME_NON_STANDARD func:req
 	.pushsection .discard.func_stack_frame_non_standard, "aw"
-		.long \func - .
+	_ASM_PTR \func
 	.popsection
 .endm
 
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
index 586d35720f13..b9c1474a571e 100644
--- a/tools/include/linux/objtool.h
+++ b/tools/include/linux/objtool.h
@@ -40,6 +40,8 @@ struct unwind_hint {
 
 #ifdef CONFIG_STACK_VALIDATION
 
+#include <asm/asm.h>
+
 #ifndef __ASSEMBLY__
 
 #define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
@@ -137,7 +139,7 @@ struct unwind_hint {
 
 .macro STACK_FRAME_NON_STANDARD func:req
 	.pushsection .discard.func_stack_frame_non_standard, "aw"
-		.long \func - .
+	_ASM_PTR \func
 	.popsection
 .endm
 
-- 
cgit v1.2.3


From c5febea0956fd3874e8fb59c6f84d68f128d68f8 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 8 Apr 2022 18:07:50 -0500
Subject: fork: Pass struct kernel_clone_args into copy_thread

With io_uring we have started supporting tasks that are for most
purposes user space tasks that exclusively run code in kernel mode.

The kernel task that exec's init and tasks that exec user mode
helpers are also user mode tasks that just run kernel code
until they call kernel execve.

Pass kernel_clone_args into copy_thread so these oddball
tasks can be supported more cleanly and easily.

v2: Fix spelling of kenrel_clone_args on h8300
Link: https://lkml.kernel.org/r/20220506141512.516114-2-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/alpha/kernel/process.c      |  8 +++++---
 arch/arc/kernel/process.c        |  8 +++++---
 arch/arm/kernel/process.c        |  7 +++++--
 arch/arm64/kernel/process.c      |  7 +++++--
 arch/csky/kernel/process.c       | 10 +++++-----
 arch/h8300/kernel/process.c      |  5 +++--
 arch/hexagon/kernel/process.c    |  7 +++++--
 arch/ia64/kernel/process.c       |  7 +++++--
 arch/m68k/kernel/process.c       |  7 +++++--
 arch/microblaze/kernel/process.c |  7 +++++--
 arch/mips/kernel/process.c       |  8 +++++---
 arch/nios2/kernel/process.c      |  7 +++++--
 arch/openrisc/kernel/process.c   |  7 +++++--
 arch/parisc/kernel/process.c     |  7 +++++--
 arch/powerpc/kernel/process.c    |  8 +++++---
 arch/riscv/kernel/process.c      |  7 +++++--
 arch/s390/kernel/process.c       |  7 +++++--
 arch/sh/kernel/process_32.c      |  7 +++++--
 arch/sparc/kernel/process_32.c   |  7 +++++--
 arch/sparc/kernel/process_64.c   |  7 +++++--
 arch/um/kernel/process.c         |  7 +++++--
 arch/x86/kernel/process.c        |  7 +++++--
 arch/xtensa/kernel/process.c     |  8 +++++---
 include/linux/sched/task.h       |  3 +--
 kernel/fork.c                    |  4 ++--
 25 files changed, 116 insertions(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 5f8527081da9..732e39217c7f 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -233,10 +233,12 @@ release_thread(struct task_struct *dead_task)
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long kthread_arg, struct task_struct *p,
-		unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long kthread_arg = args->stack_size;
+	unsigned long tls = args->tls;
 	extern void ret_from_fork(void);
 	extern void ret_from_kernel_thread(void);
 
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 5f7f5aab361f..caf948ba647c 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -162,10 +162,12 @@ asmlinkage void ret_from_fork(void);
  * |    user_r25    |
  * ------------------  <===== END of PAGE
  */
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long kthread_arg, struct task_struct *p,
-		unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long kthread_arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *c_regs;        /* child's pt_regs */
 	unsigned long *childksp;       /* to unwind out of __switch_to() */
 	struct callee_regs *c_callee;  /* child's callee regs */
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 0617af11377f..8e13b426dd26 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -238,9 +238,12 @@ void release_thread(struct task_struct *dead_task)
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
-int copy_thread(unsigned long clone_flags, unsigned long stack_start,
-		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long stack_start = args->stack;
+	unsigned long stk_sz = args->stack_size;
+	unsigned long tls = args->tls;
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7fa97df55e3a..e002f6681c8d 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -316,9 +316,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 asmlinkage void ret_from_fork(void) asm("ret_from_fork");
 
-int copy_thread(unsigned long clone_flags, unsigned long stack_start,
-		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long stack_start = args->stack;
+	unsigned long stk_sz = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
index 3d0ca22cd0e2..7dba33d37e1a 100644
--- a/arch/csky/kernel/process.c
+++ b/arch/csky/kernel/process.c
@@ -30,12 +30,12 @@ asmlinkage void ret_from_kernel_thread(void);
  */
 void flush_thread(void){}
 
-int copy_thread(unsigned long clone_flags,
-		unsigned long usp,
-		unsigned long kthread_arg,
-		struct task_struct *p,
-		unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long kthread_arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct switch_stack *childstack;
 	struct pt_regs *childregs = task_pt_regs(p);
 
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 8833fa4f5d51..752cbd9b0bf6 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -105,9 +105,10 @@ void flush_thread(void)
 {
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long topstk, struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long usp = args->stack;
+	unsigned long topstk = args->stack_size;
 	struct pt_regs *childregs;
 
 	childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1;
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index eab03c691f53..f1c1f6f21941 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -50,9 +50,12 @@ void arch_cpu_idle(void)
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct hexagon_switch_stack *ss;
 	struct pt_regs *childregs;
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index d7a256bd9d6b..10d41ded05a5 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -295,9 +295,12 @@ ia64_load_extra (struct task_struct *task)
  * so there is nothing to worry about.
  */
 int
-copy_thread(unsigned long clone_flags, unsigned long user_stack_base,
-	    unsigned long user_stack_size, struct task_struct *p, unsigned long tls)
+copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long user_stack_base = args->stack;
+	unsigned long user_stack_size = args->stack_size;
+	unsigned long tls = args->tls;
 	extern char ia64_ret_from_clone;
 	struct switch_stack *child_stack, *stack;
 	unsigned long rbs, child_rbs, rbs_size;
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index a6030dbaa089..8ac575656fc4 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -138,9 +138,12 @@ asmlinkage int m68k_clone3(struct pt_regs *regs)
 	return sys_clone3((struct clone_args __user *)regs->d1, regs->d2);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct fork_frame {
 		struct switch_stack sw;
 		struct pt_regs regs;
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 1b944d319d73..b5f549125c6a 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -52,9 +52,12 @@ void flush_thread(void)
 {
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct thread_info *ti = task_thread_info(p);
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index c2d5f4bfe1f3..a572d097b16b 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -105,10 +105,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long kthread_arg, struct task_struct *p,
-		unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long kthread_arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
 	unsigned long childksp;
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index f8ea522a1588..98c4bfe972e0 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -100,9 +100,12 @@ void flush_thread(void)
 {
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct pt_regs *regs;
 	struct switch_stack *stack;
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 3c0c91bcdcba..486e46dd5883 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -152,9 +152,12 @@ extern asmlinkage void ret_from_fork(void);
  */
 
 int
-copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
-	    struct task_struct *p, unsigned long tls)
+copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *userregs;
 	struct pt_regs *kregs;
 	unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 28b6a2a5574c..129c17de45ba 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -206,9 +206,12 @@ arch_initcall(parisc_idle_init);
  * Copy architecture-specific thread state
  */
 int
-copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
+copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long kthread_arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *cregs = &(p->thread.regs);
 	void *stack = task_stack_page(p);
 	
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 984813a4d5dc..3fd67c861d54 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1716,10 +1716,12 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp)
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long kthread_arg, struct task_struct *p,
-		unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long kthread_arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *childregs, *kregs;
 	extern void ret_from_fork(void);
 	extern void ret_from_fork_scv(void);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 504b496787aa..334382731725 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -120,9 +120,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
 	/* p->thread holds context to be restored by __switch_to() */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 71d86f73b02c..bb5daec39516 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -94,9 +94,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
-		unsigned long arg, struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long new_stackp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct fake_frame
 	{
 		struct stack_frame sf;
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index ca01286a0610..6023399b1892 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -92,9 +92,12 @@ void release_thread(struct task_struct *dead_task)
 asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
-int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs;
 
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 88c0c14aaff0..80e6775e18c0 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -259,9 +259,12 @@ clone_stackframe(struct sparc_stackf __user *dst,
 extern void ret_from_fork(void);
 extern void ret_from_kernel_thread(void);
 
-int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long sp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
 	char *new_stack;
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 9a2ceb080ac9..38c46ca826d9 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -564,9 +564,12 @@ barf:
  * Parent -->  %o0 == childs  pid, %o1 == 0
  * Child  -->  %o0 == parents pid, %o1 == 1
  */
-int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long sp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct thread_info *t = task_thread_info(p);
 	struct pt_regs *regs = current_pt_regs();
 	struct sparc_stackf *parent_sf;
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 80504680be08..fd2d2361484d 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -154,9 +154,12 @@ void fork_handler(void)
 	userspace(&current->thread.regs.regs, current_thread_info()->aux_fp_regs);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg, struct task_struct * p, unsigned long tls)
+int copy_thread(struct task_struct * p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long sp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	void (*handler)(void);
 	int kthread = current->flags & (PF_KTHREAD | PF_IO_WORKER);
 	int ret = 0;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b370767f5b19..0fce52b10dc4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -130,9 +130,12 @@ static int set_new_tls(struct task_struct *p, unsigned long tls)
 		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long sp = args->stack;
+	unsigned long arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct inactive_task_frame *frame;
 	struct fork_frame *fork_frame;
 	struct pt_regs *childregs;
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index e8bfbca5f001..15ce25073142 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -201,10 +201,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
  * involved.  Much simpler to just not copy those live frames across.
  */
 
-int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
-		unsigned long thread_fn_arg, struct task_struct *p,
-		unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long usp_thread_fn = args->stack;
+	unsigned long thread_fn_arg = args->stack_size;
+	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
 #if (XTENSA_HAVE_COPROCESSORS || XTENSA_HAVE_IO_PORTS)
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 4492266935dd..fcdcba231aac 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -68,8 +68,7 @@ extern void fork_init(void);
 
 extern void release_task(struct task_struct * p);
 
-extern int copy_thread(unsigned long, unsigned long, unsigned long,
-		       struct task_struct *, unsigned long);
+extern int copy_thread(struct task_struct *, const struct kernel_clone_args *);
 
 extern void flush_thread(void);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 27c5203750b4..d39a248a8d8d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1979,7 +1979,7 @@ static __latent_entropy struct task_struct *copy_process(
 	struct task_struct *p;
 	struct multiprocess_signals delayed;
 	struct file *pidfile = NULL;
-	u64 clone_flags = args->flags;
+	const u64 clone_flags = args->flags;
 	struct nsproxy *nsp = current->nsproxy;
 
 	/*
@@ -2240,7 +2240,7 @@ static __latent_entropy struct task_struct *copy_process(
 	retval = copy_io(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread(clone_flags, args->stack, args->stack_size, p, args->tls);
+	retval = copy_thread(p, args);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
-- 
cgit v1.2.3


From 36cb0e1cda645ee645b85a6ce652cb46a16e14e5 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 11 Apr 2022 16:17:28 -0500
Subject: fork: Explicity test for idle tasks in copy_thread

The architectures ia64 and parisc have special handling for the idle
thread in copy_process.  Add a flag named idle to kernel_clone_args
and use it to explicity test if an idle process is being created.

Fullfill the expectations of the rest of the copy_thread
implemetations and pass a function pointer in .stack from fork_idle().
This makes what is happening in copy_thread better defined, and is
useful to make idle threads less special.

Link: https://lkml.kernel.org/r/20220506141512.516114-3-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/ia64/kernel/process.c   | 2 +-
 arch/parisc/kernel/process.c | 2 +-
 include/linux/sched/task.h   | 1 +
 kernel/fork.c                | 9 +++++++++
 4 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 10d41ded05a5..8f010ae818bc 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -342,7 +342,7 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	ia64_drop_fpu(p);	/* don't pick up stale state from a CPU's fph */
 
 	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
-		if (unlikely(!user_stack_base)) {
+		if (unlikely(args->idle)) {
 			/* fork_idle() called us */
 			return 0;
 		}
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 129c17de45ba..30a5874ca845 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -224,7 +224,7 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
 		/* kernel thread */
 		memset(cregs, 0, sizeof(struct pt_regs));
-		if (!usp) /* idle thread */
+		if (args->idle) /* idle thread */
 			return 0;
 		/* Must exit via ret_from_kernel_thread in order
 		 * to call schedule_tail()
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index fcdcba231aac..3d6b99ce5408 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -33,6 +33,7 @@ struct kernel_clone_args {
 	int cgroup;
 	int io_thread;
 	int kthread;
+	int idle;
 	struct cgroup *cgrp;
 	struct css_set *cset;
 };
diff --git a/kernel/fork.c b/kernel/fork.c
index d39a248a8d8d..93d77ee921ff 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2544,12 +2544,21 @@ static inline void init_idle_pids(struct task_struct *idle)
 	}
 }
 
+static int idle_dummy(void *dummy)
+{
+	/* This function is never called */
+	return 0;
+}
+
 struct task_struct * __init fork_idle(int cpu)
 {
 	struct task_struct *task;
 	struct kernel_clone_args args = {
 		.flags		= CLONE_VM,
+		.stack		= (unsigned long)&idle_dummy,
+		.stack_size	= (unsigned long)NULL,
 		.kthread	= 1,
+		.idle		= 1,
 	};
 
 	task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args);
-- 
cgit v1.2.3


From 5bd2e97c868a8a44470950ed01846cab6328e540 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 12 Apr 2022 10:18:48 -0500
Subject: fork: Generalize PF_IO_WORKER handling

Add fn and fn_arg members into struct kernel_clone_args and test for
them in copy_thread (instead of testing for PF_KTHREAD | PF_IO_WORKER).
This allows any task that wants to be a user space task that only runs
in kernel mode to use this functionality.

The code on x86 is an exception and still retains a PF_KTHREAD test
because x86 unlikely everything else handles kthreads slightly
differently than user space tasks that start with a function.

The functions that created tasks that start with a function
have been updated to set ".fn" and ".fn_arg" instead of
".stack" and ".stack_size".  These functions are fork_idle(),
create_io_thread(), kernel_thread(), and user_mode_thread().

Link: https://lkml.kernel.org/r/20220506141512.516114-4-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/alpha/kernel/process.c      |  7 +++----
 arch/arc/kernel/process.c        |  7 +++----
 arch/arm/kernel/process.c        |  7 +++----
 arch/arm64/kernel/process.c      |  7 +++----
 arch/csky/kernel/process.c       |  7 +++----
 arch/h8300/kernel/process.c      |  7 +++----
 arch/hexagon/kernel/process.c    |  7 +++----
 arch/ia64/kernel/process.c       |  6 +++---
 arch/m68k/kernel/process.c       |  7 +++----
 arch/microblaze/kernel/process.c |  7 +++----
 arch/mips/kernel/process.c       |  7 +++----
 arch/nios2/kernel/process.c      |  7 +++----
 arch/openrisc/kernel/process.c   |  7 +++----
 arch/parisc/kernel/process.c     | 11 +++++------
 arch/powerpc/kernel/process.c    |  9 ++++-----
 arch/riscv/kernel/process.c      |  7 +++----
 arch/s390/kernel/process.c       |  7 +++----
 arch/sh/kernel/process_32.c      |  7 +++----
 arch/sparc/kernel/process_32.c   |  7 +++----
 arch/sparc/kernel/process_64.c   |  7 +++----
 arch/um/kernel/process.c         | 10 ++++------
 arch/x86/include/asm/fpu/sched.h |  2 +-
 arch/x86/include/asm/switch_to.h |  8 ++++----
 arch/x86/kernel/fpu/core.c       |  4 ++--
 arch/x86/kernel/process.c        | 13 ++++++-------
 arch/xtensa/kernel/process.c     | 11 +++++------
 include/linux/sched/task.h       |  2 ++
 kernel/fork.c                    | 16 ++++++++--------
 28 files changed, 95 insertions(+), 116 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 732e39217c7f..6cbba7370b4e 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -237,7 +237,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	extern void ret_from_fork(void);
 	extern void ret_from_kernel_thread(void);
@@ -251,13 +250,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	childti->pcb.ksp = (unsigned long) childstack;
 	childti->pcb.flags = 1;	/* set FEN, clear everything else */
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
 		memset(childstack, 0,
 			sizeof(struct switch_stack) + sizeof(struct pt_regs));
 		childstack->r26 = (unsigned long) ret_from_kernel_thread;
-		childstack->r9 = usp;	/* function */
-		childstack->r10 = kthread_arg;
+		childstack->r9 = (unsigned long) args->fn;
+		childstack->r10 = (unsigned long) args->fn_arg;
 		childregs->hae = alpha_mv.hae_cache;
 		childti->pcb.usp = 0;
 		return 0;
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index caf948ba647c..3369f0700702 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -166,7 +166,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *c_regs;        /* child's pt_regs */
 	unsigned long *childksp;       /* to unwind out of __switch_to() */
@@ -193,11 +192,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	childksp[0] = 0;			/* fp */
 	childksp[1] = (unsigned long)ret_from_fork; /* blink */
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(c_regs, 0, sizeof(struct pt_regs));
 
-		c_callee->r13 = kthread_arg;
-		c_callee->r14 = usp;  /* function */
+		c_callee->r13 = (unsigned long)args->fn_arg;
+		c_callee->r14 = (unsigned long)args->fn;
 
 		return 0;
 	}
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 8e13b426dd26..3d9cace63884 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -242,7 +242,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long stack_start = args->stack;
-	unsigned long stk_sz = args->stack_size;
 	unsigned long tls = args->tls;
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
@@ -259,15 +258,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	thread->cpu_domain = get_domain();
 #endif
 
-	if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) {
+	if (likely(!args->fn)) {
 		*childregs = *current_pt_regs();
 		childregs->ARM_r0 = 0;
 		if (stack_start)
 			childregs->ARM_sp = stack_start;
 	} else {
 		memset(childregs, 0, sizeof(struct pt_regs));
-		thread->cpu_context.r4 = stk_sz;
-		thread->cpu_context.r5 = stack_start;
+		thread->cpu_context.r4 = (unsigned long)args->fn_arg;
+		thread->cpu_context.r5 = (unsigned long)args->fn;
 		childregs->ARM_cpsr = SVC_MODE;
 	}
 	thread->cpu_context.pc = (unsigned long)ret_from_fork;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index e002f6681c8d..d0ef05c661b0 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -320,7 +320,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long stack_start = args->stack;
-	unsigned long stk_sz = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
@@ -337,7 +336,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 	ptrauth_thread_init_kernel(p);
 
-	if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) {
+	if (likely(!args->fn)) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
 
@@ -371,8 +370,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->pstate = PSR_MODE_EL1h | PSR_IL_BIT;
 
-		p->thread.cpu_context.x19 = stack_start;
-		p->thread.cpu_context.x20 = stk_sz;
+		p->thread.cpu_context.x19 = (unsigned long)args->fn;
+		p->thread.cpu_context.x20 = (unsigned long)args->fn_arg;
 	}
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
 	p->thread.cpu_context.sp = (unsigned long)childregs;
diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
index 7dba33d37e1a..9af49aea1c3b 100644
--- a/arch/csky/kernel/process.c
+++ b/arch/csky/kernel/process.c
@@ -34,7 +34,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct switch_stack *childstack;
 	struct pt_regs *childregs = task_pt_regs(p);
@@ -49,11 +48,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	/* setup thread.sp for switch_to !!! */
 	p->thread.sp = (unsigned long)childstack;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childstack->r15 = (unsigned long) ret_from_kernel_thread;
-		childstack->r10 = kthread_arg;
-		childstack->r9 = usp;
+		childstack->r10 = (unsigned long) args->fn_arg;
+		childstack->r9 = (unsigned long) args->fn;
 		childregs->sr = mfcr("psr");
 	} else {
 		*childregs = *(current_pt_regs());
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 752cbd9b0bf6..9028262c96a9 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -108,16 +108,15 @@ void flush_thread(void)
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long usp = args->stack;
-	unsigned long topstk = args->stack_size;
 	struct pt_regs *childregs;
 
 	childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->retpc = (unsigned long) ret_from_kernel_thread;
-		childregs->er4 = topstk; /* arg */
-		childregs->er5 = usp; /* fn */
+		childregs->er4 = (unsigned long) args->fn_arg;
+		childregs->er5 = (unsigned long) args->fn;
 	}  else {
 		*childregs = *current_pt_regs();
 		childregs->er0 = 0;
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index f1c1f6f21941..f0552f98a7ba 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -54,7 +54,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct hexagon_switch_stack *ss;
@@ -76,11 +75,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 						    sizeof(*ss));
 	ss->lr = (unsigned long)ret_from_fork;
 	p->thread.switch_sp = ss;
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		/* r24 <- fn, r25 <- arg */
-		ss->r24 = usp;
-		ss->r25 = arg;
+		ss->r24 = (unsigned long)args->fn;
+		ss->r25 = (unsigned long)args->fn_arg;
 		pt_set_kmode(childregs);
 		return 0;
 	}
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 8f010ae818bc..167b1765bea1 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -341,14 +341,14 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 	ia64_drop_fpu(p);	/* don't pick up stale state from a CPU's fph */
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		if (unlikely(args->idle)) {
 			/* fork_idle() called us */
 			return 0;
 		}
 		memset(child_stack, 0, sizeof(*child_ptregs) + sizeof(*child_stack));
-		child_stack->r4 = user_stack_base;	/* payload */
-		child_stack->r5 = user_stack_size;	/* argument */
+		child_stack->r4 = (unsigned long) args->fn;
+		child_stack->r5 = (unsigned long) args->fn_arg;
 		/*
 		 * Preserve PSR bits, except for bits 32-34 and 37-45,
 		 * which we can't read.
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 8ac575656fc4..221feb0269f1 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -142,7 +142,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct fork_frame {
 		struct switch_stack sw;
@@ -160,12 +159,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	 */
 	p->thread.fc = USER_DATA;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
 		memset(frame, 0, sizeof(struct fork_frame));
 		frame->regs.sr = PS_S;
-		frame->sw.a3 = usp; /* function */
-		frame->sw.d7 = arg;
+		frame->sw.a3 = (unsigned long)args->fn;
+		frame->sw.d7 = (unsigned long)args->fn_arg;
 		frame->sw.retpc = (unsigned long)ret_from_kernel_thread;
 		p->thread.usp = 0;
 		return 0;
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index b5f549125c6a..3c6241bcaea8 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -56,19 +56,18 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct thread_info *ti = task_thread_info(p);
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* if we're creating a new kernel thread then just zeroing all
 		 * the registers. That's OK for a brand new thread.*/
 		memset(childregs, 0, sizeof(struct pt_regs));
 		memset(&ti->cpu_context, 0, sizeof(struct cpu_context));
 		ti->cpu_context.r1  = (unsigned long)childregs;
-		ti->cpu_context.r20 = (unsigned long)usp; /* fn */
-		ti->cpu_context.r19 = (unsigned long)arg;
+		ti->cpu_context.r20 = (unsigned long)args->fn;
+		ti->cpu_context.r19 = (unsigned long)args->fn_arg;
 		childregs->pt_mode = 1;
 		local_save_flags(childregs->msr);
 		ti->cpu_context.msr = childregs->msr & ~MSR_IE;
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index a572d097b16b..35b912bce429 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -109,7 +109,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
@@ -122,12 +121,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	/*  Put the stack after the struct pt_regs.  */
 	childksp = (unsigned long) childregs;
 	p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK;
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
 		unsigned long status = p->thread.cp0_status;
 		memset(childregs, 0, sizeof(struct pt_regs));
-		p->thread.reg16 = usp; /* fn */
-		p->thread.reg17 = kthread_arg;
+		p->thread.reg16 = (unsigned long)args->fn;
+		p->thread.reg17 = (unsigned long)args->fn_arg;
 		p->thread.reg29 = childksp;
 		p->thread.reg31 = (unsigned long) ret_from_kernel_thread;
 #if defined(CONFIG_CPU_R3000)
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 98c4bfe972e0..29593b98567d 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -104,7 +104,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct pt_regs *regs;
@@ -112,12 +111,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	struct switch_stack *childstack =
 		((struct switch_stack *)childregs) - 1;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(childstack, 0,
 			sizeof(struct switch_stack) + sizeof(struct pt_regs));
 
-		childstack->r16 = usp;		/* fn */
-		childstack->r17 = arg;
+		childstack->r16 = (unsigned long) args->fn;
+		childstack->r17 = (unsigned long) args->fn_arg;
 		childstack->ra = (unsigned long) ret_from_kernel_thread;
 		childregs->estatus = STATUS_PIE;
 		childregs->sp = (unsigned long) childstack;
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 486e46dd5883..d9697cc9bc4d 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -156,7 +156,6 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *userregs;
 	struct pt_regs *kregs;
@@ -175,10 +174,10 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	sp -= sizeof(struct pt_regs);
 	kregs = (struct pt_regs *)sp;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(kregs, 0, sizeof(struct pt_regs));
-		kregs->gpr[20] = usp; /* fn, kernel thread */
-		kregs->gpr[22] = arg;
+		kregs->gpr[20] = (unsigned long)args->fn;
+		kregs->gpr[22] = (unsigned long)args->fn_arg;
 	} else {
 		*userregs = *current_pt_regs();
 
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 30a5874ca845..a6a2a558fc5b 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -210,7 +210,6 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *cregs = &(p->thread.regs);
 	void *stack = task_stack_page(p);
@@ -221,7 +220,7 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	extern void * const ret_from_kernel_thread;
 	extern void * const child_return;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
 		memset(cregs, 0, sizeof(struct pt_regs));
 		if (args->idle) /* idle thread */
@@ -236,12 +235,12 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		 * ret_from_kernel_thread.
 		 */
 #ifdef CONFIG_64BIT
-		cregs->gr[27] = ((unsigned long *)usp)[3];
-		cregs->gr[26] = ((unsigned long *)usp)[2];
+		cregs->gr[27] = ((unsigned long *)args->fn)[3];
+		cregs->gr[26] = ((unsigned long *)args->fn)[2];
 #else
-		cregs->gr[26] = usp;
+		cregs->gr[26] = (unsigned long) args->fn;
 #endif
-		cregs->gr[25] = kthread_arg;
+		cregs->gr[25] = (unsigned long) args->fn_arg;
 	} else {
 		/* user thread */
 		/* usp must be word aligned.  This also prevents users from
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3fd67c861d54..4f367bb68906 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1720,7 +1720,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs, *kregs;
 	extern void ret_from_fork(void);
@@ -1738,18 +1737,18 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	/* Copy registers */
 	sp -= sizeof(struct pt_regs);
 	childregs = (struct pt_regs *) sp;
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gpr[1] = sp + sizeof(struct pt_regs);
 		/* function */
-		if (usp)
-			childregs->gpr[14] = ppc_function_entry((void *)usp);
+		if (args->fn)
+			childregs->gpr[14] = ppc_function_entry((void *)args->fn);
 #ifdef CONFIG_PPC64
 		clear_tsk_thread_flag(p, TIF_32BIT);
 		childregs->softe = IRQS_ENABLED;
 #endif
-		childregs->gpr[15] = kthread_arg;
+		childregs->gpr[15] = (unsigned long)args->fn_arg;
 		p->thread.regs = NULL;	/* no user register state */
 		ti->flags |= _TIF_RESTOREALL;
 		f = ret_from_kernel_thread;
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 334382731725..24efabdbc551 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -124,12 +124,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
 	/* p->thread holds context to be restored by __switch_to() */
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* Kernel thread */
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gp = gp_in_global;
@@ -137,8 +136,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->status = SR_PP | SR_PIE;
 
 		p->thread.ra = (unsigned long)ret_from_kernel_thread;
-		p->thread.s[0] = usp; /* fn */
-		p->thread.s[1] = arg;
+		p->thread.s[0] = (unsigned long)args->fn;
+		p->thread.s[1] = (unsigned long)args->fn_arg;
 	} else {
 		*childregs = *(current_pt_regs());
 		if (usp) /* User fork */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index bb5daec39516..89949b9f3cf8 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -98,7 +98,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long new_stackp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct fake_frame
 	{
@@ -133,15 +132,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	frame->sf.gprs[9] = (unsigned long)frame;
 
 	/* Store access registers to kernel stack of new process. */
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
 		memset(&frame->childregs, 0, sizeof(struct pt_regs));
 		frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT |
 				PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
 		frame->childregs.psw.addr =
 				(unsigned long)__ret_from_fork;
-		frame->childregs.gprs[9] = new_stackp; /* function */
-		frame->childregs.gprs[10] = arg;
+		frame->childregs.gprs[9] = (unsigned long)args->fn;
+		frame->childregs.gprs[10] = (unsigned long)args->fn_arg;
 		frame->childregs.orig_gpr2 = -1;
 		frame->childregs.last_break = 1;
 		return 0;
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 6023399b1892..a808843375e7 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -96,7 +96,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs;
@@ -117,11 +116,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 	childregs = task_pt_regs(p);
 	p->thread.sp = (unsigned long) childregs;
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		p->thread.pc = (unsigned long) ret_from_kernel_thread;
-		childregs->regs[4] = arg;
-		childregs->regs[5] = usp;
+		childregs->regs[4] = (unsigned long) args->fn_arg;
+		childregs->regs[5] = (unsigned long) args->fn;
 		childregs->sr = SR_MD;
 #if defined(CONFIG_SH_FPU)
 		childregs->sr |= SR_FD;
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 80e6775e18c0..33b0215a4182 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -263,7 +263,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long sp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
@@ -299,13 +298,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	ti->ksp = (unsigned long) new_stack;
 	p->thread.kregs = childregs;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		extern int nwindows;
 		unsigned long psr;
 		memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ);
 		ti->kpc = (((unsigned long) ret_from_kernel_thread) - 0x8);
-		childregs->u_regs[UREG_G1] = sp; /* function */
-		childregs->u_regs[UREG_G2] = arg;
+		childregs->u_regs[UREG_G1] = (unsigned long) args->fn;
+		childregs->u_regs[UREG_G2] = (unsigned long) args->fn_arg;
 		psr = childregs->psr = get_psr();
 		ti->kpsr = psr | PSR_PIL;
 		ti->kwim = 1 << (((psr & PSR_CWP) + 1) % nwindows);
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 38c46ca826d9..6335b698a4b4 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -568,7 +568,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long sp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct thread_info *t = task_thread_info(p);
 	struct pt_regs *regs = current_pt_regs();
@@ -587,12 +586,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 				       sizeof(struct sparc_stackf));
 	t->fpsaved[0] = 0;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(child_trap_frame, 0, child_stack_sz);
 		__thread_flag_byte_ptr(t)[TI_FLAG_BYTE_CWP] = 
 			(current_pt_regs()->tstate + 1) & TSTATE_CWP;
-		t->kregs->u_regs[UREG_G1] = sp; /* function */
-		t->kregs->u_regs[UREG_G2] = arg;
+		t->kregs->u_regs[UREG_G1] = (unsigned long) args->fn;
+		t->kregs->u_regs[UREG_G2] = (unsigned long) args->fn_arg;
 		return 0;
 	}
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index fd2d2361484d..181cc9aafb25 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -158,15 +158,13 @@ int copy_thread(struct task_struct * p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long sp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	void (*handler)(void);
-	int kthread = current->flags & (PF_KTHREAD | PF_IO_WORKER);
 	int ret = 0;
 
 	p->thread = (struct thread_struct) INIT_THREAD;
 
-	if (!kthread) {
+	if (!args->fn) {
 	  	memcpy(&p->thread.regs.regs, current_pt_regs(),
 		       sizeof(p->thread.regs.regs));
 		PT_REGS_SET_SYSCALL_RETURN(&p->thread.regs, 0);
@@ -178,14 +176,14 @@ int copy_thread(struct task_struct * p, const struct kernel_clone_args *args)
 		arch_copy_thread(&current->thread.arch, &p->thread.arch);
 	} else {
 		get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp);
-		p->thread.request.u.thread.proc = (int (*)(void *))sp;
-		p->thread.request.u.thread.arg = (void *)arg;
+		p->thread.request.u.thread.proc = args->fn;
+		p->thread.request.u.thread.arg = args->fn_arg;
 		handler = new_thread_handler;
 	}
 
 	new_thread(task_stack_page(p), &p->thread.switch_buf, handler);
 
-	if (!kthread) {
+	if (!args->fn) {
 		clear_flushed_tls(p);
 
 		/*
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index 99a8820e8cc4..b2486b2cbc6e 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -11,7 +11,7 @@
 
 extern void save_fpregs_to_fpstate(struct fpu *fpu);
 extern void fpu__drop(struct fpu *fpu);
-extern int  fpu_clone(struct task_struct *dst, unsigned long clone_flags);
+extern int  fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal);
 extern void fpu_flush_thread(void);
 
 /*
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index b5f0d2ff47e4..c08eb0fdd11f 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -78,13 +78,13 @@ static inline void update_task_stack(struct task_struct *task)
 }
 
 static inline void kthread_frame_init(struct inactive_task_frame *frame,
-				      unsigned long fun, unsigned long arg)
+				      int (*fun)(void *), void *arg)
 {
-	frame->bx = fun;
+	frame->bx = (unsigned long)fun;
 #ifdef CONFIG_X86_32
-	frame->di = arg;
+	frame->di = (unsigned long)arg;
 #else
-	frame->r12 = arg;
+	frame->r12 = (unsigned long)arg;
 #endif
 }
 
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index c049561f373a..fbade5a3975b 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -556,7 +556,7 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu)
 }
 
 /* Clone current's FPU state on fork */
-int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
+int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal)
 {
 	struct fpu *src_fpu = &current->thread.fpu;
 	struct fpu *dst_fpu = &dst->thread.fpu;
@@ -579,7 +579,7 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
 	 * No FPU state inheritance for kernel threads and IO
 	 * worker threads.
 	 */
-	if (dst->flags & (PF_KTHREAD | PF_IO_WORKER)) {
+	if (minimal) {
 		/* Clear out the minimal state */
 		memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs,
 		       init_fpstate_copy_size());
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 0fce52b10dc4..d20eaad52a85 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -134,7 +134,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long sp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct inactive_task_frame *frame;
 	struct fork_frame *fork_frame;
@@ -172,13 +171,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	frame->flags = X86_EFLAGS_FIXED;
 #endif
 
-	fpu_clone(p, clone_flags);
+	fpu_clone(p, clone_flags, args->fn);
 
 	/* Kernel thread ? */
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		p->thread.pkru = pkru_get_init_value();
 		memset(childregs, 0, sizeof(struct pt_regs));
-		kthread_frame_init(frame, sp, arg);
+		kthread_frame_init(frame, args->fn, args->fn_arg);
 		return 0;
 	}
 
@@ -198,10 +197,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	task_user_gs(p) = get_user_gs(current_pt_regs());
 #endif
 
-	if (unlikely(p->flags & PF_IO_WORKER)) {
+	if (unlikely(args->fn)) {
 		/*
-		 * An IO thread is a user space thread, but it doesn't
-		 * return to ret_after_fork().
+		 * A user space thread, but it doesn't return to
+		 * ret_after_fork().
 		 *
 		 * In order to indicate that to tools like gdb,
 		 * we reset the stack and instruction pointers.
@@ -211,7 +210,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		 */
 		childregs->sp = 0;
 		childregs->ip = 0;
-		kthread_frame_init(frame, sp, arg);
+		kthread_frame_init(frame, args->fn, args->fn_arg);
 		return 0;
 	}
 
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 15ce25073142..c3751cc88e5d 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -205,7 +205,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp_thread_fn = args->stack;
-	unsigned long thread_fn_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
@@ -226,7 +225,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 #error Unsupported Xtensa ABI
 #endif
 
-	if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (!args->fn) {
 		struct pt_regs *regs = current_pt_regs();
 		unsigned long usp = usp_thread_fn ?
 			usp_thread_fn : regs->areg[1];
@@ -278,15 +277,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		 * Window underflow will load registers from the
 		 * spill slots on the stack on return from _switch_to.
 		 */
-		SPILL_SLOT(childregs, 2) = usp_thread_fn;
-		SPILL_SLOT(childregs, 3) = thread_fn_arg;
+		SPILL_SLOT(childregs, 2) = (unsigned long)args->fn;
+		SPILL_SLOT(childregs, 3) = (unsigned long)args->fn_arg;
 #elif defined(__XTENSA_CALL0_ABI__)
 		/*
 		 * a12 = thread_fn, a13 = thread_fn arg.
 		 * _switch_to epilogue will load registers from the stack.
 		 */
-		((unsigned long *)p->thread.sp)[0] = usp_thread_fn;
-		((unsigned long *)p->thread.sp)[1] = thread_fn_arg;
+		((unsigned long *)p->thread.sp)[0] = (unsigned long)args->fn;
+		((unsigned long *)p->thread.sp)[1] = (unsigned long)args->fn_arg;
 #else
 #error Unsupported Xtensa ABI
 #endif
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 3d6b99ce5408..505aaf9fe477 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -34,6 +34,8 @@ struct kernel_clone_args {
 	int io_thread;
 	int kthread;
 	int idle;
+	int (*fn)(void *);
+	void *fn_arg;
 	struct cgroup *cgrp;
 	struct css_set *cset;
 };
diff --git a/kernel/fork.c b/kernel/fork.c
index 93d77ee921ff..8e17c3fbce42 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2555,8 +2555,8 @@ struct task_struct * __init fork_idle(int cpu)
 	struct task_struct *task;
 	struct kernel_clone_args args = {
 		.flags		= CLONE_VM,
-		.stack		= (unsigned long)&idle_dummy,
-		.stack_size	= (unsigned long)NULL,
+		.fn		= &idle_dummy,
+		.fn_arg		= NULL,
 		.kthread	= 1,
 		.idle		= 1,
 	};
@@ -2589,8 +2589,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 		.flags		= ((lower_32_bits(flags) | CLONE_VM |
 				    CLONE_UNTRACED) & ~CSIGNAL),
 		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
-		.stack		= (unsigned long)fn,
-		.stack_size	= (unsigned long)arg,
+		.fn		= fn,
+		.fn_arg		= arg,
 		.io_thread	= 1,
 	};
 
@@ -2694,8 +2694,8 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.flags		= ((lower_32_bits(flags) | CLONE_VM |
 				    CLONE_UNTRACED) & ~CSIGNAL),
 		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
-		.stack		= (unsigned long)fn,
-		.stack_size	= (unsigned long)arg,
+		.fn		= fn,
+		.fn_arg		= arg,
 		.kthread	= 1,
 	};
 
@@ -2711,8 +2711,8 @@ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.flags		= ((lower_32_bits(flags) | CLONE_VM |
 				    CLONE_UNTRACED) & ~CSIGNAL),
 		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
-		.stack		= (unsigned long)fn,
-		.stack_size	= (unsigned long)arg,
+		.fn		= fn,
+		.fn_arg		= arg,
 	};
 
 	return kernel_clone(&args);
-- 
cgit v1.2.3


From 3d1b0d351441c2be7de082b92f43d0bfdc95a8f3 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 7 May 2022 13:48:21 -0400
Subject: Revert "SUNRPC: Ensure gss-proxy connects on setup"

This reverts commit 892de36fd4a98fab3298d417c051d9099af5448d.

The gssproxy server is unresponsive when it calls into the kernel to
start the upcall service, so it will not reply to our RPC ping at all.

Reported-by: "J.Bruce Fields" <bfields@fieldses.org>
Fixes: 892de36fd4a9 ("SUNRPC: Ensure gss-proxy connects on setup")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/clnt.h          | 1 -
 net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +-
 net/sunrpc/clnt.c                    | 3 ---
 3 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index db5149567305..267b7aeaf1a6 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -160,7 +160,6 @@ struct rpc_add_xprt_test {
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 #define RPC_CLNT_CREATE_SOFTERR		(1UL << 10)
 #define RPC_CLNT_CREATE_REUSEPORT	(1UL << 11)
-#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index 8ca1d809b78d..61c276bddaf2 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -97,7 +97,7 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt)
 		 * timeout, which would result in reconnections being
 		 * done without the correct namespace:
 		 */
-		.flags		= RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL |
+		.flags		= RPC_CLNT_CREATE_NOPING |
 				  RPC_CLNT_CREATE_NO_IDLE_TIMEOUT
 	};
 	struct rpc_clnt *clnt;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 22c28cf43eba..98133aa54f19 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -479,9 +479,6 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 
 	if (!(args->flags & RPC_CLNT_CREATE_NOPING)) {
 		int err = rpc_ping(clnt);
-		if ((args->flags & RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL) &&
-		    err == -EOPNOTSUPP)
-			err = 0;
 		if (err != 0) {
 			rpc_shutdown_client(clnt);
 			return ERR_PTR(err);
-- 
cgit v1.2.3


From fd13359f54ee854f00134abc6be32da94ec53dbf Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 7 May 2022 13:53:59 -0400
Subject: SUNRPC: Ensure that the gssproxy client can start in a connected
 state

Ensure that the gssproxy client connects to the server from the gssproxy
daemon process context so that the AF_LOCAL socket connection is done
using the correct path and namespaces.

Fixes: 1d658336b05f ("SUNRPC: Add RPC based upcall mechanism for RPCGSS auth")
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/clnt.h          |  1 +
 net/sunrpc/auth_gss/gss_rpc_upcall.c |  1 +
 net/sunrpc/clnt.c                    | 33 +++++++++++++++++++++++++++++++++
 3 files changed, 35 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 267b7aeaf1a6..90501404fa49 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -160,6 +160,7 @@ struct rpc_add_xprt_test {
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 #define RPC_CLNT_CREATE_SOFTERR		(1UL << 10)
 #define RPC_CLNT_CREATE_REUSEPORT	(1UL << 11)
+#define RPC_CLNT_CREATE_CONNECTED	(1UL << 12)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index 61c276bddaf2..f549e4c05def 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -98,6 +98,7 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt)
 		 * done without the correct namespace:
 		 */
 		.flags		= RPC_CLNT_CREATE_NOPING |
+				  RPC_CLNT_CREATE_CONNECTED |
 				  RPC_CLNT_CREATE_NO_IDLE_TIMEOUT
 	};
 	struct rpc_clnt *clnt;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 98133aa54f19..e2c6eca0271b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -76,6 +76,7 @@ static int	rpc_encode_header(struct rpc_task *task,
 static int	rpc_decode_header(struct rpc_task *task,
 				  struct xdr_stream *xdr);
 static int	rpc_ping(struct rpc_clnt *clnt);
+static int	rpc_ping_noreply(struct rpc_clnt *clnt);
 static void	rpc_check_timeout(struct rpc_task *task);
 
 static void rpc_register_client(struct rpc_clnt *clnt)
@@ -483,6 +484,12 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 			rpc_shutdown_client(clnt);
 			return ERR_PTR(err);
 		}
+	} else if (args->flags & RPC_CLNT_CREATE_CONNECTED) {
+		int err = rpc_ping_noreply(clnt);
+		if (err != 0) {
+			rpc_shutdown_client(clnt);
+			return ERR_PTR(err);
+		}
 	}
 
 	clnt->cl_softrtry = 1;
@@ -2709,6 +2716,10 @@ static const struct rpc_procinfo rpcproc_null = {
 	.p_decode = rpcproc_decode_null,
 };
 
+static const struct rpc_procinfo rpcproc_null_noreply = {
+	.p_encode = rpcproc_encode_null,
+};
+
 static void
 rpc_null_call_prepare(struct rpc_task *task, void *data)
 {
@@ -2762,6 +2773,28 @@ static int rpc_ping(struct rpc_clnt *clnt)
 	return status;
 }
 
+static int rpc_ping_noreply(struct rpc_clnt *clnt)
+{
+	struct rpc_message msg = {
+		.rpc_proc = &rpcproc_null_noreply,
+	};
+	struct rpc_task_setup task_setup_data = {
+		.rpc_client = clnt,
+		.rpc_message = &msg,
+		.callback_ops = &rpc_null_ops,
+		.flags = RPC_TASK_SOFT | RPC_TASK_SOFTCONN | RPC_TASK_NULLCREDS,
+	};
+	struct rpc_task	*task;
+	int status;
+
+	task = rpc_run_task(&task_setup_data);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	status = task->tk_status;
+	rpc_put_task(task);
+	return status;
+}
+
 struct rpc_cb_add_xprt_calldata {
 	struct rpc_xprt_switch *xps;
 	struct rpc_xprt *xprt;
-- 
cgit v1.2.3


From 813c2aee51dd7d7d9092251851e33f66719513cc Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 7 May 2022 14:33:31 +0200
Subject: ARM/pxa/mfd/power/sound: Switch Tosa to GPIO descriptors

The Tosa device (Sharp SL-6000) has a mishmash driver set-up
for the Toshiba TC6393xb MFD that includes a battery charger
and touchscreen and has some kind of relationship to the SoC
sound driver for the AC97 codec. Other devices define a chip
like this but seem only half-implemented, not really handling
battery charging etc.

This patch switches the Toshiba MFD device to provide GPIO
descriptors to the battery charger and SoC codec. As a result
some descriptors need to be moved out of the Tosa boardfile
and new one added: all SoC GPIO resources to these drivers
now comes from the main boardfile, while the MFD provide
GPIOs for its portions.

As a result we can request one GPIO from our own GPIO chip
and drop two hairy callbacks into the board file.

This platform badly needs to have its drivers split up and
converted to device tree probing to handle this quite complex
relationship in an orderly manner. I just do my best in solving
the GPIO descriptor part of the puzzle. Please don't ask me
to fix everything that is wrong with these driver to todays
standards, I am just trying to fix one aspect. I do try to
use modern devres resource management and handle deferred
probe using new functions where appropriate.

Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
Cc: Dirk Opfer <dirk@opfer-online.de>
Cc: Robert Jarzmik <robert.jarzmik@free.fr>
Cc: Daniel Mack <daniel@zonque.org>
Cc: Haojian Zhuang <haojian.zhuang@gmail.com>
Cc: Lee Jones <lee.jones@linaro.org>
Cc: Liam Girdwood <lgirdwood@gmail.com>
Reviewed-by: Dmitry Baryshkov <dbaryshkov@gmail.com>
Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/eseries.c           |   2 -
 arch/arm/mach-pxa/include/mach/tosa.h |  18 ----
 arch/arm/mach-pxa/tosa.c              |  68 ++++----------
 drivers/mfd/tc6393xb.c                | 130 ++++++++++++++++++-------
 drivers/power/supply/tosa_battery.c   | 172 +++++++++++++++++++++-------------
 include/linux/gpio/machine.h          |  12 +++
 include/linux/mfd/tc6393xb.h          |   3 -
 sound/soc/pxa/tosa.c                  |  23 ++---
 8 files changed, 241 insertions(+), 187 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index a8b6483ff665..1e9d6bbf4555 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -699,7 +699,6 @@ static struct tc6393xb_platform_data e750_tc6393xb_info = {
 	.irq_base       = IRQ_BOARD_START,
 	.scr_pll2cr     = 0x0cc1,
 	.scr_gper       = 0,
-	.gpio_base      = -1,
 	.suspend        = &eseries_tmio_suspend,
 	.resume         = &eseries_tmio_resume,
 	.enable         = &eseries_tmio_enable,
@@ -918,7 +917,6 @@ static struct tc6393xb_platform_data e800_tc6393xb_info = {
 	.irq_base       = IRQ_BOARD_START,
 	.scr_pll2cr     = 0x0cc1,
 	.scr_gper       = 0,
-	.gpio_base      = -1,
 	.suspend        = &eseries_tmio_suspend,
 	.resume         = &eseries_tmio_resume,
 	.enable         = &eseries_tmio_enable,
diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h
index 8bfaca3a8b64..3b3efa0a0e22 100644
--- a/arch/arm/mach-pxa/include/mach/tosa.h
+++ b/arch/arm/mach-pxa/include/mach/tosa.h
@@ -54,24 +54,6 @@
 /* GPIO Direction   1 : output mode / 0:input mode */
 #define TOSA_SCOOP_JC_IO_DIR (TOSA_SCOOP_JC_CARD_LIMIT_SEL)
 
-/*
- * TC6393XB GPIOs
- */
-#define TOSA_TC6393XB_GPIO_BASE		(PXA_NR_BUILTIN_GPIO + 2 * 12)
-
-#define TOSA_GPIO_TG_ON			(TOSA_TC6393XB_GPIO_BASE + 0)
-#define TOSA_GPIO_L_MUTE		(TOSA_TC6393XB_GPIO_BASE + 1)
-#define TOSA_GPIO_BL_C20MA		(TOSA_TC6393XB_GPIO_BASE + 3)
-#define TOSA_GPIO_CARD_VCC_ON		(TOSA_TC6393XB_GPIO_BASE + 4)
-#define TOSA_GPIO_CHARGE_OFF		(TOSA_TC6393XB_GPIO_BASE + 6)
-#define TOSA_GPIO_CHARGE_OFF_JC		(TOSA_TC6393XB_GPIO_BASE + 7)
-#define TOSA_GPIO_BAT0_V_ON		(TOSA_TC6393XB_GPIO_BASE + 9)
-#define TOSA_GPIO_BAT1_V_ON		(TOSA_TC6393XB_GPIO_BASE + 10)
-#define TOSA_GPIO_BU_CHRG_ON		(TOSA_TC6393XB_GPIO_BASE + 11)
-#define TOSA_GPIO_BAT_SW_ON		(TOSA_TC6393XB_GPIO_BASE + 12)
-#define TOSA_GPIO_BAT0_TH_ON		(TOSA_TC6393XB_GPIO_BASE + 14)
-#define TOSA_GPIO_BAT1_TH_ON		(TOSA_TC6393XB_GPIO_BASE + 15)
-
 /*
  * PXA GPIOs
  */
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 9476ed0f55e9..ee0e38a8f96e 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -616,6 +616,22 @@ static struct resource tc6393xb_resources[] = {
 	},
 };
 
+static struct gpiod_lookup_table tosa_battery_gpio_table = {
+	.dev_id = "wm97xx-battery",
+	.table = {
+		GPIO_LOOKUP("gpio-pxa", TOSA_GPIO_BAT0_CRG,
+			    "main battery full", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("gpio-pxa", TOSA_GPIO_BAT1_CRG,
+			    "jacket battery full", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("gpio-pxa", TOSA_GPIO_BAT0_LOW,
+			    "main battery low", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("gpio-pxa", TOSA_GPIO_BAT1_LOW,
+			    "jacket battery low", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("gpio-pxa", TOSA_GPIO_JACKET_DETECT,
+			    "jacket detect", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
 
 static int tosa_tc6393xb_enable(struct platform_device *dev)
 {
@@ -709,31 +725,6 @@ static struct tmio_nand_data tosa_tc6393xb_nand_config = {
 	.part_parsers = probes,
 };
 
-static int tosa_tc6393xb_setup(struct platform_device *dev)
-{
-	int rc;
-
-	rc = gpio_request(TOSA_GPIO_CARD_VCC_ON, "CARD_VCC_ON");
-	if (rc)
-		goto err_req;
-
-	rc = gpio_direction_output(TOSA_GPIO_CARD_VCC_ON, 1);
-	if (rc)
-		goto err_dir;
-
-	return rc;
-
-err_dir:
-	gpio_free(TOSA_GPIO_CARD_VCC_ON);
-err_req:
-	return rc;
-}
-
-static void tosa_tc6393xb_teardown(struct platform_device *dev)
-{
-	gpio_free(TOSA_GPIO_CARD_VCC_ON);
-}
-
 #ifdef CONFIG_MFD_TC6393XB
 static struct fb_videomode tosa_tc6393xb_lcd_mode[] = {
 	{
@@ -778,9 +769,6 @@ static struct tc6393xb_platform_data tosa_tc6393xb_data = {
 	.scr_gper	= 0x3300,
 
 	.irq_base	= IRQ_BOARD_START,
-	.gpio_base	= TOSA_TC6393XB_GPIO_BASE,
-	.setup		= tosa_tc6393xb_setup,
-	.teardown	= tosa_tc6393xb_teardown,
 
 	.enable		= tosa_tc6393xb_enable,
 	.disable	= tosa_tc6393xb_disable,
@@ -821,26 +809,6 @@ static struct pxa2xx_spi_controller pxa_ssp_master_info = {
 	.num_chipselect	= 1,
 };
 
-static struct gpiod_lookup_table tosa_lcd_gpio_table = {
-	.dev_id = "spi2.0",
-	.table = {
-		GPIO_LOOKUP("tc6393xb",
-			    TOSA_GPIO_TG_ON - TOSA_TC6393XB_GPIO_BASE,
-			    "tg #pwr", GPIO_ACTIVE_HIGH),
-		{ },
-	},
-};
-
-static struct gpiod_lookup_table tosa_lcd_bl_gpio_table = {
-	.dev_id = "i2c-tosa-bl",
-	.table = {
-		GPIO_LOOKUP("tc6393xb",
-			    TOSA_GPIO_BL_C20MA - TOSA_TC6393XB_GPIO_BASE,
-			    "backlight", GPIO_ACTIVE_HIGH),
-		{ },
-	},
-};
-
 static struct spi_board_info spi_board_info[] __initdata = {
 	{
 		.modalias	= "tosa-lcd",
@@ -943,6 +911,8 @@ static void __init tosa_init(void)
 	/* enable batt_fault */
 	PMCR = 0x01;
 
+	gpiod_add_lookup_table(&tosa_battery_gpio_table);
+
 	gpiod_add_lookup_table(&tosa_mci_gpio_table);
 	pxa_set_mci_info(&tosa_mci_platform_data);
 	pxa_set_ficp_info(&tosa_ficp_platform_data);
@@ -951,8 +921,6 @@ static void __init tosa_init(void)
 	platform_scoop_config = &tosa_pcmcia_config;
 
 	pxa2xx_set_spi_info(2, &pxa_ssp_master_info);
-	gpiod_add_lookup_table(&tosa_lcd_gpio_table);
-	gpiod_add_lookup_table(&tosa_lcd_bl_gpio_table);
 	spi_register_board_info(spi_board_info, ARRAY_SIZE(spi_board_info));
 
 	clk_add_alias("CLK_CK3P6MI", tc6393xb_device.name, "GPIO11_CLK", NULL);
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 3d5b14c60e20..0be5731685b4 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -22,6 +22,8 @@
 #include <linux/mfd/tmio.h>
 #include <linux/mfd/tc6393xb.h>
 #include <linux/gpio/driver.h>
+#include <linux/gpio/machine.h>
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 
 #define SCR_REVID	0x08		/* b Revision ID	*/
@@ -87,8 +89,10 @@
 
 struct tc6393xb {
 	void __iomem		*scr;
+	struct device		*dev;
 
 	struct gpio_chip	gpio;
+	struct gpio_desc	*vcc_on;
 
 	struct clk		*clk; /* 3,6 Mhz */
 
@@ -497,17 +501,93 @@ static int tc6393xb_gpio_direction_output(struct gpio_chip *chip,
 	return 0;
 }
 
-static int tc6393xb_register_gpio(struct tc6393xb *tc6393xb, int gpio_base)
+/*
+ * TC6393XB GPIOs as used on TOSA, are the only user of this chip.
+ * GPIOs 2, 5, 8 and 13 are not connected.
+ */
+#define TOSA_GPIO_TG_ON			0
+#define TOSA_GPIO_L_MUTE		1
+#define TOSA_GPIO_BL_C20MA		3
+#define TOSA_GPIO_CARD_VCC_ON		4
+#define TOSA_GPIO_CHARGE_OFF		6
+#define TOSA_GPIO_CHARGE_OFF_JC		7
+#define TOSA_GPIO_BAT0_V_ON		9
+#define TOSA_GPIO_BAT1_V_ON		10
+#define TOSA_GPIO_BU_CHRG_ON		11
+#define TOSA_GPIO_BAT_SW_ON		12
+#define TOSA_GPIO_BAT0_TH_ON		14
+#define TOSA_GPIO_BAT1_TH_ON		15
+
+
+GPIO_LOOKUP_SINGLE(tosa_lcd_gpio_lookup, "spi2.0", "tc6393xb",
+		   TOSA_GPIO_TG_ON, "tg #pwr", GPIO_ACTIVE_HIGH);
+
+GPIO_LOOKUP_SINGLE(tosa_lcd_bl_gpio_lookup, "i2c-tos-bl", "tc6393xb",
+		   TOSA_GPIO_BL_C20MA, "backlight", GPIO_ACTIVE_HIGH);
+
+GPIO_LOOKUP_SINGLE(tosa_audio_gpio_lookup, "tosa-audio", "tc6393xb",
+		   TOSA_GPIO_L_MUTE, NULL, GPIO_ACTIVE_HIGH);
+
+static struct gpiod_lookup_table tosa_battery_gpio_lookup = {
+	.dev_id = "wm97xx-battery",
+	.table = {
+		GPIO_LOOKUP("tc6393xb", TOSA_GPIO_CHARGE_OFF,
+			    "main charge off", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("tc6393xb", TOSA_GPIO_CHARGE_OFF_JC,
+			    "jacket charge off", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT0_V_ON,
+			    "main battery", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT1_V_ON,
+			    "jacket battery", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BU_CHRG_ON,
+			    "backup battery", GPIO_ACTIVE_HIGH),
+		/* BAT1 and BAT0 thermistors appear to be swapped */
+		GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT1_TH_ON,
+			    "main battery temp", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT0_TH_ON,
+			    "jacket battery temp", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("tc6393xb", TOSA_GPIO_BAT_SW_ON,
+			    "battery switch", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table *tc6393xb_gpio_lookups[] = {
+	&tosa_lcd_gpio_lookup,
+	&tosa_lcd_bl_gpio_lookup,
+	&tosa_audio_gpio_lookup,
+	&tosa_battery_gpio_lookup,
+};
+
+static int tc6393xb_register_gpio(struct tc6393xb *tc6393xb)
 {
-	tc6393xb->gpio.label = "tc6393xb";
-	tc6393xb->gpio.base = gpio_base;
-	tc6393xb->gpio.ngpio = 16;
-	tc6393xb->gpio.set = tc6393xb_gpio_set;
-	tc6393xb->gpio.get = tc6393xb_gpio_get;
-	tc6393xb->gpio.direction_input = tc6393xb_gpio_direction_input;
-	tc6393xb->gpio.direction_output = tc6393xb_gpio_direction_output;
-
-	return gpiochip_add_data(&tc6393xb->gpio, tc6393xb);
+	struct gpio_chip *gc = &tc6393xb->gpio;
+	struct device *dev = tc6393xb->dev;
+	int ret;
+
+	gc->label = "tc6393xb";
+	gc->base = -1; /* Dynamic allocation */
+	gc->ngpio = 16;
+	gc->set = tc6393xb_gpio_set;
+	gc->get = tc6393xb_gpio_get;
+	gc->direction_input = tc6393xb_gpio_direction_input;
+	gc->direction_output = tc6393xb_gpio_direction_output;
+
+	ret = devm_gpiochip_add_data(dev, gc, tc6393xb);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to add GPIO chip\n");
+
+	/* Register descriptor look-ups for consumers */
+	gpiod_add_lookup_tables(tc6393xb_gpio_lookups, ARRAY_SIZE(tc6393xb_gpio_lookups));
+
+	/* Request some of our own GPIOs */
+	tc6393xb->vcc_on = gpiochip_request_own_desc(gc, TOSA_GPIO_CARD_VCC_ON, "VCC ON",
+						     GPIO_ACTIVE_HIGH, GPIOD_OUT_HIGH);
+	if (IS_ERR(tc6393xb->vcc_on))
+		return dev_err_probe(dev, PTR_ERR(tc6393xb->vcc_on),
+				     "failed to request VCC ON GPIO\n");
+
+	return 0;
 }
 
 /*--------------------------------------------------------------------------*/
@@ -617,6 +697,7 @@ static int tc6393xb_probe(struct platform_device *dev)
 		ret = -ENOMEM;
 		goto err_kzalloc;
 	}
+	tc6393xb->dev = &dev->dev;
 
 	raw_spin_lock_init(&tc6393xb->lock);
 
@@ -676,22 +757,12 @@ static int tc6393xb_probe(struct platform_device *dev)
 			tmio_ioread8(tc6393xb->scr + SCR_REVID),
 			(unsigned long) iomem->start, tc6393xb->irq);
 
-	tc6393xb->gpio.base = -1;
-
-	if (tcpd->gpio_base >= 0) {
-		ret = tc6393xb_register_gpio(tc6393xb, tcpd->gpio_base);
-		if (ret)
-			goto err_gpio_add;
-	}
+	ret = tc6393xb_register_gpio(tc6393xb);
+	if (ret)
+		goto err_gpio_add;
 
 	tc6393xb_attach_irq(dev);
 
-	if (tcpd->setup) {
-		ret = tcpd->setup(dev);
-		if (ret)
-			goto err_setup;
-	}
-
 	tc6393xb_cells[TC6393XB_CELL_NAND].platform_data = tcpd->nand_data;
 	tc6393xb_cells[TC6393XB_CELL_NAND].pdata_size =
 						sizeof(*tcpd->nand_data);
@@ -705,15 +776,8 @@ static int tc6393xb_probe(struct platform_device *dev)
 	if (!ret)
 		return 0;
 
-	if (tcpd->teardown)
-		tcpd->teardown(dev);
-
-err_setup:
 	tc6393xb_detach_irq(dev);
-
 err_gpio_add:
-	if (tc6393xb->gpio.base != -1)
-		gpiochip_remove(&tc6393xb->gpio);
 	tcpd->disable(dev);
 err_enable:
 	clk_disable_unprepare(tc6393xb->clk);
@@ -738,14 +802,8 @@ static int tc6393xb_remove(struct platform_device *dev)
 
 	mfd_remove_devices(&dev->dev);
 
-	if (tcpd->teardown)
-		tcpd->teardown(dev);
-
 	tc6393xb_detach_irq(dev);
 
-	if (tc6393xb->gpio.base != -1)
-		gpiochip_remove(&tc6393xb->gpio);
-
 	ret = tcpd->disable(dev);
 	clk_disable_unprepare(tc6393xb->clk);
 	iounmap(tc6393xb->scr);
diff --git a/drivers/power/supply/tosa_battery.c b/drivers/power/supply/tosa_battery.c
index 32cc31cd4761..73d4aca4c386 100644
--- a/drivers/power/supply/tosa_battery.c
+++ b/drivers/power/supply/tosa_battery.c
@@ -12,10 +12,9 @@
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include <asm/mach-types.h>
-#include <mach/tosa.h>
 
 static DEFINE_MUTEX(bat_lock); /* protects gpio pins */
 static struct work_struct bat_work;
@@ -28,22 +27,23 @@ struct tosa_bat {
 	struct mutex work_lock; /* protects data */
 
 	bool (*is_present)(struct tosa_bat *bat);
-	int gpio_full;
-	int gpio_charge_off;
+	struct gpio_desc *gpiod_full;
+	struct gpio_desc *gpiod_charge_off;
 
 	int technology;
 
-	int gpio_bat;
+	struct gpio_desc *gpiod_bat;
 	int adc_bat;
 	int adc_bat_divider;
 	int bat_max;
 	int bat_min;
 
-	int gpio_temp;
+	struct gpio_desc *gpiod_temp;
 	int adc_temp;
 	int adc_temp_divider;
 };
 
+static struct gpio_desc *jacket_detect;
 static struct tosa_bat tosa_bat_main;
 static struct tosa_bat tosa_bat_jacket;
 
@@ -51,15 +51,15 @@ static unsigned long tosa_read_bat(struct tosa_bat *bat)
 {
 	unsigned long value = 0;
 
-	if (bat->gpio_bat < 0 || bat->adc_bat < 0)
+	if (!bat->gpiod_bat || bat->adc_bat < 0)
 		return 0;
 
 	mutex_lock(&bat_lock);
-	gpio_set_value(bat->gpio_bat, 1);
+	gpiod_set_value(bat->gpiod_bat, 1);
 	msleep(5);
 	value = wm97xx_read_aux_adc(dev_get_drvdata(bat->psy->dev.parent),
 			bat->adc_bat);
-	gpio_set_value(bat->gpio_bat, 0);
+	gpiod_set_value(bat->gpiod_bat, 0);
 	mutex_unlock(&bat_lock);
 
 	value = value * 1000000 / bat->adc_bat_divider;
@@ -71,15 +71,15 @@ static unsigned long tosa_read_temp(struct tosa_bat *bat)
 {
 	unsigned long value = 0;
 
-	if (bat->gpio_temp < 0 || bat->adc_temp < 0)
+	if (!bat->gpiod_temp || bat->adc_temp < 0)
 		return 0;
 
 	mutex_lock(&bat_lock);
-	gpio_set_value(bat->gpio_temp, 1);
+	gpiod_set_value(bat->gpiod_temp, 1);
 	msleep(5);
 	value = wm97xx_read_aux_adc(dev_get_drvdata(bat->psy->dev.parent),
 			bat->adc_temp);
-	gpio_set_value(bat->gpio_temp, 0);
+	gpiod_set_value(bat->gpiod_temp, 0);
 	mutex_unlock(&bat_lock);
 
 	value = value * 10000 / bat->adc_temp_divider;
@@ -136,7 +136,7 @@ static int tosa_bat_get_property(struct power_supply *psy,
 
 static bool tosa_jacket_bat_is_present(struct tosa_bat *bat)
 {
-	return gpio_get_value(TOSA_GPIO_JACKET_DETECT) == 0;
+	return gpiod_get_value(jacket_detect) == 0;
 }
 
 static void tosa_bat_external_power_changed(struct power_supply *psy)
@@ -166,23 +166,23 @@ static void tosa_bat_update(struct tosa_bat *bat)
 		bat->full_chrg = -1;
 	} else if (power_supply_am_i_supplied(psy)) {
 		if (bat->status == POWER_SUPPLY_STATUS_DISCHARGING) {
-			gpio_set_value(bat->gpio_charge_off, 0);
+			gpiod_set_value(bat->gpiod_charge_off, 0);
 			mdelay(15);
 		}
 
-		if (gpio_get_value(bat->gpio_full)) {
+		if (gpiod_get_value(bat->gpiod_full)) {
 			if (old == POWER_SUPPLY_STATUS_CHARGING ||
 					bat->full_chrg == -1)
 				bat->full_chrg = tosa_read_bat(bat);
 
-			gpio_set_value(bat->gpio_charge_off, 1);
+			gpiod_set_value(bat->gpiod_charge_off, 1);
 			bat->status = POWER_SUPPLY_STATUS_FULL;
 		} else {
-			gpio_set_value(bat->gpio_charge_off, 0);
+			gpiod_set_value(bat->gpiod_charge_off, 0);
 			bat->status = POWER_SUPPLY_STATUS_CHARGING;
 		}
 	} else {
-		gpio_set_value(bat->gpio_charge_off, 1);
+		gpiod_set_value(bat->gpiod_charge_off, 1);
 		bat->status = POWER_SUPPLY_STATUS_DISCHARGING;
 	}
 
@@ -251,18 +251,18 @@ static struct tosa_bat tosa_bat_main = {
 	.full_chrg = -1,
 	.psy = NULL,
 
-	.gpio_full = TOSA_GPIO_BAT0_CRG,
-	.gpio_charge_off = TOSA_GPIO_CHARGE_OFF,
+	.gpiod_full = NULL,
+	.gpiod_charge_off = NULL,
 
 	.technology = POWER_SUPPLY_TECHNOLOGY_LIPO,
 
-	.gpio_bat = TOSA_GPIO_BAT0_V_ON,
+	.gpiod_bat = NULL,
 	.adc_bat = WM97XX_AUX_ID3,
 	.adc_bat_divider = 414,
 	.bat_max = 4310000,
 	.bat_min = 1551 * 1000000 / 414,
 
-	.gpio_temp = TOSA_GPIO_BAT1_TH_ON,
+	.gpiod_temp = NULL,
 	.adc_temp = WM97XX_AUX_ID2,
 	.adc_temp_divider = 10000,
 };
@@ -273,18 +273,18 @@ static struct tosa_bat tosa_bat_jacket = {
 	.psy = NULL,
 
 	.is_present = tosa_jacket_bat_is_present,
-	.gpio_full = TOSA_GPIO_BAT1_CRG,
-	.gpio_charge_off = TOSA_GPIO_CHARGE_OFF_JC,
+	.gpiod_full = NULL,
+	.gpiod_charge_off = NULL,
 
 	.technology = POWER_SUPPLY_TECHNOLOGY_LIPO,
 
-	.gpio_bat = TOSA_GPIO_BAT1_V_ON,
+	.gpiod_bat = NULL,
 	.adc_bat = WM97XX_AUX_ID3,
 	.adc_bat_divider = 414,
 	.bat_max = 4310000,
 	.bat_min = 1551 * 1000000 / 414,
 
-	.gpio_temp = TOSA_GPIO_BAT0_TH_ON,
+	.gpiod_temp = NULL,
 	.adc_temp = WM97XX_AUX_ID2,
 	.adc_temp_divider = 10000,
 };
@@ -294,36 +294,20 @@ static struct tosa_bat tosa_bat_bu = {
 	.full_chrg = -1,
 	.psy = NULL,
 
-	.gpio_full = -1,
-	.gpio_charge_off = -1,
+	.gpiod_full = NULL,
+	.gpiod_charge_off = NULL,
 
 	.technology = POWER_SUPPLY_TECHNOLOGY_LiMn,
 
-	.gpio_bat = TOSA_GPIO_BU_CHRG_ON,
+	.gpiod_bat = NULL,
 	.adc_bat = WM97XX_AUX_ID4,
 	.adc_bat_divider = 1266,
 
-	.gpio_temp = -1,
+	.gpiod_temp = NULL,
 	.adc_temp = -1,
 	.adc_temp_divider = -1,
 };
 
-static struct gpio tosa_bat_gpios[] = {
-	{ TOSA_GPIO_CHARGE_OFF,	   GPIOF_OUT_INIT_HIGH, "main charge off" },
-	{ TOSA_GPIO_CHARGE_OFF_JC, GPIOF_OUT_INIT_HIGH, "jacket charge off" },
-	{ TOSA_GPIO_BAT_SW_ON,	   GPIOF_OUT_INIT_LOW,	"battery switch" },
-	{ TOSA_GPIO_BAT0_V_ON,	   GPIOF_OUT_INIT_LOW,	"main battery" },
-	{ TOSA_GPIO_BAT1_V_ON,	   GPIOF_OUT_INIT_LOW,	"jacket battery" },
-	{ TOSA_GPIO_BAT1_TH_ON,	   GPIOF_OUT_INIT_LOW,	"main battery temp" },
-	{ TOSA_GPIO_BAT0_TH_ON,	   GPIOF_OUT_INIT_LOW,	"jacket battery temp" },
-	{ TOSA_GPIO_BU_CHRG_ON,	   GPIOF_OUT_INIT_LOW,	"backup battery" },
-	{ TOSA_GPIO_BAT0_CRG,	   GPIOF_IN,		"main battery full" },
-	{ TOSA_GPIO_BAT1_CRG,	   GPIOF_IN,		"jacket battery full" },
-	{ TOSA_GPIO_BAT0_LOW,	   GPIOF_IN,		"main battery low" },
-	{ TOSA_GPIO_BAT1_LOW,	   GPIOF_IN,		"jacket battery low" },
-	{ TOSA_GPIO_JACKET_DETECT, GPIOF_IN,		"jacket detect" },
-};
-
 #ifdef CONFIG_PM
 static int tosa_bat_suspend(struct platform_device *dev, pm_message_t state)
 {
@@ -343,19 +327,83 @@ static int tosa_bat_resume(struct platform_device *dev)
 #define tosa_bat_resume NULL
 #endif
 
-static int tosa_bat_probe(struct platform_device *dev)
+static int tosa_bat_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct power_supply_config main_psy_cfg = {},
 				   jacket_psy_cfg = {},
 				   bu_psy_cfg = {};
+	struct device *dev = &pdev->dev;
+	struct gpio_desc *dummy;
 
 	if (!machine_is_tosa())
 		return -ENODEV;
 
-	ret = gpio_request_array(tosa_bat_gpios, ARRAY_SIZE(tosa_bat_gpios));
-	if (ret)
-		return ret;
+	/* Main charging control GPIOs */
+	tosa_bat_main.gpiod_charge_off = devm_gpiod_get(dev, "main charge off", GPIOD_OUT_HIGH);
+	if (IS_ERR(tosa_bat_main.gpiod_charge_off))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_main.gpiod_charge_off),
+				     "no main charger GPIO\n");
+	tosa_bat_jacket.gpiod_charge_off = devm_gpiod_get(dev, "jacket charge off", GPIOD_OUT_HIGH);
+	if (IS_ERR(tosa_bat_jacket.gpiod_charge_off))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_jacket.gpiod_charge_off),
+				     "no jacket charger GPIO\n");
+
+	/* Per-battery output check (routes battery voltage to ADC) */
+	tosa_bat_main.gpiod_bat = devm_gpiod_get(dev, "main battery", GPIOD_OUT_LOW);
+	if (IS_ERR(tosa_bat_main.gpiod_bat))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_main.gpiod_bat),
+				     "no main battery GPIO\n");
+	tosa_bat_jacket.gpiod_bat = devm_gpiod_get(dev, "jacket battery", GPIOD_OUT_LOW);
+	if (IS_ERR(tosa_bat_jacket.gpiod_bat))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_jacket.gpiod_bat),
+				     "no jacket battery GPIO\n");
+	tosa_bat_bu.gpiod_bat = devm_gpiod_get(dev, "backup battery", GPIOD_OUT_LOW);
+	if (IS_ERR(tosa_bat_bu.gpiod_bat))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_bu.gpiod_bat),
+				     "no backup battery GPIO\n");
+
+	/* Battery full detect GPIOs (using PXA SoC GPIOs) */
+	tosa_bat_main.gpiod_full = devm_gpiod_get(dev, "main battery full", GPIOD_IN);
+	if (IS_ERR(tosa_bat_main.gpiod_full))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_main.gpiod_full),
+				     "no main battery full GPIO\n");
+	tosa_bat_jacket.gpiod_full = devm_gpiod_get(dev, "jacket battery full", GPIOD_IN);
+	if (IS_ERR(tosa_bat_jacket.gpiod_full))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_jacket.gpiod_full),
+				     "no jacket battery full GPIO\n");
+
+	/* Battery temperature GPIOs (routes thermistor voltage to ADC) */
+	tosa_bat_main.gpiod_temp = devm_gpiod_get(dev, "main battery temp", GPIOD_OUT_LOW);
+	if (IS_ERR(tosa_bat_main.gpiod_temp))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_main.gpiod_temp),
+				     "no main battery temp GPIO\n");
+	tosa_bat_jacket.gpiod_temp = devm_gpiod_get(dev, "jacket battery temp", GPIOD_OUT_LOW);
+	if (IS_ERR(tosa_bat_jacket.gpiod_temp))
+		return dev_err_probe(dev, PTR_ERR(tosa_bat_jacket.gpiod_temp),
+				     "no jacket battery temp GPIO\n");
+
+	/* Jacket detect GPIO */
+	jacket_detect = devm_gpiod_get(dev, "jacket detect", GPIOD_IN);
+	if (IS_ERR(jacket_detect))
+		return dev_err_probe(dev, PTR_ERR(jacket_detect),
+				     "no jacket detect GPIO\n");
+
+	/* Battery low indication GPIOs (not used, we just request them) */
+	dummy = devm_gpiod_get(dev, "main battery low", GPIOD_IN);
+	if (IS_ERR(dummy))
+		return dev_err_probe(dev, PTR_ERR(dummy),
+				     "no main battery low GPIO\n");
+	dummy = devm_gpiod_get(dev, "jacket battery low", GPIOD_IN);
+	if (IS_ERR(dummy))
+		return dev_err_probe(dev, PTR_ERR(dummy),
+				     "no jacket battery low GPIO\n");
+
+	/* Battery switch GPIO (not used just requested) */
+	dummy = devm_gpiod_get(dev, "battery switch", GPIOD_OUT_LOW);
+	if (IS_ERR(dummy))
+		return dev_err_probe(dev, PTR_ERR(dummy),
+				     "no battery switch GPIO\n");
 
 	mutex_init(&tosa_bat_main.work_lock);
 	mutex_init(&tosa_bat_jacket.work_lock);
@@ -363,7 +411,7 @@ static int tosa_bat_probe(struct platform_device *dev)
 	INIT_WORK(&bat_work, tosa_bat_work);
 
 	main_psy_cfg.drv_data = &tosa_bat_main;
-	tosa_bat_main.psy = power_supply_register(&dev->dev,
+	tosa_bat_main.psy = power_supply_register(dev,
 						  &tosa_bat_main_desc,
 						  &main_psy_cfg);
 	if (IS_ERR(tosa_bat_main.psy)) {
@@ -372,7 +420,7 @@ static int tosa_bat_probe(struct platform_device *dev)
 	}
 
 	jacket_psy_cfg.drv_data = &tosa_bat_jacket;
-	tosa_bat_jacket.psy = power_supply_register(&dev->dev,
+	tosa_bat_jacket.psy = power_supply_register(dev,
 						    &tosa_bat_jacket_desc,
 						    &jacket_psy_cfg);
 	if (IS_ERR(tosa_bat_jacket.psy)) {
@@ -381,28 +429,28 @@ static int tosa_bat_probe(struct platform_device *dev)
 	}
 
 	bu_psy_cfg.drv_data = &tosa_bat_bu;
-	tosa_bat_bu.psy = power_supply_register(&dev->dev, &tosa_bat_bu_desc,
+	tosa_bat_bu.psy = power_supply_register(dev, &tosa_bat_bu_desc,
 						&bu_psy_cfg);
 	if (IS_ERR(tosa_bat_bu.psy)) {
 		ret = PTR_ERR(tosa_bat_bu.psy);
 		goto err_psy_reg_bu;
 	}
 
-	ret = request_irq(gpio_to_irq(TOSA_GPIO_BAT0_CRG),
+	ret = request_irq(gpiod_to_irq(tosa_bat_main.gpiod_full),
 				tosa_bat_gpio_isr,
 				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
 				"main full", &tosa_bat_main);
 	if (ret)
 		goto err_req_main;
 
-	ret = request_irq(gpio_to_irq(TOSA_GPIO_BAT1_CRG),
+	ret = request_irq(gpiod_to_irq(tosa_bat_jacket.gpiod_full),
 				tosa_bat_gpio_isr,
 				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
 				"jacket full", &tosa_bat_jacket);
 	if (ret)
 		goto err_req_jacket;
 
-	ret = request_irq(gpio_to_irq(TOSA_GPIO_JACKET_DETECT),
+	ret = request_irq(gpiod_to_irq(jacket_detect),
 				tosa_bat_gpio_isr,
 				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
 				"jacket detect", &tosa_bat_jacket);
@@ -411,9 +459,9 @@ static int tosa_bat_probe(struct platform_device *dev)
 		return 0;
 	}
 
-	free_irq(gpio_to_irq(TOSA_GPIO_BAT1_CRG), &tosa_bat_jacket);
+	free_irq(gpiod_to_irq(tosa_bat_jacket.gpiod_full), &tosa_bat_jacket);
 err_req_jacket:
-	free_irq(gpio_to_irq(TOSA_GPIO_BAT0_CRG), &tosa_bat_main);
+	free_irq(gpiod_to_irq(tosa_bat_main.gpiod_full), &tosa_bat_main);
 err_req_main:
 	power_supply_unregister(tosa_bat_bu.psy);
 err_psy_reg_bu:
@@ -425,15 +473,14 @@ err_psy_reg_main:
 	/* see comment in tosa_bat_remove */
 	cancel_work_sync(&bat_work);
 
-	gpio_free_array(tosa_bat_gpios, ARRAY_SIZE(tosa_bat_gpios));
 	return ret;
 }
 
 static int tosa_bat_remove(struct platform_device *dev)
 {
-	free_irq(gpio_to_irq(TOSA_GPIO_JACKET_DETECT), &tosa_bat_jacket);
-	free_irq(gpio_to_irq(TOSA_GPIO_BAT1_CRG), &tosa_bat_jacket);
-	free_irq(gpio_to_irq(TOSA_GPIO_BAT0_CRG), &tosa_bat_main);
+	free_irq(gpiod_to_irq(jacket_detect), &tosa_bat_jacket);
+	free_irq(gpiod_to_irq(tosa_bat_jacket.gpiod_full), &tosa_bat_jacket);
+	free_irq(gpiod_to_irq(tosa_bat_main.gpiod_full), &tosa_bat_main);
 
 	power_supply_unregister(tosa_bat_bu.psy);
 	power_supply_unregister(tosa_bat_jacket.psy);
@@ -445,7 +492,6 @@ static int tosa_bat_remove(struct platform_device *dev)
 	 * unregistered now.
 	 */
 	cancel_work_sync(&bat_work);
-	gpio_free_array(tosa_bat_gpios, ARRAY_SIZE(tosa_bat_gpios));
 	return 0;
 }
 
diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h
index 2647dd10b541..4d55da28e664 100644
--- a/include/linux/gpio/machine.h
+++ b/include/linux/gpio/machine.h
@@ -63,6 +63,18 @@ struct gpiod_hog {
 	int dflags;
 };
 
+/*
+ * Helper for lookup tables with just one single lookup for a device.
+ */
+#define GPIO_LOOKUP_SINGLE(_name, _dev_id, _key, _chip_hwnum, _con_id, _flags) \
+static struct gpiod_lookup_table _name = {				\
+	.dev_id = _dev_id,						\
+	.table = {							\
+		GPIO_LOOKUP(_key, _chip_hwnum, _con_id, _flags),	\
+		{},							\
+	},								\
+}
+
 /*
  * Simple definition of a single GPIO under a con_id
  */
diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h
index fcc8e74f0e8d..d336c541b7df 100644
--- a/include/linux/mfd/tc6393xb.h
+++ b/include/linux/mfd/tc6393xb.h
@@ -27,9 +27,6 @@ struct tc6393xb_platform_data {
 	int	(*resume)(struct platform_device *dev);
 
 	int	irq_base;	/* base for subdevice irqs */
-	int	gpio_base;
-	int	(*setup)(struct platform_device *dev);
-	void	(*teardown)(struct platform_device *dev);
 
 	struct tmio_nand_data	*nand_data;
 	struct tmio_fb_data	*fb_data;
diff --git a/sound/soc/pxa/tosa.c b/sound/soc/pxa/tosa.c
index 06226f9b863e..30f83cab0c32 100644
--- a/sound/soc/pxa/tosa.c
+++ b/sound/soc/pxa/tosa.c
@@ -16,14 +16,13 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/soc.h>
 
 #include <asm/mach-types.h>
-#include <mach/tosa.h>
 #include <linux/platform_data/asoc-pxa.h>
 
 #define TOSA_HP        0
@@ -33,6 +32,7 @@
 #define TOSA_SPK_ON    0
 #define TOSA_SPK_OFF   1
 
+static struct gpio_desc *tosa_mute;
 static int tosa_jack_func;
 static int tosa_spk_func;
 
@@ -128,7 +128,7 @@ static int tosa_set_spk(struct snd_kcontrol *kcontrol,
 static int tosa_hp_event(struct snd_soc_dapm_widget *w,
 	struct snd_kcontrol *k, int event)
 {
-	gpio_set_value(TOSA_GPIO_L_MUTE, SND_SOC_DAPM_EVENT_ON(event) ? 1 : 0);
+	gpiod_set_value(tosa_mute, SND_SOC_DAPM_EVENT_ON(event) ? 1 : 0);
 	return 0;
 }
 
@@ -222,10 +222,11 @@ static int tosa_probe(struct platform_device *pdev)
 	struct snd_soc_card *card = &tosa;
 	int ret;
 
-	ret = gpio_request_one(TOSA_GPIO_L_MUTE, GPIOF_OUT_INIT_LOW,
-			       "Headphone Jack");
-	if (ret)
-		return ret;
+	tosa_mute = devm_gpiod_get(&pdev->dev, NULL, GPIOD_OUT_LOW);
+	if (IS_ERR(tosa_mute))
+		return dev_err_probe(&pdev->dev, PTR_ERR(tosa_mute),
+				     "failed to get L_MUTE GPIO\n");
+	gpiod_set_consumer_name(tosa_mute, "Headphone Jack");
 
 	card->dev = &pdev->dev;
 
@@ -233,24 +234,16 @@ static int tosa_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n",
 			ret);
-		gpio_free(TOSA_GPIO_L_MUTE);
 	}
 	return ret;
 }
 
-static int tosa_remove(struct platform_device *pdev)
-{
-	gpio_free(TOSA_GPIO_L_MUTE);
-	return 0;
-}
-
 static struct platform_driver tosa_driver = {
 	.driver		= {
 		.name	= "tosa-audio",
 		.pm     = &snd_soc_pm_ops,
 	},
 	.probe		= tosa_probe,
-	.remove		= tosa_remove,
 };
 
 module_platform_driver(tosa_driver);
-- 
cgit v1.2.3


From ac70f4d80df414223130b04d9b4435bf56dda654 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Sep 2019 10:58:26 +0200
Subject: ARM: pxa: poodle: use platform data for poodle asoc driver

The poodle audio driver shows its age by using a custom
gpio api for the "locomo" support chip.

In a perfect world, this would get converted to use gpiolib
and a gpio lookup table.

As the world is not perfect, just pass all the required data
in a custom platform_data structure. to avoid the globally
visible mach/poodle.h header.

Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Cc: alsa-devel@alsa-project.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/include/mach/poodle.h   | 94 -------------------------------
 arch/arm/mach-pxa/poodle.c                | 30 ++++++----
 arch/arm/mach-pxa/poodle.h                | 92 ++++++++++++++++++++++++++++++
 include/linux/platform_data/asoc-poodle.h | 16 ++++++
 sound/soc/pxa/poodle.c                    | 49 ++++++++--------
 5 files changed, 154 insertions(+), 127 deletions(-)
 delete mode 100644 arch/arm/mach-pxa/include/mach/poodle.h
 create mode 100644 arch/arm/mach-pxa/poodle.h
 create mode 100644 include/linux/platform_data/asoc-poodle.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/include/mach/poodle.h b/arch/arm/mach-pxa/include/mach/poodle.h
deleted file mode 100644
index b56b19351a03..000000000000
--- a/arch/arm/mach-pxa/include/mach/poodle.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * arch/arm/mach-pxa/include/mach/poodle.h
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * Based on:
- *   arch/arm/mach-sa1100/include/mach/collie.h
- *
- * ChangeLog:
- *   04-06-2001 Lineo Japan, Inc.
- *   04-16-2001 SHARP Corporation
- *   Update to 2.6 John Lenz
- */
-#ifndef __ASM_ARCH_POODLE_H
-#define __ASM_ARCH_POODLE_H  1
-
-#include "irqs.h" /* PXA_GPIO_TO_IRQ */
-
-/*
- * GPIOs
- */
-/* PXA GPIOs */
-#define POODLE_GPIO_ON_KEY		(0)
-#define POODLE_GPIO_AC_IN		(1)
-#define POODLE_GPIO_CO			16
-#define POODLE_GPIO_TP_INT		(5)
-#define POODLE_GPIO_TP_CS		(24)
-#define POODLE_GPIO_WAKEUP		(11)	/* change battery */
-#define POODLE_GPIO_GA_INT		(10)
-#define POODLE_GPIO_IR_ON		(22)
-#define POODLE_GPIO_HP_IN		(4)
-#define POODLE_GPIO_CF_IRQ		(17)
-#define POODLE_GPIO_CF_CD		(14)
-#define POODLE_GPIO_CF_STSCHG		(14)
-#define POODLE_GPIO_SD_PWR		(33)
-#define POODLE_GPIO_SD_PWR1		(3)
-#define POODLE_GPIO_nSD_CLK		(6)
-#define POODLE_GPIO_nSD_WP		(7)
-#define POODLE_GPIO_nSD_INT		(8)
-#define POODLE_GPIO_nSD_DETECT		(9)
-#define POODLE_GPIO_MAIN_BAT_LOW	(13)
-#define POODLE_GPIO_BAT_COVER		(13)
-#define POODLE_GPIO_USB_PULLUP		(20)
-#define POODLE_GPIO_ADC_TEMP_ON		(21)
-#define POODLE_GPIO_BYPASS_ON		(36)
-#define POODLE_GPIO_CHRG_ON		(38)
-#define POODLE_GPIO_CHRG_FULL		(16)
-#define POODLE_GPIO_DISCHARGE_ON        (42) /* Enable battery discharge */
-
-/* PXA GPIOs */
-#define POODLE_IRQ_GPIO_ON_KEY		PXA_GPIO_TO_IRQ(0)
-#define POODLE_IRQ_GPIO_AC_IN		PXA_GPIO_TO_IRQ(1)
-#define POODLE_IRQ_GPIO_HP_IN		PXA_GPIO_TO_IRQ(4)
-#define POODLE_IRQ_GPIO_CO		PXA_GPIO_TO_IRQ(16)
-#define POODLE_IRQ_GPIO_TP_INT		PXA_GPIO_TO_IRQ(5)
-#define POODLE_IRQ_GPIO_WAKEUP		PXA_GPIO_TO_IRQ(11)
-#define POODLE_IRQ_GPIO_GA_INT		PXA_GPIO_TO_IRQ(10)
-#define POODLE_IRQ_GPIO_CF_IRQ		PXA_GPIO_TO_IRQ(17)
-#define POODLE_IRQ_GPIO_CF_CD		PXA_GPIO_TO_IRQ(14)
-#define POODLE_IRQ_GPIO_nSD_INT		PXA_GPIO_TO_IRQ(8)
-#define POODLE_IRQ_GPIO_nSD_DETECT	PXA_GPIO_TO_IRQ(9)
-#define POODLE_IRQ_GPIO_MAIN_BAT_LOW	PXA_GPIO_TO_IRQ(13)
-
-/* SCOOP GPIOs */
-#define POODLE_SCOOP_CHARGE_ON	SCOOP_GPCR_PA11
-#define POODLE_SCOOP_CP401	SCOOP_GPCR_PA13
-#define POODLE_SCOOP_VPEN	SCOOP_GPCR_PA18
-#define POODLE_SCOOP_L_PCLK	SCOOP_GPCR_PA20
-#define POODLE_SCOOP_L_LCLK	SCOOP_GPCR_PA21
-#define POODLE_SCOOP_HS_OUT	SCOOP_GPCR_PA22
-
-#define POODLE_SCOOP_IO_DIR	( POODLE_SCOOP_VPEN | POODLE_SCOOP_HS_OUT )
-#define POODLE_SCOOP_IO_OUT	( 0 )
-
-#define POODLE_SCOOP_GPIO_BASE	(PXA_NR_BUILTIN_GPIO)
-#define POODLE_GPIO_CHARGE_ON	(POODLE_SCOOP_GPIO_BASE + 0)
-#define POODLE_GPIO_CP401	(POODLE_SCOOP_GPIO_BASE + 2)
-#define POODLE_GPIO_VPEN	(POODLE_SCOOP_GPIO_BASE + 7)
-#define POODLE_GPIO_L_PCLK	(POODLE_SCOOP_GPIO_BASE + 9)
-#define POODLE_GPIO_L_LCLK	(POODLE_SCOOP_GPIO_BASE + 10)
-#define POODLE_GPIO_HS_OUT	(POODLE_SCOOP_GPIO_BASE + 11)
-
-#define POODLE_LOCOMO_GPIO_AMP_ON      LOCOMO_GPIO(8)
-#define POODLE_LOCOMO_GPIO_MUTE_L      LOCOMO_GPIO(10)
-#define POODLE_LOCOMO_GPIO_MUTE_R      LOCOMO_GPIO(11)
-#define POODLE_LOCOMO_GPIO_232VCC_ON   LOCOMO_GPIO(12)
-#define POODLE_LOCOMO_GPIO_JK_B        LOCOMO_GPIO(13)
-
-#define POODLE_NR_IRQS		(IRQ_BOARD_START + 4)	/* 4 for LoCoMo */
-
-extern struct platform_device poodle_locomo_device;
-
-#endif /* __ASM_ARCH_POODLE_H  */
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index ca52882433d4..7772a39430ed 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -39,11 +39,13 @@
 #include <asm/mach/irq.h>
 
 #include "pxa25x.h"
-#include <linux/platform_data/mmc-pxamci.h>
 #include "udc.h"
+#include "poodle.h"
+
+#include <linux/platform_data/mmc-pxamci.h>
 #include <linux/platform_data/irda-pxaficp.h>
-#include <mach/poodle.h>
 #include <linux/platform_data/video-pxafb.h>
+#include <linux/platform_data/asoc-poodle.h>
 
 #include <asm/hardware/scoop.h>
 #include <asm/hardware/locomo.h>
@@ -155,12 +157,6 @@ static struct scoop_pcmcia_config poodle_pcmcia_config = {
 
 EXPORT_SYMBOL(poodle_scoop_device);
 
-
-static struct platform_device poodle_audio_device = {
-	.name	= "poodle-audio",
-	.id	= -1,
-};
-
 /* LoCoMo device */
 static struct resource locomo_resources[] = {
 	[0] = {
@@ -179,7 +175,7 @@ static struct locomo_platform_data locomo_info = {
 	.irq_base	= IRQ_BOARD_START,
 };
 
-struct platform_device poodle_locomo_device = {
+static struct platform_device poodle_locomo_device = {
 	.name		= "locomo",
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(locomo_resources),
@@ -189,7 +185,21 @@ struct platform_device poodle_locomo_device = {
 	},
 };
 
-EXPORT_SYMBOL(poodle_locomo_device);
+static struct poodle_audio_platform_data poodle_audio_pdata = {
+	.locomo_dev	= &poodle_locomo_device.dev,
+
+	.gpio_amp_on   	= POODLE_LOCOMO_GPIO_AMP_ON,
+	.gpio_mute_l   	= POODLE_LOCOMO_GPIO_MUTE_L,
+	.gpio_mute_r   	= POODLE_LOCOMO_GPIO_MUTE_R,
+	.gpio_232vcc_on	= POODLE_LOCOMO_GPIO_232VCC_ON,
+	.gpio_jk_b     	= POODLE_LOCOMO_GPIO_JK_B,
+};
+
+static struct platform_device poodle_audio_device = {
+	.name	= "poodle-audio",
+	.id	= -1,
+	.dev.platform_data = &poodle_audio_pdata,
+};
 
 #if defined(CONFIG_SPI_PXA2XX) || defined(CONFIG_SPI_PXA2XX_MODULE)
 static struct pxa2xx_spi_controller poodle_spi_info = {
diff --git a/arch/arm/mach-pxa/poodle.h b/arch/arm/mach-pxa/poodle.h
new file mode 100644
index 000000000000..e675a3d1aa18
--- /dev/null
+++ b/arch/arm/mach-pxa/poodle.h
@@ -0,0 +1,92 @@
+/*
+ * arch/arm/mach-pxa/include/mach/poodle.h
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License.  See linux/COPYING for more information.
+ *
+ * Based on:
+ *   arch/arm/mach-sa1100/include/mach/collie.h
+ *
+ * ChangeLog:
+ *   04-06-2001 Lineo Japan, Inc.
+ *   04-16-2001 SHARP Corporation
+ *   Update to 2.6 John Lenz
+ */
+#ifndef __ASM_ARCH_POODLE_H
+#define __ASM_ARCH_POODLE_H  1
+
+#include <mach/irqs.h> /* PXA_GPIO_TO_IRQ */
+
+/*
+ * GPIOs
+ */
+/* PXA GPIOs */
+#define POODLE_GPIO_ON_KEY		(0)
+#define POODLE_GPIO_AC_IN		(1)
+#define POODLE_GPIO_CO			16
+#define POODLE_GPIO_TP_INT		(5)
+#define POODLE_GPIO_TP_CS		(24)
+#define POODLE_GPIO_WAKEUP		(11)	/* change battery */
+#define POODLE_GPIO_GA_INT		(10)
+#define POODLE_GPIO_IR_ON		(22)
+#define POODLE_GPIO_HP_IN		(4)
+#define POODLE_GPIO_CF_IRQ		(17)
+#define POODLE_GPIO_CF_CD		(14)
+#define POODLE_GPIO_CF_STSCHG		(14)
+#define POODLE_GPIO_SD_PWR		(33)
+#define POODLE_GPIO_SD_PWR1		(3)
+#define POODLE_GPIO_nSD_CLK		(6)
+#define POODLE_GPIO_nSD_WP		(7)
+#define POODLE_GPIO_nSD_INT		(8)
+#define POODLE_GPIO_nSD_DETECT		(9)
+#define POODLE_GPIO_MAIN_BAT_LOW	(13)
+#define POODLE_GPIO_BAT_COVER		(13)
+#define POODLE_GPIO_USB_PULLUP		(20)
+#define POODLE_GPIO_ADC_TEMP_ON		(21)
+#define POODLE_GPIO_BYPASS_ON		(36)
+#define POODLE_GPIO_CHRG_ON		(38)
+#define POODLE_GPIO_CHRG_FULL		(16)
+#define POODLE_GPIO_DISCHARGE_ON        (42) /* Enable battery discharge */
+
+/* PXA GPIOs */
+#define POODLE_IRQ_GPIO_ON_KEY		PXA_GPIO_TO_IRQ(0)
+#define POODLE_IRQ_GPIO_AC_IN		PXA_GPIO_TO_IRQ(1)
+#define POODLE_IRQ_GPIO_HP_IN		PXA_GPIO_TO_IRQ(4)
+#define POODLE_IRQ_GPIO_CO		PXA_GPIO_TO_IRQ(16)
+#define POODLE_IRQ_GPIO_TP_INT		PXA_GPIO_TO_IRQ(5)
+#define POODLE_IRQ_GPIO_WAKEUP		PXA_GPIO_TO_IRQ(11)
+#define POODLE_IRQ_GPIO_GA_INT		PXA_GPIO_TO_IRQ(10)
+#define POODLE_IRQ_GPIO_CF_IRQ		PXA_GPIO_TO_IRQ(17)
+#define POODLE_IRQ_GPIO_CF_CD		PXA_GPIO_TO_IRQ(14)
+#define POODLE_IRQ_GPIO_nSD_INT		PXA_GPIO_TO_IRQ(8)
+#define POODLE_IRQ_GPIO_nSD_DETECT	PXA_GPIO_TO_IRQ(9)
+#define POODLE_IRQ_GPIO_MAIN_BAT_LOW	PXA_GPIO_TO_IRQ(13)
+
+/* SCOOP GPIOs */
+#define POODLE_SCOOP_CHARGE_ON	SCOOP_GPCR_PA11
+#define POODLE_SCOOP_CP401	SCOOP_GPCR_PA13
+#define POODLE_SCOOP_VPEN	SCOOP_GPCR_PA18
+#define POODLE_SCOOP_L_PCLK	SCOOP_GPCR_PA20
+#define POODLE_SCOOP_L_LCLK	SCOOP_GPCR_PA21
+#define POODLE_SCOOP_HS_OUT	SCOOP_GPCR_PA22
+
+#define POODLE_SCOOP_IO_DIR	( POODLE_SCOOP_VPEN | POODLE_SCOOP_HS_OUT )
+#define POODLE_SCOOP_IO_OUT	( 0 )
+
+#define POODLE_SCOOP_GPIO_BASE	(PXA_NR_BUILTIN_GPIO)
+#define POODLE_GPIO_CHARGE_ON	(POODLE_SCOOP_GPIO_BASE + 0)
+#define POODLE_GPIO_CP401	(POODLE_SCOOP_GPIO_BASE + 2)
+#define POODLE_GPIO_VPEN	(POODLE_SCOOP_GPIO_BASE + 7)
+#define POODLE_GPIO_L_PCLK	(POODLE_SCOOP_GPIO_BASE + 9)
+#define POODLE_GPIO_L_LCLK	(POODLE_SCOOP_GPIO_BASE + 10)
+#define POODLE_GPIO_HS_OUT	(POODLE_SCOOP_GPIO_BASE + 11)
+
+#define POODLE_LOCOMO_GPIO_AMP_ON      LOCOMO_GPIO(8)
+#define POODLE_LOCOMO_GPIO_MUTE_L      LOCOMO_GPIO(10)
+#define POODLE_LOCOMO_GPIO_MUTE_R      LOCOMO_GPIO(11)
+#define POODLE_LOCOMO_GPIO_232VCC_ON   LOCOMO_GPIO(12)
+#define POODLE_LOCOMO_GPIO_JK_B        LOCOMO_GPIO(13)
+
+#define POODLE_NR_IRQS		(IRQ_BOARD_START + 4)	/* 4 for LoCoMo */
+
+#endif /* __ASM_ARCH_POODLE_H  */
diff --git a/include/linux/platform_data/asoc-poodle.h b/include/linux/platform_data/asoc-poodle.h
new file mode 100644
index 000000000000..2052fad55c5c
--- /dev/null
+++ b/include/linux/platform_data/asoc-poodle.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_PLATFORM_DATA_POODLE_AUDIO
+#define __LINUX_PLATFORM_DATA_POODLE_AUDIO
+
+/* locomo is not a proper gpio driver, and uses its own api */
+struct poodle_audio_platform_data {
+	struct device	*locomo_dev;
+
+	int		gpio_amp_on;
+	int		gpio_mute_l;
+	int		gpio_mute_r;
+	int		gpio_232vcc_on;
+	int		gpio_jk_b;
+};
+
+#endif
diff --git a/sound/soc/pxa/poodle.c b/sound/soc/pxa/poodle.c
index 176a0441235a..5fdaa477e85d 100644
--- a/sound/soc/pxa/poodle.c
+++ b/sound/soc/pxa/poodle.c
@@ -21,8 +21,8 @@
 
 #include <asm/mach-types.h>
 #include <asm/hardware/locomo.h>
-#include <mach/poodle.h>
 #include <linux/platform_data/asoc-pxa.h>
+#include <linux/platform_data/asoc-poodle.h>
 
 #include "../codecs/wm8731.h"
 #include "pxa2xx-i2s.h"
@@ -38,21 +38,23 @@
 static int poodle_jack_func;
 static int poodle_spk_func;
 
+static struct poodle_audio_platform_data *poodle_pdata;
+
 static void poodle_ext_control(struct snd_soc_dapm_context *dapm)
 {
 	/* set up jack connection */
 	if (poodle_jack_func == POODLE_HP) {
 		/* set = unmute headphone */
-		locomo_gpio_write(&poodle_locomo_device.dev,
-			POODLE_LOCOMO_GPIO_MUTE_L, 1);
-		locomo_gpio_write(&poodle_locomo_device.dev,
-			POODLE_LOCOMO_GPIO_MUTE_R, 1);
+		locomo_gpio_write(poodle_pdata->locomo_dev,
+			poodle_pdata->gpio_mute_l, 1);
+		locomo_gpio_write(poodle_pdata->locomo_dev,
+			poodle_pdata->gpio_mute_r, 1);
 		snd_soc_dapm_enable_pin(dapm, "Headphone Jack");
 	} else {
-		locomo_gpio_write(&poodle_locomo_device.dev,
-			POODLE_LOCOMO_GPIO_MUTE_L, 0);
-		locomo_gpio_write(&poodle_locomo_device.dev,
-			POODLE_LOCOMO_GPIO_MUTE_R, 0);
+		locomo_gpio_write(poodle_pdata->locomo_dev,
+			poodle_pdata->gpio_mute_l, 0);
+		locomo_gpio_write(poodle_pdata->locomo_dev,
+			poodle_pdata->gpio_mute_r, 0);
 		snd_soc_dapm_disable_pin(dapm, "Headphone Jack");
 	}
 
@@ -80,10 +82,10 @@ static int poodle_startup(struct snd_pcm_substream *substream)
 static void poodle_shutdown(struct snd_pcm_substream *substream)
 {
 	/* set = unmute headphone */
-	locomo_gpio_write(&poodle_locomo_device.dev,
-		POODLE_LOCOMO_GPIO_MUTE_L, 1);
-	locomo_gpio_write(&poodle_locomo_device.dev,
-		POODLE_LOCOMO_GPIO_MUTE_R, 1);
+	locomo_gpio_write(poodle_pdata->locomo_dev,
+		poodle_pdata->gpio_mute_l, 1);
+	locomo_gpio_write(poodle_pdata->locomo_dev,
+		poodle_pdata->gpio_mute_r, 1);
 }
 
 static int poodle_hw_params(struct snd_pcm_substream *substream,
@@ -174,11 +176,11 @@ static int poodle_amp_event(struct snd_soc_dapm_widget *w,
 	struct snd_kcontrol *k, int event)
 {
 	if (SND_SOC_DAPM_EVENT_ON(event))
-		locomo_gpio_write(&poodle_locomo_device.dev,
-			POODLE_LOCOMO_GPIO_AMP_ON, 0);
+		locomo_gpio_write(poodle_pdata->locomo_dev,
+			poodle_pdata->gpio_amp_on, 0);
 	else
-		locomo_gpio_write(&poodle_locomo_device.dev,
-			POODLE_LOCOMO_GPIO_AMP_ON, 1);
+		locomo_gpio_write(poodle_pdata->locomo_dev,
+			poodle_pdata->gpio_amp_on, 1);
 
 	return 0;
 }
@@ -254,13 +256,14 @@ static int poodle_probe(struct platform_device *pdev)
 	struct snd_soc_card *card = &poodle;
 	int ret;
 
-	locomo_gpio_set_dir(&poodle_locomo_device.dev,
-		POODLE_LOCOMO_GPIO_AMP_ON, 0);
+	poodle_pdata = pdev->dev.platform_data;
+	locomo_gpio_set_dir(poodle_pdata->locomo_dev,
+		poodle_pdata->gpio_amp_on, 0);
 	/* should we mute HP at startup - burning power ?*/
-	locomo_gpio_set_dir(&poodle_locomo_device.dev,
-		POODLE_LOCOMO_GPIO_MUTE_L, 0);
-	locomo_gpio_set_dir(&poodle_locomo_device.dev,
-		POODLE_LOCOMO_GPIO_MUTE_R, 0);
+	locomo_gpio_set_dir(poodle_pdata->locomo_dev,
+		poodle_pdata->gpio_mute_l, 0);
+	locomo_gpio_set_dir(poodle_pdata->locomo_dev,
+		poodle_pdata->gpio_mute_r, 0);
 
 	card->dev = &pdev->dev;
 
-- 
cgit v1.2.3


From a2ef926143b84664f4823c82a437b29c4667a08c Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 18 Oct 2019 13:48:33 -0700
Subject: Input: wm97xx - switch to using threaded IRQ

Instead of manually disabling and enabling interrupts and scheduling work
to access the device, let's use threaded oneshot interrupt handler. It
simplifies things.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/input/touchscreen/wm97xx-core.c | 42 ++++++---------------------------
 include/linux/wm97xx.h                  |  1 -
 2 files changed, 7 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/input/touchscreen/wm97xx-core.c b/drivers/input/touchscreen/wm97xx-core.c
index 1b58611c8084..2757c7768ffe 100644
--- a/drivers/input/touchscreen/wm97xx-core.c
+++ b/drivers/input/touchscreen/wm97xx-core.c
@@ -285,11 +285,12 @@ void wm97xx_set_suspend_mode(struct wm97xx *wm, u16 mode)
 EXPORT_SYMBOL_GPL(wm97xx_set_suspend_mode);
 
 /*
- * Handle a pen down interrupt.
+ * Codec PENDOWN irq handler
+ *
  */
-static void wm97xx_pen_irq_worker(struct work_struct *work)
+static irqreturn_t wm97xx_pen_interrupt(int irq, void *dev_id)
 {
-	struct wm97xx *wm = container_of(work, struct wm97xx, pen_event_work);
+	struct wm97xx *wm = dev_id;
 	int pen_was_down = wm->pen_is_down;
 
 	/* do we need to enable the touch panel reader */
@@ -343,27 +344,6 @@ static void wm97xx_pen_irq_worker(struct work_struct *work)
 	if (!wm->pen_is_down && wm->mach_ops->acc_enabled)
 		wm->mach_ops->acc_pen_up(wm);
 
-	wm->mach_ops->irq_enable(wm, 1);
-}
-
-/*
- * Codec PENDOWN irq handler
- *
- * We have to disable the codec interrupt in the handler because it
- * can take up to 1ms to clear the interrupt source. We schedule a task
- * in a work queue to do the actual interaction with the chip.  The
- * interrupt is then enabled again in the slow handler when the source
- * has been cleared.
- */
-static irqreturn_t wm97xx_pen_interrupt(int irq, void *dev_id)
-{
-	struct wm97xx *wm = dev_id;
-
-	if (!work_pending(&wm->pen_event_work)) {
-		wm->mach_ops->irq_enable(wm, 0);
-		queue_work(wm->ts_workq, &wm->pen_event_work);
-	}
-
 	return IRQ_HANDLED;
 }
 
@@ -374,12 +354,9 @@ static int wm97xx_init_pen_irq(struct wm97xx *wm)
 {
 	u16 reg;
 
-	/* If an interrupt is supplied an IRQ enable operation must also be
-	 * provided. */
-	BUG_ON(!wm->mach_ops->irq_enable);
-
-	if (request_irq(wm->pen_irq, wm97xx_pen_interrupt, IRQF_SHARED,
-			"wm97xx-pen", wm)) {
+	if (request_threaded_irq(wm->pen_irq, NULL, wm97xx_pen_interrupt,
+				 IRQF_SHARED | IRQF_ONESHOT,
+				 "wm97xx-pen", wm)) {
 		dev_err(wm->dev,
 			"Failed to register pen down interrupt, polling");
 		wm->pen_irq = 0;
@@ -509,7 +486,6 @@ static int wm97xx_ts_input_open(struct input_dev *idev)
 	wm->codec->dig_enable(wm, 1);
 
 	INIT_DELAYED_WORK(&wm->ts_reader, wm97xx_ts_reader);
-	INIT_WORK(&wm->pen_event_work, wm97xx_pen_irq_worker);
 
 	wm->ts_reader_min_interval = HZ >= 100 ? HZ / 100 : 1;
 	if (wm->ts_reader_min_interval < 1)
@@ -560,10 +536,6 @@ static void wm97xx_ts_input_close(struct input_dev *idev)
 
 	wm->pen_is_down = 0;
 
-	/* Balance out interrupt disables/enables */
-	if (cancel_work_sync(&wm->pen_event_work))
-		wm->mach_ops->irq_enable(wm, 1);
-
 	/* ts_reader rearms itself so we need to explicitly stop it
 	 * before we destroy the workqueue.
 	 */
diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h
index 462854f4f286..85bd8dd3caea 100644
--- a/include/linux/wm97xx.h
+++ b/include/linux/wm97xx.h
@@ -281,7 +281,6 @@ struct wm97xx {
 	unsigned long ts_reader_min_interval; /* Minimum interval */
 	unsigned int pen_irq;		/* Pen IRQ number in use */
 	struct workqueue_struct *ts_workq;
-	struct work_struct pen_event_work;
 	u16 acc_slot;			/* AC97 slot used for acc touch data */
 	u16 acc_rate;			/* acc touch data rate */
 	unsigned pen_is_down:1;		/* Pen is down */
-- 
cgit v1.2.3


From e1d8f31218aab302df9e18526345af189fd061f0 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 18 Oct 2019 13:48:34 -0700
Subject: Input: wm97xx - get rid of irq_enable method in wm97xx_mach_ops

Now that we are using oneshot threaded IRQ this method is not used anymore.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
[arnd: add the db1300 change as well]
Cc: Manuel Lauss <manuel.lauss@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/mips/alchemy/devboards/db1300.c         | 9 ---------
 drivers/input/touchscreen/mainstone-wm97xx.c | 9 ---------
 drivers/input/touchscreen/zylonite-wm97xx.c  | 9 ---------
 include/linux/wm97xx.h                       | 3 ---
 4 files changed, 30 deletions(-)

(limited to 'include/linux')

diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c
index cd72eaa1168f..e70e529ddd91 100644
--- a/arch/mips/alchemy/devboards/db1300.c
+++ b/arch/mips/alchemy/devboards/db1300.c
@@ -732,16 +732,7 @@ static struct platform_device db1300_lcd_dev = {
 /**********************************************************************/
 
 #if IS_ENABLED(CONFIG_TOUCHSCREEN_WM97XX)
-static void db1300_wm97xx_irqen(struct wm97xx *wm, int enable)
-{
-	if (enable)
-		enable_irq(DB1300_AC97_PEN_INT);
-	else
-		disable_irq_nosync(DB1300_AC97_PEN_INT);
-}
-
 static struct wm97xx_mach_ops db1300_wm97xx_ops = {
-	.irq_enable	= db1300_wm97xx_irqen,
 	.irq_gpio	= WM97XX_GPIO_3,
 };
 
diff --git a/drivers/input/touchscreen/mainstone-wm97xx.c b/drivers/input/touchscreen/mainstone-wm97xx.c
index 8f6fe68f1f99..c39f49720fe4 100644
--- a/drivers/input/touchscreen/mainstone-wm97xx.c
+++ b/drivers/input/touchscreen/mainstone-wm97xx.c
@@ -246,21 +246,12 @@ static void wm97xx_acc_shutdown(struct wm97xx *wm)
 	}
 }
 
-static void wm97xx_irq_enable(struct wm97xx *wm, int enable)
-{
-	if (enable)
-		enable_irq(wm->pen_irq);
-	else
-		disable_irq_nosync(wm->pen_irq);
-}
-
 static struct wm97xx_mach_ops mainstone_mach_ops = {
 	.acc_enabled	= 1,
 	.acc_pen_up	= wm97xx_acc_pen_up,
 	.acc_pen_down	= wm97xx_acc_pen_down,
 	.acc_startup	= wm97xx_acc_startup,
 	.acc_shutdown	= wm97xx_acc_shutdown,
-	.irq_enable	= wm97xx_irq_enable,
 	.irq_gpio	= WM97XX_GPIO_2,
 };
 
diff --git a/drivers/input/touchscreen/zylonite-wm97xx.c b/drivers/input/touchscreen/zylonite-wm97xx.c
index ed7eae638713..a70fe4abe520 100644
--- a/drivers/input/touchscreen/zylonite-wm97xx.c
+++ b/drivers/input/touchscreen/zylonite-wm97xx.c
@@ -160,20 +160,11 @@ static int wm97xx_acc_startup(struct wm97xx *wm)
 	return 0;
 }
 
-static void wm97xx_irq_enable(struct wm97xx *wm, int enable)
-{
-	if (enable)
-		enable_irq(wm->pen_irq);
-	else
-		disable_irq_nosync(wm->pen_irq);
-}
-
 static struct wm97xx_mach_ops zylonite_mach_ops = {
 	.acc_enabled	= 1,
 	.acc_pen_up	= wm97xx_acc_pen_up,
 	.acc_pen_down	= wm97xx_acc_pen_down,
 	.acc_startup	= wm97xx_acc_startup,
-	.irq_enable	= wm97xx_irq_enable,
 	.irq_gpio	= WM97XX_GPIO_2,
 };
 
diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h
index 85bd8dd3caea..332d2b0f29b9 100644
--- a/include/linux/wm97xx.h
+++ b/include/linux/wm97xx.h
@@ -254,9 +254,6 @@ struct wm97xx_mach_ops {
 	int (*acc_startup) (struct wm97xx *);
 	void (*acc_shutdown) (struct wm97xx *);
 
-	/* interrupt mask control - required for accelerated operation */
-	void (*irq_enable) (struct wm97xx *, int enable);
-
 	/* GPIO pin used for accelerated operation */
 	int irq_gpio;
 
-- 
cgit v1.2.3


From 6a946f1bd5cc966c9dd377b14efa4cec388101ce Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Sep 2019 14:50:37 +0200
Subject: ARM: pxa: pcmcia: move smemc configuration back to arch

Rather than poking at the smemc registers directly from the
pcmcia/pxa2xx_base driver, move those bits into machine file
to have a cleaner interface.

Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Link: https://lore.kernel.org/lkml/87d0egjzxk.fsf@belgarion.home/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/generic.c   | 29 +++++++++++++++++++++++++++
 drivers/pcmcia/pxa2xx_base.c  | 46 +++++++++++++++----------------------------
 include/linux/soc/pxa/smemc.h | 10 ++++++++++
 3 files changed, 55 insertions(+), 30 deletions(-)
 create mode 100644 include/linux/soc/pxa/smemc.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index f9083c4f0aea..fe1d55d328e5 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -70,6 +70,35 @@ unsigned int get_clk_frequency_khz(int info)
 }
 EXPORT_SYMBOL(get_clk_frequency_khz);
 
+void pxa_smemc_set_pcmcia_timing(int sock, u32 mcmem, u32 mcatt, u32 mcio)
+{
+	__raw_writel(mcmem, MCMEM(sock));
+	__raw_writel(mcatt, MCATT(sock));
+	__raw_writel(mcio, MCIO(sock));
+}
+EXPORT_SYMBOL_GPL(pxa_smemc_set_pcmcia_timing);
+
+void pxa_smemc_set_pcmcia_socket(int nr)
+{
+	switch (nr) {
+	case 0:
+		__raw_writel(0, MECR);
+		break;
+	case 1:
+		/*
+		 * We have at least one socket, so set MECR:CIT
+		 * (Card Is There)
+		 */
+		__raw_writel(MECR_CIT, MECR);
+		break;
+	case 2:
+		/* Set CIT and MECR:NOS (Number Of Sockets) */
+		__raw_writel(MECR_CIT | MECR_NOS, MECR);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(pxa_smemc_set_pcmcia_socket);
+
 /*
  * Intel PXA2xx internal register mapping.
  *
diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c
index 7cd1375d6087..0ea41f1411e5 100644
--- a/drivers/pcmcia/pxa2xx_base.c
+++ b/drivers/pcmcia/pxa2xx_base.c
@@ -24,11 +24,10 @@
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
 #include <linux/soc/pxa/cpu.h>
+#include <linux/soc/pxa/smemc.h>
 
-#include <mach/smemc.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <mach/pxa2xx-regs.h>
 #include <asm/mach-types.h>
 
 #include <pcmcia/ss.h>
@@ -113,7 +112,7 @@ static inline u_int pxa2xx_pcmcia_cmd_time(u_int mem_clk_10khz,
 	return (300000 * (pcmcia_mcxx_asst + 1) / mem_clk_10khz);
 }
 
-static int pxa2xx_pcmcia_set_mcmem( int sock, int speed, int clock )
+static uint32_t pxa2xx_pcmcia_mcmem(int sock, int speed, int clock)
 {
 	uint32_t val;
 
@@ -124,12 +123,10 @@ static int pxa2xx_pcmcia_set_mcmem( int sock, int speed, int clock )
 		| ((pxa2xx_mcxx_hold(speed, clock)
 		& MCXX_HOLD_MASK) << MCXX_HOLD_SHIFT);
 
-	__raw_writel(val, MCMEM(sock));
-
-	return 0;
+	return val;
 }
 
-static int pxa2xx_pcmcia_set_mcio( int sock, int speed, int clock )
+static int pxa2xx_pcmcia_mcio(int sock, int speed, int clock)
 {
 	uint32_t val;
 
@@ -140,12 +137,11 @@ static int pxa2xx_pcmcia_set_mcio( int sock, int speed, int clock )
 		| ((pxa2xx_mcxx_hold(speed, clock)
 		& MCXX_HOLD_MASK) << MCXX_HOLD_SHIFT);
 
-	__raw_writel(val, MCIO(sock));
 
-	return 0;
+	return val;
 }
 
-static int pxa2xx_pcmcia_set_mcatt( int sock, int speed, int clock )
+static int pxa2xx_pcmcia_mcatt(int sock, int speed, int clock)
 {
 	uint32_t val;
 
@@ -156,31 +152,26 @@ static int pxa2xx_pcmcia_set_mcatt( int sock, int speed, int clock )
 		| ((pxa2xx_mcxx_hold(speed, clock)
 		& MCXX_HOLD_MASK) << MCXX_HOLD_SHIFT);
 
-	__raw_writel(val, MCATT(sock));
 
-	return 0;
+	return val;
 }
 
-static int pxa2xx_pcmcia_set_mcxx(struct soc_pcmcia_socket *skt, unsigned int clk)
+static int pxa2xx_pcmcia_set_timing(struct soc_pcmcia_socket *skt)
 {
+	unsigned long clk = clk_get_rate(skt->clk) / 10000;
 	struct soc_pcmcia_timing timing;
 	int sock = skt->nr;
 
 	soc_common_pcmcia_get_timing(skt, &timing);
 
-	pxa2xx_pcmcia_set_mcmem(sock, timing.mem, clk);
-	pxa2xx_pcmcia_set_mcatt(sock, timing.attr, clk);
-	pxa2xx_pcmcia_set_mcio(sock, timing.io, clk);
+	pxa_smemc_set_pcmcia_timing(sock,
+		pxa2xx_pcmcia_mcmem(sock, timing.mem, clk),
+		pxa2xx_pcmcia_mcatt(sock, timing.attr, clk),
+		pxa2xx_pcmcia_mcio(sock, timing.io, clk));
 
 	return 0;
 }
 
-static int pxa2xx_pcmcia_set_timing(struct soc_pcmcia_socket *skt)
-{
-	unsigned long clk = clk_get_rate(skt->clk);
-	return pxa2xx_pcmcia_set_mcxx(skt, clk / 10000);
-}
-
 #ifdef CONFIG_CPU_FREQ
 
 static int
@@ -215,18 +206,13 @@ pxa2xx_pcmcia_frequency_change(struct soc_pcmcia_socket *skt,
 
 void pxa2xx_configure_sockets(struct device *dev, struct pcmcia_low_level *ops)
 {
-	/*
-	 * We have at least one socket, so set MECR:CIT
-	 * (Card Is There)
-	 */
-	uint32_t mecr = MECR_CIT;
+	int nr = 1;
 
-	/* Set MECR:NOS (Number Of Sockets) */
 	if ((ops->first + ops->nr) > 1 ||
 	    machine_is_viper() || machine_is_arcom_zeus())
-		mecr |= MECR_NOS;
+		nr = 2;
 
-	__raw_writel(mecr, MECR);
+	pxa_smemc_set_pcmcia_socket(nr);
 }
 EXPORT_SYMBOL(pxa2xx_configure_sockets);
 
diff --git a/include/linux/soc/pxa/smemc.h b/include/linux/soc/pxa/smemc.h
new file mode 100644
index 000000000000..cbf1a2d8af29
--- /dev/null
+++ b/include/linux/soc/pxa/smemc.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __PXA_REGS_H
+#define __PXA_REGS_H
+
+#include <linux/types.h>
+
+void pxa_smemc_set_pcmcia_timing(int sock, u32 mcmem, u32 mcatt, u32 mcio);
+void pxa_smemc_set_pcmcia_socket(int nr);
+
+#endif
-- 
cgit v1.2.3


From 5c6603e741921c75f67a724e798642ed50a6328e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Sep 2019 15:34:10 +0200
Subject: cpufreq: pxa3: move clk register access to clk driver

The driver needs some low-level register access for setting
the core and bus frequencies. These registers are owned
by the clk driver, so move the low-level access into that
driver with a slightly higher-level interface and avoid
any machine header file dependencies.

Cc: Michael Turquette <mturquette@baylibre.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: linux-clk@vger.kernel.org
Cc: linux-pm@vger.kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/generic.h              |  1 -
 arch/arm/mach-pxa/include/mach/generic.h |  5 ---
 arch/arm/mach-pxa/pxa3xx.c               |  1 +
 drivers/clk/pxa/clk-pxa3xx.c             | 16 ++++++++
 drivers/cpufreq/pxa2xx-cpufreq.c         |  3 --
 drivers/cpufreq/pxa3xx-cpufreq.c         | 64 ++++++++++++++++++--------------
 include/linux/clk/pxa.h                  |  9 +++++
 7 files changed, 62 insertions(+), 37 deletions(-)
 delete mode 100644 arch/arm/mach-pxa/include/mach/generic.h
 create mode 100644 include/linux/clk/pxa.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/generic.h b/arch/arm/mach-pxa/generic.h
index 2f706ef97357..487eadb0fc2a 100644
--- a/arch/arm/mach-pxa/generic.h
+++ b/arch/arm/mach-pxa/generic.h
@@ -7,7 +7,6 @@
  */
 
 #include <linux/reboot.h>
-#include <mach/generic.h>
 
 struct irq_data;
 
diff --git a/arch/arm/mach-pxa/include/mach/generic.h b/arch/arm/mach-pxa/include/mach/generic.h
deleted file mode 100644
index 613f6a299d0d..000000000000
--- a/arch/arm/mach-pxa/include/mach/generic.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_PXA3xx
-extern unsigned	pxa3xx_get_clk_frequency_khz(int);
-#else
-#define pxa3xx_get_clk_frequency_khz(x)		(0)
-#endif
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 7881888107c7..f4657f4edb3b 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -25,6 +25,7 @@
 #include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/mmp_dma.h>
 #include <linux/soc/pxa/cpu.h>
+#include <linux/clk/pxa.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 027b78183565..60a0db4f3790 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/soc/pxa/cpu.h>
 #include <mach/smemc.h>
+#include <linux/clk/pxa.h>
 #include <mach/pxa3xx-regs.h>
 
 #include <dt-bindings/clock/pxa-clock.h>
@@ -79,6 +80,21 @@ unsigned int pxa3xx_get_clk_frequency_khz(int info)
 	return (unsigned int)clks[0] / KHz;
 }
 
+void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask)
+{
+	u32 accr = ACCR;
+
+	accr &= ~disable;
+	accr |= enable;
+
+	ACCR = accr;
+	if (xclkcfg)
+		__asm__("mcr p14, 0, %0, c6, c0, 0\n" : : "r"(xclkcfg));
+
+	while ((ACSR & mask) != (accr & mask))
+		cpu_relax();
+}
+
 static unsigned long clk_pxa3xx_ac97_get_rate(struct clk_hw *hw,
 					     unsigned long parent_rate)
 {
diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c
index e74d36d6f78d..ed1ae061a687 100644
--- a/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -27,9 +27,6 @@
 #include <linux/soc/pxa/cpu.h>
 #include <linux/io.h>
 
-#include <mach/pxa2xx-regs.h>
-#include <mach/smemc.h>
-
 #ifdef DEBUG
 static unsigned int freq_debug;
 module_param(freq_debug, uint, 0);
diff --git a/drivers/cpufreq/pxa3xx-cpufreq.c b/drivers/cpufreq/pxa3xx-cpufreq.c
index d3b398b4aa6a..4afa48d172db 100644
--- a/drivers/cpufreq/pxa3xx-cpufreq.c
+++ b/drivers/cpufreq/pxa3xx-cpufreq.c
@@ -9,12 +9,10 @@
 #include <linux/init.h>
 #include <linux/cpufreq.h>
 #include <linux/soc/pxa/cpu.h>
+#include <linux/clk/pxa.h>
 #include <linux/slab.h>
 #include <linux/io.h>
 
-#include <mach/generic.h>
-#include <mach/pxa3xx-regs.h>
-
 #define HSS_104M	(0)
 #define HSS_156M	(1)
 #define HSS_208M	(2)
@@ -35,6 +33,28 @@
 #define DMCFS_26M	(0)
 #define DMCFS_260M	(3)
 
+#define ACCR_XPDIS		(1 << 31)	/* Core PLL Output Disable */
+#define ACCR_SPDIS		(1 << 30)	/* System PLL Output Disable */
+#define ACCR_D0CS		(1 << 26)	/* D0 Mode Clock Select */
+#define ACCR_PCCE		(1 << 11)	/* Power Mode Change Clock Enable */
+#define ACCR_DDR_D0CS		(1 << 7)	/* DDR SDRAM clock frequency in D0CS (PXA31x only) */
+
+#define ACCR_SMCFS_MASK		(0x7 << 23)	/* Static Memory Controller Frequency Select */
+#define ACCR_SFLFS_MASK		(0x3 << 18)	/* Frequency Select for Internal Memory Controller */
+#define ACCR_XSPCLK_MASK	(0x3 << 16)	/* Core Frequency during Frequency Change */
+#define ACCR_HSS_MASK		(0x3 << 14)	/* System Bus-Clock Frequency Select */
+#define ACCR_DMCFS_MASK		(0x3 << 12)	/* Dynamic Memory Controller Clock Frequency Select */
+#define ACCR_XN_MASK		(0x7 << 8)	/* Core PLL Turbo-Mode-to-Run-Mode Ratio */
+#define ACCR_XL_MASK		(0x1f)		/* Core PLL Run-Mode-to-Oscillator Ratio */
+
+#define ACCR_SMCFS(x)		(((x) & 0x7) << 23)
+#define ACCR_SFLFS(x)		(((x) & 0x3) << 18)
+#define ACCR_XSPCLK(x)		(((x) & 0x3) << 16)
+#define ACCR_HSS(x)		(((x) & 0x3) << 14)
+#define ACCR_DMCFS(x)		(((x) & 0x3) << 12)
+#define ACCR_XN(x)		(((x) & 0x7) << 8)
+#define ACCR_XL(x)		((x) & 0x1f)
+
 struct pxa3xx_freq_info {
 	unsigned int cpufreq_mhz;
 	unsigned int core_xl : 5;
@@ -112,41 +132,29 @@ static int setup_freqs_table(struct cpufreq_policy *policy,
 
 static void __update_core_freq(struct pxa3xx_freq_info *info)
 {
-	uint32_t mask = ACCR_XN_MASK | ACCR_XL_MASK;
-	uint32_t accr = ACCR;
-	uint32_t xclkcfg;
-
-	accr &= ~(ACCR_XN_MASK | ACCR_XL_MASK | ACCR_XSPCLK_MASK);
-	accr |= ACCR_XN(info->core_xn) | ACCR_XL(info->core_xl);
+	u32 mask, disable, enable, xclkcfg;
 
+	mask	= ACCR_XN_MASK | ACCR_XL_MASK;
+	disable = mask | ACCR_XSPCLK_MASK;
+	enable  = ACCR_XN(info->core_xn) | ACCR_XL(info->core_xl);
 	/* No clock until core PLL is re-locked */
-	accr |= ACCR_XSPCLK(XSPCLK_NONE);
-
+	enable |= ACCR_XSPCLK(XSPCLK_NONE);
 	xclkcfg = (info->core_xn == 2) ? 0x3 : 0x2;	/* turbo bit */
 
-	ACCR = accr;
-	__asm__("mcr p14, 0, %0, c6, c0, 0\n" : : "r"(xclkcfg));
-
-	while ((ACSR & mask) != (accr & mask))
-		cpu_relax();
+	pxa3xx_clk_update_accr(disable, enable, xclkcfg, mask);
 }
 
 static void __update_bus_freq(struct pxa3xx_freq_info *info)
 {
-	uint32_t mask;
-	uint32_t accr = ACCR;
-
-	mask = ACCR_SMCFS_MASK | ACCR_SFLFS_MASK | ACCR_HSS_MASK |
-		ACCR_DMCFS_MASK;
-
-	accr &= ~mask;
-	accr |= ACCR_SMCFS(info->smcfs) | ACCR_SFLFS(info->sflfs) |
-		ACCR_HSS(info->hss) | ACCR_DMCFS(info->dmcfs);
+	u32 mask, disable, enable;
 
-	ACCR = accr;
+	mask	= ACCR_SMCFS_MASK | ACCR_SFLFS_MASK | ACCR_HSS_MASK |
+		  ACCR_DMCFS_MASK;
+	disable = mask;
+	enable	= ACCR_SMCFS(info->smcfs) | ACCR_SFLFS(info->sflfs) |
+		  ACCR_HSS(info->hss) | ACCR_DMCFS(info->dmcfs);
 
-	while ((ACSR & mask) != (accr & mask))
-		cpu_relax();
+	pxa3xx_clk_update_accr(disable, enable, 0, mask);
 }
 
 static unsigned int pxa3xx_cpufreq_get(unsigned int cpu)
diff --git a/include/linux/clk/pxa.h b/include/linux/clk/pxa.h
new file mode 100644
index 000000000000..e5516c608c99
--- /dev/null
+++ b/include/linux/clk/pxa.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifdef CONFIG_PXA3xx
+extern unsigned	pxa3xx_get_clk_frequency_khz(int);
+extern void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask);
+#else
+#define pxa3xx_get_clk_frequency_khz(x)		(0)
+#define pxa3xx_clk_update_accr(disable, enable, xclkcfg, mask) do { } while (0)
+#endif
-- 
cgit v1.2.3


From fd13f8117f7a2d4054bf420ec1428e918a24a480 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Sep 2019 17:42:52 +0200
Subject: ARM: pxa: move smemc register access from clk to platform

The get_sdram_rows() and get_memclkdiv() helpers need smemc
register that are separate from the clk registers, move
them out of the clk driver, and use an extern declaration
instead.

Cc: Michael Turquette <mturquette@baylibre.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: linux-clk@vger.kernel.org
Link: https://lore.kernel.org/lkml/87pnielzo4.fsf@belgarion.home/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/generic.c   |  6 ++++++
 arch/arm/mach-pxa/pxa2xx.c    | 27 +++++++++++++++++++++++++++
 arch/arm/mach-pxa/pxa3xx.c    |  4 ++++
 arch/arm/mach-pxa/smemc.c     |  9 +++++++++
 drivers/clk/pxa/clk-pxa.c     |  4 +++-
 drivers/clk/pxa/clk-pxa.h     |  5 +++--
 drivers/clk/pxa/clk-pxa25x.c  | 30 +++---------------------------
 drivers/clk/pxa/clk-pxa27x.c  | 31 +++----------------------------
 drivers/clk/pxa/clk-pxa3xx.c  |  8 +++-----
 include/linux/soc/pxa/smemc.h |  3 +++
 10 files changed, 64 insertions(+), 63 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index 2c2c82fcf9cb..971d25e95a1a 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/soc/pxa/cpu.h>
+#include <linux/soc/pxa/smemc.h>
 
 #include <asm/mach/map.h>
 #include <asm/mach-types.h>
@@ -84,6 +85,11 @@ void pxa_smemc_set_pcmcia_socket(int nr)
 }
 EXPORT_SYMBOL_GPL(pxa_smemc_set_pcmcia_socket);
 
+void __iomem *pxa_smemc_get_mdrefr(void)
+{
+	return MDREFR;
+}
+
 /*
  * Intel PXA2xx internal register mapping.
  *
diff --git a/arch/arm/mach-pxa/pxa2xx.c b/arch/arm/mach-pxa/pxa2xx.c
index ac72acb43e26..e06699fd8a5d 100644
--- a/arch/arm/mach-pxa/pxa2xx.c
+++ b/arch/arm/mach-pxa/pxa2xx.c
@@ -14,7 +14,10 @@
 
 #include <mach/pxa2xx-regs.h>
 #include "mfp-pxa25x.h"
+#include "generic.h"
 #include <mach/reset.h>
+#include <mach/smemc.h>
+#include <linux/soc/pxa/smemc.h>
 #include <linux/platform_data/irda-pxaficp.h>
 
 void pxa2xx_clear_reset_status(unsigned int mask)
@@ -50,3 +53,27 @@ void pxa2xx_transceiver_mode(struct device *dev, int mode)
 		BUG();
 }
 EXPORT_SYMBOL_GPL(pxa2xx_transceiver_mode);
+
+#define MDCNFG_DRAC2(mdcnfg)	(((mdcnfg) >> 21) & 0x3)
+#define MDCNFG_DRAC0(mdcnfg)	(((mdcnfg) >> 5) & 0x3)
+
+int pxa2xx_smemc_get_sdram_rows(void)
+{
+	static int sdram_rows;
+	unsigned int drac2 = 0, drac0 = 0;
+	u32 mdcnfg;
+
+	if (sdram_rows)
+		return sdram_rows;
+
+	mdcnfg = readl_relaxed(MDCNFG);
+
+	if (mdcnfg & (MDCNFG_DE2 | MDCNFG_DE3))
+		drac2 = MDCNFG_DRAC2(mdcnfg);
+
+	if (mdcnfg & (MDCNFG_DE0 | MDCNFG_DE1))
+		drac0 = MDCNFG_DRAC0(mdcnfg);
+
+	sdram_rows = 1 << (11 + max(drac0, drac2));
+	return sdram_rows;
+}
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index f4657f4edb3b..d486efb79dcd 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -52,6 +52,10 @@ extern void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int));
 #define NDCR_ND_ARB_EN		(1 << 12)
 #define NDCR_ND_ARB_CNTL	(1 << 19)
 
+#define CKEN_BOOT  		11      /* < Boot rom clock enable */
+#define CKEN_TPM   		19      /* < TPM clock enable */
+#define CKEN_HSIO2 		41      /* < HSIO2 clock enable */
+
 #ifdef CONFIG_PM
 
 #define ISRAM_START	0x5c000000
diff --git a/arch/arm/mach-pxa/smemc.c b/arch/arm/mach-pxa/smemc.c
index 47b99549d616..0bbc91b9b05e 100644
--- a/arch/arm/mach-pxa/smemc.c
+++ b/arch/arm/mach-pxa/smemc.c
@@ -11,6 +11,7 @@
 #include <linux/soc/pxa/cpu.h>
 
 #include <mach/smemc.h>
+#include <linux/soc/pxa/smemc.h>
 
 #ifdef CONFIG_PM
 static unsigned long msc[2];
@@ -70,3 +71,11 @@ static int __init smemc_init(void)
 }
 subsys_initcall(smemc_init);
 #endif
+
+static const unsigned int df_clkdiv[4] = { 1, 2, 4, 1 };
+unsigned int pxa3xx_smemc_get_memclkdiv(void)
+{
+	unsigned long memclkcfg = __raw_readl(MEMCLKCFG);
+
+	return	df_clkdiv[(memclkcfg >> 16) & 0x3];
+}
diff --git a/drivers/clk/pxa/clk-pxa.c b/drivers/clk/pxa/clk-pxa.c
index cfc79f942b07..831180360069 100644
--- a/drivers/clk/pxa/clk-pxa.c
+++ b/drivers/clk/pxa/clk-pxa.c
@@ -11,6 +11,7 @@
 #include <linux/clkdev.h>
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/soc/pxa/smemc.h>
 
 #include <dt-bindings/clock/pxa-clock.h>
 #include "clk-pxa.h"
@@ -150,12 +151,13 @@ void pxa2xx_core_turbo_switch(bool on)
 }
 
 void pxa2xx_cpll_change(struct pxa2xx_freq *freq,
-			u32 (*mdrefr_dri)(unsigned int), void __iomem *mdrefr,
+			u32 (*mdrefr_dri)(unsigned int),
 			void __iomem *cccr)
 {
 	unsigned int clkcfg = freq->clkcfg;
 	unsigned int unused, preset_mdrefr, postset_mdrefr;
 	unsigned long flags;
+	void __iomem *mdrefr = pxa_smemc_get_mdrefr();
 
 	local_irq_save(flags);
 
diff --git a/drivers/clk/pxa/clk-pxa.h b/drivers/clk/pxa/clk-pxa.h
index 5768e0f728ce..bd688fdb7ecc 100644
--- a/drivers/clk/pxa/clk-pxa.h
+++ b/drivers/clk/pxa/clk-pxa.h
@@ -146,12 +146,13 @@ static inline int dummy_clk_set_parent(struct clk_hw *hw, u8 index)
 
 extern void clkdev_pxa_register(int ckid, const char *con_id,
 				const char *dev_id, struct clk *clk);
-extern int clk_pxa_cken_init(const struct desc_clk_cken *clks, int nb_clks);
+extern int clk_pxa_cken_init(const struct desc_clk_cken *clks,
+			     int nb_clks);
 void clk_pxa_dt_common_init(struct device_node *np);
 
 void pxa2xx_core_turbo_switch(bool on);
 void pxa2xx_cpll_change(struct pxa2xx_freq *freq,
-			u32 (*mdrefr_dri)(unsigned int), void __iomem *mdrefr,
+			u32 (*mdrefr_dri)(unsigned int),
 			void __iomem *cccr);
 int pxa2xx_determine_rate(struct clk_rate_request *req,
 			  struct pxa2xx_freq *freqs,  int nb_freqs);
diff --git a/drivers/clk/pxa/clk-pxa25x.c b/drivers/clk/pxa/clk-pxa25x.c
index d0f957996acb..0837d59d7a67 100644
--- a/drivers/clk/pxa/clk-pxa25x.c
+++ b/drivers/clk/pxa/clk-pxa25x.c
@@ -15,7 +15,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <mach/pxa2xx-regs.h>
-#include <mach/smemc.h>
+#include <linux/soc/pxa/smemc.h>
 
 #include <dt-bindings/clock/pxa-clock.h>
 #include "clk-pxa.h"
@@ -33,9 +33,6 @@ enum {
 	 ((T) ? CLKCFG_TURBO : 0))
 #define PXA25x_CCCR(N2, M, L) (N2 << 7 | M << 5 | L)
 
-#define MDCNFG_DRAC2(mdcnfg)	(((mdcnfg) >> 21) & 0x3)
-#define MDCNFG_DRAC0(mdcnfg)	(((mdcnfg) >> 5) & 0x3)
-
 /* Define the refresh period in mSec for the SDRAM and the number of rows */
 #define SDRAM_TREF	64	/* standard 64ms SDRAM */
 
@@ -57,30 +54,9 @@ static const char * const get_freq_khz[] = {
 	"core", "run", "cpll", "memory"
 };
 
-static int get_sdram_rows(void)
-{
-	static int sdram_rows;
-	unsigned int drac2 = 0, drac0 = 0;
-	u32 mdcnfg;
-
-	if (sdram_rows)
-		return sdram_rows;
-
-	mdcnfg = readl_relaxed(MDCNFG);
-
-	if (mdcnfg & (MDCNFG_DE2 | MDCNFG_DE3))
-		drac2 = MDCNFG_DRAC2(mdcnfg);
-
-	if (mdcnfg & (MDCNFG_DE0 | MDCNFG_DE1))
-		drac0 = MDCNFG_DRAC0(mdcnfg);
-
-	sdram_rows = 1 << (11 + max(drac0, drac2));
-	return sdram_rows;
-}
-
 static u32 mdrefr_dri(unsigned int freq_khz)
 {
-	u32 interval = freq_khz * SDRAM_TREF / get_sdram_rows();
+	u32 interval = freq_khz * SDRAM_TREF / pxa2xx_smemc_get_sdram_rows();
 
 	return interval / 32;
 }
@@ -268,7 +244,7 @@ static int clk_pxa25x_cpll_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (i >= ARRAY_SIZE(pxa25x_freqs))
 		return -EINVAL;
 
-	pxa2xx_cpll_change(&pxa25x_freqs[i], mdrefr_dri, MDREFR, CCCR);
+	pxa2xx_cpll_change(&pxa25x_freqs[i], mdrefr_dri, CCCR);
 
 	return 0;
 }
diff --git a/drivers/clk/pxa/clk-pxa27x.c b/drivers/clk/pxa/clk-pxa27x.c
index 7b123105b5de..ba3aa63f2447 100644
--- a/drivers/clk/pxa/clk-pxa27x.c
+++ b/drivers/clk/pxa/clk-pxa27x.c
@@ -12,8 +12,7 @@
 #include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/of.h>
-
-#include <mach/smemc.h>
+#include <linux/soc/pxa/smemc.h>
 
 #include <dt-bindings/clock/pxa-clock.h>
 #include "clk-pxa.h"
@@ -50,9 +49,6 @@ enum {
 	 ((T)  ? CLKCFG_TURBO : 0))
 #define PXA27x_CCCR(A, L, N2) (A << 25 | N2 << 7 | L)
 
-#define MDCNFG_DRAC2(mdcnfg)	(((mdcnfg) >> 21) & 0x3)
-#define MDCNFG_DRAC0(mdcnfg)	(((mdcnfg) >> 5) & 0x3)
-
 /* Define the refresh period in mSec for the SDRAM and the number of rows */
 #define SDRAM_TREF	64	/* standard 64ms SDRAM */
 
@@ -61,30 +57,9 @@ static const char * const get_freq_khz[] = {
 	"system_bus"
 };
 
-static int get_sdram_rows(void)
-{
-	static int sdram_rows;
-	unsigned int drac2 = 0, drac0 = 0;
-	u32 mdcnfg;
-
-	if (sdram_rows)
-		return sdram_rows;
-
-	mdcnfg = readl_relaxed(MDCNFG);
-
-	if (mdcnfg & (MDCNFG_DE2 | MDCNFG_DE3))
-		drac2 = MDCNFG_DRAC2(mdcnfg);
-
-	if (mdcnfg & (MDCNFG_DE0 | MDCNFG_DE1))
-		drac0 = MDCNFG_DRAC0(mdcnfg);
-
-	sdram_rows = 1 << (11 + max(drac0, drac2));
-	return sdram_rows;
-}
-
 static u32 mdrefr_dri(unsigned int freq_khz)
 {
-	u32 interval = freq_khz * SDRAM_TREF / get_sdram_rows();
+	u32 interval = freq_khz * SDRAM_TREF / pxa2xx_smemc_get_sdram_rows();
 
 	return (interval - 31) / 32;
 }
@@ -260,7 +235,7 @@ static int clk_pxa27x_cpll_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (i >= ARRAY_SIZE(pxa27x_freqs))
 		return -EINVAL;
 
-	pxa2xx_cpll_change(&pxa27x_freqs[i], mdrefr_dri, MDREFR, CCCR);
+	pxa2xx_cpll_change(&pxa27x_freqs[i], mdrefr_dri, CCCR);
 	return 0;
 }
 
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 60a0db4f3790..08594fc899e2 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -15,7 +15,7 @@
 #include <linux/clkdev.h>
 #include <linux/of.h>
 #include <linux/soc/pxa/cpu.h>
-#include <mach/smemc.h>
+#include <linux/soc/pxa/smemc.h>
 #include <linux/clk/pxa.h>
 #include <mach/pxa3xx-regs.h>
 
@@ -41,8 +41,6 @@ static unsigned char hss_mult[4] = { 8, 12, 16, 24 };
 
 /* crystal frequency to static memory controller multiplier (SMCFS) */
 static unsigned int smcfs_mult[8] = { 6, 0, 8, 0, 0, 16, };
-static unsigned int df_clkdiv[4] = { 1, 2, 4, 1 };
-
 static const char * const get_freq_khz[] = {
 	"core", "ring_osc_60mhz", "run", "cpll", "system_bus"
 };
@@ -118,10 +116,10 @@ static unsigned long clk_pxa3xx_smemc_get_rate(struct clk_hw *hw,
 					      unsigned long parent_rate)
 {
 	unsigned long acsr = ACSR;
-	unsigned long memclkcfg = __raw_readl(MEMCLKCFG);
 
 	return (parent_rate / 48)  * smcfs_mult[(acsr >> 23) & 0x7] /
-		df_clkdiv[(memclkcfg >> 16) & 0x3];
+		pxa3xx_smemc_get_memclkdiv();
+
 }
 PARENTS(clk_pxa3xx_smemc) = { "spll_624mhz" };
 RATE_RO_OPS(clk_pxa3xx_smemc, "smemc");
diff --git a/include/linux/soc/pxa/smemc.h b/include/linux/soc/pxa/smemc.h
index cbf1a2d8af29..f1ffea236c15 100644
--- a/include/linux/soc/pxa/smemc.h
+++ b/include/linux/soc/pxa/smemc.h
@@ -6,5 +6,8 @@
 
 void pxa_smemc_set_pcmcia_timing(int sock, u32 mcmem, u32 mcatt, u32 mcio);
 void pxa_smemc_set_pcmcia_socket(int nr);
+int pxa2xx_smemc_get_sdram_rows(void);
+unsigned int pxa3xx_smemc_get_memclkdiv(void);
+void __iomem *pxa_smemc_get_mdrefr(void);
 
 #endif
-- 
cgit v1.2.3


From 3c816d950a494ae6e16b1fa017af29bc53cb7791 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Sep 2019 20:54:17 +0200
Subject: ARM: pxa: move clk register definitions to driver

The clock register definitions are now used (almost) exclusively in the
clk driver, and that relies on no other mach/*.h header files any more.

Remove the dependency on mach/pxa*-regs.h by addressing the registers
as offsets from a void __iomem * pointer, which is either passed from
a board file, or (for the moment) ioremapped at boot time from a hardcoded
address in case of DT (this should be moved into the DT of course).

Cc: linux-clk@vger.kernel.org
Acked-by: Stephen Boyd <sboyd@kernel.org>
Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/generic.c                  |   7 +-
 arch/arm/mach-pxa/generic.h                  |   3 -
 arch/arm/mach-pxa/include/mach/pxa2xx-regs.h |  45 ----------
 arch/arm/mach-pxa/include/mach/pxa3xx-regs.h |  69 ---------------
 arch/arm/mach-pxa/sleep.S                    |   4 +-
 drivers/clk/pxa/clk-pxa.c                    |   4 +-
 drivers/clk/pxa/clk-pxa.h                    |   6 +-
 drivers/clk/pxa/clk-pxa25x.c                 |  18 ++--
 drivers/clk/pxa/clk-pxa27x.c                 |  39 +++++----
 drivers/clk/pxa/clk-pxa2xx.h                 |  58 +++++++++++++
 drivers/clk/pxa/clk-pxa3xx.c                 | 120 ++++++++++++++++++++++-----
 include/linux/clk/pxa.h                      |   7 ++
 12 files changed, 210 insertions(+), 170 deletions(-)
 create mode 100644 drivers/clk/pxa/clk-pxa2xx.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index 971d25e95a1a..91ea063dc54d 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/soc/pxa/cpu.h>
 #include <linux/soc/pxa/smemc.h>
+#include <linux/clk/pxa.h>
 
 #include <asm/mach/map.h>
 #include <asm/mach-types.h>
@@ -48,11 +49,11 @@ void clear_reset_status(unsigned int mask)
 void __init pxa_timer_init(void)
 {
 	if (cpu_is_pxa25x())
-		pxa25x_clocks_init();
+		pxa25x_clocks_init(io_p2v(0x41300000));
 	if (cpu_is_pxa27x())
-		pxa27x_clocks_init();
+		pxa27x_clocks_init(io_p2v(0x41300000));
 	if (cpu_is_pxa3xx())
-		pxa3xx_clocks_init();
+		pxa3xx_clocks_init(io_p2v(0x41340000), io_p2v(0x41350000));
 	pxa_timer_nodt_init(IRQ_OST0, io_p2v(0x40a00000));
 }
 
diff --git a/arch/arm/mach-pxa/generic.h b/arch/arm/mach-pxa/generic.h
index 487eadb0fc2a..7bb1499de4c5 100644
--- a/arch/arm/mach-pxa/generic.h
+++ b/arch/arm/mach-pxa/generic.h
@@ -22,19 +22,16 @@ extern void pxa_timer_init(void);
 #define ARRAY_AND_SIZE(x)	(x), ARRAY_SIZE(x)
 
 #define pxa25x_handle_irq icip_handle_irq
-extern int __init pxa25x_clocks_init(void);
 extern void __init pxa25x_init_irq(void);
 extern void __init pxa25x_map_io(void);
 extern void __init pxa26x_init_irq(void);
 
 #define pxa27x_handle_irq ichp_handle_irq
-extern int __init pxa27x_clocks_init(void);
 extern unsigned	pxa27x_get_clk_frequency_khz(int);
 extern void __init pxa27x_init_irq(void);
 extern void __init pxa27x_map_io(void);
 
 #define pxa3xx_handle_irq ichp_handle_irq
-extern int __init pxa3xx_clocks_init(void);
 extern void __init pxa3xx_init_irq(void);
 extern void __init pxa3xx_map_io(void);
 
diff --git a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
index f68b573ab4a0..0b7eaf6b5813 100644
--- a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
+++ b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
@@ -136,51 +136,6 @@
 #define CKEN		io_p2v(0x41300004)  /* Clock Enable Register */
 #define OSCC		io_p2v(0x41300008)  /* Oscillator Configuration Register */
 
-#define CCCR_N_MASK	0x0380	/* Run Mode Frequency to Turbo Mode Frequency Multiplier */
-#define CCCR_M_MASK	0x0060	/* Memory Frequency to Run Mode Frequency Multiplier */
-#define CCCR_L_MASK	0x001f	/* Crystal Frequency to Memory Frequency Multiplier */
-
-#define CCCR_CPDIS_BIT	(31)
-#define CCCR_PPDIS_BIT	(30)
-#define CCCR_LCD_26_BIT	(27)
-#define CCCR_A_BIT	(25)
-
-#define CCSR_N2_MASK	CCCR_N_MASK
-#define CCSR_M_MASK	CCCR_M_MASK
-#define CCSR_L_MASK	CCCR_L_MASK
-#define CCSR_N2_SHIFT	7
-
-#define CKEN_AC97CONF   (31)    /* AC97 Controller Configuration */
-#define CKEN_CAMERA	(24)	/* Camera Interface Clock Enable */
-#define CKEN_SSP1	(23)	/* SSP1 Unit Clock Enable */
-#define CKEN_MEMC	(22)	/* Memory Controller Clock Enable */
-#define CKEN_MEMSTK	(21)	/* Memory Stick Host Controller */
-#define CKEN_IM		(20)	/* Internal Memory Clock Enable */
-#define CKEN_KEYPAD	(19)	/* Keypad Interface Clock Enable */
-#define CKEN_USIM	(18)	/* USIM Unit Clock Enable */
-#define CKEN_MSL	(17)	/* MSL Unit Clock Enable */
-#define CKEN_LCD	(16)	/* LCD Unit Clock Enable */
-#define CKEN_PWRI2C	(15)	/* PWR I2C Unit Clock Enable */
-#define CKEN_I2C	(14)	/* I2C Unit Clock Enable */
-#define CKEN_FICP	(13)	/* FICP Unit Clock Enable */
-#define CKEN_MMC	(12)	/* MMC Unit Clock Enable */
-#define CKEN_USB	(11)	/* USB Unit Clock Enable */
-#define CKEN_ASSP	(10)	/* ASSP (SSP3) Clock Enable */
-#define CKEN_USBHOST	(10)	/* USB Host Unit Clock Enable */
-#define CKEN_OSTIMER	(9)	/* OS Timer Unit Clock Enable */
-#define CKEN_NSSP	(9)	/* NSSP (SSP2) Clock Enable */
-#define CKEN_I2S	(8)	/* I2S Unit Clock Enable */
-#define CKEN_BTUART	(7)	/* BTUART Unit Clock Enable */
-#define CKEN_FFUART	(6)	/* FFUART Unit Clock Enable */
-#define CKEN_STUART	(5)	/* STUART Unit Clock Enable */
-#define CKEN_HWUART	(4)	/* HWUART Unit Clock Enable */
-#define CKEN_SSP3	(4)	/* SSP3 Unit Clock Enable */
-#define CKEN_SSP	(3)	/* SSP Unit Clock Enable */
-#define CKEN_SSP2	(3)	/* SSP2 Unit Clock Enable */
-#define CKEN_AC97	(2)	/* AC97 Unit Clock Enable */
-#define CKEN_PWM1	(1)	/* PWM1 Clock Enable */
-#define CKEN_PWM0	(0)	/* PWM0 Clock Enable */
-
 #define OSCC_OON	(1 << 1)	/* 32.768kHz OON (write-once only bit) */
 #define OSCC_OOK	(1 << 0)	/* 32.768kHz OOK (read-only bit) */
 
diff --git a/arch/arm/mach-pxa/include/mach/pxa3xx-regs.h b/arch/arm/mach-pxa/include/mach/pxa3xx-regs.h
index 8eb1ba533e1c..4b11cf81a9e6 100644
--- a/arch/arm/mach-pxa/include/mach/pxa3xx-regs.h
+++ b/arch/arm/mach-pxa/include/mach/pxa3xx-regs.h
@@ -131,73 +131,4 @@
 #define CKENC		__REG(0x41340024)	/* C Clock Enable Register */
 #define AC97_DIV	__REG(0x41340014)	/* AC97 clock divisor value register */
 
-#define ACCR_XPDIS		(1 << 31)	/* Core PLL Output Disable */
-#define ACCR_SPDIS		(1 << 30)	/* System PLL Output Disable */
-#define ACCR_D0CS		(1 << 26)	/* D0 Mode Clock Select */
-#define ACCR_PCCE		(1 << 11)	/* Power Mode Change Clock Enable */
-#define ACCR_DDR_D0CS		(1 << 7)	/* DDR SDRAM clock frequency in D0CS (PXA31x only) */
-
-#define ACCR_SMCFS_MASK		(0x7 << 23)	/* Static Memory Controller Frequency Select */
-#define ACCR_SFLFS_MASK		(0x3 << 18)	/* Frequency Select for Internal Memory Controller */
-#define ACCR_XSPCLK_MASK	(0x3 << 16)	/* Core Frequency during Frequency Change */
-#define ACCR_HSS_MASK		(0x3 << 14)	/* System Bus-Clock Frequency Select */
-#define ACCR_DMCFS_MASK		(0x3 << 12)	/* Dynamic Memory Controller Clock Frequency Select */
-#define ACCR_XN_MASK		(0x7 << 8)	/* Core PLL Turbo-Mode-to-Run-Mode Ratio */
-#define ACCR_XL_MASK		(0x1f)		/* Core PLL Run-Mode-to-Oscillator Ratio */
-
-#define ACCR_SMCFS(x)		(((x) & 0x7) << 23)
-#define ACCR_SFLFS(x)		(((x) & 0x3) << 18)
-#define ACCR_XSPCLK(x)		(((x) & 0x3) << 16)
-#define ACCR_HSS(x)		(((x) & 0x3) << 14)
-#define ACCR_DMCFS(x)		(((x) & 0x3) << 12)
-#define ACCR_XN(x)		(((x) & 0x7) << 8)
-#define ACCR_XL(x)		((x) & 0x1f)
-
-/*
- * Clock Enable Bit
- */
-#define CKEN_LCD	1	/* < LCD Clock Enable */
-#define CKEN_USBH	2	/* < USB host clock enable */
-#define CKEN_CAMERA	3	/* < Camera interface clock enable */
-#define CKEN_NAND	4	/* < NAND Flash Controller Clock Enable */
-#define CKEN_USB2	6	/* < USB 2.0 client clock enable. */
-#define CKEN_DMC	8	/* < Dynamic Memory Controller clock enable */
-#define CKEN_SMC	9	/* < Static Memory Controller clock enable */
-#define CKEN_ISC	10	/* < Internal SRAM Controller clock enable */
-#define CKEN_BOOT	11	/* < Boot rom clock enable */
-#define CKEN_MMC1	12	/* < MMC1 Clock enable */
-#define CKEN_MMC2	13	/* < MMC2 clock enable */
-#define CKEN_KEYPAD	14	/* < Keypand Controller Clock Enable */
-#define CKEN_CIR	15	/* < Consumer IR Clock Enable */
-#define CKEN_USIM0	17	/* < USIM[0] Clock Enable */
-#define CKEN_USIM1	18	/* < USIM[1] Clock Enable */
-#define CKEN_TPM	19	/* < TPM clock enable */
-#define CKEN_UDC	20	/* < UDC clock enable */
-#define CKEN_BTUART	21	/* < BTUART clock enable */
-#define CKEN_FFUART	22	/* < FFUART clock enable */
-#define CKEN_STUART	23	/* < STUART clock enable */
-#define CKEN_AC97	24	/* < AC97 clock enable */
-#define CKEN_TOUCH	25	/* < Touch screen Interface Clock Enable */
-#define CKEN_SSP1	26	/* < SSP1 clock enable */
-#define CKEN_SSP2	27	/* < SSP2 clock enable */
-#define CKEN_SSP3	28	/* < SSP3 clock enable */
-#define CKEN_SSP4	29	/* < SSP4 clock enable */
-#define CKEN_MSL0	30	/* < MSL0 clock enable */
-#define CKEN_PWM0	32	/* < PWM[0] clock enable */
-#define CKEN_PWM1	33	/* < PWM[1] clock enable */
-#define CKEN_I2C	36	/* < I2C clock enable */
-#define CKEN_INTC	38	/* < Interrupt controller clock enable */
-#define CKEN_GPIO	39	/* < GPIO clock enable */
-#define CKEN_1WIRE	40	/* < 1-wire clock enable */
-#define CKEN_HSIO2	41	/* < HSIO2 clock enable */
-#define CKEN_MINI_IM	48	/* < Mini-IM */
-#define CKEN_MINI_LCD	49	/* < Mini LCD */
-
-#define CKEN_MMC3	5	/* < MMC3 Clock Enable */
-#define CKEN_MVED	43	/* < MVED clock enable */
-
-/* Note: GCU clock enable bit differs on PXA300/PXA310 and PXA320 */
-#define CKEN_PXA300_GCU		42	/* Graphics controller clock enable */
-#define CKEN_PXA320_GCU		7	/* Graphics controller clock enable */
-
 #endif /* __ASM_ARCH_PXA3XX_REGS_H */
diff --git a/arch/arm/mach-pxa/sleep.S b/arch/arm/mach-pxa/sleep.S
index 272efeb954f4..ab50fe2cf923 100644
--- a/arch/arm/mach-pxa/sleep.S
+++ b/arch/arm/mach-pxa/sleep.S
@@ -18,7 +18,9 @@
 
 #define MDREFR_KDIV	0x200a4000	// all banks
 #define CCCR_SLEEP	0x00000107	// L=7 2N=2 A=0 PPDIS=0 CPDIS=0
-
+#define CCCR_N_MASK     0x00000380
+#define CCCR_M_MASK     0x00000060
+#define CCCR_L_MASK     0x0000001f
 		.text
 
 #ifdef CONFIG_PXA3xx
diff --git a/drivers/clk/pxa/clk-pxa.c b/drivers/clk/pxa/clk-pxa.c
index 831180360069..03de634efc52 100644
--- a/drivers/clk/pxa/clk-pxa.c
+++ b/drivers/clk/pxa/clk-pxa.c
@@ -95,7 +95,8 @@ void __init clkdev_pxa_register(int ckid, const char *con_id,
 		clk_register_clkdev(clk, con_id, dev_id);
 }
 
-int __init clk_pxa_cken_init(const struct desc_clk_cken *clks, int nb_clks)
+int __init clk_pxa_cken_init(const struct desc_clk_cken *clks,
+			     int nb_clks, void __iomem *clk_regs)
 {
 	int i;
 	struct pxa_clk *pxa_clk;
@@ -107,6 +108,7 @@ int __init clk_pxa_cken_init(const struct desc_clk_cken *clks, int nb_clks)
 		pxa_clk->lp = clks[i].lp;
 		pxa_clk->hp = clks[i].hp;
 		pxa_clk->gate = clks[i].gate;
+		pxa_clk->gate.reg = clk_regs + clks[i].cken_reg;
 		pxa_clk->gate.lock = &pxa_clk_lock;
 		clk = clk_register_composite(NULL, clks[i].name,
 					     clks[i].parent_names, 2,
diff --git a/drivers/clk/pxa/clk-pxa.h b/drivers/clk/pxa/clk-pxa.h
index bd688fdb7ecc..7ec2d2821d8f 100644
--- a/drivers/clk/pxa/clk-pxa.h
+++ b/drivers/clk/pxa/clk-pxa.h
@@ -105,6 +105,7 @@
 struct desc_clk_cken {
 	struct clk_hw hw;
 	int ckid;
+	int cken_reg;
 	const char *name;
 	const char *dev_id;
 	const char *con_id;
@@ -119,11 +120,12 @@ struct desc_clk_cken {
 #define PXA_CKEN(_dev_id, _con_id, _name, parents, _mult_lp, _div_lp,	\
 		 _mult_hp, _div_hp, is_lp, _cken_reg, _cken_bit, flag)	\
 	{ .ckid = CLK_ ## _name, .name = #_name,			\
+	  .cken_reg = _cken_reg,					\
 	  .dev_id = _dev_id, .con_id = _con_id,	.parent_names = parents,\
 	  .lp = { .mult = _mult_lp, .div = _div_lp },			\
 	  .hp = { .mult = _mult_hp, .div = _div_hp },			\
 	  .is_in_low_power = is_lp,					\
-	  .gate = { .reg = (void __iomem *)_cken_reg, .bit_idx = _cken_bit }, \
+	  .gate = { .bit_idx = _cken_bit }, \
 	  .flags = flag,						\
 	}
 #define PXA_CKEN_1RATE(dev_id, con_id, name, parents, cken_reg,		\
@@ -147,7 +149,7 @@ static inline int dummy_clk_set_parent(struct clk_hw *hw, u8 index)
 extern void clkdev_pxa_register(int ckid, const char *con_id,
 				const char *dev_id, struct clk *clk);
 extern int clk_pxa_cken_init(const struct desc_clk_cken *clks,
-			     int nb_clks);
+			     int nb_clks, void __iomem *clk_regs);
 void clk_pxa_dt_common_init(struct device_node *np);
 
 void pxa2xx_core_turbo_switch(bool on);
diff --git a/drivers/clk/pxa/clk-pxa25x.c b/drivers/clk/pxa/clk-pxa25x.c
index 0837d59d7a67..93d5907b8530 100644
--- a/drivers/clk/pxa/clk-pxa25x.c
+++ b/drivers/clk/pxa/clk-pxa25x.c
@@ -14,11 +14,11 @@
 #include <linux/clkdev.h>
 #include <linux/io.h>
 #include <linux/of.h>
-#include <mach/pxa2xx-regs.h>
 #include <linux/soc/pxa/smemc.h>
 
 #include <dt-bindings/clock/pxa-clock.h>
 #include "clk-pxa.h"
+#include "clk-pxa2xx.h"
 
 #define KHz 1000
 #define MHz (1000 * 1000)
@@ -39,6 +39,7 @@ enum {
 /*
  * Various clock factors driven by the CCCR register.
  */
+static void __iomem *clk_regs;
 
 /* Crystal Frequency to Memory Frequency Multiplier (L) */
 static unsigned char L_clk_mult[32] = { 0, 27, 32, 36, 40, 45, 0, };
@@ -97,7 +98,7 @@ unsigned int pxa25x_get_clk_frequency_khz(int info)
 static unsigned long clk_pxa25x_memory_get_rate(struct clk_hw *hw,
 						unsigned long parent_rate)
 {
-	unsigned long cccr = readl(CCCR);
+	unsigned long cccr = readl(clk_regs + CCCR);
 	unsigned int m = M_clk_mult[(cccr >> 5) & 0x03];
 
 	return parent_rate / m;
@@ -201,7 +202,7 @@ MUX_OPS(clk_pxa25x_core, "core", CLK_SET_RATE_PARENT);
 static unsigned long clk_pxa25x_run_get_rate(struct clk_hw *hw,
 					     unsigned long parent_rate)
 {
-	unsigned long cccr = readl(CCCR);
+	unsigned long cccr = readl(clk_regs + CCCR);
 	unsigned int n2 = N2_clk_mult[(cccr >> 7) & 0x07];
 
 	return (parent_rate / n2) * 2;
@@ -212,7 +213,7 @@ RATE_RO_OPS(clk_pxa25x_run, "run");
 static unsigned long clk_pxa25x_cpll_get_rate(struct clk_hw *hw,
 	unsigned long parent_rate)
 {
-	unsigned long clkcfg, cccr = readl(CCCR);
+	unsigned long clkcfg, cccr = readl(clk_regs + CCCR);
 	unsigned int l, m, n2, t;
 
 	asm("mrc\tp14, 0, %0, c6, c0, 0" : "=r" (clkcfg));
@@ -244,7 +245,7 @@ static int clk_pxa25x_cpll_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (i >= ARRAY_SIZE(pxa25x_freqs))
 		return -EINVAL;
 
-	pxa2xx_cpll_change(&pxa25x_freqs[i], mdrefr_dri, CCCR);
+	pxa2xx_cpll_change(&pxa25x_freqs[i], mdrefr_dri, clk_regs + CCCR);
 
 	return 0;
 }
@@ -321,16 +322,17 @@ static void __init pxa25x_dummy_clocks_init(void)
 	}
 }
 
-int __init pxa25x_clocks_init(void)
+int __init pxa25x_clocks_init(void __iomem *regs)
 {
+	clk_regs = regs;
 	pxa25x_base_clocks_init();
 	pxa25x_dummy_clocks_init();
-	return clk_pxa_cken_init(pxa25x_clocks, ARRAY_SIZE(pxa25x_clocks));
+	return clk_pxa_cken_init(pxa25x_clocks, ARRAY_SIZE(pxa25x_clocks), clk_regs);
 }
 
 static void __init pxa25x_dt_clocks_init(struct device_node *np)
 {
-	pxa25x_clocks_init();
+	pxa25x_clocks_init(ioremap(0x41300000ul, 0x10));
 	clk_pxa_dt_common_init(np);
 }
 CLK_OF_DECLARE(pxa25x_clks, "marvell,pxa250-core-clocks",
diff --git a/drivers/clk/pxa/clk-pxa27x.c b/drivers/clk/pxa/clk-pxa27x.c
index ba3aa63f2447..116c6ac666e3 100644
--- a/drivers/clk/pxa/clk-pxa27x.c
+++ b/drivers/clk/pxa/clk-pxa27x.c
@@ -7,7 +7,6 @@
  * Heavily inspired from former arch/arm/mach-pxa/clock.c.
  */
 #include <linux/clk-provider.h>
-#include <mach/pxa2xx-regs.h>
 #include <linux/io.h>
 #include <linux/clk.h>
 #include <linux/clkdev.h>
@@ -16,6 +15,7 @@
 
 #include <dt-bindings/clock/pxa-clock.h>
 #include "clk-pxa.h"
+#include "clk-pxa2xx.h"
 
 #define KHz 1000
 #define MHz (1000 * 1000)
@@ -52,6 +52,8 @@ enum {
 /* Define the refresh period in mSec for the SDRAM and the number of rows */
 #define SDRAM_TREF	64	/* standard 64ms SDRAM */
 
+static void __iomem *clk_regs;
+
 static const char * const get_freq_khz[] = {
 	"core", "run", "cpll", "memory",
 	"system_bus"
@@ -99,7 +101,7 @@ unsigned int pxa27x_get_clk_frequency_khz(int info)
 
 bool pxa27x_is_ppll_disabled(void)
 {
-	unsigned long ccsr = readl(CCSR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 
 	return ccsr & (1 << CCCR_PPDIS_BIT);
 }
@@ -201,7 +203,7 @@ static unsigned long clk_pxa27x_cpll_get_rate(struct clk_hw *hw,
 	unsigned long clkcfg;
 	unsigned int t, ht;
 	unsigned int l, L, n2, N;
-	unsigned long ccsr = readl(CCSR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 
 	asm("mrc\tp14, 0, %0, c6, c0, 0" : "=r" (clkcfg));
 	t  = clkcfg & (1 << 0);
@@ -235,7 +237,7 @@ static int clk_pxa27x_cpll_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (i >= ARRAY_SIZE(pxa27x_freqs))
 		return -EINVAL;
 
-	pxa2xx_cpll_change(&pxa27x_freqs[i], mdrefr_dri, CCCR);
+	pxa2xx_cpll_change(&pxa27x_freqs[i], mdrefr_dri, clk_regs + CCCR);
 	return 0;
 }
 
@@ -246,8 +248,8 @@ static unsigned long clk_pxa27x_lcd_base_get_rate(struct clk_hw *hw,
 						  unsigned long parent_rate)
 {
 	unsigned int l, osc_forced;
-	unsigned long ccsr = readl(CCSR);
-	unsigned long cccr = readl(CCCR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
+	unsigned long cccr = readl(clk_regs + CCCR);
 
 	l  = ccsr & CCSR_L_MASK;
 	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
@@ -268,7 +270,7 @@ static unsigned long clk_pxa27x_lcd_base_get_rate(struct clk_hw *hw,
 static u8 clk_pxa27x_lcd_base_get_parent(struct clk_hw *hw)
 {
 	unsigned int osc_forced;
-	unsigned long ccsr = readl(CCSR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 
 	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
 	if (osc_forced)
@@ -297,7 +299,7 @@ static u8 clk_pxa27x_core_get_parent(struct clk_hw *hw)
 {
 	unsigned long clkcfg;
 	unsigned int t, ht, osc_forced;
-	unsigned long ccsr = readl(CCSR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 
 	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
 	if (osc_forced)
@@ -334,7 +336,7 @@ MUX_OPS(clk_pxa27x_core, "core", CLK_SET_RATE_PARENT);
 static unsigned long clk_pxa27x_run_get_rate(struct clk_hw *hw,
 					     unsigned long parent_rate)
 {
-	unsigned long ccsr = readl(CCSR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 	unsigned int n2 = (ccsr & CCSR_N2_MASK) >> CCSR_N2_SHIFT;
 
 	return (parent_rate / n2) * 2;
@@ -357,7 +359,7 @@ static unsigned long clk_pxa27x_system_bus_get_rate(struct clk_hw *hw,
 {
 	unsigned long clkcfg;
 	unsigned int b, osc_forced;
-	unsigned long ccsr = readl(CCSR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 
 	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
 	asm("mrc\tp14, 0, %0, c6, c0, 0" : "=r" (clkcfg));
@@ -374,7 +376,7 @@ static unsigned long clk_pxa27x_system_bus_get_rate(struct clk_hw *hw,
 static u8 clk_pxa27x_system_bus_get_parent(struct clk_hw *hw)
 {
 	unsigned int osc_forced;
-	unsigned long ccsr = readl(CCSR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 
 	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
 	if (osc_forced)
@@ -390,8 +392,8 @@ static unsigned long clk_pxa27x_memory_get_rate(struct clk_hw *hw,
 						unsigned long parent_rate)
 {
 	unsigned int a, l, osc_forced;
-	unsigned long cccr = readl(CCCR);
-	unsigned long ccsr = readl(CCSR);
+	unsigned long cccr = readl(clk_regs + CCCR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 
 	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
 	a = cccr & (1 << CCCR_A_BIT);
@@ -409,8 +411,8 @@ static unsigned long clk_pxa27x_memory_get_rate(struct clk_hw *hw,
 static u8 clk_pxa27x_memory_get_parent(struct clk_hw *hw)
 {
 	unsigned int osc_forced, a;
-	unsigned long cccr = readl(CCCR);
-	unsigned long ccsr = readl(CCSR);
+	unsigned long cccr = readl(clk_regs + CCCR);
+	unsigned long ccsr = readl(clk_regs + CCSR);
 
 	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
 	a = cccr & (1 << CCCR_A_BIT);
@@ -465,16 +467,17 @@ static void __init pxa27x_base_clocks_init(void)
 	clk_register_clk_pxa27x_lcd_base();
 }
 
-int __init pxa27x_clocks_init(void)
+int __init pxa27x_clocks_init(void __iomem *regs)
 {
+	clk_regs = regs;
 	pxa27x_base_clocks_init();
 	pxa27x_dummy_clocks_init();
-	return clk_pxa_cken_init(pxa27x_clocks, ARRAY_SIZE(pxa27x_clocks));
+	return clk_pxa_cken_init(pxa27x_clocks, ARRAY_SIZE(pxa27x_clocks), regs);
 }
 
 static void __init pxa27x_dt_clocks_init(struct device_node *np)
 {
-	pxa27x_clocks_init();
+	pxa27x_clocks_init(ioremap(0x41300000ul, 0x10));
 	clk_pxa_dt_common_init(np);
 }
 CLK_OF_DECLARE(pxa_clks, "marvell,pxa270-clocks", pxa27x_dt_clocks_init);
diff --git a/drivers/clk/pxa/clk-pxa2xx.h b/drivers/clk/pxa/clk-pxa2xx.h
new file mode 100644
index 000000000000..94b03d0e32ff
--- /dev/null
+++ b/drivers/clk/pxa/clk-pxa2xx.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __CLK_PXA2XX_H
+#define __CLK_PXA2XX_H
+
+#define CCCR		(0x0000)  /* Core Clock Configuration Register */
+#define CCSR		(0x000C)  /* Core Clock Status Register */
+#define CKEN		(0x0004)  /* Clock Enable Register */
+#define OSCC		(0x0008)  /* Oscillator Configuration Register */
+
+#define CCCR_N_MASK	0x0380	/* Run Mode Frequency to Turbo Mode Frequency Multiplier */
+#define CCCR_M_MASK	0x0060	/* Memory Frequency to Run Mode Frequency Multiplier */
+#define CCCR_L_MASK	0x001f	/* Crystal Frequency to Memory Frequency Multiplier */
+
+#define CCCR_CPDIS_BIT	(31)
+#define CCCR_PPDIS_BIT	(30)
+#define CCCR_LCD_26_BIT	(27)
+#define CCCR_A_BIT	(25)
+
+#define CCSR_N2_MASK	CCCR_N_MASK
+#define CCSR_M_MASK	CCCR_M_MASK
+#define CCSR_L_MASK	CCCR_L_MASK
+#define CCSR_N2_SHIFT	7
+
+#define CKEN_AC97CONF   (31)    /* AC97 Controller Configuration */
+#define CKEN_CAMERA	(24)	/* Camera Interface Clock Enable */
+#define CKEN_SSP1	(23)	/* SSP1 Unit Clock Enable */
+#define CKEN_MEMC	(22)	/* Memory Controller Clock Enable */
+#define CKEN_MEMSTK	(21)	/* Memory Stick Host Controller */
+#define CKEN_IM		(20)	/* Internal Memory Clock Enable */
+#define CKEN_KEYPAD	(19)	/* Keypad Interface Clock Enable */
+#define CKEN_USIM	(18)	/* USIM Unit Clock Enable */
+#define CKEN_MSL	(17)	/* MSL Unit Clock Enable */
+#define CKEN_LCD	(16)	/* LCD Unit Clock Enable */
+#define CKEN_PWRI2C	(15)	/* PWR I2C Unit Clock Enable */
+#define CKEN_I2C	(14)	/* I2C Unit Clock Enable */
+#define CKEN_FICP	(13)	/* FICP Unit Clock Enable */
+#define CKEN_MMC	(12)	/* MMC Unit Clock Enable */
+#define CKEN_USB	(11)	/* USB Unit Clock Enable */
+#define CKEN_ASSP	(10)	/* ASSP (SSP3) Clock Enable */
+#define CKEN_USBHOST	(10)	/* USB Host Unit Clock Enable */
+#define CKEN_OSTIMER	(9)	/* OS Timer Unit Clock Enable */
+#define CKEN_NSSP	(9)	/* NSSP (SSP2) Clock Enable */
+#define CKEN_I2S	(8)	/* I2S Unit Clock Enable */
+#define CKEN_BTUART	(7)	/* BTUART Unit Clock Enable */
+#define CKEN_FFUART	(6)	/* FFUART Unit Clock Enable */
+#define CKEN_STUART	(5)	/* STUART Unit Clock Enable */
+#define CKEN_HWUART	(4)	/* HWUART Unit Clock Enable */
+#define CKEN_SSP3	(4)	/* SSP3 Unit Clock Enable */
+#define CKEN_SSP	(3)	/* SSP Unit Clock Enable */
+#define CKEN_SSP2	(3)	/* SSP2 Unit Clock Enable */
+#define CKEN_AC97	(2)	/* AC97 Unit Clock Enable */
+#define CKEN_PWM1	(1)	/* PWM1 Clock Enable */
+#define CKEN_PWM0	(0)	/* PWM0 Clock Enable */
+
+#define OSCC_OON	(1 << 1)	/* 32.768kHz OON (write-once only bit) */
+#define OSCC_OOK	(1 << 0)	/* 32.768kHz OOK (read-only bit) */
+
+#endif
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 08594fc899e2..42958a542662 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -17,7 +17,6 @@
 #include <linux/soc/pxa/cpu.h>
 #include <linux/soc/pxa/smemc.h>
 #include <linux/clk/pxa.h>
-#include <mach/pxa3xx-regs.h>
 
 #include <dt-bindings/clock/pxa-clock.h>
 #include "clk-pxa.h"
@@ -25,6 +24,84 @@
 #define KHz 1000
 #define MHz (1000 * 1000)
 
+#define ACCR			(0x0000)	/* Application Subsystem Clock Configuration Register */
+#define ACSR			(0x0004)	/* Application Subsystem Clock Status Register */
+#define AICSR			(0x0008)	/* Application Subsystem Interrupt Control/Status Register */
+#define CKENA			(0x000C)	/* A Clock Enable Register */
+#define CKENB			(0x0010)	/* B Clock Enable Register */
+#define CKENC			(0x0024)	/* C Clock Enable Register */
+#define AC97_DIV		(0x0014)	/* AC97 clock divisor value register */
+
+#define ACCR_XPDIS		(1 << 31)	/* Core PLL Output Disable */
+#define ACCR_SPDIS		(1 << 30)	/* System PLL Output Disable */
+#define ACCR_D0CS		(1 << 26)	/* D0 Mode Clock Select */
+#define ACCR_PCCE		(1 << 11)	/* Power Mode Change Clock Enable */
+#define ACCR_DDR_D0CS		(1 << 7)	/* DDR SDRAM clock frequency in D0CS (PXA31x only) */
+
+#define ACCR_SMCFS_MASK		(0x7 << 23)	/* Static Memory Controller Frequency Select */
+#define ACCR_SFLFS_MASK		(0x3 << 18)	/* Frequency Select for Internal Memory Controller */
+#define ACCR_XSPCLK_MASK	(0x3 << 16)	/* Core Frequency during Frequency Change */
+#define ACCR_HSS_MASK		(0x3 << 14)	/* System Bus-Clock Frequency Select */
+#define ACCR_DMCFS_MASK		(0x3 << 12)	/* Dynamic Memory Controller Clock Frequency Select */
+#define ACCR_XN_MASK		(0x7 << 8)	/* Core PLL Turbo-Mode-to-Run-Mode Ratio */
+#define ACCR_XL_MASK		(0x1f)		/* Core PLL Run-Mode-to-Oscillator Ratio */
+
+#define ACCR_SMCFS(x)		(((x) & 0x7) << 23)
+#define ACCR_SFLFS(x)		(((x) & 0x3) << 18)
+#define ACCR_XSPCLK(x)		(((x) & 0x3) << 16)
+#define ACCR_HSS(x)		(((x) & 0x3) << 14)
+#define ACCR_DMCFS(x)		(((x) & 0x3) << 12)
+#define ACCR_XN(x)		(((x) & 0x7) << 8)
+#define ACCR_XL(x)		((x) & 0x1f)
+
+/*
+ * Clock Enable Bit
+ */
+#define CKEN_LCD	1	/* < LCD Clock Enable */
+#define CKEN_USBH	2	/* < USB host clock enable */
+#define CKEN_CAMERA	3	/* < Camera interface clock enable */
+#define CKEN_NAND	4	/* < NAND Flash Controller Clock Enable */
+#define CKEN_USB2	6	/* < USB 2.0 client clock enable. */
+#define CKEN_DMC	8	/* < Dynamic Memory Controller clock enable */
+#define CKEN_SMC	9	/* < Static Memory Controller clock enable */
+#define CKEN_ISC	10	/* < Internal SRAM Controller clock enable */
+#define CKEN_BOOT	11	/* < Boot rom clock enable */
+#define CKEN_MMC1	12	/* < MMC1 Clock enable */
+#define CKEN_MMC2	13	/* < MMC2 clock enable */
+#define CKEN_KEYPAD	14	/* < Keypand Controller Clock Enable */
+#define CKEN_CIR	15	/* < Consumer IR Clock Enable */
+#define CKEN_USIM0	17	/* < USIM[0] Clock Enable */
+#define CKEN_USIM1	18	/* < USIM[1] Clock Enable */
+#define CKEN_TPM	19	/* < TPM clock enable */
+#define CKEN_UDC	20	/* < UDC clock enable */
+#define CKEN_BTUART	21	/* < BTUART clock enable */
+#define CKEN_FFUART	22	/* < FFUART clock enable */
+#define CKEN_STUART	23	/* < STUART clock enable */
+#define CKEN_AC97	24	/* < AC97 clock enable */
+#define CKEN_TOUCH	25	/* < Touch screen Interface Clock Enable */
+#define CKEN_SSP1	26	/* < SSP1 clock enable */
+#define CKEN_SSP2	27	/* < SSP2 clock enable */
+#define CKEN_SSP3	28	/* < SSP3 clock enable */
+#define CKEN_SSP4	29	/* < SSP4 clock enable */
+#define CKEN_MSL0	30	/* < MSL0 clock enable */
+#define CKEN_PWM0	32	/* < PWM[0] clock enable */
+#define CKEN_PWM1	33	/* < PWM[1] clock enable */
+#define CKEN_I2C	36	/* < I2C clock enable */
+#define CKEN_INTC	38	/* < Interrupt controller clock enable */
+#define CKEN_GPIO	39	/* < GPIO clock enable */
+#define CKEN_1WIRE	40	/* < 1-wire clock enable */
+#define CKEN_HSIO2	41	/* < HSIO2 clock enable */
+#define CKEN_MINI_IM	48	/* < Mini-IM */
+#define CKEN_MINI_LCD	49	/* < Mini LCD */
+
+#define CKEN_MMC3	5	/* < MMC3 Clock Enable */
+#define CKEN_MVED	43	/* < MVED clock enable */
+
+/* Note: GCU clock enable bit differs on PXA300/PXA310 and PXA320 */
+#define CKEN_PXA300_GCU		42	/* Graphics controller clock enable */
+#define CKEN_PXA320_GCU		7	/* Graphics controller clock enable */
+
+
 enum {
 	PXA_CORE_60Mhz = 0,
 	PXA_CORE_RUN,
@@ -45,6 +122,8 @@ static const char * const get_freq_khz[] = {
 	"core", "ring_osc_60mhz", "run", "cpll", "system_bus"
 };
 
+static void __iomem *clk_regs;
+
 /*
  * Get the clock frequency as reflected by ACSR and the turbo flag.
  * We assume these values have been applied via a fcs.
@@ -80,16 +159,16 @@ unsigned int pxa3xx_get_clk_frequency_khz(int info)
 
 void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask)
 {
-	u32 accr = ACCR;
+	u32 accr = readl(clk_regs + ACCR);
 
 	accr &= ~disable;
 	accr |= enable;
 
-	ACCR = accr;
+	writel(accr, ACCR);
 	if (xclkcfg)
 		__asm__("mcr p14, 0, %0, c6, c0, 0\n" : : "r"(xclkcfg));
 
-	while ((ACSR & mask) != (accr & mask))
+	while ((readl(clk_regs + ACSR) & mask) != (accr & mask))
 		cpu_relax();
 }
 
@@ -98,7 +177,7 @@ static unsigned long clk_pxa3xx_ac97_get_rate(struct clk_hw *hw,
 {
 	unsigned long ac97_div, rate;
 
-	ac97_div = AC97_DIV;
+	ac97_div = readl(clk_regs + AC97_DIV);
 
 	/* This may loose precision for some rates but won't for the
 	 * standard 24.576MHz.
@@ -115,7 +194,7 @@ RATE_RO_OPS(clk_pxa3xx_ac97, "ac97");
 static unsigned long clk_pxa3xx_smemc_get_rate(struct clk_hw *hw,
 					      unsigned long parent_rate)
 {
-	unsigned long acsr = ACSR;
+	unsigned long acsr = readl(clk_regs + ACSR);
 
 	return (parent_rate / 48)  * smcfs_mult[(acsr >> 23) & 0x7] /
 		pxa3xx_smemc_get_memclkdiv();
@@ -126,7 +205,7 @@ RATE_RO_OPS(clk_pxa3xx_smemc, "smemc");
 
 static bool pxa3xx_is_ring_osc_forced(void)
 {
-	unsigned long acsr = ACSR;
+	unsigned long acsr = readl(clk_regs + ACSR);
 
 	return acsr & ACCR_D0CS;
 }
@@ -138,7 +217,7 @@ PARENTS(pxa3xx_ac97_bus) = { "ring_osc_60mhz", "ac97" };
 PARENTS(pxa3xx_sbus) = { "ring_osc_60mhz", "system_bus" };
 PARENTS(pxa3xx_smemcbus) = { "ring_osc_60mhz", "smemc" };
 
-#define CKEN_AB(bit) ((CKEN_ ## bit > 31) ? &CKENB : &CKENA)
+#define CKEN_AB(bit) ((CKEN_ ## bit > 31) ? CKENB : CKENA)
 #define PXA3XX_CKEN(dev_id, con_id, parents, mult_lp, div_lp, mult_hp,	\
 		    div_hp, bit, is_lp, flags)				\
 	PXA_CKEN(dev_id, con_id, bit, parents, mult_lp, div_lp,		\
@@ -206,7 +285,7 @@ static struct desc_clk_cken pxa93x_clocks[] __initdata = {
 static unsigned long clk_pxa3xx_system_bus_get_rate(struct clk_hw *hw,
 					    unsigned long parent_rate)
 {
-	unsigned long acsr = ACSR;
+	unsigned long acsr = readl(clk_regs + ACSR);
 	unsigned int hss = (acsr >> 14) & 0x3;
 
 	if (pxa3xx_is_ring_osc_forced())
@@ -253,7 +332,7 @@ MUX_RO_RATE_RO_OPS(clk_pxa3xx_core, "core");
 static unsigned long clk_pxa3xx_run_get_rate(struct clk_hw *hw,
 					     unsigned long parent_rate)
 {
-	unsigned long acsr = ACSR;
+	unsigned long acsr = readl(clk_regs + ACSR);
 	unsigned int xn = (acsr & ACCR_XN_MASK) >> 8;
 	unsigned int t, xclkcfg;
 
@@ -269,7 +348,7 @@ RATE_RO_OPS(clk_pxa3xx_run, "run");
 static unsigned long clk_pxa3xx_cpll_get_rate(struct clk_hw *hw,
 	unsigned long parent_rate)
 {
-	unsigned long acsr = ACSR;
+	unsigned long acsr = readl(clk_regs + ACSR);
 	unsigned int xn = (acsr & ACCR_XN_MASK) >> 8;
 	unsigned int xl = acsr & ACCR_XL_MASK;
 	unsigned int t, xclkcfg;
@@ -340,7 +419,7 @@ static void __init pxa3xx_dummy_clocks_init(void)
 	}
 }
 
-static void __init pxa3xx_base_clocks_init(void)
+static void __init pxa3xx_base_clocks_init(void __iomem *oscc_reg)
 {
 	struct clk *clk;
 
@@ -350,34 +429,35 @@ static void __init pxa3xx_base_clocks_init(void)
 	clk_register_clk_pxa3xx_ac97();
 	clk_register_clk_pxa3xx_smemc();
 	clk = clk_register_gate(NULL, "CLK_POUT",
-				"osc_13mhz", 0, OSCC, 11, 0, NULL);
+				"osc_13mhz", 0, oscc_reg, 11, 0, NULL);
 	clk_register_clkdev(clk, "CLK_POUT", NULL);
 	clkdev_pxa_register(CLK_OSTIMER, "OSTIMER0", NULL,
 			    clk_register_fixed_factor(NULL, "os-timer0",
 						      "osc_13mhz", 0, 1, 4));
 }
 
-int __init pxa3xx_clocks_init(void)
+int __init pxa3xx_clocks_init(void __iomem *regs, void __iomem *oscc_reg)
 {
 	int ret;
 
-	pxa3xx_base_clocks_init();
+	clk_regs = regs;
+	pxa3xx_base_clocks_init(oscc_reg);
 	pxa3xx_dummy_clocks_init();
-	ret = clk_pxa_cken_init(pxa3xx_clocks, ARRAY_SIZE(pxa3xx_clocks));
+	ret = clk_pxa_cken_init(pxa3xx_clocks, ARRAY_SIZE(pxa3xx_clocks), regs);
 	if (ret)
 		return ret;
 	if (cpu_is_pxa320())
 		return clk_pxa_cken_init(pxa320_clocks,
-					 ARRAY_SIZE(pxa320_clocks));
+					 ARRAY_SIZE(pxa320_clocks), regs);
 	if (cpu_is_pxa300() || cpu_is_pxa310())
 		return clk_pxa_cken_init(pxa300_310_clocks,
-					 ARRAY_SIZE(pxa300_310_clocks));
-	return clk_pxa_cken_init(pxa93x_clocks, ARRAY_SIZE(pxa93x_clocks));
+					 ARRAY_SIZE(pxa300_310_clocks), regs);
+	return clk_pxa_cken_init(pxa93x_clocks, ARRAY_SIZE(pxa93x_clocks), regs);
 }
 
 static void __init pxa3xx_dt_clocks_init(struct device_node *np)
 {
-	pxa3xx_clocks_init();
+	pxa3xx_clocks_init(ioremap(0x41340000, 0x10), ioremap(0x41350000, 4));
 	clk_pxa_dt_common_init(np);
 }
 CLK_OF_DECLARE(pxa_clks, "marvell,pxa300-clocks", pxa3xx_dt_clocks_init);
diff --git a/include/linux/clk/pxa.h b/include/linux/clk/pxa.h
index e5516c608c99..736b8bb91bd7 100644
--- a/include/linux/clk/pxa.h
+++ b/include/linux/clk/pxa.h
@@ -1,5 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+extern int pxa25x_clocks_init(void __iomem *regs);
+extern int pxa27x_clocks_init(void __iomem *regs);
+extern int pxa3xx_clocks_init(void __iomem *regs, void __iomem *oscc_reg);
+
 #ifdef CONFIG_PXA3xx
 extern unsigned	pxa3xx_get_clk_frequency_khz(int);
 extern void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask);
-- 
cgit v1.2.3


From 64dbc4dd7a7cc6642c522963a6194b62480e2a68 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 20 Sep 2019 13:33:40 +0200
Subject: ARM: pxa: move plat-pxa to drivers/soc/

There are two drivers in arch/arm/plat-pxa: mfp and ssp. Both
of them should ideally not be needed at all, as there are
proper subsystems to replace them.

OTOH, they are self-contained and can simply be normal
SoC drivers, so move them over there to eliminate one more
of the plat-* directories.

Acked-by: Robert Jarzmik <robert.jarzmik@free.fr> (mach-pxa)
Acked-by: Lubomir Rintel <lkundrak@v3.sk> (mach-mmp)
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/Kconfig                     |   4 -
 arch/arm/Makefile                    |   1 -
 arch/arm/mach-mmp/mfp.h              |   2 +-
 arch/arm/mach-pxa/include/mach/mfp.h |   2 +-
 arch/arm/mach-pxa/mfp-pxa2xx.h       |   2 +-
 arch/arm/mach-pxa/mfp-pxa3xx.h       |   2 +-
 arch/arm/plat-pxa/Kconfig            |   9 -
 arch/arm/plat-pxa/Makefile           |  10 -
 arch/arm/plat-pxa/include/plat/mfp.h | 472 -----------------------------------
 arch/arm/plat-pxa/mfp.c              | 282 ---------------------
 arch/arm/plat-pxa/ssp.c              | 231 -----------------
 drivers/soc/Kconfig                  |   1 +
 drivers/soc/Makefile                 |   1 +
 drivers/soc/pxa/Kconfig              |   8 +
 drivers/soc/pxa/Makefile             |   6 +
 drivers/soc/pxa/mfp.c                | 282 +++++++++++++++++++++
 drivers/soc/pxa/ssp.c                | 231 +++++++++++++++++
 include/linux/soc/pxa/mfp.h          | 470 ++++++++++++++++++++++++++++++++++
 18 files changed, 1003 insertions(+), 1013 deletions(-)
 delete mode 100644 arch/arm/plat-pxa/Kconfig
 delete mode 100644 arch/arm/plat-pxa/Makefile
 delete mode 100644 arch/arm/plat-pxa/include/plat/mfp.h
 delete mode 100644 arch/arm/plat-pxa/mfp.c
 delete mode 100644 arch/arm/plat-pxa/ssp.c
 create mode 100644 drivers/soc/pxa/Kconfig
 create mode 100644 drivers/soc/pxa/Makefile
 create mode 100644 drivers/soc/pxa/mfp.c
 create mode 100644 drivers/soc/pxa/ssp.c
 create mode 100644 include/linux/soc/pxa/mfp.h

(limited to 'include/linux')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2e8091e2d8a8..eef8cbf20045 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -667,7 +667,6 @@ source "arch/arm/mach-orion5x/Kconfig"
 source "arch/arm/mach-oxnas/Kconfig"
 
 source "arch/arm/mach-pxa/Kconfig"
-source "arch/arm/plat-pxa/Kconfig"
 
 source "arch/arm/mach-qcom/Kconfig"
 
@@ -753,9 +752,6 @@ config PLAT_ORION_LEGACY
 	bool
 	select PLAT_ORION
 
-config PLAT_PXA
-	bool
-
 config PLAT_VERSATILE
 	bool
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index a2391b8de5a5..206a900fc87c 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -230,7 +230,6 @@ machine-$(CONFIG_PLAT_SPEAR)		+= spear
 # by CONFIG_* macro name.
 plat-$(CONFIG_ARCH_OMAP)	+= omap
 plat-$(CONFIG_PLAT_ORION)	+= orion
-plat-$(CONFIG_PLAT_PXA)		+= pxa
 plat-$(CONFIG_PLAT_VERSATILE)	+= versatile
 
 # The byte offset of the kernel image in RAM from the start of RAM.
diff --git a/arch/arm/mach-mmp/mfp.h b/arch/arm/mach-mmp/mfp.h
index 75a4acb33b1b..6f3057987756 100644
--- a/arch/arm/mach-mmp/mfp.h
+++ b/arch/arm/mach-mmp/mfp.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_MACH_MFP_H
 #define __ASM_MACH_MFP_H
 
-#include <plat/mfp.h>
+#include <linux/soc/pxa/mfp.h>
 
 /*
  * NOTE: the MFPR register bit definitions on PXA168 processor lines are a
diff --git a/arch/arm/mach-pxa/include/mach/mfp.h b/arch/arm/mach-pxa/include/mach/mfp.h
index dbb961fb570e..7e0879bd4102 100644
--- a/arch/arm/mach-pxa/include/mach/mfp.h
+++ b/arch/arm/mach-pxa/include/mach/mfp.h
@@ -13,6 +13,6 @@
 #ifndef __ASM_ARCH_MFP_H
 #define __ASM_ARCH_MFP_H
 
-#include <plat/mfp.h>
+#include <linux/soc/pxa/mfp.h>
 
 #endif /* __ASM_ARCH_MFP_H */
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.h b/arch/arm/mach-pxa/mfp-pxa2xx.h
index 980145e7ee99..683a3ea5f154 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.h
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_ARCH_MFP_PXA2XX_H
 #define __ASM_ARCH_MFP_PXA2XX_H
 
-#include <plat/mfp.h>
+#include <linux/soc/pxa/mfp.h>
 
 /*
  * the following MFP_xxx bit definitions in mfp.h are re-used for pxa2xx:
diff --git a/arch/arm/mach-pxa/mfp-pxa3xx.h b/arch/arm/mach-pxa/mfp-pxa3xx.h
index cdd830926d1c..81fec4fa5a0f 100644
--- a/arch/arm/mach-pxa/mfp-pxa3xx.h
+++ b/arch/arm/mach-pxa/mfp-pxa3xx.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_ARCH_MFP_PXA3XX_H
 #define __ASM_ARCH_MFP_PXA3XX_H
 
-#include <plat/mfp.h>
+#include <linux/soc/pxa/mfp.h>
 
 #define MFPR_BASE	(0x40e10000)
 
diff --git a/arch/arm/plat-pxa/Kconfig b/arch/arm/plat-pxa/Kconfig
deleted file mode 100644
index 6f7a0a39c2b9..000000000000
--- a/arch/arm/plat-pxa/Kconfig
+++ /dev/null
@@ -1,9 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-if PLAT_PXA
-
-config PXA_SSP
-	tristate
-	help
-	  Enable support for PXA2xx SSP ports
-
-endif
diff --git a/arch/arm/plat-pxa/Makefile b/arch/arm/plat-pxa/Makefile
deleted file mode 100644
index 349ea0af8450..000000000000
--- a/arch/arm/plat-pxa/Makefile
+++ /dev/null
@@ -1,10 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile for code common across different PXA processor families
-#
-ccflags-$(CONFIG_ARCH_MMP) := -I$(srctree)/$(src)/include
-
-obj-$(CONFIG_PXA3xx)		+= mfp.o
-obj-$(CONFIG_ARCH_MMP)		+= mfp.o
-
-obj-$(CONFIG_PXA_SSP)		+= ssp.o
diff --git a/arch/arm/plat-pxa/include/plat/mfp.h b/arch/arm/plat-pxa/include/plat/mfp.h
deleted file mode 100644
index 3accaa9ee781..000000000000
--- a/arch/arm/plat-pxa/include/plat/mfp.h
+++ /dev/null
@@ -1,472 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/plat-pxa/include/plat/mfp.h
- *
- *   Common Multi-Function Pin Definitions
- *
- * Copyright (C) 2007 Marvell International Ltd.
- *
- * 2007-8-21: eric miao <eric.miao@marvell.com>
- *            initial version
- */
-
-#ifndef __ASM_PLAT_MFP_H
-#define __ASM_PLAT_MFP_H
-
-#define mfp_to_gpio(m)	((m) % 256)
-
-/* list of all the configurable MFP pins */
-enum {
-	MFP_PIN_INVALID = -1,
-
-	MFP_PIN_GPIO0 = 0,
-	MFP_PIN_GPIO1,
-	MFP_PIN_GPIO2,
-	MFP_PIN_GPIO3,
-	MFP_PIN_GPIO4,
-	MFP_PIN_GPIO5,
-	MFP_PIN_GPIO6,
-	MFP_PIN_GPIO7,
-	MFP_PIN_GPIO8,
-	MFP_PIN_GPIO9,
-	MFP_PIN_GPIO10,
-	MFP_PIN_GPIO11,
-	MFP_PIN_GPIO12,
-	MFP_PIN_GPIO13,
-	MFP_PIN_GPIO14,
-	MFP_PIN_GPIO15,
-	MFP_PIN_GPIO16,
-	MFP_PIN_GPIO17,
-	MFP_PIN_GPIO18,
-	MFP_PIN_GPIO19,
-	MFP_PIN_GPIO20,
-	MFP_PIN_GPIO21,
-	MFP_PIN_GPIO22,
-	MFP_PIN_GPIO23,
-	MFP_PIN_GPIO24,
-	MFP_PIN_GPIO25,
-	MFP_PIN_GPIO26,
-	MFP_PIN_GPIO27,
-	MFP_PIN_GPIO28,
-	MFP_PIN_GPIO29,
-	MFP_PIN_GPIO30,
-	MFP_PIN_GPIO31,
-	MFP_PIN_GPIO32,
-	MFP_PIN_GPIO33,
-	MFP_PIN_GPIO34,
-	MFP_PIN_GPIO35,
-	MFP_PIN_GPIO36,
-	MFP_PIN_GPIO37,
-	MFP_PIN_GPIO38,
-	MFP_PIN_GPIO39,
-	MFP_PIN_GPIO40,
-	MFP_PIN_GPIO41,
-	MFP_PIN_GPIO42,
-	MFP_PIN_GPIO43,
-	MFP_PIN_GPIO44,
-	MFP_PIN_GPIO45,
-	MFP_PIN_GPIO46,
-	MFP_PIN_GPIO47,
-	MFP_PIN_GPIO48,
-	MFP_PIN_GPIO49,
-	MFP_PIN_GPIO50,
-	MFP_PIN_GPIO51,
-	MFP_PIN_GPIO52,
-	MFP_PIN_GPIO53,
-	MFP_PIN_GPIO54,
-	MFP_PIN_GPIO55,
-	MFP_PIN_GPIO56,
-	MFP_PIN_GPIO57,
-	MFP_PIN_GPIO58,
-	MFP_PIN_GPIO59,
-	MFP_PIN_GPIO60,
-	MFP_PIN_GPIO61,
-	MFP_PIN_GPIO62,
-	MFP_PIN_GPIO63,
-	MFP_PIN_GPIO64,
-	MFP_PIN_GPIO65,
-	MFP_PIN_GPIO66,
-	MFP_PIN_GPIO67,
-	MFP_PIN_GPIO68,
-	MFP_PIN_GPIO69,
-	MFP_PIN_GPIO70,
-	MFP_PIN_GPIO71,
-	MFP_PIN_GPIO72,
-	MFP_PIN_GPIO73,
-	MFP_PIN_GPIO74,
-	MFP_PIN_GPIO75,
-	MFP_PIN_GPIO76,
-	MFP_PIN_GPIO77,
-	MFP_PIN_GPIO78,
-	MFP_PIN_GPIO79,
-	MFP_PIN_GPIO80,
-	MFP_PIN_GPIO81,
-	MFP_PIN_GPIO82,
-	MFP_PIN_GPIO83,
-	MFP_PIN_GPIO84,
-	MFP_PIN_GPIO85,
-	MFP_PIN_GPIO86,
-	MFP_PIN_GPIO87,
-	MFP_PIN_GPIO88,
-	MFP_PIN_GPIO89,
-	MFP_PIN_GPIO90,
-	MFP_PIN_GPIO91,
-	MFP_PIN_GPIO92,
-	MFP_PIN_GPIO93,
-	MFP_PIN_GPIO94,
-	MFP_PIN_GPIO95,
-	MFP_PIN_GPIO96,
-	MFP_PIN_GPIO97,
-	MFP_PIN_GPIO98,
-	MFP_PIN_GPIO99,
-	MFP_PIN_GPIO100,
-	MFP_PIN_GPIO101,
-	MFP_PIN_GPIO102,
-	MFP_PIN_GPIO103,
-	MFP_PIN_GPIO104,
-	MFP_PIN_GPIO105,
-	MFP_PIN_GPIO106,
-	MFP_PIN_GPIO107,
-	MFP_PIN_GPIO108,
-	MFP_PIN_GPIO109,
-	MFP_PIN_GPIO110,
-	MFP_PIN_GPIO111,
-	MFP_PIN_GPIO112,
-	MFP_PIN_GPIO113,
-	MFP_PIN_GPIO114,
-	MFP_PIN_GPIO115,
-	MFP_PIN_GPIO116,
-	MFP_PIN_GPIO117,
-	MFP_PIN_GPIO118,
-	MFP_PIN_GPIO119,
-	MFP_PIN_GPIO120,
-	MFP_PIN_GPIO121,
-	MFP_PIN_GPIO122,
-	MFP_PIN_GPIO123,
-	MFP_PIN_GPIO124,
-	MFP_PIN_GPIO125,
-	MFP_PIN_GPIO126,
-	MFP_PIN_GPIO127,
-
-	MFP_PIN_GPIO128,
-	MFP_PIN_GPIO129,
-	MFP_PIN_GPIO130,
-	MFP_PIN_GPIO131,
-	MFP_PIN_GPIO132,
-	MFP_PIN_GPIO133,
-	MFP_PIN_GPIO134,
-	MFP_PIN_GPIO135,
-	MFP_PIN_GPIO136,
-	MFP_PIN_GPIO137,
-	MFP_PIN_GPIO138,
-	MFP_PIN_GPIO139,
-	MFP_PIN_GPIO140,
-	MFP_PIN_GPIO141,
-	MFP_PIN_GPIO142,
-	MFP_PIN_GPIO143,
-	MFP_PIN_GPIO144,
-	MFP_PIN_GPIO145,
-	MFP_PIN_GPIO146,
-	MFP_PIN_GPIO147,
-	MFP_PIN_GPIO148,
-	MFP_PIN_GPIO149,
-	MFP_PIN_GPIO150,
-	MFP_PIN_GPIO151,
-	MFP_PIN_GPIO152,
-	MFP_PIN_GPIO153,
-	MFP_PIN_GPIO154,
-	MFP_PIN_GPIO155,
-	MFP_PIN_GPIO156,
-	MFP_PIN_GPIO157,
-	MFP_PIN_GPIO158,
-	MFP_PIN_GPIO159,
-	MFP_PIN_GPIO160,
-	MFP_PIN_GPIO161,
-	MFP_PIN_GPIO162,
-	MFP_PIN_GPIO163,
-	MFP_PIN_GPIO164,
-	MFP_PIN_GPIO165,
-	MFP_PIN_GPIO166,
-	MFP_PIN_GPIO167,
-	MFP_PIN_GPIO168,
-	MFP_PIN_GPIO169,
-	MFP_PIN_GPIO170,
-	MFP_PIN_GPIO171,
-	MFP_PIN_GPIO172,
-	MFP_PIN_GPIO173,
-	MFP_PIN_GPIO174,
-	MFP_PIN_GPIO175,
-	MFP_PIN_GPIO176,
-	MFP_PIN_GPIO177,
-	MFP_PIN_GPIO178,
-	MFP_PIN_GPIO179,
-	MFP_PIN_GPIO180,
-	MFP_PIN_GPIO181,
-	MFP_PIN_GPIO182,
-	MFP_PIN_GPIO183,
-	MFP_PIN_GPIO184,
-	MFP_PIN_GPIO185,
-	MFP_PIN_GPIO186,
-	MFP_PIN_GPIO187,
-	MFP_PIN_GPIO188,
-	MFP_PIN_GPIO189,
-	MFP_PIN_GPIO190,
-	MFP_PIN_GPIO191,
-
-	MFP_PIN_GPIO255 = 255,
-
-	MFP_PIN_GPIO0_2,
-	MFP_PIN_GPIO1_2,
-	MFP_PIN_GPIO2_2,
-	MFP_PIN_GPIO3_2,
-	MFP_PIN_GPIO4_2,
-	MFP_PIN_GPIO5_2,
-	MFP_PIN_GPIO6_2,
-	MFP_PIN_GPIO7_2,
-	MFP_PIN_GPIO8_2,
-	MFP_PIN_GPIO9_2,
-	MFP_PIN_GPIO10_2,
-	MFP_PIN_GPIO11_2,
-	MFP_PIN_GPIO12_2,
-	MFP_PIN_GPIO13_2,
-	MFP_PIN_GPIO14_2,
-	MFP_PIN_GPIO15_2,
-	MFP_PIN_GPIO16_2,
-	MFP_PIN_GPIO17_2,
-
-	MFP_PIN_ULPI_STP,
-	MFP_PIN_ULPI_NXT,
-	MFP_PIN_ULPI_DIR,
-
-	MFP_PIN_nXCVREN,
-	MFP_PIN_DF_CLE_nOE,
-	MFP_PIN_DF_nADV1_ALE,
-	MFP_PIN_DF_SCLK_E,
-	MFP_PIN_DF_SCLK_S,
-	MFP_PIN_nBE0,
-	MFP_PIN_nBE1,
-	MFP_PIN_DF_nADV2_ALE,
-	MFP_PIN_DF_INT_RnB,
-	MFP_PIN_DF_nCS0,
-	MFP_PIN_DF_nCS1,
-	MFP_PIN_nLUA,
-	MFP_PIN_nLLA,
-	MFP_PIN_DF_nWE,
-	MFP_PIN_DF_ALE_nWE,
-	MFP_PIN_DF_nRE_nOE,
-	MFP_PIN_DF_ADDR0,
-	MFP_PIN_DF_ADDR1,
-	MFP_PIN_DF_ADDR2,
-	MFP_PIN_DF_ADDR3,
-	MFP_PIN_DF_IO0,
-	MFP_PIN_DF_IO1,
-	MFP_PIN_DF_IO2,
-	MFP_PIN_DF_IO3,
-	MFP_PIN_DF_IO4,
-	MFP_PIN_DF_IO5,
-	MFP_PIN_DF_IO6,
-	MFP_PIN_DF_IO7,
-	MFP_PIN_DF_IO8,
-	MFP_PIN_DF_IO9,
-	MFP_PIN_DF_IO10,
-	MFP_PIN_DF_IO11,
-	MFP_PIN_DF_IO12,
-	MFP_PIN_DF_IO13,
-	MFP_PIN_DF_IO14,
-	MFP_PIN_DF_IO15,
-	MFP_PIN_DF_nCS0_SM_nCS2,
-	MFP_PIN_DF_nCS1_SM_nCS3,
-	MFP_PIN_SM_nCS0,
-	MFP_PIN_SM_nCS1,
-	MFP_PIN_DF_WEn,
-	MFP_PIN_DF_REn,
-	MFP_PIN_DF_CLE_SM_OEn,
-	MFP_PIN_DF_ALE_SM_WEn,
-	MFP_PIN_DF_RDY0,
-	MFP_PIN_DF_RDY1,
-
-	MFP_PIN_SM_SCLK,
-	MFP_PIN_SM_BE0,
-	MFP_PIN_SM_BE1,
-	MFP_PIN_SM_ADV,
-	MFP_PIN_SM_ADVMUX,
-	MFP_PIN_SM_RDY,
-
-	MFP_PIN_MMC1_DAT7,
-	MFP_PIN_MMC1_DAT6,
-	MFP_PIN_MMC1_DAT5,
-	MFP_PIN_MMC1_DAT4,
-	MFP_PIN_MMC1_DAT3,
-	MFP_PIN_MMC1_DAT2,
-	MFP_PIN_MMC1_DAT1,
-	MFP_PIN_MMC1_DAT0,
-	MFP_PIN_MMC1_CMD,
-	MFP_PIN_MMC1_CLK,
-	MFP_PIN_MMC1_CD,
-	MFP_PIN_MMC1_WP,
-
-	/* additional pins on PXA930 */
-	MFP_PIN_GSIM_UIO,
-	MFP_PIN_GSIM_UCLK,
-	MFP_PIN_GSIM_UDET,
-	MFP_PIN_GSIM_nURST,
-	MFP_PIN_PMIC_INT,
-	MFP_PIN_RDY,
-
-	/* additional pins on MMP2 */
-	MFP_PIN_TWSI1_SCL,
-	MFP_PIN_TWSI1_SDA,
-	MFP_PIN_TWSI4_SCL,
-	MFP_PIN_TWSI4_SDA,
-	MFP_PIN_CLK_REQ,
-
-	MFP_PIN_MAX,
-};
-
-/*
- * a possible MFP configuration is represented by a 32-bit integer
- *
- * bit  0.. 9 - MFP Pin Number (1024 Pins Maximum)
- * bit 10..12 - Alternate Function Selection
- * bit 13..15 - Drive Strength
- * bit 16..18 - Low Power Mode State
- * bit 19..20 - Low Power Mode Edge Detection
- * bit 21..22 - Run Mode Pull State
- *
- * to facilitate the definition, the following macros are provided
- *
- * MFP_CFG_DEFAULT - default MFP configuration value, with
- * 		  alternate function = 0,
- * 		  drive strength = fast 3mA (MFP_DS03X)
- * 		  low power mode = default
- * 		  edge detection = none
- *
- * MFP_CFG	- default MFPR value with alternate function
- * MFP_CFG_DRV	- default MFPR value with alternate function and
- * 		  pin drive strength
- * MFP_CFG_LPM	- default MFPR value with alternate function and
- * 		  low power mode
- * MFP_CFG_X	- default MFPR value with alternate function,
- * 		  pin drive strength and low power mode
- */
-
-typedef unsigned long mfp_cfg_t;
-
-#define MFP_PIN(x)		((x) & 0x3ff)
-
-#define MFP_AF0			(0x0 << 10)
-#define MFP_AF1			(0x1 << 10)
-#define MFP_AF2			(0x2 << 10)
-#define MFP_AF3			(0x3 << 10)
-#define MFP_AF4			(0x4 << 10)
-#define MFP_AF5			(0x5 << 10)
-#define MFP_AF6			(0x6 << 10)
-#define MFP_AF7			(0x7 << 10)
-#define MFP_AF_MASK		(0x7 << 10)
-#define MFP_AF(x)		(((x) >> 10) & 0x7)
-
-#define MFP_DS01X		(0x0 << 13)
-#define MFP_DS02X		(0x1 << 13)
-#define MFP_DS03X		(0x2 << 13)
-#define MFP_DS04X		(0x3 << 13)
-#define MFP_DS06X		(0x4 << 13)
-#define MFP_DS08X		(0x5 << 13)
-#define MFP_DS10X		(0x6 << 13)
-#define MFP_DS13X		(0x7 << 13)
-#define MFP_DS_MASK		(0x7 << 13)
-#define MFP_DS(x)		(((x) >> 13) & 0x7)
-
-#define MFP_LPM_DEFAULT		(0x0 << 16)
-#define MFP_LPM_DRIVE_LOW	(0x1 << 16)
-#define MFP_LPM_DRIVE_HIGH	(0x2 << 16)
-#define MFP_LPM_PULL_LOW	(0x3 << 16)
-#define MFP_LPM_PULL_HIGH	(0x4 << 16)
-#define MFP_LPM_FLOAT		(0x5 << 16)
-#define MFP_LPM_INPUT		(0x6 << 16)
-#define MFP_LPM_STATE_MASK	(0x7 << 16)
-#define MFP_LPM_STATE(x)	(((x) >> 16) & 0x7)
-
-#define MFP_LPM_EDGE_NONE	(0x0 << 19)
-#define MFP_LPM_EDGE_RISE	(0x1 << 19)
-#define MFP_LPM_EDGE_FALL	(0x2 << 19)
-#define MFP_LPM_EDGE_BOTH	(0x3 << 19)
-#define MFP_LPM_EDGE_MASK	(0x3 << 19)
-#define MFP_LPM_EDGE(x)		(((x) >> 19) & 0x3)
-
-#define MFP_PULL_NONE		(0x0 << 21)
-#define MFP_PULL_LOW		(0x1 << 21)
-#define MFP_PULL_HIGH		(0x2 << 21)
-#define MFP_PULL_BOTH		(0x3 << 21)
-#define MFP_PULL_FLOAT		(0x4 << 21)
-#define MFP_PULL_MASK		(0x7 << 21)
-#define MFP_PULL(x)		(((x) >> 21) & 0x7)
-
-#define MFP_CFG_DEFAULT		(MFP_AF0 | MFP_DS03X | MFP_LPM_DEFAULT |\
-				 MFP_LPM_EDGE_NONE | MFP_PULL_NONE)
-
-#define MFP_CFG(pin, af)		\
-	((MFP_CFG_DEFAULT & ~MFP_AF_MASK) |\
-	 (MFP_PIN(MFP_PIN_##pin) | MFP_##af))
-
-#define MFP_CFG_DRV(pin, af, drv)	\
-	((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK)) |\
-	 (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv))
-
-#define MFP_CFG_LPM(pin, af, lpm)	\
-	((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_LPM_STATE_MASK)) |\
-	 (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_LPM_##lpm))
-
-#define MFP_CFG_X(pin, af, drv, lpm)	\
-	((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK | MFP_LPM_STATE_MASK)) |\
-	 (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv | MFP_LPM_##lpm))
-
-#if defined(CONFIG_PXA3xx) || defined(CONFIG_ARCH_MMP)
-/*
- * each MFP pin will have a MFPR register, since the offset of the
- * register varies between processors, the processor specific code
- * should initialize the pin offsets by mfp_init()
- *
- * mfp_init_base() - accepts a virtual base for all MFPR registers and
- * initialize the MFP table to a default state
- *
- * mfp_init_addr() - accepts a table of "mfp_addr_map" structure, which
- * represents a range of MFP pins from "start" to "end", with the offset
- * beginning at "offset", to define a single pin, let "end" = -1.
- *
- * use
- *
- * MFP_ADDR_X() to define a range of pins
- * MFP_ADDR()   to define a single pin
- * MFP_ADDR_END to signal the end of pin offset definitions
- */
-struct mfp_addr_map {
-	unsigned int	start;
-	unsigned int	end;
-	unsigned long	offset;
-};
-
-#define MFP_ADDR_X(start, end, offset) \
-	{ MFP_PIN_##start, MFP_PIN_##end, offset }
-
-#define MFP_ADDR(pin, offset) \
-	{ MFP_PIN_##pin, -1, offset }
-
-#define MFP_ADDR_END	{ MFP_PIN_INVALID, 0 }
-
-void __init mfp_init_base(void __iomem *mfpr_base);
-void __init mfp_init_addr(struct mfp_addr_map *map);
-
-/*
- * mfp_{read, write}()	- for direct read/write access to the MFPR register
- * mfp_config()		- for configuring a group of MFPR registers
- * mfp_config_lpm()	- configuring all low power MFPR registers for suspend
- * mfp_config_run()	- configuring all run time  MFPR registers after resume
- */
-unsigned long mfp_read(int mfp);
-void mfp_write(int mfp, unsigned long mfpr_val);
-void mfp_config(unsigned long *mfp_cfgs, int num);
-void mfp_config_run(void);
-void mfp_config_lpm(void);
-#endif /* CONFIG_PXA3xx || CONFIG_ARCH_MMP */
-
-#endif /* __ASM_PLAT_MFP_H */
diff --git a/arch/arm/plat-pxa/mfp.c b/arch/arm/plat-pxa/mfp.c
deleted file mode 100644
index 17fc4f33f35b..000000000000
--- a/arch/arm/plat-pxa/mfp.c
+++ /dev/null
@@ -1,282 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/arch/arm/plat-pxa/mfp.c
- *
- *   Multi-Function Pin Support
- *
- * Copyright (C) 2007 Marvell Internation Ltd.
- *
- * 2007-08-21: eric miao <eric.miao@marvell.com>
- *             initial version
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/io.h>
-
-#include <plat/mfp.h>
-
-#define MFPR_SIZE	(PAGE_SIZE)
-
-/* MFPR register bit definitions */
-#define MFPR_PULL_SEL		(0x1 << 15)
-#define MFPR_PULLUP_EN		(0x1 << 14)
-#define MFPR_PULLDOWN_EN	(0x1 << 13)
-#define MFPR_SLEEP_SEL		(0x1 << 9)
-#define MFPR_SLEEP_OE_N		(0x1 << 7)
-#define MFPR_EDGE_CLEAR		(0x1 << 6)
-#define MFPR_EDGE_FALL_EN	(0x1 << 5)
-#define MFPR_EDGE_RISE_EN	(0x1 << 4)
-
-#define MFPR_SLEEP_DATA(x)	((x) << 8)
-#define MFPR_DRIVE(x)		(((x) & 0x7) << 10)
-#define MFPR_AF_SEL(x)		(((x) & 0x7) << 0)
-
-#define MFPR_EDGE_NONE		(0)
-#define MFPR_EDGE_RISE		(MFPR_EDGE_RISE_EN)
-#define MFPR_EDGE_FALL		(MFPR_EDGE_FALL_EN)
-#define MFPR_EDGE_BOTH		(MFPR_EDGE_RISE | MFPR_EDGE_FALL)
-
-/*
- * Table that determines the low power modes outputs, with actual settings
- * used in parentheses for don't-care values. Except for the float output,
- * the configured driven and pulled levels match, so if there is a need for
- * non-LPM pulled output, the same configuration could probably be used.
- *
- * Output value  sleep_oe_n  sleep_data  pullup_en  pulldown_en  pull_sel
- *                 (bit 7)    (bit 8)    (bit 14)     (bit 13)   (bit 15)
- *
- * Input            0          X(0)        X(0)        X(0)       0
- * Drive 0          0          0           0           X(1)       0
- * Drive 1          0          1           X(1)        0	  0
- * Pull hi (1)      1          X(1)        1           0	  0
- * Pull lo (0)      1          X(0)        0           1	  0
- * Z (float)        1          X(0)        0           0	  0
- */
-#define MFPR_LPM_INPUT		(0)
-#define MFPR_LPM_DRIVE_LOW	(MFPR_SLEEP_DATA(0) | MFPR_PULLDOWN_EN)
-#define MFPR_LPM_DRIVE_HIGH    	(MFPR_SLEEP_DATA(1) | MFPR_PULLUP_EN)
-#define MFPR_LPM_PULL_LOW      	(MFPR_LPM_DRIVE_LOW  | MFPR_SLEEP_OE_N)
-#define MFPR_LPM_PULL_HIGH     	(MFPR_LPM_DRIVE_HIGH | MFPR_SLEEP_OE_N)
-#define MFPR_LPM_FLOAT         	(MFPR_SLEEP_OE_N)
-#define MFPR_LPM_MASK		(0xe080)
-
-/*
- * The pullup and pulldown state of the MFP pin at run mode is by default
- * determined by the selected alternate function. In case that some buggy
- * devices need to override this default behavior,  the definitions below
- * indicates the setting of corresponding MFPR bits
- *
- * Definition       pull_sel  pullup_en  pulldown_en
- * MFPR_PULL_NONE       0         0        0
- * MFPR_PULL_LOW        1         0        1
- * MFPR_PULL_HIGH       1         1        0
- * MFPR_PULL_BOTH       1         1        1
- * MFPR_PULL_FLOAT	1         0        0
- */
-#define MFPR_PULL_NONE		(0)
-#define MFPR_PULL_LOW		(MFPR_PULL_SEL | MFPR_PULLDOWN_EN)
-#define MFPR_PULL_BOTH		(MFPR_PULL_LOW | MFPR_PULLUP_EN)
-#define MFPR_PULL_HIGH		(MFPR_PULL_SEL | MFPR_PULLUP_EN)
-#define MFPR_PULL_FLOAT		(MFPR_PULL_SEL)
-
-/* mfp_spin_lock is used to ensure that MFP register configuration
- * (most likely a read-modify-write operation) is atomic, and that
- * mfp_table[] is consistent
- */
-static DEFINE_SPINLOCK(mfp_spin_lock);
-
-static void __iomem *mfpr_mmio_base;
-
-struct mfp_pin {
-	unsigned long	config;		/* -1 for not configured */
-	unsigned long	mfpr_off;	/* MFPRxx Register offset */
-	unsigned long	mfpr_run;	/* Run-Mode Register Value */
-	unsigned long	mfpr_lpm;	/* Low Power Mode Register Value */
-};
-
-static struct mfp_pin mfp_table[MFP_PIN_MAX];
-
-/* mapping of MFP_LPM_* definitions to MFPR_LPM_* register bits */
-static const unsigned long mfpr_lpm[] = {
-	MFPR_LPM_INPUT,
-	MFPR_LPM_DRIVE_LOW,
-	MFPR_LPM_DRIVE_HIGH,
-	MFPR_LPM_PULL_LOW,
-	MFPR_LPM_PULL_HIGH,
-	MFPR_LPM_FLOAT,
-	MFPR_LPM_INPUT,
-};
-
-/* mapping of MFP_PULL_* definitions to MFPR_PULL_* register bits */
-static const unsigned long mfpr_pull[] = {
-	MFPR_PULL_NONE,
-	MFPR_PULL_LOW,
-	MFPR_PULL_HIGH,
-	MFPR_PULL_BOTH,
-	MFPR_PULL_FLOAT,
-};
-
-/* mapping of MFP_LPM_EDGE_* definitions to MFPR_EDGE_* register bits */
-static const unsigned long mfpr_edge[] = {
-	MFPR_EDGE_NONE,
-	MFPR_EDGE_RISE,
-	MFPR_EDGE_FALL,
-	MFPR_EDGE_BOTH,
-};
-
-#define mfpr_readl(off)			\
-	__raw_readl(mfpr_mmio_base + (off))
-
-#define mfpr_writel(off, val)		\
-	__raw_writel(val, mfpr_mmio_base + (off))
-
-#define mfp_configured(p)	((p)->config != -1)
-
-/*
- * perform a read-back of any valid MFPR register to make sure the
- * previous writings are finished
- */
-static unsigned long mfpr_off_readback;
-#define mfpr_sync()	(void)__raw_readl(mfpr_mmio_base + mfpr_off_readback)
-
-static inline void __mfp_config_run(struct mfp_pin *p)
-{
-	if (mfp_configured(p))
-		mfpr_writel(p->mfpr_off, p->mfpr_run);
-}
-
-static inline void __mfp_config_lpm(struct mfp_pin *p)
-{
-	if (mfp_configured(p)) {
-		unsigned long mfpr_clr = (p->mfpr_run & ~MFPR_EDGE_BOTH) | MFPR_EDGE_CLEAR;
-		if (mfpr_clr != p->mfpr_run)
-			mfpr_writel(p->mfpr_off, mfpr_clr);
-		if (p->mfpr_lpm != mfpr_clr)
-			mfpr_writel(p->mfpr_off, p->mfpr_lpm);
-	}
-}
-
-void mfp_config(unsigned long *mfp_cfgs, int num)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&mfp_spin_lock, flags);
-
-	for (i = 0; i < num; i++, mfp_cfgs++) {
-		unsigned long tmp, c = *mfp_cfgs;
-		struct mfp_pin *p;
-		int pin, af, drv, lpm, edge, pull;
-
-		pin = MFP_PIN(c);
-		BUG_ON(pin >= MFP_PIN_MAX);
-		p = &mfp_table[pin];
-
-		af  = MFP_AF(c);
-		drv = MFP_DS(c);
-		lpm = MFP_LPM_STATE(c);
-		edge = MFP_LPM_EDGE(c);
-		pull = MFP_PULL(c);
-
-		/* run-mode pull settings will conflict with MFPR bits of
-		 * low power mode state,  calculate mfpr_run and mfpr_lpm
-		 * individually if pull != MFP_PULL_NONE
-		 */
-		tmp = MFPR_AF_SEL(af) | MFPR_DRIVE(drv);
-
-		if (likely(pull == MFP_PULL_NONE)) {
-			p->mfpr_run = tmp | mfpr_lpm[lpm] | mfpr_edge[edge];
-			p->mfpr_lpm = p->mfpr_run;
-		} else {
-			p->mfpr_lpm = tmp | mfpr_lpm[lpm] | mfpr_edge[edge];
-			p->mfpr_run = tmp | mfpr_pull[pull];
-		}
-
-		p->config = c; __mfp_config_run(p);
-	}
-
-	mfpr_sync();
-	spin_unlock_irqrestore(&mfp_spin_lock, flags);
-}
-
-unsigned long mfp_read(int mfp)
-{
-	unsigned long val, flags;
-
-	BUG_ON(mfp < 0 || mfp >= MFP_PIN_MAX);
-
-	spin_lock_irqsave(&mfp_spin_lock, flags);
-	val = mfpr_readl(mfp_table[mfp].mfpr_off);
-	spin_unlock_irqrestore(&mfp_spin_lock, flags);
-
-	return val;
-}
-
-void mfp_write(int mfp, unsigned long val)
-{
-	unsigned long flags;
-
-	BUG_ON(mfp < 0 || mfp >= MFP_PIN_MAX);
-
-	spin_lock_irqsave(&mfp_spin_lock, flags);
-	mfpr_writel(mfp_table[mfp].mfpr_off, val);
-	mfpr_sync();
-	spin_unlock_irqrestore(&mfp_spin_lock, flags);
-}
-
-void __init mfp_init_base(void __iomem *mfpr_base)
-{
-	int i;
-
-	/* initialize the table with default - unconfigured */
-	for (i = 0; i < ARRAY_SIZE(mfp_table); i++)
-		mfp_table[i].config = -1;
-
-	mfpr_mmio_base = mfpr_base;
-}
-
-void __init mfp_init_addr(struct mfp_addr_map *map)
-{
-	struct mfp_addr_map *p;
-	unsigned long offset, flags;
-	int i;
-
-	spin_lock_irqsave(&mfp_spin_lock, flags);
-
-	/* mfp offset for readback */
-	mfpr_off_readback = map[0].offset;
-
-	for (p = map; p->start != MFP_PIN_INVALID; p++) {
-		offset = p->offset;
-		i = p->start;
-
-		do {
-			mfp_table[i].mfpr_off = offset;
-			mfp_table[i].mfpr_run = 0;
-			mfp_table[i].mfpr_lpm = 0;
-			offset += 4; i++;
-		} while ((i <= p->end) && (p->end != -1));
-	}
-
-	spin_unlock_irqrestore(&mfp_spin_lock, flags);
-}
-
-void mfp_config_lpm(void)
-{
-	struct mfp_pin *p = &mfp_table[0];
-	int pin;
-
-	for (pin = 0; pin < ARRAY_SIZE(mfp_table); pin++, p++)
-		__mfp_config_lpm(p);
-}
-
-void mfp_config_run(void)
-{
-	struct mfp_pin *p = &mfp_table[0];
-	int pin;
-
-	for (pin = 0; pin < ARRAY_SIZE(mfp_table); pin++, p++)
-		__mfp_config_run(p);
-}
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
deleted file mode 100644
index 563440315acd..000000000000
--- a/arch/arm/plat-pxa/ssp.c
+++ /dev/null
@@ -1,231 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  linux/arch/arm/mach-pxa/ssp.c
- *
- *  based on linux/arch/arm/mach-sa1100/ssp.c by Russell King
- *
- *  Copyright (C) 2003 Russell King.
- *  Copyright (C) 2003 Wolfson Microelectronics PLC
- *
- *  PXA2xx SSP driver.  This provides the generic core for simple
- *  IO-based SSP applications and allows easy port setup for DMA access.
- *
- *  Author: Liam Girdwood <liam.girdwood@wolfsonmicro.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/mutex.h>
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/platform_device.h>
-#include <linux/spi/pxa2xx_spi.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-
-#include <asm/irq.h>
-
-static DEFINE_MUTEX(ssp_lock);
-static LIST_HEAD(ssp_list);
-
-struct ssp_device *pxa_ssp_request(int port, const char *label)
-{
-	struct ssp_device *ssp = NULL;
-
-	mutex_lock(&ssp_lock);
-
-	list_for_each_entry(ssp, &ssp_list, node) {
-		if (ssp->port_id == port && ssp->use_count == 0) {
-			ssp->use_count++;
-			ssp->label = label;
-			break;
-		}
-	}
-
-	mutex_unlock(&ssp_lock);
-
-	if (&ssp->node == &ssp_list)
-		return NULL;
-
-	return ssp;
-}
-EXPORT_SYMBOL(pxa_ssp_request);
-
-struct ssp_device *pxa_ssp_request_of(const struct device_node *of_node,
-				      const char *label)
-{
-	struct ssp_device *ssp = NULL;
-
-	mutex_lock(&ssp_lock);
-
-	list_for_each_entry(ssp, &ssp_list, node) {
-		if (ssp->of_node == of_node && ssp->use_count == 0) {
-			ssp->use_count++;
-			ssp->label = label;
-			break;
-		}
-	}
-
-	mutex_unlock(&ssp_lock);
-
-	if (&ssp->node == &ssp_list)
-		return NULL;
-
-	return ssp;
-}
-EXPORT_SYMBOL(pxa_ssp_request_of);
-
-void pxa_ssp_free(struct ssp_device *ssp)
-{
-	mutex_lock(&ssp_lock);
-	if (ssp->use_count) {
-		ssp->use_count--;
-		ssp->label = NULL;
-	} else
-		dev_err(ssp->dev, "device already free\n");
-	mutex_unlock(&ssp_lock);
-}
-EXPORT_SYMBOL(pxa_ssp_free);
-
-#ifdef CONFIG_OF
-static const struct of_device_id pxa_ssp_of_ids[] = {
-	{ .compatible = "mrvl,pxa25x-ssp",	.data = (void *) PXA25x_SSP },
-	{ .compatible = "mvrl,pxa25x-nssp",	.data = (void *) PXA25x_NSSP },
-	{ .compatible = "mrvl,pxa27x-ssp",	.data = (void *) PXA27x_SSP },
-	{ .compatible = "mrvl,pxa3xx-ssp",	.data = (void *) PXA3xx_SSP },
-	{ .compatible = "mvrl,pxa168-ssp",	.data = (void *) PXA168_SSP },
-	{ .compatible = "mrvl,pxa910-ssp",	.data = (void *) PXA910_SSP },
-	{ .compatible = "mrvl,ce4100-ssp",	.data = (void *) CE4100_SSP },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, pxa_ssp_of_ids);
-#endif
-
-static int pxa_ssp_probe(struct platform_device *pdev)
-{
-	struct resource *res;
-	struct ssp_device *ssp;
-	struct device *dev = &pdev->dev;
-
-	ssp = devm_kzalloc(dev, sizeof(struct ssp_device), GFP_KERNEL);
-	if (ssp == NULL)
-		return -ENOMEM;
-
-	ssp->dev = dev;
-
-	ssp->clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(ssp->clk))
-		return PTR_ERR(ssp->clk);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res == NULL) {
-		dev_err(dev, "no memory resource defined\n");
-		return -ENODEV;
-	}
-
-	res = devm_request_mem_region(dev, res->start, resource_size(res),
-				      pdev->name);
-	if (res == NULL) {
-		dev_err(dev, "failed to request memory resource\n");
-		return -EBUSY;
-	}
-
-	ssp->phys_base = res->start;
-
-	ssp->mmio_base = devm_ioremap(dev, res->start, resource_size(res));
-	if (ssp->mmio_base == NULL) {
-		dev_err(dev, "failed to ioremap() registers\n");
-		return -ENODEV;
-	}
-
-	ssp->irq = platform_get_irq(pdev, 0);
-	if (ssp->irq < 0) {
-		dev_err(dev, "no IRQ resource defined\n");
-		return -ENODEV;
-	}
-
-	if (dev->of_node) {
-		const struct of_device_id *id =
-			of_match_device(of_match_ptr(pxa_ssp_of_ids), dev);
-		ssp->type = (int) id->data;
-	} else {
-		const struct platform_device_id *id =
-			platform_get_device_id(pdev);
-		ssp->type = (int) id->driver_data;
-
-		/* PXA2xx/3xx SSP ports starts from 1 and the internal pdev->id
-		 * starts from 0, do a translation here
-		 */
-		ssp->port_id = pdev->id + 1;
-	}
-
-	ssp->use_count = 0;
-	ssp->of_node = dev->of_node;
-
-	mutex_lock(&ssp_lock);
-	list_add(&ssp->node, &ssp_list);
-	mutex_unlock(&ssp_lock);
-
-	platform_set_drvdata(pdev, ssp);
-
-	return 0;
-}
-
-static int pxa_ssp_remove(struct platform_device *pdev)
-{
-	struct ssp_device *ssp;
-
-	ssp = platform_get_drvdata(pdev);
-	if (ssp == NULL)
-		return -ENODEV;
-
-	mutex_lock(&ssp_lock);
-	list_del(&ssp->node);
-	mutex_unlock(&ssp_lock);
-
-	return 0;
-}
-
-static const struct platform_device_id ssp_id_table[] = {
-	{ "pxa25x-ssp",		PXA25x_SSP },
-	{ "pxa25x-nssp",	PXA25x_NSSP },
-	{ "pxa27x-ssp",		PXA27x_SSP },
-	{ "pxa3xx-ssp",		PXA3xx_SSP },
-	{ "pxa168-ssp",		PXA168_SSP },
-	{ "pxa910-ssp",		PXA910_SSP },
-	{ },
-};
-
-static struct platform_driver pxa_ssp_driver = {
-	.probe		= pxa_ssp_probe,
-	.remove		= pxa_ssp_remove,
-	.driver		= {
-		.name		= "pxa2xx-ssp",
-		.of_match_table	= of_match_ptr(pxa_ssp_of_ids),
-	},
-	.id_table	= ssp_id_table,
-};
-
-static int __init pxa_ssp_init(void)
-{
-	return platform_driver_register(&pxa_ssp_driver);
-}
-
-static void __exit pxa_ssp_exit(void)
-{
-	platform_driver_unregister(&pxa_ssp_driver);
-}
-
-arch_initcall(pxa_ssp_init);
-module_exit(pxa_ssp_exit);
-
-MODULE_DESCRIPTION("PXA SSP driver");
-MODULE_AUTHOR("Liam Girdwood");
-MODULE_LICENSE("GPL");
diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig
index c5aae42673d3..86ccf5970bc1 100644
--- a/drivers/soc/Kconfig
+++ b/drivers/soc/Kconfig
@@ -14,6 +14,7 @@ source "drivers/soc/ixp4xx/Kconfig"
 source "drivers/soc/litex/Kconfig"
 source "drivers/soc/mediatek/Kconfig"
 source "drivers/soc/microchip/Kconfig"
+source "drivers/soc/pxa/Kconfig"
 source "drivers/soc/qcom/Kconfig"
 source "drivers/soc/renesas/Kconfig"
 source "drivers/soc/rockchip/Kconfig"
diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile
index 904eec2a7871..fd7717d597fc 100644
--- a/drivers/soc/Makefile
+++ b/drivers/soc/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_SOC_XWAY)		+= lantiq/
 obj-$(CONFIG_LITEX_SOC_CONTROLLER) += litex/
 obj-y				+= mediatek/
 obj-y				+= microchip/
+obj-y				+= pxa/
 obj-y				+= amlogic/
 obj-y				+= qcom/
 obj-y				+= renesas/
diff --git a/drivers/soc/pxa/Kconfig b/drivers/soc/pxa/Kconfig
new file mode 100644
index 000000000000..c5c265aa4f07
--- /dev/null
+++ b/drivers/soc/pxa/Kconfig
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config PLAT_PXA
+	bool
+
+config PXA_SSP
+	tristate
+	help
+	  Enable support for PXA2xx SSP ports
diff --git a/drivers/soc/pxa/Makefile b/drivers/soc/pxa/Makefile
new file mode 100644
index 000000000000..413deceddbdd
--- /dev/null
+++ b/drivers/soc/pxa/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_PXA3xx)		+= mfp.o
+obj-$(CONFIG_ARCH_MMP)		+= mfp.o
+
+obj-$(CONFIG_PXA_SSP)		+= ssp.o
diff --git a/drivers/soc/pxa/mfp.c b/drivers/soc/pxa/mfp.c
new file mode 100644
index 000000000000..6220ba321cfc
--- /dev/null
+++ b/drivers/soc/pxa/mfp.c
@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/arch/arm/plat-pxa/mfp.c
+ *
+ *   Multi-Function Pin Support
+ *
+ * Copyright (C) 2007 Marvell Internation Ltd.
+ *
+ * 2007-08-21: eric miao <eric.miao@marvell.com>
+ *             initial version
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+
+#include <linux/soc/pxa/mfp.h>
+
+#define MFPR_SIZE	(PAGE_SIZE)
+
+/* MFPR register bit definitions */
+#define MFPR_PULL_SEL		(0x1 << 15)
+#define MFPR_PULLUP_EN		(0x1 << 14)
+#define MFPR_PULLDOWN_EN	(0x1 << 13)
+#define MFPR_SLEEP_SEL		(0x1 << 9)
+#define MFPR_SLEEP_OE_N		(0x1 << 7)
+#define MFPR_EDGE_CLEAR		(0x1 << 6)
+#define MFPR_EDGE_FALL_EN	(0x1 << 5)
+#define MFPR_EDGE_RISE_EN	(0x1 << 4)
+
+#define MFPR_SLEEP_DATA(x)	((x) << 8)
+#define MFPR_DRIVE(x)		(((x) & 0x7) << 10)
+#define MFPR_AF_SEL(x)		(((x) & 0x7) << 0)
+
+#define MFPR_EDGE_NONE		(0)
+#define MFPR_EDGE_RISE		(MFPR_EDGE_RISE_EN)
+#define MFPR_EDGE_FALL		(MFPR_EDGE_FALL_EN)
+#define MFPR_EDGE_BOTH		(MFPR_EDGE_RISE | MFPR_EDGE_FALL)
+
+/*
+ * Table that determines the low power modes outputs, with actual settings
+ * used in parentheses for don't-care values. Except for the float output,
+ * the configured driven and pulled levels match, so if there is a need for
+ * non-LPM pulled output, the same configuration could probably be used.
+ *
+ * Output value  sleep_oe_n  sleep_data  pullup_en  pulldown_en  pull_sel
+ *                 (bit 7)    (bit 8)    (bit 14)     (bit 13)   (bit 15)
+ *
+ * Input            0          X(0)        X(0)        X(0)       0
+ * Drive 0          0          0           0           X(1)       0
+ * Drive 1          0          1           X(1)        0	  0
+ * Pull hi (1)      1          X(1)        1           0	  0
+ * Pull lo (0)      1          X(0)        0           1	  0
+ * Z (float)        1          X(0)        0           0	  0
+ */
+#define MFPR_LPM_INPUT		(0)
+#define MFPR_LPM_DRIVE_LOW	(MFPR_SLEEP_DATA(0) | MFPR_PULLDOWN_EN)
+#define MFPR_LPM_DRIVE_HIGH    	(MFPR_SLEEP_DATA(1) | MFPR_PULLUP_EN)
+#define MFPR_LPM_PULL_LOW      	(MFPR_LPM_DRIVE_LOW  | MFPR_SLEEP_OE_N)
+#define MFPR_LPM_PULL_HIGH     	(MFPR_LPM_DRIVE_HIGH | MFPR_SLEEP_OE_N)
+#define MFPR_LPM_FLOAT         	(MFPR_SLEEP_OE_N)
+#define MFPR_LPM_MASK		(0xe080)
+
+/*
+ * The pullup and pulldown state of the MFP pin at run mode is by default
+ * determined by the selected alternate function. In case that some buggy
+ * devices need to override this default behavior,  the definitions below
+ * indicates the setting of corresponding MFPR bits
+ *
+ * Definition       pull_sel  pullup_en  pulldown_en
+ * MFPR_PULL_NONE       0         0        0
+ * MFPR_PULL_LOW        1         0        1
+ * MFPR_PULL_HIGH       1         1        0
+ * MFPR_PULL_BOTH       1         1        1
+ * MFPR_PULL_FLOAT	1         0        0
+ */
+#define MFPR_PULL_NONE		(0)
+#define MFPR_PULL_LOW		(MFPR_PULL_SEL | MFPR_PULLDOWN_EN)
+#define MFPR_PULL_BOTH		(MFPR_PULL_LOW | MFPR_PULLUP_EN)
+#define MFPR_PULL_HIGH		(MFPR_PULL_SEL | MFPR_PULLUP_EN)
+#define MFPR_PULL_FLOAT		(MFPR_PULL_SEL)
+
+/* mfp_spin_lock is used to ensure that MFP register configuration
+ * (most likely a read-modify-write operation) is atomic, and that
+ * mfp_table[] is consistent
+ */
+static DEFINE_SPINLOCK(mfp_spin_lock);
+
+static void __iomem *mfpr_mmio_base;
+
+struct mfp_pin {
+	unsigned long	config;		/* -1 for not configured */
+	unsigned long	mfpr_off;	/* MFPRxx Register offset */
+	unsigned long	mfpr_run;	/* Run-Mode Register Value */
+	unsigned long	mfpr_lpm;	/* Low Power Mode Register Value */
+};
+
+static struct mfp_pin mfp_table[MFP_PIN_MAX];
+
+/* mapping of MFP_LPM_* definitions to MFPR_LPM_* register bits */
+static const unsigned long mfpr_lpm[] = {
+	MFPR_LPM_INPUT,
+	MFPR_LPM_DRIVE_LOW,
+	MFPR_LPM_DRIVE_HIGH,
+	MFPR_LPM_PULL_LOW,
+	MFPR_LPM_PULL_HIGH,
+	MFPR_LPM_FLOAT,
+	MFPR_LPM_INPUT,
+};
+
+/* mapping of MFP_PULL_* definitions to MFPR_PULL_* register bits */
+static const unsigned long mfpr_pull[] = {
+	MFPR_PULL_NONE,
+	MFPR_PULL_LOW,
+	MFPR_PULL_HIGH,
+	MFPR_PULL_BOTH,
+	MFPR_PULL_FLOAT,
+};
+
+/* mapping of MFP_LPM_EDGE_* definitions to MFPR_EDGE_* register bits */
+static const unsigned long mfpr_edge[] = {
+	MFPR_EDGE_NONE,
+	MFPR_EDGE_RISE,
+	MFPR_EDGE_FALL,
+	MFPR_EDGE_BOTH,
+};
+
+#define mfpr_readl(off)			\
+	__raw_readl(mfpr_mmio_base + (off))
+
+#define mfpr_writel(off, val)		\
+	__raw_writel(val, mfpr_mmio_base + (off))
+
+#define mfp_configured(p)	((p)->config != -1)
+
+/*
+ * perform a read-back of any valid MFPR register to make sure the
+ * previous writings are finished
+ */
+static unsigned long mfpr_off_readback;
+#define mfpr_sync()	(void)__raw_readl(mfpr_mmio_base + mfpr_off_readback)
+
+static inline void __mfp_config_run(struct mfp_pin *p)
+{
+	if (mfp_configured(p))
+		mfpr_writel(p->mfpr_off, p->mfpr_run);
+}
+
+static inline void __mfp_config_lpm(struct mfp_pin *p)
+{
+	if (mfp_configured(p)) {
+		unsigned long mfpr_clr = (p->mfpr_run & ~MFPR_EDGE_BOTH) | MFPR_EDGE_CLEAR;
+		if (mfpr_clr != p->mfpr_run)
+			mfpr_writel(p->mfpr_off, mfpr_clr);
+		if (p->mfpr_lpm != mfpr_clr)
+			mfpr_writel(p->mfpr_off, p->mfpr_lpm);
+	}
+}
+
+void mfp_config(unsigned long *mfp_cfgs, int num)
+{
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&mfp_spin_lock, flags);
+
+	for (i = 0; i < num; i++, mfp_cfgs++) {
+		unsigned long tmp, c = *mfp_cfgs;
+		struct mfp_pin *p;
+		int pin, af, drv, lpm, edge, pull;
+
+		pin = MFP_PIN(c);
+		BUG_ON(pin >= MFP_PIN_MAX);
+		p = &mfp_table[pin];
+
+		af  = MFP_AF(c);
+		drv = MFP_DS(c);
+		lpm = MFP_LPM_STATE(c);
+		edge = MFP_LPM_EDGE(c);
+		pull = MFP_PULL(c);
+
+		/* run-mode pull settings will conflict with MFPR bits of
+		 * low power mode state,  calculate mfpr_run and mfpr_lpm
+		 * individually if pull != MFP_PULL_NONE
+		 */
+		tmp = MFPR_AF_SEL(af) | MFPR_DRIVE(drv);
+
+		if (likely(pull == MFP_PULL_NONE)) {
+			p->mfpr_run = tmp | mfpr_lpm[lpm] | mfpr_edge[edge];
+			p->mfpr_lpm = p->mfpr_run;
+		} else {
+			p->mfpr_lpm = tmp | mfpr_lpm[lpm] | mfpr_edge[edge];
+			p->mfpr_run = tmp | mfpr_pull[pull];
+		}
+
+		p->config = c; __mfp_config_run(p);
+	}
+
+	mfpr_sync();
+	spin_unlock_irqrestore(&mfp_spin_lock, flags);
+}
+
+unsigned long mfp_read(int mfp)
+{
+	unsigned long val, flags;
+
+	BUG_ON(mfp < 0 || mfp >= MFP_PIN_MAX);
+
+	spin_lock_irqsave(&mfp_spin_lock, flags);
+	val = mfpr_readl(mfp_table[mfp].mfpr_off);
+	spin_unlock_irqrestore(&mfp_spin_lock, flags);
+
+	return val;
+}
+
+void mfp_write(int mfp, unsigned long val)
+{
+	unsigned long flags;
+
+	BUG_ON(mfp < 0 || mfp >= MFP_PIN_MAX);
+
+	spin_lock_irqsave(&mfp_spin_lock, flags);
+	mfpr_writel(mfp_table[mfp].mfpr_off, val);
+	mfpr_sync();
+	spin_unlock_irqrestore(&mfp_spin_lock, flags);
+}
+
+void __init mfp_init_base(void __iomem *mfpr_base)
+{
+	int i;
+
+	/* initialize the table with default - unconfigured */
+	for (i = 0; i < ARRAY_SIZE(mfp_table); i++)
+		mfp_table[i].config = -1;
+
+	mfpr_mmio_base = mfpr_base;
+}
+
+void __init mfp_init_addr(struct mfp_addr_map *map)
+{
+	struct mfp_addr_map *p;
+	unsigned long offset, flags;
+	int i;
+
+	spin_lock_irqsave(&mfp_spin_lock, flags);
+
+	/* mfp offset for readback */
+	mfpr_off_readback = map[0].offset;
+
+	for (p = map; p->start != MFP_PIN_INVALID; p++) {
+		offset = p->offset;
+		i = p->start;
+
+		do {
+			mfp_table[i].mfpr_off = offset;
+			mfp_table[i].mfpr_run = 0;
+			mfp_table[i].mfpr_lpm = 0;
+			offset += 4; i++;
+		} while ((i <= p->end) && (p->end != -1));
+	}
+
+	spin_unlock_irqrestore(&mfp_spin_lock, flags);
+}
+
+void mfp_config_lpm(void)
+{
+	struct mfp_pin *p = &mfp_table[0];
+	int pin;
+
+	for (pin = 0; pin < ARRAY_SIZE(mfp_table); pin++, p++)
+		__mfp_config_lpm(p);
+}
+
+void mfp_config_run(void)
+{
+	struct mfp_pin *p = &mfp_table[0];
+	int pin;
+
+	for (pin = 0; pin < ARRAY_SIZE(mfp_table); pin++, p++)
+		__mfp_config_run(p);
+}
diff --git a/drivers/soc/pxa/ssp.c b/drivers/soc/pxa/ssp.c
new file mode 100644
index 000000000000..563440315acd
--- /dev/null
+++ b/drivers/soc/pxa/ssp.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/arch/arm/mach-pxa/ssp.c
+ *
+ *  based on linux/arch/arm/mach-sa1100/ssp.c by Russell King
+ *
+ *  Copyright (C) 2003 Russell King.
+ *  Copyright (C) 2003 Wolfson Microelectronics PLC
+ *
+ *  PXA2xx SSP driver.  This provides the generic core for simple
+ *  IO-based SSP applications and allows easy port setup for DMA access.
+ *
+ *  Author: Liam Girdwood <liam.girdwood@wolfsonmicro.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/spi/pxa2xx_spi.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+#include <asm/irq.h>
+
+static DEFINE_MUTEX(ssp_lock);
+static LIST_HEAD(ssp_list);
+
+struct ssp_device *pxa_ssp_request(int port, const char *label)
+{
+	struct ssp_device *ssp = NULL;
+
+	mutex_lock(&ssp_lock);
+
+	list_for_each_entry(ssp, &ssp_list, node) {
+		if (ssp->port_id == port && ssp->use_count == 0) {
+			ssp->use_count++;
+			ssp->label = label;
+			break;
+		}
+	}
+
+	mutex_unlock(&ssp_lock);
+
+	if (&ssp->node == &ssp_list)
+		return NULL;
+
+	return ssp;
+}
+EXPORT_SYMBOL(pxa_ssp_request);
+
+struct ssp_device *pxa_ssp_request_of(const struct device_node *of_node,
+				      const char *label)
+{
+	struct ssp_device *ssp = NULL;
+
+	mutex_lock(&ssp_lock);
+
+	list_for_each_entry(ssp, &ssp_list, node) {
+		if (ssp->of_node == of_node && ssp->use_count == 0) {
+			ssp->use_count++;
+			ssp->label = label;
+			break;
+		}
+	}
+
+	mutex_unlock(&ssp_lock);
+
+	if (&ssp->node == &ssp_list)
+		return NULL;
+
+	return ssp;
+}
+EXPORT_SYMBOL(pxa_ssp_request_of);
+
+void pxa_ssp_free(struct ssp_device *ssp)
+{
+	mutex_lock(&ssp_lock);
+	if (ssp->use_count) {
+		ssp->use_count--;
+		ssp->label = NULL;
+	} else
+		dev_err(ssp->dev, "device already free\n");
+	mutex_unlock(&ssp_lock);
+}
+EXPORT_SYMBOL(pxa_ssp_free);
+
+#ifdef CONFIG_OF
+static const struct of_device_id pxa_ssp_of_ids[] = {
+	{ .compatible = "mrvl,pxa25x-ssp",	.data = (void *) PXA25x_SSP },
+	{ .compatible = "mvrl,pxa25x-nssp",	.data = (void *) PXA25x_NSSP },
+	{ .compatible = "mrvl,pxa27x-ssp",	.data = (void *) PXA27x_SSP },
+	{ .compatible = "mrvl,pxa3xx-ssp",	.data = (void *) PXA3xx_SSP },
+	{ .compatible = "mvrl,pxa168-ssp",	.data = (void *) PXA168_SSP },
+	{ .compatible = "mrvl,pxa910-ssp",	.data = (void *) PXA910_SSP },
+	{ .compatible = "mrvl,ce4100-ssp",	.data = (void *) CE4100_SSP },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, pxa_ssp_of_ids);
+#endif
+
+static int pxa_ssp_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct ssp_device *ssp;
+	struct device *dev = &pdev->dev;
+
+	ssp = devm_kzalloc(dev, sizeof(struct ssp_device), GFP_KERNEL);
+	if (ssp == NULL)
+		return -ENOMEM;
+
+	ssp->dev = dev;
+
+	ssp->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(ssp->clk))
+		return PTR_ERR(ssp->clk);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res == NULL) {
+		dev_err(dev, "no memory resource defined\n");
+		return -ENODEV;
+	}
+
+	res = devm_request_mem_region(dev, res->start, resource_size(res),
+				      pdev->name);
+	if (res == NULL) {
+		dev_err(dev, "failed to request memory resource\n");
+		return -EBUSY;
+	}
+
+	ssp->phys_base = res->start;
+
+	ssp->mmio_base = devm_ioremap(dev, res->start, resource_size(res));
+	if (ssp->mmio_base == NULL) {
+		dev_err(dev, "failed to ioremap() registers\n");
+		return -ENODEV;
+	}
+
+	ssp->irq = platform_get_irq(pdev, 0);
+	if (ssp->irq < 0) {
+		dev_err(dev, "no IRQ resource defined\n");
+		return -ENODEV;
+	}
+
+	if (dev->of_node) {
+		const struct of_device_id *id =
+			of_match_device(of_match_ptr(pxa_ssp_of_ids), dev);
+		ssp->type = (int) id->data;
+	} else {
+		const struct platform_device_id *id =
+			platform_get_device_id(pdev);
+		ssp->type = (int) id->driver_data;
+
+		/* PXA2xx/3xx SSP ports starts from 1 and the internal pdev->id
+		 * starts from 0, do a translation here
+		 */
+		ssp->port_id = pdev->id + 1;
+	}
+
+	ssp->use_count = 0;
+	ssp->of_node = dev->of_node;
+
+	mutex_lock(&ssp_lock);
+	list_add(&ssp->node, &ssp_list);
+	mutex_unlock(&ssp_lock);
+
+	platform_set_drvdata(pdev, ssp);
+
+	return 0;
+}
+
+static int pxa_ssp_remove(struct platform_device *pdev)
+{
+	struct ssp_device *ssp;
+
+	ssp = platform_get_drvdata(pdev);
+	if (ssp == NULL)
+		return -ENODEV;
+
+	mutex_lock(&ssp_lock);
+	list_del(&ssp->node);
+	mutex_unlock(&ssp_lock);
+
+	return 0;
+}
+
+static const struct platform_device_id ssp_id_table[] = {
+	{ "pxa25x-ssp",		PXA25x_SSP },
+	{ "pxa25x-nssp",	PXA25x_NSSP },
+	{ "pxa27x-ssp",		PXA27x_SSP },
+	{ "pxa3xx-ssp",		PXA3xx_SSP },
+	{ "pxa168-ssp",		PXA168_SSP },
+	{ "pxa910-ssp",		PXA910_SSP },
+	{ },
+};
+
+static struct platform_driver pxa_ssp_driver = {
+	.probe		= pxa_ssp_probe,
+	.remove		= pxa_ssp_remove,
+	.driver		= {
+		.name		= "pxa2xx-ssp",
+		.of_match_table	= of_match_ptr(pxa_ssp_of_ids),
+	},
+	.id_table	= ssp_id_table,
+};
+
+static int __init pxa_ssp_init(void)
+{
+	return platform_driver_register(&pxa_ssp_driver);
+}
+
+static void __exit pxa_ssp_exit(void)
+{
+	platform_driver_unregister(&pxa_ssp_driver);
+}
+
+arch_initcall(pxa_ssp_init);
+module_exit(pxa_ssp_exit);
+
+MODULE_DESCRIPTION("PXA SSP driver");
+MODULE_AUTHOR("Liam Girdwood");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/soc/pxa/mfp.h b/include/linux/soc/pxa/mfp.h
new file mode 100644
index 000000000000..39779cbed0c0
--- /dev/null
+++ b/include/linux/soc/pxa/mfp.h
@@ -0,0 +1,470 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *   Common Multi-Function Pin Definitions
+ *
+ * Copyright (C) 2007 Marvell International Ltd.
+ *
+ * 2007-8-21: eric miao <eric.miao@marvell.com>
+ *            initial version
+ */
+
+#ifndef __ASM_PLAT_MFP_H
+#define __ASM_PLAT_MFP_H
+
+#define mfp_to_gpio(m)	((m) % 256)
+
+/* list of all the configurable MFP pins */
+enum {
+	MFP_PIN_INVALID = -1,
+
+	MFP_PIN_GPIO0 = 0,
+	MFP_PIN_GPIO1,
+	MFP_PIN_GPIO2,
+	MFP_PIN_GPIO3,
+	MFP_PIN_GPIO4,
+	MFP_PIN_GPIO5,
+	MFP_PIN_GPIO6,
+	MFP_PIN_GPIO7,
+	MFP_PIN_GPIO8,
+	MFP_PIN_GPIO9,
+	MFP_PIN_GPIO10,
+	MFP_PIN_GPIO11,
+	MFP_PIN_GPIO12,
+	MFP_PIN_GPIO13,
+	MFP_PIN_GPIO14,
+	MFP_PIN_GPIO15,
+	MFP_PIN_GPIO16,
+	MFP_PIN_GPIO17,
+	MFP_PIN_GPIO18,
+	MFP_PIN_GPIO19,
+	MFP_PIN_GPIO20,
+	MFP_PIN_GPIO21,
+	MFP_PIN_GPIO22,
+	MFP_PIN_GPIO23,
+	MFP_PIN_GPIO24,
+	MFP_PIN_GPIO25,
+	MFP_PIN_GPIO26,
+	MFP_PIN_GPIO27,
+	MFP_PIN_GPIO28,
+	MFP_PIN_GPIO29,
+	MFP_PIN_GPIO30,
+	MFP_PIN_GPIO31,
+	MFP_PIN_GPIO32,
+	MFP_PIN_GPIO33,
+	MFP_PIN_GPIO34,
+	MFP_PIN_GPIO35,
+	MFP_PIN_GPIO36,
+	MFP_PIN_GPIO37,
+	MFP_PIN_GPIO38,
+	MFP_PIN_GPIO39,
+	MFP_PIN_GPIO40,
+	MFP_PIN_GPIO41,
+	MFP_PIN_GPIO42,
+	MFP_PIN_GPIO43,
+	MFP_PIN_GPIO44,
+	MFP_PIN_GPIO45,
+	MFP_PIN_GPIO46,
+	MFP_PIN_GPIO47,
+	MFP_PIN_GPIO48,
+	MFP_PIN_GPIO49,
+	MFP_PIN_GPIO50,
+	MFP_PIN_GPIO51,
+	MFP_PIN_GPIO52,
+	MFP_PIN_GPIO53,
+	MFP_PIN_GPIO54,
+	MFP_PIN_GPIO55,
+	MFP_PIN_GPIO56,
+	MFP_PIN_GPIO57,
+	MFP_PIN_GPIO58,
+	MFP_PIN_GPIO59,
+	MFP_PIN_GPIO60,
+	MFP_PIN_GPIO61,
+	MFP_PIN_GPIO62,
+	MFP_PIN_GPIO63,
+	MFP_PIN_GPIO64,
+	MFP_PIN_GPIO65,
+	MFP_PIN_GPIO66,
+	MFP_PIN_GPIO67,
+	MFP_PIN_GPIO68,
+	MFP_PIN_GPIO69,
+	MFP_PIN_GPIO70,
+	MFP_PIN_GPIO71,
+	MFP_PIN_GPIO72,
+	MFP_PIN_GPIO73,
+	MFP_PIN_GPIO74,
+	MFP_PIN_GPIO75,
+	MFP_PIN_GPIO76,
+	MFP_PIN_GPIO77,
+	MFP_PIN_GPIO78,
+	MFP_PIN_GPIO79,
+	MFP_PIN_GPIO80,
+	MFP_PIN_GPIO81,
+	MFP_PIN_GPIO82,
+	MFP_PIN_GPIO83,
+	MFP_PIN_GPIO84,
+	MFP_PIN_GPIO85,
+	MFP_PIN_GPIO86,
+	MFP_PIN_GPIO87,
+	MFP_PIN_GPIO88,
+	MFP_PIN_GPIO89,
+	MFP_PIN_GPIO90,
+	MFP_PIN_GPIO91,
+	MFP_PIN_GPIO92,
+	MFP_PIN_GPIO93,
+	MFP_PIN_GPIO94,
+	MFP_PIN_GPIO95,
+	MFP_PIN_GPIO96,
+	MFP_PIN_GPIO97,
+	MFP_PIN_GPIO98,
+	MFP_PIN_GPIO99,
+	MFP_PIN_GPIO100,
+	MFP_PIN_GPIO101,
+	MFP_PIN_GPIO102,
+	MFP_PIN_GPIO103,
+	MFP_PIN_GPIO104,
+	MFP_PIN_GPIO105,
+	MFP_PIN_GPIO106,
+	MFP_PIN_GPIO107,
+	MFP_PIN_GPIO108,
+	MFP_PIN_GPIO109,
+	MFP_PIN_GPIO110,
+	MFP_PIN_GPIO111,
+	MFP_PIN_GPIO112,
+	MFP_PIN_GPIO113,
+	MFP_PIN_GPIO114,
+	MFP_PIN_GPIO115,
+	MFP_PIN_GPIO116,
+	MFP_PIN_GPIO117,
+	MFP_PIN_GPIO118,
+	MFP_PIN_GPIO119,
+	MFP_PIN_GPIO120,
+	MFP_PIN_GPIO121,
+	MFP_PIN_GPIO122,
+	MFP_PIN_GPIO123,
+	MFP_PIN_GPIO124,
+	MFP_PIN_GPIO125,
+	MFP_PIN_GPIO126,
+	MFP_PIN_GPIO127,
+
+	MFP_PIN_GPIO128,
+	MFP_PIN_GPIO129,
+	MFP_PIN_GPIO130,
+	MFP_PIN_GPIO131,
+	MFP_PIN_GPIO132,
+	MFP_PIN_GPIO133,
+	MFP_PIN_GPIO134,
+	MFP_PIN_GPIO135,
+	MFP_PIN_GPIO136,
+	MFP_PIN_GPIO137,
+	MFP_PIN_GPIO138,
+	MFP_PIN_GPIO139,
+	MFP_PIN_GPIO140,
+	MFP_PIN_GPIO141,
+	MFP_PIN_GPIO142,
+	MFP_PIN_GPIO143,
+	MFP_PIN_GPIO144,
+	MFP_PIN_GPIO145,
+	MFP_PIN_GPIO146,
+	MFP_PIN_GPIO147,
+	MFP_PIN_GPIO148,
+	MFP_PIN_GPIO149,
+	MFP_PIN_GPIO150,
+	MFP_PIN_GPIO151,
+	MFP_PIN_GPIO152,
+	MFP_PIN_GPIO153,
+	MFP_PIN_GPIO154,
+	MFP_PIN_GPIO155,
+	MFP_PIN_GPIO156,
+	MFP_PIN_GPIO157,
+	MFP_PIN_GPIO158,
+	MFP_PIN_GPIO159,
+	MFP_PIN_GPIO160,
+	MFP_PIN_GPIO161,
+	MFP_PIN_GPIO162,
+	MFP_PIN_GPIO163,
+	MFP_PIN_GPIO164,
+	MFP_PIN_GPIO165,
+	MFP_PIN_GPIO166,
+	MFP_PIN_GPIO167,
+	MFP_PIN_GPIO168,
+	MFP_PIN_GPIO169,
+	MFP_PIN_GPIO170,
+	MFP_PIN_GPIO171,
+	MFP_PIN_GPIO172,
+	MFP_PIN_GPIO173,
+	MFP_PIN_GPIO174,
+	MFP_PIN_GPIO175,
+	MFP_PIN_GPIO176,
+	MFP_PIN_GPIO177,
+	MFP_PIN_GPIO178,
+	MFP_PIN_GPIO179,
+	MFP_PIN_GPIO180,
+	MFP_PIN_GPIO181,
+	MFP_PIN_GPIO182,
+	MFP_PIN_GPIO183,
+	MFP_PIN_GPIO184,
+	MFP_PIN_GPIO185,
+	MFP_PIN_GPIO186,
+	MFP_PIN_GPIO187,
+	MFP_PIN_GPIO188,
+	MFP_PIN_GPIO189,
+	MFP_PIN_GPIO190,
+	MFP_PIN_GPIO191,
+
+	MFP_PIN_GPIO255 = 255,
+
+	MFP_PIN_GPIO0_2,
+	MFP_PIN_GPIO1_2,
+	MFP_PIN_GPIO2_2,
+	MFP_PIN_GPIO3_2,
+	MFP_PIN_GPIO4_2,
+	MFP_PIN_GPIO5_2,
+	MFP_PIN_GPIO6_2,
+	MFP_PIN_GPIO7_2,
+	MFP_PIN_GPIO8_2,
+	MFP_PIN_GPIO9_2,
+	MFP_PIN_GPIO10_2,
+	MFP_PIN_GPIO11_2,
+	MFP_PIN_GPIO12_2,
+	MFP_PIN_GPIO13_2,
+	MFP_PIN_GPIO14_2,
+	MFP_PIN_GPIO15_2,
+	MFP_PIN_GPIO16_2,
+	MFP_PIN_GPIO17_2,
+
+	MFP_PIN_ULPI_STP,
+	MFP_PIN_ULPI_NXT,
+	MFP_PIN_ULPI_DIR,
+
+	MFP_PIN_nXCVREN,
+	MFP_PIN_DF_CLE_nOE,
+	MFP_PIN_DF_nADV1_ALE,
+	MFP_PIN_DF_SCLK_E,
+	MFP_PIN_DF_SCLK_S,
+	MFP_PIN_nBE0,
+	MFP_PIN_nBE1,
+	MFP_PIN_DF_nADV2_ALE,
+	MFP_PIN_DF_INT_RnB,
+	MFP_PIN_DF_nCS0,
+	MFP_PIN_DF_nCS1,
+	MFP_PIN_nLUA,
+	MFP_PIN_nLLA,
+	MFP_PIN_DF_nWE,
+	MFP_PIN_DF_ALE_nWE,
+	MFP_PIN_DF_nRE_nOE,
+	MFP_PIN_DF_ADDR0,
+	MFP_PIN_DF_ADDR1,
+	MFP_PIN_DF_ADDR2,
+	MFP_PIN_DF_ADDR3,
+	MFP_PIN_DF_IO0,
+	MFP_PIN_DF_IO1,
+	MFP_PIN_DF_IO2,
+	MFP_PIN_DF_IO3,
+	MFP_PIN_DF_IO4,
+	MFP_PIN_DF_IO5,
+	MFP_PIN_DF_IO6,
+	MFP_PIN_DF_IO7,
+	MFP_PIN_DF_IO8,
+	MFP_PIN_DF_IO9,
+	MFP_PIN_DF_IO10,
+	MFP_PIN_DF_IO11,
+	MFP_PIN_DF_IO12,
+	MFP_PIN_DF_IO13,
+	MFP_PIN_DF_IO14,
+	MFP_PIN_DF_IO15,
+	MFP_PIN_DF_nCS0_SM_nCS2,
+	MFP_PIN_DF_nCS1_SM_nCS3,
+	MFP_PIN_SM_nCS0,
+	MFP_PIN_SM_nCS1,
+	MFP_PIN_DF_WEn,
+	MFP_PIN_DF_REn,
+	MFP_PIN_DF_CLE_SM_OEn,
+	MFP_PIN_DF_ALE_SM_WEn,
+	MFP_PIN_DF_RDY0,
+	MFP_PIN_DF_RDY1,
+
+	MFP_PIN_SM_SCLK,
+	MFP_PIN_SM_BE0,
+	MFP_PIN_SM_BE1,
+	MFP_PIN_SM_ADV,
+	MFP_PIN_SM_ADVMUX,
+	MFP_PIN_SM_RDY,
+
+	MFP_PIN_MMC1_DAT7,
+	MFP_PIN_MMC1_DAT6,
+	MFP_PIN_MMC1_DAT5,
+	MFP_PIN_MMC1_DAT4,
+	MFP_PIN_MMC1_DAT3,
+	MFP_PIN_MMC1_DAT2,
+	MFP_PIN_MMC1_DAT1,
+	MFP_PIN_MMC1_DAT0,
+	MFP_PIN_MMC1_CMD,
+	MFP_PIN_MMC1_CLK,
+	MFP_PIN_MMC1_CD,
+	MFP_PIN_MMC1_WP,
+
+	/* additional pins on PXA930 */
+	MFP_PIN_GSIM_UIO,
+	MFP_PIN_GSIM_UCLK,
+	MFP_PIN_GSIM_UDET,
+	MFP_PIN_GSIM_nURST,
+	MFP_PIN_PMIC_INT,
+	MFP_PIN_RDY,
+
+	/* additional pins on MMP2 */
+	MFP_PIN_TWSI1_SCL,
+	MFP_PIN_TWSI1_SDA,
+	MFP_PIN_TWSI4_SCL,
+	MFP_PIN_TWSI4_SDA,
+	MFP_PIN_CLK_REQ,
+
+	MFP_PIN_MAX,
+};
+
+/*
+ * a possible MFP configuration is represented by a 32-bit integer
+ *
+ * bit  0.. 9 - MFP Pin Number (1024 Pins Maximum)
+ * bit 10..12 - Alternate Function Selection
+ * bit 13..15 - Drive Strength
+ * bit 16..18 - Low Power Mode State
+ * bit 19..20 - Low Power Mode Edge Detection
+ * bit 21..22 - Run Mode Pull State
+ *
+ * to facilitate the definition, the following macros are provided
+ *
+ * MFP_CFG_DEFAULT - default MFP configuration value, with
+ * 		  alternate function = 0,
+ * 		  drive strength = fast 3mA (MFP_DS03X)
+ * 		  low power mode = default
+ * 		  edge detection = none
+ *
+ * MFP_CFG	- default MFPR value with alternate function
+ * MFP_CFG_DRV	- default MFPR value with alternate function and
+ * 		  pin drive strength
+ * MFP_CFG_LPM	- default MFPR value with alternate function and
+ * 		  low power mode
+ * MFP_CFG_X	- default MFPR value with alternate function,
+ * 		  pin drive strength and low power mode
+ */
+
+typedef unsigned long mfp_cfg_t;
+
+#define MFP_PIN(x)		((x) & 0x3ff)
+
+#define MFP_AF0			(0x0 << 10)
+#define MFP_AF1			(0x1 << 10)
+#define MFP_AF2			(0x2 << 10)
+#define MFP_AF3			(0x3 << 10)
+#define MFP_AF4			(0x4 << 10)
+#define MFP_AF5			(0x5 << 10)
+#define MFP_AF6			(0x6 << 10)
+#define MFP_AF7			(0x7 << 10)
+#define MFP_AF_MASK		(0x7 << 10)
+#define MFP_AF(x)		(((x) >> 10) & 0x7)
+
+#define MFP_DS01X		(0x0 << 13)
+#define MFP_DS02X		(0x1 << 13)
+#define MFP_DS03X		(0x2 << 13)
+#define MFP_DS04X		(0x3 << 13)
+#define MFP_DS06X		(0x4 << 13)
+#define MFP_DS08X		(0x5 << 13)
+#define MFP_DS10X		(0x6 << 13)
+#define MFP_DS13X		(0x7 << 13)
+#define MFP_DS_MASK		(0x7 << 13)
+#define MFP_DS(x)		(((x) >> 13) & 0x7)
+
+#define MFP_LPM_DEFAULT		(0x0 << 16)
+#define MFP_LPM_DRIVE_LOW	(0x1 << 16)
+#define MFP_LPM_DRIVE_HIGH	(0x2 << 16)
+#define MFP_LPM_PULL_LOW	(0x3 << 16)
+#define MFP_LPM_PULL_HIGH	(0x4 << 16)
+#define MFP_LPM_FLOAT		(0x5 << 16)
+#define MFP_LPM_INPUT		(0x6 << 16)
+#define MFP_LPM_STATE_MASK	(0x7 << 16)
+#define MFP_LPM_STATE(x)	(((x) >> 16) & 0x7)
+
+#define MFP_LPM_EDGE_NONE	(0x0 << 19)
+#define MFP_LPM_EDGE_RISE	(0x1 << 19)
+#define MFP_LPM_EDGE_FALL	(0x2 << 19)
+#define MFP_LPM_EDGE_BOTH	(0x3 << 19)
+#define MFP_LPM_EDGE_MASK	(0x3 << 19)
+#define MFP_LPM_EDGE(x)		(((x) >> 19) & 0x3)
+
+#define MFP_PULL_NONE		(0x0 << 21)
+#define MFP_PULL_LOW		(0x1 << 21)
+#define MFP_PULL_HIGH		(0x2 << 21)
+#define MFP_PULL_BOTH		(0x3 << 21)
+#define MFP_PULL_FLOAT		(0x4 << 21)
+#define MFP_PULL_MASK		(0x7 << 21)
+#define MFP_PULL(x)		(((x) >> 21) & 0x7)
+
+#define MFP_CFG_DEFAULT		(MFP_AF0 | MFP_DS03X | MFP_LPM_DEFAULT |\
+				 MFP_LPM_EDGE_NONE | MFP_PULL_NONE)
+
+#define MFP_CFG(pin, af)		\
+	((MFP_CFG_DEFAULT & ~MFP_AF_MASK) |\
+	 (MFP_PIN(MFP_PIN_##pin) | MFP_##af))
+
+#define MFP_CFG_DRV(pin, af, drv)	\
+	((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK)) |\
+	 (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv))
+
+#define MFP_CFG_LPM(pin, af, lpm)	\
+	((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_LPM_STATE_MASK)) |\
+	 (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_LPM_##lpm))
+
+#define MFP_CFG_X(pin, af, drv, lpm)	\
+	((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK | MFP_LPM_STATE_MASK)) |\
+	 (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv | MFP_LPM_##lpm))
+
+#if defined(CONFIG_PXA3xx) || defined(CONFIG_ARCH_MMP)
+/*
+ * each MFP pin will have a MFPR register, since the offset of the
+ * register varies between processors, the processor specific code
+ * should initialize the pin offsets by mfp_init()
+ *
+ * mfp_init_base() - accepts a virtual base for all MFPR registers and
+ * initialize the MFP table to a default state
+ *
+ * mfp_init_addr() - accepts a table of "mfp_addr_map" structure, which
+ * represents a range of MFP pins from "start" to "end", with the offset
+ * beginning at "offset", to define a single pin, let "end" = -1.
+ *
+ * use
+ *
+ * MFP_ADDR_X() to define a range of pins
+ * MFP_ADDR()   to define a single pin
+ * MFP_ADDR_END to signal the end of pin offset definitions
+ */
+struct mfp_addr_map {
+	unsigned int	start;
+	unsigned int	end;
+	unsigned long	offset;
+};
+
+#define MFP_ADDR_X(start, end, offset) \
+	{ MFP_PIN_##start, MFP_PIN_##end, offset }
+
+#define MFP_ADDR(pin, offset) \
+	{ MFP_PIN_##pin, -1, offset }
+
+#define MFP_ADDR_END	{ MFP_PIN_INVALID, 0 }
+
+void mfp_init_base(void __iomem *mfpr_base);
+void mfp_init_addr(struct mfp_addr_map *map);
+
+/*
+ * mfp_{read, write}()	- for direct read/write access to the MFPR register
+ * mfp_config()		- for configuring a group of MFPR registers
+ * mfp_config_lpm()	- configuring all low power MFPR registers for suspend
+ * mfp_config_run()	- configuring all run time  MFPR registers after resume
+ */
+unsigned long mfp_read(int mfp);
+void mfp_write(int mfp, unsigned long mfpr_val);
+void mfp_config(unsigned long *mfp_cfgs, int num);
+void mfp_config_run(void);
+void mfp_config_lpm(void);
+#endif /* CONFIG_PXA3xx || CONFIG_ARCH_MMP */
+
+#endif /* __ASM_PLAT_MFP_H */
-- 
cgit v1.2.3


From 3b5eed3c71a2fb60aa4405ad92a2a6ad2677f220 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 3 May 2022 13:54:58 -0700
Subject: netfs: Eliminate Clang randstruct warning

Clang's structure layout randomization feature gets upset when it sees
struct inode (which is randomized) cast to struct netfs_i_context. This
is due to seeing the inode pointer as being treated as an array of inodes,
rather than "something else, following struct inode".

Since netfs can't use container_of() (since it doesn't know what the
true containing struct is), it uses this direct offset instead. Adjust
the code to better reflect what is happening: an arbitrary pointer is
being adjusted and cast to something else: use a "void *" for the math.
The resulting binary output is the same, but Clang no longer sees an
unexpected cross-structure cast:

In file included from ../fs/nfs/inode.c:50:
In file included from ../fs/nfs/fscache.h:15:
In file included from ../include/linux/fscache.h:18:
../include/linux/netfs.h:298:9: error: casting from randomized structure pointer type 'struct inode *' to 'struct netfs_i_context *'
        return (struct netfs_i_context *)(inode + 1);
               ^
1 error generated.

Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220503205503.3054173-2-keescook@chromium.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/lkml/7562f8eccd7cc0e447becfe9912179088784e3b9.camel@kernel.org
---
 include/linux/netfs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index c7bf1eaf51d5..0c33b715cbfd 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -295,7 +295,7 @@ extern void netfs_stats_show(struct seq_file *);
  */
 static inline struct netfs_i_context *netfs_i_context(struct inode *inode)
 {
-	return (struct netfs_i_context *)(inode + 1);
+	return (void *)inode + sizeof(*inode);
 }
 
 /**
@@ -307,7 +307,7 @@ static inline struct netfs_i_context *netfs_i_context(struct inode *inode)
  */
 static inline struct inode *netfs_inode(struct netfs_i_context *ctx)
 {
-	return ((struct inode *)ctx) - 1;
+	return (void *)ctx - sizeof(struct inode);
 }
 
 /**
-- 
cgit v1.2.3


From 595b893e2087de306d0781795fb8ec47873596a6 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 3 May 2022 13:55:00 -0700
Subject: randstruct: Reorganize Kconfigs and attribute macros

In preparation for Clang supporting randstruct, reorganize the Kconfigs,
move the attribute macros, and generalize the feature to be named
CONFIG_RANDSTRUCT for on/off, CONFIG_RANDSTRUCT_FULL for the full
randomization mode, and CONFIG_RANDSTRUCT_PERFORMANCE for the cache-line
sized mode.

Cc: linux-hardening@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220503205503.3054173-4-keescook@chromium.org
---
 Documentation/kbuild/reproducible-builds.rst |  7 ++--
 arch/riscv/Kconfig                           |  2 +-
 arch/x86/mm/pti.c                            |  2 +-
 include/linux/compiler-gcc.h                 |  8 ----
 include/linux/compiler_types.h               | 14 +++----
 include/linux/vermagic.h                     |  8 ++--
 kernel/panic.c                               |  2 +-
 scripts/Makefile.gcc-plugins                 |  4 +-
 scripts/gcc-plugins/Kconfig                  | 38 -----------------
 security/Kconfig.hardening                   | 62 ++++++++++++++++++++++++++++
 10 files changed, 81 insertions(+), 66 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst
index 3b25655e441b..81ff30505d35 100644
--- a/Documentation/kbuild/reproducible-builds.rst
+++ b/Documentation/kbuild/reproducible-builds.rst
@@ -99,10 +99,9 @@ unreproducible parts can be treated as sources:
 Structure randomisation
 -----------------------
 
-If you enable ``CONFIG_GCC_PLUGIN_RANDSTRUCT``, you will need to
-pre-generate the random seed in
-``scripts/gcc-plugins/randomize_layout_seed.h`` so the same value
-is used in rebuilds.
+If you enable ``CONFIG_RANDSTRUCT``, you will need to pre-generate
+the random seed in ``scripts/gcc-plugins/randomize_layout_seed.h``
+so the same value is used in rebuilds.
 
 Debug info conflicts
 --------------------
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 00fd9c548f26..3ac2a81a55eb 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -468,7 +468,7 @@ config CC_HAVE_STACKPROTECTOR_TLS
 
 config STACKPROTECTOR_PER_TASK
 	def_bool y
-	depends on !GCC_PLUGIN_RANDSTRUCT
+	depends on !RANDSTRUCT
 	depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS
 
 config PHYS_RAM_BASE_FIXED
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 5d5c7bb50ce9..ffe3b3a087fe 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -540,7 +540,7 @@ static inline bool pti_kernel_image_global_ok(void)
 	 * cases where RANDSTRUCT is in use to help keep the layout a
 	 * secret.
 	 */
-	if (IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT))
+	if (IS_ENABLED(CONFIG_RANDSTRUCT))
 		return false;
 
 	return true;
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 52299c957c98..a0c55eeaeaf1 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -66,14 +66,6 @@
 		__builtin_unreachable();	\
 	} while (0)
 
-#if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__)
-#define __randomize_layout __attribute__((randomize_layout))
-#define __no_randomize_layout __attribute__((no_randomize_layout))
-/* This anon struct can add padding, so only enable it under randstruct. */
-#define randomized_struct_fields_start	struct {
-#define randomized_struct_fields_end	} __randomize_layout;
-#endif
-
 /*
  * GCC 'asm goto' miscompiles certain code sequences:
  *
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 1c2c33ae1b37..d08dfcb0ac68 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -242,15 +242,15 @@ struct ftrace_likely_data {
 # define __latent_entropy
 #endif
 
-#ifndef __randomize_layout
+#if defined(RANDSTRUCT) && !defined(__CHECKER__)
+# define __randomize_layout __designated_init __attribute__((randomize_layout))
+# define __no_randomize_layout __attribute__((no_randomize_layout))
+/* This anon struct can add padding, so only enable it under randstruct. */
+# define randomized_struct_fields_start	struct {
+# define randomized_struct_fields_end	} __randomize_layout;
+#else
 # define __randomize_layout __designated_init
-#endif
-
-#ifndef __no_randomize_layout
 # define __no_randomize_layout
-#endif
-
-#ifndef randomized_struct_fields_start
 # define randomized_struct_fields_start
 # define randomized_struct_fields_end
 #endif
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index 329d63babaeb..efb51a2da599 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -32,11 +32,11 @@
 #else
 #define MODULE_VERMAGIC_MODVERSIONS ""
 #endif
-#ifdef RANDSTRUCT_PLUGIN
+#ifdef RANDSTRUCT
 #include <generated/randomize_layout_hash.h>
-#define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED
+#define MODULE_RANDSTRUCT "RANDSTRUCT_" RANDSTRUCT_HASHED_SEED
 #else
-#define MODULE_RANDSTRUCT_PLUGIN
+#define MODULE_RANDSTRUCT
 #endif
 
 #define VERMAGIC_STRING 						\
@@ -44,6 +44,6 @@
 	MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT 			\
 	MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS	\
 	MODULE_ARCH_VERMAGIC						\
-	MODULE_RANDSTRUCT_PLUGIN
+	MODULE_RANDSTRUCT
 
 #endif /* _LINUX_VERMAGIC_H */
diff --git a/kernel/panic.c b/kernel/panic.c
index eb4dfb932c85..8355b19676f8 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -48,7 +48,7 @@ unsigned int __read_mostly sysctl_oops_all_cpu_backtrace;
 
 int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
 static unsigned long tainted_mask =
-	IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
+	IS_ENABLED(CONFIG_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
 static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index 927c3dd57f84..827c47ce5c73 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -24,8 +24,8 @@ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK)		\
 
 gcc-plugin-$(CONFIG_GCC_PLUGIN_RANDSTRUCT)	+= randomize_layout_plugin.so
 gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT)		\
-		+= -DRANDSTRUCT_PLUGIN
-gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT_PERFORMANCE)	\
+		+= -DRANDSTRUCT
+gcc-plugin-cflags-$(CONFIG_RANDSTRUCT_PERFORMANCE)		\
 		+= -fplugin-arg-randomize_layout_plugin-performance-mode
 
 gcc-plugin-$(CONFIG_GCC_PLUGIN_STACKLEAK)	+= stackleak_plugin.so
diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig
index 51d81c3f03d6..e383cda05367 100644
--- a/scripts/gcc-plugins/Kconfig
+++ b/scripts/gcc-plugins/Kconfig
@@ -46,44 +46,6 @@ config GCC_PLUGIN_LATENT_ENTROPY
 	   * https://grsecurity.net/
 	   * https://pax.grsecurity.net/
 
-config GCC_PLUGIN_RANDSTRUCT
-	bool "Randomize layout of sensitive kernel structures"
-	select MODVERSIONS if MODULES
-	help
-	  If you say Y here, the layouts of structures that are entirely
-	  function pointers (and have not been manually annotated with
-	  __no_randomize_layout), or structures that have been explicitly
-	  marked with __randomize_layout, will be randomized at compile-time.
-	  This can introduce the requirement of an additional information
-	  exposure vulnerability for exploits targeting these structure
-	  types.
-
-	  Enabling this feature will introduce some performance impact,
-	  slightly increase memory usage, and prevent the use of forensic
-	  tools like Volatility against the system (unless the kernel
-	  source tree isn't cleaned after kernel installation).
-
-	  The seed used for compilation is located at
-	  scripts/gcc-plugins/randomize_layout_seed.h.  It remains after
-	  a make clean to allow for external modules to be compiled with
-	  the existing seed and will be removed by a make mrproper or
-	  make distclean.
-
-	  This plugin was ported from grsecurity/PaX. More information at:
-	   * https://grsecurity.net/
-	   * https://pax.grsecurity.net/
-
-config GCC_PLUGIN_RANDSTRUCT_PERFORMANCE
-	bool "Use cacheline-aware structure randomization"
-	depends on GCC_PLUGIN_RANDSTRUCT
-	depends on !COMPILE_TEST	# do not reduce test coverage
-	help
-	  If you say Y here, the RANDSTRUCT randomization will make a
-	  best effort at restricting randomization to cacheline-sized
-	  groups of elements.  It will further not randomize bitfields
-	  in structures.  This reduces the performance hit of RANDSTRUCT
-	  at the cost of weakened randomization.
-
 config GCC_PLUGIN_ARM_SSP_PER_TASK
 	bool
 	depends on GCC_PLUGINS && ARM
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index ded4d7c0d132..364e3f8c6eea 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -266,4 +266,66 @@ config ZERO_CALL_USED_REGS
 
 endmenu
 
+choice
+	prompt "Randomize layout of sensitive kernel structures"
+	default RANDSTRUCT_FULL if COMPILE_TEST && GCC_PLUGINS
+	default RANDSTRUCT_NONE
+	help
+	  If you enable this, the layouts of structures that are entirely
+	  function pointers (and have not been manually annotated with
+	  __no_randomize_layout), or structures that have been explicitly
+	  marked with __randomize_layout, will be randomized at compile-time.
+	  This can introduce the requirement of an additional information
+	  exposure vulnerability for exploits targeting these structure
+	  types.
+
+	  Enabling this feature will introduce some performance impact,
+	  slightly increase memory usage, and prevent the use of forensic
+	  tools like Volatility against the system (unless the kernel
+	  source tree isn't cleaned after kernel installation).
+
+	  The seed used for compilation is located at
+	  scripts/randomize_layout_seed.h. It remains after a "make clean"
+	  to allow for external modules to be compiled with the existing
+	  seed and will be removed by a "make mrproper" or "make distclean".
+
+	config RANDSTRUCT_NONE
+		bool "Disable structure layout randomization"
+		help
+		  Build normally: no structure layout randomization.
+
+	config RANDSTRUCT_FULL
+		bool "Fully randomize structure layout"
+		depends on GCC_PLUGINS
+		select MODVERSIONS if MODULES
+		help
+		  Fully randomize the member layout of sensitive
+		  structures as much as possible, which may have both a
+		  memory size and performance impact.
+
+	config RANDSTRUCT_PERFORMANCE
+		bool "Limit randomization of structure layout to cache-lines"
+		depends on GCC_PLUGINS
+		select MODVERSIONS if MODULES
+		help
+		  Randomization of sensitive kernel structures will make a
+		  best effort at restricting randomization to cacheline-sized
+		  groups of members. It will further not randomize bitfields
+		  in structures. This reduces the performance hit of RANDSTRUCT
+		  at the cost of weakened randomization.
+endchoice
+
+config RANDSTRUCT
+	def_bool !RANDSTRUCT_NONE
+
+config GCC_PLUGIN_RANDSTRUCT
+	def_bool GCC_PLUGINS && RANDSTRUCT
+	help
+	  Use GCC plugin to randomize structure layout.
+
+	  This plugin was ported from grsecurity/PaX. More
+	  information at:
+	   * https://grsecurity.net/
+	   * https://pax.grsecurity.net/
+
 endmenu
-- 
cgit v1.2.3


From be2b34fa9be31c60a95989f984c9a5d40cd781b6 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 3 May 2022 13:55:02 -0700
Subject: randstruct: Move seed generation into scripts/basic/

To enable Clang randstruct support, move the structure layout
randomization seed generation out of scripts/gcc-plugins/ into
scripts/basic/ so it happens early enough that it can be used by either
compiler implementation. The gcc-plugin still builds its own header file,
but now does so from the common "randstruct.seed" file.

Cc: linux-hardening@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220503205503.3054173-6-keescook@chromium.org
---
 Documentation/dontdiff                       |  1 +
 Documentation/kbuild/reproducible-builds.rst |  5 +++--
 include/linux/vermagic.h                     |  2 +-
 scripts/basic/.gitignore                     |  1 +
 scripts/basic/Makefile                       | 11 +++++++++++
 scripts/gcc-plugins/Makefile                 | 15 ++++++++++-----
 scripts/gcc-plugins/gen-random-seed.sh       |  9 ---------
 scripts/gen-randstruct-seed.sh               |  7 +++++++
 security/Kconfig.hardening                   |  9 +++++----
 9 files changed, 39 insertions(+), 21 deletions(-)
 delete mode 100755 scripts/gcc-plugins/gen-random-seed.sh
 create mode 100755 scripts/gen-randstruct-seed.sh

(limited to 'include/linux')

diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 910b30a2a7d9..352ff53a2306 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -211,6 +211,7 @@ r200_reg_safe.h
 r300_reg_safe.h
 r420_reg_safe.h
 r600_reg_safe.h
+randstruct.seed
 randomize_layout_hash.h
 randomize_layout_seed.h
 recordmcount
diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst
index 81ff30505d35..071f0151a7a4 100644
--- a/Documentation/kbuild/reproducible-builds.rst
+++ b/Documentation/kbuild/reproducible-builds.rst
@@ -100,8 +100,9 @@ Structure randomisation
 -----------------------
 
 If you enable ``CONFIG_RANDSTRUCT``, you will need to pre-generate
-the random seed in ``scripts/gcc-plugins/randomize_layout_seed.h``
-so the same value is used in rebuilds.
+the random seed in ``scripts/basic/randstruct.seed`` so the same
+value is used by each build. See ``scripts/gen-randstruct-seed.sh``
+for details.
 
 Debug info conflicts
 --------------------
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index efb51a2da599..a54046bf37e5 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -33,7 +33,7 @@
 #define MODULE_VERMAGIC_MODVERSIONS ""
 #endif
 #ifdef RANDSTRUCT
-#include <generated/randomize_layout_hash.h>
+#include <generated/randstruct_hash.h>
 #define MODULE_RANDSTRUCT "RANDSTRUCT_" RANDSTRUCT_HASHED_SEED
 #else
 #define MODULE_RANDSTRUCT
diff --git a/scripts/basic/.gitignore b/scripts/basic/.gitignore
index 961c91c8a884..07c195f605a1 100644
--- a/scripts/basic/.gitignore
+++ b/scripts/basic/.gitignore
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /fixdep
+/randstruct.seed
diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile
index eeb6a38c5551..dd289a6725ac 100644
--- a/scripts/basic/Makefile
+++ b/scripts/basic/Makefile
@@ -3,3 +3,14 @@
 # fixdep: used to generate dependency information during build process
 
 hostprogs-always-y	+= fixdep
+
+# randstruct: the seed is needed before building the gcc-plugin or
+# before running a Clang kernel build.
+gen-randstruct-seed	:= $(srctree)/scripts/gen-randstruct-seed.sh
+quiet_cmd_create_randstruct_seed = GENSEED $@
+cmd_create_randstruct_seed = \
+	$(CONFIG_SHELL) $(gen-randstruct-seed) \
+		$@ $(objtree)/include/generated/randstruct_hash.h
+$(obj)/randstruct.seed: $(gen-randstruct-seed) FORCE
+	$(call if_changed,create_randstruct_seed)
+always-$(CONFIG_RANDSTRUCT) += randstruct.seed
diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile
index 1952d3bb80c6..148f4639cf09 100644
--- a/scripts/gcc-plugins/Makefile
+++ b/scripts/gcc-plugins/Makefile
@@ -1,12 +1,17 @@
 # SPDX-License-Identifier: GPL-2.0
 
-$(obj)/randomize_layout_plugin.so: $(objtree)/$(obj)/randomize_layout_seed.h
-quiet_cmd_create_randomize_layout_seed = GENSEED $@
+$(obj)/randomize_layout_plugin.so: $(obj)/randomize_layout_seed.h
+quiet_cmd_create_randomize_layout_seed = SEEDHDR $@
 cmd_create_randomize_layout_seed = \
-  $(CONFIG_SHELL) $(srctree)/$(src)/gen-random-seed.sh $@ $(objtree)/include/generated/randomize_layout_hash.h
-$(objtree)/$(obj)/randomize_layout_seed.h: FORCE
+	SEED=$$(cat $(filter-out FORCE,$^) </dev/null); \
+	echo '/*' > $@; \
+	echo ' * This file is automatically generated. Keep it private.' >> $@; \
+	echo ' * Exposing this value will expose the layout of randomized structures.' >> $@; \
+	echo ' */' >> $@; \
+	echo "const char *randstruct_seed = \"$$SEED\";" >> $@
+$(obj)/randomize_layout_seed.h: $(objtree)/scripts/basic/randstruct.seed FORCE
 	$(call if_changed,create_randomize_layout_seed)
-targets += randomize_layout_seed.h randomize_layout_hash.h
+targets += randomize_layout_seed.h
 
 # Build rules for plugins
 #
diff --git a/scripts/gcc-plugins/gen-random-seed.sh b/scripts/gcc-plugins/gen-random-seed.sh
deleted file mode 100755
index 68af5cc20a64..000000000000
--- a/scripts/gcc-plugins/gen-random-seed.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-if [ ! -f "$1" ]; then
-	SEED=`od -A n -t x8 -N 32 /dev/urandom | tr -d ' \n'`
-	echo "const char *randstruct_seed = \"$SEED\";" > "$1"
-	HASH=`echo -n "$SEED" | sha256sum | cut -d" " -f1 | tr -d ' \n'`
-	echo "#define RANDSTRUCT_HASHED_SEED \"$HASH\"" > "$2"
-fi
diff --git a/scripts/gen-randstruct-seed.sh b/scripts/gen-randstruct-seed.sh
new file mode 100755
index 000000000000..61017b36c464
--- /dev/null
+++ b/scripts/gen-randstruct-seed.sh
@@ -0,0 +1,7 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+SEED=$(od -A n -t x8 -N 32 /dev/urandom | tr -d ' \n')
+echo "$SEED" > "$1"
+HASH=$(echo -n "$SEED" | sha256sum | cut -d" " -f1)
+echo "#define RANDSTRUCT_HASHED_SEED \"$HASH\"" > "$2"
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index 364e3f8c6eea..0277ba578779 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -284,10 +284,11 @@ choice
 	  tools like Volatility against the system (unless the kernel
 	  source tree isn't cleaned after kernel installation).
 
-	  The seed used for compilation is located at
-	  scripts/randomize_layout_seed.h. It remains after a "make clean"
-	  to allow for external modules to be compiled with the existing
-	  seed and will be removed by a "make mrproper" or "make distclean".
+	  The seed used for compilation is in scripts/basic/randomize.seed.
+	  It remains after a "make clean" to allow for external modules to
+	  be compiled with the existing seed and will be removed by a
+	  "make mrproper" or "make distclean". This file should not be made
+	  public, or the structure layout can be determined.
 
 	config RANDSTRUCT_NONE
 		bool "Disable structure layout randomization"
-- 
cgit v1.2.3


From 9ec79840d6afaf472294588a6bbe145bcdffa28b Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 27 Apr 2022 18:31:19 +0100
Subject: stackleak: rework stack low bound handling

In stackleak_task_init(), stackleak_track_stack(), and
__stackleak_erase(), we open-code skipping the STACK_END_MAGIC at the
bottom of the stack. Each case is implemented slightly differently, and
only the __stackleak_erase() case is commented.

In stackleak_task_init() and stackleak_track_stack() we unconditionally
add sizeof(unsigned long) to the lowest stack address. In
stackleak_task_init() we use end_of_stack() for this, and in
stackleak_track_stack() we use task_stack_page(). In __stackleak_erase()
we handle this by detecting if `kstack_ptr` has hit the stack end
boundary, and if so, conditionally moving it above the magic.

This patch adds a new stackleak_task_low_bound() helper which is used in
all three cases, which unconditionally adds sizeof(unsigned long) to the
lowest address on the task stack, with commentary as to why. This uses
end_of_stack() as stackleak_task_init() did prior to this patch, as this
is consistent with the code in kernel/fork.c which initializes the
STACK_END_MAGIC value.

In __stackleak_erase() we no longer need to check whether we've spilled
into the STACK_END_MAGIC value, as stackleak_track_stack() ensures that
`current->lowest_stack` stops immediately above this, and similarly the
poison scan will stop immediately above this.

For stackleak_task_init() and stackleak_track_stack() this results in no
change to code generation. For __stackleak_erase() the generated
assembly is slightly simpler and shorter.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-5-mark.rutland@arm.com
---
 include/linux/stackleak.h | 15 ++++++++++++++-
 kernel/stackleak.c        | 14 ++++----------
 2 files changed, 18 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h
index ccaab2043fcd..67430faa5c51 100644
--- a/include/linux/stackleak.h
+++ b/include/linux/stackleak.h
@@ -15,9 +15,22 @@
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 #include <asm/stacktrace.h>
 
+/*
+ * The lowest address on tsk's stack which we can plausibly erase.
+ */
+static __always_inline unsigned long
+stackleak_task_low_bound(const struct task_struct *tsk)
+{
+	/*
+	 * The lowest unsigned long on the task stack contains STACK_END_MAGIC,
+	 * which we must not corrupt.
+	 */
+	return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long);
+}
+
 static inline void stackleak_task_init(struct task_struct *t)
 {
-	t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long);
+	t->lowest_stack = stackleak_task_low_bound(t);
 # ifdef CONFIG_STACKLEAK_METRICS
 	t->prev_lowest_stack = t->lowest_stack;
 # endif
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index f7a0f8cf73c3..24b7cf01b297 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -72,9 +72,11 @@ late_initcall(stackleak_sysctls_init);
 
 static __always_inline void __stackleak_erase(void)
 {
+	const unsigned long task_stack_low = stackleak_task_low_bound(current);
+
 	/* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */
 	unsigned long kstack_ptr = current->lowest_stack;
-	unsigned long boundary = (unsigned long)end_of_stack(current);
+	unsigned long boundary = task_stack_low;
 	unsigned int poison_count = 0;
 	const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
 
@@ -88,13 +90,6 @@ static __always_inline void __stackleak_erase(void)
 		kstack_ptr -= sizeof(unsigned long);
 	}
 
-	/*
-	 * One 'long int' at the bottom of the thread stack is reserved and
-	 * should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y).
-	 */
-	if (kstack_ptr == boundary)
-		kstack_ptr += sizeof(unsigned long);
-
 #ifdef CONFIG_STACKLEAK_METRICS
 	current->prev_lowest_stack = kstack_ptr;
 #endif
@@ -140,8 +135,7 @@ void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
 	/* 'lowest_stack' should be aligned on the register width boundary */
 	sp = ALIGN(sp, sizeof(unsigned long));
 	if (sp < current->lowest_stack &&
-	    sp >= (unsigned long)task_stack_page(current) +
-						sizeof(unsigned long)) {
+	    sp >= stackleak_task_low_bound(current)) {
 		current->lowest_stack = sp;
 	}
 }
-- 
cgit v1.2.3


From 0cfa2ccd285d98ad62218add2eebdcfff69fb2c0 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 27 Apr 2022 18:31:21 +0100
Subject: stackleak: rework stack high bound handling

Prior to returning to userspace, we reset current->lowest_stack to a
reasonable high bound. Currently we do this by subtracting the arbitrary
value `THREAD_SIZE/64` from the top of the stack, for reasons lost to
history.

Looking at configurations today:

* On i386 where THREAD_SIZE is 8K, the bound will be 128 bytes. The
  pt_regs at the top of the stack is 68 bytes (with 0 to 16 bytes of
  padding above), and so this covers an additional portion of 44 to 60
  bytes.

* On x86_64 where THREAD_SIZE is at least 16K (up to 32K with KASAN) the
  bound will be at least 256 bytes (up to 512 with KASAN). The pt_regs
  at the top of the stack is 168 bytes, and so this cover an additional
  88 bytes of stack (up to 344 with KASAN).

* On arm64 where THREAD_SIZE is at least 16K (up to 64K with 64K pages
  and VMAP_STACK), the bound will be at least 256 bytes (up to 1024 with
  KASAN). The pt_regs at the top of the stack is 336 bytes, so this can
  fall within the pt_regs, or can cover an additional 688 bytes of
  stack.

Clearly the `THREAD_SIZE/64` value doesn't make much sense -- in the
worst case, this will cause more than 600 bytes of stack to be erased
for every syscall, even if actual stack usage were substantially
smaller.

This patches makes this slightly less nonsensical by consistently
resetting current->lowest_stack to the base of the task pt_regs. For
clarity and for consistency with the handling of the low bound, the
generation of the high bound is split into a helper with commentary
explaining why.

Since the pt_regs at the top of the stack will be clobbered upon the
next exception entry, we don't need to poison these at exception exit.
By using task_pt_regs() as the high stack boundary instead of
current_top_of_stack() we avoid some redundant poisoning, and the
compiler can share the address generation between the poisoning and
resetting of `current->lowest_stack`, making the generated code more
optimal.

It's not clear to me whether the existing `THREAD_SIZE/64` offset was a
dodgy heuristic to skip the pt_regs, or whether it was attempting to
minimize the number of times stackleak_check_stack() would have to
update `current->lowest_stack` when stack usage was shallow at the cost
of unconditionally poisoning a small portion of the stack for every exit
to userspace.

For now I've simply removed the offset, and if we need/want to minimize
updates for shallow stack usage it should be easy to add a better
heuristic atop, with appropriate commentary so we know what's going on.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-7-mark.rutland@arm.com
---
 include/linux/stackleak.h | 14 ++++++++++++++
 kernel/stackleak.c        | 19 ++++++++++++++-----
 2 files changed, 28 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h
index 67430faa5c51..467661aeb413 100644
--- a/include/linux/stackleak.h
+++ b/include/linux/stackleak.h
@@ -28,6 +28,20 @@ stackleak_task_low_bound(const struct task_struct *tsk)
 	return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long);
 }
 
+/*
+ * The address immediately after the highest address on tsk's stack which we
+ * can plausibly erase.
+ */
+static __always_inline unsigned long
+stackleak_task_high_bound(const struct task_struct *tsk)
+{
+	/*
+	 * The task's pt_regs lives at the top of the task stack and will be
+	 * overwritten by exception entry, so there's no need to erase them.
+	 */
+	return (unsigned long)task_pt_regs(tsk);
+}
+
 static inline void stackleak_task_init(struct task_struct *t)
 {
 	t->lowest_stack = stackleak_task_low_bound(t);
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index d5f684dc0a2d..ba346d46218f 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -73,6 +73,7 @@ late_initcall(stackleak_sysctls_init);
 static __always_inline void __stackleak_erase(void)
 {
 	const unsigned long task_stack_low = stackleak_task_low_bound(current);
+	const unsigned long task_stack_high = stackleak_task_high_bound(current);
 	unsigned long erase_low = current->lowest_stack;
 	unsigned long erase_high;
 	unsigned int poison_count = 0;
@@ -93,14 +94,22 @@ static __always_inline void __stackleak_erase(void)
 #endif
 
 	/*
-	 * Now write the poison value to the kernel stack between 'erase_low'
-	 * and 'erase_high'. We assume that the stack pointer doesn't change
-	 * when we write poison.
+	 * Write poison to the task's stack between 'erase_low' and
+	 * 'erase_high'.
+	 *
+	 * If we're running on a different stack (e.g. an entry trampoline
+	 * stack) we can erase everything below the pt_regs at the top of the
+	 * task stack.
+	 *
+	 * If we're running on the task stack itself, we must not clobber any
+	 * stack used by this function and its caller. We assume that this
+	 * function has a fixed-size stack frame, and the current stack pointer
+	 * doesn't change while we write poison.
 	 */
 	if (on_thread_stack())
 		erase_high = current_stack_pointer;
 	else
-		erase_high = current_top_of_stack();
+		erase_high = task_stack_high;
 
 	while (erase_low < erase_high) {
 		*(unsigned long *)erase_low = STACKLEAK_POISON;
@@ -108,7 +117,7 @@ static __always_inline void __stackleak_erase(void)
 	}
 
 	/* Reset the 'lowest_stack' value for the next syscall */
-	current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64;
+	current->lowest_stack = task_stack_high;
 }
 
 asmlinkage void noinstr stackleak_erase(void)
-- 
cgit v1.2.3


From 77cf2b6dee6680536a3109d894f1b1ccda3fc5bf Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 27 Apr 2022 18:31:22 +0100
Subject: stackleak: rework poison scanning

Currently we over-estimate the region of stack which must be erased.

To determine the region to be erased, we scan downwards for a contiguous
block of poison values (or the low bound of the stack). There are a few
minor problems with this today:

* When we find a block of poison values, we include this block within
  the region to erase.

  As this is included within the region to erase, this causes us to
  redundantly overwrite 'STACKLEAK_SEARCH_DEPTH' (128) bytes with
  poison.

* As the loop condition checks 'poison_count <= depth', it will run an
  additional iteration after finding the contiguous block of poison,
  decrementing 'erase_low' once more than necessary.

  As this is included within the region to erase, this causes us to
  redundantly overwrite an additional unsigned long with poison.

* As we always decrement 'erase_low' after checking an element on the
  stack, we always include the element below this within the region to
  erase.

  As this is included within the region to erase, this causes us to
  redundantly overwrite an additional unsigned long with poison.

  Note that this is not a functional problem. As the loop condition
  checks 'erase_low > task_stack_low', we'll never clobber the
  STACK_END_MAGIC. As we always decrement 'erase_low' after this, we'll
  never fail to erase the element immediately above the STACK_END_MAGIC.

In total, this can cause us to erase `128 + 2 * sizeof(unsigned long)`
bytes more than necessary, which is unfortunate.

This patch reworks the logic to find the address immediately above the
poisoned region, by finding the lowest non-poisoned address. This is
factored into a stackleak_find_top_of_poison() helper both for clarity
and so that this can be shared with the LKDTM test in subsequent
patches.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-8-mark.rutland@arm.com
---
 include/linux/stackleak.h | 26 ++++++++++++++++++++++++++
 kernel/stackleak.c        | 18 ++++--------------
 2 files changed, 30 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h
index 467661aeb413..c36e7a3b45e7 100644
--- a/include/linux/stackleak.h
+++ b/include/linux/stackleak.h
@@ -42,6 +42,32 @@ stackleak_task_high_bound(const struct task_struct *tsk)
 	return (unsigned long)task_pt_regs(tsk);
 }
 
+/*
+ * Find the address immediately above the poisoned region of the stack, where
+ * that region falls between 'low' (inclusive) and 'high' (exclusive).
+ */
+static __always_inline unsigned long
+stackleak_find_top_of_poison(const unsigned long low, const unsigned long high)
+{
+	const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
+	unsigned int poison_count = 0;
+	unsigned long poison_high = high;
+	unsigned long sp = high;
+
+	while (sp > low && poison_count < depth) {
+		sp -= sizeof(unsigned long);
+
+		if (*(unsigned long *)sp == STACKLEAK_POISON) {
+			poison_count++;
+		} else {
+			poison_count = 0;
+			poison_high = sp;
+		}
+	}
+
+	return poison_high;
+}
+
 static inline void stackleak_task_init(struct task_struct *t)
 {
 	t->lowest_stack = stackleak_task_low_bound(t);
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index ba346d46218f..afd54b8e10b8 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -74,20 +74,10 @@ static __always_inline void __stackleak_erase(void)
 {
 	const unsigned long task_stack_low = stackleak_task_low_bound(current);
 	const unsigned long task_stack_high = stackleak_task_high_bound(current);
-	unsigned long erase_low = current->lowest_stack;
-	unsigned long erase_high;
-	unsigned int poison_count = 0;
-	const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
-
-	/* Search for the poison value in the kernel stack */
-	while (erase_low > task_stack_low && poison_count <= depth) {
-		if (*(unsigned long *)erase_low == STACKLEAK_POISON)
-			poison_count++;
-		else
-			poison_count = 0;
-
-		erase_low -= sizeof(unsigned long);
-	}
+	unsigned long erase_low, erase_high;
+
+	erase_low = stackleak_find_top_of_poison(task_stack_low,
+						 current->lowest_stack);
 
 #ifdef CONFIG_STACKLEAK_METRICS
 	current->prev_lowest_stack = erase_low;
-- 
cgit v1.2.3


From 2e3afb42dd480d755cd7d97ca04586a5616c1a5e Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Sun, 8 May 2022 11:37:09 +0200
Subject: blk-mq: remove the error_count from struct request

The last two users were floppy.c and ataflop.c respectively, it was
verified that no other drivers makes use of this, so let's remove it.

Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Minh Yuan <yuanmingbuaa@gmail.com>
Cc: Denis Efremov <efremov@linux.com>,
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/blk-mq.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 7aa5c54901a9..9f07061418db 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -163,7 +163,6 @@ struct request {
 		struct rb_node rb_node;	/* sort/lookup */
 		struct bio_vec special_vec;
 		void *completion_data;
-		int error_count; /* for legacy drivers, don't use */
 	};
 
 
-- 
cgit v1.2.3


From 56f5746c414d92ae8e8314f46760822b4ecf8be3 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 22 Feb 2022 09:40:54 -0500
Subject: namei: Merge page_symlink() and __page_symlink()

There are no callers of __page_symlink() left, so we can remove that
entry point.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/porting.rst |  2 +-
 fs/namei.c                            | 13 ++-----------
 include/linux/fs.h                    |  2 --
 3 files changed, 3 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 7c1583dbeb59..2e0e4f0e0c6f 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -624,7 +624,7 @@ any symlink that might use page_follow_link_light/page_put_link() must
 have inode_nohighmem(inode) called before anything might start playing with
 its pagecache.  No highmem pages should end up in the pagecache of such
 symlinks.  That includes any preseeding that might be done during symlink
-creation.  __page_symlink() will honour the mapping gfp flags, so once
+creation.  page_symlink() will honour the mapping gfp flags, so once
 you've done inode_nohighmem() it's safe to use, but if you allocate and
 insert the page manually, make sure to use the right gfp flags.
 
diff --git a/fs/namei.c b/fs/namei.c
index 509657fdf4f5..6153581073b1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -5001,12 +5001,10 @@ int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 }
 EXPORT_SYMBOL(page_readlink);
 
-/*
- * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS
- */
-int __page_symlink(struct inode *inode, const char *symname, int len, int nofs)
+int page_symlink(struct inode *inode, const char *symname, int len)
 {
 	struct address_space *mapping = inode->i_mapping;
+	bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS);
 	struct page *page;
 	void *fsdata;
 	int err;
@@ -5034,13 +5032,6 @@ retry:
 fail:
 	return err;
 }
-EXPORT_SYMBOL(__page_symlink);
-
-int page_symlink(struct inode *inode, const char *symname, int len)
-{
-	return __page_symlink(inode, symname, len,
-			!mapping_gfp_constraint(inode->i_mapping, __GFP_FS));
-}
 EXPORT_SYMBOL(page_symlink);
 
 const struct inode_operations page_symlink_inode_operations = {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde95387a23..e108aff23a28 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3109,8 +3109,6 @@ extern int page_readlink(struct dentry *, char __user *, int);
 extern const char *page_get_link(struct dentry *, struct inode *,
 				 struct delayed_call *);
 extern void page_put_link(void *);
-extern int __page_symlink(struct inode *inode, const char *symname, int len,
-		int nofs);
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_link(void *);
-- 
cgit v1.2.3


From 236d93c4bf2d6da83241cc8e4625e89d9604cb43 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 22 Feb 2022 10:40:11 -0500
Subject: fs: Remove AOP_FLAG_NOFS

With all users of this flag gone, we can stop testing whether it's set.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/netfs/buffered_read.c | 6 +-----
 include/linux/fs.h       | 4 ----
 mm/folio-compat.c        | 2 --
 3 files changed, 1 insertion(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 281a88a5b8dc..65c17c5a5567 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -302,7 +302,6 @@ zero_out:
  * @mapping: The mapping to read from
  * @pos: File position at which the write will begin
  * @len: The length of the write (may extend beyond the end of the folio chosen)
- * @aop_flags: AOP_* flags
  * @_folio: Where to put the resultant folio
  * @_fsdata: Place for the netfs to store a cookie
  *
@@ -335,16 +334,13 @@ int netfs_write_begin(struct file *file, struct address_space *mapping,
 	struct netfs_io_request *rreq;
 	struct netfs_i_context *ctx = netfs_i_context(file_inode(file ));
 	struct folio *folio;
-	unsigned int fgp_flags;
+	unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
 	pgoff_t index = pos >> PAGE_SHIFT;
 	int ret;
 
 	DEFINE_READAHEAD(ractl, file, NULL, mapping, index);
 
 retry:
-	fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
-	if (aop_flags & AOP_FLAG_NOFS)
-		fgp_flags |= FGP_NOFS;
 	folio = __filemap_get_folio(mapping, index, fgp_flags,
 				    mapping_gfp_mask(mapping));
 	if (!folio)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e108aff23a28..f81bc5cbcbb6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -275,10 +275,6 @@ enum positive_aop_returns {
 	AOP_TRUNCATED_PAGE	= 0x80001,
 };
 
-#define AOP_FLAG_NOFS			0x0002 /* used by filesystem to direct
-						* helper code (eg buffer layer)
-						* to clear GFP_FS from alloc */
-
 /*
  * oh the beauties of C type declarations.
  */
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 46fa179e32fb..3e42ddb81918 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -135,8 +135,6 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 {
 	unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
 
-	if (flags & AOP_FLAG_NOFS)
-		fgp_flags |= FGP_NOFS;
 	return pagecache_get_page(mapping, index, fgp_flags,
 			mapping_gfp_mask(mapping));
 }
-- 
cgit v1.2.3


From de2a931150177957d37e9c975025604f4a1fe853 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 22 Feb 2022 10:47:09 -0500
Subject: fs: Remove aop_flags parameter from netfs_write_begin()

There are no more aop flags left, so remove the parameter.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/filesystems/netfs_library.rst | 1 -
 fs/9p/vfs_addr.c                            | 2 +-
 fs/afs/write.c                              | 2 +-
 fs/ceph/addr.c                              | 2 +-
 fs/netfs/buffered_read.c                    | 4 ++--
 include/linux/netfs.h                       | 2 +-
 6 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 69f00179fdfe..d51c2a5ccf57 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -142,7 +142,6 @@ Three read helpers are provided::
 			      struct address_space *mapping,
 			      loff_t pos,
 			      unsigned int len,
-			      unsigned int flags,
 			      struct folio **_folio,
 			      void **_fsdata);
 
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 501128188343..d311e68e21fd 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -275,7 +275,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
 	 * file.  We need to do this before we get a lock on the page in case
 	 * there's more than one writer competing for the same cache block.
 	 */
-	retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata);
+	retval = netfs_write_begin(filp, mapping, pos, len, &folio, fsdata);
 	if (retval < 0)
 		return retval;
 
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 4763132ca57e..af496c98d394 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -60,7 +60,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	 * file.  We need to do this before we get a lock on the page in case
 	 * there's more than one writer competing for the same cache block.
 	 */
-	ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata);
+	ret = netfs_write_begin(file, mapping, pos, len, &folio, fsdata);
 	if (ret < 0)
 		return ret;
 
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index aa25bffd4823..415f0886bc25 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1318,7 +1318,7 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 	struct folio *folio = NULL;
 	int r;
 
-	r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL);
+	r = netfs_write_begin(file, inode->i_mapping, pos, len, &folio, NULL);
 	if (r == 0)
 		folio_wait_fscache(folio);
 	if (r < 0) {
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 65c17c5a5567..1d44509455a5 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -328,8 +328,8 @@ zero_out:
  * This is usable whether or not caching is enabled.
  */
 int netfs_write_begin(struct file *file, struct address_space *mapping,
-		      loff_t pos, unsigned int len, unsigned int aop_flags,
-		      struct folio **_folio, void **_fsdata)
+		      loff_t pos, unsigned int len, struct folio **_folio,
+		      void **_fsdata)
 {
 	struct netfs_io_request *rreq;
 	struct netfs_i_context *ctx = netfs_i_context(file_inode(file ));
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index c7bf1eaf51d5..1c29f317d907 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -276,7 +276,7 @@ struct readahead_control;
 extern void netfs_readahead(struct readahead_control *);
 extern int netfs_readpage(struct file *, struct page *);
 extern int netfs_write_begin(struct file *, struct address_space *,
-			     loff_t, unsigned int, unsigned int, struct folio **,
+			     loff_t, unsigned int, struct folio **,
 			     void **);
 
 extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
-- 
cgit v1.2.3


From b3992d1e2ebcd478e0614494a6abd95e902a029b Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 22 Feb 2022 11:25:12 -0500
Subject: fs: Remove aop flags parameter from block_write_begin()

There are no more aop flags left, so remove the parameter.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 block/fops.c                | 3 +--
 fs/bfs/file.c               | 3 +--
 fs/buffer.c                 | 6 +++---
 fs/ext2/inode.c             | 3 +--
 fs/minix/inode.c            | 3 +--
 fs/nilfs2/inode.c           | 3 +--
 fs/nilfs2/recovery.c        | 2 +-
 fs/ntfs3/inode.c            | 4 ++--
 fs/omfs/file.c              | 3 +--
 fs/sysv/itree.c             | 2 +-
 fs/udf/inode.c              | 2 +-
 fs/ufs/inode.c              | 3 +--
 include/linux/buffer_head.h | 2 +-
 13 files changed, 16 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/block/fops.c b/block/fops.c
index 9f2ecec406b0..b432756570c6 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -401,8 +401,7 @@ static int blkdev_write_begin(struct file *file, struct address_space *mapping,
 		loff_t pos, unsigned len, unsigned flags, struct page **pagep,
 		void **fsdata)
 {
-	return block_write_begin(mapping, pos, len, flags, pagep,
-				 blkdev_get_block);
+	return block_write_begin(mapping, pos, len, pagep, blkdev_get_block);
 }
 
 static int blkdev_write_end(struct file *file, struct address_space *mapping,
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index 03139344568f..9408f45225cb 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -174,8 +174,7 @@ static int bfs_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, flags, pagep,
-				bfs_get_block);
+	ret = block_write_begin(mapping, pos, len, pagep, bfs_get_block);
 	if (unlikely(ret))
 		bfs_write_failed(mapping, pos + len);
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 2b5561ae5d0b..4ec6eb03c0eb 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2104,13 +2104,13 @@ static int __block_commit_write(struct inode *inode, struct page *page,
  * The filesystem needs to handle block truncation upon failure.
  */
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
-		unsigned flags, struct page **pagep, get_block_t *get_block)
+		struct page **pagep, get_block_t *get_block)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
 	struct page *page;
 	int status;
 
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index, 0);
 	if (!page)
 		return -ENOMEM;
 
@@ -2460,7 +2460,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 		(*bytes)++;
 	}
 
-	return block_write_begin(mapping, pos, len, flags, pagep, get_block);
+	return block_write_begin(mapping, pos, len, pagep, get_block);
 }
 EXPORT_SYMBOL(cont_write_begin);
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 52377a0ee735..97192932ea56 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -892,8 +892,7 @@ ext2_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, flags, pagep,
-				ext2_get_block);
+	ret = block_write_begin(mapping, pos, len, pagep, ext2_get_block);
 	if (ret < 0)
 		ext2_write_failed(mapping, pos + len);
 	return ret;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index f1a6610e4ee6..5e8d7ba661cf 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -428,8 +428,7 @@ static int minix_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, flags, pagep,
-				minix_get_block);
+	ret = block_write_begin(mapping, pos, len, pagep, minix_get_block);
 	if (unlikely(ret))
 		minix_write_failed(mapping, pos + len);
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 6045cea21f52..be09a0d10f04 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -258,8 +258,7 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping,
 	if (unlikely(err))
 		return err;
 
-	err = block_write_begin(mapping, pos, len, flags, pagep,
-				nilfs_get_block);
+	err = block_write_begin(mapping, pos, len, pagep, nilfs_get_block);
 	if (unlikely(err)) {
 		nilfs_write_failed(mapping, pos + len);
 		nilfs_transaction_abort(inode->i_sb);
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 9e2ed76c0f25..0955b657938f 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -511,7 +511,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 
 		pos = rb->blkoff << inode->i_blkbits;
 		err = block_write_begin(inode->i_mapping, pos, blocksize,
-					0, &page, nilfs_get_block);
+					&page, nilfs_get_block);
 		if (unlikely(err)) {
 			loff_t isize = inode->i_size;
 
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 9eab11e3b034..3914138fd8ba 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -894,7 +894,7 @@ static int ntfs_write_begin(struct file *file, struct address_space *mapping,
 			goto out;
 	}
 
-	err = block_write_begin(mapping, pos, len, flags, pagep,
+	err = block_write_begin(mapping, pos, len, pagep,
 				ntfs_get_block_write_begin);
 
 out:
@@ -975,7 +975,7 @@ int reset_log_file(struct inode *inode)
 
 		len = pos + PAGE_SIZE > log_size ? (log_size - pos) : PAGE_SIZE;
 
-		err = block_write_begin(mapping, pos, len, 0, &page,
+		err = block_write_begin(mapping, pos, len, &page,
 					ntfs_get_block_write_begin);
 		if (err)
 			goto out;
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 3f297b541713..349b96d89c44 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -321,8 +321,7 @@ static int omfs_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, flags, pagep,
-				omfs_get_block);
+	ret = block_write_begin(mapping, pos, len, pagep, omfs_get_block);
 	if (unlikely(ret))
 		omfs_write_failed(mapping, pos + len);
 
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 409ab5e17803..96b7fd4facf3 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -482,7 +482,7 @@ static int sysv_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, flags, pagep, get_block);
+	ret = block_write_begin(mapping, pos, len, pagep, get_block);
 	if (unlikely(ret))
 		sysv_write_failed(mapping, pos + len);
 
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index ca4fa710e562..88a95886ce8a 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -209,7 +209,7 @@ static int udf_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, flags, pagep, udf_get_block);
+	ret = block_write_begin(mapping, pos, len, pagep, udf_get_block);
 	if (unlikely(ret))
 		udf_write_failed(mapping, pos + len);
 	return ret;
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index d0dda01620f0..bd0e0c66f93d 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -500,8 +500,7 @@ static int ufs_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, flags, pagep,
-				ufs_getfrag_block);
+	ret = block_write_begin(mapping, pos, len, pagep, ufs_getfrag_block);
 	if (unlikely(ret))
 		ufs_write_failed(mapping, pos + len);
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index bcb4fe9b8575..63e49dfa7738 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -226,7 +226,7 @@ int __block_write_full_page(struct inode *inode, struct page *page,
 int block_read_full_page(struct page*, get_block_t*);
 bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
-		unsigned flags, struct page **pagep, get_block_t *get_block);
+		struct page **pagep, get_block_t *get_block);
 int __block_write_begin(struct page *page, loff_t pos, unsigned len,
 		get_block_t *get_block);
 int block_write_end(struct file *, struct address_space *,
-- 
cgit v1.2.3


From be3bbbc588118bdc10e21fdd7bfa6ee6b8c2555d Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 22 Feb 2022 11:25:12 -0500
Subject: fs: Remove aop flags parameter from cont_write_begin()

There are no more aop flags left, so remove the parameter.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/adfs/inode.c             | 2 +-
 fs/affs/file.c              | 2 +-
 fs/buffer.c                 | 2 +-
 fs/exfat/inode.c            | 2 +-
 fs/fat/inode.c              | 2 +-
 fs/hfs/inode.c              | 2 +-
 fs/hfsplus/inode.c          | 2 +-
 fs/hpfs/file.c              | 2 +-
 include/linux/buffer_head.h | 2 +-
 9 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index 561bc748c04a..b6912496bb19 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -58,7 +58,7 @@ static int adfs_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
 				adfs_get_block,
 				&ADFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))
diff --git a/fs/affs/file.c b/fs/affs/file.c
index b3f81d84ff4c..704911d6aeba 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -420,7 +420,7 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
 				affs_get_block,
 				&AFFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))
diff --git a/fs/buffer.c b/fs/buffer.c
index 4ec6eb03c0eb..fb97646d1977 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2441,7 +2441,7 @@ out:
  * We may have to extend the file.
  */
 int cont_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata,
 			get_block_t *get_block, loff_t *bytes)
 {
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index fc0ea1684880..8ed3c4b700cd 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -395,7 +395,7 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
 			       exfat_get_block,
 			       &EXFAT_I(mapping->host)->i_size_ondisk);
 
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index bf6051bdf1d1..9b34ccef2501 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -232,7 +232,7 @@ static int fat_write_begin(struct file *file, struct address_space *mapping,
 	int err;
 
 	*pagep = NULL;
-	err = cont_write_begin(file, mapping, pos, len, flags,
+	err = cont_write_begin(file, mapping, pos, len,
 				pagep, fsdata, fat_get_block,
 				&MSDOS_I(mapping->host)->mmu_private);
 	if (err < 0)
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 55f45e9b4930..396735dd3407 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -56,7 +56,7 @@ static int hfs_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
 				hfs_get_block,
 				&HFS_I(mapping->host)->phys_size);
 	if (unlikely(ret))
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 446a816aa8e1..435b6202532a 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -50,7 +50,7 @@ static int hfsplus_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
 				hfsplus_get_block,
 				&HFSPLUS_I(mapping->host)->phys_size);
 	if (unlikely(ret))
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 99493a23c5d0..8740b4ea0b52 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -200,7 +200,7 @@ static int hpfs_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
 				hpfs_get_block,
 				&hpfs_i(mapping->host)->mmu_private);
 	if (unlikely(ret))
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 63e49dfa7738..127b60fad77e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -238,7 +238,7 @@ int generic_write_end(struct file *, struct address_space *,
 void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
 void clean_page_buffers(struct page *page);
 int cont_write_begin(struct file *, struct address_space *, loff_t,
-			unsigned, unsigned, struct page **, void **,
+			unsigned, struct page **, void **,
 			get_block_t *, loff_t *);
 int generic_cont_expand_simple(struct inode *inode, loff_t size);
 int block_commit_write(struct page *page, unsigned from, unsigned to);
-- 
cgit v1.2.3


From b7446e7cf15f0926866c8e5de90ab278998bf8c8 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 22 Feb 2022 11:25:12 -0500
Subject: fs: Remove aop flags parameter from grab_cache_page_write_begin()

There are no more aop flags left, so remove the parameter.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/affs/file.c          | 2 +-
 fs/buffer.c             | 4 ++--
 fs/cifs/file.c          | 2 +-
 fs/ecryptfs/mmap.c      | 2 +-
 fs/ext4/inline.c        | 8 ++++----
 fs/ext4/inode.c         | 4 ++--
 fs/ext4/move_extent.c   | 4 ++--
 fs/f2fs/f2fs.h          | 2 +-
 fs/fuse/file.c          | 4 ++--
 fs/hostfs/hostfs_kern.c | 2 +-
 fs/jffs2/file.c         | 2 +-
 fs/libfs.c              | 2 +-
 fs/nfs/file.c           | 2 +-
 fs/ntfs3/inode.c        | 2 +-
 fs/orangefs/inode.c     | 2 +-
 fs/reiserfs/inode.c     | 2 +-
 fs/ubifs/file.c         | 4 ++--
 fs/udf/file.c           | 2 +-
 include/linux/pagemap.h | 2 +-
 mm/folio-compat.c       | 2 +-
 20 files changed, 28 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/fs/affs/file.c b/fs/affs/file.c
index 704911d6aeba..06645d05c717 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -670,7 +670,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 	}
 
 	index = pos >> PAGE_SHIFT;
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/buffer.c b/fs/buffer.c
index fb97646d1977..01630218c75f 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2110,7 +2110,7 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 	struct page *page;
 	int status;
 
-	page = grab_cache_page_write_begin(mapping, index, 0);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 
@@ -2591,7 +2591,7 @@ int nobh_write_begin(struct address_space *mapping,
 	from = pos & (PAGE_SIZE - 1);
 	to = from + len;
 
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index d511a78383c3..91aeae7fced8 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4695,7 +4695,7 @@ static int cifs_write_begin(struct file *file, struct address_space *mapping,
 	cifs_dbg(FYI, "write_begin from %lld len %d\n", (long long)pos, len);
 
 start:
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page) {
 		rc = -ENOMEM;
 		goto out;
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 9ad61b582f07..84e399a921ad 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -272,7 +272,7 @@ static int ecryptfs_write_begin(struct file *file,
 	loff_t prev_page_end_size;
 	int rc = 0;
 
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index b2ef5ba568bc..6d253edebf9f 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -563,7 +563,7 @@ retry:
 	/* We cannot recurse into the filesystem as the transaction is already
 	 * started */
 	flags = memalloc_nofs_save();
-	page = grab_cache_page_write_begin(mapping, 0, 0);
+	page = grab_cache_page_write_begin(mapping, 0);
 	memalloc_nofs_restore(flags);
 	if (!page) {
 		ret = -ENOMEM;
@@ -692,7 +692,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 		goto out;
 
 	flags = memalloc_nofs_save();
-	page = grab_cache_page_write_begin(mapping, 0, 0);
+	page = grab_cache_page_write_begin(mapping, 0);
 	memalloc_nofs_restore(flags);
 	if (!page) {
 		ret = -ENOMEM;
@@ -852,7 +852,7 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
 	int ret = 0, inline_size;
 	struct page *page;
 
-	page = grab_cache_page_write_begin(mapping, 0, 0);
+	page = grab_cache_page_write_begin(mapping, 0);
 	if (!page)
 		return -ENOMEM;
 
@@ -946,7 +946,7 @@ retry_journal:
 	 * is already started.
 	 */
 	flags = memalloc_nofs_save();
-	page = grab_cache_page_write_begin(mapping, 0, 0);
+	page = grab_cache_page_write_begin(mapping, 0);
 	memalloc_nofs_restore(flags);
 	if (!page) {
 		ret = -ENOMEM;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 01a55647c959..512d8143c765 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1171,7 +1171,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	 * the page (if needed) without using GFP_NOFS.
 	 */
 retry_grab:
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 	unlock_page(page);
@@ -2963,7 +2963,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	}
 
 retry:
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 56f21272fb00..4172a7d22471 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -141,13 +141,13 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
 	}
 
 	flags = memalloc_nofs_save();
-	page[0] = grab_cache_page_write_begin(mapping[0], index1, 0);
+	page[0] = grab_cache_page_write_begin(mapping[0], index1);
 	if (!page[0]) {
 		memalloc_nofs_restore(flags);
 		return -ENOMEM;
 	}
 
-	page[1] = grab_cache_page_write_begin(mapping[1], index2, 0);
+	page[1] = grab_cache_page_write_begin(mapping[1], index2);
 	memalloc_nofs_restore(flags);
 	if (!page[1]) {
 		unlock_page(page[0]);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 74929ade4b5e..18df53ef3d7e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2677,7 +2677,7 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
 		return grab_cache_page(mapping, index);
 
 	flags = memalloc_nofs_save();
-	page = grab_cache_page_write_begin(mapping, index, 0);
+	page = grab_cache_page_write_begin(mapping, index);
 	memalloc_nofs_restore(flags);
 
 	return page;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f18d14d5fea1..e35e394264ad 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1174,7 +1174,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 			break;
 
 		err = -ENOMEM;
-		page = grab_cache_page_write_begin(mapping, index, 0);
+		page = grab_cache_page_write_begin(mapping, index);
 		if (!page)
 			break;
 
@@ -2284,7 +2284,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping,
 
 	WARN_ON(!fc->writeback_cache);
 
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		goto error;
 
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 14f9ac973a2e..2bfd316e1bf1 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -468,7 +468,7 @@ static int hostfs_write_begin(struct file *file, struct address_space *mapping,
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
 
-	*pagep = grab_cache_page_write_begin(mapping, index, flags);
+	*pagep = grab_cache_page_write_begin(mapping, index);
 	if (!*pagep)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index bd7d58d27bfc..142d3ba9f0a8 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -213,7 +213,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	 * page in read_cache_page(), which causes a deadlock.
 	 */
 	mutex_lock(&c->alloc_sem);
-	pg = grab_cache_page_write_begin(mapping, index, flags);
+	pg = grab_cache_page_write_begin(mapping, index);
 	if (!pg) {
 		ret = -ENOMEM;
 		goto release_sem;
diff --git a/fs/libfs.c b/fs/libfs.c
index e64bdedef168..d4395e1c6696 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -557,7 +557,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 
 	index = pos >> PAGE_SHIFT;
 
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 150b7fa8f0a7..d66088dd33e7 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -325,7 +325,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 		file, mapping->host->i_ino, len, (long long) pos);
 
 start:
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 3914138fd8ba..16466c8648f3 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -872,7 +872,7 @@ static int ntfs_write_begin(struct file *file, struct address_space *mapping,
 	*pagep = NULL;
 	if (is_resident(ni)) {
 		struct page *page = grab_cache_page_write_begin(
-			mapping, pos >> PAGE_SHIFT, flags);
+			mapping, pos >> PAGE_SHIFT);
 
 		if (!page) {
 			err = -ENOMEM;
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 79c1025d18ea..809690db8be2 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -338,7 +338,7 @@ static int orangefs_write_begin(struct file *file,
 
 	index = pos >> PAGE_SHIFT;
 
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 36c59b25486c..aa31cf1dbba6 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2764,7 +2764,7 @@ static int reiserfs_write_begin(struct file *file,
 
  	inode = mapping->host;
 	index = pos >> PAGE_SHIFT;
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 0383fbdc95ff..0911fc311434 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -244,7 +244,7 @@ static int write_begin_slow(struct address_space *mapping,
 	if (unlikely(err))
 		return err;
 
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (unlikely(!page)) {
 		ubifs_release_budget(c, &req);
 		return -ENOMEM;
@@ -437,7 +437,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
 		return -EROFS;
 
 	/* Try out the fast-path part first */
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (unlikely(!page))
 		return -ENOMEM;
 
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 0f6bf2504437..724bb3141fda 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -94,7 +94,7 @@ static int udf_adinicb_write_begin(struct file *file,
 
 	if (WARN_ON_ONCE(pos >= PAGE_SIZE))
 		return -EIO;
-	page = grab_cache_page_write_begin(mapping, 0, flags);
+	page = grab_cache_page_write_begin(mapping, 0);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 993994cd943a..65ae8f96554b 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -735,7 +735,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping,
 }
 
 struct page *grab_cache_page_write_begin(struct address_space *mapping,
-			pgoff_t index, unsigned flags);
+			pgoff_t index);
 
 /*
  * Returns locked page at given index in given cache, creating it if needed.
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 3e42ddb81918..20bc15b57d93 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -131,7 +131,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 EXPORT_SYMBOL(pagecache_get_page);
 
 struct page *grab_cache_page_write_begin(struct address_space *mapping,
-					pgoff_t index, unsigned flags)
+					pgoff_t index)
 {
 	unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
 
-- 
cgit v1.2.3


From 8371f30cf774a20fd627a0f7b1ecf00e8257f3bc Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 22 Feb 2022 11:54:56 -0500
Subject: fs: Remove aop flags parameter from nobh_write_begin()

There are no more aop flags left, so remove the parameter.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/buffer.c                 | 3 +--
 fs/ext2/inode.c             | 2 +-
 fs/jfs/inode.c              | 3 +--
 include/linux/buffer_head.h | 2 +-
 4 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/buffer.c b/fs/buffer.c
index 01630218c75f..02b50e3e4fbb 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2568,8 +2568,7 @@ static void attach_nobh_buffers(struct page *page, struct buffer_head *head)
  * On exit the page is fully uptodate in the areas outside (from,to)
  * The filesystem needs to handle block truncation upon failure.
  */
-int nobh_write_begin(struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata,
 			get_block_t *get_block)
 {
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 97192932ea56..bfa69c52ce2c 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -917,7 +917,7 @@ ext2_nobh_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata,
+	ret = nobh_write_begin(mapping, pos, len, pagep, fsdata,
 			       ext2_get_block);
 	if (ret < 0)
 		ext2_write_failed(mapping, pos + len);
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index d1943a7b4b04..e16f77b4e84c 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -319,8 +319,7 @@ static int jfs_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
-	ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata,
-				jfs_get_block);
+	ret = nobh_write_begin(mapping, pos, len, pagep, fsdata, jfs_get_block);
 	if (unlikely(ret))
 		jfs_write_failed(mapping, pos + len);
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 127b60fad77e..6e5a64005fef 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -258,7 +258,7 @@ static inline vm_fault_t block_page_mkwrite_return(int err)
 }
 sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
 int block_truncate_page(struct address_space *, loff_t, get_block_t *);
-int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned,
+int nobh_write_begin(struct address_space *, loff_t, unsigned len,
 				struct page **, void **, get_block_t*);
 int nobh_write_end(struct file *, struct address_space *,
 				loff_t, unsigned, unsigned,
-- 
cgit v1.2.3


From 9d6b0cd7579844761ed68926eb3073bab1dca87b Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 22 Feb 2022 14:31:43 -0500
Subject: fs: Remove flags parameter from aops->write_begin

There are no more aop flags left, so remove the parameter.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/filesystems/locking.rst |  2 +-
 Documentation/filesystems/vfs.rst     |  5 +----
 block/fops.c                          |  3 +--
 fs/9p/vfs_addr.c                      |  2 +-
 fs/adfs/inode.c                       |  2 +-
 fs/affs/file.c                        |  6 +++---
 fs/afs/internal.h                     |  2 +-
 fs/afs/write.c                        |  2 +-
 fs/bfs/file.c                         |  2 +-
 fs/ceph/addr.c                        |  2 +-
 fs/cifs/file.c                        |  2 +-
 fs/ecryptfs/mmap.c                    |  2 +-
 fs/exfat/inode.c                      |  2 +-
 fs/ext2/inode.c                       |  6 ++----
 fs/ext4/inode.c                       | 10 +++++-----
 fs/f2fs/data.c                        |  5 ++---
 fs/f2fs/super.c                       |  2 +-
 fs/fat/inode.c                        |  2 +-
 fs/fuse/file.c                        |  3 +--
 fs/hfs/inode.c                        |  2 +-
 fs/hfsplus/inode.c                    |  2 +-
 fs/hostfs/hostfs_kern.c               |  2 +-
 fs/hpfs/file.c                        |  2 +-
 fs/hugetlbfs/inode.c                  |  2 +-
 fs/jffs2/file.c                       |  4 ++--
 fs/jfs/inode.c                        |  2 +-
 fs/libfs.c                            |  2 +-
 fs/minix/inode.c                      |  2 +-
 fs/nfs/file.c                         |  2 +-
 fs/nilfs2/inode.c                     |  2 +-
 fs/ntfs3/inode.c                      |  2 +-
 fs/ocfs2/aops.c                       |  2 +-
 fs/omfs/file.c                        |  2 +-
 fs/orangefs/inode.c                   |  5 ++---
 fs/reiserfs/inode.c                   |  2 +-
 fs/sysv/itree.c                       |  2 +-
 fs/ubifs/file.c                       |  7 +++----
 fs/udf/file.c                         |  2 +-
 fs/udf/inode.c                        |  2 +-
 fs/ufs/inode.c                        |  2 +-
 include/linux/fs.h                    |  4 ++--
 include/trace/events/ext4.h           | 21 ++++++++-------------
 include/trace/events/f2fs.h           | 12 ++++--------
 mm/filemap.c                          |  6 ++----
 mm/shmem.c                            |  2 +-
 45 files changed, 69 insertions(+), 90 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index c26d854275a0..fd9d9caf09ab 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -242,7 +242,7 @@ prototypes::
 	bool (*dirty_folio)(struct address_space *, struct folio *folio);
 	void (*readahead)(struct readahead_control *);
 	int (*write_begin)(struct file *, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
+				loff_t pos, unsigned len,
 				struct page **pagep, void **fsdata);
 	int (*write_end)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 794bd1a66bfb..30f303180a7d 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -727,7 +727,7 @@ cache in your filesystem.  The following members are defined:
 		bool (*dirty_folio)(struct address_space *, struct folio *);
 		void (*readahead)(struct readahead_control *);
 		int (*write_begin)(struct file *, struct address_space *mapping,
-				   loff_t pos, unsigned len, unsigned flags,
+				   loff_t pos, unsigned len,
 				struct page **pagep, void **fsdata);
 		int (*write_end)(struct file *, struct address_space *mapping,
 				 loff_t pos, unsigned len, unsigned copied,
@@ -832,9 +832,6 @@ cache in your filesystem.  The following members are defined:
 	passed to write_begin is greater than the number of bytes copied
 	into the page).
 
-	flags is a field for AOP_FLAG_xxx flags, described in
-	include/linux/fs.h.
-
 	A void * may be returned in fsdata, which then gets passed into
 	write_end.
 
diff --git a/block/fops.c b/block/fops.c
index b432756570c6..712affe56e29 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -398,8 +398,7 @@ static void blkdev_readahead(struct readahead_control *rac)
 }
 
 static int blkdev_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned flags, struct page **pagep,
-		void **fsdata)
+		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
 {
 	return block_write_begin(mapping, pos, len, pagep, blkdev_get_block);
 }
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index d311e68e21fd..a2d57112f53e 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -260,7 +260,7 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 }
 
 static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
-			    loff_t pos, unsigned int len, unsigned int flags,
+			    loff_t pos, unsigned int len,
 			    struct page **subpagep, void **fsdata)
 {
 	int retval;
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index b6912496bb19..f7959b1a2d52 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -52,7 +52,7 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int adfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 06645d05c717..b952f65c3f06 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -414,7 +414,7 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 }
 
 static int affs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
@@ -650,7 +650,7 @@ affs_readpage_ofs(struct file *file, struct page *page)
 }
 
 static int affs_write_begin_ofs(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
+				loff_t pos, unsigned len,
 				struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
@@ -887,7 +887,7 @@ affs_truncate(struct inode *inode)
 		loff_t isize = inode->i_size;
 		int res;
 
-		res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, 0, &page, &fsdata);
+		res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &page, &fsdata);
 		if (!res)
 			res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page, fsdata);
 		else
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 7b7ef945dc78..7a72e9c60423 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1535,7 +1535,7 @@ bool afs_dirty_folio(struct address_space *, struct folio *);
 #define afs_dirty_folio filemap_dirty_folio
 #endif
 extern int afs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata);
 extern int afs_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
diff --git a/fs/afs/write.c b/fs/afs/write.c
index af496c98d394..5224e346fbad 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -42,7 +42,7 @@ static void afs_folio_start_fscache(bool caching, struct folio *folio)
  * prepare to perform part of a write to a page
  */
 int afs_write_begin(struct file *file, struct address_space *mapping,
-		    loff_t pos, unsigned len, unsigned flags,
+		    loff_t pos, unsigned len,
 		    struct page **_page, void **fsdata)
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index 9408f45225cb..dc97c9b8f23b 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -169,7 +169,7 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int bfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 415f0886bc25..e65541a51b68 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1311,7 +1311,7 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
  * clean, or already dirty within the same snap context.
  */
 static int ceph_write_begin(struct file *file, struct address_space *mapping,
-			    loff_t pos, unsigned len, unsigned aop_flags,
+			    loff_t pos, unsigned len,
 			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = file_inode(file);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 91aeae7fced8..da362b5a0c96 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4681,7 +4681,7 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file)
 }
 
 static int cifs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int oncethru = 0;
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 84e399a921ad..47904d40ef88 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -264,7 +264,7 @@ out:
  */
 static int ecryptfs_write_begin(struct file *file,
 			struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index 8ed3c4b700cd..b9f63113db2d 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -389,7 +389,7 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int exfat_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned int len, unsigned int flags,
+		loff_t pos, unsigned int len,
 		struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index bfa69c52ce2c..d8ca8050945a 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -887,8 +887,7 @@ static void ext2_readahead(struct readahead_control *rac)
 
 static int
 ext2_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned flags,
-		struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
 {
 	int ret;
 
@@ -912,8 +911,7 @@ static int ext2_write_end(struct file *file, struct address_space *mapping,
 
 static int
 ext2_nobh_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned flags,
-		struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
 {
 	int ret;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 512d8143c765..d3a7e8581291 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1130,7 +1130,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 #endif
 
 static int ext4_write_begin(struct file *file, struct address_space *mapping,
-			    loff_t pos, unsigned len, unsigned flags,
+			    loff_t pos, unsigned len,
 			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
@@ -1144,7 +1144,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	trace_ext4_write_begin(inode, pos, len, flags);
+	trace_ext4_write_begin(inode, pos, len);
 	/*
 	 * Reserve one block more for addition to orphan list in case
 	 * we allocate blocks but write fails for some reason
@@ -2931,7 +2931,7 @@ static int ext4_nonda_switch(struct super_block *sb)
 }
 
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
-			       loff_t pos, unsigned len, unsigned flags,
+			       loff_t pos, unsigned len,
 			       struct page **pagep, void **fsdata)
 {
 	int ret, retries = 0;
@@ -2948,10 +2948,10 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	    ext4_verity_in_progress(inode)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
 		return ext4_write_begin(file, mapping, pos,
-					len, flags, pagep, fsdata);
+					len, pagep, fsdata);
 	}
 	*fsdata = (void *)0;
-	trace_ext4_da_write_begin(inode, pos, len, flags);
+	trace_ext4_da_write_begin(inode, pos, len);
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
 		ret = ext4_da_write_inline_data_begin(mapping, inode, pos, len,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9a1a526f2092..b3cf49136b9f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3314,8 +3314,7 @@ unlock_out:
 }
 
 static int f2fs_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned flags,
-		struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -3325,7 +3324,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	block_t blkaddr = NULL_ADDR;
 	int err = 0;
 
-	trace_f2fs_write_begin(inode, pos, len, flags);
+	trace_f2fs_write_begin(inode, pos, len);
 
 	if (!f2fs_is_checkpoint_ready(sbi)) {
 		err = -ENOSPC;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 4368f90571bd..ed3e8b7a8260 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2483,7 +2483,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 		tocopy = min_t(unsigned long, sb->s_blocksize - offset,
 								towrite);
 retry:
-		err = a_ops->write_begin(NULL, mapping, off, tocopy, 0,
+		err = a_ops->write_begin(NULL, mapping, off, tocopy,
 							&page, &fsdata);
 		if (unlikely(err)) {
 			if (err == -ENOMEM) {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 9b34ccef2501..1f15b0fd1bb0 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -226,7 +226,7 @@ static void fat_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int fat_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int err;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e35e394264ad..bca8c2135ec5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2273,8 +2273,7 @@ out:
  * but how to implement it without killing performance need more thinking.
  */
 static int fuse_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned flags,
-		struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
 	struct fuse_conn *fc = get_fuse_conn(file_inode(file));
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 396735dd3407..93d9aa832139 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -50,7 +50,7 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int hfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 435b6202532a..73010aa4623f 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -44,7 +44,7 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int hfsplus_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2bfd316e1bf1..e658d8edde35 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -463,7 +463,7 @@ static int hostfs_readpage(struct file *file, struct page *page)
 }
 
 static int hostfs_write_begin(struct file *file, struct address_space *mapping,
-			      loff_t pos, unsigned len, unsigned flags,
+			      loff_t pos, unsigned len,
 			      struct page **pagep, void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 8740b4ea0b52..8b590b3826c3 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -194,7 +194,7 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int hpfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index dd3a088db11d..2de9ca5d260d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -383,7 +383,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static int hugetlbfs_write_begin(struct file *file,
 			struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	return -EINVAL;
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 142d3ba9f0a8..2b35811772de 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -25,7 +25,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *pg, void *fsdata);
 static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata);
 static int jffs2_readpage (struct file *filp, struct page *pg);
 
@@ -130,7 +130,7 @@ static int jffs2_readpage (struct file *filp, struct page *pg)
 }
 
 static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	struct page *pg;
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index e16f77b4e84c..aa9f112107b2 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -314,7 +314,7 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int jfs_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
+				loff_t pos, unsigned len,
 				struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/libfs.c b/fs/libfs.c
index d4395e1c6696..a1c10d3163e0 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -549,7 +549,7 @@ static int simple_readpage(struct file *file, struct page *page)
 }
 
 int simple_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	struct page *page;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 5e8d7ba661cf..3add78bccedc 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -423,7 +423,7 @@ static void minix_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int minix_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index d66088dd33e7..314d2d7ba84a 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -313,7 +313,7 @@ static bool nfs_want_read_modify_write(struct file *file, struct page *page,
  * increment the page use counts until he is done with the page.
  */
 static int nfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index be09a0d10f04..02297ec8dc55 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -248,7 +248,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int nilfs_write_begin(struct file *file, struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+			     loff_t pos, unsigned len,
 			     struct page **pagep, void **fsdata)
 
 {
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 16466c8648f3..1364174cc6c9 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -862,7 +862,7 @@ static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn,
 }
 
 static int ntfs_write_begin(struct file *file, struct address_space *mapping,
-			    loff_t pos, u32 len, u32 flags, struct page **pagep,
+			    loff_t pos, u32 len, struct page **pagep,
 			    void **fsdata)
 {
 	int err;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 4b9af65cb61b..7cffe9dcad17 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1881,7 +1881,7 @@ out:
 }
 
 static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+			     loff_t pos, unsigned len,
 			     struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 349b96d89c44..980b0a72c172 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -316,7 +316,7 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int omfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 809690db8be2..bc7ccd15d7a3 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -326,9 +326,8 @@ static int orangefs_readpage(struct file *file, struct page *page)
 }
 
 static int orangefs_write_begin(struct file *file,
-    struct address_space *mapping,
-    loff_t pos, unsigned len, unsigned flags, struct page **pagep,
-    void **fsdata)
+		struct address_space *mapping, loff_t pos, unsigned len,
+		struct page **pagep, void **fsdata)
 {
 	struct orangefs_write_range *wr;
 	struct folio *folio;
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index aa31cf1dbba6..46ba4892030a 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2753,7 +2753,7 @@ static void reiserfs_truncate_failed_write(struct inode *inode)
 
 static int reiserfs_write_begin(struct file *file,
 				struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
+				loff_t pos, unsigned len,
 				struct page **pagep, void **fsdata)
 {
 	struct inode *inode;
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 96b7fd4facf3..96ad24fe0ffb 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -477,7 +477,7 @@ static void sysv_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int sysv_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 0911fc311434..81c085c4decf 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -215,8 +215,7 @@ static void release_existing_page_budget(struct ubifs_info *c)
 }
 
 static int write_begin_slow(struct address_space *mapping,
-			    loff_t pos, unsigned len, struct page **pagep,
-			    unsigned flags)
+			    loff_t pos, unsigned len, struct page **pagep)
 {
 	struct inode *inode = mapping->host;
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
@@ -419,7 +418,7 @@ static int allocate_budget(struct ubifs_info *c, struct page *page,
  * without forcing write-back. The slow path does not make this assumption.
  */
 static int ubifs_write_begin(struct file *file, struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+			     loff_t pos, unsigned len,
 			     struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
@@ -493,7 +492,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
 		unlock_page(page);
 		put_page(page);
 
-		return write_begin_slow(mapping, pos, len, pagep, flags);
+		return write_begin_slow(mapping, pos, len, pagep);
 	}
 
 	/*
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 724bb3141fda..3f4d5c44c784 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -87,7 +87,7 @@ static int udf_adinicb_writepage(struct page *page,
 
 static int udf_adinicb_write_begin(struct file *file,
 			struct address_space *mapping, loff_t pos,
-			unsigned len, unsigned flags, struct page **pagep,
+			unsigned len, struct page **pagep,
 			void **fsdata)
 {
 	struct page *page;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 88a95886ce8a..866f9a53248e 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -204,7 +204,7 @@ static void udf_readahead(struct readahead_control *rac)
 }
 
 static int udf_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index bd0e0c66f93d..6c973b71cab2 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -495,7 +495,7 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static int ufs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f81bc5cbcbb6..a0e73432526f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -346,7 +346,7 @@ struct address_space_operations {
 	void (*readahead)(struct readahead_control *);
 
 	int (*write_begin)(struct file *, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
+				loff_t pos, unsigned len,
 				struct page **pagep, void **fsdata);
 	int (*write_end)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
@@ -3179,7 +3179,7 @@ extern int noop_fsync(struct file *, loff_t, loff_t, int);
 extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 extern int simple_empty(struct dentry *);
 extern int simple_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata);
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index d06ffffad434..229e8fae66a3 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -335,17 +335,15 @@ TRACE_EVENT(ext4_begin_ordered_truncate,
 
 DECLARE_EVENT_CLASS(ext4__write_begin,
 
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-		 unsigned int flags),
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len),
 
-	TP_ARGS(inode, pos, len, flags),
+	TP_ARGS(inode, pos, len),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
 		__field(	loff_t,	pos			)
 		__field(	unsigned int, len		)
-		__field(	unsigned int, flags		)
 	),
 
 	TP_fast_assign(
@@ -353,29 +351,26 @@ DECLARE_EVENT_CLASS(ext4__write_begin,
 		__entry->ino	= inode->i_ino;
 		__entry->pos	= pos;
 		__entry->len	= len;
-		__entry->flags	= flags;
 	),
 
-	TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u",
+	TP_printk("dev %d,%d ino %lu pos %lld len %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->pos, __entry->len, __entry->flags)
+		  __entry->pos, __entry->len)
 );
 
 DEFINE_EVENT(ext4__write_begin, ext4_write_begin,
 
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-		 unsigned int flags),
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len),
 
-	TP_ARGS(inode, pos, len, flags)
+	TP_ARGS(inode, pos, len)
 );
 
 DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin,
 
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-		 unsigned int flags),
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len),
 
-	TP_ARGS(inode, pos, len, flags)
+	TP_ARGS(inode, pos, len)
 );
 
 DECLARE_EVENT_CLASS(ext4__write_end,
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 1779e133cea0..bea654a85e6b 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -1159,17 +1159,15 @@ DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_write_bio,
 
 TRACE_EVENT(f2fs_write_begin,
 
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-				unsigned int flags),
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len),
 
-	TP_ARGS(inode, pos, len, flags),
+	TP_ARGS(inode, pos, len),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
 		__field(loff_t,	pos)
 		__field(unsigned int, len)
-		__field(unsigned int, flags)
 	),
 
 	TP_fast_assign(
@@ -1177,14 +1175,12 @@ TRACE_EVENT(f2fs_write_begin,
 		__entry->ino	= inode->i_ino;
 		__entry->pos	= pos;
 		__entry->len	= len;
-		__entry->flags	= flags;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, flags = %u",
+	TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u",
 		show_dev_ino(__entry),
 		(unsigned long long)__entry->pos,
-		__entry->len,
-		__entry->flags)
+		__entry->len)
 );
 
 TRACE_EVENT(f2fs_write_end,
diff --git a/mm/filemap.c b/mm/filemap.c
index 9a1eef6c5d35..0751843b052f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3628,8 +3628,7 @@ int pagecache_write_begin(struct file *file, struct address_space *mapping,
 {
 	const struct address_space_operations *aops = mapping->a_ops;
 
-	return aops->write_begin(file, mapping, pos, len, flags,
-							pagep, fsdata);
+	return aops->write_begin(file, mapping, pos, len, pagep, fsdata);
 }
 EXPORT_SYMBOL(pagecache_write_begin);
 
@@ -3754,7 +3753,6 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	long status = 0;
 	ssize_t written = 0;
-	unsigned int flags = 0;
 
 	do {
 		struct page *page;
@@ -3784,7 +3782,7 @@ again:
 			break;
 		}
 
-		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
+		status = a_ops->write_begin(file, mapping, pos, bytes,
 						&page, &fsdata);
 		if (unlikely(status < 0))
 			break;
diff --git a/mm/shmem.c b/mm/shmem.c
index 4b2fea33158e..0f557a512171 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2426,7 +2426,7 @@ static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
 
 static int
 shmem_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
-- 
cgit v1.2.3


From 84a1041c60ff8f648a09d28af7b2e50a8f6345ed Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 3 Mar 2022 15:00:20 -0500
Subject: fs: Remove pagecache_write_begin() and pagecache_write_end()

These wrappers have no more users; remove them.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/fs.h | 12 ------------
 mm/filemap.c       | 20 --------------------
 2 files changed, 32 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index a0e73432526f..b35ce086a7a1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -380,18 +380,6 @@ struct address_space_operations {
 
 extern const struct address_space_operations empty_aops;
 
-/*
- * pagecache_write_begin/pagecache_write_end must be used by general code
- * to write into the pagecache.
- */
-int pagecache_write_begin(struct file *, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
-				struct page **pagep, void **fsdata);
-
-int pagecache_write_end(struct file *, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata);
-
 /**
  * struct address_space - Contents of a cacheable, mappable object.
  * @host: Owner, either the inode or the block_device.
diff --git a/mm/filemap.c b/mm/filemap.c
index 0751843b052f..c15cfc28f9ce 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3622,26 +3622,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-int pagecache_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
-				struct page **pagep, void **fsdata)
-{
-	const struct address_space_operations *aops = mapping->a_ops;
-
-	return aops->write_begin(file, mapping, pos, len, pagep, fsdata);
-}
-EXPORT_SYMBOL(pagecache_write_begin);
-
-int pagecache_write_end(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
-{
-	const struct address_space_operations *aops = mapping->a_ops;
-
-	return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
-}
-EXPORT_SYMBOL(pagecache_write_end);
-
 /*
  * Warn about a page cache invalidation failure during a direct I/O write.
  */
-- 
cgit v1.2.3


From 65aa6b5a18294b3713a90c120312ed5d63a16b82 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 4 Apr 2022 11:38:20 -0400
Subject: filemap: Remove obsolete comment in lock_page

We no longer need the page's inode pinned.  This comment dates back to
commit db37648cd6ce ("[PATCH] mm: non syncing lock_page()") which added
lock_page_nosync().  That was removed by commit 7eaceaccab5f ("block:
remove per-queue plugging") which also made this comment obsolete.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/pagemap.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 65ae8f96554b..ab47579af434 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -908,9 +908,6 @@ static inline void folio_lock(struct folio *folio)
 		__folio_lock(folio);
 }
 
-/*
- * lock_page may only be called if we have the page's inode pinned.
- */
 static inline void lock_page(struct page *page)
 {
 	struct folio *folio;
-- 
cgit v1.2.3


From cd125eeab2de8ef8ca3a0f3a284bc695375c73af Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 4 Apr 2022 13:24:36 -0400
Subject: filemap: Update the folio_lock documentation

Add kernel-doc for several functions relating to take the folio lock.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/pagemap.h | 59 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 57 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index ab47579af434..60657132080f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -888,6 +888,18 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm,
 void unlock_page(struct page *page);
 void folio_unlock(struct folio *folio);
 
+/**
+ * folio_trylock() - Attempt to lock a folio.
+ * @folio: The folio to attempt to lock.
+ *
+ * Sometimes it is undesirable to wait for a folio to be unlocked (eg
+ * when the locks are being taken in the wrong order, or if making
+ * progress through a batch of folios is more important than processing
+ * them in order).  Usually folio_lock() is the correct function to call.
+ *
+ * Context: Any context.
+ * Return: Whether the lock was successfully acquired.
+ */
 static inline bool folio_trylock(struct folio *folio)
 {
 	return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0)));
@@ -901,6 +913,28 @@ static inline int trylock_page(struct page *page)
 	return folio_trylock(page_folio(page));
 }
 
+/**
+ * folio_lock() - Lock this folio.
+ * @folio: The folio to lock.
+ *
+ * The folio lock protects against many things, probably more than it
+ * should.  It is primarily held while a folio is being brought uptodate,
+ * either from its backing file or from swap.  It is also held while a
+ * folio is being truncated from its address_space, so holding the lock
+ * is sufficient to keep folio->mapping stable.
+ *
+ * The folio lock is also held while write() is modifying the page to
+ * provide POSIX atomicity guarantees (as long as the write does not
+ * cross a page boundary).  Other modifications to the data in the folio
+ * do not hold the folio lock and can race with writes, eg DMA and stores
+ * to mapped pages.
+ *
+ * Context: May sleep.  If you need to acquire the locks of two or
+ * more folios, they must be in order of ascending index, if they are
+ * in the same address_space.  If they are in different address_spaces,
+ * acquire the lock of the folio which belongs to the address_space which
+ * has the lowest address in memory first.
+ */
 static inline void folio_lock(struct folio *folio)
 {
 	might_sleep();
@@ -908,6 +942,17 @@ static inline void folio_lock(struct folio *folio)
 		__folio_lock(folio);
 }
 
+/**
+ * lock_page() - Lock the folio containing this page.
+ * @page: The page to lock.
+ *
+ * See folio_lock() for a description of what the lock protects.
+ * This is a legacy function and new code should probably use folio_lock()
+ * instead.
+ *
+ * Context: May sleep.  Pages in the same folio share a lock, so do not
+ * attempt to lock two pages which share a folio.
+ */
 static inline void lock_page(struct page *page)
 {
 	struct folio *folio;
@@ -918,6 +963,16 @@ static inline void lock_page(struct page *page)
 		__folio_lock(folio);
 }
 
+/**
+ * folio_lock_killable() - Lock this folio, interruptible by a fatal signal.
+ * @folio: The folio to lock.
+ *
+ * Attempts to lock the folio, like folio_lock(), except that the sleep
+ * to acquire the lock is interruptible by a fatal signal.
+ *
+ * Context: May sleep; see folio_lock().
+ * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received.
+ */
 static inline int folio_lock_killable(struct folio *folio)
 {
 	might_sleep();
@@ -964,8 +1019,8 @@ int folio_wait_bit_killable(struct folio *folio, int bit_nr);
  * Wait for a folio to be unlocked.
  *
  * This must be called with the caller "holding" the folio,
- * ie with increased "page->count" so that the folio won't
- * go away during the wait..
+ * ie with increased folio reference count so that the folio won't
+ * go away during the wait.
  */
 static inline void folio_wait_locked(struct folio *folio)
 {
-- 
cgit v1.2.3


From 520f301c54faa3484e820b80d4505d48ee587163 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 17 Jan 2022 14:35:22 -0500
Subject: fs: Convert is_dirty_writeback() to take a folio

Pass a folio instead of a page to aops->is_dirty_writeback().
Convert both implementations and the caller.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/filesystems/vfs.rst | 10 +++++-----
 fs/buffer.c                       | 16 ++++++++--------
 fs/nfs/file.c                     | 21 +++++++++------------
 include/linux/buffer_head.h       |  2 +-
 include/linux/fs.h                |  2 +-
 mm/vmscan.c                       |  2 +-
 6 files changed, 25 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 30f303180a7d..469882f72fc1 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -747,7 +747,7 @@ cache in your filesystem.  The following members are defined:
 
 		bool (*is_partially_uptodate) (struct folio *, size_t from,
 					       size_t count);
-		void (*is_dirty_writeback) (struct page *, bool *, bool *);
+		void (*is_dirty_writeback)(struct folio *, bool *, bool *);
 		int (*error_remove_page) (struct mapping *mapping, struct page *page);
 		int (*swap_activate)(struct file *);
 		int (*swap_deactivate)(struct file *);
@@ -932,14 +932,14 @@ cache in your filesystem.  The following members are defined:
 	without needing I/O to bring the whole page up to date.
 
 ``is_dirty_writeback``
-	Called by the VM when attempting to reclaim a page.  The VM uses
+	Called by the VM when attempting to reclaim a folio.  The VM uses
 	dirty and writeback information to determine if it needs to
 	stall to allow flushers a chance to complete some IO.
-	Ordinarily it can use PageDirty and PageWriteback but some
-	filesystems have more complex state (unstable pages in NFS
+	Ordinarily it can use folio_test_dirty and folio_test_writeback but
+	some filesystems have more complex state (unstable folios in NFS
 	prevent reclaim) or do not set those flags due to locking
 	problems.  This callback allows a filesystem to indicate to the
-	VM if a page should be treated as dirty or writeback for the
+	VM if a folio should be treated as dirty or writeback for the
 	purposes of stalling.
 
 ``error_remove_page``
diff --git a/fs/buffer.c b/fs/buffer.c
index d538495a0553..fb4df259c92d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -79,26 +79,26 @@ void unlock_buffer(struct buffer_head *bh)
 EXPORT_SYMBOL(unlock_buffer);
 
 /*
- * Returns if the page has dirty or writeback buffers. If all the buffers
- * are unlocked and clean then the PageDirty information is stale. If
- * any of the pages are locked, it is assumed they are locked for IO.
+ * Returns if the folio has dirty or writeback buffers. If all the buffers
+ * are unlocked and clean then the folio_test_dirty information is stale. If
+ * any of the buffers are locked, it is assumed they are locked for IO.
  */
-void buffer_check_dirty_writeback(struct page *page,
+void buffer_check_dirty_writeback(struct folio *folio,
 				     bool *dirty, bool *writeback)
 {
 	struct buffer_head *head, *bh;
 	*dirty = false;
 	*writeback = false;
 
-	BUG_ON(!PageLocked(page));
+	BUG_ON(!folio_test_locked(folio));
 
-	if (!page_has_buffers(page))
+	head = folio_buffers(folio);
+	if (!head)
 		return;
 
-	if (PageWriteback(page))
+	if (folio_test_writeback(folio))
 		*writeback = true;
 
-	head = page_buffers(page);
 	bh = head;
 	do {
 		if (buffer_locked(bh))
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 314d2d7ba84a..f05c4b18b681 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -430,19 +430,16 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 	return nfs_fscache_release_page(page, gfp);
 }
 
-static void nfs_check_dirty_writeback(struct page *page,
+static void nfs_check_dirty_writeback(struct folio *folio,
 				bool *dirty, bool *writeback)
 {
 	struct nfs_inode *nfsi;
-	struct address_space *mapping = page_file_mapping(page);
-
-	if (!mapping || PageSwapCache(page))
-		return;
+	struct address_space *mapping = folio->mapping;
 
 	/*
-	 * Check if an unstable page is currently being committed and
-	 * if so, have the VM treat it as if the page is under writeback
-	 * so it will not block due to pages that will shortly be freeable.
+	 * Check if an unstable folio is currently being committed and
+	 * if so, have the VM treat it as if the folio is under writeback
+	 * so it will not block due to folios that will shortly be freeable.
 	 */
 	nfsi = NFS_I(mapping->host);
 	if (atomic_read(&nfsi->commit_info.rpcs_out)) {
@@ -451,11 +448,11 @@ static void nfs_check_dirty_writeback(struct page *page,
 	}
 
 	/*
-	 * If PagePrivate() is set, then the page is not freeable and as the
-	 * inode is not being committed, it's not going to be cleaned in the
-	 * near future so treat it as dirty
+	 * If the private flag is set, then the folio is not freeable
+	 * and as the inode is not being committed, it's not going to
+	 * be cleaned in the near future so treat it as dirty
 	 */
-	if (PagePrivate(page))
+	if (folio_test_private(folio))
 		*dirty = true;
 }
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 6e5a64005fef..805c4e12700a 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -146,7 +146,7 @@ BUFFER_FNS(Defer_Completion, defer_completion)
 #define page_has_buffers(page)	PagePrivate(page)
 #define folio_buffers(folio)		folio_get_private(folio)
 
-void buffer_check_dirty_writeback(struct page *page,
+void buffer_check_dirty_writeback(struct folio *folio,
 				     bool *dirty, bool *writeback);
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b35ce086a7a1..2be852661a29 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -369,7 +369,7 @@ struct address_space_operations {
 	int (*launder_folio)(struct folio *);
 	bool (*is_partially_uptodate) (struct folio *, size_t from,
 			size_t count);
-	void (*is_dirty_writeback) (struct page *, bool *, bool *);
+	void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb);
 	int (*error_remove_page)(struct address_space *, struct page *);
 
 	/* swapfile support */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1678802e03e7..27851232e00c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1451,7 +1451,7 @@ static void folio_check_dirty_writeback(struct folio *folio,
 
 	mapping = folio_mapping(folio);
 	if (mapping && mapping->a_ops->is_dirty_writeback)
-		mapping->a_ops->is_dirty_writeback(&folio->page, dirty, writeback);
+		mapping->a_ops->is_dirty_writeback(folio, dirty, writeback);
 }
 
 static struct page *alloc_demote_page(struct page *page, unsigned long node)
-- 
cgit v1.2.3


From 2ebdd1df316636c2faf25a1780e12553adf09cf7 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 17 Mar 2021 22:38:26 -0400
Subject: mm/readahead: Convert page_cache_async_readahead to take a folio

Removes a couple of calls to compound_head and saves a few bytes.
Also convert verity's read_file_data_page() to be folio-based.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/btrfs/relocation.c   |  5 +++--
 fs/btrfs/send.c         |  3 ++-
 fs/verity/enable.c      | 29 ++++++++++++++---------------
 include/linux/pagemap.h |  6 +++---
 4 files changed, 22 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index fdc2c4b411f0..9ae06895ffc9 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2967,8 +2967,9 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 		goto release_page;
 
 	if (PageReadahead(page))
-		page_cache_async_readahead(inode->i_mapping, ra, NULL, page,
-				   page_index, last_index + 1 - page_index);
+		page_cache_async_readahead(inode->i_mapping, ra, NULL,
+				page_folio(page), page_index,
+				last_index + 1 - page_index);
 
 	if (!PageUptodate(page)) {
 		btrfs_readpage(NULL, page);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 7d1642937274..b327dbe0cbf5 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4986,7 +4986,8 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len)
 
 		if (PageReadahead(page)) {
 			page_cache_async_readahead(inode->i_mapping, &sctx->ra,
-				NULL, page, index, last_index + 1 - index);
+						NULL, page_folio(page), index,
+						last_index + 1 - index);
 		}
 
 		if (!PageUptodate(page)) {
diff --git a/fs/verity/enable.c b/fs/verity/enable.c
index 60a4372aa4d7..f75d2c010f36 100644
--- a/fs/verity/enable.c
+++ b/fs/verity/enable.c
@@ -18,27 +18,26 @@
  * Read a file data page for Merkle tree construction.  Do aggressive readahead,
  * since we're sequentially reading the entire file.
  */
-static struct page *read_file_data_page(struct file *filp, pgoff_t index,
+static struct page *read_file_data_page(struct file *file, pgoff_t index,
 					struct file_ra_state *ra,
 					unsigned long remaining_pages)
 {
-	struct page *page;
+	DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, index);
+	struct folio *folio;
 
-	page = find_get_page_flags(filp->f_mapping, index, FGP_ACCESSED);
-	if (!page || !PageUptodate(page)) {
-		if (page)
-			put_page(page);
+	folio = __filemap_get_folio(ractl.mapping, index, FGP_ACCESSED, 0);
+	if (!folio || !folio_test_uptodate(folio)) {
+		if (folio)
+			folio_put(folio);
 		else
-			page_cache_sync_readahead(filp->f_mapping, ra, filp,
-						  index, remaining_pages);
-		page = read_mapping_page(filp->f_mapping, index, NULL);
-		if (IS_ERR(page))
-			return page;
+			page_cache_sync_ra(&ractl, remaining_pages);
+		folio = read_cache_folio(ractl.mapping, index, NULL, file);
+		if (IS_ERR(folio))
+			return &folio->page;
 	}
-	if (PageReadahead(page))
-		page_cache_async_readahead(filp->f_mapping, ra, filp, page,
-					   index, remaining_pages);
-	return page;
+	if (folio_test_readahead(folio))
+		page_cache_async_ra(&ractl, folio, remaining_pages);
+	return folio_file_page(folio, index);
 }
 
 static int build_merkle_tree_level(struct file *filp, unsigned int level,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 60657132080f..b70192f56454 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1242,7 +1242,7 @@ void page_cache_sync_readahead(struct address_space *mapping,
  * @mapping: address_space which holds the pagecache and I/O vectors
  * @ra: file_ra_state which holds the readahead state
  * @file: Used by the filesystem for authentication.
- * @page: The page at @index which triggered the readahead call.
+ * @folio: The folio at @index which triggered the readahead call.
  * @index: Index of first page to be read.
  * @req_count: Total number of pages being read by the caller.
  *
@@ -1254,10 +1254,10 @@ void page_cache_sync_readahead(struct address_space *mapping,
 static inline
 void page_cache_async_readahead(struct address_space *mapping,
 		struct file_ra_state *ra, struct file *file,
-		struct page *page, pgoff_t index, unsigned long req_count)
+		struct folio *folio, pgoff_t index, unsigned long req_count)
 {
 	DEFINE_READAHEAD(ractl, file, ra, mapping, index);
-	page_cache_async_ra(&ractl, page_folio(page), req_count);
+	page_cache_async_ra(&ractl, folio, req_count);
 }
 
 static inline struct folio *__readahead_folio(struct readahead_control *ractl)
-- 
cgit v1.2.3


From 6d97af487dee3176cb1342d4ab16637e495440ad Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Wed, 4 May 2022 08:23:50 +0200
Subject: entry: Rename arch_check_user_regs() to arch_enter_from_user_mode()

arch_check_user_regs() is used at the moment to verify that struct pt_regs
contains valid values when entering the kernel from userspace. s390 needs
a place in the generic entry code to modify a cpu data structure when
switching from userspace to kernel mode. As arch_check_user_regs() is
exactly this, rename it to arch_enter_from_user_mode().

When entering the kernel from userspace, arch_check_user_regs() is
used to verify that struct pt_regs contains valid values. Note that
the NMI codepath doesn't call this function. s390 needs a place in the
generic entry code to modify a cpu data structure when switching from
userspace to kernel mode. As arch_check_user_regs() is exactly this,
rename it to arch_enter_from_user_mode().

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20220504062351.2954280-2-tmricht@linux.ibm.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/entry-common.h | 4 ++--
 arch/x86/include/asm/entry-common.h  | 4 ++--
 include/linux/entry-common.h         | 8 ++++----
 kernel/entry/common.c                | 2 +-
 4 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h
index 2f0a1cacdf85..99d654ccd3db 100644
--- a/arch/s390/include/asm/entry-common.h
+++ b/arch/s390/include/asm/entry-common.h
@@ -15,12 +15,12 @@
 void do_per_trap(struct pt_regs *regs);
 
 #ifdef CONFIG_DEBUG_ENTRY
-static __always_inline void arch_check_user_regs(struct pt_regs *regs)
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs)
 {
 	debug_user_asce(0);
 }
 
-#define arch_check_user_regs arch_check_user_regs
+#define arch_enter_from_user_mode arch_enter_from_user_mode
 #endif /* CONFIG_DEBUG_ENTRY */
 
 static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 43184640b579..674ed46d3ced 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -10,7 +10,7 @@
 #include <asm/fpu/api.h>
 
 /* Check that the stack and regs on entry from user mode are sane. */
-static __always_inline void arch_check_user_regs(struct pt_regs *regs)
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
 		/*
@@ -42,7 +42,7 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs)
 		WARN_ON_ONCE(regs != task_pt_regs(current));
 	}
 }
-#define arch_check_user_regs arch_check_user_regs
+#define arch_enter_from_user_mode arch_enter_from_user_mode
 
 static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 						  unsigned long ti_work)
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index ab78bd4c2eb0..c92ac75d6556 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -63,7 +63,7 @@
 	 ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**
- * arch_check_user_regs - Architecture specific sanity check for user mode regs
+ * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs
  * @regs:	Pointer to currents pt_regs
  *
  * Defaults to an empty implementation. Can be replaced by architecture
@@ -73,10 +73,10 @@
  * section. Use __always_inline so the compiler cannot push it out of line
  * and make it instrumentable.
  */
-static __always_inline void arch_check_user_regs(struct pt_regs *regs);
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs);
 
-#ifndef arch_check_user_regs
-static __always_inline void arch_check_user_regs(struct pt_regs *regs) {}
+#ifndef arch_enter_from_user_mode
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
 #endif
 
 /**
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 93c3b86e781c..9e63923c5a0f 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -17,7 +17,7 @@
 /* See comment for enter_from_user_mode() in entry-common.h */
 static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
 {
-	arch_check_user_regs(regs);
+	arch_enter_from_user_mode(regs);
 	lockdep_hardirqs_off(CALLER_ADDR0);
 
 	CT_WARN_ON(ct_state() != CONTEXT_USER);
-- 
cgit v1.2.3


From 2fbdf45d7d26361a0c3ec8833fd96edf0f5812da Mon Sep 17 00:00:00 2001
From: Ricardo Martinez <ricardo.martinez@linux.intel.com>
Date: Fri, 6 May 2022 11:12:57 -0700
Subject: list: Add list_next_entry_circular() and list_prev_entry_circular()

Add macros to get the next or previous entries and wraparound if
needed. For example, calling list_next_entry_circular() on the last
element should return the first element in the list.

Signed-off-by: Ricardo Martinez <ricardo.martinez@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/list.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/list.h b/include/linux/list.h
index dd6c2041d09c..c147eeb2d39d 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -563,6 +563,19 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_next_entry(pos, member) \
 	list_entry((pos)->member.next, typeof(*(pos)), member)
 
+/**
+ * list_next_entry_circular - get the next element in list
+ * @pos:	the type * to cursor.
+ * @head:	the list head to take the element from.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Wraparound if pos is the last element (return the first element).
+ * Note, that list is expected to be not empty.
+ */
+#define list_next_entry_circular(pos, head, member) \
+	(list_is_last(&(pos)->member, head) ? \
+	list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member))
+
 /**
  * list_prev_entry - get the prev element in list
  * @pos:	the type * to cursor
@@ -571,6 +584,19 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_prev_entry(pos, member) \
 	list_entry((pos)->member.prev, typeof(*(pos)), member)
 
+/**
+ * list_prev_entry_circular - get the prev element in list
+ * @pos:	the type * to cursor.
+ * @head:	the list head to take the element from.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Wraparound if pos is the first element (return the last element).
+ * Note, that list is expected to be not empty.
+ */
+#define list_prev_entry_circular(pos, head, member) \
+	(list_is_first(&(pos)->member, head) ? \
+	list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member))
+
 /**
  * list_for_each	-	iterate over a list
  * @pos:	the &struct list_head to use as a loop cursor.
-- 
cgit v1.2.3


From a4ff365346c98081311c299955d91d657123e8aa Mon Sep 17 00:00:00 2001
From: Ricardo Martinez <ricardo.martinez@linux.intel.com>
Date: Fri, 6 May 2022 11:12:58 -0700
Subject: net: skb: introduce skb_data_area_size()

Helper to calculate the linear data space in the skb.

Signed-off-by: Ricardo Martinez <ricardo.martinez@linux.intel.com>
Reviewed-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5c2599e3fe7d..d58669d6cb91 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1665,6 +1665,11 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 }
 #endif
 
+static inline unsigned int skb_data_area_size(struct sk_buff *skb)
+{
+	return skb_end_pointer(skb) - skb->data;
+}
+
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 				       struct ubuf_info *uarg);
 
-- 
cgit v1.2.3


From ca4567f1e6f660f86fcd04f3563c0045b0d4772f Mon Sep 17 00:00:00 2001
From: Alaa Mohamed <eng.alaamohamedsoliman.am@gmail.com>
Date: Thu, 5 May 2022 17:09:57 +0200
Subject: rtnetlink: add extack support in fdb del handlers

Add extack support to .ndo_fdb_del in netdevice.h and
all related methods.

Signed-off-by: Alaa Mohamed <eng.alaamohamedsoliman.am@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ice/ice_main.c        | 3 ++-
 drivers/net/ethernet/mscc/ocelot_net.c           | 3 ++-
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 3 ++-
 drivers/net/macvlan.c                            | 3 ++-
 drivers/net/vxlan/vxlan_core.c                   | 3 ++-
 include/linux/netdevice.h                        | 2 +-
 net/bridge/br_fdb.c                              | 3 ++-
 net/bridge/br_private.h                          | 3 ++-
 net/core/rtnetlink.c                             | 4 ++--
 9 files changed, 17 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 049a3f48caff..867908f94661 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5688,11 +5688,12 @@ ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
  * @dev: the net device pointer
  * @addr: the MAC address entry being added
  * @vid: VLAN ID
+ * @extack: netlink extended ack
  */
 static int
 ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
 	    struct net_device *dev, const unsigned char *addr,
-	    __always_unused u16 vid)
+	    __always_unused u16 vid, struct netlink_ext_ack *extack)
 {
 	int err;
 
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 247bc105bdd2..616d8127ef51 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -774,7 +774,8 @@ static int ocelot_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 
 static int ocelot_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 			       struct net_device *dev,
-			       const unsigned char *addr, u16 vid)
+			       const unsigned char *addr, u16 vid,
+				   struct netlink_ext_ack *extack)
 {
 	struct ocelot_port_private *priv = netdev_priv(dev);
 	struct ocelot_port *ocelot_port = &priv->port;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index d320567b2cca..28476b982bab 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -368,7 +368,8 @@ static int qlcnic_set_mac(struct net_device *netdev, void *p)
 
 static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 			struct net_device *netdev,
-			const unsigned char *addr, u16 vid)
+			const unsigned char *addr, u16 vid,
+			struct netlink_ext_ack *extack)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	int err = -EOPNOTSUPP;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 0017bd0fe3bb..eff75beb1395 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1020,7 +1020,8 @@ static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 
 static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 			   struct net_device *dev,
-			   const unsigned char *addr, u16 vid)
+			   const unsigned char *addr, u16 vid,
+			   struct netlink_ext_ack *extack)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	int err = -EINVAL;
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 2bda692f70c5..91b7bb01fb10 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1280,7 +1280,8 @@ out:
 /* Delete entry (via netlink) */
 static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 			    struct net_device *dev,
-			    const unsigned char *addr, u16 vid)
+			    const unsigned char *addr, u16 vid,
+				struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	union vxlan_addr ip;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8cf0ac616cb9..74c97a34921d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1513,7 +1513,7 @@ struct net_device_ops {
 					       struct nlattr *tb[],
 					       struct net_device *dev,
 					       const unsigned char *addr,
-					       u16 vid);
+					       u16 vid, struct netlink_ext_ack *extack);
 	int			(*ndo_fdb_del_bulk)(struct ndmsg *ndm,
 						    struct nlattr *tb[],
 						    struct net_device *dev,
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 1a3d583fbc8e..e7f4fccb6adb 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -1253,7 +1253,8 @@ static int __br_fdb_delete(struct net_bridge *br,
 /* Remove neighbor entry with RTM_DELNEIGH */
 int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		  struct net_device *dev,
-		  const unsigned char *addr, u16 vid)
+		  const unsigned char *addr, u16 vid,
+		  struct netlink_ext_ack *extack)
 {
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p = NULL;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 6ae882cfae1c..06e5f6faa431 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -793,7 +793,8 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 		   const unsigned char *addr, u16 vid, unsigned long flags);
 
 int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
-		  struct net_device *dev, const unsigned char *addr, u16 vid);
+		  struct net_device *dev, const unsigned char *addr, u16 vid,
+		  struct netlink_ext_ack *extack);
 int br_fdb_delete_bulk(struct ndmsg *ndm, struct nlattr *tb[],
 		       struct net_device *dev, u16 vid,
 		       struct netlink_ext_ack *extack);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e6d4b9272995..6aff02df9ba5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4258,7 +4258,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		ops = br_dev->netdev_ops;
 		if (!del_bulk) {
 			if (ops->ndo_fdb_del)
-				err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
+				err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid, extack);
 		} else {
 			if (ops->ndo_fdb_del_bulk)
 				err = ops->ndo_fdb_del_bulk(ndm, tb, dev, vid,
@@ -4276,7 +4276,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		ops = dev->netdev_ops;
 		if (!del_bulk) {
 			if (ops->ndo_fdb_del)
-				err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
+				err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid, extack);
 			else
 				err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
 		} else {
-- 
cgit v1.2.3


From 90532850eb210dff70423eaf20e323a91ef542d8 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 6 May 2022 06:23:52 +0200
Subject: net: phy: introduce genphy_c45_pma_baset1_setup_master_slave()

Move baset1 specific part of genphy_c45_pma_setup_forced() code to
separate function to make it reusable by PHY drivers.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-c45.c | 49 +++++++++++++++++++++++++++++------------------
 include/linux/phy.h       |  1 +
 2 files changed, 31 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 0014aa6e73c0..ffa2d5cd09fc 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -70,6 +70,35 @@ int genphy_c45_pma_suspend(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(genphy_c45_pma_suspend);
 
+/**
+ * genphy_c45_pma_baset1_setup_master_slave - configures forced master/slave
+ * role of BaseT1 devices.
+ * @phydev: target phy_device struct
+ */
+int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev)
+{
+	int ctl = 0;
+
+	switch (phydev->master_slave_set) {
+	case MASTER_SLAVE_CFG_MASTER_PREFERRED:
+	case MASTER_SLAVE_CFG_MASTER_FORCE:
+		ctl = MDIO_PMA_PMD_BT1_CTRL_CFG_MST;
+		break;
+	case MASTER_SLAVE_CFG_SLAVE_FORCE:
+	case MASTER_SLAVE_CFG_SLAVE_PREFERRED:
+	case MASTER_SLAVE_CFG_UNKNOWN:
+	case MASTER_SLAVE_CFG_UNSUPPORTED:
+		break;
+	default:
+		phydev_warn(phydev, "Unsupported Master/Slave mode\n");
+		return -EOPNOTSUPP;
+	}
+
+	return phy_modify_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1_CTRL,
+			     MDIO_PMA_PMD_BT1_CTRL_CFG_MST, ctl);
+}
+EXPORT_SYMBOL_GPL(genphy_c45_pma_baset1_setup_master_slave);
+
 /**
  * genphy_c45_pma_setup_forced - configures a forced speed
  * @phydev: target phy_device struct
@@ -141,25 +170,7 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev)
 		return ret;
 
 	if (genphy_c45_baset1_able(phydev)) {
-		int ctl = 0;
-
-		switch (phydev->master_slave_set) {
-		case MASTER_SLAVE_CFG_MASTER_PREFERRED:
-		case MASTER_SLAVE_CFG_MASTER_FORCE:
-			ctl = MDIO_PMA_PMD_BT1_CTRL_CFG_MST;
-			break;
-		case MASTER_SLAVE_CFG_SLAVE_FORCE:
-		case MASTER_SLAVE_CFG_SLAVE_PREFERRED:
-		case MASTER_SLAVE_CFG_UNKNOWN:
-		case MASTER_SLAVE_CFG_UNSUPPORTED:
-			break;
-		default:
-			phydev_warn(phydev, "Unsupported Master/Slave mode\n");
-			return -EOPNOTSUPP;
-		}
-
-		ret = phy_modify_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1_CTRL,
-				     MDIO_PMA_PMD_BT1_CTRL_CFG_MST, ctl);
+		ret = genphy_c45_pma_baset1_setup_master_slave(phydev);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 2d12054932ba..d3f924d3b235 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1614,6 +1614,7 @@ int genphy_c45_read_link(struct phy_device *phydev);
 int genphy_c45_read_lpa(struct phy_device *phydev);
 int genphy_c45_read_pma(struct phy_device *phydev);
 int genphy_c45_pma_setup_forced(struct phy_device *phydev);
+int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev);
 int genphy_c45_an_config_aneg(struct phy_device *phydev);
 int genphy_c45_an_disable_aneg(struct phy_device *phydev);
 int genphy_c45_read_mdix(struct phy_device *phydev);
-- 
cgit v1.2.3


From b9a366f3d874ce1c9c0148ec399f2ce4ab05a467 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 6 May 2022 06:23:54 +0200
Subject: net: phy: introduce genphy_c45_pma_baset1_read_master_slave()

Move baset1 specific part of genphy_c45_read_pma() code to
separate function to make it reusable by PHY drivers.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-c45.c | 31 +++++++++++++++++++++++++------
 include/linux/phy.h       |  1 +
 2 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index b1f7c63f66cd..d440b76a18b4 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -550,6 +550,30 @@ int genphy_c45_read_lpa(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(genphy_c45_read_lpa);
 
+/**
+ * genphy_c45_pma_baset1_read_master_slave - read forced master/slave
+ * configuration
+ * @phydev: target phy_device struct
+ */
+int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev)
+{
+	int val;
+
+	phydev->master_slave_state = MASTER_SLAVE_STATE_UNKNOWN;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1_CTRL);
+	if (val < 0)
+		return val;
+
+	if (val & MDIO_PMA_PMD_BT1_CTRL_CFG_MST)
+		phydev->master_slave_state = MASTER_SLAVE_STATE_MASTER;
+	else
+		phydev->master_slave_state = MASTER_SLAVE_STATE_SLAVE;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genphy_c45_pma_baset1_read_master_slave);
+
 /**
  * genphy_c45_read_pma - read link speed etc from PMA
  * @phydev: target phy_device struct
@@ -591,14 +615,9 @@ int genphy_c45_read_pma(struct phy_device *phydev)
 	phydev->duplex = DUPLEX_FULL;
 
 	if (genphy_c45_baset1_able(phydev)) {
-		val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1_CTRL);
+		val = genphy_c45_pma_baset1_read_master_slave(phydev);
 		if (val < 0)
 			return val;
-
-		if (MDIO_PMA_PMD_BT1_CTRL_CFG_MST)
-			phydev->master_slave_state = MASTER_SLAVE_STATE_MASTER;
-		else
-			phydev->master_slave_state = MASTER_SLAVE_STATE_SLAVE;
 	}
 
 	return 0;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index d3f924d3b235..4713c95d65fb 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1619,6 +1619,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev);
 int genphy_c45_an_disable_aneg(struct phy_device *phydev);
 int genphy_c45_read_mdix(struct phy_device *phydev);
 int genphy_c45_pma_read_abilities(struct phy_device *phydev);
+int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev);
 int genphy_c45_read_status(struct phy_device *phydev);
 int genphy_c45_config_aneg(struct phy_device *phydev);
 int genphy_c45_loopback(struct phy_device *phydev, bool enable);
-- 
cgit v1.2.3


From 2013ad8836aceb828c0fb5b16fa8bb98fd3d9b28 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 6 May 2022 06:23:56 +0200
Subject: net: phy: export genphy_c45_baset1_read_status()

Export genphy_c45_baset1_read_status() to make it reusable by PHY drivers.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-c45.c | 3 ++-
 include/linux/phy.h       | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index a0684c716a2e..29b1df03f3e8 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -785,7 +785,7 @@ EXPORT_SYMBOL_GPL(genphy_c45_pma_read_abilities);
  * is forced or not, it is read from BASE-T1 AN advertisement
  * register 7.514.
  */
-static int genphy_c45_baset1_read_status(struct phy_device *phydev)
+int genphy_c45_baset1_read_status(struct phy_device *phydev)
 {
 	int ret;
 	int cfg;
@@ -815,6 +815,7 @@ static int genphy_c45_baset1_read_status(struct phy_device *phydev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(genphy_c45_baset1_read_status);
 
 /**
  * genphy_c45_read_status - read PHY status
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4713c95d65fb..508f1149665b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1621,6 +1621,7 @@ int genphy_c45_read_mdix(struct phy_device *phydev);
 int genphy_c45_pma_read_abilities(struct phy_device *phydev);
 int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev);
 int genphy_c45_read_status(struct phy_device *phydev);
+int genphy_c45_baset1_read_status(struct phy_device *phydev);
 int genphy_c45_config_aneg(struct phy_device *phydev);
 int genphy_c45_loopback(struct phy_device *phydev, bool enable);
 int genphy_c45_pma_resume(struct phy_device *phydev);
-- 
cgit v1.2.3


From 0257be79fc4a16a3252ce80aa13b3640f728c425 Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Fri, 29 Apr 2022 12:20:18 +0200
Subject: mtd: spi-nor: expose internal parameters via debugfs

There is no way to gather all information to verify support for a new
flash chip. Also if you want to convert an existing flash chip to the
new SFDP parsing, there is not enough information to determine if the
flash will work like before. To ease this development, expose internal
parameters via the debugfs.

Signed-off-by: Michael Walle <michael@walle.cc>
Signed-off-by: Pratyush Yadav <p.yadav@ti.com>
Reviewed-by: Pratyush Yadav <p.yadav@ti.com>
Link: https://lore.kernel.org/r/20220429102018.2361038-2-michael@walle.cc
---
 drivers/mtd/spi-nor/Makefile  |   1 +
 drivers/mtd/spi-nor/core.c    |   2 +
 drivers/mtd/spi-nor/core.h    |   7 ++
 drivers/mtd/spi-nor/debugfs.c | 249 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/spi-nor.h   |   2 +
 5 files changed, 261 insertions(+)
 create mode 100644 drivers/mtd/spi-nor/debugfs.c

(limited to 'include/linux')

diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile
index 6b904e439372..e347b435a038 100644
--- a/drivers/mtd/spi-nor/Makefile
+++ b/drivers/mtd/spi-nor/Makefile
@@ -17,6 +17,7 @@ spi-nor-objs			+= sst.o
 spi-nor-objs			+= winbond.o
 spi-nor-objs			+= xilinx.o
 spi-nor-objs			+= xmc.o
+spi-nor-$(CONFIG_DEBUG_FS)	+= debugfs.o
 obj-$(CONFIG_MTD_SPI_NOR)	+= spi-nor.o
 
 obj-$(CONFIG_MTD_SPI_NOR)	+= controllers/
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 8377bd1842da..502967c76c5f 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -3132,6 +3132,8 @@ static int spi_nor_probe(struct spi_mem *spimem)
 	if (ret)
 		return ret;
 
+	spi_nor_debugfs_register(nor);
+
 	/*
 	 * None of the existing parts have > 512B pages, but let's play safe
 	 * and add this logic so that if anyone ever adds support for such
diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h
index ef37e179c615..3f841ec36e56 100644
--- a/drivers/mtd/spi-nor/core.h
+++ b/drivers/mtd/spi-nor/core.h
@@ -114,6 +114,7 @@
 		   SPI_MEM_OP_NO_ADDR,					\
 		   SPI_MEM_OP_NO_DATA)
 
+/* Keep these in sync with the list in debugfs.c */
 enum spi_nor_option_flags {
 	SNOR_F_HAS_SR_TB	= BIT(0),
 	SNOR_F_NO_OP_CHIP_ERASE	= BIT(1),
@@ -700,4 +701,10 @@ static inline struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd)
 	return container_of(mtd, struct spi_nor, mtd);
 }
 
+#ifdef CONFIG_DEBUG_FS
+void spi_nor_debugfs_register(struct spi_nor *nor);
+#else
+static inline void spi_nor_debugfs_register(struct spi_nor *nor) {}
+#endif
+
 #endif /* __LINUX_MTD_SPI_NOR_INTERNAL_H */
diff --git a/drivers/mtd/spi-nor/debugfs.c b/drivers/mtd/spi-nor/debugfs.c
new file mode 100644
index 000000000000..1949905eefea
--- /dev/null
+++ b/drivers/mtd/spi-nor/debugfs.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mtd/spi-nor.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+#include <linux/debugfs.h>
+
+#include "core.h"
+
+#define SPI_NOR_DEBUGFS_ROOT "spi-nor"
+
+#define SNOR_F_NAME(name) [ilog2(SNOR_F_##name)] = #name
+static const char *const snor_f_names[] = {
+	SNOR_F_NAME(HAS_SR_TB),
+	SNOR_F_NAME(NO_OP_CHIP_ERASE),
+	SNOR_F_NAME(BROKEN_RESET),
+	SNOR_F_NAME(4B_OPCODES),
+	SNOR_F_NAME(HAS_4BAIT),
+	SNOR_F_NAME(HAS_LOCK),
+	SNOR_F_NAME(HAS_16BIT_SR),
+	SNOR_F_NAME(NO_READ_CR),
+	SNOR_F_NAME(HAS_SR_TB_BIT6),
+	SNOR_F_NAME(HAS_4BIT_BP),
+	SNOR_F_NAME(HAS_SR_BP3_BIT6),
+	SNOR_F_NAME(IO_MODE_EN_VOLATILE),
+	SNOR_F_NAME(SOFT_RESET),
+	SNOR_F_NAME(SWP_IS_VOLATILE),
+};
+#undef SNOR_F_NAME
+
+static const char *spi_nor_protocol_name(enum spi_nor_protocol proto)
+{
+	switch (proto) {
+	case SNOR_PROTO_1_1_1:     return "1S-1S-1S";
+	case SNOR_PROTO_1_1_2:     return "1S-1S-2S";
+	case SNOR_PROTO_1_1_4:     return "1S-1S-4S";
+	case SNOR_PROTO_1_1_8:     return "1S-1S-8S";
+	case SNOR_PROTO_1_2_2:     return "1S-2S-2S";
+	case SNOR_PROTO_1_4_4:     return "1S-4S-4S";
+	case SNOR_PROTO_1_8_8:     return "1S-8S-8S";
+	case SNOR_PROTO_2_2_2:     return "2S-2S-2S";
+	case SNOR_PROTO_4_4_4:     return "4S-4S-4S";
+	case SNOR_PROTO_8_8_8:     return "8S-8S-8S";
+	case SNOR_PROTO_1_1_1_DTR: return "1D-1D-1D";
+	case SNOR_PROTO_1_2_2_DTR: return "1D-2D-2D";
+	case SNOR_PROTO_1_4_4_DTR: return "1D-4D-4D";
+	case SNOR_PROTO_1_8_8_DTR: return "1D-8D-8D";
+	case SNOR_PROTO_8_8_8_DTR: return "8D-8D-8D";
+	}
+
+	return "<unknown>";
+}
+
+static void spi_nor_print_flags(struct seq_file *s, unsigned long flags,
+				const char *const *names, int names_len)
+{
+	bool sep = false;
+	int i;
+
+	for (i = 0; i < sizeof(flags) * BITS_PER_BYTE; i++) {
+		if (!(flags & BIT(i)))
+			continue;
+		if (sep)
+			seq_puts(s, " | ");
+		sep = true;
+		if (i < names_len && names[i])
+			seq_puts(s, names[i]);
+		else
+			seq_printf(s, "1<<%d", i);
+	}
+}
+
+static int spi_nor_params_show(struct seq_file *s, void *data)
+{
+	struct spi_nor *nor = s->private;
+	struct spi_nor_flash_parameter *params = nor->params;
+	struct spi_nor_erase_map *erase_map = &params->erase_map;
+	struct spi_nor_erase_region *region;
+	const struct flash_info *info = nor->info;
+	char buf[16], *str;
+	int i;
+
+	seq_printf(s, "name\t\t%s\n", info->name);
+	seq_printf(s, "id\t\t%*phn\n", info->id_len, info->id);
+	string_get_size(params->size, 1, STRING_UNITS_2, buf, sizeof(buf));
+	seq_printf(s, "size\t\t%s\n", buf);
+	seq_printf(s, "write size\t%u\n", params->writesize);
+	seq_printf(s, "page size\t%u\n", params->page_size);
+	seq_printf(s, "address width\t%u\n", nor->addr_width);
+
+	seq_puts(s, "flags\t\t");
+	spi_nor_print_flags(s, nor->flags, snor_f_names, sizeof(snor_f_names));
+	seq_puts(s, "\n");
+
+	seq_puts(s, "\nopcodes\n");
+	seq_printf(s, " read\t\t0x%02x\n", nor->read_opcode);
+	seq_printf(s, "  dummy cycles\t%u\n", nor->read_dummy);
+	seq_printf(s, " erase\t\t0x%02x\n", nor->erase_opcode);
+	seq_printf(s, " program\t0x%02x\n", nor->program_opcode);
+
+	switch (nor->cmd_ext_type) {
+	case SPI_NOR_EXT_NONE:
+		str = "none";
+		break;
+	case SPI_NOR_EXT_REPEAT:
+		str = "repeat";
+		break;
+	case SPI_NOR_EXT_INVERT:
+		str = "invert";
+		break;
+	default:
+		str = "<unknown>";
+		break;
+	}
+	seq_printf(s, " 8D extension\t%s\n", str);
+
+	seq_puts(s, "\nprotocols\n");
+	seq_printf(s, " read\t\t%s\n",
+		   spi_nor_protocol_name(nor->read_proto));
+	seq_printf(s, " write\t\t%s\n",
+		   spi_nor_protocol_name(nor->write_proto));
+	seq_printf(s, " register\t%s\n",
+		   spi_nor_protocol_name(nor->reg_proto));
+
+	seq_puts(s, "\nerase commands\n");
+	for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) {
+		struct spi_nor_erase_type *et = &erase_map->erase_type[i];
+
+		if (et->size) {
+			string_get_size(et->size, 1, STRING_UNITS_2, buf,
+					sizeof(buf));
+			seq_printf(s, " %02x (%s) [%d]\n", et->opcode, buf, i);
+		}
+	}
+
+	if (!(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
+		string_get_size(params->size, 1, STRING_UNITS_2, buf, sizeof(buf));
+		seq_printf(s, " %02x (%s)\n", SPINOR_OP_CHIP_ERASE, buf);
+	}
+
+	seq_puts(s, "\nsector map\n");
+	seq_puts(s, " region (in hex)   | erase mask | flags\n");
+	seq_puts(s, " ------------------+------------+----------\n");
+	for (region = erase_map->regions;
+	     region;
+	     region = spi_nor_region_next(region)) {
+		u64 start = region->offset & ~SNOR_ERASE_FLAGS_MASK;
+		u64 flags = region->offset & SNOR_ERASE_FLAGS_MASK;
+		u64 end = start + region->size - 1;
+
+		seq_printf(s, " %08llx-%08llx |     [%c%c%c%c] | %s\n",
+			   start, end,
+			   flags & BIT(0) ? '0' : ' ',
+			   flags & BIT(1) ? '1' : ' ',
+			   flags & BIT(2) ? '2' : ' ',
+			   flags & BIT(3) ? '3' : ' ',
+			   flags & SNOR_OVERLAID_REGION ? "overlaid" : "");
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(spi_nor_params);
+
+static void spi_nor_print_read_cmd(struct seq_file *s, u32 cap,
+				   struct spi_nor_read_command *cmd)
+{
+	seq_printf(s, " %s%s\n", spi_nor_protocol_name(cmd->proto),
+		   cap == SNOR_HWCAPS_READ_FAST ? " (fast read)" : "");
+	seq_printf(s, "  opcode\t0x%02x\n", cmd->opcode);
+	seq_printf(s, "  mode cycles\t%u\n", cmd->num_mode_clocks);
+	seq_printf(s, "  dummy cycles\t%u\n", cmd->num_wait_states);
+}
+
+static void spi_nor_print_pp_cmd(struct seq_file *s,
+				 struct spi_nor_pp_command *cmd)
+{
+	seq_printf(s, " %s\n", spi_nor_protocol_name(cmd->proto));
+	seq_printf(s, "  opcode\t0x%02x\n", cmd->opcode);
+}
+
+static int spi_nor_capabilities_show(struct seq_file *s, void *data)
+{
+	struct spi_nor *nor = s->private;
+	struct spi_nor_flash_parameter *params = nor->params;
+	u32 hwcaps = params->hwcaps.mask;
+	int i, cmd;
+
+	seq_puts(s, "Supported read modes by the flash\n");
+	for (i = 0; i < sizeof(hwcaps) * BITS_PER_BYTE; i++) {
+		if (!(hwcaps & BIT(i)))
+			continue;
+
+		cmd = spi_nor_hwcaps_read2cmd(BIT(i));
+		if (cmd < 0)
+			continue;
+
+		spi_nor_print_read_cmd(s, BIT(i), &params->reads[cmd]);
+		hwcaps &= ~BIT(i);
+	}
+
+	seq_puts(s, "\nSupported page program modes by the flash\n");
+	for (i = 0; i < sizeof(hwcaps) * BITS_PER_BYTE; i++) {
+		if (!(hwcaps & BIT(i)))
+			continue;
+
+		cmd = spi_nor_hwcaps_pp2cmd(BIT(i));
+		if (cmd < 0)
+			continue;
+
+		spi_nor_print_pp_cmd(s, &params->page_programs[cmd]);
+		hwcaps &= ~BIT(i);
+	}
+
+	if (hwcaps)
+		seq_printf(s, "\nunknown hwcaps 0x%x\n", hwcaps);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(spi_nor_capabilities);
+
+static void spi_nor_debugfs_unregister(void *data)
+{
+	struct spi_nor *nor = data;
+
+	debugfs_remove(nor->debugfs_root);
+	nor->debugfs_root = NULL;
+}
+
+void spi_nor_debugfs_register(struct spi_nor *nor)
+{
+	struct dentry *rootdir, *d;
+	int ret;
+
+	/* Create rootdir once. Will never be deleted again. */
+	rootdir = debugfs_lookup(SPI_NOR_DEBUGFS_ROOT, NULL);
+	if (!rootdir)
+		rootdir = debugfs_create_dir(SPI_NOR_DEBUGFS_ROOT, NULL);
+
+	ret = devm_add_action(nor->dev, spi_nor_debugfs_unregister, nor);
+	if (ret)
+		return;
+
+	d = debugfs_create_dir(dev_name(nor->dev), rootdir);
+	nor->debugfs_root = d;
+
+	debugfs_create_file("params", 0444, d, nor, &spi_nor_params_fops);
+	debugfs_create_file("capabilities", 0444, d, nor,
+			    &spi_nor_capabilities_fops);
+}
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index e505c4a5c530..1ede4c89805a 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -363,6 +363,7 @@ struct spi_nor_flash_parameter;
  * @write_proto:	the SPI protocol for write operations
  * @reg_proto:		the SPI protocol for read_reg/write_reg/erase operations
  * @sfdp:		the SFDP data of the flash
+ * @debugfs_root:	pointer to the debugfs directory
  * @controller_ops:	SPI NOR controller driver specific operations.
  * @params:		[FLASH-SPECIFIC] SPI NOR flash parameters and settings.
  *                      The structure includes legacy flash parameters and
@@ -392,6 +393,7 @@ struct spi_nor {
 	u32			flags;
 	enum spi_nor_cmd_ext	cmd_ext_type;
 	struct sfdp		*sfdp;
+	struct dentry		*debugfs_root;
 
 	const struct spi_nor_controller_ops *controller_ops;
 
-- 
cgit v1.2.3


From b1c5f3085149e9643b125eb10aae0e74644d7dcc Mon Sep 17 00:00:00 2001
From: Ricky WU <ricky_wu@realtek.com>
Date: Mon, 21 Mar 2022 11:18:30 +0000
Subject: misc: rtsx: add rts5261 efuse function

move rts5261_fetch_vendor_settings() to rts5261_init_from_hw()
make sure it be called from S3 or D3

add more register setting when efuse is set
read efuse setting to register on init flow

Signed-off-by: Ricky Wu <Ricky_wu@realtek.com>
Link: https://lore.kernel.org/r/18101ecb0f0749ccb9f564eda171ba40@realtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rts5261.c | 115 ++++++++++++++++++++------------------
 include/linux/rtsx_pci.h          |   3 +
 2 files changed, 65 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
index a77585ab0f30..749cc5a46d13 100644
--- a/drivers/misc/cardreader/rts5261.c
+++ b/drivers/misc/cardreader/rts5261.c
@@ -57,40 +57,6 @@ static void rts5261_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
 			 0xFF, driving[drive_sel][2]);
 }
 
-static void rtsx5261_fetch_vendor_settings(struct rtsx_pcr *pcr)
-{
-	struct pci_dev *pdev = pcr->pci;
-	u32 reg;
-
-	/* 0x814~0x817 */
-	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
-	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
-
-	if (!rts5261_vendor_setting_valid(reg)) {
-		/* Not support MMC default */
-		pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
-		pcr_dbg(pcr, "skip fetch vendor setting\n");
-		return;
-	}
-
-	if (!rts5261_reg_check_mmc_support(reg))
-		pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
-
-	/* TO do: need to add rtd3 function */
-	pcr->rtd3_en = rts5261_reg_to_rtd3(reg);
-
-	if (rts5261_reg_check_reverse_socket(reg))
-		pcr->flags |= PCR_REVERSE_SOCKET;
-
-	/* 0x724~0x727 */
-	pci_read_config_dword(pdev, PCR_SETTING_REG1, &reg);
-	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
-
-	pcr->aspm_en = rts5261_reg_to_aspm(reg);
-	pcr->sd30_drive_sel_1v8 = rts5261_reg_to_sd30_drive_sel_1v8(reg);
-	pcr->sd30_drive_sel_3v3 = rts5261_reg_to_sd30_drive_sel_3v3(reg);
-}
-
 static void rts5261_force_power_down(struct rtsx_pcr *pcr, u8 pm_state, bool runtime)
 {
 	/* Set relink_time to 0 */
@@ -391,11 +357,11 @@ static void rts5261_process_ocp(struct rtsx_pcr *pcr)
 
 }
 
-static int rts5261_init_from_hw(struct rtsx_pcr *pcr)
+static void rts5261_init_from_hw(struct rtsx_pcr *pcr)
 {
 	struct pci_dev *pdev = pcr->pci;
-	int retval;
-	u32 lval, i;
+	u32 lval1, lval2, i;
+	u16 setting_reg1, setting_reg2;
 	u8 valid, efuse_valid, tmp;
 
 	rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL,
@@ -418,26 +384,70 @@ static int rts5261_init_from_hw(struct rtsx_pcr *pcr)
 	efuse_valid = ((tmp & 0x0C) >> 2);
 	pcr_dbg(pcr, "Load efuse valid: 0x%x\n", efuse_valid);
 
-	if (efuse_valid == 0) {
-		retval = pci_read_config_dword(pdev, PCR_SETTING_REG2, &lval);
-		if (retval != 0)
-			pcr_dbg(pcr, "read 0x814 DW fail\n");
-		pcr_dbg(pcr, "DW from 0x814: 0x%x\n", lval);
-		/* 0x816 */
-		valid = (u8)((lval >> 16) & 0x03);
-		pcr_dbg(pcr, "0x816: %d\n", valid);
-	}
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &lval2);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, lval2);
+	/* 0x816 */
+	valid = (u8)((lval2 >> 16) & 0x03);
+
 	rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL,
 		REG_EFUSE_POR, 0);
 	pcr_dbg(pcr, "Disable efuse por!\n");
 
-	pci_read_config_dword(pdev, PCR_SETTING_REG2, &lval);
-	lval = lval & 0x00FFFFFF;
-	retval = pci_write_config_dword(pdev, PCR_SETTING_REG2, lval);
-	if (retval != 0)
-		pcr_dbg(pcr, "write config fail\n");
+	if (efuse_valid == 2 || efuse_valid == 3) {
+		if (valid == 3) {
+			/* Bypass efuse */
+			setting_reg1 = PCR_SETTING_REG1;
+			setting_reg2 = PCR_SETTING_REG2;
+		} else {
+			/* Use efuse data */
+			setting_reg1 = PCR_SETTING_REG4;
+			setting_reg2 = PCR_SETTING_REG5;
+		}
+	} else if (efuse_valid == 0) {
+		// default
+		setting_reg1 = PCR_SETTING_REG1;
+		setting_reg2 = PCR_SETTING_REG2;
+	}
+
+	pci_read_config_dword(pdev, setting_reg2, &lval2);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg2, lval2);
+
+	if (!rts5261_vendor_setting_valid(lval2)) {
+		/* Not support MMC default */
+		pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
+		pcr_dbg(pcr, "skip fetch vendor setting\n");
+		return;
+	}
+
+	if (!rts5261_reg_check_mmc_support(lval2))
+		pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
 
-	return retval;
+	pcr->rtd3_en = rts5261_reg_to_rtd3(lval2);
+
+	if (rts5261_reg_check_reverse_socket(lval2))
+		pcr->flags |= PCR_REVERSE_SOCKET;
+
+	pci_read_config_dword(pdev, setting_reg1, &lval1);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg1, lval1);
+
+	pcr->aspm_en = rts5261_reg_to_aspm(lval1);
+	pcr->sd30_drive_sel_1v8 = rts5261_reg_to_sd30_drive_sel_1v8(lval1);
+	pcr->sd30_drive_sel_3v3 = rts5261_reg_to_sd30_drive_sel_3v3(lval1);
+
+	if (setting_reg1 == PCR_SETTING_REG1) {
+		/* store setting */
+		rtsx_pci_write_register(pcr, 0xFF0C, 0xFF, (u8)(lval1 & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0D, 0xFF, (u8)((lval1 >> 8) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0E, 0xFF, (u8)((lval1 >> 16) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0F, 0xFF, (u8)((lval1 >> 24) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF10, 0xFF, (u8)(lval2 & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF11, 0xFF, (u8)((lval2 >> 8) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF12, 0xFF, (u8)((lval2 >> 16) & 0xFF));
+
+		pci_write_config_dword(pdev, PCR_SETTING_REG4, lval1);
+		lval2 = lval2 & 0x00FFFFFF;
+		pci_write_config_dword(pdev, PCR_SETTING_REG5, lval2);
+	}
 }
 
 static void rts5261_init_from_cfg(struct rtsx_pcr *pcr)
@@ -636,7 +646,6 @@ static void rts5261_set_l1off_cfg_sub_d0(struct rtsx_pcr *pcr, int active)
 }
 
 static const struct pcr_ops rts5261_pcr_ops = {
-	.fetch_vendor_settings = rtsx5261_fetch_vendor_settings,
 	.turn_on_led = rts5261_turn_on_led,
 	.turn_off_led = rts5261_turn_off_led,
 	.extra_init_hw = rts5261_extra_init_hw,
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 3d780b44e678..534038d962e4 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -1067,6 +1067,9 @@
 #define PCR_SETTING_REG1		0x724
 #define PCR_SETTING_REG2		0x814
 #define PCR_SETTING_REG3		0x747
+#define PCR_SETTING_REG4		0x818
+#define PCR_SETTING_REG5		0x81C
+
 
 #define rtsx_pci_init_cmd(pcr)		((pcr)->ci = 0)
 
-- 
cgit v1.2.3


From dbc2f62061c6bfba0aee93161ee3194dcee84bd0 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 29 Apr 2022 17:26:46 +0100
Subject: nvmem: core: support passing DT node in cell info
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some hardware may have NVMEM cells described in Device Tree using
individual nodes. Let drivers pass such nodes to the NVMEM subsystem so
they can be later used by NVMEM consumers.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20220429162701.2222-2-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           | 1 +
 include/linux/nvmem-consumer.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index f58d9bc7aa08..1e3c754efd0d 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -467,6 +467,7 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem,
 
 	cell->bit_offset = info->bit_offset;
 	cell->nbits = info->nbits;
+	cell->np = info->np;
 
 	if (cell->nbits)
 		cell->bytes = DIV_ROUND_UP(cell->nbits + cell->bit_offset,
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index c0c0cefc3b92..980f9c9ac0bc 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -25,6 +25,7 @@ struct nvmem_cell_info {
 	unsigned int		bytes;
 	unsigned int		bit_offset;
 	unsigned int		nbits;
+	struct device_node	*np;
 };
 
 /**
-- 
cgit v1.2.3


From 5efe7448a1426250b5747c10ad438517f44f1e51 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 08:43:23 -0400
Subject: fs: Introduce aops->read_folio

Change all the callers of ->readpage to call ->read_folio in preference,
if it exists.  This is a transitional duplication, and will be removed
by the end of the series.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 fs/btrfs/file.c         |  2 +-
 fs/buffer.c             |  5 ++++-
 fs/ceph/addr.c          |  2 +-
 include/linux/fs.h      |  1 +
 kernel/events/uprobes.c |  6 ++++--
 mm/filemap.c            |  9 +++++++--
 mm/readahead.c          | 14 +++++++++-----
 mm/swapfile.c           |  2 +-
 8 files changed, 28 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 380054c94e4b..59510d7b1c65 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2401,7 +2401,7 @@ static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = filp->f_mapping;
 
-	if (!mapping->a_ops->readpage)
+	if (!mapping->a_ops->readpage && !mapping->a_ops->read_folio)
 		return -ENOEXEC;
 
 	file_accessed(filp);
diff --git a/fs/buffer.c b/fs/buffer.c
index 9737e0dbe3ec..225d03cd622d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2824,7 +2824,10 @@ int nobh_truncate_page(struct address_space *mapping,
 
 	/* Ok, it's mapped. Make sure it's up-to-date */
 	if (!folio_test_uptodate(folio)) {
-		err = mapping->a_ops->readpage(NULL, &folio->page);
+		if (mapping->a_ops->read_folio)
+			err = mapping->a_ops->read_folio(NULL, folio);
+		else
+			err = mapping->a_ops->readpage(NULL, &folio->page);
 		if (err) {
 			folio_put(folio);
 			goto out;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e65541a51b68..42bba2b5d98b 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1772,7 +1772,7 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = file->f_mapping;
 
-	if (!mapping->a_ops->readpage)
+	if (!mapping->a_ops->readpage && !mapping->a_ops->read_folio)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &ceph_vmops;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2be852661a29..5ad942183a2c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -336,6 +336,7 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb)
 struct address_space_operations {
 	int (*writepage)(struct page *page, struct writeback_control *wbc);
 	int (*readpage)(struct file *, struct page *);
+	int (*read_folio)(struct file *, struct folio *);
 
 	/* Write back some dirty pages from this mapping. */
 	int (*writepages)(struct address_space *, struct writeback_control *);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 6418083901d4..2c7815d20038 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -790,7 +790,7 @@ static int __copy_insn(struct address_space *mapping, struct file *filp,
 	 * and in page-cache. If ->readpage == NULL it must be shmem_mapping(),
 	 * see uprobe_register().
 	 */
-	if (mapping->a_ops->readpage)
+	if (mapping->a_ops->read_folio || mapping->a_ops->readpage)
 		page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp);
 	else
 		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
@@ -1143,7 +1143,9 @@ static int __uprobe_register(struct inode *inode, loff_t offset,
 		return -EINVAL;
 
 	/* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */
-	if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping))
+	if (!inode->i_mapping->a_ops->read_folio &&
+	    !inode->i_mapping->a_ops->readpage &&
+	    !shmem_mapping(inode->i_mapping))
 		return -EIO;
 	/* Racy, just to catch the obvious mistakes */
 	if (offset > i_size_read(inode))
diff --git a/mm/filemap.c b/mm/filemap.c
index c15cfc28f9ce..96e3d7ffd98e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2419,7 +2419,10 @@ static int filemap_read_folio(struct file *file, struct address_space *mapping,
 	 */
 	folio_clear_error(folio);
 	/* Start the actual read. The read will unlock the page. */
-	error = mapping->a_ops->readpage(file, &folio->page);
+	if (mapping->a_ops->read_folio)
+		error = mapping->a_ops->read_folio(file, folio);
+	else
+		error = mapping->a_ops->readpage(file, &folio->page);
 	if (error)
 		return error;
 
@@ -3447,7 +3450,7 @@ int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = file->f_mapping;
 
-	if (!mapping->a_ops->readpage)
+	if (!mapping->a_ops->read_folio && !mapping->a_ops->readpage)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &generic_file_vm_ops;
@@ -3505,6 +3508,8 @@ repeat:
 filler:
 		if (filler)
 			err = filler(data, &folio->page);
+		else if (mapping->a_ops->read_folio)
+			err = mapping->a_ops->read_folio(data, folio);
 		else
 			err = mapping->a_ops->readpage(data, &folio->page);
 
diff --git a/mm/readahead.c b/mm/readahead.c
index 60a28af25c4e..76024c20a5a5 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -15,7 +15,7 @@
  * explicitly requested by the application.  Readahead only ever
  * attempts to read folios that are not yet in the page cache.  If a
  * folio is present but not up-to-date, readahead will not try to read
- * it. In that case a simple ->readpage() will be requested.
+ * it. In that case a simple ->read_folio() will be requested.
  *
  * Readahead is triggered when an application read request (whether a
  * system call or a page fault) finds that the requested folio is not in
@@ -78,7 +78,7 @@
  * address space operation, for which mpage_readahead() is a canonical
  * implementation.  ->readahead() should normally initiate reads on all
  * folios, but may fail to read any or all folios without causing an I/O
- * error.  The page cache reading code will issue a ->readpage() request
+ * error.  The page cache reading code will issue a ->read_folio() request
  * for any folio which ->readahead() did not read, and only an error
  * from this will be final.
  *
@@ -110,7 +110,7 @@
  * were not fetched with readahead_folio().  This will allow a
  * subsequent synchronous readahead request to try them again.  If they
  * are left in the page cache, then they will be read individually using
- * ->readpage() which may be less efficient.
+ * ->read_folio() which may be less efficient.
  */
 
 #include <linux/kernel.h>
@@ -170,8 +170,11 @@ static void read_pages(struct readahead_control *rac)
 			}
 			folio_unlock(folio);
 		}
+	} else if (aops->read_folio) {
+		while ((folio = readahead_folio(rac)) != NULL)
+			aops->read_folio(rac->file, folio);
 	} else {
-		while ((folio = readahead_folio(rac)))
+		while ((folio = readahead_folio(rac)) != NULL)
 			aops->readpage(rac->file, &folio->page);
 	}
 
@@ -302,7 +305,8 @@ void force_page_cache_ra(struct readahead_control *ractl,
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	unsigned long max_pages, index;
 
-	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readahead))
+	if (unlikely(!mapping->a_ops->read_folio &&
+		     !mapping->a_ops->readpage && !mapping->a_ops->readahead))
 		return;
 
 	/*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 63c61f8b2611..7c19098b8b45 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3041,7 +3041,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	/*
 	 * Read the swap header.
 	 */
-	if (!mapping->a_ops->readpage) {
+	if (!mapping->a_ops->read_folio && !mapping->a_ops->readpage) {
 		error = -EINVAL;
 		goto bad_swap_unlock_inode;
 	}
-- 
cgit v1.2.3


From 6c62371b7fd77628feb5b806bc29433caecedff8 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 08:49:28 -0400
Subject: fs: Convert netfs_readpage to netfs_read_folio

This is straightforward because netfs already worked in terms of folios.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 fs/9p/vfs_addr.c         |  2 +-
 fs/afs/file.c            |  2 +-
 fs/ceph/addr.c           |  2 +-
 fs/netfs/buffered_read.c | 15 +++++++--------
 include/linux/netfs.h    |  2 +-
 5 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index a2d57112f53e..3a84167f4893 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -336,7 +336,7 @@ static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio)
 #endif
 
 const struct address_space_operations v9fs_addr_operations = {
-	.readpage = netfs_readpage,
+	.read_folio = netfs_read_folio,
 	.readahead = netfs_readahead,
 	.dirty_folio = v9fs_dirty_folio,
 	.writepage = v9fs_vfs_writepage,
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 26292a110a8f..e277fbe55262 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -50,7 +50,7 @@ const struct inode_operations afs_file_inode_operations = {
 };
 
 const struct address_space_operations afs_file_aops = {
-	.readpage	= netfs_readpage,
+	.read_folio	= netfs_read_folio,
 	.readahead	= netfs_readahead,
 	.dirty_folio	= afs_dirty_folio,
 	.launder_folio	= afs_launder_folio,
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 42bba2b5d98b..be3e47784f08 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1372,7 +1372,7 @@ out:
 }
 
 const struct address_space_operations ceph_aops = {
-	.readpage = netfs_readpage,
+	.read_folio = netfs_read_folio,
 	.readahead = netfs_readahead,
 	.writepage = ceph_writepage,
 	.writepages = ceph_writepages_start,
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 1d44509455a5..8742d22dfd2b 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -198,22 +198,21 @@ cleanup_free:
 EXPORT_SYMBOL(netfs_readahead);
 
 /**
- * netfs_readpage - Helper to manage a readpage request
+ * netfs_read_folio - Helper to manage a read_folio request
  * @file: The file to read from
- * @subpage: A subpage of the folio to read
+ * @folio: The folio to read
  *
- * Fulfil a readpage request by drawing data from the cache if possible, or the
- * netfs if not.  Space beyond the EOF is zero-filled.  Multiple I/O requests
- * from different sources will get munged together.
+ * Fulfil a read_folio request by drawing data from the cache if
+ * possible, or the netfs if not.  Space beyond the EOF is zero-filled.
+ * Multiple I/O requests from different sources will get munged together.
  *
  * The calling netfs must initialise a netfs context contiguous to the vfs
  * inode before calling this.
  *
  * This is usable whether or not caching is enabled.
  */
-int netfs_readpage(struct file *file, struct page *subpage)
+int netfs_read_folio(struct file *file, struct folio *folio)
 {
-	struct folio *folio = page_folio(subpage);
 	struct address_space *mapping = folio_file_mapping(folio);
 	struct netfs_io_request *rreq;
 	struct netfs_i_context *ctx = netfs_i_context(mapping->host);
@@ -245,7 +244,7 @@ alloc_error:
 	folio_unlock(folio);
 	return ret;
 }
-EXPORT_SYMBOL(netfs_readpage);
+EXPORT_SYMBOL(netfs_read_folio);
 
 /*
  * Prepare a folio for writing without reading first
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 1c29f317d907..4bd5ee709daa 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -274,7 +274,7 @@ struct netfs_cache_ops {
 
 struct readahead_control;
 extern void netfs_readahead(struct readahead_control *);
-extern int netfs_readpage(struct file *, struct page *);
+int netfs_read_folio(struct file *, struct folio *);
 extern int netfs_write_begin(struct file *, struct address_space *,
 			     loff_t, unsigned int, struct folio **,
 			     void **);
-- 
cgit v1.2.3


From 7479c505b4ab5ed5f81f35fdd68c44c58d6f0439 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 08:54:32 -0400
Subject: fs: Convert iomap_readpage to iomap_read_folio

A straightforward conversion as iomap_readpage already worked in folios.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 fs/erofs/data.c        |  6 +++---
 fs/gfs2/aops.c         |  3 ++-
 fs/iomap/buffered-io.c | 12 +++++-------
 fs/xfs/xfs_aops.c      |  8 ++++----
 fs/zonefs/super.c      |  6 +++---
 include/linux/iomap.h  |  2 +-
 6 files changed, 18 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 780db1e5f4b7..2edca5669578 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -337,9 +337,9 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
  * since we dont have write or truncate flows, so no inode
  * locking needs to be held at the moment.
  */
-static int erofs_readpage(struct file *file, struct page *page)
+static int erofs_read_folio(struct file *file, struct folio *folio)
 {
-	return iomap_readpage(page, &erofs_iomap_ops);
+	return iomap_read_folio(folio, &erofs_iomap_ops);
 }
 
 static void erofs_readahead(struct readahead_control *rac)
@@ -394,7 +394,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 /* for uncompressed (aligned) files and raw access for other files */
 const struct address_space_operations erofs_raw_access_aops = {
-	.readpage = erofs_readpage,
+	.read_folio = erofs_read_folio,
 	.readahead = erofs_readahead,
 	.bmap = erofs_bmap,
 	.direct_IO = noop_direct_IO,
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 72c9f31ce724..a29eb1e5bfe2 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -467,6 +467,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 
 static int __gfs2_readpage(void *file, struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	struct inode *inode = page->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -474,7 +475,7 @@ static int __gfs2_readpage(void *file, struct page *page)
 
 	if (!gfs2_is_jdata(ip) ||
 	    (i_blocksize(inode) == PAGE_SIZE && !page_has_buffers(page))) {
-		error = iomap_readpage(page, &gfs2_iomap_ops);
+		error = iomap_read_folio(folio, &gfs2_iomap_ops);
 	} else if (gfs2_is_stuffed(ip)) {
 		error = stuffed_readpage(ip, page);
 		unlock_page(page);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 8ce8720093b9..72f63d719c7c 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -320,10 +320,8 @@ done:
 	return pos - orig_pos + plen;
 }
 
-int
-iomap_readpage(struct page *page, const struct iomap_ops *ops)
+int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
 {
-	struct folio *folio = page_folio(page);
 	struct iomap_iter iter = {
 		.inode		= folio->mapping->host,
 		.pos		= folio_pos(folio),
@@ -352,12 +350,12 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops)
 
 	/*
 	 * Just like mpage_readahead and block_read_full_page, we always
-	 * return 0 and just mark the page as PageError on errors.  This
+	 * return 0 and just set the folio error flag on errors.  This
 	 * should be cleaned up throughout the stack eventually.
 	 */
 	return 0;
 }
-EXPORT_SYMBOL_GPL(iomap_readpage);
+EXPORT_SYMBOL_GPL(iomap_read_folio);
 
 static loff_t iomap_readahead_iter(const struct iomap_iter *iter,
 		struct iomap_readpage_ctx *ctx)
@@ -663,10 +661,10 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
 
 	/*
 	 * The blocks that were entirely written will now be uptodate, so we
-	 * don't have to worry about a readpage reading them and overwriting a
+	 * don't have to worry about a read_folio reading them and overwriting a
 	 * partial write.  However, if we've encountered a short write and only
 	 * partially written into a block, it will not be marked uptodate, so a
-	 * readpage might come in and destroy our partial write.
+	 * read_folio might come in and destroy our partial write.
 	 *
 	 * Do the simplest thing and just treat any short write to a
 	 * non-uptodate page as a zero-length write, and force the caller to
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 90b7f4d127de..a9c4bb500d53 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -538,11 +538,11 @@ xfs_vm_bmap(
 }
 
 STATIC int
-xfs_vm_readpage(
+xfs_vm_read_folio(
 	struct file		*unused,
-	struct page		*page)
+	struct folio		*folio)
 {
-	return iomap_readpage(page, &xfs_read_iomap_ops);
+	return iomap_read_folio(folio, &xfs_read_iomap_ops);
 }
 
 STATIC void
@@ -564,7 +564,7 @@ xfs_iomap_swapfile_activate(
 }
 
 const struct address_space_operations xfs_address_space_operations = {
-	.readpage		= xfs_vm_readpage,
+	.read_folio		= xfs_vm_read_folio,
 	.readahead		= xfs_vm_readahead,
 	.writepages		= xfs_vm_writepages,
 	.dirty_folio		= filemap_dirty_folio,
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index e20e7c841489..c3a38f711b24 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -124,9 +124,9 @@ static const struct iomap_ops zonefs_iomap_ops = {
 	.iomap_begin	= zonefs_iomap_begin,
 };
 
-static int zonefs_readpage(struct file *unused, struct page *page)
+static int zonefs_read_folio(struct file *unused, struct folio *folio)
 {
-	return iomap_readpage(page, &zonefs_iomap_ops);
+	return iomap_read_folio(folio, &zonefs_iomap_ops);
 }
 
 static void zonefs_readahead(struct readahead_control *rac)
@@ -192,7 +192,7 @@ static int zonefs_swap_activate(struct swap_info_struct *sis,
 }
 
 static const struct address_space_operations zonefs_file_aops = {
-	.readpage		= zonefs_readpage,
+	.read_folio		= zonefs_read_folio,
 	.readahead		= zonefs_readahead,
 	.writepage		= zonefs_writepage,
 	.writepages		= zonefs_writepages,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index b76f0dd149fb..5b2aa45ddda3 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -225,7 +225,7 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i)
 
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
-int iomap_readpage(struct page *page, const struct iomap_ops *ops);
+int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
 void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
 bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
 int iomap_releasepage(struct page *page, gfp_t gfp_mask);
-- 
cgit v1.2.3


From 2c69e2057962b6bd76d72446453862eb59325b49 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 10:40:40 -0400
Subject: fs: Convert block_read_full_page() to block_read_full_folio()

This function is NOT converted to handle large folios, so include
an assert that the filesystem isn't passing one in.  Otherwise, use
the folio functions instead of the page functions, where they exist.
Convert all filesystems which use block_read_full_page().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 block/fops.c                |  6 ++---
 fs/adfs/inode.c             |  6 ++---
 fs/affs/file.c              |  6 ++---
 fs/befs/linuxvfs.c          | 10 ++++-----
 fs/bfs/file.c               |  6 ++---
 fs/buffer.c                 | 53 ++++++++++++++++++++++++---------------------
 fs/efs/inode.c              |  8 ++++---
 fs/ext4/readpage.c          |  4 ++--
 fs/freevxfs/vxfs_subr.c     | 17 +++++++--------
 fs/hfs/inode.c              |  8 +++----
 fs/hfsplus/inode.c          |  8 +++----
 fs/iomap/buffered-io.c      |  2 +-
 fs/minix/inode.c            |  6 ++---
 fs/mpage.c                  | 10 ++++-----
 fs/ntfs/compress.c          |  4 ++--
 fs/ocfs2/aops.c             |  6 ++---
 fs/ocfs2/refcounttree.c     |  6 +++--
 fs/omfs/file.c              |  6 ++---
 fs/qnx4/inode.c             |  7 +++---
 fs/reiserfs/file.c          |  2 +-
 fs/reiserfs/inode.c         | 12 +++++-----
 fs/sysv/itree.c             |  6 ++---
 fs/ufs/inode.c              |  8 +++----
 include/linux/buffer_head.h |  2 +-
 24 files changed, 108 insertions(+), 101 deletions(-)

(limited to 'include/linux')

diff --git a/block/fops.c b/block/fops.c
index 712affe56e29..06feb41d798b 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -387,9 +387,9 @@ static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, blkdev_get_block, wbc);
 }
 
-static int blkdev_readpage(struct file * file, struct page * page)
+static int blkdev_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, blkdev_get_block);
+	return block_read_full_folio(folio, blkdev_get_block);
 }
 
 static void blkdev_readahead(struct readahead_control *rac)
@@ -425,7 +425,7 @@ static int blkdev_writepages(struct address_space *mapping,
 const struct address_space_operations def_blk_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= blkdev_readpage,
+	.read_folio	= blkdev_read_folio,
 	.readahead	= blkdev_readahead,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index f7959b1a2d52..ee22278b0cfc 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -38,9 +38,9 @@ static int adfs_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, adfs_get_block, wbc);
 }
 
-static int adfs_readpage(struct file *file, struct page *page)
+static int adfs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, adfs_get_block);
+	return block_read_full_folio(folio, adfs_get_block);
 }
 
 static void adfs_write_failed(struct address_space *mapping, loff_t to)
@@ -75,7 +75,7 @@ static sector_t _adfs_bmap(struct address_space *mapping, sector_t block)
 static const struct address_space_operations adfs_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= adfs_readpage,
+	.read_folio	= adfs_read_folio,
 	.writepage	= adfs_writepage,
 	.write_begin	= adfs_write_begin,
 	.write_end	= generic_write_end,
diff --git a/fs/affs/file.c b/fs/affs/file.c
index b952f65c3f06..5da562cc7fb7 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -375,9 +375,9 @@ static int affs_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, affs_get_block, wbc);
 }
 
-static int affs_readpage(struct file *file, struct page *page)
+static int affs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, affs_get_block);
+	return block_read_full_folio(folio, affs_get_block);
 }
 
 static void affs_write_failed(struct address_space *mapping, loff_t to)
@@ -455,7 +455,7 @@ static sector_t _affs_bmap(struct address_space *mapping, sector_t block)
 const struct address_space_operations affs_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage = affs_readpage,
+	.read_folio = affs_read_folio,
 	.writepage = affs_writepage,
 	.write_begin = affs_write_begin,
 	.write_end = affs_write_end,
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index b4b3567ac655..25350dd22cda 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -40,7 +40,7 @@ MODULE_LICENSE("GPL");
 
 static int befs_readdir(struct file *, struct dir_context *);
 static int befs_get_block(struct inode *, sector_t, struct buffer_head *, int);
-static int befs_readpage(struct file *file, struct page *page);
+static int befs_read_folio(struct file *file, struct folio *folio);
 static sector_t befs_bmap(struct address_space *mapping, sector_t block);
 static struct dentry *befs_lookup(struct inode *, struct dentry *,
 				  unsigned int);
@@ -87,7 +87,7 @@ static const struct inode_operations befs_dir_inode_operations = {
 };
 
 static const struct address_space_operations befs_aops = {
-	.readpage	= befs_readpage,
+	.read_folio	= befs_read_folio,
 	.bmap		= befs_bmap,
 };
 
@@ -102,16 +102,16 @@ static const struct export_operations befs_export_operations = {
 };
 
 /*
- * Called by generic_file_read() to read a page of data
+ * Called by generic_file_read() to read a folio of data
  *
  * In turn, simply calls a generic block read function and
  * passes it the address of befs_get_block, for mapping file
  * positions to disk blocks.
  */
 static int
-befs_readpage(struct file *file, struct page *page)
+befs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, befs_get_block);
+	return block_read_full_folio(folio, befs_get_block);
 }
 
 static sector_t
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index dc97c9b8f23b..57ae5ee6deec 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -155,9 +155,9 @@ static int bfs_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, bfs_get_block, wbc);
 }
 
-static int bfs_readpage(struct file *file, struct page *page)
+static int bfs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, bfs_get_block);
+	return block_read_full_folio(folio, bfs_get_block);
 }
 
 static void bfs_write_failed(struct address_space *mapping, loff_t to)
@@ -189,7 +189,7 @@ static sector_t bfs_bmap(struct address_space *mapping, sector_t block)
 const struct address_space_operations bfs_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= bfs_readpage,
+	.read_folio	= bfs_read_folio,
 	.writepage	= bfs_writepage,
 	.write_begin	= bfs_write_begin,
 	.write_end	= generic_write_end,
diff --git a/fs/buffer.c b/fs/buffer.c
index 225d03cd622d..ec0c52c8848e 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -314,7 +314,7 @@ static void decrypt_bh(struct work_struct *work)
 }
 
 /*
- * I/O completion handler for block_read_full_page() - pages
+ * I/O completion handler for block_read_full_folio() - pages
  * which come unlocked at the end of I/O.
  */
 static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
@@ -1060,8 +1060,8 @@ __getblk_slow(struct block_device *bdev, sector_t block,
  * Also.  When blockdev buffers are explicitly read with bread(), they
  * individually become uptodate.  But their backing page remains not
  * uptodate - even if all of its buffers are uptodate.  A subsequent
- * block_read_full_page() against that page will discover all the uptodate
- * buffers, will set the page uptodate and will perform no I/O.
+ * block_read_full_folio() against that folio will discover all the uptodate
+ * buffers, will set the folio uptodate and will perform no I/O.
  */
 
 /**
@@ -2088,7 +2088,7 @@ static int __block_commit_write(struct inode *inode, struct page *page,
 
 	/*
 	 * If this is a partial write which happened to make all buffers
-	 * uptodate then we can optimize away a bogus readpage() for
+	 * uptodate then we can optimize away a bogus read_folio() for
 	 * the next read(). Here we 'discover' whether the page went
 	 * uptodate as a result of this (potentially partial) write.
 	 */
@@ -2137,12 +2137,12 @@ int block_write_end(struct file *file, struct address_space *mapping,
 
 	if (unlikely(copied < len)) {
 		/*
-		 * The buffers that were written will now be uptodate, so we
-		 * don't have to worry about a readpage reading them and
-		 * overwriting a partial write. However if we have encountered
-		 * a short write and only partially written into a buffer, it
-		 * will not be marked uptodate, so a readpage might come in and
-		 * destroy our partial write.
+		 * The buffers that were written will now be uptodate, so
+		 * we don't have to worry about a read_folio reading them
+		 * and overwriting a partial write. However if we have
+		 * encountered a short write and only partially written
+		 * into a buffer, it will not be marked uptodate, so a
+		 * read_folio might come in and destroy our partial write.
 		 *
 		 * Do the simplest thing, and just treat any short write to a
 		 * non uptodate page as a zero-length write, and force the
@@ -2245,26 +2245,28 @@ bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
 EXPORT_SYMBOL(block_is_partially_uptodate);
 
 /*
- * Generic "read page" function for block devices that have the normal
+ * Generic "read_folio" function for block devices that have the normal
  * get_block functionality. This is most of the block device filesystems.
- * Reads the page asynchronously --- the unlock_buffer() and
+ * Reads the folio asynchronously --- the unlock_buffer() and
  * set/clear_buffer_uptodate() functions propagate buffer state into the
- * page struct once IO has completed.
+ * folio once IO has completed.
  */
-int block_read_full_page(struct page *page, get_block_t *get_block)
+int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	sector_t iblock, lblock;
 	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
 	unsigned int blocksize, bbits;
 	int nr, i;
 	int fully_mapped = 1;
 
-	head = create_page_buffers(page, inode, 0);
+	VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
+
+	head = create_page_buffers(&folio->page, inode, 0);
 	blocksize = head->b_size;
 	bbits = block_size_bits(blocksize);
 
-	iblock = (sector_t)page->index << (PAGE_SHIFT - bbits);
+	iblock = (sector_t)folio->index << (PAGE_SHIFT - bbits);
 	lblock = (i_size_read(inode)+blocksize-1) >> bbits;
 	bh = head;
 	nr = 0;
@@ -2282,10 +2284,11 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
 				WARN_ON(bh->b_size != blocksize);
 				err = get_block(inode, iblock, bh, 0);
 				if (err)
-					SetPageError(page);
+					folio_set_error(folio);
 			}
 			if (!buffer_mapped(bh)) {
-				zero_user(page, i * blocksize, blocksize);
+				folio_zero_range(folio, i * blocksize,
+						blocksize);
 				if (!err)
 					set_buffer_uptodate(bh);
 				continue;
@@ -2301,16 +2304,16 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
 	} while (i++, iblock++, (bh = bh->b_this_page) != head);
 
 	if (fully_mapped)
-		SetPageMappedToDisk(page);
+		folio_set_mappedtodisk(folio);
 
 	if (!nr) {
 		/*
-		 * All buffers are uptodate - we can set the page uptodate
+		 * All buffers are uptodate - we can set the folio uptodate
 		 * as well. But not if get_block() returned an error.
 		 */
-		if (!PageError(page))
-			SetPageUptodate(page);
-		unlock_page(page);
+		if (!folio_test_error(folio))
+			folio_mark_uptodate(folio);
+		folio_unlock(folio);
 		return 0;
 	}
 
@@ -2335,7 +2338,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
 	}
 	return 0;
 }
-EXPORT_SYMBOL(block_read_full_page);
+EXPORT_SYMBOL(block_read_full_folio);
 
 /* utility function for filesystems that need to do work on expanding
  * truncates.  Uses filesystem pagecache writes to allow the filesystem to
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index 89e73a6f0d36..3ba94bb005a6 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -14,16 +14,18 @@
 #include "efs.h"
 #include <linux/efs_fs_sb.h>
 
-static int efs_readpage(struct file *file, struct page *page)
+static int efs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page,efs_get_block);
+	return block_read_full_folio(folio, efs_get_block);
 }
+
 static sector_t _efs_bmap(struct address_space *mapping, sector_t block)
 {
 	return generic_block_bmap(mapping,block,efs_get_block);
 }
+
 static const struct address_space_operations efs_aops = {
-	.readpage = efs_readpage,
+	.read_folio = efs_read_folio,
 	.bmap = _efs_bmap
 };
 
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index af491e170c4a..e02a5f14e021 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -163,7 +163,7 @@ static bool bio_post_read_required(struct bio *bio)
  *
  * The mpage code never puts partial pages into a BIO (except for end-of-file).
  * If a page does not map to a contiguous run of blocks then it simply falls
- * back to block_read_full_page().
+ * back to block_read_full_folio().
  *
  * Why is this?  If a page's completion depends on a number of different BIOs
  * which can complete in any order (or at the same time) then determining the
@@ -394,7 +394,7 @@ int ext4_mpage_readpages(struct inode *inode,
 			bio = NULL;
 		}
 		if (!PageUptodate(page))
-			block_read_full_page(page, ext4_get_block);
+			block_read_full_folio(page_folio(page), ext4_get_block);
 		else
 			unlock_page(page);
 	next_page:
diff --git a/fs/freevxfs/vxfs_subr.c b/fs/freevxfs/vxfs_subr.c
index e806694d4145..6143ebab940d 100644
--- a/fs/freevxfs/vxfs_subr.c
+++ b/fs/freevxfs/vxfs_subr.c
@@ -38,11 +38,11 @@
 #include "vxfs_extern.h"
 
 
-static int		vxfs_readpage(struct file *, struct page *);
+static int		vxfs_read_folio(struct file *, struct folio *);
 static sector_t		vxfs_bmap(struct address_space *, sector_t);
 
 const struct address_space_operations vxfs_aops = {
-	.readpage =		vxfs_readpage,
+	.read_folio =		vxfs_read_folio,
 	.bmap =			vxfs_bmap,
 };
 
@@ -141,24 +141,23 @@ vxfs_getblk(struct inode *ip, sector_t iblock,
 }
 
 /**
- * vxfs_readpage - read one page synchronously into the pagecache
+ * vxfs_read_folio - read one page synchronously into the pagecache
  * @file:	file context (unused)
- * @page:	page frame to fill in.
+ * @folio:	folio to fill in.
  *
  * Description:
- *   The vxfs_readpage routine reads @page synchronously into the
+ *   The vxfs_read_folio routine reads @folio synchronously into the
  *   pagecache.
  *
  * Returns:
  *   Zero on success, else a negative error code.
  *
  * Locking status:
- *   @page is locked and will be unlocked.
+ *   @folio is locked and will be unlocked.
  */
-static int
-vxfs_readpage(struct file *file, struct page *page)
+static int vxfs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, vxfs_getblk);
+	return block_read_full_folio(folio, vxfs_getblk);
 }
  
 /**
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 9a26b9510da0..ba3ff9cd7cfc 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -34,9 +34,9 @@ static int hfs_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, hfs_get_block, wbc);
 }
 
-static int hfs_readpage(struct file *file, struct page *page)
+static int hfs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, hfs_get_block);
+	return block_read_full_folio(folio, hfs_get_block);
 }
 
 static void hfs_write_failed(struct address_space *mapping, loff_t to)
@@ -160,7 +160,7 @@ static int hfs_writepages(struct address_space *mapping,
 const struct address_space_operations hfs_btree_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= hfs_readpage,
+	.read_folio	= hfs_read_folio,
 	.writepage	= hfs_writepage,
 	.write_begin	= hfs_write_begin,
 	.write_end	= generic_write_end,
@@ -171,7 +171,7 @@ const struct address_space_operations hfs_btree_aops = {
 const struct address_space_operations hfs_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= hfs_readpage,
+	.read_folio	= hfs_read_folio,
 	.writepage	= hfs_writepage,
 	.write_begin	= hfs_write_begin,
 	.write_end	= generic_write_end,
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 905ae3660315..982b34eefec7 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -23,9 +23,9 @@
 #include "hfsplus_raw.h"
 #include "xattr.h"
 
-static int hfsplus_readpage(struct file *file, struct page *page)
+static int hfsplus_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, hfsplus_get_block);
+	return block_read_full_folio(folio, hfsplus_get_block);
 }
 
 static int hfsplus_writepage(struct page *page, struct writeback_control *wbc)
@@ -157,7 +157,7 @@ static int hfsplus_writepages(struct address_space *mapping,
 const struct address_space_operations hfsplus_btree_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= hfsplus_readpage,
+	.read_folio	= hfsplus_read_folio,
 	.writepage	= hfsplus_writepage,
 	.write_begin	= hfsplus_write_begin,
 	.write_end	= generic_write_end,
@@ -168,7 +168,7 @@ const struct address_space_operations hfsplus_btree_aops = {
 const struct address_space_operations hfsplus_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= hfsplus_readpage,
+	.read_folio	= hfsplus_read_folio,
 	.writepage	= hfsplus_writepage,
 	.write_begin	= hfsplus_write_begin,
 	.write_end	= generic_write_end,
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 72f63d719c7c..75eb0c27a0e8 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -349,7 +349,7 @@ int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
 	}
 
 	/*
-	 * Just like mpage_readahead and block_read_full_page, we always
+	 * Just like mpage_readahead and block_read_full_folio, we always
 	 * return 0 and just set the folio error flag on errors.  This
 	 * should be cleaned up throughout the stack eventually.
 	 */
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 3add78bccedc..da8bdd1712a7 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -402,9 +402,9 @@ static int minix_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, minix_get_block, wbc);
 }
 
-static int minix_readpage(struct file *file, struct page *page)
+static int minix_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page,minix_get_block);
+	return block_read_full_folio(folio, minix_get_block);
 }
 
 int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len)
@@ -443,7 +443,7 @@ static sector_t minix_bmap(struct address_space *mapping, sector_t block)
 static const struct address_space_operations minix_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage = minix_readpage,
+	.read_folio = minix_read_folio,
 	.writepage = minix_writepage,
 	.write_begin = minix_write_begin,
 	.write_end = generic_write_end,
diff --git a/fs/mpage.c b/fs/mpage.c
index 1fe56f8c495f..a04439b84ae2 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -36,7 +36,7 @@
  *
  * The mpage code never puts partial pages into a BIO (except for end-of-file).
  * If a page does not map to a contiguous run of blocks then it simply falls
- * back to block_read_full_page().
+ * back to block_read_full_folio().
  *
  * Why is this?  If a page's completion depends on a number of different BIOs
  * which can complete in any order (or at the same time) then determining the
@@ -68,7 +68,7 @@ static struct bio *mpage_bio_submit(struct bio *bio)
 /*
  * support function for mpage_readahead.  The fs supplied get_block might
  * return an up to date buffer.  This is used to map that buffer into
- * the page, which allows readpage to avoid triggering a duplicate call
+ * the page, which allows read_folio to avoid triggering a duplicate call
  * to get_block.
  *
  * The idea is to avoid adding buffers to pages that don't already have
@@ -296,7 +296,7 @@ confused:
 	if (args->bio)
 		args->bio = mpage_bio_submit(args->bio);
 	if (!PageUptodate(page))
-		block_read_full_page(page, args->get_block);
+		block_read_full_folio(page_folio(page), args->get_block);
 	else
 		unlock_page(page);
 	goto out;
@@ -425,7 +425,7 @@ static void clean_buffers(struct page *page, unsigned first_unmapped)
 
 	/*
 	 * we cannot drop the bh if the page is not uptodate or a concurrent
-	 * readpage would fail to serialize with the bh and it would read from
+	 * read_folio would fail to serialize with the bh and it would read from
 	 * disk before we reach the platter.
 	 */
 	if (buffer_heads_over_limit && PageUptodate(page))
@@ -510,7 +510,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 		/*
 		 * Page has buffers, but they are all unmapped. The page was
 		 * created by pagein or read over a hole which was handled by
-		 * block_read_full_page().  If this address_space is also
+		 * block_read_full_folio().  If this address_space is also
 		 * using mpage_readahead then this can rarely happen.
 		 */
 		goto confused;
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index d2f9d6a0ee32..a60f543e7557 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -780,12 +780,12 @@ lock_retry_remap:
 		/* Uncompressed cb, copy it to the destination pages. */
 		/*
 		 * TODO: As a big optimization, we could detect this case
-		 * before we read all the pages and use block_read_full_page()
+		 * before we read all the pages and use block_read_full_folio()
 		 * on all full pages instead (we still have to treat partial
 		 * pages especially but at least we are getting rid of the
 		 * synchronous io for the majority of pages.
 		 * Or if we choose not to do the read-ahead/-behind stuff, we
-		 * could just return block_read_full_page(pages[xpage]) as long
+		 * could just return block_read_full_folio(pages[xpage]) as long
 		 * as PAGE_SIZE <= cb_size.
 		 */
 		if (cb_max_ofs)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 7cffe9dcad17..7bf4b6fd93bf 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -309,7 +309,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	/*
 	 * i_size might have just been updated as we grabed the meta lock.  We
 	 * might now be discovering a truncate that hit on another node.
-	 * block_read_full_page->get_block freaks out if it is asked to read
+	 * block_read_full_folio->get_block freaks out if it is asked to read
 	 * beyond the end of a file, so we check here.  Callers
 	 * (generic_file_read, vm_ops->fault) are clever enough to check i_size
 	 * and notice that the page they just read isn't needed.
@@ -326,7 +326,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		ret = ocfs2_readpage_inline(inode, page);
 	else
-		ret = block_read_full_page(page, ocfs2_get_block);
+		ret = block_read_full_folio(page_folio(page), ocfs2_get_block);
 	unlock = 0;
 
 out_alloc:
@@ -1897,7 +1897,7 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
 	/*
 	 * Take alloc sem here to prevent concurrent lookups. That way
 	 * the mapping, zeroing and tree manipulation within
-	 * ocfs2_write() will be safe against ->readpage(). This
+	 * ocfs2_write() will be safe against ->read_folio(). This
 	 * should also serve to lock out allocation from a shared
 	 * writeable region.
 	 */
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 7f6355cbb587..e04358a46b68 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2961,12 +2961,14 @@ retry:
 		}
 
 		if (!PageUptodate(page)) {
-			ret = block_read_full_page(page, ocfs2_get_block);
+			struct folio *folio = page_folio(page);
+
+			ret = block_read_full_folio(folio, ocfs2_get_block);
 			if (ret) {
 				mlog_errno(ret);
 				goto unlock;
 			}
-			lock_page(page);
+			folio_lock(folio);
 		}
 
 		if (page_has_buffers(page)) {
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 980b0a72c172..fa7fe2393ff6 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -284,9 +284,9 @@ out:
 	return ret;
 }
 
-static int omfs_readpage(struct file *file, struct page *page)
+static int omfs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page, omfs_get_block);
+	return block_read_full_folio(folio, omfs_get_block);
 }
 
 static void omfs_readahead(struct readahead_control *rac)
@@ -373,7 +373,7 @@ const struct inode_operations omfs_file_inops = {
 const struct address_space_operations omfs_aops = {
 	.dirty_folio = block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage = omfs_readpage,
+	.read_folio = omfs_read_folio,
 	.readahead = omfs_readahead,
 	.writepage = omfs_writepage,
 	.writepages = omfs_writepages,
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index a635bb6615e9..391ea402920d 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -245,17 +245,18 @@ static void qnx4_kill_sb(struct super_block *sb)
 	}
 }
 
-static int qnx4_readpage(struct file *file, struct page *page)
+static int qnx4_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page,qnx4_get_block);
+	return block_read_full_folio(folio, qnx4_get_block);
 }
 
 static sector_t qnx4_bmap(struct address_space *mapping, sector_t block)
 {
 	return generic_block_bmap(mapping,block,qnx4_get_block);
 }
+
 static const struct address_space_operations qnx4_aops = {
-	.readpage	= qnx4_readpage,
+	.read_folio	= qnx4_read_folio,
 	.bmap		= qnx4_bmap
 };
 
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 203a47232707..6e228bfbe7ef 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -227,7 +227,7 @@ drop_write_lock:
 	}
 	/*
 	 * If this is a partial write which happened to make all buffers
-	 * uptodate then we can optimize away a bogus readpage() for
+	 * uptodate then we can optimize away a bogus read_folio() for
 	 * the next read(). Here we 'discover' whether the page went
 	 * uptodate as a result of this (potentially partial) write.
 	 */
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 46ba4892030a..33a9555f77b9 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -167,10 +167,10 @@ inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
  * cutting the code is fine, since it really isn't in use yet and is easy
  * to add back in.  But, Vladimir has a really good idea here.  Think
  * about what happens for reading a file.  For each page,
- * The VFS layer calls reiserfs_readpage, who searches the tree to find
+ * The VFS layer calls reiserfs_read_folio, who searches the tree to find
  * an indirect item.  This indirect item has X number of pointers, where
  * X is a big number if we've done the block allocation right.  But,
- * we only use one or two of these pointers during each call to readpage,
+ * we only use one or two of these pointers during each call to read_folio,
  * needlessly researching again later on.
  *
  * The size of the cache could be dynamic based on the size of the file.
@@ -966,7 +966,7 @@ research:
 			 * it is important the set_buffer_uptodate is done
 			 * after the direct2indirect.  The buffer might
 			 * contain valid data newer than the data on disk
-			 * (read by readpage, changed, and then sent here by
+			 * (read by read_folio, changed, and then sent here by
 			 * writepage).  direct2indirect needs to know if unbh
 			 * was already up to date, so it can decide if the
 			 * data in unbh needs to be replaced with data from
@@ -2733,9 +2733,9 @@ fail:
 	goto done;
 }
 
-static int reiserfs_readpage(struct file *f, struct page *page)
+static int reiserfs_read_folio(struct file *f, struct folio *folio)
 {
-	return block_read_full_page(page, reiserfs_get_block);
+	return block_read_full_folio(folio, reiserfs_get_block);
 }
 
 static int reiserfs_writepage(struct page *page, struct writeback_control *wbc)
@@ -3421,7 +3421,7 @@ out:
 
 const struct address_space_operations reiserfs_address_space_operations = {
 	.writepage = reiserfs_writepage,
-	.readpage = reiserfs_readpage,
+	.read_folio = reiserfs_read_folio,
 	.readahead = reiserfs_readahead,
 	.releasepage = reiserfs_releasepage,
 	.invalidate_folio = reiserfs_invalidate_folio,
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 96ad24fe0ffb..d4ec9bb97de9 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -456,9 +456,9 @@ static int sysv_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page,get_block,wbc);
 }
 
-static int sysv_readpage(struct file *file, struct page *page)
+static int sysv_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page,get_block);
+	return block_read_full_folio(folio, get_block);
 }
 
 int sysv_prepare_chunk(struct page *page, loff_t pos, unsigned len)
@@ -497,7 +497,7 @@ static sector_t sysv_bmap(struct address_space *mapping, sector_t block)
 const struct address_space_operations sysv_aops = {
 	.dirty_folio = block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage = sysv_readpage,
+	.read_folio = sysv_read_folio,
 	.writepage = sysv_writepage,
 	.write_begin = sysv_write_begin,
 	.write_end = generic_write_end,
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 6c973b71cab2..a873de7dec1c 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -390,7 +390,7 @@ out:
 
 /**
  * ufs_getfrag_block() - `get_block_t' function, interface between UFS and
- * readpage, writepage and so on
+ * read_folio, writepage and so on
  */
 
 static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create)
@@ -472,9 +472,9 @@ static int ufs_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page,ufs_getfrag_block,wbc);
 }
 
-static int ufs_readpage(struct file *file, struct page *page)
+static int ufs_read_folio(struct file *file, struct folio *folio)
 {
-	return block_read_full_page(page,ufs_getfrag_block);
+	return block_read_full_folio(folio, ufs_getfrag_block);
 }
 
 int ufs_prepare_chunk(struct page *page, loff_t pos, unsigned len)
@@ -527,7 +527,7 @@ static sector_t ufs_bmap(struct address_space *mapping, sector_t block)
 const struct address_space_operations ufs_aops = {
 	.dirty_folio = block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage = ufs_readpage,
+	.read_folio = ufs_read_folio,
 	.writepage = ufs_writepage,
 	.write_begin = ufs_write_begin,
 	.write_end = ufs_write_end,
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 805c4e12700a..31d82fd9abe8 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -223,7 +223,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 int __block_write_full_page(struct inode *inode, struct page *page,
 			get_block_t *get_block, struct writeback_control *wbc,
 			bh_end_io_t *handler);
-int block_read_full_page(struct page*, get_block_t*);
+int block_read_full_folio(struct folio *, get_block_t *);
 bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		struct page **pagep, get_block_t *get_block);
-- 
cgit v1.2.3


From f132ab7d3ab03c5bae28d31fb80ba77c4da05500 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 11:47:39 -0400
Subject: fs: Convert mpage_readpage to mpage_read_folio

mpage_readpage still works in terms of pages, and has not been audited
for correctness with large folios, so include an assertion that the
filesystem is not passing it large folios.  Convert all the filesystems
to call mpage_read_folio() instead of mpage_readpage().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 fs/exfat/inode.c       |  6 +++---
 fs/ext2/inode.c        |  8 ++++----
 fs/fat/inode.c         |  6 +++---
 fs/gfs2/aops.c         | 15 +++++++--------
 fs/hpfs/file.c         |  6 +++---
 fs/iomap/buffered-io.c |  2 +-
 fs/isofs/inode.c       |  6 +++---
 fs/jfs/inode.c         |  6 +++---
 fs/mpage.c             |  8 +++++---
 fs/nilfs2/inode.c      | 10 +++++-----
 fs/ntfs3/inode.c       |  9 +++++----
 fs/qnx6/inode.c        |  6 +++---
 fs/udf/inode.c         |  6 +++---
 include/linux/mpage.h  |  2 +-
 14 files changed, 49 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index b9f63113db2d..0133d385d8e8 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -357,9 +357,9 @@ unlock_ret:
 	return err;
 }
 
-static int exfat_readpage(struct file *file, struct page *page)
+static int exfat_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, exfat_get_block);
+	return mpage_read_folio(folio, exfat_get_block);
 }
 
 static void exfat_readahead(struct readahead_control *rac)
@@ -492,7 +492,7 @@ int exfat_block_truncate_page(struct inode *inode, loff_t from)
 static const struct address_space_operations exfat_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= exfat_readpage,
+	.read_folio	= exfat_read_folio,
 	.readahead	= exfat_readahead,
 	.writepage	= exfat_writepage,
 	.writepages	= exfat_writepages,
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index d8ca8050945a..9e1ecd89f47f 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -875,9 +875,9 @@ static int ext2_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, ext2_get_block, wbc);
 }
 
-static int ext2_readpage(struct file *file, struct page *page)
+static int ext2_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, ext2_get_block);
+	return mpage_read_folio(folio, ext2_get_block);
 }
 
 static void ext2_readahead(struct readahead_control *rac)
@@ -966,7 +966,7 @@ ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc
 const struct address_space_operations ext2_aops = {
 	.dirty_folio		= block_dirty_folio,
 	.invalidate_folio	= block_invalidate_folio,
-	.readpage		= ext2_readpage,
+	.read_folio		= ext2_read_folio,
 	.readahead		= ext2_readahead,
 	.writepage		= ext2_writepage,
 	.write_begin		= ext2_write_begin,
@@ -982,7 +982,7 @@ const struct address_space_operations ext2_aops = {
 const struct address_space_operations ext2_nobh_aops = {
 	.dirty_folio		= block_dirty_folio,
 	.invalidate_folio	= block_invalidate_folio,
-	.readpage		= ext2_readpage,
+	.read_folio		= ext2_read_folio,
 	.readahead		= ext2_readahead,
 	.writepage		= ext2_nobh_writepage,
 	.write_begin		= ext2_nobh_write_begin,
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 1f15b0fd1bb0..8a81017f8d60 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -205,9 +205,9 @@ static int fat_writepages(struct address_space *mapping,
 	return mpage_writepages(mapping, wbc, fat_get_block);
 }
 
-static int fat_readpage(struct file *file, struct page *page)
+static int fat_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, fat_get_block);
+	return mpage_read_folio(folio, fat_get_block);
 }
 
 static void fat_readahead(struct readahead_control *rac)
@@ -344,7 +344,7 @@ int fat_block_truncate_page(struct inode *inode, loff_t from)
 static const struct address_space_operations fat_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= fat_readpage,
+	.read_folio	= fat_read_folio,
 	.readahead	= fat_readahead,
 	.writepage	= fat_writepage,
 	.writepages	= fat_writepages,
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index a29eb1e5bfe2..340bf5d0e835 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -480,7 +480,7 @@ static int __gfs2_readpage(void *file, struct page *page)
 		error = stuffed_readpage(ip, page);
 		unlock_page(page);
 	} else {
-		error = mpage_readpage(page, gfs2_block_map);
+		error = mpage_read_folio(folio, gfs2_block_map);
 	}
 
 	if (unlikely(gfs2_withdrawn(sdp)))
@@ -490,14 +490,13 @@ static int __gfs2_readpage(void *file, struct page *page)
 }
 
 /**
- * gfs2_readpage - read a page of a file
+ * gfs2_read_folio - read a folio from a file
  * @file: The file to read
- * @page: The page of the file
+ * @folio: The folio in the file
  */
-
-static int gfs2_readpage(struct file *file, struct page *page)
+static int gfs2_read_folio(struct file *file, struct folio *folio)
 {
-	return __gfs2_readpage(file, page);
+	return __gfs2_readpage(file, &folio->page);
 }
 
 /**
@@ -773,7 +772,7 @@ cannot_release:
 static const struct address_space_operations gfs2_aops = {
 	.writepage = gfs2_writepage,
 	.writepages = gfs2_writepages,
-	.readpage = gfs2_readpage,
+	.read_folio = gfs2_read_folio,
 	.readahead = gfs2_readahead,
 	.dirty_folio = filemap_dirty_folio,
 	.releasepage = iomap_releasepage,
@@ -788,7 +787,7 @@ static const struct address_space_operations gfs2_aops = {
 static const struct address_space_operations gfs2_jdata_aops = {
 	.writepage = gfs2_jdata_writepage,
 	.writepages = gfs2_jdata_writepages,
-	.readpage = gfs2_readpage,
+	.read_folio = gfs2_read_folio,
 	.readahead = gfs2_readahead,
 	.dirty_folio = jdata_dirty_folio,
 	.bmap = gfs2_bmap,
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 8b590b3826c3..f7547a62c81f 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -158,9 +158,9 @@ static const struct iomap_ops hpfs_iomap_ops = {
 	.iomap_begin		= hpfs_iomap_begin,
 };
 
-static int hpfs_readpage(struct file *file, struct page *page)
+static int hpfs_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, hpfs_get_block);
+	return mpage_read_folio(folio, hpfs_get_block);
 }
 
 static int hpfs_writepage(struct page *page, struct writeback_control *wbc)
@@ -247,7 +247,7 @@ static int hpfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 const struct address_space_operations hpfs_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage = hpfs_readpage,
+	.read_folio = hpfs_read_folio,
 	.writepage = hpfs_writepage,
 	.readahead = hpfs_readahead,
 	.writepages = hpfs_writepages,
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 75eb0c27a0e8..2de087ac87b6 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -297,7 +297,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
 		/*
 		 * If the bio_alloc fails, try it again for a single page to
 		 * avoid having to deal with partial page reads.  This emulates
-		 * what do_mpage_readpage does.
+		 * what do_mpage_read_folio does.
 		 */
 		if (!ctx->bio) {
 			ctx->bio = bio_alloc(iomap->bdev, 1, REQ_OP_READ,
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index d7491692aea3..88bf20303466 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1174,9 +1174,9 @@ struct buffer_head *isofs_bread(struct inode *inode, sector_t block)
 	return sb_bread(inode->i_sb, blknr);
 }
 
-static int isofs_readpage(struct file *file, struct page *page)
+static int isofs_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, isofs_get_block);
+	return mpage_read_folio(folio, isofs_get_block);
 }
 
 static void isofs_readahead(struct readahead_control *rac)
@@ -1190,7 +1190,7 @@ static sector_t _isofs_bmap(struct address_space *mapping, sector_t block)
 }
 
 static const struct address_space_operations isofs_aops = {
-	.readpage = isofs_readpage,
+	.read_folio = isofs_read_folio,
 	.readahead = isofs_readahead,
 	.bmap = _isofs_bmap
 };
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index aa9f112107b2..a5dd7e53754a 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -293,9 +293,9 @@ static int jfs_writepages(struct address_space *mapping,
 	return mpage_writepages(mapping, wbc, jfs_get_block);
 }
 
-static int jfs_readpage(struct file *file, struct page *page)
+static int jfs_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, jfs_get_block);
+	return mpage_read_folio(folio, jfs_get_block);
 }
 
 static void jfs_readahead(struct readahead_control *rac)
@@ -359,7 +359,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 const struct address_space_operations jfs_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= jfs_readpage,
+	.read_folio	= jfs_read_folio,
 	.readahead	= jfs_readahead,
 	.writepage	= jfs_writepage,
 	.writepages	= jfs_writepages,
diff --git a/fs/mpage.c b/fs/mpage.c
index a04439b84ae2..6df9c3aa5728 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -364,20 +364,22 @@ EXPORT_SYMBOL(mpage_readahead);
 /*
  * This isn't called much at all
  */
-int mpage_readpage(struct page *page, get_block_t get_block)
+int mpage_read_folio(struct folio *folio, get_block_t get_block)
 {
 	struct mpage_readpage_args args = {
-		.page = page,
+		.page = &folio->page,
 		.nr_pages = 1,
 		.get_block = get_block,
 	};
 
+	VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
+
 	args.bio = do_mpage_readpage(&args);
 	if (args.bio)
 		mpage_bio_submit(args.bio);
 	return 0;
 }
-EXPORT_SYMBOL(mpage_readpage);
+EXPORT_SYMBOL(mpage_read_folio);
 
 /*
  * Writing is not so simple.
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 02297ec8dc55..26b8065401b0 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -140,14 +140,14 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
 }
 
 /**
- * nilfs_readpage() - implement readpage() method of nilfs_aops {}
+ * nilfs_read_folio() - implement read_folio() method of nilfs_aops {}
  * address_space_operations.
  * @file - file struct of the file to be read
- * @page - the page to be read
+ * @folio - the folio to be read
  */
-static int nilfs_readpage(struct file *file, struct page *page)
+static int nilfs_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, nilfs_get_block);
+	return mpage_read_folio(folio, nilfs_get_block);
 }
 
 static void nilfs_readahead(struct readahead_control *rac)
@@ -298,7 +298,7 @@ nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 const struct address_space_operations nilfs_aops = {
 	.writepage		= nilfs_writepage,
-	.readpage		= nilfs_readpage,
+	.read_folio		= nilfs_read_folio,
 	.writepages		= nilfs_writepages,
 	.dirty_folio		= nilfs_dirty_folio,
 	.readahead		= nilfs_readahead,
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index bfd71f384e21..74f60c457f28 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -676,8 +676,9 @@ static sector_t ntfs_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping, block, ntfs_get_block_bmap);
 }
 
-static int ntfs_readpage(struct file *file, struct page *page)
+static int ntfs_read_folio(struct file *file, struct folio *folio)
 {
+	struct page *page = &folio->page;
 	int err;
 	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;
@@ -701,7 +702,7 @@ static int ntfs_readpage(struct file *file, struct page *page)
 	}
 
 	/* Normal + sparse files. */
-	return mpage_readpage(page, ntfs_get_block);
+	return mpage_read_folio(folio, ntfs_get_block);
 }
 
 static void ntfs_readahead(struct readahead_control *rac)
@@ -1940,7 +1941,7 @@ const struct inode_operations ntfs_link_inode_operations = {
 };
 
 const struct address_space_operations ntfs_aops = {
-	.readpage	= ntfs_readpage,
+	.read_folio	= ntfs_read_folio,
 	.readahead	= ntfs_readahead,
 	.writepage	= ntfs_writepage,
 	.writepages	= ntfs_writepages,
@@ -1952,7 +1953,7 @@ const struct address_space_operations ntfs_aops = {
 };
 
 const struct address_space_operations ntfs_aops_cmpr = {
-	.readpage	= ntfs_readpage,
+	.read_folio	= ntfs_read_folio,
 	.readahead	= ntfs_readahead,
 };
 // clang-format on
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 9d8e7e9788a1..b9895afca9d1 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -94,9 +94,9 @@ static int qnx6_check_blockptr(__fs32 ptr)
 	return 1;
 }
 
-static int qnx6_readpage(struct file *file, struct page *page)
+static int qnx6_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, qnx6_get_block);
+	return mpage_read_folio(folio, qnx6_get_block);
 }
 
 static void qnx6_readahead(struct readahead_control *rac)
@@ -496,7 +496,7 @@ static sector_t qnx6_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping, block, qnx6_get_block);
 }
 static const struct address_space_operations qnx6_aops = {
-	.readpage	= qnx6_readpage,
+	.read_folio	= qnx6_read_folio,
 	.readahead	= qnx6_readahead,
 	.bmap		= qnx6_bmap
 };
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 866f9a53248e..edc88716751a 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -193,9 +193,9 @@ static int udf_writepages(struct address_space *mapping,
 	return mpage_writepages(mapping, wbc, udf_get_block);
 }
 
-static int udf_readpage(struct file *file, struct page *page)
+static int udf_read_folio(struct file *file, struct folio *folio)
 {
-	return mpage_readpage(page, udf_get_block);
+	return mpage_read_folio(folio, udf_get_block);
 }
 
 static void udf_readahead(struct readahead_control *rac)
@@ -237,7 +237,7 @@ static sector_t udf_bmap(struct address_space *mapping, sector_t block)
 const struct address_space_operations udf_aops = {
 	.dirty_folio	= block_dirty_folio,
 	.invalidate_folio = block_invalidate_folio,
-	.readpage	= udf_readpage,
+	.read_folio	= udf_read_folio,
 	.readahead	= udf_readahead,
 	.writepage	= udf_writepage,
 	.writepages	= udf_writepages,
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index f4f5e90a6844..43986f7ec4dd 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -16,7 +16,7 @@ struct writeback_control;
 struct readahead_control;
 
 void mpage_readahead(struct readahead_control *, get_block_t get_block);
-int mpage_readpage(struct page *page, get_block_t get_block);
+int mpage_read_folio(struct folio *folio, get_block_t get_block);
 int mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,
-- 
cgit v1.2.3


From 65d023af7f29eb1250a6105141a74776bae7e1f8 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 11:12:16 -0400
Subject: nfs: Convert nfs to read_folio

This is a "weak" conversion which converts straight back to using pages.
A full conversion should be performed at some point, hopefully by
someone familiar with the filesystem.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 fs/nfs/file.c          | 4 ++--
 fs/nfs/read.c          | 3 ++-
 include/linux/nfs_fs.h | 2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index f05c4b18b681..4f6d1f90b87f 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -337,7 +337,7 @@ start:
 	} else if (!once_thru &&
 		   nfs_want_read_modify_write(file, page, pos, len)) {
 		once_thru = 1;
-		ret = nfs_readpage(file, page);
+		ret = nfs_read_folio(file, page_folio(page));
 		put_page(page);
 		if (!ret)
 			goto start;
@@ -514,7 +514,7 @@ static void nfs_swap_deactivate(struct file *file)
 }
 
 const struct address_space_operations nfs_file_aops = {
-	.readpage = nfs_readpage,
+	.read_folio = nfs_read_folio,
 	.readahead = nfs_readahead,
 	.dirty_folio = filemap_dirty_folio,
 	.writepage = nfs_writepage,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 5e7657374bc3..5a9b043662e9 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -333,8 +333,9 @@ out:
  *  -	The error flag is set for this page. This happens only when a
  *	previous async read operation failed.
  */
-int nfs_readpage(struct file *file, struct page *page)
+int nfs_read_folio(struct file *file, struct folio *folio)
 {
+	struct page *page = &folio->page;
 	struct nfs_readdesc desc;
 	struct inode *inode = page_file_mapping(page)->host;
 	int ret;
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b48b9259e02c..1bba71757d62 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -594,7 +594,7 @@ static inline bool nfs_have_writebacks(const struct inode *inode)
 /*
  * linux/fs/nfs/read.c
  */
-extern int  nfs_readpage(struct file *, struct page *);
+int  nfs_read_folio(struct file *, struct folio *);
 void nfs_readahead(struct readahead_control *);
 
 /*
-- 
cgit v1.2.3


From 7e0a126519b82648b254afcd95a168c15f65ea40 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 11:53:28 -0400
Subject: mm,fs: Remove aops->readpage

With all implementations of aops->readpage converted to aops->read_folio,
we can stop checking whether it's set and remove the member from aops.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 fs/btrfs/file.c         |  2 +-
 fs/buffer.c             |  5 +----
 fs/ceph/addr.c          |  2 +-
 include/linux/fs.h      |  3 +--
 kernel/events/uprobes.c |  5 ++---
 mm/filemap.c            | 15 +++++----------
 mm/memory.c             |  4 ++--
 mm/readahead.c          | 12 ++++--------
 mm/shmem.c              |  2 +-
 mm/swapfile.c           |  2 +-
 10 files changed, 19 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 373df5ebaf8d..57fba5abb059 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2402,7 +2402,7 @@ static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = filp->f_mapping;
 
-	if (!mapping->a_ops->readpage && !mapping->a_ops->read_folio)
+	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
 
 	file_accessed(filp);
diff --git a/fs/buffer.c b/fs/buffer.c
index ec0c52c8848e..786ef5b98c80 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2827,10 +2827,7 @@ int nobh_truncate_page(struct address_space *mapping,
 
 	/* Ok, it's mapped. Make sure it's up-to-date */
 	if (!folio_test_uptodate(folio)) {
-		if (mapping->a_ops->read_folio)
-			err = mapping->a_ops->read_folio(NULL, folio);
-		else
-			err = mapping->a_ops->readpage(NULL, &folio->page);
+		err = mapping->a_ops->read_folio(NULL, folio);
 		if (err) {
 			folio_put(folio);
 			goto out;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index be3e47784f08..e040b92bb17c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1772,7 +1772,7 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = file->f_mapping;
 
-	if (!mapping->a_ops->readpage && !mapping->a_ops->read_folio)
+	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &ceph_vmops;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5ad942183a2c..f812f5aa07dd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -262,7 +262,7 @@ struct iattr {
  *  			trying again.  The aop will be taking reasonable
  *  			precautions not to livelock.  If the caller held a page
  *  			reference, it should drop it before retrying.  Returned
- *  			by readpage().
+ *  			by read_folio().
  *
  * address_space_operation functions return these large constants to indicate
  * special semantics to the caller.  These are much larger than the bytes in a
@@ -335,7 +335,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb)
 
 struct address_space_operations {
 	int (*writepage)(struct page *page, struct writeback_control *wbc);
-	int (*readpage)(struct file *, struct page *);
 	int (*read_folio)(struct file *, struct folio *);
 
 	/* Write back some dirty pages from this mapping. */
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2c7815d20038..a9bc3c98f76a 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -787,10 +787,10 @@ static int __copy_insn(struct address_space *mapping, struct file *filp,
 	struct page *page;
 	/*
 	 * Ensure that the page that has the original instruction is populated
-	 * and in page-cache. If ->readpage == NULL it must be shmem_mapping(),
+	 * and in page-cache. If ->read_folio == NULL it must be shmem_mapping(),
 	 * see uprobe_register().
 	 */
-	if (mapping->a_ops->read_folio || mapping->a_ops->readpage)
+	if (mapping->a_ops->read_folio)
 		page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp);
 	else
 		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
@@ -1144,7 +1144,6 @@ static int __uprobe_register(struct inode *inode, loff_t offset,
 
 	/* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */
 	if (!inode->i_mapping->a_ops->read_folio &&
-	    !inode->i_mapping->a_ops->readpage &&
 	    !shmem_mapping(inode->i_mapping))
 		return -EIO;
 	/* Racy, just to catch the obvious mistakes */
diff --git a/mm/filemap.c b/mm/filemap.c
index 96e3d7ffd98e..079f8cca7959 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2414,15 +2414,12 @@ static int filemap_read_folio(struct file *file, struct address_space *mapping,
 
 	/*
 	 * A previous I/O error may have been due to temporary failures,
-	 * eg. multipath errors.  PG_error will be set again if readpage
+	 * eg. multipath errors.  PG_error will be set again if read_folio
 	 * fails.
 	 */
 	folio_clear_error(folio);
 	/* Start the actual read. The read will unlock the page. */
-	if (mapping->a_ops->read_folio)
-		error = mapping->a_ops->read_folio(file, folio);
-	else
-		error = mapping->a_ops->readpage(file, &folio->page);
+	error = mapping->a_ops->read_folio(file, folio);
 	if (error)
 		return error;
 
@@ -2639,7 +2636,7 @@ err:
  * @already_read: Number of bytes already read by the caller.
  *
  * Copies data from the page cache.  If the data is not currently present,
- * uses the readahead and readpage address_space operations to fetch it.
+ * uses the readahead and read_folio address_space operations to fetch it.
  *
  * Return: Total number of bytes copied, including those already read by
  * the caller.  If an error happens before any bytes are copied, returns
@@ -3450,7 +3447,7 @@ int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = file->f_mapping;
 
-	if (!mapping->a_ops->read_folio && !mapping->a_ops->readpage)
+	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &generic_file_vm_ops;
@@ -3508,10 +3505,8 @@ repeat:
 filler:
 		if (filler)
 			err = filler(data, &folio->page);
-		else if (mapping->a_ops->read_folio)
-			err = mapping->a_ops->read_folio(data, folio);
 		else
-			err = mapping->a_ops->readpage(data, &folio->page);
+			err = mapping->a_ops->read_folio(data, folio);
 
 		if (err < 0) {
 			folio_put(folio);
diff --git a/mm/memory.c b/mm/memory.c
index 76e3af9639d9..2a12028a3749 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -555,11 +555,11 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 		dump_page(page, "bad pte");
 	pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n",
 		 (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
-	pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n",
+	pr_alert("file:%pD fault:%ps mmap:%ps read_folio:%ps\n",
 		 vma->vm_file,
 		 vma->vm_ops ? vma->vm_ops->fault : NULL,
 		 vma->vm_file ? vma->vm_file->f_op->mmap : NULL,
-		 mapping ? mapping->a_ops->readpage : NULL);
+		 mapping ? mapping->a_ops->read_folio : NULL);
 	dump_stack();
 	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 }
diff --git a/mm/readahead.c b/mm/readahead.c
index 76024c20a5a5..39983a3a93f0 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -170,12 +170,9 @@ static void read_pages(struct readahead_control *rac)
 			}
 			folio_unlock(folio);
 		}
-	} else if (aops->read_folio) {
-		while ((folio = readahead_folio(rac)) != NULL)
-			aops->read_folio(rac->file, folio);
 	} else {
 		while ((folio = readahead_folio(rac)) != NULL)
-			aops->readpage(rac->file, &folio->page);
+			aops->read_folio(rac->file, folio);
 	}
 
 	blk_finish_plug(&plug);
@@ -256,8 +253,8 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	}
 
 	/*
-	 * Now start the IO.  We ignore I/O errors - if the page is not
-	 * uptodate then the caller will launch readpage again, and
+	 * Now start the IO.  We ignore I/O errors - if the folio is not
+	 * uptodate then the caller will launch read_folio again, and
 	 * will then handle the error.
 	 */
 	read_pages(ractl);
@@ -305,8 +302,7 @@ void force_page_cache_ra(struct readahead_control *ractl,
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	unsigned long max_pages, index;
 
-	if (unlikely(!mapping->a_ops->read_folio &&
-		     !mapping->a_ops->readpage && !mapping->a_ops->readahead))
+	if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead))
 		return;
 
 	/*
diff --git a/mm/shmem.c b/mm/shmem.c
index 0f557a512171..f3e8de8ff75c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -4162,7 +4162,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
  *
  * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)",
  * with any new page allocations done using the specified allocation flags.
- * But read_cache_page_gfp() uses the ->readpage() method: which does not
+ * But read_cache_page_gfp() uses the ->read_folio() method: which does not
  * suit tmpfs, since it may have pages in swapcache, and needs to find those
  * for itself; although drivers/gpu/drm i915 and ttm rely upon this support.
  *
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 7c19098b8b45..ecd45bdbad9b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3041,7 +3041,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	/*
 	 * Read the swap header.
 	 */
-	if (!mapping->a_ops->read_folio && !mapping->a_ops->readpage) {
+	if (!mapping->a_ops->read_folio) {
 		error = -EINVAL;
 		goto bad_swap_unlock_inode;
 	}
-- 
cgit v1.2.3


From e9b5b23e957ef9260fec811d8d8081125889308a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 1 May 2022 21:39:29 -0400
Subject: fs: Change the type of filler_t

By making filler_t the same as read_folio, we can use the same function
for both in gfs2.  We can push the use of folios down one more level
in jffs2 and nfs.  We also increase type safety for future users of the
various read_cache_page() family of functions by forcing the parameter
to be a pointer to struct file (or NULL).

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/aops.c          | 29 +++++++++++------------------
 fs/jffs2/file.c         |  9 ++++-----
 fs/jffs2/gc.c           |  2 +-
 fs/jffs2/os-linux.h     |  2 +-
 fs/nfs/symlink.c        | 14 +++++++-------
 include/linux/pagemap.h |  6 +++---
 mm/filemap.c            | 40 ++++++++++++++++++++--------------------
 7 files changed, 47 insertions(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 340bf5d0e835..1016631bcbdc 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -464,21 +464,24 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 	return 0;
 }
 
-
-static int __gfs2_readpage(void *file, struct page *page)
+/**
+ * gfs2_read_folio - read a folio from a file
+ * @file: The file to read
+ * @folio: The folio in the file
+ */
+static int gfs2_read_folio(struct file *file, struct folio *folio)
 {
-	struct folio *folio = page_folio(page);
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	int error;
 
 	if (!gfs2_is_jdata(ip) ||
-	    (i_blocksize(inode) == PAGE_SIZE && !page_has_buffers(page))) {
+	    (i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) {
 		error = iomap_read_folio(folio, &gfs2_iomap_ops);
 	} else if (gfs2_is_stuffed(ip)) {
-		error = stuffed_readpage(ip, page);
-		unlock_page(page);
+		error = stuffed_readpage(ip, &folio->page);
+		folio_unlock(folio);
 	} else {
 		error = mpage_read_folio(folio, gfs2_block_map);
 	}
@@ -489,16 +492,6 @@ static int __gfs2_readpage(void *file, struct page *page)
 	return error;
 }
 
-/**
- * gfs2_read_folio - read a folio from a file
- * @file: The file to read
- * @folio: The folio in the file
- */
-static int gfs2_read_folio(struct file *file, struct folio *folio)
-{
-	return __gfs2_readpage(file, &folio->page);
-}
-
 /**
  * gfs2_internal_read - read an internal file
  * @ip: The gfs2 inode
@@ -523,7 +516,7 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
 		amt = size - copied;
 		if (offset + size > PAGE_SIZE)
 			amt = PAGE_SIZE - offset;
-		page = read_cache_page(mapping, index, __gfs2_readpage, NULL);
+		page = read_cache_page(mapping, index, gfs2_read_folio, NULL);
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 		p = kmap_atomic(page);
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 492fb2da0403..ba86acbe12d3 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -110,21 +110,20 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
 	return ret;
 }
 
-int jffs2_do_readpage_unlock(void *data, struct page *pg)
+int __jffs2_read_folio(struct file *file, struct folio *folio)
 {
-	int ret = jffs2_do_readpage_nolock(pg->mapping->host, pg);
-	unlock_page(pg);
+	int ret = jffs2_do_readpage_nolock(folio->mapping->host, &folio->page);
+	folio_unlock(folio);
 	return ret;
 }
 
-
 static int jffs2_read_folio(struct file *file, struct folio *folio)
 {
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(folio->mapping->host);
 	int ret;
 
 	mutex_lock(&f->sem);
-	ret = jffs2_do_readpage_unlock(file, &folio->page);
+	ret = __jffs2_read_folio(file, folio);
 	mutex_unlock(&f->sem);
 	return ret;
 }
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index a53bac7569b6..5c6602f3c189 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -1327,7 +1327,7 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 	 * trying to write out, read_cache_page() will not deadlock. */
 	mutex_unlock(&f->sem);
 	page = read_cache_page(inode->i_mapping, start >> PAGE_SHIFT,
-			       jffs2_do_readpage_unlock, NULL);
+			       __jffs2_read_folio, NULL);
 	if (IS_ERR(page)) {
 		pr_warn("read_cache_page() returned error: %ld\n",
 			PTR_ERR(page));
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index 173eccac691d..921d782583d6 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -155,7 +155,7 @@ extern const struct file_operations jffs2_file_operations;
 extern const struct inode_operations jffs2_file_inode_operations;
 extern const struct address_space_operations jffs2_file_address_operations;
 int jffs2_fsync(struct file *, loff_t, loff_t, int);
-int jffs2_do_readpage_unlock(void *data, struct page *pg);
+int __jffs2_read_folio(struct file *file, struct folio *folio);
 
 /* ioctl.c */
 long jffs2_ioctl(struct file *, unsigned int, unsigned long);
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index 8b53538bcc75..0e27a2e4e68b 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -26,21 +26,21 @@
  * and straight-forward than readdir caching.
  */
 
-static int nfs_symlink_filler(void *data, struct page *page)
+static int nfs_symlink_filler(struct file *file, struct folio *folio)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	int error;
 
-	error = NFS_PROTO(inode)->readlink(inode, page, 0, PAGE_SIZE);
+	error = NFS_PROTO(inode)->readlink(inode, &folio->page, 0, PAGE_SIZE);
 	if (error < 0)
 		goto error;
-	SetPageUptodate(page);
-	unlock_page(page);
+	folio_mark_uptodate(folio);
+	folio_unlock(folio);
 	return 0;
 
 error:
-	SetPageError(page);
-	unlock_page(page);
+	folio_set_error(folio);
+	folio_unlock(folio);
 	return -EIO;
 }
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index b70192f56454..831b28dab01a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -492,7 +492,7 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x)
 	return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN;
 }
 
-typedef int filler_t(void *, struct page *);
+typedef int filler_t(struct file *, struct folio *);
 
 pgoff_t page_cache_next_miss(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan);
@@ -747,9 +747,9 @@ static inline struct page *grab_cache_page(struct address_space *mapping,
 }
 
 struct folio *read_cache_folio(struct address_space *, pgoff_t index,
-		filler_t *filler, void *data);
+		filler_t *filler, struct file *file);
 struct page *read_cache_page(struct address_space *, pgoff_t index,
-		filler_t *filler, void *data);
+		filler_t *filler, struct file *file);
 extern struct page * read_cache_page_gfp(struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 079f8cca7959..81a0ed08a82c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3483,7 +3483,7 @@ EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
 static struct folio *do_read_cache_folio(struct address_space *mapping,
-		pgoff_t index, filler_t filler, void *data, gfp_t gfp)
+		pgoff_t index, filler_t filler, struct file *file, gfp_t gfp)
 {
 	struct folio *folio;
 	int err;
@@ -3504,9 +3504,9 @@ repeat:
 
 filler:
 		if (filler)
-			err = filler(data, &folio->page);
+			err = filler(file, folio);
 		else
-			err = mapping->a_ops->read_folio(data, folio);
+			err = mapping->a_ops->read_folio(file, folio);
 
 		if (err < 0) {
 			folio_put(folio);
@@ -3557,44 +3557,44 @@ out:
 }
 
 /**
- * read_cache_folio - read into page cache, fill it if needed
- * @mapping:	the page's address_space
- * @index:	the page index
- * @filler:	function to perform the read
- * @data:	first arg to filler(data, page) function, often left as NULL
- *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page and wait for it to become unlocked.
+ * read_cache_folio - Read into page cache, fill it if needed.
+ * @mapping: The address_space to read from.
+ * @index: The index to read.
+ * @filler: Function to perform the read, or NULL to use aops->read_folio().
+ * @file: Passed to filler function, may be NULL if not required.
  *
- * If the page does not get brought uptodate, return -EIO.
+ * Read one page into the page cache.  If it succeeds, the folio returned
+ * will contain @index, but it may not be the first page of the folio.
  *
- * The function expects mapping->invalidate_lock to be already held.
+ * If the filler function returns an error, it will be returned to the
+ * caller.
  *
- * Return: up to date page on success, ERR_PTR() on failure.
+ * Context: May sleep.  Expects mapping->invalidate_lock to be held.
+ * Return: An uptodate folio on success, ERR_PTR() on failure.
  */
 struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index,
-		filler_t filler, void *data)
+		filler_t filler, struct file *file)
 {
-	return do_read_cache_folio(mapping, index, filler, data,
+	return do_read_cache_folio(mapping, index, filler, file,
 			mapping_gfp_mask(mapping));
 }
 EXPORT_SYMBOL(read_cache_folio);
 
 static struct page *do_read_cache_page(struct address_space *mapping,
-		pgoff_t index, filler_t *filler, void *data, gfp_t gfp)
+		pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp)
 {
 	struct folio *folio;
 
-	folio = do_read_cache_folio(mapping, index, filler, data, gfp);
+	folio = do_read_cache_folio(mapping, index, filler, file, gfp);
 	if (IS_ERR(folio))
 		return &folio->page;
 	return folio_file_page(folio, index);
 }
 
 struct page *read_cache_page(struct address_space *mapping,
-				pgoff_t index, filler_t *filler, void *data)
+			pgoff_t index, filler_t *filler, struct file *file)
 {
-	return do_read_cache_page(mapping, index, filler, data,
+	return do_read_cache_page(mapping, index, filler, file,
 			mapping_gfp_mask(mapping));
 }
 EXPORT_SYMBOL(read_cache_page);
-- 
cgit v1.2.3


From 218d921b581eadf312c8ef0e09113b111f104eeb Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Apr 2022 22:08:54 -0700
Subject: fscrypt: add new helper functions for test_dummy_encryption

Unfortunately the design of fscrypt_set_test_dummy_encryption() doesn't
work properly for the new mount API, as it combines too many steps into
one function:

  - Parse the argument to test_dummy_encryption
  - Check the setting against the filesystem instance
  - Apply the setting to the filesystem instance

The new mount API has split these into separate steps.  ext4 partially
worked around this by duplicating some of the logic, but it still had
some bugs.  To address this, add some new helper functions that split up
the steps of fscrypt_set_test_dummy_encryption():

  - fscrypt_parse_test_dummy_encryption()
  - fscrypt_dummy_policies_equal()
  - fscrypt_add_test_dummy_key()

While we're add it, also add a function fscrypt_is_dummy_policy_set()
which will be useful to avoid some #ifdef's.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20220501050857.538984-5-ebiggers@kernel.org
---
 fs/crypto/fscrypt_private.h |   4 +-
 fs/crypto/keyring.c         |  64 ++++++++++++++++++++-----
 fs/crypto/policy.c          | 112 +++++++++++++++++++++++---------------------
 include/linux/fscrypt.h     |  39 +++++++++++++++
 4 files changed, 151 insertions(+), 68 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 7c93325161b0..6b4c8094cc7b 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -545,8 +545,8 @@ struct key *
 fscrypt_find_master_key(struct super_block *sb,
 			const struct fscrypt_key_specifier *mk_spec);
 
-int fscrypt_add_test_dummy_key(struct super_block *sb,
-			       struct fscrypt_key_specifier *key_spec);
+int fscrypt_get_test_dummy_key_identifier(
+			  u8 key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]);
 
 int fscrypt_verify_key_added(struct super_block *sb,
 			     const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]);
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 0b3ffbb4faf4..caee9f8620dd 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -688,28 +688,68 @@ out_wipe_secret:
 }
 EXPORT_SYMBOL_GPL(fscrypt_ioctl_add_key);
 
-/*
- * Add the key for '-o test_dummy_encryption' to the filesystem keyring.
- *
- * Use a per-boot random key to prevent people from misusing this option.
- */
-int fscrypt_add_test_dummy_key(struct super_block *sb,
-			       struct fscrypt_key_specifier *key_spec)
+static void
+fscrypt_get_test_dummy_secret(struct fscrypt_master_key_secret *secret)
 {
 	static u8 test_key[FSCRYPT_MAX_KEY_SIZE];
+
+	get_random_once(test_key, FSCRYPT_MAX_KEY_SIZE);
+
+	memset(secret, 0, sizeof(*secret));
+	secret->size = FSCRYPT_MAX_KEY_SIZE;
+	memcpy(secret->raw, test_key, FSCRYPT_MAX_KEY_SIZE);
+}
+
+int fscrypt_get_test_dummy_key_identifier(
+				u8 key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE])
+{
 	struct fscrypt_master_key_secret secret;
 	int err;
 
-	get_random_once(test_key, FSCRYPT_MAX_KEY_SIZE);
+	fscrypt_get_test_dummy_secret(&secret);
 
-	memset(&secret, 0, sizeof(secret));
-	secret.size = FSCRYPT_MAX_KEY_SIZE;
-	memcpy(secret.raw, test_key, FSCRYPT_MAX_KEY_SIZE);
+	err = fscrypt_init_hkdf(&secret.hkdf, secret.raw, secret.size);
+	if (err)
+		goto out;
+	err = fscrypt_hkdf_expand(&secret.hkdf, HKDF_CONTEXT_KEY_IDENTIFIER,
+				  NULL, 0, key_identifier,
+				  FSCRYPT_KEY_IDENTIFIER_SIZE);
+out:
+	wipe_master_key_secret(&secret);
+	return err;
+}
+
+/**
+ * fscrypt_add_test_dummy_key() - add the test dummy encryption key
+ * @sb: the filesystem instance to add the key to
+ * @dummy_policy: the encryption policy for test_dummy_encryption
+ *
+ * If needed, add the key for the test_dummy_encryption mount option to the
+ * filesystem.  To prevent misuse of this mount option, a per-boot random key is
+ * used instead of a hardcoded one.  This makes it so that any encrypted files
+ * created using this option won't be accessible after a reboot.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fscrypt_add_test_dummy_key(struct super_block *sb,
+			       const struct fscrypt_dummy_policy *dummy_policy)
+{
+	const union fscrypt_policy *policy = dummy_policy->policy;
+	struct fscrypt_key_specifier key_spec;
+	struct fscrypt_master_key_secret secret;
+	int err;
 
-	err = add_master_key(sb, &secret, key_spec);
+	if (!policy)
+		return 0;
+	err = fscrypt_policy_to_key_spec(policy, &key_spec);
+	if (err)
+		return err;
+	fscrypt_get_test_dummy_secret(&secret);
+	err = add_master_key(sb, &secret, &key_spec);
 	wipe_master_key_secret(&secret);
 	return err;
 }
+EXPORT_SYMBOL_GPL(fscrypt_add_test_dummy_key);
 
 /*
  * Verify that the current user has added a master key with the given identifier
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 2a11276913a9..5f858cee1e3b 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -10,6 +10,7 @@
  * Modified by Eric Biggers, 2019 for v2 policy support.
  */
 
+#include <linux/fs_context.h>
 #include <linux/random.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
@@ -724,73 +725,45 @@ int fscrypt_set_context(struct inode *inode, void *fs_data)
 EXPORT_SYMBOL_GPL(fscrypt_set_context);
 
 /**
- * fscrypt_set_test_dummy_encryption() - handle '-o test_dummy_encryption'
- * @sb: the filesystem on which test_dummy_encryption is being specified
- * @arg: the argument to the test_dummy_encryption option.  May be NULL.
- * @dummy_policy: the filesystem's current dummy policy (input/output, see
- *		  below)
+ * fscrypt_parse_test_dummy_encryption() - parse the test_dummy_encryption mount option
+ * @param: the mount option
+ * @dummy_policy: (input/output) the place to write the dummy policy that will
+ *	result from parsing the option.  Zero-initialize this.  If a policy is
+ *	already set here (due to test_dummy_encryption being given multiple
+ *	times), then this function will verify that the policies are the same.
  *
- * Handle the test_dummy_encryption mount option by creating a dummy encryption
- * policy, saving it in @dummy_policy, and adding the corresponding dummy
- * encryption key to the filesystem.  If the @dummy_policy is already set, then
- * instead validate that it matches @arg.  Don't support changing it via
- * remount, as that is difficult to do safely.
- *
- * Return: 0 on success (dummy policy set, or the same policy is already set);
- *         -EEXIST if a different dummy policy is already set;
- *         or another -errno value.
+ * Return: 0 on success; -EINVAL if the argument is invalid; -EEXIST if the
+ *	   argument conflicts with one already specified; or -ENOMEM.
  */
-int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
-				      struct fscrypt_dummy_policy *dummy_policy)
+int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param,
+				struct fscrypt_dummy_policy *dummy_policy)
 {
-	struct fscrypt_key_specifier key_spec = { 0 };
-	int version;
-	union fscrypt_policy *policy = NULL;
+	const char *arg = "v2";
+	union fscrypt_policy *policy;
 	int err;
 
-	if (!arg)
-		arg = "v2";
-
-	if (!strcmp(arg, "v1")) {
-		version = FSCRYPT_POLICY_V1;
-		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
-		memset(key_spec.u.descriptor, 0x42,
-		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
-	} else if (!strcmp(arg, "v2")) {
-		version = FSCRYPT_POLICY_V2;
-		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
-		/* key_spec.u.identifier gets filled in when adding the key */
-	} else {
-		err = -EINVAL;
-		goto out;
-	}
+	if (param->type == fs_value_is_string && *param->string)
+		arg = param->string;
 
 	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
-	if (!policy) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	err = fscrypt_add_test_dummy_key(sb, &key_spec);
-	if (err)
-		goto out;
+	if (!policy)
+		return -ENOMEM;
 
-	policy->version = version;
-	switch (policy->version) {
-	case FSCRYPT_POLICY_V1:
+	if (!strcmp(arg, "v1")) {
+		policy->version = FSCRYPT_POLICY_V1;
 		policy->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
 		policy->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
-		memcpy(policy->v1.master_key_descriptor, key_spec.u.descriptor,
+		memset(policy->v1.master_key_descriptor, 0x42,
 		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
-		break;
-	case FSCRYPT_POLICY_V2:
+	} else if (!strcmp(arg, "v2")) {
+		policy->version = FSCRYPT_POLICY_V2;
 		policy->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
 		policy->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
-		memcpy(policy->v2.master_key_identifier, key_spec.u.identifier,
-		       FSCRYPT_KEY_IDENTIFIER_SIZE);
-		break;
-	default:
-		WARN_ON(1);
+		err = fscrypt_get_test_dummy_key_identifier(
+				policy->v2.master_key_identifier);
+		if (err)
+			goto out;
+	} else {
 		err = -EINVAL;
 		goto out;
 	}
@@ -809,6 +782,37 @@ out:
 	kfree(policy);
 	return err;
 }
+EXPORT_SYMBOL_GPL(fscrypt_parse_test_dummy_encryption);
+
+/**
+ * fscrypt_dummy_policies_equal() - check whether two dummy policies are equal
+ * @p1: the first test dummy policy (may be unset)
+ * @p2: the second test dummy policy (may be unset)
+ *
+ * Return: %true if the dummy policies are both set and equal, or both unset.
+ */
+bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1,
+				  const struct fscrypt_dummy_policy *p2)
+{
+	if (!p1->policy && !p2->policy)
+		return true;
+	if (!p1->policy || !p2->policy)
+		return false;
+	return fscrypt_policies_equal(p1->policy, p2->policy);
+}
+EXPORT_SYMBOL_GPL(fscrypt_dummy_policies_equal);
+
+/* Deprecated, do not use */
+int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
+				      struct fscrypt_dummy_policy *dummy_policy)
+{
+	struct fs_parameter param = {
+		.type = fs_value_is_string,
+		.string = arg ? (char *)arg : "",
+	};
+	return fscrypt_parse_test_dummy_encryption(&param, dummy_policy) ?:
+		fscrypt_add_test_dummy_key(sb, dummy_policy);
+}
 EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption);
 
 /**
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index efc7f96e5e26..e60d57c99cb6 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -32,6 +32,7 @@
 
 union fscrypt_policy;
 struct fscrypt_info;
+struct fs_parameter;
 struct seq_file;
 
 struct fscrypt_str {
@@ -289,10 +290,19 @@ struct fscrypt_dummy_policy {
 	const union fscrypt_policy *policy;
 };
 
+int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param,
+				    struct fscrypt_dummy_policy *dummy_policy);
+bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1,
+				  const struct fscrypt_dummy_policy *p2);
 int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
 				struct fscrypt_dummy_policy *dummy_policy);
 void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
 					struct super_block *sb);
+static inline bool
+fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy)
+{
+	return dummy_policy->policy != NULL;
+}
 static inline void
 fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 {
@@ -303,6 +313,8 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 /* keyring.c */
 void fscrypt_sb_free(struct super_block *sb);
 int fscrypt_ioctl_add_key(struct file *filp, void __user *arg);
+int fscrypt_add_test_dummy_key(struct super_block *sb,
+			       const struct fscrypt_dummy_policy *dummy_policy);
 int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg);
 int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg);
 int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg);
@@ -477,12 +489,32 @@ static inline int fscrypt_set_context(struct inode *inode, void *fs_data)
 struct fscrypt_dummy_policy {
 };
 
+static inline int
+fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param,
+				    struct fscrypt_dummy_policy *dummy_policy)
+{
+	return -EINVAL;
+}
+
+static inline bool
+fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1,
+			     const struct fscrypt_dummy_policy *p2)
+{
+	return true;
+}
+
 static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq,
 						      char sep,
 						      struct super_block *sb)
 {
 }
 
+static inline bool
+fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy)
+{
+	return false;
+}
+
 static inline void
 fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 {
@@ -498,6 +530,13 @@ static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg)
 	return -EOPNOTSUPP;
 }
 
+static inline int
+fscrypt_add_test_dummy_key(struct super_block *sb,
+			   const struct fscrypt_dummy_policy *dummy_policy)
+{
+	return 0;
+}
+
 static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 623a1ddfeb232526275ddd0c8378771e6712aad4 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:42 -0700
Subject: mm/hugetlb: take src_mm->write_protect_seq in
 copy_hugetlb_page_range()

Let's do it just like copy_page_range(), taking the seqlock and making
sure the mmap_lock is held in write mode.

This allows for add a VM_BUG_ON to page_needs_cow_for_dma() and properly
synchronizes concurrent fork() with GUP-fast of hugetlb pages, which will
be relevant for further changes.

Link: https://lkml.kernel.org/r/20220428083441.37290-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 4 ++++
 mm/hugetlb.c       | 8 ++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index b9316b2c11ce..a02812178562 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1576,6 +1576,8 @@ static inline bool page_maybe_dma_pinned(struct page *page)
 /*
  * This should most likely only be called during fork() to see whether we
  * should break the cow immediately for a page on the src mm.
+ *
+ * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq.
  */
 static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 					  struct page *page)
@@ -1583,6 +1585,8 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 	if (!is_cow_mapping(vma->vm_flags))
 		return false;
 
+	VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1));
+
 	if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
 		return false;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4e017940b26f..7389cd8a9a87 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4735,6 +4735,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 					vma->vm_start,
 					vma->vm_end);
 		mmu_notifier_invalidate_range_start(&range);
+		mmap_assert_write_locked(src);
+		raw_write_seqcount_begin(&src->write_protect_seq);
 	} else {
 		/*
 		 * For shared mappings i_mmap_rwsem must be held to call
@@ -4867,10 +4869,12 @@ again:
 		spin_unlock(dst_ptl);
 	}
 
-	if (cow)
+	if (cow) {
+		raw_write_seqcount_end(&src->write_protect_seq);
 		mmu_notifier_invalidate_range_end(&range);
-	else
+	} else {
 		i_mmap_unlock_read(mapping);
+	}
 
 	return ret;
 }
-- 
cgit v1.2.3


From fb3d824d1a46c5bb0584ea88f32dc2495544aebf Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:43 -0700
Subject: mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and
 page_try_dup_anon_rmap()

...  and move the special check for pinned pages into
page_try_dup_anon_rmap() to prepare for tracking exclusive anonymous pages
via a new pageflag, clearing it only after making sure that there are no
GUP pins on the anonymous page.

We really only care about pins on anonymous pages, because they are prone
to getting replaced in the COW handler once mapped R/O.  For !anon pages
in cow-mappings (!VM_SHARED && VM_MAYWRITE) we shouldn't really care about
that, at least not that I could come up with an example.

Let's drop the is_cow_mapping() check from page_needs_cow_for_dma(), as we
know we're dealing with anonymous pages.  Also, drop the handling of
pinned pages from copy_huge_pud() and add a comment if ever supporting
anonymous pages on the PUD level.

This is a preparation for tracking exclusivity of anonymous pages in the
rmap code, and disallowing marking a page shared (-> failing to duplicate)
if there are GUP pins on a page.

Link: https://lkml.kernel.org/r/20220428083441.37290-5-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h   |  5 +----
 include/linux/rmap.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++-
 mm/huge_memory.c     | 27 ++++++++-------------------
 mm/hugetlb.c         | 16 +++++++++-------
 mm/memory.c          | 17 ++++++++++++-----
 mm/migrate.c         |  2 +-
 6 files changed, 79 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index a02812178562..9ee3ae51e8e3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1575,16 +1575,13 @@ static inline bool page_maybe_dma_pinned(struct page *page)
 
 /*
  * This should most likely only be called during fork() to see whether we
- * should break the cow immediately for a page on the src mm.
+ * should break the cow immediately for an anon page on the src mm.
  *
  * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq.
  */
 static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 					  struct page *page)
 {
-	if (!is_cow_mapping(vma->vm_flags))
-		return false;
-
 	VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1));
 
 	if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 8573aae50d96..73f41544084f 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -12,6 +12,7 @@
 #include <linux/memcontrol.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/memremap.h>
 
 /*
  * The anon_vma heads a list of private "related" vmas, to scan if
@@ -182,11 +183,57 @@ void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,
 void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address);
 
-static inline void page_dup_rmap(struct page *page, bool compound)
+static inline void __page_dup_rmap(struct page *page, bool compound)
 {
 	atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount);
 }
 
+static inline void page_dup_file_rmap(struct page *page, bool compound)
+{
+	__page_dup_rmap(page, compound);
+}
+
+/**
+ * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped
+ *			    anonymous page
+ * @page: the page to duplicate the mapping for
+ * @compound: the page is mapped as compound or as a small page
+ * @vma: the source vma
+ *
+ * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq.
+ *
+ * Duplicating the mapping can only fail if the page may be pinned; device
+ * private pages cannot get pinned and consequently this function cannot fail.
+ *
+ * If duplicating the mapping succeeds, the page has to be mapped R/O into
+ * the parent and the child. It must *not* get mapped writable after this call.
+ *
+ * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
+ */
+static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
+					 struct vm_area_struct *vma)
+{
+	VM_BUG_ON_PAGE(!PageAnon(page), page);
+
+	/*
+	 * If this page may have been pinned by the parent process,
+	 * don't allow to duplicate the mapping but instead require to e.g.,
+	 * copy the page immediately for the child so that we'll always
+	 * guarantee the pinned page won't be randomly replaced in the
+	 * future on write faults.
+	 */
+	if (likely(!is_device_private_page(page) &&
+	    unlikely(page_needs_cow_for_dma(vma, page))))
+		return -EBUSY;
+
+	/*
+	 * It's okay to share the anon page between both processes, mapping
+	 * the page R/O into both processes.
+	 */
+	__page_dup_rmap(page, compound);
+	return 0;
+}
+
 /*
  * Called from mm/vmscan.c to handle paging out
  */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c468fee595ff..baf4ea6d8e1a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1097,23 +1097,16 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	src_page = pmd_page(pmd);
 	VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
 
-	/*
-	 * If this page is a potentially pinned page, split and retry the fault
-	 * with smaller page size.  Normally this should not happen because the
-	 * userspace should use MADV_DONTFORK upon pinned regions.  This is a
-	 * best effort that the pinned pages won't be replaced by another
-	 * random page during the coming copy-on-write.
-	 */
-	if (unlikely(page_needs_cow_for_dma(src_vma, src_page))) {
+	get_page(src_page);
+	if (unlikely(page_try_dup_anon_rmap(src_page, true, src_vma))) {
+		/* Page maybe pinned: split and retry the fault on PTEs. */
+		put_page(src_page);
 		pte_free(dst_mm, pgtable);
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
 		__split_huge_pmd(src_vma, src_pmd, addr, false, NULL);
 		return -EAGAIN;
 	}
-
-	get_page(src_page);
-	page_dup_rmap(src_page, true);
 	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 out_zero_page:
 	mm_inc_nr_ptes(dst_mm);
@@ -1217,14 +1210,10 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		/* No huge zero pud yet */
 	}
 
-	/* Please refer to comments in copy_huge_pmd() */
-	if (unlikely(page_needs_cow_for_dma(vma, pud_page(pud)))) {
-		spin_unlock(src_ptl);
-		spin_unlock(dst_ptl);
-		__split_huge_pud(vma, src_pud, addr);
-		return -EAGAIN;
-	}
-
+	/*
+	 * TODO: once we support anonymous pages, use page_try_dup_anon_rmap()
+	 * and split if duplicating fails.
+	 */
 	pudp_set_wrprotect(src_mm, addr, src_pud);
 	pud = pud_mkold(pud_wrprotect(pud));
 	set_pud_at(dst_mm, addr, dst_pud, pud);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7389cd8a9a87..7a6052a984e9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4806,15 +4806,18 @@ again:
 			get_page(ptepage);
 
 			/*
-			 * This is a rare case where we see pinned hugetlb
-			 * pages while they're prone to COW.  We need to do the
-			 * COW earlier during fork.
+			 * Failing to duplicate the anon rmap is a rare case
+			 * where we see pinned hugetlb pages while they're
+			 * prone to COW. We need to do the COW earlier during
+			 * fork.
 			 *
 			 * When pre-allocating the page or copying data, we
 			 * need to be without the pgtable locks since we could
 			 * sleep during the process.
 			 */
-			if (unlikely(page_needs_cow_for_dma(vma, ptepage))) {
+			if (!PageAnon(ptepage)) {
+				page_dup_file_rmap(ptepage, true);
+			} else if (page_try_dup_anon_rmap(ptepage, true, vma)) {
 				pte_t src_pte_old = entry;
 				struct page *new;
 
@@ -4861,7 +4864,6 @@ again:
 				entry = huge_pte_wrprotect(entry);
 			}
 
-			page_dup_rmap(ptepage, true);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 			hugetlb_count_add(npages, dst);
 		}
@@ -5541,7 +5543,7 @@ retry:
 		ClearHPageRestoreReserve(page);
 		hugepage_add_new_anon_rmap(page, vma, haddr);
 	} else
-		page_dup_rmap(page, true);
+		page_dup_file_rmap(page, true);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, haddr, ptep, new_pte);
@@ -5902,7 +5904,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		goto out_release_unlock;
 
 	if (vm_shared) {
-		page_dup_rmap(page, true);
+		page_dup_file_rmap(page, true);
 	} else {
 		ClearHPageRestoreReserve(page);
 		hugepage_add_new_anon_rmap(page, dst_vma, dst_addr);
diff --git a/mm/memory.c b/mm/memory.c
index 9bdfce15e98f..9f5f829a1b1f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -825,7 +825,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		 */
 		get_page(page);
 		rss[mm_counter(page)]++;
-		page_dup_rmap(page, false);
+		/* Cannot fail as these pages cannot get pinned. */
+		BUG_ON(page_try_dup_anon_rmap(page, false, src_vma));
 
 		/*
 		 * We do not preserve soft-dirty information, because so
@@ -921,18 +922,24 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	struct page *page;
 
 	page = vm_normal_page(src_vma, addr, pte);
-	if (page && unlikely(page_needs_cow_for_dma(src_vma, page))) {
+	if (page && PageAnon(page)) {
 		/*
 		 * If this page may have been pinned by the parent process,
 		 * copy the page immediately for the child so that we'll always
 		 * guarantee the pinned page won't be randomly replaced in the
 		 * future.
 		 */
-		return copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
-					 addr, rss, prealloc, page);
+		get_page(page);
+		if (unlikely(page_try_dup_anon_rmap(page, false, src_vma))) {
+			/* Page maybe pinned, we have to copy. */
+			put_page(page);
+			return copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
+						 addr, rss, prealloc, page);
+		}
+		rss[mm_counter(page)]++;
 	} else if (page) {
 		get_page(page);
-		page_dup_rmap(page, false);
+		page_dup_file_rmap(page, false);
 		rss[mm_counter(page)]++;
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 77592288fbc0..6ca6e89ded94 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -234,7 +234,7 @@ static bool remove_migration_pte(struct folio *folio,
 			if (folio_test_anon(folio))
 				hugepage_add_anon_rmap(new, vma, pvmw.address);
 			else
-				page_dup_rmap(new, true);
+				page_dup_file_rmap(new, true);
 			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
 		} else
 #endif
-- 
cgit v1.2.3


From 14f9135d547060d1d0c182501201f8da19895fe3 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:43 -0700
Subject: mm/rmap: convert RMAP flags to a proper distinct rmap_t type

We want to pass the flags to more than one anon rmap function, getting rid
of special "do_page_add_anon_rmap()".  So let's pass around a distinct
__bitwise type and refine documentation.

Link: https://lkml.kernel.org/r/20220428083441.37290-6-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 22 ++++++++++++++++++----
 mm/memory.c          |  6 +++---
 mm/rmap.c            |  7 ++++---
 3 files changed, 25 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 73f41544084f..c53a38151089 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -160,9 +160,23 @@ static inline void anon_vma_merge(struct vm_area_struct *vma,
 
 struct anon_vma *page_get_anon_vma(struct page *page);
 
-/* bitflags for do_page_add_anon_rmap() */
-#define RMAP_EXCLUSIVE 0x01
-#define RMAP_COMPOUND 0x02
+/* RMAP flags, currently only relevant for some anon rmap operations. */
+typedef int __bitwise rmap_t;
+
+/*
+ * No special request: if the page is a subpage of a compound page, it is
+ * mapped via a PTE. The mapped (sub)page is possibly shared between processes.
+ */
+#define RMAP_NONE		((__force rmap_t)0)
+
+/* The (sub)page is exclusive to a single process. */
+#define RMAP_EXCLUSIVE		((__force rmap_t)BIT(0))
+
+/*
+ * The compound page is not mapped via PTEs, but instead via a single PMD and
+ * should be accounted accordingly.
+ */
+#define RMAP_COMPOUND		((__force rmap_t)BIT(1))
 
 /*
  * rmap interfaces called when adding or removing pte of page
@@ -171,7 +185,7 @@ void page_move_anon_rmap(struct page *, struct vm_area_struct *);
 void page_add_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, bool compound);
 void do_page_add_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long address, int flags);
+		unsigned long address, rmap_t flags);
 void page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, bool compound);
 void page_add_file_rmap(struct page *, struct vm_area_struct *,
diff --git a/mm/memory.c b/mm/memory.c
index 9f5f829a1b1f..4cd8cadf1268 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3511,10 +3511,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = NULL, *swapcache;
 	struct swap_info_struct *si = NULL;
+	rmap_t rmap_flags = RMAP_NONE;
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
-	int exclusive = 0;
 	vm_fault_t ret = 0;
 	void *shadow = NULL;
 
@@ -3689,7 +3689,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 		vmf->flags &= ~FAULT_FLAG_WRITE;
 		ret |= VM_FAULT_WRITE;
-		exclusive = RMAP_EXCLUSIVE;
+		rmap_flags |= RMAP_EXCLUSIVE;
 	}
 	flush_icache_page(vma, page);
 	if (pte_swp_soft_dirty(vmf->orig_pte))
@@ -3705,7 +3705,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
-		do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
+		do_page_add_anon_rmap(page, vma, vmf->address, rmap_flags);
 	}
 
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
diff --git a/mm/rmap.c b/mm/rmap.c
index 91a63dc636ad..23a41132995e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1181,7 +1181,8 @@ static void __page_check_anon_rmap(struct page *page,
 void page_add_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address, bool compound)
 {
-	do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0);
+	do_page_add_anon_rmap(page, vma, address,
+			      compound ? RMAP_COMPOUND : RMAP_NONE);
 }
 
 /*
@@ -1190,7 +1191,7 @@ void page_add_anon_rmap(struct page *page,
  * Everybody else should continue to use page_add_anon_rmap above.
  */
 void do_page_add_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address, int flags)
+	struct vm_area_struct *vma, unsigned long address, rmap_t flags)
 {
 	bool compound = flags & RMAP_COMPOUND;
 	bool first;
@@ -1229,7 +1230,7 @@ void do_page_add_anon_rmap(struct page *page,
 	/* address might be in next vma when migration races vma_adjust */
 	else if (first)
 		__page_set_anon_rmap(page, vma, address,
-				flags & RMAP_EXCLUSIVE);
+				     !!(flags & RMAP_EXCLUSIVE));
 	else
 		__page_check_anon_rmap(page, vma, address);
 
-- 
cgit v1.2.3


From f1e2db12e45baaa2d366f87c885968096c2ff5aa Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:43 -0700
Subject: mm/rmap: remove do_page_add_anon_rmap()

... and instead convert page_add_anon_rmap() to accept flags.

Passing flags instead of bools is usually nicer either way, and we want to
more often also pass RMAP_EXCLUSIVE in follow up patches when detecting
that an anonymous page is exclusive: for example, when restoring an
anonymous page from a writable migration entry.

This is a preparation for marking an anonymous page inside
page_add_anon_rmap() as exclusive when RMAP_EXCLUSIVE is passed.

Link: https://lkml.kernel.org/r/20220428083441.37290-7-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |  2 --
 mm/huge_memory.c     |  2 +-
 mm/ksm.c             |  2 +-
 mm/memory.c          |  4 ++--
 mm/migrate.c         |  3 ++-
 mm/rmap.c            | 14 +-------------
 mm/swapfile.c        |  2 +-
 7 files changed, 8 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c53a38151089..643801a937f3 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -183,8 +183,6 @@ typedef int __bitwise rmap_t;
  */
 void page_move_anon_rmap(struct page *, struct vm_area_struct *);
 void page_add_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long address, bool compound);
-void do_page_add_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
 void page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, bool compound);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index baf4ea6d8e1a..6232b6817fab 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3072,7 +3072,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 		pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde));
 
 	if (PageAnon(new))
-		page_add_anon_rmap(new, vma, mmun_start, true);
+		page_add_anon_rmap(new, vma, mmun_start, RMAP_COMPOUND);
 	else
 		page_add_file_rmap(new, vma, true);
 	set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
diff --git a/mm/ksm.c b/mm/ksm.c
index 94bb0f049806..2b6692a7df6a 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1156,7 +1156,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	 */
 	if (!is_zero_pfn(page_to_pfn(kpage))) {
 		get_page(kpage);
-		page_add_anon_rmap(kpage, vma, addr, false);
+		page_add_anon_rmap(kpage, vma, addr, RMAP_NONE);
 		newpte = mk_pte(kpage, vma->vm_page_prot);
 	} else {
 		newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage),
diff --git a/mm/memory.c b/mm/memory.c
index 4cd8cadf1268..8e92010f3d89 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -725,7 +725,7 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
 	 * created when the swap entry was made.
 	 */
 	if (PageAnon(page))
-		page_add_anon_rmap(page, vma, address, false);
+		page_add_anon_rmap(page, vma, address, RMAP_NONE);
 	else
 		/*
 		 * Currently device exclusive access only supports anonymous
@@ -3705,7 +3705,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
-		do_page_add_anon_rmap(page, vma, vmf->address, rmap_flags);
+		page_add_anon_rmap(page, vma, vmf->address, rmap_flags);
 	}
 
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
diff --git a/mm/migrate.c b/mm/migrate.c
index 6ca6e89ded94..381c7e05e8d4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -240,7 +240,8 @@ static bool remove_migration_pte(struct folio *folio,
 #endif
 		{
 			if (folio_test_anon(folio))
-				page_add_anon_rmap(new, vma, pvmw.address, false);
+				page_add_anon_rmap(new, vma, pvmw.address,
+						   RMAP_NONE);
 			else
 				page_add_file_rmap(new, vma, false);
 			set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
diff --git a/mm/rmap.c b/mm/rmap.c
index 23a41132995e..a0cbbf201c98 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1171,7 +1171,7 @@ static void __page_check_anon_rmap(struct page *page,
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
- * @compound:	charge the page as compound or small page
+ * @flags:	the rmap flags
  *
  * The caller needs to hold the pte lock, and the page must be locked in
  * the anon_vma case: to serialize mapping,index checking after setting,
@@ -1179,18 +1179,6 @@ static void __page_check_anon_rmap(struct page *page,
  * (but PageKsm is never downgraded to PageAnon).
  */
 void page_add_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address, bool compound)
-{
-	do_page_add_anon_rmap(page, vma, address,
-			      compound ? RMAP_COMPOUND : RMAP_NONE);
-}
-
-/*
- * Special version of the above for do_swap_page, which often runs
- * into pages that are exclusively owned by the current process.
- * Everybody else should continue to use page_add_anon_rmap above.
- */
-void do_page_add_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address, rmap_t flags)
 {
 	bool compound = flags & RMAP_COMPOUND;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 63c61f8b2611..1ba525a2179d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1800,7 +1800,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 	get_page(page);
 	if (page == swapcache) {
-		page_add_anon_rmap(page, vma, addr, false);
+		page_add_anon_rmap(page, vma, addr, RMAP_NONE);
 	} else { /* ksm created a completely new copy */
 		page_add_new_anon_rmap(page, vma, addr, false);
 		lru_cache_add_inactive_or_unevictable(page, vma);
-- 
cgit v1.2.3


From 28c5209dfd5f86f4398ce01bfac8508b2c4d4050 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:43 -0700
Subject: mm/rmap: pass rmap flags to hugepage_add_anon_rmap()

Let's prepare for passing RMAP_EXCLUSIVE, similarly as we do for
page_add_anon_rmap() now.  RMAP_COMPOUND is implicit for hugetlb pages and
ignored.

Link: https://lkml.kernel.org/r/20220428083441.37290-8-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 2 +-
 mm/migrate.c         | 3 ++-
 mm/rmap.c            | 9 ++++++---
 3 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 643801a937f3..90e1e6925789 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -191,7 +191,7 @@ void page_add_file_rmap(struct page *, struct vm_area_struct *,
 void page_remove_rmap(struct page *, struct vm_area_struct *,
 		bool compound);
 void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long address);
+		unsigned long address, rmap_t flags);
 void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 381c7e05e8d4..92e932f08be5 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -232,7 +232,8 @@ static bool remove_migration_pte(struct folio *folio,
 			pte = pte_mkhuge(pte);
 			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
 			if (folio_test_anon(folio))
-				hugepage_add_anon_rmap(new, vma, pvmw.address);
+				hugepage_add_anon_rmap(new, vma, pvmw.address,
+						       RMAP_NONE);
 			else
 				page_dup_file_rmap(new, true);
 			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
diff --git a/mm/rmap.c b/mm/rmap.c
index a0cbbf201c98..32630f1b1ee1 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2391,9 +2391,11 @@ void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc)
  * The following two functions are for anonymous (private mapped) hugepages.
  * Unlike common anonymous pages, anonymous hugepages have no accounting code
  * and no lru code, because we handle hugepages differently from common pages.
+ *
+ * RMAP_COMPOUND is ignored.
  */
-void hugepage_add_anon_rmap(struct page *page,
-			    struct vm_area_struct *vma, unsigned long address)
+void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
+			    unsigned long address, rmap_t flags)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	int first;
@@ -2403,7 +2405,8 @@ void hugepage_add_anon_rmap(struct page *page,
 	/* address might be in next vma when migration races vma_adjust */
 	first = atomic_inc_and_test(compound_mapcount_ptr(page));
 	if (first)
-		__page_set_anon_rmap(page, vma, address, 0);
+		__page_set_anon_rmap(page, vma, address,
+				     !!(flags & RMAP_EXCLUSIVE));
 }
 
 void hugepage_add_new_anon_rmap(struct page *page,
-- 
cgit v1.2.3


From 40f2bbf71161fa9195c7869004290003af152375 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:43 -0700
Subject: mm/rmap: drop "compound" parameter from page_add_new_anon_rmap()

New anonymous pages are always mapped natively: only THP/khugepaged code
maps a new compound anonymous page and passes "true".  Otherwise, we're
just dealing with simple, non-compound pages.

Let's give the interface clearer semantics and document these.  Remove the
PageTransCompound() sanity check from page_add_new_anon_rmap().

Link: https://lkml.kernel.org/r/20220428083441.37290-9-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h    |  3 ++-
 kernel/events/uprobes.c |  2 +-
 mm/huge_memory.c        |  2 +-
 mm/khugepaged.c         |  2 +-
 mm/memory.c             | 10 +++++-----
 mm/migrate_device.c     |  2 +-
 mm/rmap.c               | 11 ++++++-----
 mm/swapfile.c           |  2 +-
 mm/userfaultfd.c        |  2 +-
 9 files changed, 19 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 90e1e6925789..e4156921eea9 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -185,11 +185,12 @@ void page_move_anon_rmap(struct page *, struct vm_area_struct *);
 void page_add_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
 void page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long address, bool compound);
+		unsigned long address);
 void page_add_file_rmap(struct page *, struct vm_area_struct *,
 		bool compound);
 void page_remove_rmap(struct page *, struct vm_area_struct *,
 		bool compound);
+
 void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
 void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *,
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 6418083901d4..4ef5385815d3 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -180,7 +180,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	if (new_page) {
 		get_page(new_page);
-		page_add_new_anon_rmap(new_page, vma, addr, false);
+		page_add_new_anon_rmap(new_page, vma, addr);
 		lru_cache_add_inactive_or_unevictable(new_page, vma);
 	} else
 		/* no new page, just dec_mm_counter for old_page */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6232b6817fab..c0365280b481 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -647,7 +647,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		page_add_new_anon_rmap(page, vma, haddr, true);
+		page_add_new_anon_rmap(page, vma, haddr);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index ac53ad2c9bb1..a2560f970881 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1183,7 +1183,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
-	page_add_new_anon_rmap(new_page, vma, address, true);
+	page_add_new_anon_rmap(new_page, vma, address);
 	lru_cache_add_inactive_or_unevictable(new_page, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
diff --git a/mm/memory.c b/mm/memory.c
index 8e92010f3d89..3dedb575baef 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -893,7 +893,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 	*prealloc = NULL;
 	copy_user_highpage(new_page, page, addr, src_vma);
 	__SetPageUptodate(new_page);
-	page_add_new_anon_rmap(new_page, dst_vma, addr, false);
+	page_add_new_anon_rmap(new_page, dst_vma, addr);
 	lru_cache_add_inactive_or_unevictable(new_page, dst_vma);
 	rss[mm_counter(new_page)]++;
 
@@ -3058,7 +3058,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		 * some TLBs while the old PTE remains in others.
 		 */
 		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
-		page_add_new_anon_rmap(new_page, vma, vmf->address, false);
+		page_add_new_anon_rmap(new_page, vma, vmf->address);
 		lru_cache_add_inactive_or_unevictable(new_page, vma);
 		/*
 		 * We call the notify macro here because, when using secondary
@@ -3702,7 +3702,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 	/* ksm created a completely new copy */
 	if (unlikely(page != swapcache && swapcache)) {
-		page_add_new_anon_rmap(page, vma, vmf->address, false);
+		page_add_new_anon_rmap(page, vma, vmf->address);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		page_add_anon_rmap(page, vma, vmf->address, rmap_flags);
@@ -3852,7 +3852,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	}
 
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, vma, vmf->address, false);
+	page_add_new_anon_rmap(page, vma, vmf->address);
 	lru_cache_add_inactive_or_unevictable(page, vma);
 setpte:
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
@@ -4039,7 +4039,7 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 	/* copy-on-write page */
 	if (write && !(vma->vm_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-		page_add_new_anon_rmap(page, vma, addr, false);
+		page_add_new_anon_rmap(page, vma, addr);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 70c7dc05bbfc..fb6d7d5499f5 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -610,7 +610,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 		goto unlock_abort;
 
 	inc_mm_counter(mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, vma, addr, false);
+	page_add_new_anon_rmap(page, vma, addr);
 	if (!is_zone_device_page(page))
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	get_page(page);
diff --git a/mm/rmap.c b/mm/rmap.c
index 32630f1b1ee1..90f92c53476f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1226,19 +1226,22 @@ void page_add_anon_rmap(struct page *page,
 }
 
 /**
- * page_add_new_anon_rmap - add pte mapping to a new anonymous page
+ * page_add_new_anon_rmap - add mapping to a new anonymous page
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
- * @compound:	charge the page as compound or small page
+ *
+ * If it's a compound page, it is accounted as a compound page. As the page
+ * is new, it's assume to get mapped exclusively by a single process.
  *
  * Same as page_add_anon_rmap but must only be called on *new* pages.
  * This means the inc-and-test can be bypassed.
  * Page does not have to be locked.
  */
 void page_add_new_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address, bool compound)
+	struct vm_area_struct *vma, unsigned long address)
 {
+	const bool compound = PageCompound(page);
 	int nr = compound ? thp_nr_pages(page) : 1;
 
 	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
@@ -1251,8 +1254,6 @@ void page_add_new_anon_rmap(struct page *page,
 
 		__mod_lruvec_page_state(page, NR_ANON_THPS, nr);
 	} else {
-		/* Anon THP always mapped first with PMD */
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
 		/* increment count (starts at -1) */
 		atomic_set(&page->_mapcount, 0);
 	}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1ba525a2179d..0ad7ed7ded21 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1802,7 +1802,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	if (page == swapcache) {
 		page_add_anon_rmap(page, vma, addr, RMAP_NONE);
 	} else { /* ksm created a completely new copy */
-		page_add_new_anon_rmap(page, vma, addr, false);
+		page_add_new_anon_rmap(page, vma, addr);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	}
 	set_pte_at(vma->vm_mm, addr, pte,
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index e9bb6db002aa..dae25d985d15 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -104,7 +104,7 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 			lru_cache_add(page);
 		page_add_file_rmap(page, dst_vma, false);
 	} else {
-		page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
+		page_add_new_anon_rmap(page, dst_vma, dst_addr);
 		lru_cache_add_inactive_or_unevictable(page, dst_vma);
 	}
 
-- 
cgit v1.2.3


From 78fbe906cc900b33ce078102e13e0e99b5b8c406 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:44 -0700
Subject: mm/page-flags: reuse PG_mappedtodisk as PG_anon_exclusive for
 PageAnon() pages

The basic question we would like to have a reliable and efficient answer
to is: is this anonymous page exclusive to a single process or might it be
shared?  We need that information for ordinary/single pages, hugetlb
pages, and possibly each subpage of a THP.

Introduce a way to mark an anonymous page as exclusive, with the ultimate
goal of teaching our COW logic to not do "wrong COWs", whereby GUP pins
lose consistency with the pages mapped into the page table, resulting in
reported memory corruptions.

Most pageflags already have semantics for anonymous pages, however,
PG_mappedtodisk should never apply to pages in the swapcache, so let's
reuse that flag.

As PG_has_hwpoisoned also uses that flag on the second tail page of a
compound page, convert it to PG_error instead, which is marked as
PF_NO_TAIL, so never used for tail pages.

Use custom page flag modification functions such that we can do additional
sanity checks.  The semantics we'll put into some kernel doc in the future
are:

"
  PG_anon_exclusive is *usually* only expressive in combination with a
  page table entry. Depending on the page table entry type it might
  store the following information:

       Is what's mapped via this page table entry exclusive to the
       single process and can be mapped writable without further
       checks? If not, it might be shared and we might have to COW.

  For now, we only expect PTE-mapped THPs to make use of
  PG_anon_exclusive in subpages. For other anonymous compound
  folios (i.e., hugetlb), only the head page is logically mapped and
  holds this information.

  For example, an exclusive, PMD-mapped THP only has PG_anon_exclusive
  set on the head page. When replacing the PMD by a page table full
  of PTEs, PG_anon_exclusive, if set on the head page, will be set on
  all tail pages accordingly. Note that converting from a PTE-mapping
  to a PMD mapping using the same compound page is currently not
  possible and consequently doesn't require care.

  If GUP wants to take a reliable pin (FOLL_PIN) on an anonymous page,
  it should only pin if the relevant PG_anon_exclusive is set. In that
  case, the pin will be fully reliable and stay consistent with the pages
  mapped into the page table, as the bit cannot get cleared (e.g., by
  fork(), KSM) while the page is pinned. For anonymous pages that
  are mapped R/W, PG_anon_exclusive can be assumed to always be set
  because such pages cannot possibly be shared.

  The page table lock protecting the page table entry is the primary
  synchronization mechanism for PG_anon_exclusive; GUP-fast that does
  not take the PT lock needs special care when trying to clear the
  flag.

  Page table entry types and PG_anon_exclusive:
  * Present: PG_anon_exclusive applies.
  * Swap: the information is lost. PG_anon_exclusive was cleared.
  * Migration: the entry holds this information instead.
               PG_anon_exclusive was cleared.
  * Device private: PG_anon_exclusive applies.
  * Device exclusive: PG_anon_exclusive applies.
  * HW Poison: PG_anon_exclusive is stale and not changed.

  If the page may be pinned (FOLL_PIN), clearing PG_anon_exclusive is
  not allowed and the flag will stick around until the page is freed
  and folio->mapping is cleared.
"

We won't be clearing PG_anon_exclusive on destructive unmapping (i.e.,
zapping) of page table entries, page freeing code will handle that when
also invalidate page->mapping to not indicate PageAnon() anymore.  Letting
information about exclusivity stick around will be an important property
when adding sanity checks to unpinning code.

Note that we properly clear the flag in free_pages_prepare() via
PAGE_FLAGS_CHECK_AT_PREP for each individual subpage of a compound page,
so there is no need to manually clear the flag.

Link: https://lkml.kernel.org/r/20220428083441.37290-12-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 39 ++++++++++++++++++++++++++++++++++++++-
 mm/hugetlb.c               |  2 ++
 mm/memory.c                | 11 +++++++++++
 mm/memremap.c              |  9 +++++++++
 mm/swapfile.c              |  4 ++++
 tools/vm/page-types.c      |  8 +++++++-
 6 files changed, 71 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1ea896887ee4..b70124b9c7c1 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -142,6 +142,15 @@ enum pageflags {
 
 	PG_readahead = PG_reclaim,
 
+	/*
+	 * Depending on the way an anonymous folio can be mapped into a page
+	 * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped
+	 * THP), PG_anon_exclusive may be set only for the head page or for
+	 * tail pages of an anonymous folio. For now, we only expect it to be
+	 * set on tail pages for PTE-mapped THP.
+	 */
+	PG_anon_exclusive = PG_mappedtodisk,
+
 	/* Filesystems */
 	PG_checked = PG_owner_priv_1,
 
@@ -176,7 +185,7 @@ enum pageflags {
 	 * Indicates that at least one subpage is hwpoisoned in the
 	 * THP.
 	 */
-	PG_has_hwpoisoned = PG_mappedtodisk,
+	PG_has_hwpoisoned = PG_error,
 #endif
 
 	/* non-lru isolated movable page */
@@ -1002,6 +1011,34 @@ extern bool is_free_buddy_page(struct page *page);
 
 PAGEFLAG(Isolated, isolated, PF_ANY);
 
+static __always_inline int PageAnonExclusive(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
+	VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
+	return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+}
+
+static __always_inline void SetPageAnonExclusive(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page);
+	VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
+	set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+}
+
+static __always_inline void ClearPageAnonExclusive(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page);
+	VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
+	clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+}
+
+static __always_inline void __ClearPageAnonExclusive(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
+	VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
+	__clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+}
+
 #ifdef CONFIG_MMU
 #define __PG_MLOCKED		(1UL << PG_mlocked)
 #else
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7a6052a984e9..03cbb75bcb54 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1677,6 +1677,8 @@ void free_huge_page(struct page *page)
 	VM_BUG_ON_PAGE(page_mapcount(page), page);
 
 	hugetlb_set_page_subpool(page, NULL);
+	if (PageAnon(page))
+		__ClearPageAnonExclusive(page);
 	page->mapping = NULL;
 	restore_reserve = HPageRestoreReserve(page);
 	ClearHPageRestoreReserve(page);
diff --git a/mm/memory.c b/mm/memory.c
index d4dba178e130..0b0727758c86 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3667,6 +3667,17 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		goto out_nomap;
 	}
 
+	/*
+	 * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte
+	 * must never point at an anonymous page in the swapcache that is
+	 * PG_anon_exclusive. Sanity check that this holds and especially, that
+	 * no filesystem set PG_mappedtodisk on a page in the swapcache. Sanity
+	 * check after taking the PT lock and making sure that nobody
+	 * concurrently faulted in this page and set PG_anon_exclusive.
+	 */
+	BUG_ON(!PageAnon(page) && PageMappedToDisk(page));
+	BUG_ON(PageAnon(page) && PageAnonExclusive(page));
+
 	/*
 	 * Remove the swap entry and conditionally try to free up the swapcache.
 	 * We're already holding a reference on the page but haven't mapped it
diff --git a/mm/memremap.c b/mm/memremap.c
index c33bcd0398c9..2b92e97cb25b 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -459,6 +459,15 @@ void free_zone_device_page(struct page *page)
 
 	mem_cgroup_uncharge(page_folio(page));
 
+	/*
+	 * Note: we don't expect anonymous compound pages yet. Once supported
+	 * and we could PTE-map them similar to THP, we'd have to clear
+	 * PG_anon_exclusive on all tail pages.
+	 */
+	VM_BUG_ON_PAGE(PageAnon(page) && PageCompound(page), page);
+	if (PageAnon(page))
+		__ClearPageAnonExclusive(page);
+
 	/*
 	 * When a device managed page is freed, the page->mapping field
 	 * may still contain a (stale) mapping value. For example, the
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0ad7ed7ded21..a7847324d476 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1796,6 +1796,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		goto out;
 	}
 
+	/* See do_swap_page() */
+	BUG_ON(!PageAnon(page) && PageMappedToDisk(page));
+	BUG_ON(PageAnon(page) && PageAnonExclusive(page));
+
 	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 	get_page(page);
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index b1ed76d9a979..381dcc00cb62 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -80,9 +80,10 @@
 #define KPF_SOFTDIRTY		40
 #define KPF_ARCH_2		41
 
-/* [48-] take some arbitrary free slots for expanding overloaded flags
+/* [47-] take some arbitrary free slots for expanding overloaded flags
  * not part of kernel API
  */
+#define KPF_ANON_EXCLUSIVE	47
 #define KPF_READAHEAD		48
 #define KPF_SLOB_FREE		49
 #define KPF_SLUB_FROZEN		50
@@ -138,6 +139,7 @@ static const char * const page_flag_names[] = {
 	[KPF_SOFTDIRTY]		= "f:softdirty",
 	[KPF_ARCH_2]		= "H:arch_2",
 
+	[KPF_ANON_EXCLUSIVE]	= "d:anon_exclusive",
 	[KPF_READAHEAD]		= "I:readahead",
 	[KPF_SLOB_FREE]		= "P:slob_free",
 	[KPF_SLUB_FROZEN]	= "A:slub_frozen",
@@ -472,6 +474,10 @@ static int bit_mask_ok(uint64_t flags)
 
 static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
 {
+	/* Anonymous pages overload PG_mappedtodisk */
+	if ((flags & BIT(ANON)) && (flags & BIT(MAPPEDTODISK)))
+		flags ^= BIT(MAPPEDTODISK) | BIT(ANON_EXCLUSIVE);
+
 	/* SLOB/SLUB overload several page flags */
 	if (flags & BIT(SLAB)) {
 		if (flags & BIT(PRIVATE))
-- 
cgit v1.2.3


From 6c287605fd56466e645693eff3ae7c08fba56e0a Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:44 -0700
Subject: mm: remember exclusively mapped anonymous pages with
 PG_anon_exclusive

Let's mark exclusively mapped anonymous pages with PG_anon_exclusive as
exclusive, and use that information to make GUP pins reliable and stay
consistent with the page mapped into the page table even if the page table
entry gets write-protected.

With that information at hand, we can extend our COW logic to always reuse
anonymous pages that are exclusive.  For anonymous pages that might be
shared, the existing logic applies.

As already documented, PG_anon_exclusive is usually only expressive in
combination with a page table entry.  Especially PTE vs.  PMD-mapped
anonymous pages require more thought, some examples: due to mremap() we
can easily have a single compound page PTE-mapped into multiple page
tables exclusively in a single process -- multiple page table locks apply.
Further, due to MADV_WIPEONFORK we might not necessarily write-protect
all PTEs, and only some subpages might be pinned.  Long story short: once
PTE-mapped, we have to track information about exclusivity per sub-page,
but until then, we can just track it for the compound page in the head
page and not having to update a whole bunch of subpages all of the time
for a simple PMD mapping of a THP.

For simplicity, this commit mostly talks about "anonymous pages", while
it's for THP actually "the part of an anonymous folio referenced via a
page table entry".

To not spill PG_anon_exclusive code all over the mm code-base, we let the
anon rmap code to handle all PG_anon_exclusive logic it can easily handle.

If a writable, present page table entry points at an anonymous (sub)page,
that (sub)page must be PG_anon_exclusive.  If GUP wants to take a reliably
pin (FOLL_PIN) on an anonymous page references via a present page table
entry, it must only pin if PG_anon_exclusive is set for the mapped
(sub)page.

This commit doesn't adjust GUP, so this is only implicitly handled for
FOLL_WRITE, follow-up commits will teach GUP to also respect it for
FOLL_PIN without FOLL_WRITE, to make all GUP pins of anonymous pages fully
reliable.

Whenever an anonymous page is to be shared (fork(), KSM), or when
temporarily unmapping an anonymous page (swap, migration), the relevant
PG_anon_exclusive bit has to be cleared to mark the anonymous page
possibly shared.  Clearing will fail if there are GUP pins on the page:

* For fork(), this means having to copy the page and not being able to
  share it.  fork() protects against concurrent GUP using the PT lock and
  the src_mm->write_protect_seq.

* For KSM, this means sharing will fail.  For swap this means, unmapping
  will fail, For migration this means, migration will fail early.  All
  three cases protect against concurrent GUP using the PT lock and a
  proper clear/invalidate+flush of the relevant page table entry.

This fixes memory corruptions reported for FOLL_PIN | FOLL_WRITE, when a
pinned page gets mapped R/O and the successive write fault ends up
replacing the page instead of reusing it.  It improves the situation for
O_DIRECT/vmsplice/...  that still use FOLL_GET instead of FOLL_PIN, if
fork() is *not* involved, however swapout and fork() are still
problematic.  Properly using FOLL_PIN instead of FOLL_GET for these GUP
users will fix the issue for them.

I. Details about basic handling

I.1. Fresh anonymous pages

page_add_new_anon_rmap() and hugepage_add_new_anon_rmap() will mark the
given page exclusive via __page_set_anon_rmap(exclusive=1).  As that is
the mechanism fresh anonymous pages come into life (besides migration code
where we copy the page->mapping), all fresh anonymous pages will start out
as exclusive.

I.2. COW reuse handling of anonymous pages

When a COW handler stumbles over a (sub)page that's marked exclusive, it
simply reuses it.  Otherwise, the handler tries harder under page lock to
detect if the (sub)page is exclusive and can be reused.  If exclusive,
page_move_anon_rmap() will mark the given (sub)page exclusive.

Note that hugetlb code does not yet check for PageAnonExclusive(), as it
still uses the old COW logic that is prone to the COW security issue
because hugetlb code cannot really tolerate unnecessary/wrong COW as huge
pages are a scarce resource.

I.3. Migration handling

try_to_migrate() has to try marking an exclusive anonymous page shared via
page_try_share_anon_rmap().  If it fails because there are GUP pins on the
page, unmap fails.  migrate_vma_collect_pmd() and
__split_huge_pmd_locked() are handled similarly.

Writable migration entries implicitly point at shared anonymous pages.
For readable migration entries that information is stored via a new
"readable-exclusive" migration entry, specific to anonymous pages.

When restoring a migration entry in remove_migration_pte(), information
about exlusivity is detected via the migration entry type, and
RMAP_EXCLUSIVE is set accordingly for
page_add_anon_rmap()/hugepage_add_anon_rmap() to restore that information.

I.4. Swapout handling

try_to_unmap() has to try marking the mapped page possibly shared via
page_try_share_anon_rmap().  If it fails because there are GUP pins on the
page, unmap fails.  For now, information about exclusivity is lost.  In
the future, we might want to remember that information in the swap entry
in some cases, however, it requires more thought, care, and a way to store
that information in swap entries.

I.5. Swapin handling

do_swap_page() will never stumble over exclusive anonymous pages in the
swap cache, as try_to_migrate() prohibits that.  do_swap_page() always has
to detect manually if an anonymous page is exclusive and has to set
RMAP_EXCLUSIVE for page_add_anon_rmap() accordingly.

I.6. THP handling

__split_huge_pmd_locked() has to move the information about exclusivity
from the PMD to the PTEs.

a) In case we have a readable-exclusive PMD migration entry, simply
   insert readable-exclusive PTE migration entries.

b) In case we have a present PMD entry and we don't want to freeze
   ("convert to migration entries"), simply forward PG_anon_exclusive to
   all sub-pages, no need to temporarily clear the bit.

c) In case we have a present PMD entry and want to freeze, handle it
   similar to try_to_migrate(): try marking the page shared first.  In
   case we fail, we ignore the "freeze" instruction and simply split
   ordinarily.  try_to_migrate() will properly fail because the THP is
   still mapped via PTEs.

When splitting a compound anonymous folio (THP), the information about
exclusivity is implicitly handled via the migration entries: no need to
replicate PG_anon_exclusive manually.

I.7.  fork() handling fork() handling is relatively easy, because
PG_anon_exclusive is only expressive for some page table entry types.

a) Present anonymous pages

page_try_dup_anon_rmap() will mark the given subpage shared -- which will
fail if the page is pinned.  If it failed, we have to copy (or PTE-map a
PMD to handle it on the PTE level).

Note that device exclusive entries are just a pointer at a PageAnon()
page.  fork() will first convert a device exclusive entry to a present
page table and handle it just like present anonymous pages.

b) Device private entry

Device private entries point at PageAnon() pages that cannot be mapped
directly and, therefore, cannot get pinned.

page_try_dup_anon_rmap() will mark the given subpage shared, which cannot
fail because they cannot get pinned.

c) HW poison entries

PG_anon_exclusive will remain untouched and is stale -- the page table
entry is just a placeholder after all.

d) Migration entries

Writable and readable-exclusive entries are converted to readable entries:
possibly shared.

I.8. mprotect() handling

mprotect() only has to properly handle the new readable-exclusive
migration entry:

When write-protecting a migration entry that points at an anonymous page,
remember the information about exclusivity via the "readable-exclusive"
migration entry type.

II. Migration and GUP-fast

Whenever replacing a present page table entry that maps an exclusive
anonymous page by a migration entry, we have to mark the page possibly
shared and synchronize against GUP-fast by a proper clear/invalidate+flush
to make the following scenario impossible:

1. try_to_migrate() places a migration entry after checking for GUP pins
   and marks the page possibly shared.

2. GUP-fast pins the page due to lack of synchronization

3. fork() converts the "writable/readable-exclusive" migration entry into a
   readable migration entry

4. Migration fails due to the GUP pin (failing to freeze the refcount)

5. Migration entries are restored. PG_anon_exclusive is lost

-> We have a pinned page that is not marked exclusive anymore.

Note that we move information about exclusivity from the page to the
migration entry as it otherwise highly overcomplicates fork() and
PTE-mapping a THP.

III. Swapout and GUP-fast

Whenever replacing a present page table entry that maps an exclusive
anonymous page by a swap entry, we have to mark the page possibly shared
and synchronize against GUP-fast by a proper clear/invalidate+flush to
make the following scenario impossible:

1. try_to_unmap() places a swap entry after checking for GUP pins and
   clears exclusivity information on the page.

2. GUP-fast pins the page due to lack of synchronization.

-> We have a pinned page that is not marked exclusive anymore.

If we'd ever store information about exclusivity in the swap entry,
similar to migration handling, the same considerations as in II would
apply.  This is future work.

Link: https://lkml.kernel.org/r/20220428083441.37290-13-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h    | 40 +++++++++++++++++++++++++
 include/linux/swap.h    | 15 +++++++---
 include/linux/swapops.h | 25 ++++++++++++++++
 mm/huge_memory.c        | 78 ++++++++++++++++++++++++++++++++++++++++++++-----
 mm/hugetlb.c            | 15 +++++++---
 mm/ksm.c                | 13 ++++++++-
 mm/memory.c             | 33 ++++++++++++++++-----
 mm/migrate.c            | 14 +++++++--
 mm/migrate_device.c     | 21 ++++++++++++-
 mm/mprotect.c           |  8 +++--
 mm/rmap.c               | 61 ++++++++++++++++++++++++++++++++++----
 11 files changed, 289 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index e4156921eea9..cbe279a6f0de 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -228,6 +228,13 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
 {
 	VM_BUG_ON_PAGE(!PageAnon(page), page);
 
+	/*
+	 * No need to check+clear for already shared pages, including KSM
+	 * pages.
+	 */
+	if (!PageAnonExclusive(page))
+		goto dup;
+
 	/*
 	 * If this page may have been pinned by the parent process,
 	 * don't allow to duplicate the mapping but instead require to e.g.,
@@ -239,14 +246,47 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
 	    unlikely(page_needs_cow_for_dma(vma, page))))
 		return -EBUSY;
 
+	ClearPageAnonExclusive(page);
 	/*
 	 * It's okay to share the anon page between both processes, mapping
 	 * the page R/O into both processes.
 	 */
+dup:
 	__page_dup_rmap(page, compound);
 	return 0;
 }
 
+/**
+ * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly
+ *			      shared to prepare for KSM or temporary unmapping
+ * @page: the exclusive anonymous page to try marking possibly shared
+ *
+ * The caller needs to hold the PT lock and has to have the page table entry
+ * cleared/invalidated+flushed, to properly sync against GUP-fast.
+ *
+ * This is similar to page_try_dup_anon_rmap(), however, not used during fork()
+ * to duplicate a mapping, but instead to prepare for KSM or temporarily
+ * unmapping a page (swap, migration) via page_remove_rmap().
+ *
+ * Marking the page shared can only fail if the page may be pinned; device
+ * private pages cannot get pinned and consequently this function cannot fail.
+ *
+ * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY
+ * otherwise.
+ */
+static inline int page_try_share_anon_rmap(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page);
+
+	/* See page_try_dup_anon_rmap(). */
+	if (likely(!is_device_private_page(page) &&
+	    unlikely(page_maybe_dma_pinned(page))))
+		return -EBUSY;
+
+	ClearPageAnonExclusive(page);
+	return 0;
+}
+
 /*
  * Called from mm/vmscan.c to handle paging out
  */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 27093b477c5f..e6d70a4156e8 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -78,12 +78,19 @@ static inline int current_is_kswapd(void)
 #endif
 
 /*
- * NUMA node memory migration support
+ * Page migration support.
+ *
+ * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and
+ * indicates that the referenced (part of) an anonymous page is exclusive to
+ * a single process. For SWP_MIGRATION_WRITE, that information is implicit:
+ * (part of) an anonymous page that are mapped writable are exclusive to a
+ * single process.
  */
 #ifdef CONFIG_MIGRATION
-#define SWP_MIGRATION_NUM 2
-#define SWP_MIGRATION_READ	(MAX_SWAPFILES + SWP_HWPOISON_NUM)
-#define SWP_MIGRATION_WRITE	(MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
+#define SWP_MIGRATION_NUM 3
+#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM)
+#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
+#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2)
 #else
 #define SWP_MIGRATION_NUM 0
 #endif
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 5af852b68805..6648b97244e7 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -194,6 +194,7 @@ static inline bool is_writable_device_exclusive_entry(swp_entry_t entry)
 static inline int is_migration_entry(swp_entry_t entry)
 {
 	return unlikely(swp_type(entry) == SWP_MIGRATION_READ ||
+			swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE ||
 			swp_type(entry) == SWP_MIGRATION_WRITE);
 }
 
@@ -202,11 +203,26 @@ static inline int is_writable_migration_entry(swp_entry_t entry)
 	return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE);
 }
 
+static inline int is_readable_migration_entry(swp_entry_t entry)
+{
+	return unlikely(swp_type(entry) == SWP_MIGRATION_READ);
+}
+
+static inline int is_readable_exclusive_migration_entry(swp_entry_t entry)
+{
+	return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE);
+}
+
 static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
 {
 	return swp_entry(SWP_MIGRATION_READ, offset);
 }
 
+static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset)
+{
+	return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset);
+}
+
 static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
 {
 	return swp_entry(SWP_MIGRATION_WRITE, offset);
@@ -224,6 +240,11 @@ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
 	return swp_entry(0, 0);
 }
 
+static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset)
+{
+	return swp_entry(0, 0);
+}
+
 static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
 {
 	return swp_entry(0, 0);
@@ -244,6 +265,10 @@ static inline int is_writable_migration_entry(swp_entry_t entry)
 {
 	return 0;
 }
+static inline int is_readable_migration_entry(swp_entry_t entry)
+{
+	return 0;
+}
 
 #endif
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cb5bcd833d9e..231911b7bf9d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1054,7 +1054,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		swp_entry_t entry = pmd_to_swp_entry(pmd);
 
 		VM_BUG_ON(!is_pmd_migration_entry(pmd));
-		if (is_writable_migration_entry(entry)) {
+		if (!is_readable_migration_entry(entry)) {
 			entry = make_readable_migration_entry(
 							swp_offset(entry));
 			pmd = swp_entry_to_pmd(entry);
@@ -1292,6 +1292,10 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 	page = pmd_page(orig_pmd);
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
+	/* Early check when only holding the PT lock. */
+	if (PageAnonExclusive(page))
+		goto reuse;
+
 	if (!trylock_page(page)) {
 		get_page(page);
 		spin_unlock(vmf->ptl);
@@ -1306,6 +1310,12 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 		put_page(page);
 	}
 
+	/* Recheck after temporarily dropping the PT lock. */
+	if (PageAnonExclusive(page)) {
+		unlock_page(page);
+		goto reuse;
+	}
+
 	/*
 	 * See do_wp_page(): we can only map the page writable if there are
 	 * no additional references. Note that we always drain the LRU
@@ -1319,11 +1329,12 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 		pmd_t entry;
 
 		page_move_anon_rmap(page, vma);
+		unlock_page(page);
+reuse:
 		entry = pmd_mkyoung(orig_pmd);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1))
 			update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
-		unlock_page(page);
 		spin_unlock(vmf->ptl);
 		return VM_FAULT_WRITE;
 	}
@@ -1708,6 +1719,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 	if (is_swap_pmd(*pmd)) {
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
+		struct page *page = pfn_swap_entry_to_page(entry);
 
 		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
 		if (is_writable_migration_entry(entry)) {
@@ -1716,8 +1728,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			 * A protection check is difficult so
 			 * just be safe and disable write
 			 */
-			entry = make_readable_migration_entry(
-							swp_offset(entry));
+			if (PageAnon(page))
+				entry = make_readable_exclusive_migration_entry(swp_offset(entry));
+			else
+				entry = make_readable_migration_entry(swp_offset(entry));
 			newpmd = swp_entry_to_pmd(entry);
 			if (pmd_swp_soft_dirty(*pmd))
 				newpmd = pmd_swp_mksoft_dirty(newpmd);
@@ -1937,6 +1951,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pgtable_t pgtable;
 	pmd_t old_pmd, _pmd;
 	bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false;
+	bool anon_exclusive = false;
 	unsigned long addr;
 	int i;
 
@@ -2018,6 +2033,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		entry = pmd_to_swp_entry(old_pmd);
 		page = pfn_swap_entry_to_page(entry);
 		write = is_writable_migration_entry(entry);
+		if (PageAnon(page))
+			anon_exclusive = is_readable_exclusive_migration_entry(entry);
 		young = false;
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);
 		uffd_wp = pmd_swp_uffd_wp(old_pmd);
@@ -2029,8 +2046,26 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		young = pmd_young(old_pmd);
 		soft_dirty = pmd_soft_dirty(old_pmd);
 		uffd_wp = pmd_uffd_wp(old_pmd);
+
 		VM_BUG_ON_PAGE(!page_count(page), page);
 		page_ref_add(page, HPAGE_PMD_NR - 1);
+
+		/*
+		 * Without "freeze", we'll simply split the PMD, propagating the
+		 * PageAnonExclusive() flag for each PTE by setting it for
+		 * each subpage -- no need to (temporarily) clear.
+		 *
+		 * With "freeze" we want to replace mapped pages by
+		 * migration entries right away. This is only possible if we
+		 * managed to clear PageAnonExclusive() -- see
+		 * set_pmd_migration_entry().
+		 *
+		 * In case we cannot clear PageAnonExclusive(), split the PMD
+		 * only and let try_to_migrate_one() fail later.
+		 */
+		anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
+		if (freeze && anon_exclusive && page_try_share_anon_rmap(page))
+			freeze = false;
 	}
 
 	/*
@@ -2052,6 +2087,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			if (write)
 				swp_entry = make_writable_migration_entry(
 							page_to_pfn(page + i));
+			else if (anon_exclusive)
+				swp_entry = make_readable_exclusive_migration_entry(
+							page_to_pfn(page + i));
 			else
 				swp_entry = make_readable_migration_entry(
 							page_to_pfn(page + i));
@@ -2063,6 +2101,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		} else {
 			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
 			entry = maybe_mkwrite(entry, vma);
+			if (anon_exclusive)
+				SetPageAnonExclusive(page + i);
 			if (!write)
 				entry = pte_wrprotect(entry);
 			if (!young)
@@ -2294,6 +2334,13 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	 *
 	 * After successful get_page_unless_zero() might follow flags change,
 	 * for example lock_page() which set PG_waiters.
+	 *
+	 * Note that for mapped sub-pages of an anonymous THP,
+	 * PG_anon_exclusive has been cleared in unmap_page() and is stored in
+	 * the migration entry instead from where remap_page() will restore it.
+	 * We can still have PG_anon_exclusive set on effectively unmapped and
+	 * unreferenced sub-pages of an anonymous THP: we can simply drop
+	 * PG_anon_exclusive (-> PG_mappedtodisk) for these here.
 	 */
 	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	page_tail->flags |= (head->flags &
@@ -3025,6 +3072,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	struct vm_area_struct *vma = pvmw->vma;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address = pvmw->address;
+	bool anon_exclusive;
 	pmd_t pmdval;
 	swp_entry_t entry;
 	pmd_t pmdswp;
@@ -3034,10 +3082,19 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 
 	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
 	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
+
+	anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
+	if (anon_exclusive && page_try_share_anon_rmap(page)) {
+		set_pmd_at(mm, address, pvmw->pmd, pmdval);
+		return;
+	}
+
 	if (pmd_dirty(pmdval))
 		set_page_dirty(page);
 	if (pmd_write(pmdval))
 		entry = make_writable_migration_entry(page_to_pfn(page));
+	else if (anon_exclusive)
+		entry = make_readable_exclusive_migration_entry(page_to_pfn(page));
 	else
 		entry = make_readable_migration_entry(page_to_pfn(page));
 	pmdswp = swp_entry_to_pmd(entry);
@@ -3071,10 +3128,17 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	if (pmd_swp_uffd_wp(*pvmw->pmd))
 		pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde));
 
-	if (PageAnon(new))
-		page_add_anon_rmap(new, vma, mmun_start, RMAP_COMPOUND);
-	else
+	if (PageAnon(new)) {
+		rmap_t rmap_flags = RMAP_COMPOUND;
+
+		if (!is_readable_migration_entry(entry))
+			rmap_flags |= RMAP_EXCLUSIVE;
+
+		page_add_anon_rmap(new, vma, mmun_start, rmap_flags);
+	} else {
 		page_add_file_rmap(new, vma, true);
+	}
+	VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new));
 	set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
 
 	/* No need to invalidate - it was non-present before */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 03cbb75bcb54..c0012b4a8eec 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4790,7 +4790,7 @@ again:
 				    is_hugetlb_entry_hwpoisoned(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
 
-			if (is_writable_migration_entry(swp_entry) && cow) {
+			if (!is_readable_migration_entry(swp_entry) && cow) {
 				/*
 				 * COW mappings require pages in both
 				 * parent and child to be set to read.
@@ -5190,6 +5190,8 @@ retry_avoidcopy:
 		set_huge_ptep_writable(vma, haddr, ptep);
 		return 0;
 	}
+	VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page),
+		       old_page);
 
 	/*
 	 * If the process that created a MAP_PRIVATE mapping is about to
@@ -6187,12 +6189,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 		if (unlikely(is_hugetlb_entry_migration(pte))) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
+			struct page *page = pfn_swap_entry_to_page(entry);
 
-			if (is_writable_migration_entry(entry)) {
+			if (!is_readable_migration_entry(entry)) {
 				pte_t newpte;
 
-				entry = make_readable_migration_entry(
-							swp_offset(entry));
+				if (PageAnon(page))
+					entry = make_readable_exclusive_migration_entry(
+								swp_offset(entry));
+				else
+					entry = make_readable_migration_entry(
+								swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				set_huge_swap_pte_at(mm, address, ptep,
 						     newpte, huge_page_size(h));
diff --git a/mm/ksm.c b/mm/ksm.c
index 2b6692a7df6a..38360285497a 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -872,6 +872,7 @@ static inline struct stable_node *page_stable_node(struct page *page)
 static inline void set_page_stable_node(struct page *page,
 					struct stable_node *stable_node)
 {
+	VM_BUG_ON_PAGE(PageAnon(page) && PageAnonExclusive(page), page);
 	page->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM);
 }
 
@@ -1044,6 +1045,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 	int swapped;
 	int err = -EFAULT;
 	struct mmu_notifier_range range;
+	bool anon_exclusive;
 
 	pvmw.address = page_address_in_vma(page, vma);
 	if (pvmw.address == -EFAULT)
@@ -1061,9 +1063,10 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 	if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?"))
 		goto out_unlock;
 
+	anon_exclusive = PageAnonExclusive(page);
 	if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) ||
 	    (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte)) ||
-						mm_tlb_flush_pending(mm)) {
+	    anon_exclusive || mm_tlb_flush_pending(mm)) {
 		pte_t entry;
 
 		swapped = PageSwapCache(page);
@@ -1091,6 +1094,12 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 			set_pte_at(mm, pvmw.address, pvmw.pte, entry);
 			goto out_unlock;
 		}
+
+		if (anon_exclusive && page_try_share_anon_rmap(page)) {
+			set_pte_at(mm, pvmw.address, pvmw.pte, entry);
+			goto out_unlock;
+		}
+
 		if (pte_dirty(entry))
 			set_page_dirty(page);
 
@@ -1149,6 +1158,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 		pte_unmap_unlock(ptep, ptl);
 		goto out_mn;
 	}
+	VM_BUG_ON_PAGE(PageAnonExclusive(page), page);
+	VM_BUG_ON_PAGE(PageAnon(kpage) && PageAnonExclusive(kpage), kpage);
 
 	/*
 	 * No need to check ksm_use_zero_pages here: we can only have a
diff --git a/mm/memory.c b/mm/memory.c
index 0b0727758c86..454ecc05ad85 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -720,6 +720,8 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
 	else if (is_writable_device_exclusive_entry(entry))
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 
+	VM_BUG_ON(pte_write(pte) && !(PageAnon(page) && PageAnonExclusive(page)));
+
 	/*
 	 * No need to take a page reference as one was already
 	 * created when the swap entry was made.
@@ -796,11 +798,12 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 		rss[mm_counter(page)]++;
 
-		if (is_writable_migration_entry(entry) &&
+		if (!is_readable_migration_entry(entry) &&
 				is_cow_mapping(vm_flags)) {
 			/*
-			 * COW mappings require pages in both
-			 * parent and child to be set to read.
+			 * COW mappings require pages in both parent and child
+			 * to be set to read. A previously exclusive entry is
+			 * now shared.
 			 */
 			entry = make_readable_migration_entry(
 							swp_offset(entry));
@@ -951,6 +954,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 		ptep_set_wrprotect(src_mm, addr, src_pte);
 		pte = pte_wrprotect(pte);
 	}
+	VM_BUG_ON(page && PageAnon(page) && PageAnonExclusive(page));
 
 	/*
 	 * If it's a shared mapping, mark it clean in
@@ -2949,6 +2953,9 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = vmf->page;
 	pte_t entry;
+
+	VM_BUG_ON(PageAnon(page) && !PageAnonExclusive(page));
+
 	/*
 	 * Clear the pages cpupid information as the existing
 	 * information potentially belongs to a now completely
@@ -3273,6 +3280,13 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	if (PageAnon(vmf->page)) {
 		struct page *page = vmf->page;
 
+		/*
+		 * If the page is exclusive to this process we must reuse the
+		 * page without further checks.
+		 */
+		if (PageAnonExclusive(page))
+			goto reuse;
+
 		/*
 		 * We have to verify under page lock: these early checks are
 		 * just an optimization to avoid locking the page and freeing
@@ -3305,6 +3319,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		 */
 		page_move_anon_rmap(page, vma);
 		unlock_page(page);
+reuse:
 		wp_page_reuse(vmf);
 		return VM_FAULT_WRITE;
 	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
@@ -3696,11 +3711,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	 * that are certainly not shared because we just allocated them without
 	 * exposing them to the swapcache.
 	 */
-	if ((vmf->flags & FAULT_FLAG_WRITE) && !PageKsm(page) &&
-	    (page != swapcache || page_count(page) == 1)) {
-		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
-		vmf->flags &= ~FAULT_FLAG_WRITE;
-		ret |= VM_FAULT_WRITE;
+	if (!PageKsm(page) && (page != swapcache || page_count(page) == 1)) {
+		if (vmf->flags & FAULT_FLAG_WRITE) {
+			pte = maybe_mkwrite(pte_mkdirty(pte), vma);
+			vmf->flags &= ~FAULT_FLAG_WRITE;
+			ret |= VM_FAULT_WRITE;
+		}
 		rmap_flags |= RMAP_EXCLUSIVE;
 	}
 	flush_icache_page(vma, page);
@@ -3720,6 +3736,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		page_add_anon_rmap(page, vma, vmf->address, rmap_flags);
 	}
 
+	VM_BUG_ON(!PageAnon(page) || (pte_write(pte) && !PageAnonExclusive(page)));
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 	arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 92e932f08be5..b2678279eb43 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -177,6 +177,7 @@ static bool remove_migration_pte(struct folio *folio,
 	DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION);
 
 	while (page_vma_mapped_walk(&pvmw)) {
+		rmap_t rmap_flags = RMAP_NONE;
 		pte_t pte;
 		swp_entry_t entry;
 		struct page *new;
@@ -211,6 +212,9 @@ static bool remove_migration_pte(struct folio *folio,
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
+		if (folio_test_anon(folio) && !is_readable_migration_entry(entry))
+			rmap_flags |= RMAP_EXCLUSIVE;
+
 		if (unlikely(is_device_private_page(new))) {
 			if (pte_write(pte))
 				entry = make_writable_device_private_entry(
@@ -233,7 +237,7 @@ static bool remove_migration_pte(struct folio *folio,
 			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
 			if (folio_test_anon(folio))
 				hugepage_add_anon_rmap(new, vma, pvmw.address,
-						       RMAP_NONE);
+						       rmap_flags);
 			else
 				page_dup_file_rmap(new, true);
 			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
@@ -242,7 +246,7 @@ static bool remove_migration_pte(struct folio *folio,
 		{
 			if (folio_test_anon(folio))
 				page_add_anon_rmap(new, vma, pvmw.address,
-						   RMAP_NONE);
+						   rmap_flags);
 			else
 				page_add_file_rmap(new, vma, false);
 			set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
@@ -514,6 +518,12 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
 		folio_set_workingset(newfolio);
 	if (folio_test_checked(folio))
 		folio_set_checked(newfolio);
+	/*
+	 * PG_anon_exclusive (-> PG_mappedtodisk) is always migrated via
+	 * migration entries. We can still have PG_anon_exclusive set on an
+	 * effectively unmapped and unreferenced first sub-pages of an
+	 * anonymous THP: we can simply copy it here via PG_mappedtodisk.
+	 */
 	if (folio_test_mappedtodisk(folio))
 		folio_set_mappedtodisk(newfolio);
 
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index fb6d7d5499f5..5052093d0262 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -184,15 +184,34 @@ again:
 		 * set up a special migration page table entry now.
 		 */
 		if (trylock_page(page)) {
+			bool anon_exclusive;
 			pte_t swp_pte;
 
+			anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
+			if (anon_exclusive) {
+				flush_cache_page(vma, addr, pte_pfn(*ptep));
+				ptep_clear_flush(vma, addr, ptep);
+
+				if (page_try_share_anon_rmap(page)) {
+					set_pte_at(mm, addr, ptep, pte);
+					unlock_page(page);
+					put_page(page);
+					mpfn = 0;
+					goto next;
+				}
+			} else {
+				ptep_get_and_clear(mm, addr, ptep);
+			}
+
 			migrate->cpages++;
-			ptep_get_and_clear(mm, addr, ptep);
 
 			/* Setup special migration page table entry */
 			if (mpfn & MIGRATE_PFN_WRITE)
 				entry = make_writable_migration_entry(
 							page_to_pfn(page));
+			else if (anon_exclusive)
+				entry = make_readable_exclusive_migration_entry(
+							page_to_pfn(page));
 			else
 				entry = make_readable_migration_entry(
 							page_to_pfn(page));
diff --git a/mm/mprotect.c b/mm/mprotect.c
index b69ce7a7b2b7..56060acdabd3 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -152,6 +152,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			pages++;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
+			struct page *page = pfn_swap_entry_to_page(entry);
 			pte_t newpte;
 
 			if (is_writable_migration_entry(entry)) {
@@ -159,8 +160,11 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				 * A protection check is difficult so
 				 * just be safe and disable write
 				 */
-				entry = make_readable_migration_entry(
-							swp_offset(entry));
+				if (PageAnon(page))
+					entry = make_readable_exclusive_migration_entry(
+							     swp_offset(entry));
+				else
+					entry = make_readable_migration_entry(swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_soft_dirty(oldpte))
 					newpte = pte_swp_mksoft_dirty(newpte);
diff --git a/mm/rmap.c b/mm/rmap.c
index 90f92c53476f..0d63e7ce35cc 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1088,6 +1088,7 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
 void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
+	struct page *subpage = page;
 
 	page = compound_head(page);
 
@@ -1101,6 +1102,7 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma)
 	 * folio_test_anon()) will not see one without the other.
 	 */
 	WRITE_ONCE(page->mapping, (struct address_space *) anon_vma);
+	SetPageAnonExclusive(subpage);
 }
 
 /**
@@ -1118,7 +1120,7 @@ static void __page_set_anon_rmap(struct page *page,
 	BUG_ON(!anon_vma);
 
 	if (PageAnon(page))
-		return;
+		goto out;
 
 	/*
 	 * If the page isn't exclusively mapped into this vma,
@@ -1137,6 +1139,9 @@ static void __page_set_anon_rmap(struct page *page,
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
 	WRITE_ONCE(page->mapping, (struct address_space *) anon_vma);
 	page->index = linear_page_index(vma, address);
+out:
+	if (exclusive)
+		SetPageAnonExclusive(page);
 }
 
 /**
@@ -1198,6 +1203,8 @@ void page_add_anon_rmap(struct page *page,
 	} else {
 		first = atomic_inc_and_test(&page->_mapcount);
 	}
+	VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page);
+	VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page);
 
 	if (first) {
 		int nr = compound ? thp_nr_pages(page) : 1;
@@ -1459,7 +1466,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
 	pte_t pteval;
 	struct page *subpage;
-	bool ret = true;
+	bool anon_exclusive, ret = true;
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 
@@ -1515,6 +1522,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 		subpage = folio_page(folio,
 					pte_pfn(*pvmw.pte) - folio_pfn(folio));
 		address = pvmw.address;
+		anon_exclusive = folio_test_anon(folio) &&
+				 PageAnonExclusive(subpage);
 
 		if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
 			/*
@@ -1550,9 +1559,12 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			}
 		}
 
-		/* Nuke the page table entry. */
+		/*
+		 * Nuke the page table entry. When having to clear
+		 * PageAnonExclusive(), we always have to flush.
+		 */
 		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
-		if (should_defer_flush(mm, flags)) {
+		if (should_defer_flush(mm, flags) && !anon_exclusive) {
 			/*
 			 * We clear the PTE but do not flush so potentially
 			 * a remote CPU could still be writing to the folio.
@@ -1677,6 +1689,24 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				page_vma_mapped_walk_done(&pvmw);
 				break;
 			}
+			if (anon_exclusive &&
+			    page_try_share_anon_rmap(subpage)) {
+				swap_free(entry);
+				set_pte_at(mm, address, pvmw.pte, pteval);
+				ret = false;
+				page_vma_mapped_walk_done(&pvmw);
+				break;
+			}
+			/*
+			 * Note: We *don't* remember yet if the page was mapped
+			 * exclusively in the swap entry, so swapin code has
+			 * to re-determine that manually and might detect the
+			 * page as possibly shared, for example, if there are
+			 * other references on the page or if the page is under
+			 * writeback. We made sure that there are no GUP pins
+			 * on the page that would rely on it, so for GUP pins
+			 * this is fine.
+			 */
 			if (list_empty(&mm->mmlist)) {
 				spin_lock(&mmlist_lock);
 				if (list_empty(&mm->mmlist))
@@ -1776,7 +1806,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
 	pte_t pteval;
 	struct page *subpage;
-	bool ret = true;
+	bool anon_exclusive, ret = true;
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 
@@ -1837,6 +1867,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 		subpage = folio_page(folio,
 				pte_pfn(*pvmw.pte) - folio_pfn(folio));
 		address = pvmw.address;
+		anon_exclusive = folio_test_anon(folio) &&
+				 PageAnonExclusive(subpage);
 
 		if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
 			/*
@@ -1888,6 +1920,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			swp_entry_t entry;
 			pte_t swp_pte;
 
+			if (anon_exclusive)
+				BUG_ON(page_try_share_anon_rmap(subpage));
+
 			/*
 			 * Store the pfn of the page in a special migration
 			 * pte. do_swap_page() will wait until the migration
@@ -1896,6 +1931,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			entry = pte_to_swp_entry(pteval);
 			if (is_writable_device_private_entry(entry))
 				entry = make_writable_migration_entry(pfn);
+			else if (anon_exclusive)
+				entry = make_readable_exclusive_migration_entry(pfn);
 			else
 				entry = make_readable_migration_entry(pfn);
 			swp_pte = swp_entry_to_pte(entry);
@@ -1960,6 +1997,15 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				page_vma_mapped_walk_done(&pvmw);
 				break;
 			}
+			VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) &&
+				       !anon_exclusive, subpage);
+			if (anon_exclusive &&
+			    page_try_share_anon_rmap(subpage)) {
+				set_pte_at(mm, address, pvmw.pte, pteval);
+				ret = false;
+				page_vma_mapped_walk_done(&pvmw);
+				break;
+			}
 
 			/*
 			 * Store the pfn of the page in a special migration
@@ -1969,6 +2015,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			if (pte_write(pteval))
 				entry = make_writable_migration_entry(
 							page_to_pfn(subpage));
+			else if (anon_exclusive)
+				entry = make_readable_exclusive_migration_entry(
+							page_to_pfn(subpage));
 			else
 				entry = make_readable_migration_entry(
 							page_to_pfn(subpage));
@@ -2405,6 +2454,8 @@ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
 	BUG_ON(!anon_vma);
 	/* address might be in next vma when migration races vma_adjust */
 	first = atomic_inc_and_test(compound_mapcount_ptr(page));
+	VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page);
+	VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page);
 	if (first)
 		__page_set_anon_rmap(page, vma, address,
 				     !!(flags & RMAP_EXCLUSIVE));
-- 
cgit v1.2.3


From 7f5abe609b3dcbc62a36e18b1437f4f3521ecb75 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:44 -0700
Subject: mm/rmap: fail try_to_migrate() early when setting a PMD migration
 entry fails

Let's fail right away in case we cannot clear PG_anon_exclusive because
the anon THP may be pinned.  Right now, we continue trying to install
migration entries and the caller of try_to_migrate() will realize that the
page is still mapped and has to restore the migration entries.  Let's just
fail fast just like for PTE migration entries.

Link: https://lkml.kernel.org/r/20220428083441.37290-14-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swapops.h | 4 ++--
 mm/huge_memory.c        | 8 +++++---
 mm/rmap.c               | 6 +++++-
 3 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 6648b97244e7..e476a8fed537 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -299,7 +299,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry)
 struct page_vma_mapped_walk;
 
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
-extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
+extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		struct page *page);
 
 extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw,
@@ -332,7 +332,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
 	return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
 }
 #else
-static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
+static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		struct page *page)
 {
 	BUILD_BUG();
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 231911b7bf9d..14d7fa6dc793 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3066,7 +3066,7 @@ late_initcall(split_huge_pages_debugfs);
 #endif
 
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
-void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
+int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		struct page *page)
 {
 	struct vm_area_struct *vma = pvmw->vma;
@@ -3078,7 +3078,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	pmd_t pmdswp;
 
 	if (!(pvmw->pmd && !pvmw->pte))
-		return;
+		return 0;
 
 	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
 	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
@@ -3086,7 +3086,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
 	if (anon_exclusive && page_try_share_anon_rmap(page)) {
 		set_pmd_at(mm, address, pvmw->pmd, pmdval);
-		return;
+		return -EBUSY;
 	}
 
 	if (pmd_dirty(pmdval))
@@ -3104,6 +3104,8 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	page_remove_rmap(page, vma, true);
 	put_page(page);
 	trace_set_migration_pmd(address, pmd_val(pmdswp));
+
+	return 0;
 }
 
 void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
diff --git a/mm/rmap.c b/mm/rmap.c
index 0d63e7ce35cc..f96cc7eb23ec 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1856,7 +1856,11 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
 					!folio_test_pmd_mappable(folio), folio);
 
-			set_pmd_migration_entry(&pvmw, subpage);
+			if (set_pmd_migration_entry(&pvmw, subpage)) {
+				ret = false;
+				page_vma_mapped_walk_done(&pvmw);
+				break;
+			}
 			continue;
 		}
 #endif
-- 
cgit v1.2.3


From c89357e27f20dda3fff6791d27bb6c91eae99f4a Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:45 -0700
Subject: mm: support GUP-triggered unsharing of anonymous pages

Whenever GUP currently ends up taking a R/O pin on an anonymous page that
might be shared -- mapped R/O and !PageAnonExclusive() -- any write fault
on the page table entry will end up replacing the mapped anonymous page
due to COW, resulting in the GUP pin no longer being consistent with the
page actually mapped into the page table.

The possible ways to deal with this situation are:
 (1) Ignore and pin -- what we do right now.
 (2) Fail to pin -- which would be rather surprising to callers and
     could break user space.
 (3) Trigger unsharing and pin the now exclusive page -- reliable R/O
     pins.

We want to implement 3) because it provides the clearest semantics and
allows for checking in unpin_user_pages() and friends for possible BUGs:
when trying to unpin a page that's no longer exclusive, clearly something
went very wrong and might result in memory corruptions that might be hard
to debug.  So we better have a nice way to spot such issues.

To implement 3), we need a way for GUP to trigger unsharing:
FAULT_FLAG_UNSHARE.  FAULT_FLAG_UNSHARE is only applicable to R/O mapped
anonymous pages and resembles COW logic during a write fault.  However, in
contrast to a write fault, GUP-triggered unsharing will, for example,
still maintain the write protection.

Let's implement FAULT_FLAG_UNSHARE by hooking into the existing write
fault handlers for all applicable anonymous page types: ordinary pages,
THP and hugetlb.

* If FAULT_FLAG_UNSHARE finds a R/O-mapped anonymous page that has been
  marked exclusive in the meantime by someone else, there is nothing to do.
* If FAULT_FLAG_UNSHARE finds a R/O-mapped anonymous page that's not
  marked exclusive, it will try detecting if the process is the exclusive
  owner. If exclusive, it can be set exclusive similar to reuse logic
  during write faults via page_move_anon_rmap() and there is nothing
  else to do; otherwise, we either have to copy and map a fresh,
  anonymous exclusive page R/O (ordinary pages, hugetlb), or split the
  THP.

This commit is heavily based on patches by Andrea.

Link: https://lkml.kernel.org/r/20220428083441.37290-16-david@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Co-developed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm_types.h |   8 ++++
 mm/huge_memory.c         |  10 ++++-
 mm/hugetlb.c             |  56 +++++++++++++++----------
 mm/memory.c              | 107 ++++++++++++++++++++++++++++++++---------------
 4 files changed, 126 insertions(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 87eddd509de2..7216d77a5884 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -819,6 +819,9 @@ typedef struct {
  * @FAULT_FLAG_REMOTE: The fault is not for current task/mm.
  * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch.
  * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals.
+ * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark
+ *                      exclusive) a possibly shared anonymous page that is
+ *                      mapped R/O.
  *
  * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
  * whether we would allow page faults to retry by specifying these two
@@ -838,6 +841,10 @@ typedef struct {
  * continuous faults with flags (b).  We should always try to detect pending
  * signals before a retry to make sure the continuous page faults can still be
  * interrupted if necessary.
+ *
+ * The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal.
+ * FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when
+ * no existing R/O-mapped anonymous page is encountered.
  */
 enum fault_flag {
 	FAULT_FLAG_WRITE =		1 << 0,
@@ -850,6 +857,7 @@ enum fault_flag {
 	FAULT_FLAG_REMOTE =		1 << 7,
 	FAULT_FLAG_INSTRUCTION =	1 << 8,
 	FAULT_FLAG_INTERRUPTIBLE =	1 << 9,
+	FAULT_FLAG_UNSHARE =		1 << 10,
 };
 
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 14d7fa6dc793..17ec6c939e7f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1271,6 +1271,7 @@ unlock:
 
 vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 {
+	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
 	struct vm_area_struct *vma = vmf->vma;
 	struct page *page;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
@@ -1279,6 +1280,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 	vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
 	VM_BUG_ON_VMA(!vma->anon_vma, vma);
 
+	VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE));
+	VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE));
+
 	if (is_huge_zero_pmd(orig_pmd))
 		goto fallback;
 
@@ -1317,7 +1321,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 	}
 
 	/*
-	 * See do_wp_page(): we can only map the page writable if there are
+	 * See do_wp_page(): we can only reuse the page exclusively if there are
 	 * no additional references. Note that we always drain the LRU
 	 * pagevecs immediately after adding a THP.
 	 */
@@ -1331,6 +1335,10 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 		page_move_anon_rmap(page, vma);
 		unlock_page(page);
 reuse:
+		if (unlikely(unshare)) {
+			spin_unlock(vmf->ptl);
+			return 0;
+		}
 		entry = pmd_mkyoung(orig_pmd);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1))
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e0308a44ba16..9cefa3dd9af3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5162,15 +5162,16 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /*
- * Hugetlb_cow() should be called with page lock of the original hugepage held.
+ * hugetlb_wp() should be called with page lock of the original hugepage held.
  * Called with hugetlb_fault_mutex_table held and pte_page locked so we
  * cannot race with other handlers or page migration.
  * Keep the pte_same checks anyway to make transition from the mutex easier.
  */
-static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
-		       unsigned long address, pte_t *ptep,
+static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
+		       unsigned long address, pte_t *ptep, unsigned int flags,
 		       struct page *pagecache_page, spinlock_t *ptl)
 {
+	const bool unshare = flags & FAULT_FLAG_UNSHARE;
 	pte_t pte;
 	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
@@ -5179,15 +5180,22 @@ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long haddr = address & huge_page_mask(h);
 	struct mmu_notifier_range range;
 
+	VM_BUG_ON(unshare && (flags & FOLL_WRITE));
+	VM_BUG_ON(!unshare && !(flags & FOLL_WRITE));
+
 	pte = huge_ptep_get(ptep);
 	old_page = pte_page(pte);
 
 retry_avoidcopy:
-	/* If no-one else is actually using this page, avoid the copy
-	 * and just make the page writable */
+	/*
+	 * If no-one else is actually using this page, we're the exclusive
+	 * owner and can reuse this page.
+	 */
 	if (page_mapcount(old_page) == 1 && PageAnon(old_page)) {
-		page_move_anon_rmap(old_page, vma);
-		set_huge_ptep_writable(vma, haddr, ptep);
+		if (!PageAnonExclusive(old_page))
+			page_move_anon_rmap(old_page, vma);
+		if (likely(!unshare))
+			set_huge_ptep_writable(vma, haddr, ptep);
 		return 0;
 	}
 	VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page),
@@ -5290,13 +5298,13 @@ retry_avoidcopy:
 	if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) {
 		ClearHPageRestoreReserve(new_page);
 
-		/* Break COW */
+		/* Break COW or unshare */
 		huge_ptep_clear_flush(vma, haddr, ptep);
 		mmu_notifier_invalidate_range(mm, range.start, range.end);
 		page_remove_rmap(old_page, vma, true);
 		hugepage_add_new_anon_rmap(new_page, vma, haddr);
 		set_huge_pte_at(mm, haddr, ptep,
-				make_huge_pte(vma, new_page, 1));
+				make_huge_pte(vma, new_page, !unshare));
 		SetHPageMigratable(new_page);
 		/* Make the old page be freed below */
 		new_page = old_page;
@@ -5304,7 +5312,10 @@ retry_avoidcopy:
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(&range);
 out_release_all:
-	/* No restore in case of successful pagetable update (Break COW) */
+	/*
+	 * No restore in case of successful pagetable update (Break COW or
+	 * unshare)
+	 */
 	if (new_page != old_page)
 		restore_reserve_on_error(h, vma, haddr, new_page);
 	put_page(new_page);
@@ -5429,7 +5440,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	/*
 	 * Currently, we are forced to kill the process in the event the
 	 * original mapper has unmapped pages from the child due to a failed
-	 * COW. Warn that such a situation has occurred as it may not be obvious
+	 * COW/unsharing. Warn that such a situation has occurred as it may not
+	 * be obvious.
 	 */
 	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
 		pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n",
@@ -5555,7 +5567,7 @@ retry:
 	hugetlb_count_add(pages_per_huge_page(h), mm);
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_cow(mm, vma, address, ptep, page, ptl);
+		ret = hugetlb_wp(mm, vma, address, ptep, flags, page, ptl);
 	}
 
 	spin_unlock(ptl);
@@ -5685,14 +5697,15 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_mutex;
 
 	/*
-	 * If we are going to COW the mapping later, we examine the pending
-	 * reservations for this page now. This will ensure that any
+	 * If we are going to COW/unshare the mapping later, we examine the
+	 * pending reservations for this page now. This will ensure that any
 	 * allocations necessary to record that reservation occur outside the
 	 * spinlock. For private mappings, we also lookup the pagecache
 	 * page now as it is used to determine if a reservation has been
 	 * consumed.
 	 */
-	if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) {
+	if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
+	    !huge_pte_write(entry)) {
 		if (vma_needs_reservation(h, vma, haddr) < 0) {
 			ret = VM_FAULT_OOM;
 			goto out_mutex;
@@ -5707,12 +5720,12 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	ptl = huge_pte_lock(h, mm, ptep);
 
-	/* Check for a racing update before calling hugetlb_cow */
+	/* Check for a racing update before calling hugetlb_wp() */
 	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
 		goto out_ptl;
 
 	/*
-	 * hugetlb_cow() requires page locks of pte_page(entry) and
+	 * hugetlb_wp() requires page locks of pte_page(entry) and
 	 * pagecache_page, so here we need take the former one
 	 * when page != pagecache_page or !pagecache_page.
 	 */
@@ -5725,13 +5738,14 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	get_page(page);
 
-	if (flags & FAULT_FLAG_WRITE) {
+	if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) {
 		if (!huge_pte_write(entry)) {
-			ret = hugetlb_cow(mm, vma, address, ptep,
-					  pagecache_page, ptl);
+			ret = hugetlb_wp(mm, vma, address, ptep, flags,
+					 pagecache_page, ptl);
 			goto out_put_page;
+		} else if (likely(flags & FAULT_FLAG_WRITE)) {
+			entry = huge_pte_mkdirty(entry);
 		}
-		entry = huge_pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
 	if (huge_ptep_set_access_flags(vma, haddr, ptep, entry,
diff --git a/mm/memory.c b/mm/memory.c
index 454ecc05ad85..a75040a47fcc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2745,8 +2745,8 @@ static inline int pte_unmap_same(struct vm_fault *vmf)
 	return same;
 }
 
-static inline bool cow_user_page(struct page *dst, struct page *src,
-				 struct vm_fault *vmf)
+static inline bool __wp_page_copy_user(struct page *dst, struct page *src,
+				       struct vm_fault *vmf)
 {
 	bool ret;
 	void *kaddr;
@@ -2954,6 +2954,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	pte_t entry;
 
+	VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE));
 	VM_BUG_ON(PageAnon(page) && !PageAnonExclusive(page));
 
 	/*
@@ -2974,7 +2975,8 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 }
 
 /*
- * Handle the case of a page which we actually need to copy to a new page.
+ * Handle the case of a page which we actually need to copy to a new page,
+ * either due to COW or unsharing.
  *
  * Called with mmap_lock locked and the old page referenced, but
  * without the ptl held.
@@ -2991,6 +2993,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
  */
 static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 {
+	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
 	struct vm_area_struct *vma = vmf->vma;
 	struct mm_struct *mm = vma->vm_mm;
 	struct page *old_page = vmf->page;
@@ -3013,7 +3016,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		if (!new_page)
 			goto oom;
 
-		if (!cow_user_page(new_page, old_page, vmf)) {
+		if (!__wp_page_copy_user(new_page, old_page, vmf)) {
 			/*
 			 * COW failed, if the fault was solved by other,
 			 * it's fine. If not, userspace would re-fault on
@@ -3055,7 +3058,14 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 		entry = mk_pte(new_page, vma->vm_page_prot);
 		entry = pte_sw_mkyoung(entry);
-		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		if (unlikely(unshare)) {
+			if (pte_soft_dirty(vmf->orig_pte))
+				entry = pte_mksoft_dirty(entry);
+			if (pte_uffd_wp(vmf->orig_pte))
+				entry = pte_mkuffd_wp(entry);
+		} else {
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		}
 
 		/*
 		 * Clear the pte entry and flush it first, before updating the
@@ -3072,6 +3082,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		 * mmu page tables (such as kvm shadow page tables), we want the
 		 * new page to be mapped directly into the secondary page table.
 		 */
+		BUG_ON(unshare && pte_write(entry));
 		set_pte_at_notify(mm, vmf->address, vmf->pte, entry);
 		update_mmu_cache(vma, vmf->address, vmf->pte);
 		if (old_page) {
@@ -3121,7 +3132,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			free_swap_cache(old_page);
 		put_page(old_page);
 	}
-	return page_copied ? VM_FAULT_WRITE : 0;
+	return (page_copied && !unshare) ? VM_FAULT_WRITE : 0;
 oom_free_new:
 	put_page(new_page);
 oom:
@@ -3221,18 +3232,22 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf)
 }
 
 /*
- * This routine handles present pages, when users try to write
- * to a shared page. It is done by copying the page to a new address
- * and decrementing the shared-page counter for the old page.
+ * This routine handles present pages, when
+ * * users try to write to a shared page (FAULT_FLAG_WRITE)
+ * * GUP wants to take a R/O pin on a possibly shared anonymous page
+ *   (FAULT_FLAG_UNSHARE)
+ *
+ * It is done by copying the page to a new address and decrementing the
+ * shared-page counter for the old page.
  *
  * Note that this routine assumes that the protection checks have been
  * done by the caller (the low-level page fault routine in most cases).
- * Thus we can safely just mark it writable once we've done any necessary
- * COW.
+ * Thus, with FAULT_FLAG_WRITE, we can safely just mark it writable once we've
+ * done any necessary COW.
  *
- * We also mark the page dirty at this point even though the page will
- * change only once the write actually happens. This avoids a few races,
- * and potentially makes it more efficient.
+ * In case of FAULT_FLAG_WRITE, we also mark the page dirty at this point even
+ * though the page will change only once the write actually happens. This
+ * avoids a few races, and potentially makes it more efficient.
  *
  * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), with pte both mapped and locked.
@@ -3241,23 +3256,35 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf)
 static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	__releases(vmf->ptl)
 {
+	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
 	struct vm_area_struct *vma = vmf->vma;
 
-	if (userfaultfd_pte_wp(vma, *vmf->pte)) {
-		pte_unmap_unlock(vmf->pte, vmf->ptl);
-		return handle_userfault(vmf, VM_UFFD_WP);
-	}
+	VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE));
+	VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE));
 
-	/*
-	 * Userfaultfd write-protect can defer flushes. Ensure the TLB
-	 * is flushed in this case before copying.
-	 */
-	if (unlikely(userfaultfd_wp(vmf->vma) &&
-		     mm_tlb_flush_pending(vmf->vma->vm_mm)))
-		flush_tlb_page(vmf->vma, vmf->address);
+	if (likely(!unshare)) {
+		if (userfaultfd_pte_wp(vma, *vmf->pte)) {
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			return handle_userfault(vmf, VM_UFFD_WP);
+		}
+
+		/*
+		 * Userfaultfd write-protect can defer flushes. Ensure the TLB
+		 * is flushed in this case before copying.
+		 */
+		if (unlikely(userfaultfd_wp(vmf->vma) &&
+			     mm_tlb_flush_pending(vmf->vma->vm_mm)))
+			flush_tlb_page(vmf->vma, vmf->address);
+	}
 
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
 	if (!vmf->page) {
+		if (unlikely(unshare)) {
+			/* No anonymous page -> nothing to do. */
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			return 0;
+		}
+
 		/*
 		 * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
 		 * VM_PFNMAP VMA.
@@ -3320,8 +3347,16 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		page_move_anon_rmap(page, vma);
 		unlock_page(page);
 reuse:
+		if (unlikely(unshare)) {
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			return 0;
+		}
 		wp_page_reuse(vmf);
 		return VM_FAULT_WRITE;
+	} else if (unshare) {
+		/* No anonymous page -> nothing to do. */
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		return 0;
 	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
 		return wp_page_shared(vmf);
@@ -4523,8 +4558,11 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 /* `inline' is required to avoid gcc 4.1.2 build error */
 static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
 {
+	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
+
 	if (vma_is_anonymous(vmf->vma)) {
-		if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
+		if (likely(!unshare) &&
+		    userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
 			return handle_userfault(vmf, VM_UFFD_WP);
 		return do_huge_pmd_wp_page(vmf);
 	}
@@ -4659,10 +4697,11 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		update_mmu_tlb(vmf->vma, vmf->address, vmf->pte);
 		goto unlock;
 	}
-	if (vmf->flags & FAULT_FLAG_WRITE) {
+	if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) {
 		if (!pte_write(entry))
 			return do_wp_page(vmf);
-		entry = pte_mkdirty(entry);
+		else if (likely(vmf->flags & FAULT_FLAG_WRITE))
+			entry = pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
 	if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry,
@@ -4703,7 +4742,6 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		.pgoff = linear_page_index(vma, address),
 		.gfp_mask = __get_fault_gfp_mask(vma),
 	};
-	unsigned int dirty = flags & FAULT_FLAG_WRITE;
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -4728,9 +4766,11 @@ retry_pud:
 		barrier();
 		if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
 
-			/* NUMA case for anonymous PUDs would go here */
-
-			if (dirty && !pud_write(orig_pud)) {
+			/*
+			 * TODO once we support anonymous PUDs: NUMA case and
+			 * FAULT_FLAG_UNSHARE handling.
+			 */
+			if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) {
 				ret = wp_huge_pud(&vmf, orig_pud);
 				if (!(ret & VM_FAULT_FALLBACK))
 					return ret;
@@ -4768,7 +4808,8 @@ retry_pud:
 			if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
 				return do_huge_pmd_numa_page(&vmf);
 
-			if (dirty && !pmd_write(vmf.orig_pmd)) {
+			if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
+			    !pmd_write(vmf.orig_pmd)) {
 				ret = wp_huge_pmd(&vmf);
 				if (!(ret & VM_FAULT_FALLBACK))
 					return ret;
-- 
cgit v1.2.3


From a7f226604170acd6b142b76472c1a49c12ebb83d Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:45 -0700
Subject: mm/gup: trigger FAULT_FLAG_UNSHARE when R/O-pinning a possibly shared
 anonymous page

Whenever GUP currently ends up taking a R/O pin on an anonymous page that
might be shared -- mapped R/O and !PageAnonExclusive() -- any write fault
on the page table entry will end up replacing the mapped anonymous page
due to COW, resulting in the GUP pin no longer being consistent with the
page actually mapped into the page table.

The possible ways to deal with this situation are:
 (1) Ignore and pin -- what we do right now.
 (2) Fail to pin -- which would be rather surprising to callers and
     could break user space.
 (3) Trigger unsharing and pin the now exclusive page -- reliable R/O
     pins.

Let's implement 3) because it provides the clearest semantics and allows
for checking in unpin_user_pages() and friends for possible BUGs: when
trying to unpin a page that's no longer exclusive, clearly something went
very wrong and might result in memory corruptions that might be hard to
debug.  So we better have a nice way to spot such issues.

This change implies that whenever user space *wrote* to a private mapping
(IOW, we have an anonymous page mapped), that GUP pins will always remain
consistent: reliable R/O GUP pins of anonymous pages.

As a side note, this commit fixes the COW security issue for hugetlb with
FOLL_PIN as documented in:
  https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com
The vmsplice reproducer still applies, because vmsplice uses FOLL_GET
instead of FOLL_PIN.

Note that follow_huge_pmd() doesn't apply because we cannot end up in
there with FOLL_PIN.

This commit is heavily based on prototype patches by Andrea.

Link: https://lkml.kernel.org/r/20220428083441.37290-17-david@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Co-developed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 39 +++++++++++++++++++++++++++++++++++++++
 mm/gup.c           | 42 +++++++++++++++++++++++++++++++++++++++---
 mm/huge_memory.c   |  3 +++
 mm/hugetlb.c       | 27 ++++++++++++++++++++++++---
 4 files changed, 105 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9ee3ae51e8e3..5dc5005ccc9b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3002,6 +3002,45 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
 	return 0;
 }
 
+/*
+ * Indicates for which pages that are write-protected in the page table,
+ * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the
+ * GUP pin will remain consistent with the pages mapped into the page tables
+ * of the MM.
+ *
+ * Temporary unmapping of PageAnonExclusive() pages or clearing of
+ * PageAnonExclusive() has to protect against concurrent GUP:
+ * * Ordinary GUP: Using the PT lock
+ * * GUP-fast and fork(): mm->write_protect_seq
+ * * GUP-fast and KSM or temporary unmapping (swap, migration):
+ *   clear/invalidate+flush of the page table entry
+ *
+ * Must be called with the (sub)page that's actually referenced via the
+ * page table entry, which might not necessarily be the head page for a
+ * PTE-mapped THP.
+ */
+static inline bool gup_must_unshare(unsigned int flags, struct page *page)
+{
+	/*
+	 * FOLL_WRITE is implicitly handled correctly as the page table entry
+	 * has to be writable -- and if it references (part of) an anonymous
+	 * folio, that part is required to be marked exclusive.
+	 */
+	if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN)
+		return false;
+	/*
+	 * Note: PageAnon(page) is stable until the page is actually getting
+	 * freed.
+	 */
+	if (!PageAnon(page))
+		return false;
+	/*
+	 * Note that PageKsm() pages cannot be exclusive, and consequently,
+	 * cannot get pinned.
+	 */
+	return !PageAnonExclusive(page);
+}
+
 typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
 extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
 			       unsigned long size, pte_fn_t fn, void *data);
diff --git a/mm/gup.c b/mm/gup.c
index f424abf5e792..4d089d467e58 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -506,6 +506,10 @@ retry:
 		}
 	}
 
+	if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+		page = ERR_PTR(-EMLINK);
+		goto out;
+	}
 	/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
 	if (unlikely(!try_grab_page(page, flags))) {
 		page = ERR_PTR(-ENOMEM);
@@ -732,6 +736,11 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
  * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
  * the device's dev_pagemap metadata to avoid repeating expensive lookups.
  *
+ * When getting an anonymous page and the caller has to trigger unsharing
+ * of a shared anonymous page first, -EMLINK is returned. The caller should
+ * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only
+ * relevant with FOLL_PIN and !FOLL_WRITE.
+ *
  * On output, the @ctx->page_mask is set according to the size of the page.
  *
  * Return: the mapped (struct page *), %NULL if no mapping exists, or
@@ -855,7 +864,8 @@ unmap:
  * is, *@locked will be set to 0 and -EBUSY returned.
  */
 static int faultin_page(struct vm_area_struct *vma,
-		unsigned long address, unsigned int *flags, int *locked)
+		unsigned long address, unsigned int *flags, bool unshare,
+		int *locked)
 {
 	unsigned int fault_flags = 0;
 	vm_fault_t ret;
@@ -877,6 +887,11 @@ static int faultin_page(struct vm_area_struct *vma,
 		 */
 		fault_flags |= FAULT_FLAG_TRIED;
 	}
+	if (unshare) {
+		fault_flags |= FAULT_FLAG_UNSHARE;
+		/* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */
+		VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE);
+	}
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
 	if (ret & VM_FAULT_ERROR) {
@@ -1098,8 +1113,9 @@ retry:
 		cond_resched();
 
 		page = follow_page_mask(vma, start, foll_flags, &ctx);
-		if (!page) {
-			ret = faultin_page(vma, start, &foll_flags, locked);
+		if (!page || PTR_ERR(page) == -EMLINK) {
+			ret = faultin_page(vma, start, &foll_flags,
+					   PTR_ERR(page) == -EMLINK, locked);
 			switch (ret) {
 			case 0:
 				goto retry;
@@ -2201,6 +2217,11 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			goto pte_unmap;
 		}
 
+		if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+			gup_put_folio(folio, 1, flags);
+			goto pte_unmap;
+		}
+
 		/*
 		 * We need to make the page accessible if and only if we are
 		 * going to access its content (the FOLL_PIN case).  Please
@@ -2381,6 +2402,11 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 		return 0;
 	}
 
+	if (!pte_write(pte) && gup_must_unshare(flags, &folio->page)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
@@ -2442,6 +2468,11 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 	}
 
+	if (!pmd_write(orig) && gup_must_unshare(flags, &folio->page)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
@@ -2477,6 +2508,11 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
+	if (!pud_write(orig) && gup_must_unshare(flags, &folio->page)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
 	*nr += refs;
 	folio_set_referenced(folio);
 	return 1;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 17ec6c939e7f..4414111998df 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1389,6 +1389,9 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	page = pmd_page(*pmd);
 	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
 
+	if (!pmd_write(*pmd) && gup_must_unshare(flags, page))
+		return ERR_PTR(-EMLINK);
+
 	if (!try_grab_page(page, flags))
 		return ERR_PTR(-ENOMEM);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9cefa3dd9af3..5f8d3a77a2ec 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5982,6 +5982,25 @@ static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma,
 	}
 }
 
+static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte,
+					       bool *unshare)
+{
+	pte_t pteval = huge_ptep_get(pte);
+
+	*unshare = false;
+	if (is_swap_pte(pteval))
+		return true;
+	if (huge_pte_write(pteval))
+		return false;
+	if (flags & FOLL_WRITE)
+		return true;
+	if (gup_must_unshare(flags, pte_page(pteval))) {
+		*unshare = true;
+		return true;
+	}
+	return false;
+}
+
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 struct page **pages, struct vm_area_struct **vmas,
 			 unsigned long *position, unsigned long *nr_pages,
@@ -5996,6 +6015,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
 		spinlock_t *ptl = NULL;
+		bool unshare = false;
 		int absent;
 		struct page *page;
 
@@ -6046,9 +6066,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * both cases, and because we can't follow correct pages
 		 * directly from any kind of swap entries.
 		 */
-		if (absent || is_swap_pte(huge_ptep_get(pte)) ||
-		    ((flags & FOLL_WRITE) &&
-		      !huge_pte_write(huge_ptep_get(pte)))) {
+		if (absent ||
+		    __follow_hugetlb_must_fault(flags, pte, &unshare)) {
 			vm_fault_t ret;
 			unsigned int fault_flags = 0;
 
@@ -6056,6 +6075,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				spin_unlock(ptl);
 			if (flags & FOLL_WRITE)
 				fault_flags |= FAULT_FLAG_WRITE;
+			else if (unshare)
+				fault_flags |= FAULT_FLAG_UNSHARE;
 			if (locked)
 				fault_flags |= FAULT_FLAG_ALLOW_RETRY |
 					FAULT_FLAG_KILLABLE;
-- 
cgit v1.2.3


From 1493a1913e34b0ac366e33f9ebad721e69fd06ac Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 9 May 2022 18:20:45 -0700
Subject: mm/swap: remember PG_anon_exclusive via a swp pte bit

Patch series "mm: COW fixes part 3: reliable GUP R/W FOLL_GET of anonymous pages", v2.

This series fixes memory corruptions when a GUP R/W reference (FOLL_WRITE
| FOLL_GET) was taken on an anonymous page and COW logic fails to detect
exclusivity of the page to then replacing the anonymous page by a copy in
the page table: The GUP reference lost synchronicity with the pages mapped
into the page tables.  This series focuses on x86, arm64, s390x and
ppc64/book3s -- other architectures are fairly easy to support by
implementing __HAVE_ARCH_PTE_SWP_EXCLUSIVE.

This primarily fixes the O_DIRECT memory corruptions that can happen on
concurrent swapout, whereby we lose DMA reads to a page (modifying the
user page by writing to it).

O_DIRECT currently uses FOLL_GET for short-term (!FOLL_LONGTERM) DMA
from/to a user page.  In the long run, we want to convert it to properly
use FOLL_PIN, and John is working on it, but that might take a while and
might not be easy to backport.  In the meantime, let's restore what used
to work before we started modifying our COW logic: make R/W FOLL_GET
references reliable as long as there is no fork() after GUP involved.

This is just the natural follow-up of part 2, that will also further
reduce "wrong COW" on the swapin path, for example, when we cannot remove
a page from the swapcache due to concurrent writeback, or if we have two
threads faulting on the same swapped-out page.  Fixing O_DIRECT is just a
nice side-product

This issue, including other related COW issues, has been summarized in [3]
under 2):
"
  2. Intra Process Memory Corruptions due to Wrong COW (FOLL_GET)

  It was discovered that we can create a memory corruption by reading a
  file via O_DIRECT to a part (e.g., first 512 bytes) of a page,
  concurrently writing to an unrelated part (e.g., last byte) of the same
  page, and concurrently write-protecting the page via clear_refs
  SOFTDIRTY tracking [6].

  For the reproducer, the issue is that O_DIRECT grabs a reference of the
  target page (via FOLL_GET) and clear_refs write-protects the relevant
  page table entry. On successive write access to the page from the
  process itself, we wrongly COW the page when resolving the write fault,
  resulting in a loss of synchronicity and consequently a memory corruption.

  While some people might think that using clear_refs in this combination
  is a corner cases, it turns out to be a more generic problem unfortunately.

  For example, it was just recently discovered that we can similarly
  create a memory corruption without clear_refs, simply by concurrently
  swapping out the buffer pages [7]. Note that we nowadays even use the
  swap infrastructure in Linux without an actual swap disk/partition: the
  prime example is zram which is enabled as default under Fedora [10].

  The root issue is that a write-fault on a page that has additional
  references results in a COW and thereby a loss of synchronicity
  and consequently a memory corruption if two parties believe they are
  referencing the same page.
"

We don't particularly care about R/O FOLL_GET references: they were never
reliable and O_DIRECT doesn't expect to observe modifications from a page
after DMA was started.

Note that:
* this only fixes the issue on x86, arm64, s390x and ppc64/book3s
  ("enterprise architectures"). Other architectures have to implement
  __HAVE_ARCH_PTE_SWP_EXCLUSIVE to achieve the same.
* this does *not * consider any kind of fork() after taking the reference:
  fork() after GUP never worked reliably with FOLL_GET.
* Not losing PG_anon_exclusive during swapout was the last remaining
  piece. KSM already makes sure that there are no other references on
  a page before considering it for sharing. Page migration maintains
  PG_anon_exclusive and simply fails when there are additional references
  (freezing the refcount fails). Only swapout code dropped the
  PG_anon_exclusive flag because it requires more work to remember +
  restore it.

With this series in place, most COW issues of [3] are fixed on said
architectures. Other architectures can implement
__HAVE_ARCH_PTE_SWP_EXCLUSIVE fairly easily.

[1] https://lkml.kernel.org/r/20220329160440.193848-1-david@redhat.com
[2] https://lkml.kernel.org/r/20211217113049.23850-1-david@redhat.com
[3] https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com


This patch (of 8):

Currently, we clear PG_anon_exclusive in try_to_unmap() and forget about
it.  We do this, to keep fork() logic on swap entries easy and efficient:
for example, if we wouldn't clear it when unmapping, we'd have to lookup
the page in the swapcache for each and every swap entry during fork() and
clear PG_anon_exclusive if set.

Instead, we want to store that information directly in the swap pte,
protected by the page table lock, similarly to how we handle
SWP_MIGRATION_READ_EXCLUSIVE for migration entries.  However, for actual
swap entries, we don't want to mess with the swap type (e.g., still one
bit) because it overcomplicates swap code.

In try_to_unmap(), we already reject to unmap in case the page might be
pinned, because we must not lose PG_anon_exclusive on pinned pages ever.
Checking if there are other unexpected references reliably *before*
completely unmapping a page is unfortunately not really possible: THP
heavily overcomplicate the situation.  Once fully unmapped it's easier --
we, for example, make sure that there are no unexpected references *after*
unmapping a page before starting writeback on that page.

So, we currently might end up unmapping a page and clearing
PG_anon_exclusive if that page has additional references, for example, due
to a FOLL_GET.

do_swap_page() has to re-determine if a page is exclusive, which will
easily fail if there are other references on a page, most prominently GUP
references via FOLL_GET.  This can currently result in memory corruptions
when taking a FOLL_GET | FOLL_WRITE reference on a page even when fork()
is never involved: try_to_unmap() will succeed, and when refaulting the
page, it cannot be marked exclusive and will get replaced by a copy in the
page tables on the next write access, resulting in writes via the GUP
reference to the page being lost.

In an ideal world, everybody that uses GUP and wants to modify page
content, such as O_DIRECT, would properly use FOLL_PIN.  However, that
conversion will take a while.  It's easier to fix what used to work in the
past (FOLL_GET | FOLL_WRITE) remembering PG_anon_exclusive.  In addition,
by remembering PG_anon_exclusive we can further reduce unnecessary COW in
some cases, so it's the natural thing to do.

So let's transfer the PG_anon_exclusive information to the swap pte and
store it via an architecture-dependant pte bit; use that information when
restoring the swap pte in do_swap_page() and unuse_pte().  During fork(),
we simply have to clear the pte bit and are done.

Of course, there is one corner case to handle: swap backends that don't
support concurrent page modifications while the page is under writeback.
Special case these, and drop the exclusive marker.  Add a comment why that
is just fine (also, reuse_swap_page() would have done the same in the
past).

In the future, we'll hopefully have all architectures support
__HAVE_ARCH_PTE_SWP_EXCLUSIVE, such that we can get rid of the empty stubs
and the define completely.  Then, we can also convert
SWP_MIGRATION_READ_EXCLUSIVE.  For architectures it's fairly easy to
support: either simply use a yet unused pte bit that can be used for swap
entries, steal one from the arch type bits if they exceed 5, or steal one
from the offset bits.

Note: R/O FOLL_GET references were never really reliable, especially when
taking one on a shared page and then writing to the page (e.g., GUP after
fork()).  FOLL_GET, including R/W references, were never really reliable
once fork was involved (e.g., GUP before fork(), GUP during fork()).  KSM
steps back in case it stumbles over unexpected references and is,
therefore, fine.

[david@redhat.com: fix SWP_STABLE_WRITES test]
  Link: https://lkml.kernel.org/r/ac725bcb-313a-4fff-250a-68ba9a8f85fb@redhat.comLink: https://lkml.kernel.org/r/20220329164329.208407-1-david@redhat.com
Link: https://lkml.kernel.org/r/20220329164329.208407-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Jann Horn <jannh@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pgtable.h | 29 ++++++++++++++++++++++++++
 include/linux/swapops.h |  2 ++
 mm/memory.c             | 55 +++++++++++++++++++++++++++++++++++++++++++++----
 mm/rmap.c               | 19 ++++++++++-------
 mm/swapfile.c           | 13 +++++++++++-
 5 files changed, 105 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index f4f4077b97aa..53750224e176 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1003,6 +1003,35 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define arch_start_context_switch(prev)	do {} while (0)
 #endif
 
+/*
+ * When replacing an anonymous page by a real (!non) swap entry, we clear
+ * PG_anon_exclusive from the page and instead remember whether the flag was
+ * set in the swp pte. During fork(), we have to mark the entry as !exclusive
+ * (possibly shared). On swapin, we use that information to restore
+ * PG_anon_exclusive, which is very helpful in cases where we might have
+ * additional (e.g., FOLL_GET) references on a page and wouldn't be able to
+ * detect exclusivity.
+ *
+ * These functions don't apply to non-swap entries (e.g., migration, hwpoison,
+ * ...).
+ */
+#ifndef __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return pte;
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return false;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return pte;
+}
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION
 static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index e476a8fed537..d1b728904d4e 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -26,6 +26,8 @@
 /* Clear all flags but only keep swp_entry_t related information */
 static inline pte_t pte_swp_clear_flags(pte_t pte)
 {
+	if (pte_swp_exclusive(pte))
+		pte = pte_swp_clear_exclusive(pte);
 	if (pte_swp_soft_dirty(pte))
 		pte = pte_swp_clear_soft_dirty(pte);
 	if (pte_swp_uffd_wp(pte))
diff --git a/mm/memory.c b/mm/memory.c
index a75040a47fcc..bca60092b4d5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -792,6 +792,11 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 						&src_mm->mmlist);
 			spin_unlock(&mmlist_lock);
 		}
+		/* Mark the swap entry as shared. */
+		if (pte_swp_exclusive(*src_pte)) {
+			pte = pte_swp_clear_exclusive(*src_pte);
+			set_pte_at(src_mm, addr, src_pte, pte);
+		}
 		rss[MM_SWAPENTS]++;
 	} else if (is_migration_entry(entry)) {
 		page = pfn_swap_entry_to_page(entry);
@@ -3563,6 +3568,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	struct page *page = NULL, *swapcache;
 	struct swap_info_struct *si = NULL;
 	rmap_t rmap_flags = RMAP_NONE;
+	bool exclusive = false;
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
@@ -3728,6 +3734,46 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	BUG_ON(!PageAnon(page) && PageMappedToDisk(page));
 	BUG_ON(PageAnon(page) && PageAnonExclusive(page));
 
+	/*
+	 * Check under PT lock (to protect against concurrent fork() sharing
+	 * the swap entry concurrently) for certainly exclusive pages.
+	 */
+	if (!PageKsm(page)) {
+		/*
+		 * Note that pte_swp_exclusive() == false for architectures
+		 * without __HAVE_ARCH_PTE_SWP_EXCLUSIVE.
+		 */
+		exclusive = pte_swp_exclusive(vmf->orig_pte);
+		if (page != swapcache) {
+			/*
+			 * We have a fresh page that is not exposed to the
+			 * swapcache -> certainly exclusive.
+			 */
+			exclusive = true;
+		} else if (exclusive && PageWriteback(page) &&
+			  (swp_swap_info(entry)->flags & SWP_STABLE_WRITES)) {
+			/*
+			 * This is tricky: not all swap backends support
+			 * concurrent page modifications while under writeback.
+			 *
+			 * So if we stumble over such a page in the swapcache
+			 * we must not set the page exclusive, otherwise we can
+			 * map it writable without further checks and modify it
+			 * while still under writeback.
+			 *
+			 * For these problematic swap backends, simply drop the
+			 * exclusive marker: this is perfectly fine as we start
+			 * writeback only if we fully unmapped the page and
+			 * there are no unexpected references on the page after
+			 * unmapping succeeded. After fully unmapped, no
+			 * further GUP references (FOLL_GET and FOLL_PIN) can
+			 * appear, so dropping the exclusive marker and mapping
+			 * it only R/O is fine.
+			 */
+			exclusive = false;
+		}
+	}
+
 	/*
 	 * Remove the swap entry and conditionally try to free up the swapcache.
 	 * We're already holding a reference on the page but haven't mapped it
@@ -3742,11 +3788,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	pte = mk_pte(page, vma->vm_page_prot);
 
 	/*
-	 * Same logic as in do_wp_page(); however, optimize for fresh pages
-	 * that are certainly not shared because we just allocated them without
-	 * exposing them to the swapcache.
+	 * Same logic as in do_wp_page(); however, optimize for pages that are
+	 * certainly not shared either because we just allocated them without
+	 * exposing them to the swapcache or because the swap entry indicates
+	 * exclusivity.
 	 */
-	if (!PageKsm(page) && (page != swapcache || page_count(page) == 1)) {
+	if (!PageKsm(page) && (exclusive || page_count(page) == 1)) {
 		if (vmf->flags & FAULT_FLAG_WRITE) {
 			pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 			vmf->flags &= ~FAULT_FLAG_WRITE;
diff --git a/mm/rmap.c b/mm/rmap.c
index f96cc7eb23ec..86ed2865210d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1698,14 +1698,15 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				break;
 			}
 			/*
-			 * Note: We *don't* remember yet if the page was mapped
-			 * exclusively in the swap entry, so swapin code has
-			 * to re-determine that manually and might detect the
-			 * page as possibly shared, for example, if there are
-			 * other references on the page or if the page is under
-			 * writeback. We made sure that there are no GUP pins
-			 * on the page that would rely on it, so for GUP pins
-			 * this is fine.
+			 * Note: We *don't* remember if the page was mapped
+			 * exclusively in the swap pte if the architecture
+			 * doesn't support __HAVE_ARCH_PTE_SWP_EXCLUSIVE. In
+			 * that case, swapin code has to re-determine that
+			 * manually and might detect the page as possibly
+			 * shared, for example, if there are other references on
+			 * the page or if the page is under writeback. We made
+			 * sure that there are no GUP pins on the page that
+			 * would rely on it, so for GUP pins this is fine.
 			 */
 			if (list_empty(&mm->mmlist)) {
 				spin_lock(&mmlist_lock);
@@ -1716,6 +1717,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			dec_mm_counter(mm, MM_ANONPAGES);
 			inc_mm_counter(mm, MM_SWAPENTS);
 			swp_pte = swp_entry_to_pte(entry);
+			if (anon_exclusive)
+				swp_pte = pte_swp_mkexclusive(swp_pte);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
 			if (pte_uffd_wp(pteval))
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a7847324d476..7279b2d2d71d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1804,7 +1804,18 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 	get_page(page);
 	if (page == swapcache) {
-		page_add_anon_rmap(page, vma, addr, RMAP_NONE);
+		rmap_t rmap_flags = RMAP_NONE;
+
+		/*
+		 * See do_swap_page(): PageWriteback() would be problematic.
+		 * However, we do a wait_on_page_writeback() just before this
+		 * call and have the page locked.
+		 */
+		VM_BUG_ON_PAGE(PageWriteback(page), page);
+		if (pte_swp_exclusive(*pte))
+			rmap_flags |= RMAP_EXCLUSIVE;
+
+		page_add_anon_rmap(page, vma, addr, rmap_flags);
 	} else { /* ksm created a completely new copy */
 		page_add_new_anon_rmap(page, vma, addr);
 		lru_cache_add_inactive_or_unevictable(page, vma);
-- 
cgit v1.2.3


From 014bb1de4fc17d54907d54418126a9a9736f4aff Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 9 May 2022 18:20:47 -0700
Subject: mm: create new mm/swap.h header file

Patch series "MM changes to improve swap-over-NFS support".

Assorted improvements for swap-via-filesystem.

This is a resend of these patches, rebased on current HEAD.  The only
substantial changes is that swap_dirty_folio has replaced
swap_set_page_dirty.

Currently swap-via-fs (SWP_FS_OPS) doesn't work for any filesystem.  It
has previously worked for NFS but that broke a few releases back.  This
series changes to use a new ->swap_rw rather than ->readpage and
->direct_IO.  It also makes other improvements.

There is a companion series already in linux-next which fixes various
issues with NFS.  Once both series land, a final patch is needed which
changes NFS over to use ->swap_rw.


This patch (of 10):

Many functions declared in include/linux/swap.h are only used within mm/

Create a new "mm/swap.h" and move some of these declarations there.
Remove the redundant 'extern' from the function declarations.

[akpm@linux-foundation.org: mm/memory-failure.c needs mm/swap.h]
Link: https://lkml.kernel.org/r/164859751830.29473.5309689752169286816.stgit@noble.brown
Link: https://lkml.kernel.org/r/164859778120.29473.11725907882296224053.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h | 121 ----------------------------------------------
 mm/huge_memory.c     |   1 +
 mm/madvise.c         |   1 +
 mm/memcontrol.c      |   1 +
 mm/memory-failure.c  |   1 +
 mm/memory.c          |   1 +
 mm/mincore.c         |   1 +
 mm/page_alloc.c      |   1 +
 mm/page_io.c         |   1 +
 mm/shmem.c           |   1 +
 mm/swap.h            | 133 +++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/swap_state.c      |   1 +
 mm/swapfile.c        |   1 +
 mm/util.c            |   1 +
 mm/vmscan.c          |   1 +
 mm/zswap.c           |   2 +
 16 files changed, 148 insertions(+), 121 deletions(-)
 create mode 100644 mm/swap.h

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index e6d70a4156e8..def67112dce4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -427,62 +427,19 @@ extern void kswapd_stop(int nid);
 
 #ifdef CONFIG_SWAP
 
-#include <linux/blk_types.h> /* for bio_end_io_t */
-
-/* linux/mm/page_io.c */
-extern int swap_readpage(struct page *page, bool do_poll);
-extern int swap_writepage(struct page *page, struct writeback_control *wbc);
-extern void end_swap_bio_write(struct bio *bio);
-extern int __swap_writepage(struct page *page, struct writeback_control *wbc,
-	bio_end_io_t end_write_func);
 bool swap_dirty_folio(struct address_space *mapping, struct folio *folio);
-
 int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
 		unsigned long nr_pages, sector_t start_block);
 int generic_swapfile_activate(struct swap_info_struct *, struct file *,
 		sector_t *);
 
-/* linux/mm/swap_state.c */
-/* One swap address space for each 64M swap space */
-#define SWAP_ADDRESS_SPACE_SHIFT	14
-#define SWAP_ADDRESS_SPACE_PAGES	(1 << SWAP_ADDRESS_SPACE_SHIFT)
-extern struct address_space *swapper_spaces[];
-#define swap_address_space(entry)			    \
-	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
-		>> SWAP_ADDRESS_SPACE_SHIFT])
 static inline unsigned long total_swapcache_pages(void)
 {
 	return global_node_page_state(NR_SWAPCACHE);
 }
 
-extern void show_swap_cache_info(void);
-extern int add_to_swap(struct page *page);
-extern void *get_shadow_from_swap_cache(swp_entry_t entry);
-extern int add_to_swap_cache(struct page *page, swp_entry_t entry,
-			gfp_t gfp, void **shadowp);
-extern void __delete_from_swap_cache(struct page *page,
-			swp_entry_t entry, void *shadow);
-extern void delete_from_swap_cache(struct page *);
-extern void clear_shadow_from_swap_cache(int type, unsigned long begin,
-				unsigned long end);
-extern void free_swap_cache(struct page *);
 extern void free_page_and_swap_cache(struct page *);
 extern void free_pages_and_swap_cache(struct page **, int);
-extern struct page *lookup_swap_cache(swp_entry_t entry,
-				      struct vm_area_struct *vma,
-				      unsigned long addr);
-struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index);
-extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
-			struct vm_area_struct *vma, unsigned long addr,
-			bool do_poll);
-extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
-			struct vm_area_struct *vma, unsigned long addr,
-			bool *new_page_allocated);
-extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
-				struct vm_fault *vmf);
-extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
-				struct vm_fault *vmf);
-
 /* linux/mm/swapfile.c */
 extern atomic_long_t nr_swap_pages;
 extern long total_swap_pages;
@@ -535,12 +492,6 @@ static inline void put_swap_device(struct swap_info_struct *si)
 }
 
 #else /* CONFIG_SWAP */
-
-static inline int swap_readpage(struct page *page, bool do_poll)
-{
-	return 0;
-}
-
 static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 {
 	return NULL;
@@ -555,11 +506,6 @@ static inline void put_swap_device(struct swap_info_struct *si)
 {
 }
 
-static inline struct address_space *swap_address_space(swp_entry_t entry)
-{
-	return NULL;
-}
-
 #define get_nr_swap_pages()			0L
 #define total_swap_pages			0L
 #define total_swapcache_pages()			0UL
@@ -574,14 +520,6 @@ static inline struct address_space *swap_address_space(swp_entry_t entry)
 #define free_pages_and_swap_cache(pages, nr) \
 	release_pages((pages), (nr));
 
-static inline void free_swap_cache(struct page *page)
-{
-}
-
-static inline void show_swap_cache_info(void)
-{
-}
-
 /* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */
 #define free_swap_and_cache(e) is_pfn_swap_entry(e)
 
@@ -607,65 +545,6 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp)
 {
 }
 
-static inline struct page *swap_cluster_readahead(swp_entry_t entry,
-				gfp_t gfp_mask, struct vm_fault *vmf)
-{
-	return NULL;
-}
-
-static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
-			struct vm_fault *vmf)
-{
-	return NULL;
-}
-
-static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
-{
-	return 0;
-}
-
-static inline struct page *lookup_swap_cache(swp_entry_t swp,
-					     struct vm_area_struct *vma,
-					     unsigned long addr)
-{
-	return NULL;
-}
-
-static inline
-struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
-{
-	return find_get_page(mapping, index);
-}
-
-static inline int add_to_swap(struct page *page)
-{
-	return 0;
-}
-
-static inline void *get_shadow_from_swap_cache(swp_entry_t entry)
-{
-	return NULL;
-}
-
-static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
-					gfp_t gfp_mask, void **shadowp)
-{
-	return -1;
-}
-
-static inline void __delete_from_swap_cache(struct page *page,
-					swp_entry_t entry, void *shadow)
-{
-}
-
-static inline void delete_from_swap_cache(struct page *page)
-{
-}
-
-static inline void clear_shadow_from_swap_cache(int type, unsigned long begin,
-				unsigned long end)
-{
-}
 
 static inline int page_swapcount(struct page *page)
 {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a2f44d8d3d47..86eae6834db7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -39,6 +39,7 @@
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
 #include "internal.h"
+#include "swap.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/thp.h>
diff --git a/mm/madvise.c b/mm/madvise.c
index c965fac7b13a..b19daedde0ea 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -35,6 +35,7 @@
 #include <asm/tlb.h>
 
 #include "internal.h"
+#include "swap.h"
 
 struct madvise_walk_private {
 	struct mmu_gather *tlb;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d180ef985b17..235c85e17c2d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -67,6 +67,7 @@
 #include <net/sock.h>
 #include <net/ip.h>
 #include "slab.h"
+#include "swap.h"
 
 #include <linux/uaccess.h>
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9711c0eb70b0..1d117190c350 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -59,6 +59,7 @@
 #include <linux/page-isolation.h>
 #include <linux/pagewalk.h>
 #include <linux/shmem_fs.h>
+#include "swap.h"
 #include "internal.h"
 #include "ras/ras_event.h"
 
diff --git a/mm/memory.c b/mm/memory.c
index bca60092b4d5..6e9428ae6d66 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -86,6 +86,7 @@
 
 #include "pgalloc-track.h"
 #include "internal.h"
+#include "swap.h"
 
 #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
 #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
diff --git a/mm/mincore.c b/mm/mincore.c
index 9122676b54d6..f4f627325e12 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -20,6 +20,7 @@
 #include <linux/pgtable.h>
 
 #include <linux/uaccess.h>
+#include "swap.h"
 
 static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
 			unsigned long end, struct mm_walk *walk)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f01c71e41bcf..e85a0dc22761 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -81,6 +81,7 @@
 #include "internal.h"
 #include "shuffle.h"
 #include "page_reporting.h"
+#include "swap.h"
 
 /* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */
 typedef int __bitwise fpi_t;
diff --git a/mm/page_io.c b/mm/page_io.c
index 89fbf3cae30f..4b359e59bfdc 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -26,6 +26,7 @@
 #include <linux/uio.h>
 #include <linux/sched/task.h>
 #include <linux/delayacct.h>
+#include "swap.h"
 
 void end_swap_bio_write(struct bio *bio)
 {
diff --git a/mm/shmem.c b/mm/shmem.c
index e504d734177b..913c0b039333 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -38,6 +38,7 @@
 #include <linux/hugetlb.h>
 #include <linux/fs_parser.h>
 #include <linux/swapfile.h>
+#include "swap.h"
 
 static struct vfsmount *shm_mnt;
 
diff --git a/mm/swap.h b/mm/swap.h
new file mode 100644
index 000000000000..f8265bf0ce00
--- /dev/null
+++ b/mm/swap.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MM_SWAP_H
+#define _MM_SWAP_H
+
+#ifdef CONFIG_SWAP
+#include <linux/blk_types.h> /* for bio_end_io_t */
+
+/* linux/mm/page_io.c */
+int swap_readpage(struct page *page, bool do_poll);
+int swap_writepage(struct page *page, struct writeback_control *wbc);
+void end_swap_bio_write(struct bio *bio);
+int __swap_writepage(struct page *page, struct writeback_control *wbc,
+		     bio_end_io_t end_write_func);
+
+/* linux/mm/swap_state.c */
+/* One swap address space for each 64M swap space */
+#define SWAP_ADDRESS_SPACE_SHIFT	14
+#define SWAP_ADDRESS_SPACE_PAGES	(1 << SWAP_ADDRESS_SPACE_SHIFT)
+extern struct address_space *swapper_spaces[];
+#define swap_address_space(entry)			    \
+	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
+		>> SWAP_ADDRESS_SPACE_SHIFT])
+
+void show_swap_cache_info(void);
+int add_to_swap(struct page *page);
+void *get_shadow_from_swap_cache(swp_entry_t entry);
+int add_to_swap_cache(struct page *page, swp_entry_t entry,
+		      gfp_t gfp, void **shadowp);
+void __delete_from_swap_cache(struct page *page,
+			      swp_entry_t entry, void *shadow);
+void delete_from_swap_cache(struct page *page);
+void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				  unsigned long end);
+void free_swap_cache(struct page *page);
+struct page *lookup_swap_cache(swp_entry_t entry,
+			       struct vm_area_struct *vma,
+			       unsigned long addr);
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index);
+
+struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+				   struct vm_area_struct *vma,
+				   unsigned long addr,
+				   bool do_poll);
+struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+				     struct vm_area_struct *vma,
+				     unsigned long addr,
+				     bool *new_page_allocated);
+struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
+				    struct vm_fault *vmf);
+struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
+			      struct vm_fault *vmf);
+
+#else /* CONFIG_SWAP */
+static inline int swap_readpage(struct page *page, bool do_poll)
+{
+	return 0;
+}
+
+static inline struct address_space *swap_address_space(swp_entry_t entry)
+{
+	return NULL;
+}
+
+static inline void free_swap_cache(struct page *page)
+{
+}
+
+static inline void show_swap_cache_info(void)
+{
+}
+
+static inline struct page *swap_cluster_readahead(swp_entry_t entry,
+				gfp_t gfp_mask, struct vm_fault *vmf)
+{
+	return NULL;
+}
+
+static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
+			struct vm_fault *vmf)
+{
+	return NULL;
+}
+
+static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
+{
+	return 0;
+}
+
+static inline struct page *lookup_swap_cache(swp_entry_t swp,
+					     struct vm_area_struct *vma,
+					     unsigned long addr)
+{
+	return NULL;
+}
+
+static inline
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
+{
+	return find_get_page(mapping, index);
+}
+
+static inline int add_to_swap(struct page *page)
+{
+	return 0;
+}
+
+static inline void *get_shadow_from_swap_cache(swp_entry_t entry)
+{
+	return NULL;
+}
+
+static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
+					gfp_t gfp_mask, void **shadowp)
+{
+	return -1;
+}
+
+static inline void __delete_from_swap_cache(struct page *page,
+					swp_entry_t entry, void *shadow)
+{
+}
+
+static inline void delete_from_swap_cache(struct page *page)
+{
+}
+
+static inline void clear_shadow_from_swap_cache(int type, unsigned long begin,
+				unsigned long end)
+{
+}
+
+#endif /* CONFIG_SWAP */
+#endif /* _MM_SWAP_H */
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 013856004825..5437dd317cf3 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -23,6 +23,7 @@
 #include <linux/huge_mm.h>
 #include <linux/shmem_fs.h>
 #include "internal.h"
+#include "swap.h"
 
 /*
  * swapper_space is a fiction, retained to simplify the path through
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 7279b2d2d71d..f08bf675a613 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -44,6 +44,7 @@
 #include <asm/tlbflush.h>
 #include <linux/swapops.h>
 #include <linux/swap_cgroup.h>
+#include "swap.h"
 
 static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
 				 unsigned char);
diff --git a/mm/util.c b/mm/util.c
index 3492a9e81aa3..f27c796239b1 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -27,6 +27,7 @@
 #include <linux/uaccess.h>
 
 #include "internal.h"
+#include "swap.h"
 
 /**
  * kfree_const - conditionally free memory
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6e255e2867d2..b1b91d5b9f49 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -59,6 +59,7 @@
 #include <linux/sched/sysctl.h>
 
 #include "internal.h"
+#include "swap.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/vmscan.h>
diff --git a/mm/zswap.c b/mm/zswap.c
index 3efd8cae315e..2c5db4cbedea 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -36,6 +36,8 @@
 #include <linux/pagemap.h>
 #include <linux/workqueue.h>
 
+#include "swap.h"
+
 /*********************************
 * statistics
 **********************************/
-- 
cgit v1.2.3


From 4c4a763406ef903b78334bd2ccea168d2f7a741a Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 9 May 2022 18:20:47 -0700
Subject: mm: drop swap_dirty_folio

folios that are written to swap are owned by the MM subsystem - not any
filesystem.

When such a folio is passed to a filesystem to be written out to a
swap-file, the filesystem handles the data, but the folio itself does not
belong to the filesystem.  So calling the filesystem's ->dirty_folio()
address_space operation makes no sense.  This is for folios in the given
address space, and a folio to be written to swap does not exist in the
given address space.

So drop swap_dirty_folio() which calls the address-space's
->dirty_folio(), and always use noop_dirty_folio(), which is appropriate
for folios being swapped out.

Link: https://lkml.kernel.org/r/164859778123.29473.6900942583784889976.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h |  1 -
 mm/page_io.c         | 17 -----------------
 mm/swap_state.c      |  2 +-
 3 files changed, 1 insertion(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index def67112dce4..8170254c56b0 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -427,7 +427,6 @@ extern void kswapd_stop(int nid);
 
 #ifdef CONFIG_SWAP
 
-bool swap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
 		unsigned long nr_pages, sector_t start_block);
 int generic_swapfile_activate(struct swap_info_struct *, struct file *,
diff --git a/mm/page_io.c b/mm/page_io.c
index 4b359e59bfdc..77fa0fb263f4 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -385,20 +385,3 @@ out:
 	delayacct_swapin_end();
 	return ret;
 }
-
-bool swap_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	struct swap_info_struct *sis = swp_swap_info(folio_swap_entry(folio));
-
-	if (data_race(sis->flags & SWP_FS_OPS)) {
-		const struct address_space_operations *aops;
-
-		mapping = sis->swap_file->f_mapping;
-		aops = mapping->a_ops;
-
-		VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
-		return aops->dirty_folio(mapping, folio);
-	} else {
-		return noop_dirty_folio(mapping, folio);
-	}
-}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 5437dd317cf3..f3ab01801629 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -31,7 +31,7 @@
  */
 static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
-	.dirty_folio	= swap_dirty_folio,
+	.dirty_folio	= noop_dirty_folio,
 #ifdef CONFIG_MIGRATION
 	.migratepage	= migrate_page,
 #endif
-- 
cgit v1.2.3


From 4b60c0ff2f2021ab99b7fb9da63b7ed1579ef1d8 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 9 May 2022 18:20:48 -0700
Subject: mm: move responsibility for setting SWP_FS_OPS to ->swap_activate

If a filesystem wishes to handle all swap IO itself (via ->direct_IO and
->readpage), rather than just providing devices addresses for
submit_bio(), SWP_FS_OPS must be set.

Currently the protocol for setting this it to have ->swap_activate return
zero.  In that case SWP_FS_OPS is set, and add_swap_extent() is called for
the entire file.

This is a little clumsy as different return values for ->swap_activate
have quite different meanings, and it makes it hard to search for which
filesystems require SWP_FS_OPS to be set.

So remove the special meaning of a zero return, and require the filesystem
to set SWP_FS_OPS if it so desires, and to always call add_swap_extent()
as required.

Currently only NFS and CIFS return zero for add_swap_extent().

Link: https://lkml.kernel.org/r/164859778123.29473.17908205846599043598.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/cifs/file.c       |  3 ++-
 fs/nfs/file.c        | 14 ++++++++++++--
 include/linux/swap.h |  6 ++++++
 mm/swapfile.c        | 10 +++-------
 4 files changed, 23 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index d511a78383c3..14d29404c834 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4933,7 +4933,8 @@ static int cifs_swap_activate(struct swap_info_struct *sis,
 	 * from reading or writing the file
 	 */
 
-	return 0;
+	sis->flags |= SWP_FS_OPS;
+	return add_swap_extent(sis, 0, sis->max, 0);
 }
 
 static void cifs_swap_deactivate(struct file *file)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 150b7fa8f0a7..a3a073604070 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -483,6 +483,7 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 {
 	unsigned long blocks;
 	long long isize;
+	int ret;
 	struct inode *inode = file_inode(file);
 	struct rpc_clnt *clnt = NFS_CLIENT(inode);
 	struct nfs_client *cl = NFS_SERVER(inode)->nfs_client;
@@ -496,13 +497,22 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		return -EINVAL;
 	}
 
-	*span = sis->pages;
+	ret = rpc_clnt_swap_activate(clnt);
+	if (ret)
+		return ret;
+	ret = add_swap_extent(sis, 0, sis->max, 0);
+	if (ret < 0) {
+		rpc_clnt_swap_deactivate(clnt);
+		return ret;
+	}
 
+	*span = sis->pages;
 
 	if (cl->rpc_ops->enable_swap)
 		cl->rpc_ops->enable_swap(inode);
 
-	return rpc_clnt_swap_activate(clnt);
+	sis->flags |= SWP_FS_OPS;
+	return ret;
 }
 
 static void nfs_swap_deactivate(struct file *file)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8170254c56b0..7daae5a4b3e1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -577,6 +577,12 @@ static inline swp_entry_t get_swap_page(struct page *page)
 	return entry;
 }
 
+static inline int add_swap_extent(struct swap_info_struct *sis,
+				  unsigned long start_page,
+				  unsigned long nr_pages, sector_t start_block)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_SWAP */
 
 #ifdef CONFIG_THP_SWAP
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f08bf675a613..d811458c0a88 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2259,13 +2259,9 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 
 	if (mapping->a_ops->swap_activate) {
 		ret = mapping->a_ops->swap_activate(sis, swap_file, span);
-		if (ret >= 0)
-			sis->flags |= SWP_ACTIVATED;
-		if (!ret) {
-			sis->flags |= SWP_FS_OPS;
-			ret = add_swap_extent(sis, 0, sis->max, 0);
-			*span = sis->pages;
-		}
+		if (ret < 0)
+			return ret;
+		sis->flags |= SWP_ACTIVATED;
 		return ret;
 	}
 
-- 
cgit v1.2.3


From e1209d3a7a67c281260ba9989621060ba7328b8c Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 9 May 2022 18:20:48 -0700
Subject: mm: introduce ->swap_rw and use it for reads from SWP_FS_OPS
 swap-space

swap currently uses ->readpage to read swap pages.  This can only request
one page at a time from the filesystem, which is not most efficient.

swap uses ->direct_IO for writes which while this is adequate is an
inappropriate over-loading.  ->direct_IO may need to had handle allocate
space for holes or other details that are not relevant for swap.

So this patch introduces a new address_space operation: ->swap_rw.  In
this patch it is used for reads, and a subsequent patch will switch writes
to use it.

No filesystem yet supports ->swap_rw, but that is not a problem because
no filesystem actually works with filesystem-based swap.
Only two filesystems set SWP_FS_OPS:
- cifs sets the flag, but ->direct_IO always fails so swap cannot work.
- nfs sets the flag, but ->direct_IO calls generic_write_checks()
  which has failed on swap files for several releases.

To ensure that a NULL ->swap_rw isn't called, ->activate_swap() for both
NFS and cifs are changed to fail if ->swap_rw is not set.  This can be
removed if/when the function is added.

Future patches will restore swap-over-NFS functionality.

To submit an async read with ->swap_rw() we need to allocate a structure
to hold the kiocb and other details.  swap_readpage() cannot handle
transient failure, so we create a mempool to provide the structures.

Link: https://lkml.kernel.org/r/164859778125.29473.13430559328221330589.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/cifs/file.c     |  4 ++++
 fs/nfs/file.c      |  4 ++++
 include/linux/fs.h |  1 +
 mm/page_io.c       | 68 +++++++++++++++++++++++++++++++++++++++++++++++++-----
 mm/swap.h          |  1 +
 mm/swapfile.c      |  5 ++++
 6 files changed, 77 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 14d29404c834..794e2cc23e3f 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4905,6 +4905,10 @@ static int cifs_swap_activate(struct swap_info_struct *sis,
 
 	cifs_dbg(FYI, "swap activate\n");
 
+	if (!swap_file->f_mapping->a_ops->swap_rw)
+		/* Cannot support swap */
+		return -EINVAL;
+
 	spin_lock(&inode->i_lock);
 	blocks = inode->i_blocks;
 	isize = inode->i_size;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index a3a073604070..55bc8c8ca71a 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -488,6 +488,10 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	struct rpc_clnt *clnt = NFS_CLIENT(inode);
 	struct nfs_client *cl = NFS_SERVER(inode)->nfs_client;
 
+	if (!file->f_mapping->a_ops->swap_rw)
+		/* Cannot support swap */
+		return -EINVAL;
+
 	spin_lock(&inode->i_lock);
 	blocks = inode->i_blocks;
 	isize = inode->i_size;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde95387a23..dbc5d10328df 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -380,6 +380,7 @@ struct address_space_operations {
 	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
 				sector_t *span);
 	void (*swap_deactivate)(struct file *file);
+	int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
 };
 
 extern const struct address_space_operations empty_aops;
diff --git a/mm/page_io.c b/mm/page_io.c
index 77fa0fb263f4..2724d6389104 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -235,6 +235,25 @@ static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
 #define bio_associate_blkg_from_page(bio, page)		do { } while (0)
 #endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
 
+struct swap_iocb {
+	struct kiocb		iocb;
+	struct bio_vec		bvec;
+};
+static mempool_t *sio_pool;
+
+int sio_pool_init(void)
+{
+	if (!sio_pool) {
+		mempool_t *pool = mempool_create_kmalloc_pool(
+			SWAP_CLUSTER_MAX, sizeof(struct swap_iocb));
+		if (cmpxchg(&sio_pool, NULL, pool))
+			mempool_destroy(pool);
+	}
+	if (!sio_pool)
+		return -ENOMEM;
+	return 0;
+}
+
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		bio_end_io_t end_write_func)
 {
@@ -306,6 +325,48 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	return 0;
 }
 
+static void sio_read_complete(struct kiocb *iocb, long ret)
+{
+	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
+	struct page *page = sio->bvec.bv_page;
+
+	if (ret != 0 && ret != PAGE_SIZE) {
+		SetPageError(page);
+		ClearPageUptodate(page);
+		pr_alert_ratelimited("Read-error on swap-device\n");
+	} else {
+		SetPageUptodate(page);
+		count_vm_event(PSWPIN);
+	}
+	unlock_page(page);
+	mempool_free(sio, sio_pool);
+}
+
+static int swap_readpage_fs(struct page *page)
+{
+	struct swap_info_struct *sis = page_swap_info(page);
+	struct file *swap_file = sis->swap_file;
+	struct address_space *mapping = swap_file->f_mapping;
+	struct iov_iter from;
+	struct swap_iocb *sio;
+	loff_t pos = page_file_offset(page);
+	int ret;
+
+	sio = mempool_alloc(sio_pool, GFP_KERNEL);
+	init_sync_kiocb(&sio->iocb, swap_file);
+	sio->iocb.ki_pos = pos;
+	sio->iocb.ki_complete = sio_read_complete;
+	sio->bvec.bv_page = page;
+	sio->bvec.bv_len = PAGE_SIZE;
+	sio->bvec.bv_offset = 0;
+
+	iov_iter_bvec(&from, READ, &sio->bvec, 1, PAGE_SIZE);
+	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	if (ret != -EIOCBQUEUED)
+		sio_read_complete(&sio->iocb, ret);
+	return ret;
+}
+
 int swap_readpage(struct page *page, bool synchronous)
 {
 	struct bio *bio;
@@ -334,12 +395,7 @@ int swap_readpage(struct page *page, bool synchronous)
 	}
 
 	if (data_race(sis->flags & SWP_FS_OPS)) {
-		struct file *swap_file = sis->swap_file;
-		struct address_space *mapping = swap_file->f_mapping;
-
-		ret = mapping->a_ops->readpage(swap_file, page);
-		if (!ret)
-			count_vm_event(PSWPIN);
+		ret = swap_readpage_fs(page);
 		goto out;
 	}
 
diff --git a/mm/swap.h b/mm/swap.h
index e19f185df5e2..eafac80b18d9 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -6,6 +6,7 @@
 #include <linux/blk_types.h> /* for bio_end_io_t */
 
 /* linux/mm/page_io.c */
+int sio_pool_init(void);
 int swap_readpage(struct page *page, bool do_poll);
 int swap_writepage(struct page *page, struct writeback_control *wbc);
 void end_swap_bio_write(struct bio *bio);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index d811458c0a88..9398e915b36b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2262,6 +2262,11 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 		if (ret < 0)
 			return ret;
 		sis->flags |= SWP_ACTIVATED;
+		if ((sis->flags & SWP_FS_OPS) &&
+		    sio_pool_init() != 0) {
+			destroy_swap_extents(sis);
+			return -ENOMEM;
+		}
 		return ret;
 	}
 
-- 
cgit v1.2.3


From eb79f3af9395fbe448e91b0940a6c395b7d06be4 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 9 May 2022 18:20:48 -0700
Subject: nfs: rename nfs_direct_IO and use as ->swap_rw

The nfs_direct_IO() exists to support SWAP IO, but hasn't worked for a
while.  We now need a ->swap_rw function which behaves slightly
differently, returning zero for success rather than a byte count.

So modify nfs_direct_IO accordingly, rename it, and use it as the
->swap_rw function.

Link: https://lkml.kernel.org/r/165119301493.15698.7491285551903597618.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be> (on Renesas RSK+RZA1 with 32 MiB of SDRAM)
Cc: David Howells <dhowells@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nfs/direct.c        | 23 ++++++++++-------------
 fs/nfs/file.c          |  5 +----
 include/linux/nfs_fs.h |  2 +-
 3 files changed, 12 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 11c566d8769f..4eb2a8380a28 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -153,28 +153,25 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq,
 }
 
 /**
- * nfs_direct_IO - NFS address space operation for direct I/O
+ * nfs_swap_rw - NFS address space operation for swap I/O
  * @iocb: target I/O control block
  * @iter: I/O buffer
  *
- * The presence of this routine in the address space ops vector means
- * the NFS client supports direct I/O. However, for most direct IO, we
- * shunt off direct read and write requests before the VFS gets them,
- * so this method is only ever called for swap.
+ * Perform IO to the swap-file.  This is much like direct IO.
  */
-ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct inode *inode = iocb->ki_filp->f_mapping->host;
-
-	/* we only support swap file calling nfs_direct_IO */
-	if (!IS_SWAPFILE(inode))
-		return 0;
+	ssize_t ret;
 
 	VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
 
 	if (iov_iter_rw(iter) == READ)
-		return nfs_file_direct_read(iocb, iter, true);
-	return nfs_file_direct_write(iocb, iter, true);
+		ret = nfs_file_direct_read(iocb, iter, true);
+	else
+		ret = nfs_file_direct_write(iocb, iter, true);
+	if (ret < 0)
+		return ret;
+	return 0;
 }
 
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 55bc8c8ca71a..0e7686a5d0de 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -488,10 +488,6 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	struct rpc_clnt *clnt = NFS_CLIENT(inode);
 	struct nfs_client *cl = NFS_SERVER(inode)->nfs_client;
 
-	if (!file->f_mapping->a_ops->swap_rw)
-		/* Cannot support swap */
-		return -EINVAL;
-
 	spin_lock(&inode->i_lock);
 	blocks = inode->i_blocks;
 	isize = inode->i_size;
@@ -549,6 +545,7 @@ const struct address_space_operations nfs_file_aops = {
 	.error_remove_page = generic_error_remove_page,
 	.swap_activate = nfs_swap_activate,
 	.swap_deactivate = nfs_swap_deactivate,
+	.swap_rw = nfs_swap_rw,
 };
 
 /*
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b48b9259e02c..fd5543486a3f 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -507,7 +507,7 @@ static inline const struct cred *nfs_file_cred(struct file *file)
 /*
  * linux/fs/nfs/direct.c
  */
-extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *);
+int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter);
 ssize_t nfs_file_direct_read(struct kiocb *iocb,
 			     struct iov_iter *iter, bool swap);
 ssize_t nfs_file_direct_write(struct kiocb *iocb,
-- 
cgit v1.2.3


From 2282679fb20bf036a714ed49fadd0230c278a203 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 9 May 2022 18:20:49 -0700
Subject: mm: submit multipage write for SWP_FS_OPS swap-space

swap_writepage() is given one page at a time, but may be called repeatedly
in succession.

For block-device swapspace, the blk_plug functionality allows the multiple
pages to be combined together at lower layers.  That cannot be used for
SWP_FS_OPS as blk_plug may not exist - it is only active when
CONFIG_BLOCK=y.  Consequently all swap reads over NFS are single page
reads.

With this patch we pass a pointer-to-pointer via the wbc.  swap_writepage
can store state between calls - much like the pointer passed explicitly to
swap_readpage.  After calling swap_writepage() some number of times, the
state will be passed to swap_write_unplug() which can submit the combined
request.

Link: https://lkml.kernel.org/r/164859778128.29473.5191868522654408537.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/writeback.h |  7 +++++
 mm/page_io.c              | 78 ++++++++++++++++++++++++++++++++++-------------
 mm/swap.h                 |  4 +++
 mm/vmscan.c               |  9 ++++--
 4 files changed, 74 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fec248ab1fec..32b35f21cb97 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -80,6 +80,13 @@ struct writeback_control {
 
 	unsigned punt_to_cgroup:1;	/* cgrp punting, see __REQ_CGROUP_PUNT */
 
+	/* To enable batching of swap writes to non-block-device backends,
+	 * "plug" can be set point to a 'struct swap_iocb *'.  When all swap
+	 * writes have been submitted, if with swap_iocb is not NULL,
+	 * swap_write_unplug() should be called.
+	 */
+	struct swap_iocb **swap_plug;
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct bdi_writeback *wb;	/* wb this writeback is issued under */
 	struct inode *inode;		/* inode being written out */
diff --git a/mm/page_io.c b/mm/page_io.c
index a63510fd6611..c132511f521c 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -259,8 +259,9 @@ static void sio_write_complete(struct kiocb *iocb, long ret)
 {
 	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
 	struct page *page = sio->bvec[0].bv_page;
+	int p;
 
-	if (ret != PAGE_SIZE) {
+	if (ret != PAGE_SIZE * sio->pages) {
 		/*
 		 * In the case of swap-over-nfs, this can be a
 		 * temporary failure if the system has limited
@@ -271,43 +272,63 @@ static void sio_write_complete(struct kiocb *iocb, long ret)
 		 * the normal direct-to-bio case as it could
 		 * be temporary.
 		 */
-		set_page_dirty(page);
-		ClearPageReclaim(page);
 		pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
 				   ret, page_file_offset(page));
+		for (p = 0; p < sio->pages; p++) {
+			page = sio->bvec[p].bv_page;
+			set_page_dirty(page);
+			ClearPageReclaim(page);
+		}
 	} else
-		count_vm_event(PSWPOUT);
-	end_page_writeback(page);
+		count_vm_events(PSWPOUT, sio->pages);
+
+	for (p = 0; p < sio->pages; p++)
+		end_page_writeback(sio->bvec[p].bv_page);
+
 	mempool_free(sio, sio_pool);
 }
 
 static int swap_writepage_fs(struct page *page, struct writeback_control *wbc)
 {
-	struct swap_iocb *sio;
+	struct swap_iocb *sio = NULL;
 	struct swap_info_struct *sis = page_swap_info(page);
 	struct file *swap_file = sis->swap_file;
-	struct address_space *mapping = swap_file->f_mapping;
-	struct iov_iter from;
-	int ret;
+	loff_t pos = page_file_offset(page);
 
 	set_page_writeback(page);
 	unlock_page(page);
-	sio = mempool_alloc(sio_pool, GFP_NOIO);
-	init_sync_kiocb(&sio->iocb, swap_file);
-	sio->iocb.ki_complete = sio_write_complete;
-	sio->iocb.ki_pos = page_file_offset(page);
-	sio->bvec[0].bv_page = page;
-	sio->bvec[0].bv_len = PAGE_SIZE;
-	sio->bvec[0].bv_offset = 0;
-	iov_iter_bvec(&from, WRITE, &sio->bvec[0], 1, PAGE_SIZE);
-	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
-	if (ret != -EIOCBQUEUED)
-		sio_write_complete(&sio->iocb, ret);
-	return ret;
+	if (wbc->swap_plug)
+		sio = *wbc->swap_plug;
+	if (sio) {
+		if (sio->iocb.ki_filp != swap_file ||
+		    sio->iocb.ki_pos + sio->pages * PAGE_SIZE != pos) {
+			swap_write_unplug(sio);
+			sio = NULL;
+		}
+	}
+	if (!sio) {
+		sio = mempool_alloc(sio_pool, GFP_NOIO);
+		init_sync_kiocb(&sio->iocb, swap_file);
+		sio->iocb.ki_complete = sio_write_complete;
+		sio->iocb.ki_pos = pos;
+		sio->pages = 0;
+	}
+	sio->bvec[sio->pages].bv_page = page;
+	sio->bvec[sio->pages].bv_len = PAGE_SIZE;
+	sio->bvec[sio->pages].bv_offset = 0;
+	sio->pages += 1;
+	if (sio->pages == ARRAY_SIZE(sio->bvec) || !wbc->swap_plug) {
+		swap_write_unplug(sio);
+		sio = NULL;
+	}
+	if (wbc->swap_plug)
+		*wbc->swap_plug = sio;
+
+	return 0;
 }
 
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
-		bio_end_io_t end_write_func)
+		     bio_end_io_t end_write_func)
 {
 	struct bio *bio;
 	int ret;
@@ -344,6 +365,19 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	return 0;
 }
 
+void swap_write_unplug(struct swap_iocb *sio)
+{
+	struct iov_iter from;
+	struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
+	int ret;
+
+	iov_iter_bvec(&from, WRITE, sio->bvec, sio->pages,
+		      PAGE_SIZE * sio->pages);
+	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	if (ret != -EIOCBQUEUED)
+		sio_write_complete(&sio->iocb, ret);
+}
+
 static void sio_read_complete(struct kiocb *iocb, long ret)
 {
 	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
diff --git a/mm/swap.h b/mm/swap.h
index 0389ab147837..a6da8f612904 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -16,6 +16,7 @@ static inline void swap_read_unplug(struct swap_iocb *plug)
 	if (unlikely(plug))
 		__swap_read_unplug(plug);
 }
+void swap_write_unplug(struct swap_iocb *sio);
 int swap_writepage(struct page *page, struct writeback_control *wbc);
 void end_swap_bio_write(struct bio *bio);
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
@@ -71,6 +72,9 @@ static inline int swap_readpage(struct page *page, bool do_poll,
 {
 	return 0;
 }
+static inline void swap_write_unplug(struct swap_iocb *sio)
+{
+}
 
 static inline struct address_space *swap_address_space(swp_entry_t entry)
 {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 95ebcb5b3e12..a9761b04564c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1156,7 +1156,8 @@ typedef enum {
  * pageout is called by shrink_page_list() for each dirty page.
  * Calls ->writepage().
  */
-static pageout_t pageout(struct folio *folio, struct address_space *mapping)
+static pageout_t pageout(struct folio *folio, struct address_space *mapping,
+			 struct swap_iocb **plug)
 {
 	/*
 	 * If the folio is dirty, only perform writeback if that write
@@ -1201,6 +1202,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping)
 			.range_start = 0,
 			.range_end = LLONG_MAX,
 			.for_reclaim = 1,
+			.swap_plug = plug,
 		};
 
 		folio_set_reclaim(folio);
@@ -1533,6 +1535,7 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 	unsigned int nr_reclaimed = 0;
 	unsigned int pgactivate = 0;
 	bool do_demote_pass;
+	struct swap_iocb *plug = NULL;
 
 	memset(stat, 0, sizeof(*stat));
 	cond_resched();
@@ -1814,7 +1817,7 @@ retry:
 			 * starts and then write it out here.
 			 */
 			try_to_unmap_flush_dirty();
-			switch (pageout(folio, mapping)) {
+			switch (pageout(folio, mapping, &plug)) {
 			case PAGE_KEEP:
 				goto keep_locked;
 			case PAGE_ACTIVATE:
@@ -1968,6 +1971,8 @@ keep:
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
 
+	if (plug)
+		swap_write_unplug(plug);
 	return nr_reclaimed;
 }
 
-- 
cgit v1.2.3


From a2ad63daa88b9d6846976fd2a0b5e4f5cfc58377 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 9 May 2022 18:20:49 -0700
Subject: VFS: add FMODE_CAN_ODIRECT file flag

Currently various places test if direct IO is possible on a file by
checking for the existence of the direct_IO address space operation.
This is a poor choice, as the direct_IO operation may not be used - it is
only used if the generic_file_*_iter functions are called for direct IO
and some filesystems - particularly NFS - don't do this.

Instead, introduce a new f_mode flag: FMODE_CAN_ODIRECT and change the
various places to check this (avoiding pointer dereferences).
do_dentry_open() will set this flag if ->direct_IO is present, so
filesystems do not need to be changed.

NFS *is* changed, to set the flag explicitly and discard the direct_IO
entry in the address_space_operations for files.

Other filesystems which currently use noop_direct_IO could usefully be
changed to set this flag instead.

Link: https://lkml.kernel.org/r/164859778128.29473.15189737957277399416.stgit@noble.brown
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: NeilBrown <neilb@suse.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/block/loop.c |  4 ++--
 fs/fcntl.c           |  9 ++++-----
 fs/nfs/file.c        |  3 ++-
 fs/open.c            |  9 ++++-----
 fs/overlayfs/file.c  | 13 ++++---------
 include/linux/fs.h   |  3 +++
 6 files changed, 19 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a58595f5ee2c..75ef2e177e1b 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -186,8 +186,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
 	 */
 	if (dio) {
 		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
-				!(lo->lo_offset & dio_align) &&
-				mapping->a_ops->direct_IO)
+		    !(lo->lo_offset & dio_align) &&
+		    (file->f_mode & FMODE_CAN_ODIRECT))
 			use_dio = true;
 		else
 			use_dio = false;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index f15d885b9796..34a3faa4886d 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -56,11 +56,10 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 		   arg |= O_NONBLOCK;
 
 	/* Pipe packetized mode is controlled by O_DIRECT flag */
-	if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) {
-		if (!filp->f_mapping || !filp->f_mapping->a_ops ||
-			!filp->f_mapping->a_ops->direct_IO)
-				return -EINVAL;
-	}
+	if (!S_ISFIFO(inode->i_mode) &&
+	    (arg & O_DIRECT) &&
+	    !(filp->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
 
 	if (filp->f_op->check_flags)
 		error = filp->f_op->check_flags(arg);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 0e7686a5d0de..bfb4b707b07e 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -69,6 +69,8 @@ nfs_file_open(struct inode *inode, struct file *filp)
 		return res;
 
 	res = nfs_open(inode, filp);
+	if (res == 0)
+		filp->f_mode |= FMODE_CAN_ODIRECT;
 	return res;
 }
 
@@ -536,7 +538,6 @@ const struct address_space_operations nfs_file_aops = {
 	.write_end = nfs_write_end,
 	.invalidate_folio = nfs_invalidate_folio,
 	.releasepage = nfs_release_page,
-	.direct_IO = nfs_direct_IO,
 #ifdef CONFIG_MIGRATION
 	.migratepage = nfs_migrate_page,
 #endif
diff --git a/fs/open.c b/fs/open.c
index 1315253e0247..7b50d7a2f51d 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -834,16 +834,15 @@ static int do_dentry_open(struct file *f,
 	if ((f->f_mode & FMODE_WRITE) &&
 	     likely(f->f_op->write || f->f_op->write_iter))
 		f->f_mode |= FMODE_CAN_WRITE;
+	if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO)
+		f->f_mode |= FMODE_CAN_ODIRECT;
 
 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
-	/* NB: we're sure to have correct a_ops only after f_op->open */
-	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
-			return -EINVAL;
-	}
+	if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
 
 	/*
 	 * XXX: Huge page cache doesn't support writing yet. Drop all page
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index fa125feed0ff..9d69b4dbb8c4 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -82,11 +82,8 @@ static int ovl_change_flags(struct file *file, unsigned int flags)
 	if (((flags ^ file->f_flags) & O_APPEND) && IS_APPEND(inode))
 		return -EPERM;
 
-	if (flags & O_DIRECT) {
-		if (!file->f_mapping->a_ops ||
-		    !file->f_mapping->a_ops->direct_IO)
-			return -EINVAL;
-	}
+	if ((flags & O_DIRECT) && !(file->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
 
 	if (file->f_op->check_flags) {
 		err = file->f_op->check_flags(flags);
@@ -306,8 +303,7 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 	ret = -EINVAL;
 	if (iocb->ki_flags & IOCB_DIRECT &&
-	    (!real.file->f_mapping->a_ops ||
-	     !real.file->f_mapping->a_ops->direct_IO))
+	    !(real.file->f_mode & FMODE_CAN_ODIRECT))
 		goto out_fdput;
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
@@ -367,8 +363,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 	ret = -EINVAL;
 	if (iocb->ki_flags & IOCB_DIRECT &&
-	    (!real.file->f_mapping->a_ops ||
-	     !real.file->f_mapping->a_ops->direct_IO))
+	    !(real.file->f_mode & FMODE_CAN_ODIRECT))
 		goto out_fdput;
 
 	if (!ovl_should_sync(OVL_FS(inode->i_sb)))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dbc5d10328df..b81cacc51d2f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -162,6 +162,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File is stream-like */
 #define FMODE_STREAM		((__force fmode_t)0x200000)
 
+/* File supports DIRECT IO */
+#define	FMODE_CAN_ODIRECT	((__force fmode_t)0x400000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
-- 
cgit v1.2.3


From fa29000b6b2603ec2bfdc4c73249fcb00cd54f85 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 29 Apr 2022 17:00:05 -0400
Subject: fs: Add aops->release_folio

This replaces aops->releasepage.  Update the documentation, and call it
if it exists.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 Documentation/filesystems/caching/netfs-api.rst |  4 +--
 Documentation/filesystems/locking.rst           | 14 ++++----
 Documentation/filesystems/vfs.rst               | 45 ++++++++++++-------------
 include/linux/fs.h                              |  1 +
 mm/filemap.c                                    |  2 ++
 5 files changed, 34 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/caching/netfs-api.rst b/Documentation/filesystems/caching/netfs-api.rst
index 7308d76a29dc..1d18e9def183 100644
--- a/Documentation/filesystems/caching/netfs-api.rst
+++ b/Documentation/filesystems/caching/netfs-api.rst
@@ -433,11 +433,11 @@ has done a write and then the page it wrote from has been released by the VM,
 after which it *has* to look in the cache.
 
 To inform fscache that a page might now be in the cache, the following function
-should be called from the ``releasepage`` address space op::
+should be called from the ``release_folio`` address space op::
 
 	void fscache_note_page_release(struct fscache_cookie *cookie);
 
-if the page has been released (ie. releasepage returned true).
+if the page has been released (ie. release_folio returned true).
 
 Page release and page invalidation should also wait for any mark left on the
 page to say that a DIO write is underway from that page::
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index aeba2475a53c..ddef4a753e73 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -249,7 +249,7 @@ prototypes::
 				struct page *page, void *fsdata);
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidate_folio) (struct folio *, size_t start, size_t len);
-	int (*releasepage) (struct page *, int);
+	bool (*release_folio)(struct folio *, gfp_t);
 	void (*freepage)(struct page *);
 	int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 	bool (*isolate_page) (struct page *, isolate_mode_t);
@@ -270,13 +270,13 @@ ops			PageLocked(page)	 i_rwsem	invalidate_lock
 writepage:		yes, unlocks (see below)
 read_folio:		yes, unlocks				shared
 writepages:
-dirty_folio		maybe
+dirty_folio:		maybe
 readahead:		yes, unlocks				shared
 write_begin:		locks the page		 exclusive
 write_end:		yes, unlocks		 exclusive
 bmap:
 invalidate_folio:	yes					exclusive
-releasepage:		yes
+release_folio:		yes
 freepage:		yes
 direct_IO:
 isolate_page:		yes
@@ -372,10 +372,10 @@ invalidate_lock before invalidating page cache in truncate / hole punch
 path (and thus calling into ->invalidate_folio) to block races between page
 cache invalidation and page cache filling functions (fault, read, ...).
 
-->releasepage() is called when the kernel is about to try to drop the
-buffers from the page in preparation for freeing it.  It returns zero to
-indicate that the buffers are (or may be) freeable.  If ->releasepage is zero,
-the kernel assumes that the fs has no private interest in the buffers.
+->release_folio() is called when the kernel is about to try to drop the
+buffers from the folio in preparation for freeing it.  It returns false to
+indicate that the buffers are (or may be) freeable.  If ->release_folio is
+NULL, the kernel assumes that the fs has no private interest in the buffers.
 
 ->freepage() is called when the kernel is done dropping the page
 from the page cache.
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 0919a4ad973a..679887b5c8fc 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -620,9 +620,9 @@ Writeback.
 The first can be used independently to the others.  The VM can try to
 either write dirty pages in order to clean them, or release clean pages
 in order to reuse them.  To do this it can call the ->writepage method
-on dirty pages, and ->releasepage on clean pages with PagePrivate set.
-Clean pages without PagePrivate and with no external references will be
-released without notice being given to the address_space.
+on dirty pages, and ->release_folio on clean folios with the private
+flag set.  Clean pages without PagePrivate and with no external references
+will be released without notice being given to the address_space.
 
 To achieve this functionality, pages need to be placed on an LRU with
 lru_cache_add and mark_page_active needs to be called whenever the page
@@ -734,7 +734,7 @@ cache in your filesystem.  The following members are defined:
 				 struct page *page, void *fsdata);
 		sector_t (*bmap)(struct address_space *, sector_t);
 		void (*invalidate_folio) (struct folio *, size_t start, size_t len);
-		int (*releasepage) (struct page *, int);
+		bool (*release_folio)(struct folio *, gfp_t);
 		void (*freepage)(struct page *);
 		ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 		/* isolate a page for migration */
@@ -864,33 +864,32 @@ cache in your filesystem.  The following members are defined:
 	address space.  This generally corresponds to either a
 	truncation, punch hole or a complete invalidation of the address
 	space (in the latter case 'offset' will always be 0 and 'length'
-	will be folio_size()).  Any private data associated with the page
+	will be folio_size()).  Any private data associated with the folio
 	should be updated to reflect this truncation.  If offset is 0
 	and length is folio_size(), then the private data should be
-	released, because the page must be able to be completely
-	discarded.  This may be done by calling the ->releasepage
+	released, because the folio must be able to be completely
+	discarded.  This may be done by calling the ->release_folio
 	function, but in this case the release MUST succeed.
 
-``releasepage``
-	releasepage is called on PagePrivate pages to indicate that the
-	page should be freed if possible.  ->releasepage should remove
-	any private data from the page and clear the PagePrivate flag.
-	If releasepage() fails for some reason, it must indicate failure
-	with a 0 return value.  releasepage() is used in two distinct
-	though related cases.  The first is when the VM finds a clean
-	page with no active users and wants to make it a free page.  If
-	->releasepage succeeds, the page will be removed from the
-	address_space and become free.
+``release_folio``
+	release_folio is called on folios with private data to tell the
+	filesystem that the folio is about to be freed.  ->release_folio
+	should remove any private data from the folio and clear the
+	private flag.  If release_folio() fails, it should return false.
+	release_folio() is used in two distinct though related cases.
+	The first is when the VM wants to free a clean folio with no
+	active users.  If ->release_folio succeeds, the folio will be
+	removed from the address_space and be freed.
 
 	The second case is when a request has been made to invalidate
-	some or all pages in an address_space.  This can happen through
-	the fadvise(POSIX_FADV_DONTNEED) system call or by the
-	filesystem explicitly requesting it as nfs and 9fs do (when they
+	some or all folios in an address_space.  This can happen
+	through the fadvise(POSIX_FADV_DONTNEED) system call or by the
+	filesystem explicitly requesting it as nfs and 9p do (when they
 	believe the cache may be out of date with storage) by calling
 	invalidate_inode_pages2().  If the filesystem makes such a call,
-	and needs to be certain that all pages are invalidated, then its
-	releasepage will need to ensure this.  Possibly it can clear the
-	PageUptodate bit if it cannot free private data yet.
+	and needs to be certain that all folios are invalidated, then
+	its release_folio will need to ensure this.  Possibly it can
+	clear the uptodate flag if it cannot free private data yet.
 
 ``freepage``
 	freepage is called once the page is no longer visible in the
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f812f5aa07dd..ad768f13f485 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -355,6 +355,7 @@ struct address_space_operations {
 	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidate_folio) (struct folio *, size_t offset, size_t len);
+	bool (*release_folio)(struct folio *, gfp_t);
 	int (*releasepage) (struct page *, gfp_t);
 	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
diff --git a/mm/filemap.c b/mm/filemap.c
index 9b7fa47feb5e..78e4a7dc3a56 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3955,6 +3955,8 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
 	if (folio_test_writeback(folio))
 		return false;
 
+	if (mapping && mapping->a_ops->release_folio)
+		return mapping->a_ops->release_folio(folio, gfp);
 	if (mapping && mapping->a_ops->releasepage)
 		return mapping->a_ops->releasepage(&folio->page, gfp);
 	return try_to_free_buffers(&folio->page);
-- 
cgit v1.2.3


From 8597447dc565a6a3fa7bc503674452b7ae2b914c Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sat, 30 Apr 2022 23:01:08 -0400
Subject: iomap: Convert to release_folio

Change all the filesystems which used iomap_releasepage to use the
new function.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/gfs2/aops.c         |  2 +-
 fs/iomap/buffered-io.c | 22 ++++++++++------------
 fs/iomap/trace.h       |  2 +-
 fs/xfs/xfs_aops.c      |  2 +-
 fs/zonefs/super.c      |  2 +-
 include/linux/iomap.h  |  2 +-
 6 files changed, 15 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 1016631bcbdc..3d6c5c5eb4f1 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -768,7 +768,7 @@ static const struct address_space_operations gfs2_aops = {
 	.read_folio = gfs2_read_folio,
 	.readahead = gfs2_readahead,
 	.dirty_folio = filemap_dirty_folio,
-	.releasepage = iomap_releasepage,
+	.release_folio = iomap_release_folio,
 	.invalidate_folio = iomap_invalidate_folio,
 	.bmap = gfs2_bmap,
 	.direct_IO = noop_direct_IO,
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 2de087ac87b6..8532f0e2e2d6 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -452,25 +452,23 @@ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
 }
 EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
 
-int
-iomap_releasepage(struct page *page, gfp_t gfp_mask)
+bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags)
 {
-	struct folio *folio = page_folio(page);
-
-	trace_iomap_releasepage(folio->mapping->host, folio_pos(folio),
+	trace_iomap_release_folio(folio->mapping->host, folio_pos(folio),
 			folio_size(folio));
 
 	/*
-	 * mm accommodates an old ext3 case where clean pages might not have had
-	 * the dirty bit cleared. Thus, it can send actual dirty pages to
-	 * ->releasepage() via shrink_active_list(); skip those here.
+	 * mm accommodates an old ext3 case where clean folios might
+	 * not have had the dirty bit cleared.  Thus, it can send actual
+	 * dirty folios to ->release_folio() via shrink_active_list();
+	 * skip those here.
 	 */
 	if (folio_test_dirty(folio) || folio_test_writeback(folio))
-		return 0;
+		return false;
 	iomap_page_release(folio);
-	return 1;
+	return true;
 }
-EXPORT_SYMBOL_GPL(iomap_releasepage);
+EXPORT_SYMBOL_GPL(iomap_release_folio);
 
 void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len)
 {
@@ -1483,7 +1481,7 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
 		 * Skip the page if it's fully outside i_size, e.g. due to a
 		 * truncate operation that's in progress. We must redirty the
 		 * page so that reclaim stops reclaiming it. Otherwise
-		 * iomap_vm_releasepage() is called on it and gets confused.
+		 * iomap_release_folio() is called on it and gets confused.
 		 *
 		 * Note that the end_index is unsigned long.  If the given
 		 * offset is greater than 16TB on a 32-bit system then if we
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index a6689a563c6e..d48868fc40d7 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -80,7 +80,7 @@ DEFINE_EVENT(iomap_range_class, name,	\
 	TP_PROTO(struct inode *inode, loff_t off, u64 len),\
 	TP_ARGS(inode, off, len))
 DEFINE_RANGE_EVENT(iomap_writepage);
-DEFINE_RANGE_EVENT(iomap_releasepage);
+DEFINE_RANGE_EVENT(iomap_release_folio);
 DEFINE_RANGE_EVENT(iomap_invalidate_folio);
 DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail);
 
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index a9c4bb500d53..2acbfc6925dd 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -568,7 +568,7 @@ const struct address_space_operations xfs_address_space_operations = {
 	.readahead		= xfs_vm_readahead,
 	.writepages		= xfs_vm_writepages,
 	.dirty_folio		= filemap_dirty_folio,
-	.releasepage		= iomap_releasepage,
+	.release_folio		= iomap_release_folio,
 	.invalidate_folio	= iomap_invalidate_folio,
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= noop_direct_IO,
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index c3a38f711b24..b1a428f860b3 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -197,7 +197,7 @@ static const struct address_space_operations zonefs_file_aops = {
 	.writepage		= zonefs_writepage,
 	.writepages		= zonefs_writepages,
 	.dirty_folio		= filemap_dirty_folio,
-	.releasepage		= iomap_releasepage,
+	.release_folio		= iomap_release_folio,
 	.invalidate_folio	= iomap_invalidate_folio,
 	.migratepage		= iomap_migrate_page,
 	.is_partially_uptodate	= iomap_is_partially_uptodate,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 5b2aa45ddda3..0d674695b6d3 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -228,7 +228,7 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
 void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
 bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
-int iomap_releasepage(struct page *page, gfp_t gfp_mask);
+bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
 void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
 #ifdef CONFIG_MIGRATION
 int iomap_migrate_page(struct address_space *mapping, struct page *newpage,
-- 
cgit v1.2.3


From 704ead2bed202579f025a4754e52e9ab21ff3ada Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 1 May 2022 00:27:53 -0400
Subject: fs: Remove last vestiges of releasepage

All users are now converted to release_folio

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 include/linux/fs.h         | 1 -
 include/linux/page-flags.h | 2 +-
 mm/filemap.c               | 2 --
 3 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index ad768f13f485..1cee64d9724b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -356,7 +356,6 @@ struct address_space_operations {
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidate_folio) (struct folio *, size_t offset, size_t len);
 	bool (*release_folio)(struct folio *, gfp_t);
-	int (*releasepage) (struct page *, gfp_t);
 	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 	/*
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 9d8eeaa67d05..af10149a6c31 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -516,7 +516,7 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
 /*
  * Private page markings that may be used by the filesystem that owns the page
  * for its own purposes.
- * - PG_private and PG_private_2 cause releasepage() and co to be invoked
+ * - PG_private and PG_private_2 cause release_folio() and co to be invoked
  */
 PAGEFLAG(Private, private, PF_ANY)
 PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
diff --git a/mm/filemap.c b/mm/filemap.c
index 78e4a7dc3a56..ee892853a214 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3957,8 +3957,6 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
 
 	if (mapping && mapping->a_ops->release_folio)
 		return mapping->a_ops->release_folio(folio, gfp);
-	if (mapping && mapping->a_ops->releasepage)
-		return mapping->a_ops->releasepage(&folio->page, gfp);
 	return try_to_free_buffers(&folio->page);
 }
 EXPORT_SYMBOL(filemap_release_folio);
-- 
cgit v1.2.3


From c56a6eb03deb187c989a966fda5a254249b56c2a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 1 May 2022 00:46:03 -0400
Subject: jbd2: Convert jbd2_journal_try_to_free_buffers to take a folio

Also convert it to return a bool since it's called from release_folio().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/ext4/inode.c       |  2 +-
 fs/jbd2/transaction.c | 12 ++++++------
 include/linux/jbd2.h  |  2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 52c46ac5bc8a..943937cb5302 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3253,7 +3253,7 @@ static bool ext4_release_folio(struct folio *folio, gfp_t wait)
 	if (folio_test_checked(folio))
 		return false;
 	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, &folio->page);
+		return jbd2_journal_try_to_free_buffers(journal, folio);
 	else
 		return try_to_free_buffers(&folio->page);
 }
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index fcb9175016a5..ee33d277d51e 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2143,17 +2143,17 @@ out:
  * cannot happen because we never reallocate freed data as metadata
  * while the data is part of a transaction.  Yes?
  *
- * Return 0 on failure, 1 on success
+ * Return false on failure, true on success
  */
-int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page)
+bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio)
 {
 	struct buffer_head *head;
 	struct buffer_head *bh;
-	int ret = 0;
+	bool ret = false;
 
-	J_ASSERT(PageLocked(page));
+	J_ASSERT(folio_test_locked(folio));
 
-	head = page_buffers(page);
+	head = folio_buffers(folio);
 	bh = head;
 	do {
 		struct journal_head *jh;
@@ -2175,7 +2175,7 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page)
 			goto busy;
 	} while ((bh = bh->b_this_page) != head);
 
-	ret = try_to_free_buffers(page);
+	ret = try_to_free_buffers(&folio->page);
 busy:
 	return ret;
 }
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index de9536680b2b..e79d6e0b14e8 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1529,7 +1529,7 @@ extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
 int jbd2_journal_invalidate_folio(journal_t *, struct folio *,
 					size_t offset, size_t length);
-extern int	 jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page);
+bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio);
 extern int	 jbd2_journal_stop(handle_t *);
 extern int	 jbd2_journal_flush(journal_t *journal, unsigned int flags);
 extern void	 jbd2_journal_lock_updates (journal_t *);
-- 
cgit v1.2.3


From 68189fef88c7d02eb92e038be3d6428ebd0d2945 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 1 May 2022 01:08:08 -0400
Subject: fs: Change try_to_free_buffers() to take a folio

All but two of the callers already have a folio; pass a folio into
try_to_free_buffers().  This removes the last user of cancel_dirty_page()
so remove that wrapper function too.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/buffer.c                 | 42 +++++++++++++++++++++---------------------
 fs/ext4/inode.c             |  2 +-
 fs/gfs2/aops.c              |  2 +-
 fs/hfs/inode.c              |  2 +-
 fs/hfsplus/inode.c          |  2 +-
 fs/jbd2/commit.c            |  2 +-
 fs/jbd2/transaction.c       |  4 ++--
 fs/mpage.c                  |  2 +-
 fs/ocfs2/aops.c             |  2 +-
 fs/reiserfs/inode.c         |  2 +-
 fs/reiserfs/journal.c       |  2 +-
 include/linux/buffer_head.h |  4 ++--
 include/linux/pagemap.h     |  4 ----
 mm/filemap.c                |  2 +-
 mm/migrate.c                |  2 +-
 mm/vmscan.c                 |  2 +-
 16 files changed, 37 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/fs/buffer.c b/fs/buffer.c
index 786ef5b98c80..701af0035802 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -955,7 +955,7 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 						size);
 			goto done;
 		}
-		if (!try_to_free_buffers(page))
+		if (!try_to_free_buffers(page_folio(page)))
 			goto failed;
 	}
 
@@ -3155,20 +3155,20 @@ int sync_dirty_buffer(struct buffer_head *bh)
 EXPORT_SYMBOL(sync_dirty_buffer);
 
 /*
- * try_to_free_buffers() checks if all the buffers on this particular page
+ * try_to_free_buffers() checks if all the buffers on this particular folio
  * are unused, and releases them if so.
  *
  * Exclusion against try_to_free_buffers may be obtained by either
- * locking the page or by holding its mapping's private_lock.
+ * locking the folio or by holding its mapping's private_lock.
  *
- * If the page is dirty but all the buffers are clean then we need to
- * be sure to mark the page clean as well.  This is because the page
+ * If the folio is dirty but all the buffers are clean then we need to
+ * be sure to mark the folio clean as well.  This is because the folio
  * may be against a block device, and a later reattachment of buffers
- * to a dirty page will set *all* buffers dirty.  Which would corrupt
+ * to a dirty folio will set *all* buffers dirty.  Which would corrupt
  * filesystem data on the same device.
  *
- * The same applies to regular filesystem pages: if all the buffers are
- * clean then we set the page clean and proceed.  To do that, we require
+ * The same applies to regular filesystem folios: if all the buffers are
+ * clean then we set the folio clean and proceed.  To do that, we require
  * total exclusion from block_dirty_folio().  That is obtained with
  * private_lock.
  *
@@ -3207,40 +3207,40 @@ failed:
 	return 0;
 }
 
-int try_to_free_buffers(struct page *page)
+bool try_to_free_buffers(struct folio *folio)
 {
-	struct address_space * const mapping = page->mapping;
+	struct address_space * const mapping = folio->mapping;
 	struct buffer_head *buffers_to_free = NULL;
-	int ret = 0;
+	bool ret = 0;
 
-	BUG_ON(!PageLocked(page));
-	if (PageWriteback(page))
-		return 0;
+	BUG_ON(!folio_test_locked(folio));
+	if (folio_test_writeback(folio))
+		return false;
 
 	if (mapping == NULL) {		/* can this still happen? */
-		ret = drop_buffers(page, &buffers_to_free);
+		ret = drop_buffers(&folio->page, &buffers_to_free);
 		goto out;
 	}
 
 	spin_lock(&mapping->private_lock);
-	ret = drop_buffers(page, &buffers_to_free);
+	ret = drop_buffers(&folio->page, &buffers_to_free);
 
 	/*
 	 * If the filesystem writes its buffers by hand (eg ext3)
-	 * then we can have clean buffers against a dirty page.  We
-	 * clean the page here; otherwise the VM will never notice
+	 * then we can have clean buffers against a dirty folio.  We
+	 * clean the folio here; otherwise the VM will never notice
 	 * that the filesystem did any IO at all.
 	 *
 	 * Also, during truncate, discard_buffer will have marked all
-	 * the page's buffers clean.  We discover that here and clean
-	 * the page also.
+	 * the folio's buffers clean.  We discover that here and clean
+	 * the folio also.
 	 *
 	 * private_lock must be held over this entire operation in order
 	 * to synchronise against block_dirty_folio and prevent the
 	 * dirty bit from being lost.
 	 */
 	if (ret)
-		cancel_dirty_page(page);
+		folio_cancel_dirty(folio);
 	spin_unlock(&mapping->private_lock);
 out:
 	if (buffers_to_free) {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 943937cb5302..987ea77e672d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3255,7 +3255,7 @@ static bool ext4_release_folio(struct folio *folio, gfp_t wait)
 	if (journal)
 		return jbd2_journal_try_to_free_buffers(journal, folio);
 	else
-		return try_to_free_buffers(&folio->page);
+		return try_to_free_buffers(folio);
 }
 
 static bool ext4_inode_datasync_dirty(struct inode *inode)
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 95a674d70c04..106e90a36583 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -757,7 +757,7 @@ bool gfs2_release_folio(struct folio *folio, gfp_t gfp_mask)
 	} while (bh != head);
 	gfs2_log_unlock(sdp);
 
-	return try_to_free_buffers(&folio->page);
+	return try_to_free_buffers(folio);
 
 cannot_release:
 	gfs2_log_unlock(sdp);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 86fd50e5fccb..c4526f16355d 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -124,7 +124,7 @@ static bool hfs_release_folio(struct folio *folio, gfp_t mask)
 		} while (--i && nidx < tree->node_count);
 		spin_unlock(&tree->hash_lock);
 	}
-	return res ? try_to_free_buffers(&folio->page) : false;
+	return res ? try_to_free_buffers(folio) : false;
 }
 
 static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index f723e0e91d51..aeab83ed1c9c 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -121,7 +121,7 @@ static bool hfsplus_release_folio(struct folio *folio, gfp_t mask)
 		} while (--i && nidx < tree->node_count);
 		spin_unlock(&tree->hash_lock);
 	}
-	return res ? try_to_free_buffers(&folio->page) : false;
+	return res ? try_to_free_buffers(folio) : false;
 }
 
 static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 2f37108da0ec..eb315e81f1a6 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -82,7 +82,7 @@ static void release_buffer_page(struct buffer_head *bh)
 
 	folio_get(folio);
 	__brelse(bh);
-	try_to_free_buffers(&folio->page);
+	try_to_free_buffers(folio);
 	folio_unlock(folio);
 	folio_put(folio);
 	return;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index ee33d277d51e..e49bb0938376 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2175,7 +2175,7 @@ bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio)
 			goto busy;
 	} while ((bh = bh->b_this_page) != head);
 
-	ret = try_to_free_buffers(&folio->page);
+	ret = try_to_free_buffers(folio);
 busy:
 	return ret;
 }
@@ -2482,7 +2482,7 @@ int jbd2_journal_invalidate_folio(journal_t *journal, struct folio *folio,
 	} while (bh != head);
 
 	if (!partial_page) {
-		if (may_free && try_to_free_buffers(&folio->page))
+		if (may_free && try_to_free_buffers(folio))
 			J_ASSERT(!folio_buffers(folio));
 	}
 	return 0;
diff --git a/fs/mpage.c b/fs/mpage.c
index 6df9c3aa5728..0d25f44f5707 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -431,7 +431,7 @@ static void clean_buffers(struct page *page, unsigned first_unmapped)
 	 * disk before we reach the platter.
 	 */
 	if (buffer_heads_over_limit && PageUptodate(page))
-		try_to_free_buffers(page);
+		try_to_free_buffers(page_folio(page));
 }
 
 /*
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 7d7b86ca078f..35d40a67204c 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -502,7 +502,7 @@ static bool ocfs2_release_folio(struct folio *folio, gfp_t wait)
 {
 	if (!folio_buffers(folio))
 		return false;
-	return try_to_free_buffers(&folio->page);
+	return try_to_free_buffers(folio);
 }
 
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 9cf2e1420a74..0cffe054b78e 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3234,7 +3234,7 @@ static bool reiserfs_release_folio(struct folio *folio, gfp_t unused_gfp_flags)
 		bh = bh->b_this_page;
 	} while (bh != head);
 	if (ret)
-		ret = try_to_free_buffers(&folio->page);
+		ret = try_to_free_buffers(folio);
 	spin_unlock(&j->j_dirty_buffers_lock);
 	return ret;
 }
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 99ba495b0f28..d8cc9a366124 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -606,7 +606,7 @@ static void release_buffer_page(struct buffer_head *bh)
 		folio_get(folio);
 		put_bh(bh);
 		if (!folio->mapping)
-			try_to_free_buffers(&folio->page);
+			try_to_free_buffers(folio);
 		folio_unlock(folio);
 		folio_put(folio);
 	} else {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 31d82fd9abe8..c9d1463bb20f 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -158,7 +158,7 @@ void mark_buffer_write_io_error(struct buffer_head *bh);
 void touch_buffer(struct buffer_head *bh);
 void set_bh_page(struct buffer_head *bh,
 		struct page *page, unsigned long offset);
-int try_to_free_buffers(struct page *);
+bool try_to_free_buffers(struct folio *);
 struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 		bool retry);
 void create_empty_buffers(struct page *, unsigned long,
@@ -402,7 +402,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio);
 #else /* CONFIG_BLOCK */
 
 static inline void buffer_init(void) {}
-static inline int try_to_free_buffers(struct page *page) { return 1; }
+static inline bool try_to_free_buffers(struct folio *folio) { return true; }
 static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 831b28dab01a..82dfb279e0c4 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1067,10 +1067,6 @@ static inline void folio_cancel_dirty(struct folio *folio)
 	if (folio_test_dirty(folio))
 		__folio_cancel_dirty(folio);
 }
-static inline void cancel_dirty_page(struct page *page)
-{
-	folio_cancel_dirty(page_folio(page));
-}
 bool folio_clear_dirty_for_io(struct folio *folio);
 bool clear_page_dirty_for_io(struct page *page);
 void folio_invalidate(struct folio *folio, size_t offset, size_t length);
diff --git a/mm/filemap.c b/mm/filemap.c
index ee892853a214..d335a154a0d9 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3957,6 +3957,6 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
 
 	if (mapping && mapping->a_ops->release_folio)
 		return mapping->a_ops->release_folio(folio, gfp);
-	return try_to_free_buffers(&folio->page);
+	return try_to_free_buffers(folio);
 }
 EXPORT_SYMBOL(filemap_release_folio);
diff --git a/mm/migrate.c b/mm/migrate.c
index 6c31ee1e1c9b..21d82636c291 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1013,7 +1013,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	if (!page->mapping) {
 		VM_BUG_ON_PAGE(PageAnon(page), page);
 		if (page_has_private(page)) {
-			try_to_free_buffers(page);
+			try_to_free_buffers(folio);
 			goto out_unlock_both;
 		}
 	} else if (page_mapped(page)) {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 27851232e00c..f3f7ce2c4068 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1181,7 +1181,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping)
 		 * folio->mapping == NULL while being dirty with clean buffers.
 		 */
 		if (folio_test_private(folio)) {
-			if (try_to_free_buffers(&folio->page)) {
+			if (try_to_free_buffers(folio)) {
 				folio_clear_dirty(folio);
 				pr_info("%s: orphaned folio\n", __func__);
 				return PAGE_CLEAN;
-- 
cgit v1.2.3


From d2329aa0c78f4a8dd368bb706f196ab99f692eaa Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 1 May 2022 07:35:31 -0400
Subject: fs: Add free_folio address space operation

Include documentation and convert the callers to use ->free_folio as
well as ->freepage.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 Documentation/filesystems/locking.rst | 10 +++++-----
 Documentation/filesystems/vfs.rst     |  6 +++---
 include/linux/fs.h                    |  1 +
 mm/filemap.c                          |  9 ++++++++-
 mm/vmscan.c                           |  6 +++++-
 5 files changed, 22 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index ddef4a753e73..515bc48ab58b 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -250,7 +250,7 @@ prototypes::
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidate_folio) (struct folio *, size_t start, size_t len);
 	bool (*release_folio)(struct folio *, gfp_t);
-	void (*freepage)(struct page *);
+	void (*free_folio)(struct folio *);
 	int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 	bool (*isolate_page) (struct page *, isolate_mode_t);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
@@ -262,10 +262,10 @@ prototypes::
 	int (*swap_deactivate)(struct file *);
 
 locking rules:
-	All except dirty_folio and freepage may block
+	All except dirty_folio and free_folio may block
 
 ======================	======================== =========	===============
-ops			PageLocked(page)	 i_rwsem	invalidate_lock
+ops			folio locked		 i_rwsem	invalidate_lock
 ======================	======================== =========	===============
 writepage:		yes, unlocks (see below)
 read_folio:		yes, unlocks				shared
@@ -277,7 +277,7 @@ write_end:		yes, unlocks		 exclusive
 bmap:
 invalidate_folio:	yes					exclusive
 release_folio:		yes
-freepage:		yes
+free_folio:		yes
 direct_IO:
 isolate_page:		yes
 migratepage:		yes (both)
@@ -377,7 +377,7 @@ buffers from the folio in preparation for freeing it.  It returns false to
 indicate that the buffers are (or may be) freeable.  If ->release_folio is
 NULL, the kernel assumes that the fs has no private interest in the buffers.
 
-->freepage() is called when the kernel is done dropping the page
+->free_folio() is called when the kernel has dropped the folio
 from the page cache.
 
 ->launder_folio() may be called prior to releasing a folio if
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 679887b5c8fc..12a011d2cbc6 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -735,7 +735,7 @@ cache in your filesystem.  The following members are defined:
 		sector_t (*bmap)(struct address_space *, sector_t);
 		void (*invalidate_folio) (struct folio *, size_t start, size_t len);
 		bool (*release_folio)(struct folio *, gfp_t);
-		void (*freepage)(struct page *);
+		void (*free_folio)(struct folio *);
 		ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 		/* isolate a page for migration */
 		bool (*isolate_page) (struct page *, isolate_mode_t);
@@ -891,8 +891,8 @@ cache in your filesystem.  The following members are defined:
 	its release_folio will need to ensure this.  Possibly it can
 	clear the uptodate flag if it cannot free private data yet.
 
-``freepage``
-	freepage is called once the page is no longer visible in the
+``free_folio``
+	free_folio is called once the folio is no longer visible in the
 	page cache in order to allow the cleanup of any private data.
 	Since it may be called by the memory reclaimer, it should not
 	assume that the original address_space mapping still exists, and
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1cee64d9724b..915844e6293e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -356,6 +356,7 @@ struct address_space_operations {
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidate_folio) (struct folio *, size_t offset, size_t len);
 	bool (*release_folio)(struct folio *, gfp_t);
+	void (*free_folio)(struct folio *folio);
 	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 	/*
diff --git a/mm/filemap.c b/mm/filemap.c
index d335a154a0d9..adcdef56890f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -226,8 +226,12 @@ void __filemap_remove_folio(struct folio *folio, void *shadow)
 void filemap_free_folio(struct address_space *mapping, struct folio *folio)
 {
 	void (*freepage)(struct page *);
+	void (*free_folio)(struct folio *);
 	int refs = 1;
 
+	free_folio = mapping->a_ops->free_folio;
+	if (free_folio)
+		free_folio(folio);
 	freepage = mapping->a_ops->freepage;
 	if (freepage)
 		freepage(&folio->page);
@@ -807,6 +811,7 @@ void replace_page_cache_page(struct page *old, struct page *new)
 	struct folio *fold = page_folio(old);
 	struct folio *fnew = page_folio(new);
 	struct address_space *mapping = old->mapping;
+	void (*free_folio)(struct folio *) = mapping->a_ops->free_folio;
 	void (*freepage)(struct page *) = mapping->a_ops->freepage;
 	pgoff_t offset = old->index;
 	XA_STATE(xas, &mapping->i_pages, offset);
@@ -835,9 +840,11 @@ void replace_page_cache_page(struct page *old, struct page *new)
 	if (PageSwapBacked(new))
 		__inc_lruvec_page_state(new, NR_SHMEM);
 	xas_unlock_irq(&xas);
+	if (free_folio)
+		free_folio(fold);
 	if (freepage)
 		freepage(old);
-	put_page(old);
+	folio_put(fold);
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f3f7ce2c4068..d8a031128ad0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1282,8 +1282,10 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 		xa_unlock_irq(&mapping->i_pages);
 		put_swap_page(&folio->page, swap);
 	} else {
+		void (*free_folio)(struct folio *);
 		void (*freepage)(struct page *);
 
+		free_folio = mapping->a_ops->free_folio;
 		freepage = mapping->a_ops->freepage;
 		/*
 		 * Remember a shadow entry for reclaimed file cache in
@@ -1310,7 +1312,9 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 			inode_add_lru(mapping->host);
 		spin_unlock(&mapping->host->i_lock);
 
-		if (freepage != NULL)
+		if (free_folio)
+			free_folio(folio);
+		if (freepage)
 			freepage(&folio->page);
 	}
 
-- 
cgit v1.2.3


From 8560cb1a7d75048af275dd23fb0cf05382b3c2b9 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 5 May 2022 00:43:09 -0400
Subject: fs: Remove aops->freepage

All implementations now use free_folio so we can delete the callers
and the method.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/fs.h | 1 -
 mm/filemap.c       | 7 -------
 mm/vmscan.c        | 4 ----
 3 files changed, 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 915844e6293e..6f305f1097a5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -357,7 +357,6 @@ struct address_space_operations {
 	void (*invalidate_folio) (struct folio *, size_t offset, size_t len);
 	bool (*release_folio)(struct folio *, gfp_t);
 	void (*free_folio)(struct folio *folio);
-	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 	/*
 	 * migrate the contents of a page to the specified target. If
diff --git a/mm/filemap.c b/mm/filemap.c
index adcdef56890f..fa0ca674450f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -225,16 +225,12 @@ void __filemap_remove_folio(struct folio *folio, void *shadow)
 
 void filemap_free_folio(struct address_space *mapping, struct folio *folio)
 {
-	void (*freepage)(struct page *);
 	void (*free_folio)(struct folio *);
 	int refs = 1;
 
 	free_folio = mapping->a_ops->free_folio;
 	if (free_folio)
 		free_folio(folio);
-	freepage = mapping->a_ops->freepage;
-	if (freepage)
-		freepage(&folio->page);
 
 	if (folio_test_large(folio) && !folio_test_hugetlb(folio))
 		refs = folio_nr_pages(folio);
@@ -812,7 +808,6 @@ void replace_page_cache_page(struct page *old, struct page *new)
 	struct folio *fnew = page_folio(new);
 	struct address_space *mapping = old->mapping;
 	void (*free_folio)(struct folio *) = mapping->a_ops->free_folio;
-	void (*freepage)(struct page *) = mapping->a_ops->freepage;
 	pgoff_t offset = old->index;
 	XA_STATE(xas, &mapping->i_pages, offset);
 
@@ -842,8 +837,6 @@ void replace_page_cache_page(struct page *old, struct page *new)
 	xas_unlock_irq(&xas);
 	if (free_folio)
 		free_folio(fold);
-	if (freepage)
-		freepage(old);
 	folio_put(fold);
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d8a031128ad0..edc89f26b738 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1283,10 +1283,8 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 		put_swap_page(&folio->page, swap);
 	} else {
 		void (*free_folio)(struct folio *);
-		void (*freepage)(struct page *);
 
 		free_folio = mapping->a_ops->free_folio;
-		freepage = mapping->a_ops->freepage;
 		/*
 		 * Remember a shadow entry for reclaimed file cache in
 		 * order to detect refaults, thus thrashing, later on.
@@ -1314,8 +1312,6 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 
 		if (free_folio)
 			free_folio(folio);
-		if (freepage)
-			freepage(&folio->page);
 	}
 
 	return 1;
-- 
cgit v1.2.3


From 8324a02c342a36336114a497130826612ed5520d Mon Sep 17 00:00:00 2001
From: Gavin Li <gavinl@nvidia.com>
Date: Sun, 27 Mar 2022 17:45:32 +0300
Subject: net/mlx5: Add exit route when waiting for FW

Currently, removing a device needs to get the driver interface lock before
doing any cleanup. If the driver is waiting in a loop for FW init, there
is no way to cancel the wait, instead the device cleanup waits for the
loop to conclude and release the lock.

To allow immediate response to remove device commands, check the TEARDOWN
flag while waiting for FW init, and exit the loop if it has been set.

Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 ++++-
 include/linux/mlx5/driver.h                    | 1 +
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 35e48ef04845..f28a3526aafa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -189,7 +189,8 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
 		fw_initializing = ioread32be(&dev->iseg->initializing);
 		if (!(fw_initializing >> 31))
 			break;
-		if (time_after(jiffies, end)) {
+		if (time_after(jiffies, end) ||
+		    test_and_clear_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state)) {
 			err = -EBUSY;
 			break;
 		}
@@ -1602,6 +1603,7 @@ static void remove_one(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
 
+	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
 	devlink_unregister(devlink);
 	mlx5_sriov_disable(pdev);
 	mlx5_crdump_disable(dev);
@@ -1785,6 +1787,7 @@ static void shutdown(struct pci_dev *pdev)
 	int err;
 
 	mlx5_core_info(dev, "Shutdown was called\n");
+	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
 	err = mlx5_try_fast_unload(dev);
 	if (err)
 		mlx5_unload_one(dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ff47d49d8be4..f327d0544038 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -632,6 +632,7 @@ enum mlx5_device_state {
 
 enum mlx5_interface_state {
 	MLX5_INTERFACE_STATE_UP = BIT(0),
+	MLX5_BREAK_FW_WAIT = BIT(1),
 };
 
 enum mlx5_pci_status {
-- 
cgit v1.2.3


From 34a30d7635a8e37275a7b63bec09035ed762969b Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 1 Mar 2022 15:42:01 +0000
Subject: net/mlx5: Lag, expose number of lag ports

Downstream patches will add support for hardware lag with
more than 2 ports. Add a way for users to query the number of lag ports.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/gsi.c                  | 2 +-
 drivers/infiniband/hw/mlx5/main.c                 | 1 +
 drivers/infiniband/hw/mlx5/mlx5_ib.h              | 1 +
 drivers/infiniband/hw/mlx5/qp.c                   | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 6 ++++++
 include/linux/mlx5/driver.h                       | 1 +
 6 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/gsi.c b/drivers/infiniband/hw/mlx5/gsi.c
index 3ad8f637c589..b804f2dd5628 100644
--- a/drivers/infiniband/hw/mlx5/gsi.c
+++ b/drivers/infiniband/hw/mlx5/gsi.c
@@ -100,7 +100,7 @@ int mlx5_ib_create_gsi(struct ib_pd *pd, struct mlx5_ib_qp *mqp,
 				 port_type) == MLX5_CAP_PORT_TYPE_IB)
 			num_qps = pd->device->attrs.max_pkeys;
 		else if (dev->lag_active)
-			num_qps = MLX5_MAX_PORTS;
+			num_qps = dev->lag_ports;
 	}
 
 	gsi = &mqp->gsi;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 61aa196d6484..61a3b767262f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2991,6 +2991,7 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)
 	}
 
 	dev->flow_db->lag_demux_ft = ft;
+	dev->lag_ports = mlx5_lag_get_num_ports(mdev);
 	dev->lag_active = true;
 	return 0;
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 4f04bb55c4c6..8b3c83c0b70a 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1131,6 +1131,7 @@ struct mlx5_ib_dev {
 	struct xarray sig_mrs;
 	struct mlx5_port_caps port_caps[MLX5_MAX_PORTS];
 	u16 pkey_table_len;
+	u8 lag_ports;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 3f467557d34e..fb8669c02546 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3907,7 +3907,7 @@ static unsigned int get_tx_affinity_rr(struct mlx5_ib_dev *dev,
 		tx_port_affinity = &dev->port[port_num].roce.tx_port_affinity;
 
 	return (unsigned int)atomic_add_return(1, tx_port_affinity) %
-		MLX5_MAX_PORTS + 1;
+		(dev->lag_active ? dev->lag_ports : MLX5_CAP_GEN(dev->mdev, num_lag_ports)) + 1;
 }
 
 static bool qp_supports_affinity(struct mlx5_ib_qp *qp)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 6cad3b72c133..fe34cce77d07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1185,6 +1185,12 @@ unlock:
 }
 EXPORT_SYMBOL(mlx5_lag_get_slave_port);
 
+u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev)
+{
+	return MLX5_MAX_PORTS;
+}
+EXPORT_SYMBOL(mlx5_lag_get_num_ports);
+
 struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_dev *peer_dev = NULL;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f327d0544038..62ea1120de9c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1142,6 +1142,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 				 int num_counters,
 				 size_t *offsets);
 struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev);
+u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev);
 struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
 void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
 int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
-- 
cgit v1.2.3


From 4cd14d44b11dabf195d1e66dadbb954336224658 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 1 Mar 2022 17:34:58 +0000
Subject: net/mlx5: Support devices with more than 2 ports

Increase the define MLX5_MAX_PORTS to 4 as the driver is ready
to support NICs with 4 ports.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c     | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 3 ++-
 include/linux/mlx5/driver.h                       | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 3e750b827a19..11f7c03ae81b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -586,7 +586,8 @@ static int next_phys_dev_lag(struct device *dev, const void *data)
 
 	if (!MLX5_CAP_GEN(mdev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(mdev, lag_master) ||
-	    MLX5_CAP_GEN(mdev, num_lag_ports) != MLX5_MAX_PORTS)
+	    (MLX5_CAP_GEN(mdev, num_lag_ports) > MLX5_MAX_PORTS ||
+	     MLX5_CAP_GEN(mdev, num_lag_ports) <= 1))
 		return 0;
 
 	return _next_phys_dev(mdev, data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index f2659b0f8cc5..716e073c80d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1050,7 +1050,8 @@ void mlx5_lag_add_mdev(struct mlx5_core_dev *dev)
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(dev, lag_master) ||
-	    MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS)
+	    (MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_MAX_PORTS ||
+	     MLX5_CAP_GEN(dev, num_lag_ports) <= 1))
 		return;
 
 recheck:
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 62ea1120de9c..fdb9d07a05a4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -84,7 +84,7 @@ enum mlx5_sqp_t {
 };
 
 enum {
-	MLX5_MAX_PORTS	= 2,
+	MLX5_MAX_PORTS	= 4,
 };
 
 enum {
-- 
cgit v1.2.3


From 7f46a0b7327ae261f9981888708dbca22c283900 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 15 Mar 2022 16:56:50 +0000
Subject: net/mlx5: Lag, add debugfs to query hardware lag state

Lag state has become very complicated with many modes, flags, types and
port selections methods and future work will add additional features.

Add a debugfs to query the current lag state. A new directory named "lag"
will be created under the mlx5 debugfs directory. As the driver has
debugfs per pci function the location will be: <debugfs>/mlx5/<BDF>/lag

For example:
/sys/kernel/debug/mlx5/0000:08:00.0/lag

The following files are exposed:

- state: Returns "active" or "disabled". If "active" it means hardware
         lag is active.

- members: Returns the BDFs of all the members of lag object.

- type: Returns the type of the lag currently configured. Valid only
	if hardware lag is active.
	* "roce" - Members are bare metal PFs.
	* "switchdev" - Members are in switchdev mode.
	* "multipath" - ECMP offloads.

- port_sel_mode: Returns the egress port selection method, valid
		 only if hardware lag is active.
		 * "queue_affinity" - Egress port is selected by
		   the QP/SQ affinity.
		 * "hash" - Egress port is selected by hash done on
		   each packet. Controlled by: xmit_hash_policy of the
		   bond device.
- flags: Returns flags that are specific per lag @type. Valid only if
	 hardware lag is active.
	 * "shared_fdb" - "on" or "off", if "on" single FDB is used.

- mapping: Returns the mapping which is used to select egress port.
	   Valid only if hardware lag is active.
	   If @port_sel_mode is "hash" returns the active egress ports.
	   The hash result will select only active ports.
	   if @port_sel_mode is "queue_affinity" returns the mapping
	   between the configured port affinity of the QP/SQ and actual
	   egress port. For example:
	   * 1:1 - Mapping means if the configured affinity is port 1
	           traffic will egress via port 1.
	   * 1:2 - Mapping means if the configured affinity is port 1
		   traffic will egress via port 2. This can happen
		   if port 1 is down or in active/backup mode and port 1
		   is backup.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 .../net/ethernet/mellanox/mlx5/core/lag/debugfs.c  | 173 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c  |  11 +-
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h  |   9 ++
 include/linux/mlx5/driver.h                        |   1 +
 5 files changed, 192 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 81620c25c77e..7895ed7cc285 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o port.o mr.o pd.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
-		fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \
+		fs_counters.o fs_ft_pool.o rl.o lag/debugfs.o lag/lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
 		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \
 		fw_reset.o qos.o lib/tout.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
new file mode 100644
index 000000000000..443daf6e3d4b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "lag.h"
+
+static char *get_str_mode_type(struct mlx5_lag *ldev)
+{
+	if (ldev->flags & MLX5_LAG_FLAG_ROCE)
+		return "roce";
+	if (ldev->flags & MLX5_LAG_FLAG_SRIOV)
+		return "switchdev";
+	if (ldev->flags & MLX5_LAG_FLAG_MULTIPATH)
+		return "multipath";
+
+	return NULL;
+}
+
+static int type_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	char *mode = NULL;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	if (__mlx5_lag_is_active(ldev))
+		mode = get_str_mode_type(ldev);
+	mutex_unlock(&ldev->lock);
+	if (!mode)
+		return -EINVAL;
+	seq_printf(file, "%s\n", mode);
+
+	return 0;
+}
+
+static int port_sel_mode_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	int ret = 0;
+	char *mode;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	if (__mlx5_lag_is_active(ldev))
+		mode = get_str_port_sel_mode(ldev->flags);
+	else
+		ret = -EINVAL;
+	mutex_unlock(&ldev->lock);
+	if (ret || !mode)
+		return ret;
+
+	seq_printf(file, "%s\n", mode);
+	return 0;
+}
+
+static int state_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	bool active;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	active = __mlx5_lag_is_active(ldev);
+	mutex_unlock(&ldev->lock);
+	seq_printf(file, "%s\n", active ? "active" : "disabled");
+	return 0;
+}
+
+static int flags_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	bool shared_fdb;
+	bool lag_active;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	lag_active = __mlx5_lag_is_active(ldev);
+	if (lag_active)
+		shared_fdb = ldev->shared_fdb;
+
+	mutex_unlock(&ldev->lock);
+	if (!lag_active)
+		return -EINVAL;
+
+	seq_printf(file, "%s:%s\n", "shared_fdb", shared_fdb ? "on" : "off");
+	return 0;
+}
+
+static int mapping_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	u8 ports[MLX5_MAX_PORTS] = {};
+	struct mlx5_lag *ldev;
+	bool hash = false;
+	bool lag_active;
+	int num_ports;
+	int i;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	lag_active = __mlx5_lag_is_active(ldev);
+	if (lag_active) {
+		if (ldev->flags & MLX5_LAG_FLAG_HASH_BASED) {
+			mlx5_infer_tx_enabled(&ldev->tracker, ldev->ports, ports,
+					      &num_ports);
+			hash = true;
+		} else {
+			for (i = 0; i < ldev->ports; i++)
+				ports[i] = ldev->v2p_map[i];
+			num_ports = ldev->ports;
+		}
+	}
+	mutex_unlock(&ldev->lock);
+	if (!lag_active)
+		return -EINVAL;
+
+	for (i = 0; i < num_ports; i++) {
+		if (hash)
+			seq_printf(file, "%d\n", ports[i] + 1);
+		else
+			seq_printf(file, "%d:%d\n", i + 1, ports[i]);
+	}
+
+	return 0;
+}
+
+static int members_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	int i;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	for (i = 0; i < ldev->ports; i++) {
+		if (!ldev->pf[i].dev)
+			continue;
+		seq_printf(file, "%s\n", dev_name(ldev->pf[i].dev->device));
+	}
+	mutex_unlock(&ldev->lock);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(type);
+DEFINE_SHOW_ATTRIBUTE(port_sel_mode);
+DEFINE_SHOW_ATTRIBUTE(state);
+DEFINE_SHOW_ATTRIBUTE(flags);
+DEFINE_SHOW_ATTRIBUTE(mapping);
+DEFINE_SHOW_ATTRIBUTE(members);
+
+void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev)
+{
+	struct dentry *dbg;
+
+	dbg = debugfs_create_dir("lag", mlx5_debugfs_get_dev_root(dev));
+	dev->priv.dbg.lag_debugfs = dbg;
+
+	debugfs_create_file("type", 0444, dbg, dev, &type_fops);
+	debugfs_create_file("port_sel_mode", 0444, dbg, dev, &port_sel_mode_fops);
+	debugfs_create_file("state", 0444, dbg, dev, &state_fops);
+	debugfs_create_file("flags", 0444, dbg, dev, &flags_fops);
+	debugfs_create_file("mapping", 0444, dbg, dev, &mapping_fops);
+	debugfs_create_file("members", 0444, dbg, dev, &members_fops);
+}
+
+void mlx5_ldev_remove_debugfs(struct dentry *dbg)
+{
+	debugfs_remove_recursive(dbg);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 8a74c409b501..b6dd9043061f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -120,8 +120,8 @@ static void mlx5_infer_tx_disabled(struct lag_tracker *tracker, u8 num_ports,
 	}
 }
 
-static void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
-				  u8 *ports, int *num_enabled)
+void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
+			   u8 *ports, int *num_enabled)
 {
 	int i;
 
@@ -454,7 +454,7 @@ static int mlx5_lag_set_port_sel_mode(struct mlx5_lag *ldev,
 	return mlx5_lag_set_port_sel_mode_offloads(ldev, tracker, flags);
 }
 
-static char *get_str_port_sel_mode(u8 flags)
+char *get_str_port_sel_mode(u8 flags)
 {
 	if (flags &  MLX5_LAG_FLAG_HASH_BASED)
 		return "hash";
@@ -1106,6 +1106,10 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev)
 	if (!ldev)
 		return;
 
+	/* mdev is being removed, might as well remove debugfs
+	 * as early as possible.
+	 */
+	mlx5_ldev_remove_debugfs(dev->priv.dbg.lag_debugfs);
 recheck:
 	mutex_lock(&ldev->lock);
 	if (ldev->mode_changes_in_progress) {
@@ -1137,6 +1141,7 @@ recheck:
 		msleep(100);
 		goto recheck;
 	}
+	mlx5_ldev_add_debugfs(dev);
 }
 
 void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 0c90d0ed03be..46683b84ff84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -4,6 +4,8 @@
 #ifndef __MLX5_LAG_H__
 #define __MLX5_LAG_H__
 
+#include <linux/debugfs.h>
+
 #define MLX5_LAG_MAX_HASH_BUCKETS 16
 #include "mlx5_core.h"
 #include "mp.h"
@@ -90,4 +92,11 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 				struct net_device *ndev);
 
+char *get_str_port_sel_mode(u8 flags);
+void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
+			   u8 *ports, int *num_enabled);
+
+void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev);
+void mlx5_ldev_remove_debugfs(struct dentry *dbg);
+
 #endif /* __MLX5_LAG_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index fdb9d07a05a4..d6bac3976913 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -558,6 +558,7 @@ struct mlx5_debugfs_entries {
 	struct dentry *cq_debugfs;
 	struct dentry *cmdif_debugfs;
 	struct dentry *pages_debugfs;
+	struct dentry *lag_debugfs;
 };
 
 struct mlx5_ft_pool;
-- 
cgit v1.2.3


From 42704b26b0f1d891f6cf4ebc877dbac0d17c690d Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Fri, 6 May 2022 22:01:37 +0200
Subject: ptp: Add cycles support for virtual clocks

ptp vclocks require a free running time for their timecounter.
Currently only a physical clock forced to free running is supported.
If vclocks are used, then the physical clock cannot be synchronized
anymore. The synchronized time is not available in hardware in this
case. As a result, timed transmission with TAPRIO hardware support
is not possible anymore.

If hardware would support a free running time additionally to the
physical clock, then the physical clock does not need to be forced to
free running. Thus, the physical clocks can still be synchronized
while vclocks are in use.

The physical clock could be used to synchronize the time domain of the
TSN network and trigger TAPRIO. In parallel vclocks can be used to
synchronize other time domains.

Introduce support for a free running cycle counter called cycles to
physical clocks. Rework ptp vclocks to use this free running cycle
counter. Default implementation is based on time of physical clock.
Thus, behavior of ptp vclocks based on physical clocks without free
running cycle counter is identical to previous behavior.

Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/ptp/ptp_clock.c          | 31 +++++++++++++++++++++++++++----
 drivers/ptp/ptp_private.h        | 10 ++++++++++
 drivers/ptp/ptp_sysfs.c          | 11 +++++++----
 drivers/ptp/ptp_vclock.c         | 13 +++++--------
 include/linux/ptp_clock_kernel.h | 31 +++++++++++++++++++++++++++++++
 5 files changed, 80 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index b6f2cfd15dd2..688cde320bb0 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -77,8 +77,8 @@ static int ptp_clock_settime(struct posix_clock *pc, const struct timespec64 *tp
 {
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
 
-	if (ptp_vclock_in_use(ptp)) {
-		pr_err("ptp: virtual clock in use\n");
+	if (ptp_clock_freerun(ptp)) {
+		pr_err("ptp: physical clock is free running\n");
 		return -EBUSY;
 	}
 
@@ -103,8 +103,8 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx)
 	struct ptp_clock_info *ops;
 	int err = -EOPNOTSUPP;
 
-	if (ptp_vclock_in_use(ptp)) {
-		pr_err("ptp: virtual clock in use\n");
+	if (ptp_clock_freerun(ptp)) {
+		pr_err("ptp: physical clock is free running\n");
 		return -EBUSY;
 	}
 
@@ -178,6 +178,14 @@ static void ptp_clock_release(struct device *dev)
 	kfree(ptp);
 }
 
+static int ptp_getcycles64(struct ptp_clock_info *info, struct timespec64 *ts)
+{
+	if (info->getcyclesx64)
+		return info->getcyclesx64(info, ts, NULL);
+	else
+		return info->gettime64(info, ts);
+}
+
 static void ptp_aux_kworker(struct kthread_work *work)
 {
 	struct ptp_clock *ptp = container_of(work, struct ptp_clock,
@@ -225,6 +233,21 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	mutex_init(&ptp->n_vclocks_mux);
 	init_waitqueue_head(&ptp->tsev_wq);
 
+	if (ptp->info->getcycles64 || ptp->info->getcyclesx64) {
+		ptp->has_cycles = true;
+		if (!ptp->info->getcycles64 && ptp->info->getcyclesx64)
+			ptp->info->getcycles64 = ptp_getcycles64;
+	} else {
+		/* Free running cycle counter not supported, use time. */
+		ptp->info->getcycles64 = ptp_getcycles64;
+
+		if (ptp->info->gettimex64)
+			ptp->info->getcyclesx64 = ptp->info->gettimex64;
+
+		if (ptp->info->getcrosststamp)
+			ptp->info->getcrosscycles = ptp->info->getcrosststamp;
+	}
+
 	if (ptp->info->do_aux_work) {
 		kthread_init_delayed_work(&ptp->aux_work, ptp_aux_kworker);
 		ptp->kworker = kthread_create_worker(0, "ptp%d", ptp->index);
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index dba6be477067..ab47c10b3874 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -52,6 +52,7 @@ struct ptp_clock {
 	int *vclock_index;
 	struct mutex n_vclocks_mux; /* protect concurrent n_vclocks access */
 	bool is_virtual_clock;
+	bool has_cycles;
 };
 
 #define info_to_vclock(d) container_of((d), struct ptp_vclock, info)
@@ -96,6 +97,15 @@ static inline bool ptp_vclock_in_use(struct ptp_clock *ptp)
 	return in_use;
 }
 
+/* Check if ptp clock shall be free running */
+static inline bool ptp_clock_freerun(struct ptp_clock *ptp)
+{
+	if (ptp->has_cycles)
+		return false;
+
+	return ptp_vclock_in_use(ptp);
+}
+
 extern struct class *ptp_class;
 
 /*
diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c
index 9233bfedeb17..f30b0a439470 100644
--- a/drivers/ptp/ptp_sysfs.c
+++ b/drivers/ptp/ptp_sysfs.c
@@ -231,10 +231,13 @@ static ssize_t n_vclocks_store(struct device *dev,
 			*(ptp->vclock_index + ptp->n_vclocks - i) = -1;
 	}
 
-	if (num == 0)
-		dev_info(dev, "only physical clock in use now\n");
-	else
-		dev_info(dev, "guarantee physical clock free running\n");
+	/* Need to inform about changed physical clock behavior */
+	if (!ptp->has_cycles) {
+		if (num == 0)
+			dev_info(dev, "only physical clock in use now\n");
+		else
+			dev_info(dev, "guarantee physical clock free running\n");
+	}
 
 	ptp->n_vclocks = num;
 	mutex_unlock(&ptp->n_vclocks_mux);
diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c
index cb179a3ea508..3a095eab9cc5 100644
--- a/drivers/ptp/ptp_vclock.c
+++ b/drivers/ptp/ptp_vclock.c
@@ -68,7 +68,7 @@ static int ptp_vclock_gettimex(struct ptp_clock_info *ptp,
 	int err;
 	u64 ns;
 
-	err = pptp->info->gettimex64(pptp->info, &pts, sts);
+	err = pptp->info->getcyclesx64(pptp->info, &pts, sts);
 	if (err)
 		return err;
 
@@ -104,7 +104,7 @@ static int ptp_vclock_getcrosststamp(struct ptp_clock_info *ptp,
 	int err;
 	u64 ns;
 
-	err = pptp->info->getcrosststamp(pptp->info, xtstamp);
+	err = pptp->info->getcrosscycles(pptp->info, xtstamp);
 	if (err)
 		return err;
 
@@ -143,10 +143,7 @@ static u64 ptp_vclock_read(const struct cyclecounter *cc)
 	struct ptp_clock *ptp = vclock->pclock;
 	struct timespec64 ts = {};
 
-	if (ptp->info->gettimex64)
-		ptp->info->gettimex64(ptp->info, &ts, NULL);
-	else
-		ptp->info->gettime64(ptp->info, &ts);
+	ptp->info->getcycles64(ptp->info, &ts);
 
 	return timespec64_to_ns(&ts);
 }
@@ -168,11 +165,11 @@ struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock)
 
 	vclock->pclock = pclock;
 	vclock->info = ptp_vclock_info;
-	if (pclock->info->gettimex64)
+	if (pclock->info->getcyclesx64)
 		vclock->info.gettimex64 = ptp_vclock_gettimex;
 	else
 		vclock->info.gettime64 = ptp_vclock_gettime;
-	if (pclock->info->getcrosststamp)
+	if (pclock->info->getcrosscycles)
 		vclock->info.getcrosststamp = ptp_vclock_getcrosststamp;
 	vclock->cc = ptp_vclock_cc;
 
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index e8cc8b6bbf50..ad309202cf9f 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -108,6 +108,32 @@ struct ptp_system_timestamp {
  * @settime64:  Set the current time on the hardware clock.
  *              parameter ts: Time value to set.
  *
+ * @getcycles64:  Reads the current free running cycle counter from the hardware
+ *                clock.
+ *                If @getcycles64 and @getcyclesx64 are not supported, then
+ *                @gettime64 or @gettimex64 will be used as default
+ *                implementation.
+ *                parameter ts: Holds the result.
+ *
+ * @getcyclesx64:  Reads the current free running cycle counter from the
+ *                 hardware clock and optionally also the system clock.
+ *                 If @getcycles64 and @getcyclesx64 are not supported, then
+ *                 @gettimex64 will be used as default implementation if
+ *                 available.
+ *                 parameter ts: Holds the PHC timestamp.
+ *                 parameter sts: If not NULL, it holds a pair of timestamps
+ *                 from the system clock. The first reading is made right before
+ *                 reading the lowest bits of the PHC timestamp and the second
+ *                 reading immediately follows that.
+ *
+ * @getcrosscycles:  Reads the current free running cycle counter from the
+ *                   hardware clock and system clock simultaneously.
+ *                   If @getcycles64 and @getcyclesx64 are not supported, then
+ *                   @getcrosststamp will be used as default implementation if
+ *                   available.
+ *                   parameter cts: Contains timestamp (device,system) pair,
+ *                   where system time is realtime and monotonic.
+ *
  * @enable:   Request driver to enable or disable an ancillary feature.
  *            parameter request: Desired resource to enable or disable.
  *            parameter on: Caller passes one to enable or zero to disable.
@@ -155,6 +181,11 @@ struct ptp_clock_info {
 	int (*getcrosststamp)(struct ptp_clock_info *ptp,
 			      struct system_device_crosststamp *cts);
 	int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts);
+	int (*getcycles64)(struct ptp_clock_info *ptp, struct timespec64 *ts);
+	int (*getcyclesx64)(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			    struct ptp_system_timestamp *sts);
+	int (*getcrosscycles)(struct ptp_clock_info *ptp,
+			      struct system_device_crosststamp *cts);
 	int (*enable)(struct ptp_clock_info *ptp,
 		      struct ptp_clock_request *request, int on);
 	int (*verify)(struct ptp_clock_info *ptp, unsigned int pin,
-- 
cgit v1.2.3


From 51eb7492af276b5b4d27cfa4474d40bdac7b9cf8 Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Fri, 6 May 2022 22:01:38 +0200
Subject: ptp: Request cycles for TX timestamp

The free running cycle counter of physical clocks called cycles shall be
used for hardware timestamps to enable synchronisation.

Introduce new flag SKBTX_HW_TSTAMP_USE_CYCLES, which signals driver to
provide a TX timestamp based on cycles if cycles are supported.

Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/skbuff.h |  7 ++++++-
 net/socket.c           | 11 ++++++++++-
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d58669d6cb91..4a4f25975ca2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -615,6 +615,9 @@ enum {
 	/* device driver is going to provide hardware time stamp */
 	SKBTX_IN_PROGRESS = 1 << 2,
 
+	/* generate hardware time stamp based on cycles if supported */
+	SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3,
+
 	/* generate wifi status information (where possible) */
 	SKBTX_WIFI_STATUS = 1 << 4,
 
@@ -624,7 +627,9 @@ enum {
 
 #define SKBTX_ANY_SW_TSTAMP	(SKBTX_SW_TSTAMP    | \
 				 SKBTX_SCHED_TSTAMP)
-#define SKBTX_ANY_TSTAMP	(SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP)
+#define SKBTX_ANY_TSTAMP	(SKBTX_HW_TSTAMP | \
+				 SKBTX_HW_TSTAMP_USE_CYCLES | \
+				 SKBTX_ANY_SW_TSTAMP)
 
 /* Definitions for flags in struct skb_shared_info */
 enum {
diff --git a/net/socket.c b/net/socket.c
index f0c39c874665..5c1c5e6100e1 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -683,9 +683,18 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
 {
 	u8 flags = *tx_flags;
 
-	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE)
+	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) {
 		flags |= SKBTX_HW_TSTAMP;
 
+		/* PTP hardware clocks can provide a free running cycle counter
+		 * as a time base for virtual clocks. Tell driver to use the
+		 * free running cycle counter for timestamp if socket is bound
+		 * to virtual clock.
+		 */
+		if (tsflags & SOF_TIMESTAMPING_BIND_PHC)
+			flags |= SKBTX_HW_TSTAMP_USE_CYCLES;
+	}
+
 	if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE)
 		flags |= SKBTX_SW_TSTAMP;
 
-- 
cgit v1.2.3


From d58809d854c9ee19e4cd41023e137e65e9dc3f94 Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Fri, 6 May 2022 22:01:39 +0200
Subject: ptp: Pass hwtstamp to ptp_convert_timestamp()

ptp_convert_timestamp() converts only the timestamp hwtstamp, which is
a field of the argument with the type struct skb_shared_hwtstamps *. So
a pointer to the hwtstamp field of this structure is sufficient.

Rework ptp_convert_timestamp() to use an argument of type ktime_t *.
This allows to add additional timestamp manipulation stages before the
call of ptp_convert_timestamp().

Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/ptp/ptp_vclock.c         | 5 ++---
 include/linux/ptp_clock_kernel.h | 7 +++----
 net/socket.c                     | 2 +-
 3 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c
index 3a095eab9cc5..c30bcce2bb43 100644
--- a/drivers/ptp/ptp_vclock.c
+++ b/drivers/ptp/ptp_vclock.c
@@ -232,8 +232,7 @@ out:
 }
 EXPORT_SYMBOL(ptp_get_vclocks_index);
 
-ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps,
-			      int vclock_index)
+ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index)
 {
 	char name[PTP_CLOCK_NAME_LEN] = "";
 	struct ptp_vclock *vclock;
@@ -255,7 +254,7 @@ ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps,
 
 	vclock = info_to_vclock(ptp->info);
 
-	ns = ktime_to_ns(hwtstamps->hwtstamp);
+	ns = ktime_to_ns(*hwtstamp);
 
 	spin_lock_irqsave(&vclock->lock, flags);
 	ns = timecounter_cyc2time(&vclock->tc, ns);
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index ad309202cf9f..92b44161408e 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -384,17 +384,16 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index);
 /**
  * ptp_convert_timestamp() - convert timestamp to a ptp vclock time
  *
- * @hwtstamps:    skb_shared_hwtstamps structure pointer
+ * @hwtstamp:     timestamp
  * @vclock_index: phc index of ptp vclock.
  *
  * Returns converted timestamp, or 0 on error.
  */
-ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps,
-			      int vclock_index);
+ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index);
 #else
 static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index)
 { return 0; }
-static inline ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps,
+static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp,
 					    int vclock_index)
 { return 0; }
 
diff --git a/net/socket.c b/net/socket.c
index 5c1c5e6100e1..0f680c7d968a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -888,7 +888,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	    (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
 	    !skb_is_swtx_tstamp(skb, false_tstamp)) {
 		if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
-			hwtstamp = ptp_convert_timestamp(shhwtstamps,
+			hwtstamp = ptp_convert_timestamp(&shhwtstamps->hwtstamp,
 							 sk->sk_bind_phc);
 		else
 			hwtstamp = shhwtstamps->hwtstamp;
-- 
cgit v1.2.3


From 97dc7cd92ac67f6e05df418df1772ba4a7fbf693 Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Fri, 6 May 2022 22:01:40 +0200
Subject: ptp: Support late timestamp determination

If a physical clock supports a free running cycle counter, then
timestamps shall be based on this time too. For TX it is known in
advance before the transmission if a timestamp based on the free running
cycle counter is needed. For RX it is impossible to know which timestamp
is needed before the packet is received and assigned to a socket.

Support late timestamp determination by a network device. Therefore, an
address/cookie is stored within the new netdev_data field of struct
skb_shared_hwtstamps. This address/cookie is provided to a new network
device function called ndo_get_tstamp(), which returns a timestamp based
on the normal/adjustable time or based on the free running cycle
counter. If function is not supported, then timestamp handling is not
changed.

This mechanism is intended for RX, but TX use is also possible.

Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h | 21 ++++++++++++++++++++
 include/linux/skbuff.h    | 14 +++++++++++---
 net/socket.c              | 49 +++++++++++++++++++++++++++++++++++++----------
 3 files changed, 71 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 74c97a34921d..51fe143091cf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1356,6 +1356,12 @@ struct netdev_net_notifier {
  *	The caller must be under RCU read context.
  * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path);
  *     Get the forwarding path to reach the real device from the HW destination address
+ * ktime_t (*ndo_get_tstamp)(struct net_device *dev,
+ *			     const struct skb_shared_hwtstamps *hwtstamps,
+ *			     bool cycles);
+ *	Get hardware timestamp based on normal/adjustable time or free running
+ *	cycle counter. This function is required if physical clock supports a
+ *	free running cycle counter.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1578,6 +1584,9 @@ struct net_device_ops {
 	struct net_device *	(*ndo_get_peer_dev)(struct net_device *dev);
 	int                     (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
                                                          struct net_device_path *path);
+	ktime_t			(*ndo_get_tstamp)(struct net_device *dev,
+						  const struct skb_shared_hwtstamps *hwtstamps,
+						  bool cycles);
 };
 
 /**
@@ -4761,6 +4770,18 @@ static inline void netdev_rx_csum_fault(struct net_device *dev,
 void net_enable_timestamp(void);
 void net_disable_timestamp(void);
 
+static inline ktime_t netdev_get_tstamp(struct net_device *dev,
+					const struct skb_shared_hwtstamps *hwtstamps,
+					bool cycles)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (ops->ndo_get_tstamp)
+		return ops->ndo_get_tstamp(dev, hwtstamps, cycles);
+
+	return hwtstamps->hwtstamp;
+}
+
 static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
 					      struct sk_buff *skb, struct net_device *dev,
 					      bool more)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4a4f25975ca2..97de40bcfef6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -588,8 +588,10 @@ static inline bool skb_frag_must_loop(struct page *p)
 
 /**
  * struct skb_shared_hwtstamps - hardware time stamps
- * @hwtstamp:	hardware time stamp transformed into duration
- *		since arbitrary point in time
+ * @hwtstamp:		hardware time stamp transformed into duration
+ *			since arbitrary point in time
+ * @netdev_data:	address/cookie of network device driver used as
+ *			reference to actual hardware time stamp
  *
  * Software time stamps generated by ktime_get_real() are stored in
  * skb->tstamp.
@@ -601,7 +603,10 @@ static inline bool skb_frag_must_loop(struct page *p)
  * &skb_shared_info. Use skb_hwtstamps() to get a pointer.
  */
 struct skb_shared_hwtstamps {
-	ktime_t	hwtstamp;
+	union {
+		ktime_t	hwtstamp;
+		void *netdev_data;
+	};
 };
 
 /* Definitions for tx_flags in struct skb_shared_info */
@@ -621,6 +626,9 @@ enum {
 	/* generate wifi status information (where possible) */
 	SKBTX_WIFI_STATUS = 1 << 4,
 
+	/* determine hardware time stamp based on time or cycles */
+	SKBTX_HW_TSTAMP_NETDEV = 1 << 5,
+
 	/* generate software time stamp when entering packet scheduling */
 	SKBTX_SCHED_TSTAMP = 1 << 6,
 };
diff --git a/net/socket.c b/net/socket.c
index 0f680c7d968a..6ee634c01eca 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -805,7 +805,28 @@ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp)
 	return skb->tstamp && !false_tstamp && skb_is_err_queue(skb);
 }
 
-static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb)
+static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index)
+{
+	bool cycles = sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC;
+	struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
+	struct net_device *orig_dev;
+	ktime_t hwtstamp;
+
+	rcu_read_lock();
+	orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
+	if (orig_dev) {
+		*if_index = orig_dev->ifindex;
+		hwtstamp = netdev_get_tstamp(orig_dev, shhwtstamps, cycles);
+	} else {
+		hwtstamp = shhwtstamps->hwtstamp;
+	}
+	rcu_read_unlock();
+
+	return hwtstamp;
+}
+
+static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb,
+			   int if_index)
 {
 	struct scm_ts_pktinfo ts_pktinfo;
 	struct net_device *orig_dev;
@@ -815,11 +836,14 @@ static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 
 	memset(&ts_pktinfo, 0, sizeof(ts_pktinfo));
 
-	rcu_read_lock();
-	orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
-	if (orig_dev)
-		ts_pktinfo.if_index = orig_dev->ifindex;
-	rcu_read_unlock();
+	if (!if_index) {
+		rcu_read_lock();
+		orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
+		if (orig_dev)
+			if_index = orig_dev->ifindex;
+		rcu_read_unlock();
+	}
+	ts_pktinfo.if_index = if_index;
 
 	ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb);
 	put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO,
@@ -839,6 +863,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	int empty = 1, false_tstamp = 0;
 	struct skb_shared_hwtstamps *shhwtstamps =
 		skb_hwtstamps(skb);
+	int if_index;
 	ktime_t hwtstamp;
 
 	/* Race occurred between timestamp enabling and packet
@@ -887,18 +912,22 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	if (shhwtstamps &&
 	    (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
 	    !skb_is_swtx_tstamp(skb, false_tstamp)) {
-		if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
-			hwtstamp = ptp_convert_timestamp(&shhwtstamps->hwtstamp,
-							 sk->sk_bind_phc);
+		if_index = 0;
+		if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV)
+			hwtstamp = get_timestamp(sk, skb, &if_index);
 		else
 			hwtstamp = shhwtstamps->hwtstamp;
 
+		if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
+			hwtstamp = ptp_convert_timestamp(&hwtstamp,
+							 sk->sk_bind_phc);
+
 		if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) {
 			empty = 0;
 
 			if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
 			    !skb_is_err_queue(skb))
-				put_ts_pktinfo(msg, skb);
+				put_ts_pktinfo(msg, skb, if_index);
 		}
 	}
 	if (!empty) {
-- 
cgit v1.2.3


From 57ce2e406fe1fa005e8fdbf20936c791252ac7bc Mon Sep 17 00:00:00 2001
From: Nava kishore Manne <nava.manne@xilinx.com>
Date: Sat, 23 Apr 2022 22:32:32 +0530
Subject: fpga: fix for coding style issues

fixes the below checks reported by checkpatch.pl:
- Lines should not end with a '('
- Alignment should match open parenthesis

Signed-off-by: Nava kishore Manne <nava.manne@xilinx.com>
Link: https://lore.kernel.org/r/20220423170235.2115479-3-nava.manne@xilinx.com
Signed-off-by: Xu Yilun <yilun.xu@intel.com>
---
 drivers/fpga/fpga-mgr.c          | 9 +++++----
 drivers/fpga/fpga-region.c       | 6 +++---
 drivers/fpga/of-fpga-region.c    | 6 +++---
 include/linux/fpga/fpga-region.h | 6 +++---
 4 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c
index d49a9ce34568..24dee27c7897 100644
--- a/drivers/fpga/fpga-mgr.c
+++ b/drivers/fpga/fpga-mgr.c
@@ -148,11 +148,12 @@ static int fpga_mgr_write_init_buf(struct fpga_manager *mgr,
 	int ret;
 
 	mgr->state = FPGA_MGR_STATE_WRITE_INIT;
-	if (!mgr->mops->initial_header_size)
+	if (!mgr->mops->initial_header_size) {
 		ret = fpga_mgr_write_init(mgr, info, NULL, 0);
-	else
-		ret = fpga_mgr_write_init(
-		    mgr, info, buf, min(mgr->mops->initial_header_size, count));
+	} else {
+		count = min(mgr->mops->initial_header_size, count);
+		ret = fpga_mgr_write_init(mgr, info, buf, count);
+	}
 
 	if (ret) {
 		dev_err(&mgr->dev, "Error preparing FPGA for writing\n");
diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c
index b0ac18de4885..485948e3c0db 100644
--- a/drivers/fpga/fpga-region.c
+++ b/drivers/fpga/fpga-region.c
@@ -18,9 +18,9 @@
 static DEFINE_IDA(fpga_region_ida);
 static struct class *fpga_region_class;
 
-struct fpga_region *fpga_region_class_find(
-	struct device *start, const void *data,
-	int (*match)(struct device *, const void *))
+struct fpga_region *
+fpga_region_class_find(struct device *start, const void *data,
+		       int (*match)(struct device *, const void *))
 {
 	struct device *dev;
 
diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c
index 50b83057c048..a598d03626af 100644
--- a/drivers/fpga/of-fpga-region.c
+++ b/drivers/fpga/of-fpga-region.c
@@ -189,9 +189,9 @@ static int child_regions_with_firmware(struct device_node *overlay)
  *   fpga_image_info struct if there is an image to program.
  *   error code for invalid overlay.
  */
-static struct fpga_image_info *of_fpga_region_parse_ov(
-						struct fpga_region *region,
-						struct device_node *overlay)
+static struct fpga_image_info *
+of_fpga_region_parse_ov(struct fpga_region *region,
+			struct device_node *overlay)
 {
 	struct device *dev = &region->dev;
 	struct fpga_image_info *info;
diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h
index 3b87f232425c..9d4d32909340 100644
--- a/include/linux/fpga/fpga-region.h
+++ b/include/linux/fpga/fpga-region.h
@@ -52,9 +52,9 @@ struct fpga_region {
 
 #define to_fpga_region(d) container_of(d, struct fpga_region, dev)
 
-struct fpga_region *fpga_region_class_find(
-	struct device *start, const void *data,
-	int (*match)(struct device *, const void *));
+struct fpga_region *
+fpga_region_class_find(struct device *start, const void *data,
+		       int (*match)(struct device *, const void *));
 
 int fpga_region_program_fpga(struct fpga_region *region);
 
-- 
cgit v1.2.3


From 846e437387e74c44ddc9f3eeec472fd37ca3cdb9 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 10 May 2022 12:02:03 +0300
Subject: net/mlx5: Expose mlx5_sriov_blocking_notifier_register / unregister
 APIs

Expose mlx5_sriov_blocking_notifier_register / unregister APIs to let a
VF register to be notified for its enablement / disablement by the PF.

Upon VF probe it will call mlx5_sriov_blocking_notifier_register() with
its notifier block and upon VF remove it will call
mlx5_sriov_blocking_notifier_unregister() to drop its registration.

This can give a VF the ability to clean some resources upon disable
before that the command interface goes down and on the other hand sets
some stuff before that it's enabled.

This may be used by a VF which is migration capable in few cases.(e.g.
PF load/unload upon an health recovery).

Link: https://lore.kernel.org/r/20220510090206.90374-2-yishaih@nvidia.com
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 65 ++++++++++++++++++++++++-
 include/linux/mlx5/driver.h                     | 12 +++++
 2 files changed, 76 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 887ee0f729d1..2935614f6fa9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -87,6 +87,11 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 enable_vfs_hca:
 	num_msix_count = mlx5_get_default_msix_vec_count(dev, num_vfs);
 	for (vf = 0; vf < num_vfs; vf++) {
+		/* Notify the VF before its enablement to let it set
+		 * some stuff.
+		 */
+		blocking_notifier_call_chain(&sriov->vfs_ctx[vf].notifier,
+					     MLX5_PF_NOTIFY_ENABLE_VF, dev);
 		err = mlx5_core_enable_hca(dev, vf + 1);
 		if (err) {
 			mlx5_core_warn(dev, "failed to enable VF %d (%d)\n", vf, err);
@@ -127,6 +132,11 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf)
 	for (vf = num_vfs - 1; vf >= 0; vf--) {
 		if (!sriov->vfs_ctx[vf].enabled)
 			continue;
+		/* Notify the VF before its disablement to let it clean
+		 * some resources.
+		 */
+		blocking_notifier_call_chain(&sriov->vfs_ctx[vf].notifier,
+					     MLX5_PF_NOTIFY_DISABLE_VF, dev);
 		err = mlx5_core_disable_hca(dev, vf + 1);
 		if (err) {
 			mlx5_core_warn(dev, "failed to disable VF %d\n", vf);
@@ -257,7 +267,7 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
 	struct pci_dev *pdev = dev->pdev;
-	int total_vfs;
+	int total_vfs, i;
 
 	if (!mlx5_core_is_pf(dev))
 		return 0;
@@ -269,6 +279,9 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 	if (!sriov->vfs_ctx)
 		return -ENOMEM;
 
+	for (i = 0; i < total_vfs; i++)
+		BLOCKING_INIT_NOTIFIER_HEAD(&sriov->vfs_ctx[i].notifier);
+
 	return 0;
 }
 
@@ -281,3 +294,53 @@ void mlx5_sriov_cleanup(struct mlx5_core_dev *dev)
 
 	kfree(sriov->vfs_ctx);
 }
+
+/**
+ * mlx5_sriov_blocking_notifier_unregister - Unregister a VF from
+ * a notification block chain.
+ *
+ * @mdev: The mlx5 core device.
+ * @vf_id: The VF id.
+ * @nb: The notifier block to be unregistered.
+ */
+void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev,
+					     int vf_id,
+					     struct notifier_block *nb)
+{
+	struct mlx5_vf_context *vfs_ctx;
+	struct mlx5_core_sriov *sriov;
+
+	sriov = &mdev->priv.sriov;
+	if (WARN_ON(vf_id < 0 || vf_id >= sriov->num_vfs))
+		return;
+
+	vfs_ctx = &sriov->vfs_ctx[vf_id];
+	blocking_notifier_chain_unregister(&vfs_ctx->notifier, nb);
+}
+EXPORT_SYMBOL(mlx5_sriov_blocking_notifier_unregister);
+
+/**
+ * mlx5_sriov_blocking_notifier_register - Register a VF notification
+ * block chain.
+ *
+ * @mdev: The mlx5 core device.
+ * @vf_id: The VF id.
+ * @nb: The notifier block to be called upon the VF events.
+ *
+ * Returns 0 on success or an error code.
+ */
+int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev,
+					  int vf_id,
+					  struct notifier_block *nb)
+{
+	struct mlx5_vf_context *vfs_ctx;
+	struct mlx5_core_sriov *sriov;
+
+	sriov = &mdev->priv.sriov;
+	if (vf_id < 0 || vf_id >= sriov->num_vfs)
+		return -EINVAL;
+
+	vfs_ctx = &sriov->vfs_ctx[vf_id];
+	return blocking_notifier_chain_register(&vfs_ctx->notifier, nb);
+}
+EXPORT_SYMBOL(mlx5_sriov_blocking_notifier_register);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ff47d49d8be4..6fac5427d899 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -445,6 +445,11 @@ struct mlx5_qp_table {
 	struct radix_tree_root	tree;
 };
 
+enum {
+	MLX5_PF_NOTIFY_DISABLE_VF,
+	MLX5_PF_NOTIFY_ENABLE_VF,
+};
+
 struct mlx5_vf_context {
 	int	enabled;
 	u64	port_guid;
@@ -455,6 +460,7 @@ struct mlx5_vf_context {
 	u8	port_guid_valid:1;
 	u8	node_guid_valid:1;
 	enum port_state_policy	policy;
+	struct blocking_notifier_head notifier;
 };
 
 struct mlx5_core_sriov {
@@ -1152,6 +1158,12 @@ int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type
 struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev);
 void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev);
 
+int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev,
+					  int vf_id,
+					  struct notifier_block *nb);
+void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev,
+					     int vf_id,
+					     struct notifier_block *nb);
 #ifdef CONFIG_MLX5_CORE_IPOIB
 struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
 					  struct ib_device *ibdev,
-- 
cgit v1.2.3


From 1ff297584fad2eef390f212b860e0fbb7363e0e8 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 10 May 2022 10:29:36 -0700
Subject: randomize_kstack: Improve docs on requirements/rationale

There were some recent questions about where and why to use the
random_kstack routines when applying them to new architectures[1].
Update the header comments to reflect the design choices for the
routines.

[1] https://lore.kernel.org/lkml/1652173338.7bltwybi0c.astroid@bobo.none

Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Xiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/randomize_kstack.h | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h
index 1468caf001c0..5d868505a94e 100644
--- a/include/linux/randomize_kstack.h
+++ b/include/linux/randomize_kstack.h
@@ -40,10 +40,14 @@ DECLARE_PER_CPU(u32, kstack_offset);
  */
 #define KSTACK_OFFSET_MAX(x)	((x) & 0x3FF)
 
-/*
- * These macros must be used during syscall entry when interrupts and
+/**
+ * add_random_kstack_offset - Increase stack utilization by previously
+ *			      chosen random offset
+ *
+ * This should be used in the syscall entry path when interrupts and
  * preempt are disabled, and after user registers have been stored to
- * the stack.
+ * the stack. For testing the resulting entropy, please see:
+ * tools/testing/selftests/lkdtm/stack-entropy.sh
  */
 #define add_random_kstack_offset() do {					\
 	if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,	\
@@ -55,6 +59,23 @@ DECLARE_PER_CPU(u32, kstack_offset);
 	}								\
 } while (0)
 
+/**
+ * choose_random_kstack_offset - Choose the random offset for the next
+ *				 add_random_kstack_offset()
+ *
+ * This should only be used during syscall exit when interrupts and
+ * preempt are disabled. This position in the syscall flow is done to
+ * frustrate attacks from userspace attempting to learn the next offset:
+ * - Maximize the timing uncertainty visible from userspace: if the
+ *   offset is chosen at syscall entry, userspace has much more control
+ *   over the timing between choosing offsets. "How long will we be in
+ *   kernel mode?" tends to be more difficult to predict than "how long
+ *   will we be in user mode?"
+ * - Reduce the lifetime of the new offset sitting in memory during
+ *   kernel mode execution. Exposure of "thread-local" memory content
+ *   (e.g. current, percpu, etc) tends to be easier than arbitrary
+ *   location memory exposure.
+ */
 #define choose_random_kstack_offset(rand) do {				\
 	if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,	\
 				&randomize_kstack_offset)) {		\
-- 
cgit v1.2.3


From 9f88361273082825d9f0d13a543d49f9fa0d44a8 Mon Sep 17 00:00:00 2001
From: Dmitrii Dolgov <9erthalion6@gmail.com>
Date: Tue, 10 May 2022 17:52:30 +0200
Subject: bpf: Add bpf_link iterator

Implement bpf_link iterator to traverse links via bpf_seq_file
operations. The changeset is mostly shamelessly copied from
commit a228a64fc1e4 ("bpf: Add bpf_prog iterator")

Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20220510155233.9815-2-9erthalion6@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h    |   1 +
 kernel/bpf/Makefile    |   2 +-
 kernel/bpf/link_iter.c | 107 +++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c   |  19 +++++++++
 4 files changed, 128 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/link_iter.c

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index be94833d390a..551b7198ae8a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1544,6 +1544,7 @@ void bpf_link_put(struct bpf_link *link);
 int bpf_link_new_fd(struct bpf_link *link);
 struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
+struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
 
 int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
 int bpf_obj_get_user(const char __user *pathname, int flags);
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index c1a9be6a4b9f..057ba8e01e70 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
 endif
 CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
diff --git a/kernel/bpf/link_iter.c b/kernel/bpf/link_iter.c
new file mode 100644
index 000000000000..fec8005a121c
--- /dev/null
+++ b/kernel/bpf/link_iter.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2022 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <linux/fs.h>
+#include <linux/filter.h>
+#include <linux/kernel.h>
+#include <linux/btf_ids.h>
+
+struct bpf_iter_seq_link_info {
+	u32 link_id;
+};
+
+static void *bpf_link_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_link_info *info = seq->private;
+	struct bpf_link *link;
+
+	link = bpf_link_get_curr_or_next(&info->link_id);
+	if (!link)
+		return NULL;
+
+	if (*pos == 0)
+		++*pos;
+	return link;
+}
+
+static void *bpf_link_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_link_info *info = seq->private;
+
+	++*pos;
+	++info->link_id;
+	bpf_link_put((struct bpf_link *)v);
+	return bpf_link_get_curr_or_next(&info->link_id);
+}
+
+struct bpf_iter__bpf_link {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_link *, link);
+};
+
+DEFINE_BPF_ITER_FUNC(bpf_link, struct bpf_iter_meta *meta, struct bpf_link *link)
+
+static int __bpf_link_seq_show(struct seq_file *seq, void *v, bool in_stop)
+{
+	struct bpf_iter__bpf_link ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	ctx.meta = &meta;
+	ctx.link = v;
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (prog)
+		ret = bpf_iter_run_prog(prog, &ctx);
+
+	return ret;
+}
+
+static int bpf_link_seq_show(struct seq_file *seq, void *v)
+{
+	return __bpf_link_seq_show(seq, v, false);
+}
+
+static void bpf_link_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)__bpf_link_seq_show(seq, v, true);
+	else
+		bpf_link_put((struct bpf_link *)v);
+}
+
+static const struct seq_operations bpf_link_seq_ops = {
+	.start	= bpf_link_seq_start,
+	.next	= bpf_link_seq_next,
+	.stop	= bpf_link_seq_stop,
+	.show	= bpf_link_seq_show,
+};
+
+BTF_ID_LIST(btf_bpf_link_id)
+BTF_ID(struct, bpf_link)
+
+static const struct bpf_iter_seq_info bpf_link_seq_info = {
+	.seq_ops		= &bpf_link_seq_ops,
+	.init_seq_private	= NULL,
+	.fini_seq_private	= NULL,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_link_info),
+};
+
+static struct bpf_iter_reg bpf_link_reg_info = {
+	.target			= "bpf_link",
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__bpf_link, link),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &bpf_link_seq_info,
+};
+
+static int __init bpf_link_iter_init(void)
+{
+	bpf_link_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_link_id;
+	return bpf_iter_reg_target(&bpf_link_reg_info);
+}
+
+late_initcall(bpf_link_iter_init);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e0aead17dff4..50164d324eaf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4680,6 +4680,25 @@ struct bpf_link *bpf_link_by_id(u32 id)
 	return link;
 }
 
+struct bpf_link *bpf_link_get_curr_or_next(u32 *id)
+{
+	struct bpf_link *link;
+
+	spin_lock_bh(&link_idr_lock);
+again:
+	link = idr_get_next(&link_idr, id);
+	if (link) {
+		link = bpf_link_inc_not_zero(link);
+		if (IS_ERR(link)) {
+			(*id)++;
+			goto again;
+		}
+	}
+	spin_unlock_bh(&link_idr_lock);
+
+	return link;
+}
+
 #define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id
 
 static int bpf_link_get_fd_by_id(const union bpf_attr *attr)
-- 
cgit v1.2.3


From d721def7392a7348ffb9f3583b264239cbd3702c Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 10 May 2022 14:26:12 +0200
Subject: kallsyms: Make kallsyms_on_each_symbol generally available

Making kallsyms_on_each_symbol generally available, so it can be
used outside CONFIG_LIVEPATCH option in following changes.

Rather than adding another ifdef option let's make the function
generally available (when CONFIG_KALLSYMS option is defined).

Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20220510122616.2652285-2-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/kallsyms.h | 7 ++++++-
 kernel/kallsyms.c        | 2 --
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index ce1bd2fbf23e..ad39636e0c3f 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -65,11 +65,11 @@ static inline void *dereference_symbol_descriptor(void *ptr)
 	return ptr;
 }
 
+#ifdef CONFIG_KALLSYMS
 int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 				      unsigned long),
 			    void *data);
 
-#ifdef CONFIG_KALLSYMS
 /* Lookup the address for a symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name);
 
@@ -163,6 +163,11 @@ static inline bool kallsyms_show_value(const struct cred *cred)
 	return false;
 }
 
+static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
+					  unsigned long), void *data)
+{
+	return -EOPNOTSUPP;
+}
 #endif /*CONFIG_KALLSYMS*/
 
 static inline void print_ip_sym(const char *loglvl, unsigned long ip)
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 79f2eb617a62..fdfd308bebc4 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -228,7 +228,6 @@ unsigned long kallsyms_lookup_name(const char *name)
 	return module_kallsyms_lookup_name(name);
 }
 
-#ifdef CONFIG_LIVEPATCH
 /*
  * Iterate over all symbols in vmlinux.  For symbols from modules use
  * module_kallsyms_on_each_symbol instead.
@@ -251,7 +250,6 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 	}
 	return 0;
 }
-#endif /* CONFIG_LIVEPATCH */
 
 static unsigned long get_symbol_pos(unsigned long addr,
 				    unsigned long *symbolsize,
-- 
cgit v1.2.3


From bed0d9a50dacee6fcf785c555cfb0d2573355afc Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 10 May 2022 14:26:13 +0200
Subject: ftrace: Add ftrace_lookup_symbols function

Adding ftrace_lookup_symbols function that resolves array of symbols
with single pass over kallsyms.

The user provides array of string pointers with count and pointer to
allocated array for resolved values.

  int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt,
                            unsigned long *addrs)

It iterates all kallsyms symbols and tries to loop up each in provided
symbols array with bsearch. The symbols array needs to be sorted by
name for this reason.

We also check each symbol to pass ftrace_location, because this API
will be used for fprobe symbols resolving.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20220510122616.2652285-3-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/ftrace.h |  6 +++++
 kernel/kallsyms.c      |  1 +
 kernel/trace/ftrace.c  | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 69 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4816b7e11047..820500430eae 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -303,6 +303,8 @@ int unregister_ftrace_function(struct ftrace_ops *ops);
 extern void ftrace_stub(unsigned long a0, unsigned long a1,
 			struct ftrace_ops *op, struct ftrace_regs *fregs);
 
+
+int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs);
 #else /* !CONFIG_FUNCTION_TRACER */
 /*
  * (un)register_ftrace_function must be a macro since the ops parameter
@@ -313,6 +315,10 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1,
 static inline void ftrace_kill(void) { }
 static inline void ftrace_free_init_mem(void) { }
 static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
+static inline int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_FUNCTION_TRACER */
 
 struct ftrace_func_entry {
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fdfd308bebc4..fbdf8d3279ac 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -29,6 +29,7 @@
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/bsearch.h>
 
 /*
  * These will be re-linked against their real values
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f1d2f5e7263..07d87c7a525d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7964,3 +7964,65 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	mutex_unlock(&ftrace_lock);
 	return ret;
 }
+
+static int symbols_cmp(const void *a, const void *b)
+{
+	const char **str_a = (const char **) a;
+	const char **str_b = (const char **) b;
+
+	return strcmp(*str_a, *str_b);
+}
+
+struct kallsyms_data {
+	unsigned long *addrs;
+	const char **syms;
+	size_t cnt;
+	size_t found;
+};
+
+static int kallsyms_callback(void *data, const char *name,
+			     struct module *mod, unsigned long addr)
+{
+	struct kallsyms_data *args = data;
+
+	if (!bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp))
+		return 0;
+
+	addr = ftrace_location(addr);
+	if (!addr)
+		return 0;
+
+	args->addrs[args->found++] = addr;
+	return args->found == args->cnt ? 1 : 0;
+}
+
+/**
+ * ftrace_lookup_symbols - Lookup addresses for array of symbols
+ *
+ * @sorted_syms: array of symbols pointers symbols to resolve,
+ * must be alphabetically sorted
+ * @cnt: number of symbols/addresses in @syms/@addrs arrays
+ * @addrs: array for storing resulting addresses
+ *
+ * This function looks up addresses for array of symbols provided in
+ * @syms array (must be alphabetically sorted) and stores them in
+ * @addrs array, which needs to be big enough to store at least @cnt
+ * addresses.
+ *
+ * This function returns 0 if all provided symbols are found,
+ * -ESRCH otherwise.
+ */
+int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs)
+{
+	struct kallsyms_data args;
+	int err;
+
+	args.addrs = addrs;
+	args.syms = sorted_syms;
+	args.cnt = cnt;
+	args.found = 0;
+	err = kallsyms_on_each_symbol(kallsyms_callback, &args);
+	if (err < 0)
+		return err;
+	return args.found == args.cnt ? 0 : -ESRCH;
+}
-- 
cgit v1.2.3


From ddccc9ef55992716ad477d38fbcd9f8f1d34fc67 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 9 May 2022 09:04:54 -0700
Subject: skbuff: add a basic intro doc

Add basic skb documentation. It's mostly an intro to the subsequent
patches - it would looks strange if we documented advanced topics
without covering the basics in any way.

Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/skbuff.rst | 25 +++++++++++++++++++++++
 include/linux/skbuff.h              | 40 +++++++++++++++++++++++++++++++++++++
 2 files changed, 65 insertions(+)
 create mode 100644 Documentation/networking/skbuff.rst

(limited to 'include/linux')

diff --git a/Documentation/networking/skbuff.rst b/Documentation/networking/skbuff.rst
new file mode 100644
index 000000000000..b4a008feceb4
--- /dev/null
+++ b/Documentation/networking/skbuff.rst
@@ -0,0 +1,25 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+struct sk_buff
+==============
+
+:c:type:`sk_buff` is the main networking structure representing
+a packet.
+
+Basic sk_buff geometry
+----------------------
+
+.. kernel-doc:: include/linux/skbuff.h
+   :doc: Basic sk_buff geometry
+
+Shared skbs and skb clones
+--------------------------
+
+:c:member:`sk_buff.users` is a simple refcount allowing multiple entities
+to keep a struct sk_buff alive. skbs with a ``sk_buff.users != 1`` are referred
+to as shared skbs (see skb_shared()).
+
+skb_clone() allows for fast duplication of skbs. None of the data buffers
+get copied, but caller gets a new metadata struct (struct sk_buff).
+&skb_shared_info.refcount indicates the number of skbs pointing at the same
+packet data (i.e. clones).
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 97de40bcfef6..69802624276d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -800,6 +800,46 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
+/**
+ * DOC: Basic sk_buff geometry
+ *
+ * struct sk_buff itself is a metadata structure and does not hold any packet
+ * data. All the data is held in associated buffers.
+ *
+ * &sk_buff.head points to the main "head" buffer. The head buffer is divided
+ * into two parts:
+ *
+ *  - data buffer, containing headers and sometimes payload;
+ *    this is the part of the skb operated on by the common helpers
+ *    such as skb_put() or skb_pull();
+ *  - shared info (struct skb_shared_info) which holds an array of pointers
+ *    to read-only data in the (page, offset, length) format.
+ *
+ * Optionally &skb_shared_info.frag_list may point to another skb.
+ *
+ * Basic diagram may look like this::
+ *
+ *                                  ---------------
+ *                                 | sk_buff       |
+ *                                  ---------------
+ *     ,---------------------------  + head
+ *    /          ,-----------------  + data
+ *   /          /      ,-----------  + tail
+ *  |          |      |            , + end
+ *  |          |      |           |
+ *  v          v      v           v
+ *   -----------------------------------------------
+ *  | headroom | data |  tailroom | skb_shared_info |
+ *   -----------------------------------------------
+ *                                 + [page frag]
+ *                                 + [page frag]
+ *                                 + [page frag]
+ *                                 + [page frag]       ---------
+ *                                 + frag_list    --> | sk_buff |
+ *                                                     ---------
+ *
+ */
+
 /**
  *	struct sk_buff - socket buffer
  *	@next: Next buffer in list
-- 
cgit v1.2.3


From 9ec7ea1462084df695f34c5ac2d2d2250d9d6897 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 9 May 2022 09:04:55 -0700
Subject: skbuff: rewrite the doc for data-only skbs

The comment about shinfo->dataref split is really unhelpful,
at least to me. Rewrite it and render it to skb documentation.

Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/index.rst  |  1 +
 Documentation/networking/skbuff.rst |  6 ++++++
 include/linux/skbuff.h              | 42 ++++++++++++++++++++++++++-----------
 3 files changed, 37 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 72cf33579b78..a1c271fe484e 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -97,6 +97,7 @@ Contents:
    sctp
    secid
    seg6-sysctl
+   skbuff
    smc-sysctl
    statistics
    strparser
diff --git a/Documentation/networking/skbuff.rst b/Documentation/networking/skbuff.rst
index b4a008feceb4..94681523e345 100644
--- a/Documentation/networking/skbuff.rst
+++ b/Documentation/networking/skbuff.rst
@@ -23,3 +23,9 @@ skb_clone() allows for fast duplication of skbs. None of the data buffers
 get copied, but caller gets a new metadata struct (struct sk_buff).
 &skb_shared_info.refcount indicates the number of skbs pointing at the same
 packet data (i.e. clones).
+
+dataref and headerless skbs
+---------------------------
+
+.. kernel-doc:: include/linux/skbuff.h
+   :doc: dataref and headerless skbs
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 69802624276d..0e492f9bf532 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -727,16 +727,32 @@ struct skb_shared_info {
 	skb_frag_t	frags[MAX_SKB_FRAGS];
 };
 
-/* We divide dataref into two halves.  The higher 16 bits hold references
- * to the payload part of skb->data.  The lower 16 bits hold references to
- * the entire skb->data.  A clone of a headerless skb holds the length of
- * the header in skb->hdr_len.
- *
- * All users must obey the rule that the skb->data reference count must be
- * greater than or equal to the payload reference count.
- *
- * Holding a reference to the payload part means that the user does not
- * care about modifications to the header part of skb->data.
+/**
+ * DOC: dataref and headerless skbs
+ *
+ * Transport layers send out clones of payload skbs they hold for
+ * retransmissions. To allow lower layers of the stack to prepend their headers
+ * we split &skb_shared_info.dataref into two halves.
+ * The lower 16 bits count the overall number of references.
+ * The higher 16 bits indicate how many of the references are payload-only.
+ * skb_header_cloned() checks if skb is allowed to add / write the headers.
+ *
+ * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr
+ * (via __skb_header_release()). Any clone created from marked skb will get
+ * &sk_buff.hdr_len populated with the available headroom.
+ * If there's the only clone in existence it's able to modify the headroom
+ * at will. The sequence of calls inside the transport layer is::
+ *
+ *  <alloc skb>
+ *  skb_reserve()
+ *  __skb_header_release()
+ *  skb_clone()
+ *  // send the clone down the stack
+ *
+ * This is not a very generic construct and it depends on the transport layers
+ * doing the right thing. In practice there's usually only one payload-only skb.
+ * Having multiple payload-only skbs with different lengths of hdr_len is not
+ * possible. The payload-only skbs should never leave their owner.
  */
 #define SKB_DATAREF_SHIFT 16
 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1)
@@ -2027,8 +2043,10 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri)
 }
 
 /**
- *	__skb_header_release - release reference to header
- *	@skb: buffer to operate on
+ * __skb_header_release() - allow clones to use the headroom
+ * @skb: buffer to operate on
+ *
+ * See "DOC: dataref and headerless skbs".
  */
 static inline void __skb_header_release(struct sk_buff *skb)
 {
-- 
cgit v1.2.3


From 9facd94114b59afebd405e74b3bc2bf184efe986 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 9 May 2022 09:04:56 -0700
Subject: skbuff: render the checksum comment to documentation

Long time ago Tom added a giant comment to skbuff.h explaining
checksums. Now that we have a place in Documentation for skbuff
docs we should render it. Sprinkle some markup while at it.

Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/skbuff.rst |   6 +
 include/linux/skbuff.h              | 219 ++++++++++++++++++++----------------
 2 files changed, 130 insertions(+), 95 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/skbuff.rst b/Documentation/networking/skbuff.rst
index 94681523e345..5b74275a73a3 100644
--- a/Documentation/networking/skbuff.rst
+++ b/Documentation/networking/skbuff.rst
@@ -29,3 +29,9 @@ dataref and headerless skbs
 
 .. kernel-doc:: include/linux/skbuff.h
    :doc: dataref and headerless skbs
+
+Checksum information
+--------------------
+
+.. kernel-doc:: include/linux/skbuff.h
+   :doc: skb checksums
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0e492f9bf532..5296b2c37f62 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -43,98 +43,112 @@
 #include <linux/netfilter/nf_conntrack_common.h>
 #endif
 
-/* The interface for checksum offload between the stack and networking drivers
+/**
+ * DOC: skb checksums
+ *
+ * The interface for checksum offload between the stack and networking drivers
  * is as follows...
  *
- * A. IP checksum related features
+ * IP checksum related features
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  * Drivers advertise checksum offload capabilities in the features of a device.
  * From the stack's point of view these are capabilities offered by the driver.
  * A driver typically only advertises features that it is capable of offloading
  * to its device.
  *
- * The checksum related features are:
- *
- *	NETIF_F_HW_CSUM	- The driver (or its device) is able to compute one
- *			  IP (one's complement) checksum for any combination
- *			  of protocols or protocol layering. The checksum is
- *			  computed and set in a packet per the CHECKSUM_PARTIAL
- *			  interface (see below).
- *
- *	NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain
- *			  TCP or UDP packets over IPv4. These are specifically
- *			  unencapsulated packets of the form IPv4|TCP or
- *			  IPv4|UDP where the Protocol field in the IPv4 header
- *			  is TCP or UDP. The IPv4 header may contain IP options.
- *			  This feature cannot be set in features for a device
- *			  with NETIF_F_HW_CSUM also set. This feature is being
- *			  DEPRECATED (see below).
- *
- *	NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain
- *			  TCP or UDP packets over IPv6. These are specifically
- *			  unencapsulated packets of the form IPv6|TCP or
- *			  IPv6|UDP where the Next Header field in the IPv6
- *			  header is either TCP or UDP. IPv6 extension headers
- *			  are not supported with this feature. This feature
- *			  cannot be set in features for a device with
- *			  NETIF_F_HW_CSUM also set. This feature is being
- *			  DEPRECATED (see below).
- *
- *	NETIF_F_RXCSUM - Driver (device) performs receive checksum offload.
- *			 This flag is only used to disable the RX checksum
- *			 feature for a device. The stack will accept receive
- *			 checksum indication in packets received on a device
- *			 regardless of whether NETIF_F_RXCSUM is set.
- *
- * B. Checksumming of received packets by device. Indication of checksum
- *    verification is set in skb->ip_summed. Possible values are:
- *
- * CHECKSUM_NONE:
+ * .. flat-table:: Checksum related device features
+ *   :widths: 1 10
+ *
+ *   * - %NETIF_F_HW_CSUM
+ *     - The driver (or its device) is able to compute one
+ *	 IP (one's complement) checksum for any combination
+ *	 of protocols or protocol layering. The checksum is
+ *	 computed and set in a packet per the CHECKSUM_PARTIAL
+ *	 interface (see below).
+ *
+ *   * - %NETIF_F_IP_CSUM
+ *     - Driver (device) is only able to checksum plain
+ *	 TCP or UDP packets over IPv4. These are specifically
+ *	 unencapsulated packets of the form IPv4|TCP or
+ *	 IPv4|UDP where the Protocol field in the IPv4 header
+ *	 is TCP or UDP. The IPv4 header may contain IP options.
+ *	 This feature cannot be set in features for a device
+ *	 with NETIF_F_HW_CSUM also set. This feature is being
+ *	 DEPRECATED (see below).
+ *
+ *   * - %NETIF_F_IPV6_CSUM
+ *     - Driver (device) is only able to checksum plain
+ *	 TCP or UDP packets over IPv6. These are specifically
+ *	 unencapsulated packets of the form IPv6|TCP or
+ *	 IPv6|UDP where the Next Header field in the IPv6
+ *	 header is either TCP or UDP. IPv6 extension headers
+ *	 are not supported with this feature. This feature
+ *	 cannot be set in features for a device with
+ *	 NETIF_F_HW_CSUM also set. This feature is being
+ *	 DEPRECATED (see below).
+ *
+ *   * - %NETIF_F_RXCSUM
+ *     - Driver (device) performs receive checksum offload.
+ *	 This flag is only used to disable the RX checksum
+ *	 feature for a device. The stack will accept receive
+ *	 checksum indication in packets received on a device
+ *	 regardless of whether NETIF_F_RXCSUM is set.
+ *
+ * Checksumming of received packets by device
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * Indication of checksum verification is set in &sk_buff.ip_summed.
+ * Possible values are:
+ *
+ * - %CHECKSUM_NONE
  *
  *   Device did not checksum this packet e.g. due to lack of capabilities.
  *   The packet contains full (though not verified) checksum in packet but
  *   not in skb->csum. Thus, skb->csum is undefined in this case.
  *
- * CHECKSUM_UNNECESSARY:
+ * - %CHECKSUM_UNNECESSARY
  *
  *   The hardware you're dealing with doesn't calculate the full checksum
- *   (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums
- *   for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY
- *   if their checksums are okay. skb->csum is still undefined in this case
+ *   (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums
+ *   for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY
+ *   if their checksums are okay. &sk_buff.csum is still undefined in this case
  *   though. A driver or device must never modify the checksum field in the
  *   packet even if checksum is verified.
  *
- *   CHECKSUM_UNNECESSARY is applicable to following protocols:
- *     TCP: IPv6 and IPv4.
- *     UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a
+ *   %CHECKSUM_UNNECESSARY is applicable to following protocols:
+ *
+ *     - TCP: IPv6 and IPv4.
+ *     - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a
  *       zero UDP checksum for either IPv4 or IPv6, the networking stack
  *       may perform further validation in this case.
- *     GRE: only if the checksum is present in the header.
- *     SCTP: indicates the CRC in SCTP header has been validated.
- *     FCOE: indicates the CRC in FC frame has been validated.
+ *     - GRE: only if the checksum is present in the header.
+ *     - SCTP: indicates the CRC in SCTP header has been validated.
+ *     - FCOE: indicates the CRC in FC frame has been validated.
  *
- *   skb->csum_level indicates the number of consecutive checksums found in
- *   the packet minus one that have been verified as CHECKSUM_UNNECESSARY.
+ *   &sk_buff.csum_level indicates the number of consecutive checksums found in
+ *   the packet minus one that have been verified as %CHECKSUM_UNNECESSARY.
  *   For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet
  *   and a device is able to verify the checksums for UDP (possibly zero),
- *   GRE (checksum flag is set) and TCP, skb->csum_level would be set to
+ *   GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to
  *   two. If the device were only able to verify the UDP checksum and not
  *   GRE, either because it doesn't support GRE checksum or because GRE
  *   checksum is bad, skb->csum_level would be set to zero (TCP checksum is
  *   not considered in this case).
  *
- * CHECKSUM_COMPLETE:
+ * - %CHECKSUM_COMPLETE
  *
  *   This is the most generic way. The device supplied checksum of the _whole_
- *   packet as seen by netif_rx() and fills in skb->csum. This means the
+ *   packet as seen by netif_rx() and fills in &sk_buff.csum. This means the
  *   hardware doesn't need to parse L3/L4 headers to implement this.
  *
  *   Notes:
+ *
  *   - Even if device supports only some protocols, but is able to produce
  *     skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY.
  *   - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols.
  *
- * CHECKSUM_PARTIAL:
+ * - %CHECKSUM_PARTIAL
  *
  *   A checksum is set up to be offloaded to a device as described in the
  *   output description for CHECKSUM_PARTIAL. This may occur on a packet
@@ -146,14 +160,18 @@
  *   packet that are after the checksum being offloaded are not considered to
  *   be verified.
  *
- * C. Checksumming on transmit for non-GSO. The stack requests checksum offload
- *    in the skb->ip_summed for a packet. Values are:
+ * Checksumming on transmit for non-GSO
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * The stack requests checksum offload in the &sk_buff.ip_summed for a packet.
+ * Values are:
  *
- * CHECKSUM_PARTIAL:
+ * - %CHECKSUM_PARTIAL
  *
  *   The driver is required to checksum the packet as seen by hard_start_xmit()
- *   from skb->csum_start up to the end, and to record/write the checksum at
- *   offset skb->csum_start + skb->csum_offset. A driver may verify that the
+ *   from &sk_buff.csum_start up to the end, and to record/write the checksum at
+ *   offset &sk_buff.csum_start + &sk_buff.csum_offset.
+ *   A driver may verify that the
  *   csum_start and csum_offset values are valid values given the length and
  *   offset of the packet, but it should not attempt to validate that the
  *   checksum refers to a legitimate transport layer checksum -- it is the
@@ -165,55 +183,66 @@
  *   checksum calculation to the device, or call skb_checksum_help (in the case
  *   that the device does not support offload for a particular checksum).
  *
- *   NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of
- *   NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate
+ *   %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of
+ *   %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate
  *   checksum offload capability.
- *   skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based
+ *   skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based
  *   on network device checksumming capabilities: if a packet does not match
- *   them, skb_checksum_help or skb_crc32c_help (depending on the value of
- *   csum_not_inet, see item D.) is called to resolve the checksum.
+ *   them, skb_checksum_help() or skb_crc32c_help() (depending on the value of
+ *   &sk_buff.csum_not_inet, see :ref:`crc`)
+ *   is called to resolve the checksum.
  *
- * CHECKSUM_NONE:
+ * - %CHECKSUM_NONE
  *
  *   The skb was already checksummed by the protocol, or a checksum is not
  *   required.
  *
- * CHECKSUM_UNNECESSARY:
+ * - %CHECKSUM_UNNECESSARY
  *
  *   This has the same meaning as CHECKSUM_NONE for checksum offload on
  *   output.
  *
- * CHECKSUM_COMPLETE:
+ * - %CHECKSUM_COMPLETE
+ *
  *   Not used in checksum output. If a driver observes a packet with this value
- *   set in skbuff, it should treat the packet as if CHECKSUM_NONE were set.
- *
- * D. Non-IP checksum (CRC) offloads
- *
- *   NETIF_F_SCTP_CRC - This feature indicates that a device is capable of
- *     offloading the SCTP CRC in a packet. To perform this offload the stack
- *     will set csum_start and csum_offset accordingly, set ip_summed to
- *     CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in
- *     the skbuff that the CHECKSUM_PARTIAL refers to CRC32c.
- *     A driver that supports both IP checksum offload and SCTP CRC32c offload
- *     must verify which offload is configured for a packet by testing the
- *     value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve
- *     CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1.
- *
- *   NETIF_F_FCOE_CRC - This feature indicates that a device is capable of
- *     offloading the FCOE CRC in a packet. To perform this offload the stack
- *     will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset
- *     accordingly. Note that there is no indication in the skbuff that the
- *     CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports
- *     both IP checksum offload and FCOE CRC offload must verify which offload
- *     is configured for a packet, presumably by inspecting packet headers.
- *
- * E. Checksumming on output with GSO.
- *
- * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload
+ *   set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set.
+ *
+ * .. _crc:
+ *
+ * Non-IP checksum (CRC) offloads
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * .. flat-table::
+ *   :widths: 1 10
+ *
+ *   * - %NETIF_F_SCTP_CRC
+ *     - This feature indicates that a device is capable of
+ *	 offloading the SCTP CRC in a packet. To perform this offload the stack
+ *	 will set csum_start and csum_offset accordingly, set ip_summed to
+ *	 %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication
+ *	 in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c.
+ *	 A driver that supports both IP checksum offload and SCTP CRC32c offload
+ *	 must verify which offload is configured for a packet by testing the
+ *	 value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to
+ *	 resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1.
+ *
+ *   * - %NETIF_F_FCOE_CRC
+ *     - This feature indicates that a device is capable of offloading the FCOE
+ *	 CRC in a packet. To perform this offload the stack will set ip_summed
+ *	 to %CHECKSUM_PARTIAL and set csum_start and csum_offset
+ *	 accordingly. Note that there is no indication in the skbuff that the
+ *	 %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports
+ *	 both IP checksum offload and FCOE CRC offload must verify which offload
+ *	 is configured for a packet, presumably by inspecting packet headers.
+ *
+ * Checksumming on output with GSO
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * In the case of a GSO packet (skb_is_gso() is true), checksum offload
  * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the
- * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as
+ * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as
  * part of the GSO operation is implied. If a checksum is being offloaded
- * with GSO then ip_summed is CHECKSUM_PARTIAL, and both csum_start and
+ * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and
  * csum_offset are set to refer to the outermost checksum being offloaded
  * (two offloaded checksums are possible with UDP encapsulation).
  */
-- 
cgit v1.2.3


From f7e0beaf39d3868dc700d4954b26cf8443c5d423 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <kuifeng@fb.com>
Date: Tue, 10 May 2022 13:59:19 -0700
Subject: bpf, x86: Generate trampolines from bpf_tramp_links

Replace struct bpf_tramp_progs with struct bpf_tramp_links to collect
struct bpf_tramp_link(s) for a trampoline.  struct bpf_tramp_link
extends bpf_link to act as a linked list node.

arch_prepare_bpf_trampoline() accepts a struct bpf_tramp_links to
collects all bpf_tramp_link(s) that a trampoline should call.

Change BPF trampoline and bpf_struct_ops to pass bpf_tramp_links
instead of bpf_tramp_progs.

Signed-off-by: Kui-Feng Lee <kuifeng@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220510205923.3206889-2-kuifeng@fb.com
---
 arch/x86/net/bpf_jit_comp.c    | 36 +++++++++++----------
 include/linux/bpf.h            | 36 ++++++++++++++-------
 include/linux/bpf_types.h      |  1 +
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/bpf_struct_ops.c    | 71 +++++++++++++++++++++++++++-------------
 kernel/bpf/syscall.c           | 23 +++++--------
 kernel/bpf/trampoline.c        | 73 ++++++++++++++++++++++++------------------
 net/bpf/bpf_dummy_struct_ops.c | 24 +++++++++++---
 tools/bpf/bpftool/link.c       |  1 +
 tools/include/uapi/linux/bpf.h |  1 +
 10 files changed, 164 insertions(+), 103 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 16b6efacf7c6..38eb43159230 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1762,10 +1762,12 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 }
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
-			   struct bpf_prog *p, int stack_size, bool save_ret)
+			   struct bpf_tramp_link *l, int stack_size,
+			   bool save_ret)
 {
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
+	struct bpf_prog *p = l->link.prog;
 
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
@@ -1850,14 +1852,14 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 }
 
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
-		      struct bpf_tramp_progs *tp, int stack_size,
+		      struct bpf_tramp_links *tl, int stack_size,
 		      bool save_ret)
 {
 	int i;
 	u8 *prog = *pprog;
 
-	for (i = 0; i < tp->nr_progs; i++) {
-		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size,
+	for (i = 0; i < tl->nr_links; i++) {
+		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size,
 				    save_ret))
 			return -EINVAL;
 	}
@@ -1866,7 +1868,7 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 }
 
 static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
-			      struct bpf_tramp_progs *tp, int stack_size,
+			      struct bpf_tramp_links *tl, int stack_size,
 			      u8 **branches)
 {
 	u8 *prog = *pprog;
@@ -1877,8 +1879,8 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 	 */
 	emit_mov_imm32(&prog, false, BPF_REG_0, 0);
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
-	for (i = 0; i < tp->nr_progs; i++) {
-		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, true))
+	for (i = 0; i < tl->nr_links; i++) {
+		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, true))
 			return -EINVAL;
 
 		/* mod_ret prog stored return value into [rbp - 8]. Emit:
@@ -1980,14 +1982,14 @@ static bool is_valid_bpf_tramp_flags(unsigned int flags)
  */
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
-				struct bpf_tramp_progs *tprogs,
+				struct bpf_tramp_links *tlinks,
 				void *orig_call)
 {
 	int ret, i, nr_args = m->nr_args;
 	int regs_off, ip_off, args_off, stack_size = nr_args * 8;
-	struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY];
-	struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT];
-	struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN];
+	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
+	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
+	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
 	u8 **branches = NULL;
 	u8 *prog;
 	bool save_ret;
@@ -2078,13 +2080,13 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		}
 	}
 
-	if (fentry->nr_progs)
+	if (fentry->nr_links)
 		if (invoke_bpf(m, &prog, fentry, regs_off,
 			       flags & BPF_TRAMP_F_RET_FENTRY_RET))
 			return -EINVAL;
 
-	if (fmod_ret->nr_progs) {
-		branches = kcalloc(fmod_ret->nr_progs, sizeof(u8 *),
+	if (fmod_ret->nr_links) {
+		branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *),
 				   GFP_KERNEL);
 		if (!branches)
 			return -ENOMEM;
@@ -2111,7 +2113,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		prog += X86_PATCH_SIZE;
 	}
 
-	if (fmod_ret->nr_progs) {
+	if (fmod_ret->nr_links) {
 		/* From Intel 64 and IA-32 Architectures Optimization
 		 * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler
 		 * Coding Rule 11: All branch targets should be 16-byte
@@ -2121,12 +2123,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		/* Update the branches saved in invoke_bpf_mod_ret with the
 		 * aligned address of do_fexit.
 		 */
-		for (i = 0; i < fmod_ret->nr_progs; i++)
+		for (i = 0; i < fmod_ret->nr_links; i++)
 			emit_cond_near_jump(&branches[i], prog, branches[i],
 					    X86_JNE);
 	}
 
-	if (fexit->nr_progs)
+	if (fexit->nr_links)
 		if (invoke_bpf(m, &prog, fexit, regs_off, false)) {
 			ret = -EINVAL;
 			goto cleanup;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 551b7198ae8a..75e0110a65e1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -723,11 +723,11 @@ struct btf_func_model {
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.  Pick a number to fit into BPF_IMAGE_SIZE / 2
  */
-#define BPF_MAX_TRAMP_PROGS 38
+#define BPF_MAX_TRAMP_LINKS 38
 
-struct bpf_tramp_progs {
-	struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS];
-	int nr_progs;
+struct bpf_tramp_links {
+	struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS];
+	int nr_links;
 };
 
 /* Different use cases for BPF trampoline:
@@ -753,7 +753,7 @@ struct bpf_tramp_progs {
 struct bpf_tramp_image;
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
-				struct bpf_tramp_progs *tprogs,
+				struct bpf_tramp_links *tlinks,
 				void *orig_call);
 /* these two functions are called from generated trampoline */
 u64 notrace __bpf_prog_enter(struct bpf_prog *prog);
@@ -852,9 +852,10 @@ static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
 {
 	return bpf_func(ctx, insnsi);
 }
+
 #ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
+int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
+int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
@@ -905,12 +906,12 @@ int bpf_jit_charge_modmem(u32 size);
 void bpf_jit_uncharge_modmem(u32 size);
 bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
 #else
-static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
+static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
 					   struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;
 }
-static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog,
+static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
 					     struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;
@@ -1009,7 +1010,6 @@ struct bpf_prog_aux {
 	bool tail_call_reachable;
 	bool xdp_has_frags;
 	bool use_bpf_prog_pack;
-	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
@@ -1096,6 +1096,18 @@ struct bpf_link_ops {
 			      struct bpf_link_info *info);
 };
 
+struct bpf_tramp_link {
+	struct bpf_link link;
+	struct hlist_node tramp_hlist;
+};
+
+struct bpf_tracing_link {
+	struct bpf_tramp_link link;
+	enum bpf_attach_type attach_type;
+	struct bpf_trampoline *trampoline;
+	struct bpf_prog *tgt_prog;
+};
+
 struct bpf_link_primer {
 	struct bpf_link *link;
 	struct file *file;
@@ -1133,8 +1145,8 @@ bool bpf_struct_ops_get(const void *kdata);
 void bpf_struct_ops_put(const void *kdata);
 int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
 				       void *value);
-int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs,
-				      struct bpf_prog *prog,
+int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
+				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
 				      void *image, void *image_end);
 static inline bool bpf_try_module_get(const void *data, struct module *owner)
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 3e24ad0c4b3c..2b9112b80171 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -141,3 +141,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
 BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
 #endif
 BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi)
+BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 95a3d1ff6255..3d032ea1b6a3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1013,6 +1013,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_XDP = 6,
 	BPF_LINK_TYPE_PERF_EVENT = 7,
 	BPF_LINK_TYPE_KPROBE_MULTI = 8,
+	BPF_LINK_TYPE_STRUCT_OPS = 9,
 
 	MAX_BPF_LINK_TYPE,
 };
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 3a0103ad97bc..d9a3c9207240 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -33,15 +33,15 @@ struct bpf_struct_ops_map {
 	const struct bpf_struct_ops *st_ops;
 	/* protect map_update */
 	struct mutex lock;
-	/* progs has all the bpf_prog that is populated
+	/* link has all the bpf_links that is populated
 	 * to the func ptr of the kernel's struct
 	 * (in kvalue.data).
 	 */
-	struct bpf_prog **progs;
+	struct bpf_link **links;
 	/* image is a page that has all the trampolines
 	 * that stores the func args before calling the bpf_prog.
 	 * A PAGE_SIZE "image" is enough to store all trampoline for
-	 * "progs[]".
+	 * "links[]".
 	 */
 	void *image;
 	/* uvalue->data stores the kernel struct
@@ -283,9 +283,9 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map)
 	u32 i;
 
 	for (i = 0; i < btf_type_vlen(t); i++) {
-		if (st_map->progs[i]) {
-			bpf_prog_put(st_map->progs[i]);
-			st_map->progs[i] = NULL;
+		if (st_map->links[i]) {
+			bpf_link_put(st_map->links[i]);
+			st_map->links[i] = NULL;
 		}
 	}
 }
@@ -316,18 +316,34 @@ static int check_zero_holes(const struct btf_type *t, void *data)
 	return 0;
 }
 
-int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs,
-				      struct bpf_prog *prog,
+static void bpf_struct_ops_link_release(struct bpf_link *link)
+{
+}
+
+static void bpf_struct_ops_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_tramp_link *tlink = container_of(link, struct bpf_tramp_link, link);
+
+	kfree(tlink);
+}
+
+const struct bpf_link_ops bpf_struct_ops_link_lops = {
+	.release = bpf_struct_ops_link_release,
+	.dealloc = bpf_struct_ops_link_dealloc,
+};
+
+int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
+				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
 				      void *image, void *image_end)
 {
 	u32 flags;
 
-	tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
-	tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
+	tlinks[BPF_TRAMP_FENTRY].links[0] = link;
+	tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
 	flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
 	return arch_prepare_bpf_trampoline(NULL, image, image_end,
-					   model, flags, tprogs, NULL);
+					   model, flags, tlinks, NULL);
 }
 
 static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
@@ -338,7 +354,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	struct bpf_struct_ops_value *uvalue, *kvalue;
 	const struct btf_member *member;
 	const struct btf_type *t = st_ops->type;
-	struct bpf_tramp_progs *tprogs = NULL;
+	struct bpf_tramp_links *tlinks = NULL;
 	void *udata, *kdata;
 	int prog_fd, err = 0;
 	void *image, *image_end;
@@ -362,8 +378,8 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	if (uvalue->state || refcount_read(&uvalue->refcnt))
 		return -EINVAL;
 
-	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
-	if (!tprogs)
+	tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL);
+	if (!tlinks)
 		return -ENOMEM;
 
 	uvalue = (struct bpf_struct_ops_value *)st_map->uvalue;
@@ -386,6 +402,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	for_each_member(i, t, member) {
 		const struct btf_type *mtype, *ptype;
 		struct bpf_prog *prog;
+		struct bpf_tramp_link *link;
 		u32 moff;
 
 		moff = __btf_member_bit_offset(t, member) / 8;
@@ -439,16 +456,26 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			err = PTR_ERR(prog);
 			goto reset_unlock;
 		}
-		st_map->progs[i] = prog;
 
 		if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
 		    prog->aux->attach_btf_id != st_ops->type_id ||
 		    prog->expected_attach_type != i) {
+			bpf_prog_put(prog);
 			err = -EINVAL;
 			goto reset_unlock;
 		}
 
-		err = bpf_struct_ops_prepare_trampoline(tprogs, prog,
+		link = kzalloc(sizeof(*link), GFP_USER);
+		if (!link) {
+			bpf_prog_put(prog);
+			err = -ENOMEM;
+			goto reset_unlock;
+		}
+		bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS,
+			      &bpf_struct_ops_link_lops, prog);
+		st_map->links[i] = &link->link;
+
+		err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 							&st_ops->func_models[i],
 							image, image_end);
 		if (err < 0)
@@ -491,7 +518,7 @@ reset_unlock:
 	memset(uvalue, 0, map->value_size);
 	memset(kvalue, 0, map->value_size);
 unlock:
-	kfree(tprogs);
+	kfree(tlinks);
 	mutex_unlock(&st_map->lock);
 	return err;
 }
@@ -546,9 +573,9 @@ static void bpf_struct_ops_map_free(struct bpf_map *map)
 {
 	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
 
-	if (st_map->progs)
+	if (st_map->links)
 		bpf_struct_ops_map_put_progs(st_map);
-	bpf_map_area_free(st_map->progs);
+	bpf_map_area_free(st_map->links);
 	bpf_jit_free_exec(st_map->image);
 	bpf_map_area_free(st_map->uvalue);
 	bpf_map_area_free(st_map);
@@ -597,11 +624,11 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	map = &st_map->map;
 
 	st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
-	st_map->progs =
-		bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *),
+	st_map->links =
+		bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
 				   NUMA_NO_NODE);
 	st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
-	if (!st_map->uvalue || !st_map->progs || !st_map->image) {
+	if (!st_map->uvalue || !st_map->links || !st_map->image) {
 		bpf_struct_ops_map_free(map);
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 50164d324eaf..2dc582773344 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2864,19 +2864,12 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 }
 EXPORT_SYMBOL(bpf_link_get_from_fd);
 
-struct bpf_tracing_link {
-	struct bpf_link link;
-	enum bpf_attach_type attach_type;
-	struct bpf_trampoline *trampoline;
-	struct bpf_prog *tgt_prog;
-};
-
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
-	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog,
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link,
 						tr_link->trampoline));
 
 	bpf_trampoline_put(tr_link->trampoline);
@@ -2889,7 +2882,7 @@ static void bpf_tracing_link_release(struct bpf_link *link)
 static void bpf_tracing_link_dealloc(struct bpf_link *link)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	kfree(tr_link);
 }
@@ -2898,7 +2891,7 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
 					 struct seq_file *seq)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	seq_printf(seq,
 		   "attach_type:\t%d\n",
@@ -2909,7 +2902,7 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
 					   struct bpf_link_info *info)
 {
 	struct bpf_tracing_link *tr_link =
-		container_of(link, struct bpf_tracing_link, link);
+		container_of(link, struct bpf_tracing_link, link.link);
 
 	info->tracing.attach_type = tr_link->attach_type;
 	bpf_trampoline_unpack_key(tr_link->trampoline->key,
@@ -2990,7 +2983,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 		err = -ENOMEM;
 		goto out_put_prog;
 	}
-	bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING,
+	bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING,
 		      &bpf_tracing_link_lops, prog);
 	link->attach_type = prog->expected_attach_type;
 
@@ -3060,11 +3053,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 		tgt_prog = prog->aux->dst_prog;
 	}
 
-	err = bpf_link_prime(&link->link, &link_primer);
+	err = bpf_link_prime(&link->link.link, &link_primer);
 	if (err)
 		goto out_unlock;
 
-	err = bpf_trampoline_link_prog(prog, tr);
+	err = bpf_trampoline_link_prog(&link->link, tr);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
 		link = NULL;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index ada97751ae1b..d5e6bc5517cb 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -168,30 +168,30 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 	return ret;
 }
 
-static struct bpf_tramp_progs *
+static struct bpf_tramp_links *
 bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg)
 {
-	const struct bpf_prog_aux *aux;
-	struct bpf_tramp_progs *tprogs;
-	struct bpf_prog **progs;
+	struct bpf_tramp_link *link;
+	struct bpf_tramp_links *tlinks;
+	struct bpf_tramp_link **links;
 	int kind;
 
 	*total = 0;
-	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
-	if (!tprogs)
+	tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL);
+	if (!tlinks)
 		return ERR_PTR(-ENOMEM);
 
 	for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
-		tprogs[kind].nr_progs = tr->progs_cnt[kind];
+		tlinks[kind].nr_links = tr->progs_cnt[kind];
 		*total += tr->progs_cnt[kind];
-		progs = tprogs[kind].progs;
+		links = tlinks[kind].links;
 
-		hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) {
-			*ip_arg |= aux->prog->call_get_func_ip;
-			*progs++ = aux->prog;
+		hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) {
+			*ip_arg |= link->link.prog->call_get_func_ip;
+			*links++ = link;
 		}
 	}
-	return tprogs;
+	return tlinks;
 }
 
 static void __bpf_tramp_image_put_deferred(struct work_struct *work)
@@ -330,14 +330,14 @@ out:
 static int bpf_trampoline_update(struct bpf_trampoline *tr)
 {
 	struct bpf_tramp_image *im;
-	struct bpf_tramp_progs *tprogs;
+	struct bpf_tramp_links *tlinks;
 	u32 flags = BPF_TRAMP_F_RESTORE_REGS;
 	bool ip_arg = false;
 	int err, total;
 
-	tprogs = bpf_trampoline_get_progs(tr, &total, &ip_arg);
-	if (IS_ERR(tprogs))
-		return PTR_ERR(tprogs);
+	tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg);
+	if (IS_ERR(tlinks))
+		return PTR_ERR(tlinks);
 
 	if (total == 0) {
 		err = unregister_fentry(tr, tr->cur_image->image);
@@ -353,15 +353,15 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 		goto out;
 	}
 
-	if (tprogs[BPF_TRAMP_FEXIT].nr_progs ||
-	    tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
+	if (tlinks[BPF_TRAMP_FEXIT].nr_links ||
+	    tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links)
 		flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
 
 	if (ip_arg)
 		flags |= BPF_TRAMP_F_IP_ARG;
 
 	err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
-					  &tr->func.model, flags, tprogs,
+					  &tr->func.model, flags, tlinks,
 					  tr->func.addr);
 	if (err < 0)
 		goto out;
@@ -381,7 +381,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 	tr->cur_image = im;
 	tr->selector++;
 out:
-	kfree(tprogs);
+	kfree(tlinks);
 	return err;
 }
 
@@ -407,13 +407,14 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
 	}
 }
 
-int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
+int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
+	struct bpf_tramp_link *link_exiting;
 	int err = 0;
 	int cnt;
 
-	kind = bpf_attach_type_to_tramp(prog);
+	kind = bpf_attach_type_to_tramp(link->link.prog);
 	mutex_lock(&tr->mutex);
 	if (tr->extension_prog) {
 		/* cannot attach fentry/fexit if extension prog is attached.
@@ -429,25 +430,33 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 			err = -EBUSY;
 			goto out;
 		}
-		tr->extension_prog = prog;
+		tr->extension_prog = link->link.prog;
 		err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL,
-					 prog->bpf_func);
+					 link->link.prog->bpf_func);
 		goto out;
 	}
-	if (cnt >= BPF_MAX_TRAMP_PROGS) {
+	if (cnt >= BPF_MAX_TRAMP_LINKS) {
 		err = -E2BIG;
 		goto out;
 	}
-	if (!hlist_unhashed(&prog->aux->tramp_hlist)) {
+	if (!hlist_unhashed(&link->tramp_hlist)) {
 		/* prog already linked */
 		err = -EBUSY;
 		goto out;
 	}
-	hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]);
+	hlist_for_each_entry(link_exiting, &tr->progs_hlist[kind], tramp_hlist) {
+		if (link_exiting->link.prog != link->link.prog)
+			continue;
+		/* prog already linked */
+		err = -EBUSY;
+		goto out;
+	}
+
+	hlist_add_head(&link->tramp_hlist, &tr->progs_hlist[kind]);
 	tr->progs_cnt[kind]++;
 	err = bpf_trampoline_update(tr);
 	if (err) {
-		hlist_del_init(&prog->aux->tramp_hlist);
+		hlist_del_init(&link->tramp_hlist);
 		tr->progs_cnt[kind]--;
 	}
 out:
@@ -456,12 +465,12 @@ out:
 }
 
 /* bpf_trampoline_unlink_prog() should never fail. */
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
+int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
 	int err;
 
-	kind = bpf_attach_type_to_tramp(prog);
+	kind = bpf_attach_type_to_tramp(link->link.prog);
 	mutex_lock(&tr->mutex);
 	if (kind == BPF_TRAMP_REPLACE) {
 		WARN_ON_ONCE(!tr->extension_prog);
@@ -470,7 +479,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 		tr->extension_prog = NULL;
 		goto out;
 	}
-	hlist_del_init(&prog->aux->tramp_hlist);
+	hlist_del_init(&link->tramp_hlist);
 	tr->progs_cnt[kind]--;
 	err = bpf_trampoline_update(tr);
 out:
@@ -635,7 +644,7 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr)
 int __weak
 arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,
-			    struct bpf_tramp_progs *tprogs,
+			    struct bpf_tramp_links *tlinks,
 			    void *orig_call)
 {
 	return -ENOTSUPP;
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index d0e54e30658a..e78dadfc5829 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -72,13 +72,16 @@ static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args)
 		    args->args[3], args->args[4]);
 }
 
+extern const struct bpf_link_ops bpf_struct_ops_link_lops;
+
 int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 			    union bpf_attr __user *uattr)
 {
 	const struct bpf_struct_ops *st_ops = &bpf_bpf_dummy_ops;
 	const struct btf_type *func_proto;
 	struct bpf_dummy_ops_test_args *args;
-	struct bpf_tramp_progs *tprogs;
+	struct bpf_tramp_links *tlinks;
+	struct bpf_tramp_link *link = NULL;
 	void *image = NULL;
 	unsigned int op_idx;
 	int prog_ret;
@@ -92,8 +95,8 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (IS_ERR(args))
 		return PTR_ERR(args);
 
-	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
-	if (!tprogs) {
+	tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL);
+	if (!tlinks) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -105,8 +108,17 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	}
 	set_vm_flush_reset_perms(image);
 
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
+		err = -ENOMEM;
+		goto out;
+	}
+	/* prog doesn't take the ownership of the reference from caller */
+	bpf_prog_inc(prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_link_lops, prog);
+
 	op_idx = prog->expected_attach_type;
-	err = bpf_struct_ops_prepare_trampoline(tprogs, prog,
+	err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 						&st_ops->func_models[op_idx],
 						image, image + PAGE_SIZE);
 	if (err < 0)
@@ -124,7 +136,9 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 out:
 	kfree(args);
 	bpf_jit_free_exec(image);
-	kfree(tprogs);
+	if (link)
+		bpf_link_put(&link->link);
+	kfree(tlinks);
 	return err;
 }
 
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 8fb0116f9136..6353a789322b 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -23,6 +23,7 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_XDP]			= "xdp",
 	[BPF_LINK_TYPE_PERF_EVENT]		= "perf_event",
 	[BPF_LINK_TYPE_KPROBE_MULTI]		= "kprobe_multi",
+	[BPF_LINK_TYPE_STRUCT_OPS]               = "struct_ops",
 };
 
 static struct hashmap *link_table;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 95a3d1ff6255..3d032ea1b6a3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1013,6 +1013,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_XDP = 6,
 	BPF_LINK_TYPE_PERF_EVENT = 7,
 	BPF_LINK_TYPE_KPROBE_MULTI = 8,
+	BPF_LINK_TYPE_STRUCT_OPS = 9,
 
 	MAX_BPF_LINK_TYPE,
 };
-- 
cgit v1.2.3


From e384c7b7b46d0a5f4bf3c554f963e6e9622d0ab1 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <kuifeng@fb.com>
Date: Tue, 10 May 2022 13:59:20 -0700
Subject: bpf, x86: Create bpf_tramp_run_ctx on the caller thread's stack

BPF trampolines will create a bpf_tramp_run_ctx, a bpf_run_ctx, on
stacks and set/reset the current bpf_run_ctx before/after calling a
bpf_prog.

Signed-off-by: Kui-Feng Lee <kuifeng@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220510205923.3206889-3-kuifeng@fb.com
---
 arch/x86/net/bpf_jit_comp.c | 41 ++++++++++++++++++++++++++++++++---------
 include/linux/bpf.h         | 17 +++++++++++++----
 kernel/bpf/syscall.c        |  7 +++++--
 kernel/bpf/trampoline.c     | 20 ++++++++++++++++----
 4 files changed, 66 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 38eb43159230..1fbc5cf1c7a7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1763,14 +1763,30 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			   struct bpf_tramp_link *l, int stack_size,
-			   bool save_ret)
+			   int run_ctx_off, bool save_ret)
 {
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
+	int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
 	struct bpf_prog *p = l->link.prog;
 
+	/* mov rdi, 0 */
+	emit_mov_imm64(&prog, BPF_REG_1, 0, 0);
+
+	/* Prepare struct bpf_tramp_run_ctx.
+	 *
+	 * bpf_tramp_run_ctx is already preserved by
+	 * arch_prepare_bpf_trampoline().
+	 *
+	 * mov QWORD PTR [rbp - run_ctx_off + ctx_cookie_off], rdi
+	 */
+	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off);
+
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
+	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
+	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
+
 	if (emit_call(&prog,
 		      p->aux->sleepable ? __bpf_prog_enter_sleepable :
 		      __bpf_prog_enter, prog))
@@ -1816,6 +1832,8 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
 	/* arg2: mov rsi, rbx <- start time in nsec */
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+	/* arg3: lea rdx, [rbp - run_ctx_off] */
+	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
 	if (emit_call(&prog,
 		      p->aux->sleepable ? __bpf_prog_exit_sleepable :
 		      __bpf_prog_exit, prog))
@@ -1853,14 +1871,14 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 		      struct bpf_tramp_links *tl, int stack_size,
-		      bool save_ret)
+		      int run_ctx_off, bool save_ret)
 {
 	int i;
 	u8 *prog = *pprog;
 
 	for (i = 0; i < tl->nr_links; i++) {
 		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size,
-				    save_ret))
+				    run_ctx_off, save_ret))
 			return -EINVAL;
 	}
 	*pprog = prog;
@@ -1869,7 +1887,7 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 
 static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 			      struct bpf_tramp_links *tl, int stack_size,
-			      u8 **branches)
+			      int run_ctx_off, u8 **branches)
 {
 	u8 *prog = *pprog;
 	int i;
@@ -1880,7 +1898,7 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_imm32(&prog, false, BPF_REG_0, 0);
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 	for (i = 0; i < tl->nr_links; i++) {
-		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, true))
+		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true))
 			return -EINVAL;
 
 		/* mod_ret prog stored return value into [rbp - 8]. Emit:
@@ -1986,7 +2004,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 				void *orig_call)
 {
 	int ret, i, nr_args = m->nr_args;
-	int regs_off, ip_off, args_off, stack_size = nr_args * 8;
+	int regs_off, ip_off, args_off, stack_size = nr_args * 8, run_ctx_off;
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
@@ -2016,6 +2034,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	 * RBP - args_off  [ args count      ]  always
 	 *
 	 * RBP - ip_off    [ traced function ]  BPF_TRAMP_F_IP_ARG flag
+	 *
+	 * RBP - run_ctx_off [ bpf_tramp_run_ctx ]
 	 */
 
 	/* room for return value of orig_call or fentry prog */
@@ -2034,6 +2054,9 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 
 	ip_off = stack_size;
 
+	stack_size += (sizeof(struct bpf_tramp_run_ctx) + 7) & ~0x7;
+	run_ctx_off = stack_size;
+
 	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
@@ -2081,7 +2104,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (fentry->nr_links)
-		if (invoke_bpf(m, &prog, fentry, regs_off,
+		if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
 			       flags & BPF_TRAMP_F_RET_FENTRY_RET))
 			return -EINVAL;
 
@@ -2092,7 +2115,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 			return -ENOMEM;
 
 		if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off,
-				       branches)) {
+				       run_ctx_off, branches)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2129,7 +2152,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (fexit->nr_links)
-		if (invoke_bpf(m, &prog, fexit, regs_off, false)) {
+		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 75e0110a65e1..256fb802e580 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -730,6 +730,8 @@ struct bpf_tramp_links {
 	int nr_links;
 };
 
+struct bpf_tramp_run_ctx;
+
 /* Different use cases for BPF trampoline:
  * 1. replace nop at the function entry (kprobe equivalent)
  *    flags = BPF_TRAMP_F_RESTORE_REGS
@@ -756,10 +758,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i
 				struct bpf_tramp_links *tlinks,
 				void *orig_call);
 /* these two functions are called from generated trampoline */
-u64 notrace __bpf_prog_enter(struct bpf_prog *prog);
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
-u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog);
-void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start);
+u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx);
+u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
+				       struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
 void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
 
@@ -1351,6 +1354,12 @@ struct bpf_trace_run_ctx {
 	u64 bpf_cookie;
 };
 
+struct bpf_tramp_run_ctx {
+	struct bpf_run_ctx run_ctx;
+	u64 bpf_cookie;
+	struct bpf_run_ctx *saved_run_ctx;
+};
+
 static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx)
 {
 	struct bpf_run_ctx *old_ctx = NULL;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2dc582773344..d48165fccf49 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5020,6 +5020,7 @@ static bool syscall_prog_is_valid_access(int off, int size,
 BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
 {
 	struct bpf_prog * __maybe_unused prog;
+	struct bpf_tramp_run_ctx __maybe_unused run_ctx;
 
 	switch (cmd) {
 	case BPF_MAP_CREATE:
@@ -5047,13 +5048,15 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
 			return -EINVAL;
 		}
 
-		if (!__bpf_prog_enter_sleepable(prog)) {
+		run_ctx.bpf_cookie = 0;
+		run_ctx.saved_run_ctx = NULL;
+		if (!__bpf_prog_enter_sleepable(prog, &run_ctx)) {
 			/* recursion detected */
 			bpf_prog_put(prog);
 			return -EBUSY;
 		}
 		attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in);
-		__bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */);
+		__bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx);
 		bpf_prog_put(prog);
 		return 0;
 #endif
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index d5e6bc5517cb..baf1b65d523e 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -568,11 +568,14 @@ static void notrace inc_misses_counter(struct bpf_prog *prog)
  * [2..MAX_U64] - execute bpf prog and record execution time.
  *     This is start time.
  */
-u64 notrace __bpf_prog_enter(struct bpf_prog *prog)
+u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
 	__acquires(RCU)
 {
 	rcu_read_lock();
 	migrate_disable();
+
+	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
 	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
 		inc_misses_counter(prog);
 		return 0;
@@ -602,29 +605,38 @@ static void notrace update_prog_stats(struct bpf_prog *prog,
 	}
 }
 
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx)
 	__releases(RCU)
 {
+	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
 	update_prog_stats(prog, start);
 	__this_cpu_dec(*(prog->active));
 	migrate_enable();
 	rcu_read_unlock();
 }
 
-u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog)
+u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
 {
 	rcu_read_lock_trace();
 	migrate_disable();
 	might_fault();
+
 	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
 		inc_misses_counter(prog);
 		return 0;
 	}
+
+	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
 	return bpf_prog_start_time();
 }
 
-void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start)
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
+				       struct bpf_tramp_run_ctx *run_ctx)
 {
+	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
 	update_prog_stats(prog, start);
 	__this_cpu_dec(*(prog->active));
 	migrate_enable();
-- 
cgit v1.2.3


From 2fcc82411e74e5e6aba336561cf56fb899bfae4e Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <kuifeng@fb.com>
Date: Tue, 10 May 2022 13:59:21 -0700
Subject: bpf, x86: Attach a cookie to fentry/fexit/fmod_ret/lsm.

Pass a cookie along with BPF_LINK_CREATE requests.

Add a bpf_cookie field to struct bpf_tracing_link to attach a cookie.
The cookie of a bpf_tracing_link is available by calling
bpf_get_attach_cookie when running the BPF program of the attached
link.

The value of a cookie will be set at bpf_tramp_run_ctx by the
trampoline of the link.

Signed-off-by: Kui-Feng Lee <kuifeng@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220510205923.3206889-4-kuifeng@fb.com
---
 arch/x86/net/bpf_jit_comp.c    |  5 +++--
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       |  9 +++++++++
 kernel/bpf/bpf_lsm.c           | 17 +++++++++++++++++
 kernel/bpf/syscall.c           | 12 ++++++++----
 kernel/bpf/trampoline.c        |  7 +++++--
 kernel/trace/bpf_trace.c       | 17 +++++++++++++++++
 tools/include/uapi/linux/bpf.h |  9 +++++++++
 8 files changed, 69 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 1fbc5cf1c7a7..a2b6d197c226 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1769,9 +1769,10 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	u8 *jmp_insn;
 	int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
 	struct bpf_prog *p = l->link.prog;
+	u64 cookie = l->cookie;
 
-	/* mov rdi, 0 */
-	emit_mov_imm64(&prog, BPF_REG_1, 0, 0);
+	/* mov rdi, cookie */
+	emit_mov_imm64(&prog, BPF_REG_1, (long) cookie >> 32, (u32) (long) cookie);
 
 	/* Prepare struct bpf_tramp_run_ctx.
 	 *
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 256fb802e580..aba7ded56436 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1102,6 +1102,7 @@ struct bpf_link_ops {
 struct bpf_tramp_link {
 	struct bpf_link link;
 	struct hlist_node tramp_hlist;
+	u64 cookie;
 };
 
 struct bpf_tracing_link {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3d032ea1b6a3..bc7f89948f54 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1490,6 +1490,15 @@ union bpf_attr {
 				__aligned_u64	addrs;
 				__aligned_u64	cookies;
 			} kprobe_multi;
+			struct {
+				/* this is overlaid with the target_btf_id above. */
+				__u32		target_btf_id;
+				/* black box user-provided value passed through
+				 * to BPF program at the execution time and
+				 * accessible through bpf_get_attach_cookie() BPF helper
+				 */
+				__u64		cookie;
+			} tracing;
 		};
 	} link_create;
 
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 064eccba641d..c1351df9f7ee 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -117,6 +117,21 @@ static const struct bpf_func_proto bpf_ima_file_hash_proto = {
 	.allowed	= bpf_ima_inode_hash_allowed,
 };
 
+BPF_CALL_1(bpf_get_attach_cookie, void *, ctx)
+{
+	struct bpf_trace_run_ctx *run_ctx;
+
+	run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx);
+	return run_ctx->bpf_cookie;
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto = {
+	.func		= bpf_get_attach_cookie,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 static const struct bpf_func_proto *
 bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -141,6 +156,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL;
 	case BPF_FUNC_ima_file_hash:
 		return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL;
+	case BPF_FUNC_get_attach_cookie:
+		return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL;
 	default:
 		return tracing_prog_func_proto(func_id, prog);
 	}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d48165fccf49..72e53489165d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2921,7 +2921,8 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
 
 static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 				   int tgt_prog_fd,
-				   u32 btf_id)
+				   u32 btf_id,
+				   u64 bpf_cookie)
 {
 	struct bpf_link_primer link_primer;
 	struct bpf_prog *tgt_prog = NULL;
@@ -2986,6 +2987,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING,
 		      &bpf_tracing_link_lops, prog);
 	link->attach_type = prog->expected_attach_type;
+	link->link.cookie = bpf_cookie;
 
 	mutex_lock(&prog->aux->dst_mutex);
 
@@ -3271,7 +3273,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
 			tp_name = prog->aux->attach_func_name;
 			break;
 		}
-		return bpf_tracing_prog_attach(prog, 0, 0);
+		return bpf_tracing_prog_attach(prog, 0, 0, 0);
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 		if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0)
@@ -4524,7 +4526,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_EXT:
 		ret = bpf_tracing_prog_attach(prog,
 					      attr->link_create.target_fd,
-					      attr->link_create.target_btf_id);
+					      attr->link_create.target_btf_id,
+					      attr->link_create.tracing.cookie);
 		break;
 	case BPF_PROG_TYPE_LSM:
 	case BPF_PROG_TYPE_TRACING:
@@ -4539,7 +4542,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		else
 			ret = bpf_tracing_prog_attach(prog,
 						      attr->link_create.target_fd,
-						      attr->link_create.target_btf_id);
+						      attr->link_create.target_btf_id,
+						      attr->link_create.tracing.cookie);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_SK_LOOKUP:
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index baf1b65d523e..0e9b3aefc34a 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -30,9 +30,12 @@ static DEFINE_MUTEX(trampoline_mutex);
 bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
 {
 	enum bpf_attach_type eatype = prog->expected_attach_type;
+	enum bpf_prog_type ptype = prog->type;
 
-	return eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT ||
-	       eatype == BPF_MODIFY_RETURN;
+	return (ptype == BPF_PROG_TYPE_TRACING &&
+		(eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT ||
+		 eatype == BPF_MODIFY_RETURN)) ||
+		(ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC);
 }
 
 void *bpf_jit_alloc_exec_page(void)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7fd11c17558d..2eaac094caf8 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1091,6 +1091,21 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_attach_cookie_tracing, void *, ctx)
+{
+	struct bpf_trace_run_ctx *run_ctx;
+
+	run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx);
+	return run_ctx->bpf_cookie;
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto_tracing = {
+	.func		= bpf_get_attach_cookie_tracing,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags)
 {
 #ifndef CONFIG_X86
@@ -1719,6 +1734,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL;
 	case BPF_FUNC_get_func_arg_cnt:
 		return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL;
+	case BPF_FUNC_get_attach_cookie:
+		return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto_tracing : NULL;
 	default:
 		fn = raw_tp_prog_func_proto(func_id, prog);
 		if (!fn && prog->expected_attach_type == BPF_TRACE_ITER)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3d032ea1b6a3..bc7f89948f54 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1490,6 +1490,15 @@ union bpf_attr {
 				__aligned_u64	addrs;
 				__aligned_u64	cookies;
 			} kprobe_multi;
+			struct {
+				/* this is overlaid with the target_btf_id above. */
+				__u32		target_btf_id;
+				/* black box user-provided value passed through
+				 * to BPF program at the execution time and
+				 * accessible through bpf_get_attach_cookie() BPF helper
+				 */
+				__u64		cookie;
+			} tracing;
 		};
 	} link_create;
 
-- 
cgit v1.2.3


From 5b87be9e4978fe507c7e14c0bdff147d10d39aec Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 May 2022 20:57:37 -0700
Subject: net: add include/net/net_debug.h

Remove from include/linux/netdevice.h helpers
that send debug/info/warnings to syslog.

We plan adding more helpers in following patches.

v2: added two includes, and 'struct net_device' forward declaration
    to avoid compile errors (kernel bots)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 141 +------------------------------------------
 include/net/net_debug.h   | 151 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 152 insertions(+), 140 deletions(-)
 create mode 100644 include/net/net_debug.h

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 51fe143091cf..536321691c72 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -50,6 +50,7 @@
 #include <linux/hashtable.h>
 #include <linux/rbtree.h>
 #include <net/net_trackers.h>
+#include <net/net_debug.h>
 
 struct netpoll_info;
 struct device;
@@ -5071,81 +5072,9 @@ static inline const char *netdev_reg_state(const struct net_device *dev)
 	return " (unknown)";
 }
 
-__printf(3, 4) __cold
-void netdev_printk(const char *level, const struct net_device *dev,
-		   const char *format, ...);
-__printf(2, 3) __cold
-void netdev_emerg(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_alert(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_crit(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_err(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_warn(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_notice(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_info(const struct net_device *dev, const char *format, ...);
-
-#define netdev_level_once(level, dev, fmt, ...)			\
-do {								\
-	static bool __section(".data.once") __print_once;	\
-								\
-	if (!__print_once) {					\
-		__print_once = true;				\
-		netdev_printk(level, dev, fmt, ##__VA_ARGS__);	\
-	}							\
-} while (0)
-
-#define netdev_emerg_once(dev, fmt, ...) \
-	netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__)
-#define netdev_alert_once(dev, fmt, ...) \
-	netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__)
-#define netdev_crit_once(dev, fmt, ...) \
-	netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__)
-#define netdev_err_once(dev, fmt, ...) \
-	netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__)
-#define netdev_warn_once(dev, fmt, ...) \
-	netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__)
-#define netdev_notice_once(dev, fmt, ...) \
-	netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__)
-#define netdev_info_once(dev, fmt, ...) \
-	netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__)
-
 #define MODULE_ALIAS_NETDEV(device) \
 	MODULE_ALIAS("netdev-" device)
 
-#if defined(CONFIG_DYNAMIC_DEBUG) || \
-	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
-#define netdev_dbg(__dev, format, args...)			\
-do {								\
-	dynamic_netdev_dbg(__dev, format, ##args);		\
-} while (0)
-#elif defined(DEBUG)
-#define netdev_dbg(__dev, format, args...)			\
-	netdev_printk(KERN_DEBUG, __dev, format, ##args)
-#else
-#define netdev_dbg(__dev, format, args...)			\
-({								\
-	if (0)							\
-		netdev_printk(KERN_DEBUG, __dev, format, ##args); \
-})
-#endif
-
-#if defined(VERBOSE_DEBUG)
-#define netdev_vdbg	netdev_dbg
-#else
-
-#define netdev_vdbg(dev, format, args...)			\
-({								\
-	if (0)							\
-		netdev_printk(KERN_DEBUG, dev, format, ##args);	\
-	0;							\
-})
-#endif
-
 /*
  * netdev_WARN() acts like dev_printk(), but with the key difference
  * of using a WARN/WARN_ON to get the message out, including the
@@ -5159,74 +5088,6 @@ do {								\
 	WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev),	\
 		  netdev_reg_state(dev), ##args)
 
-/* netif printk helpers, similar to netdev_printk */
-
-#define netif_printk(priv, type, level, dev, fmt, args...)	\
-do {					  			\
-	if (netif_msg_##type(priv))				\
-		netdev_printk(level, (dev), fmt, ##args);	\
-} while (0)
-
-#define netif_level(level, priv, type, dev, fmt, args...)	\
-do {								\
-	if (netif_msg_##type(priv))				\
-		netdev_##level(dev, fmt, ##args);		\
-} while (0)
-
-#define netif_emerg(priv, type, dev, fmt, args...)		\
-	netif_level(emerg, priv, type, dev, fmt, ##args)
-#define netif_alert(priv, type, dev, fmt, args...)		\
-	netif_level(alert, priv, type, dev, fmt, ##args)
-#define netif_crit(priv, type, dev, fmt, args...)		\
-	netif_level(crit, priv, type, dev, fmt, ##args)
-#define netif_err(priv, type, dev, fmt, args...)		\
-	netif_level(err, priv, type, dev, fmt, ##args)
-#define netif_warn(priv, type, dev, fmt, args...)		\
-	netif_level(warn, priv, type, dev, fmt, ##args)
-#define netif_notice(priv, type, dev, fmt, args...)		\
-	netif_level(notice, priv, type, dev, fmt, ##args)
-#define netif_info(priv, type, dev, fmt, args...)		\
-	netif_level(info, priv, type, dev, fmt, ##args)
-
-#if defined(CONFIG_DYNAMIC_DEBUG) || \
-	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
-#define netif_dbg(priv, type, netdev, format, args...)		\
-do {								\
-	if (netif_msg_##type(priv))				\
-		dynamic_netdev_dbg(netdev, format, ##args);	\
-} while (0)
-#elif defined(DEBUG)
-#define netif_dbg(priv, type, dev, format, args...)		\
-	netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
-#else
-#define netif_dbg(priv, type, dev, format, args...)			\
-({									\
-	if (0)								\
-		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
-	0;								\
-})
-#endif
-
-/* if @cond then downgrade to debug, else print at @level */
-#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...)     \
-	do {                                                              \
-		if (cond)                                                 \
-			netif_dbg(priv, type, netdev, fmt, ##args);       \
-		else                                                      \
-			netif_ ## level(priv, type, netdev, fmt, ##args); \
-	} while (0)
-
-#if defined(VERBOSE_DEBUG)
-#define netif_vdbg	netif_dbg
-#else
-#define netif_vdbg(priv, type, dev, format, args...)		\
-({								\
-	if (0)							\
-		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
-	0;							\
-})
-#endif
-
 /*
  *	The list of packet types we will receive (as opposed to discard)
  *	and the routines to invoke.
diff --git a/include/net/net_debug.h b/include/net/net_debug.h
new file mode 100644
index 000000000000..19cd2700c20e
--- /dev/null
+++ b/include/net/net_debug.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NET_DEBUG_H
+#define _LINUX_NET_DEBUG_H
+
+#include <linux/bug.h>
+#include <linux/kern_levels.h>
+
+struct net_device;
+
+__printf(3, 4) __cold
+void netdev_printk(const char *level, const struct net_device *dev,
+		   const char *format, ...);
+__printf(2, 3) __cold
+void netdev_emerg(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_alert(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_crit(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_err(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_warn(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_notice(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_info(const struct net_device *dev, const char *format, ...);
+
+#define netdev_level_once(level, dev, fmt, ...)			\
+do {								\
+	static bool __section(".data.once") __print_once;	\
+								\
+	if (!__print_once) {					\
+		__print_once = true;				\
+		netdev_printk(level, dev, fmt, ##__VA_ARGS__);	\
+	}							\
+} while (0)
+
+#define netdev_emerg_once(dev, fmt, ...) \
+	netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__)
+#define netdev_alert_once(dev, fmt, ...) \
+	netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__)
+#define netdev_crit_once(dev, fmt, ...) \
+	netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__)
+#define netdev_err_once(dev, fmt, ...) \
+	netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__)
+#define netdev_warn_once(dev, fmt, ...) \
+	netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__)
+#define netdev_notice_once(dev, fmt, ...) \
+	netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__)
+#define netdev_info_once(dev, fmt, ...) \
+	netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__)
+
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+#define netdev_dbg(__dev, format, args...)			\
+do {								\
+	dynamic_netdev_dbg(__dev, format, ##args);		\
+} while (0)
+#elif defined(DEBUG)
+#define netdev_dbg(__dev, format, args...)			\
+	netdev_printk(KERN_DEBUG, __dev, format, ##args)
+#else
+#define netdev_dbg(__dev, format, args...)			\
+({								\
+	if (0)							\
+		netdev_printk(KERN_DEBUG, __dev, format, ##args); \
+})
+#endif
+
+#if defined(VERBOSE_DEBUG)
+#define netdev_vdbg	netdev_dbg
+#else
+
+#define netdev_vdbg(dev, format, args...)			\
+({								\
+	if (0)							\
+		netdev_printk(KERN_DEBUG, dev, format, ##args);	\
+	0;							\
+})
+#endif
+
+/* netif printk helpers, similar to netdev_printk */
+
+#define netif_printk(priv, type, level, dev, fmt, args...)	\
+do {					  			\
+	if (netif_msg_##type(priv))				\
+		netdev_printk(level, (dev), fmt, ##args);	\
+} while (0)
+
+#define netif_level(level, priv, type, dev, fmt, args...)	\
+do {								\
+	if (netif_msg_##type(priv))				\
+		netdev_##level(dev, fmt, ##args);		\
+} while (0)
+
+#define netif_emerg(priv, type, dev, fmt, args...)		\
+	netif_level(emerg, priv, type, dev, fmt, ##args)
+#define netif_alert(priv, type, dev, fmt, args...)		\
+	netif_level(alert, priv, type, dev, fmt, ##args)
+#define netif_crit(priv, type, dev, fmt, args...)		\
+	netif_level(crit, priv, type, dev, fmt, ##args)
+#define netif_err(priv, type, dev, fmt, args...)		\
+	netif_level(err, priv, type, dev, fmt, ##args)
+#define netif_warn(priv, type, dev, fmt, args...)		\
+	netif_level(warn, priv, type, dev, fmt, ##args)
+#define netif_notice(priv, type, dev, fmt, args...)		\
+	netif_level(notice, priv, type, dev, fmt, ##args)
+#define netif_info(priv, type, dev, fmt, args...)		\
+	netif_level(info, priv, type, dev, fmt, ##args)
+
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+#define netif_dbg(priv, type, netdev, format, args...)		\
+do {								\
+	if (netif_msg_##type(priv))				\
+		dynamic_netdev_dbg(netdev, format, ##args);	\
+} while (0)
+#elif defined(DEBUG)
+#define netif_dbg(priv, type, dev, format, args...)		\
+	netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
+#else
+#define netif_dbg(priv, type, dev, format, args...)			\
+({									\
+	if (0)								\
+		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
+	0;								\
+})
+#endif
+
+/* if @cond then downgrade to debug, else print at @level */
+#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...)     \
+	do {                                                              \
+		if (cond)                                                 \
+			netif_dbg(priv, type, netdev, fmt, ##args);       \
+		else                                                      \
+			netif_ ## level(priv, type, netdev, fmt, ##args); \
+	} while (0)
+
+#if defined(VERBOSE_DEBUG)
+#define netif_vdbg	netif_dbg
+#else
+#define netif_vdbg(priv, type, dev, format, args...)		\
+({								\
+	if (0)							\
+		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
+	0;							\
+})
+#endif
+
+
+#endif	/* _LINUX_NET_DEBUG_H */
-- 
cgit v1.2.3


From 66e4c8d950083df8e12981babca788e1635c92b6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 May 2022 20:57:39 -0700
Subject: net: warn if transport header was not set

Make sure skb_transport_header() and skb_transport_offset() uses
are not fooled if the transport header has not been set.

This change will likely expose existing bugs in linux networking stacks.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5296b2c37f62..b91d225fdc13 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -42,6 +42,7 @@
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <linux/netfilter/nf_conntrack_common.h>
 #endif
+#include <net/net_debug.h>
 
 /**
  * DOC: skb checksums
@@ -2904,6 +2905,7 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb)
 
 static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
 {
+	DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb));
 	return skb->head + skb->transport_header;
 }
 
-- 
cgit v1.2.3


From ee692a21e9bf8354bd3ec816f1cf4bff8619ed77 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 11 May 2022 11:17:45 +0530
Subject: fs,io_uring: add infrastructure for uring-cmd

file_operations->uring_cmd is a file private handler.
This is somewhat similar to ioctl but hopefully a lot more sane and
useful as it can be used to enable many io_uring capabilities for the
underlying operation.

IORING_OP_URING_CMD is a file private kind of request. io_uring doesn't
know what is in this command type, it's for the provider of ->uring_cmd()
to deal with.

Co-developed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220511054750.20432-2-joshi.k@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 135 ++++++++++++++++++++++++++++++++++++------
 include/linux/fs.h            |   2 +
 include/linux/io_uring.h      |  33 +++++++++++
 include/uapi/linux/io_uring.h |  21 ++++---
 4 files changed, 165 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index ceaf7826ed71..44c57dca358d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -202,13 +202,6 @@ struct io_rings {
 	struct io_uring_cqe	cqes[] ____cacheline_aligned_in_smp;
 };
 
-enum io_uring_cmd_flags {
-	IO_URING_F_COMPLETE_DEFER	= 1,
-	IO_URING_F_UNLOCKED		= 2,
-	/* int's last bit, sign checks are usually faster than a bit test */
-	IO_URING_F_NONBLOCK		= INT_MIN,
-};
-
 struct io_mapped_ubuf {
 	u64		ubuf;
 	u64		ubuf_end;
@@ -972,6 +965,7 @@ struct io_kiocb {
 		struct io_xattr		xattr;
 		struct io_socket	sock;
 		struct io_nop		nop;
+		struct io_uring_cmd	uring_cmd;
 	};
 
 	u8				opcode;
@@ -1050,6 +1044,14 @@ struct io_cancel_data {
 	int seq;
 };
 
+/*
+ * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into
+ * the following sqe if SQE128 is used.
+ */
+#define uring_cmd_pdu_size(is_sqe128)				\
+	((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) -	\
+		offsetof(struct io_uring_sqe, cmd))
+
 struct io_op_def {
 	/* needs req->file assigned */
 	unsigned		needs_file : 1;
@@ -1289,6 +1291,12 @@ static const struct io_op_def io_op_defs[] = {
 	[IORING_OP_SOCKET] = {
 		.audit_skip		= 1,
 	},
+	[IORING_OP_URING_CMD] = {
+		.needs_file		= 1,
+		.plug			= 1,
+		.needs_async_setup	= 1,
+		.async_size		= uring_cmd_pdu_size(1),
+	},
 };
 
 /* requests with any of those set should undergo io_disarm_next() */
@@ -1428,6 +1436,8 @@ const char *io_uring_get_opcode(u8 opcode)
 		return "GETXATTR";
 	case IORING_OP_SOCKET:
 		return "SOCKET";
+	case IORING_OP_URING_CMD:
+		return "URING_CMD";
 	case IORING_OP_LAST:
 		return "INVALID";
 	}
@@ -4507,10 +4517,6 @@ static int __io_getxattr_prep(struct io_kiocb *req,
 	const char __user *name;
 	int ret;
 
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
-		return -EINVAL;
-	if (unlikely(sqe->ioprio))
-		return -EINVAL;
 	if (unlikely(req->flags & REQ_F_FIXED_FILE))
 		return -EBADF;
 
@@ -4620,10 +4626,6 @@ static int __io_setxattr_prep(struct io_kiocb *req,
 	const char __user *name;
 	int ret;
 
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
-		return -EINVAL;
-	if (unlikely(sqe->ioprio))
-		return -EINVAL;
 	if (unlikely(req->flags & REQ_F_FIXED_FILE))
 		return -EBADF;
 
@@ -4910,6 +4912,96 @@ static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
 	return 0;
 }
 
+static void io_uring_cmd_work(struct io_kiocb *req, bool *locked)
+{
+	req->uring_cmd.task_work_cb(&req->uring_cmd);
+}
+
+void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *))
+{
+	struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
+
+	req->uring_cmd.task_work_cb = task_work_cb;
+	req->io_task_work.func = io_uring_cmd_work;
+	io_req_task_work_add(req, !!(req->ctx->flags & IORING_SETUP_SQPOLL));
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task);
+
+/*
+ * Called by consumers of io_uring_cmd, if they originally returned
+ * -EIOCBQUEUED upon receiving the command.
+ */
+void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2)
+{
+	struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
+
+	if (ret < 0)
+		req_set_fail(req);
+	if (req->ctx->flags & IORING_SETUP_CQE32)
+		__io_req_complete32(req, 0, ret, 0, res2, 0);
+	else
+		io_req_complete(req, ret);
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_done);
+
+static int io_uring_cmd_prep_async(struct io_kiocb *req)
+{
+	size_t cmd_size;
+
+	cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128);
+
+	memcpy(req->async_data, req->uring_cmd.cmd, cmd_size);
+	return 0;
+}
+
+static int io_uring_cmd_prep(struct io_kiocb *req,
+			     const struct io_uring_sqe *sqe)
+{
+	struct io_uring_cmd *ioucmd = &req->uring_cmd;
+
+	if (sqe->rw_flags)
+		return -EINVAL;
+	ioucmd->cmd = sqe->cmd;
+	ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
+	return 0;
+}
+
+static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_uring_cmd *ioucmd = &req->uring_cmd;
+	struct io_ring_ctx *ctx = req->ctx;
+	struct file *file = req->file;
+	int ret;
+
+	if (!req->file->f_op->uring_cmd)
+		return -EOPNOTSUPP;
+
+	if (ctx->flags & IORING_SETUP_SQE128)
+		issue_flags |= IO_URING_F_SQE128;
+	if (ctx->flags & IORING_SETUP_CQE32)
+		issue_flags |= IO_URING_F_CQE32;
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		issue_flags |= IO_URING_F_IOPOLL;
+
+	if (req_has_async_data(req))
+		ioucmd->cmd = req->async_data;
+
+	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
+	if (ret == -EAGAIN) {
+		if (!req_has_async_data(req)) {
+			if (io_alloc_async_data(req))
+				return -ENOMEM;
+			io_uring_cmd_prep_async(req);
+		}
+		return -EAGAIN;
+	}
+
+	if (ret != -EIOCBQUEUED)
+		io_uring_cmd_done(ioucmd, ret, 0);
+	return 0;
+}
+
 static int io_shutdown_prep(struct io_kiocb *req,
 			    const struct io_uring_sqe *sqe)
 {
@@ -6305,9 +6397,7 @@ static int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_socket *sock = &req->sock;
 
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
-		return -EINVAL;
-	if (sqe->ioprio || sqe->addr || sqe->rw_flags || sqe->buf_index)
+	if (sqe->addr || sqe->rw_flags || sqe->buf_index)
 		return -EINVAL;
 
 	sock->domain = READ_ONCE(sqe->fd);
@@ -7755,6 +7845,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return io_getxattr_prep(req, sqe);
 	case IORING_OP_SOCKET:
 		return io_socket_prep(req, sqe);
+	case IORING_OP_URING_CMD:
+		return io_uring_cmd_prep(req, sqe);
 	}
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
@@ -7787,6 +7879,8 @@ static int io_req_prep_async(struct io_kiocb *req)
 		return io_recvmsg_prep_async(req);
 	case IORING_OP_CONNECT:
 		return io_connect_prep_async(req);
+	case IORING_OP_URING_CMD:
+		return io_uring_cmd_prep_async(req);
 	}
 	printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n",
 		    req->opcode);
@@ -8081,6 +8175,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 	case IORING_OP_SOCKET:
 		ret = io_socket(req, issue_flags);
 		break;
+	case IORING_OP_URING_CMD:
+		ret = io_uring_cmd(req, issue_flags);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -12699,6 +12796,8 @@ static int __init io_uring_init(void)
 
 	BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32));
 
+	BUILD_BUG_ON(sizeof(struct io_uring_cmd) > 64);
+
 	req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
 				SLAB_ACCOUNT);
 	return 0;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde95387a23..87b5af1d9fbe 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1953,6 +1953,7 @@ struct dir_context {
 #define REMAP_FILE_ADVISORY		(REMAP_FILE_CAN_SHORTEN)
 
 struct iov_iter;
+struct io_uring_cmd;
 
 struct file_operations {
 	struct module *owner;
@@ -1995,6 +1996,7 @@ struct file_operations {
 				   struct file *file_out, loff_t pos_out,
 				   loff_t len, unsigned int remap_flags);
 	int (*fadvise)(struct file *, loff_t, loff_t, int);
+	int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
 } __randomize_layout;
 
 struct inode_operations {
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 24651c229ed2..4a2f6cc5a492 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -5,7 +5,32 @@
 #include <linux/sched.h>
 #include <linux/xarray.h>
 
+enum io_uring_cmd_flags {
+	IO_URING_F_COMPLETE_DEFER	= 1,
+	IO_URING_F_UNLOCKED		= 2,
+	/* int's last bit, sign checks are usually faster than a bit test */
+	IO_URING_F_NONBLOCK		= INT_MIN,
+
+	/* ctx state flags, for URING_CMD */
+	IO_URING_F_SQE128		= 4,
+	IO_URING_F_CQE32		= 8,
+	IO_URING_F_IOPOLL		= 16,
+};
+
+struct io_uring_cmd {
+	struct file	*file;
+	const void	*cmd;
+	/* callback to defer completions to task context */
+	void (*task_work_cb)(struct io_uring_cmd *cmd);
+	u32		cmd_op;
+	u32		pad;
+	u8		pdu[32]; /* available inline for free use */
+};
+
 #if defined(CONFIG_IO_URING)
+void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2);
+void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *));
 struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
@@ -30,6 +55,14 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 #else
+static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
+		ssize_t ret2)
+{
+}
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *))
+{
+}
 static inline struct sock *io_uring_get_socket(struct file *file)
 {
 	return NULL;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index ac2d90d669c3..23618be55dd2 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -22,6 +22,7 @@ struct io_uring_sqe {
 	union {
 		__u64	off;	/* offset into file */
 		__u64	addr2;
+		__u32	cmd_op;
 	};
 	union {
 		__u64	addr;	/* pointer to buffer or iovecs */
@@ -61,14 +62,17 @@ struct io_uring_sqe {
 		__s32	splice_fd_in;
 		__u32	file_index;
 	};
-	__u64	addr3;
-	__u64	__pad2[1];
-
-	/*
-	 * If the ring is initialized with IORING_SETUP_SQE128, then this field
-	 * contains 64-bytes of padding, doubling the size of the SQE.
-	 */
-	__u64	__big_sqe_pad[0];
+	union {
+		struct {
+			__u64	addr3;
+			__u64	__pad2[1];
+		};
+		/*
+		 * If the ring is initialized with IORING_SETUP_SQE128, then
+		 * this field is used for 80 bytes of arbitrary command data
+		 */
+		__u8	cmd[0];
+	};
 };
 
 enum {
@@ -175,6 +179,7 @@ enum io_uring_op {
 	IORING_OP_FGETXATTR,
 	IORING_OP_GETXATTR,
 	IORING_OP_SOCKET,
+	IORING_OP_URING_CMD,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
-- 
cgit v1.2.3


From deaf7c4b4bf8b802cc465bb9b33fe6c76e812924 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 May 2022 21:03:43 +0200
Subject: lockdep: Delete local_irq_enable_in_hardirq()

No more users and there is no desire to grow new ones.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/8735hir0j4.ffs@tglx
---
 include/linux/interrupt.h | 18 ------------------
 1 file changed, 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index f40754caaefa..b5e06a6e4019 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -222,24 +222,6 @@ devm_request_any_context_irq(struct device *dev, unsigned int irq,
 
 extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 
-/*
- * On lockdep we dont want to enable hardirqs in hardirq
- * context. Use local_irq_enable_in_hardirq() to annotate
- * kernel code that has to do this nevertheless (pretty much
- * the only valid case is for old/broken hardware that is
- * insanely slow).
- *
- * NOTE: in theory this might break fragile code that relies
- * on hardirq delivery - in practice we dont seem to have such
- * places left. So the only effect should be slightly increased
- * irqs-off latencies.
- */
-#ifdef CONFIG_LOCKDEP
-# define local_irq_enable_in_hardirq()	do { } while (0)
-#else
-# define local_irq_enable_in_hardirq()	local_irq_enable()
-#endif
-
 bool irq_has_action(unsigned int irq);
 extern void disable_irq_nosync(unsigned int irq);
 extern bool disable_hardirq(unsigned int irq);
-- 
cgit v1.2.3


From abcebcd39fe094b68826cc04f2eca835606697f9 Mon Sep 17 00:00:00 2001
From: Michael Shych <michaelsh@nvidia.com>
Date: Sat, 30 Apr 2022 14:58:07 +0300
Subject: platform_data/mlxreg: Add field for notification callback

Add notification callback to inform caller that platform driver probing
has been completed. It allows to caller to perform some initialization
flow steps depending on specific driver probing completion.

Signed-off-by: Michael Shych <michaelsh@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Link: https://lore.kernel.org/r/20220430115809.54565-2-michaelsh@nvidia.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/platform_data/mlxreg.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index 40185f9d7c14..a6bd74e29b6b 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -216,6 +216,8 @@ struct mlxreg_core_platform_data {
  * @mask_low: low aggregation interrupt common mask;
  * @deferred_nr: I2C adapter number must be exist prior probing execution;
  * @shift_nr: I2C adapter numbers must be incremented by this value;
+ * @handle: handle to be passed by callback;
+ * @completion_notify: callback to notify when platform driver probing is done;
  */
 struct mlxreg_core_hotplug_platform_data {
 	struct mlxreg_core_item *items;
@@ -228,6 +230,8 @@ struct mlxreg_core_hotplug_platform_data {
 	u32 mask_low;
 	int deferred_nr;
 	int shift_nr;
+	void *handle;
+	int (*completion_notify)(void *handle, int id);
 };
 
 #endif /* __LINUX_PLATFORM_DATA_MLXREG_H */
-- 
cgit v1.2.3


From f9d76d15072caf1ec5558fa7cc6d93c7b9d33488 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 10 May 2022 11:51:29 -0400
Subject: USB: gadget: Add ID numbers to gadget names

Putting USB gadgets on a new bus of their own encounters a problem
when multiple gadgets are present: They all have the same name!  The
driver core fails with a "sys: cannot create duplicate filename" error
when creating any of the /sys/bus/gadget/devices/<gadget-name>
symbolic links after the first.

This patch fixes the problem by adding a ".N" suffix to each gadget's
name when the gadget is registered (where N is a unique ID number),
thus making the names distinct.

Reported-and-tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Fixes: fc274c1e9973 ("USB: gadget: Add a new bus for gadgets")
Link: https://lore.kernel.org/r/YnqKAXKyp9Vq/pbn@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/core.c | 16 ++++++++++++++--
 include/linux/usb/gadget.h    |  2 ++
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 3281d8a3dae7..7886497253cc 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/list.h>
+#include <linux/idr.h>
 #include <linux/err.h>
 #include <linux/dma-mapping.h>
 #include <linux/sched/task_stack.h>
@@ -23,6 +24,8 @@
 
 #include "trace.h"
 
+static DEFINE_IDA(gadget_id_numbers);
+
 static struct bus_type gadget_bus_type;
 
 /**
@@ -1248,7 +1251,6 @@ static void usb_udc_nop_release(struct device *dev)
 void usb_initialize_gadget(struct device *parent, struct usb_gadget *gadget,
 		void (*release)(struct device *dev))
 {
-	dev_set_name(&gadget->dev, "gadget");
 	INIT_WORK(&gadget->work, usb_gadget_state_work);
 	gadget->dev.parent = parent;
 
@@ -1304,12 +1306,21 @@ int usb_add_gadget(struct usb_gadget *gadget)
 	usb_gadget_set_state(gadget, USB_STATE_NOTATTACHED);
 	udc->vbus = true;
 
+	ret = ida_alloc(&gadget_id_numbers, GFP_KERNEL);
+	if (ret < 0)
+		goto err_del_udc;
+	gadget->id_number = ret;
+	dev_set_name(&gadget->dev, "gadget.%d", ret);
+
 	ret = device_add(&gadget->dev);
 	if (ret)
-		goto err_del_udc;
+		goto err_free_id;
 
 	return 0;
 
+ err_free_id:
+	ida_free(&gadget_id_numbers, gadget->id_number);
+
  err_del_udc:
 	flush_work(&gadget->work);
 	device_del(&udc->dev);
@@ -1417,6 +1428,7 @@ void usb_del_gadget(struct usb_gadget *gadget)
 	kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE);
 	flush_work(&gadget->work);
 	device_del(&gadget->dev);
+	ida_free(&gadget_id_numbers, gadget->id_number);
 	device_unregister(&udc->dev);
 }
 EXPORT_SYMBOL_GPL(usb_del_gadget);
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index cf7af8a0a6e9..3ad58b7a0824 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -386,6 +386,7 @@ struct usb_gadget_ops {
  * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag
  *	indicates that it supports LPM as per the LPM ECN & errata.
  * @irq: the interrupt number for device controller.
+ * @id_number: a unique ID number for ensuring that gadget names are distinct
  *
  * Gadgets have a mostly-portable "gadget driver" implementing device
  * functions, handling all usb configurations and interfaces.  Gadget
@@ -446,6 +447,7 @@ struct usb_gadget {
 	unsigned			connected:1;
 	unsigned			lpm_capable:1;
 	int				irq;
+	int				id_number;
 };
 #define work_to_gadget(w)	(container_of((w), struct usb_gadget, work))
 
-- 
cgit v1.2.3


From a6b94c6b49198266eaf78095a632df7245ef5196 Mon Sep 17 00:00:00 2001
From: Michael Kelley <mikelley@microsoft.com>
Date: Mon, 2 May 2022 09:36:28 -0700
Subject: Drivers: hv: vmbus: Remove support for Hyper-V 2008 and Hyper-V
 2008R2/Win7

The VMbus driver has special case code for running on the first released
versions of Hyper-V: 2008 and 2008 R2/Windows 7. These versions are now
out of support (except for extended security updates) and lack the
performance features needed for effective production usage of Linux
guests.

Simplify the code by removing the negotiation of the VMbus protocol
versions required for these releases of Hyper-V, and by removing the
special case code for handling these VMbus protocol versions.

Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Reviewed-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/1651509391-2058-2-git-send-email-mikelley@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel_mgmt.c | 29 +++++++++--------------
 drivers/hv/connection.c   |  6 ++---
 drivers/hv/vmbus_drv.c    | 60 ++++++++++-------------------------------------
 include/linux/hyperv.h    | 10 +++++---
 4 files changed, 33 insertions(+), 72 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 0db1b775e013..97d8f5646778 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -714,15 +714,13 @@ static bool hv_cpuself_used(u32 cpu, struct vmbus_channel *chn)
 static int next_numa_node_id;
 
 /*
- * Starting with Win8, we can statically distribute the incoming
- * channel interrupt load by binding a channel to VCPU.
+ * We can statically distribute the incoming channel interrupt load
+ * by binding a channel to VCPU.
  *
- * For pre-win8 hosts or non-performance critical channels we assign the
- * VMBUS_CONNECT_CPU.
- *
- * Starting with win8, performance critical channels will be distributed
- * evenly among all the available NUMA nodes.  Once the node is assigned,
- * we will assign the CPU based on a simple round robin scheme.
+ * For non-performance critical channels we assign the VMBUS_CONNECT_CPU.
+ * Performance critical channels will be distributed evenly among all
+ * the available NUMA nodes.  Once the node is assigned, we will assign
+ * the CPU based on a simple round robin scheme.
  */
 static void init_vp_index(struct vmbus_channel *channel)
 {
@@ -733,13 +731,10 @@ static void init_vp_index(struct vmbus_channel *channel)
 	u32 target_cpu;
 	int numa_node;
 
-	if ((vmbus_proto_version == VERSION_WS2008) ||
-	    (vmbus_proto_version == VERSION_WIN7) || (!perf_chn) ||
+	if (!perf_chn ||
 	    !alloc_cpumask_var(&available_mask, GFP_KERNEL)) {
 		/*
-		 * Prior to win8, all channel interrupts are
-		 * delivered on VMBUS_CONNECT_CPU.
-		 * Also if the channel is not a performance critical
+		 * If the channel is not a performance critical
 		 * channel, bind it to VMBUS_CONNECT_CPU.
 		 * In case alloc_cpumask_var() fails, bind it to
 		 * VMBUS_CONNECT_CPU.
@@ -932,11 +927,9 @@ static void vmbus_setup_channel_state(struct vmbus_channel *channel,
 	 */
 	channel->sig_event = VMBUS_EVENT_CONNECTION_ID;
 
-	if (vmbus_proto_version != VERSION_WS2008) {
-		channel->is_dedicated_interrupt =
-				(offer->is_dedicated_interrupt != 0);
-		channel->sig_event = offer->connection_id;
-	}
+	channel->is_dedicated_interrupt =
+			(offer->is_dedicated_interrupt != 0);
+	channel->sig_event = offer->connection_id;
 
 	memcpy(&channel->offermsg, offer,
 	       sizeof(struct vmbus_channel_offer_channel));
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index a3d8be8d6cfb..6218bbf6863a 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -47,6 +47,8 @@ EXPORT_SYMBOL_GPL(vmbus_proto_version);
 
 /*
  * Table of VMBus versions listed from newest to oldest.
+ * VERSION_WIN7 and VERSION_WS2008 are no longer supported in
+ * Linux guests and are not listed.
  */
 static __u32 vmbus_versions[] = {
 	VERSION_WIN10_V5_3,
@@ -56,9 +58,7 @@ static __u32 vmbus_versions[] = {
 	VERSION_WIN10_V4_1,
 	VERSION_WIN10,
 	VERSION_WIN8_1,
-	VERSION_WIN8,
-	VERSION_WIN7,
-	VERSION_WS2008
+	VERSION_WIN8
 };
 
 /*
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 14de17087864..9c1b3620775c 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1263,23 +1263,17 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
 	unsigned long *recv_int_page;
 	u32 maxbits, relid;
 
-	if (vmbus_proto_version < VERSION_WIN8) {
-		maxbits = MAX_NUM_CHANNELS_SUPPORTED;
-		recv_int_page = vmbus_connection.recv_int_page;
-	} else {
-		/*
-		 * When the host is win8 and beyond, the event page
-		 * can be directly checked to get the id of the channel
-		 * that has the interrupt pending.
-		 */
-		void *page_addr = hv_cpu->synic_event_page;
-		union hv_synic_event_flags *event
-			= (union hv_synic_event_flags *)page_addr +
-						 VMBUS_MESSAGE_SINT;
+	/*
+	 * The event page can be directly checked to get the id of
+	 * the channel that has the interrupt pending.
+	 */
+	void *page_addr = hv_cpu->synic_event_page;
+	union hv_synic_event_flags *event
+		= (union hv_synic_event_flags *)page_addr +
+					 VMBUS_MESSAGE_SINT;
 
-		maxbits = HV_EVENT_FLAGS_COUNT;
-		recv_int_page = event->flags;
-	}
+	maxbits = HV_EVENT_FLAGS_COUNT;
+	recv_int_page = event->flags;
 
 	if (unlikely(!recv_int_page))
 		return;
@@ -1351,40 +1345,10 @@ static void vmbus_isr(void)
 {
 	struct hv_per_cpu_context *hv_cpu
 		= this_cpu_ptr(hv_context.cpu_context);
-	void *page_addr = hv_cpu->synic_event_page;
+	void *page_addr;
 	struct hv_message *msg;
-	union hv_synic_event_flags *event;
-	bool handled = false;
-
-	if (unlikely(page_addr == NULL))
-		return;
-
-	event = (union hv_synic_event_flags *)page_addr +
-					 VMBUS_MESSAGE_SINT;
-	/*
-	 * Check for events before checking for messages. This is the order
-	 * in which events and messages are checked in Windows guests on
-	 * Hyper-V, and the Windows team suggested we do the same.
-	 */
-
-	if ((vmbus_proto_version == VERSION_WS2008) ||
-		(vmbus_proto_version == VERSION_WIN7)) {
-
-		/* Since we are a child, we only need to check bit 0 */
-		if (sync_test_and_clear_bit(0, event->flags))
-			handled = true;
-	} else {
-		/*
-		 * Our host is win8 or above. The signaling mechanism
-		 * has changed and we can directly look at the event page.
-		 * If bit n is set then we have an interrup on the channel
-		 * whose id is n.
-		 */
-		handled = true;
-	}
 
-	if (handled)
-		vmbus_chan_sched(hv_cpu);
+	vmbus_chan_sched(hv_cpu);
 
 	page_addr = hv_cpu->synic_message_page;
 	msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index c440c45887c2..a2464295c14a 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -230,15 +230,19 @@ static inline u32 hv_get_avail_to_write_percent(
  * two 16 bit quantities: major_number. minor_number.
  *
  * 0 . 13 (Windows Server 2008)
- * 1 . 1  (Windows 7)
- * 2 . 4  (Windows 8)
- * 3 . 0  (Windows 8 R2)
+ * 1 . 1  (Windows 7, WS2008 R2)
+ * 2 . 4  (Windows 8, WS2012)
+ * 3 . 0  (Windows 8.1, WS2012 R2)
  * 4 . 0  (Windows 10)
  * 4 . 1  (Windows 10 RS3)
  * 5 . 0  (Newer Windows 10)
  * 5 . 1  (Windows 10 RS4)
  * 5 . 2  (Windows Server 2019, RS5)
  * 5 . 3  (Windows Server 2022)
+ *
+ * The WS2008 and WIN7 versions are listed here for
+ * completeness but are no longer supported in the
+ * Linux kernel.
  */
 
 #define VERSION_WS2008  ((0 << 16) | (13))
-- 
cgit v1.2.3


From 09ea48efffa3156218980e20aaf23dcc7d6000fc Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 11 May 2022 13:12:58 -0600
Subject: vfio: Make vfio_(un)register_notifier accept a vfio_device

All callers have a struct vfio_device trivially available, pass it in
directly and avoid calling the expensive vfio_group_get_from_dev().

Acked-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Jason J. Herne <jjherne@linux.ibm.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c  | 24 ++++++++++++------------
 drivers/s390/cio/vfio_ccw_ops.c   |  7 +++----
 drivers/s390/crypto/vfio_ap_ops.c | 14 +++++++-------
 drivers/vfio/vfio.c               | 28 +++++++++-------------------
 include/linux/vfio.h              |  4 ++--
 5 files changed, 33 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 0787ba5c301f..1cec4f1fdfac 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -810,8 +810,8 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 	vgpu->group_notifier.notifier_call = intel_vgpu_group_notifier;
 
 	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(vfio_dev->dev, VFIO_IOMMU_NOTIFY, &events,
-				&vgpu->iommu_notifier);
+	ret = vfio_register_notifier(vfio_dev, VFIO_IOMMU_NOTIFY, &events,
+				     &vgpu->iommu_notifier);
 	if (ret != 0) {
 		gvt_vgpu_err("vfio_register_notifier for iommu failed: %d\n",
 			ret);
@@ -819,8 +819,8 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 	}
 
 	events = VFIO_GROUP_NOTIFY_SET_KVM;
-	ret = vfio_register_notifier(vfio_dev->dev, VFIO_GROUP_NOTIFY, &events,
-				&vgpu->group_notifier);
+	ret = vfio_register_notifier(vfio_dev, VFIO_GROUP_NOTIFY, &events,
+				     &vgpu->group_notifier);
 	if (ret != 0) {
 		gvt_vgpu_err("vfio_register_notifier for group failed: %d\n",
 			ret);
@@ -873,12 +873,12 @@ undo_group:
 	vgpu->vfio_group = NULL;
 
 undo_register:
-	vfio_unregister_notifier(vfio_dev->dev, VFIO_GROUP_NOTIFY,
-					&vgpu->group_notifier);
+	vfio_unregister_notifier(vfio_dev, VFIO_GROUP_NOTIFY,
+				 &vgpu->group_notifier);
 
 undo_iommu:
-	vfio_unregister_notifier(vfio_dev->dev, VFIO_IOMMU_NOTIFY,
-					&vgpu->iommu_notifier);
+	vfio_unregister_notifier(vfio_dev, VFIO_IOMMU_NOTIFY,
+				 &vgpu->iommu_notifier);
 out:
 	return ret;
 }
@@ -907,13 +907,13 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)
 
 	intel_gvt_release_vgpu(vgpu);
 
-	ret = vfio_unregister_notifier(vgpu->vfio_device.dev, VFIO_IOMMU_NOTIFY,
-					&vgpu->iommu_notifier);
+	ret = vfio_unregister_notifier(&vgpu->vfio_device, VFIO_IOMMU_NOTIFY,
+				       &vgpu->iommu_notifier);
 	drm_WARN(&i915->drm, ret,
 		 "vfio_unregister_notifier for iommu failed: %d\n", ret);
 
-	ret = vfio_unregister_notifier(vgpu->vfio_device.dev, VFIO_GROUP_NOTIFY,
-					&vgpu->group_notifier);
+	ret = vfio_unregister_notifier(&vgpu->vfio_device, VFIO_GROUP_NOTIFY,
+				       &vgpu->group_notifier);
 	drm_WARN(&i915->drm, ret,
 		 "vfio_unregister_notifier for group failed: %d\n", ret);
 
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index c4d60cdbf247..b49e2e9db2dc 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -183,7 +183,7 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 
 	private->nb.notifier_call = vfio_ccw_mdev_notifier;
 
-	ret = vfio_register_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
+	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY,
 				     &events, &private->nb);
 	if (ret)
 		return ret;
@@ -204,8 +204,7 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 
 out_unregister:
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
-				 &private->nb);
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 	return ret;
 }
 
@@ -223,7 +222,7 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 
 	cp_free(&private->cp);
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY, &private->nb);
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 }
 
 static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index ee0a3bf8f476..bfa7ee6ef532 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -1406,21 +1406,21 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)
 	matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier;
 	events = VFIO_GROUP_NOTIFY_SET_KVM;
 
-	ret = vfio_register_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
-				     &events, &matrix_mdev->group_notifier);
+	ret = vfio_register_notifier(vdev, VFIO_GROUP_NOTIFY, &events,
+				     &matrix_mdev->group_notifier);
 	if (ret)
 		return ret;
 
 	matrix_mdev->iommu_notifier.notifier_call = vfio_ap_mdev_iommu_notifier;
 	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
-				     &events, &matrix_mdev->iommu_notifier);
+	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY, &events,
+				     &matrix_mdev->iommu_notifier);
 	if (ret)
 		goto out_unregister_group;
 	return 0;
 
 out_unregister_group:
-	vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
+	vfio_unregister_notifier(vdev, VFIO_GROUP_NOTIFY,
 				 &matrix_mdev->group_notifier);
 	return ret;
 }
@@ -1430,9 +1430,9 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev)
 	struct ap_matrix_mdev *matrix_mdev =
 		container_of(vdev, struct ap_matrix_mdev, vdev);
 
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY,
 				 &matrix_mdev->iommu_notifier);
-	vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
+	vfio_unregister_notifier(vdev, VFIO_GROUP_NOTIFY,
 				 &matrix_mdev->group_notifier);
 	vfio_ap_mdev_unset_kvm(matrix_mdev);
 }
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 7b0a7b85e77e..cb4730756510 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -2484,19 +2484,16 @@ static int vfio_unregister_group_notifier(struct vfio_group *group,
 	return ret;
 }
 
-int vfio_register_notifier(struct device *dev, enum vfio_notify_type type,
-			   unsigned long *events, struct notifier_block *nb)
+int vfio_register_notifier(struct vfio_device *device,
+			   enum vfio_notify_type type, unsigned long *events,
+			   struct notifier_block *nb)
 {
-	struct vfio_group *group;
+	struct vfio_group *group = device->group;
 	int ret;
 
-	if (!dev || !nb || !events || (*events == 0))
+	if (!nb || !events || (*events == 0))
 		return -EINVAL;
 
-	group = vfio_group_get_from_dev(dev);
-	if (!group)
-		return -ENODEV;
-
 	switch (type) {
 	case VFIO_IOMMU_NOTIFY:
 		ret = vfio_register_iommu_notifier(group, events, nb);
@@ -2507,25 +2504,20 @@ int vfio_register_notifier(struct device *dev, enum vfio_notify_type type,
 	default:
 		ret = -EINVAL;
 	}
-
-	vfio_group_put(group);
 	return ret;
 }
 EXPORT_SYMBOL(vfio_register_notifier);
 
-int vfio_unregister_notifier(struct device *dev, enum vfio_notify_type type,
+int vfio_unregister_notifier(struct vfio_device *device,
+			     enum vfio_notify_type type,
 			     struct notifier_block *nb)
 {
-	struct vfio_group *group;
+	struct vfio_group *group = device->group;
 	int ret;
 
-	if (!dev || !nb)
+	if (!nb)
 		return -EINVAL;
 
-	group = vfio_group_get_from_dev(dev);
-	if (!group)
-		return -ENODEV;
-
 	switch (type) {
 	case VFIO_IOMMU_NOTIFY:
 		ret = vfio_unregister_iommu_notifier(group, nb);
@@ -2536,8 +2528,6 @@ int vfio_unregister_notifier(struct device *dev, enum vfio_notify_type type,
 	default:
 		ret = -EINVAL;
 	}
-
-	vfio_group_put(group);
 	return ret;
 }
 EXPORT_SYMBOL(vfio_unregister_notifier);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 66dda06ec42d..a00fd722f044 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -178,11 +178,11 @@ enum vfio_notify_type {
 /* events for VFIO_GROUP_NOTIFY */
 #define VFIO_GROUP_NOTIFY_SET_KVM	BIT(0)
 
-extern int vfio_register_notifier(struct device *dev,
+extern int vfio_register_notifier(struct vfio_device *device,
 				  enum vfio_notify_type type,
 				  unsigned long *required_events,
 				  struct notifier_block *nb);
-extern int vfio_unregister_notifier(struct device *dev,
+extern int vfio_unregister_notifier(struct vfio_device *device,
 				    enum vfio_notify_type type,
 				    struct notifier_block *nb);
 
-- 
cgit v1.2.3


From 8e432bb015b6c327d016b1dca509964e189c4770 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 11 May 2022 13:12:59 -0600
Subject: vfio/mdev: Pass in a struct vfio_device * to vfio_pin/unpin_pages()

Every caller has a readily available vfio_device pointer, use that instead
of passing in a generic struct device. The struct vfio_device already
contains the group we need so this avoids complexity, extra refcountings,
and a confusing lifecycle model.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Jason J. Herne <jjherne@linux.ibm.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/3-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 Documentation/driver-api/vfio-mediated-device.rst |  4 +-
 drivers/s390/cio/vfio_ccw_cp.c                    |  6 +--
 drivers/s390/crypto/vfio_ap_ops.c                 |  9 ++---
 drivers/vfio/vfio.c                               | 46 ++++++++---------------
 include/linux/vfio.h                              |  4 +-
 5 files changed, 27 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/vfio-mediated-device.rst b/Documentation/driver-api/vfio-mediated-device.rst
index 784bbeb22adc..eded8719180f 100644
--- a/Documentation/driver-api/vfio-mediated-device.rst
+++ b/Documentation/driver-api/vfio-mediated-device.rst
@@ -262,10 +262,10 @@ Translation APIs for Mediated Devices
 The following APIs are provided for translating user pfn to host pfn in a VFIO
 driver::
 
-	extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
+	int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn,
 				  int npage, int prot, unsigned long *phys_pfn);
 
-	extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
+	int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn,
 				    int npage);
 
 These functions call back into the back-end IOMMU module by using the pin_pages
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 7a1cf3091cd6..0c2be9421ab7 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -103,13 +103,13 @@ static int pfn_array_pin(struct pfn_array *pa, struct vfio_device *vdev)
 {
 	int ret = 0;
 
-	ret = vfio_pin_pages(vdev->dev, pa->pa_iova_pfn, pa->pa_nr,
+	ret = vfio_pin_pages(vdev, pa->pa_iova_pfn, pa->pa_nr,
 			     IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
 
 	if (ret < 0) {
 		goto err_out;
 	} else if (ret > 0 && ret != pa->pa_nr) {
-		vfio_unpin_pages(vdev->dev, pa->pa_iova_pfn, ret);
+		vfio_unpin_pages(vdev, pa->pa_iova_pfn, ret);
 		ret = -EINVAL;
 		goto err_out;
 	}
@@ -127,7 +127,7 @@ static void pfn_array_unpin_free(struct pfn_array *pa, struct vfio_device *vdev)
 {
 	/* Only unpin if any pages were pinned to begin with */
 	if (pa->pa_nr)
-		vfio_unpin_pages(vdev->dev, pa->pa_iova_pfn, pa->pa_nr);
+		vfio_unpin_pages(vdev, pa->pa_iova_pfn, pa->pa_nr);
 	pa->pa_nr = 0;
 	kfree(pa->pa_iova_pfn);
 }
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index bfa7ee6ef532..e8914024f5b1 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -124,8 +124,7 @@ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q)
 		q->saved_isc = VFIO_AP_ISC_INVALID;
 	}
 	if (q->saved_pfn && !WARN_ON(!q->matrix_mdev)) {
-		vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev),
-				 &q->saved_pfn, 1);
+		vfio_unpin_pages(&q->matrix_mdev->vdev, &q->saved_pfn, 1);
 		q->saved_pfn = 0;
 	}
 }
@@ -258,7 +257,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		return status;
 	}
 
-	ret = vfio_pin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1,
+	ret = vfio_pin_pages(&q->matrix_mdev->vdev, &g_pfn, 1,
 			     IOMMU_READ | IOMMU_WRITE, &h_pfn);
 	switch (ret) {
 	case 1:
@@ -301,7 +300,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		break;
 	case AP_RESPONSE_OTHERWISE_CHANGED:
 		/* We could not modify IRQ setings: clear new configuration */
-		vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1);
+		vfio_unpin_pages(&q->matrix_mdev->vdev, &g_pfn, 1);
 		kvm_s390_gisc_unregister(kvm, isc);
 		break;
 	default:
@@ -1250,7 +1249,7 @@ static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb,
 		struct vfio_iommu_type1_dma_unmap *unmap = data;
 		unsigned long g_pfn = unmap->iova >> PAGE_SHIFT;
 
-		vfio_unpin_pages(mdev_dev(matrix_mdev->mdev), &g_pfn, 1);
+		vfio_unpin_pages(&matrix_mdev->vdev, &g_pfn, 1);
 		return NOTIFY_OK;
 	}
 
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index cb4730756510..0f85e789fbd3 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -2134,7 +2134,7 @@ EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare);
 /*
  * Pin a set of guest PFNs and return their associated host PFNs for local
  * domain only.
- * @dev [in]     : device
+ * @device [in]  : device
  * @user_pfn [in]: array of user/guest PFNs to be pinned.
  * @npage [in]   : count of elements in user_pfn array.  This count should not
  *		   be greater VFIO_PIN_PAGES_MAX_ENTRIES.
@@ -2142,32 +2142,26 @@ EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare);
  * @phys_pfn[out]: array of host PFNs
  * Return error or number of pages pinned.
  */
-int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
-		   int prot, unsigned long *phys_pfn)
+int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn,
+		   int npage, int prot, unsigned long *phys_pfn)
 {
 	struct vfio_container *container;
-	struct vfio_group *group;
+	struct vfio_group *group = device->group;
 	struct vfio_iommu_driver *driver;
 	int ret;
 
-	if (!dev || !user_pfn || !phys_pfn || !npage)
+	if (!user_pfn || !phys_pfn || !npage)
 		return -EINVAL;
 
 	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
 		return -E2BIG;
 
-	group = vfio_group_get_from_dev(dev);
-	if (!group)
-		return -ENODEV;
-
-	if (group->dev_counter > 1) {
-		ret = -EINVAL;
-		goto err_pin_pages;
-	}
+	if (group->dev_counter > 1)
+		return -EINVAL;
 
 	ret = vfio_group_add_container_user(group);
 	if (ret)
-		goto err_pin_pages;
+		return ret;
 
 	container = group->container;
 	driver = container->iommu_driver;
@@ -2180,43 +2174,37 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
 
 	vfio_group_try_dissolve_container(group);
 
-err_pin_pages:
-	vfio_group_put(group);
 	return ret;
 }
 EXPORT_SYMBOL(vfio_pin_pages);
 
 /*
  * Unpin set of host PFNs for local domain only.
- * @dev [in]     : device
+ * @device [in]  : device
  * @user_pfn [in]: array of user/guest PFNs to be unpinned. Number of user/guest
  *		   PFNs should not be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
  * @npage [in]   : count of elements in user_pfn array.  This count should not
  *                 be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
  * Return error or number of pages unpinned.
  */
-int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage)
+int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn,
+		     int npage)
 {
 	struct vfio_container *container;
-	struct vfio_group *group;
 	struct vfio_iommu_driver *driver;
 	int ret;
 
-	if (!dev || !user_pfn || !npage)
+	if (!user_pfn || !npage)
 		return -EINVAL;
 
 	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
 		return -E2BIG;
 
-	group = vfio_group_get_from_dev(dev);
-	if (!group)
-		return -ENODEV;
-
-	ret = vfio_group_add_container_user(group);
+	ret = vfio_group_add_container_user(device->group);
 	if (ret)
-		goto err_unpin_pages;
+		return ret;
 
-	container = group->container;
+	container = device->group->container;
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->unpin_pages))
 		ret = driver->ops->unpin_pages(container->iommu_data, user_pfn,
@@ -2224,10 +2212,8 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage)
 	else
 		ret = -ENOTTY;
 
-	vfio_group_try_dissolve_container(group);
+	vfio_group_try_dissolve_container(device->group);
 
-err_unpin_pages:
-	vfio_group_put(group);
 	return ret;
 }
 EXPORT_SYMBOL(vfio_unpin_pages);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index a00fd722f044..bddc70f88899 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -150,9 +150,9 @@ extern long vfio_external_check_extension(struct vfio_group *group,
 
 #define VFIO_PIN_PAGES_MAX_ENTRIES	(PAGE_SIZE/sizeof(unsigned long))
 
-extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
+extern int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn,
 			  int npage, int prot, unsigned long *phys_pfn);
-extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
+extern int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn,
 			    int npage);
 
 extern int vfio_group_pin_pages(struct vfio_group *group,
-- 
cgit v1.2.3


From c6250ffbacc5989a5db3b9acce34b93570938f60 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 11 May 2022 13:12:59 -0600
Subject: vfio/mdev: Pass in a struct vfio_device * to vfio_dma_rw()

Every caller has a readily available vfio_device pointer, use that instead
of passing in a generic struct device. Change vfio_dma_rw() to take in the
struct vfio_device and move the container users that would have been held
by vfio_group_get_external_user_from_dev() to vfio_dma_rw() directly, like
vfio_pin/unpin_pages().

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/4-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gvt.h |  4 ++--
 drivers/vfio/vfio.c            | 24 +++++++++++-------------
 include/linux/vfio.h           |  2 +-
 3 files changed, 14 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 03ecffc2ba56..5a28ee965b7f 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -732,7 +732,7 @@ static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa,
 {
 	if (!vgpu->attached)
 		return -ESRCH;
-	return vfio_dma_rw(vgpu->vfio_group, gpa, buf, len, false);
+	return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, false);
 }
 
 /**
@@ -750,7 +750,7 @@ static inline int intel_gvt_write_gpa(struct intel_vgpu *vgpu,
 {
 	if (!vgpu->attached)
 		return -ESRCH;
-	return vfio_dma_rw(vgpu->vfio_group, gpa, buf, len, true);
+	return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, true);
 }
 
 void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu);
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 0f85e789fbd3..1dfd019aaaae 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -2323,32 +2323,28 @@ EXPORT_SYMBOL(vfio_group_unpin_pages);
  * As the read/write of user space memory is conducted via the CPUs and is
  * not a real device DMA, it is not necessary to pin the user space memory.
  *
- * The caller needs to call vfio_group_get_external_user() or
- * vfio_group_get_external_user_from_dev() prior to calling this interface,
- * so as to prevent the VFIO group from disposal in the middle of the call.
- * But it can keep the reference to the VFIO group for several calls into
- * this interface.
- * After finishing using of the VFIO group, the caller needs to release the
- * VFIO group by calling vfio_group_put_external_user().
- *
- * @group [in]		: VFIO group
+ * @device [in]		: VFIO device
  * @user_iova [in]	: base IOVA of a user space buffer
  * @data [in]		: pointer to kernel buffer
  * @len [in]		: kernel buffer length
  * @write		: indicate read or write
  * Return error code on failure or 0 on success.
  */
-int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
-		void *data, size_t len, bool write)
+int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, void *data,
+		size_t len, bool write)
 {
 	struct vfio_container *container;
 	struct vfio_iommu_driver *driver;
 	int ret = 0;
 
-	if (!group || !data || len <= 0)
+	if (!data || len <= 0)
 		return -EINVAL;
 
-	container = group->container;
+	ret = vfio_group_add_container_user(device->group);
+	if (ret)
+		return ret;
+
+	container = device->group->container;
 	driver = container->iommu_driver;
 
 	if (likely(driver && driver->ops->dma_rw))
@@ -2357,6 +2353,8 @@ int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
 	else
 		ret = -ENOTTY;
 
+	vfio_group_try_dissolve_container(device->group);
+
 	return ret;
 }
 EXPORT_SYMBOL(vfio_dma_rw);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index bddc70f88899..8a1510258717 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -161,7 +161,7 @@ extern int vfio_group_pin_pages(struct vfio_group *group,
 extern int vfio_group_unpin_pages(struct vfio_group *group,
 				  unsigned long *user_iova_pfn, int npage);
 
-extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
+extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,
 		       void *data, size_t len, bool write);
 
 extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group);
-- 
cgit v1.2.3


From 231657b345046552b35670b45b892cfce2610e12 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 11 May 2022 13:13:00 -0600
Subject: vfio: Remove dead code

Now that callers have been updated to use the vfio_device APIs the driver
facing group interface is no longer used, delete it:

- vfio_group_get_external_user_from_dev()
- vfio_group_pin_pages()
- vfio_group_unpin_pages()
- vfio_group_iommu_domain()

--

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/6-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio.c  | 151 ---------------------------------------------------
 include/linux/vfio.h |  11 ----
 2 files changed, 162 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 1dfd019aaaae..b9396424a9f9 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1947,44 +1947,6 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep)
 }
 EXPORT_SYMBOL_GPL(vfio_group_get_external_user);
 
-/*
- * External user API, exported by symbols to be linked dynamically.
- * The external user passes in a device pointer
- * to verify that:
- *	- A VFIO group is assiciated with the device;
- *	- IOMMU is set for the group.
- * If both checks passed, vfio_group_get_external_user_from_dev()
- * increments the container user counter to prevent the VFIO group
- * from disposal before external user exits and returns the pointer
- * to the VFIO group.
- *
- * When the external user finishes using the VFIO group, it calls
- * vfio_group_put_external_user() to release the VFIO group and
- * decrement the container user counter.
- *
- * @dev [in]	: device
- * Return error PTR or pointer to VFIO group.
- */
-
-struct vfio_group *vfio_group_get_external_user_from_dev(struct device *dev)
-{
-	struct vfio_group *group;
-	int ret;
-
-	group = vfio_group_get_from_dev(dev);
-	if (!group)
-		return ERR_PTR(-ENODEV);
-
-	ret = vfio_group_add_container_user(group);
-	if (ret) {
-		vfio_group_put(group);
-		return ERR_PTR(ret);
-	}
-
-	return group;
-}
-EXPORT_SYMBOL_GPL(vfio_group_get_external_user_from_dev);
-
 void vfio_group_put_external_user(struct vfio_group *group)
 {
 	vfio_group_try_dissolve_container(group);
@@ -2218,101 +2180,6 @@ int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn,
 }
 EXPORT_SYMBOL(vfio_unpin_pages);
 
-/*
- * Pin a set of guest IOVA PFNs and return their associated host PFNs for a
- * VFIO group.
- *
- * The caller needs to call vfio_group_get_external_user() or
- * vfio_group_get_external_user_from_dev() prior to calling this interface,
- * so as to prevent the VFIO group from disposal in the middle of the call.
- * But it can keep the reference to the VFIO group for several calls into
- * this interface.
- * After finishing using of the VFIO group, the caller needs to release the
- * VFIO group by calling vfio_group_put_external_user().
- *
- * @group [in]		: VFIO group
- * @user_iova_pfn [in]	: array of user/guest IOVA PFNs to be pinned.
- * @npage [in]		: count of elements in user_iova_pfn array.
- *			  This count should not be greater
- *			  VFIO_PIN_PAGES_MAX_ENTRIES.
- * @prot [in]		: protection flags
- * @phys_pfn [out]	: array of host PFNs
- * Return error or number of pages pinned.
- */
-int vfio_group_pin_pages(struct vfio_group *group,
-			 unsigned long *user_iova_pfn, int npage,
-			 int prot, unsigned long *phys_pfn)
-{
-	struct vfio_container *container;
-	struct vfio_iommu_driver *driver;
-	int ret;
-
-	if (!group || !user_iova_pfn || !phys_pfn || !npage)
-		return -EINVAL;
-
-	if (group->dev_counter > 1)
-		return -EINVAL;
-
-	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
-		return -E2BIG;
-
-	container = group->container;
-	driver = container->iommu_driver;
-	if (likely(driver && driver->ops->pin_pages))
-		ret = driver->ops->pin_pages(container->iommu_data,
-					     group->iommu_group, user_iova_pfn,
-					     npage, prot, phys_pfn);
-	else
-		ret = -ENOTTY;
-
-	return ret;
-}
-EXPORT_SYMBOL(vfio_group_pin_pages);
-
-/*
- * Unpin a set of guest IOVA PFNs for a VFIO group.
- *
- * The caller needs to call vfio_group_get_external_user() or
- * vfio_group_get_external_user_from_dev() prior to calling this interface,
- * so as to prevent the VFIO group from disposal in the middle of the call.
- * But it can keep the reference to the VFIO group for several calls into
- * this interface.
- * After finishing using of the VFIO group, the caller needs to release the
- * VFIO group by calling vfio_group_put_external_user().
- *
- * @group [in]		: vfio group
- * @user_iova_pfn [in]	: array of user/guest IOVA PFNs to be unpinned.
- * @npage [in]		: count of elements in user_iova_pfn array.
- *			  This count should not be greater than
- *			  VFIO_PIN_PAGES_MAX_ENTRIES.
- * Return error or number of pages unpinned.
- */
-int vfio_group_unpin_pages(struct vfio_group *group,
-			   unsigned long *user_iova_pfn, int npage)
-{
-	struct vfio_container *container;
-	struct vfio_iommu_driver *driver;
-	int ret;
-
-	if (!group || !user_iova_pfn || !npage)
-		return -EINVAL;
-
-	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
-		return -E2BIG;
-
-	container = group->container;
-	driver = container->iommu_driver;
-	if (likely(driver && driver->ops->unpin_pages))
-		ret = driver->ops->unpin_pages(container->iommu_data,
-					       user_iova_pfn, npage);
-	else
-		ret = -ENOTTY;
-
-	return ret;
-}
-EXPORT_SYMBOL(vfio_group_unpin_pages);
-
-
 /*
  * This interface allows the CPUs to perform some sort of virtual DMA on
  * behalf of the device.
@@ -2516,24 +2383,6 @@ int vfio_unregister_notifier(struct vfio_device *device,
 }
 EXPORT_SYMBOL(vfio_unregister_notifier);
 
-struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group)
-{
-	struct vfio_container *container;
-	struct vfio_iommu_driver *driver;
-
-	if (!group)
-		return ERR_PTR(-EINVAL);
-
-	container = group->container;
-	driver = container->iommu_driver;
-	if (likely(driver && driver->ops->group_iommu_domain))
-		return driver->ops->group_iommu_domain(container->iommu_data,
-						       group->iommu_group);
-
-	return ERR_PTR(-ENOTTY);
-}
-EXPORT_SYMBOL_GPL(vfio_group_iommu_domain);
-
 /*
  * Module/class support
  */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 8a1510258717..6195edd2edcd 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -140,8 +140,6 @@ int vfio_mig_get_next_state(struct vfio_device *device,
  */
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
-extern struct vfio_group *vfio_group_get_external_user_from_dev(struct device
-								*dev);
 extern bool vfio_external_group_match_file(struct vfio_group *group,
 					   struct file *filep);
 extern int vfio_external_user_iommu_id(struct vfio_group *group);
@@ -154,18 +152,9 @@ extern int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn,
 			  int npage, int prot, unsigned long *phys_pfn);
 extern int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn,
 			    int npage);
-
-extern int vfio_group_pin_pages(struct vfio_group *group,
-				unsigned long *user_iova_pfn, int npage,
-				int prot, unsigned long *phys_pfn);
-extern int vfio_group_unpin_pages(struct vfio_group *group,
-				  unsigned long *user_iova_pfn, int npage);
-
 extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,
 		       void *data, size_t len, bool write);
 
-extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group);
-
 /* each type has independent events */
 enum vfio_notify_type {
 	VFIO_IOMMU_NOTIFY = 0,
-- 
cgit v1.2.3


From ff806cbd90bd2cc3d08a026e26157e5b5a6b5e03 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 11 May 2022 13:19:07 -0600
Subject: vfio/pci: Remove vfio_device_get_from_dev()

The last user of this function is in PCI callbacks that want to convert
their struct pci_dev to a vfio_device. Instead of searching use the
vfio_device available trivially through the drvdata.

When a callback in the device_driver is called, the caller must hold the
device_lock() on dev. The purpose of the device_lock is to prevent
remove() from being called (see __device_release_driver), and allow the
driver to safely interact with its drvdata without races.

The PCI core correctly follows this and holds the device_lock() when
calling error_detected (see report_error_detected) and
sriov_configure (see sriov_numvfs_store).

Further, since the drvdata holds a positive refcount on the vfio_device
any access of the drvdata, under the device_lock(), from a driver callback
needs no further protection or refcounting.

Thus the remark in the vfio_device_get_from_dev() comment does not apply
here, VFIO PCI drivers all call vfio_unregister_group_dev() from their
remove callbacks under the device_lock() and cannot race with the
remaining callers.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/2-v4-c841817a0349+8f-vfio_get_from_dev_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c      |  4 +++-
 drivers/vfio/pci/vfio_pci_core.c | 32 ++++++-------------------------
 drivers/vfio/vfio.c              | 41 +---------------------------------------
 include/linux/vfio.h             |  2 --
 include/linux/vfio_pci_core.h    |  3 ++-
 5 files changed, 12 insertions(+), 70 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 8c990a1a7def..cdee5f81f49d 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -174,10 +174,12 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 
 static int vfio_pci_sriov_configure(struct pci_dev *pdev, int nr_virtfn)
 {
+	struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev);
+
 	if (!enable_sriov)
 		return -ENOENT;
 
-	return vfio_pci_core_sriov_configure(pdev, nr_virtfn);
+	return vfio_pci_core_sriov_configure(vdev, nr_virtfn);
 }
 
 static const struct pci_device_id vfio_pci_table[] = {
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 65587fd5c021..100ab98c7ff0 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1894,9 +1894,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_register_device);
 
 void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev)
 {
-	struct pci_dev *pdev = vdev->pdev;
-
-	vfio_pci_core_sriov_configure(pdev, 0);
+	vfio_pci_core_sriov_configure(vdev, 0);
 
 	vfio_unregister_group_dev(&vdev->vdev);
 
@@ -1911,14 +1909,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_unregister_device);
 pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 						pci_channel_state_t state)
 {
-	struct vfio_pci_core_device *vdev;
-	struct vfio_device *device;
-
-	device = vfio_device_get_from_dev(&pdev->dev);
-	if (device == NULL)
-		return PCI_ERS_RESULT_DISCONNECT;
-
-	vdev = container_of(device, struct vfio_pci_core_device, vdev);
+	struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev);
 
 	mutex_lock(&vdev->igate);
 
@@ -1927,26 +1918,18 @@ pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 
 	mutex_unlock(&vdev->igate);
 
-	vfio_device_put(device);
-
 	return PCI_ERS_RESULT_CAN_RECOVER;
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_aer_err_detected);
 
-int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn)
+int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
+				  int nr_virtfn)
 {
-	struct vfio_pci_core_device *vdev;
-	struct vfio_device *device;
+	struct pci_dev *pdev = vdev->pdev;
 	int ret = 0;
 
 	device_lock_assert(&pdev->dev);
 
-	device = vfio_device_get_from_dev(&pdev->dev);
-	if (!device)
-		return -ENODEV;
-
-	vdev = container_of(device, struct vfio_pci_core_device, vdev);
-
 	if (nr_virtfn) {
 		mutex_lock(&vfio_pci_sriov_pfs_mutex);
 		/*
@@ -1964,8 +1947,7 @@ int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn)
 		ret = pci_enable_sriov(pdev, nr_virtfn);
 		if (ret)
 			goto out_del;
-		ret = nr_virtfn;
-		goto out_put;
+		return nr_virtfn;
 	}
 
 	pci_disable_sriov(pdev);
@@ -1975,8 +1957,6 @@ out_del:
 	list_del_init(&vdev->sriov_pfs_item);
 out_unlock:
 	mutex_unlock(&vfio_pci_sriov_pfs_mutex);
-out_put:
-	vfio_device_put(device);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure);
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 0339adeee16b..56b80c39a3c0 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -473,31 +473,15 @@ static void vfio_group_get(struct vfio_group *group)
 	refcount_inc(&group->users);
 }
 
-static struct vfio_group *vfio_group_get_from_dev(struct device *dev)
-{
-	struct iommu_group *iommu_group;
-	struct vfio_group *group;
-
-	iommu_group = iommu_group_get(dev);
-	if (!iommu_group)
-		return NULL;
-
-	group = vfio_group_get_from_iommu(iommu_group);
-	iommu_group_put(iommu_group);
-
-	return group;
-}
-
 /*
  * Device objects - create, release, get, put, search
  */
 /* Device reference always implies a group reference */
-void vfio_device_put(struct vfio_device *device)
+static void vfio_device_put(struct vfio_device *device)
 {
 	if (refcount_dec_and_test(&device->refcount))
 		complete(&device->comp);
 }
-EXPORT_SYMBOL_GPL(vfio_device_put);
 
 static bool vfio_device_try_get(struct vfio_device *device)
 {
@@ -831,29 +815,6 @@ int vfio_register_emulated_iommu_dev(struct vfio_device *device)
 }
 EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev);
 
-/*
- * Get a reference to the vfio_device for a device.  Even if the
- * caller thinks they own the device, they could be racing with a
- * release call path, so we can't trust drvdata for the shortcut.
- * Go the long way around, from the iommu_group to the vfio_group
- * to the vfio_device.
- */
-struct vfio_device *vfio_device_get_from_dev(struct device *dev)
-{
-	struct vfio_group *group;
-	struct vfio_device *device;
-
-	group = vfio_group_get_from_dev(dev);
-	if (!group)
-		return NULL;
-
-	device = vfio_group_get_device(group, dev);
-	vfio_group_put(group);
-
-	return device;
-}
-EXPORT_SYMBOL_GPL(vfio_device_get_from_dev);
-
 static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
 						     char *buf)
 {
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 6195edd2edcd..be1e7db4a314 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -125,8 +125,6 @@ void vfio_uninit_group_dev(struct vfio_device *device);
 int vfio_register_group_dev(struct vfio_device *device);
 int vfio_register_emulated_iommu_dev(struct vfio_device *device);
 void vfio_unregister_group_dev(struct vfio_device *device);
-extern struct vfio_device *vfio_device_get_from_dev(struct device *dev);
-extern void vfio_device_put(struct vfio_device *device);
 
 int vfio_assign_device_set(struct vfio_device *device, void *set_id);
 
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 48f2dd3c568c..23c176d4b073 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -227,8 +227,9 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev,
 int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev);
-int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn);
 extern const struct pci_error_handlers vfio_pci_core_err_handlers;
+int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev,
+				  int nr_virtfn);
 long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
 		unsigned long arg);
 int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags,
-- 
cgit v1.2.3


From 157cc18122b4a1456d19048e151a164216c4a704 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 22 Apr 2022 09:48:54 -0500
Subject: signal: Rename send_signal send_signal_locked

Rename send_signal and __send_signal to send_signal_locked and
__send_signal_locked to make send_signal usable outside of
signal.c.

Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-1-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/signal.h |  2 ++
 kernel/signal.c        | 24 ++++++++++++------------
 2 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/signal.h b/include/linux/signal.h
index a6db6f2ae113..55605bdf5ce9 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -283,6 +283,8 @@ extern int do_send_sig_info(int sig, struct kernel_siginfo *info,
 extern int group_send_sig_info(int sig, struct kernel_siginfo *info,
 			       struct task_struct *p, enum pid_type type);
 extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *);
+extern int send_signal_locked(int sig, struct kernel_siginfo *info,
+			      struct task_struct *p, enum pid_type type);
 extern int sigprocmask(int, sigset_t *, sigset_t *);
 extern void set_current_blocked(sigset_t *);
 extern void __set_current_blocked(const sigset_t *);
diff --git a/kernel/signal.c b/kernel/signal.c
index 30cd1ca43bcd..b0403197b0ad 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1071,8 +1071,8 @@ static inline bool legacy_queue(struct sigpending *signals, int sig)
 	return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
 }
 
-static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t,
-			enum pid_type type, bool force)
+static int __send_signal_locked(int sig, struct kernel_siginfo *info,
+				struct task_struct *t, enum pid_type type, bool force)
 {
 	struct sigpending *pending;
 	struct sigqueue *q;
@@ -1212,8 +1212,8 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info)
 	return ret;
 }
 
-static int send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t,
-			enum pid_type type)
+int send_signal_locked(int sig, struct kernel_siginfo *info,
+		       struct task_struct *t, enum pid_type type)
 {
 	/* Should SIGKILL or SIGSTOP be received by a pid namespace init? */
 	bool force = false;
@@ -1245,7 +1245,7 @@ static int send_signal(int sig, struct kernel_siginfo *info, struct task_struct
 			force = true;
 		}
 	}
-	return __send_signal(sig, info, t, type, force);
+	return __send_signal_locked(sig, info, t, type, force);
 }
 
 static void print_fatal_signal(int signr)
@@ -1284,7 +1284,7 @@ __setup("print-fatal-signals=", setup_print_fatal_signals);
 int
 __group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p)
 {
-	return send_signal(sig, info, p, PIDTYPE_TGID);
+	return send_signal_locked(sig, info, p, PIDTYPE_TGID);
 }
 
 int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p,
@@ -1294,7 +1294,7 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p
 	int ret = -ESRCH;
 
 	if (lock_task_sighand(p, &flags)) {
-		ret = send_signal(sig, info, p, type);
+		ret = send_signal_locked(sig, info, p, type);
 		unlock_task_sighand(p, &flags);
 	}
 
@@ -1347,7 +1347,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
 	if (action->sa.sa_handler == SIG_DFL &&
 	    (!t->ptrace || (handler == HANDLER_EXIT)))
 		t->signal->flags &= ~SIGNAL_UNKILLABLE;
-	ret = send_signal(sig, info, t, PIDTYPE_PID);
+	ret = send_signal_locked(sig, info, t, PIDTYPE_PID);
 	spin_unlock_irqrestore(&t->sighand->siglock, flags);
 
 	return ret;
@@ -1567,7 +1567,7 @@ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr,
 
 	if (sig) {
 		if (lock_task_sighand(p, &flags)) {
-			ret = __send_signal(sig, &info, p, PIDTYPE_TGID, false);
+			ret = __send_signal_locked(sig, &info, p, PIDTYPE_TGID, false);
 			unlock_task_sighand(p, &flags);
 		} else
 			ret = -ESRCH;
@@ -2103,7 +2103,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 	 * parent's namespaces.
 	 */
 	if (valid_signal(sig) && sig)
-		__send_signal(sig, &info, tsk->parent, PIDTYPE_TGID, false);
+		__send_signal_locked(sig, &info, tsk->parent, PIDTYPE_TGID, false);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
 
@@ -2601,7 +2601,7 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type)
 	/* If the (new) signal is now blocked, requeue it.  */
 	if (sigismember(&current->blocked, signr) ||
 	    fatal_signal_pending(current)) {
-		send_signal(signr, info, current, type);
+		send_signal_locked(signr, info, current, type);
 		signr = 0;
 	}
 
@@ -4793,7 +4793,7 @@ void kdb_send_sig(struct task_struct *t, int sig)
 			   "the deadlock.\n");
 		return;
 	}
-	ret = send_signal(sig, SEND_SIG_PRIV, t, PIDTYPE_PID);
+	ret = send_signal_locked(sig, SEND_SIG_PRIV, t, PIDTYPE_PID);
 	spin_unlock(&t->sighand->siglock);
 	if (ret)
 		kdb_printf("Fail to deliver Signal %d to process %d.\n",
-- 
cgit v1.2.3


From e71ba124078e391879e0bf111529fa2d630d106c Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 22 Apr 2022 09:28:50 -0500
Subject: signal: Replace __group_send_sig_info with send_signal_locked

The function __group_send_sig_info is just a light wrapper around
send_signal_locked with one parameter fixed to a constant value.  As
the wrapper adds no real value update the code to directly call the
wrapped function.

Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-2-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 drivers/tty/tty_jobctrl.c      | 4 ++--
 include/linux/signal.h         | 1 -
 kernel/signal.c                | 8 +-------
 kernel/time/posix-cpu-timers.c | 6 +++---
 4 files changed, 6 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/tty_jobctrl.c b/drivers/tty/tty_jobctrl.c
index 80b86a7992b5..0d04287da098 100644
--- a/drivers/tty/tty_jobctrl.c
+++ b/drivers/tty/tty_jobctrl.c
@@ -215,8 +215,8 @@ int tty_signal_session_leader(struct tty_struct *tty, int exit_session)
 				spin_unlock_irq(&p->sighand->siglock);
 				continue;
 			}
-			__group_send_sig_info(SIGHUP, SEND_SIG_PRIV, p);
-			__group_send_sig_info(SIGCONT, SEND_SIG_PRIV, p);
+			send_signal_locked(SIGHUP, SEND_SIG_PRIV, p, PIDTYPE_TGID);
+			send_signal_locked(SIGCONT, SEND_SIG_PRIV, p, PIDTYPE_TGID);
 			put_pid(p->signal->tty_old_pgrp);  /* A noop */
 			spin_lock(&tty->ctrl.lock);
 			tty_pgrp = get_pid(tty->ctrl.pgrp);
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 55605bdf5ce9..3b98e7a28538 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -282,7 +282,6 @@ extern int do_send_sig_info(int sig, struct kernel_siginfo *info,
 				struct task_struct *p, enum pid_type type);
 extern int group_send_sig_info(int sig, struct kernel_siginfo *info,
 			       struct task_struct *p, enum pid_type type);
-extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *);
 extern int send_signal_locked(int sig, struct kernel_siginfo *info,
 			      struct task_struct *p, enum pid_type type);
 extern int sigprocmask(int, sigset_t *, sigset_t *);
diff --git a/kernel/signal.c b/kernel/signal.c
index b0403197b0ad..72d96614effc 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1281,12 +1281,6 @@ static int __init setup_print_fatal_signals(char *str)
 
 __setup("print-fatal-signals=", setup_print_fatal_signals);
 
-int
-__group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p)
-{
-	return send_signal_locked(sig, info, p, PIDTYPE_TGID);
-}
-
 int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p,
 			enum pid_type type)
 {
@@ -2173,7 +2167,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 	spin_lock_irqsave(&sighand->siglock, flags);
 	if (sighand->action[SIGCHLD-1].sa.sa_handler != SIG_IGN &&
 	    !(sighand->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
-		__group_send_sig_info(SIGCHLD, &info, parent);
+		send_signal_locked(SIGCHLD, &info, parent, PIDTYPE_TGID);
 	/*
 	 * Even if SIGCHLD is not generated, we must wake up wait4 calls.
 	 */
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 0a97193984db..cb925e8ef9a8 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -870,7 +870,7 @@ static inline void check_dl_overrun(struct task_struct *tsk)
 {
 	if (tsk->dl.dl_overrun) {
 		tsk->dl.dl_overrun = 0;
-		__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+		send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
 	}
 }
 
@@ -884,7 +884,7 @@ static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
 			rt ? "RT" : "CPU", hard ? "hard" : "soft",
 			current->comm, task_pid_nr(current));
 	}
-	__group_send_sig_info(signo, SEND_SIG_PRIV, current);
+	send_signal_locked(signo, SEND_SIG_PRIV, current, PIDTYPE_TGID);
 	return true;
 }
 
@@ -958,7 +958,7 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
 		trace_itimer_expire(signo == SIGPROF ?
 				    ITIMER_PROF : ITIMER_VIRTUAL,
 				    task_tgid(tsk), cur_time);
-		__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+		send_signal_locked(signo, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
 	}
 
 	if (it->expires && it->expires < *expires)
-- 
cgit v1.2.3


From c200e4bb44e80b343c09841e7caaaca0aac5e5fa Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 26 Apr 2022 16:30:17 -0500
Subject: ptrace/um: Replace PT_DTRACE with TIF_SINGLESTEP

User mode linux is the last user of the PT_DTRACE flag.  Using the flag to indicate
single stepping is a little confusing and worse changing tsk->ptrace without locking
could potentionally cause problems.

So use a thread info flag with a better name instead of flag in tsk->ptrace.

Remove the definition PT_DTRACE as uml is the last user.

Cc: stable@vger.kernel.org
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-3-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/um/include/asm/thread_info.h | 2 ++
 arch/um/kernel/exec.c             | 2 +-
 arch/um/kernel/process.c          | 2 +-
 arch/um/kernel/ptrace.c           | 8 ++++----
 arch/um/kernel/signal.c           | 4 ++--
 include/linux/ptrace.h            | 1 -
 6 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index 1395cbd7e340..c7b4b49826a2 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -60,6 +60,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_RESTORE_SIGMASK	7
 #define TIF_NOTIFY_RESUME	8
 #define TIF_SECCOMP		9	/* secure computing */
+#define TIF_SINGLESTEP		10	/* single stepping userspace */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
@@ -68,5 +69,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 
 #endif
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index c85e40c72779..58938d75871a 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -43,7 +43,7 @@ void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp)
 {
 	PT_REGS_IP(regs) = eip;
 	PT_REGS_SP(regs) = esp;
-	current->ptrace &= ~PT_DTRACE;
+	clear_thread_flag(TIF_SINGLESTEP);
 #ifdef SUBARCH_EXECVE1
 	SUBARCH_EXECVE1(regs->regs);
 #endif
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 80504680be08..88c5c7844281 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -335,7 +335,7 @@ int singlestepping(void * t)
 {
 	struct task_struct *task = t ? t : current;
 
-	if (!(task->ptrace & PT_DTRACE))
+	if (!test_thread_flag(TIF_SINGLESTEP))
 		return 0;
 
 	if (task->thread.singlestep_syscall)
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index bfaf6ab1ac03..5154b27de580 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -11,7 +11,7 @@
 
 void user_enable_single_step(struct task_struct *child)
 {
-	child->ptrace |= PT_DTRACE;
+	set_tsk_thread_flag(child, TIF_SINGLESTEP);
 	child->thread.singlestep_syscall = 0;
 
 #ifdef SUBARCH_SET_SINGLESTEPPING
@@ -21,7 +21,7 @@ void user_enable_single_step(struct task_struct *child)
 
 void user_disable_single_step(struct task_struct *child)
 {
-	child->ptrace &= ~PT_DTRACE;
+	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
 	child->thread.singlestep_syscall = 0;
 
 #ifdef SUBARCH_SET_SINGLESTEPPING
@@ -120,7 +120,7 @@ static void send_sigtrap(struct uml_pt_regs *regs, int error_code)
 }
 
 /*
- * XXX Check PT_DTRACE vs TIF_SINGLESTEP for singlestepping check and
+ * XXX Check TIF_SINGLESTEP for singlestepping check and
  * PT_PTRACED vs TIF_SYSCALL_TRACE for syscall tracing check
  */
 int syscall_trace_enter(struct pt_regs *regs)
@@ -144,7 +144,7 @@ void syscall_trace_leave(struct pt_regs *regs)
 	audit_syscall_exit(regs);
 
 	/* Fake a debug trap */
-	if (ptraced & PT_DTRACE)
+	if (test_thread_flag(TIF_SINGLESTEP))
 		send_sigtrap(&regs->regs, 0);
 
 	if (!test_thread_flag(TIF_SYSCALL_TRACE))
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index 88cd9b5c1b74..ae4658f576ab 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -53,7 +53,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	unsigned long sp;
 	int err;
 
-	if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
+	if (test_thread_flag(TIF_SINGLESTEP) && (current->ptrace & PT_PTRACED))
 		singlestep = 1;
 
 	/* Did we come from a system call? */
@@ -128,7 +128,7 @@ void do_signal(struct pt_regs *regs)
 	 * on the host.  The tracing thread will check this flag and
 	 * PTRACE_SYSCALL if necessary.
 	 */
-	if (current->ptrace & PT_DTRACE)
+	if (test_thread_flag(TIF_SINGLESTEP))
 		current->thread.singlestep_syscall =
 			is_syscall(PT_REGS_IP(&current->thread.regs));
 
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 15b3d176b6b4..4c06f9f8ef3f 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -30,7 +30,6 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 
 #define PT_SEIZED	0x00010000	/* SEIZE used, enable new behavior */
 #define PT_PTRACED	0x00000001
-#define PT_DTRACE	0x00000002	/* delayed trace (used on m68k, i386) */
 
 #define PT_OPT_FLAG_SHIFT	3
 /* PT_TRACE_* event enable flags */
-- 
cgit v1.2.3


From 4a3d2717d140401df7501a95e454180831a0c5af Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 26 Apr 2022 16:45:37 -0500
Subject: ptrace/xtensa: Replace PT_SINGLESTEP with TIF_SINGLESTEP

xtensa is the last user of the PT_SINGLESTEP flag.  Changing tsk->ptrace in
user_enable_single_step and user_disable_single_step without locking could
potentiallly cause problems.

So use a thread info flag instead of a flag in tsk->ptrace.  Use TIF_SINGLESTEP
that xtensa already had defined but unused.

Remove the definitions of PT_SINGLESTEP and PT_BLOCKSTEP as they have no more users.

Cc: stable@vger.kernel.org
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-4-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 arch/xtensa/kernel/ptrace.c | 4 ++--
 arch/xtensa/kernel/signal.c | 4 ++--
 include/linux/ptrace.h      | 6 ------
 3 files changed, 4 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index 323c678a691f..b952e67cc0cc 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -225,12 +225,12 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 
 void user_enable_single_step(struct task_struct *child)
 {
-	child->ptrace |= PT_SINGLESTEP;
+	set_tsk_thread_flag(child, TIF_SINGLESTEP);
 }
 
 void user_disable_single_step(struct task_struct *child)
 {
-	child->ptrace &= ~PT_SINGLESTEP;
+	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
 }
 
 /*
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 6f68649e86ba..ac50ec46c8f1 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -473,7 +473,7 @@ static void do_signal(struct pt_regs *regs)
 		/* Set up the stack frame */
 		ret = setup_frame(&ksig, sigmask_to_save(), regs);
 		signal_setup_done(ret, &ksig, 0);
-		if (current->ptrace & PT_SINGLESTEP)
+		if (test_thread_flag(TIF_SINGLESTEP))
 			task_pt_regs(current)->icountlevel = 1;
 
 		return;
@@ -499,7 +499,7 @@ static void do_signal(struct pt_regs *regs)
 	/* If there's no signal to deliver, we just restore the saved mask.  */
 	restore_saved_sigmask();
 
-	if (current->ptrace & PT_SINGLESTEP)
+	if (test_thread_flag(TIF_SINGLESTEP))
 		task_pt_regs(current)->icountlevel = 1;
 	return;
 }
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 4c06f9f8ef3f..c952c5ba8fab 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -46,12 +46,6 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 #define PT_EXITKILL		(PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT)
 #define PT_SUSPEND_SECCOMP	(PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT)
 
-/* single stepping state bits (used on ARM and PA-RISC) */
-#define PT_SINGLESTEP_BIT	31
-#define PT_SINGLESTEP		(1<<PT_SINGLESTEP_BIT)
-#define PT_BLOCKSTEP_BIT	30
-#define PT_BLOCKSTEP		(1<<PT_BLOCKSTEP_BIT)
-
 extern long arch_ptrace(struct task_struct *child, long request,
 			unsigned long addr, unsigned long data);
 extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len);
-- 
cgit v1.2.3


From 2500ad1c7fa42ad734677853961a3a8bec0772c5 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 29 Apr 2022 08:43:34 -0500
Subject: ptrace: Don't change __state

Stop playing with tsk->__state to remove TASK_WAKEKILL while a ptrace
command is executing.

Instead remove TASK_WAKEKILL from the definition of TASK_TRACED, and
implement a new jobctl flag TASK_PTRACE_FROZEN.  This new flag is set
in jobctl_freeze_task and cleared when ptrace_stop is awoken or in
jobctl_unfreeze_task (when ptrace_stop remains asleep).

In signal_wake_up add __TASK_TRACED to state along with TASK_WAKEKILL
when the wake up is for a fatal signal.  Skip adding __TASK_TRACED
when TASK_PTRACE_FROZEN is not set.  This has the same effect as
changing TASK_TRACED to __TASK_TRACED as all of the wake_ups that use
TASK_KILLABLE go through signal_wake_up.

Handle a ptrace_stop being called with a pending fatal signal.
Previously it would have been handled by schedule simply failing to
sleep.  As TASK_WAKEKILL is no longer part of TASK_TRACED schedule
will sleep with a fatal_signal_pending.   The code in signal_wake_up
guarantees that the code will be awaked by any fatal signal that
codes after TASK_TRACED is set.

Previously the __state value of __TASK_TRACED was changed to
TASK_RUNNING when woken up or back to TASK_TRACED when the code was
left in ptrace_stop.  Now when woken up ptrace_stop now clears
JOBCTL_PTRACE_FROZEN and when left sleeping ptrace_unfreezed_traced
clears JOBCTL_PTRACE_FROZEN.

Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-10-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/sched.h        |  2 +-
 include/linux/sched/jobctl.h |  2 ++
 include/linux/sched/signal.h |  5 +++--
 kernel/ptrace.c              | 21 ++++++++-------------
 kernel/sched/core.c          |  5 +----
 kernel/signal.c              | 14 ++++++--------
 6 files changed, 21 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d5e3c00b74e1..610f2fdb1e2c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -103,7 +103,7 @@ struct task_group;
 /* Convenience macros for the sake of set_current_state: */
 #define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
 #define TASK_STOPPED			(TASK_WAKEKILL | __TASK_STOPPED)
-#define TASK_TRACED			(TASK_WAKEKILL | __TASK_TRACED)
+#define TASK_TRACED			__TASK_TRACED
 
 #define TASK_IDLE			(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
 
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index fa067de9f1a9..d556c3425963 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,6 +19,7 @@ struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
+#define JOBCTL_PTRACE_FROZEN_BIT	24	/* frozen for ptrace */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -28,6 +29,7 @@ struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
+#define JOBCTL_PTRACE_FROZEN	(1UL << JOBCTL_PTRACE_FROZEN_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 3c8b34876744..e66948abbee4 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -435,9 +435,10 @@ extern void calculate_sigpending(void);
 
 extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
 
-static inline void signal_wake_up(struct task_struct *t, bool resume)
+static inline void signal_wake_up(struct task_struct *t, bool fatal)
 {
-	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+	fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN);
+	signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0);
 }
 static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
 {
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 05953ac9f7bd..83ed28262708 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -197,7 +197,7 @@ static bool ptrace_freeze_traced(struct task_struct *task)
 	spin_lock_irq(&task->sighand->siglock);
 	if (task_is_traced(task) && !looks_like_a_spurious_pid(task) &&
 	    !__fatal_signal_pending(task)) {
-		WRITE_ONCE(task->__state, __TASK_TRACED);
+		task->jobctl |= JOBCTL_PTRACE_FROZEN;
 		ret = true;
 	}
 	spin_unlock_irq(&task->sighand->siglock);
@@ -207,23 +207,19 @@ static bool ptrace_freeze_traced(struct task_struct *task)
 
 static void ptrace_unfreeze_traced(struct task_struct *task)
 {
-	if (READ_ONCE(task->__state) != __TASK_TRACED)
-		return;
-
-	WARN_ON(!task->ptrace || task->parent != current);
+	unsigned long flags;
 
 	/*
-	 * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
-	 * Recheck state under the lock to close this race.
+	 * The child may be awake and may have cleared
+	 * JOBCTL_PTRACE_FROZEN (see ptrace_resume).  The child will
+	 * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew.
 	 */
-	spin_lock_irq(&task->sighand->siglock);
-	if (READ_ONCE(task->__state) == __TASK_TRACED) {
+	if (lock_task_sighand(task, &flags)) {
+		task->jobctl &= ~JOBCTL_PTRACE_FROZEN;
 		if (__fatal_signal_pending(task))
 			wake_up_state(task, __TASK_TRACED);
-		else
-			WRITE_ONCE(task->__state, TASK_TRACED);
+		unlock_task_sighand(task, &flags);
 	}
-	spin_unlock_irq(&task->sighand->siglock);
 }
 
 /**
@@ -256,7 +252,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	 */
 	read_lock(&tasklist_lock);
 	if (child->ptrace && child->parent == current) {
-		WARN_ON(READ_ONCE(child->__state) == __TASK_TRACED);
 		/*
 		 * child->sighand can't be NULL, release_task()
 		 * does ptrace_unlink() before __exit_signal().
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d575b4914925..3c351707e830 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6304,10 +6304,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 
 	/*
 	 * We must load prev->state once (task_struct::state is volatile), such
-	 * that:
-	 *
-	 *  - we form a control dependency vs deactivate_task() below.
-	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
+	 * that we form a control dependency vs deactivate_task() below.
 	 */
 	prev_state = READ_ONCE(prev->__state);
 	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
diff --git a/kernel/signal.c b/kernel/signal.c
index d2d0c753156c..a58b68a2d3c6 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2209,14 +2209,12 @@ static int ptrace_stop(int exit_code, int why, unsigned long message,
 	}
 
 	/*
-	 * schedule() will not sleep if there is a pending signal that
-	 * can awaken the task.
-	 *
-	 * After this point ptrace_signal_wake_up will clear TASK_TRACED
-	 * if ptrace_unlink happens.  Handle previous ptrace_unlinks
-	 * here to prevent ptrace_stop sleeping in schedule.
+	 * After this point ptrace_signal_wake_up or signal_wake_up
+	 * will clear TASK_TRACED if ptrace_unlink happens or a fatal
+	 * signal comes in.  Handle previous ptrace_unlinks and fatal
+	 * signals here to prevent ptrace_stop sleeping in schedule.
 	 */
-	if (!current->ptrace)
+	if (!current->ptrace || __fatal_signal_pending(current))
 		return exit_code;
 
 	set_special_state(TASK_TRACED);
@@ -2305,7 +2303,7 @@ static int ptrace_stop(int exit_code, int why, unsigned long message,
 	current->exit_code = 0;
 
 	/* LISTENING can be set only during STOP traps, clear it */
-	current->jobctl &= ~JOBCTL_LISTENING;
+	current->jobctl &= ~(JOBCTL_LISTENING | JOBCTL_PTRACE_FROZEN);
 
 	/*
 	 * Queued signals ignored us while we were stopped for tracing.
-- 
cgit v1.2.3


From 31cae1eaae4fd65095ad6a3659db467bc3c2599e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 May 2022 15:57:47 -0500
Subject: sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state

Currently ptrace_stop() / do_signal_stop() rely on the special states
TASK_TRACED and TASK_STOPPED resp. to keep unique state. That is, this
state exists only in task->__state and nowhere else.

There's two spots of bother with this:

 - PREEMPT_RT has task->saved_state which complicates matters,
   meaning task_is_{traced,stopped}() needs to check an additional
   variable.

 - An alternative freezer implementation that itself relies on a
   special TASK state would loose TASK_TRACED/TASK_STOPPED and will
   result in misbehaviour.

As such, add additional state to task->jobctl to track this state
outside of task->__state.

NOTE: this doesn't actually fix anything yet, just adds extra state.

--EWB
  * didn't add a unnecessary newline in signal.h
  * Update t->jobctl in signal_wake_up and ptrace_signal_wake_up
    instead of in signal_wake_up_state.  This prevents the clearing
    of TASK_STOPPED and TASK_TRACED from getting lost.
  * Added warnings if JOBCTL_STOPPED or JOBCTL_TRACED are not cleared

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220421150654.757693825@infradead.org
Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-12-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 include/linux/sched.h        |  8 +++-----
 include/linux/sched/jobctl.h |  6 ++++++
 include/linux/sched/signal.h | 19 +++++++++++++++----
 kernel/ptrace.c              | 16 +++++++++++++---
 kernel/signal.c              | 10 ++++++++--
 5 files changed, 45 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 610f2fdb1e2c..cbe5c899599c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -118,11 +118,9 @@ struct task_group;
 
 #define task_is_running(task)		(READ_ONCE((task)->__state) == TASK_RUNNING)
 
-#define task_is_traced(task)		((READ_ONCE(task->__state) & __TASK_TRACED) != 0)
-
-#define task_is_stopped(task)		((READ_ONCE(task->__state) & __TASK_STOPPED) != 0)
-
-#define task_is_stopped_or_traced(task)	((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0)
+#define task_is_traced(task)		((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0)
+#define task_is_stopped(task)		((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0)
+#define task_is_stopped_or_traced(task)	((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0)
 
 /*
  * Special states are those that do not use the normal wait-loop pattern. See
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index d556c3425963..68876d0a7ef9 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -21,6 +21,9 @@ struct task_struct;
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
 #define JOBCTL_PTRACE_FROZEN_BIT	24	/* frozen for ptrace */
 
+#define JOBCTL_STOPPED_BIT	26	/* do_signal_stop() */
+#define JOBCTL_TRACED_BIT	27	/* ptrace_stop() */
+
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
 #define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
@@ -31,6 +34,9 @@ struct task_struct;
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
 #define JOBCTL_PTRACE_FROZEN	(1UL << JOBCTL_PTRACE_FROZEN_BIT)
 
+#define JOBCTL_STOPPED		(1UL << JOBCTL_STOPPED_BIT)
+#define JOBCTL_TRACED		(1UL << JOBCTL_TRACED_BIT)
+
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index e66948abbee4..07ba3404fcde 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -294,8 +294,10 @@ static inline int kernel_dequeue_signal(void)
 static inline void kernel_signal_stop(void)
 {
 	spin_lock_irq(&current->sighand->siglock);
-	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+	if (current->jobctl & JOBCTL_STOP_DEQUEUED) {
+		current->jobctl |= JOBCTL_STOPPED;
 		set_special_state(TASK_STOPPED);
+	}
 	spin_unlock_irq(&current->sighand->siglock);
 
 	schedule();
@@ -437,12 +439,21 @@ extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
 
 static inline void signal_wake_up(struct task_struct *t, bool fatal)
 {
-	fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN);
-	signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0);
+	unsigned int state = 0;
+	if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) {
+		t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED);
+		state = TASK_WAKEKILL | __TASK_TRACED;
+	}
+	signal_wake_up_state(t, state);
 }
 static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
 {
-	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+	unsigned int state = 0;
+	if (resume) {
+		t->jobctl &= ~JOBCTL_TRACED;
+		state = __TASK_TRACED;
+	}
+	signal_wake_up_state(t, state);
 }
 
 void task_join_group_stop(struct task_struct *task);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 36a5b7a00d2f..328a34a99124 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -185,7 +185,12 @@ static bool looks_like_a_spurious_pid(struct task_struct *task)
 	return true;
 }
 
-/* Ensure that nothing can wake it up, even SIGKILL */
+/*
+ * Ensure that nothing can wake it up, even SIGKILL
+ *
+ * A task is switched to this state while a ptrace operation is in progress;
+ * such that the ptrace operation is uninterruptible.
+ */
 static bool ptrace_freeze_traced(struct task_struct *task)
 {
 	bool ret = false;
@@ -216,8 +221,10 @@ static void ptrace_unfreeze_traced(struct task_struct *task)
 	 */
 	if (lock_task_sighand(task, &flags)) {
 		task->jobctl &= ~JOBCTL_PTRACE_FROZEN;
-		if (__fatal_signal_pending(task))
+		if (__fatal_signal_pending(task)) {
+			task->jobctl &= ~TASK_TRACED;
 			wake_up_state(task, __TASK_TRACED);
+		}
 		unlock_task_sighand(task, &flags);
 	}
 }
@@ -462,8 +469,10 @@ static int ptrace_attach(struct task_struct *task, long request,
 	 * in and out of STOPPED are protected by siglock.
 	 */
 	if (task_is_stopped(task) &&
-	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
+	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
+		task->jobctl &= ~JOBCTL_STOPPED;
 		signal_wake_up_state(task, __TASK_STOPPED);
+	}
 
 	spin_unlock(&task->sighand->siglock);
 
@@ -875,6 +884,7 @@ static int ptrace_resume(struct task_struct *child, long request,
 	 */
 	spin_lock_irq(&child->sighand->siglock);
 	child->exit_code = data;
+	child->jobctl &= ~JOBCTL_TRACED;
 	wake_up_state(child, __TASK_TRACED);
 	spin_unlock_irq(&child->sighand->siglock);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index a58b68a2d3c6..e782c2611b64 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -762,7 +762,10 @@ still_pending:
  */
 void signal_wake_up_state(struct task_struct *t, unsigned int state)
 {
+	lockdep_assert_held(&t->sighand->siglock);
+
 	set_tsk_thread_flag(t, TIF_SIGPENDING);
+
 	/*
 	 * TASK_WAKEKILL also means wake it up in the stopped/traced/killable
 	 * case. We don't check t->state here because there is a race with it
@@ -930,9 +933,10 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
 		for_each_thread(p, t) {
 			flush_sigqueue_mask(&flush, &t->pending);
 			task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING);
-			if (likely(!(t->ptrace & PT_SEIZED)))
+			if (likely(!(t->ptrace & PT_SEIZED))) {
+				t->jobctl &= ~JOBCTL_STOPPED;
 				wake_up_state(t, __TASK_STOPPED);
-			else
+			} else
 				ptrace_trap_notify(t);
 		}
 
@@ -2218,6 +2222,7 @@ static int ptrace_stop(int exit_code, int why, unsigned long message,
 		return exit_code;
 
 	set_special_state(TASK_TRACED);
+	current->jobctl |= JOBCTL_TRACED;
 
 	/*
 	 * We're committing to trapping.  TRACED should be visible before
@@ -2436,6 +2441,7 @@ static bool do_signal_stop(int signr)
 		if (task_participate_group_stop(current))
 			notify = CLD_STOPPED;
 
+		current->jobctl |= JOBCTL_STOPPED;
 		set_special_state(TASK_STOPPED);
 		spin_unlock_irq(&current->sighand->siglock);
 
-- 
cgit v1.2.3


From 5b74c690e1c55953ec99fd9dab74f72dbee4fe95 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 12 May 2022 01:16:51 +0530
Subject: bpf: Fix sparse warning for bpf_kptr_xchg_proto

Kernel Test Robot complained about missing static storage class
annotation for bpf_kptr_xchg_proto variable.

sparse: symbol 'bpf_kptr_xchg_proto' was not declared. Should it be static?

This caused by missing extern definition in the header. Add it to
suppress the sparse warning.

Fixes: c0a5a21c25f3 ("bpf: Allow storing referenced kptr in map")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20220511194654.765705-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index aba7ded56436..3ded8711457f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2246,6 +2246,7 @@ extern const struct bpf_func_proto bpf_find_vma_proto;
 extern const struct bpf_func_proto bpf_loop_proto;
 extern const struct bpf_func_proto bpf_strncmp_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_task_proto;
+extern const struct bpf_func_proto bpf_kptr_xchg_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);
-- 
cgit v1.2.3


From 07343110b293456d30393e89b86c4dee1ac051c8 Mon Sep 17 00:00:00 2001
From: Feng Zhou <zhoufeng.zf@bytedance.com>
Date: Wed, 11 May 2022 17:38:53 +0800
Subject: bpf: add bpf_map_lookup_percpu_elem for percpu map

Add new ebpf helpers bpf_map_lookup_percpu_elem.

The implementation method is relatively simple, refer to the implementation
method of map_lookup_elem of percpu map, increase the parameters of cpu, and
obtain it according to the specified cpu.

Signed-off-by: Feng Zhou <zhoufeng.zf@bytedance.com>
Link: https://lore.kernel.org/r/20220511093854.411-2-zhoufeng.zf@bytedance.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            |  2 ++
 include/uapi/linux/bpf.h       |  9 +++++++++
 kernel/bpf/arraymap.c          | 15 +++++++++++++++
 kernel/bpf/core.c              |  1 +
 kernel/bpf/hashtab.c           | 32 ++++++++++++++++++++++++++++++++
 kernel/bpf/helpers.c           | 18 ++++++++++++++++++
 kernel/bpf/verifier.c          | 17 +++++++++++++++--
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h |  9 +++++++++
 9 files changed, 103 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3ded8711457f..5061ccd8b2dc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -89,6 +89,7 @@ struct bpf_map_ops {
 	int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
 	int (*map_pop_elem)(struct bpf_map *map, void *value);
 	int (*map_peek_elem)(struct bpf_map *map, void *value);
+	void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu);
 
 	/* funcs called by prog_array and perf_event_array map */
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
@@ -2184,6 +2185,7 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto;
 extern const struct bpf_func_proto bpf_map_push_elem_proto;
 extern const struct bpf_func_proto bpf_map_pop_elem_proto;
 extern const struct bpf_func_proto bpf_map_peek_elem_proto;
+extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto;
 
 extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
 extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index bc7f89948f54..0210f85131b3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5164,6 +5164,14 @@ union bpf_attr {
  *		if not NULL, is a reference which must be released using its
  *		corresponding release function, or moved into a BPF map before
  *		program exit.
+ *
+ * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu)
+ * 	Description
+ * 		Perform a lookup in *percpu map* for an entry associated to
+ * 		*key* on *cpu*.
+ * 	Return
+ * 		Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * 		was found or *cpu* is invalid.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5361,6 +5369,7 @@ union bpf_attr {
 	FN(skb_set_tstamp),		\
 	FN(ima_file_hash),		\
 	FN(kptr_xchg),			\
+	FN(map_lookup_percpu_elem),     \
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 724613da6576..fe40d3b9458f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -243,6 +243,20 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
 	return this_cpu_ptr(array->pptrs[index & array->index_mask]);
 }
 
+static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+
+	if (cpu >= nr_cpu_ids)
+		return NULL;
+
+	if (unlikely(index >= array->map.max_entries))
+		return NULL;
+
+	return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu);
+}
+
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
@@ -725,6 +739,7 @@ const struct bpf_map_ops percpu_array_map_ops = {
 	.map_lookup_elem = percpu_array_map_lookup_elem,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
+	.map_lookup_percpu_elem = percpu_array_map_lookup_percpu_elem,
 	.map_seq_show_elem = percpu_array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
 	.map_lookup_batch = generic_map_lookup_batch,
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 13e9dbeeedf3..76f68d0a7ae8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2619,6 +2619,7 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
 const struct bpf_func_proto bpf_map_push_elem_proto __weak;
 const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
 const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
+const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto __weak;
 const struct bpf_func_proto bpf_spin_lock_proto __weak;
 const struct bpf_func_proto bpf_spin_unlock_proto __weak;
 const struct bpf_func_proto bpf_jiffies64_proto __weak;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 705841279d16..17fb69c0e0dc 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2199,6 +2199,20 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 		return NULL;
 }
 
+static void *htab_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
+{
+	struct htab_elem *l;
+
+	if (cpu >= nr_cpu_ids)
+		return NULL;
+
+	l = __htab_map_lookup_elem(map, key);
+	if (l)
+		return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu);
+	else
+		return NULL;
+}
+
 static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct htab_elem *l = __htab_map_lookup_elem(map, key);
@@ -2211,6 +2225,22 @@ static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 	return NULL;
 }
 
+static void *htab_lru_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
+{
+	struct htab_elem *l;
+
+	if (cpu >= nr_cpu_ids)
+		return NULL;
+
+	l = __htab_map_lookup_elem(map, key);
+	if (l) {
+		bpf_lru_node_set_ref(&l->lru_node);
+		return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu);
+	}
+
+	return NULL;
+}
+
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
 {
 	struct htab_elem *l;
@@ -2300,6 +2330,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem,
 	.map_update_elem = htab_percpu_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
+	.map_lookup_percpu_elem = htab_percpu_map_lookup_percpu_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
@@ -2318,6 +2349,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem,
 	.map_update_elem = htab_lru_percpu_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
+	.map_lookup_percpu_elem = htab_lru_percpu_map_lookup_percpu_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 3e709fed5306..d5f104a39092 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -119,6 +119,22 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = {
 	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
 };
 
+BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu);
+}
+
+const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto = {
+	.func		= bpf_map_lookup_percpu_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_KEY,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto bpf_get_prandom_u32_proto = {
 	.func		= bpf_user_rnd_u32,
 	.gpl_only	= false,
@@ -1420,6 +1436,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_map_pop_elem_proto;
 	case BPF_FUNC_map_peek_elem:
 		return &bpf_map_peek_elem_proto;
+	case BPF_FUNC_map_lookup_percpu_elem:
+		return &bpf_map_lookup_percpu_elem_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_get_smp_processor_id:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c27fee73a2cb..05c1b6656824 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6137,6 +6137,12 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    map->map_type != BPF_MAP_TYPE_BLOOM_FILTER)
 			goto error;
 		break;
+	case BPF_FUNC_map_lookup_percpu_elem:
+		if (map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY &&
+		    map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
+		    map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH)
+			goto error;
+		break;
 	case BPF_FUNC_sk_storage_get:
 	case BPF_FUNC_sk_storage_delete:
 		if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
@@ -6750,7 +6756,8 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	    func_id != BPF_FUNC_map_pop_elem &&
 	    func_id != BPF_FUNC_map_peek_elem &&
 	    func_id != BPF_FUNC_for_each_map_elem &&
-	    func_id != BPF_FUNC_redirect_map)
+	    func_id != BPF_FUNC_redirect_map &&
+	    func_id != BPF_FUNC_map_lookup_percpu_elem)
 		return 0;
 
 	if (map == NULL) {
@@ -13810,7 +13817,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		     insn->imm == BPF_FUNC_map_pop_elem    ||
 		     insn->imm == BPF_FUNC_map_peek_elem   ||
 		     insn->imm == BPF_FUNC_redirect_map    ||
-		     insn->imm == BPF_FUNC_for_each_map_elem)) {
+		     insn->imm == BPF_FUNC_for_each_map_elem ||
+		     insn->imm == BPF_FUNC_map_lookup_percpu_elem)) {
 			aux = &env->insn_aux_data[i + delta];
 			if (bpf_map_ptr_poisoned(aux))
 				goto patch_call_imm;
@@ -13859,6 +13867,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 					      bpf_callback_t callback_fn,
 					      void *callback_ctx,
 					      u64 flags))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_lookup_percpu_elem,
+				     (void *(*)(struct bpf_map *map, void *key, u32 cpu))NULL));
 
 patch_map_ops_generic:
 			switch (insn->imm) {
@@ -13886,6 +13896,9 @@ patch_map_ops_generic:
 			case BPF_FUNC_for_each_map_elem:
 				insn->imm = BPF_CALL_IMM(ops->map_for_each_callback);
 				continue;
+			case BPF_FUNC_map_lookup_percpu_elem:
+				insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem);
+				continue;
 			}
 
 			goto patch_call_imm;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2eaac094caf8..7141ca8a1c2d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1197,6 +1197,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_map_pop_elem_proto;
 	case BPF_FUNC_map_peek_elem:
 		return &bpf_map_peek_elem_proto;
+	case BPF_FUNC_map_lookup_percpu_elem:
+		return &bpf_map_lookup_percpu_elem_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bc7f89948f54..0210f85131b3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5164,6 +5164,14 @@ union bpf_attr {
  *		if not NULL, is a reference which must be released using its
  *		corresponding release function, or moved into a BPF map before
  *		program exit.
+ *
+ * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu)
+ * 	Description
+ * 		Perform a lookup in *percpu map* for an entry associated to
+ * 		*key* on *cpu*.
+ * 	Return
+ * 		Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * 		was found or *cpu* is invalid.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5361,6 +5369,7 @@ union bpf_attr {
 	FN(skb_set_tstamp),		\
 	FN(ima_file_hash),		\
 	FN(kptr_xchg),			\
+	FN(map_lookup_percpu_elem),     \
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 43213daed6d6cb60e8cf69058a6db8648a556d9d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 10 May 2022 19:53:01 -0700
Subject: fortify: Provide a memcpy trap door for sharp corners

As we continue to narrow the scope of what the FORTIFY memcpy() will
accept and build alternative APIs that give the compiler appropriate
visibility into more complex memcpy scenarios, there is a need for
"unfortified" memcpy use in rare cases where combinations of compiler
behaviors, source code layout, etc, result in cases where the stricter
memcpy checks need to be bypassed until appropriate solutions can be
developed (i.e. fix compiler bugs, code refactoring, new API, etc). The
intention is for this to be used only if there's no other reasonable
solution, for its use to include a justification that can be used
to assess future solutions, and for it to be temporary.

Example usage included, based on analysis and discussion from:
https://lore.kernel.org/netdev/CANn89iLS_2cshtuXPyNUGDPaic=sJiYfvTb_wNLgWrZRyBxZ_g@mail.gmail.com

Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Tariq Toukan <tariqt@nvidia.com>
Cc: Saeed Mahameed <saeedm@nvidia.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: netdev@vger.kernel.org
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220511025301.3636666-1-keescook@chromium.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c |  8 +++++++-
 include/linux/fortify-string.h                  | 16 ++++++++++++++++
 include/linux/string.h                          |  4 ++++
 3 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 2dc48406cd08..5855d8f9c509 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -386,7 +386,13 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			stats->added_vlan_packets++;
 		} else {
 			eseg->inline_hdr.sz |= cpu_to_be16(attr->ihs);
-			memcpy(eseg->inline_hdr.start, skb->data, attr->ihs);
+			unsafe_memcpy(eseg->inline_hdr.start, skb->data, attr->ihs,
+				/* This copy has been bounds-checked earlier in
+				 * mlx5i_sq_calc_wqe_attr() and intentionally
+				 * crosses a flex array boundary. Since it is
+				 * performance sensitive, splitting the copy is
+				 * undesirable.
+				 */);
 		}
 		dseg += wqe_attr->ds_cnt_inl;
 	} else if (skb_vlan_tag_present(skb)) {
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 295637a66c46..3b401fa0f374 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -52,6 +52,22 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
 #define __underlying_strncpy	__builtin_strncpy
 #endif
 
+/**
+ * unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking
+ *
+ * @dst: Destination memory address to write to
+ * @src: Source memory address to read from
+ * @bytes: How many bytes to write to @dst from @src
+ * @justification: Free-form text or comment describing why the use is needed
+ *
+ * This should be used for corner cases where the compiler cannot do the
+ * right thing, or during transitions between APIs, etc. It should be used
+ * very rarely, and includes a place for justification detailing where bounds
+ * checking has happened, and why existing solutions cannot be employed.
+ */
+#define unsafe_memcpy(dst, src, bytes, justification)		\
+	__underlying_memcpy(dst, src, bytes)
+
 /*
  * Clang's use of __builtin_object_size() within inlines needs hinting via
  * __pass_object_size(). The preference is to only ever use type 1 (member
diff --git a/include/linux/string.h b/include/linux/string.h
index b6572aeca2f5..61ec7e4f6311 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -252,6 +252,10 @@ static inline const char *kbasename(const char *path)
 #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
 #include <linux/fortify-string.h>
 #endif
+#ifndef unsafe_memcpy
+#define unsafe_memcpy(dst, src, bytes, justification)		\
+	memcpy(dst, src, bytes)
+#endif
 
 void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count,
 		    int pad);
-- 
cgit v1.2.3


From a44623d9279086c89f631201d993aa332f7c9e66 Mon Sep 17 00:00:00 2001
From: Kishon Vijay Abraham I <kishon@ti.com>
Date: Tue, 10 May 2022 14:46:29 +0530
Subject: usb: core: hcd: Add support for deferring roothub registration

It has been observed with certain PCIe USB cards (like Inateck connected
to AM64 EVM or J7200 EVM) that as soon as the primary roothub is
registered, port status change is handled even before xHC is running
leading to cold plug USB devices not detected. For such cases, registering
both the root hubs along with the second HCD is required. Add support for
deferring roothub registration in usb_add_hcd(), so that both primary and
secondary roothubs are registered along with the second HCD.

This patch has been added and reverted earier as it triggered a race
in usb device enumeration.
That race is now fixed in 5.16-rc3, and in stable back to 5.4
commit 6cca13de26ee ("usb: hub: Fix locking issues with address0_mutex")
commit 6ae6dc22d2d1 ("usb: hub: Fix usb enumeration issue due to address0
race")

CC: stable@vger.kernel.org # 5.4+
Suggested-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Tested-by: Chris Chiu <chris.chiu@canonical.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Link: https://lore.kernel.org/r/20220510091630.16564-2-kishon@ti.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c  | 29 +++++++++++++++++++++++------
 include/linux/usb/hcd.h |  2 ++
 2 files changed, 25 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index d9712c2602af..06eea8848ccc 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2816,6 +2816,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 {
 	int retval;
 	struct usb_device *rhdev;
+	struct usb_hcd *shared_hcd;
 
 	if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) {
 		hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev);
@@ -2976,13 +2977,26 @@ int usb_add_hcd(struct usb_hcd *hcd,
 		goto err_hcd_driver_start;
 	}
 
+	/* starting here, usbcore will pay attention to the shared HCD roothub */
+	shared_hcd = hcd->shared_hcd;
+	if (!usb_hcd_is_primary_hcd(hcd) && shared_hcd && HCD_DEFER_RH_REGISTER(shared_hcd)) {
+		retval = register_root_hub(shared_hcd);
+		if (retval != 0)
+			goto err_register_root_hub;
+
+		if (shared_hcd->uses_new_polling && HCD_POLL_RH(shared_hcd))
+			usb_hcd_poll_rh_status(shared_hcd);
+	}
+
 	/* starting here, usbcore will pay attention to this root hub */
-	retval = register_root_hub(hcd);
-	if (retval != 0)
-		goto err_register_root_hub;
+	if (!HCD_DEFER_RH_REGISTER(hcd)) {
+		retval = register_root_hub(hcd);
+		if (retval != 0)
+			goto err_register_root_hub;
 
-	if (hcd->uses_new_polling && HCD_POLL_RH(hcd))
-		usb_hcd_poll_rh_status(hcd);
+		if (hcd->uses_new_polling && HCD_POLL_RH(hcd))
+			usb_hcd_poll_rh_status(hcd);
+	}
 
 	return retval;
 
@@ -3020,6 +3034,7 @@ EXPORT_SYMBOL_GPL(usb_add_hcd);
 void usb_remove_hcd(struct usb_hcd *hcd)
 {
 	struct usb_device *rhdev = hcd->self.root_hub;
+	bool rh_registered;
 
 	dev_info(hcd->self.controller, "remove, state %x\n", hcd->state);
 
@@ -3030,6 +3045,7 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 
 	dev_dbg(hcd->self.controller, "roothub graceful disconnect\n");
 	spin_lock_irq (&hcd_root_hub_lock);
+	rh_registered = hcd->rh_registered;
 	hcd->rh_registered = 0;
 	spin_unlock_irq (&hcd_root_hub_lock);
 
@@ -3039,7 +3055,8 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	cancel_work_sync(&hcd->died_work);
 
 	mutex_lock(&usb_bus_idr_lock);
-	usb_disconnect(&rhdev);		/* Sets rhdev to NULL */
+	if (rh_registered)
+		usb_disconnect(&rhdev);		/* Sets rhdev to NULL */
 	mutex_unlock(&usb_bus_idr_lock);
 
 	/*
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 548a028f2dab..2c1fc9212cf2 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -124,6 +124,7 @@ struct usb_hcd {
 #define HCD_FLAG_RH_RUNNING		5	/* root hub is running? */
 #define HCD_FLAG_DEAD			6	/* controller has died? */
 #define HCD_FLAG_INTF_AUTHORIZED	7	/* authorize interfaces? */
+#define HCD_FLAG_DEFER_RH_REGISTER	8	/* Defer roothub registration */
 
 	/* The flags can be tested using these macros; they are likely to
 	 * be slightly faster than test_bit().
@@ -134,6 +135,7 @@ struct usb_hcd {
 #define HCD_WAKEUP_PENDING(hcd)	((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING))
 #define HCD_RH_RUNNING(hcd)	((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING))
 #define HCD_DEAD(hcd)		((hcd)->flags & (1U << HCD_FLAG_DEAD))
+#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER))
 
 	/*
 	 * Specifies if interfaces are authorized by default
-- 
cgit v1.2.3


From 5ce7729f25c16d5045deff4c9577e6d565da2d8d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 12 May 2022 08:14:08 +0200
Subject: block: reorder the REQ_ flags

Keep the op-specific flag last so that they are clearly separate from
the generic flags.  Various recent commits just kept adding new flags
at the end.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220512061408.1826595-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 4968cb17b13b..30f9a5391fd5 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -408,16 +408,17 @@ enum req_flag_bits {
 	 * work item to avoid such priority inversions.
 	 */
 	__REQ_CGROUP_PUNT,
-
-	/* command specific flags for REQ_OP_WRITE_ZEROES: */
-	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
-
 	__REQ_POLLED,		/* caller polls for completion using bio_poll */
 	__REQ_ALLOC_CACHE,	/* allocate IO from cache if available */
+	__REQ_SWAP,		/* swap I/O */
+	__REQ_DRV,		/* for driver use */
+
+	/*
+	 * Command specific flags, keep last:
+	 */
+	/* for REQ_OP_WRITE_ZEROES: */
+	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
 
-	/* for driver use */
-	__REQ_DRV,
-	__REQ_SWAP,		/* swapping request. */
 	__REQ_NR_BITS,		/* stops here */
 };
 
-- 
cgit v1.2.3


From 5d2ae14276e698c76fa0c8ce870103f343b38263 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 11 May 2022 16:51:52 -0700
Subject: block: Fix the bio.bi_opf comment

Commit ef295ecf090d modified the Linux kernel such that the bottom bits
of the bi_opf member contain the operation instead of the topmost bits.
That commit did not update the comment next to bi_opf. Hence this patch.

From commit ef295ecf090d:
-#define bio_op(bio)    ((bio)->bi_opf >> BIO_OP_SHIFT)
+#define bio_op(bio)    ((bio)->bi_opf & REQ_OP_MASK)

Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Fixes: ef295ecf090d ("block: better op and flags encoding")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220511235152.1082246-1-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 30f9a5391fd5..40e815400611 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -246,9 +246,8 @@ typedef unsigned int blk_qc_t;
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct block_device	*bi_bdev;
-	unsigned int		bi_opf;		/* bottom bits req flags,
-						 * top bits REQ_OP. Use
-						 * accessors.
+	unsigned int		bi_opf;		/* bottom bits REQ_OP, top bits
+						 * req_flags.
 						 */
 	unsigned short		bi_flags;	/* BIO_* below */
 	unsigned short		bi_ioprio;
-- 
cgit v1.2.3


From 2760f5a415c3b86c6394738c6cff740c8b4ce664 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 6 May 2022 15:54:01 -0700
Subject: stop_machine: Add stop_core_cpuslocked() for per-core operations

Hardware core level testing features require near simultaneous execution
of WRMSR instructions on all threads of a core to initiate a test.

Provide a customized cut down version of stop_machine_cpuslocked() that
just operates on the threads of a single core.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20220506225410.1652287-4-tony.luck@intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/stop_machine.h | 16 ++++++++++++++++
 kernel/stop_machine.c        | 21 +++++++++++++++++++++
 2 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 46fb3ebdd16e..ea7a74ea7389 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -124,6 +124,22 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
  */
 int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
+/**
+ * stop_core_cpuslocked: - stop all threads on just one core
+ * @cpu: any cpu in the targeted core
+ * @fn: the function to run
+ * @data: the data ptr for @fn()
+ *
+ * Same as above, but instead of every CPU, only the logical CPUs of a
+ * single core are affected.
+ *
+ * Context: Must be called from within a cpus_read_lock() protected region.
+ *
+ * Return: 0 if all executions of @fn returned 0, any non zero return
+ * value if any returned non zero.
+ */
+int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data);
+
 int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
 #else	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index cbc30271ea4d..0887b3af609e 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -633,6 +633,27 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 }
 EXPORT_SYMBOL_GPL(stop_machine);
 
+#ifdef CONFIG_SCHED_SMT
+int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data)
+{
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+
+	struct multi_stop_data msdata = {
+		.fn = fn,
+		.data = data,
+		.num_threads = cpumask_weight(smt_mask),
+		.active_cpus = smt_mask,
+	};
+
+	lockdep_assert_cpus_held();
+
+	/* Set the initial state and stop all online cpus. */
+	set_state(&msdata, MULTI_STOP_PREPARE);
+	return stop_cpus(smt_mask, multi_cpu_stop, &msdata);
+}
+EXPORT_SYMBOL_GPL(stop_core_cpuslocked);
+#endif
+
 /**
  * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU
  * @fn: the function to run
-- 
cgit v1.2.3


From 75d6fe48a21a0ea1565228c12b9c16f3fb37b673 Mon Sep 17 00:00:00 2001
From: Siddh Raman Pant <siddhpant.gh@gmail.com>
Date: Thu, 12 May 2022 20:06:45 +0530
Subject: spi: Doc fix - Describe add_lock and dma_map_dev in spi_controller

This fixes the corresponding warnings during building the docs.

Signed-off-by: Siddh Raman Pant <siddhpant.gh@gmail.com>
Link: https://lore.kernel.org/r/4e6187a4-d0f8-4750-e407-e09cc1c91789@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 5f8c063ddff4..df70eb1a671e 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -347,6 +347,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  * @max_message_size: function that returns the max message size for
  *	a &spi_device; may be %NULL, so the default %SIZE_MAX will be used.
  * @io_mutex: mutex for physical bus access
+ * @add_lock: mutex to avoid adding devices to the same chipselect
  * @bus_lock_spinlock: spinlock for SPI bus locking
  * @bus_lock_mutex: mutex for exclusion of multiple callers
  * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use
@@ -361,6 +362,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  * @transfer: adds a message to the controller's transfer queue.
  * @cleanup: frees controller-specific state
  * @can_dma: determine whether this controller supports DMA
+ * @dma_map_dev: device which can be used for DMA mapping
  * @queued: whether this controller is providing an internal message queue
  * @kworker: pointer to thread struct for message pump
  * @pump_messages: work struct for scheduling work to the message pump
-- 
cgit v1.2.3


From 9824117dd964ecebf5d81990dbf21dfb56445049 Mon Sep 17 00:00:00 2001
From: Corey Minyard <cminyard@mvista.com>
Date: Tue, 12 Apr 2022 15:38:51 -0500
Subject: ipmi: Add an intializer for ipmi_smi_msg struct

There was a "type" element added to this structure, but some static
values were missed.  The default value will be zero, which is correct,
but create an initializer for the type and initialize the type properly
in the initializer to avoid future issues.

Reported-by: Joe Wiese <jwiese@rackspace.com>
Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 drivers/char/ipmi/ipmi_poweroff.c |  4 +---
 drivers/char/ipmi/ipmi_watchdog.c | 14 +++++---------
 include/linux/ipmi_smi.h          |  6 ++++++
 3 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c
index bc3a18daf97a..62e71c46ac5f 100644
--- a/drivers/char/ipmi/ipmi_poweroff.c
+++ b/drivers/char/ipmi/ipmi_poweroff.c
@@ -94,9 +94,7 @@ static void dummy_recv_free(struct ipmi_recv_msg *msg)
 {
 	atomic_dec(&dummy_count);
 }
-static struct ipmi_smi_msg halt_smi_msg = {
-	.done = dummy_smi_free
-};
+static struct ipmi_smi_msg halt_smi_msg = INIT_IPMI_SMI_MSG(dummy_smi_free);
 static struct ipmi_recv_msg halt_recv_msg = {
 	.done = dummy_recv_free
 };
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 0604abdd249a..4c1e9663ea47 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -354,9 +354,7 @@ static void msg_free_recv(struct ipmi_recv_msg *msg)
 			complete(&msg_wait);
 	}
 }
-static struct ipmi_smi_msg smi_msg = {
-	.done = msg_free_smi
-};
+static struct ipmi_smi_msg smi_msg = INIT_IPMI_SMI_MSG(msg_free_smi);
 static struct ipmi_recv_msg recv_msg = {
 	.done = msg_free_recv
 };
@@ -475,9 +473,8 @@ static void panic_recv_free(struct ipmi_recv_msg *msg)
 	atomic_dec(&panic_done_count);
 }
 
-static struct ipmi_smi_msg panic_halt_heartbeat_smi_msg = {
-	.done = panic_smi_free
-};
+static struct ipmi_smi_msg panic_halt_heartbeat_smi_msg =
+	INIT_IPMI_SMI_MSG(panic_smi_free);
 static struct ipmi_recv_msg panic_halt_heartbeat_recv_msg = {
 	.done = panic_recv_free
 };
@@ -516,9 +513,8 @@ static void panic_halt_ipmi_heartbeat(void)
 		atomic_sub(2, &panic_done_count);
 }
 
-static struct ipmi_smi_msg panic_halt_smi_msg = {
-	.done = panic_smi_free
-};
+static struct ipmi_smi_msg panic_halt_smi_msg =
+	INIT_IPMI_SMI_MSG(panic_smi_free);
 static struct ipmi_recv_msg panic_halt_recv_msg = {
 	.done = panic_recv_free
 };
diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h
index 9277d21c2690..5d69820d8b02 100644
--- a/include/linux/ipmi_smi.h
+++ b/include/linux/ipmi_smi.h
@@ -125,6 +125,12 @@ struct ipmi_smi_msg {
 	void (*done)(struct ipmi_smi_msg *msg);
 };
 
+#define INIT_IPMI_SMI_MSG(done_handler) \
+{						\
+	.done = done_handler,			\
+	.type = IPMI_SMI_MSG_TYPE_NORMAL	\
+}
+
 struct ipmi_smi_handlers {
 	struct module *owner;
 
-- 
cgit v1.2.3


From f214549d717310f795c20db9497db3938116399d Mon Sep 17 00:00:00 2001
From: Corey Minyard <cminyard@mvista.com>
Date: Tue, 12 Apr 2022 15:49:47 -0500
Subject: ipmi: Add an intializer for ipmi_recv_msg struct

Don't hand-initialize the struct here, create a macro to initialize it
so new fields added don't get forgotten in places.

Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 drivers/char/ipmi/ipmi_poweroff.c |  4 +---
 drivers/char/ipmi/ipmi_watchdog.c | 14 +++++---------
 include/linux/ipmi.h              |  5 +++++
 3 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c
index 62e71c46ac5f..163ec9749e55 100644
--- a/drivers/char/ipmi/ipmi_poweroff.c
+++ b/drivers/char/ipmi/ipmi_poweroff.c
@@ -95,9 +95,7 @@ static void dummy_recv_free(struct ipmi_recv_msg *msg)
 	atomic_dec(&dummy_count);
 }
 static struct ipmi_smi_msg halt_smi_msg = INIT_IPMI_SMI_MSG(dummy_smi_free);
-static struct ipmi_recv_msg halt_recv_msg = {
-	.done = dummy_recv_free
-};
+static struct ipmi_recv_msg halt_recv_msg = INIT_IPMI_RECV_MSG(dummy_recv_free);
 
 
 /*
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 4c1e9663ea47..5b4e677929ca 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -355,9 +355,7 @@ static void msg_free_recv(struct ipmi_recv_msg *msg)
 	}
 }
 static struct ipmi_smi_msg smi_msg = INIT_IPMI_SMI_MSG(msg_free_smi);
-static struct ipmi_recv_msg recv_msg = {
-	.done = msg_free_recv
-};
+static struct ipmi_recv_msg recv_msg = INIT_IPMI_RECV_MSG(msg_free_recv);
 
 static int __ipmi_set_timeout(struct ipmi_smi_msg  *smi_msg,
 			      struct ipmi_recv_msg *recv_msg,
@@ -475,9 +473,8 @@ static void panic_recv_free(struct ipmi_recv_msg *msg)
 
 static struct ipmi_smi_msg panic_halt_heartbeat_smi_msg =
 	INIT_IPMI_SMI_MSG(panic_smi_free);
-static struct ipmi_recv_msg panic_halt_heartbeat_recv_msg = {
-	.done = panic_recv_free
-};
+static struct ipmi_recv_msg panic_halt_heartbeat_recv_msg =
+	INIT_IPMI_RECV_MSG(panic_recv_free);
 
 static void panic_halt_ipmi_heartbeat(void)
 {
@@ -515,9 +512,8 @@ static void panic_halt_ipmi_heartbeat(void)
 
 static struct ipmi_smi_msg panic_halt_smi_msg =
 	INIT_IPMI_SMI_MSG(panic_smi_free);
-static struct ipmi_recv_msg panic_halt_recv_msg = {
-	.done = panic_recv_free
-};
+static struct ipmi_recv_msg panic_halt_recv_msg =
+	INIT_IPMI_RECV_MSG(panic_recv_free);
 
 /*
  * Special call, doesn't claim any locks.  This is only to be called
diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index 163831a087ef..a1c9c0d48ebf 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -72,6 +72,11 @@ struct ipmi_recv_msg {
 	unsigned char   msg_data[IPMI_MAX_MSG_LENGTH];
 };
 
+#define INIT_IPMI_RECV_MSG(done_handler) \
+{					\
+	.done = done_handler		\
+}
+
 /* Allocate and free the receive message. */
 void ipmi_free_recv_msg(struct ipmi_recv_msg *msg);
 
-- 
cgit v1.2.3


From 80140a81f7f833998d732102eea0fea230b88067 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 27 Apr 2022 11:03:21 +0200
Subject: module.h: simplify MODULE_IMPORT_NS

In commit ca321ec74322 ("module.h: allow #define strings to work with
MODULE_IMPORT_NS") I fixed up the MODULE_IMPORT_NS() macro to allow
defined strings to work with it.  Unfortunatly I did it in a two-stage
process, when it could just be done with the __stringify() macro as
pointed out by Masahiro Yamada.

Clean this up to only be one macro instead of two steps to achieve the
same end result.

Fixes: ca321ec74322 ("module.h: allow #define strings to work with MODULE_IMPORT_NS")
Reported-by: Masahiro Yamada <masahiroy@kernel.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Matthias Maennich <maennich@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/module.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 46d4d5f2516e..abd9fa916b7d 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -290,8 +290,7 @@ extern typeof(name) __mod_##type##__##name##_device_table		\
  * files require multiple MODULE_FIRMWARE() specifiers */
 #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware)
 
-#define _MODULE_IMPORT_NS(ns)	MODULE_INFO(import_ns, #ns)
-#define MODULE_IMPORT_NS(ns)	_MODULE_IMPORT_NS(ns)
+#define MODULE_IMPORT_NS(ns)	MODULE_INFO(import_ns, __stringify(ns))
 
 struct notifier_block;
 
-- 
cgit v1.2.3


From 0df65743537dd6e1c8b0924714f14dc367cba2be Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 11 May 2022 10:23:05 -0700
Subject: skbuff: replace a BUG_ON() with the new DEBUG_NET_WARN_ON_ONCE()

Very few drivers actually have Kconfig knobs for adding
-DDEBUG. 8 according to a quick grep, while there are
93 users of skb_checksum_none_assert(). Switch to the
new DEBUG_NET_WARN_ON_ONCE() to catch bad skbs.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20220511172305.1382810-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b91d225fdc13..9d82a8b6c8f1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -5048,9 +5048,7 @@ static inline void skb_forward_csum(struct sk_buff *skb)
  */
 static inline void skb_checksum_none_assert(const struct sk_buff *skb)
 {
-#ifdef DEBUG
-	BUG_ON(skb->ip_summed != CHECKSUM_NONE);
-#endif
+	DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE);
 }
 
 bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
-- 
cgit v1.2.3


From 58e4a2d27d3255e4e8c507fdc13734dccc9fc4c7 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 17 Dec 2021 09:28:46 +0300
Subject: extcon: Fix extcon_get_extcon_dev() error handling

The extcon_get_extcon_dev() function returns error pointers on error,
NULL when it's a -EPROBE_DEFER defer situation, and ERR_PTR(-ENODEV)
when the CONFIG_EXTCON option is disabled.  This is very complicated for
the callers to handle and a number of them had bugs that would lead to
an Oops.

In real life, there are two things which prevented crashes.  First,
error pointers would only be returned if there was bug in the caller
where they passed a NULL "extcon_name" and none of them do that.
Second, only two out of the eight drivers will build when CONFIG_EXTCON
is disabled.

The normal way to write this would be to return -EPROBE_DEFER directly
when appropriate and return NULL when CONFIG_EXTCON is disabled.  Then
the error handling is simple and just looks like:

	dev->edev = extcon_get_extcon_dev(acpi_dev_name(adev));
	if (IS_ERR(dev->edev))
		return PTR_ERR(dev->edev);

For the two drivers which can build with CONFIG_EXTCON disabled, then
extcon_get_extcon_dev() will now return NULL which is not treated as an
error and the probe will continue successfully.  Those two drivers are
"typec_fusb302" and "max8997-battery".  In the original code, the
typec_fusb302 driver had an 800ms hang in tcpm_get_current_limit() but
now that function is a no-op.  For the max8997-battery driver everything
should continue working as is.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/extcon/extcon-axp288.c         |  4 ++--
 drivers/extcon/extcon.c                |  4 +++-
 drivers/power/supply/axp288_charger.c  | 17 ++++++++++-------
 drivers/power/supply/charger-manager.c |  7 ++-----
 drivers/power/supply/max8997_charger.c |  8 ++++----
 drivers/usb/dwc3/drd.c                 |  9 ++-------
 drivers/usb/phy/phy-omap-otg.c         |  4 ++--
 drivers/usb/typec/tcpm/fusb302.c       |  4 ++--
 include/linux/extcon.h                 |  2 +-
 9 files changed, 28 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c
index 7c6d5857ff25..180be768c215 100644
--- a/drivers/extcon/extcon-axp288.c
+++ b/drivers/extcon/extcon-axp288.c
@@ -394,8 +394,8 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 		if (adev) {
 			info->id_extcon = extcon_get_extcon_dev(acpi_dev_name(adev));
 			put_device(&adev->dev);
-			if (!info->id_extcon)
-				return -EPROBE_DEFER;
+			if (IS_ERR(info->id_extcon))
+				return PTR_ERR(info->id_extcon);
 
 			dev_info(dev, "controlling USB role\n");
 		} else {
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index a09e704fd0fa..adb957470c65 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -851,6 +851,8 @@ EXPORT_SYMBOL_GPL(extcon_set_property_capability);
  * @extcon_name:	the extcon name provided with extcon_dev_register()
  *
  * Return the pointer of extcon device if success or ERR_PTR(err) if fail.
+ * NOTE: This function returns -EPROBE_DEFER so it may only be called from
+ * probe() functions.
  */
 struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name)
 {
@@ -864,7 +866,7 @@ struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name)
 		if (!strcmp(sd->name, extcon_name))
 			goto out;
 	}
-	sd = NULL;
+	sd = ERR_PTR(-EPROBE_DEFER);
 out:
 	mutex_unlock(&extcon_dev_list_lock);
 	return sd;
diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
index 19746e658a6a..15219ed43ce9 100644
--- a/drivers/power/supply/axp288_charger.c
+++ b/drivers/power/supply/axp288_charger.c
@@ -865,17 +865,20 @@ static int axp288_charger_probe(struct platform_device *pdev)
 	info->regmap_irqc = axp20x->regmap_irqc;
 
 	info->cable.edev = extcon_get_extcon_dev(AXP288_EXTCON_DEV_NAME);
-	if (info->cable.edev == NULL) {
-		dev_dbg(dev, "%s is not ready, probe deferred\n",
-			AXP288_EXTCON_DEV_NAME);
-		return -EPROBE_DEFER;
+	if (IS_ERR(info->cable.edev)) {
+		dev_err_probe(dev, PTR_ERR(info->cable.edev),
+			      "extcon_get_extcon_dev(%s) failed\n",
+			      AXP288_EXTCON_DEV_NAME);
+		return PTR_ERR(info->cable.edev);
 	}
 
 	if (acpi_dev_present(USB_HOST_EXTCON_HID, NULL, -1)) {
 		info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_NAME);
-		if (info->otg.cable == NULL) {
-			dev_dbg(dev, "EXTCON_USB_HOST is not ready, probe deferred\n");
-			return -EPROBE_DEFER;
+		if (IS_ERR(info->otg.cable)) {
+			dev_err_probe(dev, PTR_ERR(info->otg.cable),
+				      "extcon_get_extcon_dev(%s) failed\n",
+				      USB_HOST_EXTCON_NAME);
+			return PTR_ERR(info->otg.cable);
 		}
 		dev_info(dev, "Using " USB_HOST_EXTCON_HID " extcon for usb-id\n");
 	}
diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c
index d67edb760c94..92db79400a6a 100644
--- a/drivers/power/supply/charger-manager.c
+++ b/drivers/power/supply/charger-manager.c
@@ -985,13 +985,10 @@ static int charger_extcon_init(struct charger_manager *cm,
 	cable->nb.notifier_call = charger_extcon_notifier;
 
 	cable->extcon_dev = extcon_get_extcon_dev(cable->extcon_name);
-	if (IS_ERR_OR_NULL(cable->extcon_dev)) {
+	if (IS_ERR(cable->extcon_dev)) {
 		pr_err("Cannot find extcon_dev for %s (cable: %s)\n",
 			cable->extcon_name, cable->name);
-		if (cable->extcon_dev == NULL)
-			return -EPROBE_DEFER;
-		else
-			return PTR_ERR(cable->extcon_dev);
+		return PTR_ERR(cable->extcon_dev);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(extcon_mapping); i++) {
diff --git a/drivers/power/supply/max8997_charger.c b/drivers/power/supply/max8997_charger.c
index 127c73b0b3bd..1ec3535a257d 100644
--- a/drivers/power/supply/max8997_charger.c
+++ b/drivers/power/supply/max8997_charger.c
@@ -242,10 +242,10 @@ static int max8997_battery_probe(struct platform_device *pdev)
 		dev_info(&pdev->dev, "couldn't get charger regulator\n");
 	}
 	charger->edev = extcon_get_extcon_dev("max8997-muic");
-	if (IS_ERR_OR_NULL(charger->edev)) {
-		if (!charger->edev)
-			return -EPROBE_DEFER;
-		dev_info(charger->dev, "couldn't get extcon device\n");
+	if (IS_ERR(charger->edev)) {
+		dev_err_probe(charger->dev, PTR_ERR(charger->edev),
+			      "couldn't get extcon device: max8997-muic\n");
+		return PTR_ERR(charger->edev);
 	}
 
 	if (!IS_ERR(charger->reg) && !IS_ERR_OR_NULL(charger->edev)) {
diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index 8cad9e7d3368..4982edd13047 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -455,13 +455,8 @@ static struct extcon_dev *dwc3_get_extcon(struct dwc3 *dwc)
 	 * This device property is for kernel internal use only and
 	 * is expected to be set by the glue code.
 	 */
-	if (device_property_read_string(dev, "linux,extcon-name", &name) == 0) {
-		edev = extcon_get_extcon_dev(name);
-		if (!edev)
-			return ERR_PTR(-EPROBE_DEFER);
-
-		return edev;
-	}
+	if (device_property_read_string(dev, "linux,extcon-name", &name) == 0)
+		return extcon_get_extcon_dev(name);
 
 	/*
 	 * Try to get an extcon device from the USB PHY controller's "port"
diff --git a/drivers/usb/phy/phy-omap-otg.c b/drivers/usb/phy/phy-omap-otg.c
index ee0863c6553e..6e6ef8c0bc7e 100644
--- a/drivers/usb/phy/phy-omap-otg.c
+++ b/drivers/usb/phy/phy-omap-otg.c
@@ -95,8 +95,8 @@ static int omap_otg_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	extcon = extcon_get_extcon_dev(config->extcon);
-	if (!extcon)
-		return -EPROBE_DEFER;
+	if (IS_ERR(extcon))
+		return PTR_ERR(extcon);
 
 	otg_dev = devm_kzalloc(&pdev->dev, sizeof(*otg_dev), GFP_KERNEL);
 	if (!otg_dev)
diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c
index 72f9001b0792..96c55eaf3f80 100644
--- a/drivers/usb/typec/tcpm/fusb302.c
+++ b/drivers/usb/typec/tcpm/fusb302.c
@@ -1708,8 +1708,8 @@ static int fusb302_probe(struct i2c_client *client,
 	 */
 	if (device_property_read_string(dev, "linux,extcon-name", &name) == 0) {
 		chip->extcon = extcon_get_extcon_dev(name);
-		if (!chip->extcon)
-			return -EPROBE_DEFER;
+		if (IS_ERR(chip->extcon))
+			return PTR_ERR(chip->extcon);
 	}
 
 	chip->vbus = devm_regulator_get(chip->dev, "vbus");
diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index 0c19010da77f..685401d94d39 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -296,7 +296,7 @@ static inline void devm_extcon_unregister_notifier_all(struct device *dev,
 
 static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name)
 {
-	return ERR_PTR(-ENODEV);
+	return NULL;
 }
 
 static inline struct extcon_dev *extcon_find_edev_by_node(struct device_node *node)
-- 
cgit v1.2.3


From 59fba9eed5a736caa257df4738c57ff72492365f Mon Sep 17 00:00:00 2001
From: Yunfei Dong <yunfei.dong@mediatek.com>
Date: Thu, 12 May 2022 04:19:47 +0200
Subject: media: mediatek: vcodec: support stateless H.264 decoding for mt8192
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adds h264 lat and core architecture driver for mt8192,
and the decode mode is frame based for stateless decoder.

Signed-off-by: Yunfei Dong <yunfei.dong@mediatek.com>
Tested-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/platform/mediatek/vcodec/Makefile    |   1 +
 .../mediatek/vcodec/vdec/vdec_h264_req_multi_if.c  | 626 +++++++++++++++++++++
 .../media/platform/mediatek/vcodec/vdec_drv_if.c   |   9 +-
 .../media/platform/mediatek/vcodec/vdec_drv_if.h   |   1 +
 .../media/platform/mediatek/vcodec/vdec_vpu_if.h   |   2 +
 include/linux/remoteproc/mtk_scp.h                 |   2 +
 6 files changed, 640 insertions(+), 1 deletion(-)
 create mode 100644 drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c

(limited to 'include/linux')

diff --git a/drivers/media/platform/mediatek/vcodec/Makefile b/drivers/media/platform/mediatek/vcodec/Makefile
index 3f41d748eee5..22edb1c86598 100644
--- a/drivers/media/platform/mediatek/vcodec/Makefile
+++ b/drivers/media/platform/mediatek/vcodec/Makefile
@@ -10,6 +10,7 @@ mtk-vcodec-dec-y := vdec/vdec_h264_if.o \
 		vdec/vdec_vp9_if.o \
 		vdec/vdec_h264_req_if.o \
 		vdec/vdec_h264_req_common.o \
+		vdec/vdec_h264_req_multi_if.o \
 		mtk_vcodec_dec_drv.o \
 		vdec_drv_if.o \
 		vdec_vpu_if.o \
diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c
new file mode 100644
index 000000000000..a96f203b5d54
--- /dev/null
+++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 MediaTek Inc.
+ * Author: Yunfei Dong <yunfei.dong@mediatek.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <media/v4l2-h264.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "../mtk_vcodec_util.h"
+#include "../mtk_vcodec_dec.h"
+#include "../mtk_vcodec_intr.h"
+#include "../vdec_drv_base.h"
+#include "../vdec_drv_if.h"
+#include "../vdec_vpu_if.h"
+#include "vdec_h264_req_common.h"
+
+/**
+ * enum vdec_h264_core_dec_err_type  - core decode error type
+ *
+ * @TRANS_BUFFER_FULL: trans buffer is full
+ * @SLICE_HEADER_FULL: slice header buffer is full
+ */
+enum vdec_h264_core_dec_err_type {
+	TRANS_BUFFER_FULL = 1,
+	SLICE_HEADER_FULL,
+};
+
+/**
+ * struct vdec_h264_slice_lat_dec_param  - parameters for decode current frame
+ *
+ * @sps:		h264 sps syntax parameters
+ * @pps:		h264 pps syntax parameters
+ * @slice_header:	h264 slice header syntax parameters
+ * @scaling_matrix:	h264 scaling list parameters
+ * @decode_params:	decoder parameters of each frame used for hardware decode
+ * @h264_dpb_info:	dpb reference list
+ */
+struct vdec_h264_slice_lat_dec_param {
+	struct mtk_h264_sps_param sps;
+	struct mtk_h264_pps_param pps;
+	struct mtk_h264_slice_hd_param slice_header;
+	struct slice_api_h264_scaling_matrix scaling_matrix;
+	struct slice_api_h264_decode_param decode_params;
+	struct mtk_h264_dpb_info h264_dpb_info[V4L2_H264_NUM_DPB_ENTRIES];
+};
+
+/**
+ * struct vdec_h264_slice_info - decode information
+ *
+ * @nal_info:		nal info of current picture
+ * @timeout:		Decode timeout: 1 timeout, 0 no timeount
+ * @bs_buf_size:	bitstream size
+ * @bs_buf_addr:	bitstream buffer dma address
+ * @y_fb_dma:		Y frame buffer dma address
+ * @c_fb_dma:		C frame buffer dma address
+ * @vdec_fb_va:	VDEC frame buffer struct virtual address
+ * @crc:		Used to check whether hardware's status is right
+ */
+struct vdec_h264_slice_info {
+	u16 nal_info;
+	u16 timeout;
+	u32 bs_buf_size;
+	u64 bs_buf_addr;
+	u64 y_fb_dma;
+	u64 c_fb_dma;
+	u64 vdec_fb_va;
+	u32 crc[8];
+};
+
+/**
+ * struct vdec_h264_slice_vsi - shared memory for decode information exchange
+ *        between SCP and Host.
+ *
+ * @wdma_err_addr:		wdma error dma address
+ * @wdma_start_addr:		wdma start dma address
+ * @wdma_end_addr:		wdma end dma address
+ * @slice_bc_start_addr:	slice bc start dma address
+ * @slice_bc_end_addr:		slice bc end dma address
+ * @row_info_start_addr:	row info start dma address
+ * @row_info_end_addr:		row info end dma address
+ * @trans_start:		trans start dma address
+ * @trans_end:			trans end dma address
+ * @wdma_end_addr_offset:	wdma end address offset
+ *
+ * @mv_buf_dma:		HW working motion vector buffer
+ *				dma address (AP-W, VPU-R)
+ * @dec:			decode information (AP-R, VPU-W)
+ * @h264_slice_params:		decode parameters for hw used
+ */
+struct vdec_h264_slice_vsi {
+	/* LAT dec addr */
+	u64 wdma_err_addr;
+	u64 wdma_start_addr;
+	u64 wdma_end_addr;
+	u64 slice_bc_start_addr;
+	u64 slice_bc_end_addr;
+	u64 row_info_start_addr;
+	u64 row_info_end_addr;
+	u64 trans_start;
+	u64 trans_end;
+	u64 wdma_end_addr_offset;
+
+	u64 mv_buf_dma[H264_MAX_MV_NUM];
+	struct vdec_h264_slice_info dec;
+	struct vdec_h264_slice_lat_dec_param h264_slice_params;
+};
+
+/**
+ * struct vdec_h264_slice_share_info - shared information used to exchange
+ *                                     message between lat and core
+ *
+ * @sps:		sequence header information from user space
+ * @dec_params:	decoder params from user space
+ * @h264_slice_params:	decoder params used for hardware
+ * @trans_start:	trans start dma address
+ * @trans_end:		trans end dma address
+ * @nal_info:		nal info of current picture
+ */
+struct vdec_h264_slice_share_info {
+	struct v4l2_ctrl_h264_sps sps;
+	struct v4l2_ctrl_h264_decode_params dec_params;
+	struct vdec_h264_slice_lat_dec_param h264_slice_params;
+	u64 trans_start;
+	u64 trans_end;
+	u16 nal_info;
+};
+
+/**
+ * struct vdec_h264_slice_inst - h264 decoder instance
+ *
+ * @slice_dec_num:	how many picture be decoded
+ * @ctx:		point to mtk_vcodec_ctx
+ * @pred_buf:		HW working predication buffer
+ * @mv_buf:		HW working motion vector buffer
+ * @vpu:		VPU instance
+ * @vsi:		vsi used for lat
+ * @vsi_core:		vsi used for core
+ *
+ * @resolution_changed:resolution changed
+ * @realloc_mv_buf:	reallocate mv buffer
+ * @cap_num_planes:	number of capture queue plane
+ *
+ * @dpb:		decoded picture buffer used to store reference
+ *			buffer information
+ *@is_field_bitstream:	is field bitstream
+ */
+struct vdec_h264_slice_inst {
+	unsigned int slice_dec_num;
+	struct mtk_vcodec_ctx *ctx;
+	struct mtk_vcodec_mem pred_buf;
+	struct mtk_vcodec_mem mv_buf[H264_MAX_MV_NUM];
+	struct vdec_vpu_inst vpu;
+	struct vdec_h264_slice_vsi *vsi;
+	struct vdec_h264_slice_vsi *vsi_core;
+
+	unsigned int resolution_changed;
+	unsigned int realloc_mv_buf;
+	unsigned int cap_num_planes;
+
+	struct v4l2_h264_dpb_entry dpb[16];
+	bool is_field_bitstream;
+};
+
+static int vdec_h264_slice_fill_decode_parameters(struct vdec_h264_slice_inst *inst,
+						  struct vdec_h264_slice_share_info *share_info)
+{
+	struct vdec_h264_slice_lat_dec_param *slice_param = &inst->vsi->h264_slice_params;
+	const struct v4l2_ctrl_h264_decode_params *dec_params;
+	const struct v4l2_ctrl_h264_scaling_matrix *src_matrix;
+	const struct v4l2_ctrl_h264_sps *sps;
+	const struct v4l2_ctrl_h264_pps *pps;
+
+	dec_params =
+		mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS);
+	if (IS_ERR(dec_params))
+		return PTR_ERR(dec_params);
+
+	src_matrix =
+		mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SCALING_MATRIX);
+	if (IS_ERR(src_matrix))
+		return PTR_ERR(src_matrix);
+
+	sps = mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SPS);
+	if (IS_ERR(sps))
+		return PTR_ERR(sps);
+
+	pps = mtk_vdec_h264_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_PPS);
+	if (IS_ERR(pps))
+		return PTR_ERR(pps);
+
+	if (dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC) {
+		mtk_vcodec_err(inst, "No support for H.264 field decoding.");
+		inst->is_field_bitstream = true;
+		return -EINVAL;
+	}
+
+	mtk_vdec_h264_copy_sps_params(&slice_param->sps, sps);
+	mtk_vdec_h264_copy_pps_params(&slice_param->pps, pps);
+	mtk_vdec_h264_copy_scaling_matrix(&slice_param->scaling_matrix, src_matrix);
+
+	memcpy(&share_info->sps, sps, sizeof(*sps));
+	memcpy(&share_info->dec_params, dec_params, sizeof(*dec_params));
+
+	return 0;
+}
+
+static void vdec_h264_slice_fill_decode_reflist(struct vdec_h264_slice_inst *inst,
+						struct vdec_h264_slice_lat_dec_param *slice_param,
+						struct vdec_h264_slice_share_info *share_info)
+{
+	struct v4l2_ctrl_h264_decode_params *dec_params = &share_info->dec_params;
+	struct v4l2_ctrl_h264_sps *sps = &share_info->sps;
+	struct v4l2_h264_reflist_builder reflist_builder;
+	u8 *p0_reflist = slice_param->decode_params.ref_pic_list_p0;
+	u8 *b0_reflist = slice_param->decode_params.ref_pic_list_b0;
+	u8 *b1_reflist = slice_param->decode_params.ref_pic_list_b1;
+
+	mtk_vdec_h264_update_dpb(dec_params, inst->dpb);
+
+	mtk_vdec_h264_copy_decode_params(&slice_param->decode_params, dec_params,
+					 inst->dpb);
+	mtk_vdec_h264_fill_dpb_info(inst->ctx, &slice_param->decode_params,
+				    slice_param->h264_dpb_info);
+
+	mtk_v4l2_debug(3, "cur poc = %d\n", dec_params->bottom_field_order_cnt);
+	/* Build the reference lists */
+	v4l2_h264_init_reflist_builder(&reflist_builder, dec_params, sps,
+				       inst->dpb);
+	v4l2_h264_build_p_ref_list(&reflist_builder, p0_reflist);
+	v4l2_h264_build_b_ref_lists(&reflist_builder, b0_reflist, b1_reflist);
+
+	/* Adapt the built lists to the firmware's expectations */
+	mtk_vdec_h264_fixup_ref_list(p0_reflist, reflist_builder.num_valid);
+	mtk_vdec_h264_fixup_ref_list(b0_reflist, reflist_builder.num_valid);
+	mtk_vdec_h264_fixup_ref_list(b1_reflist, reflist_builder.num_valid);
+}
+
+static int vdec_h264_slice_alloc_mv_buf(struct vdec_h264_slice_inst *inst,
+					struct vdec_pic_info *pic)
+{
+	unsigned int buf_sz = mtk_vdec_h264_get_mv_buf_size(pic->buf_w, pic->buf_h);
+	struct mtk_vcodec_mem *mem;
+	int i, err;
+
+	mtk_v4l2_debug(3, "size = 0x%x", buf_sz);
+	for (i = 0; i < H264_MAX_MV_NUM; i++) {
+		mem = &inst->mv_buf[i];
+		if (mem->va)
+			mtk_vcodec_mem_free(inst->ctx, mem);
+		mem->size = buf_sz;
+		err = mtk_vcodec_mem_alloc(inst->ctx, mem);
+		if (err) {
+			mtk_vcodec_err(inst, "failed to allocate mv buf");
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void vdec_h264_slice_free_mv_buf(struct vdec_h264_slice_inst *inst)
+{
+	int i;
+	struct mtk_vcodec_mem *mem;
+
+	for (i = 0; i < H264_MAX_MV_NUM; i++) {
+		mem = &inst->mv_buf[i];
+		if (mem->va)
+			mtk_vcodec_mem_free(inst->ctx, mem);
+	}
+}
+
+static void vdec_h264_slice_get_pic_info(struct vdec_h264_slice_inst *inst)
+{
+	struct mtk_vcodec_ctx *ctx = inst->ctx;
+	u32 data[3];
+
+	data[0] = ctx->picinfo.pic_w;
+	data[1] = ctx->picinfo.pic_h;
+	data[2] = ctx->capture_fourcc;
+	vpu_dec_get_param(&inst->vpu, data, 3, GET_PARAM_PIC_INFO);
+
+	ctx->picinfo.buf_w = ALIGN(ctx->picinfo.pic_w, VCODEC_DEC_ALIGNED_64);
+	ctx->picinfo.buf_h = ALIGN(ctx->picinfo.pic_h, VCODEC_DEC_ALIGNED_64);
+	ctx->picinfo.fb_sz[0] = inst->vpu.fb_sz[0];
+	ctx->picinfo.fb_sz[1] = inst->vpu.fb_sz[1];
+	inst->cap_num_planes =
+		ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes;
+
+	mtk_vcodec_debug(inst, "pic(%d, %d), buf(%d, %d)",
+			 ctx->picinfo.pic_w, ctx->picinfo.pic_h,
+			 ctx->picinfo.buf_w, ctx->picinfo.buf_h);
+	mtk_vcodec_debug(inst, "Y/C(%d, %d)", ctx->picinfo.fb_sz[0],
+			 ctx->picinfo.fb_sz[1]);
+
+	if (ctx->last_decoded_picinfo.pic_w != ctx->picinfo.pic_w ||
+	    ctx->last_decoded_picinfo.pic_h != ctx->picinfo.pic_h) {
+		inst->resolution_changed = true;
+		if (ctx->last_decoded_picinfo.buf_w != ctx->picinfo.buf_w ||
+		    ctx->last_decoded_picinfo.buf_h != ctx->picinfo.buf_h)
+			inst->realloc_mv_buf = true;
+
+		mtk_v4l2_debug(1, "resChg: (%d %d) : old(%d, %d) -> new(%d, %d)",
+			       inst->resolution_changed,
+			       inst->realloc_mv_buf,
+			       ctx->last_decoded_picinfo.pic_w,
+			       ctx->last_decoded_picinfo.pic_h,
+			       ctx->picinfo.pic_w, ctx->picinfo.pic_h);
+	}
+}
+
+static void vdec_h264_slice_get_crop_info(struct vdec_h264_slice_inst *inst,
+					  struct v4l2_rect *cr)
+{
+	cr->left = 0;
+	cr->top = 0;
+	cr->width = inst->ctx->picinfo.pic_w;
+	cr->height = inst->ctx->picinfo.pic_h;
+
+	mtk_vcodec_debug(inst, "l=%d, t=%d, w=%d, h=%d",
+			 cr->left, cr->top, cr->width, cr->height);
+}
+
+static int vdec_h264_slice_init(struct mtk_vcodec_ctx *ctx)
+{
+	struct vdec_h264_slice_inst *inst;
+	int err, vsi_size;
+
+	inst = kzalloc(sizeof(*inst), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	inst->ctx = ctx;
+
+	inst->vpu.id = SCP_IPI_VDEC_LAT;
+	inst->vpu.core_id = SCP_IPI_VDEC_CORE;
+	inst->vpu.ctx = ctx;
+	inst->vpu.codec_type = ctx->current_codec;
+	inst->vpu.capture_type = ctx->capture_fourcc;
+
+	err = vpu_dec_init(&inst->vpu);
+	if (err) {
+		mtk_vcodec_err(inst, "vdec_h264 init err=%d", err);
+		goto error_free_inst;
+	}
+
+	vsi_size = round_up(sizeof(struct vdec_h264_slice_vsi), VCODEC_DEC_ALIGNED_64);
+	inst->vsi = inst->vpu.vsi;
+	inst->vsi_core =
+		(struct vdec_h264_slice_vsi *)(((char *)inst->vpu.vsi) + vsi_size);
+	inst->resolution_changed = true;
+	inst->realloc_mv_buf = true;
+
+	mtk_vcodec_debug(inst, "lat struct size = %d,%d,%d,%d vsi: %d\n",
+			 (int)sizeof(struct mtk_h264_sps_param),
+			 (int)sizeof(struct mtk_h264_pps_param),
+			 (int)sizeof(struct vdec_h264_slice_lat_dec_param),
+			 (int)sizeof(struct mtk_h264_dpb_info),
+			 vsi_size);
+	mtk_vcodec_debug(inst, "lat H264 instance >> %p, codec_type = 0x%x",
+			 inst, inst->vpu.codec_type);
+
+	ctx->drv_handle = inst;
+	return 0;
+
+error_free_inst:
+	kfree(inst);
+	return err;
+}
+
+static void vdec_h264_slice_deinit(void *h_vdec)
+{
+	struct vdec_h264_slice_inst *inst = h_vdec;
+
+	mtk_vcodec_debug_enter(inst);
+
+	vpu_dec_deinit(&inst->vpu);
+	vdec_h264_slice_free_mv_buf(inst);
+	vdec_msg_queue_deinit(&inst->ctx->msg_queue, inst->ctx);
+
+	kfree(inst);
+}
+
+static int vdec_h264_slice_core_decode(struct vdec_lat_buf *lat_buf)
+{
+	struct vdec_fb *fb;
+	u64 vdec_fb_va;
+	u64 y_fb_dma, c_fb_dma;
+	int err, timeout, i;
+	struct mtk_vcodec_ctx *ctx = lat_buf->ctx;
+	struct vdec_h264_slice_inst *inst = ctx->drv_handle;
+	struct vb2_v4l2_buffer *vb2_v4l2;
+	struct vdec_h264_slice_share_info *share_info = lat_buf->private_data;
+	struct mtk_vcodec_mem *mem;
+	struct vdec_vpu_inst *vpu = &inst->vpu;
+
+	mtk_vcodec_debug(inst, "[h264-core] vdec_h264 core decode");
+	memcpy(&inst->vsi_core->h264_slice_params, &share_info->h264_slice_params,
+	       sizeof(share_info->h264_slice_params));
+
+	fb = ctx->dev->vdec_pdata->get_cap_buffer(ctx);
+	y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0;
+	vdec_fb_va = (unsigned long)fb;
+
+	if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 1)
+		c_fb_dma =
+			y_fb_dma + inst->ctx->picinfo.buf_w * inst->ctx->picinfo.buf_h;
+	else
+		c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0;
+
+	mtk_vcodec_debug(inst, "[h264-core] y/c addr = 0x%llx 0x%llx", y_fb_dma,
+			 c_fb_dma);
+
+	inst->vsi_core->dec.y_fb_dma = y_fb_dma;
+	inst->vsi_core->dec.c_fb_dma = c_fb_dma;
+	inst->vsi_core->dec.vdec_fb_va = vdec_fb_va;
+	inst->vsi_core->dec.nal_info = share_info->nal_info;
+	inst->vsi_core->wdma_start_addr =
+		lat_buf->ctx->msg_queue.wdma_addr.dma_addr;
+	inst->vsi_core->wdma_end_addr =
+		lat_buf->ctx->msg_queue.wdma_addr.dma_addr +
+		lat_buf->ctx->msg_queue.wdma_addr.size;
+	inst->vsi_core->wdma_err_addr = lat_buf->wdma_err_addr.dma_addr;
+	inst->vsi_core->slice_bc_start_addr = lat_buf->slice_bc_addr.dma_addr;
+	inst->vsi_core->slice_bc_end_addr = lat_buf->slice_bc_addr.dma_addr +
+		lat_buf->slice_bc_addr.size;
+	inst->vsi_core->trans_start = share_info->trans_start;
+	inst->vsi_core->trans_end = share_info->trans_end;
+	for (i = 0; i < H264_MAX_MV_NUM; i++) {
+		mem = &inst->mv_buf[i];
+		inst->vsi_core->mv_buf_dma[i] = mem->dma_addr;
+	}
+
+	vb2_v4l2 = v4l2_m2m_next_dst_buf(ctx->m2m_ctx);
+	v4l2_m2m_buf_copy_metadata(&lat_buf->ts_info, vb2_v4l2, true);
+
+	vdec_h264_slice_fill_decode_reflist(inst, &inst->vsi_core->h264_slice_params,
+					    share_info);
+
+	err = vpu_dec_core(vpu);
+	if (err) {
+		mtk_vcodec_err(inst, "core decode err=%d", err);
+		goto vdec_dec_end;
+	}
+
+	/* wait decoder done interrupt */
+	timeout = mtk_vcodec_wait_for_done_ctx(inst->ctx, MTK_INST_IRQ_RECEIVED,
+					       WAIT_INTR_TIMEOUT_MS, MTK_VDEC_CORE);
+	if (timeout)
+		mtk_vcodec_err(inst, "core decode timeout: pic_%d",
+			       ctx->decoded_frame_cnt);
+	inst->vsi_core->dec.timeout = !!timeout;
+
+	vpu_dec_core_end(vpu);
+	mtk_vcodec_debug(inst, "pic[%d] crc: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x",
+			 ctx->decoded_frame_cnt,
+			 inst->vsi_core->dec.crc[0], inst->vsi_core->dec.crc[1],
+			 inst->vsi_core->dec.crc[2], inst->vsi_core->dec.crc[3],
+			 inst->vsi_core->dec.crc[4], inst->vsi_core->dec.crc[5],
+			 inst->vsi_core->dec.crc[6], inst->vsi_core->dec.crc[7]);
+
+vdec_dec_end:
+	vdec_msg_queue_update_ube_rptr(&lat_buf->ctx->msg_queue, share_info->trans_end);
+	ctx->dev->vdec_pdata->cap_to_disp(ctx, !!err, lat_buf->src_buf_req);
+	mtk_vcodec_debug(inst, "core decode done err=%d", err);
+	ctx->decoded_frame_cnt++;
+	return 0;
+}
+
+static int vdec_h264_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
+				      struct vdec_fb *fb, bool *res_chg)
+{
+	struct vdec_h264_slice_inst *inst = h_vdec;
+	struct vdec_vpu_inst *vpu = &inst->vpu;
+	struct mtk_video_dec_buf *src_buf_info;
+	int nal_start_idx, err, timeout = 0, i;
+	unsigned int data[2];
+	struct vdec_lat_buf *lat_buf;
+	struct vdec_h264_slice_share_info *share_info;
+	unsigned char *buf;
+	struct mtk_vcodec_mem *mem;
+
+	if (vdec_msg_queue_init(&inst->ctx->msg_queue, inst->ctx,
+				vdec_h264_slice_core_decode,
+				sizeof(*share_info)))
+		return -ENOMEM;
+
+	/* bs NULL means flush decoder */
+	if (!bs) {
+		vdec_msg_queue_wait_lat_buf_full(&inst->ctx->msg_queue);
+		return vpu_dec_reset(vpu);
+	}
+
+	if (inst->is_field_bitstream)
+		return -EINVAL;
+
+	lat_buf = vdec_msg_queue_dqbuf(&inst->ctx->msg_queue.lat_ctx);
+	if (!lat_buf) {
+		mtk_vcodec_err(inst, "failed to get lat buffer");
+		return -EINVAL;
+	}
+	share_info = lat_buf->private_data;
+	src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer);
+
+	buf = (unsigned char *)bs->va;
+	nal_start_idx = mtk_vdec_h264_find_start_code(buf, bs->size);
+	if (nal_start_idx < 0) {
+		err = -EINVAL;
+		goto err_free_fb_out;
+	}
+
+	inst->vsi->dec.nal_info = buf[nal_start_idx];
+	inst->vsi->dec.bs_buf_addr = (u64)bs->dma_addr;
+	inst->vsi->dec.bs_buf_size = bs->size;
+
+	lat_buf->src_buf_req = src_buf_info->m2m_buf.vb.vb2_buf.req_obj.req;
+	v4l2_m2m_buf_copy_metadata(&src_buf_info->m2m_buf.vb, &lat_buf->ts_info, true);
+
+	err = vdec_h264_slice_fill_decode_parameters(inst, share_info);
+	if (err)
+		goto err_free_fb_out;
+
+	*res_chg = inst->resolution_changed;
+	if (inst->resolution_changed) {
+		mtk_vcodec_debug(inst, "- resolution changed -");
+		if (inst->realloc_mv_buf) {
+			err = vdec_h264_slice_alloc_mv_buf(inst, &inst->ctx->picinfo);
+			inst->realloc_mv_buf = false;
+			if (err)
+				goto err_free_fb_out;
+		}
+		inst->resolution_changed = false;
+	}
+	for (i = 0; i < H264_MAX_MV_NUM; i++) {
+		mem = &inst->mv_buf[i];
+		inst->vsi->mv_buf_dma[i] = mem->dma_addr;
+	}
+	inst->vsi->wdma_start_addr = lat_buf->ctx->msg_queue.wdma_addr.dma_addr;
+	inst->vsi->wdma_end_addr = lat_buf->ctx->msg_queue.wdma_addr.dma_addr +
+		lat_buf->ctx->msg_queue.wdma_addr.size;
+	inst->vsi->wdma_err_addr = lat_buf->wdma_err_addr.dma_addr;
+	inst->vsi->slice_bc_start_addr = lat_buf->slice_bc_addr.dma_addr;
+	inst->vsi->slice_bc_end_addr = lat_buf->slice_bc_addr.dma_addr +
+		lat_buf->slice_bc_addr.size;
+
+	inst->vsi->trans_end = inst->ctx->msg_queue.wdma_rptr_addr;
+	inst->vsi->trans_start = inst->ctx->msg_queue.wdma_wptr_addr;
+	mtk_vcodec_debug(inst, "lat:trans(0x%llx 0x%llx) err:0x%llx",
+			 inst->vsi->wdma_start_addr,
+			 inst->vsi->wdma_end_addr,
+			 inst->vsi->wdma_err_addr);
+
+	mtk_vcodec_debug(inst, "slice(0x%llx 0x%llx) rprt((0x%llx 0x%llx))",
+			 inst->vsi->slice_bc_start_addr,
+			 inst->vsi->slice_bc_end_addr,
+			 inst->vsi->trans_start,
+			 inst->vsi->trans_end);
+	err = vpu_dec_start(vpu, data, 2);
+	if (err) {
+		mtk_vcodec_debug(inst, "lat decode err: %d", err);
+		goto err_scp_decode;
+	}
+
+	/* wait decoder done interrupt */
+	timeout = mtk_vcodec_wait_for_done_ctx(inst->ctx, MTK_INST_IRQ_RECEIVED,
+					       WAIT_INTR_TIMEOUT_MS, MTK_VDEC_LAT0);
+	inst->vsi->dec.timeout = !!timeout;
+
+	err = vpu_dec_end(vpu);
+	if (err == SLICE_HEADER_FULL || timeout || err == TRANS_BUFFER_FULL) {
+		err = -EINVAL;
+		goto err_scp_decode;
+	}
+
+	share_info->trans_end = inst->ctx->msg_queue.wdma_addr.dma_addr +
+		inst->vsi->wdma_end_addr_offset;
+	share_info->trans_start = inst->ctx->msg_queue.wdma_wptr_addr;
+	share_info->nal_info = inst->vsi->dec.nal_info;
+	vdec_msg_queue_update_ube_wptr(&lat_buf->ctx->msg_queue, share_info->trans_end);
+
+	memcpy(&share_info->h264_slice_params, &inst->vsi->h264_slice_params,
+	       sizeof(share_info->h264_slice_params));
+	vdec_msg_queue_qbuf(&inst->ctx->dev->msg_queue_core_ctx, lat_buf);
+
+	inst->slice_dec_num++;
+	return 0;
+
+err_scp_decode:
+err_free_fb_out:
+	vdec_msg_queue_qbuf(&inst->ctx->msg_queue.lat_ctx, lat_buf);
+	mtk_vcodec_err(inst, "slice dec number: %d err: %d", inst->slice_dec_num, err);
+	return err;
+}
+
+static int vdec_h264_slice_get_param(void *h_vdec, enum vdec_get_param_type type,
+				     void *out)
+{
+	struct vdec_h264_slice_inst *inst = h_vdec;
+
+	switch (type) {
+	case GET_PARAM_PIC_INFO:
+		vdec_h264_slice_get_pic_info(inst);
+		break;
+	case GET_PARAM_DPB_SIZE:
+		*(unsigned int *)out = 6;
+		break;
+	case GET_PARAM_CROP_INFO:
+		vdec_h264_slice_get_crop_info(inst, out);
+		break;
+	default:
+		mtk_vcodec_err(inst, "invalid get parameter type=%d", type);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+const struct vdec_common_if vdec_h264_slice_multi_if = {
+	.init		= vdec_h264_slice_init,
+	.decode		= vdec_h264_slice_lat_decode,
+	.get_param	= vdec_h264_slice_get_param,
+	.deinit		= vdec_h264_slice_deinit,
+};
diff --git a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c
index c93dd0ea3537..75497c2e476f 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c
+++ b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c
@@ -16,11 +16,18 @@
 
 int vdec_if_init(struct mtk_vcodec_ctx *ctx, unsigned int fourcc)
 {
+	enum mtk_vdec_hw_arch hw_arch = ctx->dev->vdec_pdata->hw_arch;
 	int ret = 0;
 
 	switch (fourcc) {
 	case V4L2_PIX_FMT_H264_SLICE:
-		ctx->dec_if = &vdec_h264_slice_if;
+		if (!ctx->dev->vdec_pdata->is_subdev_supported) {
+			ctx->dec_if = &vdec_h264_slice_if;
+			ctx->hw_id = MTK_VDEC_CORE;
+		} else {
+			ctx->dec_if = &vdec_h264_slice_multi_if;
+			ctx->hw_id = IS_VDEC_LAT_ARCH(hw_arch) ? MTK_VDEC_LAT0 : MTK_VDEC_CORE;
+		}
 		break;
 	case V4L2_PIX_FMT_H264:
 		ctx->dec_if = &vdec_h264_if;
diff --git a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h
index d467e8af4a84..f00980ee5abf 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h
+++ b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h
@@ -56,6 +56,7 @@ struct vdec_fb_node {
 
 extern const struct vdec_common_if vdec_h264_if;
 extern const struct vdec_common_if vdec_h264_slice_if;
+extern const struct vdec_common_if vdec_h264_slice_multi_if;
 extern const struct vdec_common_if vdec_vp8_if;
 extern const struct vdec_common_if vdec_vp9_if;
 
diff --git a/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.h b/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.h
index fe6815d31e50..0436bba91457 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.h
+++ b/drivers/media/platform/mediatek/vcodec/vdec_vpu_if.h
@@ -28,6 +28,7 @@ struct mtk_vcodec_ctx;
  * @wq          : wait queue to wait VPU message ack
  * @handler     : ipi handler for each decoder
  * @codec_type     : use codec type to separate different codecs
+ * @capture_type:	used capture type to separate different capture format
  * @fb_sz  : frame buffer size of each plane
  */
 struct vdec_vpu_inst {
@@ -43,6 +44,7 @@ struct vdec_vpu_inst {
 	wait_queue_head_t wq;
 	mtk_vcodec_ipi_handler handler;
 	unsigned int codec_type;
+	unsigned int capture_type;
 	unsigned int fb_sz[2];
 };
 
diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h
index b47416f7aeb8..7c2b7cc9fe6c 100644
--- a/include/linux/remoteproc/mtk_scp.h
+++ b/include/linux/remoteproc/mtk_scp.h
@@ -41,6 +41,8 @@ enum scp_ipi_id {
 	SCP_IPI_ISP_FRAME,
 	SCP_IPI_FD_CMD,
 	SCP_IPI_CROS_HOST_CMD,
+	SCP_IPI_VDEC_LAT,
+	SCP_IPI_VDEC_CORE,
 	SCP_IPI_NS_SERVICE = 0xFF,
 	SCP_IPI_MAX = 0x100,
 };
-- 
cgit v1.2.3


From ea661ad6e1573d5b08c27444ff2ed403bf39ff66 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Tue, 10 May 2022 10:34:03 +0800
Subject: iommu/vt-d: Size Page Request Queue to avoid overflow condition

PRQ overflow may cause I/O throughput congestion, resulting in unnecessary
degradation of I/O performance. Appropriately increasing the length of PRQ
can greatly reduce the occurrence of PRQ overflow. The count of maximum
page requests that can be generated in parallel by a PCIe device is
statically defined in the Outstanding Page Request Capacity field of the
PCIe ATS configure space.

The new length of PRQ is calculated by summing up the value of Outstanding
Page Request Capacity register across all devices where Page Requests are
supported on the real PR-capable platform (Intel Sapphire Rapids). The
result is round to the nearest higher power of 2.

The PRQ length is also double sized as the VT-d IOMMU driver only updates
the Page Request Queue Head Register (PQH_REG) after processing the entire
queue.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220421113558.3504874-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20220510023407.2759143-5-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/intel-svm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index b3b125b332aa..207ef06ba3e1 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -9,7 +9,7 @@
 #define __INTEL_SVM_H__
 
 /* Page Request Queue depth */
-#define PRQ_ORDER	2
+#define PRQ_ORDER	4
 #define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
 #define PRQ_DEPTH	((0x1000 << PRQ_ORDER) >> 5)
 
-- 
cgit v1.2.3


From fc0051cb95909ab56bd8c929f24d48c9870c3e3a Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Tue, 10 May 2022 10:34:05 +0800
Subject: iommu/vt-d: Check domain force_snooping against attached devices

As domain->force_snooping only impacts the devices attached with the
domain, there's no need to check against all IOMMU units. On the other
hand, force_snooping could be set on a domain no matter whether it has
been attached or not, and once set it is an immutable flag. If no
device attached, the operation always succeeds. Then this empty domain
can be only attached to a device of which the IOMMU supports snoop
control.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220508123525.1973626-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20220510023407.2759143-7-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 53 ++++++++++++++++++++++++++++++++++++++++++---
 drivers/iommu/intel/pasid.c | 42 +++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/pasid.h |  2 ++
 include/linux/intel-iommu.h |  1 +
 4 files changed, 95 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 23985cb5c8ee..f366e8c49636 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2438,7 +2438,7 @@ static int domain_setup_first_level(struct intel_iommu *iommu,
 	if (level == 5)
 		flags |= PASID_FLAG_FL5LP;
 
-	if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED)
+	if (domain->force_snooping)
 		flags |= PASID_FLAG_PAGE_SNOOP;
 
 	return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
@@ -4410,7 +4410,7 @@ static int intel_iommu_map(struct iommu_domain *domain,
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= DMA_PTE_WRITE;
-	if (dmar_domain->force_snooping)
+	if (dmar_domain->set_pte_snp)
 		prot |= DMA_PTE_SNP;
 
 	max_addr = iova + size;
@@ -4533,13 +4533,60 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
+static bool domain_support_force_snooping(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	bool support = true;
+
+	assert_spin_locked(&device_domain_lock);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!ecap_sc_support(info->iommu->ecap)) {
+			support = false;
+			break;
+		}
+	}
+
+	return support;
+}
+
+static void domain_set_force_snooping(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+
+	assert_spin_locked(&device_domain_lock);
+
+	/*
+	 * Second level page table supports per-PTE snoop control. The
+	 * iommu_map() interface will handle this by setting SNP bit.
+	 */
+	if (!domain_use_first_level(domain)) {
+		domain->set_pte_snp = true;
+		return;
+	}
+
+	list_for_each_entry(info, &domain->devices, link)
+		intel_pasid_setup_page_snoop_control(info->iommu, info->dev,
+						     PASID_RID2PASID);
+}
+
 static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long flags;
 
-	if (!domain_update_iommu_snooping(NULL))
+	if (dmar_domain->force_snooping)
+		return true;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	if (!domain_support_force_snooping(dmar_domain)) {
+		spin_unlock_irqrestore(&device_domain_lock, flags);
 		return false;
+	}
+
+	domain_set_force_snooping(dmar_domain);
 	dmar_domain->force_snooping = true;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
 	return true;
 }
 
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index f8d215d85695..d19dd66a670c 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -762,3 +762,45 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 
 	return 0;
 }
+
+/*
+ * Set the page snoop control for a pasid entry which has been set up.
+ */
+void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
+					  struct device *dev, u32 pasid)
+{
+	struct pasid_entry *pte;
+	u16 did;
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte || !pasid_pte_is_present(pte))) {
+		spin_unlock(&iommu->lock);
+		return;
+	}
+
+	pasid_set_pgsnp(pte);
+	did = pasid_get_domain_id(pte);
+	spin_unlock(&iommu->lock);
+
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	/*
+	 * VT-d spec 3.4 table23 states guides for cache invalidation:
+	 *
+	 * - PASID-selective-within-Domain PASID-cache invalidation
+	 * - PASID-selective PASID-based IOTLB invalidation
+	 * - If (pasid is RID_PASID)
+	 *    - Global Device-TLB invalidation to affected functions
+	 *   Else
+	 *    - PASID-based Device-TLB invalidation (with S=1 and
+	 *      Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions
+	 */
+	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+
+	/* Device IOTLB doesn't need to be flushed in caching mode. */
+	if (!cap_caching_mode(iommu->cap))
+		devtlb_invalidation_with_pasid(iommu, dev, pasid);
+}
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index ab4408c824a5..583ea67fc783 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -123,4 +123,6 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 bool fault_ignore);
 int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
 void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
+void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
+					  struct device *dev, u32 pasid);
 #endif /* __INTEL_PASID_H */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 72e5d7900e71..4f29139bbfc3 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -540,6 +540,7 @@ struct dmar_domain {
 	u8 has_iotlb_device: 1;
 	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
 	u8 force_snooping : 1;		/* Create IOPTEs with snoop control */
+	u8 set_pte_snp:1;
 
 	struct list_head devices;	/* all devices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
-- 
cgit v1.2.3


From 4a18419f71cdf9155d2d2a6c79546f720978b990 Mon Sep 17 00:00:00 2001
From: Nadav Amit <namit@vmware.com>
Date: Mon, 9 May 2022 18:20:50 -0700
Subject: mm/mprotect: use mmu_gather

Patch series "mm/mprotect: avoid unnecessary TLB flushes", v6.

This patchset is intended to remove unnecessary TLB flushes during
mprotect() syscalls.  Once this patch-set make it through, similar and
further optimizations for MADV_COLD and userfaultfd would be possible.

Basically, there are 3 optimizations in this patch-set:

1. Use TLB batching infrastructure to batch flushes across VMAs and do
   better/fewer flushes.  This would also be handy for later userfaultfd
   enhancements.

2. Avoid unnecessary TLB flushes.  This optimization is the one that
   provides most of the performance benefits.  Unlike previous versions,
   we now only avoid flushes that would not result in spurious
   page-faults.

3. Avoiding TLB flushes on change_huge_pmd() that are only needed to
   prevent the A/D bits from changing.

Andrew asked for some benchmark numbers.  I do not have an easy
determinate macrobenchmark in which it is easy to show benefit.  I
therefore ran a microbenchmark: a loop that does the following on
anonymous memory, just as a sanity check to see that time is saved by
avoiding TLB flushes.  The loop goes:

	mprotect(p, PAGE_SIZE, PROT_READ)
	mprotect(p, PAGE_SIZE, PROT_READ|PROT_WRITE)
	*p = 0; // make the page writable

The test was run in KVM guest with 1 or 2 threads (the second thread was
busy-looping).  I measured the time (cycles) of each operation:

		1 thread		2 threads
		mmots	+patch		mmots	+patch
PROT_READ	3494	2725 (-22%)	8630	7788 (-10%)
PROT_READ|WRITE	3952	2724 (-31%)	9075	2865 (-68%)

[ mmots = v5.17-rc6-mmots-2022-03-06-20-38 ]

The exact numbers are really meaningless, but the benefit is clear.  There
are 2 interesting results though.

(1) PROT_READ is cheaper, while one can expect it not to be affected.
This is presumably due to TLB miss that is saved

(2) Without memory access (*p = 0), the speedup of the patch is even
greater.  In that scenario mprotect(PROT_READ) also avoids the TLB flush.
As a result both operations on the patched kernel take roughly ~1500
cycles (with either 1 or 2 threads), whereas on mmotm their cost is as
high as presented in the table.


This patch (of 3):

change_pXX_range() currently does not use mmu_gather, but instead
implements its own deferred TLB flushes scheme.  This both complicates the
code, as developers need to be aware of different invalidation schemes,
and prevents opportunities to avoid TLB flushes or perform them in finer
granularity.

The use of mmu_gather for modified PTEs has benefits in various scenarios
even if pages are not released.  For instance, if only a single page needs
to be flushed out of a range of many pages, only that page would be
flushed.  If a THP page is flushed, on x86 a single TLB invlpg instruction
can be used instead of 512 instructions (or a full TLB flush, which would
Linux would actually use by default).  mprotect() over multiple VMAs
requires a single flush.

Use mmu_gather in change_pXX_range().  As the pages are not released, only
record the flushed range using tlb_flush_pXX_range().

Handle THP similarly and get rid of flush_cache_range() which becomes
redundant since tlb_start_vma() calls it when needed.

Link: https://lkml.kernel.org/r/20220401180821.1986781-1-namit@vmware.com
Link: https://lkml.kernel.org/r/20220401180821.1986781-2-namit@vmware.com
Signed-off-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Nick Piggin <npiggin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/exec.c               |  6 +++-
 include/linux/huge_mm.h |  5 +--
 include/linux/mm.h      |  5 +--
 mm/huge_memory.c        | 10 ++++--
 mm/mempolicy.c          |  9 ++++-
 mm/mprotect.c           | 92 +++++++++++++++++++++++++++----------------------
 mm/userfaultfd.c        |  6 +++-
 7 files changed, 82 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index e3e55d5e0be1..14b4b3755580 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -758,6 +758,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	unsigned long stack_size;
 	unsigned long stack_expand;
 	unsigned long rlim_stack;
+	struct mmu_gather tlb;
 
 #ifdef CONFIG_STACK_GROWSUP
 	/* Limit stack size */
@@ -812,8 +813,11 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	vm_flags |= mm->def_flags;
 	vm_flags |= VM_STACK_INCOMPLETE_SETUP;
 
-	ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end,
+	tlb_gather_mmu(&tlb, mm);
+	ret = mprotect_fixup(&tlb, vma, &prev, vma->vm_start, vma->vm_end,
 			vm_flags);
+	tlb_finish_mmu(&tlb);
+
 	if (ret)
 		goto out_unlock;
 	BUG_ON(prev != vma);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 2999190adc22..9a26bd10e083 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -36,8 +36,9 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud,
 		 unsigned long addr);
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		   unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd);
-int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
-		    pgprot_t newprot, unsigned long cp_flags);
+int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
+		    unsigned long cp_flags);
 vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
 				   pgprot_t pgprot, bool write);
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5dc5005ccc9b..d63ba0e0e068 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1967,10 +1967,11 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 #define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
 					    MM_CP_UFFD_WP_RESOLVE)
 
-extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+extern unsigned long change_protection(struct mmu_gather *tlb,
+			      struct vm_area_struct *vma, unsigned long start,
 			      unsigned long end, pgprot_t newprot,
 			      unsigned long cp_flags);
-extern int mprotect_fixup(struct vm_area_struct *vma,
+extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			  struct vm_area_struct **pprev, unsigned long start,
 			  unsigned long end, unsigned long newflags);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 86eae6834db7..8db17c042aed 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1709,8 +1709,9 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
  *      or if prot_numa but THP migration is not supported
  *  - HPAGE_PMD_NR if protections changed and TLB flush necessary
  */
-int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, pgprot_t newprot, unsigned long cp_flags)
+int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
+		    unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
@@ -1721,6 +1722,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
+	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
+
 	if (prot_numa && !thp_migration_supported())
 		return 1;
 
@@ -1819,6 +1822,9 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	}
 	ret = HPAGE_PMD_NR;
 	set_pmd_at(mm, addr, pmd, entry);
+
+	tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE);
+
 	BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
 unlock:
 	spin_unlock(ptl);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0288ffaea064..3934476fb708 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -104,6 +104,7 @@
 #include <linux/swapops.h>
 
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 #include <linux/uaccess.h>
 
 #include "internal.h"
@@ -630,12 +631,18 @@ unlock:
 unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long addr, unsigned long end)
 {
+	struct mmu_gather tlb;
 	int nr_updated;
 
-	nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA);
+	tlb_gather_mmu(&tlb, vma->vm_mm);
+
+	nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE,
+				       MM_CP_PROT_NUMA);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 
+	tlb_finish_mmu(&tlb);
+
 	return nr_updated;
 }
 #else
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 56060acdabd3..420be0201118 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -33,12 +33,13 @@
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 
 #include "internal.h"
 
-static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		unsigned long cp_flags)
+static unsigned long change_pte_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
@@ -49,6 +50,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
+	tlb_change_page_size(tlb, PAGE_SIZE);
+
 	/*
 	 * Can be called with only the mmap_lock for reading by
 	 * prot_numa so we must check the pmd isn't constantly
@@ -149,6 +152,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				ptent = pte_mkwrite(ptent);
 			}
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
+			tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
 			pages++;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
@@ -234,9 +238,9 @@ static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
 	return 0;
 }
 
-static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
-		pud_t *pud, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_pmd_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pud_t *pud, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -276,8 +280,12 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			if (next - addr != HPAGE_PMD_SIZE) {
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
 			} else {
-				int nr_ptes = change_huge_pmd(vma, pmd, addr,
-							      newprot, cp_flags);
+				/*
+				 * change_huge_pmd() does not defer TLB flushes,
+				 * so no need to propagate the tlb argument.
+				 */
+				int nr_ptes = change_huge_pmd(tlb, vma, pmd,
+						addr, newprot, cp_flags);
 
 				if (nr_ptes) {
 					if (nr_ptes == HPAGE_PMD_NR) {
@@ -291,8 +299,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			}
 			/* fall through, the trans huge pmd just split */
 		}
-		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
-					      cp_flags);
+		this_pages = change_pte_range(tlb, vma, pmd, addr, next,
+					      newprot, cp_flags);
 		pages += this_pages;
 next:
 		cond_resched();
@@ -306,9 +314,9 @@ next:
 	return pages;
 }
 
-static inline unsigned long change_pud_range(struct vm_area_struct *vma,
-		p4d_t *p4d, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_pud_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -319,16 +327,16 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		pages += change_pmd_range(vma, pud, addr, next, newprot,
+		pages += change_pmd_range(tlb, vma, pud, addr, next, newprot,
 					  cp_flags);
 	} while (pud++, addr = next, addr != end);
 
 	return pages;
 }
 
-static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
-		pgd_t *pgd, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline unsigned long change_p4d_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	p4d_t *p4d;
 	unsigned long next;
@@ -339,44 +347,40 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 		next = p4d_addr_end(addr, end);
 		if (p4d_none_or_clear_bad(p4d))
 			continue;
-		pages += change_pud_range(vma, p4d, addr, next, newprot,
+		pages += change_pud_range(tlb, vma, p4d, addr, next, newprot,
 					  cp_flags);
 	} while (p4d++, addr = next, addr != end);
 
 	return pages;
 }
 
-static unsigned long change_protection_range(struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		unsigned long cp_flags)
+static unsigned long change_protection_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long start = addr;
 	unsigned long pages = 0;
 
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
-	flush_cache_range(vma, addr, end);
-	inc_tlb_flush_pending(mm);
+	tlb_start_vma(tlb, vma);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		pages += change_p4d_range(vma, pgd, addr, next, newprot,
+		pages += change_p4d_range(tlb, vma, pgd, addr, next, newprot,
 					  cp_flags);
 	} while (pgd++, addr = next, addr != end);
 
-	/* Only flush the TLB if we actually modified any entries: */
-	if (pages)
-		flush_tlb_range(vma, start, end);
-	dec_tlb_flush_pending(mm);
+	tlb_end_vma(tlb, vma);
 
 	return pages;
 }
 
-unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+unsigned long change_protection(struct mmu_gather *tlb,
+		       struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end, pgprot_t newprot,
 		       unsigned long cp_flags)
 {
@@ -387,7 +391,7 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else
-		pages = change_protection_range(vma, start, end, newprot,
+		pages = change_protection_range(tlb, vma, start, end, newprot,
 						cp_flags);
 
 	return pages;
@@ -421,8 +425,9 @@ static const struct mm_walk_ops prot_none_walk_ops = {
 };
 
 int
-mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
-	unsigned long start, unsigned long end, unsigned long newflags)
+mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma,
+	       struct vm_area_struct **pprev, unsigned long start,
+	       unsigned long end, unsigned long newflags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long oldflags = vma->vm_flags;
@@ -509,7 +514,7 @@ success:
 	dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
 	vma_set_page_prot(vma);
 
-	change_protection(vma, start, end, vma->vm_page_prot,
+	change_protection(tlb, vma, start, end, vma->vm_page_prot,
 			  dirty_accountable ? MM_CP_DIRTY_ACCT : 0);
 
 	/*
@@ -543,6 +548,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
 	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
 				(prot & PROT_READ);
+	struct mmu_gather tlb;
 
 	start = untagged_addr(start);
 
@@ -602,6 +608,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	else
 		prev = vma->vm_prev;
 
+	tlb_gather_mmu(&tlb, current->mm);
 	for (nstart = start ; ; ) {
 		unsigned long mask_off_old_flags;
 		unsigned long newflags;
@@ -628,18 +635,18 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
 		if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) {
 			error = -EACCES;
-			goto out;
+			break;
 		}
 
 		/* Allow architectures to sanity-check the new flags */
 		if (!arch_validate_flags(newflags)) {
 			error = -EINVAL;
-			goto out;
+			break;
 		}
 
 		error = security_file_mprotect(vma, reqprot, prot);
 		if (error)
-			goto out;
+			break;
 
 		tmp = vma->vm_end;
 		if (tmp > end)
@@ -648,27 +655,28 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		if (vma->vm_ops && vma->vm_ops->mprotect) {
 			error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags);
 			if (error)
-				goto out;
+				break;
 		}
 
-		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
+		error = mprotect_fixup(&tlb, vma, &prev, nstart, tmp, newflags);
 		if (error)
-			goto out;
+			break;
 
 		nstart = tmp;
 
 		if (nstart < prev->vm_end)
 			nstart = prev->vm_end;
 		if (nstart >= end)
-			goto out;
+			break;
 
 		vma = prev->vm_next;
 		if (!vma || vma->vm_start != nstart) {
 			error = -ENOMEM;
-			goto out;
+			break;
 		}
 		prot = reqprot;
 	}
+	tlb_finish_mmu(&tlb);
 out:
 	mmap_write_unlock(current->mm);
 	return error;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index dae25d985d15..9cdaed939203 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -16,6 +16,7 @@
 #include <linux/hugetlb.h>
 #include <linux/shmem_fs.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 #include "internal.h"
 
 static __always_inline
@@ -687,6 +688,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 			atomic_t *mmap_changing)
 {
 	struct vm_area_struct *dst_vma;
+	struct mmu_gather tlb;
 	pgprot_t newprot;
 	int err;
 
@@ -728,8 +730,10 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 	else
 		newprot = vm_get_page_prot(dst_vma->vm_flags);
 
-	change_protection(dst_vma, start, start + len, newprot,
+	tlb_gather_mmu(&tlb, dst_mm);
+	change_protection(&tlb, dst_vma, start, start + len, newprot,
 			  enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE);
+	tlb_finish_mmu(&tlb);
 
 	err = 0;
 out_unlock:
-- 
cgit v1.2.3


From 4f83145721f362c2f4d312edc4755269a2069488 Mon Sep 17 00:00:00 2001
From: Nadav Amit <namit@vmware.com>
Date: Mon, 9 May 2022 18:20:50 -0700
Subject: mm: avoid unnecessary flush on change_huge_pmd()

Calls to change_protection_range() on THP can trigger, at least on x86,
two TLB flushes for one page: one immediately, when pmdp_invalidate() is
called by change_huge_pmd(), and then another one later (that can be
batched) when change_protection_range() finishes.

The first TLB flush is only necessary to prevent the dirty bit (and with a
lesser importance the access bit) from changing while the PTE is modified.
However, this is not necessary as the x86 CPUs set the dirty-bit
atomically with an additional check that the PTE is (still) present.  One
caveat is Intel's Knights Landing that has a bug and does not do so.

Leverage this behavior to eliminate the unnecessary TLB flush in
change_huge_pmd().  Introduce a new arch specific pmdp_invalidate_ad()
that only invalidates the access and dirty bit from further changes.

Link: https://lkml.kernel.org/r/20220401180821.1986781-4-namit@vmware.com
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Nick Piggin <npiggin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/include/asm/pgtable.h |  5 +++++
 arch/x86/mm/pgtable.c          | 10 ++++++++++
 include/linux/pgtable.h        | 20 ++++++++++++++++++++
 mm/huge_memory.c               |  4 ++--
 mm/pgtable-generic.c           |  8 ++++++++
 5 files changed, 45 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1e09519af143..0821f87d495f 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1168,6 +1168,11 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 	}
 }
 #endif
+
+#define __HAVE_ARCH_PMDP_INVALIDATE_AD
+extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
+				unsigned long address, pmd_t *pmdp);
+
 /*
  * Page table pages are page-aligned.  The lower half of the top
  * level is used for userspace and the top half for the kernel.
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3481b35cb4ec..f16059e9a85e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -608,6 +608,16 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 
 	return young;
 }
+
+pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
+			 pmd_t *pmdp)
+{
+	/*
+	 * No flush is necessary. Once an invalid PTE is established, the PTE's
+	 * access and dirty bits cannot be updated.
+	 */
+	return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
+}
 #endif
 
 /**
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 53750224e176..530b1817b58c 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -570,6 +570,26 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
+
+/*
+ * pmdp_invalidate_ad() invalidates the PMD while changing a transparent
+ * hugepage mapping in the page tables. This function is similar to
+ * pmdp_invalidate(), but should only be used if the access and dirty bits would
+ * not be cleared by the software in the new PMD value. The function ensures
+ * that hardware changes of the access and dirty bits updates would not be lost.
+ *
+ * Doing so can allow in certain architectures to avoid a TLB flush in most
+ * cases. Yet, another TLB flush might be necessary later if the PMD update
+ * itself requires such flush (e.g., if protection was set to be stricter). Yet,
+ * even when a TLB flush is needed because of the update, the caller may be able
+ * to batch these TLB flushing operations, so fewer TLB flush operations are
+ * needed.
+ */
+extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
+				unsigned long address, pmd_t *pmdp);
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2befa9cfb46e..6f37f77eb48c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1801,10 +1801,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	 * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
 	 * which may break userspace.
 	 *
-	 * pmdp_invalidate() is required to make sure we don't miss
+	 * pmdp_invalidate_ad() is required to make sure we don't miss
 	 * dirty/young flags set by hardware.
 	 */
-	oldpmd = pmdp_invalidate(vma, addr, pmd);
+	oldpmd = pmdp_invalidate_ad(vma, addr, pmd);
 
 	entry = pmd_modify(oldpmd, newprot);
 	if (preserve_write)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 6523fda274e5..90ab721a12a8 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -201,6 +201,14 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 }
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
+pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
+			 pmd_t *pmdp)
+{
+	return pmdp_invalidate(vma, address, pmdp);
+}
+#endif
+
 #ifndef pmdp_collapse_flush
 pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
 			  pmd_t *pmdp)
-- 
cgit v1.2.3


From f38adfef7e6bfe681d6602b6668be31fe1310ed0 Mon Sep 17 00:00:00 2001
From: "Fabio M. De Francesco" <fmdefrancesco@gmail.com>
Date: Mon, 9 May 2022 18:20:51 -0700
Subject: mm/highmem: VM_BUG_ON() if offset + len > PAGE_SIZE

Add VM_BUG_ON() bounds checking to make sure that, if "offset + len>
PAGE_SIZE", memset() does not corrupt data in adjacent pages.

Mainly to match all the similar functions in highmem.h.

Link: https://lkml.kernel.org/r/20220426193020.8710-1-fmdefrancesco@gmail.com
Signed-off-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Peter Collingbourne <pcc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/highmem.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 39bb9b47fa9c..67720bfd6ade 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -358,6 +358,8 @@ static inline void memcpy_to_page(struct page *page, size_t offset,
 static inline void memzero_page(struct page *page, size_t offset, size_t len)
 {
 	char *addr = kmap_local_page(page);
+
+	VM_BUG_ON(offset + len > PAGE_SIZE);
 	memset(addr + offset, 0, len);
 	flush_dcache_page(page);
 	kunmap_local(addr);
-- 
cgit v1.2.3


From 152e56178ad72037bc6a2f08d4a608543bc67cdf Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Mon, 9 May 2022 18:20:51 -0700
Subject: mm/damon/core: add a function for damon_operations registration
 checks

Patch series "mm/damon: allow users know which monitoring ops are available".

DAMON users can configure it for vaious address spaces including virtual
address spaces and the physical address space by setting its monitoring
operations set with appropriate one for their purpose.  However, there is
no celan and simple way to know exactly which monitoring operations sets
are available on the currently running kernel.

This patchset adds functions for the purpose on DAMON's kernel API
('damon_is_registered_ops()') and sysfs interface ('avail_operations' file
under each context directory).


This patch (of 4):

To know if a specific 'damon_operations' is registered, users need to
check the kernel config or try 'damon_select_ops()' with the ops of the
question, and then see if it successes.  In the latter case, the user
should also revert the change.  To make the process simple and convenient,
this commit adds a function for checking if a specific 'damon_operations'
is registered or not.

Link: https://lkml.kernel.org/r/20220426203843.45238-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20220426203843.45238-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h |  1 +
 mm/damon/core.c       | 24 +++++++++++++++++++++---
 2 files changed, 22 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index f23cbfa4248d..73ff0e2d2a4d 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -509,6 +509,7 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
 int damon_set_schemes(struct damon_ctx *ctx,
 			struct damos **schemes, ssize_t nr_schemes);
 int damon_nr_running_ctxs(void);
+bool damon_is_registered_ops(enum damon_ops_id id);
 int damon_register_ops(struct damon_operations *ops);
 int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id);
 
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 5fe42e47c57b..997cf7b17779 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -30,7 +30,7 @@ static DEFINE_MUTEX(damon_ops_lock);
 static struct damon_operations damon_registered_ops[NR_DAMON_OPS];
 
 /* Should be called under damon_ops_lock with id smaller than NR_DAMON_OPS */
-static bool damon_registered_ops_id(enum damon_ops_id id)
+static bool __damon_is_registered_ops(enum damon_ops_id id)
 {
 	struct damon_operations empty_ops = {};
 
@@ -39,6 +39,24 @@ static bool damon_registered_ops_id(enum damon_ops_id id)
 	return true;
 }
 
+/**
+ * damon_is_registered_ops() - Check if a given damon_operations is registered.
+ * @id:	Id of the damon_operations to check if registered.
+ *
+ * Return: true if the ops is set, false otherwise.
+ */
+bool damon_is_registered_ops(enum damon_ops_id id)
+{
+	bool registered;
+
+	if (id >= NR_DAMON_OPS)
+		return false;
+	mutex_lock(&damon_ops_lock);
+	registered = __damon_is_registered_ops(id);
+	mutex_unlock(&damon_ops_lock);
+	return registered;
+}
+
 /**
  * damon_register_ops() - Register a monitoring operations set to DAMON.
  * @ops:	monitoring operations set to register.
@@ -56,7 +74,7 @@ int damon_register_ops(struct damon_operations *ops)
 		return -EINVAL;
 	mutex_lock(&damon_ops_lock);
 	/* Fail for already registered ops */
-	if (damon_registered_ops_id(ops->id)) {
+	if (__damon_is_registered_ops(ops->id)) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -84,7 +102,7 @@ int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id)
 		return -EINVAL;
 
 	mutex_lock(&damon_ops_lock);
-	if (!damon_registered_ops_id(id))
+	if (!__damon_is_registered_ops(id))
 		err = -EINVAL;
 	else
 		ctx->ops = damon_registered_ops[id];
-- 
cgit v1.2.3


From de6d01542a5c4f6fe6f0c65c14694b760f896acc Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Mon, 9 May 2022 18:20:52 -0700
Subject: mm/damon/vaddr: register a damon_operations for fixed virtual address
 ranges monitoring

Patch series "support fixed virtual address ranges monitoring".

The monitoring operations set for virtual address spaces automatically
updates the monitoring target regions to cover entire mappings of the
virtual address spaces as much as possible.  Some users could have more
information about their programs than kernel and therefore have interest
in not entire regions but only specific regions.  For such cases, the
automatic monitoring target regions updates are only unnecessary overhead
or distractions.

This patchset adds supports for the use case on DAMON's kernel API
(DAMON_OPS_FVADDR) and sysfs interface ('fvaddr' keyword for 'operations'
sysfs file).


This patch (of 3):

The monitoring operations set for virtual address spaces automatically
updates the monitoring target regions to cover entire mappings of the
virtual address spaces as much as possible.  Some users could have more
information about their programs than kernel and therefore have interest
in not entire regions but only specific regions.  For such cases, the
automatic monitoring target regions updates are only unnecessary overheads
or distractions.

For such cases, DAMON's API users can simply set the '->init()' and
'->update()' of the DAMON context's '->ops' NULL, and set the target
monitoring regions when creating the context.  But, that would be a dirty
hack.  Worse yet, the hack is unavailable for DAMON user space interface
users.

To support the use case in a clean way that can easily exported to the
user space, this commit adds another monitoring operations set called
'fvaddr', which is same to 'vaddr' but does not automatically update the
monitoring regions.  Instead, it will only respect the virtual address
regions which have explicitly passed at the initial context creation.

Note that this commit leave sysfs interface not supporting the feature
yet.  The support will be made in a following commit.

Link: https://lkml.kernel.org/r/20220426231750.48822-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20220426231750.48822-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h |  3 +++
 mm/damon/sysfs.c      |  4 ++++
 mm/damon/vaddr.c      | 15 +++++++++++++--
 3 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 73ff0e2d2a4d..09a5d0d02c00 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -261,10 +261,13 @@ struct damos {
  * enum damon_ops_id - Identifier for each monitoring operations implementation
  *
  * @DAMON_OPS_VADDR:	Monitoring operations for virtual address spaces
+ * @DAMON_OPS_FVADDR:	Monitoring operations for only fixed ranges of virtual
+ *			address spaces
  * @DAMON_OPS_PADDR:	Monitoring operations for the physical address space
  */
 enum damon_ops_id {
 	DAMON_OPS_VADDR,
+	DAMON_OPS_FVADDR,
 	DAMON_OPS_PADDR,
 	NR_DAMON_OPS,
 };
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index 6ad6364780b8..719a286d378f 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1694,6 +1694,7 @@ static struct kobj_type damon_sysfs_attrs_ktype = {
 /* This should match with enum damon_ops_id */
 static const char * const damon_sysfs_ops_strs[] = {
 	"vaddr",
+	"unsupported",	/* fvaddr is not supported by sysfs yet */
 	"paddr",
 };
 
@@ -1843,6 +1844,9 @@ static ssize_t operations_store(struct kobject *kobj,
 
 	for (id = 0; id < NR_DAMON_OPS; id++) {
 		if (sysfs_streq(buf, damon_sysfs_ops_strs[id])) {
+			/* fvaddr is not supported by sysfs yet */
+			if (id == DAMON_OPS_FVADDR)
+				return -EINVAL;
 			context->ops_id = id;
 			return count;
 		}
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index b2ec0aa1ff45..5ba82ab4943b 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -753,8 +753,19 @@ static int __init damon_va_initcall(void)
 		.apply_scheme = damon_va_apply_scheme,
 		.get_scheme_score = damon_va_scheme_score,
 	};
-
-	return damon_register_ops(&ops);
+	/* ops for fixed virtual address ranges */
+	struct damon_operations ops_fvaddr = ops;
+	int err;
+
+	/* Don't set the monitoring target regions for the entire mapping */
+	ops_fvaddr.id = DAMON_OPS_FVADDR;
+	ops_fvaddr.init = NULL;
+	ops_fvaddr.update = NULL;
+
+	err = damon_register_ops(&ops);
+	if (err)
+		return err;
+	return damon_register_ops(&ops_fvaddr);
 };
 
 subsys_initcall(damon_va_initcall);
-- 
cgit v1.2.3


From 534aa1dc975ac883ad89110534585a96630802a0 Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Mon, 9 May 2022 18:20:53 -0700
Subject: printk: stop including cache.h from printk.h

An inclusion of cache.h in printk.h was added in 2014 in commit
c28aa1f0a847 ("printk/cache: mark printk_once test variable
__read_mostly") in order to bring in the definition of __read_mostly.  The
usage of __read_mostly was later removed in commit 3ec25826ae33 ("printk:
Tie printk_once / printk_deferred_once into .data.once for reset") which
made the inclusion of cache.h unnecessary, so remove it.

We have a small amount of code that depended on the inclusion of cache.h
from printk.h; fix that code to include the appropriate header.

This fixes a circular inclusion on arm64 (linux/printk.h -> linux/cache.h
-> asm/cache.h -> linux/kasan-enabled.h -> linux/static_key.h ->
linux/jump_label.h -> linux/bug.h -> asm/bug.h -> linux/printk.h) that
would otherwise be introduced by the next patch.

Build tested using {allyesconfig,defconfig} x {arm64,x86_64}.

Link: https://linux-review.googlesource.com/id/I8fd51f72c9ef1f2d6afd3b2cbc875aa4792c1fba
Link: https://lkml.kernel.org/r/20220427195820.1716975-1-pcc@google.com
Signed-off-by: Peter Collingbourne <pcc@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm64/include/asm/mte-kasan.h | 1 +
 arch/arm64/include/asm/percpu.h    | 1 +
 arch/csky/include/asm/processor.h  | 2 +-
 drivers/firmware/smccc/kvm_guest.c | 1 +
 include/linux/printk.h             | 1 -
 kernel/bpf/bpf_lru_list.h          | 1 +
 6 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
index a857bcacf0fe..9f79425fc65a 100644
--- a/arch/arm64/include/asm/mte-kasan.h
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -6,6 +6,7 @@
 #define __ASM_MTE_KASAN_H
 
 #include <asm/compiler.h>
+#include <asm/cputype.h>
 #include <asm/mte-def.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 8f1661603b78..b9ba19dbdb69 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -10,6 +10,7 @@
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
 #include <asm/stack_pointer.h>
+#include <asm/sysreg.h>
 
 static inline void set_my_cpu_offset(unsigned long off)
 {
diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h
index 688c7548b559..9638206bc44f 100644
--- a/arch/csky/include/asm/processor.h
+++ b/arch/csky/include/asm/processor.h
@@ -4,9 +4,9 @@
 #define __ASM_CSKY_PROCESSOR_H
 
 #include <linux/bitops.h>
+#include <linux/cache.h>
 #include <asm/ptrace.h>
 #include <asm/current.h>
-#include <asm/cache.h>
 #include <abi/reg_ops.h>
 #include <abi/regdef.h>
 #include <abi/switch_context.h>
diff --git a/drivers/firmware/smccc/kvm_guest.c b/drivers/firmware/smccc/kvm_guest.c
index 2d3e866decaa..89a68e7eeaa6 100644
--- a/drivers/firmware/smccc/kvm_guest.c
+++ b/drivers/firmware/smccc/kvm_guest.c
@@ -4,6 +4,7 @@
 
 #include <linux/arm-smccc.h>
 #include <linux/bitmap.h>
+#include <linux/cache.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 1522df223c0f..8e8d74edf121 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -6,7 +6,6 @@
 #include <linux/init.h>
 #include <linux/kern_levels.h>
 #include <linux/linkage.h>
-#include <linux/cache.h>
 #include <linux/ratelimit_types.h>
 #include <linux/once_lite.h>
 
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index 6b12f06ee18c..4ea227c9c1ad 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -4,6 +4,7 @@
 #ifndef __BPF_LRU_LIST_H_
 #define __BPF_LRU_LIST_H_
 
+#include <linux/cache.h>
 #include <linux/list.h>
 #include <linux/spinlock_types.h>
 
-- 
cgit v1.2.3


From d949a8155d139aa890795b802004a196b7f00598 Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Mon, 9 May 2022 18:20:53 -0700
Subject: mm: make minimum slab alignment a runtime property

When CONFIG_KASAN_HW_TAGS is enabled we currently increase the minimum
slab alignment to 16.  This happens even if MTE is not supported in
hardware or disabled via kasan=off, which creates an unnecessary memory
overhead in those cases.  Eliminate this overhead by making the minimum
slab alignment a runtime property and only aligning to 16 if KASAN is
enabled at runtime.

On a DragonBoard 845c (non-MTE hardware) with a kernel built with
CONFIG_KASAN_HW_TAGS, waiting for quiescence after a full Android boot I
see the following Slab measurements in /proc/meminfo (median of 3
reboots):

Before: 169020 kB
After:  167304 kB

[akpm@linux-foundation.org: make slab alignment type `unsigned int' to avoid casting]
Link: https://linux-review.googlesource.com/id/I752e725179b43b144153f4b6f584ceb646473ead
Link: https://lkml.kernel.org/r/20220427195820.1716975-2-pcc@google.com
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm64/include/asm/cache.h | 17 ++++++++++++-----
 include/linux/slab.h           | 12 ++++++++++++
 mm/slab.c                      |  7 +++----
 mm/slab_common.c               |  3 +--
 mm/slob.c                      | 16 +++++++++++-----
 5 files changed, 39 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index a074459f8f2f..7c2181c72116 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -6,6 +6,7 @@
 #define __ASM_CACHE_H
 
 #include <asm/cputype.h>
+#include <asm/mte-def.h>
 
 #define CTR_L1IP_SHIFT		14
 #define CTR_L1IP_MASK		3
@@ -49,16 +50,22 @@
  */
 #define ARCH_DMA_MINALIGN	(128)
 
+#ifndef __ASSEMBLY__
+
+#include <linux/bitops.h>
+#include <linux/kasan-enabled.h>
+
 #ifdef CONFIG_KASAN_SW_TAGS
 #define ARCH_SLAB_MINALIGN	(1ULL << KASAN_SHADOW_SCALE_SHIFT)
 #elif defined(CONFIG_KASAN_HW_TAGS)
-#define ARCH_SLAB_MINALIGN	MTE_GRANULE_SIZE
+static inline unsigned int arch_slab_minalign(void)
+{
+	return kasan_hw_tags_enabled() ? MTE_GRANULE_SIZE :
+					 __alignof__(unsigned long long);
+}
+#define arch_slab_minalign() arch_slab_minalign()
 #endif
 
-#ifndef __ASSEMBLY__
-
-#include <linux/bitops.h>
-
 #define ICACHEF_ALIASING	0
 #define ICACHEF_VPIPT		1
 extern unsigned long __icache_flags;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 373b3ef99f4e..3d2f2a3ca17e 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -209,6 +209,18 @@ void kmem_dump_obj(void *object);
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
 
+/*
+ * Arches can define this function if they want to decide the minimum slab
+ * alignment at runtime. The value returned by the function must be a power
+ * of two and >= ARCH_SLAB_MINALIGN.
+ */
+#ifndef arch_slab_minalign
+static inline unsigned int arch_slab_minalign(void)
+{
+	return ARCH_SLAB_MINALIGN;
+}
+#endif
+
 /*
  * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned
  * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN
diff --git a/mm/slab.c b/mm/slab.c
index 0edb474edef1..8fb259511305 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3009,10 +3009,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON)
 		cachep->ctor(objp);
-	if (ARCH_SLAB_MINALIGN &&
-	    ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) {
-		pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n",
-		       objp, (int)ARCH_SLAB_MINALIGN);
+	if ((unsigned long)objp & (arch_slab_minalign() - 1)) {
+		pr_err("0x%px: not aligned to arch_slab_minalign()=%u\n", objp,
+		       arch_slab_minalign());
 	}
 	return objp;
 }
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2b3206a2c3b5..987e6917d850 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -154,8 +154,7 @@ static unsigned int calculate_alignment(slab_flags_t flags,
 		align = max(align, ralign);
 	}
 
-	if (align < ARCH_SLAB_MINALIGN)
-		align = ARCH_SLAB_MINALIGN;
+	align = max(align, arch_slab_minalign());
 
 	return ALIGN(align, sizeof(void *));
 }
diff --git a/mm/slob.c b/mm/slob.c
index 40ea6e2d4ccd..f47811f09aca 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -478,9 +478,11 @@ static __always_inline void *
 __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 {
 	unsigned int *m;
-	int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	unsigned int minalign;
 	void *ret;
 
+	minalign = max_t(unsigned int, ARCH_KMALLOC_MINALIGN,
+			 arch_slab_minalign());
 	gfp &= gfp_allowed_mask;
 
 	might_alloc(gfp);
@@ -493,7 +495,7 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 		 * kmalloc()'d objects.
 		 */
 		if (is_power_of_2(size))
-			align = max(minalign, (int) size);
+			align = max_t(unsigned int, minalign, size);
 
 		if (!size)
 			return ZERO_SIZE_PTR;
@@ -555,8 +557,11 @@ void kfree(const void *block)
 
 	sp = virt_to_folio(block);
 	if (folio_test_slab(sp)) {
-		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+		unsigned int align = max_t(unsigned int,
+					   ARCH_KMALLOC_MINALIGN,
+					   arch_slab_minalign());
 		unsigned int *m = (unsigned int *)(block - align);
+
 		slob_free(m, *m + align);
 	} else {
 		unsigned int order = folio_order(sp);
@@ -573,7 +578,7 @@ EXPORT_SYMBOL(kfree);
 size_t __ksize(const void *block)
 {
 	struct folio *folio;
-	int align;
+	unsigned int align;
 	unsigned int *m;
 
 	BUG_ON(!block);
@@ -584,7 +589,8 @@ size_t __ksize(const void *block)
 	if (unlikely(!folio_test_slab(folio)))
 		return folio_size(folio);
 
-	align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	align = max_t(unsigned int, ARCH_KMALLOC_MINALIGN,
+		      arch_slab_minalign());
 	m = (unsigned int *)(block - align);
 	return SLOB_UNITS(*m) * SLOB_UNIT;
 }
-- 
cgit v1.2.3


From b304c6f0d39d927a87e72a8ac6c89b96ac25f355 Mon Sep 17 00:00:00 2001
From: Hongchen Zhang <zhanghongchen@loongson.cn>
Date: Mon, 9 May 2022 18:20:53 -0700
Subject: mm/swapops: make is_pmd_migration_entry more strict

A pmd migration entry should first be a swap pmd,so use is_swap_pmd(pmd)
instead of !pmd_present(pmd).

On the other hand, some architecture (MIPS for example) may misjudge a
pmd_none entry as a pmd migration entry.

Link: https://lkml.kernel.org/r/1651131333-6386-1-git-send-email-zhanghongchen@loongson.cn
Signed-off-by: Hongchen Zhang <zhanghongchen@loongson.cn>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swapops.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index d1b728904d4e..82265b055a0d 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -331,7 +331,7 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
 
 static inline int is_pmd_migration_entry(pmd_t pmd)
 {
-	return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
+	return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
 }
 #else
 static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
-- 
cgit v1.2.3


From 6e74d2bf5a265113ca54a8323783d2f3fdde96b7 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Mon, 9 May 2022 18:20:54 -0700
Subject: mm/damon/core: add a new callback for watermarks checks

Patch series "mm/damon: Support online tuning".

Effects of DAMON and DAMON-based Operation Schemes highly depends on the
configurations.  Wrong configurations could even result in unexpected
efficiency degradations.  For finding a best configuration, repeating
incremental configuration changes and results measurements, in other
words, online tuning, could be helpful.

Nevertheless, DAMON kernel API supports only restrictive online tuning.
Worse yet, the sysfs-based DAMON user interface doesn't support online
tuning at all.  DAMON_RECLAIM also doesn't support online tuning.

This patchset makes the DAMON kernel API, DAMON sysfs interface, and
DAMON_RECLAIM supports online tuning.

Sequence of patches
-------------------

First two patches enhance DAMON online tuning for kernel API users.
Specifically, patch 1 let kernel API users to be able to do DAMON online
tuning without a restriction, and patch 2 makes error handling easier.

Following seven patches (patches 3-9) refactor code for better readability
and easier reuse of code fragments that will be useful for online tuning
support.

Patch 10 introduces DAMON callback based user request handling structure
for DAMON sysfs interface, and patch 11 enables DAMON online tuning via
DAMON sysfs interface.  Documentation patch (patch 12) for usage of it
follows.

Patch 13 enables online tuning of DAMON_RECLAIM and finally patch 14
documents the DAMON_RECLAIM online tuning usage.


This patch (of 14):

For updating input parameters for running DAMON contexts, DAMON kernel API
users can use the contexts' callbacks, as it is the safe place for context
internal data accesses.  When the context has DAMON-based operation
schemes and all schemes are deactivated due to their watermarks, however,
DAMON does nothing but only watermarks checks.  As a result, no callbacks
will be called back, and therefore the kernel API users cannot update the
input parameters including monitoring attributes, DAMON-based operation
schemes, and watermarks.

To let users easily update such DAMON input parameters in such a case,
this commit adds a new callback, 'after_wmarks_check()'.  It will be
called after each watermarks check.  Users can do the online input
parameters update in the callback even under the schemes deactivated case.

Link: https://lkml.kernel.org/r/20220429160606.127307-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 7 +++++++
 mm/damon/core.c       | 8 +++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 09a5d0d02c00..6cb5ab5d8e9d 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -343,6 +343,7 @@ struct damon_operations {
  * struct damon_callback - Monitoring events notification callbacks.
  *
  * @before_start:	Called before starting the monitoring.
+ * @after_wmarks_check:	Called after each schemes' watermarks check.
  * @after_sampling:	Called after each sampling.
  * @after_aggregation:	Called after each aggregation.
  * @before_terminate:	Called before terminating the monitoring.
@@ -353,6 +354,11 @@ struct damon_operations {
  * respectively.  Therefore, those are good places for installing and cleaning
  * @private.
  *
+ * The monitoring thread calls @after_wmarks_check after each DAMON-based
+ * operation schemes' watermarks check.  If users need to make changes to the
+ * attributes of the monitoring context while it's deactivated due to the
+ * watermarks, this is the good place to do.
+ *
  * The monitoring thread calls @after_sampling and @after_aggregation for each
  * of the sampling intervals and aggregation intervals, respectively.
  * Therefore, users can safely access the monitoring results without additional
@@ -365,6 +371,7 @@ struct damon_callback {
 	void *private;
 
 	int (*before_start)(struct damon_ctx *context);
+	int (*after_wmarks_check)(struct damon_ctx *context);
 	int (*after_sampling)(struct damon_ctx *context);
 	int (*after_aggregation)(struct damon_ctx *context);
 	void (*before_terminate)(struct damon_ctx *context);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 997cf7b17779..44fe7e452a1e 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1051,6 +1051,10 @@ static int kdamond_wait_activation(struct damon_ctx *ctx)
 			return 0;
 
 		kdamond_usleep(min_wait_time);
+
+		if (ctx->callback.after_wmarks_check &&
+				ctx->callback.after_wmarks_check(ctx))
+			break;
 	}
 	return -EBUSY;
 }
@@ -1077,8 +1081,10 @@ static int kdamond_fn(void *data)
 	sz_limit = damon_region_sz_limit(ctx);
 
 	while (!kdamond_need_stop(ctx) && !done) {
-		if (kdamond_wait_activation(ctx))
+		if (kdamond_wait_activation(ctx)) {
+			done = true;
 			continue;
+		}
 
 		if (ctx->ops.prepare_access_checks)
 			ctx->ops.prepare_access_checks(ctx);
-- 
cgit v1.2.3


From d0723bc04185b15ed96ade0a0bf9277ef00008db Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Mon, 9 May 2022 18:20:55 -0700
Subject: mm/damon/vaddr: move 'damon_set_regions()' to core

This commit moves 'damon_set_regions()' from vaddr to core, as it is aimed
to be used by not only 'vaddr' but also other parts of DAMON.

Link: https://lkml.kernel.org/r/20220429160606.127307-5-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h |  2 ++
 mm/damon/core.c       | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/damon/vaddr.c      | 73 ---------------------------------------------------
 3 files changed, 75 insertions(+), 73 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 6cb5ab5d8e9d..d1e6ee28a2ff 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -494,6 +494,8 @@ static inline void damon_insert_region(struct damon_region *r,
 
 void damon_add_region(struct damon_region *r, struct damon_target *t);
 void damon_destroy_region(struct damon_region *r, struct damon_target *t);
+int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
+		unsigned int nr_ranges);
 
 struct damos *damon_new_scheme(
 		unsigned long min_sz_region, unsigned long max_sz_region,
diff --git a/mm/damon/core.c b/mm/damon/core.c
index b6daaff37bec..7d25dc582fe3 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -157,6 +157,79 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t)
 	damon_free_region(r);
 }
 
+/*
+ * Check whether a region is intersecting an address range
+ *
+ * Returns true if it is.
+ */
+static bool damon_intersect(struct damon_region *r,
+		struct damon_addr_range *re)
+{
+	return !(r->ar.end <= re->start || re->end <= r->ar.start);
+}
+
+/*
+ * damon_set_regions() - Set regions of a target for given address ranges.
+ * @t:		the given target.
+ * @ranges:	array of new monitoring target ranges.
+ * @nr_ranges:	length of @ranges.
+ *
+ * This function adds new regions to, or modify existing regions of a
+ * monitoring target to fit in specific ranges.
+ *
+ * Return: 0 if success, or negative error code otherwise.
+ */
+int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
+		unsigned int nr_ranges)
+{
+	struct damon_region *r, *next;
+	unsigned int i;
+
+	/* Remove regions which are not in the new ranges */
+	damon_for_each_region_safe(r, next, t) {
+		for (i = 0; i < nr_ranges; i++) {
+			if (damon_intersect(r, &ranges[i]))
+				break;
+		}
+		if (i == nr_ranges)
+			damon_destroy_region(r, t);
+	}
+
+	/* Add new regions or resize existing regions to fit in the ranges */
+	for (i = 0; i < nr_ranges; i++) {
+		struct damon_region *first = NULL, *last, *newr;
+		struct damon_addr_range *range;
+
+		range = &ranges[i];
+		/* Get the first/last regions intersecting with the range */
+		damon_for_each_region(r, t) {
+			if (damon_intersect(r, range)) {
+				if (!first)
+					first = r;
+				last = r;
+			}
+			if (r->ar.start >= range->end)
+				break;
+		}
+		if (!first) {
+			/* no region intersects with this range */
+			newr = damon_new_region(
+					ALIGN_DOWN(range->start,
+						DAMON_MIN_REGION),
+					ALIGN(range->end, DAMON_MIN_REGION));
+			if (!newr)
+				return -ENOMEM;
+			damon_insert_region(newr, damon_prev_region(r), r, t);
+		} else {
+			/* resize intersecting regions to fit in this range */
+			first->ar.start = ALIGN_DOWN(range->start,
+					DAMON_MIN_REGION);
+			last->ar.end = ALIGN(range->end, DAMON_MIN_REGION);
+		}
+	}
+	return 0;
+}
+
 struct damos *damon_new_scheme(
 		unsigned long min_sz_region, unsigned long max_sz_region,
 		unsigned int min_nr_accesses, unsigned int max_nr_accesses,
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 26e9ad80f9ea..fcb44210204a 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -285,79 +285,6 @@ static void damon_va_init(struct damon_ctx *ctx)
  * Functions for the dynamic monitoring target regions update
  */
 
-/*
- * Check whether a region is intersecting an address range
- *
- * Returns true if it is.
- */
-static bool damon_intersect(struct damon_region *r,
-		struct damon_addr_range *re)
-{
-	return !(r->ar.end <= re->start || re->end <= r->ar.start);
-}
-
-/*
- * damon_set_regions() - Set regions of a target for given address ranges.
- * @t:		the given target.
- * @ranges:	array of new monitoring target ranges.
- * @nr_ranges:	length of @ranges.
- *
- * This function adds new regions to, or modify existing regions of a
- * monitoring target to fit in specific ranges.
- *
- * Return: 0 if success, or negative error code otherwise.
- */
-static int damon_set_regions(struct damon_target *t,
-		struct damon_addr_range *ranges, unsigned int nr_ranges)
-{
-	struct damon_region *r, *next;
-	unsigned int i;
-
-	/* Remove regions which are not in the new ranges */
-	damon_for_each_region_safe(r, next, t) {
-		for (i = 0; i < nr_ranges; i++) {
-			if (damon_intersect(r, &ranges[i]))
-				break;
-		}
-		if (i == nr_ranges)
-			damon_destroy_region(r, t);
-	}
-
-	/* Add new regions or resize existing regions to fit in the ranges */
-	for (i = 0; i < nr_ranges; i++) {
-		struct damon_region *first = NULL, *last, *newr;
-		struct damon_addr_range *range;
-
-		range = &ranges[i];
-		/* Get the first/last regions intersecting with the range */
-		damon_for_each_region(r, t) {
-			if (damon_intersect(r, range)) {
-				if (!first)
-					first = r;
-				last = r;
-			}
-			if (r->ar.start >= range->end)
-				break;
-		}
-		if (!first) {
-			/* no region intersects with this range */
-			newr = damon_new_region(
-					ALIGN_DOWN(range->start,
-						DAMON_MIN_REGION),
-					ALIGN(range->end, DAMON_MIN_REGION));
-			if (!newr)
-				return -ENOMEM;
-			damon_insert_region(newr, damon_prev_region(r), r, t);
-		} else {
-			/* resize intersecting regions to fit in this range */
-			first->ar.start = ALIGN_DOWN(range->start,
-					DAMON_MIN_REGION);
-			last->ar.end = ALIGN(range->end, DAMON_MIN_REGION);
-		}
-	}
-	return 0;
-}
-
 /*
  * Update damon regions for the three big regions of the given target
  *
-- 
cgit v1.2.3


From 679d103319101800567c8bb7e341b5eee39f6685 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:52 -0700
Subject: mm: introduce PTE_MARKER swap entry

Patch series "userfaultfd-wp: Support shmem and hugetlbfs", v8.


Overview
========

Userfaultfd-wp anonymous support was merged two years ago.  There're quite
a few applications that started to leverage this capability either to take
snapshots for user-app memory, or use it for full user controled swapping.

This series tries to complete the feature for uffd-wp so as to cover all
the RAM-based memory types.  So far uffd-wp is the only missing piece of
the rest features (uffd-missing & uffd-minor mode).

One major reason to do so is that anonymous pages are sometimes not
satisfying the need of applications, and there're growing users of either
shmem and hugetlbfs for either sharing purpose (e.g., sharing guest mem
between hypervisor process and device emulation process, shmem local live
migration for upgrades), or for performance on tlb hits.

All these mean that if a uffd-wp app wants to switch to any of the memory
types, it'll stop working.  I think it's worthwhile to have the kernel to
cover all these aspects.

This series chose to protect pages in pte level not page level.

One major reason is safety.  I have no idea how we could make it safe if
any of the uffd-privileged app can wr-protect a page that any other
application can use.  It means this app can block any process potentially
for any time it wants.

The other reason is that it aligns very well with not only the anonymous
uffd-wp solution, but also uffd as a whole.  For example, userfaultfd is
implemented fundamentally based on VMAs.  We set flags to VMAs showing the
status of uffd tracking.  For another per-page based protection solution,
it'll be crossing the fundation line on VMA-based, and it could simply be
too far away already from what's called userfaultfd.

PTE markers
===========

The patchset is based on the idea called PTE markers.  It was discussed in
one of the mm alignment sessions, proposed starting from v6, and this is
the 2nd version of it using PTE marker idea.

PTE marker is a new type of swap entry that is ony applicable to file
backed memories like shmem and hugetlbfs.  It's used to persist some
pte-level information even if the original present ptes in pgtable are
zapped.

Logically pte markers can store more than uffd-wp information, but so far
only one bit is used for uffd-wp purpose.  When the pte marker is
installed with uffd-wp bit set, it means this pte is wr-protected by uffd.

It solves the problem on e.g.  file-backed memory mapped ptes got zapped
due to any reason (e.g.  thp split, or swapped out), we can still keep the
wr-protect information in the ptes.  Then when the page fault triggers
again, we'll know this pte is wr-protected so we can treat the pte the
same as a normal uffd wr-protected pte.

The extra information is encoded into the swap entry, or swp_offset to be
explicit, with the swp_type being PTE_MARKER.  So far uffd-wp only uses
one bit out of the swap entry, the rest bits of swp_offset are still
reserved for other purposes.

There're two configs to enable/disable PTE markers:

  CONFIG_PTE_MARKER
  CONFIG_PTE_MARKER_UFFD_WP

We can set !PTE_MARKER to completely disable all the PTE markers, along
with uffd-wp support.  I made two config so we can also enable PTE marker
but disable uffd-wp file-backed for other purposes.  At the end of current
series, I'll enable CONFIG_PTE_MARKER by default, but that patch is
standalone and if anyone worries about having it by default, we can also
consider turn it off by dropping that oneliner patch.  So far I don't see
a huge risk of doing so, so I kept that patch.

In most cases, PTE markers should be treated as none ptes.  It is because
that unlike most of the other swap entry types, there's no PFN or block
offset information encoded into PTE markers but some extra well-defined
bits showing the status of the pte.  These bits should only be used as
extra data when servicing an upcoming page fault, and then we behave as if
it's a none pte.

I did spend a lot of time observing all the pte_none() users this time.
It is indeed a challenge because there're a lot, and I hope I didn't miss
a single of them when we should take care of pte markers.  Luckily, I
don't think it'll need to be considered in many cases, for example: boot
code, arch code (especially non-x86), kernel-only page handlings (e.g.
CPA), or device driver codes when we're tackling with pure PFN mappings.

I introduced pte_none_mostly() in this series when we need to handle pte
markers the same as none pte, the "mostly" is the other way to write
"either none pte or a pte marker".

I didn't replace pte_none() to cover pte markers for below reasons:

  - Very rare case of pte_none() callers will handle pte markers.  E.g., all
    the kernel pages do not require knowledge of pte markers.  So we don't
    pollute the major use cases.

  - Unconditionally change pte_none() semantics could confuse people, because
    pte_none() existed for so long a time.

  - Unconditionally change pte_none() semantics could make pte_none() slower
    even if in many cases pte markers do not exist.

  - There're cases where we'd like to handle pte markers differntly from
    pte_none(), so a full replace is also impossible.  E.g. khugepaged should
    still treat pte markers as normal swap ptes rather than none ptes, because
    pte markers will always need a fault-in to merge the marker with a valid
    pte.  Or the smap code will need to parse PTE markers not none ptes.

Patch Layout
============

Introducing PTE marker and uffd-wp bit in PTE marker:

  mm: Introduce PTE_MARKER swap entry
  mm: Teach core mm about pte markers
  mm: Check against orig_pte for finish_fault()
  mm/uffd: PTE_MARKER_UFFD_WP

Adding support for shmem uffd-wp:

  mm/shmem: Take care of UFFDIO_COPY_MODE_WP
  mm/shmem: Handle uffd-wp special pte in page fault handler
  mm/shmem: Persist uffd-wp bit across zapping for file-backed
  mm/shmem: Allow uffd wr-protect none pte for file-backed mem
  mm/shmem: Allows file-back mem to be uffd wr-protected on thps
  mm/shmem: Handle uffd-wp during fork()

Adding support for hugetlbfs uffd-wp:

  mm/hugetlb: Introduce huge pte version of uffd-wp helpers
  mm/hugetlb: Hook page faults for uffd write protection
  mm/hugetlb: Take care of UFFDIO_COPY_MODE_WP
  mm/hugetlb: Handle UFFDIO_WRITEPROTECT
  mm/hugetlb: Handle pte markers in page faults
  mm/hugetlb: Allow uffd wr-protect none ptes
  mm/hugetlb: Only drop uffd-wp special pte if required
  mm/hugetlb: Handle uffd-wp during fork()

Misc handling on the rest mm for uffd-wp file-backed:

  mm/khugepaged: Don't recycle vma pgtable if uffd-wp registered
  mm/pagemap: Recognize uffd-wp bit for shmem/hugetlbfs

Enabling of uffd-wp on file-backed memory:

  mm/uffd: Enable write protection for shmem & hugetlbfs
  mm: Enable PTE markers by default
  selftests/uffd: Enable uffd-wp for shmem/hugetlbfs

Tests
=====

- Compile test on x86_64 and aarch64 on different configs
- Kernel selftests
- uffd-test [0]
- Umapsort [1,2] test for shmem/hugetlb, with swap on/off

[0] https://github.com/xzpeter/clibs/tree/master/uffd-test
[1] https://github.com/xzpeter/umap-apps/tree/peter
[2] https://github.com/xzpeter/umap/tree/peter-shmem-hugetlbfs


This patch (of 23):

Introduces a new swap entry type called PTE_MARKER.  It can be installed
for any pte that maps a file-backed memory when the pte is temporarily
zapped, so as to maintain per-pte information.

The information that kept in the pte is called a "marker".  Here we define
the marker as "unsigned long" just to match pgoff_t, however it will only
work if it still fits in swp_offset(), which is e.g.  currently 58 bits on
x86_64.

A new config CONFIG_PTE_MARKER is introduced too; it's by default off.  A
bunch of helpers are defined altogether to service the rest of the pte
marker code.

[peterx@redhat.com: fixup]
  Link: https://lkml.kernel.org/r/Yk2rdB7SXZf+2BDF@xz-m1.local
Link: https://lkml.kernel.org/r/20220405014646.13522-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20220405014646.13522-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/s390/include/asm/hugetlb.h |  5 +++
 include/asm-generic/hugetlb.h   |  9 +++++
 include/linux/swap.h            | 15 +++++++-
 include/linux/swapops.h         | 78 +++++++++++++++++++++++++++++++++++++++++
 mm/Kconfig                      |  6 ++++
 5 files changed, 112 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index bea47e7cc6a0..f0bc4d31e852 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -85,6 +85,11 @@ static inline int huge_pte_none(pte_t pte)
 	return pte_none(pte);
 }
 
+static inline int huge_pte_none_mostly(pte_t pte)
+{
+	return huge_pte_none(pte);
+}
+
 static inline int huge_pte_write(pte_t pte)
 {
 	return pte_write(pte);
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 8e1e6244a89d..f39cad20ffc6 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -2,6 +2,9 @@
 #ifndef _ASM_GENERIC_HUGETLB_H
 #define _ASM_GENERIC_HUGETLB_H
 
+#include <linux/swap.h>
+#include <linux/swapops.h>
+
 static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
 {
 	return mk_pte(page, pgprot);
@@ -80,6 +83,12 @@ static inline int huge_pte_none(pte_t pte)
 }
 #endif
 
+/* Please refer to comments above pte_none_mostly() for the usage */
+static inline int huge_pte_none_mostly(pte_t pte)
+{
+	return huge_pte_none(pte) || is_pte_marker(pte);
+}
+
 #ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7daae5a4b3e1..5553189d0215 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -55,6 +55,19 @@ static inline int current_is_kswapd(void)
  * actions on faults.
  */
 
+/*
+ * PTE markers are used to persist information onto PTEs that are mapped with
+ * file-backed memories.  As its name "PTE" hints, it should only be applied to
+ * the leaves of pgtables.
+ */
+#ifdef CONFIG_PTE_MARKER
+#define SWP_PTE_MARKER_NUM 1
+#define SWP_PTE_MARKER     (MAX_SWAPFILES + SWP_HWPOISON_NUM + \
+			    SWP_MIGRATION_NUM + SWP_DEVICE_NUM)
+#else
+#define SWP_PTE_MARKER_NUM 0
+#endif
+
 /*
  * Unaddressable device memory support. See include/linux/hmm.h and
  * Documentation/vm/hmm.rst. Short description is we need struct pages for
@@ -107,7 +120,7 @@ static inline int current_is_kswapd(void)
 
 #define MAX_SWAPFILES \
 	((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \
-	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
+	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM)
 
 /*
  * Magic header for a swap area. The first part of the union is
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 82265b055a0d..bb70da461b7d 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -274,6 +274,84 @@ static inline int is_readable_migration_entry(swp_entry_t entry)
 
 #endif
 
+typedef unsigned long pte_marker;
+
+#define  PTE_MARKER_MASK     (0)
+
+#ifdef CONFIG_PTE_MARKER
+
+static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
+{
+	return swp_entry(SWP_PTE_MARKER, marker);
+}
+
+static inline bool is_pte_marker_entry(swp_entry_t entry)
+{
+	return swp_type(entry) == SWP_PTE_MARKER;
+}
+
+static inline pte_marker pte_marker_get(swp_entry_t entry)
+{
+	return swp_offset(entry) & PTE_MARKER_MASK;
+}
+
+static inline bool is_pte_marker(pte_t pte)
+{
+	return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte));
+}
+
+#else /* CONFIG_PTE_MARKER */
+
+static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
+{
+	/* This should never be called if !CONFIG_PTE_MARKER */
+	WARN_ON_ONCE(1);
+	return swp_entry(0, 0);
+}
+
+static inline bool is_pte_marker_entry(swp_entry_t entry)
+{
+	return false;
+}
+
+static inline pte_marker pte_marker_get(swp_entry_t entry)
+{
+	return 0;
+}
+
+static inline bool is_pte_marker(pte_t pte)
+{
+	return false;
+}
+
+#endif /* CONFIG_PTE_MARKER */
+
+static inline pte_t make_pte_marker(pte_marker marker)
+{
+	return swp_entry_to_pte(make_pte_marker_entry(marker));
+}
+
+/*
+ * This is a special version to check pte_none() just to cover the case when
+ * the pte is a pte marker.  It existed because in many cases the pte marker
+ * should be seen as a none pte; it's just that we have stored some information
+ * onto the none pte so it becomes not-none any more.
+ *
+ * It should be used when the pte is file-backed, ram-based and backing
+ * userspace pages, like shmem.  It is not needed upon pgtables that do not
+ * support pte markers at all.  For example, it's not needed on anonymous
+ * memory, kernel-only memory (including when the system is during-boot),
+ * non-ram based generic file-system.  It's fine to be used even there, but the
+ * extra pte marker check will be pure overhead.
+ *
+ * For systems configured with !CONFIG_PTE_MARKER this will be automatically
+ * optimized to pte_none().
+ */
+static inline int pte_none_mostly(pte_t pte)
+{
+	return pte_none(pte) || is_pte_marker(pte);
+}
+
 static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
 {
 	struct page *p = pfn_to_page(swp_offset(entry));
diff --git a/mm/Kconfig b/mm/Kconfig
index 3f7b6d7b69df..2262f211b53e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -909,6 +909,12 @@ config ANON_VMA_NAME
 	  area from being merged with adjacent virtual memory areas due to the
 	  difference in their name.
 
+config PTE_MARKER
+	bool "Marker PTEs support"
+
+	help
+	  Allows to create marker PTEs for file-backed memory.
+
 source "mm/damon/Kconfig"
 
 endmenu
-- 
cgit v1.2.3


From f46f2adecdcc1ba0799383e67fe98f65f41fea5c Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:52 -0700
Subject: mm: check against orig_pte for finish_fault()

This patch allows do_fault() to trigger on !pte_none() cases too.  This
prepares for the pte markers to be handled by do_fault() just like none
pte.

To achieve this, instead of unconditionally check against pte_none() in
finish_fault(), we may hit the case that the orig_pte was some pte marker
so what we want to do is to replace the pte marker with some valid pte
entry.  Then if orig_pte was set we'd want to check the current *pte
(under pgtable lock) against orig_pte rather than none pte.

Right now there's no solid way to safely reference orig_pte because when
pmd is not allocated handle_pte_fault() will not initialize orig_pte, so
it's not safe to reference it.

There's another solution proposed before this patch to do pte_clear() for
vmf->orig_pte for pmd==NULL case, however it turns out it'll break arm32
because arm32 could have assumption that pte_t* pointer will always reside
on a real ram32 pgtable, not any kernel stack variable.

To solve this, we add a new flag FAULT_FLAG_ORIG_PTE_VALID, and it'll be
set along with orig_pte when there is valid orig_pte, or it'll be cleared
when orig_pte was not initialized.

It'll be updated every time we call handle_pte_fault(), so e.g.  if a page
fault retry happened it'll be properly updated along with orig_pte.

[1] https://lore.kernel.org/lkml/710c48c9-406d-e4c5-a394-10501b951316@samsung.com/

[akpm@linux-foundation.org: coding-style cleanups]
[peterx@redhat.com: fix crash reported by Marek]
  Link: https://lkml.kernel.org/r/Ylb9rXJyPm8/ao8f@xz-m1.local
Link: https://lkml.kernel.org/r/20220405014836.14077-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm_types.h |  3 +++
 mm/memory.c              | 12 +++++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7216d77a5884..dd382270ae40 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -822,6 +822,8 @@ typedef struct {
  * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark
  *                      exclusive) a possibly shared anonymous page that is
  *                      mapped R/O.
+ * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached.
+ *                        We should only access orig_pte if this flag set.
  *
  * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
  * whether we would allow page faults to retry by specifying these two
@@ -858,6 +860,7 @@ enum fault_flag {
 	FAULT_FLAG_INSTRUCTION =	1 << 8,
 	FAULT_FLAG_INTERRUPTIBLE =	1 << 9,
 	FAULT_FLAG_UNSHARE =		1 << 10,
+	FAULT_FLAG_ORIG_PTE_VALID =	1 << 11,
 };
 
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/mm/memory.c b/mm/memory.c
index 9743c8b74bf2..878da420d97b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4183,6 +4183,14 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 	set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
 }
 
+static bool vmf_pte_changed(struct vm_fault *vmf)
+{
+	if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)
+		return !pte_same(*vmf->pte, vmf->orig_pte);
+
+	return !pte_none(*vmf->pte);
+}
+
 /**
  * finish_fault - finish page fault once we have prepared the page to fault
  *
@@ -4241,7 +4249,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 				      vmf->address, &vmf->ptl);
 	ret = 0;
 	/* Re-check under ptl */
-	if (likely(pte_none(*vmf->pte)))
+	if (likely(!vmf_pte_changed(vmf)))
 		do_set_pte(vmf, page, vmf->address);
 	else
 		ret = VM_FAULT_NOPAGE;
@@ -4709,6 +4717,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		 * concurrent faults and from rmap lookups.
 		 */
 		vmf->pte = NULL;
+		vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID;
 	} else {
 		/*
 		 * If a huge pmd materialized under us just retry later.  Use
@@ -4732,6 +4741,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		 */
 		vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
 		vmf->orig_pte = *vmf->pte;
+		vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID;
 
 		/*
 		 * some architectures can have larger ptes than wordsize,
-- 
cgit v1.2.3


From 1db9dbc2ef05205bf1022f9b14aa29b1dd8efd7e Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:52 -0700
Subject: mm/uffd: PTE_MARKER_UFFD_WP

This patch introduces the 1st user of pte marker: the uffd-wp marker.

When the pte marker is installed with the uffd-wp bit set, it means this
pte was wr-protected by uffd.

We will use this special pte to arm the ptes that got either unmapped or
swapped out for a file-backed region that was previously wr-protected.
This special pte could trigger a page fault just like swap entries.

This idea is greatly inspired by Hugh and Andrea in the discussion, which
is referenced in the links below.

Some helpers are introduced to detect whether a swap pte is uffd
wr-protected.  After the pte marker introduced, one swap pte can be
wr-protected in two forms: either it is a normal swap pte and it has
_PAGE_SWP_UFFD_WP set, or it's a pte marker that has PTE_MARKER_UFFD_WP
set.

[peterx@redhat.com: fixup]
  Link: https://lkml.kernel.org/r/YkzKiM8tI4+qOfXF@xz-m1.local
Link: https://lore.kernel.org/lkml/20201126222359.8120-1-peterx@redhat.com/
Link: https://lore.kernel.org/lkml/20201130230603.46187-1-peterx@redhat.com/
Link: https://lkml.kernel.org/r/20220405014838.14131-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Suggested-by: Andrea Arcangeli <aarcange@redhat.com>
Suggested-by: Hugh Dickins <hughd@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swapops.h       |  3 ++-
 include/linux/userfaultfd_k.h | 47 +++++++++++++++++++++++++++++++++++++++++++
 mm/Kconfig                    |  9 +++++++++
 3 files changed, 58 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index bb70da461b7d..09945342bf76 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -276,7 +276,8 @@ static inline int is_readable_migration_entry(swp_entry_t entry)
 
 typedef unsigned long pte_marker;
 
-#define  PTE_MARKER_MASK     (0)
+#define  PTE_MARKER_UFFD_WP  BIT(0)
+#define  PTE_MARKER_MASK     (PTE_MARKER_UFFD_WP)
 
 #ifdef CONFIG_PTE_MARKER
 
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 33cea484d1ad..3354d9ddc35f 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -15,6 +15,8 @@
 
 #include <linux/fcntl.h>
 #include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 #include <asm-generic/pgtable_uffd.h>
 
 /* The set of all possible UFFD-related VM flags. */
@@ -236,4 +238,49 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
 
 #endif /* CONFIG_USERFAULTFD */
 
+static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry)
+{
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
+	return is_pte_marker_entry(entry) &&
+	    (pte_marker_get(entry) & PTE_MARKER_UFFD_WP);
+#else
+	return false;
+#endif
+}
+
+static inline bool pte_marker_uffd_wp(pte_t pte)
+{
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
+	swp_entry_t entry;
+
+	if (!is_swap_pte(pte))
+		return false;
+
+	entry = pte_to_swp_entry(pte);
+
+	return pte_marker_entry_uffd_wp(entry);
+#else
+	return false;
+#endif
+}
+
+/*
+ * Returns true if this is a swap pte and was uffd-wp wr-protected in either
+ * forms (pte marker or a normal swap pte), false otherwise.
+ */
+static inline bool pte_swp_uffd_wp_any(pte_t pte)
+{
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
+	if (!is_swap_pte(pte))
+		return false;
+
+	if (pte_swp_uffd_wp(pte))
+		return true;
+
+	if (pte_marker_uffd_wp(pte))
+		return true;
+#endif
+	return false;
+}
+
 #endif /* _LINUX_USERFAULTFD_K_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index 2262f211b53e..71c653260a44 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -915,6 +915,15 @@ config PTE_MARKER
 	help
 	  Allows to create marker PTEs for file-backed memory.
 
+config PTE_MARKER_UFFD_WP
+	bool "Marker PTEs support for userfaultfd write protection"
+	depends on PTE_MARKER && HAVE_ARCH_USERFAULTFD_WP
+
+	help
+	  Allows to create marker PTEs for userfaultfd write protection
+	  purposes.  It is required to enable userfaultfd write protection on
+	  file-backed memory types like shmem and hugetlbfs.
+
 source "mm/damon/Kconfig"
 
 endmenu
-- 
cgit v1.2.3


From 8ee79edff6d3b43b2d0c1e41f92b32e128988b22 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:52 -0700
Subject: mm/shmem: take care of UFFDIO_COPY_MODE_WP

Pass wp_copy into shmem_mfill_atomic_pte() through the stack, then apply
the UFFD_WP bit properly when the UFFDIO_COPY on shmem is with
UFFDIO_COPY_MODE_WP.  wp_copy lands mfill_atomic_install_pte() finally.

Note: we must do pte_wrprotect() if !writable in
mfill_atomic_install_pte(), as mk_pte() could return a writable pte (e.g.,
when VM_SHARED on a shmem file).

Link: https://lkml.kernel.org/r/20220405014841.14185-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/shmem_fs.h |  4 ++--
 mm/shmem.c               |  4 ++--
 mm/userfaultfd.c         | 23 ++++++++++++++++++-----
 3 files changed, 22 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 3e915cc550bc..a68f982f22d1 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -145,11 +145,11 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 				  struct vm_area_struct *dst_vma,
 				  unsigned long dst_addr,
 				  unsigned long src_addr,
-				  bool zeropage,
+				  bool zeropage, bool wp_copy,
 				  struct page **pagep);
 #else /* !CONFIG_SHMEM */
 #define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \
-			       src_addr, zeropage, pagep)       ({ BUG(); 0; })
+			       src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; })
 #endif /* CONFIG_SHMEM */
 #endif /* CONFIG_USERFAULTFD */
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 913c0b039333..4a4a2e628289 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2319,7 +2319,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 			   struct vm_area_struct *dst_vma,
 			   unsigned long dst_addr,
 			   unsigned long src_addr,
-			   bool zeropage,
+			   bool zeropage, bool wp_copy,
 			   struct page **pagep)
 {
 	struct inode *inode = file_inode(dst_vma->vm_file);
@@ -2392,7 +2392,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 		goto out_release;
 
 	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
-				       page, true, false);
+				       page, true, wp_copy);
 	if (ret)
 		goto out_delete_from_cache;
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 9cdaed939203..2b6ec3352147 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -78,10 +78,19 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 	 * Always mark a PTE as write-protected when needed, regardless of
 	 * VM_WRITE, which the user might change.
 	 */
-	if (wp_copy)
+	if (wp_copy) {
 		_dst_pte = pte_mkuffd_wp(_dst_pte);
-	else if (writable)
+		writable = false;
+	}
+
+	if (writable)
 		_dst_pte = pte_mkwrite(_dst_pte);
+	else
+		/*
+		 * We need this to make sure write bit removed; as mk_pte()
+		 * could return a pte with write bit set.
+		 */
+		_dst_pte = pte_wrprotect(_dst_pte);
 
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
 
@@ -96,7 +105,12 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 	}
 
 	ret = -EEXIST;
-	if (!pte_none(*dst_pte))
+	/*
+	 * We allow to overwrite a pte marker: consider when both MISSING|WP
+	 * registered, we firstly wr-protect a none pte which has no page cache
+	 * page backing it, then access the page.
+	 */
+	if (!pte_none_mostly(*dst_pte))
 		goto out_unlock;
 
 	if (page_in_cache) {
@@ -480,11 +494,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 			err = mfill_zeropage_pte(dst_mm, dst_pmd,
 						 dst_vma, dst_addr);
 	} else {
-		VM_WARN_ON_ONCE(wp_copy);
 		err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
 					     dst_addr, src_addr,
 					     mode != MCOPY_ATOMIC_NORMAL,
-					     page);
+					     wp_copy, page);
 	}
 
 	return err;
-- 
cgit v1.2.3


From 9c28a205c06123b9f0a0c4d819ece9f5f552d004 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:53 -0700
Subject: mm/shmem: handle uffd-wp special pte in page fault handler

File-backed memories are prone to unmap/swap so the ptes are always
unstable, because they can be easily faulted back later using the page
cache.  This could lead to uffd-wp getting lost when unmapping or swapping
out such memory.  One example is shmem.  PTE markers are needed to store
those information.

This patch prepares it by handling uffd-wp pte markers first it is applied
elsewhere, so that the page fault handler can recognize uffd-wp pte
markers.

The handling of uffd-wp pte markers is similar to missing fault, it's just
that we'll handle this "missing fault" when we see the pte markers,
meanwhile we need to make sure the marker information is kept during
processing the fault.

This is a slow path of uffd-wp handling, because zapping of wr-protected
shmem ptes should be rare.  So far it should only trigger in two
conditions:

  (1) When trying to punch holes in shmem_fallocate(), there is an
      optimization to zap the pgtables before evicting the page.

  (2) When swapping out shmem pages.

Because of this, the page fault handling is simplifed too by not sending
the wr-protect message in the 1st page fault, instead the page will be
installed read-only, so the uffd-wp message will be generated in the next
fault, which will trigger the do_wp_page() path of general uffd-wp
handling.

Disable fault-around for all uffd-wp registered ranges for extra safety
just like uffd-minor fault, and clean the code up.

Link: https://lkml.kernel.org/r/20220405014844.14239-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/userfaultfd_k.h | 17 +++++++++++
 mm/memory.c                   | 67 +++++++++++++++++++++++++++++++++++++------
 2 files changed, 75 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 3354d9ddc35f..e7afcdfd4b46 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -96,6 +96,18 @@ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma)
 	return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR);
 }
 
+/*
+ * Don't do fault around for either WP or MINOR registered uffd range.  For
+ * MINOR registered range, fault around will be a total disaster and ptes can
+ * be installed without notifications; for WP it should mostly be fine as long
+ * as the fault around checks for pte_none() before the installation, however
+ * to be super safe we just forbid it.
+ */
+static inline bool uffd_disable_fault_around(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR);
+}
+
 static inline bool userfaultfd_missing(struct vm_area_struct *vma)
 {
 	return vma->vm_flags & VM_UFFD_MISSING;
@@ -236,6 +248,11 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
 {
 }
 
+static inline bool uffd_disable_fault_around(struct vm_area_struct *vma)
+{
+	return false;
+}
+
 #endif /* CONFIG_USERFAULTFD */
 
 static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry)
diff --git a/mm/memory.c b/mm/memory.c
index 878da420d97b..c16f873373a2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3559,6 +3559,39 @@ static inline bool should_try_to_free_swap(struct page *page,
 		page_count(page) == 2;
 }
 
+static vm_fault_t pte_marker_clear(struct vm_fault *vmf)
+{
+	vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
+				       vmf->address, &vmf->ptl);
+	/*
+	 * Be careful so that we will only recover a special uffd-wp pte into a
+	 * none pte.  Otherwise it means the pte could have changed, so retry.
+	 */
+	if (is_pte_marker(*vmf->pte))
+		pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
+	return 0;
+}
+
+/*
+ * This is actually a page-missing access, but with uffd-wp special pte
+ * installed.  It means this pte was wr-protected before being unmapped.
+ */
+static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf)
+{
+	/*
+	 * Just in case there're leftover special ptes even after the region
+	 * got unregistered - we can simply clear them.  We can also do that
+	 * proactively when e.g. when we do UFFDIO_UNREGISTER upon some uffd-wp
+	 * ranges, but it should be more efficient to be done lazily here.
+	 */
+	if (unlikely(!userfaultfd_wp(vmf->vma) || vma_is_anonymous(vmf->vma)))
+		return pte_marker_clear(vmf);
+
+	/* do_fault() can handle pte markers too like none pte */
+	return do_fault(vmf);
+}
+
 static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
 {
 	swp_entry_t entry = pte_to_swp_entry(vmf->orig_pte);
@@ -3572,8 +3605,11 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
 	if (WARN_ON_ONCE(vma_is_anonymous(vmf->vma) || !marker))
 		return VM_FAULT_SIGBUS;
 
-	/* TODO: handle pte markers */
-	return 0;
+	if (pte_marker_entry_uffd_wp(entry))
+		return pte_marker_handle_uffd_wp(vmf);
+
+	/* This is an unknown pte marker */
+	return VM_FAULT_SIGBUS;
 }
 
 /*
@@ -4157,6 +4193,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	bool uffd_wp = pte_marker_uffd_wp(vmf->orig_pte);
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	bool prefault = vmf->address != addr;
 	pte_t entry;
@@ -4171,6 +4208,8 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+	if (unlikely(uffd_wp))
+		entry = pte_mkuffd_wp(pte_wrprotect(entry));
 	/* copy-on-write page */
 	if (write && !(vma->vm_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
@@ -4352,9 +4391,21 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 	return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff);
 }
 
+/* Return true if we should do read fault-around, false otherwise */
+static inline bool should_fault_around(struct vm_fault *vmf)
+{
+	/* No ->map_pages?  No way to fault around... */
+	if (!vmf->vma->vm_ops->map_pages)
+		return false;
+
+	if (uffd_disable_fault_around(vmf->vma))
+		return false;
+
+	return fault_around_bytes >> PAGE_SHIFT > 1;
+}
+
 static vm_fault_t do_read_fault(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret = 0;
 
 	/*
@@ -4362,12 +4413,10 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf)
 	 * if page by the offset is not ready to be mapped (cold cache or
 	 * something).
 	 */
-	if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
-		if (likely(!userfaultfd_minor(vmf->vma))) {
-			ret = do_fault_around(vmf);
-			if (ret)
-				return ret;
-		}
+	if (should_fault_around(vmf)) {
+		ret = do_fault_around(vmf);
+		if (ret)
+			return ret;
 	}
 
 	ret = __do_fault(vmf);
-- 
cgit v1.2.3


From 999dad824c39ed14dee7c4412aae531ba9e74a90 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:53 -0700
Subject: mm/shmem: persist uffd-wp bit across zapping for file-backed

File-backed memory is prone to being unmapped at any time.  It means all
information in the pte will be dropped, including the uffd-wp flag.

To persist the uffd-wp flag, we'll use the pte markers.  This patch
teaches the zap code to understand uffd-wp and know when to keep or drop
the uffd-wp bit.

Add a new flag ZAP_FLAG_DROP_MARKER and set it in zap_details when we
don't want to persist such an information, for example, when destroying
the whole vma, or punching a hole in a shmem file.  For the rest cases we
should never drop the uffd-wp bit, or the wr-protect information will get
lost.

The new ZAP_FLAG_DROP_MARKER needs to be put into mm.h rather than
memory.c because it'll be further referenced in hugetlb files later.

Link: https://lkml.kernel.org/r/20220405014847.14295-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h        | 10 ++++++++++
 include/linux/mm_inline.h | 43 +++++++++++++++++++++++++++++++++++++++++
 mm/memory.c               | 49 ++++++++++++++++++++++++++++++++++++++++++++---
 mm/rmap.c                 |  8 ++++++++
 4 files changed, 107 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d63ba0e0e068..61786259e52a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3428,4 +3428,14 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 }
 #endif
 
+typedef unsigned int __bitwise zap_flags_t;
+
+/*
+ * Whether to drop the pte markers, for example, the uffd-wp information for
+ * file-backed memory.  This should only be specified when we will completely
+ * drop the page in the mm, either by truncation or unmapping of the vma.  By
+ * default, the flag is not set.
+ */
+#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
+
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index ac32125745ab..7b25b53c474a 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -6,6 +6,8 @@
 #include <linux/huge_mm.h>
 #include <linux/swap.h>
 #include <linux/string.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/swapops.h>
 
 /**
  * folio_is_file_lru - Should the folio be on a file LRU or anon LRU?
@@ -316,5 +318,46 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
 	return atomic_read(&mm->tlb_flush_pending) > 1;
 }
 
+/*
+ * If this pte is wr-protected by uffd-wp in any form, arm the special pte to
+ * replace a none pte.  NOTE!  This should only be called when *pte is already
+ * cleared so we will never accidentally replace something valuable.  Meanwhile
+ * none pte also means we are not demoting the pte so tlb flushed is not needed.
+ * E.g., when pte cleared the caller should have taken care of the tlb flush.
+ *
+ * Must be called with pgtable lock held so that no thread will see the none
+ * pte, and if they see it, they'll fault and serialize at the pgtable lock.
+ *
+ * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled.
+ */
+static inline void
+pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
+			      pte_t *pte, pte_t pteval)
+{
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
+	bool arm_uffd_pte = false;
+
+	/* The current status of the pte should be "cleared" before calling */
+	WARN_ON_ONCE(!pte_none(*pte));
+
+	if (vma_is_anonymous(vma) || !userfaultfd_wp(vma))
+		return;
+
+	/* A uffd-wp wr-protected normal pte */
+	if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval)))
+		arm_uffd_pte = true;
+
+	/*
+	 * A uffd-wp wr-protected swap pte.  Note: this should even cover an
+	 * existing pte marker with uffd-wp bit set.
+	 */
+	if (unlikely(pte_swp_uffd_wp_any(pteval)))
+		arm_uffd_pte = true;
+
+	if (unlikely(arm_uffd_pte))
+		set_pte_at(vma->vm_mm, addr, pte,
+			   make_pte_marker(PTE_MARKER_UFFD_WP));
+#endif
+}
 
 #endif
diff --git a/mm/memory.c b/mm/memory.c
index c16f873373a2..ecb1d58dcaef 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -74,6 +74,7 @@
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/vmalloc.h>
+#include <linux/mm_inline.h>
 
 #include <trace/events/kmem.h>
 
@@ -1306,6 +1307,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 struct zap_details {
 	struct folio *single_folio;	/* Locked folio to be unmapped */
 	bool even_cows;			/* Zap COWed private pages too? */
+	zap_flags_t zap_flags;		/* Extra flags for zapping */
 };
 
 /* Whether we should zap all COWed (private) pages too */
@@ -1334,6 +1336,29 @@ static inline bool should_zap_page(struct zap_details *details, struct page *pag
 	return !PageAnon(page);
 }
 
+static inline bool zap_drop_file_uffd_wp(struct zap_details *details)
+{
+	if (!details)
+		return false;
+
+	return details->zap_flags & ZAP_FLAG_DROP_MARKER;
+}
+
+/*
+ * This function makes sure that we'll replace the none pte with an uffd-wp
+ * swap special pte marker when necessary. Must be with the pgtable lock held.
+ */
+static inline void
+zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
+			      unsigned long addr, pte_t *pte,
+			      struct zap_details *details, pte_t pteval)
+{
+	if (zap_drop_file_uffd_wp(details))
+		return;
+
+	pte_install_uffd_wp_if_needed(vma, addr, pte, pteval);
+}
+
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end,
@@ -1371,6 +1396,8 @@ again:
 			ptent = ptep_get_and_clear_full(mm, addr, pte,
 							tlb->fullmm);
 			tlb_remove_tlb_entry(tlb, pte, addr);
+			zap_install_uffd_wp_if_needed(vma, addr, pte, details,
+						      ptent);
 			if (unlikely(!page))
 				continue;
 
@@ -1401,6 +1428,13 @@ again:
 			page = pfn_swap_entry_to_page(entry);
 			if (unlikely(!should_zap_page(details, page)))
 				continue;
+			/*
+			 * Both device private/exclusive mappings should only
+			 * work with anonymous page so far, so we don't need to
+			 * consider uffd-wp bit when zap. For more information,
+			 * see zap_install_uffd_wp_if_needed().
+			 */
+			WARN_ON_ONCE(!vma_is_anonymous(vma));
 			rss[mm_counter(page)]--;
 			if (is_device_private_entry(entry))
 				page_remove_rmap(page, vma, false);
@@ -1417,8 +1451,10 @@ again:
 			if (!should_zap_page(details, page))
 				continue;
 			rss[mm_counter(page)]--;
-		} else if (is_pte_marker_entry(entry)) {
-			/* By default, simply drop all pte markers when zap */
+		} else if (pte_marker_entry_uffd_wp(entry)) {
+			/* Only drop the uffd-wp marker if explicitly requested */
+			if (!zap_drop_file_uffd_wp(details))
+				continue;
 		} else if (is_hwpoison_entry(entry)) {
 			if (!should_zap_cows(details))
 				continue;
@@ -1427,6 +1463,7 @@ again:
 			WARN_ON_ONCE(1);
 		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+		zap_install_uffd_wp_if_needed(vma, addr, pte, details, ptent);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
 	add_mm_rss_vec(mm, rss);
@@ -1637,12 +1674,17 @@ void unmap_vmas(struct mmu_gather *tlb,
 		unsigned long end_addr)
 {
 	struct mmu_notifier_range range;
+	struct zap_details details = {
+		.zap_flags = ZAP_FLAG_DROP_MARKER,
+		/* Careful - we need to zap private pages too! */
+		.even_cows = true,
+	};
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
 				start_addr, end_addr);
 	mmu_notifier_invalidate_range_start(&range);
 	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
-		unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
+		unmap_single_vma(tlb, vma, start_addr, end_addr, &details);
 	mmu_notifier_invalidate_range_end(&range);
 }
 
@@ -3438,6 +3480,7 @@ void unmap_mapping_folio(struct folio *folio)
 
 	details.even_cows = false;
 	details.single_folio = folio;
+	details.zap_flags = ZAP_FLAG_DROP_MARKER;
 
 	i_mmap_lock_read(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
diff --git a/mm/rmap.c b/mm/rmap.c
index 72464378e1a6..94d6b24a1ac2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -73,6 +73,7 @@
 #include <linux/page_idle.h>
 #include <linux/memremap.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/mm_inline.h>
 
 #include <asm/tlbflush.h>
 
@@ -1585,6 +1586,13 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			pteval = ptep_clear_flush(vma, address, pvmw.pte);
 		}
 
+		/*
+		 * Now the pte is cleared. If this pte was uffd-wp armed,
+		 * we may want to replace a none pte with a marker pte if
+		 * it's file-backed, so we don't lose the tracking info.
+		 */
+		pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval);
+
 		/* Set the dirty flag on the folio now the pte is gone. */
 		if (pte_dirty(pteval))
 			folio_mark_dirty(folio);
-- 
cgit v1.2.3


From 6041c69179034278ac6d57f90a55b09e588f4b90 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:54 -0700
Subject: mm/hugetlb: take care of UFFDIO_COPY_MODE_WP

Pass the wp_copy variable into hugetlb_mcopy_atomic_pte() thoughout the
stack.  Apply the UFFD_WP bit if UFFDIO_COPY_MODE_WP is with UFFDIO_COPY.

Hugetlb pages are only managed by hugetlbfs, so we're safe even without
setting dirty bit in the huge pte if the page is installed as read-only.
However we'd better still keep the dirty bit set for a read-only
UFFDIO_COPY pte (when UFFDIO_COPY_MODE_WP bit is set), not only to match
what we do with shmem, but also because the page does contain dirty data
that the kernel just copied from the userspace.

Link: https://lkml.kernel.org/r/20220405014904.14643-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h |  6 ++++--
 mm/hugetlb.c            | 29 +++++++++++++++++++++++------
 mm/userfaultfd.c        | 14 +++++++++-----
 3 files changed, 36 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ac2ece9e9c79..159b253e523d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -160,7 +160,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte,
 				unsigned long dst_addr,
 				unsigned long src_addr,
 				enum mcopy_atomic_mode mode,
-				struct page **pagep);
+				struct page **pagep,
+				bool wp_copy);
 #endif /* CONFIG_USERFAULTFD */
 bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
@@ -356,7 +357,8 @@ static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 						unsigned long dst_addr,
 						unsigned long src_addr,
 						enum mcopy_atomic_mode mode,
-						struct page **pagep)
+						struct page **pagep,
+						bool wp_copy)
 {
 	BUG();
 	return 0;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0a2b3b8e765b..2550b434cabd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5821,7 +5821,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    unsigned long dst_addr,
 			    unsigned long src_addr,
 			    enum mcopy_atomic_mode mode,
-			    struct page **pagep)
+			    struct page **pagep,
+			    bool wp_copy)
 {
 	bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE);
 	struct hstate *h = hstate_vma(dst_vma);
@@ -5951,7 +5952,12 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		goto out_release_unlock;
 
 	ret = -EEXIST;
-	if (!huge_pte_none(huge_ptep_get(dst_pte)))
+	/*
+	 * We allow to overwrite a pte marker: consider when both MISSING|WP
+	 * registered, we firstly wr-protect a none pte which has no page cache
+	 * page backing it, then access the page.
+	 */
+	if (!huge_pte_none_mostly(huge_ptep_get(dst_pte)))
 		goto out_release_unlock;
 
 	if (vm_shared) {
@@ -5961,17 +5967,28 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		hugepage_add_new_anon_rmap(page, dst_vma, dst_addr);
 	}
 
-	/* For CONTINUE on a non-shared VMA, don't set VM_WRITE for CoW. */
-	if (is_continue && !vm_shared)
+	/*
+	 * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY
+	 * with wp flag set, don't set pte write bit.
+	 */
+	if (wp_copy || (is_continue && !vm_shared))
 		writable = 0;
 	else
 		writable = dst_vma->vm_flags & VM_WRITE;
 
 	_dst_pte = make_huge_pte(dst_vma, page, writable);
-	if (writable)
-		_dst_pte = huge_pte_mkdirty(_dst_pte);
+	/*
+	 * Always mark UFFDIO_COPY page dirty; note that this may not be
+	 * extremely important for hugetlbfs for now since swapping is not
+	 * supported, but we should still be clear in that this page cannot be
+	 * thrown away at will, even if write bit not set.
+	 */
+	_dst_pte = huge_pte_mkdirty(_dst_pte);
 	_dst_pte = pte_mkyoung(_dst_pte);
 
+	if (wp_copy)
+		_dst_pte = huge_pte_mkuffd_wp(_dst_pte);
+
 	set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
 
 	(void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte,
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 2b6ec3352147..be2a61f4b55e 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -305,7 +305,8 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 					      unsigned long dst_start,
 					      unsigned long src_start,
 					      unsigned long len,
-					      enum mcopy_atomic_mode mode)
+					      enum mcopy_atomic_mode mode,
+					      bool wp_copy)
 {
 	int vm_shared = dst_vma->vm_flags & VM_SHARED;
 	ssize_t err;
@@ -393,7 +394,7 @@ retry:
 		}
 
 		if (mode != MCOPY_ATOMIC_CONTINUE &&
-		    !huge_pte_none(huge_ptep_get(dst_pte))) {
+		    !huge_pte_none_mostly(huge_ptep_get(dst_pte))) {
 			err = -EEXIST;
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			i_mmap_unlock_read(mapping);
@@ -401,7 +402,8 @@ retry:
 		}
 
 		err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma,
-					       dst_addr, src_addr, mode, &page);
+					       dst_addr, src_addr, mode, &page,
+					       wp_copy);
 
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		i_mmap_unlock_read(mapping);
@@ -456,7 +458,8 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 				      unsigned long dst_start,
 				      unsigned long src_start,
 				      unsigned long len,
-				      enum mcopy_atomic_mode mode);
+				      enum mcopy_atomic_mode mode,
+				      bool wp_copy);
 #endif /* CONFIG_HUGETLB_PAGE */
 
 static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
@@ -576,7 +579,8 @@ retry:
 	 */
 	if (is_vm_hugetlb_page(dst_vma))
 		return  __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start,
-						src_start, len, mcopy_mode);
+					       src_start, len, mcopy_mode,
+					       wp_copy);
 
 	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;
-- 
cgit v1.2.3


From 5a90d5a103c2badfcf12d48e2fec350969e3f486 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:54 -0700
Subject: mm/hugetlb: handle UFFDIO_WRITEPROTECT

This starts from passing cp_flags into hugetlb_change_protection() so
hugetlb will be able to handle MM_CP_UFFD_WP[_RESOLVE] requests.

huge_pte_clear_uffd_wp() is introduced to handle the case where the
UFFDIO_WRITEPROTECT is requested upon migrating huge page entries.

Link: https://lkml.kernel.org/r/20220405014906.14708-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h |  6 ++++--
 mm/hugetlb.c            | 13 ++++++++++++-
 mm/mprotect.c           |  3 ++-
 mm/userfaultfd.c        |  8 ++++++++
 4 files changed, 26 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 159b253e523d..f1143f1fb444 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -211,7 +211,8 @@ struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pud);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
-		unsigned long address, unsigned long end, pgprot_t newprot);
+		unsigned long address, unsigned long end, pgprot_t newprot,
+		unsigned long cp_flags);
 
 bool is_hugetlb_entry_migration(pte_t pte);
 void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
@@ -397,7 +398,8 @@ static inline void move_hugetlb_state(struct page *oldpage,
 
 static inline unsigned long hugetlb_change_protection(
 			struct vm_area_struct *vma, unsigned long address,
-			unsigned long end, pgprot_t newprot)
+			unsigned long end, pgprot_t newprot,
+			unsigned long cp_flags)
 {
 	return 0;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2550b434cabd..4b8f413e011d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6233,7 +6233,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
-		unsigned long address, unsigned long end, pgprot_t newprot)
+		unsigned long address, unsigned long end,
+		pgprot_t newprot, unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long start = address;
@@ -6243,6 +6244,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	unsigned long pages = 0;
 	bool shared_pmd = false;
 	struct mmu_notifier_range range;
+	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
+	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
 	/*
 	 * In the case of shared PMDs, the area to flush could be beyond
@@ -6289,6 +6292,10 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 					entry = make_readable_migration_entry(
 								swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
+				if (uffd_wp)
+					newpte = pte_swp_mkuffd_wp(newpte);
+				else if (uffd_wp_resolve)
+					newpte = pte_swp_clear_uffd_wp(newpte);
 				set_huge_swap_pte_at(mm, address, ptep,
 						     newpte, huge_page_size(h));
 				pages++;
@@ -6303,6 +6310,10 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			old_pte = huge_ptep_modify_prot_start(vma, address, ptep);
 			pte = huge_pte_modify(old_pte, newprot);
 			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
+			if (uffd_wp)
+				pte = huge_pte_mkuffd_wp(huge_pte_wrprotect(pte));
+			else if (uffd_wp_resolve)
+				pte = huge_pte_clear_uffd_wp(pte);
 			huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte);
 			pages++;
 		}
diff --git a/mm/mprotect.c b/mm/mprotect.c
index cccad7974b3b..ba5592655ee3 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -460,7 +460,8 @@ unsigned long change_protection(struct mmu_gather *tlb,
 	BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL);
 
 	if (is_vm_hugetlb_page(vma))
-		pages = hugetlb_change_protection(vma, start, end, newprot);
+		pages = hugetlb_change_protection(vma, start, end, newprot,
+						  cp_flags);
 	else
 		pages = change_protection_range(tlb, vma, start, end, newprot,
 						cp_flags);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index be2a61f4b55e..01edc18902c5 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -705,6 +705,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 			atomic_t *mmap_changing)
 {
 	struct vm_area_struct *dst_vma;
+	unsigned long page_mask;
 	struct mmu_gather tlb;
 	pgprot_t newprot;
 	int err;
@@ -742,6 +743,13 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 	if (!vma_is_anonymous(dst_vma))
 		goto out_unlock;
 
+	if (is_vm_hugetlb_page(dst_vma)) {
+		err = -EINVAL;
+		page_mask = vma_kernel_pagesize(dst_vma) - 1;
+		if ((start & page_mask) || (len & page_mask))
+			goto out_unlock;
+	}
+
 	if (enable_wp)
 		newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE));
 	else
-- 
cgit v1.2.3


From 05e90bd05eea33fc77d6b11e121e2da01fee379f Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:55 -0700
Subject: mm/hugetlb: only drop uffd-wp special pte if required

As with shmem uffd-wp special ptes, only drop the uffd-wp special swap pte
if unmapping an entire vma or synchronized such that faults can not race
with the unmap operation.  This requires passing zap_flags all the way to
the lowest level hugetlb unmap routine: __unmap_hugepage_range.

In general, unmap calls originated in hugetlbfs code will pass the
ZAP_FLAG_DROP_MARKER flag as synchronization is in place to prevent
faults.  The exception is hole punch which will first unmap without any
synchronization.  Later when hole punch actually removes the page from the
file, it will check to see if there was a subsequent fault and if so take
the hugetlb fault mutex while unmapping again.  This second unmap will
pass in ZAP_FLAG_DROP_MARKER.

The justification of "whether to apply ZAP_FLAG_DROP_MARKER flag when
unmap a hugetlb range" is (IMHO): we should never reach a state when a
page fault could errornously fault in a page-cache page that was
wr-protected to be writable, even in an extremely short period.  That
could happen if e.g.  we pass ZAP_FLAG_DROP_MARKER when
hugetlbfs_punch_hole() calls hugetlb_vmdelete_list(), because if a page
faults after that call and before remove_inode_hugepages() is executed,
the page cache can be mapped writable again in the small racy window, that
can cause unexpected data overwritten.

[peterx@redhat.com: fix sparse warning]
  Link: https://lkml.kernel.org/r/Ylcdw8I1L5iAoWhb@xz-m1.local
[akpm@linux-foundation.org: move zap_flags_t from mm.h to mm_types.h to fix build issues]
Link: https://lkml.kernel.org/r/20220405014915.14873-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/hugetlbfs/inode.c     | 15 +++++++++------
 include/linux/hugetlb.h  |  8 +++++---
 include/linux/mm.h       |  2 --
 include/linux/mm_types.h |  2 ++
 mm/hugetlb.c             | 33 +++++++++++++++++++++++++--------
 mm/memory.c              |  5 ++++-
 6 files changed, 45 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 591599829e2a..5945caccf003 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -405,7 +405,8 @@ static void remove_huge_page(struct page *page)
 }
 
 static void
-hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
+hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
+		      zap_flags_t zap_flags)
 {
 	struct vm_area_struct *vma;
 
@@ -439,7 +440,7 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
 		}
 
 		unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
-									NULL);
+				     NULL, zap_flags);
 	}
 }
 
@@ -517,7 +518,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 				mutex_lock(&hugetlb_fault_mutex_table[hash]);
 				hugetlb_vmdelete_list(&mapping->i_mmap,
 					index * pages_per_huge_page(h),
-					(index + 1) * pages_per_huge_page(h));
+					(index + 1) * pages_per_huge_page(h),
+					ZAP_FLAG_DROP_MARKER);
 				i_mmap_unlock_write(mapping);
 			}
 
@@ -583,7 +585,8 @@ static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	i_mmap_lock_write(mapping);
 	i_size_write(inode, offset);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
-		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
+		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0,
+				      ZAP_FLAG_DROP_MARKER);
 	i_mmap_unlock_write(mapping);
 	remove_inode_hugepages(inode, offset, LLONG_MAX);
 }
@@ -616,8 +619,8 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		i_mmap_lock_write(mapping);
 		if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
 			hugetlb_vmdelete_list(&mapping->i_mmap,
-						hole_start >> PAGE_SHIFT,
-						hole_end  >> PAGE_SHIFT);
+					      hole_start >> PAGE_SHIFT,
+					      hole_end >> PAGE_SHIFT, 0);
 		i_mmap_unlock_write(mapping);
 		remove_inode_hugepages(inode, hole_start, hole_end);
 		inode_unlock(inode);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index f1143f1fb444..19cec415f546 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -143,11 +143,12 @@ long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			 unsigned long *, unsigned long *, long, unsigned int,
 			 int *);
 void unmap_hugepage_range(struct vm_area_struct *,
-			  unsigned long, unsigned long, struct page *);
+			  unsigned long, unsigned long, struct page *,
+			  zap_flags_t);
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 			  struct vm_area_struct *vma,
 			  unsigned long start, unsigned long end,
-			  struct page *ref_page);
+			  struct page *ref_page, zap_flags_t zap_flags);
 void hugetlb_report_meminfo(struct seq_file *);
 int hugetlb_report_node_meminfo(char *buf, int len, int nid);
 void hugetlb_show_meminfo(void);
@@ -406,7 +407,8 @@ static inline unsigned long hugetlb_change_protection(
 
 static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 			struct vm_area_struct *vma, unsigned long start,
-			unsigned long end, struct page *ref_page)
+			unsigned long end, struct page *ref_page,
+			zap_flags_t zap_flags)
 {
 	BUG();
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 61786259e52a..de32c0383387 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3428,8 +3428,6 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 }
 #endif
 
-typedef unsigned int __bitwise zap_flags_t;
-
 /*
  * Whether to drop the pte markers, for example, the uffd-wp information for
  * file-backed memory.  This should only be specified when we will completely
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index dd382270ae40..b34ff2cdbc4f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -863,4 +863,6 @@ enum fault_flag {
 	FAULT_FLAG_ORIG_PTE_VALID =	1 << 11,
 };
 
+typedef unsigned int __bitwise zap_flags_t;
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ec9774ed84c0..99281aecbd28 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4973,7 +4973,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 
 static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end,
-				   struct page *ref_page)
+				   struct page *ref_page, zap_flags_t zap_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -5029,7 +5029,18 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 		 * unmapped and its refcount is dropped, so just clear pte here.
 		 */
 		if (unlikely(!pte_present(pte))) {
-			huge_pte_clear(mm, address, ptep, sz);
+			/*
+			 * If the pte was wr-protected by uffd-wp in any of the
+			 * swap forms, meanwhile the caller does not want to
+			 * drop the uffd-wp bit in this zap, then replace the
+			 * pte with a marker.
+			 */
+			if (pte_swp_uffd_wp_any(pte) &&
+			    !(zap_flags & ZAP_FLAG_DROP_MARKER))
+				set_huge_pte_at(mm, address, ptep,
+						make_pte_marker(PTE_MARKER_UFFD_WP));
+			else
+				huge_pte_clear(mm, address, ptep, sz);
 			spin_unlock(ptl);
 			continue;
 		}
@@ -5057,7 +5068,11 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 		tlb_remove_huge_tlb_entry(h, tlb, ptep, address);
 		if (huge_pte_dirty(pte))
 			set_page_dirty(page);
-
+		/* Leave a uffd-wp pte marker if needed */
+		if (huge_pte_uffd_wp(pte) &&
+		    !(zap_flags & ZAP_FLAG_DROP_MARKER))
+			set_huge_pte_at(mm, address, ptep,
+					make_pte_marker(PTE_MARKER_UFFD_WP));
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		page_remove_rmap(page, vma, true);
 
@@ -5091,9 +5106,10 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 			  struct vm_area_struct *vma, unsigned long start,
-			  unsigned long end, struct page *ref_page)
+			  unsigned long end, struct page *ref_page,
+			  zap_flags_t zap_flags)
 {
-	__unmap_hugepage_range(tlb, vma, start, end, ref_page);
+	__unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
 
 	/*
 	 * Clear this flag so that x86's huge_pmd_share page_table_shareable
@@ -5109,12 +5125,13 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
-			  unsigned long end, struct page *ref_page)
+			  unsigned long end, struct page *ref_page,
+			  zap_flags_t zap_flags)
 {
 	struct mmu_gather tlb;
 
 	tlb_gather_mmu(&tlb, vma->vm_mm);
-	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
+	__unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags);
 	tlb_finish_mmu(&tlb);
 }
 
@@ -5169,7 +5186,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
 			unmap_hugepage_range(iter_vma, address,
-					     address + huge_page_size(h), page);
+					     address + huge_page_size(h), page, 0);
 	}
 	i_mmap_unlock_write(mapping);
 }
diff --git a/mm/memory.c b/mm/memory.c
index 8827157cf392..82adda885605 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1675,8 +1675,11 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			 * safe to do nothing in this case.
 			 */
 			if (vma->vm_file) {
+				zap_flags_t zap_flags = details ?
+				    details->zap_flags : 0;
 				i_mmap_lock_write(vma->vm_file->f_mapping);
-				__unmap_hugepage_range_final(tlb, vma, start, end, NULL);
+				__unmap_hugepage_range_final(tlb, vma, start, end,
+							     NULL, zap_flags);
 				i_mmap_unlock_write(vma->vm_file->f_mapping);
 			}
 		} else
-- 
cgit v1.2.3


From bc70fbf269fdff410b0b6d75c3770b9f59117b90 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:55 -0700
Subject: mm/hugetlb: handle uffd-wp during fork()

Firstly, we'll need to pass in dst_vma into copy_hugetlb_page_range()
because for uffd-wp it's the dst vma that matters on deciding how we
should treat uffd-wp protected ptes.

We should recognize pte markers during fork and do the pte copy if needed.

[lkp@intel.com: vma_needs_copy can be static]
  Link: https://lkml.kernel.org/r/Ylb0CGeFJlc4EzLk@7ec4ff11d4ae
Link: https://lkml.kernel.org/r/20220405014918.14932-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h |  7 +++++--
 mm/hugetlb.c            | 42 ++++++++++++++++++++++++++++--------------
 mm/memory.c             |  4 ++--
 3 files changed, 35 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 19cec415f546..04f0186b089b 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -137,7 +137,8 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 			     struct vm_area_struct *new_vma,
 			     unsigned long old_addr, unsigned long new_addr,
 			     unsigned long len);
-int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
+int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
+			    struct vm_area_struct *, struct vm_area_struct *);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			 struct page **, struct vm_area_struct **,
 			 unsigned long *, unsigned long *, long, unsigned int,
@@ -269,7 +270,9 @@ static inline struct page *follow_huge_addr(struct mm_struct *mm,
 }
 
 static inline int copy_hugetlb_page_range(struct mm_struct *dst,
-			struct mm_struct *src, struct vm_area_struct *vma)
+					  struct mm_struct *src,
+					  struct vm_area_struct *dst_vma,
+					  struct vm_area_struct *src_vma)
 {
 	BUG();
 	return 0;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 99281aecbd28..01f0e2e5ab48 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4719,23 +4719,24 @@ hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr
 }
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
-			    struct vm_area_struct *vma)
+			    struct vm_area_struct *dst_vma,
+			    struct vm_area_struct *src_vma)
 {
 	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
-	bool cow = is_cow_mapping(vma->vm_flags);
-	struct hstate *h = hstate_vma(vma);
+	bool cow = is_cow_mapping(src_vma->vm_flags);
+	struct hstate *h = hstate_vma(src_vma);
 	unsigned long sz = huge_page_size(h);
 	unsigned long npages = pages_per_huge_page(h);
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = src_vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
 	int ret = 0;
 
 	if (cow) {
-		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src,
-					vma->vm_start,
-					vma->vm_end);
+		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src_vma, src,
+					src_vma->vm_start,
+					src_vma->vm_end);
 		mmu_notifier_invalidate_range_start(&range);
 		mmap_assert_write_locked(src);
 		raw_write_seqcount_begin(&src->write_protect_seq);
@@ -4749,12 +4750,12 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		i_mmap_lock_read(mapping);
 	}
 
-	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
+	for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr, sz);
 		if (!src_pte)
 			continue;
-		dst_pte = huge_pte_alloc(dst, vma, addr, sz);
+		dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
 			break;
@@ -4789,6 +4790,7 @@ again:
 		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
 				    is_hugetlb_entry_hwpoisoned(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
+			bool uffd_wp = huge_pte_uffd_wp(entry);
 
 			if (!is_readable_migration_entry(swp_entry) && cow) {
 				/*
@@ -4798,10 +4800,21 @@ again:
 				swp_entry = make_readable_migration_entry(
 							swp_offset(swp_entry));
 				entry = swp_entry_to_pte(swp_entry);
+				if (userfaultfd_wp(src_vma) && uffd_wp)
+					entry = huge_pte_mkuffd_wp(entry);
 				set_huge_swap_pte_at(src, addr, src_pte,
 						     entry, sz);
 			}
+			if (!userfaultfd_wp(dst_vma) && uffd_wp)
+				entry = huge_pte_clear_uffd_wp(entry);
 			set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
+		} else if (unlikely(is_pte_marker(entry))) {
+			/*
+			 * We copy the pte marker only if the dst vma has
+			 * uffd-wp enabled.
+			 */
+			if (userfaultfd_wp(dst_vma))
+				set_huge_pte_at(dst, addr, dst_pte, entry);
 		} else {
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
@@ -4819,20 +4832,21 @@ again:
 			 */
 			if (!PageAnon(ptepage)) {
 				page_dup_file_rmap(ptepage, true);
-			} else if (page_try_dup_anon_rmap(ptepage, true, vma)) {
+			} else if (page_try_dup_anon_rmap(ptepage, true,
+							  src_vma)) {
 				pte_t src_pte_old = entry;
 				struct page *new;
 
 				spin_unlock(src_ptl);
 				spin_unlock(dst_ptl);
 				/* Do not use reserve as it's private owned */
-				new = alloc_huge_page(vma, addr, 1);
+				new = alloc_huge_page(dst_vma, addr, 1);
 				if (IS_ERR(new)) {
 					put_page(ptepage);
 					ret = PTR_ERR(new);
 					break;
 				}
-				copy_user_huge_page(new, ptepage, addr, vma,
+				copy_user_huge_page(new, ptepage, addr, dst_vma,
 						    npages);
 				put_page(ptepage);
 
@@ -4842,13 +4856,13 @@ again:
 				spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 				entry = huge_ptep_get(src_pte);
 				if (!pte_same(src_pte_old, entry)) {
-					restore_reserve_on_error(h, vma, addr,
+					restore_reserve_on_error(h, dst_vma, addr,
 								new);
 					put_page(new);
 					/* dst_entry won't change as in child */
 					goto again;
 				}
-				hugetlb_install_page(vma, dst_pte, addr, new);
+				hugetlb_install_page(dst_vma, dst_pte, addr, new);
 				spin_unlock(src_ptl);
 				spin_unlock(dst_ptl);
 				continue;
diff --git a/mm/memory.c b/mm/memory.c
index 82adda885605..f4161fb07ffa 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1234,7 +1234,7 @@ copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
  * false when we can speed up fork() by allowing lazy page faults later until
  * when the child accesses the memory range.
  */
-bool
+static bool
 vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 {
 	/*
@@ -1278,7 +1278,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		return 0;
 
 	if (is_vm_hugetlb_page(src_vma))
-		return copy_hugetlb_page_range(dst_mm, src_mm, src_vma);
+		return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma);
 
 	if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
 		/*
-- 
cgit v1.2.3


From b1f9e876862d8f7176299ec4fb2108bc1045cbc8 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 12 May 2022 20:22:56 -0700
Subject: mm/uffd: enable write protection for shmem & hugetlbfs

We've had all the necessary changes ready for both shmem and hugetlbfs.
Turn on all the shmem/hugetlbfs switches for userfaultfd-wp.

We can expand UFFD_API_RANGE_IOCTLS_BASIC with _UFFDIO_WRITEPROTECT too
because all existing types now support write protection mode.

Since vma_can_userfault() will be used elsewhere, move into userfaultfd_k.h.

Link: https://lkml.kernel.org/r/20220405014926.15101-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/userfaultfd.c                 | 21 +++------------------
 include/linux/userfaultfd_k.h    | 20 ++++++++++++++++++++
 include/uapi/linux/userfaultfd.h | 10 ++++++++--
 mm/userfaultfd.c                 |  9 +++------
 4 files changed, 34 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 78b68e0f9774..e943370107d0 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1258,24 +1258,6 @@ static __always_inline int validate_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline bool vma_can_userfault(struct vm_area_struct *vma,
-				     unsigned long vm_flags)
-{
-	/* FIXME: add WP support to hugetlbfs and shmem */
-	if (vm_flags & VM_UFFD_WP) {
-		if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma))
-			return false;
-	}
-
-	if (vm_flags & VM_UFFD_MINOR) {
-		if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
-			return false;
-	}
-
-	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
-	       vma_is_shmem(vma);
-}
-
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				unsigned long arg)
 {
@@ -1956,6 +1938,9 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 #endif
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 	uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
+#endif
+#ifndef CONFIG_PTE_MARKER_UFFD_WP
+	uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
 #endif
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index e7afcdfd4b46..732b522bacb7 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -18,6 +18,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <asm-generic/pgtable_uffd.h>
+#include <linux/hugetlb_inline.h>
 
 /* The set of all possible UFFD-related VM flags. */
 #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR)
@@ -140,6 +141,25 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 	return vma->vm_flags & __VM_UFFD_FLAGS;
 }
 
+static inline bool vma_can_userfault(struct vm_area_struct *vma,
+				     unsigned long vm_flags)
+{
+	if (vm_flags & VM_UFFD_MINOR)
+		return is_vm_hugetlb_page(vma) || vma_is_shmem(vma);
+
+#ifndef CONFIG_PTE_MARKER_UFFD_WP
+	/*
+	 * If user requested uffd-wp but not enabled pte markers for
+	 * uffd-wp, then shmem & hugetlbfs are not supported but only
+	 * anonymous.
+	 */
+	if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma))
+		return false;
+#endif
+	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
+	    vma_is_shmem(vma);
+}
+
 extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
 extern void dup_userfaultfd_complete(struct list_head *);
 
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index ef739054cb1c..7d32b1e797fb 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -33,7 +33,8 @@
 			   UFFD_FEATURE_THREAD_ID |		\
 			   UFFD_FEATURE_MINOR_HUGETLBFS |	\
 			   UFFD_FEATURE_MINOR_SHMEM |		\
-			   UFFD_FEATURE_EXACT_ADDRESS)
+			   UFFD_FEATURE_EXACT_ADDRESS |		\
+			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -47,7 +48,8 @@
 #define UFFD_API_RANGE_IOCTLS_BASIC		\
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
-	 (__u64)1 << _UFFDIO_CONTINUE)
+	 (__u64)1 << _UFFDIO_CONTINUE |		\
+	 (__u64)1 << _UFFDIO_WRITEPROTECT)
 
 /*
  * Valid ioctl command number range with this API is from 0x00 to
@@ -194,6 +196,9 @@ struct uffdio_api {
 	 * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page
 	 * faults would be provided and the offset within the page would not be
 	 * masked.
+	 *
+	 * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd
+	 * write-protection mode is supported on both shmem and hugetlbfs.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -207,6 +212,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_MINOR_HUGETLBFS		(1<<9)
 #define UFFD_FEATURE_MINOR_SHMEM		(1<<10)
 #define UFFD_FEATURE_EXACT_ADDRESS		(1<<11)
+#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM		(1<<12)
 	__u64 features;
 
 	__u64 ioctls;
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 01edc18902c5..4f4892a5f767 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -732,15 +732,12 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 
 	err = -ENOENT;
 	dst_vma = find_dst_vma(dst_mm, start, len);
-	/*
-	 * Make sure the vma is not shared, that the dst range is
-	 * both valid and fully within a single existing vma.
-	 */
-	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+
+	if (!dst_vma)
 		goto out_unlock;
 	if (!userfaultfd_wp(dst_vma))
 		goto out_unlock;
-	if (!vma_is_anonymous(dst_vma))
+	if (!vma_can_userfault(dst_vma, dst_vma->vm_flags))
 		goto out_unlock;
 
 	if (is_vm_hugetlb_page(dst_vma)) {
-- 
cgit v1.2.3


From b48d8a8e5ce53e3114a1ffe96563e3555b51d40b Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Thu, 12 May 2022 20:22:57 -0700
Subject: mm: page_isolation: move has_unmovable_pages() to mm/page_isolation.c

Patch series "Use pageblock_order for cma and alloc_contig_range alignment", v11.

This patchset tries to remove the MAX_ORDER-1 alignment requirement for CMA
and alloc_contig_range(). It prepares for my upcoming changes to make
MAX_ORDER adjustable at boot time[1].

The MAX_ORDER - 1 alignment requirement comes from that
alloc_contig_range() isolates pageblocks to remove free memory from buddy
allocator but isolating only a subset of pageblocks within a page spanning
across multiple pageblocks causes free page accounting issues.  Isolated
page might not be put into the right free list, since the code assumes the
migratetype of the first pageblock as the whole free page migratetype.
This is based on the discussion at [2].

To remove the requirement, this patchset:
1. isolates pages at pageblock granularity instead of
   max(MAX_ORDER_NR_PAEGS, pageblock_nr_pages);
2. splits free pages across the specified range or migrates in-use pages
   across the specified range then splits the freed page to avoid free page
   accounting issues (it happens when multiple pageblocks within a single page
   have different migratetypes);
3. only checks unmovable pages within the range instead of MAX_ORDER - 1 aligned
   range during isolation to avoid alloc_contig_range() failure when pageblocks
   within a MAX_ORDER - 1 aligned range are allocated separately.
4. returns pages not in the range as it did before.

One optimization might come later:
1. make MIGRATE_ISOLATE a separate bit to be able to restore the original
   migratetypes when isolation fails in the middle of the range.

[1] https://lore.kernel.org/linux-mm/20210805190253.2795604-1-zi.yan@sent.com/
[2] https://lore.kernel.org/linux-mm/d19fb078-cb9b-f60f-e310-fdeea1b947d2@redhat.com/


This patch (of 6):

has_unmovable_pages() is only used in mm/page_isolation.c.  Move it from
mm/page_alloc.c and make it static.

Link: https://lkml.kernel.org/r/20220425143118.2850746-2-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Eric Ren <renzhengeek@gmail.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Minchan Kim <minchan@kernel.org>
Cc: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-isolation.h |   2 -
 mm/page_alloc.c                | 119 -----------------------------------------
 mm/page_isolation.c            | 119 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 119 insertions(+), 121 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 572458016331..e14eddf6741a 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -33,8 +33,6 @@ static inline bool is_migrate_isolate(int migratetype)
 #define MEMORY_OFFLINE	0x1
 #define REPORT_FAILURE	0x2
 
-struct page *has_unmovable_pages(struct zone *zone, struct page *page,
-				 int migratetype, int flags);
 void set_pageblock_migratetype(struct page *page, int migratetype);
 int move_freepages_block(struct zone *zone, struct page *page,
 				int migratetype, int *num_movable);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ddb0575c6b4a..0756f046b644 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8918,125 +8918,6 @@ void *__init alloc_large_system_hash(const char *tablename,
 	return table;
 }
 
-/*
- * This function checks whether pageblock includes unmovable pages or not.
- *
- * PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
- * check without lock_page also may miss some movable non-lru pages at
- * race condition. So you can't expect this function should be exact.
- *
- * Returns a page without holding a reference. If the caller wants to
- * dereference that page (e.g., dumping), it has to make sure that it
- * cannot get removed (e.g., via memory unplug) concurrently.
- *
- */
-struct page *has_unmovable_pages(struct zone *zone, struct page *page,
-				 int migratetype, int flags)
-{
-	unsigned long iter = 0;
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long offset = pfn % pageblock_nr_pages;
-
-	if (is_migrate_cma_page(page)) {
-		/*
-		 * CMA allocations (alloc_contig_range) really need to mark
-		 * isolate CMA pageblocks even when they are not movable in fact
-		 * so consider them movable here.
-		 */
-		if (is_migrate_cma(migratetype))
-			return NULL;
-
-		return page;
-	}
-
-	for (; iter < pageblock_nr_pages - offset; iter++) {
-		page = pfn_to_page(pfn + iter);
-
-		/*
-		 * Both, bootmem allocations and memory holes are marked
-		 * PG_reserved and are unmovable. We can even have unmovable
-		 * allocations inside ZONE_MOVABLE, for example when
-		 * specifying "movablecore".
-		 */
-		if (PageReserved(page))
-			return page;
-
-		/*
-		 * If the zone is movable and we have ruled out all reserved
-		 * pages then it should be reasonably safe to assume the rest
-		 * is movable.
-		 */
-		if (zone_idx(zone) == ZONE_MOVABLE)
-			continue;
-
-		/*
-		 * Hugepages are not in LRU lists, but they're movable.
-		 * THPs are on the LRU, but need to be counted as #small pages.
-		 * We need not scan over tail pages because we don't
-		 * handle each tail page individually in migration.
-		 */
-		if (PageHuge(page) || PageTransCompound(page)) {
-			struct page *head = compound_head(page);
-			unsigned int skip_pages;
-
-			if (PageHuge(page)) {
-				if (!hugepage_migration_supported(page_hstate(head)))
-					return page;
-			} else if (!PageLRU(head) && !__PageMovable(head)) {
-				return page;
-			}
-
-			skip_pages = compound_nr(head) - (page - head);
-			iter += skip_pages - 1;
-			continue;
-		}
-
-		/*
-		 * We can't use page_count without pin a page
-		 * because another CPU can free compound page.
-		 * This check already skips compound tails of THP
-		 * because their page->_refcount is zero at all time.
-		 */
-		if (!page_ref_count(page)) {
-			if (PageBuddy(page))
-				iter += (1 << buddy_order(page)) - 1;
-			continue;
-		}
-
-		/*
-		 * The HWPoisoned page may be not in buddy system, and
-		 * page_count() is not 0.
-		 */
-		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
-			continue;
-
-		/*
-		 * We treat all PageOffline() pages as movable when offlining
-		 * to give drivers a chance to decrement their reference count
-		 * in MEM_GOING_OFFLINE in order to indicate that these pages
-		 * can be offlined as there are no direct references anymore.
-		 * For actually unmovable PageOffline() where the driver does
-		 * not support this, we will fail later when trying to actually
-		 * move these pages that still have a reference count > 0.
-		 * (false negatives in this function only)
-		 */
-		if ((flags & MEMORY_OFFLINE) && PageOffline(page))
-			continue;
-
-		if (__PageMovable(page) || PageLRU(page))
-			continue;
-
-		/*
-		 * If there are RECLAIMABLE pages, we need to check
-		 * it.  But now, memory offline itself doesn't call
-		 * shrink_node_slabs() and it still to be fixed.
-		 */
-		return page;
-	}
-	return NULL;
-}
-
 #ifdef CONFIG_CONTIG_ALLOC
 static unsigned long pfn_max_align_down(unsigned long pfn)
 {
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index ff0ea6308299..df49f86a6ed1 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -15,6 +15,125 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/page_isolation.h>
 
+/*
+ * This function checks whether pageblock includes unmovable pages or not.
+ *
+ * PageLRU check without isolation or lru_lock could race so that
+ * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
+ * check without lock_page also may miss some movable non-lru pages at
+ * race condition. So you can't expect this function should be exact.
+ *
+ * Returns a page without holding a reference. If the caller wants to
+ * dereference that page (e.g., dumping), it has to make sure that it
+ * cannot get removed (e.g., via memory unplug) concurrently.
+ *
+ */
+static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+				 int migratetype, int flags)
+{
+	unsigned long iter = 0;
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long offset = pfn % pageblock_nr_pages;
+
+	if (is_migrate_cma_page(page)) {
+		/*
+		 * CMA allocations (alloc_contig_range) really need to mark
+		 * isolate CMA pageblocks even when they are not movable in fact
+		 * so consider them movable here.
+		 */
+		if (is_migrate_cma(migratetype))
+			return NULL;
+
+		return page;
+	}
+
+	for (; iter < pageblock_nr_pages - offset; iter++) {
+		page = pfn_to_page(pfn + iter);
+
+		/*
+		 * Both, bootmem allocations and memory holes are marked
+		 * PG_reserved and are unmovable. We can even have unmovable
+		 * allocations inside ZONE_MOVABLE, for example when
+		 * specifying "movablecore".
+		 */
+		if (PageReserved(page))
+			return page;
+
+		/*
+		 * If the zone is movable and we have ruled out all reserved
+		 * pages then it should be reasonably safe to assume the rest
+		 * is movable.
+		 */
+		if (zone_idx(zone) == ZONE_MOVABLE)
+			continue;
+
+		/*
+		 * Hugepages are not in LRU lists, but they're movable.
+		 * THPs are on the LRU, but need to be counted as #small pages.
+		 * We need not scan over tail pages because we don't
+		 * handle each tail page individually in migration.
+		 */
+		if (PageHuge(page) || PageTransCompound(page)) {
+			struct page *head = compound_head(page);
+			unsigned int skip_pages;
+
+			if (PageHuge(page)) {
+				if (!hugepage_migration_supported(page_hstate(head)))
+					return page;
+			} else if (!PageLRU(head) && !__PageMovable(head)) {
+				return page;
+			}
+
+			skip_pages = compound_nr(head) - (page - head);
+			iter += skip_pages - 1;
+			continue;
+		}
+
+		/*
+		 * We can't use page_count without pin a page
+		 * because another CPU can free compound page.
+		 * This check already skips compound tails of THP
+		 * because their page->_refcount is zero at all time.
+		 */
+		if (!page_ref_count(page)) {
+			if (PageBuddy(page))
+				iter += (1 << buddy_order(page)) - 1;
+			continue;
+		}
+
+		/*
+		 * The HWPoisoned page may be not in buddy system, and
+		 * page_count() is not 0.
+		 */
+		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
+			continue;
+
+		/*
+		 * We treat all PageOffline() pages as movable when offlining
+		 * to give drivers a chance to decrement their reference count
+		 * in MEM_GOING_OFFLINE in order to indicate that these pages
+		 * can be offlined as there are no direct references anymore.
+		 * For actually unmovable PageOffline() where the driver does
+		 * not support this, we will fail later when trying to actually
+		 * move these pages that still have a reference count > 0.
+		 * (false negatives in this function only)
+		 */
+		if ((flags & MEMORY_OFFLINE) && PageOffline(page))
+			continue;
+
+		if (__PageMovable(page) || PageLRU(page))
+			continue;
+
+		/*
+		 * If there are RECLAIMABLE pages, we need to check
+		 * it.  But now, memory offline itself doesn't call
+		 * shrink_node_slabs() and it still to be fixed.
+		 */
+		return page;
+	}
+	return NULL;
+}
+
 static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
 {
 	struct zone *zone = page_zone(page);
-- 
cgit v1.2.3


From b2c9e2fbba32539626522b6aed30d1dde7b7e971 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Thu, 12 May 2022 20:22:58 -0700
Subject: mm: make alloc_contig_range work at pageblock granularity

alloc_contig_range() worked at MAX_ORDER_NR_PAGES granularity to avoid
merging pageblocks with different migratetypes.  It might unnecessarily
convert extra pageblocks at the beginning and at the end of the range.
Change alloc_contig_range() to work at pageblock granularity.

Special handling is needed for free pages and in-use pages across the
boundaries of the range specified by alloc_contig_range().  Because these=

Partially isolated pages causes free page accounting issues.  The free
pages will be split and freed into separate migratetype lists; the in-use=

Pages will be migrated then the freed pages will be handled in the
aforementioned way.

[ziy@nvidia.com: fix deadlock/crash]
  Link: https://lkml.kernel.org/r/23A7297E-6C84-4138-A9FE-3598234004E6@nvidia.com
Link: https://lkml.kernel.org/r/20220425143118.2850746-4-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Eric Ren <renzhengeek@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-isolation.h |   4 +-
 mm/internal.h                  |   6 ++
 mm/memory_hotplug.c            |   3 +-
 mm/page_alloc.c                |  54 +++++++++---
 mm/page_isolation.c            | 193 +++++++++++++++++++++++++++++++++++++++--
 5 files changed, 242 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index e14eddf6741a..5456b7be38ae 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -42,7 +42,7 @@ int move_freepages_block(struct zone *zone, struct page *page,
  */
 int
 start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			 unsigned migratetype, int flags);
+			 int migratetype, int flags, gfp_t gfp_flags);
 
 /*
  * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
@@ -50,7 +50,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  */
 void
 undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			unsigned migratetype);
+			int migratetype);
 
 /*
  * Test all pages in [start_pfn, end_pfn) are isolated or not.
diff --git a/mm/internal.h b/mm/internal.h
index ddd09245a6db..a770029beb08 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -359,6 +359,9 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
 			  phys_addr_t min_addr,
 			  int nid, bool exact_nid);
 
+void split_free_page(struct page *free_page,
+				int order, unsigned long split_pfn_offset);
+
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
 /*
@@ -422,6 +425,9 @@ isolate_freepages_range(struct compact_control *cc,
 int
 isolate_migratepages_range(struct compact_control *cc,
 			   unsigned long low_pfn, unsigned long end_pfn);
+
+int __alloc_contig_migrate_range(struct compact_control *cc,
+					unsigned long start, unsigned long end);
 #endif
 int find_suitable_fallback(struct free_area *area, unsigned int order,
 			int migratetype, bool only_stealable, bool *can_steal);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e99fd60548f5..945191708ef6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1837,7 +1837,8 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	/* set above range as isolated */
 	ret = start_isolate_page_range(start_pfn, end_pfn,
 				       MIGRATE_MOVABLE,
-				       MEMORY_OFFLINE | REPORT_FAILURE);
+				       MEMORY_OFFLINE | REPORT_FAILURE,
+				       GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL);
 	if (ret) {
 		reason = "failure to isolate range";
 		goto failed_removal_pcplists_disabled;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0756f046b644..0c7252ed14a0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1094,6 +1094,43 @@ done_merging:
 		page_reporting_notify_free(order);
 }
 
+/**
+ * split_free_page() -- split a free page at split_pfn_offset
+ * @free_page:		the original free page
+ * @order:		the order of the page
+ * @split_pfn_offset:	split offset within the page
+ *
+ * It is used when the free page crosses two pageblocks with different migratetypes
+ * at split_pfn_offset within the page. The split free page will be put into
+ * separate migratetype lists afterwards. Otherwise, the function achieves
+ * nothing.
+ */
+void split_free_page(struct page *free_page,
+				int order, unsigned long split_pfn_offset)
+{
+	struct zone *zone = page_zone(free_page);
+	unsigned long free_page_pfn = page_to_pfn(free_page);
+	unsigned long pfn;
+	unsigned long flags;
+	int free_page_order;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	del_page_from_free_list(free_page, zone, order);
+	for (pfn = free_page_pfn;
+	     pfn < free_page_pfn + (1UL << order);) {
+		int mt = get_pfnblock_migratetype(pfn_to_page(pfn), pfn);
+
+		free_page_order = ffs(split_pfn_offset) - 1;
+		__free_one_page(pfn_to_page(pfn), pfn, zone, free_page_order,
+				mt, FPI_NONE);
+		pfn += 1UL << free_page_order;
+		split_pfn_offset -= (1UL << free_page_order);
+		/* we have done the first part, now switch to second part */
+		if (split_pfn_offset == 0)
+			split_pfn_offset = (1UL << order) - (pfn - free_page_pfn);
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+}
 /*
  * A bad page could be due to a number of fields. Instead of multiple branches,
  * try and check multiple fields with one check. The caller must do a detailed
@@ -8951,7 +8988,7 @@ static inline void alloc_contig_dump_pages(struct list_head *page_list)
 #endif
 
 /* [start, end) must belong to a single zone. */
-static int __alloc_contig_migrate_range(struct compact_control *cc,
+int __alloc_contig_migrate_range(struct compact_control *cc,
 					unsigned long start, unsigned long end)
 {
 	/* This function is based on compact_zone() from compaction.c. */
@@ -9034,7 +9071,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		       unsigned migratetype, gfp_t gfp_mask)
 {
 	unsigned long outer_start, outer_end;
-	unsigned int order;
+	int order;
 	int ret = 0;
 
 	struct compact_control cc = {
@@ -9053,14 +9090,11 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 * What we do here is we mark all pageblocks in range as
 	 * MIGRATE_ISOLATE.  Because pageblock and max order pages may
 	 * have different sizes, and due to the way page allocator
-	 * work, we align the range to biggest of the two pages so
-	 * that page allocator won't try to merge buddies from
-	 * different pageblocks and change MIGRATE_ISOLATE to some
-	 * other migration type.
+	 * work, start_isolate_page_range() has special handlings for this.
 	 *
 	 * Once the pageblocks are marked as MIGRATE_ISOLATE, we
 	 * migrate the pages from an unaligned range (ie. pages that
-	 * we are interested in).  This will put all the pages in
+	 * we are interested in). This will put all the pages in
 	 * range back to page allocator as MIGRATE_ISOLATE.
 	 *
 	 * When this is done, we take the pages in range from page
@@ -9074,9 +9108,9 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 */
 
 	ret = start_isolate_page_range(pfn_max_align_down(start),
-				       pfn_max_align_up(end), migratetype, 0);
+				pfn_max_align_up(end), migratetype, 0, gfp_mask);
 	if (ret)
-		return ret;
+		goto done;
 
 	drain_all_pages(cc.zone);
 
@@ -9096,7 +9130,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	ret = 0;
 
 	/*
-	 * Pages from [start, end) are within a MAX_ORDER_NR_PAGES
+	 * Pages from [start, end) are within a pageblock_nr_pages
 	 * aligned blocks that are marked as MIGRATE_ISOLATE.  What's
 	 * more, all pages in [start, end) are free in page allocator.
 	 * What we are going to do is to allocate all pages from
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index c2f7a8bb634d..8a0f16d2e4c3 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -203,7 +203,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	return -EBUSY;
 }
 
-static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
+static void unset_migratetype_isolate(struct page *page, int migratetype)
 {
 	struct zone *zone;
 	unsigned long flags, nr_pages;
@@ -279,6 +279,166 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
 	return NULL;
 }
 
+/**
+ * isolate_single_pageblock() -- tries to isolate a pageblock that might be
+ * within a free or in-use page.
+ * @boundary_pfn:		pageblock-aligned pfn that a page might cross
+ * @gfp_flags:			GFP flags used for migrating pages
+ * @isolate_before:	isolate the pageblock before the boundary_pfn
+ *
+ * Free and in-use pages can be as big as MAX_ORDER-1 and contain more than one
+ * pageblock. When not all pageblocks within a page are isolated at the same
+ * time, free page accounting can go wrong. For example, in the case of
+ * MAX_ORDER-1 = pageblock_order + 1, a MAX_ORDER-1 page has two pagelbocks.
+ * [         MAX_ORDER-1         ]
+ * [  pageblock0  |  pageblock1  ]
+ * When either pageblock is isolated, if it is a free page, the page is not
+ * split into separate migratetype lists, which is supposed to; if it is an
+ * in-use page and freed later, __free_one_page() does not split the free page
+ * either. The function handles this by splitting the free page or migrating
+ * the in-use page then splitting the free page.
+ */
+static int isolate_single_pageblock(unsigned long boundary_pfn, gfp_t gfp_flags,
+			bool isolate_before)
+{
+	unsigned char saved_mt;
+	unsigned long start_pfn;
+	unsigned long isolate_pageblock;
+	unsigned long pfn;
+	struct zone *zone;
+
+	VM_BUG_ON(!IS_ALIGNED(boundary_pfn, pageblock_nr_pages));
+
+	if (isolate_before)
+		isolate_pageblock = boundary_pfn - pageblock_nr_pages;
+	else
+		isolate_pageblock = boundary_pfn;
+
+	/*
+	 * scan at the beginning of MAX_ORDER_NR_PAGES aligned range to avoid
+	 * only isolating a subset of pageblocks from a bigger than pageblock
+	 * free or in-use page. Also make sure all to-be-isolated pageblocks
+	 * are within the same zone.
+	 */
+	zone  = page_zone(pfn_to_page(isolate_pageblock));
+	start_pfn  = max(ALIGN_DOWN(isolate_pageblock, MAX_ORDER_NR_PAGES),
+				      zone->zone_start_pfn);
+
+	saved_mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
+	set_pageblock_migratetype(pfn_to_page(isolate_pageblock), MIGRATE_ISOLATE);
+
+	/*
+	 * Bail out early when the to-be-isolated pageblock does not form
+	 * a free or in-use page across boundary_pfn:
+	 *
+	 * 1. isolate before boundary_pfn: the page after is not online
+	 * 2. isolate after boundary_pfn: the page before is not online
+	 *
+	 * This also ensures correctness. Without it, when isolate after
+	 * boundary_pfn and [start_pfn, boundary_pfn) are not online,
+	 * __first_valid_page() will return unexpected NULL in the for loop
+	 * below.
+	 */
+	if (isolate_before) {
+		if (!pfn_to_online_page(boundary_pfn))
+			return 0;
+	} else {
+		if (!pfn_to_online_page(boundary_pfn - 1))
+			return 0;
+	}
+
+	for (pfn = start_pfn; pfn < boundary_pfn;) {
+		struct page *page = __first_valid_page(pfn, boundary_pfn - pfn);
+
+		VM_BUG_ON(!page);
+		pfn = page_to_pfn(page);
+		/*
+		 * start_pfn is MAX_ORDER_NR_PAGES aligned, if there is any
+		 * free pages in [start_pfn, boundary_pfn), its head page will
+		 * always be in the range.
+		 */
+		if (PageBuddy(page)) {
+			int order = buddy_order(page);
+
+			if (pfn + (1UL << order) > boundary_pfn)
+				split_free_page(page, order, boundary_pfn - pfn);
+			pfn += (1UL << order);
+			continue;
+		}
+		/*
+		 * migrate compound pages then let the free page handling code
+		 * above do the rest. If migration is not possible, just fail.
+		 */
+		if (PageCompound(page)) {
+			unsigned long nr_pages = compound_nr(page);
+			struct page *head = compound_head(page);
+			unsigned long head_pfn = page_to_pfn(head);
+
+			if (head_pfn + nr_pages < boundary_pfn) {
+				pfn = head_pfn + nr_pages;
+				continue;
+			}
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+			/*
+			 * hugetlb, lru compound (THP), and movable compound pages
+			 * can be migrated. Otherwise, fail the isolation.
+			 */
+			if (PageHuge(page) || PageLRU(page) || __PageMovable(page)) {
+				int order;
+				unsigned long outer_pfn;
+				int ret;
+				struct compact_control cc = {
+					.nr_migratepages = 0,
+					.order = -1,
+					.zone = page_zone(pfn_to_page(head_pfn)),
+					.mode = MIGRATE_SYNC,
+					.ignore_skip_hint = true,
+					.no_set_skip_hint = true,
+					.gfp_mask = gfp_flags,
+					.alloc_contig = true,
+				};
+				INIT_LIST_HEAD(&cc.migratepages);
+
+				ret = __alloc_contig_migrate_range(&cc, head_pfn,
+							head_pfn + nr_pages);
+
+				if (ret)
+					goto failed;
+				/*
+				 * reset pfn to the head of the free page, so
+				 * that the free page handling code above can split
+				 * the free page to the right migratetype list.
+				 *
+				 * head_pfn is not used here as a hugetlb page order
+				 * can be bigger than MAX_ORDER-1, but after it is
+				 * freed, the free page order is not. Use pfn within
+				 * the range to find the head of the free page.
+				 */
+				order = 0;
+				outer_pfn = pfn;
+				while (!PageBuddy(pfn_to_page(outer_pfn))) {
+					if (++order >= MAX_ORDER) {
+						outer_pfn = pfn;
+						break;
+					}
+					outer_pfn &= ~0UL << order;
+				}
+				pfn = outer_pfn;
+				continue;
+			} else
+#endif
+				goto failed;
+		}
+
+		pfn++;
+	}
+	return 0;
+failed:
+	/* restore the original migratetype */
+	set_pageblock_migratetype(pfn_to_page(isolate_pageblock), saved_mt);
+	return -EBUSY;
+}
+
 /**
  * start_isolate_page_range() - make page-allocation-type of range of pages to
  * be MIGRATE_ISOLATE.
@@ -293,6 +453,8 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  *					 and PageOffline() pages.
  *			REPORT_FAILURE - report details about the failure to
  *			isolate the range
+ * @gfp_flags:		GFP flags used for migrating pages that sit across the
+ *			range boundaries.
  *
  * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
  * the range will never be allocated. Any free pages and pages freed in the
@@ -301,6 +463,10 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * pages in the range finally, the caller have to free all pages in the range.
  * test_page_isolated() can be used for test it.
  *
+ * The function first tries to isolate the pageblocks at the beginning and end
+ * of the range, since there might be pages across the range boundaries.
+ * Afterwards, it isolates the rest of the range.
+ *
  * There is no high level synchronization mechanism that prevents two threads
  * from trying to isolate overlapping ranges. If this happens, one thread
  * will notice pageblocks in the overlapping range already set to isolate.
@@ -321,21 +487,38 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * Return: 0 on success and -EBUSY if any part of range cannot be isolated.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     unsigned migratetype, int flags)
+			     int migratetype, int flags, gfp_t gfp_flags)
 {
 	unsigned long pfn;
 	struct page *page;
+	int ret;
 
 	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
 	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
 
-	for (pfn = start_pfn;
-	     pfn < end_pfn;
+	/* isolate [start_pfn, start_pfn + pageblock_nr_pages) pageblock */
+	ret = isolate_single_pageblock(start_pfn, gfp_flags, false);
+	if (ret)
+		return ret;
+
+	/* isolate [end_pfn - pageblock_nr_pages, end_pfn) pageblock */
+	ret = isolate_single_pageblock(end_pfn, gfp_flags, true);
+	if (ret) {
+		unset_migratetype_isolate(pfn_to_page(start_pfn), migratetype);
+		return ret;
+	}
+
+	/* skip isolated pageblocks at the beginning and end */
+	for (pfn = start_pfn + pageblock_nr_pages;
+	     pfn < end_pfn - pageblock_nr_pages;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
 		if (page && set_migratetype_isolate(page, migratetype, flags,
 					start_pfn, end_pfn)) {
 			undo_isolate_page_range(start_pfn, pfn, migratetype);
+			unset_migratetype_isolate(
+				pfn_to_page(end_pfn - pageblock_nr_pages),
+				migratetype);
 			return -EBUSY;
 		}
 	}
@@ -346,7 +529,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * Make isolated pages available again.
  */
 void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			    unsigned migratetype)
+			    int migratetype)
 {
 	unsigned long pfn;
 	struct page *page;
-- 
cgit v1.2.3


From 11ac3e87ce09c27f4587a8c4fe0829d814021a82 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Thu, 12 May 2022 20:22:58 -0700
Subject: mm: cma: use pageblock_order as the single alignment

Now alloc_contig_range() works at pageblock granularity.  Change CMA
allocation, which uses alloc_contig_range(), to use pageblock_nr_pages
alignment.

Link: https://lkml.kernel.org/r/20220425143118.2850746-6-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Eric Ren <renzhengeek@gmail.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/cma.h    | 4 ++--
 include/linux/mmzone.h | 5 +----
 mm/page_alloc.c        | 4 ++--
 3 files changed, 5 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cma.h b/include/linux/cma.h
index a6f637342740..63873b93deaa 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -17,11 +17,11 @@
 #define CMA_MAX_NAME 64
 
 /*
- * TODO: once the buddy -- especially pageblock merging and alloc_contig_range()
+ *  the buddy -- especially pageblock merging and alloc_contig_range()
  * -- can deal with only some pageblocks of a higher-order page being
  *  MIGRATE_CMA, we can use pageblock_nr_pages.
  */
-#define CMA_MIN_ALIGNMENT_PAGES MAX_ORDER_NR_PAGES
+#define CMA_MIN_ALIGNMENT_PAGES pageblock_nr_pages
 #define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES)
 
 struct cma;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 46ffab808f03..aab70355d64f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -54,10 +54,7 @@ enum migratetype {
 	 *
 	 * The way to use it is to change migratetype of a range of
 	 * pageblocks to MIGRATE_CMA which can be done by
-	 * __free_pageblock_cma() function.  What is important though
-	 * is that a range of pageblocks must be aligned to
-	 * MAX_ORDER_NR_PAGES should biggest page be bigger than
-	 * a single pageblock.
+	 * __free_pageblock_cma() function.
 	 */
 	MIGRATE_CMA,
 #endif
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3d7de8a96143..732e01e9d0e0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -9046,8 +9046,8 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
  *			be either of the two.
  * @gfp_mask:	GFP mask to use during compaction
  *
- * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
- * aligned.  The PFN range must belong to a single zone.
+ * The PFN range does not have to be pageblock aligned. The PFN range must
+ * belong to a single zone.
  *
  * The first thing this routine does is attempt to MIGRATE_ISOLATE all
  * pageblocks in the range.  Once isolated, the pageblocks should not
-- 
cgit v1.2.3


From adf88aa8ea7ff143825a2a8a7193f92e0e6fc79b Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 May 2022 20:23:01 -0700
Subject: mm: remove alloc_pages_vma()

All callers have now been converted to use vma_alloc_folio(), so convert
the body of alloc_pages_vma() to allocate folios instead.

Link: https://lkml.kernel.org/r/20220504182857.4013401-5-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/gfp.h | 18 +++++++-----------
 mm/mempolicy.c      | 51 +++++++++++++++++++++++++--------------------------
 2 files changed, 32 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 3e3d36fc2109..2a08a3c4ba95 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -613,13 +613,8 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 #ifdef CONFIG_NUMA
 struct page *alloc_pages(gfp_t gfp, unsigned int order);
 struct folio *folio_alloc(gfp_t gfp, unsigned order);
-struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
-			struct vm_area_struct *vma, unsigned long addr,
-			bool hugepage);
 struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, bool hugepage);
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
-	alloc_pages_vma(gfp_mask, order, vma, addr, true)
 #else
 static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
 {
@@ -629,16 +624,17 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
 {
 	return __folio_alloc_node(gfp, order, numa_node_id());
 }
-#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \
-	alloc_pages(gfp_mask, order)
 #define vma_alloc_folio(gfp, order, vma, addr, hugepage)		\
 	folio_alloc(gfp, order)
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
-	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
-#define alloc_page_vma(gfp_mask, vma, addr)			\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, false)
+static inline struct page *alloc_page_vma(gfp_t gfp,
+		struct vm_area_struct *vma, unsigned long addr)
+{
+	struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false);
+
+	return &folio->page;
+}
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3934476fb708..ed055e34d20c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2136,44 +2136,55 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
 }
 
 /**
- * alloc_pages_vma - Allocate a page for a VMA.
+ * vma_alloc_folio - Allocate a folio for a VMA.
  * @gfp: GFP flags.
- * @order: Order of the GFP allocation.
+ * @order: Order of the folio.
  * @vma: Pointer to VMA or NULL if not available.
  * @addr: Virtual address of the allocation.  Must be inside @vma.
  * @hugepage: For hugepages try only the preferred node if possible.
  *
- * Allocate a page for a specific address in @vma, using the appropriate
+ * Allocate a folio for a specific address in @vma, using the appropriate
  * NUMA policy.  When @vma is not NULL the caller must hold the mmap_lock
  * of the mm_struct of the VMA to prevent it from going away.  Should be
- * used for all allocations for pages that will be mapped into user space.
+ * used for all allocations for folios that will be mapped into user space.
  *
- * Return: The page on success or NULL if allocation fails.
+ * Return: The folio on success or NULL if allocation fails.
  */
-struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
+struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, bool hugepage)
 {
 	struct mempolicy *pol;
 	int node = numa_node_id();
-	struct page *page;
+	struct folio *folio;
 	int preferred_nid;
 	nodemask_t *nmask;
 
 	pol = get_vma_policy(vma, addr);
 
 	if (pol->mode == MPOL_INTERLEAVE) {
+		struct page *page;
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
+		gfp |= __GFP_COMP;
 		page = alloc_page_interleave(gfp, order, nid);
+		if (page && order > 1)
+			prep_transhuge_page(page);
+		folio = (struct folio *)page;
 		goto out;
 	}
 
 	if (pol->mode == MPOL_PREFERRED_MANY) {
+		struct page *page;
+
 		node = policy_node(gfp, pol, node);
+		gfp |= __GFP_COMP;
 		page = alloc_pages_preferred_many(gfp, order, node, pol);
 		mpol_cond_put(pol);
+		if (page && order > 1)
+			prep_transhuge_page(page);
+		folio = (struct folio *)page;
 		goto out;
 	}
 
@@ -2200,8 +2211,8 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 			 * First, try to allocate THP only on local node, but
 			 * don't reclaim unnecessarily, just compact.
 			 */
-			page = __alloc_pages_node(hpage_node,
-				gfp | __GFP_THISNODE | __GFP_NORETRY, order);
+			folio = __folio_alloc_node(gfp | __GFP_THISNODE |
+					__GFP_NORETRY, order, hpage_node);
 
 			/*
 			 * If hugepage allocations are configured to always
@@ -2209,8 +2220,9 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 			 * to prefer hugepage backing, retry allowing remote
 			 * memory with both reclaim and compact as well.
 			 */
-			if (!page && (gfp & __GFP_DIRECT_RECLAIM))
-				page = __alloc_pages(gfp, order, hpage_node, nmask);
+			if (!folio && (gfp & __GFP_DIRECT_RECLAIM))
+				folio = __folio_alloc(gfp, order, hpage_node,
+						      nmask);
 
 			goto out;
 		}
@@ -2218,25 +2230,12 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 
 	nmask = policy_nodemask(gfp, pol);
 	preferred_nid = policy_node(gfp, pol, node);
-	page = __alloc_pages(gfp, order, preferred_nid, nmask);
+	folio = __folio_alloc(gfp, order, preferred_nid, nmask);
 	mpol_cond_put(pol);
 out:
-	return page;
-}
-EXPORT_SYMBOL(alloc_pages_vma);
-
-struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, bool hugepage)
-{
-	struct folio *folio;
-
-	folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr,
-			hugepage);
-	if (folio && order > 1)
-		prep_transhuge_page(&folio->page);
-
 	return folio;
 }
+EXPORT_SYMBOL(vma_alloc_folio);
 
 /**
  * alloc_pages - Allocate pages.
-- 
cgit v1.2.3


From e2e3fdc7d4afdb8e7ba981eba7827993f2d390a8 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 May 2022 20:23:02 -0700
Subject: swap: turn get_swap_page() into folio_alloc_swap()

This removes an assumption that a large folio is HPAGE_PMD_NR pages
in size.

Link: https://lkml.kernel.org/r/20220504182857.4013401-8-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h | 13 +++++++------
 mm/memcontrol.c      | 16 ++++++++--------
 mm/shmem.c           |  3 ++-
 mm/swap_slots.c      | 14 +++++++-------
 mm/swap_state.c      |  3 ++-
 mm/swapfile.c        | 17 +++++++++--------
 6 files changed, 35 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5553189d0215..252c23a6667f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -470,7 +470,7 @@ static inline long get_nr_swap_pages(void)
 }
 
 extern void si_swapinfo(struct sysinfo *);
-extern swp_entry_t get_swap_page(struct page *page);
+swp_entry_t folio_alloc_swap(struct folio *folio);
 extern void put_swap_page(struct page *page, swp_entry_t entry);
 extern swp_entry_t get_swap_page_of_type(int);
 extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
@@ -583,7 +583,7 @@ static inline int try_to_free_swap(struct page *page)
 	return 0;
 }
 
-static inline swp_entry_t get_swap_page(struct page *page)
+static inline swp_entry_t folio_alloc_swap(struct folio *folio)
 {
 	swp_entry_t entry;
 	entry.val = 0;
@@ -643,12 +643,13 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
 
 #ifdef CONFIG_MEMCG_SWAP
 void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry);
-extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
-static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry);
+static inline int mem_cgroup_try_charge_swap(struct folio *folio,
+		swp_entry_t entry)
 {
 	if (mem_cgroup_disabled())
 		return 0;
-	return __mem_cgroup_try_charge_swap(page, entry);
+	return __mem_cgroup_try_charge_swap(folio, entry);
 }
 
 extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages);
@@ -666,7 +667,7 @@ static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 {
 }
 
-static inline int mem_cgroup_try_charge_swap(struct page *page,
+static inline int mem_cgroup_try_charge_swap(struct folio *folio,
 					     swp_entry_t entry)
 {
 	return 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6e74ca98c862..e1b5823ac060 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -7162,17 +7162,17 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 }
 
 /**
- * __mem_cgroup_try_charge_swap - try charging swap space for a page
- * @page: page being added to swap
+ * __mem_cgroup_try_charge_swap - try charging swap space for a folio
+ * @folio: folio being added to swap
  * @entry: swap entry to charge
  *
- * Try to charge @page's memcg for the swap space at @entry.
+ * Try to charge @folio's memcg for the swap space at @entry.
  *
  * Returns 0 on success, -ENOMEM on failure.
  */
-int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
 {
-	unsigned int nr_pages = thp_nr_pages(page);
+	unsigned int nr_pages = folio_nr_pages(folio);
 	struct page_counter *counter;
 	struct mem_cgroup *memcg;
 	unsigned short oldid;
@@ -7180,9 +7180,9 @@ int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return 0;
 
-	memcg = page_memcg(page);
+	memcg = folio_memcg(folio);
 
-	VM_WARN_ON_ONCE_PAGE(!memcg, page);
+	VM_WARN_ON_ONCE_FOLIO(!memcg, folio);
 	if (!memcg)
 		return 0;
 
@@ -7205,7 +7205,7 @@ int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	if (nr_pages > 1)
 		mem_cgroup_id_get_many(memcg, nr_pages - 1);
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages);
-	VM_BUG_ON_PAGE(oldid, page);
+	VM_BUG_ON_FOLIO(oldid, folio);
 	mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
 
 	return 0;
diff --git a/mm/shmem.c b/mm/shmem.c
index 7994421588a3..7cfe76347f63 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1313,6 +1313,7 @@ int shmem_unuse(unsigned int type)
  */
 static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 {
+	struct folio *folio = page_folio(page);
 	struct shmem_inode_info *info;
 	struct address_space *mapping;
 	struct inode *inode;
@@ -1386,7 +1387,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		SetPageUptodate(page);
 	}
 
-	swap = get_swap_page(page);
+	swap = folio_alloc_swap(folio);
 	if (!swap.val)
 		goto redirty;
 
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 2b5531840583..0218ec1cd24c 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -117,7 +117,7 @@ static int alloc_swap_slot_cache(unsigned int cpu)
 
 	/*
 	 * Do allocation outside swap_slots_cache_mutex
-	 * as kvzalloc could trigger reclaim and get_swap_page,
+	 * as kvzalloc could trigger reclaim and folio_alloc_swap,
 	 * which can lock swap_slots_cache_mutex.
 	 */
 	slots = kvcalloc(SWAP_SLOTS_CACHE_SIZE, sizeof(swp_entry_t),
@@ -213,7 +213,7 @@ static void __drain_swap_slots_cache(unsigned int type)
 	 * this function can be invoked in the cpu
 	 * hot plug path:
 	 * cpu_up -> lock cpu_hotplug -> cpu hotplug state callback
-	 *   -> memory allocation -> direct reclaim -> get_swap_page
+	 *   -> memory allocation -> direct reclaim -> folio_alloc_swap
 	 *   -> drain_swap_slots_cache
 	 *
 	 * Hence the loop over current online cpu below could miss cpu that
@@ -301,16 +301,16 @@ direct_free:
 	return 0;
 }
 
-swp_entry_t get_swap_page(struct page *page)
+swp_entry_t folio_alloc_swap(struct folio *folio)
 {
 	swp_entry_t entry;
 	struct swap_slots_cache *cache;
 
 	entry.val = 0;
 
-	if (PageTransHuge(page)) {
+	if (folio_test_large(folio)) {
 		if (IS_ENABLED(CONFIG_THP_SWAP))
-			get_swap_pages(1, &entry, HPAGE_PMD_NR);
+			get_swap_pages(1, &entry, folio_nr_pages(folio));
 		goto out;
 	}
 
@@ -344,8 +344,8 @@ repeat:
 
 	get_swap_pages(1, &entry, 1);
 out:
-	if (mem_cgroup_try_charge_swap(page, entry)) {
-		put_swap_page(page, entry);
+	if (mem_cgroup_try_charge_swap(folio, entry)) {
+		put_swap_page(&folio->page, entry);
 		entry.val = 0;
 	}
 	return entry;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 27c4e28f795f..2dc0d02f8d79 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -184,13 +184,14 @@ void __delete_from_swap_cache(struct page *page,
  */
 int add_to_swap(struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	swp_entry_t entry;
 	int err;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(!PageUptodate(page), page);
 
-	entry = get_swap_page(page);
+	entry = folio_alloc_swap(folio);
 	if (!entry.val)
 		return 0;
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 9398e915b36b..bfa41bf5e190 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -77,9 +77,9 @@ static PLIST_HEAD(swap_active_head);
 /*
  * all available (active, not full) swap_info_structs
  * protected with swap_avail_lock, ordered by priority.
- * This is used by get_swap_page() instead of swap_active_head
+ * This is used by folio_alloc_swap() instead of swap_active_head
  * because swap_active_head includes all swap_info_structs,
- * but get_swap_page() doesn't need to look at full ones.
+ * but folio_alloc_swap() doesn't need to look at full ones.
  * This uses its own lock instead of swap_lock because when a
  * swap_info_struct changes between not-full/full, it needs to
  * add/remove itself to/from this list, but the swap_info_struct->lock
@@ -2109,11 +2109,12 @@ retry:
 	 * Under global memory pressure, swap entries can be reinserted back
 	 * into process space after the mmlist loop above passes over them.
 	 *
-	 * Limit the number of retries? No: when mmget_not_zero() above fails,
-	 * that mm is likely to be freeing swap from exit_mmap(), which proceeds
-	 * at its own independent pace; and even shmem_writepage() could have
-	 * been preempted after get_swap_page(), temporarily hiding that swap.
-	 * It's easy and robust (though cpu-intensive) just to keep retrying.
+	 * Limit the number of retries? No: when mmget_not_zero()
+	 * above fails, that mm is likely to be freeing swap from
+	 * exit_mmap(), which proceeds at its own independent pace;
+	 * and even shmem_writepage() could have been preempted after
+	 * folio_alloc_swap(), temporarily hiding that swap.  It's easy
+	 * and robust (though cpu-intensive) just to keep retrying.
 	 */
 	if (READ_ONCE(si->inuse_pages)) {
 		if (!signal_pending(current))
@@ -2327,7 +2328,7 @@ static void _enable_swap_info(struct swap_info_struct *p)
 	 * which on removal of any swap_info_struct with an auto-assigned
 	 * (i.e. negative) priority increments the auto-assigned priority
 	 * of any lower-priority swap_info_structs.
-	 * swap_avail_head needs to be priority ordered for get_swap_page(),
+	 * swap_avail_head needs to be priority ordered for folio_alloc_swap(),
 	 * which allocates swap pages from the highest available priority
 	 * swap_info_struct.
 	 */
-- 
cgit v1.2.3


From 64daa5d818ae3430f0785206b0af13ef528cb9ef Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 May 2022 20:23:03 -0700
Subject: vmscan: convert lazy freeing to folios

Remove a hidden call to compound_head(), and account nr_pages instead of a
single page.  This matches the code in lru_lazyfree_fn() that accounts
nr_pages to PGLAZYFREE.

Link: https://lkml.kernel.org/r/20220504182857.4013401-12-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h | 14 ++++++++++++++
 mm/vmscan.c                | 18 +++++++++---------
 2 files changed, 23 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index fe580cb96683..8ea4b541c31e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1057,6 +1057,15 @@ static inline void count_memcg_page_event(struct page *page,
 		count_memcg_events(memcg, idx, 1);
 }
 
+static inline void count_memcg_folio_events(struct folio *folio,
+		enum vm_event_item idx, unsigned long nr)
+{
+	struct mem_cgroup *memcg = folio_memcg(folio);
+
+	if (memcg)
+		count_memcg_events(memcg, idx, nr);
+}
+
 static inline void count_memcg_event_mm(struct mm_struct *mm,
 					enum vm_event_item idx)
 {
@@ -1494,6 +1503,11 @@ static inline void count_memcg_page_event(struct page *page,
 {
 }
 
+static inline void count_memcg_folio_events(struct folio *folio,
+		enum vm_event_item idx, unsigned long nr)
+{
+}
+
 static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 00b985caf40d..972557e2fb92 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1902,20 +1902,20 @@ retry:
 			}
 		}
 
-		if (PageAnon(page) && !PageSwapBacked(page)) {
+		if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) {
 			/* follow __remove_mapping for reference */
-			if (!page_ref_freeze(page, 1))
+			if (!folio_ref_freeze(folio, 1))
 				goto keep_locked;
 			/*
-			 * The page has only one reference left, which is
+			 * The folio has only one reference left, which is
 			 * from the isolation. After the caller puts the
-			 * page back on lru and drops the reference, the
-			 * page will be freed anyway. It doesn't matter
-			 * which lru it goes. So we don't bother checking
-			 * PageDirty here.
+			 * folio back on the lru and drops the reference, the
+			 * folio will be freed anyway. It doesn't matter
+			 * which lru it goes on. So we don't bother checking
+			 * the dirty flag here.
 			 */
-			count_vm_event(PGLAZYFREED);
-			count_memcg_page_event(page, PGLAZYFREED);
+			count_vm_events(PGLAZYFREED, nr_pages);
+			count_memcg_folio_events(folio, PGLAZYFREED, nr_pages);
 		} else if (!mapping || !__remove_mapping(mapping, folio, true,
 							 sc->target_mem_cgroup))
 			goto keep_locked;
-- 
cgit v1.2.3


From dc786690a6a1d9a680e6872821291ad7ca9f520d Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 May 2022 20:23:03 -0700
Subject: mm: allow can_split_folio() to be called when THP are disabled

The call to can_split_folio() in vmscan is currently guarded by a test of
PageTransHuge() so the BUILD_BUG() is eliminated if THP are disabled.  The
next patch replaces that test with folio_test_large() which may be true,
even when THP are disabled.  However, if THP are disabled, we cannot
split, so an unconditional return of false is appropriate.

Link: https://lkml.kernel.org/r/20220504182857.4013401-15-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/huge_mm.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9a26bd10e083..fbf36bb1be22 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -348,7 +348,6 @@ static inline void prep_transhuge_page(struct page *page) {}
 static inline bool
 can_split_folio(struct folio *folio, int *pextra_pins)
 {
-	BUILD_BUG();
 	return false;
 }
 static inline int
-- 
cgit v1.2.3


From 039bc1240165c99b932fb4be2f784948d1038eea Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 May 2022 20:23:04 -0700
Subject: mm/swap: add folio_throttle_swaprate

The only use of the page argument to cgroup_throttle_swaprate() is to get
the node ID, and this will be the same for all pages in the folio, so just
pass in the first page of the folio.

Link: https://lkml.kernel.org/r/20220504182857.4013401-18-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 252c23a6667f..6bf1506e5080 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -640,6 +640,10 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
 {
 }
 #endif
+static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
+{
+	cgroup_throttle_swaprate(&folio->page, gfp);
+}
 
 #ifdef CONFIG_MEMCG_SWAP
 void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry);
-- 
cgit v1.2.3


From da08e9b7932345aff0a748c55f8a25709505f2a3 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 May 2022 20:23:05 -0700
Subject: mm/shmem: convert shmem_swapin_page() to shmem_swapin_folio()

shmem_swapin_page() only brings in order-0 pages, which are folios
by definition.

Link: https://lkml.kernel.org/r/20220504182857.4013401-24-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm64/include/asm/pgtable.h |   6 +--
 include/linux/pgtable.h          |   2 +-
 mm/shmem.c                       | 110 ++++++++++++++++++---------------------
 3 files changed, 55 insertions(+), 63 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 3278c6c0d873..8ebf1cec5d90 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -981,10 +981,10 @@ static inline void arch_swap_invalidate_area(int type)
 }
 
 #define __HAVE_ARCH_SWAP_RESTORE
-static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
+static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 {
-	if (system_supports_mte() && mte_restore_tags(entry, page))
-		set_bit(PG_mte_tagged, &page->flags);
+	if (system_supports_mte() && mte_restore_tags(entry, &folio->page))
+		set_bit(PG_mte_tagged, &folio->flags);
 }
 
 #endif /* CONFIG_ARM64_MTE */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 530b1817b58c..39fa93e94b80 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -758,7 +758,7 @@ static inline void arch_swap_invalidate_area(int type)
 #endif
 
 #ifndef __HAVE_ARCH_SWAP_RESTORE
-static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
+static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 {
 }
 #endif
diff --git a/mm/shmem.c b/mm/shmem.c
index edcaba7c67ff..29701be579f8 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -135,8 +135,8 @@ static unsigned long shmem_default_max_inodes(void)
 }
 #endif
 
-static int shmem_swapin_page(struct inode *inode, pgoff_t index,
-			     struct page **pagep, enum sgp_type sgp,
+static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
+			     struct folio **foliop, enum sgp_type sgp,
 			     gfp_t gfp, struct vm_area_struct *vma,
 			     vm_fault_t *fault_type);
 static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
@@ -1159,69 +1159,64 @@ static void shmem_evict_inode(struct inode *inode)
 }
 
 static int shmem_find_swap_entries(struct address_space *mapping,
-				   pgoff_t start, unsigned int nr_entries,
-				   struct page **entries, pgoff_t *indices,
-				   unsigned int type)
+				   pgoff_t start, struct folio_batch *fbatch,
+				   pgoff_t *indices, unsigned int type)
 {
 	XA_STATE(xas, &mapping->i_pages, start);
-	struct page *page;
+	struct folio *folio;
 	swp_entry_t entry;
 	unsigned int ret = 0;
 
-	if (!nr_entries)
-		return 0;
-
 	rcu_read_lock();
-	xas_for_each(&xas, page, ULONG_MAX) {
-		if (xas_retry(&xas, page))
+	xas_for_each(&xas, folio, ULONG_MAX) {
+		if (xas_retry(&xas, folio))
 			continue;
 
-		if (!xa_is_value(page))
+		if (!xa_is_value(folio))
 			continue;
 
-		entry = radix_to_swp_entry(page);
+		entry = radix_to_swp_entry(folio);
 		if (swp_type(entry) != type)
 			continue;
 
 		indices[ret] = xas.xa_index;
-		entries[ret] = page;
+		if (!folio_batch_add(fbatch, folio))
+			break;
 
 		if (need_resched()) {
 			xas_pause(&xas);
 			cond_resched_rcu();
 		}
-		if (++ret == nr_entries)
-			break;
 	}
 	rcu_read_unlock();
 
-	return ret;
+	return xas.xa_index;
 }
 
 /*
  * Move the swapped pages for an inode to page cache. Returns the count
  * of pages swapped in, or the error in case of failure.
  */
-static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec,
-				    pgoff_t *indices)
+static int shmem_unuse_swap_entries(struct inode *inode,
+		struct folio_batch *fbatch, pgoff_t *indices)
 {
 	int i = 0;
 	int ret = 0;
 	int error = 0;
 	struct address_space *mapping = inode->i_mapping;
 
-	for (i = 0; i < pvec.nr; i++) {
-		struct page *page = pvec.pages[i];
+	for (i = 0; i < folio_batch_count(fbatch); i++) {
+		struct folio *folio = fbatch->folios[i];
 
-		if (!xa_is_value(page))
+		if (!xa_is_value(folio))
 			continue;
-		error = shmem_swapin_page(inode, indices[i],
-					  &page, SGP_CACHE,
+		error = shmem_swapin_folio(inode, indices[i],
+					  &folio, SGP_CACHE,
 					  mapping_gfp_mask(mapping),
 					  NULL, NULL);
 		if (error == 0) {
-			unlock_page(page);
-			put_page(page);
+			folio_unlock(folio);
+			folio_put(folio);
 			ret++;
 		}
 		if (error == -ENOMEM)
@@ -1238,26 +1233,23 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type)
 {
 	struct address_space *mapping = inode->i_mapping;
 	pgoff_t start = 0;
-	struct pagevec pvec;
+	struct folio_batch fbatch;
 	pgoff_t indices[PAGEVEC_SIZE];
 	int ret = 0;
 
-	pagevec_init(&pvec);
 	do {
-		unsigned int nr_entries = PAGEVEC_SIZE;
-
-		pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries,
-						  pvec.pages, indices, type);
-		if (pvec.nr == 0) {
+		folio_batch_init(&fbatch);
+		shmem_find_swap_entries(mapping, start, &fbatch, indices, type);
+		if (folio_batch_count(&fbatch) == 0) {
 			ret = 0;
 			break;
 		}
 
-		ret = shmem_unuse_swap_entries(inode, pvec, indices);
+		ret = shmem_unuse_swap_entries(inode, &fbatch, indices);
 		if (ret < 0)
 			break;
 
-		start = indices[pvec.nr - 1];
+		start = indices[folio_batch_count(&fbatch) - 1];
 	} while (true);
 
 	return ret;
@@ -1687,22 +1679,22 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
  * Returns 0 and the page in pagep if success. On failure, returns the
  * error code and NULL in *pagep.
  */
-static int shmem_swapin_page(struct inode *inode, pgoff_t index,
-			     struct page **pagep, enum sgp_type sgp,
+static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
+			     struct folio **foliop, enum sgp_type sgp,
 			     gfp_t gfp, struct vm_area_struct *vma,
 			     vm_fault_t *fault_type)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL;
-	struct page *page = NULL;
-	struct folio *folio;
+	struct page *page;
+	struct folio *folio = NULL;
 	swp_entry_t swap;
 	int error;
 
-	VM_BUG_ON(!*pagep || !xa_is_value(*pagep));
-	swap = radix_to_swp_entry(*pagep);
-	*pagep = NULL;
+	VM_BUG_ON(!*foliop || !xa_is_value(*foliop));
+	swap = radix_to_swp_entry(*foliop);
+	*foliop = NULL;
 
 	/* Look it up and read it in.. */
 	page = lookup_swap_cache(swap, NULL, 0);
@@ -1720,27 +1712,28 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 			goto failed;
 		}
 	}
+	folio = page_folio(page);
 
 	/* We have to do this with page locked to prevent races */
-	lock_page(page);
-	if (!PageSwapCache(page) || page_private(page) != swap.val ||
+	folio_lock(folio);
+	if (!folio_test_swapcache(folio) ||
+	    folio_swap_entry(folio).val != swap.val ||
 	    !shmem_confirm_swap(mapping, index, swap)) {
 		error = -EEXIST;
 		goto unlock;
 	}
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		error = -EIO;
 		goto failed;
 	}
-	wait_on_page_writeback(page);
+	folio_wait_writeback(folio);
 
 	/*
 	 * Some architectures may have to restore extra metadata to the
-	 * physical page after reading from swap.
+	 * folio after reading from swap.
 	 */
-	arch_swap_restore(swap, page);
+	arch_swap_restore(swap, folio);
 
-	folio = page_folio(page);
 	if (shmem_should_replace_folio(folio, gfp)) {
 		error = shmem_replace_page(&page, gfp, info, index);
 		if (error)
@@ -1759,21 +1752,21 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 	spin_unlock_irq(&info->lock);
 
 	if (sgp == SGP_WRITE)
-		mark_page_accessed(page);
+		folio_mark_accessed(folio);
 
-	delete_from_swap_cache(page);
-	set_page_dirty(page);
+	delete_from_swap_cache(&folio->page);
+	folio_mark_dirty(folio);
 	swap_free(swap);
 
-	*pagep = page;
+	*foliop = folio;
 	return 0;
 failed:
 	if (!shmem_confirm_swap(mapping, index, swap))
 		error = -EEXIST;
 unlock:
-	if (page) {
-		unlock_page(page);
-		put_page(page);
+	if (folio) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	return error;
@@ -1827,13 +1820,12 @@ repeat:
 	}
 
 	if (xa_is_value(folio)) {
-		struct page *page = &folio->page;
-		error = shmem_swapin_page(inode, index, &page,
+		error = shmem_swapin_folio(inode, index, &folio,
 					  sgp, gfp, vma, fault_type);
 		if (error == -EEXIST)
 			goto repeat;
 
-		*pagep = page;
+		*pagep = &folio->page;
 		return error;
 	}
 
-- 
cgit v1.2.3


From a9595b305c0f6cbbf9505325509d95637f6a7062 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 May 2022 20:23:05 -0700
Subject: mm: add folio_mapping_flags()

This is the equivalent of PageMappingFlags and is needed for converting
mm/migrate.c to folios.

Link: https://lkml.kernel.org/r/20220504182857.4013401-25-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index b70124b9c7c1..97eb88dbcbbc 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -650,6 +650,11 @@ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND)
 #define PAGE_MAPPING_KSM	(PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
 #define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
 
+static __always_inline bool folio_mapping_flags(struct folio *folio)
+{
+	return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0;
+}
+
 static __always_inline int PageMappingFlags(struct page *page)
 {
 	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0;
-- 
cgit v1.2.3


From 8b463be3a0241558071e6ba9bf11e4bf42ccc856 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 May 2022 20:23:05 -0700
Subject: mm: add folio_test_movable()

This is the folio equivalent of PageMovable() which is needed to
convert mm/migrate.c to folios.

Link: https://lkml.kernel.org/r/20220504182857.4013401-26-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/migrate.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 2707bfd43a0d..069a89e847f3 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -105,6 +105,11 @@ static inline void __ClearPageMovable(struct page *page)
 }
 #endif
 
+static inline bool folio_test_movable(struct folio *folio)
+{
+	return PageMovable(&folio->page);
+}
+
 #ifdef CONFIG_NUMA_BALANCING
 extern int migrate_misplaced_page(struct page *page,
 				  struct vm_area_struct *vma, int node);
-- 
cgit v1.2.3


From de8c8e52836d0082188508548d0b939f49f7f0e6 Mon Sep 17 00:00:00 2001
From: Tong Tiangen <tongtiangen@huawei.com>
Date: Thu, 12 May 2022 20:23:06 -0700
Subject: mm: page_table_check: add hooks to public helpers

Move ptep_clear() to the include/linux/pgtable.h and add page table check
relate hooks to some helpers, it's prepare for support page table check
feature on new architecture.

Optimize the implementation of ptep_clear(), page table hooks added page
table check stubs, the interface control should be at stubs, there is no
rationale for doing a IS_ENABLED() check here.

For architectures that do not enable CONFIG_PAGE_TABLE_CHECK, they will
call a fallback page table check stubs[1] when getting their page table
helpers[2] in include/linux/pgtable.h.

[1] page table check stubs defined in include/linux/page_table_check.h
[2] ptep_clear() ptep_get_and_clear()  pmdp_huge_get_and_clear()
pudp_huge_get_and_clear()

Link: https://lkml.kernel.org/r/20220507110114.4128854-4-tongtiangen@huawei.com
Signed-off-by: Tong Tiangen <tongtiangen@huawei.com>
Acked-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/include/asm/pgtable.h | 10 ----------
 include/linux/pgtable.h        | 23 +++++++++++++++--------
 2 files changed, 15 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 46fa65d818bd..44e2d6f1dbaa 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1072,16 +1072,6 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	return pte;
 }
 
-#define __HAVE_ARCH_PTEP_CLEAR
-static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
-{
-	if (IS_ENABLED(CONFIG_PAGE_TABLE_CHECK))
-		ptep_get_and_clear(mm, addr, ptep);
-	else
-		pte_clear(mm, addr, ptep);
-}
-
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm,
 				      unsigned long addr, pte_t *ptep)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 39fa93e94b80..e0a449b477c5 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -12,6 +12,7 @@
 #include <linux/bug.h>
 #include <linux/errno.h>
 #include <asm-generic/pgtable_uffd.h>
+#include <linux/page_table_check.h>
 
 #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
 	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
@@ -259,14 +260,6 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
-#ifndef __HAVE_ARCH_PTEP_CLEAR
-static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
-{
-	pte_clear(mm, addr, ptep);
-}
-#endif
-
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address,
@@ -274,10 +267,19 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 {
 	pte_t pte = *ptep;
 	pte_clear(mm, address, ptep);
+	page_table_check_pte_clear(mm, address, pte);
 	return pte;
 }
 #endif
 
+#ifndef __HAVE_ARCH_PTEP_CLEAR
+static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep)
+{
+	ptep_get_and_clear(mm, addr, ptep);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_GET
 static inline pte_t ptep_get(pte_t *ptep)
 {
@@ -347,7 +349,10 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
+
 	pmd_clear(pmdp);
+	page_table_check_pmd_clear(mm, address, pmd);
+
 	return pmd;
 }
 #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
@@ -359,6 +364,8 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
 	pud_t pud = *pudp;
 
 	pud_clear(pudp);
+	page_table_check_pud_clear(mm, address, pud);
+
 	return pud;
 }
 #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
-- 
cgit v1.2.3


From 2e7dc2b632a324c670ff11dd6c84d711043c683f Mon Sep 17 00:00:00 2001
From: Tong Tiangen <tongtiangen@huawei.com>
Date: Thu, 12 May 2022 20:23:06 -0700
Subject: mm: remove __HAVE_ARCH_PTEP_CLEAR in pgtable.h

Currently, there is no architecture definition __HAVE_ARCH_PTEP_CLEAR,
Generic ptep_clear() is the only definition for all architecture, So drop
the "#ifndef __HAVE_ARCH_PTEP_CLEAR".

Link: https://lkml.kernel.org/r/20220507110114.4128854-5-tongtiangen@huawei.com
Signed-off-by: Tong Tiangen <tongtiangen@huawei.com>
Suggested-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pgtable.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e0a449b477c5..ecb4c762d760 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -272,13 +272,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 #endif
 
-#ifndef __HAVE_ARCH_PTEP_CLEAR
 static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
 	ptep_get_and_clear(mm, addr, ptep);
 }
-#endif
 
 #ifndef __HAVE_ARCH_PTEP_GET
 static inline pte_t ptep_get(pte_t *ptep)
-- 
cgit v1.2.3


From c8db8c2628afc7088a43de3f7cfbcc2ef1f182f7 Mon Sep 17 00:00:00 2001
From: Li kunyu <kunyu@nfschina.com>
Date: Thu, 12 May 2022 20:23:07 -0700
Subject: mm: functions may simplify the use of return values

p4d_clear_huge may be optimized for void return type and function usage.
vunmap_p4d_range function saves a few steps here.

Link: https://lkml.kernel.org/r/20220507150630.90399-1-kunyu@nfschina.com
Signed-off-by: Li kunyu <kunyu@nfschina.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/mm/pgtable.c   |  3 +--
 include/linux/pgtable.h | 12 +++---------
 mm/vmalloc.c            |  7 ++-----
 3 files changed, 6 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index f16059e9a85e..a932d7712d85 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -686,9 +686,8 @@ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
  *
  * No 512GB pages yet -- always return 0
  */
-int p4d_clear_huge(p4d_t *p4d)
+void p4d_clear_huge(p4d_t *p4d)
 {
-	return 0;
 }
 #endif
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index ecb4c762d760..3cdc16cfd867 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1448,16 +1448,13 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #ifndef __PAGETABLE_P4D_FOLDED
 int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
-int p4d_clear_huge(p4d_t *p4d);
+void p4d_clear_huge(p4d_t *p4d);
 #else
 static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
 }
-static inline int p4d_clear_huge(p4d_t *p4d)
-{
-	return 0;
-}
+static inline void p4d_clear_huge(p4d_t *p4d) { }
 #endif /* !__PAGETABLE_P4D_FOLDED */
 
 int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
@@ -1480,10 +1477,7 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
 }
-static inline int p4d_clear_huge(p4d_t *p4d)
-{
-	return 0;
-}
+static inline void p4d_clear_huge(p4d_t *p4d) { }
 static inline int pud_clear_huge(pud_t *pud)
 {
 	return 0;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c3af9b28e54f..5b59ccafcd46 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -389,18 +389,15 @@ static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 {
 	p4d_t *p4d;
 	unsigned long next;
-	int cleared;
 
 	p4d = p4d_offset(pgd, addr);
 	do {
 		next = p4d_addr_end(addr, end);
 
-		cleared = p4d_clear_huge(p4d);
-		if (cleared || p4d_bad(*p4d))
+		p4d_clear_huge(p4d);
+		if (p4d_bad(*p4d))
 			*mask |= PGTBL_P4D_MODIFIED;
 
-		if (cleared)
-			continue;
 		if (p4d_none_or_clear_bad(p4d))
 			continue;
 		vunmap_pud_range(p4d, addr, next, mask);
-- 
cgit v1.2.3


From fe573327ffb1deba802c91dd1d4ff41dafa97a0e Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@openvz.org>
Date: Thu, 12 May 2022 20:23:08 -0700
Subject: tracing: incorrect gfp_t conversion

Fixes the following sparse warnings:

include/trace/events/*: sparse: cast to restricted gfp_t
include/trace/events/*: sparse: restricted gfp_t degrades to integer

gfp_t type is bitwise and requires __force attributes for any casts.

Link: https://lkml.kernel.org/r/331d88fe-f4f7-657c-02a2-d977f15fbff6@openvz.org
Signed-off-by: Vasily Averin <vvs@openvz.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/gfp.h               |  2 +-
 include/trace/events/btrfs.h      |  4 +-
 include/trace/events/compaction.h |  4 +-
 include/trace/events/kmem.h       | 12 +++---
 include/trace/events/mmflags.h    | 78 +++++++++++++++++++--------------------
 include/trace/events/vmscan.h     | 16 ++++----
 mm/compaction.c                   |  2 +-
 7 files changed, 59 insertions(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2a08a3c4ba95..2d2ccae933c2 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -367,7 +367,7 @@ static inline int gfp_migratetype(const gfp_t gfp_flags)
 		return MIGRATE_UNMOVABLE;
 
 	/* Group based on mobility */
-	return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
+	return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
 }
 #undef GFP_MOVABLE_MASK
 #undef GFP_MOVABLE_SHIFT
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index f068ff30d654..ed92c80331ea 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1344,13 +1344,13 @@ TRACE_EVENT(alloc_extent_state,
 
 	TP_STRUCT__entry(
 		__field(const struct extent_state *, state)
-		__field(gfp_t, mask)
+		__field(unsigned long, mask)
 		__field(const void*, ip)
 	),
 
 	TP_fast_assign(
 		__entry->state	= state,
-		__entry->mask	= mask,
+		__entry->mask	= (__force unsigned long)mask,
 		__entry->ip	= (const void *)IP
 	),
 
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index c6d5d70dc7a5..3313eb83c117 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -162,13 +162,13 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages,
 
 	TP_STRUCT__entry(
 		__field(int, order)
-		__field(gfp_t, gfp_mask)
+		__field(unsigned long, gfp_mask)
 		__field(int, prio)
 	),
 
 	TP_fast_assign(
 		__entry->order = order;
-		__entry->gfp_mask = gfp_mask;
+		__entry->gfp_mask = (__force unsigned long)gfp_mask;
 		__entry->prio = prio;
 	),
 
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index ddc8c944f417..71c141804222 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -24,7 +24,7 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__field(	const void *,	ptr		)
 		__field(	size_t,		bytes_req	)
 		__field(	size_t,		bytes_alloc	)
-		__field(	gfp_t,		gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 	),
 
 	TP_fast_assign(
@@ -32,7 +32,7 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__entry->ptr		= ptr;
 		__entry->bytes_req	= bytes_req;
 		__entry->bytes_alloc	= bytes_alloc;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 	),
 
 	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
@@ -75,7 +75,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__field(	const void *,	ptr		)
 		__field(	size_t,		bytes_req	)
 		__field(	size_t,		bytes_alloc	)
-		__field(	gfp_t,		gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 		__field(	int,		node		)
 	),
 
@@ -84,7 +84,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__entry->ptr		= ptr;
 		__entry->bytes_req	= bytes_req;
 		__entry->bytes_alloc	= bytes_alloc;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 		__entry->node		= node;
 	),
 
@@ -208,14 +208,14 @@ TRACE_EVENT(mm_page_alloc,
 	TP_STRUCT__entry(
 		__field(	unsigned long,	pfn		)
 		__field(	unsigned int,	order		)
-		__field(	gfp_t,		gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 		__field(	int,		migratetype	)
 	),
 
 	TP_fast_assign(
 		__entry->pfn		= page ? page_to_pfn(page) : -1UL;
 		__entry->order		= order;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 		__entry->migratetype	= migratetype;
 	),
 
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 6532119a6bf1..fcb1ffb2cc8d 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -14,48 +14,48 @@
  */
 
 #define __def_gfpflag_names						\
-	{(unsigned long)GFP_TRANSHUGE,		"GFP_TRANSHUGE"},	\
-	{(unsigned long)GFP_TRANSHUGE_LIGHT,	"GFP_TRANSHUGE_LIGHT"}, \
-	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"},\
-	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
-	{(unsigned long)GFP_USER,		"GFP_USER"},		\
-	{(unsigned long)GFP_KERNEL_ACCOUNT,	"GFP_KERNEL_ACCOUNT"},	\
-	{(unsigned long)GFP_KERNEL,		"GFP_KERNEL"},		\
-	{(unsigned long)GFP_NOFS,		"GFP_NOFS"},		\
-	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
-	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
-	{(unsigned long)GFP_NOWAIT,		"GFP_NOWAIT"},		\
-	{(unsigned long)GFP_DMA,		"GFP_DMA"},		\
-	{(unsigned long)__GFP_HIGHMEM,		"__GFP_HIGHMEM"},	\
-	{(unsigned long)GFP_DMA32,		"GFP_DMA32"},		\
-	{(unsigned long)__GFP_HIGH,		"__GFP_HIGH"},		\
-	{(unsigned long)__GFP_ATOMIC,		"__GFP_ATOMIC"},	\
-	{(unsigned long)__GFP_IO,		"__GFP_IO"},		\
-	{(unsigned long)__GFP_FS,		"__GFP_FS"},		\
-	{(unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
-	{(unsigned long)__GFP_RETRY_MAYFAIL,	"__GFP_RETRY_MAYFAIL"},	\
-	{(unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
-	{(unsigned long)__GFP_NORETRY,		"__GFP_NORETRY"},	\
-	{(unsigned long)__GFP_COMP,		"__GFP_COMP"},		\
-	{(unsigned long)__GFP_ZERO,		"__GFP_ZERO"},		\
-	{(unsigned long)__GFP_NOMEMALLOC,	"__GFP_NOMEMALLOC"},	\
-	{(unsigned long)__GFP_MEMALLOC,		"__GFP_MEMALLOC"},	\
-	{(unsigned long)__GFP_HARDWALL,		"__GFP_HARDWALL"},	\
-	{(unsigned long)__GFP_THISNODE,		"__GFP_THISNODE"},	\
-	{(unsigned long)__GFP_RECLAIMABLE,	"__GFP_RECLAIMABLE"},	\
-	{(unsigned long)__GFP_MOVABLE,		"__GFP_MOVABLE"},	\
-	{(unsigned long)__GFP_ACCOUNT,		"__GFP_ACCOUNT"},	\
-	{(unsigned long)__GFP_WRITE,		"__GFP_WRITE"},		\
-	{(unsigned long)__GFP_RECLAIM,		"__GFP_RECLAIM"},	\
-	{(unsigned long)__GFP_DIRECT_RECLAIM,	"__GFP_DIRECT_RECLAIM"},\
-	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"__GFP_KSWAPD_RECLAIM"},\
-	{(unsigned long)__GFP_ZEROTAGS,		"__GFP_ZEROTAGS"}	\
+	{(__force unsigned long)GFP_TRANSHUGE,		"GFP_TRANSHUGE"},	\
+	{(__force unsigned long)GFP_TRANSHUGE_LIGHT,	"GFP_TRANSHUGE_LIGHT"}, \
+	{(__force unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"},\
+	{(__force unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
+	{(__force unsigned long)GFP_USER,		"GFP_USER"},		\
+	{(__force unsigned long)GFP_KERNEL_ACCOUNT,	"GFP_KERNEL_ACCOUNT"},	\
+	{(__force unsigned long)GFP_KERNEL,		"GFP_KERNEL"},		\
+	{(__force unsigned long)GFP_NOFS,		"GFP_NOFS"},		\
+	{(__force unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
+	{(__force unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
+	{(__force unsigned long)GFP_NOWAIT,		"GFP_NOWAIT"},		\
+	{(__force unsigned long)GFP_DMA,		"GFP_DMA"},		\
+	{(__force unsigned long)__GFP_HIGHMEM,		"__GFP_HIGHMEM"},	\
+	{(__force unsigned long)GFP_DMA32,		"GFP_DMA32"},		\
+	{(__force unsigned long)__GFP_HIGH,		"__GFP_HIGH"},		\
+	{(__force unsigned long)__GFP_ATOMIC,		"__GFP_ATOMIC"},	\
+	{(__force unsigned long)__GFP_IO,		"__GFP_IO"},		\
+	{(__force unsigned long)__GFP_FS,		"__GFP_FS"},		\
+	{(__force unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
+	{(__force unsigned long)__GFP_RETRY_MAYFAIL,	"__GFP_RETRY_MAYFAIL"},	\
+	{(__force unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
+	{(__force unsigned long)__GFP_NORETRY,		"__GFP_NORETRY"},	\
+	{(__force unsigned long)__GFP_COMP,		"__GFP_COMP"},		\
+	{(__force unsigned long)__GFP_ZERO,		"__GFP_ZERO"},		\
+	{(__force unsigned long)__GFP_NOMEMALLOC,	"__GFP_NOMEMALLOC"},	\
+	{(__force unsigned long)__GFP_MEMALLOC,		"__GFP_MEMALLOC"},	\
+	{(__force unsigned long)__GFP_HARDWALL,		"__GFP_HARDWALL"},	\
+	{(__force unsigned long)__GFP_THISNODE,		"__GFP_THISNODE"},	\
+	{(__force unsigned long)__GFP_RECLAIMABLE,	"__GFP_RECLAIMABLE"},	\
+	{(__force unsigned long)__GFP_MOVABLE,		"__GFP_MOVABLE"},	\
+	{(__force unsigned long)__GFP_ACCOUNT,		"__GFP_ACCOUNT"},	\
+	{(__force unsigned long)__GFP_WRITE,		"__GFP_WRITE"},		\
+	{(__force unsigned long)__GFP_RECLAIM,		"__GFP_RECLAIM"},	\
+	{(__force unsigned long)__GFP_DIRECT_RECLAIM,	"__GFP_DIRECT_RECLAIM"},\
+	{(__force unsigned long)__GFP_KSWAPD_RECLAIM,	"__GFP_KSWAPD_RECLAIM"},\
+	{(__force unsigned long)__GFP_ZEROTAGS,		"__GFP_ZEROTAGS"}	\
 
 #ifdef CONFIG_KASAN_HW_TAGS
 #define __def_gfpflag_names_kasan ,					       \
-	{(unsigned long)__GFP_SKIP_ZERO,	   "__GFP_SKIP_ZERO"},	       \
-	{(unsigned long)__GFP_SKIP_KASAN_POISON,   "__GFP_SKIP_KASAN_POISON"}, \
-	{(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"}
+	{(__force unsigned long)__GFP_SKIP_ZERO,	   "__GFP_SKIP_ZERO"},	       \
+	{(__force unsigned long)__GFP_SKIP_KASAN_POISON,   "__GFP_SKIP_KASAN_POISON"}, \
+	{(__force unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"}
 #else
 #define __def_gfpflag_names_kasan
 #endif
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index de136dbd623a..408c86244d64 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -96,14 +96,14 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
 		__field(	int,	nid		)
 		__field(	int,	zid		)
 		__field(	int,	order		)
-		__field(	gfp_t,	gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 	),
 
 	TP_fast_assign(
 		__entry->nid		= nid;
 		__entry->zid		= zid;
 		__entry->order		= order;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 	),
 
 	TP_printk("nid=%d order=%d gfp_flags=%s",
@@ -120,12 +120,12 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
 
 	TP_STRUCT__entry(
 		__field(	int,	order		)
-		__field(	gfp_t,	gfp_flags	)
+		__field(	unsigned long,	gfp_flags	)
 	),
 
 	TP_fast_assign(
 		__entry->order		= order;
-		__entry->gfp_flags	= gfp_flags;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 	),
 
 	TP_printk("order=%d gfp_flags=%s",
@@ -210,7 +210,7 @@ TRACE_EVENT(mm_shrink_slab_start,
 		__field(void *, shrink)
 		__field(int, nid)
 		__field(long, nr_objects_to_shrink)
-		__field(gfp_t, gfp_flags)
+		__field(unsigned long, gfp_flags)
 		__field(unsigned long, cache_items)
 		__field(unsigned long long, delta)
 		__field(unsigned long, total_scan)
@@ -222,7 +222,7 @@ TRACE_EVENT(mm_shrink_slab_start,
 		__entry->shrink = shr->scan_objects;
 		__entry->nid = sc->nid;
 		__entry->nr_objects_to_shrink = nr_objects_to_shrink;
-		__entry->gfp_flags = sc->gfp_mask;
+		__entry->gfp_flags = (__force unsigned long)sc->gfp_mask;
 		__entry->cache_items = cache_items;
 		__entry->delta = delta;
 		__entry->total_scan = total_scan;
@@ -446,13 +446,13 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin,
 	TP_STRUCT__entry(
 		__field(int, nid)
 		__field(int, order)
-		__field(gfp_t, gfp_flags)
+		__field(unsigned long, gfp_flags)
 	),
 
 	TP_fast_assign(
 		__entry->nid = nid;
 		__entry->order = order;
-		__entry->gfp_flags = gfp_flags;
+		__entry->gfp_flags = (__force unsigned long)gfp_flags;
 	),
 
 	TP_printk("nid=%d order=%d gfp_flags=%s",
diff --git a/mm/compaction.c b/mm/compaction.c
index 65970107b789..0e0ef9e44530 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2569,7 +2569,7 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
 		enum compact_priority prio, struct page **capture)
 {
-	int may_perform_io = gfp_mask & __GFP_IO;
+	int may_perform_io = (__force int)(gfp_mask & __GFP_IO);
 	struct zoneref *z;
 	struct zone *zone;
 	enum compact_result rc = COMPACT_SKIPPED;
-- 
cgit v1.2.3


From 50d63b5bbfd12262069ad062611cd5e69c5e9e05 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 4 May 2022 16:14:41 -0300
Subject: vfio: Change vfio_external_user_iommu_id() to vfio_file_iommu_group()

The only caller wants to get a pointer to the struct iommu_group
associated with the VFIO group file. Instead of returning the group ID
then searching sysfs for that string to get the struct iommu_group just
directly return the iommu_group pointer already held by the vfio_group
struct.

It already has a safe lifetime due to the struct file kref, the vfio_group
and thus the iommu_group cannot be destroyed while the group file is open.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/3-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio.c  | 21 ++++++++++++++-------
 include/linux/vfio.h |  2 +-
 virt/kvm/vfio.c      | 37 ++++++++++++-------------------------
 3 files changed, 27 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 8cb7ba03aa16..25f90f3773de 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1653,10 +1653,7 @@ static const struct file_operations vfio_device_fops = {
  * increments the container user counter to prevent
  * the VFIO group from disposal before KVM exits.
  *
- * 3. The external user calls vfio_external_user_iommu_id()
- * to know an IOMMU ID.
- *
- * 4. When the external KVM finishes, it calls
+ * 3. When the external KVM finishes, it calls
  * vfio_group_put_external_user() to release the VFIO group.
  * This call decrements the container user counter.
  */
@@ -1697,11 +1694,21 @@ bool vfio_external_group_match_file(struct vfio_group *test_group,
 }
 EXPORT_SYMBOL_GPL(vfio_external_group_match_file);
 
-int vfio_external_user_iommu_id(struct vfio_group *group)
+/**
+ * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
+ * @file: VFIO group file
+ *
+ * The returned iommu_group is valid as long as a ref is held on the file.
+ */
+struct iommu_group *vfio_file_iommu_group(struct file *file)
 {
-	return iommu_group_id(group->iommu_group);
+	struct vfio_group *group = file->private_data;
+
+	if (file->f_op != &vfio_group_fops)
+		return NULL;
+	return group->iommu_group;
 }
-EXPORT_SYMBOL_GPL(vfio_external_user_iommu_id);
+EXPORT_SYMBOL_GPL(vfio_file_iommu_group);
 
 long vfio_external_check_extension(struct vfio_group *group, unsigned long arg)
 {
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index be1e7db4a314..d8c34c8490cb 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -140,7 +140,7 @@ extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
 extern bool vfio_external_group_match_file(struct vfio_group *group,
 					   struct file *filep);
-extern int vfio_external_user_iommu_id(struct vfio_group *group);
+extern struct iommu_group *vfio_file_iommu_group(struct file *file);
 extern long vfio_external_check_extension(struct vfio_group *group,
 					  unsigned long arg);
 
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 3bd2615154d0..9b7384dde158 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -108,43 +108,31 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
 }
 
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
+static struct iommu_group *kvm_vfio_file_iommu_group(struct file *file)
 {
-	int (*fn)(struct vfio_group *);
-	int ret = -EINVAL;
+	struct iommu_group *(*fn)(struct file *file);
+	struct iommu_group *ret;
 
-	fn = symbol_get(vfio_external_user_iommu_id);
+	fn = symbol_get(vfio_file_iommu_group);
 	if (!fn)
-		return ret;
+		return NULL;
 
-	ret = fn(vfio_group);
+	ret = fn(file);
 
-	symbol_put(vfio_external_user_iommu_id);
+	symbol_put(vfio_file_iommu_group);
 
 	return ret;
 }
 
-static struct iommu_group *kvm_vfio_group_get_iommu_group(
-		struct vfio_group *group)
-{
-	int group_id = kvm_vfio_external_user_iommu_id(group);
-
-	if (group_id < 0)
-		return NULL;
-
-	return iommu_group_get_by_id(group_id);
-}
-
 static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
-		struct vfio_group *vfio_group)
+					     struct kvm_vfio_group *kvg)
 {
-	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
+	struct iommu_group *grp = kvm_vfio_file_iommu_group(kvg->file);
 
 	if (WARN_ON_ONCE(!grp))
 		return;
 
 	kvm_spapr_tce_release_iommu_group(kvm, grp);
-	iommu_group_put(grp);
 }
 #endif
 
@@ -258,7 +246,7 @@ static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd)
 		list_del(&kvg->node);
 		kvm_arch_end_assignment(dev->kvm);
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
+		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg);
 #endif
 		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
@@ -304,7 +292,7 @@ static int kvm_vfio_group_set_spapr_tce(struct kvm_device *dev,
 		if (kvg->file != f.file)
 			continue;
 
-		grp = kvm_vfio_group_get_iommu_group(kvg->vfio_group);
+		grp = kvm_vfio_file_iommu_group(kvg->file);
 		if (WARN_ON_ONCE(!grp)) {
 			ret = -EIO;
 			goto err_fdput;
@@ -312,7 +300,6 @@ static int kvm_vfio_group_set_spapr_tce(struct kvm_device *dev,
 
 		ret = kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd,
 						       grp);
-		iommu_group_put(grp);
 		break;
 	}
 
@@ -388,7 +375,7 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 
 	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
+		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg);
 #endif
 		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
-- 
cgit v1.2.3


From c38ff5b0c373fbbd6a249eb461ffd4ae0f9dbfa0 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 4 May 2022 16:14:42 -0300
Subject: vfio: Remove vfio_external_group_match_file()

vfio_group_fops_open() ensures there is only ever one struct file open for
any struct vfio_group at any time:

	/* Do we need multiple instances of the group open?  Seems not. */
	opened = atomic_cmpxchg(&group->opened, 0, 1);
	if (opened) {
		vfio_group_put(group);
		return -EBUSY;

Therefor the struct file * can be used directly to search the list of VFIO
groups that KVM keeps instead of using the
vfio_external_group_match_file() callback to try to figure out if the
passed in FD matches the list or not.

Delete vfio_external_group_match_file().

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/4-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio.c  |  9 ---------
 include/linux/vfio.h |  2 --
 virt/kvm/vfio.c      | 19 +------------------
 3 files changed, 1 insertion(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 25f90f3773de..4805e18f2272 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1685,15 +1685,6 @@ void vfio_group_put_external_user(struct vfio_group *group)
 }
 EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
 
-bool vfio_external_group_match_file(struct vfio_group *test_group,
-				    struct file *filep)
-{
-	struct vfio_group *group = filep->private_data;
-
-	return (filep->f_op == &vfio_group_fops) && (group == test_group);
-}
-EXPORT_SYMBOL_GPL(vfio_external_group_match_file);
-
 /**
  * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
  * @file: VFIO group file
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index d8c34c8490cb..df0adecdf1ea 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -138,8 +138,6 @@ int vfio_mig_get_next_state(struct vfio_device *device,
  */
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
-extern bool vfio_external_group_match_file(struct vfio_group *group,
-					   struct file *filep);
 extern struct iommu_group *vfio_file_iommu_group(struct file *file);
 extern long vfio_external_check_extension(struct vfio_group *group,
 					  unsigned long arg);
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 9b7384dde158..0b84916c3f71 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -49,22 +49,6 @@ static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
 	return vfio_group;
 }
 
-static bool kvm_vfio_external_group_match_file(struct vfio_group *group,
-					       struct file *filep)
-{
-	bool ret, (*fn)(struct vfio_group *, struct file *);
-
-	fn = symbol_get(vfio_external_group_match_file);
-	if (!fn)
-		return false;
-
-	ret = fn(group, filep);
-
-	symbol_put(vfio_external_group_match_file);
-
-	return ret;
-}
-
 static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
 {
 	void (*fn)(struct vfio_group *);
@@ -239,8 +223,7 @@ static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd)
 	mutex_lock(&kv->lock);
 
 	list_for_each_entry(kvg, &kv->group_list, node) {
-		if (!kvm_vfio_external_group_match_file(kvg->vfio_group,
-							f.file))
+		if (kvg->file != f.file)
 			continue;
 
 		list_del(&kvg->node);
-- 
cgit v1.2.3


From a905ad043f32bbb0c35d4325036397f20f30c8a9 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 4 May 2022 16:14:43 -0300
Subject: vfio: Change vfio_external_check_extension() to
 vfio_file_enforced_coherent()

Instead of a general extension check change the function into a limited
test if the iommu_domain has enforced coherency, which is the only thing
kvm needs to query.

Make the new op self contained by properly refcounting the container
before touching it.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/5-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio.c  | 30 +++++++++++++++++++++++++++---
 include/linux/vfio.h |  3 +--
 virt/kvm/vfio.c      | 16 ++++++++--------
 3 files changed, 36 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 4805e18f2272..c2a360437e6c 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1701,11 +1701,35 @@ struct iommu_group *vfio_file_iommu_group(struct file *file)
 }
 EXPORT_SYMBOL_GPL(vfio_file_iommu_group);
 
-long vfio_external_check_extension(struct vfio_group *group, unsigned long arg)
+/**
+ * vfio_file_enforced_coherent - True if the DMA associated with the VFIO file
+ *        is always CPU cache coherent
+ * @file: VFIO group file
+ *
+ * Enforced coherency means that the IOMMU ignores things like the PCIe no-snoop
+ * bit in DMA transactions. A return of false indicates that the user has
+ * rights to access additional instructions such as wbinvd on x86.
+ */
+bool vfio_file_enforced_coherent(struct file *file)
 {
-	return vfio_ioctl_check_extension(group->container, arg);
+	struct vfio_group *group = file->private_data;
+	bool ret;
+
+	if (file->f_op != &vfio_group_fops)
+		return true;
+
+	/*
+	 * Since the coherency state is determined only once a container is
+	 * attached the user must do so before they can prove they have
+	 * permission.
+	 */
+	if (vfio_group_add_container_user(group))
+		return true;
+	ret = vfio_ioctl_check_extension(group->container, VFIO_DMA_CC_IOMMU);
+	vfio_group_try_dissolve_container(group);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(vfio_external_check_extension);
+EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);
 
 /*
  * Sub-module support
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index df0adecdf1ea..7cc374da4839 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -139,8 +139,7 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
 extern struct iommu_group *vfio_file_iommu_group(struct file *file);
-extern long vfio_external_check_extension(struct vfio_group *group,
-					  unsigned long arg);
+extern bool vfio_file_enforced_coherent(struct file *file);
 
 #define VFIO_PIN_PAGES_MAX_ENTRIES	(PAGE_SIZE/sizeof(unsigned long))
 
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 0b84916c3f71..d44cb3efb0b9 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -75,20 +75,20 @@ static void kvm_vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
 	symbol_put(vfio_group_set_kvm);
 }
 
-static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
+static bool kvm_vfio_file_enforced_coherent(struct file *file)
 {
-	long (*fn)(struct vfio_group *, unsigned long);
-	long ret;
+	bool (*fn)(struct file *file);
+	bool ret;
 
-	fn = symbol_get(vfio_external_check_extension);
+	fn = symbol_get(vfio_file_enforced_coherent);
 	if (!fn)
 		return false;
 
-	ret = fn(vfio_group, VFIO_DMA_CC_IOMMU);
+	ret = fn(file);
 
-	symbol_put(vfio_external_check_extension);
+	symbol_put(vfio_file_enforced_coherent);
 
-	return ret > 0;
+	return ret;
 }
 
 #ifdef CONFIG_SPAPR_TCE_IOMMU
@@ -136,7 +136,7 @@ static void kvm_vfio_update_coherency(struct kvm_device *dev)
 	mutex_lock(&kv->lock);
 
 	list_for_each_entry(kvg, &kv->group_list, node) {
-		if (!kvm_vfio_group_is_coherent(kvg->vfio_group)) {
+		if (!kvm_vfio_file_enforced_coherent(kvg->file)) {
 			noncoherent = true;
 			break;
 		}
-- 
cgit v1.2.3


From ba70a89f3c2a8279809ea0fc7684857c91938b8a Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 4 May 2022 16:14:44 -0300
Subject: vfio: Change vfio_group_set_kvm() to vfio_file_set_kvm()

Just change the argument from struct vfio_group to struct file *.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/6-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio.c  | 29 +++++++++++++++++++++--------
 include/linux/vfio.h |  5 +++--
 virt/kvm/vfio.c      | 16 ++++++++--------
 3 files changed, 32 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index c2a360437e6c..a0f73bd8e53f 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1731,6 +1731,27 @@ bool vfio_file_enforced_coherent(struct file *file)
 }
 EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);
 
+/**
+ * vfio_file_set_kvm - Link a kvm with VFIO drivers
+ * @file: VFIO group file
+ * @kvm: KVM to link
+ *
+ * The kvm pointer will be forwarded to all the vfio_device's attached to the
+ * VFIO file via the VFIO_GROUP_NOTIFY_SET_KVM notifier.
+ */
+void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
+{
+	struct vfio_group *group = file->private_data;
+
+	if (file->f_op != &vfio_group_fops)
+		return;
+
+	group->kvm = kvm;
+	blocking_notifier_call_chain(&group->notifier,
+				     VFIO_GROUP_NOTIFY_SET_KVM, kvm);
+}
+EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
+
 /*
  * Sub-module support
  */
@@ -1999,14 +2020,6 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group,
 	return ret;
 }
 
-void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
-{
-	group->kvm = kvm;
-	blocking_notifier_call_chain(&group->notifier,
-				VFIO_GROUP_NOTIFY_SET_KVM, kvm);
-}
-EXPORT_SYMBOL_GPL(vfio_group_set_kvm);
-
 static int vfio_register_group_notifier(struct vfio_group *group,
 					unsigned long *events,
 					struct notifier_block *nb)
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 7cc374da4839..b298a26c4f07 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -15,6 +15,8 @@
 #include <linux/poll.h>
 #include <uapi/linux/vfio.h>
 
+struct kvm;
+
 /*
  * VFIO devices can be placed in a set, this allows all devices to share this
  * structure and the VFIO core will provide a lock that is held around
@@ -140,6 +142,7 @@ extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
 extern struct iommu_group *vfio_file_iommu_group(struct file *file);
 extern bool vfio_file_enforced_coherent(struct file *file);
+extern void vfio_file_set_kvm(struct file *file, struct kvm *kvm);
 
 #define VFIO_PIN_PAGES_MAX_ENTRIES	(PAGE_SIZE/sizeof(unsigned long))
 
@@ -170,8 +173,6 @@ extern int vfio_unregister_notifier(struct vfio_device *device,
 				    enum vfio_notify_type type,
 				    struct notifier_block *nb);
 
-struct kvm;
-extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm);
 
 /*
  * Sub-module helpers
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index d44cb3efb0b9..b4e1bc22b7c5 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -62,17 +62,17 @@ static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
 	symbol_put(vfio_group_put_external_user);
 }
 
-static void kvm_vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
+static void kvm_vfio_file_set_kvm(struct file *file, struct kvm *kvm)
 {
-	void (*fn)(struct vfio_group *, struct kvm *);
+	void (*fn)(struct file *file, struct kvm *kvm);
 
-	fn = symbol_get(vfio_group_set_kvm);
+	fn = symbol_get(vfio_file_set_kvm);
 	if (!fn)
 		return;
 
-	fn(group, kvm);
+	fn(file, kvm);
 
-	symbol_put(vfio_group_set_kvm);
+	symbol_put(vfio_file_set_kvm);
 }
 
 static bool kvm_vfio_file_enforced_coherent(struct file *file)
@@ -195,7 +195,7 @@ static int kvm_vfio_group_add(struct kvm_device *dev, unsigned int fd)
 
 	mutex_unlock(&kv->lock);
 
-	kvm_vfio_group_set_kvm(vfio_group, dev->kvm);
+	kvm_vfio_file_set_kvm(kvg->file, dev->kvm);
 	kvm_vfio_update_coherency(dev);
 
 	return 0;
@@ -231,7 +231,7 @@ static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd)
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg);
 #endif
-		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
+		kvm_vfio_file_set_kvm(kvg->file, NULL);
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
 		fput(kvg->file);
 		kfree(kvg);
@@ -360,7 +360,7 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg);
 #endif
-		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
+		kvm_vfio_file_set_kvm(kvg->file, NULL);
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
 		fput(kvg->file);
 		list_del(&kvg->node);
-- 
cgit v1.2.3


From 6a985ae80befcf2c00e7c889336bfe9e9739e2ef Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 4 May 2022 16:14:46 -0300
Subject: vfio/pci: Use the struct file as the handle not the vfio_group

VFIO PCI does a security check as part of hot reset to prove that the user
has permission to manipulate all the devices that will be impacted by the
reset.

Use a new API vfio_file_has_dev() to perform this security check against
the struct file directly and remove the vfio_group from VFIO PCI.

Since VFIO PCI was the last user of vfio_group_get_external_user() and
vfio_group_put_external_user() remove it as well.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/8-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci_core.c | 42 ++++++++++++------------
 drivers/vfio/vfio.c              | 70 +++++++++++-----------------------------
 include/linux/vfio.h             |  3 +-
 3 files changed, 40 insertions(+), 75 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 100ab98c7ff0..05a3aa95ba52 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -556,7 +556,7 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
 
 struct vfio_pci_group_info {
 	int count;
-	struct vfio_group **groups;
+	struct file **files;
 };
 
 static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot)
@@ -1018,10 +1018,10 @@ reset_info_exit:
 	} else if (cmd == VFIO_DEVICE_PCI_HOT_RESET) {
 		struct vfio_pci_hot_reset hdr;
 		int32_t *group_fds;
-		struct vfio_group **groups;
+		struct file **files;
 		struct vfio_pci_group_info info;
 		bool slot = false;
-		int group_idx, count = 0, ret = 0;
+		int file_idx, count = 0, ret = 0;
 
 		minsz = offsetofend(struct vfio_pci_hot_reset, count);
 
@@ -1054,17 +1054,17 @@ reset_info_exit:
 			return -EINVAL;
 
 		group_fds = kcalloc(hdr.count, sizeof(*group_fds), GFP_KERNEL);
-		groups = kcalloc(hdr.count, sizeof(*groups), GFP_KERNEL);
-		if (!group_fds || !groups) {
+		files = kcalloc(hdr.count, sizeof(*files), GFP_KERNEL);
+		if (!group_fds || !files) {
 			kfree(group_fds);
-			kfree(groups);
+			kfree(files);
 			return -ENOMEM;
 		}
 
 		if (copy_from_user(group_fds, (void __user *)(arg + minsz),
 				   hdr.count * sizeof(*group_fds))) {
 			kfree(group_fds);
-			kfree(groups);
+			kfree(files);
 			return -EFAULT;
 		}
 
@@ -1073,22 +1073,22 @@ reset_info_exit:
 		 * user interface and store the group and iommu ID.  This
 		 * ensures the group is held across the reset.
 		 */
-		for (group_idx = 0; group_idx < hdr.count; group_idx++) {
-			struct vfio_group *group;
-			struct fd f = fdget(group_fds[group_idx]);
-			if (!f.file) {
+		for (file_idx = 0; file_idx < hdr.count; file_idx++) {
+			struct file *file = fget(group_fds[file_idx]);
+
+			if (!file) {
 				ret = -EBADF;
 				break;
 			}
 
-			group = vfio_group_get_external_user(f.file);
-			fdput(f);
-			if (IS_ERR(group)) {
-				ret = PTR_ERR(group);
+			/* Ensure the FD is a vfio group FD.*/
+			if (!vfio_file_iommu_group(file)) {
+				fput(file);
+				ret = -EINVAL;
 				break;
 			}
 
-			groups[group_idx] = group;
+			files[file_idx] = file;
 		}
 
 		kfree(group_fds);
@@ -1098,15 +1098,15 @@ reset_info_exit:
 			goto hot_reset_release;
 
 		info.count = hdr.count;
-		info.groups = groups;
+		info.files = files;
 
 		ret = vfio_pci_dev_set_hot_reset(vdev->vdev.dev_set, &info);
 
 hot_reset_release:
-		for (group_idx--; group_idx >= 0; group_idx--)
-			vfio_group_put_external_user(groups[group_idx]);
+		for (file_idx--; file_idx >= 0; file_idx--)
+			fput(files[file_idx]);
 
-		kfree(groups);
+		kfree(files);
 		return ret;
 	} else if (cmd == VFIO_DEVICE_IOEVENTFD) {
 		struct vfio_device_ioeventfd ioeventfd;
@@ -1972,7 +1972,7 @@ static bool vfio_dev_in_groups(struct vfio_pci_core_device *vdev,
 	unsigned int i;
 
 	for (i = 0; i < groups->count; i++)
-		if (groups->groups[i] == vdev->vdev.group)
+		if (vfio_file_has_dev(groups->files[i], &vdev->vdev))
 			return true;
 	return false;
 }
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index a0f73bd8e53f..1758d96f43f4 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1633,58 +1633,6 @@ static const struct file_operations vfio_device_fops = {
 	.mmap		= vfio_device_fops_mmap,
 };
 
-/*
- * External user API, exported by symbols to be linked dynamically.
- *
- * The protocol includes:
- *  1. do normal VFIO init operation:
- *	- opening a new container;
- *	- attaching group(s) to it;
- *	- setting an IOMMU driver for a container.
- * When IOMMU is set for a container, all groups in it are
- * considered ready to use by an external user.
- *
- * 2. User space passes a group fd to an external user.
- * The external user calls vfio_group_get_external_user()
- * to verify that:
- *	- the group is initialized;
- *	- IOMMU is set for it.
- * If both checks passed, vfio_group_get_external_user()
- * increments the container user counter to prevent
- * the VFIO group from disposal before KVM exits.
- *
- * 3. When the external KVM finishes, it calls
- * vfio_group_put_external_user() to release the VFIO group.
- * This call decrements the container user counter.
- */
-struct vfio_group *vfio_group_get_external_user(struct file *filep)
-{
-	struct vfio_group *group = filep->private_data;
-	int ret;
-
-	if (filep->f_op != &vfio_group_fops)
-		return ERR_PTR(-EINVAL);
-
-	ret = vfio_group_add_container_user(group);
-	if (ret)
-		return ERR_PTR(ret);
-
-	/*
-	 * Since the caller holds the fget on the file group->users must be >= 1
-	 */
-	vfio_group_get(group);
-
-	return group;
-}
-EXPORT_SYMBOL_GPL(vfio_group_get_external_user);
-
-void vfio_group_put_external_user(struct vfio_group *group)
-{
-	vfio_group_try_dissolve_container(group);
-	vfio_group_put(group);
-}
-EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
-
 /**
  * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
  * @file: VFIO group file
@@ -1752,6 +1700,24 @@ void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
 
+/**
+ * vfio_file_has_dev - True if the VFIO file is a handle for device
+ * @file: VFIO file to check
+ * @device: Device that must be part of the file
+ *
+ * Returns true if given file has permission to manipulate the given device.
+ */
+bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
+{
+	struct vfio_group *group = file->private_data;
+
+	if (file->f_op != &vfio_group_fops)
+		return false;
+
+	return group == device->group;
+}
+EXPORT_SYMBOL_GPL(vfio_file_has_dev);
+
 /*
  * Sub-module support
  */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index b298a26c4f07..45b287826ce6 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -138,11 +138,10 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 /*
  * External user API
  */
-extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
-extern void vfio_group_put_external_user(struct vfio_group *group);
 extern struct iommu_group *vfio_file_iommu_group(struct file *file);
 extern bool vfio_file_enforced_coherent(struct file *file);
 extern void vfio_file_set_kvm(struct file *file, struct kvm *kvm);
+extern bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
 
 #define VFIO_PIN_PAGES_MAX_ENTRIES	(PAGE_SIZE/sizeof(unsigned long))
 
-- 
cgit v1.2.3


From 1af0e4a0233fea7e8226cb977d379dc20f9bbe11 Mon Sep 17 00:00:00 2001
From: Christian Göttsche <cgzones@googlemail.com>
Date: Thu, 17 Feb 2022 15:18:57 +0100
Subject: security: declare member holding string literal const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The struct security_hook_list member lsm is assigned in
security_add_hooks() with string literals passed from the individual
security modules.  Declare the function parameter and the struct member
const to signal their immutability.

Reported by Clang [-Wwrite-strings]:

    security/selinux/hooks.c:7388:63: error: passing 'const char [8]'
      to parameter of type 'char *' discards qualifiers
      [-Werror,-Wincompatible-pointer-types-discards-qualifiers]
            security_add_hooks(selinux_hooks,
                               ARRAY_SIZE(selinux_hooks), selinux);
                                                          ^~~~~~~~~
    ./include/linux/lsm_hooks.h:1629:11: note: passing argument to
      parameter 'lsm' here
                                    char *lsm);
                                          ^

Signed-off-by: Christian Göttsche <cgzones@googlemail.com>
Reviewed-by: Paul Moore <paul@paul-moore.com>
Reviewed-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/lsm_hooks.h | 4 ++--
 security/security.c       | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 419b5febc3ca..47cdf3fbecef 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1595,7 +1595,7 @@ struct security_hook_list {
 	struct hlist_node		list;
 	struct hlist_head		*head;
 	union security_list_options	hook;
-	char				*lsm;
+	const char			*lsm;
 } __randomize_layout;
 
 /*
@@ -1630,7 +1630,7 @@ extern struct security_hook_heads security_hook_heads;
 extern char *lsm_names;
 
 extern void security_add_hooks(struct security_hook_list *hooks, int count,
-				char *lsm);
+				const char *lsm);
 
 #define LSM_FLAG_LEGACY_MAJOR	BIT(0)
 #define LSM_FLAG_EXCLUSIVE	BIT(1)
diff --git a/security/security.c b/security/security.c
index b7cf5cbfdc67..985afd150dd6 100644
--- a/security/security.c
+++ b/security/security.c
@@ -478,7 +478,7 @@ static int lsm_append(const char *new, char **result)
  * Each LSM has to register its hooks with the infrastructure.
  */
 void __init security_add_hooks(struct security_hook_list *hooks, int count,
-				char *lsm)
+				const char *lsm)
 {
 	int i;
 
-- 
cgit v1.2.3


From 1366992e16bddd5e2d9a561687f367f9f802e2e4 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sun, 10 Apr 2022 16:49:50 +0200
Subject: timekeeping: Add raw clock fallback for random_get_entropy()

The addition of random_get_entropy_fallback() provides access to
whichever time source has the highest frequency, which is useful for
gathering entropy on platforms without available cycle counters. It's
not necessarily as good as being able to quickly access a cycle counter
that the CPU has, but it's still something, even when it falls back to
being jiffies-based.

In the event that a given arch does not define get_cycles(), falling
back to the get_cycles() default implementation that returns 0 is really
not the best we can do. Instead, at least calling
random_get_entropy_fallback() would be preferable, because that always
needs to return _something_, even falling back to jiffies eventually.
It's not as though random_get_entropy_fallback() is super high precision
or guaranteed to be entropic, but basically anything that's not zero all
the time is better than returning zero all the time.

Finally, since random_get_entropy_fallback() is used during extremely
early boot when randomizing freelists in mm_init(), it can be called
before timekeeping has been initialized. In that case there really is
nothing we can do; jiffies hasn't even started ticking yet. So just give
up and return 0.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Theodore Ts'o <tytso@mit.edu>
---
 include/linux/timex.h     |  8 ++++++++
 kernel/time/timekeeping.c | 15 +++++++++++++++
 2 files changed, 23 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/timex.h b/include/linux/timex.h
index 5745c90c8800..3871b06bd302 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -62,6 +62,8 @@
 #include <linux/types.h>
 #include <linux/param.h>
 
+unsigned long random_get_entropy_fallback(void);
+
 #include <asm/timex.h>
 
 #ifndef random_get_entropy
@@ -74,8 +76,14 @@
  *
  * By default we use get_cycles() for this purpose, but individual
  * architectures may override this in their asm/timex.h header file.
+ * If a given arch does not have get_cycles(), then we fallback to
+ * using random_get_entropy_fallback().
  */
+#ifdef get_cycles
 #define random_get_entropy()	((unsigned long)get_cycles())
+#else
+#define random_get_entropy()	random_get_entropy_fallback()
+#endif
 #endif
 
 /*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3b1398fbddaf..871c912860ed 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -17,6 +17,7 @@
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
 #include <linux/time.h>
+#include <linux/timex.h>
 #include <linux/tick.h>
 #include <linux/stop_machine.h>
 #include <linux/pvclock_gtod.h>
@@ -2380,6 +2381,20 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc)
 	return 0;
 }
 
+/**
+ * random_get_entropy_fallback - Returns the raw clock source value,
+ * used by random.c for platforms with no valid random_get_entropy().
+ */
+unsigned long random_get_entropy_fallback(void)
+{
+	struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono;
+	struct clocksource *clock = READ_ONCE(tkr->clock);
+
+	if (unlikely(timekeeping_suspended || !clock))
+		return 0;
+	return clock->read(clock);
+}
+EXPORT_SYMBOL_GPL(random_get_entropy_fallback);
 
 /**
  * do_adjtimex() - Accessor function to NTP __do_adjtimex function
-- 
cgit v1.2.3


From 16d1e00c7e8a4950e914223b3112144289a82913 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Mon, 9 May 2022 15:42:52 -0700
Subject: bpf: Add MEM_UNINIT as a bpf_type_flag

Instead of having uninitialized versions of arguments as separate
bpf_arg_types (eg ARG_PTR_TO_UNINIT_MEM as the uninitialized version
of ARG_PTR_TO_MEM), we can instead use MEM_UNINIT as a bpf_type_flag
modifier to denote that the argument is uninitialized.

Doing so cleans up some of the logic in the verifier. We no longer
need to do two checks against an argument type (eg "if
(base_type(arg_type) == ARG_PTR_TO_MEM || base_type(arg_type) ==
ARG_PTR_TO_UNINIT_MEM)"), since uninitialized and initialized
versions of the same argument type will now share the same base type.

In the near future, MEM_UNINIT will be used by dynptr helper functions
as well.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/r/20220509224257.3222614-2-joannelkoong@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   | 18 ++++++++++--------
 kernel/bpf/helpers.c  |  4 ++--
 kernel/bpf/verifier.c | 28 ++++++++--------------------
 3 files changed, 20 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5061ccd8b2dc..c107392b0ba7 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -390,7 +390,10 @@ enum bpf_type_flag {
 	 */
 	PTR_UNTRUSTED		= BIT(6 + BPF_BASE_TYPE_BITS),
 
-	__BPF_TYPE_LAST_FLAG	= PTR_UNTRUSTED,
+	MEM_UNINIT		= BIT(7 + BPF_BASE_TYPE_BITS),
+
+	__BPF_TYPE_FLAG_MAX,
+	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
 
 /* Max number of base types. */
@@ -409,16 +412,11 @@ enum bpf_arg_type {
 	ARG_CONST_MAP_PTR,	/* const argument used as pointer to bpf_map */
 	ARG_PTR_TO_MAP_KEY,	/* pointer to stack used as map key */
 	ARG_PTR_TO_MAP_VALUE,	/* pointer to stack used as map value */
-	ARG_PTR_TO_UNINIT_MAP_VALUE,	/* pointer to valid memory used to store a map value */
 
-	/* the following constraints used to prototype bpf_memcmp() and other
-	 * functions that access data on eBPF program stack
+	/* Used to prototype bpf_memcmp() and other functions that access data
+	 * on eBPF program stack
 	 */
 	ARG_PTR_TO_MEM,		/* pointer to valid memory (stack, packet, map value) */
-	ARG_PTR_TO_UNINIT_MEM,	/* pointer to memory does not need to be initialized,
-				 * helper function must fill all bytes or clear
-				 * them in error case.
-				 */
 
 	ARG_CONST_SIZE,		/* number of bytes accessed from memory */
 	ARG_CONST_SIZE_OR_ZERO,	/* number of bytes accessed from memory or 0 */
@@ -450,6 +448,10 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM,
 	ARG_PTR_TO_STACK_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
 	ARG_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
+	/* pointer to memory does not need to be initialized, helper function must fill
+	 * all bytes or clear them in error case.
+	 */
+	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | ARG_PTR_TO_MEM,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index d5f104a39092..bad96131a510 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -103,7 +103,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
+	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
 };
 
 BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
@@ -116,7 +116,7 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
+	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
 };
 
 BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 05c1b6656824..9b59581026f8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5377,12 +5377,6 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno,
 	return 0;
 }
 
-static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
-{
-	return base_type(type) == ARG_PTR_TO_MEM ||
-	       base_type(type) == ARG_PTR_TO_UNINIT_MEM;
-}
-
 static bool arg_type_is_mem_size(enum bpf_arg_type type)
 {
 	return type == ARG_CONST_SIZE ||
@@ -5522,7 +5516,6 @@ static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } }
 static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
 	[ARG_PTR_TO_MAP_VALUE]		= &map_key_value_types,
-	[ARG_PTR_TO_UNINIT_MAP_VALUE]	= &map_key_value_types,
 	[ARG_CONST_SIZE]		= &scalar_types,
 	[ARG_CONST_SIZE_OR_ZERO]	= &scalar_types,
 	[ARG_CONST_ALLOC_SIZE_OR_ZERO]	= &scalar_types,
@@ -5536,7 +5529,6 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
 	[ARG_PTR_TO_SPIN_LOCK]		= &spin_lock_types,
 	[ARG_PTR_TO_MEM]		= &mem_types,
-	[ARG_PTR_TO_UNINIT_MEM]		= &mem_types,
 	[ARG_PTR_TO_ALLOC_MEM]		= &alloc_mem_types,
 	[ARG_PTR_TO_INT]		= &int_ptr_types,
 	[ARG_PTR_TO_LONG]		= &int_ptr_types,
@@ -5710,8 +5702,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		return -EACCES;
 	}
 
-	if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
-	    base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+	if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE) {
 		err = resolve_map_arg_type(env, meta, &arg_type);
 		if (err)
 			return err;
@@ -5797,8 +5788,7 @@ skip_type_check:
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->key_size, false,
 					      NULL);
-	} else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
-		   base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+	} else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE) {
 		if (type_may_be_null(arg_type) && register_is_null(reg))
 			return 0;
 
@@ -5810,7 +5800,7 @@ skip_type_check:
 			verbose(env, "invalid map_ptr to access map->value\n");
 			return -EACCES;
 		}
-		meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE);
+		meta->raw_mode = arg_type & MEM_UNINIT;
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->value_size, false,
 					      meta);
@@ -5837,11 +5827,11 @@ skip_type_check:
 			return -EACCES;
 	} else if (arg_type == ARG_PTR_TO_FUNC) {
 		meta->subprogno = reg->subprogno;
-	} else if (arg_type_is_mem_ptr(arg_type)) {
+	} else if (base_type(arg_type) == ARG_PTR_TO_MEM) {
 		/* The access to this pointer is only checked when we hit the
 		 * next is_mem_size argument below.
 		 */
-		meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MEM);
+		meta->raw_mode = arg_type & MEM_UNINIT;
 	} else if (arg_type_is_mem_size(arg_type)) {
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
 
@@ -6194,10 +6184,8 @@ static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
 static bool check_args_pair_invalid(enum bpf_arg_type arg_curr,
 				    enum bpf_arg_type arg_next)
 {
-	return (arg_type_is_mem_ptr(arg_curr) &&
-	        !arg_type_is_mem_size(arg_next)) ||
-	       (!arg_type_is_mem_ptr(arg_curr) &&
-		arg_type_is_mem_size(arg_next));
+	return (base_type(arg_curr) == ARG_PTR_TO_MEM) !=
+		arg_type_is_mem_size(arg_next);
 }
 
 static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
@@ -6208,7 +6196,7 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
 	 * helper function specification.
 	 */
 	if (arg_type_is_mem_size(fn->arg1_type) ||
-	    arg_type_is_mem_ptr(fn->arg5_type)  ||
+	    base_type(fn->arg5_type) == ARG_PTR_TO_MEM ||
 	    check_args_pair_invalid(fn->arg1_type, fn->arg2_type) ||
 	    check_args_pair_invalid(fn->arg2_type, fn->arg3_type) ||
 	    check_args_pair_invalid(fn->arg3_type, fn->arg4_type) ||
-- 
cgit v1.2.3


From e7392b4eca84e86718a7b73aea8fa5573b06ba76 Mon Sep 17 00:00:00 2001
From: "Fabio M. De Francesco" <fmdefrancesco@gmail.com>
Date: Fri, 13 May 2022 16:48:55 -0700
Subject: mm/highmem: fix kernel-doc warnings in highmem*.h

Patch series "Extend and reorganize Highmem's documentation", v4.

This series has the purpose to extend and reorganize Highmem's
documentation.

This is a work in progress because some information should still be moved
from highmem.rst to highmem.h and highmem-internal.h.  Specifically I'm
talking about moving the "how to" information to the relevant headers, as
it as been suggested by Ira Weiny (Intel).

Also, this is a work in progress because some kdocs in highmem.h and
highmem-internal.h should be improved.


This patch (of 4):

`scripts/kernel-doc -v -none include/linux/highmem*` reports the following
warnings:

include/linux/highmem.h:160: warning: expecting prototype for kunmap_atomic(). Prototype was for nr_free_highpages() instead
include/linux/highmem.h:204: warning: No description found for return value of 'alloc_zeroed_user_highpage_movable'
include/linux/highmem-internal.h:256: warning: Function parameter or member '__addr' not described in 'kunmap_atomic'
include/linux/highmem-internal.h:256: warning: Excess function parameter 'addr' description in 'kunmap_atomic'

Fix these warnings by (1) moving the kernel-doc comments from highmem.h to
highmem-internal.h (which is the file were the kunmap_atomic() macro is
actually defined), (2) extending and merging it with the comment which was
already in highmem-internal.h, and (3) using correct parameter names (4)
correcting a few technical inaccuracies in comments, and (5) adding a
deprecation notice in kunmap_atomic() for consistency with kmap_atomic().

Link: https://lkml.kernel.org/r/20220428212455.892-1-fmdefrancesco@gmail.com
Link: https://lkml.kernel.org/r/20220428212455.892-2-fmdefrancesco@gmail.com
Signed-off-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/highmem-internal.h | 18 +++++++++++++++---
 include/linux/highmem.h          | 22 ++++++++--------------
 2 files changed, 23 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index a77be5630209..a694ca95c4ed 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -236,9 +236,21 @@ static inline unsigned long totalhigh_pages(void) { return 0UL; }
 
 #endif /* CONFIG_HIGHMEM */
 
-/*
- * Prevent people trying to call kunmap_atomic() as if it were kunmap()
- * kunmap_atomic() should get the return value of kmap_atomic, not the page.
+/**
+ * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated!
+ * @__addr:       Virtual address to be unmapped
+ *
+ * Unmaps an address previously mapped by kmap_atomic() and re-enables
+ * pagefaults. Depending on PREEMP_RT configuration, re-enables also
+ * migration and preemption. Users should not count on these side effects.
+ *
+ * Mappings should be unmapped in the reverse order that they were mapped.
+ * See kmap_local_page() for details on nesting.
+ *
+ * @__addr can be any address within the mapped page, so there is no need
+ * to subtract any offset that has been added. In contrast to kunmap(),
+ * this function takes the address returned from kmap_atomic(), not the
+ * page passed to it. The compiler will warn you if you pass the page.
  */
 #define kunmap_atomic(__addr)					\
 do {								\
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 67720bfd6ade..c05ae395898a 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -37,7 +37,7 @@ static inline void *kmap(struct page *page);
 
 /**
  * kunmap - Unmap the virtual address mapped by kmap()
- * @addr:	Virtual address to be unmapped
+ * @page:	Pointer to the page which was mapped by kmap()
  *
  * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of
  * pages in the low memory area.
@@ -138,24 +138,16 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset);
  *
  * Returns: The virtual address of the mapping
  *
- * Effectively a wrapper around kmap_local_page() which disables pagefaults
- * and preemption.
+ * In fact a wrapper around kmap_local_page() which also disables pagefaults
+ * and, depending on PREEMPT_RT configuration, also CPU migration and
+ * preemption. Therefore users should not count on the latter two side effects.
+ *
+ * Mappings should always be released by kunmap_atomic().
  *
  * Do not use in new code. Use kmap_local_page() instead.
  */
 static inline void *kmap_atomic(struct page *page);
 
-/**
- * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic()
- * @addr:	Virtual address to be unmapped
- *
- * Counterpart to kmap_atomic().
- *
- * Effectively a wrapper around kunmap_local() which additionally undoes
- * the side effects of kmap_atomic(), i.e. reenabling pagefaults and
- * preemption.
- */
-
 /* Highmem related interfaces for management code */
 static inline unsigned int nr_free_highpages(void);
 static inline unsigned long totalhigh_pages(void);
@@ -191,6 +183,8 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
  * @vma: The VMA the page is to be allocated for
  * @vaddr: The virtual address the page will be inserted into
  *
+ * Returns: The allocated and zeroed HIGHMEM page
+ *
  * This function will allocate a page for a VMA that the caller knows will
  * be able to migrate in the future using move_pages() or reclaimed
  *
-- 
cgit v1.2.3


From 85a85e7601263f2b4edc86136dd0172c2cfbfaa1 Mon Sep 17 00:00:00 2001
From: "Fabio M. De Francesco" <fmdefrancesco@gmail.com>
Date: Fri, 13 May 2022 16:48:55 -0700
Subject: Documentation/vm: move "Using kmap-atomic" to highmem.h

The use of kmap_atomic() is new code is being deprecated in favor of
kmap_local_page().  For this reason the "Using kmap_atomic" section in
highmem.rst is obsolete and unnecessary, but it can still help developers
if it were moved to kdocs in highmem.h.

Therefore, move the relevant parts of this section from highmem.rst and
merge them with the kdocs in highmem.h.

Link: https://lkml.kernel.org/r/20220428212455.892-4-fmdefrancesco@gmail.com
Signed-off-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
Suggested-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/vm/highmem.rst | 35 -----------------------------------
 include/linux/highmem.h      | 31 +++++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/vm/highmem.rst b/Documentation/vm/highmem.rst
index ccff08a8211d..e05bf5524174 100644
--- a/Documentation/vm/highmem.rst
+++ b/Documentation/vm/highmem.rst
@@ -72,41 +72,6 @@ The kernel contains several ways of creating temporary mappings:
   It may be assumed that k[un]map_atomic() won't fail.
 
 
-Using kmap_atomic
-=================
-
-When and where to use kmap_atomic() is straightforward.  It is used when code
-wants to access the contents of a page that might be allocated from high memory
-(see __GFP_HIGHMEM), for example a page in the pagecache.  The API has two
-functions, and they can be used in a manner similar to the following::
-
-	/* Find the page of interest. */
-	struct page *page = find_get_page(mapping, offset);
-
-	/* Gain access to the contents of that page. */
-	void *vaddr = kmap_atomic(page);
-
-	/* Do something to the contents of that page. */
-	memset(vaddr, 0, PAGE_SIZE);
-
-	/* Unmap that page. */
-	kunmap_atomic(vaddr);
-
-Note that the kunmap_atomic() call takes the result of the kmap_atomic() call
-not the argument.
-
-If you need to map two pages because you want to copy from one page to
-another you need to keep the kmap_atomic calls strictly nested, like::
-
-	vaddr1 = kmap_atomic(page1);
-	vaddr2 = kmap_atomic(page2);
-
-	memcpy(vaddr1, vaddr2, PAGE_SIZE);
-
-	kunmap_atomic(vaddr2);
-	kunmap_atomic(vaddr1);
-
-
 Cost of Temporary Mappings
 ==========================
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index c05ae395898a..3af34de54330 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -145,6 +145,37 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset);
  * Mappings should always be released by kunmap_atomic().
  *
  * Do not use in new code. Use kmap_local_page() instead.
+ *
+ * It is used in atomic context when code wants to access the contents of a
+ * page that might be allocated from high memory (see __GFP_HIGHMEM), for
+ * example a page in the pagecache.  The API has two functions, and they
+ * can be used in a manner similar to the following:
+ *
+ * -- Find the page of interest. --
+ * struct page *page = find_get_page(mapping, offset);
+ *
+ * -- Gain access to the contents of that page. --
+ * void *vaddr = kmap_atomic(page);
+ *
+ * -- Do something to the contents of that page. --
+ * memset(vaddr, 0, PAGE_SIZE);
+ *
+ * -- Unmap that page. --
+ * kunmap_atomic(vaddr);
+ *
+ * Note that the kunmap_atomic() call takes the result of the kmap_atomic()
+ * call, not the argument.
+ *
+ * If you need to map two pages because you want to copy from one page to
+ * another you need to keep the kmap_atomic calls strictly nested, like:
+ *
+ * vaddr1 = kmap_atomic(page1);
+ * vaddr2 = kmap_atomic(page2);
+ *
+ * memcpy(vaddr1, vaddr2, PAGE_SIZE);
+ *
+ * kunmap_atomic(vaddr2);
+ * kunmap_atomic(vaddr1);
  */
 static inline void *kmap_atomic(struct page *page);
 
-- 
cgit v1.2.3


From 5d4af6195c87c6b162b7963e0ad00a214b80d764 Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Fri, 13 May 2022 16:48:55 -0700
Subject: mm: rmap: fix CONT-PTE/PMD size hugetlb issue when migration

On some architectures (like ARM64), it can support CONT-PTE/PMD size
hugetlb, which means it can support not only PMD/PUD size hugetlb: 2M and
1G, but also CONT-PTE/PMD size: 64K and 32M if a 4K page size specified.

When migrating a hugetlb page, we will get the relevant page table entry
by huge_pte_offset() only once to nuke it and remap it with a migration
pte entry.  This is correct for PMD or PUD size hugetlb, since they always
contain only one pmd entry or pud entry in the page table.

However this is incorrect for CONT-PTE and CONT-PMD size hugetlb, since
they can contain several continuous pte or pmd entry with same page table
attributes.  So we will nuke or remap only one pte or pmd entry for this
CONT-PTE/PMD size hugetlb page, which is not expected for hugetlb
migration.  The problem is we can still continue to modify the subpages'
data of a hugetlb page during migrating a hugetlb page, which can cause a
serious data consistent issue, since we did not nuke the page table entry
and set a migration pte for the subpages of a hugetlb page.

To fix this issue, we should change to use huge_ptep_clear_flush() to nuke
a hugetlb page table, and remap it with set_huge_pte_at() and
set_huge_swap_pte_at() when migrating a hugetlb page, which already
considered the CONT-PTE or CONT-PMD size hugetlb.

[akpm@linux-foundation.org: fix nommu build]
[baolin.wang@linux.alibaba.com: fix build errors for !CONFIG_MMU]
  Link: https://lkml.kernel.org/r/a4baca670aca637e7198d9ae4543b8873cb224dc.1652270205.git.baolin.wang@linux.alibaba.com
Link: https://lkml.kernel.org/r/ea5abf529f0997b5430961012bfda6166c1efc8c.1652147571.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.osdn.me>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h | 11 +++++++++++
 mm/rmap.c               | 24 ++++++++++++++++++------
 2 files changed, 29 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 04f0186b089b..0f2894d01333 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1093,6 +1093,17 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 					pte_t *ptep, pte_t pte, unsigned long sz)
 {
 }
+
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/mm/rmap.c b/mm/rmap.c
index 94d6b24a1ac2..4e96daff9293 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1926,13 +1926,15 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 					break;
 				}
 			}
+
+			/* Nuke the hugetlb page table entry */
+			pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
 		} else {
 			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+			/* Nuke the page table entry. */
+			pteval = ptep_clear_flush(vma, address, pvmw.pte);
 		}
 
-		/* Nuke the page table entry. */
-		pteval = ptep_clear_flush(vma, address, pvmw.pte);
-
 		/* Set the dirty flag on the folio now the pte is gone. */
 		if (pte_dirty(pteval))
 			folio_mark_dirty(folio);
@@ -2017,7 +2019,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			pte_t swp_pte;
 
 			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
-				set_pte_at(mm, address, pvmw.pte, pteval);
+				if (folio_test_hugetlb(folio))
+					set_huge_pte_at(mm, address, pvmw.pte, pteval);
+				else
+					set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
 				break;
@@ -2026,7 +2031,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				       !anon_exclusive, subpage);
 			if (anon_exclusive &&
 			    page_try_share_anon_rmap(subpage)) {
-				set_pte_at(mm, address, pvmw.pte, pteval);
+				if (folio_test_hugetlb(folio))
+					set_huge_pte_at(mm, address, pvmw.pte, pteval);
+				else
+					set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
 				break;
@@ -2052,7 +2060,11 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
 			if (pte_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
-			set_pte_at(mm, address, pvmw.pte, swp_pte);
+			if (folio_test_hugetlb(folio))
+				set_huge_swap_pte_at(mm, address, pvmw.pte,
+						     swp_pte, vma_mmu_pagesize(vma));
+			else
+				set_pte_at(mm, address, pvmw.pte, swp_pte);
 			trace_set_migration_pte(address, pte_val(swp_pte),
 						compound_order(&folio->page));
 			/*
-- 
cgit v1.2.3


From 78f39084b41d287aedb2ea55f2c1895cfa11d61a Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Fri, 13 May 2022 16:48:56 -0700
Subject: mm: hugetlb_vmemmap: add hugetlb_optimize_vmemmap sysctl

We must add hugetlb_free_vmemmap=on (or "off") to the boot cmdline and
reboot the server to enable or disable the feature of optimizing vmemmap
pages associated with HugeTLB pages.  However, rebooting usually takes a
long time.  So add a sysctl to enable or disable the feature at runtime
without rebooting.  Why we need this?  There are 3 use cases.

1) The feature of minimizing overhead of struct page associated with
   each HugeTLB is disabled by default without passing
   "hugetlb_free_vmemmap=on" to the boot cmdline.  When we (ByteDance)
   deliver the servers to the users who want to enable this feature, they
   have to configure the grub (change boot cmdline) and reboot the
   servers, whereas rebooting usually takes a long time (we have thousands
   of servers).  It's a very bad experience for the users.  So we need a
   approach to enable this feature after rebooting.  This is a use case in
   our practical environment.

2) Some use cases are that HugeTLB pages are allocated 'on the fly'
   instead of being pulled from the HugeTLB pool, those workloads would be
   affected with this feature enabled.  Those workloads could be
   identified by the characteristics of they never explicitly allocating
   huge pages with 'nr_hugepages' but only set 'nr_overcommit_hugepages'
   and then let the pages be allocated from the buddy allocator at fault
   time.  We can confirm it is a real use case from the commit
   099730d67417.  For those workloads, the page fault time could be ~2x
   slower than before.  We suspect those users want to disable this
   feature if the system has enabled this before and they don't think the
   memory savings benefit is enough to make up for the performance drop.

3) If the workload which wants vmemmap pages to be optimized and the
   workload which wants to set 'nr_overcommit_hugepages' and does not want
   the extera overhead at fault time when the overcommitted pages be
   allocated from the buddy allocator are deployed in the same server.
   The user could enable this feature and set 'nr_hugepages' and
   'nr_overcommit_hugepages', then disable the feature.  In this case, the
   overcommited HugeTLB pages will not encounter the extra overhead at
   fault time.

Link: https://lkml.kernel.org/r/20220512041142.39501-5-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/sysctl/vm.rst | 39 ++++++++++++++
 include/linux/memory_hotplug.h          |  9 ++++
 mm/hugetlb_vmemmap.c                    | 93 +++++++++++++++++++++++++++++----
 mm/memory_hotplug.c                     |  7 +--
 4 files changed, 133 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index 747e325ebcd0..5c9aa171a0d3 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -562,6 +562,45 @@ Change the minimum size of the hugepage pool.
 See Documentation/admin-guide/mm/hugetlbpage.rst
 
 
+hugetlb_optimize_vmemmap
+========================
+
+This knob is not available when memory_hotplug.memmap_on_memory (kernel parameter)
+is configured or the size of 'struct page' (a structure defined in
+include/linux/mm_types.h) is not power of two (an unusual system config could
+result in this).
+
+Enable (set to 1) or disable (set to 0) the feature of optimizing vmemmap pages
+associated with each HugeTLB page.
+
+Once enabled, the vmemmap pages of subsequent allocation of HugeTLB pages from
+buddy allocator will be optimized (7 pages per 2MB HugeTLB page and 4095 pages
+per 1GB HugeTLB page), whereas already allocated HugeTLB pages will not be
+optimized.  When those optimized HugeTLB pages are freed from the HugeTLB pool
+to the buddy allocator, the vmemmap pages representing that range needs to be
+remapped again and the vmemmap pages discarded earlier need to be rellocated
+again.  If your use case is that HugeTLB pages are allocated 'on the fly' (e.g.
+never explicitly allocating HugeTLB pages with 'nr_hugepages' but only set
+'nr_overcommit_hugepages', those overcommitted HugeTLB pages are allocated 'on
+the fly') instead of being pulled from the HugeTLB pool, you should weigh the
+benefits of memory savings against the more overhead (~2x slower than before)
+of allocation or freeing HugeTLB pages between the HugeTLB pool and the buddy
+allocator.  Another behavior to note is that if the system is under heavy memory
+pressure, it could prevent the user from freeing HugeTLB pages from the HugeTLB
+pool to the buddy allocator since the allocation of vmemmap pages could be
+failed, you have to retry later if your system encounter this situation.
+
+Once disabled, the vmemmap pages of subsequent allocation of HugeTLB pages from
+buddy allocator will not be optimized meaning the extra overhead at allocation
+time from buddy allocator disappears, whereas already optimized HugeTLB pages
+will not be affected.  If you want to make sure there are no optimized HugeTLB
+pages, you can set "nr_hugepages" to 0 first and then disable this.  Note that
+writing 0 to nr_hugepages will make any "in use" HugeTLB pages become surplus
+pages.  So, those surplus pages are still optimized until they are no longer
+in use.  You would need to wait for those surplus pages to be released before
+there are no optimized pages in the system.
+
+
 nr_hugepages_mempolicy
 ======================
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index e0b2209ab71c..20d7edf62a6a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -351,4 +351,13 @@ void arch_remove_linear_mapping(u64 start, u64 size);
 extern bool mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+bool mhp_memmap_on_memory(void);
+#else
+static inline bool mhp_memmap_on_memory(void)
+{
+	return false;
+}
+#endif
+
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index cc4ec752ec16..fcd9f7872064 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -10,6 +10,7 @@
  */
 #define pr_fmt(fmt)	"HugeTLB: " fmt
 
+#include <linux/memory_hotplug.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -22,21 +23,40 @@
 #define RESERVE_VMEMMAP_NR		1U
 #define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
 
+enum vmemmap_optimize_mode {
+	VMEMMAP_OPTIMIZE_OFF,
+	VMEMMAP_OPTIMIZE_ON,
+};
+
 DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON,
 			hugetlb_optimize_vmemmap_key);
 EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key);
 
+static enum vmemmap_optimize_mode vmemmap_optimize_mode =
+	IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON);
+
+static void vmemmap_optimize_mode_switch(enum vmemmap_optimize_mode to)
+{
+	if (vmemmap_optimize_mode == to)
+		return;
+
+	if (to == VMEMMAP_OPTIMIZE_OFF)
+		static_branch_dec(&hugetlb_optimize_vmemmap_key);
+	else
+		static_branch_inc(&hugetlb_optimize_vmemmap_key);
+	WRITE_ONCE(vmemmap_optimize_mode, to);
+}
+
 static int __init hugetlb_vmemmap_early_param(char *buf)
 {
 	bool enable;
+	enum vmemmap_optimize_mode mode;
 
 	if (kstrtobool(buf, &enable))
 		return -EINVAL;
 
-	if (enable)
-		static_branch_enable(&hugetlb_optimize_vmemmap_key);
-	else
-		static_branch_disable(&hugetlb_optimize_vmemmap_key);
+	mode = enable ? VMEMMAP_OPTIMIZE_ON : VMEMMAP_OPTIMIZE_OFF;
+	vmemmap_optimize_mode_switch(mode);
 
 	return 0;
 }
@@ -69,8 +89,10 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
 	 */
 	ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse,
 				  GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE);
-	if (!ret)
+	if (!ret) {
 		ClearHPageVmemmapOptimized(head);
+		static_branch_dec(&hugetlb_optimize_vmemmap_key);
+	}
 
 	return ret;
 }
@@ -84,6 +106,11 @@ void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
 	if (!vmemmap_pages)
 		return;
 
+	if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF)
+		return;
+
+	static_branch_inc(&hugetlb_optimize_vmemmap_key);
+
 	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
 	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
 	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;
@@ -93,7 +120,9 @@ void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
 	 * to the page which @vmemmap_reuse is mapped to, then free the pages
 	 * which the range [@vmemmap_addr, @vmemmap_end] is mapped to.
 	 */
-	if (!vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse))
+	if (vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse))
+		static_branch_dec(&hugetlb_optimize_vmemmap_key);
+	else
 		SetHPageVmemmapOptimized(head);
 }
 
@@ -110,9 +139,6 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	BUILD_BUG_ON(__NR_USED_SUBPAGE >=
 		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));
 
-	if (!hugetlb_optimize_vmemmap_enabled())
-		return;
-
 	if (!is_power_of_2(sizeof(struct page))) {
 		pr_warn_once("cannot optimize vmemmap pages because \"struct page\" crosses page boundaries\n");
 		static_branch_disable(&hugetlb_optimize_vmemmap_key);
@@ -134,3 +160,52 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	pr_info("can optimize %d vmemmap pages for %s\n",
 		h->optimize_vmemmap_pages, h->name);
 }
+
+#ifdef CONFIG_PROC_SYSCTL
+static int hugetlb_optimize_vmemmap_handler(struct ctl_table *table, int write,
+					    void *buffer, size_t *length,
+					    loff_t *ppos)
+{
+	int ret;
+	enum vmemmap_optimize_mode mode;
+	static DEFINE_MUTEX(sysctl_mutex);
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	mutex_lock(&sysctl_mutex);
+	mode = vmemmap_optimize_mode;
+	table->data = &mode;
+	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
+	if (write && !ret)
+		vmemmap_optimize_mode_switch(mode);
+	mutex_unlock(&sysctl_mutex);
+
+	return ret;
+}
+
+static struct ctl_table hugetlb_vmemmap_sysctls[] = {
+	{
+		.procname	= "hugetlb_optimize_vmemmap",
+		.maxlen		= sizeof(enum vmemmap_optimize_mode),
+		.mode		= 0644,
+		.proc_handler	= hugetlb_optimize_vmemmap_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{ }
+};
+
+static __init int hugetlb_vmemmap_sysctls_init(void)
+{
+	/*
+	 * If "memory_hotplug.memmap_on_memory" is enabled or "struct page"
+	 * crosses page boundaries, the vmemmap pages cannot be optimized.
+	 */
+	if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page)))
+		register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
+
+	return 0;
+}
+late_initcall(hugetlb_vmemmap_sysctls_init);
+#endif /* CONFIG_PROC_SYSCTL */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6951bf0bc2e6..1213d0c67a53 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -63,15 +63,10 @@ static bool memmap_on_memory __ro_after_init;
 module_param_cb(memmap_on_memory, &memmap_on_memory_ops, &memmap_on_memory, 0444);
 MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
 
-static inline bool mhp_memmap_on_memory(void)
+bool mhp_memmap_on_memory(void)
 {
 	return memmap_on_memory;
 }
-#else
-static inline bool mhp_memmap_on_memory(void)
-{
-	return false;
-}
 #endif
 
 enum {
-- 
cgit v1.2.3


From d4a157f5a26fbf1f1fd5da47a4772a738306348f Mon Sep 17 00:00:00 2001
From: Gautam Menghani <gautammenghani201@gmail.com>
Date: Fri, 13 May 2022 16:48:57 -0700
Subject: mm/damon: add documentation for Enum value

Fix the warning - "Enum value 'NR_DAMON_OPS' not described in enum
'damon_ops_id'" generated by the command "make pdfdocs"

Link: https://lkml.kernel.org/r/20220508073316.141401-1-gautammenghani201@gmail.com
Signed-off-by: Gautam Menghani <gautammenghani201@gmail.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index d1e6ee28a2ff..7c62da31ce4b 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -264,6 +264,7 @@ struct damos {
  * @DAMON_OPS_FVADDR:	Monitoring operations for only fixed ranges of virtual
  *			address spaces
  * @DAMON_OPS_PADDR:	Monitoring operations for the physical address space
+ * @NR_DAMON_OPS:	Number of monitoring operations implementations
  */
 enum damon_ops_id {
 	DAMON_OPS_VADDR,
-- 
cgit v1.2.3


From 81132a39c152ca09832b9e4cb748129cee5f55ec Mon Sep 17 00:00:00 2001
From: Gou Hao <gouhao@uniontech.com>
Date: Tue, 2 Nov 2021 10:46:48 +0800
Subject: fs: remove fget_many and fput_many interface

These two interface were added in 091141a42 commit,
but now there is no place to call them.

The only user of fput/fget_many() was removed in commit
62906e89e63b ("io_uring: remove file batch-get optimisation").

A user of get_file_rcu_many() were removed in commit
f073531070d2 ("init: add an init_dup helper").

And replace atomic_long_sub/add to atomic_long_dec/inc
can improve performance.

Here are the test results of unixbench:

Cmd: ./Run -c 64 context1

Without patch:
System Benchmarks Partial Index              BASELINE       RESULT    INDEX
Pipe-based Context Switching                   4000.0    2798407.0   6996.0
                                                                   ========
System Benchmarks Index Score (Partial Only)                         6996.0

With patch:
System Benchmarks Partial Index              BASELINE       RESULT    INDEX
Pipe-based Context Switching                   4000.0    3486268.8   8715.7
                                                                   ========
System Benchmarks Index Score (Partial Only)                         8715.7

Signed-off-by: Gou Hao <gouhao@uniontech.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file.c            | 33 +++++++++++++--------------------
 fs/file_table.c      |  9 ++-------
 include/linux/file.h |  2 --
 include/linux/fs.h   |  4 +---
 4 files changed, 16 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index ee9317346702..4c59f410a48d 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -871,7 +871,7 @@ void do_close_on_exec(struct files_struct *files)
 }
 
 static inline struct file *__fget_files_rcu(struct files_struct *files,
-	unsigned int fd, fmode_t mask, unsigned int refs)
+	unsigned int fd, fmode_t mask)
 {
 	for (;;) {
 		struct file *file;
@@ -897,10 +897,9 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		 * Such a race can take two forms:
 		 *
 		 *  (a) the file ref already went down to zero,
-		 *      and get_file_rcu_many() fails. Just try
-		 *      again:
+		 *      and get_file_rcu() fails. Just try again:
 		 */
-		if (unlikely(!get_file_rcu_many(file, refs)))
+		if (unlikely(!get_file_rcu(file)))
 			continue;
 
 		/*
@@ -909,11 +908,11 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		 *       pointer having changed, because it always goes
 		 *       hand-in-hand with 'fdt'.
 		 *
-		 * If so, we need to put our refs and try again.
+		 * If so, we need to put our ref and try again.
 		 */
 		if (unlikely(rcu_dereference_raw(files->fdt) != fdt) ||
 		    unlikely(rcu_dereference_raw(*fdentry) != file)) {
-			fput_many(file, refs);
+			fput(file);
 			continue;
 		}
 
@@ -926,37 +925,31 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 }
 
 static struct file *__fget_files(struct files_struct *files, unsigned int fd,
-				 fmode_t mask, unsigned int refs)
+				 fmode_t mask)
 {
 	struct file *file;
 
 	rcu_read_lock();
-	file = __fget_files_rcu(files, fd, mask, refs);
+	file = __fget_files_rcu(files, fd, mask);
 	rcu_read_unlock();
 
 	return file;
 }
 
-static inline struct file *__fget(unsigned int fd, fmode_t mask,
-				  unsigned int refs)
-{
-	return __fget_files(current->files, fd, mask, refs);
-}
-
-struct file *fget_many(unsigned int fd, unsigned int refs)
+static inline struct file *__fget(unsigned int fd, fmode_t mask)
 {
-	return __fget(fd, FMODE_PATH, refs);
+	return __fget_files(current->files, fd, mask);
 }
 
 struct file *fget(unsigned int fd)
 {
-	return __fget(fd, FMODE_PATH, 1);
+	return __fget(fd, FMODE_PATH);
 }
 EXPORT_SYMBOL(fget);
 
 struct file *fget_raw(unsigned int fd)
 {
-	return __fget(fd, 0, 1);
+	return __fget(fd, 0);
 }
 EXPORT_SYMBOL(fget_raw);
 
@@ -966,7 +959,7 @@ struct file *fget_task(struct task_struct *task, unsigned int fd)
 
 	task_lock(task);
 	if (task->files)
-		file = __fget_files(task->files, fd, 0, 1);
+		file = __fget_files(task->files, fd, 0);
 	task_unlock(task);
 
 	return file;
@@ -1035,7 +1028,7 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 			return 0;
 		return (unsigned long)file;
 	} else {
-		file = __fget(fd, mask, 1);
+		file = __fget(fd, mask);
 		if (!file)
 			return 0;
 		return FDPUT_FPUT | (unsigned long)file;
diff --git a/fs/file_table.c b/fs/file_table.c
index 7d2e692b66a9..1ffd74bbbed6 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -368,9 +368,9 @@ EXPORT_SYMBOL_GPL(flush_delayed_fput);
 
 static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
 
-void fput_many(struct file *file, unsigned int refs)
+void fput(struct file *file)
 {
-	if (atomic_long_sub_and_test(refs, &file->f_count)) {
+	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
 
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
@@ -389,11 +389,6 @@ void fput_many(struct file *file, unsigned int refs)
 	}
 }
 
-void fput(struct file *file)
-{
-	fput_many(file, 1);
-}
-
 /*
  * synchronous analog of fput(); for kernel threads that might be needed
  * in some umount() (and thus can't use flush_delayed_fput() without
diff --git a/include/linux/file.h b/include/linux/file.h
index 51e830b4fe3a..39704eae83e2 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -14,7 +14,6 @@
 struct file;
 
 extern void fput(struct file *);
-extern void fput_many(struct file *, unsigned int);
 
 struct file_operations;
 struct task_struct;
@@ -47,7 +46,6 @@ static inline void fdput(struct fd fd)
 }
 
 extern struct file *fget(unsigned int fd);
-extern struct file *fget_many(unsigned int fd, unsigned int refs);
 extern struct file *fget_raw(unsigned int fd);
 extern struct file *fget_task(struct task_struct *task, unsigned int fd);
 extern unsigned long __fdget(unsigned int fd);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde95387a23..3660c338bb16 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -981,9 +981,7 @@ static inline struct file *get_file(struct file *f)
 	atomic_long_inc(&f->f_count);
 	return f;
 }
-#define get_file_rcu_many(x, cnt)	\
-	atomic_long_add_unless(&(x)->f_count, (cnt), 0)
-#define get_file_rcu(x) get_file_rcu_many((x), 1)
+#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
 #define file_count(x)	atomic_long_read(&(x)->f_count)
 
 #define	MAX_NON_LFS	((1UL<<31) - 1)
-- 
cgit v1.2.3


From 6319194ec57b0452dcda4589d24c4e7db299c5bf Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 12 May 2022 17:08:03 -0400
Subject: Unify the primitives for file descriptor closing

Currently we have 3 primitives for removing an opened file from descriptor
table - pick_file(), __close_fd_get_file() and close_fd_get_file().  Their
calling conventions are rather odd and there's a code duplication for no
good reason.  They can be unified -

1) have __range_close() cap max_fd in the very beginning; that way
we don't need separate way for pick_file() to report being past the end
of descriptor table.

2) make {__,}close_fd_get_file() return file (or NULL) directly, rather
than returning it via struct file ** argument.  Don't bother with
(bogus) return value - nobody wants that -ENOENT.

3) make pick_file() return NULL on unopened descriptor - the only caller
that used to care about the distinction between descriptor past the end
of descriptor table and finding NULL in descriptor table doesn't give
a damn after (1).

4) lift ->files_lock out of pick_file()

That actually simplifies the callers, as well as the primitives themselves.
Code duplication is also gone...

Reviewed-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/android/binder.c |  2 +-
 fs/file.c                | 77 ++++++++++++++++++------------------------------
 fs/internal.h            |  2 +-
 fs/io_uring.c            |  7 ++---
 include/linux/fdtable.h  |  2 +-
 5 files changed, 34 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 8351c5638880..27c9b004823a 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1855,7 +1855,7 @@ static void binder_deferred_fd_close(int fd)
 	if (!twcb)
 		return;
 	init_task_work(&twcb->twork, binder_do_fd_close);
-	close_fd_get_file(fd, &twcb->file);
+	twcb->file = close_fd_get_file(fd);
 	if (twcb->file) {
 		filp_close(twcb->file, current->files);
 		task_work_add(current, &twcb->twork, TWA_RESUME);
diff --git a/fs/file.c b/fs/file.c
index 4c59f410a48d..dd6692048f4f 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -630,32 +630,23 @@ EXPORT_SYMBOL(fd_install);
  * @files: file struct to retrieve file from
  * @fd: file descriptor to retrieve file for
  *
- * If this functions returns an EINVAL error pointer the fd was beyond the
- * current maximum number of file descriptors for that fdtable.
+ * Context: files_lock must be held.
  *
- * Returns: The file associated with @fd, on error returns an error pointer.
+ * Returns: The file associated with @fd (NULL if @fd is not open)
  */
 static struct file *pick_file(struct files_struct *files, unsigned fd)
 {
+	struct fdtable *fdt = files_fdtable(files);
 	struct file *file;
-	struct fdtable *fdt;
 
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	if (fd >= fdt->max_fds) {
-		file = ERR_PTR(-EINVAL);
-		goto out_unlock;
-	}
+	if (fd >= fdt->max_fds)
+		return NULL;
+
 	file = fdt->fd[fd];
-	if (!file) {
-		file = ERR_PTR(-EBADF);
-		goto out_unlock;
+	if (file) {
+		rcu_assign_pointer(fdt->fd[fd], NULL);
+		__put_unused_fd(files, fd);
 	}
-	rcu_assign_pointer(fdt->fd[fd], NULL);
-	__put_unused_fd(files, fd);
-
-out_unlock:
-	spin_unlock(&files->file_lock);
 	return file;
 }
 
@@ -664,8 +655,10 @@ int close_fd(unsigned fd)
 	struct files_struct *files = current->files;
 	struct file *file;
 
+	spin_lock(&files->file_lock);
 	file = pick_file(files, fd);
-	if (IS_ERR(file))
+	spin_unlock(&files->file_lock);
+	if (!file)
 		return -EBADF;
 
 	return filp_close(file, files);
@@ -702,20 +695,25 @@ static inline void __range_cloexec(struct files_struct *cur_fds,
 static inline void __range_close(struct files_struct *cur_fds, unsigned int fd,
 				 unsigned int max_fd)
 {
+	unsigned n;
+
+	rcu_read_lock();
+	n = last_fd(files_fdtable(cur_fds));
+	rcu_read_unlock();
+	max_fd = min(max_fd, n);
+
 	while (fd <= max_fd) {
 		struct file *file;
 
+		spin_lock(&cur_fds->file_lock);
 		file = pick_file(cur_fds, fd++);
-		if (!IS_ERR(file)) {
+		spin_unlock(&cur_fds->file_lock);
+
+		if (file) {
 			/* found a valid file to close */
 			filp_close(file, cur_fds);
 			cond_resched();
-			continue;
 		}
-
-		/* beyond the last fd in that table */
-		if (PTR_ERR(file) == -EINVAL)
-			return;
 	}
 }
 
@@ -795,26 +793,9 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
  * See close_fd_get_file() below, this variant assumes current->files->file_lock
  * is held.
  */
-int __close_fd_get_file(unsigned int fd, struct file **res)
+struct file *__close_fd_get_file(unsigned int fd)
 {
-	struct files_struct *files = current->files;
-	struct file *file;
-	struct fdtable *fdt;
-
-	fdt = files_fdtable(files);
-	if (fd >= fdt->max_fds)
-		goto out_err;
-	file = fdt->fd[fd];
-	if (!file)
-		goto out_err;
-	rcu_assign_pointer(fdt->fd[fd], NULL);
-	__put_unused_fd(files, fd);
-	get_file(file);
-	*res = file;
-	return 0;
-out_err:
-	*res = NULL;
-	return -ENOENT;
+	return pick_file(current->files, fd);
 }
 
 /*
@@ -822,16 +803,16 @@ out_err:
  * The caller must ensure that filp_close() called on the file, and then
  * an fput().
  */
-int close_fd_get_file(unsigned int fd, struct file **res)
+struct file *close_fd_get_file(unsigned int fd)
 {
 	struct files_struct *files = current->files;
-	int ret;
+	struct file *file;
 
 	spin_lock(&files->file_lock);
-	ret = __close_fd_get_file(fd, res);
+	file = pick_file(files, fd);
 	spin_unlock(&files->file_lock);
 
-	return ret;
+	return file;
 }
 
 void do_close_on_exec(struct files_struct *files)
diff --git a/fs/internal.h b/fs/internal.h
index 08503dc68d2b..4065e2679103 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -125,7 +125,7 @@ extern struct file *do_file_open_root(const struct path *,
 		const char *, const struct open_flags *);
 extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
-extern int __close_fd_get_file(unsigned int fd, struct file **res);
+extern struct file *__close_fd_get_file(unsigned int fd);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int chmod_common(const struct path *path, umode_t mode);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index dc580a30723d..7257b0870353 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5137,13 +5137,10 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags)
 		return -EAGAIN;
 	}
 
-	ret = __close_fd_get_file(close->fd, &file);
+	file = __close_fd_get_file(close->fd);
 	spin_unlock(&files->file_lock);
-	if (ret < 0) {
-		if (ret == -ENOENT)
-			ret = -EBADF;
+	if (!file)
 		goto err;
-	}
 
 	/* No ->flush() or already async, safely close from here */
 	ret = filp_close(file, current->files);
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index d0e78174874a..e066816f3519 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -125,7 +125,7 @@ int iterate_fd(struct files_struct *, unsigned,
 
 extern int close_fd(unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-extern int close_fd_get_file(unsigned int fd, struct file **res);
+extern struct file *close_fd_get_file(unsigned int fd);
 extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 		      struct files_struct **new_fdp);
 
-- 
cgit v1.2.3


From 03fea699b050805ad6ee111f9db04f223f3e835e Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Sun, 15 May 2022 21:58:30 +0100
Subject: cdrom: remove the unused driver specific disc change ioctl

This was only used by the ide-cd driver, which went away in
commit b7fb14d3ac63 ("ide: remove the legacy ide driver")
so we might as well take advantage of that and get rid of
this hook as well.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Phillip Potter <phil@philpotter.co.uk>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Link: https://lore.kernel.org/all/20220427132436.12795-2-paul.gortmaker@windriver.com
Signed-off-by: Phillip Potter <phil@philpotter.co.uk>
Link: https://lore.kernel.org/r/20220515205833.944139-3-phil@philpotter.co.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/cdrom/cdrom-standard.rst | 10 ----------
 drivers/cdrom/cdrom.c                  |  8 --------
 include/linux/cdrom.h                  |  1 -
 3 files changed, 19 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst
index 52ea7b6b2fe8..7964fe134277 100644
--- a/Documentation/cdrom/cdrom-standard.rst
+++ b/Documentation/cdrom/cdrom-standard.rst
@@ -218,7 +218,6 @@ current *struct* is::
 		int (*tray_move)(struct cdrom_device_info *, int);
 		int (*lock_door)(struct cdrom_device_info *, int);
 		int (*select_speed)(struct cdrom_device_info *, int);
-		int (*select_disc)(struct cdrom_device_info *, int);
 		int (*get_last_session) (struct cdrom_device_info *,
 					 struct cdrom_multisession *);
 		int (*get_mcn)(struct cdrom_device_info *, struct cdrom_mcn *);
@@ -419,15 +418,6 @@ this `auto-selection` capability, the decision should be made on the
 current disc loaded and the return value should be positive. A negative
 return value indicates an error.
 
-::
-
-	int select_disc(struct cdrom_device_info *cdi, int number)
-
-If the drive can store multiple discs (a juke-box) this function
-will perform disc selection. It should return the number of the
-selected disc on success, a negative value on error. Currently, only
-the ide-cd driver supports this functionality.
-
 ::
 
 	int get_last_session(struct cdrom_device_info *cdi,
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 7e2174f597f3..e43bb071fe92 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2452,14 +2452,6 @@ static int cdrom_ioctl_select_disc(struct cdrom_device_info *cdi,
 			return -EINVAL;
 	}
 
-	/*
-	 * ->select_disc is a hook to allow a driver-specific way of
-	 * seleting disc.  However, since there is no equivalent hook for
-	 * cdrom_slot_status this may not actually be useful...
-	 */
-	if (cdi->ops->select_disc)
-		return cdi->ops->select_disc(cdi, arg);
-
 	cd_dbg(CD_CHANGER, "Using generic cdrom_select_disc()\n");
 	return cdrom_select_disc(cdi, arg);
 }
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 0a89f111e00e..67caa909e3e6 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -77,7 +77,6 @@ struct cdrom_device_ops {
 	int (*tray_move) (struct cdrom_device_info *, int);
 	int (*lock_door) (struct cdrom_device_info *, int);
 	int (*select_speed) (struct cdrom_device_info *, int);
-	int (*select_disc) (struct cdrom_device_info *, int);
 	int (*get_last_session) (struct cdrom_device_info *,
 				 struct cdrom_multisession *);
 	int (*get_mcn) (struct cdrom_device_info *,
-- 
cgit v1.2.3


From ca2d89925ae3f3d5c65182ff75e58bc9b484e69c Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <mgurtovoy@nvidia.com>
Date: Thu, 28 Apr 2022 12:19:35 +0300
Subject: nvme: add missing status values to verbose logging

Log a few more path related status codes.

Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/constants.c | 3 +++
 include/linux/nvme.h          | 2 ++
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 7d49eb34b348..465aee42fced 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -155,10 +155,13 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_COMPARE_FAILED] = "Compare Failure",
 	[NVME_SC_ACCESS_DENIED] = "Access Denied",
 	[NVME_SC_UNWRITTEN_BLOCK] = "Deallocated or Unwritten Logical Block",
+	[NVME_SC_INTERNAL_PATH_ERROR] = "Internal Pathing Error",
 	[NVME_SC_ANA_PERSISTENT_LOSS] = "Asymmetric Access Persistent Loss",
 	[NVME_SC_ANA_INACCESSIBLE] = "Asymmetric Access Inaccessible",
 	[NVME_SC_ANA_TRANSITION] = "Asymmetric Access Transition",
+	[NVME_SC_CTRL_PATH_ERROR] = "Controller Pathing Error",
 	[NVME_SC_HOST_PATH_ERROR] = "Host Pathing Error",
+	[NVME_SC_HOST_ABORTED_CMD] = "Host Aborted Command",
 };
 
 const unsigned char *nvme_get_error_status_str(u16 status)
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index f626a445d1a8..bbabdc7600da 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1679,9 +1679,11 @@ enum {
 	/*
 	 * Path-related Errors:
 	 */
+	NVME_SC_INTERNAL_PATH_ERROR	= 0x300,
 	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
 	NVME_SC_ANA_INACCESSIBLE	= 0x302,
 	NVME_SC_ANA_TRANSITION		= 0x303,
+	NVME_SC_CTRL_PATH_ERROR		= 0x360,
 	NVME_SC_HOST_PATH_ERROR		= 0x370,
 	NVME_SC_HOST_ABORTED_CMD	= 0x371,
 
-- 
cgit v1.2.3


From 7c4e983c4f3cf94fcd879730c6caa877e0768a4d Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Fri, 13 May 2022 11:33:57 -0700
Subject: net: allow gso_max_size to exceed 65536

The code for gso_max_size was added originally to allow for debugging and
workaround of buggy devices that couldn't support TSO with blocks 64K in
size. The original reason for limiting it to 64K was because that was the
existing limits of IPv4 and non-jumbogram IPv6 length fields.

With the addition of Big TCP we can remove this limit and allow the value
to potentially go up to UINT_MAX and instead be limited by the tso_max_size
value.

So in order to support this we need to go through and clean up the
remaining users of the gso_max_size value so that the values will cap at
64K for non-TCPv6 flows. In addition we can clean up the GSO_MAX_SIZE value
so that 64K becomes GSO_LEGACY_MAX_SIZE and UINT_MAX will now be the upper
limit for GSO_MAX_SIZE.

v6: (edumazet) fixed a compile error if CONFIG_IPV6=n,
               in a new sk_trim_gso_size() helper.
               netif_set_tso_max_size() caps the requested TSO size
               with GSO_MAX_SIZE.

Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe.h            |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c |  2 +-
 drivers/net/ethernet/sfc/ef100_nic.c            |  3 ++-
 drivers/net/ethernet/sfc/falcon/tx.c            |  3 ++-
 drivers/net/ethernet/sfc/tx_common.c            |  3 ++-
 drivers/net/ethernet/synopsys/dwc-xlgmac.h      |  3 ++-
 drivers/net/hyperv/rndis_filter.c               |  2 +-
 drivers/scsi/fcoe/fcoe.c                        |  2 +-
 include/linux/netdevice.h                       |  4 +++-
 net/bpf/test_run.c                              |  2 +-
 net/core/dev.c                                  |  7 ++++---
 net/core/rtnetlink.c                            |  2 +-
 net/core/sock.c                                 | 14 ++++++++++++++
 net/ipv4/tcp_bbr.c                              |  2 +-
 net/ipv4/tcp_output.c                           |  2 +-
 net/sctp/output.c                               |  3 ++-
 16 files changed, 40 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index 607a2c90513b..d9547552ceef 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -151,7 +151,8 @@
 #define XGBE_TX_MAX_BUF_SIZE	(0x3fff & ~(64 - 1))
 
 /* Descriptors required for maximum contiguous TSO/GSO packet */
-#define XGBE_TX_MAX_SPLIT	((GSO_MAX_SIZE / XGBE_TX_MAX_BUF_SIZE) + 1)
+#define XGBE_TX_MAX_SPLIT	\
+	((GSO_LEGACY_MAX_SIZE / XGBE_TX_MAX_BUF_SIZE) + 1)
 
 /* Maximum possible descriptors needed for an SKB:
  * - Maximum number of SKB frags
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index fb11081001a0..838870bc6dbd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2038,7 +2038,7 @@ mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt)
 {
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 
-	return PAGE_SIZE * nr_frags + data_bcnt <= GSO_MAX_SIZE;
+	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_MAX_SIZE;
 }
 
 static void
diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c
index a69d756e09b9..b2536d2c218a 100644
--- a/drivers/net/ethernet/sfc/ef100_nic.c
+++ b/drivers/net/ethernet/sfc/ef100_nic.c
@@ -1008,7 +1008,8 @@ static int ef100_process_design_param(struct efx_nic *efx,
 		}
 		return 0;
 	case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN:
-		nic_data->tso_max_payload_len = min_t(u64, reader->value, GSO_MAX_SIZE);
+		nic_data->tso_max_payload_len = min_t(u64, reader->value,
+						      GSO_LEGACY_MAX_SIZE);
 		netif_set_tso_max_size(efx->net_dev,
 				       nic_data->tso_max_payload_len);
 		return 0;
diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c
index f7306e93a8b8..b9369483758c 100644
--- a/drivers/net/ethernet/sfc/falcon/tx.c
+++ b/drivers/net/ethernet/sfc/falcon/tx.c
@@ -98,7 +98,8 @@ unsigned int ef4_tx_max_skb_descs(struct ef4_nic *efx)
 	/* Possibly more for PCIe page boundaries within input fragments */
 	if (PAGE_SIZE > EF4_PAGE_SIZE)
 		max_descs += max_t(unsigned int, MAX_SKB_FRAGS,
-				   DIV_ROUND_UP(GSO_MAX_SIZE, EF4_PAGE_SIZE));
+				   DIV_ROUND_UP(GSO_LEGACY_MAX_SIZE,
+						EF4_PAGE_SIZE));
 
 	return max_descs;
 }
diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c
index 9bc8281b7f5b..658ea2d34070 100644
--- a/drivers/net/ethernet/sfc/tx_common.c
+++ b/drivers/net/ethernet/sfc/tx_common.c
@@ -416,7 +416,8 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
 	/* Possibly more for PCIe page boundaries within input fragments */
 	if (PAGE_SIZE > EFX_PAGE_SIZE)
 		max_descs += max_t(unsigned int, MAX_SKB_FRAGS,
-				   DIV_ROUND_UP(GSO_MAX_SIZE, EFX_PAGE_SIZE));
+				   DIV_ROUND_UP(GSO_LEGACY_MAX_SIZE,
+						EFX_PAGE_SIZE));
 
 	return max_descs;
 }
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h
index 98e3a271e017..a848e10f3ea4 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac.h
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h
@@ -38,7 +38,8 @@
 #define XLGMAC_RX_DESC_MAX_DIRTY	(XLGMAC_RX_DESC_CNT >> 3)
 
 /* Descriptors required for maximum contiguous TSO/GSO packet */
-#define XLGMAC_TX_MAX_SPLIT	((GSO_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1)
+#define XLGMAC_TX_MAX_SPLIT	\
+	((GSO_LEGACY_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1)
 
 /* Maximum possible descriptors needed for a SKB */
 #define XLGMAC_TX_MAX_DESC_NR	(MAX_SKB_FRAGS + XLGMAC_TX_MAX_SPLIT + 2)
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 866af2cc27a3..6da36cb8af80 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1349,7 +1349,7 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
 	struct net_device_context *net_device_ctx = netdev_priv(net);
 	struct ndis_offload hwcaps;
 	struct ndis_offload_params offloads;
-	unsigned int gso_max_size = GSO_MAX_SIZE;
+	unsigned int gso_max_size = GSO_LEGACY_MAX_SIZE;
 	int ret;
 
 	/* Find HW offload capabilities */
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 44ca6110213c..79b2827e4081 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -667,7 +667,7 @@ static void fcoe_netdev_features_change(struct fc_lport *lport,
 
 	if (netdev->features & NETIF_F_FSO) {
 		lport->seq_offload = 1;
-		lport->lso_max = netdev->gso_max_size;
+		lport->lso_max = min(netdev->gso_max_size, GSO_LEGACY_MAX_SIZE);
 		FCOE_NETDEV_DBG(netdev, "Supports LSO for max len 0x%x\n",
 				lport->lso_max);
 	} else {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 536321691c72..ce780e352f43 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2272,7 +2272,9 @@ struct net_device {
 	const struct rtnl_link_ops *rtnl_link_ops;
 
 	/* for setting kernel sock attribute on TCP connection setup */
-#define GSO_MAX_SIZE		65536
+#define GSO_LEGACY_MAX_SIZE	65536u
+#define GSO_MAX_SIZE		UINT_MAX
+
 	unsigned int		gso_max_size;
 #define TSO_LEGACY_MAX_SIZE	65536
 #define TSO_MAX_SIZE		UINT_MAX
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 8d54fef9a568..9b5a1f630bb0 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -1001,7 +1001,7 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
 		cb->pkt_len = skb->len;
 	} else {
 		if (__skb->wire_len < skb->len ||
-		    __skb->wire_len > GSO_MAX_SIZE)
+		    __skb->wire_len > GSO_LEGACY_MAX_SIZE)
 			return -EINVAL;
 		cb->pkt_len = __skb->wire_len;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index a601da3b4a7c..830beb05161a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2998,11 +2998,12 @@ EXPORT_SYMBOL(netif_set_real_num_queues);
  * @size:	max skb->len of a TSO frame
  *
  * Set the limit on the size of TSO super-frames the device can handle.
- * Unless explicitly set the stack will assume the value of %GSO_MAX_SIZE.
+ * Unless explicitly set the stack will assume the value of
+ * %GSO_LEGACY_MAX_SIZE.
  */
 void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
 {
-	dev->tso_max_size = size;
+	dev->tso_max_size = min(GSO_MAX_SIZE, size);
 	if (size < READ_ONCE(dev->gso_max_size))
 		netif_set_gso_max_size(dev, size);
 }
@@ -10595,7 +10596,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev_net_set(dev, &init_net);
 
-	dev->gso_max_size = GSO_MAX_SIZE;
+	dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
 	dev->gro_max_size = GRO_MAX_SIZE;
 	dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f35cc21298ac..f2b0f747d3d2 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2817,7 +2817,7 @@ static int do_setlink(const struct sk_buff *skb,
 	if (tb[IFLA_GSO_MAX_SIZE]) {
 		u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);
 
-		if (max_size > GSO_MAX_SIZE || max_size > dev->tso_max_size) {
+		if (max_size > dev->tso_max_size) {
 			err = -EINVAL;
 			goto errout;
 		}
diff --git a/net/core/sock.c b/net/core/sock.c
index 6b287eb5427b..24a46a1e4f28 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2293,6 +2293,19 @@ void sk_free_unlock_clone(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
 
+static void sk_trim_gso_size(struct sock *sk)
+{
+	if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE)
+		return;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6 &&
+	    sk_is_tcp(sk) &&
+	    !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+		return;
+#endif
+	sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;
+}
+
 void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
 	u32 max_segs = 1;
@@ -2312,6 +2325,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
 			/* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */
 			sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size);
+			sk_trim_gso_size(sk);
 			sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1);
 			/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
 			max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index c7d30a3bbd81..075e744bfb48 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -310,7 +310,7 @@ static u32 bbr_tso_segs_goal(struct sock *sk)
 	 */
 	bytes = min_t(unsigned long,
 		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
-		      GSO_MAX_SIZE - 1 - MAX_TCP_HEADER);
+		      GSO_LEGACY_MAX_SIZE - 1 - MAX_TCP_HEADER);
 	segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk));
 
 	return min(segs, 0x7FU);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b092228e4342..b4b2284ed4a2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1553,7 +1553,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	 * SO_SNDBUF values.
 	 * Also allow first and last skb in retransmit queue to be split.
 	 */
-	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
+	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_LEGACY_MAX_SIZE);
 	if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
 		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
 		     skb != tcp_rtx_queue_head(sk) &&
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 72fe6669c50d..a63df055ac57 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -134,7 +134,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 		dst_hold(tp->dst);
 		sk_setup_caps(sk, tp->dst);
 	}
-	packet->max_size = sk_can_gso(sk) ? READ_ONCE(tp->dst->dev->gso_max_size)
+	packet->max_size = sk_can_gso(sk) ? min(READ_ONCE(tp->dst->dev->gso_max_size),
+						GSO_LEGACY_MAX_SIZE)
 					  : asoc->pathmtu;
 	rcu_read_unlock();
 }
-- 
cgit v1.2.3


From 34b92e8d19da1e44070dc0ecc2747871469ac534 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 13 May 2022 11:33:58 -0700
Subject: net: limit GSO_MAX_SIZE to 524280 bytes

Make sure we will not overflow shinfo->gso_segs

Minimal TCP MSS size is 8 bytes, and shinfo->gso_segs
is a 16bit field.

TCP_MIN_GSO_SIZE is currently defined in include/net/tcp.h,
it seems cleaner to not bring tcp details into include/linux/netdevice.h

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ce780e352f43..fd38847d0dc7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2272,14 +2272,17 @@ struct net_device {
 	const struct rtnl_link_ops *rtnl_link_ops;
 
 	/* for setting kernel sock attribute on TCP connection setup */
+#define GSO_MAX_SEGS		65535u
 #define GSO_LEGACY_MAX_SIZE	65536u
-#define GSO_MAX_SIZE		UINT_MAX
+/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
+ * and shinfo->gso_segs is a 16bit field.
+ */
+#define GSO_MAX_SIZE		(8 * GSO_MAX_SEGS)
 
 	unsigned int		gso_max_size;
 #define TSO_LEGACY_MAX_SIZE	65536
 #define TSO_MAX_SIZE		UINT_MAX
 	unsigned int		tso_max_size;
-#define GSO_MAX_SEGS		65535
 	u16			gso_max_segs;
 #define TSO_MAX_SEGS		U16_MAX
 	u16			tso_max_segs;
-- 
cgit v1.2.3


From 0fe79f28bfaf73b66b7b1562d2468f94aa03bd12 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Fri, 13 May 2022 11:34:03 -0700
Subject: net: allow gro_max_size to exceed 65536

Allow the gro_max_size to exceed a value larger than 65536.

There weren't really any external limitations that prevented this other
than the fact that IPv4 only supports a 16 bit length field. Since we have
the option of adding a hop-by-hop header for IPv6 we can allow IPv6 to
exceed this value and for IPv4 and non-TCP flows we can cap things at 65536
via a constant rather than relying on gro_max_size.

[edumazet] limit GRO_MAX_SIZE to (8 * 65535) to avoid overflows.

Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +-
 include/linux/netdevice.h                       | 6 +++++-
 include/net/ipv6.h                              | 2 +-
 net/core/dev.c                                  | 2 +-
 net/core/gro.c                                  | 8 ++++++++
 net/core/rtnetlink.c                            | 8 --------
 6 files changed, 16 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 838870bc6dbd..24de37b79f5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2038,7 +2038,7 @@ mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt)
 {
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 
-	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_MAX_SIZE;
+	return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
 }
 
 static void
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fd38847d0dc7..d57ce248004c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2161,7 +2161,11 @@ struct net_device {
 	struct bpf_prog __rcu	*xdp_prog;
 	unsigned long		gro_flush_timeout;
 	int			napi_defer_hard_irqs;
-#define GRO_MAX_SIZE		65536
+#define GRO_LEGACY_MAX_SIZE	65536u
+/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
+ * and shinfo->gso_segs is a 16bit field.
+ */
+#define GRO_MAX_SIZE		(8 * 65535u)
 	unsigned int		gro_max_size;
 	rx_handler_func_t __rcu	*rx_handler;
 	void __rcu		*rx_handler_data;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index b6df0314aa02..5b38bf1a586b 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -477,7 +477,7 @@ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
 	const struct hop_jumbo_hdr *jhdr;
 	const struct ipv6hdr *nhdr;
 
-	if (likely(skb->len <= GRO_MAX_SIZE))
+	if (likely(skb->len <= GRO_LEGACY_MAX_SIZE))
 		return 0;
 
 	if (skb->protocol != htons(ETH_P_IPV6))
diff --git a/net/core/dev.c b/net/core/dev.c
index 830beb05161a..d93456c75b55 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10598,7 +10598,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
-	dev->gro_max_size = GRO_MAX_SIZE;
+	dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
 	dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
 	dev->tso_max_segs = TSO_MAX_SEGS;
 	dev->upper_level = 1;
diff --git a/net/core/gro.c b/net/core/gro.c
index 78110edf5d4b..b4190eb08467 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -167,6 +167,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
+	if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
+		if (p->protocol != htons(ETH_P_IPV6) ||
+		    skb_headroom(p) < sizeof(struct hop_jumbo_hdr) ||
+		    ipv6_hdr(p)->nexthdr != IPPROTO_TCP ||
+		    p->encapsulation)
+			return -E2BIG;
+	}
+
 	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f2b0f747d3d2..ac45328607f7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2360,14 +2360,6 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
 		}
 	}
 
-	if (tb[IFLA_GRO_MAX_SIZE]) {
-		u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]);
-
-		if (gro_max_size > GRO_MAX_SIZE) {
-			NL_SET_ERR_MSG(extack, "too big gro_max_size");
-			return -EINVAL;
-		}
-	}
 	return 0;
 }
 
-- 
cgit v1.2.3


From 80e425b613421911f89664663a7060216abcaed2 Mon Sep 17 00:00:00 2001
From: Coco Li <lixiaoyan@google.com>
Date: Fri, 13 May 2022 11:34:04 -0700
Subject: ipv6: Add hop-by-hop header to jumbograms in ip6_output

Instead of simply forcing a 0 payload_len in IPv6 header,
implement RFC 2675 and insert a custom extension header.

Note that only TCP stack is currently potentially generating
jumbograms, and that this extension header is purely local,
it wont be sent on a physical link.

This is needed so that packet capture (tcpdump and friends)
can properly dissect these large packets.

Signed-off-by: Coco Li <lixiaoyan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h  |  1 +
 net/ipv6/ip6_output.c | 22 ++++++++++++++++++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ec5ca392eaa3..38c8203d52cb 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -145,6 +145,7 @@ struct inet6_skb_parm {
 #define IP6SKB_L3SLAVE         64
 #define IP6SKB_JUMBOGRAM      128
 #define IP6SKB_SEG6	      256
+#define IP6SKB_FAKEJUMBO      512
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index afa5bd4ad167..4081b12a01ff 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -182,7 +182,9 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 #endif
 
 	mtu = ip6_skb_dst_mtu(skb);
-	if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+	if (skb_is_gso(skb) &&
+	    !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+	    !skb_gso_validate_network_len(skb, mtu))
 		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
 
 	if ((skb->len > mtu && !skb_is_gso(skb)) ||
@@ -252,6 +254,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
 	struct inet6_dev *idev = ip6_dst_idev(dst);
+	struct hop_jumbo_hdr *hop_jumbo;
+	int hoplen = sizeof(*hop_jumbo);
 	unsigned int head_room;
 	struct ipv6hdr *hdr;
 	u8  proto = fl6->flowi6_proto;
@@ -259,7 +263,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	int hlimit = -1;
 	u32 mtu;
 
-	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dev);
+	head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev);
 	if (opt)
 		head_room += opt->opt_nflen + opt->opt_flen;
 
@@ -282,6 +286,20 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 					     &fl6->saddr);
 	}
 
+	if (unlikely(seg_len > IPV6_MAXPLEN)) {
+		hop_jumbo = skb_push(skb, hoplen);
+
+		hop_jumbo->nexthdr = proto;
+		hop_jumbo->hdrlen = 0;
+		hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
+		hop_jumbo->tlv_len = 4;
+		hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen);
+
+		proto = IPPROTO_HOPOPTS;
+		seg_len = 0;
+		IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO;
+	}
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
-- 
cgit v1.2.3


From 7ebd3f3ee51a9e02994cd0a1be44fbd325d1e0dc Mon Sep 17 00:00:00 2001
From: Menglong Dong <imagedong@tencent.com>
Date: Fri, 13 May 2022 11:03:38 +0800
Subject: net: skb: change the definition SKB_DR_SET()

The SKB_DR_OR() is used to set the drop reason to a value when it is
not set or specified yet. SKB_NOT_DROPPED_YET should also be considered
as not set.

Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9d82a8b6c8f1..5a2b29df6cab 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -510,7 +510,8 @@ enum skb_drop_reason {
 	(name = SKB_DROP_REASON_##reason)
 #define SKB_DR_OR(name, reason)					\
 	do {							\
-		if (name == SKB_DROP_REASON_NOT_SPECIFIED)	\
+		if (name == SKB_DROP_REASON_NOT_SPECIFIED ||	\
+		    name == SKB_NOT_DROPPED_YET)		\
 			SKB_DR_SET(name, reason);		\
 	} while (0)
 
-- 
cgit v1.2.3


From 97e719a82b43c6c2bb5eebdb3c5d479a332ac2ac Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 15 May 2022 21:24:53 -0700
Subject: net: fix possible race in skb_attempt_defer_free()

A cpu can observe sd->defer_count reaching 128,
and call smp_call_function_single_async()

Problem is that the remote CPU can clear sd->defer_count
before the IPI is run/acknowledged.

Other cpus can queue more packets and also decide
to call smp_call_function_single_async() while the pending
IPI was not yet delivered.

This is a common issue with smp_call_function_single_async().
Callers must ensure correct synchronization and serialization.

I triggered this issue while experimenting smaller threshold.
Performing the call to smp_call_function_single_async()
under sd->defer_lock protection did not solve the problem.

Commit 5a18ceca6350 ("smp: Allow smp_call_function_single_async()
to insert locked csd") replaced an informative WARN_ON_ONCE()
with a return of -EBUSY, which is often ignored.
Test of CSD_FLAG_LOCK presence is racy anyway.

Fixes: 68822bdf76f1 ("net: generalize skb freeing deferral to per-cpu lists")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 1 +
 net/core/dev.c            | 7 +++++--
 net/core/skbuff.c         | 5 ++---
 3 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d57ce248004c..cbaf312e365b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3136,6 +3136,7 @@ struct softnet_data {
 	/* Another possibly contended cache line */
 	spinlock_t		defer_lock ____cacheline_aligned_in_smp;
 	int			defer_count;
+	int			defer_ipi_scheduled;
 	struct sk_buff		*defer_list;
 	call_single_data_t	defer_csd;
 };
diff --git a/net/core/dev.c b/net/core/dev.c
index d93456c75b55..a5e663e1a75a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4582,9 +4582,12 @@ static void rps_trigger_softirq(void *data)
 #endif /* CONFIG_RPS */
 
 /* Called from hardirq (IPI) context */
-static void trigger_rx_softirq(void *data __always_unused)
+static void trigger_rx_softirq(void *data)
 {
+	struct softnet_data *sd = data;
+
 	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	smp_store_release(&sd->defer_ipi_scheduled, 0);
 }
 
 /*
@@ -11382,7 +11385,7 @@ static int __init net_dev_init(void)
 		INIT_CSD(&sd->csd, rps_trigger_softirq, sd);
 		sd->cpu = i;
 #endif
-		INIT_CSD(&sd->defer_csd, trigger_rx_softirq, NULL);
+		INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd);
 		spin_lock_init(&sd->defer_lock);
 
 		init_gro_hash(&sd->backlog);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2fea964f09d8..b40c8cdf4785 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6516,8 +6516,7 @@ void skb_attempt_defer_free(struct sk_buff *skb)
 	sd->defer_count++;
 
 	/* kick every time queue length reaches 128.
-	 * This should avoid blocking in smp_call_function_single_async().
-	 * This condition should hardly be bit under normal conditions,
+	 * This condition should hardly be hit under normal conditions,
 	 * unless cpu suddenly stopped to receive NIC interrupts.
 	 */
 	kick = sd->defer_count == 128;
@@ -6527,6 +6526,6 @@ void skb_attempt_defer_free(struct sk_buff *skb)
 	/* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU
 	 * if we are unlucky enough (this seems very unlikely).
 	 */
-	if (unlikely(kick))
+	if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1))
 		smp_call_function_single_async(cpu, &sd->defer_csd);
 }
-- 
cgit v1.2.3


From cf2df74e202d81b09f09d84c2d8903e0e87e9274 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 9 May 2022 14:26:15 +0200
Subject: net: fix dev_fill_forward_path with pppoe + bridge

When calling dev_fill_forward_path on a pppoe device, the provided destination
address is invalid. In order for the bridge fdb lookup to succeed, the pppoe
code needs to update ctx->daddr to the correct value.
Fix this by storing the address inside struct net_device_path_ctx

Fixes: f6efc675c9dd ("net: ppp: resolve forwarding path for bridge pppoe devices")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 drivers/net/ppp/pppoe.c   | 1 +
 include/linux/netdevice.h | 2 +-
 net/core/dev.c            | 2 +-
 3 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 3619520340b7..e172743948ed 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -988,6 +988,7 @@ static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx,
 	path->encap.proto = htons(ETH_P_PPP_SES);
 	path->encap.id = be16_to_cpu(po->num);
 	memcpy(path->encap.h_dest, po->pppoe_pa.remote, ETH_ALEN);
+	memcpy(ctx->daddr, po->pppoe_pa.remote, ETH_ALEN);
 	path->dev = ctx->dev;
 	ctx->dev = dev;
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b1fbe21650bb..f736c020cde2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -900,7 +900,7 @@ struct net_device_path_stack {
 
 struct net_device_path_ctx {
 	const struct net_device *dev;
-	const u8		*daddr;
+	u8			daddr[ETH_ALEN];
 
 	int			num_vlans;
 	struct {
diff --git a/net/core/dev.c b/net/core/dev.c
index 1461c2d9dec8..2771fd22dc6a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -681,11 +681,11 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
 	const struct net_device *last_dev;
 	struct net_device_path_ctx ctx = {
 		.dev	= dev,
-		.daddr	= daddr,
 	};
 	struct net_device_path *path;
 	int ret = 0;
 
+	memcpy(ctx.daddr, daddr, sizeof(ctx.daddr));
 	stack->num_paths = 0;
 	while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) {
 		last_dev = ctx.dev;
-- 
cgit v1.2.3


From 9db69df4bdd37eb1f65b6931ee067fb15b9a4d5c Mon Sep 17 00:00:00 2001
From: TingHan Shen <tinghan.shen@mediatek.com>
Date: Thu, 12 May 2022 16:22:13 +0800
Subject: firmware: mediatek: Add adsp ipc protocol interface

Some of mediatek processors contain
the Tensilica HiFix DSP for audio processing.

The communication between Host CPU and DSP firmware is
taking place using a shared memory area for message passing.

ADSP IPC protocol offers (send/recv) interfaces using
mediatek-mailbox APIs.

We use two mbox channels to implement a request-reply protocol.

Signed-off-by: Allen-KH Cheng <allen-kh.cheng@mediatek.com>
Signed-off-by: TingHan Shen <tinghan.shen@mediatek.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Curtis Malainey <cujomalainey@chromium.org>
Reviewed-by: Tzung-Bi Shih <tzungbi@google.com>
Reviewed-by: YC Hung <yc.hung@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/r/20220512082215.3018-2-tinghan.shen@mediatek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/firmware/Kconfig                       |   9 ++
 drivers/firmware/Makefile                      |   1 +
 drivers/firmware/mtk-adsp-ipc.c                | 157 +++++++++++++++++++++++++
 include/linux/firmware/mediatek/mtk-adsp-ipc.h |  65 ++++++++++
 4 files changed, 232 insertions(+)
 create mode 100644 drivers/firmware/mtk-adsp-ipc.c
 create mode 100644 include/linux/firmware/mediatek/mtk-adsp-ipc.h

(limited to 'include/linux')

diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index e5cfb01353d8..f7bc8306631b 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -203,6 +203,15 @@ config INTEL_STRATIX10_RSU
 
 	  Say Y here if you want Intel RSU support.
 
+config MTK_ADSP_IPC
+	tristate "MTK ADSP IPC Protocol driver"
+	depends on MTK_ADSP_MBOX
+	help
+	  Say yes here to add support for the MediaTek ADSP IPC
+	  between host AP (Linux) and the firmware running on ADSP.
+	  ADSP exists on some mtk processors.
+	  Client might use shared memory to exchange information with ADSP.
+
 config QCOM_SCM
 	tristate
 
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 4e58cb474a68..1be0e8295222 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_INTEL_STRATIX10_RSU)     += stratix10-rsu.o
 obj-$(CONFIG_ISCSI_IBFT_FIND)	+= iscsi_ibft_find.o
 obj-$(CONFIG_ISCSI_IBFT)	+= iscsi_ibft.o
 obj-$(CONFIG_FIRMWARE_MEMMAP)	+= memmap.o
+obj-$(CONFIG_MTK_ADSP_IPC)	+= mtk-adsp-ipc.o
 obj-$(CONFIG_RASPBERRYPI_FIRMWARE) += raspberrypi.o
 obj-$(CONFIG_FW_CFG_SYSFS)	+= qemu_fw_cfg.o
 obj-$(CONFIG_QCOM_SCM)		+= qcom-scm.o
diff --git a/drivers/firmware/mtk-adsp-ipc.c b/drivers/firmware/mtk-adsp-ipc.c
new file mode 100644
index 000000000000..cb255a99170c
--- /dev/null
+++ b/drivers/firmware/mtk-adsp-ipc.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 MediaTek Corporation. All rights reserved.
+ * Author: Allen-KH Cheng <allen-kh.cheng@mediatek.com>
+ */
+
+#include <linux/firmware/mediatek/mtk-adsp-ipc.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_client.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+/*
+ * mtk_adsp_ipc_send - send ipc cmd to MTK ADSP
+ *
+ * @ipc: ADSP IPC handle
+ * @idx: index of the mailbox channel
+ * @msg: IPC cmd (reply or request)
+ *
+ * Returns zero for success from mbox_send_message
+ * negative value for error
+ */
+int mtk_adsp_ipc_send(struct mtk_adsp_ipc *ipc, unsigned int idx, uint32_t msg)
+{
+	struct mtk_adsp_chan *adsp_chan;
+	int ret;
+
+	if (idx >= MTK_ADSP_MBOX_NUM)
+		return -EINVAL;
+
+	adsp_chan = &ipc->chans[idx];
+	ret = mbox_send_message(adsp_chan->ch, &msg);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mtk_adsp_ipc_send);
+
+/*
+ * mtk_adsp_ipc_recv - recv callback used by MTK ADSP mailbox
+ *
+ * @c: mbox client
+ * @msg: message received
+ *
+ * Users of ADSP IPC will need to privde handle_reply and handle_request
+ * callbacks.
+ */
+static void mtk_adsp_ipc_recv(struct mbox_client *c, void *msg)
+{
+	struct mtk_adsp_chan *chan = container_of(c, struct mtk_adsp_chan, cl);
+	struct device *dev = c->dev;
+
+	switch (chan->idx) {
+	case MTK_ADSP_MBOX_REPLY:
+		chan->ipc->ops->handle_reply(chan->ipc);
+		break;
+	case MTK_ADSP_MBOX_REQUEST:
+		chan->ipc->ops->handle_request(chan->ipc);
+		break;
+	default:
+		dev_err(dev, "wrong mbox chan %d\n", chan->idx);
+		break;
+	}
+}
+
+static int mtk_adsp_ipc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mtk_adsp_ipc *adsp_ipc;
+	struct mtk_adsp_chan *adsp_chan;
+	struct mbox_client *cl;
+	char *chan_name;
+	int ret;
+	int i, j;
+
+	device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent);
+
+	adsp_ipc = devm_kzalloc(dev, sizeof(*adsp_ipc), GFP_KERNEL);
+	if (!adsp_ipc)
+		return -ENOMEM;
+
+	for (i = 0; i < MTK_ADSP_MBOX_NUM; i++) {
+		chan_name = kasprintf(GFP_KERNEL, "mbox%d", i);
+		if (!chan_name) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		adsp_chan = &adsp_ipc->chans[i];
+		cl = &adsp_chan->cl;
+		cl->dev = dev->parent;
+		cl->tx_block = false;
+		cl->knows_txdone = false;
+		cl->tx_prepare = NULL;
+		cl->rx_callback = mtk_adsp_ipc_recv;
+
+		adsp_chan->ipc = adsp_ipc;
+		adsp_chan->idx = i;
+		adsp_chan->ch = mbox_request_channel_byname(cl, chan_name);
+		if (IS_ERR(adsp_chan->ch)) {
+			ret = PTR_ERR(adsp_chan->ch);
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "Failed to request mbox chan %d ret %d\n",
+					i, ret);
+			goto out_free;
+		}
+
+		dev_dbg(dev, "request mbox chan %s\n", chan_name);
+		kfree(chan_name);
+	}
+
+	adsp_ipc->dev = dev;
+	dev_set_drvdata(dev, adsp_ipc);
+	dev_dbg(dev, "MTK ADSP IPC initialized\n");
+
+	return 0;
+
+out_free:
+	kfree(chan_name);
+out:
+	for (j = 0; j < i; j++) {
+		adsp_chan = &adsp_ipc->chans[j];
+		mbox_free_channel(adsp_chan->ch);
+	}
+
+	return ret;
+}
+
+static int mtk_adsp_ipc_remove(struct platform_device *pdev)
+{
+	struct mtk_adsp_ipc *adsp_ipc = dev_get_drvdata(&pdev->dev);
+	struct mtk_adsp_chan *adsp_chan;
+	int i;
+
+	for (i = 0; i < MTK_ADSP_MBOX_NUM; i++) {
+		adsp_chan = &adsp_ipc->chans[i];
+		mbox_free_channel(adsp_chan->ch);
+	}
+
+	return 0;
+}
+
+static struct platform_driver mtk_adsp_ipc_driver = {
+	.driver = {
+		.name = "mtk-adsp-ipc",
+	},
+	.probe = mtk_adsp_ipc_probe,
+	.remove = mtk_adsp_ipc_remove,
+};
+builtin_platform_driver(mtk_adsp_ipc_driver);
+
+MODULE_AUTHOR("Allen-KH Cheng <allen-kh.cheng@mediatek.com>");
+MODULE_DESCRIPTION("MTK ADSP IPC Driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/firmware/mediatek/mtk-adsp-ipc.h b/include/linux/firmware/mediatek/mtk-adsp-ipc.h
new file mode 100644
index 000000000000..28fd313340b8
--- /dev/null
+++ b/include/linux/firmware/mediatek/mtk-adsp-ipc.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022 MediaTek Inc.
+ */
+
+#ifndef MTK_ADSP_IPC_H
+#define MTK_ADSP_IPC_H
+
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox_client.h>
+
+#define MTK_ADSP_IPC_REQ 0
+#define MTK_ADSP_IPC_RSP 1
+#define MTK_ADSP_IPC_OP_REQ 0x1
+#define MTK_ADSP_IPC_OP_RSP 0x2
+
+enum {
+	MTK_ADSP_MBOX_REPLY,
+	MTK_ADSP_MBOX_REQUEST,
+	MTK_ADSP_MBOX_NUM,
+};
+
+struct mtk_adsp_ipc;
+
+struct mtk_adsp_ipc_ops {
+	void (*handle_reply)(struct mtk_adsp_ipc *ipc);
+	void (*handle_request)(struct mtk_adsp_ipc *ipc);
+};
+
+struct mtk_adsp_chan {
+	struct mtk_adsp_ipc *ipc;
+	struct mbox_client cl;
+	struct mbox_chan *ch;
+	char *name;
+	int idx;
+};
+
+struct mtk_adsp_ipc {
+	struct mtk_adsp_chan chans[MTK_ADSP_MBOX_NUM];
+	struct device *dev;
+	struct mtk_adsp_ipc_ops *ops;
+	void *private_data;
+};
+
+static inline void mtk_adsp_ipc_set_data(struct mtk_adsp_ipc *ipc, void *data)
+{
+	if (!ipc)
+		return;
+
+	ipc->private_data = data;
+}
+
+static inline void *mtk_adsp_ipc_get_data(struct mtk_adsp_ipc *ipc)
+{
+	if (!ipc)
+		return NULL;
+
+	return ipc->private_data;
+}
+
+int mtk_adsp_ipc_send(struct mtk_adsp_ipc *ipc, unsigned int idx, uint32_t op);
+
+#endif /* MTK_ADSP_IPC_H */
-- 
cgit v1.2.3


From 7f8d12ea96352275c2850c24a1367166179392d2 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Tue, 29 Mar 2022 15:55:59 +0900
Subject: fs: add a lockdep check function for sb_start_write()

Add a function sb_write_started() to allow callers to verify if
sb_start_write() is properly called. It will be used for assertion in
btrfs.

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 include/linux/fs.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde95387a23..01d61984ce7a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1708,6 +1708,11 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
 #define __sb_writers_release(sb, lev)	\
 	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
 
+static inline bool sb_write_started(const struct super_block *sb)
+{
+	return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1);
+}
+
 /**
  * sb_end_write - drop write access to a superblock
  * @sb: the super we wrote to
-- 
cgit v1.2.3


From 908c54909ae72dcbf1d7e1440f7297187d06c275 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 5 May 2022 15:11:10 -0500
Subject: iomap: allow the file system to provide a bio_set for direct I/O

Allow the file system to provide a specific bio_set for allocating
direct I/O bios.  This will allow file systems that use the
->submit_io hook to stash away additional information for file system
use.

To make use of this additional space for information in the completion
path, the file system needs to override the ->bi_end_io callback and
then call back into iomap, so export iomap_dio_bio_end_io for that.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/iomap/direct-io.c  | 17 +++++++++++++----
 include/linux/iomap.h | 11 +++++++++++
 2 files changed, 24 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index b08f5dc31780..314d8235f4ab 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -51,6 +51,15 @@ struct iomap_dio {
 	};
 };
 
+static struct bio *iomap_dio_alloc_bio(const struct iomap_iter *iter,
+		struct iomap_dio *dio, unsigned short nr_vecs, unsigned int opf)
+{
+	if (dio->dops && dio->dops->bio_set)
+		return bio_alloc_bioset(iter->iomap.bdev, nr_vecs, opf,
+					GFP_KERNEL, dio->dops->bio_set);
+	return bio_alloc(iter->iomap.bdev, nr_vecs, opf, GFP_KERNEL);
+}
+
 static void iomap_dio_submit_bio(const struct iomap_iter *iter,
 		struct iomap_dio *dio, struct bio *bio, loff_t pos)
 {
@@ -144,7 +153,7 @@ static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret)
 	cmpxchg(&dio->error, 0, ret);
 }
 
-static void iomap_dio_bio_end_io(struct bio *bio)
+void iomap_dio_bio_end_io(struct bio *bio)
 {
 	struct iomap_dio *dio = bio->bi_private;
 	bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY);
@@ -176,16 +185,16 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		bio_put(bio);
 	}
 }
+EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io);
 
 static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
 		loff_t pos, unsigned len)
 {
 	struct inode *inode = file_inode(dio->iocb->ki_filp);
 	struct page *page = ZERO_PAGE(0);
-	int flags = REQ_SYNC | REQ_IDLE;
 	struct bio *bio;
 
-	bio = bio_alloc(iter->iomap.bdev, 1, REQ_OP_WRITE | flags, GFP_KERNEL);
+	bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE);
 	fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
 				  GFP_KERNEL);
 	bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos);
@@ -311,7 +320,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 			goto out;
 		}
 
-		bio = bio_alloc(iomap->bdev, nr_pages, bio_opf, GFP_KERNEL);
+		bio = iomap_dio_alloc_bio(iter, dio, nr_pages, bio_opf);
 		fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
 					  GFP_KERNEL);
 		bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index b76f0dd149fb..cf903f1a230f 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -320,6 +320,16 @@ struct iomap_dio_ops {
 		      unsigned flags);
 	void (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
 		          loff_t file_offset);
+
+	/*
+	 * Filesystems wishing to attach private information to a direct io bio
+	 * must provide a ->submit_io method that attaches the additional
+	 * information to the bio and changes the ->bi_end_io callback to a
+	 * custom function.  This function should, at a minimum, perform any
+	 * relevant post-processing of the bio and end with a call to
+	 * iomap_dio_bio_end_io.
+	 */
+	struct bio_set *bio_set;
 };
 
 /*
@@ -349,6 +359,7 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, size_t done_before);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
+void iomap_dio_bio_end_io(struct bio *bio);
 
 #ifdef CONFIG_SWAP
 struct file;
-- 
cgit v1.2.3


From 786f847f43a54e63161474fe85a4f1764d871a35 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 5 May 2022 15:11:11 -0500
Subject: iomap: add per-iomap_iter private data

Allow the file system to keep state for all iterations.  For now only
wire it up for direct I/O as there is an immediate need for it there.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c      | 2 +-
 fs/erofs/data.c       | 2 +-
 fs/ext4/file.c        | 4 ++--
 fs/f2fs/file.c        | 4 ++--
 fs/gfs2/file.c        | 4 ++--
 fs/iomap/direct-io.c  | 8 +++++---
 fs/xfs/xfs_file.c     | 6 +++---
 fs/zonefs/super.c     | 4 ++--
 include/linux/iomap.h | 5 +++--
 9 files changed, 21 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index eb951ac52d22..954e91b74d21 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8167,7 +8167,7 @@ static const struct iomap_dio_ops btrfs_dio_ops = {
 ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before)
 {
 	return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			    IOMAP_DIO_PARTIAL, done_before);
+			    IOMAP_DIO_PARTIAL, NULL, done_before);
 }
 
 static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 780db1e5f4b7..91c11d5bb999 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -385,7 +385,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 		if (!err)
 			return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
-					    NULL, 0, 0);
+					    NULL, 0, NULL, 0);
 		if (err < 0)
 			return err;
 	}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6feb07e3e1eb..109d07629f81 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -76,7 +76,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		return generic_file_read_iter(iocb, to);
 	}
 
-	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, 0);
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, NULL, 0);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);
@@ -565,7 +565,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		iomap_ops = &ext4_iomap_overwrite_ops;
 	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
 			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0,
-			   0);
+			   NULL, 0);
 	if (ret == -ENOTBLK)
 		ret = 0;
 
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5b89af0f27f0..04bc8709314b 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -4309,7 +4309,7 @@ static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	 */
 	inc_page_count(sbi, F2FS_DIO_READ);
 	dio = __iomap_dio_rw(iocb, to, &f2fs_iomap_ops,
-			     &f2fs_iomap_dio_read_ops, 0, 0);
+			     &f2fs_iomap_dio_read_ops, 0, NULL, 0);
 	if (IS_ERR_OR_NULL(dio)) {
 		ret = PTR_ERR_OR_ZERO(dio);
 		if (ret != -EIOCBQUEUED)
@@ -4527,7 +4527,7 @@ static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from,
 	if (pos + count > inode->i_size)
 		dio_flags |= IOMAP_DIO_FORCE_WAIT;
 	dio = __iomap_dio_rw(iocb, from, &f2fs_iomap_ops,
-			     &f2fs_iomap_dio_write_ops, dio_flags, 0);
+			     &f2fs_iomap_dio_write_ops, dio_flags, NULL, 0);
 	if (IS_ERR_OR_NULL(dio)) {
 		ret = PTR_ERR_OR_ZERO(dio);
 		if (ret == -ENOTBLK)
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 2556ae1f92ea..0b07d5a7bb81 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -835,7 +835,7 @@ retry:
 	pagefault_disable();
 	to->nofault = true;
 	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL,
-			   IOMAP_DIO_PARTIAL, read);
+			   IOMAP_DIO_PARTIAL, NULL, read);
 	to->nofault = false;
 	pagefault_enable();
 	if (ret <= 0 && ret != -EFAULT)
@@ -898,7 +898,7 @@ retry:
 
 	from->nofault = true;
 	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL,
-			   IOMAP_DIO_PARTIAL, written);
+			   IOMAP_DIO_PARTIAL, NULL, written);
 	from->nofault = false;
 	if (ret <= 0) {
 		if (ret == -ENOTBLK)
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 314d8235f4ab..cf224a8bb311 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -483,7 +483,7 @@ static loff_t iomap_dio_iter(const struct iomap_iter *iter,
 struct iomap_dio *
 __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags, size_t done_before)
+		unsigned int dio_flags, void *private, size_t done_before)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
@@ -492,6 +492,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		.pos		= iocb->ki_pos,
 		.len		= iov_iter_count(iter),
 		.flags		= IOMAP_DIRECT,
+		.private	= private,
 	};
 	loff_t end = iomi.pos + iomi.len - 1, ret = 0;
 	bool wait_for_completion =
@@ -683,11 +684,12 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw);
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags, size_t done_before)
+		unsigned int dio_flags, void *private, size_t done_before)
 {
 	struct iomap_dio *dio;
 
-	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before);
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, private,
+			     done_before);
 	if (IS_ERR_OR_NULL(dio))
 		return PTR_ERR_OR_ZERO(dio);
 	return iomap_dio_complete(dio);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5bddb1e9e0b3..85c412107a10 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -225,7 +225,7 @@ xfs_file_dio_read(
 	ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED);
 	if (ret)
 		return ret;
-	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, 0);
+	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, NULL, 0);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;
@@ -534,7 +534,7 @@ xfs_file_dio_write_aligned(
 	}
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, 0, 0);
+			   &xfs_dio_write_ops, 0, NULL, 0);
 out_unlock:
 	if (iolock)
 		xfs_iunlock(ip, iolock);
@@ -612,7 +612,7 @@ retry_exclusive:
 
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, flags, 0);
+			   &xfs_dio_write_ops, flags, NULL, 0);
 
 	/*
 	 * Retry unaligned I/O with exclusive blocking semantics if the DIO
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index e20e7c841489..777fe626c2b3 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -861,7 +861,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 		ret = zonefs_file_dio_append(iocb, from);
 	else
 		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
-				   &zonefs_write_dio_ops, 0, 0);
+				   &zonefs_write_dio_ops, 0, NULL, 0);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
 		if (ret > 0)
@@ -996,7 +996,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		}
 		file_accessed(iocb->ki_filp);
 		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
-				   &zonefs_read_dio_ops, 0, 0);
+				   &zonefs_read_dio_ops, 0, NULL, 0);
 	} else {
 		ret = generic_file_read_iter(iocb, to);
 		if (ret == -EIO)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index cf903f1a230f..5b6f64f4d771 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -188,6 +188,7 @@ struct iomap_iter {
 	unsigned flags;
 	struct iomap iomap;
 	struct iomap srcmap;
+	void *private;
 };
 
 int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops);
@@ -354,10 +355,10 @@ struct iomap_dio_ops {
 
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags, size_t done_before);
+		unsigned int dio_flags, void *private, size_t done_before);
 struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags, size_t done_before);
+		unsigned int dio_flags, void *private, size_t done_before);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
 void iomap_dio_bio_end_io(struct bio *bio);
 
-- 
cgit v1.2.3


From b3fdf9398a16f01dc013967a4ab25e99c3f4fc12 Mon Sep 17 00:00:00 2001
From: Jane Chu <jane.chu@oracle.com>
Date: Mon, 16 May 2022 11:21:46 -0700
Subject: x86/mce: relocate set{clear}_mce_nospec() functions

Relocate the twin mce functions to arch/x86/mm/pat/set_memory.c
file where they belong.

While at it, fixup a function name in a comment.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Acked-by: Borislav Petkov <bp@suse.de>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
[sfr: gate {set,clear}_mce_nospec() by CONFIG_X86_64]
Link: https://lore.kernel.org/r/165272527328.90175.8336008202048685278.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/x86/include/asm/set_memory.h | 52 ---------------------------------------
 arch/x86/mm/pat/set_memory.c      | 50 +++++++++++++++++++++++++++++++++++--
 include/linux/set_memory.h        |  8 +++---
 3 files changed, 52 insertions(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 78ca53512486..b45c4d27fd46 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -86,56 +86,4 @@ bool kernel_page_present(struct page *page);
 
 extern int kernel_set_to_readonly;
 
-#ifdef CONFIG_X86_64
-/*
- * Prevent speculative access to the page by either unmapping
- * it (if we do not require access to any part of the page) or
- * marking it uncacheable (if we want to try to retrieve data
- * from non-poisoned lines in the page).
- */
-static inline int set_mce_nospec(unsigned long pfn, bool unmap)
-{
-	unsigned long decoy_addr;
-	int rc;
-
-	/* SGX pages are not in the 1:1 map */
-	if (arch_is_platform_page(pfn << PAGE_SHIFT))
-		return 0;
-	/*
-	 * We would like to just call:
-	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
-	 * but doing that would radically increase the odds of a
-	 * speculative access to the poison page because we'd have
-	 * the virtual address of the kernel 1:1 mapping sitting
-	 * around in registers.
-	 * Instead we get tricky.  We create a non-canonical address
-	 * that looks just like the one we want, but has bit 63 flipped.
-	 * This relies on set_memory_XX() properly sanitizing any __pa()
-	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
-	 */
-	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
-
-	if (unmap)
-		rc = set_memory_np(decoy_addr, 1);
-	else
-		rc = set_memory_uc(decoy_addr, 1);
-	if (rc)
-		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
-	return rc;
-}
-#define set_mce_nospec set_mce_nospec
-
-/* Restore full speculative operation to the pfn. */
-static inline int clear_mce_nospec(unsigned long pfn)
-{
-	return set_memory_wb((unsigned long) pfn_to_kaddr(pfn), 1);
-}
-#define clear_mce_nospec clear_mce_nospec
-#else
-/*
- * Few people would run a 32-bit kernel on a machine that supports
- * recoverable errors because they have too much memory to boot 32-bit.
- */
-#endif
-
 #endif /* _ASM_X86_SET_MEMORY_H */
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index abf5ed76e4b7..0caf4b0edcbc 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -19,6 +19,7 @@
 #include <linux/vmstat.h>
 #include <linux/kernel.h>
 #include <linux/cc_platform.h>
+#include <linux/set_memory.h>
 
 #include <asm/e820/api.h>
 #include <asm/processor.h>
@@ -29,7 +30,6 @@
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #include <asm/memtype.h>
-#include <asm/set_memory.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 
@@ -1816,7 +1816,7 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages,
 }
 
 /*
- * _set_memory_prot is an internal helper for callers that have been passed
+ * __set_memory_prot is an internal helper for callers that have been passed
  * a pgprot_t value from upper layers and a reservation has already been taken.
  * If you want to set the pgprot to a specific page protocol, use the
  * set_memory_xx() functions.
@@ -1925,6 +1925,52 @@ int set_memory_wb(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL(set_memory_wb);
 
+/*
+ * Prevent speculative access to the page by either unmapping
+ * it (if we do not require access to any part of the page) or
+ * marking it uncacheable (if we want to try to retrieve data
+ * from non-poisoned lines in the page).
+ */
+#ifdef CONFIG_X86_64
+int set_mce_nospec(unsigned long pfn, bool unmap)
+{
+	unsigned long decoy_addr;
+	int rc;
+
+	/* SGX pages are not in the 1:1 map */
+	if (arch_is_platform_page(pfn << PAGE_SHIFT))
+		return 0;
+	/*
+	 * We would like to just call:
+	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
+	 * but doing that would radically increase the odds of a
+	 * speculative access to the poison page because we'd have
+	 * the virtual address of the kernel 1:1 mapping sitting
+	 * around in registers.
+	 * Instead we get tricky.  We create a non-canonical address
+	 * that looks just like the one we want, but has bit 63 flipped.
+	 * This relies on set_memory_XX() properly sanitizing any __pa()
+	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
+	 */
+	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
+
+	if (unmap)
+		rc = set_memory_np(decoy_addr, 1);
+	else
+		rc = set_memory_uc(decoy_addr, 1);
+	if (rc)
+		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
+	return rc;
+}
+
+/* Restore full speculative operation to the pfn. */
+int clear_mce_nospec(unsigned long pfn)
+{
+	return set_memory_wb((unsigned long) pfn_to_kaddr(pfn), 1);
+}
+EXPORT_SYMBOL_GPL(clear_mce_nospec);
+#endif /* CONFIG_X86_64 */
+
 int set_memory_x(unsigned long addr, int numpages)
 {
 	if (!(__supported_pte_mask & _PAGE_NX))
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index f36be5166c19..683a6c3f7179 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -42,14 +42,14 @@ static inline bool can_set_direct_map(void)
 #endif
 #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 
-#ifndef set_mce_nospec
+#ifdef CONFIG_X86_64
+int set_mce_nospec(unsigned long pfn, bool unmap);
+int clear_mce_nospec(unsigned long pfn);
+#else
 static inline int set_mce_nospec(unsigned long pfn, bool unmap)
 {
 	return 0;
 }
-#endif
-
-#ifndef clear_mce_nospec
 static inline int clear_mce_nospec(unsigned long pfn)
 {
 	return 0;
-- 
cgit v1.2.3


From 5898b43af954b83c4a4ee4ab85c4dbafa395822a Mon Sep 17 00:00:00 2001
From: Jane Chu <jane.chu@oracle.com>
Date: Mon, 16 May 2022 11:38:10 -0700
Subject: mce: fix set_mce_nospec to always unmap the whole page

The set_memory_uc() approach doesn't work well in all cases.
As Dan pointed out when "The VMM unmapped the bad page from
guest physical space and passed the machine check to the guest."
"The guest gets virtual #MC on an access to that page. When
the guest tries to do set_memory_uc() and instructs cpa_flush()
to do clean caches that results in taking another fault / exception
perhaps because the VMM unmapped the page from the guest."

Since the driver has special knowledge to handle NP or UC,
mark the poisoned page with NP and let driver handle it when
it comes down to repair.

Please refer to discussions here for more details.
https://lore.kernel.org/all/CAPcyv4hrXPb1tASBZUg-GgdVs0OOFKXMXLiHmktg_kFi7YBMyQ@mail.gmail.com/

Now since poisoned page is marked as not-present, in order to
avoid writing to a not-present page and trigger kernel Oops,
also fix pmem_do_write().

Fixes: 284ce4011ba6 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/r/165272615484.103830.2563950688772226611.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/x86/kernel/cpu/mce/core.c |  6 +++---
 arch/x86/mm/pat/set_memory.c   | 23 +++++++++++------------
 drivers/nvdimm/pmem.c          | 30 +++++++-----------------------
 include/linux/set_memory.h     |  4 ++--
 4 files changed, 23 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 981496e6bc0e..fa67bb9d1afe 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -579,7 +579,7 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
 
 	pfn = mce->addr >> PAGE_SHIFT;
 	if (!memory_failure(pfn, 0)) {
-		set_mce_nospec(pfn, whole_page(mce));
+		set_mce_nospec(pfn);
 		mce->kflags |= MCE_HANDLED_UC;
 	}
 
@@ -1316,7 +1316,7 @@ static void kill_me_maybe(struct callback_head *cb)
 
 	ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags);
 	if (!ret) {
-		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
 		sync_core();
 		return;
 	}
@@ -1342,7 +1342,7 @@ static void kill_me_never(struct callback_head *cb)
 	p->mce_count = 0;
 	pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr);
 	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0))
-		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
 }
 
 static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *))
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 0caf4b0edcbc..44f0d4260bd8 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -1925,14 +1925,9 @@ int set_memory_wb(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL(set_memory_wb);
 
-/*
- * Prevent speculative access to the page by either unmapping
- * it (if we do not require access to any part of the page) or
- * marking it uncacheable (if we want to try to retrieve data
- * from non-poisoned lines in the page).
- */
+/* Prevent speculative access to a page by marking it not-present */
 #ifdef CONFIG_X86_64
-int set_mce_nospec(unsigned long pfn, bool unmap)
+int set_mce_nospec(unsigned long pfn)
 {
 	unsigned long decoy_addr;
 	int rc;
@@ -1954,19 +1949,23 @@ int set_mce_nospec(unsigned long pfn, bool unmap)
 	 */
 	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
 
-	if (unmap)
-		rc = set_memory_np(decoy_addr, 1);
-	else
-		rc = set_memory_uc(decoy_addr, 1);
+	rc = set_memory_np(decoy_addr, 1);
 	if (rc)
 		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
 	return rc;
 }
 
+static int set_memory_present(unsigned long *addr, int numpages)
+{
+	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
 /* Restore full speculative operation to the pfn. */
 int clear_mce_nospec(unsigned long pfn)
 {
-	return set_memory_wb((unsigned long) pfn_to_kaddr(pfn), 1);
+	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
+
+	return set_memory_present(&addr, 1);
 }
 EXPORT_SYMBOL_GPL(clear_mce_nospec);
 #endif /* CONFIG_X86_64 */
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 58d95242a836..4aa17132a557 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -158,36 +158,20 @@ static blk_status_t pmem_do_write(struct pmem_device *pmem,
 			struct page *page, unsigned int page_off,
 			sector_t sector, unsigned int len)
 {
-	blk_status_t rc = BLK_STS_OK;
-	bool bad_pmem = false;
 	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
 	void *pmem_addr = pmem->virt_addr + pmem_off;
 
-	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
-		bad_pmem = true;
+	if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) {
+		blk_status_t rc = pmem_clear_poison(pmem, pmem_off, len);
+
+		if (rc != BLK_STS_OK)
+			return rc;
+	}
 
-	/*
-	 * Note that we write the data both before and after
-	 * clearing poison.  The write before clear poison
-	 * handles situations where the latest written data is
-	 * preserved and the clear poison operation simply marks
-	 * the address range as valid without changing the data.
-	 * In this case application software can assume that an
-	 * interrupted write will either return the new good
-	 * data or an error.
-	 *
-	 * However, if pmem_clear_poison() leaves the data in an
-	 * indeterminate state we need to perform the write
-	 * after clear poison.
-	 */
 	flush_dcache_page(page);
 	write_pmem(pmem_addr, page, page_off, len);
-	if (unlikely(bad_pmem)) {
-		rc = pmem_clear_poison(pmem, pmem_off, len);
-		write_pmem(pmem_addr, page, page_off, len);
-	}
 
-	return rc;
+	return BLK_STS_OK;
 }
 
 static void pmem_submit_bio(struct bio *bio)
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index 683a6c3f7179..369769ce7399 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -43,10 +43,10 @@ static inline bool can_set_direct_map(void)
 #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 
 #ifdef CONFIG_X86_64
-int set_mce_nospec(unsigned long pfn, bool unmap);
+int set_mce_nospec(unsigned long pfn);
 int clear_mce_nospec(unsigned long pfn);
 #else
-static inline int set_mce_nospec(unsigned long pfn, bool unmap)
+static inline int set_mce_nospec(unsigned long pfn)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From e511c4a3d2a1f64aafc1f5df37a2ffcf7ef91b55 Mon Sep 17 00:00:00 2001
From: Jane Chu <jane.chu@oracle.com>
Date: Fri, 13 May 2022 15:10:58 -0700
Subject: dax: introduce DAX_RECOVERY_WRITE dax access mode

Up till now, dax_direct_access() is used implicitly for normal
access, but for the purpose of recovery write, dax range with
poison is requested.  To make the interface clear, introduce
	enum dax_access_mode {
		DAX_ACCESS,
		DAX_RECOVERY_WRITE,
	}
where DAX_ACCESS is used for normal dax access, and
DAX_RECOVERY_WRITE is used for dax recovery write.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Vivek Goyal <vgoyal@redhat.com>
Link: https://lore.kernel.org/r/165247982851.52965.11024212198889762949.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/super.c             | 5 +++--
 drivers/md/dm-linear.c          | 5 +++--
 drivers/md/dm-log-writes.c      | 5 +++--
 drivers/md/dm-stripe.c          | 5 +++--
 drivers/md/dm-target.c          | 4 +++-
 drivers/md/dm-writecache.c      | 7 ++++---
 drivers/md/dm.c                 | 5 +++--
 drivers/nvdimm/pmem.c           | 8 +++++---
 drivers/nvdimm/pmem.h           | 5 ++++-
 drivers/s390/block/dcssblk.c    | 9 ++++++---
 fs/dax.c                        | 9 +++++----
 fs/fuse/dax.c                   | 4 ++--
 fs/fuse/virtio_fs.c             | 6 ++++--
 include/linux/dax.h             | 9 +++++++--
 include/linux/device-mapper.h   | 4 +++-
 tools/testing/nvdimm/pmem-dax.c | 4 +++-
 16 files changed, 61 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 0211e6f7b47a..5405eb553430 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -117,6 +117,7 @@ enum dax_device_flags {
  * @dax_dev: a dax_device instance representing the logical memory range
  * @pgoff: offset in pages from the start of the device to translate
  * @nr_pages: number of consecutive pages caller can handle relative to @pfn
+ * @mode: indicator on normal access or recovery write
  * @kaddr: output parameter that returns a virtual address mapping of pfn
  * @pfn: output parameter that returns an absolute pfn translation of @pgoff
  *
@@ -124,7 +125,7 @@ enum dax_device_flags {
  * pages accessible at the device relative @pgoff.
  */
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn)
+		enum dax_access_mode mode, void **kaddr, pfn_t *pfn)
 {
 	long avail;
 
@@ -138,7 +139,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		return -EINVAL;
 
 	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
-			kaddr, pfn);
+			mode, kaddr, pfn);
 	if (!avail)
 		return -ERANGE;
 	return min(avail, nr_pages);
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 76b486e4d2be..13e263299c9c 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -172,11 +172,12 @@ static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 }
 
 static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index c9d036d6bb2e..06bdbed65eb1 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -889,11 +889,12 @@ static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
 }
 
 static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-					 long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index c81d331d1afe..77d72900e997 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -315,11 +315,12 @@ static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 }
 
 static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
 
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 64dd0b34fcf4..8cd5184e62f0 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/bio.h>
+#include <linux/dax.h>
 
 #define DM_MSG_PREFIX "target"
 
@@ -142,7 +143,8 @@ static void io_err_release_clone_rq(struct request *clone,
 }
 
 static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	return -EIO;
 }
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 5630b470ba42..d74c5a7a0ab4 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -286,7 +286,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 
 	id = dax_read_lock();
 
-	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn);
+	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, DAX_ACCESS,
+			&wc->memory_map, &pfn);
 	if (da < 0) {
 		wc->memory_map = NULL;
 		r = da;
@@ -308,8 +309,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		i = 0;
 		do {
 			long daa;
-			daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i,
-						NULL, &pfn);
+			daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i,
+					p - i, DAX_ACCESS, NULL, &pfn);
 			if (daa <= 0) {
 				r = daa ? daa : -EINVAL;
 				goto err3;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 82957bd460e8..9c452641c3d5 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1093,7 +1093,8 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
 }
 
 static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-				 long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct mapped_device *md = dax_get_private(dax_dev);
 	sector_t sector = pgoff * PAGE_SECTORS;
@@ -1111,7 +1112,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	if (len < 1)
 		goto out;
 	nr_pages = min(len, nr_pages);
-	ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
+	ret = ti->type->direct_access(ti, pgoff, nr_pages, mode, kaddr, pfn);
 
  out:
 	dm_put_live_table(md, srcu_idx);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 4aa17132a557..47f34c50f944 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -239,7 +239,8 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 
 /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
 __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
 
@@ -278,11 +279,12 @@ static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 
 static long pmem_dax_direct_access(struct dax_device *dax_dev,
-		pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
+		pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
+		void **kaddr, pfn_t *pfn)
 {
 	struct pmem_device *pmem = dax_get_private(dax_dev);
 
-	return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
+	return __pmem_direct_access(pmem, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
 static const struct dax_operations pmem_dax_ops = {
diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index 1f51a2361429..392b0b38acb9 100644
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -8,6 +8,8 @@
 #include <linux/pfn_t.h>
 #include <linux/fs.h>
 
+enum dax_access_mode;
+
 /* this definition is in it's own header for tools/testing/nvdimm to consume */
 struct pmem_device {
 	/* One contiguous memory region per device */
@@ -28,7 +30,8 @@ struct pmem_device {
 };
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn);
 
 #ifdef CONFIG_MEMORY_FAILURE
 static inline bool test_and_clear_pmem_poison(struct page *page)
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index d614843caf6c..8d0d0eaa3059 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -32,7 +32,8 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_submit_bio(struct bio *bio);
 static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -50,7 +51,8 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
 	long rc;
 	void *kaddr;
 
-	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, DAX_ACCESS,
+			&kaddr, NULL);
 	if (rc < 0)
 		return rc;
 	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
@@ -927,7 +929,8 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
 
 static long
 dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	struct dcssblk_dev_info *dev_info = dax_get_private(dax_dev);
 
diff --git a/fs/dax.c b/fs/dax.c
index 67a08a32fccb..ef3103107104 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -721,7 +721,8 @@ static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter
 	int id;
 
 	id = dax_read_lock();
-	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL);
+	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, DAX_ACCESS,
+				&kaddr, NULL);
 	if (rc < 0) {
 		dax_read_unlock(id);
 		return rc;
@@ -1013,7 +1014,7 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size,
 
 	id = dax_read_lock();
 	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
-				   NULL, pfnp);
+				   DAX_ACCESS, NULL, pfnp);
 	if (length < 0) {
 		rc = length;
 		goto out;
@@ -1122,7 +1123,7 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
 	void *kaddr;
 	long ret;
 
-	ret = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+	ret = dax_direct_access(dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, NULL);
 	if (ret > 0) {
 		memset(kaddr + offset, 0, size);
 		dax_flush(dax_dev, kaddr + offset, size);
@@ -1247,7 +1248,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		}
 
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
-				&kaddr, NULL);
+				DAX_ACCESS, &kaddr, NULL);
 		if (map_len < 0) {
 			ret = map_len;
 			break;
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index d7d3a7f06862..10eb50cbf398 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -1241,8 +1241,8 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd)
 	INIT_DELAYED_WORK(&fcd->free_work, fuse_dax_free_mem_worker);
 
 	id = dax_read_lock();
-	nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), NULL,
-				     NULL);
+	nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size),
+			DAX_ACCESS, NULL, NULL);
 	dax_read_unlock(id);
 	if (nr_pages < 0) {
 		pr_debug("dax_direct_access() returned %ld\n", nr_pages);
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 86b7dbb6a0d4..8db53fa67359 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -752,7 +752,8 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev,
  * offset.
  */
 static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-				    long nr_pages, void **kaddr, pfn_t *pfn)
+				    long nr_pages, enum dax_access_mode mode,
+				    void **kaddr, pfn_t *pfn)
 {
 	struct virtio_fs *fs = dax_get_private(dax_dev);
 	phys_addr_t offset = PFN_PHYS(pgoff);
@@ -772,7 +773,8 @@ static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
 	long rc;
 	void *kaddr;
 
-	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, DAX_ACCESS, &kaddr,
+			       NULL);
 	if (rc < 0)
 		return rc;
 	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9fc5f99a0ae2..3f1339bce3c0 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -14,6 +14,11 @@ struct iomap_ops;
 struct iomap_iter;
 struct iomap;
 
+enum dax_access_mode {
+	DAX_ACCESS,
+	DAX_RECOVERY_WRITE,
+};
+
 struct dax_operations {
 	/*
 	 * direct_access: translate a device-relative
@@ -21,7 +26,7 @@ struct dax_operations {
 	 * number of pages available for DAX at that pfn.
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
-			void **, pfn_t *);
+			enum dax_access_mode, void **, pfn_t *);
 	/*
 	 * Validate whether this device is usable as an fsdax backing
 	 * device.
@@ -178,7 +183,7 @@ static inline void dax_read_unlock(int id)
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn);
+		enum dax_access_mode mode, void **kaddr, pfn_t *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index c2a3758c4aaa..acdedda0d12b 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -20,6 +20,7 @@ struct dm_table;
 struct dm_report_zones_args;
 struct mapped_device;
 struct bio_vec;
+enum dax_access_mode;
 
 /*
  * Type of table, mapped_device's mempool and request_queue
@@ -146,7 +147,8 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  * >= 0 : the number of bytes accessible at the address
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, enum dax_access_mode node, void **kaddr,
+		pfn_t *pfn);
 typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
 		size_t nr_pages);
 
diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c
index af19c85558e7..c1ec099a3b1d 100644
--- a/tools/testing/nvdimm/pmem-dax.c
+++ b/tools/testing/nvdimm/pmem-dax.c
@@ -4,11 +4,13 @@
  */
 #include "test/nfit_test.h"
 #include <linux/blkdev.h>
+#include <linux/dax.h>
 #include <pmem.h>
 #include <nd.h>
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		pfn_t *pfn)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
 
-- 
cgit v1.2.3


From 047218ec904da19c45c4a70274fc3f818a1fcba1 Mon Sep 17 00:00:00 2001
From: Jane Chu <jane.chu@oracle.com>
Date: Fri, 22 Apr 2022 16:45:06 -0600
Subject: dax: add .recovery_write dax_operation

Introduce dax_recovery_write() operation. The function is used to
recover a dax range that contains poison. Typical use case is when
a user process receives a SIGBUS with si_code BUS_MCEERR_AR
indicating poison(s) in a dax range, in response, the user process
issues a pwrite() to the page-aligned dax range, thus clears the
poison and puts valid data in the range.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Link: https://lore.kernel.org/r/20220422224508.440670-6-jane.chu@oracle.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/super.c           |  9 +++++++++
 drivers/md/dm-linear.c        | 10 ++++++++++
 drivers/md/dm-log-writes.c    | 10 ++++++++++
 drivers/md/dm-stripe.c        | 10 ++++++++++
 drivers/md/dm.c               | 20 ++++++++++++++++++++
 drivers/nvdimm/pmem.c         |  7 +++++++
 fs/dax.c                      | 13 ++++++++++++-
 include/linux/dax.h           | 13 +++++++++++++
 include/linux/device-mapper.h |  9 +++++++++
 9 files changed, 100 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 5405eb553430..50a08b2ec247 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -195,6 +195,15 @@ int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 EXPORT_SYMBOL_GPL(dax_zero_page_range);
 
+size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *iter)
+{
+	if (!dax_dev->ops->recovery_write)
+		return 0;
+	return dax_dev->ops->recovery_write(dax_dev, pgoff, addr, bytes, iter);
+}
+EXPORT_SYMBOL_GPL(dax_recovery_write);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 13e263299c9c..cdf48bc8c5b0 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -188,9 +188,18 @@ static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
 }
 
+static size_t linear_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
+
+	return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define linear_dax_direct_access NULL
 #define linear_dax_zero_page_range NULL
+#define linear_dax_recovery_write NULL
 #endif
 
 static struct target_type linear_target = {
@@ -208,6 +217,7 @@ static struct target_type linear_target = {
 	.iterate_devices = linear_iterate_devices,
 	.direct_access = linear_dax_direct_access,
 	.dax_zero_page_range = linear_dax_zero_page_range,
+	.dax_recovery_write = linear_dax_recovery_write,
 };
 
 int __init dm_linear_init(void)
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 06bdbed65eb1..22739dccdd17 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -905,9 +905,18 @@ static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages << PAGE_SHIFT);
 }
 
+static size_t log_writes_dax_recovery_write(struct dm_target *ti,
+		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
+
+	return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define log_writes_dax_direct_access NULL
 #define log_writes_dax_zero_page_range NULL
+#define log_writes_dax_recovery_write NULL
 #endif
 
 static struct target_type log_writes_target = {
@@ -925,6 +934,7 @@ static struct target_type log_writes_target = {
 	.io_hints = log_writes_io_hints,
 	.direct_access = log_writes_dax_direct_access,
 	.dax_zero_page_range = log_writes_dax_zero_page_range,
+	.dax_recovery_write = log_writes_dax_recovery_write,
 };
 
 static int __init dm_log_writes_init(void)
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 77d72900e997..baa085cc67bd 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -331,9 +331,18 @@ static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
 }
 
+static size_t stripe_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
+
+	return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define stripe_dax_direct_access NULL
 #define stripe_dax_zero_page_range NULL
+#define stripe_dax_recovery_write NULL
 #endif
 
 /*
@@ -470,6 +479,7 @@ static struct target_type stripe_target = {
 	.io_hints = stripe_io_hints,
 	.direct_access = stripe_dax_direct_access,
 	.dax_zero_page_range = stripe_dax_zero_page_range,
+	.dax_recovery_write = stripe_dax_recovery_write,
 };
 
 int __init dm_stripe_init(void)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 9c452641c3d5..3fe76ab20069 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1147,6 +1147,25 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static size_t dm_dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dm_target *ti;
+	int srcu_idx;
+	long ret = 0;
+
+	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+	if (!ti || !ti->type->dax_recovery_write)
+		goto out;
+
+	ret = ti->type->dax_recovery_write(ti, pgoff, addr, bytes, i);
+out:
+	dm_put_live_table(md, srcu_idx);
+	return ret;
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_* zone management
@@ -3147,6 +3166,7 @@ static const struct block_device_operations dm_rq_blk_dops = {
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
 	.zero_page_range = dm_dax_zero_page_range,
+	.recovery_write = dm_dax_recovery_write,
 };
 
 /*
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 47f34c50f944..e5e288135af7 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -287,9 +287,16 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
 	return __pmem_direct_access(pmem, pgoff, nr_pages, mode, kaddr, pfn);
 }
 
+static size_t pmem_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	return 0;
+}
+
 static const struct dax_operations pmem_dax_ops = {
 	.direct_access = pmem_dax_direct_access,
 	.zero_page_range = pmem_dax_zero_page_range,
+	.recovery_write = pmem_recovery_write,
 };
 
 static ssize_t write_cache_show(struct device *dev,
diff --git a/fs/dax.c b/fs/dax.c
index ef3103107104..a1e4b45cbf55 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1240,6 +1240,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		const size_t size = ALIGN(length + offset, PAGE_SIZE);
 		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 		ssize_t map_len;
+		bool recovery = false;
 		void *kaddr;
 
 		if (fatal_signal_pending(current)) {
@@ -1249,6 +1250,13 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
 				DAX_ACCESS, &kaddr, NULL);
+		if (map_len == -EIO && iov_iter_rw(iter) == WRITE) {
+			map_len = dax_direct_access(dax_dev, pgoff,
+					PHYS_PFN(size), DAX_RECOVERY_WRITE,
+					&kaddr, NULL);
+			if (map_len > 0)
+				recovery = true;
+		}
 		if (map_len < 0) {
 			ret = map_len;
 			break;
@@ -1260,7 +1268,10 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		if (map_len > end - pos)
 			map_len = end - pos;
 
-		if (iov_iter_rw(iter) == WRITE)
+		if (recovery)
+			xfer = dax_recovery_write(dax_dev, pgoff, kaddr,
+					map_len, iter);
+		else if (iov_iter_rw(iter) == WRITE)
 			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 		else
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 3f1339bce3c0..e7b81634c52a 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -35,6 +35,12 @@ struct dax_operations {
 			sector_t, sector_t);
 	/* zero_page_range: required operation. Zero page range   */
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
+	/*
+	 * recovery_write: recover a poisoned range by DAX device driver
+	 * capable of clearing poison.
+	 */
+	size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff,
+			void *addr, size_t bytes, struct iov_iter *iter);
 };
 
 #if IS_ENABLED(CONFIG_DAX)
@@ -45,6 +51,8 @@ void dax_write_cache(struct dax_device *dax_dev, bool wc);
 bool dax_write_cache_enabled(struct dax_device *dax_dev);
 bool dax_synchronous(struct dax_device *dax_dev);
 void set_dax_synchronous(struct dax_device *dax_dev);
+size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i);
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
@@ -92,6 +100,11 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 {
 	return !(vma->vm_flags & VM_SYNC);
 }
+static inline size_t dax_recovery_write(struct dax_device *dax_dev,
+		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+	return 0;
+}
 #endif
 
 void set_dax_nocache(struct dax_device *dax_dev);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index acdedda0d12b..47a01c7cffdf 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -152,6 +152,14 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
 		size_t nr_pages);
 
+/*
+ * Returns:
+ * != 0 : number of bytes transferred
+ * 0    : recovery write failed
+ */
+typedef size_t (*dm_dax_recovery_write_fn)(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i);
+
 void dm_error(const char *message);
 
 struct dm_dev {
@@ -201,6 +209,7 @@ struct target_type {
 	dm_io_hints_fn io_hints;
 	dm_dax_direct_access_fn direct_access;
 	dm_dax_zero_page_range_fn dax_zero_page_range;
+	dm_dax_recovery_write_fn dax_recovery_write;
 
 	/* For internal device-mapper use. */
 	struct list_head list;
-- 
cgit v1.2.3


From 89af2ce2d95c80f6da9388d9da2e35c84c2573b1 Mon Sep 17 00:00:00 2001
From: Ricardo Martinez <ricardo.martinez@linux.intel.com>
Date: Fri, 13 May 2022 10:34:00 -0700
Subject: net: skb: Remove skb_data_area_size()

skb_data_area_size() is not needed. As Jakub pointed out [1]:
For Rx, drivers can use the size passed during skb allocation or
use skb_tailroom().
For Tx, drivers should use skb_headlen().

[1] https://lore.kernel.org/netdev/CAHNKnsTmH-rGgWi3jtyC=ktM1DW2W1VJkYoTMJV2Z_Bt498bsg@mail.gmail.com/

Signed-off-by: Ricardo Martinez <ricardo.martinez@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5a2b29df6cab..da96f0d3e753 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1765,11 +1765,6 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 }
 #endif
 
-static inline unsigned int skb_data_area_size(struct sk_buff *skb)
-{
-	return skb_end_pointer(skb) - skb->data;
-}
-
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 				       struct ubuf_info *uarg);
 
-- 
cgit v1.2.3


From e626f37e657adbab2a7abe51480925891662a5f3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 May 2022 14:29:43 +0200
Subject: nvme: split the enum used for various register constants

Instead of having one big enum add one for each register or field.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
---
 include/linux/nvme.h | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index bbabdc7600da..5f6d432fa06a 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -204,8 +204,9 @@ enum {
 	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
 	NVME_CC_IOSQES		= NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
 	NVME_CC_IOCQES		= NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
-	NVME_CAP_CSS_NVM	= 1 << 0,
-	NVME_CAP_CSS_CSI	= 1 << 6,
+};
+
+enum {
 	NVME_CSTS_RDY		= 1 << 0,
 	NVME_CSTS_CFS		= 1 << 1,
 	NVME_CSTS_NSSRO		= 1 << 4,
@@ -214,10 +215,18 @@ enum {
 	NVME_CSTS_SHST_OCCUR	= 1 << 2,
 	NVME_CSTS_SHST_CMPLT	= 2 << 2,
 	NVME_CSTS_SHST_MASK	= 3 << 2,
+};
+
+enum {
 	NVME_CMBMSC_CRE		= 1 << 0,
 	NVME_CMBMSC_CMSE	= 1 << 1,
 };
 
+enum {
+	NVME_CAP_CSS_NVM	= 1 << 0,
+	NVME_CAP_CSS_CSI	= 1 << 6,
+};
+
 struct nvme_id_power_state {
 	__le16			max_power;	/* centiwatts */
 	__u8			rsvd2;
-- 
cgit v1.2.3


From a03dacb0316f74400846aaf144d6c73f4217ca08 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <skannan@codeaurora.org>
Date: Tue, 2 Mar 2021 15:58:21 +0900
Subject: PM / devfreq: Add cpu based scaling support to passive governor

Many CPU architectures have caches that can scale independent of the
CPUs. Frequency scaling of the caches is necessary to make sure that the
cache is not a performance bottleneck that leads to poor performance and
power. The same idea applies for RAM/DDR.

To achieve this, this patch adds support for cpu based scaling to the
passive governor. This is accomplished by taking the current frequency
of each CPU frequency domain and then adjust the frequency of the cache
(or any devfreq device) based on the frequency of the CPUs. It listens
to CPU frequency transition notifiers to keep itself up to date on the
current CPU frequency.

To decide the frequency of the device, the governor does one of the
following:
* Derives the optimal devfreq device opp from required-opps property of
  the parent cpu opp_table.

* Scales the device frequency in proportion to the CPU frequency. So, if
  the CPUs are running at their max frequency, the device runs at its
  max frequency. If the CPUs are running at their min frequency, the
  device runs at its min frequency. It is interpolated for frequencies
  in between.

Tested-by: Chen-Yu Tsai <wenst@chromium.org>
Tested-by: Johnson Wang <johnson.wang@mediatek.com>
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
[Sibi: Integrated cpu-freqmap governor into passive_governor]
Signed-off-by: Sibi Sankar <sibis@codeaurora.org>
[Chanwoo: Fix conflict with latest code and cleanup code]
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/governor.h         |  22 +++
 drivers/devfreq/governor_passive.c | 298 +++++++++++++++++++++++++++++++++++--
 include/linux/devfreq.h            |  17 ++-
 3 files changed, 323 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index b0dbfee8bbf2..335c4a491254 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -47,6 +47,28 @@
 #define DEVFREQ_GOV_ATTR_POLLING_INTERVAL		BIT(0)
 #define DEVFREQ_GOV_ATTR_TIMER				BIT(1)
 
+/**
+ * struct devfreq_cpu_data - Hold the per-cpu data
+ * @dev:	reference to cpu device.
+ * @first_cpu:	the cpumask of the first cpu of a policy.
+ * @opp_table:	reference to cpu opp table.
+ * @cur_freq:	the current frequency of the cpu.
+ * @min_freq:	the min frequency of the cpu.
+ * @max_freq:	the max frequency of the cpu.
+ *
+ * This structure stores the required cpu_data of a cpu.
+ * This is auto-populated by the governor.
+ */
+struct devfreq_cpu_data {
+	struct device *dev;
+	unsigned int first_cpu;
+
+	struct opp_table *opp_table;
+	unsigned int cur_freq;
+	unsigned int min_freq;
+	unsigned int max_freq;
+};
+
 /**
  * struct devfreq_governor - Devfreq policy governor
  * @node:		list node - contains registered devfreq governors
diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c
index fc09324a03e0..7f30088b500b 100644
--- a/drivers/devfreq/governor_passive.c
+++ b/drivers/devfreq/governor_passive.c
@@ -8,11 +8,85 @@
  */
 
 #include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/devfreq.h>
 #include "governor.h"
 
-static int devfreq_passive_get_target_freq(struct devfreq *devfreq,
+#define HZ_PER_KHZ	1000
+
+static unsigned long get_target_freq_by_required_opp(struct device *p_dev,
+						struct opp_table *p_opp_table,
+						struct opp_table *opp_table,
+						unsigned long *freq)
+{
+	struct dev_pm_opp *opp = NULL, *p_opp = NULL;
+	unsigned long target_freq;
+
+	if (!p_dev || !p_opp_table || !opp_table || !freq)
+		return 0;
+
+	p_opp = devfreq_recommended_opp(p_dev, freq, 0);
+	if (IS_ERR(p_opp))
+		return 0;
+
+	opp = dev_pm_opp_xlate_required_opp(p_opp_table, opp_table, p_opp);
+	dev_pm_opp_put(p_opp);
+
+	if (IS_ERR(opp))
+		return 0;
+
+	target_freq = dev_pm_opp_get_freq(opp);
+	dev_pm_opp_put(opp);
+
+	return target_freq;
+}
+
+static int get_target_freq_with_cpufreq(struct devfreq *devfreq,
+					unsigned long *target_freq)
+{
+	struct devfreq_passive_data *p_data =
+				(struct devfreq_passive_data *)devfreq->data;
+	struct devfreq_cpu_data *parent_cpu_data;
+	unsigned long cpu, cpu_cur, cpu_min, cpu_max, cpu_percent;
+	unsigned long dev_min, dev_max;
+	unsigned long freq = 0;
+
+	for_each_online_cpu(cpu) {
+		parent_cpu_data = p_data->parent_cpu_data[cpu];
+		if (!parent_cpu_data || parent_cpu_data->first_cpu != cpu)
+			continue;
+
+		/* Get target freq via required opps */
+		cpu_cur = parent_cpu_data->cur_freq * HZ_PER_KHZ;
+		freq = get_target_freq_by_required_opp(parent_cpu_data->dev,
+					parent_cpu_data->opp_table,
+					devfreq->opp_table, &cpu_cur);
+		if (freq) {
+			*target_freq = max(freq, *target_freq);
+			continue;
+		}
+
+		/* Use interpolation if required opps is not available */
+		devfreq_get_freq_range(devfreq, &dev_min, &dev_max);
+
+		cpu_min = parent_cpu_data->min_freq;
+		cpu_max = parent_cpu_data->max_freq;
+		cpu_cur = parent_cpu_data->cur_freq;
+
+		cpu_percent = ((cpu_cur - cpu_min) * 100) / (cpu_max - cpu_min);
+		freq = dev_min + mult_frac(dev_max - dev_min, cpu_percent, 100);
+
+		*target_freq = max(freq, *target_freq);
+	}
+
+	return 0;
+}
+
+static int get_target_freq_with_devfreq(struct devfreq *devfreq,
 					unsigned long *freq)
 {
 	struct devfreq_passive_data *p_data
@@ -99,6 +173,181 @@ no_required_opp:
 	return 0;
 }
 
+static int devfreq_passive_get_target_freq(struct devfreq *devfreq,
+					   unsigned long *freq)
+{
+	struct devfreq_passive_data *p_data =
+				(struct devfreq_passive_data *)devfreq->data;
+	int ret;
+
+	if (!p_data)
+		return -EINVAL;
+
+	/*
+	 * If the devfreq device with passive governor has the specific method
+	 * to determine the next frequency, should use the get_target_freq()
+	 * of struct devfreq_passive_data.
+	 */
+	if (p_data->get_target_freq)
+		return p_data->get_target_freq(devfreq, freq);
+
+	switch (p_data->parent_type) {
+	case DEVFREQ_PARENT_DEV:
+		ret = get_target_freq_with_devfreq(devfreq, freq);
+		break;
+	case CPUFREQ_PARENT_DEV:
+		ret = get_target_freq_with_cpufreq(devfreq, freq);
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(&devfreq->dev, "Invalid parent type\n");
+		break;
+	}
+
+	return ret;
+}
+
+static int cpufreq_passive_notifier_call(struct notifier_block *nb,
+					 unsigned long event, void *ptr)
+{
+	struct devfreq_passive_data *p_data =
+			container_of(nb, struct devfreq_passive_data, nb);
+	struct devfreq *devfreq = (struct devfreq *)p_data->this;
+	struct devfreq_cpu_data *parent_cpu_data;
+	struct cpufreq_freqs *freqs = ptr;
+	unsigned int cur_freq;
+	int ret;
+
+	if (event != CPUFREQ_POSTCHANGE || !freqs ||
+		!p_data->parent_cpu_data[freqs->policy->cpu])
+		return 0;
+
+	parent_cpu_data = p_data->parent_cpu_data[freqs->policy->cpu];
+	if (parent_cpu_data->cur_freq == freqs->new)
+		return 0;
+
+	cur_freq = parent_cpu_data->cur_freq;
+	parent_cpu_data->cur_freq = freqs->new;
+
+	mutex_lock(&devfreq->lock);
+	ret = devfreq_update_target(devfreq, freqs->new);
+	mutex_unlock(&devfreq->lock);
+	if (ret) {
+		parent_cpu_data->cur_freq = cur_freq;
+		dev_err(&devfreq->dev, "failed to update the frequency.\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int cpufreq_passive_unregister_notifier(struct devfreq *devfreq)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct devfreq_cpu_data *parent_cpu_data;
+	int cpu, ret;
+
+	if (p_data->nb.notifier_call) {
+		ret = cpufreq_unregister_notifier(&p_data->nb,
+					CPUFREQ_TRANSITION_NOTIFIER);
+		if (ret < 0)
+			return ret;
+	}
+
+	for_each_possible_cpu(cpu) {
+		parent_cpu_data = p_data->parent_cpu_data[cpu];
+		if (!parent_cpu_data)
+			continue;
+
+		if (parent_cpu_data->opp_table)
+			dev_pm_opp_put_opp_table(parent_cpu_data->opp_table);
+		kfree(parent_cpu_data);
+	}
+
+	return 0;
+}
+
+static int cpufreq_passive_register_notifier(struct devfreq *devfreq)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct device *dev = devfreq->dev.parent;
+	struct opp_table *opp_table = NULL;
+	struct devfreq_cpu_data *parent_cpu_data;
+	struct cpufreq_policy *policy;
+	struct device *cpu_dev;
+	unsigned int cpu;
+	int ret;
+
+	p_data->nb.notifier_call = cpufreq_passive_notifier_call;
+	ret = cpufreq_register_notifier(&p_data->nb, CPUFREQ_TRANSITION_NOTIFIER);
+	if (ret) {
+		dev_err(dev, "failed to register cpufreq notifier\n");
+		p_data->nb.notifier_call = NULL;
+		goto err;
+	}
+
+	for_each_possible_cpu(cpu) {
+		if (p_data->parent_cpu_data[cpu])
+			continue;
+
+		policy = cpufreq_cpu_get(cpu);
+		if (!policy) {
+			ret = -EPROBE_DEFER;
+			goto err;
+		}
+
+		parent_cpu_data = kzalloc(sizeof(*parent_cpu_data),
+						GFP_KERNEL);
+		if (!parent_cpu_data) {
+			ret = -ENOMEM;
+			goto err_put_policy;
+		}
+
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			dev_err(dev, "failed to get cpu device\n");
+			ret = -ENODEV;
+			goto err_free_cpu_data;
+		}
+
+		opp_table = dev_pm_opp_get_opp_table(cpu_dev);
+		if (IS_ERR(opp_table)) {
+			dev_err(dev, "failed to get opp_table of cpu%d\n", cpu);
+			ret = PTR_ERR(opp_table);
+			goto err_free_cpu_data;
+		}
+
+		parent_cpu_data->dev = cpu_dev;
+		parent_cpu_data->opp_table = opp_table;
+		parent_cpu_data->first_cpu = cpumask_first(policy->related_cpus);
+		parent_cpu_data->cur_freq = policy->cur;
+		parent_cpu_data->min_freq = policy->cpuinfo.min_freq;
+		parent_cpu_data->max_freq = policy->cpuinfo.max_freq;
+
+		p_data->parent_cpu_data[cpu] = parent_cpu_data;
+		cpufreq_cpu_put(policy);
+	}
+
+	mutex_lock(&devfreq->lock);
+	ret = devfreq_update_target(devfreq, 0L);
+	mutex_unlock(&devfreq->lock);
+	if (ret)
+		dev_err(dev, "failed to update the frequency\n");
+
+	return ret;
+
+err_free_cpu_data:
+	kfree(parent_cpu_data);
+err_put_policy:
+	cpufreq_cpu_put(policy);
+err:
+	WARN_ON(cpufreq_passive_unregister_notifier(devfreq));
+
+	return ret;
+}
+
 static int devfreq_passive_notifier_call(struct notifier_block *nb,
 				unsigned long event, void *ptr)
 {
@@ -131,30 +380,55 @@ static int devfreq_passive_notifier_call(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-static int devfreq_passive_event_handler(struct devfreq *devfreq,
-				unsigned int event, void *data)
+static int devfreq_passive_unregister_notifier(struct devfreq *devfreq)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct devfreq *parent = (struct devfreq *)p_data->parent;
+	struct notifier_block *nb = &p_data->nb;
+
+	return devfreq_unregister_notifier(parent, nb, DEVFREQ_TRANSITION_NOTIFIER);
+}
+
+static int devfreq_passive_register_notifier(struct devfreq *devfreq)
 {
 	struct devfreq_passive_data *p_data
 			= (struct devfreq_passive_data *)devfreq->data;
 	struct devfreq *parent = (struct devfreq *)p_data->parent;
 	struct notifier_block *nb = &p_data->nb;
-	int ret = 0;
 
 	if (!parent)
 		return -EPROBE_DEFER;
 
+	nb->notifier_call = devfreq_passive_notifier_call;
+	return devfreq_register_notifier(parent, nb, DEVFREQ_TRANSITION_NOTIFIER);
+}
+
+static int devfreq_passive_event_handler(struct devfreq *devfreq,
+				unsigned int event, void *data)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	int ret = -EINVAL;
+
+	if (!p_data)
+		return -EINVAL;
+
+	if (!p_data->this)
+		p_data->this = devfreq;
+
 	switch (event) {
 	case DEVFREQ_GOV_START:
-		if (!p_data->this)
-			p_data->this = devfreq;
-
-		nb->notifier_call = devfreq_passive_notifier_call;
-		ret = devfreq_register_notifier(parent, nb,
-					DEVFREQ_TRANSITION_NOTIFIER);
+		if (p_data->parent_type == DEVFREQ_PARENT_DEV)
+			ret = devfreq_passive_register_notifier(devfreq);
+		else if (p_data->parent_type == CPUFREQ_PARENT_DEV)
+			ret = cpufreq_passive_register_notifier(devfreq);
 		break;
 	case DEVFREQ_GOV_STOP:
-		WARN_ON(devfreq_unregister_notifier(parent, nb,
-					DEVFREQ_TRANSITION_NOTIFIER));
+		if (p_data->parent_type == DEVFREQ_PARENT_DEV)
+			WARN_ON(devfreq_passive_unregister_notifier(devfreq));
+		else if (p_data->parent_type == CPUFREQ_PARENT_DEV)
+			WARN_ON(cpufreq_passive_unregister_notifier(devfreq));
 		break;
 	default:
 		break;
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 142474b4af96..b1e4a6f796ce 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -38,6 +38,7 @@ enum devfreq_timer {
 
 struct devfreq;
 struct devfreq_governor;
+struct devfreq_cpu_data;
 struct thermal_cooling_device;
 
 /**
@@ -288,6 +289,11 @@ struct devfreq_simple_ondemand_data {
 #endif
 
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE)
+enum devfreq_parent_dev_type {
+	DEVFREQ_PARENT_DEV,
+	CPUFREQ_PARENT_DEV,
+};
+
 /**
  * struct devfreq_passive_data - ``void *data`` fed to struct devfreq
  *	and devfreq_add_device
@@ -299,8 +305,11 @@ struct devfreq_simple_ondemand_data {
  *			using governors except for passive governor.
  *			If the devfreq device has the specific method to decide
  *			the next frequency, should use this callback.
- * @this:	the devfreq instance of own device.
- * @nb:		the notifier block for DEVFREQ_TRANSITION_NOTIFIER list
+ * @parent_type:	the parent type of the device.
+ * @this:		the devfreq instance of own device.
+ * @nb:			the notifier block for DEVFREQ_TRANSITION_NOTIFIER or
+ *			CPUFREQ_TRANSITION_NOTIFIER list.
+ * @parent_cpu_data:	the state min/max/current frequency of all online cpu's.
  *
  * The devfreq_passive_data have to set the devfreq instance of parent
  * device with governors except for the passive governor. But, don't need to
@@ -314,9 +323,13 @@ struct devfreq_passive_data {
 	/* Optional callback to decide the next frequency of passvice device */
 	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
 
+	/* Should set the type of parent device */
+	enum devfreq_parent_dev_type parent_type;
+
 	/* For passive governor's internal use. Don't need to set them */
 	struct devfreq *this;
 	struct notifier_block nb;
+	struct devfreq_cpu_data *parent_cpu_data[NR_CPUS];
 };
 #endif
 
-- 
cgit v1.2.3


From 26984d9d581e5049bd75091d2e789b9cc3ea12e0 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Wed, 27 Apr 2022 03:49:19 +0900
Subject: PM / devfreq: passive: Keep cpufreq_policy for possible cpus

The passive governor requires the cpu data to get the next target frequency
of devfreq device if depending on cpu. In order to reduce the unnecessary
memory data, keep cpufreq_policy data for possible cpus instead of NR_CPU.

Tested-by: Chen-Yu Tsai <wenst@chromium.org>
Tested-by: Johnson Wang <johnson.wang@mediatek.com>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/governor.h         |  3 ++
 drivers/devfreq/governor_passive.c | 75 ++++++++++++++++++++++++++++++--------
 include/linux/devfreq.h            |  4 +-
 3 files changed, 64 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index 335c4a491254..0adfebc0467a 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -49,6 +49,7 @@
 
 /**
  * struct devfreq_cpu_data - Hold the per-cpu data
+ * @node:	list node
  * @dev:	reference to cpu device.
  * @first_cpu:	the cpumask of the first cpu of a policy.
  * @opp_table:	reference to cpu opp table.
@@ -60,6 +61,8 @@
  * This is auto-populated by the governor.
  */
 struct devfreq_cpu_data {
+	struct list_head node;
+
 	struct device *dev;
 	unsigned int first_cpu;
 
diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c
index ffcce613a48c..7306e943a234 100644
--- a/drivers/devfreq/governor_passive.c
+++ b/drivers/devfreq/governor_passive.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+	// SPDX-License-Identifier: GPL-2.0-only
 /*
  * linux/drivers/devfreq/governor_passive.c
  *
@@ -18,6 +18,22 @@
 
 #define HZ_PER_KHZ	1000
 
+static struct devfreq_cpu_data *
+get_parent_cpu_data(struct devfreq_passive_data *p_data,
+		    struct cpufreq_policy *policy)
+{
+	struct devfreq_cpu_data *parent_cpu_data;
+
+	if (!p_data || !policy)
+		return NULL;
+
+	list_for_each_entry(parent_cpu_data, &p_data->cpu_data_list, node)
+		if (parent_cpu_data->first_cpu == cpumask_first(policy->related_cpus))
+			return parent_cpu_data;
+
+	return NULL;
+}
+
 static unsigned long get_target_freq_by_required_opp(struct device *p_dev,
 						struct opp_table *p_opp_table,
 						struct opp_table *opp_table,
@@ -51,14 +67,24 @@ static int get_target_freq_with_cpufreq(struct devfreq *devfreq,
 	struct devfreq_passive_data *p_data =
 				(struct devfreq_passive_data *)devfreq->data;
 	struct devfreq_cpu_data *parent_cpu_data;
+	struct cpufreq_policy *policy;
 	unsigned long cpu, cpu_cur, cpu_min, cpu_max, cpu_percent;
 	unsigned long dev_min, dev_max;
 	unsigned long freq = 0;
+	int ret = 0;
 
 	for_each_online_cpu(cpu) {
-		parent_cpu_data = p_data->parent_cpu_data[cpu];
-		if (!parent_cpu_data || parent_cpu_data->first_cpu != cpu)
+		policy = cpufreq_cpu_get(cpu);
+		if (!policy) {
+			ret = -EINVAL;
+			continue;
+		}
+
+		parent_cpu_data = get_parent_cpu_data(p_data, policy);
+		if (!parent_cpu_data) {
+			cpufreq_cpu_put(policy);
 			continue;
+		}
 
 		/* Get target freq via required opps */
 		cpu_cur = parent_cpu_data->cur_freq * HZ_PER_KHZ;
@@ -67,6 +93,7 @@ static int get_target_freq_with_cpufreq(struct devfreq *devfreq,
 					devfreq->opp_table, &cpu_cur);
 		if (freq) {
 			*target_freq = max(freq, *target_freq);
+			cpufreq_cpu_put(policy);
 			continue;
 		}
 
@@ -81,9 +108,10 @@ static int get_target_freq_with_cpufreq(struct devfreq *devfreq,
 		freq = dev_min + mult_frac(dev_max - dev_min, cpu_percent, 100);
 
 		*target_freq = max(freq, *target_freq);
+		cpufreq_cpu_put(policy);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int get_target_freq_with_devfreq(struct devfreq *devfreq,
@@ -168,12 +196,11 @@ static int cpufreq_passive_notifier_call(struct notifier_block *nb,
 	unsigned int cur_freq;
 	int ret;
 
-	if (event != CPUFREQ_POSTCHANGE || !freqs ||
-		!p_data->parent_cpu_data[freqs->policy->cpu])
+	if (event != CPUFREQ_POSTCHANGE || !freqs)
 		return 0;
 
-	parent_cpu_data = p_data->parent_cpu_data[freqs->policy->cpu];
-	if (parent_cpu_data->cur_freq == freqs->new)
+	parent_cpu_data = get_parent_cpu_data(p_data, freqs->policy);
+	if (!parent_cpu_data || parent_cpu_data->cur_freq == freqs->new)
 		return 0;
 
 	cur_freq = parent_cpu_data->cur_freq;
@@ -196,7 +223,7 @@ static int cpufreq_passive_unregister_notifier(struct devfreq *devfreq)
 	struct devfreq_passive_data *p_data
 			= (struct devfreq_passive_data *)devfreq->data;
 	struct devfreq_cpu_data *parent_cpu_data;
-	int cpu, ret;
+	int cpu, ret = 0;
 
 	if (p_data->nb.notifier_call) {
 		ret = cpufreq_unregister_notifier(&p_data->nb,
@@ -206,16 +233,26 @@ static int cpufreq_passive_unregister_notifier(struct devfreq *devfreq)
 	}
 
 	for_each_possible_cpu(cpu) {
-		parent_cpu_data = p_data->parent_cpu_data[cpu];
-		if (!parent_cpu_data)
+		struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+		if (!policy) {
+			ret = -EINVAL;
 			continue;
+		}
 
+		parent_cpu_data = get_parent_cpu_data(p_data, policy);
+		if (!parent_cpu_data) {
+			cpufreq_cpu_put(policy);
+			continue;
+		}
+
+		list_del(&parent_cpu_data->node);
 		if (parent_cpu_data->opp_table)
 			dev_pm_opp_put_opp_table(parent_cpu_data->opp_table);
 		kfree(parent_cpu_data);
+		cpufreq_cpu_put(policy);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int cpufreq_passive_register_notifier(struct devfreq *devfreq)
@@ -230,6 +267,9 @@ static int cpufreq_passive_register_notifier(struct devfreq *devfreq)
 	unsigned int cpu;
 	int ret;
 
+	p_data->cpu_data_list
+		= (struct list_head)LIST_HEAD_INIT(p_data->cpu_data_list);
+
 	p_data->nb.notifier_call = cpufreq_passive_notifier_call;
 	ret = cpufreq_register_notifier(&p_data->nb, CPUFREQ_TRANSITION_NOTIFIER);
 	if (ret) {
@@ -239,15 +279,18 @@ static int cpufreq_passive_register_notifier(struct devfreq *devfreq)
 	}
 
 	for_each_possible_cpu(cpu) {
-		if (p_data->parent_cpu_data[cpu])
-			continue;
-
 		policy = cpufreq_cpu_get(cpu);
 		if (!policy) {
 			ret = -EPROBE_DEFER;
 			goto err;
 		}
 
+		parent_cpu_data = get_parent_cpu_data(p_data, policy);
+		if (parent_cpu_data) {
+			cpufreq_cpu_put(policy);
+			continue;
+		}
+
 		parent_cpu_data = kzalloc(sizeof(*parent_cpu_data),
 						GFP_KERNEL);
 		if (!parent_cpu_data) {
@@ -276,7 +319,7 @@ static int cpufreq_passive_register_notifier(struct devfreq *devfreq)
 		parent_cpu_data->min_freq = policy->cpuinfo.min_freq;
 		parent_cpu_data->max_freq = policy->cpuinfo.max_freq;
 
-		p_data->parent_cpu_data[cpu] = parent_cpu_data;
+		list_add_tail(&parent_cpu_data->node, &p_data->cpu_data_list);
 		cpufreq_cpu_put(policy);
 	}
 
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index b1e4a6f796ce..dc10bee75a72 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -309,7 +309,7 @@ enum devfreq_parent_dev_type {
  * @this:		the devfreq instance of own device.
  * @nb:			the notifier block for DEVFREQ_TRANSITION_NOTIFIER or
  *			CPUFREQ_TRANSITION_NOTIFIER list.
- * @parent_cpu_data:	the state min/max/current frequency of all online cpu's.
+ * @cpu_data_list:	the list of cpu frequency data for all cpufreq_policy.
  *
  * The devfreq_passive_data have to set the devfreq instance of parent
  * device with governors except for the passive governor. But, don't need to
@@ -329,7 +329,7 @@ struct devfreq_passive_data {
 	/* For passive governor's internal use. Don't need to set them */
 	struct devfreq *this;
 	struct notifier_block nb;
-	struct devfreq_cpu_data *parent_cpu_data[NR_CPUS];
+	struct list_head cpu_data_list;
 };
 #endif
 
-- 
cgit v1.2.3


From 1ad6c3b7ef132e1d8c5d606008069724625c8daf Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Tue, 5 Apr 2022 11:24:51 +0200
Subject: hwmon: introduce hwmon_sanitize_name()

More and more drivers will check for bad characters in the hwmon name
and all are using the same code snippet. Consolidate that code by adding
a new hwmon_sanitize_name() function.

Signed-off-by: Michael Walle <michael@walle.cc>
Reviewed-by: Tom Rix <trix@redhat.com>
Link: https://lore.kernel.org/r/20220405092452.4033674-2-michael@walle.cc
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/hwmon-kernel-api.rst | 16 ++++++++++
 drivers/hwmon/hwmon.c                    | 53 ++++++++++++++++++++++++++++++++
 include/linux/hwmon.h                    |  3 ++
 3 files changed, 72 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/hwmon/hwmon-kernel-api.rst b/Documentation/hwmon/hwmon-kernel-api.rst
index c41eb6108103..e2975d5caf34 100644
--- a/Documentation/hwmon/hwmon-kernel-api.rst
+++ b/Documentation/hwmon/hwmon-kernel-api.rst
@@ -50,6 +50,10 @@ register/unregister functions::
 
   void devm_hwmon_device_unregister(struct device *dev);
 
+  char *hwmon_sanitize_name(const char *name);
+
+  char *devm_hwmon_sanitize_name(struct device *dev, const char *name);
+
 hwmon_device_register_with_groups registers a hardware monitoring device.
 The first parameter of this function is a pointer to the parent device.
 The name parameter is a pointer to the hwmon device name. The registration
@@ -95,6 +99,18 @@ All supported hwmon device registration functions only accept valid device
 names. Device names including invalid characters (whitespace, '*', or '-')
 will be rejected. The 'name' parameter is mandatory.
 
+If the driver doesn't use a static device name (for example it uses
+dev_name()), and therefore cannot make sure the name only contains valid
+characters, hwmon_sanitize_name can be used. This convenience function
+will duplicate the string and replace any invalid characters with an
+underscore. It will allocate memory for the new string and it is the
+responsibility of the caller to release the memory when the device is
+removed.
+
+devm_hwmon_sanitize_name is the resource managed version of
+hwmon_sanitize_name; the memory will be freed automatically on device
+removal.
+
 Using devm_hwmon_device_register_with_info()
 --------------------------------------------
 
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 989e2c8496dd..5915ccfdb7d9 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -1057,6 +1057,59 @@ void devm_hwmon_device_unregister(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(devm_hwmon_device_unregister);
 
+static char *__hwmon_sanitize_name(struct device *dev, const char *old_name)
+{
+	char *name, *p;
+
+	if (dev)
+		name = devm_kstrdup(dev, old_name, GFP_KERNEL);
+	else
+		name = kstrdup(old_name, GFP_KERNEL);
+	if (!name)
+		return ERR_PTR(-ENOMEM);
+
+	for (p = name; *p; p++)
+		if (hwmon_is_bad_char(*p))
+			*p = '_';
+
+	return name;
+}
+
+/**
+ * hwmon_sanitize_name - Replaces invalid characters in a hwmon name
+ * @name: NUL-terminated name
+ *
+ * Allocates a new string where any invalid characters will be replaced
+ * by an underscore. It is the responsibility of the caller to release
+ * the memory.
+ *
+ * Returns newly allocated name, or ERR_PTR on error.
+ */
+char *hwmon_sanitize_name(const char *name)
+{
+	return __hwmon_sanitize_name(NULL, name);
+}
+EXPORT_SYMBOL_GPL(hwmon_sanitize_name);
+
+/**
+ * devm_hwmon_sanitize_name - resource managed hwmon_sanitize_name()
+ * @dev: device to allocate memory for
+ * @name: NUL-terminated name
+ *
+ * Allocates a new string where any invalid characters will be replaced
+ * by an underscore.
+ *
+ * Returns newly allocated name, or ERR_PTR on error.
+ */
+char *devm_hwmon_sanitize_name(struct device *dev, const char *name)
+{
+	if (!dev)
+		return ERR_PTR(-EINVAL);
+
+	return __hwmon_sanitize_name(dev, name);
+}
+EXPORT_SYMBOL_GPL(devm_hwmon_sanitize_name);
+
 static void __init hwmon_pci_quirks(void)
 {
 #if defined CONFIG_X86 && defined CONFIG_PCI
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index eba380b76d15..4efaf06fd2b8 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -461,6 +461,9 @@ void devm_hwmon_device_unregister(struct device *dev);
 int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type,
 		       u32 attr, int channel);
 
+char *hwmon_sanitize_name(const char *name);
+char *devm_hwmon_sanitize_name(struct device *dev, const char *name);
+
 /**
  * hwmon_is_bad_char - Is the char invalid in a hwmon name
  * @ch: the char to be considered
-- 
cgit v1.2.3


From c8383054506c77b814489c09877b5db83fd4abf2 Mon Sep 17 00:00:00 2001
From: Jeffle Xu <jefflexu@linux.alibaba.com>
Date: Mon, 25 Apr 2022 20:21:24 +0800
Subject: cachefiles: notify the user daemon when looking up cookie

Fscache/CacheFiles used to serve as a local cache for a remote
networking fs. A new on-demand read mode will be introduced for
CacheFiles, which can boost the scenario where on-demand read semantics
are needed, e.g. container image distribution.

The essential difference between these two modes is seen when a cache
miss occurs: In the original mode, the netfs will fetch the data from
the remote server and then write it to the cache file; in on-demand
read mode, fetching the data and writing it into the cache is delegated
to a user daemon.

As the first step, notify the user daemon when looking up cookie. In
this case, an anonymous fd is sent to the user daemon, through which the
user daemon can write the fetched data to the cache file. Since the user
daemon may move the anonymous fd around, e.g. through dup(), an object
ID uniquely identifying the cache file is also attached.

Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that
the cache file size shall be retrieved at runtime. This helps the
scenario where one cache file contains multiple netfs files, e.g. for
the purpose of deduplication. In this case, netfs itself has no idea the
size of the cache file, whilst the user daemon should give the hint on
it.

Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/cachefiles/Kconfig             |  12 ++
 fs/cachefiles/Makefile            |   1 +
 fs/cachefiles/daemon.c            |  81 ++++++--
 fs/cachefiles/internal.h          |  51 +++++
 fs/cachefiles/namei.c             |  16 +-
 fs/cachefiles/ondemand.c          | 378 ++++++++++++++++++++++++++++++++++++++
 include/linux/fscache.h           |   1 +
 include/trace/events/cachefiles.h |   2 +
 include/uapi/linux/cachefiles.h   |  50 +++++
 9 files changed, 577 insertions(+), 15 deletions(-)
 create mode 100644 fs/cachefiles/ondemand.c
 create mode 100644 include/uapi/linux/cachefiles.h

(limited to 'include/linux')

diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig
index 719faeeda168..8df715640a48 100644
--- a/fs/cachefiles/Kconfig
+++ b/fs/cachefiles/Kconfig
@@ -26,3 +26,15 @@ config CACHEFILES_ERROR_INJECTION
 	help
 	  This permits error injection to be enabled in cachefiles whilst a
 	  cache is in service.
+
+config CACHEFILES_ONDEMAND
+	bool "Support for on-demand read"
+	depends on CACHEFILES
+	default n
+	help
+	  This permits userspace to enable the cachefiles on-demand read mode.
+	  In this mode, when a cache miss occurs, responsibility for fetching
+	  the data lies with the cachefiles backend instead of with the netfs
+	  and is delegated to userspace.
+
+	  If unsure, say N.
diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile
index 16d811f1a2fa..c37a7a9af10b 100644
--- a/fs/cachefiles/Makefile
+++ b/fs/cachefiles/Makefile
@@ -16,5 +16,6 @@ cachefiles-y := \
 	xattr.o
 
 cachefiles-$(CONFIG_CACHEFILES_ERROR_INJECTION) += error_inject.o
+cachefiles-$(CONFIG_CACHEFILES_ONDEMAND) += ondemand.o
 
 obj-$(CONFIG_CACHEFILES) := cachefiles.o
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 7ac04ee2c0a0..d5417da7f792 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -75,6 +75,9 @@ static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = {
 	{ "inuse",	cachefiles_daemon_inuse		},
 	{ "secctx",	cachefiles_daemon_secctx	},
 	{ "tag",	cachefiles_daemon_tag		},
+#ifdef CONFIG_CACHEFILES_ONDEMAND
+	{ "copen",	cachefiles_ondemand_copen	},
+#endif
 	{ "",		NULL				}
 };
 
@@ -108,6 +111,8 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file)
 	INIT_LIST_HEAD(&cache->volumes);
 	INIT_LIST_HEAD(&cache->object_list);
 	spin_lock_init(&cache->object_list_lock);
+	xa_init_flags(&cache->reqs, XA_FLAGS_ALLOC);
+	xa_init_flags(&cache->ondemand_ids, XA_FLAGS_ALLOC1);
 
 	/* set default caching limits
 	 * - limit at 1% free space and/or free files
@@ -126,6 +131,39 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static void cachefiles_flush_reqs(struct cachefiles_cache *cache)
+{
+	struct xarray *xa = &cache->reqs;
+	struct cachefiles_req *req;
+	unsigned long index;
+
+	/*
+	 * Make sure the following two operations won't be reordered.
+	 *   1) set CACHEFILES_DEAD bit
+	 *   2) flush requests in the xarray
+	 * Otherwise the request may be enqueued after xarray has been
+	 * flushed, leaving the orphan request never being completed.
+	 *
+	 * CPU 1			CPU 2
+	 * =====			=====
+	 * flush requests in the xarray
+	 *				test CACHEFILES_DEAD bit
+	 *				enqueue the request
+	 * set CACHEFILES_DEAD bit
+	 */
+	smp_mb();
+
+	xa_lock(xa);
+	xa_for_each(xa, index, req) {
+		req->error = -EIO;
+		complete(&req->done);
+	}
+	xa_unlock(xa);
+
+	xa_destroy(&cache->reqs);
+	xa_destroy(&cache->ondemand_ids);
+}
+
 /*
  * Release a cache.
  */
@@ -139,6 +177,8 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file)
 
 	set_bit(CACHEFILES_DEAD, &cache->flags);
 
+	if (cachefiles_in_ondemand_mode(cache))
+		cachefiles_flush_reqs(cache);
 	cachefiles_daemon_unbind(cache);
 
 	/* clean up the control file interface */
@@ -152,23 +192,14 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-/*
- * Read the cache state.
- */
-static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
-				      size_t buflen, loff_t *pos)
+static ssize_t cachefiles_do_daemon_read(struct cachefiles_cache *cache,
+					 char __user *_buffer, size_t buflen)
 {
-	struct cachefiles_cache *cache = file->private_data;
 	unsigned long long b_released;
 	unsigned f_released;
 	char buffer[256];
 	int n;
 
-	//_enter(",,%zu,", buflen);
-
-	if (!test_bit(CACHEFILES_READY, &cache->flags))
-		return 0;
-
 	/* check how much space the cache has */
 	cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check);
 
@@ -206,6 +237,25 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 	return n;
 }
 
+/*
+ * Read the cache state.
+ */
+static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
+				      size_t buflen, loff_t *pos)
+{
+	struct cachefiles_cache *cache = file->private_data;
+
+	//_enter(",,%zu,", buflen);
+
+	if (!test_bit(CACHEFILES_READY, &cache->flags))
+		return 0;
+
+	if (cachefiles_in_ondemand_mode(cache))
+		return cachefiles_ondemand_daemon_read(cache, _buffer, buflen);
+	else
+		return cachefiles_do_daemon_read(cache, _buffer, buflen);
+}
+
 /*
  * Take a command from cachefilesd, parse it and act on it.
  */
@@ -297,8 +347,13 @@ static __poll_t cachefiles_daemon_poll(struct file *file,
 	poll_wait(file, &cache->daemon_pollwq, poll);
 	mask = 0;
 
-	if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))
-		mask |= EPOLLIN;
+	if (cachefiles_in_ondemand_mode(cache)) {
+		if (!xa_empty(&cache->reqs))
+			mask |= EPOLLIN;
+	} else {
+		if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))
+			mask |= EPOLLIN;
+	}
 
 	if (test_bit(CACHEFILES_CULLING, &cache->flags))
 		mask |= EPOLLOUT;
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index e80673d0ab97..4f5150a96849 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -15,6 +15,8 @@
 #include <linux/fscache-cache.h>
 #include <linux/cred.h>
 #include <linux/security.h>
+#include <linux/xarray.h>
+#include <linux/cachefiles.h>
 
 #define CACHEFILES_DIO_BLOCK_SIZE 4096
 
@@ -58,8 +60,13 @@ struct cachefiles_object {
 	enum cachefiles_content		content_info:8;	/* Info about content presence */
 	unsigned long			flags;
 #define CACHEFILES_OBJECT_USING_TMPFILE	0		/* Have an unlinked tmpfile */
+#ifdef CONFIG_CACHEFILES_ONDEMAND
+	int				ondemand_id;
+#endif
 };
 
+#define CACHEFILES_ONDEMAND_ID_CLOSED	-1
+
 /*
  * Cache files cache definition
  */
@@ -98,11 +105,30 @@ struct cachefiles_cache {
 #define CACHEFILES_DEAD			1	/* T if cache dead */
 #define CACHEFILES_CULLING		2	/* T if cull engaged */
 #define CACHEFILES_STATE_CHANGED	3	/* T if state changed (poll trigger) */
+#define CACHEFILES_ONDEMAND_MODE	4	/* T if in on-demand read mode */
 	char				*rootdirname;	/* name of cache root directory */
 	char				*secctx;	/* LSM security context */
 	char				*tag;		/* cache binding tag */
+	struct xarray			reqs;		/* xarray of pending on-demand requests */
+	struct xarray			ondemand_ids;	/* xarray for ondemand_id allocation */
+	u32				ondemand_id_next;
 };
 
+static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache)
+{
+	return IS_ENABLED(CONFIG_CACHEFILES_ONDEMAND) &&
+		test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags);
+}
+
+struct cachefiles_req {
+	struct cachefiles_object *object;
+	struct completion done;
+	int error;
+	struct cachefiles_msg msg;
+};
+
+#define CACHEFILES_REQ_NEW	XA_MARK_1
+
 #include <trace/events/cachefiles.h>
 
 static inline
@@ -250,6 +276,31 @@ extern struct file *cachefiles_create_tmpfile(struct cachefiles_object *object);
 extern bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache,
 				      struct cachefiles_object *object);
 
+/*
+ * ondemand.c
+ */
+#ifdef CONFIG_CACHEFILES_ONDEMAND
+extern ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
+					char __user *_buffer, size_t buflen);
+
+extern int cachefiles_ondemand_copen(struct cachefiles_cache *cache,
+				     char *args);
+
+extern int cachefiles_ondemand_init_object(struct cachefiles_object *object);
+
+#else
+static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
+					char __user *_buffer, size_t buflen)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int cachefiles_ondemand_init_object(struct cachefiles_object *object)
+{
+	return 0;
+}
+#endif
+
 /*
  * security.c
  */
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ca9f3e4ec4b3..facf2ebe464b 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -452,10 +452,9 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object)
 	struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash];
 	struct file *file;
 	struct path path;
-	uint64_t ni_size = object->cookie->object_size;
+	uint64_t ni_size;
 	long ret;
 
-	ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE);
 
 	cachefiles_begin_secure(cache, &saved_cred);
 
@@ -481,6 +480,15 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object)
 		goto out_dput;
 	}
 
+	ret = cachefiles_ondemand_init_object(object);
+	if (ret < 0) {
+		file = ERR_PTR(ret);
+		goto out_unuse;
+	}
+
+	ni_size = object->cookie->object_size;
+	ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE);
+
 	if (ni_size > 0) {
 		trace_cachefiles_trunc(object, d_backing_inode(path.dentry), 0, ni_size,
 				       cachefiles_trunc_expand_tmpfile);
@@ -586,6 +594,10 @@ static bool cachefiles_open_file(struct cachefiles_object *object,
 	}
 	_debug("file -> %pd positive", dentry);
 
+	ret = cachefiles_ondemand_init_object(object);
+	if (ret < 0)
+		goto error_fput;
+
 	ret = cachefiles_check_auxdata(object, file);
 	if (ret < 0)
 		goto check_failed;
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
new file mode 100644
index 000000000000..64fc312b16d3
--- /dev/null
+++ b/fs/cachefiles/ondemand.c
@@ -0,0 +1,378 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/fdtable.h>
+#include <linux/anon_inodes.h>
+#include <linux/uio.h>
+#include "internal.h"
+
+static int cachefiles_ondemand_fd_release(struct inode *inode,
+					  struct file *file)
+{
+	struct cachefiles_object *object = file->private_data;
+	struct cachefiles_cache *cache = object->volume->cache;
+	int object_id = object->ondemand_id;
+
+	object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED;
+	xa_erase(&cache->ondemand_ids, object_id);
+	cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd);
+	return 0;
+}
+
+static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb,
+						 struct iov_iter *iter)
+{
+	struct cachefiles_object *object = kiocb->ki_filp->private_data;
+	struct cachefiles_cache *cache = object->volume->cache;
+	struct file *file = object->file;
+	size_t len = iter->count;
+	loff_t pos = kiocb->ki_pos;
+	const struct cred *saved_cred;
+	int ret;
+
+	if (!file)
+		return -ENOBUFS;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = __cachefiles_prepare_write(object, file, &pos, &len, true);
+	cachefiles_end_secure(cache, saved_cred);
+	if (ret < 0)
+		return ret;
+
+	ret = __cachefiles_write(object, file, pos, iter, NULL, NULL);
+	if (!ret)
+		ret = len;
+
+	return ret;
+}
+
+static loff_t cachefiles_ondemand_fd_llseek(struct file *filp, loff_t pos,
+					    int whence)
+{
+	struct cachefiles_object *object = filp->private_data;
+	struct file *file = object->file;
+
+	if (!file)
+		return -ENOBUFS;
+
+	return vfs_llseek(file, pos, whence);
+}
+
+static const struct file_operations cachefiles_ondemand_fd_fops = {
+	.owner		= THIS_MODULE,
+	.release	= cachefiles_ondemand_fd_release,
+	.write_iter	= cachefiles_ondemand_fd_write_iter,
+	.llseek		= cachefiles_ondemand_fd_llseek,
+};
+
+/*
+ * OPEN request Completion (copen)
+ * - command: "copen <id>,<cache_size>"
+ *   <cache_size> indicates the object size if >=0, error code if negative
+ */
+int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
+{
+	struct cachefiles_req *req;
+	struct fscache_cookie *cookie;
+	char *pid, *psize;
+	unsigned long id;
+	long size;
+	int ret;
+
+	if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags))
+		return -EOPNOTSUPP;
+
+	if (!*args) {
+		pr_err("Empty id specified\n");
+		return -EINVAL;
+	}
+
+	pid = args;
+	psize = strchr(args, ',');
+	if (!psize) {
+		pr_err("Cache size is not specified\n");
+		return -EINVAL;
+	}
+
+	*psize = 0;
+	psize++;
+
+	ret = kstrtoul(pid, 0, &id);
+	if (ret)
+		return ret;
+
+	req = xa_erase(&cache->reqs, id);
+	if (!req)
+		return -EINVAL;
+
+	/* fail OPEN request if copen format is invalid */
+	ret = kstrtol(psize, 0, &size);
+	if (ret) {
+		req->error = ret;
+		goto out;
+	}
+
+	/* fail OPEN request if daemon reports an error */
+	if (size < 0) {
+		if (!IS_ERR_VALUE(size))
+			size = -EINVAL;
+		req->error = size;
+		goto out;
+	}
+
+	cookie = req->object->cookie;
+	cookie->object_size = size;
+	if (size)
+		clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags);
+	else
+		set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags);
+
+out:
+	complete(&req->done);
+	return ret;
+}
+
+static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct cachefiles_open *load;
+	struct file *file;
+	u32 object_id;
+	int ret, fd;
+
+	object = cachefiles_grab_object(req->object,
+			cachefiles_obj_get_ondemand_fd);
+	cache = object->volume->cache;
+
+	ret = xa_alloc_cyclic(&cache->ondemand_ids, &object_id, NULL,
+			      XA_LIMIT(1, INT_MAX),
+			      &cache->ondemand_id_next, GFP_KERNEL);
+	if (ret < 0)
+		goto err;
+
+	fd = get_unused_fd_flags(O_WRONLY);
+	if (fd < 0) {
+		ret = fd;
+		goto err_free_id;
+	}
+
+	file = anon_inode_getfile("[cachefiles]", &cachefiles_ondemand_fd_fops,
+				  object, O_WRONLY);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto err_put_fd;
+	}
+
+	file->f_mode |= FMODE_PWRITE | FMODE_LSEEK;
+	fd_install(fd, file);
+
+	load = (void *)req->msg.data;
+	load->fd = fd;
+	req->msg.object_id = object_id;
+	object->ondemand_id = object_id;
+	return 0;
+
+err_put_fd:
+	put_unused_fd(fd);
+err_free_id:
+	xa_erase(&cache->ondemand_ids, object_id);
+err:
+	cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd);
+	return ret;
+}
+
+ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
+					char __user *_buffer, size_t buflen)
+{
+	struct cachefiles_req *req;
+	struct cachefiles_msg *msg;
+	unsigned long id = 0;
+	size_t n;
+	int ret = 0;
+	XA_STATE(xas, &cache->reqs, 0);
+
+	/*
+	 * Search for a request that has not ever been processed, to prevent
+	 * requests from being processed repeatedly.
+	 */
+	xa_lock(&cache->reqs);
+	req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW);
+	if (!req) {
+		xa_unlock(&cache->reqs);
+		return 0;
+	}
+
+	msg = &req->msg;
+	n = msg->len;
+
+	if (n > buflen) {
+		xa_unlock(&cache->reqs);
+		return -EMSGSIZE;
+	}
+
+	xas_clear_mark(&xas, CACHEFILES_REQ_NEW);
+	xa_unlock(&cache->reqs);
+
+	id = xas.xa_index;
+	msg->msg_id = id;
+
+	if (msg->opcode == CACHEFILES_OP_OPEN) {
+		ret = cachefiles_ondemand_get_fd(req);
+		if (ret)
+			goto error;
+	}
+
+	if (copy_to_user(_buffer, msg, n) != 0) {
+		ret = -EFAULT;
+		goto err_put_fd;
+	}
+
+	return n;
+
+err_put_fd:
+	if (msg->opcode == CACHEFILES_OP_OPEN)
+		close_fd(((struct cachefiles_open *)msg->data)->fd);
+error:
+	xa_erase(&cache->reqs, id);
+	req->error = ret;
+	complete(&req->done);
+	return ret;
+}
+
+typedef int (*init_req_fn)(struct cachefiles_req *req, void *private);
+
+static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
+					enum cachefiles_opcode opcode,
+					size_t data_len,
+					init_req_fn init_req,
+					void *private)
+{
+	struct cachefiles_cache *cache = object->volume->cache;
+	struct cachefiles_req *req;
+	XA_STATE(xas, &cache->reqs, 0);
+	int ret;
+
+	if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags))
+		return 0;
+
+	if (test_bit(CACHEFILES_DEAD, &cache->flags))
+		return -EIO;
+
+	req = kzalloc(sizeof(*req) + data_len, GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	req->object = object;
+	init_completion(&req->done);
+	req->msg.opcode = opcode;
+	req->msg.len = sizeof(struct cachefiles_msg) + data_len;
+
+	ret = init_req(req, private);
+	if (ret)
+		goto out;
+
+	do {
+		/*
+		 * Stop enqueuing the request when daemon is dying. The
+		 * following two operations need to be atomic as a whole.
+		 *   1) check cache state, and
+		 *   2) enqueue request if cache is alive.
+		 * Otherwise the request may be enqueued after xarray has been
+		 * flushed, leaving the orphan request never being completed.
+		 *
+		 * CPU 1			CPU 2
+		 * =====			=====
+		 *				test CACHEFILES_DEAD bit
+		 * set CACHEFILES_DEAD bit
+		 * flush requests in the xarray
+		 *				enqueue the request
+		 */
+		xas_lock(&xas);
+
+		if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
+			xas_unlock(&xas);
+			ret = -EIO;
+			goto out;
+		}
+
+		/* coupled with the barrier in cachefiles_flush_reqs() */
+		smp_mb();
+
+		xas.xa_index = 0;
+		xas_find_marked(&xas, UINT_MAX, XA_FREE_MARK);
+		if (xas.xa_node == XAS_RESTART)
+			xas_set_err(&xas, -EBUSY);
+		xas_store(&xas, req);
+		xas_clear_mark(&xas, XA_FREE_MARK);
+		xas_set_mark(&xas, CACHEFILES_REQ_NEW);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, GFP_KERNEL));
+
+	ret = xas_error(&xas);
+	if (ret)
+		goto out;
+
+	wake_up_all(&cache->daemon_pollwq);
+	wait_for_completion(&req->done);
+	ret = req->error;
+out:
+	kfree(req);
+	return ret;
+}
+
+static int cachefiles_ondemand_init_open_req(struct cachefiles_req *req,
+					     void *private)
+{
+	struct cachefiles_object *object = req->object;
+	struct fscache_cookie *cookie = object->cookie;
+	struct fscache_volume *volume = object->volume->vcookie;
+	struct cachefiles_open *load = (void *)req->msg.data;
+	size_t volume_key_size, cookie_key_size;
+	void *volume_key, *cookie_key;
+
+	/*
+	 * Volume key is a NUL-terminated string. key[0] stores strlen() of the
+	 * string, followed by the content of the string (excluding '\0').
+	 */
+	volume_key_size = volume->key[0] + 1;
+	volume_key = volume->key + 1;
+
+	/* Cookie key is binary data, which is netfs specific. */
+	cookie_key_size = cookie->key_len;
+	cookie_key = fscache_get_key(cookie);
+
+	if (!(object->cookie->advice & FSCACHE_ADV_WANT_CACHE_SIZE)) {
+		pr_err("WANT_CACHE_SIZE is needed for on-demand mode\n");
+		return -EINVAL;
+	}
+
+	load->volume_key_size = volume_key_size;
+	load->cookie_key_size = cookie_key_size;
+	memcpy(load->data, volume_key, volume_key_size);
+	memcpy(load->data + volume_key_size, cookie_key, cookie_key_size);
+
+	return 0;
+}
+
+int cachefiles_ondemand_init_object(struct cachefiles_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+	struct fscache_volume *volume = object->volume->vcookie;
+	size_t volume_key_size, cookie_key_size, data_len;
+
+	/*
+	 * CacheFiles will firstly check the cache file under the root cache
+	 * directory. If the coherency check failed, it will fallback to
+	 * creating a new tmpfile as the cache file. Reuse the previously
+	 * allocated object ID if any.
+	 */
+	if (object->ondemand_id > 0)
+		return 0;
+
+	volume_key_size = volume->key[0] + 1;
+	cookie_key_size = cookie->key_len;
+	data_len = sizeof(struct cachefiles_open) +
+		   volume_key_size + cookie_key_size;
+
+	return cachefiles_ondemand_send_req(object, CACHEFILES_OP_OPEN,
+			data_len, cachefiles_ondemand_init_open_req, NULL);
+}
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index e25539072463..72585c9729a2 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -39,6 +39,7 @@ struct fscache_cookie;
 #define FSCACHE_ADV_SINGLE_CHUNK	0x01 /* The object is a single chunk of data */
 #define FSCACHE_ADV_WRITE_CACHE		0x00 /* Do cache if written to locally */
 #define FSCACHE_ADV_WRITE_NOCACHE	0x02 /* Don't cache if written to locally */
+#define FSCACHE_ADV_WANT_CACHE_SIZE	0x04 /* Retrieve cache size at runtime */
 
 #define FSCACHE_INVAL_DIO_WRITE		0x01 /* Invalidate due to DIO write */
 
diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h
index 311c14a20e70..93df9391bd7f 100644
--- a/include/trace/events/cachefiles.h
+++ b/include/trace/events/cachefiles.h
@@ -31,6 +31,8 @@ enum cachefiles_obj_ref_trace {
 	cachefiles_obj_see_lookup_failed,
 	cachefiles_obj_see_withdraw_cookie,
 	cachefiles_obj_see_withdrawal,
+	cachefiles_obj_get_ondemand_fd,
+	cachefiles_obj_put_ondemand_fd,
 };
 
 enum fscache_why_object_killed {
diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h
new file mode 100644
index 000000000000..521f2fe4fe9c
--- /dev/null
+++ b/include/uapi/linux/cachefiles.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_CACHEFILES_H
+#define _LINUX_CACHEFILES_H
+
+#include <linux/types.h>
+
+/*
+ * Fscache ensures that the maximum length of cookie key is 255. The volume key
+ * is controlled by netfs, and generally no bigger than 255.
+ */
+#define CACHEFILES_MSG_MAX_SIZE	1024
+
+enum cachefiles_opcode {
+	CACHEFILES_OP_OPEN,
+};
+
+/*
+ * Message Header
+ *
+ * @msg_id	a unique ID identifying this message
+ * @opcode	message type, CACHEFILE_OP_*
+ * @len		message length, including message header and following data
+ * @object_id	a unique ID identifying a cache file
+ * @data	message type specific payload
+ */
+struct cachefiles_msg {
+	__u32 msg_id;
+	__u32 opcode;
+	__u32 len;
+	__u32 object_id;
+	__u8  data[];
+};
+
+/*
+ * @data contains the volume_key followed directly by the cookie_key. volume_key
+ * is a NUL-terminated string; @volume_key_size indicates the size of the volume
+ * key in bytes. cookie_key is binary data, which is netfs specific;
+ * @cookie_key_size indicates the size of the cookie key in bytes.
+ *
+ * @fd identifies an anon_fd referring to the cache file.
+ */
+struct cachefiles_open {
+	__u32 volume_key_size;
+	__u32 cookie_key_size;
+	__u32 fd;
+	__u32 flags;
+	__u8  data[];
+};
+
+#endif
-- 
cgit v1.2.3


From 9032b6e8589f269743984aac53e82e4835be16dc Mon Sep 17 00:00:00 2001
From: Jeffle Xu <jefflexu@linux.alibaba.com>
Date: Mon, 25 Apr 2022 20:21:27 +0800
Subject: cachefiles: implement on-demand read

Implement the data plane of on-demand read mode.

The early implementation [1] place the entry to
cachefiles_ondemand_read() in fscache_read(). However, fscache_read()
can only detect if the requested file range is fully cache miss, whilst
we need to notify the user daemon as long as there's a hole inside the
requested file range.

Thus the entry is now placed in cachefiles_prepare_read(). When working
in on-demand read mode, once a hole detected, the read routine will send
a READ request to the user daemon. The user daemon needs to fetch the
data and write it to the cache file. After sending the READ request, the
read routine will hang there, until the READ request is handled by the
user daemon. Then it will retry to read from the same file range. If no
progress encountered, the read routine will fail then.

A new NETFS_SREQ_ONDEMAND flag is introduced to indicate that on-demand
read should be done when a cache miss encountered.

[1] https://lore.kernel.org/all/20220406075612.60298-6-jefflexu@linux.alibaba.com/ #v8

Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
Acked-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20220425122143.56815-6-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/cachefiles/internal.h        |  9 +++++
 fs/cachefiles/io.c              | 15 ++++++--
 fs/cachefiles/ondemand.c        | 77 +++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h           |  1 +
 include/uapi/linux/cachefiles.h | 17 +++++++++
 5 files changed, 117 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index da388ba127eb..6cba2c6de2f9 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -292,6 +292,9 @@ extern int cachefiles_ondemand_copen(struct cachefiles_cache *cache,
 extern int cachefiles_ondemand_init_object(struct cachefiles_object *object);
 extern void cachefiles_ondemand_clean_object(struct cachefiles_object *object);
 
+extern int cachefiles_ondemand_read(struct cachefiles_object *object,
+				    loff_t pos, size_t len);
+
 #else
 static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 					char __user *_buffer, size_t buflen)
@@ -307,6 +310,12 @@ static inline int cachefiles_ondemand_init_object(struct cachefiles_object *obje
 static inline void cachefiles_ondemand_clean_object(struct cachefiles_object *object)
 {
 }
+
+static inline int cachefiles_ondemand_read(struct cachefiles_object *object,
+					   loff_t pos, size_t len)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 /*
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 50a14e8f0aac..000a28f46e59 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -403,6 +403,7 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *
 	enum netfs_io_source ret = NETFS_DOWNLOAD_FROM_SERVER;
 	loff_t off, to;
 	ino_t ino = file ? file_inode(file)->i_ino : 0;
+	int rc;
 
 	_enter("%zx @%llx/%llx", subreq->len, subreq->start, i_size);
 
@@ -415,7 +416,8 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *
 	if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) {
 		__set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
 		why = cachefiles_trace_read_no_data;
-		goto out_no_object;
+		if (!test_bit(NETFS_SREQ_ONDEMAND, &subreq->flags))
+			goto out_no_object;
 	}
 
 	/* The object and the file may be being created in the background. */
@@ -432,7 +434,7 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *
 	object = cachefiles_cres_object(cres);
 	cache = object->volume->cache;
 	cachefiles_begin_secure(cache, &saved_cred);
-
+retry:
 	off = cachefiles_inject_read_error();
 	if (off == 0)
 		off = vfs_llseek(file, subreq->start, SEEK_DATA);
@@ -483,6 +485,15 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *
 
 download_and_store:
 	__set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
+	if (test_bit(NETFS_SREQ_ONDEMAND, &subreq->flags)) {
+		rc = cachefiles_ondemand_read(object, subreq->start,
+					      subreq->len);
+		if (!rc) {
+			__clear_bit(NETFS_SREQ_ONDEMAND, &subreq->flags);
+			goto retry;
+		}
+		ret = NETFS_INVALID_READ;
+	}
 out:
 	cachefiles_end_secure(cache, saved_cred);
 out_no_object:
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 11b1c15ac697..3470d4e8f0cb 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -10,8 +10,25 @@ static int cachefiles_ondemand_fd_release(struct inode *inode,
 	struct cachefiles_object *object = file->private_data;
 	struct cachefiles_cache *cache = object->volume->cache;
 	int object_id = object->ondemand_id;
+	struct cachefiles_req *req;
+	XA_STATE(xas, &cache->reqs, 0);
 
+	xa_lock(&cache->reqs);
 	object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED;
+
+	/*
+	 * Flush all pending READ requests since their completion depends on
+	 * anon_fd.
+	 */
+	xas_for_each(&xas, req, ULONG_MAX) {
+		if (req->msg.opcode == CACHEFILES_OP_READ) {
+			req->error = -EIO;
+			complete(&req->done);
+			xas_store(&xas, NULL);
+		}
+	}
+	xa_unlock(&cache->reqs);
+
 	xa_erase(&cache->ondemand_ids, object_id);
 	cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd);
 	cachefiles_put_unbind_pincount(cache);
@@ -57,11 +74,35 @@ static loff_t cachefiles_ondemand_fd_llseek(struct file *filp, loff_t pos,
 	return vfs_llseek(file, pos, whence);
 }
 
+static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl,
+					 unsigned long arg)
+{
+	struct cachefiles_object *object = filp->private_data;
+	struct cachefiles_cache *cache = object->volume->cache;
+	struct cachefiles_req *req;
+	unsigned long id;
+
+	if (ioctl != CACHEFILES_IOC_READ_COMPLETE)
+		return -EINVAL;
+
+	if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags))
+		return -EOPNOTSUPP;
+
+	id = arg;
+	req = xa_erase(&cache->reqs, id);
+	if (!req)
+		return -EINVAL;
+
+	complete(&req->done);
+	return 0;
+}
+
 static const struct file_operations cachefiles_ondemand_fd_fops = {
 	.owner		= THIS_MODULE,
 	.release	= cachefiles_ondemand_fd_release,
 	.write_iter	= cachefiles_ondemand_fd_write_iter,
 	.llseek		= cachefiles_ondemand_fd_llseek,
+	.unlocked_ioctl	= cachefiles_ondemand_fd_ioctl,
 };
 
 /*
@@ -388,6 +429,32 @@ static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req,
 	return 0;
 }
 
+struct cachefiles_read_ctx {
+	loff_t off;
+	size_t len;
+};
+
+static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req,
+					     void *private)
+{
+	struct cachefiles_object *object = req->object;
+	struct cachefiles_read *load = (void *)req->msg.data;
+	struct cachefiles_read_ctx *read_ctx = private;
+	int object_id = object->ondemand_id;
+
+	/* Stop enqueuing requests when daemon has closed anon_fd. */
+	if (object_id <= 0) {
+		WARN_ON_ONCE(object_id == 0);
+		pr_info_once("READ: anonymous fd closed prematurely.\n");
+		return -EIO;
+	}
+
+	req->msg.object_id = object_id;
+	load->off = read_ctx->off;
+	load->len = read_ctx->len;
+	return 0;
+}
+
 int cachefiles_ondemand_init_object(struct cachefiles_object *object)
 {
 	struct fscache_cookie *cookie = object->cookie;
@@ -417,3 +484,13 @@ void cachefiles_ondemand_clean_object(struct cachefiles_object *object)
 	cachefiles_ondemand_send_req(object, CACHEFILES_OP_CLOSE, 0,
 			cachefiles_ondemand_init_close_req, NULL);
 }
+
+int cachefiles_ondemand_read(struct cachefiles_object *object,
+			     loff_t pos, size_t len)
+{
+	struct cachefiles_read_ctx read_ctx = {pos, len};
+
+	return cachefiles_ondemand_send_req(object, CACHEFILES_OP_READ,
+			sizeof(struct cachefiles_read),
+			cachefiles_ondemand_init_read_req, &read_ctx);
+}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index c7bf1eaf51d5..057d04efaf79 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -159,6 +159,7 @@ struct netfs_io_subrequest {
 #define NETFS_SREQ_SHORT_IO		2	/* Set if the I/O was short */
 #define NETFS_SREQ_SEEK_DATA_READ	3	/* Set if ->read() should SEEK_DATA first */
 #define NETFS_SREQ_NO_PROGRESS		4	/* Set if we didn't manage to read any data */
+#define NETFS_SREQ_ONDEMAND		5	/* Set if it's from on-demand read mode */
 };
 
 enum netfs_io_origin {
diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h
index 37a0071037c8..78caa73e5343 100644
--- a/include/uapi/linux/cachefiles.h
+++ b/include/uapi/linux/cachefiles.h
@@ -3,6 +3,7 @@
 #define _LINUX_CACHEFILES_H
 
 #include <linux/types.h>
+#include <linux/ioctl.h>
 
 /*
  * Fscache ensures that the maximum length of cookie key is 255. The volume key
@@ -13,6 +14,7 @@
 enum cachefiles_opcode {
 	CACHEFILES_OP_OPEN,
 	CACHEFILES_OP_CLOSE,
+	CACHEFILES_OP_READ,
 };
 
 /*
@@ -48,4 +50,19 @@ struct cachefiles_open {
 	__u8  data[];
 };
 
+/*
+ * @off		indicates the starting offset of the requested file range
+ * @len		indicates the length of the requested file range
+ */
+struct cachefiles_read {
+	__u64 off;
+	__u64 len;
+};
+
+/*
+ * Reply for READ request
+ * @arg for this ioctl is the @id field of READ request.
+ */
+#define CACHEFILES_IOC_READ_COMPLETE	_IOW(0x98, 1, int)
+
 #endif
-- 
cgit v1.2.3


From 7b8b44eb7710e34a1ea5278392417993a549fabf Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 14 May 2022 10:36:58 -0400
Subject: NFSv4: Specify the type of ACL to cache

When caching a NFSv4 ACL, we want to specify whether we are caching an
NFSv4.0 type acl, the NFSv4.1 dacl or the NFSv4.1 sacl.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       | 59 +++++++++++++++++++++++++++++++++----------------
 include/linux/nfs4.h    |  2 ++
 include/linux/nfs_xdr.h |  7 ++++++
 3 files changed, 49 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index bf3ba541b9fb..e6c830d4db0b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5772,9 +5772,17 @@ static int nfs4_proc_renew(struct nfs_client *clp, const struct cred *cred)
 	return 0;
 }
 
-static inline int nfs4_server_supports_acls(struct nfs_server *server)
+static bool nfs4_server_supports_acls(const struct nfs_server *server,
+				      enum nfs4_acl_type type)
 {
-	return server->caps & NFS_CAP_ACLS;
+	switch (type) {
+	default:
+		return server->attr_bitmask[0] & FATTR4_WORD0_ACL;
+	case NFS4ACL_DACL:
+		return server->attr_bitmask[1] & FATTR4_WORD1_DACL;
+	case NFS4ACL_SACL:
+		return server->attr_bitmask[1] & FATTR4_WORD1_SACL;
+	}
 }
 
 /* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that
@@ -5813,6 +5821,7 @@ unwind:
 }
 
 struct nfs4_cached_acl {
+	enum nfs4_acl_type type;
 	int cached;
 	size_t len;
 	char data[];
@@ -5833,7 +5842,8 @@ static void nfs4_zap_acl_attr(struct inode *inode)
 	nfs4_set_cached_acl(inode, NULL);
 }
 
-static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_t buflen)
+static ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf,
+				    size_t buflen, enum nfs4_acl_type type)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs4_cached_acl *acl;
@@ -5843,6 +5853,8 @@ static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_
 	acl = nfsi->nfs4_acl;
 	if (acl == NULL)
 		goto out;
+	if (acl->type != type)
+		goto out;
 	if (buf == NULL) /* user is just asking for length */
 		goto out_len;
 	if (acl->cached == 0)
@@ -5858,7 +5870,9 @@ out:
 	return ret;
 }
 
-static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len)
+static void nfs4_write_cached_acl(struct inode *inode, struct page **pages,
+				  size_t pgbase, size_t acl_len,
+				  enum nfs4_acl_type type)
 {
 	struct nfs4_cached_acl *acl;
 	size_t buflen = sizeof(*acl) + acl_len;
@@ -5875,6 +5889,7 @@ static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size
 			goto out;
 		acl->cached = 0;
 	}
+	acl->type = type;
 	acl->len = acl_len;
 out:
 	nfs4_set_cached_acl(inode, acl);
@@ -5890,7 +5905,8 @@ out:
  * length. The next getxattr call will then produce another round trip to
  * the server, this time with the input buf of the required size.
  */
-static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
+static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf,
+				       size_t buflen, enum nfs4_acl_type type)
 {
 	struct page **pages;
 	struct nfs_getaclargs args = {
@@ -5947,7 +5963,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		ret = -ERANGE;
 		goto out_free;
 	}
-	nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len);
+	nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len,
+			      type);
 	if (buf) {
 		if (res.acl_len > buflen) {
 			ret = -ERANGE;
@@ -5967,14 +5984,15 @@ out_free:
 	return ret;
 }
 
-static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
+static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf,
+				     size_t buflen, enum nfs4_acl_type type)
 {
 	struct nfs4_exception exception = {
 		.interruptible = true,
 	};
 	ssize_t ret;
 	do {
-		ret = __nfs4_get_acl_uncached(inode, buf, buflen);
+		ret = __nfs4_get_acl_uncached(inode, buf, buflen, type);
 		trace_nfs4_get_acl(inode, ret);
 		if (ret >= 0)
 			break;
@@ -5983,27 +6001,29 @@ static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bufl
 	return ret;
 }
 
-static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
+static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen,
+				 enum nfs4_acl_type type)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	int ret;
 
-	if (!nfs4_server_supports_acls(server))
+	if (!nfs4_server_supports_acls(server, type))
 		return -EOPNOTSUPP;
 	ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
 	if (ret < 0)
 		return ret;
 	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
 		nfs_zap_acl_cache(inode);
-	ret = nfs4_read_cached_acl(inode, buf, buflen);
+	ret = nfs4_read_cached_acl(inode, buf, buflen, type);
 	if (ret != -ENOENT)
 		/* -ENOENT is returned if there is no ACL or if there is an ACL
 		 * but no cached acl data, just the acl length */
 		return ret;
-	return nfs4_get_acl_uncached(inode, buf, buflen);
+	return nfs4_get_acl_uncached(inode, buf, buflen, type);
 }
 
-static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen)
+static int __nfs4_proc_set_acl(struct inode *inode, const void *buf,
+			       size_t buflen, enum nfs4_acl_type type)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct page *pages[NFS4ACL_MAXPAGES];
@@ -6024,7 +6044,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	/* You can't remove system.nfs4_acl: */
 	if (buflen == 0)
 		return -EINVAL;
-	if (!nfs4_server_supports_acls(server))
+	if (!nfs4_server_supports_acls(server, type))
 		return -EOPNOTSUPP;
 	if (npages > ARRAY_SIZE(pages))
 		return -ERANGE;
@@ -6055,12 +6075,13 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	return ret;
 }
 
-static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen)
+static int nfs4_proc_set_acl(struct inode *inode, const void *buf,
+			     size_t buflen, enum nfs4_acl_type type)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
-		err = __nfs4_proc_set_acl(inode, buf, buflen);
+		err = __nfs4_proc_set_acl(inode, buf, buflen, type);
 		trace_nfs4_set_acl(inode, err);
 		if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) {
 			/*
@@ -7659,19 +7680,19 @@ static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler,
 				   const char *key, const void *buf,
 				   size_t buflen, int flags)
 {
-	return nfs4_proc_set_acl(inode, buf, buflen);
+	return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_ACL);
 }
 
 static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler,
 				   struct dentry *unused, struct inode *inode,
 				   const char *key, void *buf, size_t buflen)
 {
-	return nfs4_proc_get_acl(inode, buf, buflen);
+	return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_ACL);
 }
 
 static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
 {
-	return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)));
+	return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_ACL);
 }
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 5662d8be04eb..8d04b6a5964c 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -451,6 +451,8 @@ enum lock_type4 {
 #define FATTR4_WORD1_TIME_MODIFY        (1UL << 21)
 #define FATTR4_WORD1_TIME_MODIFY_SET    (1UL << 22)
 #define FATTR4_WORD1_MOUNTED_ON_FILEID  (1UL << 23)
+#define FATTR4_WORD1_DACL               (1UL << 26)
+#define FATTR4_WORD1_SACL               (1UL << 27)
 #define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
 #define FATTR4_WORD2_LAYOUT_TYPES       (1UL << 0)
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 2863e5a69c6a..13d068c57d8d 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -800,6 +800,13 @@ struct nfs_setattrargs {
 	const struct nfs4_label		*label;
 };
 
+enum nfs4_acl_type {
+	NFS4ACL_NONE = 0,
+	NFS4ACL_ACL,
+	NFS4ACL_DACL,
+	NFS4ACL_SACL,
+};
+
 struct nfs_setaclargs {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *			fh;
-- 
cgit v1.2.3


From db145db021abf75aa1a5810e631425055cfbed47 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 14 May 2022 10:36:59 -0400
Subject: NFSv4: Add encoders/decoders for the NFSv4.1 dacl and sacl attributes

Add the ability to set or retrieve the acl using the NFSv4.1 'dacl' and
'sacl' attributes to the NFSv4 xdr encoders/decoders.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       |  9 +++--
 fs/nfs/nfs4xdr.c        | 95 ++++++++++++++++++++++++++++++++-----------------
 include/linux/nfs_xdr.h |  3 ++
 3 files changed, 71 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e6c830d4db0b..b2ddbaf32a95 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5911,9 +5911,11 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf,
 	struct page **pages;
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
+		.acl_type = type,
 		.acl_len = buflen,
 	};
 	struct nfs_getaclres res = {
+		.acl_type = type,
 		.acl_len = buflen,
 	};
 	struct rpc_message msg = {
@@ -6028,9 +6030,10 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf,
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct page *pages[NFS4ACL_MAXPAGES];
 	struct nfs_setaclargs arg = {
-		.fh		= NFS_FH(inode),
-		.acl_pages	= pages,
-		.acl_len	= buflen,
+		.fh = NFS_FH(inode),
+		.acl_type = type,
+		.acl_len = buflen,
+		.acl_pages = pages,
 	};
 	struct nfs_setaclres res;
 	struct rpc_message msg = {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 86a5f6516928..0b41e00e754f 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1680,19 +1680,35 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 	encode_op_hdr(xdr, OP_RESTOREFH, decode_restorefh_maxsz, hdr);
 }
 
-static void
-encode_setacl(struct xdr_stream *xdr, const struct nfs_setaclargs *arg,
-		struct compound_hdr *hdr)
+static void nfs4_acltype_to_bitmap(enum nfs4_acl_type type, __u32 bitmap[2])
 {
-	__be32 *p;
+	switch (type) {
+	default:
+		bitmap[0] = FATTR4_WORD0_ACL;
+		bitmap[1] = 0;
+		break;
+	case NFS4ACL_DACL:
+		bitmap[0] = 0;
+		bitmap[1] = FATTR4_WORD1_DACL;
+		break;
+	case NFS4ACL_SACL:
+		bitmap[0] = 0;
+		bitmap[1] = FATTR4_WORD1_SACL;
+	}
+}
+
+static void encode_setacl(struct xdr_stream *xdr,
+			  const struct nfs_setaclargs *arg,
+			  struct compound_hdr *hdr)
+{
+	__u32 bitmap[2];
+
+	nfs4_acltype_to_bitmap(arg->acl_type, bitmap);
 
 	encode_op_hdr(xdr, OP_SETATTR, decode_setacl_maxsz, hdr);
 	encode_nfs4_stateid(xdr, &zero_stateid);
-	p = reserve_space(xdr, 2*4);
-	*p++ = cpu_to_be32(1);
-	*p = cpu_to_be32(FATTR4_WORD0_ACL);
-	p = reserve_space(xdr, 4);
-	*p = cpu_to_be32(arg->acl_len);
+	xdr_encode_bitmap4(xdr, bitmap, ARRAY_SIZE(bitmap));
+	encode_uint32(xdr, arg->acl_len);
 	xdr_write_pages(xdr, arg->acl_pages, 0, arg->acl_len);
 }
 
@@ -2587,11 +2603,11 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
-	const __u32 nfs4_acl_bitmap[1] = {
-		[0] = FATTR4_WORD0_ACL,
-	};
+	__u32 nfs4_acl_bitmap[2];
 	uint32_t replen;
 
+	nfs4_acltype_to_bitmap(args->acl_type, nfs4_acl_bitmap);
+
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
@@ -5386,7 +5402,7 @@ decode_restorefh(struct xdr_stream *xdr)
 }
 
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
-			 struct nfs_getaclres *res)
+			 struct nfs_getaclres *res, enum nfs4_acl_type type)
 {
 	unsigned int savep;
 	uint32_t attrlen,
@@ -5404,26 +5420,39 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 	if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
 		goto out;
 
-	if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
-		return -EIO;
-	if (likely(bitmap[0] & FATTR4_WORD0_ACL)) {
-
-		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
-		 * are stored with the acl data to handle the problem of
-		 * variable length bitmaps.*/
-		res->acl_data_offset = xdr_page_pos(xdr);
-		res->acl_len = attrlen;
-
-		/* Check for receive buffer overflow */
-		if (res->acl_len > xdr_stream_remaining(xdr) ||
-		    res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
-			res->acl_flags |= NFS4_ACL_TRUNC;
-			dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
-				attrlen, xdr_stream_remaining(xdr));
-		}
-	} else
-		status = -EOPNOTSUPP;
+	switch (type) {
+	default:
+		if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
+			return -EIO;
+		if (!(bitmap[0] & FATTR4_WORD0_ACL))
+			return -EOPNOTSUPP;
+		break;
+	case NFS4ACL_DACL:
+		if (unlikely(bitmap[0] || bitmap[1] & (FATTR4_WORD1_DACL - 1U)))
+			return -EIO;
+		if (!(bitmap[1] & FATTR4_WORD1_DACL))
+			return -EOPNOTSUPP;
+		break;
+	case NFS4ACL_SACL:
+		if (unlikely(bitmap[0] || bitmap[1] & (FATTR4_WORD1_SACL - 1U)))
+			return -EIO;
+		if (!(bitmap[1] & FATTR4_WORD1_SACL))
+			return -EOPNOTSUPP;
+	}
 
+	/* The bitmap (xdr len + bitmaps) and the attr xdr len words
+	 * are stored with the acl data to handle the problem of
+	 * variable length bitmaps.*/
+	res->acl_data_offset = xdr_page_pos(xdr);
+	res->acl_len = attrlen;
+
+	/* Check for receive buffer overflow */
+	if (res->acl_len > xdr_stream_remaining(xdr) ||
+	    res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
+		res->acl_flags |= NFS4_ACL_TRUNC;
+		dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
+			attrlen, xdr_stream_remaining(xdr));
+	}
 out:
 	return status;
 }
@@ -6486,7 +6515,7 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_getacl(xdr, rqstp, res);
+	status = decode_getacl(xdr, rqstp, res, res->acl_type);
 
 out:
 	return status;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 13d068c57d8d..4a8ba84f848e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -810,6 +810,7 @@ enum nfs4_acl_type {
 struct nfs_setaclargs {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *			fh;
+	enum nfs4_acl_type		acl_type;
 	size_t				acl_len;
 	struct page **			acl_pages;
 };
@@ -821,6 +822,7 @@ struct nfs_setaclres {
 struct nfs_getaclargs {
 	struct nfs4_sequence_args 	seq_args;
 	struct nfs_fh *			fh;
+	enum nfs4_acl_type		acl_type;
 	size_t				acl_len;
 	struct page **			acl_pages;
 };
@@ -829,6 +831,7 @@ struct nfs_getaclargs {
 #define NFS4_ACL_TRUNC		0x0001	/* ACL was truncated */
 struct nfs_getaclres {
 	struct nfs4_sequence_res	seq_res;
+	enum nfs4_acl_type		acl_type;
 	size_t				acl_len;
 	size_t				acl_data_offset;
 	int				acl_flags;
-- 
cgit v1.2.3


From 69e9cd66ae1392437234a63a3a1d60b6655f92ef Mon Sep 17 00:00:00 2001
From: Julian Orth <ju.orth@gmail.com>
Date: Tue, 17 May 2022 12:32:53 +0200
Subject: audit,io_uring,io-wq: call __audit_uring_exit for dummy contexts

Not calling the function for dummy contexts will cause the context to
not be reset. During the next syscall, this will cause an error in
__audit_syscall_entry:

	WARN_ON(context->context != AUDIT_CTX_UNUSED);
	WARN_ON(context->name_count);
	if (context->context != AUDIT_CTX_UNUSED || context->name_count) {
		audit_panic("unrecoverable error in audit_syscall_entry()");
		return;
	}

These problematic dummy contexts are created via the following call
chain:

       exit_to_user_mode_prepare
    -> arch_do_signal_or_restart
    -> get_signal
    -> task_work_run
    -> tctx_task_work
    -> io_req_task_submit
    -> io_issue_sqe
    -> audit_uring_entry

Cc: stable@vger.kernel.org
Fixes: 5bd2182d58e9 ("audit,io_uring,io-wq: add some basic audit support to io_uring")
Signed-off-by: Julian Orth <ju.orth@gmail.com>
[PM: subject line tweaks]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/audit.h | 2 +-
 kernel/auditsc.c      | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index d06134ac6245..cece70231138 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -339,7 +339,7 @@ static inline void audit_uring_entry(u8 op)
 }
 static inline void audit_uring_exit(int success, long code)
 {
-	if (unlikely(!audit_dummy_context()))
+	if (unlikely(audit_context()))
 		__audit_uring_exit(success, code);
 }
 static inline void audit_syscall_entry(int major, unsigned long a0,
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index ea2ee1181921..f3a2abd6d1a1 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1959,6 +1959,12 @@ void __audit_uring_exit(int success, long code)
 {
 	struct audit_context *ctx = audit_context();
 
+	if (ctx->dummy) {
+		if (ctx->context != AUDIT_CTX_URING)
+			return;
+		goto out;
+	}
+
 	if (ctx->context == AUDIT_CTX_SYSCALL) {
 		/*
 		 * NOTE: See the note in __audit_uring_entry() about the case
-- 
cgit v1.2.3


From 0aa7be05d83cc584da0782405e8007e351dfb6cc Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Sun, 15 May 2022 20:42:03 +0200
Subject: locking/atomic: Add generic try_cmpxchg64 support

Add generic support for try_cmpxchg64{,_acquire,_release,_relaxed}
and their falbacks involving cmpxchg64.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220515184205.103089-2-ubizjak@gmail.com
---
 include/linux/atomic/atomic-arch-fallback.h | 72 ++++++++++++++++++++++++++++-
 include/linux/atomic/atomic-instrumented.h  | 40 +++++++++++++++-
 scripts/atomic/gen-atomic-fallback.sh       | 31 +++++++------
 scripts/atomic/gen-atomic-instrumented.sh   |  2 +-
 4 files changed, 129 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h
index 6db58d180866..77bc5522e61c 100644
--- a/include/linux/atomic/atomic-arch-fallback.h
+++ b/include/linux/atomic/atomic-arch-fallback.h
@@ -147,6 +147,76 @@
 
 #endif /* arch_try_cmpxchg_relaxed */
 
+#ifndef arch_try_cmpxchg64_relaxed
+#ifdef arch_try_cmpxchg64
+#define arch_try_cmpxchg64_acquire arch_try_cmpxchg64
+#define arch_try_cmpxchg64_release arch_try_cmpxchg64
+#define arch_try_cmpxchg64_relaxed arch_try_cmpxchg64
+#endif /* arch_try_cmpxchg64 */
+
+#ifndef arch_try_cmpxchg64
+#define arch_try_cmpxchg64(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg64((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg64 */
+
+#ifndef arch_try_cmpxchg64_acquire
+#define arch_try_cmpxchg64_acquire(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg64_acquire((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg64_acquire */
+
+#ifndef arch_try_cmpxchg64_release
+#define arch_try_cmpxchg64_release(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg64_release((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg64_release */
+
+#ifndef arch_try_cmpxchg64_relaxed
+#define arch_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg64_relaxed((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg64_relaxed */
+
+#else /* arch_try_cmpxchg64_relaxed */
+
+#ifndef arch_try_cmpxchg64_acquire
+#define arch_try_cmpxchg64_acquire(...) \
+	__atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__)
+#endif
+
+#ifndef arch_try_cmpxchg64_release
+#define arch_try_cmpxchg64_release(...) \
+	__atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__)
+#endif
+
+#ifndef arch_try_cmpxchg64
+#define arch_try_cmpxchg64(...) \
+	__atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__)
+#endif
+
+#endif /* arch_try_cmpxchg64_relaxed */
+
 #ifndef arch_atomic_read_acquire
 static __always_inline int
 arch_atomic_read_acquire(const atomic_t *v)
@@ -2386,4 +2456,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae
+// b5e87bdd5ede61470c29f7a7e4de781af3770f09
diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h
index 5d69b143c28e..7a139ec030b0 100644
--- a/include/linux/atomic/atomic-instrumented.h
+++ b/include/linux/atomic/atomic-instrumented.h
@@ -2006,6 +2006,44 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
+#define try_cmpxchg64(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	kcsan_mb(); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg64_acquire(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg64_release(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	kcsan_release(); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg64_relaxed(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
 #define cmpxchg_local(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
@@ -2045,4 +2083,4 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 })
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-// 87c974b93032afd42143613434d1a7788fa598f9
+// 764f741eb77a7ad565dc8d99ce2837d5542e8aee
diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh
index 8e2da71f1d5f..3a07695e3c89 100755
--- a/scripts/atomic/gen-atomic-fallback.sh
+++ b/scripts/atomic/gen-atomic-fallback.sh
@@ -164,41 +164,44 @@ gen_xchg_fallbacks()
 
 gen_try_cmpxchg_fallback()
 {
+	local cmpxchg="$1"; shift;
 	local order="$1"; shift;
 
 cat <<EOF
-#ifndef arch_try_cmpxchg${order}
-#define arch_try_cmpxchg${order}(_ptr, _oldp, _new) \\
+#ifndef arch_try_${cmpxchg}${order}
+#define arch_try_${cmpxchg}${order}(_ptr, _oldp, _new) \\
 ({ \\
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \\
-	___r = arch_cmpxchg${order}((_ptr), ___o, (_new)); \\
+	___r = arch_${cmpxchg}${order}((_ptr), ___o, (_new)); \\
 	if (unlikely(___r != ___o)) \\
 		*___op = ___r; \\
 	likely(___r == ___o); \\
 })
-#endif /* arch_try_cmpxchg${order} */
+#endif /* arch_try_${cmpxchg}${order} */
 
 EOF
 }
 
 gen_try_cmpxchg_fallbacks()
 {
-	printf "#ifndef arch_try_cmpxchg_relaxed\n"
-	printf "#ifdef arch_try_cmpxchg\n"
+	local cmpxchg="$1"; shift;
 
-	gen_basic_fallbacks "arch_try_cmpxchg"
+	printf "#ifndef arch_try_${cmpxchg}_relaxed\n"
+	printf "#ifdef arch_try_${cmpxchg}\n"
 
-	printf "#endif /* arch_try_cmpxchg */\n\n"
+	gen_basic_fallbacks "arch_try_${cmpxchg}"
+
+	printf "#endif /* arch_try_${cmpxchg} */\n\n"
 
 	for order in "" "_acquire" "_release" "_relaxed"; do
-		gen_try_cmpxchg_fallback "${order}"
+		gen_try_cmpxchg_fallback "${cmpxchg}" "${order}"
 	done
 
-	printf "#else /* arch_try_cmpxchg_relaxed */\n"
+	printf "#else /* arch_try_${cmpxchg}_relaxed */\n"
 
-	gen_order_fallbacks "arch_try_cmpxchg"
+	gen_order_fallbacks "arch_try_${cmpxchg}"
 
-	printf "#endif /* arch_try_cmpxchg_relaxed */\n\n"
+	printf "#endif /* arch_try_${cmpxchg}_relaxed */\n\n"
 }
 
 cat << EOF
@@ -218,7 +221,9 @@ for xchg in "arch_xchg" "arch_cmpxchg" "arch_cmpxchg64"; do
 	gen_xchg_fallbacks "${xchg}"
 done
 
-gen_try_cmpxchg_fallbacks
+for cmpxchg in "cmpxchg" "cmpxchg64"; do
+	gen_try_cmpxchg_fallbacks "${cmpxchg}"
+done
 
 grep '^[a-z]' "$1" | while read name meta args; do
 	gen_proto "${meta}" "${name}" "atomic" "int" ${args}
diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh
index 68f902731d01..77c06526a574 100755
--- a/scripts/atomic/gen-atomic-instrumented.sh
+++ b/scripts/atomic/gen-atomic-instrumented.sh
@@ -166,7 +166,7 @@ grep '^[a-z]' "$1" | while read name meta args; do
 done
 
 
-for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg"; do
+for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg" "try_cmpxchg64"; do
 	for order in "" "_acquire" "_release" "_relaxed"; do
 		gen_xchg "${xchg}" "${order}" ""
 		printf "\n"
-- 
cgit v1.2.3


From bec67592521ec816371f5f072b1a340e1c2ad434 Mon Sep 17 00:00:00 2001
From: Min Li <min.li.xe@renesas.com>
Date: Mon, 16 May 2022 10:47:06 -0400
Subject: ptp: ptp_clockmatrix: Add PTP_CLK_REQ_EXTTS support

Use TOD_READ_SECONDARY for extts to keep TOD_READ_PRIMARY
for gettime and settime exclusively. Before this change,
TOD_READ_PRIMARY was used for both extts and gettime/settime,
which would result in changing TOD read/write triggers between
operations. Using TOD_READ_SECONDARY would make extts
independent of gettime/settime operation

Signed-off-by: Min Li <min.li.xe@renesas.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://lore.kernel.org/r/1652712427-14703-1-git-send-email-min.li.xe@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_clockmatrix.c    | 289 ++++++++++++++++++++++++---------------
 drivers/ptp/ptp_clockmatrix.h    |   5 +
 include/linux/mfd/idt8a340_reg.h |  12 +-
 3 files changed, 196 insertions(+), 110 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c
index 08e429a06922..25075764eea4 100644
--- a/drivers/ptp/ptp_clockmatrix.c
+++ b/drivers/ptp/ptp_clockmatrix.c
@@ -239,73 +239,97 @@ static int wait_for_boot_status_ready(struct idtcm *idtcm)
 	return -EBUSY;
 }
 
-static int _idtcm_set_scsr_read_trig(struct idtcm_channel *channel,
-				     enum scsr_read_trig_sel trig, u8 ref)
+static int arm_tod_read_trig_sel_refclk(struct idtcm_channel *channel, u8 ref)
 {
 	struct idtcm *idtcm = channel->idtcm;
-	u16 tod_read_cmd = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_READ_PRIMARY_CMD);
-	u8 val;
+	u16 tod_read_cmd = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_READ_SECONDARY_CMD);
+	u8 val = 0;
 	int err;
 
-	if (trig == SCSR_TOD_READ_TRIG_SEL_REFCLK) {
-		err = idtcm_read(idtcm, channel->tod_read_primary,
-				 TOD_READ_PRIMARY_SEL_CFG_0, &val, sizeof(val));
-		if (err)
-			return err;
-
-		val &= ~(WR_REF_INDEX_MASK << WR_REF_INDEX_SHIFT);
-		val |= (ref << WR_REF_INDEX_SHIFT);
-
-		err = idtcm_write(idtcm, channel->tod_read_primary,
-				  TOD_READ_PRIMARY_SEL_CFG_0, &val, sizeof(val));
-		if (err)
-			return err;
-	}
+	val &= ~(WR_REF_INDEX_MASK << WR_REF_INDEX_SHIFT);
+	val |= (ref << WR_REF_INDEX_SHIFT);
 
-	err = idtcm_read(idtcm, channel->tod_read_primary,
-			 tod_read_cmd, &val, sizeof(val));
+	err = idtcm_write(idtcm, channel->tod_read_secondary,
+			  TOD_READ_SECONDARY_SEL_CFG_0, &val, sizeof(val));
 	if (err)
 		return err;
 
-	val &= ~(TOD_READ_TRIGGER_MASK << TOD_READ_TRIGGER_SHIFT);
-	val |= (trig << TOD_READ_TRIGGER_SHIFT);
-	val &= ~TOD_READ_TRIGGER_MODE; /* single shot */
+	val = 0 | (SCSR_TOD_READ_TRIG_SEL_REFCLK << TOD_READ_TRIGGER_SHIFT);
+
+	err = idtcm_write(idtcm, channel->tod_read_secondary, tod_read_cmd,
+			  &val, sizeof(val));
+	if (err)
+		dev_err(idtcm->dev, "%s: err = %d", __func__, err);
 
-	err = idtcm_write(idtcm, channel->tod_read_primary,
-			  tod_read_cmd, &val, sizeof(val));
 	return err;
 }
 
-static int idtcm_enable_extts(struct idtcm_channel *channel, u8 todn, u8 ref,
-			      bool enable)
+static bool is_single_shot(u8 mask)
 {
-	struct idtcm *idtcm = channel->idtcm;
-	u8 old_mask = idtcm->extts_mask;
-	u8 mask = 1 << todn;
+	/* Treat single bit ToD masks as continuous trigger */
+	return mask <= 8 && is_power_of_2(mask);
+}
+
+static int idtcm_extts_enable(struct idtcm_channel *channel,
+			      struct ptp_clock_request *rq, int on)
+{
+	u8 index = rq->extts.index;
+	struct idtcm *idtcm;
+	u8 mask = 1 << index;
 	int err = 0;
+	u8 old_mask;
+	int ref;
+
+	idtcm = channel->idtcm;
+	old_mask = idtcm->extts_mask;
 
-	if (todn >= MAX_TOD)
+	/* Reject requests with unsupported flags */
+	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
+				PTP_RISING_EDGE |
+				PTP_FALLING_EDGE |
+				PTP_STRICT_FLAGS))
+		return -EOPNOTSUPP;
+
+	/* Reject requests to enable time stamping on falling edge */
+	if ((rq->extts.flags & PTP_ENABLE_FEATURE) &&
+	    (rq->extts.flags & PTP_FALLING_EDGE))
+		return -EOPNOTSUPP;
+
+	if (index >= MAX_TOD)
 		return -EINVAL;
 
-	if (enable) {
-		if (ref > 0xF) /* E_REF_CLK15 */
-			return -EINVAL;
-		if (idtcm->extts_mask & mask)
-			return 0;
-		err = _idtcm_set_scsr_read_trig(&idtcm->channel[todn],
-						SCSR_TOD_READ_TRIG_SEL_REFCLK,
-						ref);
+	if (on) {
+		/* Support triggering more than one TOD_0/1/2/3 by same pin */
+		/* Use the pin configured for the channel */
+		ref = ptp_find_pin(channel->ptp_clock, PTP_PF_EXTTS, channel->tod);
+
+		if (ref < 0) {
+			dev_err(idtcm->dev, "%s: No valid pin found for TOD%d!\n",
+				__func__, channel->tod);
+			return -EBUSY;
+		}
+
+		err = arm_tod_read_trig_sel_refclk(&idtcm->channel[index], ref);
+
 		if (err == 0) {
 			idtcm->extts_mask |= mask;
-			idtcm->event_channel[todn] = channel;
-			idtcm->channel[todn].refn = ref;
+			idtcm->event_channel[index] = channel;
+			idtcm->channel[index].refn = ref;
+			idtcm->extts_single_shot = is_single_shot(idtcm->extts_mask);
+
+			if (old_mask)
+				return 0;
+
+			schedule_delayed_work(&idtcm->extts_work,
+					      msecs_to_jiffies(EXTTS_PERIOD_MS));
 		}
-	} else
+	} else {
 		idtcm->extts_mask &= ~mask;
+		idtcm->extts_single_shot = is_single_shot(idtcm->extts_mask);
 
-	if (old_mask == 0 && idtcm->extts_mask)
-		schedule_delayed_work(&idtcm->extts_work,
-				      msecs_to_jiffies(EXTTS_PERIOD_MS));
+		if (idtcm->extts_mask == 0)
+			cancel_delayed_work(&idtcm->extts_work);
+	}
 
 	return err;
 }
@@ -371,6 +395,31 @@ static void wait_for_chip_ready(struct idtcm *idtcm)
 			 "Continuing while SYS APLL/DPLL is not locked");
 }
 
+static int _idtcm_gettime_triggered(struct idtcm_channel *channel,
+				    struct timespec64 *ts)
+{
+	struct idtcm *idtcm = channel->idtcm;
+	u16 tod_read_cmd = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_READ_SECONDARY_CMD);
+	u8 buf[TOD_BYTE_COUNT];
+	u8 trigger;
+	int err;
+
+	err = idtcm_read(idtcm, channel->tod_read_secondary,
+			 tod_read_cmd, &trigger, sizeof(trigger));
+	if (err)
+		return err;
+
+	if (trigger & TOD_READ_TRIGGER_MASK)
+		return -EBUSY;
+
+	err = idtcm_read(idtcm, channel->tod_read_secondary,
+			 TOD_READ_SECONDARY_BASE, buf, sizeof(buf));
+	if (err)
+		return err;
+
+	return char_array_to_timespec(buf, sizeof(buf), ts);
+}
+
 static int _idtcm_gettime(struct idtcm_channel *channel,
 			  struct timespec64 *ts, u8 timeout)
 {
@@ -396,7 +445,7 @@ static int _idtcm_gettime(struct idtcm_channel *channel,
 	} while (trigger & TOD_READ_TRIGGER_MASK);
 
 	err = idtcm_read(idtcm, channel->tod_read_primary,
-			 TOD_READ_PRIMARY, buf, sizeof(buf));
+			 TOD_READ_PRIMARY_BASE, buf, sizeof(buf));
 	if (err)
 		return err;
 
@@ -415,67 +464,38 @@ static int idtcm_extts_check_channel(struct idtcm *idtcm, u8 todn)
 
 	extts_channel = &idtcm->channel[todn];
 	ptp_channel = idtcm->event_channel[todn];
+
 	if (extts_channel == ptp_channel)
 		dco_delay = ptp_channel->dco_delay;
 
-	err = _idtcm_gettime(extts_channel, &ts, 1);
-	if (err == 0) {
-		event.type = PTP_CLOCK_EXTTS;
-		event.index = todn;
-		event.timestamp = timespec64_to_ns(&ts) - dco_delay;
-		ptp_clock_event(ptp_channel->ptp_clock, &event);
-	}
-	return err;
-}
-
-static u8 idtcm_enable_extts_mask(struct idtcm_channel *channel,
-				    u8 extts_mask, bool enable)
-{
-	struct idtcm *idtcm = channel->idtcm;
-	int i, err;
+	err = _idtcm_gettime_triggered(extts_channel, &ts);
+	if (err)
+		return err;
 
-	for (i = 0; i < MAX_TOD; i++) {
-		u8 mask = 1 << i;
-		u8 refn = idtcm->channel[i].refn;
-
-		if (extts_mask & mask) {
-			/* check extts before disabling it */
-			if (enable == false) {
-				err = idtcm_extts_check_channel(idtcm, i);
-				/* trigger happened so we won't re-enable it */
-				if (err == 0)
-					extts_mask &= ~mask;
-			}
-			(void)idtcm_enable_extts(channel, i, refn, enable);
-		}
-	}
+	/* Triggered - save timestamp */
+	event.type = PTP_CLOCK_EXTTS;
+	event.index = todn;
+	event.timestamp = timespec64_to_ns(&ts) - dco_delay;
+	ptp_clock_event(ptp_channel->ptp_clock, &event);
 
-	return extts_mask;
+	return err;
 }
 
 static int _idtcm_gettime_immediate(struct idtcm_channel *channel,
 				    struct timespec64 *ts)
 {
 	struct idtcm *idtcm = channel->idtcm;
-	u8 extts_mask = 0;
-	int err;
 
-	/* Disable extts */
-	if (idtcm->extts_mask) {
-		extts_mask = idtcm_enable_extts_mask(channel, idtcm->extts_mask,
-						     false);
-	}
-
-	err = _idtcm_set_scsr_read_trig(channel,
-					SCSR_TOD_READ_TRIG_SEL_IMMEDIATE, 0);
-	if (err == 0)
-		err = _idtcm_gettime(channel, ts, 10);
+	u16 tod_read_cmd = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_READ_PRIMARY_CMD);
+	u8 val = (SCSR_TOD_READ_TRIG_SEL_IMMEDIATE << TOD_READ_TRIGGER_SHIFT);
+	int err;
 
-	/* Re-enable extts */
-	if (extts_mask)
-		idtcm_enable_extts_mask(channel, extts_mask, true);
+	err = idtcm_write(idtcm, channel->tod_read_primary,
+			  tod_read_cmd, &val, sizeof(val));
+	if (err)
+		return err;
 
-	return err;
+	return _idtcm_gettime(channel, ts, 10);
 }
 
 static int _sync_pll_output(struct idtcm *idtcm,
@@ -1702,6 +1722,9 @@ static int initialize_dco_operating_mode(struct idtcm_channel *channel)
 /*
  * Maximum absolute value for write phase offset in picoseconds
  *
+ * @channel:  channel
+ * @delta_ns: delta in nanoseconds
+ *
  * Destination signed register is 32-bit register in resolution of 50ps
  *
  * 0x7fffffff * 50 =  2147483647 * 50 = 107374182350
@@ -1958,8 +1981,7 @@ static int idtcm_enable(struct ptp_clock_info *ptp,
 			err = idtcm_perout_enable(channel, &rq->perout, true);
 		break;
 	case PTP_CLK_REQ_EXTTS:
-		err = idtcm_enable_extts(channel, rq->extts.index,
-					 rq->extts.rsv[0], on);
+		err = idtcm_extts_enable(channel, rq, on);
 		break;
 	default:
 		break;
@@ -1982,13 +2004,6 @@ static int idtcm_enable_tod(struct idtcm_channel *channel)
 	u8 cfg;
 	int err;
 
-	/* STEELAI-366 - Temporary workaround for ts2phc compatibility */
-	if (0) {
-		err = idtcm_output_mask_enable(channel, false);
-		if (err)
-			return err;
-	}
-
 	/*
 	 * Start the TOD clock ticking.
 	 */
@@ -2038,17 +2053,35 @@ static void idtcm_set_version_info(struct idtcm *idtcm)
 		 product_id, hw_rev_id, config_select);
 }
 
+static int idtcm_verify_pin(struct ptp_clock_info *ptp, unsigned int pin,
+			    enum ptp_pin_function func, unsigned int chan)
+{
+	switch (func) {
+	case PTP_PF_NONE:
+	case PTP_PF_EXTTS:
+		break;
+	case PTP_PF_PEROUT:
+	case PTP_PF_PHYSYNC:
+		return -1;
+	}
+	return 0;
+}
+
+static struct ptp_pin_desc pin_config[MAX_TOD][MAX_REF_CLK];
+
 static const struct ptp_clock_info idtcm_caps = {
 	.owner		= THIS_MODULE,
 	.max_adj	= 244000,
 	.n_per_out	= 12,
 	.n_ext_ts	= MAX_TOD,
+	.n_pins		= MAX_REF_CLK,
 	.adjphase	= &idtcm_adjphase,
 	.adjfine	= &idtcm_adjfine,
 	.adjtime	= &idtcm_adjtime,
 	.gettime64	= &idtcm_gettime,
 	.settime64	= &idtcm_settime,
 	.enable		= &idtcm_enable,
+	.verify		= &idtcm_verify_pin,
 	.do_aux_work	= &idtcm_work_handler,
 };
 
@@ -2057,12 +2090,14 @@ static const struct ptp_clock_info idtcm_caps_deprecated = {
 	.max_adj	= 244000,
 	.n_per_out	= 12,
 	.n_ext_ts	= MAX_TOD,
+	.n_pins		= MAX_REF_CLK,
 	.adjphase	= &idtcm_adjphase,
 	.adjfine	= &idtcm_adjfine,
 	.adjtime	= &idtcm_adjtime_deprecated,
 	.gettime64	= &idtcm_gettime,
 	.settime64	= &idtcm_settime_deprecated,
 	.enable		= &idtcm_enable,
+	.verify		= &idtcm_verify_pin,
 	.do_aux_work	= &idtcm_work_handler,
 };
 
@@ -2174,8 +2209,9 @@ static u32 idtcm_get_dco_delay(struct idtcm_channel *channel)
 		n = 1;
 
 	fodFreq = (u32)div_u64(m, n);
+
 	if (fodFreq >= 500000000)
-		return 18 * (u32)div_u64(NSEC_PER_SEC, fodFreq);
+		return (u32)div_u64(18 * (u64)NSEC_PER_SEC, fodFreq);
 
 	return 0;
 }
@@ -2188,24 +2224,28 @@ static int configure_channel_tod(struct idtcm_channel *channel, u32 index)
 	switch (index) {
 	case 0:
 		channel->tod_read_primary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_PRIMARY_0);
+		channel->tod_read_secondary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_SECONDARY_0);
 		channel->tod_write = IDTCM_FW_REG(fw_ver, V520, TOD_WRITE_0);
 		channel->tod_n = IDTCM_FW_REG(fw_ver, V520, TOD_0);
 		channel->sync_src = SYNC_SOURCE_DPLL0_TOD_PPS;
 		break;
 	case 1:
 		channel->tod_read_primary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_PRIMARY_1);
+		channel->tod_read_secondary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_SECONDARY_1);
 		channel->tod_write = IDTCM_FW_REG(fw_ver, V520, TOD_WRITE_1);
 		channel->tod_n = IDTCM_FW_REG(fw_ver, V520, TOD_1);
 		channel->sync_src = SYNC_SOURCE_DPLL1_TOD_PPS;
 		break;
 	case 2:
 		channel->tod_read_primary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_PRIMARY_2);
+		channel->tod_read_secondary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_SECONDARY_2);
 		channel->tod_write = IDTCM_FW_REG(fw_ver, V520, TOD_WRITE_2);
 		channel->tod_n = IDTCM_FW_REG(fw_ver, V520, TOD_2);
 		channel->sync_src = SYNC_SOURCE_DPLL2_TOD_PPS;
 		break;
 	case 3:
 		channel->tod_read_primary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_PRIMARY_3);
+		channel->tod_read_secondary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_SECONDARY_3);
 		channel->tod_write = IDTCM_FW_REG(fw_ver, V520, TOD_WRITE_3);
 		channel->tod_n = IDTCM_FW_REG(fw_ver, V520, TOD_3);
 		channel->sync_src = SYNC_SOURCE_DPLL3_TOD_PPS;
@@ -2221,6 +2261,7 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index)
 {
 	struct idtcm_channel *channel;
 	int err;
+	int i;
 
 	if (!(index < MAX_TOD))
 		return -EINVAL;
@@ -2248,6 +2289,17 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index)
 	snprintf(channel->caps.name, sizeof(channel->caps.name),
 		 "IDT CM TOD%u", index);
 
+	channel->caps.pin_config = pin_config[index];
+
+	for (i = 0; i < channel->caps.n_pins; ++i) {
+		struct ptp_pin_desc *ppd = &channel->caps.pin_config[i];
+
+		snprintf(ppd->name, sizeof(ppd->name), "input_ref%d", i);
+		ppd->index = i;
+		ppd->func = PTP_PF_NONE;
+		ppd->chan = index;
+	}
+
 	err = initialize_dco_operating_mode(channel);
 	if (err)
 		return err;
@@ -2302,26 +2354,40 @@ static int idtcm_enable_extts_channel(struct idtcm *idtcm, u32 index)
 static void idtcm_extts_check(struct work_struct *work)
 {
 	struct idtcm *idtcm = container_of(work, struct idtcm, extts_work.work);
-	int err, i;
+	struct idtcm_channel *channel;
+	u8 mask;
+	int err;
+	int i;
 
 	if (idtcm->extts_mask == 0)
 		return;
 
 	mutex_lock(idtcm->lock);
+
 	for (i = 0; i < MAX_TOD; i++) {
-		u8 mask = 1 << i;
+		mask = 1 << i;
+
+		if ((idtcm->extts_mask & mask) == 0)
+			continue;
+
+		err = idtcm_extts_check_channel(idtcm, i);
 
-		if (idtcm->extts_mask & mask) {
-			err = idtcm_extts_check_channel(idtcm, i);
+		if (err == 0) {
 			/* trigger clears itself, so clear the mask */
-			if (err == 0)
+			if (idtcm->extts_single_shot) {
 				idtcm->extts_mask &= ~mask;
+			} else {
+				/* Re-arm */
+				channel = &idtcm->channel[i];
+				arm_tod_read_trig_sel_refclk(channel, channel->refn);
+			}
 		}
 	}
 
 	if (idtcm->extts_mask)
 		schedule_delayed_work(&idtcm->extts_work,
 				      msecs_to_jiffies(EXTTS_PERIOD_MS));
+
 	mutex_unlock(idtcm->lock);
 }
 
@@ -2342,6 +2408,11 @@ static void set_default_masks(struct idtcm *idtcm)
 	idtcm->tod_mask = DEFAULT_TOD_MASK;
 	idtcm->extts_mask = 0;
 
+	idtcm->channel[0].tod = 0;
+	idtcm->channel[1].tod = 1;
+	idtcm->channel[2].tod = 2;
+	idtcm->channel[3].tod = 3;
+
 	idtcm->channel[0].pll = DEFAULT_TOD0_PTP_PLL;
 	idtcm->channel[1].pll = DEFAULT_TOD1_PTP_PLL;
 	idtcm->channel[2].pll = DEFAULT_TOD2_PTP_PLL;
@@ -2420,8 +2491,8 @@ static int idtcm_remove(struct platform_device *pdev)
 {
 	struct idtcm *idtcm = platform_get_drvdata(pdev);
 
+	idtcm->extts_mask = 0;
 	ptp_clock_unregister_all(idtcm);
-
 	cancel_delayed_work_sync(&idtcm->extts_work);
 
 	return 0;
diff --git a/drivers/ptp/ptp_clockmatrix.h b/drivers/ptp/ptp_clockmatrix.h
index 0f3059ae1fff..43796508031f 100644
--- a/drivers/ptp/ptp_clockmatrix.h
+++ b/drivers/ptp/ptp_clockmatrix.h
@@ -10,11 +10,13 @@
 
 #include <linux/ktime.h>
 #include <linux/mfd/idt8a340_reg.h>
+#include <linux/ptp_clock.h>
 #include <linux/regmap.h>
 
 #define FW_FILENAME	"idtcm.bin"
 #define MAX_TOD		(4)
 #define MAX_PLL		(8)
+#define MAX_REF_CLK	(16)
 
 #define MAX_ABS_WRITE_PHASE_PICOSECONDS (107374182350LL)
 
@@ -90,6 +92,7 @@ struct idtcm_channel {
 	u16			dpll_ctrl_n;
 	u16			dpll_phase_pull_in;
 	u16			tod_read_primary;
+	u16			tod_read_secondary;
 	u16			tod_write;
 	u16			tod_n;
 	u16			hw_dpll_n;
@@ -105,6 +108,7 @@ struct idtcm_channel {
 	/* last input trigger for extts */
 	u8			refn;
 	u8			pll;
+	u8			tod;
 	u16			output_mask;
 };
 
@@ -116,6 +120,7 @@ struct idtcm {
 	enum fw_version		fw_ver;
 	/* Polls for external time stamps */
 	u8			extts_mask;
+	bool			extts_single_shot;
 	struct delayed_work	extts_work;
 	/* Remember the ptp channel to report extts */
 	struct idtcm_channel	*event_channel[MAX_TOD];
diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h
index a18c1539a152..0c706085c205 100644
--- a/include/linux/mfd/idt8a340_reg.h
+++ b/include/linux/mfd/idt8a340_reg.h
@@ -407,7 +407,7 @@
 #define TOD_READ_PRIMARY_0                0xcc40
 #define TOD_READ_PRIMARY_0_V520           0xcc50
 /* 8-bit subns, 32-bit ns, 48-bit seconds */
-#define TOD_READ_PRIMARY                  0x0000
+#define TOD_READ_PRIMARY_BASE             0x0000
 /* Counter increments after TOD write is completed */
 #define TOD_READ_PRIMARY_COUNTER          0x000b
 /* Read trigger configuration */
@@ -424,6 +424,16 @@
 
 #define TOD_READ_SECONDARY_0              0xcc90
 #define TOD_READ_SECONDARY_0_V520         0xcca0
+/* 8-bit subns, 32-bit ns, 48-bit seconds */
+#define TOD_READ_SECONDARY_BASE           0x0000
+/* Counter increments after TOD write is completed */
+#define TOD_READ_SECONDARY_COUNTER        0x000b
+/* Read trigger configuration */
+#define TOD_READ_SECONDARY_SEL_CFG_0      0x000c
+/* Read trigger selection */
+#define TOD_READ_SECONDARY_CMD            0x000e
+#define TOD_READ_SECONDARY_CMD_V520       0x000f
+
 #define TOD_READ_SECONDARY_1              0xcca0
 #define TOD_READ_SECONDARY_1_V520         0xccb0
 #define TOD_READ_SECONDARY_2              0xccb0
-- 
cgit v1.2.3


From 1d2c717bc7f7fd3c9cf38d4a0d5d7ede06adf05b Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Fri, 13 May 2022 06:19:31 +0300
Subject: net/mlx5: Add last command failure syndrome to debugfs

Add syndrome of last command failure per command type to debugfs to ease
debugging of such failure.
last_failed_syndrome - last command failed syndrome returned by FW.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c     | 7 +++++--
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 2 ++
 include/linux/mlx5/driver.h                       | 2 ++
 3 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 26ba94cb432e..0377392848d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1887,7 +1887,8 @@ out_in:
 	return err;
 }
 
-static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, int err)
+static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status,
+			   u32 syndrome, int err)
 {
 	struct mlx5_cmd_stats *stats;
 
@@ -1902,6 +1903,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, int
 	if (err == -EREMOTEIO) {
 		stats->failed_mbox_status++;
 		stats->last_failed_mbox_status = status;
+		stats->last_failed_syndrome = syndrome;
 	}
 	spin_unlock_irq(&stats->lock);
 }
@@ -1909,6 +1911,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, int
 /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */
 static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *out)
 {
+	u32 syndrome = MLX5_GET(mbox_out, out, syndrome);
 	u8 status = MLX5_GET(mbox_out, out, status);
 
 	if (err == -EREMOTEIO) /* -EREMOTEIO is preserved */
@@ -1917,7 +1920,7 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *
 	if (!err && status != MLX5_CMD_STAT_OK)
 		err = -EREMOTEIO;
 
-	cmd_status_log(dev, opcode, status, err);
+	cmd_status_log(dev, opcode, status, syndrome, err);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 3d3e55a5cb11..9caa1b52321b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -192,6 +192,8 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 					   &stats->last_failed_errno);
 			debugfs_create_u8("last_failed_mbox_status", 0400, stats->root,
 					  &stats->last_failed_mbox_status);
+			debugfs_create_x32("last_failed_syndrome", 0400, stats->root,
+					   &stats->last_failed_syndrome);
 		}
 	}
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d6bac3976913..74c8cfb771a2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -272,6 +272,8 @@ struct mlx5_cmd_stats {
 	u32		last_failed_errno;
 	/* last bad status returned by FW */
 	u8		last_failed_mbox_status;
+	/* last command failed syndrome returned by FW */
+	u32		last_failed_syndrome;
 	struct dentry  *root;
 	/* protect command average calculations */
 	spinlock_t	lock;
-- 
cgit v1.2.3


From 9b45bde82c229fda94618896ff530dcba9d66fe0 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 25 Jan 2022 14:47:36 +0200
Subject: net/mlx5: Inline db alloc API function

Take the wrapper version which picks default node into a header file.
This reduces the number of exported functions.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/alloc.c | 6 ------
 include/linux/mlx5/driver.h                     | 7 ++++++-
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index e52b0bac09da..6aca004e88cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -213,12 +213,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_db_alloc_node);
 
-int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db)
-{
-	return mlx5_db_alloc_node(dev, db, dev->priv.numa_node);
-}
-EXPORT_SYMBOL_GPL(mlx5_db_alloc);
-
 void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 {
 	u32 db_per_page = PAGE_SIZE / cache_line_size();
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 74c8cfb771a2..b064bc278f52 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1053,9 +1053,14 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
 			 int size_in, void *data_out, int size_out,
 			 u16 reg_num, int arg, int write);
 
-int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db);
 int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db,
 		       int node);
+
+static inline int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db)
+{
+	return mlx5_db_alloc_node(dev, db, dev->priv.numa_node);
+}
+
 void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db);
 
 const char *mlx5_command_str(int command);
-- 
cgit v1.2.3


From 94db3317781922ba52722c58061e0e8517d4d80d Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Mon, 31 Jan 2022 07:49:51 +0200
Subject: net/mlx5: Support multiport eswitch mode

Multiport eswitch mode is a LAG mode that allows to add rules that
forward traffic to a specific physical port without being affected by LAG
affinity configuration.

This mode of operation is mutual exclusive with the other LAG modes used
by multipath and bonding.

To make the transition between the modes, we maintain a counter on the
number of rules specifying one of the uplink representors as the target
of mirred egress redirect action.

An example of such rule would be:

$ tc filter add dev enp8s0f0_0 prot all root flower dst_mac \
  00:11:22:33:44:55 action mirred egress redirect dev enp8s0f0

If the reference count just grows to one and LAG is not in use, we
create the LAG in multiport eswitch mode. Other mode changes are not
allowed while in this mode. When the reference count reaches zero, we
destroy the LAG and let other modes be used if needed.

logic also changed such that if forwarding to some uplink destination
cannot be guaranteed, we fail the operation so the rule will eventually
be in software and not in hardware.

Signed-off-by: Eli Cohen <elic@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 .../ethernet/mellanox/mlx5/core/en/tc/act/mirred.c |  14 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |  28 +++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h    |   7 ++
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |   3 +
 .../net/ethernet/mellanox/mlx5/core/lag/debugfs.c  |  17 ++--
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c  |  86 ++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h  |  10 +-
 .../net/ethernet/mellanox/mlx5/core/lag/mpesw.c    | 101 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/lag/mpesw.h    |  26 ++++++
 include/linux/mlx5/mlx5_ifc.h                      |   5 +-
 11 files changed, 259 insertions(+), 40 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 7895ed7cc285..9ea867a45764 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -39,7 +39,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
 mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)     += lag/mp.o lag/port_sel.o lib/geneve.o lib/port_tun.o \
 					en_rep.o en/rep/bond.o en/mod_hdr.o \
-					en/mapping.o
+					en/mapping.o lag/mpesw.o
 mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
 					lib/fs_chains.o en/tc_tun.o \
 					esw/indir_table.o en/tc_tun_encap.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
index 2b002c6a2e73..4ac7de3f6afa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
@@ -10,6 +10,7 @@
 #include "en/tc_tun_encap.h"
 #include "en/tc_priv.h"
 #include "en_rep.h"
+#include "lag/lag.h"
 
 static bool
 same_vf_reps(struct mlx5e_priv *priv, struct net_device *out_dev)
@@ -215,6 +216,7 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state,
 	struct net_device *uplink_dev;
 	struct mlx5e_priv *out_priv;
 	struct mlx5_eswitch *esw;
+	bool is_uplink_rep;
 	int *ifindexes;
 	int if_count;
 	int err;
@@ -229,6 +231,10 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state,
 
 	parse_state->ifindexes[if_count] = out_dev->ifindex;
 	parse_state->if_count++;
+	is_uplink_rep = mlx5e_eswitch_uplink_rep(out_dev);
+	err = mlx5_lag_do_mirred(priv->mdev, out_dev);
+	if (err)
+		return err;
 
 	out_dev = get_fdb_out_dev(uplink_dev, out_dev);
 	if (!out_dev)
@@ -268,6 +274,14 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state,
 	rpriv = out_priv->ppriv;
 	esw_attr->dests[esw_attr->out_count].rep = rpriv->rep;
 	esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev;
+
+	/* If output device is bond master then rules are not explicit
+	 * so we don't attempt to count them.
+	 */
+	if (is_uplink_rep && MLX5_CAP_PORT_SELECTION(priv->mdev, port_select_flow_table) &&
+	    MLX5_CAP_GEN(priv->mdev, create_lag_when_not_master_up))
+		attr->lag.count = true;
+
 	esw_attr->out_count++;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ac0f73074f7a..49dea02a12d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1740,6 +1740,9 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 
 	free_flow_post_acts(flow);
 
+	if (flow->attr->lag.count)
+		mlx5_lag_del_mpesw_rule(esw->dev);
+
 	kvfree(attr->esw_attr->rx_tun_attr);
 	kvfree(attr->parse_attr);
 	kfree(flow->attr);
@@ -3788,12 +3791,25 @@ static bool is_lag_dev(struct mlx5e_priv *priv,
 		 same_hw_reps(priv, peer_netdev));
 }
 
+static bool is_multiport_eligible(struct mlx5e_priv *priv, struct net_device *out_dev)
+{
+	if (mlx5e_eswitch_uplink_rep(out_dev) &&
+	    MLX5_CAP_PORT_SELECTION(priv->mdev, port_select_flow_table) &&
+	    MLX5_CAP_GEN(priv->mdev, create_lag_when_not_master_up))
+		return true;
+
+	return false;
+}
+
 bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv,
 				    struct net_device *out_dev)
 {
 	if (is_merged_eswitch_vfs(priv, out_dev))
 		return true;
 
+	if (is_multiport_eligible(priv, out_dev))
+		return true;
+
 	if (is_lag_dev(priv, out_dev))
 		return true;
 
@@ -4050,6 +4066,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		     struct mlx5_core_dev *in_mdev)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_flow *flow;
@@ -4085,17 +4102,26 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
+	if (flow->attr->lag.count) {
+		err = mlx5_lag_add_mpesw_rule(esw->dev);
+		if (err)
+			goto err_free;
+	}
+
 	err = mlx5e_tc_add_fdb_flow(priv, flow, extack);
 	complete_all(&flow->init_done);
 	if (err) {
 		if (!(err == -ENETUNREACH && mlx5_lag_is_multipath(in_mdev)))
-			goto err_free;
+			goto err_lag;
 
 		add_unready_flow(flow);
 	}
 
 	return flow;
 
+err_lag:
+	if (flow->attr->lag.count)
+		mlx5_lag_del_mpesw_rule(esw->dev);
 err_free:
 	mlx5e_flow_put(priv, flow);
 out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index a80b00946f1b..e2a1250aeca1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -85,6 +85,13 @@ struct mlx5_flow_attr {
 	u32 flags;
 	struct list_head list;
 	struct mlx5e_post_act_handle *post_act_handle;
+	struct {
+		/* Indicate whether the parsed flow should be counted for lag mode decision
+		 * making
+		 */
+		bool count;
+	} lag;
+	/* keep this union last */
 	union {
 		struct mlx5_esw_flow_attr esw_attr[0];
 		struct mlx5_nic_flow_attr nic_attr[0];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 3b151332e2f8..217cac29057f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -49,6 +49,7 @@
 #include "en_tc.h"
 #include "en/mapping.h"
 #include "devlink.h"
+#include "lag/lag.h"
 
 #define mlx5_esw_for_each_rep(esw, i, rep) \
 	xa_for_each(&((esw)->offloads.vport_reps), i, rep)
@@ -418,6 +419,8 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f
 		dest[dest_idx].vport.vhca_id =
 			MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
 		dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+		if (mlx5_lag_mpesw_is_activated(esw->dev))
+			dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK;
 	}
 	if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) {
 		if (pkt_reformat) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
index 6e7001c0cfd4..15e41dc84d53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
@@ -5,12 +5,13 @@
 
 static char *get_str_mode_type(struct mlx5_lag *ldev)
 {
-	if (ldev->mode == MLX5_LAG_MODE_ROCE)
-		return "roce";
-	if (ldev->mode == MLX5_LAG_MODE_SRIOV)
-		return "switchdev";
-	if (ldev->mode == MLX5_LAG_MODE_MULTIPATH)
-		return "multipath";
+	switch (ldev->mode) {
+	case MLX5_LAG_MODE_ROCE: return "roce";
+	case MLX5_LAG_MODE_SRIOV: return "switchdev";
+	case MLX5_LAG_MODE_MULTIPATH: return "multipath";
+	case MLX5_LAG_MODE_MPESW: return "multiport_eswitch";
+	default: return "invalid";
+	}
 
 	return NULL;
 }
@@ -43,11 +44,11 @@ static int port_sel_mode_show(struct seq_file *file, void *priv)
 	ldev = dev->priv.lag;
 	mutex_lock(&ldev->lock);
 	if (__mlx5_lag_is_active(ldev))
-		mode = get_str_port_sel_mode(ldev->mode_flags);
+		mode = mlx5_get_str_port_sel_mode(ldev);
 	else
 		ret = -EINVAL;
 	mutex_unlock(&ldev->lock);
-	if (ret || !mode)
+	if (ret)
 		return ret;
 
 	seq_printf(file, "%s\n", mode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 5c3900586d23..552b6e26e701 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -41,6 +41,7 @@
 #include "esw/acl/ofld.h"
 #include "lag.h"
 #include "mp.h"
+#include "mpesw.h"
 
 enum {
 	MLX5_LAG_EGRESS_PORT_1 = 1,
@@ -58,6 +59,9 @@ static int get_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags)
 	if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags))
 		return MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT;
 
+	if (mode == MLX5_LAG_MODE_MPESW)
+		return MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_MPESW;
+
 	return MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY;
 }
 
@@ -196,7 +200,8 @@ static void mlx5_ldev_free(struct kref *ref)
 	if (ldev->nb.notifier_call)
 		unregister_netdevice_notifier_net(&init_net, &ldev->nb);
 	mlx5_lag_mp_cleanup(ldev);
-	cancel_delayed_work_sync(&ldev->bond_work);
+	mlx5_lag_mpesw_cleanup(ldev);
+	cancel_work_sync(&ldev->mpesw_work);
 	destroy_workqueue(ldev->wq);
 	mutex_destroy(&ldev->lock);
 	kfree(ldev);
@@ -242,6 +247,8 @@ static struct mlx5_lag *mlx5_lag_dev_alloc(struct mlx5_core_dev *dev)
 	if (err)
 		mlx5_core_err(dev, "Failed to init multipath lag err=%d\n",
 			      err);
+
+	mlx5_lag_mpesw_init(ldev);
 	ldev->ports = MLX5_CAP_GEN(dev, num_lag_ports);
 	ldev->buckets = 1;
 
@@ -442,16 +449,19 @@ static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
 	return 0;
 }
 
-static int mlx5_lag_set_port_sel_mode_offloads(struct mlx5_lag *ldev,
-					       struct lag_tracker *tracker, unsigned long *flags)
+static void mlx5_lag_set_port_sel_mode_offloads(struct mlx5_lag *ldev,
+						struct lag_tracker *tracker,
+						enum mlx5_lag_mode mode,
+						unsigned long *flags)
 {
 	struct lag_func *dev0 = &ldev->pf[MLX5_LAG_P1];
 
+	if (mode == MLX5_LAG_MODE_MPESW)
+		return;
+
 	if (MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) &&
 	    tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH)
 		set_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, flags);
-
-	return 0;
 }
 
 static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
@@ -467,14 +477,20 @@ static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 	if (roce_lag)
 		return mlx5_lag_set_port_sel_mode_roce(ldev, flags);
 
-	return mlx5_lag_set_port_sel_mode_offloads(ldev, tracker, flags);
+	mlx5_lag_set_port_sel_mode_offloads(ldev, tracker, mode, flags);
+	return 0;
 }
 
-char *get_str_port_sel_mode(unsigned long flags)
+char *mlx5_get_str_port_sel_mode(struct mlx5_lag *ldev)
 {
-	if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags))
-		return "hash";
-	return "queue_affinity";
+	int port_sel_mode = get_port_sel_mode(ldev->mode, ldev->mode_flags);
+
+	switch (port_sel_mode) {
+	case MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY: return "queue_affinity";
+	case MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT: return "hash";
+	case MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_MPESW: return "mpesw";
+	default: return "invalid";
+	}
 }
 
 static int mlx5_create_lag(struct mlx5_lag *ldev,
@@ -488,9 +504,10 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 	u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {};
 	int err;
 
-	mlx5_lag_print_mapping(dev0, ldev, tracker, flags);
+	if (tracker)
+		mlx5_lag_print_mapping(dev0, ldev, tracker, flags);
 	mlx5_core_info(dev0, "shared_fdb:%d mode:%s\n",
-		       shared_fdb, get_str_port_sel_mode(flags));
+		       shared_fdb, mlx5_get_str_port_sel_mode(ldev));
 
 	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map, mode, flags);
 	if (err) {
@@ -526,22 +543,24 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 {
 	bool roce_lag = mode == MLX5_LAG_MODE_ROCE;
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
-	unsigned long flags;
+	unsigned long flags = 0;
 	int err;
 
 	err = mlx5_lag_set_flags(ldev, mode, tracker, shared_fdb, &flags);
 	if (err)
 		return err;
 
-	mlx5_infer_tx_affinity_mapping(tracker, ldev->ports, ldev->buckets, ldev->v2p_map);
-	if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) {
-		err = mlx5_lag_port_sel_create(ldev, tracker->hash_type,
-					       ldev->v2p_map);
-		if (err) {
-			mlx5_core_err(dev0,
-				      "Failed to create LAG port selection(%d)\n",
-				      err);
-			return err;
+	if (mode != MLX5_LAG_MODE_MPESW) {
+		mlx5_infer_tx_affinity_mapping(tracker, ldev->ports, ldev->buckets, ldev->v2p_map);
+		if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) {
+			err = mlx5_lag_port_sel_create(ldev, tracker->hash_type,
+						       ldev->v2p_map);
+			if (err) {
+				mlx5_core_err(dev0,
+					      "Failed to create LAG port selection(%d)\n",
+					      err);
+				return err;
+			}
 		}
 	}
 
@@ -559,7 +578,7 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 		return err;
 	}
 
-	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP &&
+	if (tracker && tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP &&
 	    !roce_lag)
 		mlx5_lag_drop_rule_setup(ldev, tracker);
 
@@ -675,7 +694,7 @@ static void mlx5_lag_remove_devices(struct mlx5_lag *ldev)
 	}
 }
 
-static void mlx5_disable_lag(struct mlx5_lag *ldev)
+void mlx5_disable_lag(struct mlx5_lag *ldev)
 {
 	bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
@@ -712,7 +731,7 @@ static void mlx5_disable_lag(struct mlx5_lag *ldev)
 	}
 }
 
-static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
+bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
@@ -748,6 +767,18 @@ static bool mlx5_lag_is_roce_lag(struct mlx5_lag *ldev)
 	return roce_lag;
 }
 
+static bool mlx5_lag_should_modify_lag(struct mlx5_lag *ldev, bool do_bond)
+{
+	return do_bond && __mlx5_lag_is_active(ldev) &&
+	       ldev->mode != MLX5_LAG_MODE_MPESW;
+}
+
+static bool mlx5_lag_should_disable_lag(struct mlx5_lag *ldev, bool do_bond)
+{
+	return !do_bond && __mlx5_lag_is_active(ldev) &&
+	       ldev->mode != MLX5_LAG_MODE_MPESW;
+}
+
 static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
@@ -810,9 +841,9 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 				return;
 			}
 		}
-	} else if (do_bond && __mlx5_lag_is_active(ldev)) {
+	} else if (mlx5_lag_should_modify_lag(ldev, do_bond)) {
 		mlx5_modify_lag(ldev, &tracker);
-	} else if (!do_bond && __mlx5_lag_is_active(ldev)) {
+	} else if (mlx5_lag_should_disable_lag(ldev, do_bond)) {
 		mlx5_disable_lag(ldev);
 	}
 }
@@ -986,6 +1017,7 @@ static int mlx5_handle_changeinfodata_event(struct mlx5_lag *ldev,
 	return 1;
 }
 
+/* this handler is always registered to netdev events */
 static int mlx5_lag_netdev_event(struct notifier_block *this,
 				 unsigned long event, void *ptr)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 244b548e1420..72f70fad4641 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -10,6 +10,7 @@
 #include "mlx5_core.h"
 #include "mp.h"
 #include "port_sel.h"
+#include "mpesw.h"
 
 enum {
 	MLX5_LAG_P1,
@@ -30,6 +31,7 @@ enum mlx5_lag_mode {
 	MLX5_LAG_MODE_ROCE,
 	MLX5_LAG_MODE_SRIOV,
 	MLX5_LAG_MODE_MULTIPATH,
+	MLX5_LAG_MODE_MPESW,
 };
 
 struct lag_func {
@@ -63,11 +65,13 @@ struct mlx5_lag {
 	struct lag_tracker        tracker;
 	struct workqueue_struct   *wq;
 	struct delayed_work       bond_work;
+	struct work_struct	  mpesw_work;
 	struct notifier_block     nb;
 	struct lag_mp             lag_mp;
 	struct mlx5_lag_port_sel  port_sel;
 	/* Protect lag fields/state changes */
 	struct mutex		  lock;
+	struct lag_mpesw	  lag_mpesw;
 };
 
 static inline struct mlx5_lag *
@@ -96,12 +100,16 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 		      bool shared_fdb);
 int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 				struct net_device *ndev);
+bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev);
+void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev);
+int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev);
 
-char *get_str_port_sel_mode(unsigned long flags);
+char *mlx5_get_str_port_sel_mode(struct mlx5_lag *ldev);
 void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
 			   u8 *ports, int *num_enabled);
 
 void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev);
 void mlx5_ldev_remove_debugfs(struct dentry *dbg);
+void mlx5_disable_lag(struct mlx5_lag *ldev);
 
 #endif /* __MLX5_LAG_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
new file mode 100644
index 000000000000..ee4b25a50315
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <linux/netdevice.h>
+#include <net/nexthop.h>
+#include "lag/lag.h"
+#include "eswitch.h"
+#include "lib/mlx5.h"
+
+void mlx5_mpesw_work(struct work_struct *work)
+{
+	struct mlx5_lag *ldev = container_of(work, struct mlx5_lag, mpesw_work);
+
+	mutex_lock(&ldev->lock);
+	mlx5_disable_lag(ldev);
+	mutex_unlock(&ldev->lock);
+}
+
+static void mlx5_lag_disable_mpesw(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev = dev->priv.lag;
+
+	if (!queue_work(ldev->wq, &ldev->mpesw_work))
+		mlx5_core_warn(dev, "failed to queue work\n");
+}
+
+void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev = dev->priv.lag;
+
+	if (!ldev)
+		return;
+
+	mutex_lock(&ldev->lock);
+	if (!atomic_dec_return(&ldev->lag_mpesw.mpesw_rule_count) &&
+	    ldev->mode == MLX5_LAG_MODE_MPESW)
+		mlx5_lag_disable_mpesw(dev);
+	mutex_unlock(&ldev->lock);
+}
+
+int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev = dev->priv.lag;
+	bool shared_fdb;
+	int err = 0;
+
+	if (!ldev)
+		return 0;
+
+	mutex_lock(&ldev->lock);
+	if (atomic_add_return(1, &ldev->lag_mpesw.mpesw_rule_count) != 1)
+		goto out;
+
+	if (ldev->mode != MLX5_LAG_MODE_NONE) {
+		err = -EINVAL;
+		goto out;
+	}
+	shared_fdb = mlx5_shared_fdb_supported(ldev);
+	err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, shared_fdb);
+	if (err)
+		mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err);
+
+out:
+	mutex_unlock(&ldev->lock);
+	return err;
+}
+
+int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev)
+{
+	struct mlx5_lag *ldev = mdev->priv.lag;
+
+	if (!netif_is_bond_master(out_dev) || !ldev)
+		return 0;
+
+	mutex_lock(&ldev->lock);
+	if (ldev->mode == MLX5_LAG_MODE_MPESW) {
+		mutex_unlock(&ldev->lock);
+		return -EOPNOTSUPP;
+	}
+	mutex_unlock(&ldev->lock);
+	return 0;
+}
+
+bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev)
+{
+	bool ret;
+
+	ret = dev->priv.lag && dev->priv.lag->mode == MLX5_LAG_MODE_MPESW;
+	return ret;
+}
+
+void mlx5_lag_mpesw_init(struct mlx5_lag *ldev)
+{
+	INIT_WORK(&ldev->mpesw_work, mlx5_mpesw_work);
+	atomic_set(&ldev->lag_mpesw.mpesw_rule_count, 0);
+}
+
+void mlx5_lag_mpesw_cleanup(struct mlx5_lag *ldev)
+{
+	cancel_delayed_work_sync(&ldev->bond_work);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
new file mode 100644
index 000000000000..d39a02280e29
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_LAG_MPESW_H__
+#define __MLX5_LAG_MPESW_H__
+
+#include "lag.h"
+#include "mlx5_core.h"
+
+struct lag_mpesw {
+	struct work_struct mpesw_work;
+	atomic_t mpesw_rule_count;
+};
+
+void mlx5_mpesw_work(struct work_struct *work);
+int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev);
+bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev);
+#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
+void mlx5_lag_mpesw_init(struct mlx5_lag *ldev);
+void mlx5_lag_mpesw_cleanup(struct mlx5_lag *ldev);
+#else
+void mlx5_lag_mpesw_init(struct mlx5_lag *ldev) {}
+void mlx5_lag_mpesw_cleanup(struct mlx5_lag *ldev) {}
+#endif
+
+#endif /* __MLX5_LAG_MPESW_H__ */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 7bab3e51c61e..78b3d3465dd7 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1359,7 +1359,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vhca_resource_manager[0x1];
 
 	u8         hca_cap_2[0x1];
-	u8         reserved_at_21[0x1];
+	u8         create_lag_when_not_master_up[0x1];
 	u8         dtor[0x1];
 	u8         event_on_vhca_state_teardown_request[0x1];
 	u8         event_on_vhca_state_in_use[0x1];
@@ -10816,7 +10816,8 @@ struct mlx5_ifc_dcbx_param_bits {
 
 enum {
 	MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0,
-	MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT,
+	MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT = 1,
+	MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_MPESW = 2,
 };
 
 struct mlx5_ifc_lagc_bits {
-- 
cgit v1.2.3


From 41929c9f628b9990d33a200c54bb0c919e089aa8 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 6 Apr 2022 22:55:05 +0200
Subject: clocksource/drivers/ixp4xx: Drop boardfile probe path

The boardfiles for IXP4xx have been deleted. Delete all the
quirks and code dealing with that boot path and rely solely on
device tree boot.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20220406205505.2332821-1-linus.walleij@linaro.org
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/clocksource/Kconfig                |  2 +-
 drivers/clocksource/timer-ixp4xx.c         | 25 -------------------------
 include/linux/platform_data/timer-ixp4xx.h | 11 -----------
 3 files changed, 1 insertion(+), 37 deletions(-)
 delete mode 100644 include/linux/platform_data/timer-ixp4xx.h

(limited to 'include/linux')

diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 1589ae7d5abb..8182ff2d12fe 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -80,7 +80,7 @@ config IXP4XX_TIMER
 	bool "Intel XScale IXP4xx timer driver" if COMPILE_TEST
 	depends on HAS_IOMEM
 	select CLKSRC_MMIO
-	select TIMER_OF if OF
+	select TIMER_OF
 	help
 	  Enables support for the Intel XScale IXP4xx SoC timer.
 
diff --git a/drivers/clocksource/timer-ixp4xx.c b/drivers/clocksource/timer-ixp4xx.c
index cbb184953510..720ed70a2964 100644
--- a/drivers/clocksource/timer-ixp4xx.c
+++ b/drivers/clocksource/timer-ixp4xx.c
@@ -19,8 +19,6 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
-/* Goes away with OF conversion */
-#include <linux/platform_data/timer-ixp4xx.h>
 
 /*
  * Constants to make it easy to access Timer Control/Status registers
@@ -263,28 +261,6 @@ static struct platform_driver ixp4xx_timer_driver = {
 };
 builtin_platform_driver(ixp4xx_timer_driver);
 
-/**
- * ixp4xx_timer_setup() - Timer setup function to be called from boardfiles
- * @timerbase: physical base of timer block
- * @timer_irq: Linux IRQ number for the timer
- * @timer_freq: Fixed frequency of the timer
- */
-void __init ixp4xx_timer_setup(resource_size_t timerbase,
-			       int timer_irq,
-			       unsigned int timer_freq)
-{
-	void __iomem *base;
-
-	base = ioremap(timerbase, 0x100);
-	if (!base) {
-		pr_crit("IXP4xx: can't remap timer\n");
-		return;
-	}
-	ixp4xx_timer_register(base, timer_irq, timer_freq);
-}
-EXPORT_SYMBOL_GPL(ixp4xx_timer_setup);
-
-#ifdef CONFIG_OF
 static __init int ixp4xx_of_timer_init(struct device_node *np)
 {
 	void __iomem *base;
@@ -315,4 +291,3 @@ out_unmap:
 	return ret;
 }
 TIMER_OF_DECLARE(ixp4xx, "intel,ixp4xx-timer", ixp4xx_of_timer_init);
-#endif
diff --git a/include/linux/platform_data/timer-ixp4xx.h b/include/linux/platform_data/timer-ixp4xx.h
deleted file mode 100644
index ee92ae7edaed..000000000000
--- a/include/linux/platform_data/timer-ixp4xx.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __TIMER_IXP4XX_H
-#define __TIMER_IXP4XX_H
-
-#include <linux/ioport.h>
-
-void __init ixp4xx_timer_setup(resource_size_t timerbase,
-			       int timer_irq,
-			       unsigned int timer_freq);
-
-#endif
-- 
cgit v1.2.3


From 14362a2541797cf9df0e86fb12dcd7950baf566e Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 11 May 2022 22:02:12 +0300
Subject: fsnotify: introduce mark type iterator

fsnotify_foreach_iter_mark_type() is used to reduce boilerplate code
of iterating all marks of a specific group interested in an event
by consulting the iterator report_mask.

Use an open coded version of that iterator in fsnotify_iter_next()
that collects all marks of the current iteration group without
consulting the iterator report_mask.

At the moment, the two iterator variants are the same, but this
decoupling will allow us to exclude some of the group's marks from
reporting the event, for example for event on child and inode marks
on parent did not request to watch events on children.

Fixes: 2f02fd3fa13e ("fanotify: fix ignore mask logic for events on child and on dir")
Reported-by: Jan Kara <jack@suse.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220511190213.831646-2-amir73il@gmail.com
---
 fs/notify/fanotify/fanotify.c    | 14 +++--------
 fs/notify/fsnotify.c             | 53 ++++++++++++++++++++--------------------
 include/linux/fsnotify_backend.h | 31 +++++++++++++++++------
 3 files changed, 54 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 985e995d2a39..263d303d8f8f 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -319,11 +319,7 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 			return 0;
 	}
 
-	fsnotify_foreach_iter_type(type) {
-		if (!fsnotify_iter_should_report_type(iter_info, type))
-			continue;
-		mark = iter_info->marks[type];
-
+	fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
 		/* Apply ignore mask regardless of ISDIR and ON_CHILD flags */
 		marks_ignored_mask |= mark->ignored_mask;
 
@@ -849,16 +845,14 @@ out:
  */
 static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 {
+	struct fsnotify_mark *mark;
 	int type;
 	__kernel_fsid_t fsid = {};
 
-	fsnotify_foreach_iter_type(type) {
+	fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
 		struct fsnotify_mark_connector *conn;
 
-		if (!fsnotify_iter_should_report_type(iter_info, type))
-			continue;
-
-		conn = READ_ONCE(iter_info->marks[type]->connector);
+		conn = READ_ONCE(mark->connector);
 		/* Mark is just getting destroyed or created? */
 		if (!conn)
 			continue;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 6eee19d15e8c..35740a64ee45 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -335,31 +335,23 @@ static int send_to_group(__u32 mask, const void *data, int data_type,
 	struct fsnotify_mark *mark;
 	int type;
 
-	if (WARN_ON(!iter_info->report_mask))
+	if (!iter_info->report_mask)
 		return 0;
 
 	/* clear ignored on inode modification */
 	if (mask & FS_MODIFY) {
-		fsnotify_foreach_iter_type(type) {
-			if (!fsnotify_iter_should_report_type(iter_info, type))
-				continue;
-			mark = iter_info->marks[type];
-			if (mark &&
-			    !(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
+		fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+			if (!(mark->flags &
+			      FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
 				mark->ignored_mask = 0;
 		}
 	}
 
-	fsnotify_foreach_iter_type(type) {
-		if (!fsnotify_iter_should_report_type(iter_info, type))
-			continue;
-		mark = iter_info->marks[type];
-		/* does the object mark tell us to do something? */
-		if (mark) {
-			group = mark->group;
-			marks_mask |= mark->mask;
-			marks_ignored_mask |= mark->ignored_mask;
-		}
+	/* Are any of the group marks interested in this event? */
+	fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+		group = mark->group;
+		marks_mask |= mark->mask;
+		marks_ignored_mask |= mark->ignored_mask;
 	}
 
 	pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignored_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
@@ -403,11 +395,11 @@ static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark)
 
 /*
  * iter_info is a multi head priority queue of marks.
- * Pick a subset of marks from queue heads, all with the
- * same group and set the report_mask for selected subset.
- * Returns the report_mask of the selected subset.
+ * Pick a subset of marks from queue heads, all with the same group
+ * and set the report_mask to a subset of the selected marks.
+ * Returns false if there are no more groups to iterate.
  */
-static unsigned int fsnotify_iter_select_report_types(
+static bool fsnotify_iter_select_report_types(
 		struct fsnotify_iter_info *iter_info)
 {
 	struct fsnotify_group *max_prio_group = NULL;
@@ -423,30 +415,37 @@ static unsigned int fsnotify_iter_select_report_types(
 	}
 
 	if (!max_prio_group)
-		return 0;
+		return false;
 
 	/* Set the report mask for marks from same group as max prio group */
+	iter_info->current_group = max_prio_group;
 	iter_info->report_mask = 0;
 	fsnotify_foreach_iter_type(type) {
 		mark = iter_info->marks[type];
-		if (mark &&
-		    fsnotify_compare_groups(max_prio_group, mark->group) == 0)
+		if (mark && mark->group == iter_info->current_group)
 			fsnotify_iter_set_report_type(iter_info, type);
 	}
 
-	return iter_info->report_mask;
+	return true;
 }
 
 /*
- * Pop from iter_info multi head queue, the marks that were iterated in the
+ * Pop from iter_info multi head queue, the marks that belong to the group of
  * current iteration step.
  */
 static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
 {
+	struct fsnotify_mark *mark;
 	int type;
 
+	/*
+	 * We cannot use fsnotify_foreach_iter_mark_type() here because we
+	 * may need to advance a mark of type X that belongs to current_group
+	 * but was not selected for reporting.
+	 */
 	fsnotify_foreach_iter_type(type) {
-		if (fsnotify_iter_should_report_type(iter_info, type))
+		mark = iter_info->marks[type];
+		if (mark && mark->group == iter_info->current_group)
 			iter_info->marks[type] =
 				fsnotify_next_mark(iter_info->marks[type]);
 	}
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 9a1a9e78f69f..9560734759fa 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -399,6 +399,7 @@ static inline bool fsnotify_valid_obj_type(unsigned int obj_type)
 
 struct fsnotify_iter_info {
 	struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT];
+	struct fsnotify_group *current_group;
 	unsigned int report_mask;
 	int srcu_idx;
 };
@@ -415,20 +416,31 @@ static inline void fsnotify_iter_set_report_type(
 	iter_info->report_mask |= (1U << iter_type);
 }
 
-static inline void fsnotify_iter_set_report_type_mark(
-		struct fsnotify_iter_info *iter_info, int iter_type,
-		struct fsnotify_mark *mark)
+static inline struct fsnotify_mark *fsnotify_iter_mark(
+		struct fsnotify_iter_info *iter_info, int iter_type)
 {
-	iter_info->marks[iter_type] = mark;
-	iter_info->report_mask |= (1U << iter_type);
+	if (fsnotify_iter_should_report_type(iter_info, iter_type))
+		return iter_info->marks[iter_type];
+	return NULL;
+}
+
+static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type,
+				     struct fsnotify_mark **markp)
+{
+	while (type < FSNOTIFY_ITER_TYPE_COUNT) {
+		*markp = fsnotify_iter_mark(iter, type);
+		if (*markp)
+			break;
+		type++;
+	}
+	return type;
 }
 
 #define FSNOTIFY_ITER_FUNCS(name, NAME) \
 static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \
 		struct fsnotify_iter_info *iter_info) \
 { \
-	return (iter_info->report_mask & (1U << FSNOTIFY_ITER_TYPE_##NAME)) ? \
-		iter_info->marks[FSNOTIFY_ITER_TYPE_##NAME] : NULL; \
+	return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \
 }
 
 FSNOTIFY_ITER_FUNCS(inode, INODE)
@@ -438,6 +450,11 @@ FSNOTIFY_ITER_FUNCS(sb, SB)
 
 #define fsnotify_foreach_iter_type(type) \
 	for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++)
+#define fsnotify_foreach_iter_mark_type(iter, mark, type) \
+	for (type = 0; \
+	     type = fsnotify_iter_step(iter, type, &mark), \
+	     type < FSNOTIFY_ITER_TYPE_COUNT; \
+	     type++)
 
 /*
  * fsnotify_connp_t is what we embed in objects which connector can be attached
-- 
cgit v1.2.3


From e73aaae2fa9024832e1f42e30c787c7baf61d014 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sat, 7 May 2022 14:03:46 +0200
Subject: siphash: use one source of truth for siphash permutations

The SipHash family of permutations is currently used in three places:

- siphash.c itself, used in the ordinary way it was intended.
- random32.c, in a construction from an anonymous contributor.
- random.c, as part of its fast_mix function.

Each one of these places reinvents the wheel with the same C code, same
rotation constants, and same symmetry-breaking constants.

This commit tidies things up a bit by placing macros for the
permutations and constants into siphash.h, where each of the three .c
users can access them. It also leaves a note dissuading more users of
them from emerging.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 drivers/char/random.c   | 30 +++++++-----------------------
 include/linux/prandom.h | 23 +++++++----------------
 include/linux/siphash.h | 28 ++++++++++++++++++++++++++++
 lib/siphash.c           | 32 ++++++++++----------------------
 4 files changed, 52 insertions(+), 61 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 8be3efd65ef2..c1763bcbcaed 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -52,6 +52,7 @@
 #include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <linux/suspend.h>
+#include <linux/siphash.h>
 #include <crypto/chacha.h>
 #include <crypto/blake2s.h>
 #include <asm/processor.h>
@@ -1086,12 +1087,11 @@ struct fast_pool {
 
 static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = {
 #ifdef CONFIG_64BIT
-	/* SipHash constants */
-	.pool = { 0x736f6d6570736575UL, 0x646f72616e646f6dUL,
-		  0x6c7967656e657261UL, 0x7465646279746573UL }
+#define FASTMIX_PERM SIPHASH_PERMUTATION
+	.pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 }
 #else
-	/* HalfSipHash constants */
-	.pool = { 0, 0, 0x6c796765U, 0x74656462U }
+#define FASTMIX_PERM HSIPHASH_PERMUTATION
+	.pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 }
 #endif
 };
 
@@ -1103,27 +1103,11 @@ static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = {
  */
 static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2)
 {
-#ifdef CONFIG_64BIT
-#define PERM() do { \
-	s[0] += s[1]; s[1] = rol64(s[1], 13); s[1] ^= s[0]; s[0] = rol64(s[0], 32); \
-	s[2] += s[3]; s[3] = rol64(s[3], 16); s[3] ^= s[2]; \
-	s[0] += s[3]; s[3] = rol64(s[3], 21); s[3] ^= s[0]; \
-	s[2] += s[1]; s[1] = rol64(s[1], 17); s[1] ^= s[2]; s[2] = rol64(s[2], 32); \
-} while (0)
-#else
-#define PERM() do { \
-	s[0] += s[1]; s[1] = rol32(s[1],  5); s[1] ^= s[0]; s[0] = rol32(s[0], 16); \
-	s[2] += s[3]; s[3] = rol32(s[3],  8); s[3] ^= s[2]; \
-	s[0] += s[3]; s[3] = rol32(s[3],  7); s[3] ^= s[0]; \
-	s[2] += s[1]; s[1] = rol32(s[1], 13); s[1] ^= s[2]; s[2] = rol32(s[2], 16); \
-} while (0)
-#endif
-
 	s[3] ^= v1;
-	PERM();
+	FASTMIX_PERM(s[0], s[1], s[2], s[3]);
 	s[0] ^= v1;
 	s[3] ^= v2;
-	PERM();
+	FASTMIX_PERM(s[0], s[1], s[2], s[3]);
 	s[0] ^= v2;
 }
 
diff --git a/include/linux/prandom.h b/include/linux/prandom.h
index 056d31317e49..a4aadd2dc153 100644
--- a/include/linux/prandom.h
+++ b/include/linux/prandom.h
@@ -10,6 +10,7 @@
 
 #include <linux/types.h>
 #include <linux/percpu.h>
+#include <linux/siphash.h>
 
 u32 prandom_u32(void);
 void prandom_bytes(void *buf, size_t nbytes);
@@ -27,15 +28,10 @@ DECLARE_PER_CPU(unsigned long, net_rand_noise);
  * The core SipHash round function.  Each line can be executed in
  * parallel given enough CPU resources.
  */
-#define PRND_SIPROUND(v0, v1, v2, v3) ( \
-	v0 += v1, v1 = rol64(v1, 13),  v2 += v3, v3 = rol64(v3, 16), \
-	v1 ^= v0, v0 = rol64(v0, 32),  v3 ^= v2,                     \
-	v0 += v3, v3 = rol64(v3, 21),  v2 += v1, v1 = rol64(v1, 17), \
-	v3 ^= v0,                      v1 ^= v2, v2 = rol64(v2, 32)  \
-)
+#define PRND_SIPROUND(v0, v1, v2, v3) SIPHASH_PERMUTATION(v0, v1, v2, v3)
 
-#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261)
-#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573)
+#define PRND_K0 (SIPHASH_CONST_0 ^ SIPHASH_CONST_2)
+#define PRND_K1 (SIPHASH_CONST_1 ^ SIPHASH_CONST_3)
 
 #elif BITS_PER_LONG == 32
 /*
@@ -43,14 +39,9 @@ DECLARE_PER_CPU(unsigned long, net_rand_noise);
  * This is weaker, but 32-bit machines are not used for high-traffic
  * applications, so there is less output for an attacker to analyze.
  */
-#define PRND_SIPROUND(v0, v1, v2, v3) ( \
-	v0 += v1, v1 = rol32(v1,  5),  v2 += v3, v3 = rol32(v3,  8), \
-	v1 ^= v0, v0 = rol32(v0, 16),  v3 ^= v2,                     \
-	v0 += v3, v3 = rol32(v3,  7),  v2 += v1, v1 = rol32(v1, 13), \
-	v3 ^= v0,                      v1 ^= v2, v2 = rol32(v2, 16)  \
-)
-#define PRND_K0 0x6c796765
-#define PRND_K1 0x74656462
+#define PRND_SIPROUND(v0, v1, v2, v3) HSIPHASH_PERMUTATION(v0, v1, v2, v3)
+#define PRND_K0 (HSIPHASH_CONST_0 ^ HSIPHASH_CONST_2)
+#define PRND_K1 (HSIPHASH_CONST_1 ^ HSIPHASH_CONST_3)
 
 #else
 #error Unsupported BITS_PER_LONG
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index cce8a9acc76c..3af1428da559 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -138,4 +138,32 @@ static inline u32 hsiphash(const void *data, size_t len,
 	return ___hsiphash_aligned(data, len, key);
 }
 
+/*
+ * These macros expose the raw SipHash and HalfSipHash permutations.
+ * Do not use them directly! If you think you have a use for them,
+ * be sure to CC the maintainer of this file explaining why.
+ */
+
+#define SIPHASH_PERMUTATION(a, b, c, d) ( \
+	(a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \
+	(c) += (d), (d) = rol64((d), 16), (d) ^= (c), \
+	(a) += (d), (d) = rol64((d), 21), (d) ^= (a), \
+	(c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32))
+
+#define SIPHASH_CONST_0 0x736f6d6570736575ULL
+#define SIPHASH_CONST_1 0x646f72616e646f6dULL
+#define SIPHASH_CONST_2 0x6c7967656e657261ULL
+#define SIPHASH_CONST_3 0x7465646279746573ULL
+
+#define HSIPHASH_PERMUTATION(a, b, c, d) ( \
+	(a) += (b), (b) = rol32((b), 5), (b) ^= (a), (a) = rol32((a), 16), \
+	(c) += (d), (d) = rol32((d), 8), (d) ^= (c), \
+	(a) += (d), (d) = rol32((d), 7), (d) ^= (a), \
+	(c) += (b), (b) = rol32((b), 13), (b) ^= (c), (c) = rol32((c), 16))
+
+#define HSIPHASH_CONST_0 0U
+#define HSIPHASH_CONST_1 0U
+#define HSIPHASH_CONST_2 0x6c796765U
+#define HSIPHASH_CONST_3 0x74656462U
+
 #endif /* _LINUX_SIPHASH_H */
diff --git a/lib/siphash.c b/lib/siphash.c
index 72b9068ab57b..71d315a6ad62 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -18,19 +18,13 @@
 #include <asm/word-at-a-time.h>
 #endif
 
-#define SIPROUND \
-	do { \
-	v0 += v1; v1 = rol64(v1, 13); v1 ^= v0; v0 = rol64(v0, 32); \
-	v2 += v3; v3 = rol64(v3, 16); v3 ^= v2; \
-	v0 += v3; v3 = rol64(v3, 21); v3 ^= v0; \
-	v2 += v1; v1 = rol64(v1, 17); v1 ^= v2; v2 = rol64(v2, 32); \
-	} while (0)
+#define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3)
 
 #define PREAMBLE(len) \
-	u64 v0 = 0x736f6d6570736575ULL; \
-	u64 v1 = 0x646f72616e646f6dULL; \
-	u64 v2 = 0x6c7967656e657261ULL; \
-	u64 v3 = 0x7465646279746573ULL; \
+	u64 v0 = SIPHASH_CONST_0; \
+	u64 v1 = SIPHASH_CONST_1; \
+	u64 v2 = SIPHASH_CONST_2; \
+	u64 v3 = SIPHASH_CONST_3; \
 	u64 b = ((u64)(len)) << 56; \
 	v3 ^= key->key[1]; \
 	v2 ^= key->key[0]; \
@@ -389,19 +383,13 @@ u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third,
 }
 EXPORT_SYMBOL(hsiphash_4u32);
 #else
-#define HSIPROUND \
-	do { \
-	v0 += v1; v1 = rol32(v1, 5); v1 ^= v0; v0 = rol32(v0, 16); \
-	v2 += v3; v3 = rol32(v3, 8); v3 ^= v2; \
-	v0 += v3; v3 = rol32(v3, 7); v3 ^= v0; \
-	v2 += v1; v1 = rol32(v1, 13); v1 ^= v2; v2 = rol32(v2, 16); \
-	} while (0)
+#define HSIPROUND HSIPHASH_PERMUTATION(v0, v1, v2, v3)
 
 #define HPREAMBLE(len) \
-	u32 v0 = 0; \
-	u32 v1 = 0; \
-	u32 v2 = 0x6c796765U; \
-	u32 v3 = 0x74656462U; \
+	u32 v0 = HSIPHASH_CONST_0; \
+	u32 v1 = HSIPHASH_CONST_1; \
+	u32 v2 = HSIPHASH_CONST_2; \
+	u32 v3 = HSIPHASH_CONST_3; \
 	u32 b = ((u32)(len)) << 24; \
 	v3 ^= key->key[1]; \
 	v2 ^= key->key[0]; \
-- 
cgit v1.2.3


From d4150779e60fb6c49be25572596b2cdfc5d46a09 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 11 May 2022 16:11:29 +0200
Subject: random32: use real rng for non-deterministic randomness
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

random32.c has two random number generators in it: one that is meant to
be used deterministically, with some predefined seed, and one that does
the same exact thing as random.c, except does it poorly. The first one
has some use cases. The second one no longer does and can be replaced
with calls to random.c's proper random number generator.

The relatively recent siphash-based bad random32.c code was added in
response to concerns that the prior random32.c was too deterministic.
Out of fears that random.c was (at the time) too slow, this code was
anonymously contributed. Then out of that emerged a kind of shadow
entropy gathering system, with its own tentacles throughout various net
code, added willy nilly.

Stop👏making👏bespoke👏random👏number👏generators👏.

Fortunately, recent advances in random.c mean that we can stop playing
with this sketchiness, and just use get_random_u32(), which is now fast
enough. In micro benchmarks using RDPMC, I'm seeing the same median
cycle count between the two functions, with the mean being _slightly_
higher due to batches refilling (which we can optimize further need be).
However, when doing *real* benchmarks of the net functions that actually
use these random numbers, the mean cycles actually *decreased* slightly
(with the median still staying the same), likely because the additional
prandom code means icache misses and complexity, whereas random.c is
generally already being used by something else nearby.

The biggest benefit of this is that there are many users of prandom who
probably should be using cryptographically secure random numbers. This
makes all of those accidental cases become secure by just flipping a
switch. Later on, we can do a tree-wide cleanup to remove the static
inline wrapper functions that this commit adds.

There are also some low-ish hanging fruits for making this even faster
in the future: a get_random_u16() function for use in the networking
stack will give a 2x performance boost there, using SIMD for ChaCha20
will let us compute 4 or 8 or 16 blocks of output in parallel, instead
of just one, giving us large buffers for cheap, and introducing a
get_random_*_bh() function that assumes irqs are already disabled will
shave off a few cycles for ordinary calls. These are things we can chip
away at down the road.

Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 include/linux/prandom.h |  52 +-------
 kernel/time/timer.c     |   2 -
 lib/random32.c          | 347 +-----------------------------------------------
 net/core/dev.c          |   3 -
 net/ipv4/devinet.c      |   4 +-
 net/ipv6/addrconf.c     |   2 -
 6 files changed, 15 insertions(+), 395 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/prandom.h b/include/linux/prandom.h
index a4aadd2dc153..deace5fb4e62 100644
--- a/include/linux/prandom.h
+++ b/include/linux/prandom.h
@@ -10,53 +10,16 @@
 
 #include <linux/types.h>
 #include <linux/percpu.h>
-#include <linux/siphash.h>
+#include <linux/random.h>
 
-u32 prandom_u32(void);
-void prandom_bytes(void *buf, size_t nbytes);
-void prandom_seed(u32 seed);
-void prandom_reseed_late(void);
-
-DECLARE_PER_CPU(unsigned long, net_rand_noise);
-
-#define PRANDOM_ADD_NOISE(a, b, c, d) \
-	prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \
-			      (unsigned long)(c), (unsigned long)(d))
-
-#if BITS_PER_LONG == 64
-/*
- * The core SipHash round function.  Each line can be executed in
- * parallel given enough CPU resources.
- */
-#define PRND_SIPROUND(v0, v1, v2, v3) SIPHASH_PERMUTATION(v0, v1, v2, v3)
-
-#define PRND_K0 (SIPHASH_CONST_0 ^ SIPHASH_CONST_2)
-#define PRND_K1 (SIPHASH_CONST_1 ^ SIPHASH_CONST_3)
-
-#elif BITS_PER_LONG == 32
-/*
- * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash.
- * This is weaker, but 32-bit machines are not used for high-traffic
- * applications, so there is less output for an attacker to analyze.
- */
-#define PRND_SIPROUND(v0, v1, v2, v3) HSIPHASH_PERMUTATION(v0, v1, v2, v3)
-#define PRND_K0 (HSIPHASH_CONST_0 ^ HSIPHASH_CONST_2)
-#define PRND_K1 (HSIPHASH_CONST_1 ^ HSIPHASH_CONST_3)
-
-#else
-#error Unsupported BITS_PER_LONG
-#endif
+static inline u32 prandom_u32(void)
+{
+	return get_random_u32();
+}
 
-static inline void prandom_u32_add_noise(unsigned long a, unsigned long b,
-					 unsigned long c, unsigned long d)
+static inline void prandom_bytes(void *buf, size_t nbytes)
 {
-	/*
-	 * This is not used cryptographically; it's just
-	 * a convenient 4-word hash function. (3 xor, 2 add, 2 rol)
-	 */
-	a ^= raw_cpu_read(net_rand_noise);
-	PRND_SIPROUND(a, b, c, d);
-	raw_cpu_write(net_rand_noise, d);
+	return get_random_bytes(buf, nbytes);
 }
 
 struct rnd_state {
@@ -108,7 +71,6 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 	state->s2 = __seed(i,   8U);
 	state->s3 = __seed(i,  16U);
 	state->s4 = __seed(i, 128U);
-	PRANDOM_ADD_NOISE(state, i, 0, 0);
 }
 
 /* Pseudo random number generator from numerical recipes. */
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 9dd2a39cb3b0..c12fe329c9ff 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1780,8 +1780,6 @@ void update_process_times(int user_tick)
 {
 	struct task_struct *p = current;
 
-	PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0);
-
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
 	run_local_timers();
diff --git a/lib/random32.c b/lib/random32.c
index 976632003ec6..d5d9029362cb 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -245,25 +245,13 @@ static struct prandom_test2 {
 	{  407983964U, 921U,  728767059U },
 };
 
-static u32 __extract_hwseed(void)
-{
-	unsigned int val = 0;
-
-	(void)(arch_get_random_seed_int(&val) ||
-	       arch_get_random_int(&val));
-
-	return val;
-}
-
-static void prandom_seed_early(struct rnd_state *state, u32 seed,
-			       bool mix_with_hwseed)
+static void prandom_state_selftest_seed(struct rnd_state *state, u32 seed)
 {
 #define LCG(x)	 ((x) * 69069U)	/* super-duper LCG */
-#define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0)
-	state->s1 = __seed(HWSEED() ^ LCG(seed),        2U);
-	state->s2 = __seed(HWSEED() ^ LCG(state->s1),   8U);
-	state->s3 = __seed(HWSEED() ^ LCG(state->s2),  16U);
-	state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U);
+	state->s1 = __seed(LCG(seed),        2U);
+	state->s2 = __seed(LCG(state->s1),   8U);
+	state->s3 = __seed(LCG(state->s2),  16U);
+	state->s4 = __seed(LCG(state->s3), 128U);
 }
 
 static int __init prandom_state_selftest(void)
@@ -274,7 +262,7 @@ static int __init prandom_state_selftest(void)
 	for (i = 0; i < ARRAY_SIZE(test1); i++) {
 		struct rnd_state state;
 
-		prandom_seed_early(&state, test1[i].seed, false);
+		prandom_state_selftest_seed(&state, test1[i].seed);
 		prandom_warmup(&state);
 
 		if (test1[i].result != prandom_u32_state(&state))
@@ -289,7 +277,7 @@ static int __init prandom_state_selftest(void)
 	for (i = 0; i < ARRAY_SIZE(test2); i++) {
 		struct rnd_state state;
 
-		prandom_seed_early(&state, test2[i].seed, false);
+		prandom_state_selftest_seed(&state, test2[i].seed);
 		prandom_warmup(&state);
 
 		for (j = 0; j < test2[i].iteration - 1; j++)
@@ -310,324 +298,3 @@ static int __init prandom_state_selftest(void)
 }
 core_initcall(prandom_state_selftest);
 #endif
-
-/*
- * The prandom_u32() implementation is now completely separate from the
- * prandom_state() functions, which are retained (for now) for compatibility.
- *
- * Because of (ab)use in the networking code for choosing random TCP/UDP port
- * numbers, which open DoS possibilities if guessable, we want something
- * stronger than a standard PRNG.  But the performance requirements of
- * the network code do not allow robust crypto for this application.
- *
- * So this is a homebrew Junior Spaceman implementation, based on the
- * lowest-latency trustworthy crypto primitive available, SipHash.
- * (The authors of SipHash have not been consulted about this abuse of
- * their work.)
- *
- * Standard SipHash-2-4 uses 2n+4 rounds to hash n words of input to
- * one word of output.  This abbreviated version uses 2 rounds per word
- * of output.
- */
-
-struct siprand_state {
-	unsigned long v0;
-	unsigned long v1;
-	unsigned long v2;
-	unsigned long v3;
-};
-
-static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy;
-DEFINE_PER_CPU(unsigned long, net_rand_noise);
-EXPORT_PER_CPU_SYMBOL(net_rand_noise);
-
-/*
- * This is the core CPRNG function.  As "pseudorandom", this is not used
- * for truly valuable things, just intended to be a PITA to guess.
- * For maximum speed, we do just two SipHash rounds per word.  This is
- * the same rate as 4 rounds per 64 bits that SipHash normally uses,
- * so hopefully it's reasonably secure.
- *
- * There are two changes from the official SipHash finalization:
- * - We omit some constants XORed with v2 in the SipHash spec as irrelevant;
- *   they are there only to make the output rounds distinct from the input
- *   rounds, and this application has no input rounds.
- * - Rather than returning v0^v1^v2^v3, return v1+v3.
- *   If you look at the SipHash round, the last operation on v3 is
- *   "v3 ^= v0", so "v0 ^ v3" just undoes that, a waste of time.
- *   Likewise "v1 ^= v2".  (The rotate of v2 makes a difference, but
- *   it still cancels out half of the bits in v2 for no benefit.)
- *   Second, since the last combining operation was xor, continue the
- *   pattern of alternating xor/add for a tiny bit of extra non-linearity.
- */
-static inline u32 siprand_u32(struct siprand_state *s)
-{
-	unsigned long v0 = s->v0, v1 = s->v1, v2 = s->v2, v3 = s->v3;
-	unsigned long n = raw_cpu_read(net_rand_noise);
-
-	v3 ^= n;
-	PRND_SIPROUND(v0, v1, v2, v3);
-	PRND_SIPROUND(v0, v1, v2, v3);
-	v0 ^= n;
-	s->v0 = v0;  s->v1 = v1;  s->v2 = v2;  s->v3 = v3;
-	return v1 + v3;
-}
-
-
-/**
- *	prandom_u32 - pseudo random number generator
- *
- *	A 32 bit pseudo-random number is generated using a fast
- *	algorithm suitable for simulation. This algorithm is NOT
- *	considered safe for cryptographic use.
- */
-u32 prandom_u32(void)
-{
-	struct siprand_state *state = get_cpu_ptr(&net_rand_state);
-	u32 res = siprand_u32(state);
-
-	put_cpu_ptr(&net_rand_state);
-	return res;
-}
-EXPORT_SYMBOL(prandom_u32);
-
-/**
- *	prandom_bytes - get the requested number of pseudo-random bytes
- *	@buf: where to copy the pseudo-random bytes to
- *	@bytes: the requested number of bytes
- */
-void prandom_bytes(void *buf, size_t bytes)
-{
-	struct siprand_state *state = get_cpu_ptr(&net_rand_state);
-	u8 *ptr = buf;
-
-	while (bytes >= sizeof(u32)) {
-		put_unaligned(siprand_u32(state), (u32 *)ptr);
-		ptr += sizeof(u32);
-		bytes -= sizeof(u32);
-	}
-
-	if (bytes > 0) {
-		u32 rem = siprand_u32(state);
-
-		do {
-			*ptr++ = (u8)rem;
-			rem >>= BITS_PER_BYTE;
-		} while (--bytes > 0);
-	}
-	put_cpu_ptr(&net_rand_state);
-}
-EXPORT_SYMBOL(prandom_bytes);
-
-/**
- *	prandom_seed - add entropy to pseudo random number generator
- *	@entropy: entropy value
- *
- *	Add some additional seed material to the prandom pool.
- *	The "entropy" is actually our IP address (the only caller is
- *	the network code), not for unpredictability, but to ensure that
- *	different machines are initialized differently.
- */
-void prandom_seed(u32 entropy)
-{
-	int i;
-
-	add_device_randomness(&entropy, sizeof(entropy));
-
-	for_each_possible_cpu(i) {
-		struct siprand_state *state = per_cpu_ptr(&net_rand_state, i);
-		unsigned long v0 = state->v0, v1 = state->v1;
-		unsigned long v2 = state->v2, v3 = state->v3;
-
-		do {
-			v3 ^= entropy;
-			PRND_SIPROUND(v0, v1, v2, v3);
-			PRND_SIPROUND(v0, v1, v2, v3);
-			v0 ^= entropy;
-		} while (unlikely(!v0 || !v1 || !v2 || !v3));
-
-		WRITE_ONCE(state->v0, v0);
-		WRITE_ONCE(state->v1, v1);
-		WRITE_ONCE(state->v2, v2);
-		WRITE_ONCE(state->v3, v3);
-	}
-}
-EXPORT_SYMBOL(prandom_seed);
-
-/*
- *	Generate some initially weak seeding values to allow
- *	the prandom_u32() engine to be started.
- */
-static int __init prandom_init_early(void)
-{
-	int i;
-	unsigned long v0, v1, v2, v3;
-
-	if (!arch_get_random_long(&v0))
-		v0 = jiffies;
-	if (!arch_get_random_long(&v1))
-		v1 = random_get_entropy();
-	v2 = v0 ^ PRND_K0;
-	v3 = v1 ^ PRND_K1;
-
-	for_each_possible_cpu(i) {
-		struct siprand_state *state;
-
-		v3 ^= i;
-		PRND_SIPROUND(v0, v1, v2, v3);
-		PRND_SIPROUND(v0, v1, v2, v3);
-		v0 ^= i;
-
-		state = per_cpu_ptr(&net_rand_state, i);
-		state->v0 = v0;  state->v1 = v1;
-		state->v2 = v2;  state->v3 = v3;
-	}
-
-	return 0;
-}
-core_initcall(prandom_init_early);
-
-
-/* Stronger reseeding when available, and periodically thereafter. */
-static void prandom_reseed(struct timer_list *unused);
-
-static DEFINE_TIMER(seed_timer, prandom_reseed);
-
-static void prandom_reseed(struct timer_list *unused)
-{
-	unsigned long expires;
-	int i;
-
-	/*
-	 * Reinitialize each CPU's PRNG with 128 bits of key.
-	 * No locking on the CPUs, but then somewhat random results are,
-	 * well, expected.
-	 */
-	for_each_possible_cpu(i) {
-		struct siprand_state *state;
-		unsigned long v0 = get_random_long(), v2 = v0 ^ PRND_K0;
-		unsigned long v1 = get_random_long(), v3 = v1 ^ PRND_K1;
-#if BITS_PER_LONG == 32
-		int j;
-
-		/*
-		 * On 32-bit machines, hash in two extra words to
-		 * approximate 128-bit key length.  Not that the hash
-		 * has that much security, but this prevents a trivial
-		 * 64-bit brute force.
-		 */
-		for (j = 0; j < 2; j++) {
-			unsigned long m = get_random_long();
-
-			v3 ^= m;
-			PRND_SIPROUND(v0, v1, v2, v3);
-			PRND_SIPROUND(v0, v1, v2, v3);
-			v0 ^= m;
-		}
-#endif
-		/*
-		 * Probably impossible in practice, but there is a
-		 * theoretical risk that a race between this reseeding
-		 * and the target CPU writing its state back could
-		 * create the all-zero SipHash fixed point.
-		 *
-		 * To ensure that never happens, ensure the state
-		 * we write contains no zero words.
-		 */
-		state = per_cpu_ptr(&net_rand_state, i);
-		WRITE_ONCE(state->v0, v0 ? v0 : -1ul);
-		WRITE_ONCE(state->v1, v1 ? v1 : -1ul);
-		WRITE_ONCE(state->v2, v2 ? v2 : -1ul);
-		WRITE_ONCE(state->v3, v3 ? v3 : -1ul);
-	}
-
-	/* reseed every ~60 seconds, in [40 .. 80) interval with slack */
-	expires = round_jiffies(jiffies + 40 * HZ + prandom_u32_max(40 * HZ));
-	mod_timer(&seed_timer, expires);
-}
-
-/*
- * The random ready callback can be called from almost any interrupt.
- * To avoid worrying about whether it's safe to delay that interrupt
- * long enough to seed all CPUs, just schedule an immediate timer event.
- */
-static int prandom_timer_start(struct notifier_block *nb,
-			       unsigned long action, void *data)
-{
-	mod_timer(&seed_timer, jiffies);
-	return 0;
-}
-
-#ifdef CONFIG_RANDOM32_SELFTEST
-/* Principle: True 32-bit random numbers will all have 16 differing bits on
- * average. For each 32-bit number, there are 601M numbers differing by 16
- * bits, and 89% of the numbers differ by at least 12 bits. Note that more
- * than 16 differing bits also implies a correlation with inverted bits. Thus
- * we take 1024 random numbers and compare each of them to the other ones,
- * counting the deviation of correlated bits to 16. Constants report 32,
- * counters 32-log2(TEST_SIZE), and pure randoms, around 6 or lower. With the
- * u32 total, TEST_SIZE may be as large as 4096 samples.
- */
-#define TEST_SIZE 1024
-static int __init prandom32_state_selftest(void)
-{
-	unsigned int x, y, bits, samples;
-	u32 xor, flip;
-	u32 total;
-	u32 *data;
-
-	data = kmalloc(sizeof(*data) * TEST_SIZE, GFP_KERNEL);
-	if (!data)
-		return 0;
-
-	for (samples = 0; samples < TEST_SIZE; samples++)
-		data[samples] = prandom_u32();
-
-	flip = total = 0;
-	for (x = 0; x < samples; x++) {
-		for (y = 0; y < samples; y++) {
-			if (x == y)
-				continue;
-			xor = data[x] ^ data[y];
-			flip |= xor;
-			bits = hweight32(xor);
-			total += (bits - 16) * (bits - 16);
-		}
-	}
-
-	/* We'll return the average deviation as 2*sqrt(corr/samples), which
-	 * is also sqrt(4*corr/samples) which provides a better resolution.
-	 */
-	bits = int_sqrt(total / (samples * (samples - 1)) * 4);
-	if (bits > 6)
-		pr_warn("prandom32: self test failed (at least %u bits"
-			" correlated, fixed_mask=%#x fixed_value=%#x\n",
-			bits, ~flip, data[0] & ~flip);
-	else
-		pr_info("prandom32: self test passed (less than %u bits"
-			" correlated)\n",
-			bits+1);
-	kfree(data);
-	return 0;
-}
-core_initcall(prandom32_state_selftest);
-#endif /*  CONFIG_RANDOM32_SELFTEST */
-
-/*
- * Start periodic full reseeding as soon as strong
- * random numbers are available.
- */
-static int __init prandom_init_late(void)
-{
-	static struct notifier_block random_ready = {
-		.notifier_call = prandom_timer_start
-	};
-	int ret = register_random_ready_notifier(&random_ready);
-
-	if (ret == -EALREADY) {
-		prandom_timer_start(&random_ready, 0, NULL);
-		ret = 0;
-	}
-	return ret;
-}
-late_initcall(prandom_init_late);
diff --git a/net/core/dev.c b/net/core/dev.c
index 1461c2d9dec8..19c9beb1136b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3527,7 +3527,6 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
-	PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies);
 	trace_net_dev_start_xmit(skb, dev);
 	rc = netdev_start_xmit(skb, dev, txq, more);
 	trace_net_dev_xmit(skb, rc, dev, len);
@@ -4168,7 +4167,6 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 
-			PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
@@ -4234,7 +4232,6 @@ int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	skb_set_queue_mapping(skb, queue_id);
 	txq = skb_get_tx_queue(dev, skb);
-	PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 
 	local_bh_disable();
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 53a6b14dc50a..3d6d33ac20cc 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -536,10 +536,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 		return ret;
 	}
 
-	if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {
-		prandom_seed((__force u32) ifa->ifa_local);
+	if (!(ifa->ifa_flags & IFA_F_SECONDARY))
 		ifap = last_primary;
-	}
 
 	rcu_assign_pointer(ifa->ifa_next, *ifap);
 	rcu_assign_pointer(*ifap, ifa);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b22504176588..e7c68fa12fae 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3972,8 +3972,6 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 
 	addrconf_join_solict(dev, &ifp->addr);
 
-	prandom_seed((__force u32) ifp->addr.s6_addr32[3]);
-
 	read_lock_bh(&idev->lock);
 	spin_lock(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_DEAD)
-- 
cgit v1.2.3


From 2f14062bb14b0fcfcc21e6dc7d5b5c0d25966164 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 5 May 2022 02:20:22 +0200
Subject: random: handle latent entropy and command line from random_init()

Currently, start_kernel() adds latent entropy and the command line to
the entropy bool *after* the RNG has been initialized, deferring when
it's actually used by things like stack canaries until the next time
the pool is seeded. This surely is not intended.

Rather than splitting up which entropy gets added where and when between
start_kernel() and random_init(), just do everything in random_init(),
which should eliminate these kinds of bugs in the future.

While we're at it, rename the awkwardly titled "rand_initialize()" to
the more standard "random_init()" nomenclature.

Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 arch/openrisc/kernel/head.S |  2 +-
 drivers/char/random.c       | 17 ++++++++++-------
 include/linux/random.h      | 15 +++++++--------
 init/main.c                 | 10 +++-------
 4 files changed, 21 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S
index 871f4c858859..2fa6cefa62ca 100644
--- a/arch/openrisc/kernel/head.S
+++ b/arch/openrisc/kernel/head.S
@@ -525,7 +525,7 @@ _start:
 	 * Start the TTCR as early as possible, so that the RNG can make use of
 	 * measurements of boot time from the earliest opportunity. Especially
 	 * important is that the TTCR does not return zero by the time we reach
-	 * rand_initialize().
+	 * random_init().
 	 */
 	l.movhi r3,hi(SPR_TTMR_CR)
 	l.mtspr r0,r3,SPR_TTMR
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 9024aeba2d28..95982dc08669 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -919,12 +919,13 @@ static struct notifier_block pm_notifier = { .notifier_call = random_pm_notifica
 
 /*
  * The first collection of entropy occurs at system boot while interrupts
- * are still turned off. Here we push in RDSEED, a timestamp, and utsname().
- * Depending on the above configuration knob, RDSEED may be considered
- * sufficient for initialization. Note that much earlier setup may already
- * have pushed entropy into the input pool by the time we get here.
+ * are still turned off. Here we push in latent entropy, RDSEED, a timestamp,
+ * utsname(), and the command line. Depending on the above configuration knob,
+ * RDSEED may be considered sufficient for initialization. Note that much
+ * earlier setup may already have pushed entropy into the input pool by the
+ * time we get here.
  */
-int __init rand_initialize(void)
+int __init random_init(const char *command_line)
 {
 	size_t i;
 	ktime_t now = ktime_get_real();
@@ -946,6 +947,8 @@ int __init rand_initialize(void)
 	}
 	_mix_pool_bytes(&now, sizeof(now));
 	_mix_pool_bytes(utsname(), sizeof(*(utsname())));
+	_mix_pool_bytes(command_line, strlen(command_line));
+	add_latent_entropy();
 
 	if (crng_ready())
 		crng_reseed();
@@ -1685,8 +1688,8 @@ static struct ctl_table random_table[] = {
 };
 
 /*
- * rand_initialize() is called before sysctl_init(),
- * so we cannot call register_sysctl_init() in rand_initialize()
+ * random_init() is called before sysctl_init(),
+ * so we cannot call register_sysctl_init() in random_init()
  */
 static int __init random_sysctls_init(void)
 {
diff --git a/include/linux/random.h b/include/linux/random.h
index f673fbb838b3..b52963955a99 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -14,22 +14,21 @@ struct notifier_block;
 
 extern void add_device_randomness(const void *, size_t);
 extern void add_bootloader_randomness(const void *, size_t);
+extern void add_input_randomness(unsigned int type, unsigned int code,
+				 unsigned int value) __latent_entropy;
+extern void add_interrupt_randomness(int irq) __latent_entropy;
+extern void add_hwgenerator_randomness(const void *buffer, size_t count,
+				       size_t entropy);
 
 #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 static inline void add_latent_entropy(void)
 {
-	add_device_randomness((const void *)&latent_entropy,
-			      sizeof(latent_entropy));
+	add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy));
 }
 #else
 static inline void add_latent_entropy(void) {}
 #endif
 
-extern void add_input_randomness(unsigned int type, unsigned int code,
-				 unsigned int value) __latent_entropy;
-extern void add_interrupt_randomness(int irq) __latent_entropy;
-extern void add_hwgenerator_randomness(const void *buffer, size_t count,
-				       size_t entropy);
 #if IS_ENABLED(CONFIG_VMGENID)
 extern void add_vmfork_randomness(const void *unique_vm_id, size_t size);
 extern int register_random_vmfork_notifier(struct notifier_block *nb);
@@ -41,7 +40,7 @@ static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) {
 
 extern void get_random_bytes(void *buf, size_t nbytes);
 extern int wait_for_random_bytes(void);
-extern int __init rand_initialize(void);
+extern int __init random_init(const char *command_line);
 extern bool rng_is_initialized(void);
 extern int register_random_ready_notifier(struct notifier_block *nb);
 extern int unregister_random_ready_notifier(struct notifier_block *nb);
diff --git a/init/main.c b/init/main.c
index 92783732a36f..f057c49f1d9d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1040,15 +1040,11 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
 	/*
 	 * For best initial stack canary entropy, prepare it after:
 	 * - setup_arch() for any UEFI RNG entropy and boot cmdline access
-	 * - timekeeping_init() for ktime entropy used in rand_initialize()
+	 * - timekeeping_init() for ktime entropy used in random_init()
 	 * - time_init() for making random_get_entropy() work on some platforms
-	 * - rand_initialize() to get any arch-specific entropy like RDRAND
-	 * - add_latent_entropy() to get any latent entropy
-	 * - adding command line entropy
+	 * - random_init() to initialize the RNG from from early entropy sources
 	 */
-	rand_initialize();
-	add_latent_entropy();
-	add_device_randomness(command_line, strlen(command_line));
+	random_init(command_line);
 	boot_init_stack_canary();
 
 	perf_event_init();
-- 
cgit v1.2.3


From 354201c53e61e493017b15327294b0c8ab522d69 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 May 2022 15:09:21 +0200
Subject: nvme: add support for TP4084 - Time-to-Ready Enhancements

Add support for using longer timeouts during controller initialization
and letting the controller come up with namespaces that are not ready
for I/O yet.  We skip these not ready namespaces during scanning and
only bring them online once anoter scan is kicked off by the AEN that
is set when the NRDY bit gets set in the  I/O Command Set Independent
Identify Namespace Data Structure.   This asynchronous probing avoids
blocking the kernel boot when controllers take a very long time to
recover after unclean shutdowns (up to minutes).

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 drivers/nvme/host/constants.c |  1 +
 drivers/nvme/host/core.c      | 76 +++++++++++++++++++++++++++++++++++++++----
 include/linux/nvme.h          | 31 ++++++++++++++++++
 3 files changed, 102 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 1dd1d78de295..4910543f00ff 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -91,6 +91,7 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_NS_WRITE_PROTECTED] = "Namespace is Write Protected",
 	[NVME_SC_CMD_INTERRUPTED] = "Command Interrupted",
 	[NVME_SC_TRANSIENT_TR_ERR] = "Transient Transport Error",
+	[NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY] = "Admin Command Media Not Ready",
 	[NVME_SC_INVALID_IO_CMD_SET] = "Invalid IO Command Set",
 	[NVME_SC_LBA_RANGE] = "LBA Out of Range",
 	[NVME_SC_CAP_EXCEEDED] = "Capacity Exceeded",
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 42f9772abc4d..faeb03271913 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1427,6 +1427,32 @@ out_free_id:
 	return error;
 }
 
+static int nvme_identify_ns_cs_indep(struct nvme_ctrl *ctrl, unsigned nsid,
+			struct nvme_id_ns_cs_indep **id)
+{
+	struct nvme_command c = {
+		.identify.opcode	= nvme_admin_identify,
+		.identify.nsid		= cpu_to_le32(nsid),
+		.identify.cns		= NVME_ID_CNS_NS_CS_INDEP,
+	};
+	int ret;
+
+	*id = kmalloc(sizeof(**id), GFP_KERNEL);
+	if (!*id)
+		return -ENOMEM;
+
+	ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id));
+	if (ret) {
+		dev_warn(ctrl->device,
+			 "Identify namespace (CS independent) failed (%d)\n",
+			 ret);
+		kfree(*id);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
 		unsigned int dword11, void *buffer, size_t buflen, u32 *result)
 {
@@ -2103,10 +2129,9 @@ static const struct block_device_operations nvme_bdev_ops = {
 	.pr_ops		= &nvme_pr_ops,
 };
 
-static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
+static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 timeout, bool enabled)
 {
-	unsigned long timeout =
-		((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
+	unsigned long timeout_jiffies = ((timeout + 1) * HZ / 2) + jiffies;
 	u32 csts, bit = enabled ? NVME_CSTS_RDY : 0;
 	int ret;
 
@@ -2119,7 +2144,7 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
 		usleep_range(1000, 2000);
 		if (fatal_signal_pending(current))
 			return -EINTR;
-		if (time_after(jiffies, timeout)) {
+		if (time_after(jiffies, timeout_jiffies)) {
 			dev_err(ctrl->device,
 				"Device not ready; aborting %s, CSTS=0x%x\n",
 				enabled ? "initialisation" : "reset", csts);
@@ -2150,13 +2175,14 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl)
 	if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
 		msleep(NVME_QUIRK_DELAY_AMOUNT);
 
-	return nvme_wait_ready(ctrl, ctrl->cap, false);
+	return nvme_wait_ready(ctrl, NVME_CAP_TIMEOUT(ctrl->cap), false);
 }
 EXPORT_SYMBOL_GPL(nvme_disable_ctrl);
 
 int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 {
 	unsigned dev_page_min;
+	u32 timeout;
 	int ret;
 
 	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
@@ -2177,6 +2203,27 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 		ctrl->ctrl_config = NVME_CC_CSS_CSI;
 	else
 		ctrl->ctrl_config = NVME_CC_CSS_NVM;
+
+	if (ctrl->cap & NVME_CAP_CRMS_CRWMS) {
+		u32 crto;
+
+		ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto);
+		if (ret) {
+			dev_err(ctrl->device, "Reading CRTO failed (%d)\n",
+				ret);
+			return ret;
+		}
+
+		if (ctrl->cap & NVME_CAP_CRMS_CRIMS) {
+			ctrl->ctrl_config |= NVME_CC_CRIME;
+			timeout = NVME_CRTO_CRIMT(crto);
+		} else {
+			timeout = NVME_CRTO_CRWMT(crto);
+		}
+	} else {
+		timeout = NVME_CAP_TIMEOUT(ctrl->cap);
+	}
+
 	ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
 	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
 	ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
@@ -2185,7 +2232,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)
 		return ret;
-	return nvme_wait_ready(ctrl, ctrl->cap, true);
+	return nvme_wait_ready(ctrl, timeout, true);
 }
 EXPORT_SYMBOL_GPL(nvme_enable_ctrl);
 
@@ -4092,11 +4139,26 @@ out:
 static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 {
 	struct nvme_ns_ids ids = { };
+	struct nvme_id_ns_cs_indep *id;
 	struct nvme_ns *ns;
+	bool ready = true;
 
 	if (nvme_identify_ns_descs(ctrl, nsid, &ids))
 		return;
 
+	/*
+	 * Check if the namespace is ready.  If not ignore it, we will get an
+	 * AEN once it becomes ready and restart the scan.
+	 */
+	if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) &&
+	    !nvme_identify_ns_cs_indep(ctrl, nsid, &id)) {
+		ready = id->nstat & NVME_NSTAT_NRDY;
+		kfree(id);
+	}
+
+	if (!ready)
+		return;
+
 	ns = nvme_find_get_ns(ctrl, nsid);
 	if (ns) {
 		nvme_validate_ns(ns, &ids);
@@ -4841,6 +4903,8 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ns_cs_indep) !=
+			NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns_nvm) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 5f6d432fa06a..29ec3e3481ff 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -137,6 +137,7 @@ enum {
 	NVME_REG_CMBMSC = 0x0050,	/* Controller Memory Buffer Memory
 					 * Space Control
 					 */
+	NVME_REG_CRTO	= 0x0068,	/* Controller Ready Timeouts */
 	NVME_REG_PMRCAP	= 0x0e00,	/* Persistent Memory Capabilities */
 	NVME_REG_PMRCTL	= 0x0e04,	/* Persistent Memory Region Control */
 	NVME_REG_PMRSTS	= 0x0e08,	/* Persistent Memory Region Status */
@@ -161,6 +162,9 @@ enum {
 #define NVME_CMB_BIR(cmbloc)	((cmbloc) & 0x7)
 #define NVME_CMB_OFST(cmbloc)	(((cmbloc) >> 12) & 0xfffff)
 
+#define NVME_CRTO_CRIMT(crto)	((crto) >> 16)
+#define NVME_CRTO_CRWMT(crto)	((crto) & 0xffff)
+
 enum {
 	NVME_CMBSZ_SQS		= 1 << 0,
 	NVME_CMBSZ_CQS		= 1 << 1,
@@ -204,6 +208,7 @@ enum {
 	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
 	NVME_CC_IOSQES		= NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
 	NVME_CC_IOCQES		= NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
+	NVME_CC_CRIME		= 1 << 24,
 };
 
 enum {
@@ -227,6 +232,11 @@ enum {
 	NVME_CAP_CSS_CSI	= 1 << 6,
 };
 
+enum {
+	NVME_CAP_CRMS_CRIMS	= 1ULL << 59,
+	NVME_CAP_CRMS_CRWMS	= 1ULL << 60,
+};
+
 struct nvme_id_power_state {
 	__le16			max_power;	/* centiwatts */
 	__u8			rsvd2;
@@ -414,6 +424,21 @@ struct nvme_id_ns {
 	__u8			vs[3712];
 };
 
+/* I/O Command Set Independent Identify Namespace Data Structure */
+struct nvme_id_ns_cs_indep {
+	__u8			nsfeat;
+	__u8			nmic;
+	__u8			rescap;
+	__u8			fpi;
+	__le32			anagrpid;
+	__u8			nsattr;
+	__u8			rsvd9;
+	__le16			nvmsetid;
+	__le16			endgid;
+	__u8			nstat;
+	__u8			rsvd15[4081];
+};
+
 struct nvme_zns_lbafe {
 	__le64			zsze;
 	__u8			zdes;
@@ -478,6 +503,7 @@ enum {
 	NVME_ID_CNS_NS_DESC_LIST	= 0x03,
 	NVME_ID_CNS_CS_NS		= 0x05,
 	NVME_ID_CNS_CS_CTRL		= 0x06,
+	NVME_ID_CNS_NS_CS_INDEP		= 0x08,
 	NVME_ID_CNS_NS_PRESENT_LIST	= 0x10,
 	NVME_ID_CNS_NS_PRESENT		= 0x11,
 	NVME_ID_CNS_CTRL_NS_LIST	= 0x12,
@@ -531,6 +557,10 @@ enum {
 	NVME_NS_DPS_PI_TYPE3	= 3,
 };
 
+enum {
+	NVME_NSTAT_NRDY		= 1 << 0,
+};
+
 enum {
 	NVME_NVM_NS_16B_GUARD	= 0,
 	NVME_NVM_NS_32B_GUARD	= 1,
@@ -1592,6 +1622,7 @@ enum {
 	NVME_SC_NS_WRITE_PROTECTED	= 0x20,
 	NVME_SC_CMD_INTERRUPTED		= 0x21,
 	NVME_SC_TRANSIENT_TR_ERR	= 0x22,
+	NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY = 0x24,
 	NVME_SC_INVALID_IO_CMD_SET	= 0x2C,
 
 	NVME_SC_LBA_RANGE		= 0x80,
-- 
cgit v1.2.3


From 75dbb685f4e8786c33ddef8279bab0eadfb0731f Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Sat, 14 May 2022 12:16:47 +0200
Subject: libceph: fix potential use-after-free on linger ping and resends

request_reinit() is not only ugly as the comment rightfully suggests,
but also unsafe.  Even though it is called with osdc->lock held for
write in all cases, resetting the OSD request refcount can still race
with handle_reply() and result in use-after-free.  Taking linger ping
as an example:

    handle_timeout thread                     handle_reply thread

                                              down_read(&osdc->lock)
                                              req = lookup_request(...)
                                              ...
                                              finish_request(req)  # unregisters
                                              up_read(&osdc->lock)
                                              __complete_request(req)
                                                linger_ping_cb(req)

      # req->r_kref == 2 because handle_reply still holds its ref

    down_write(&osdc->lock)
    send_linger_ping(lreq)
      req = lreq->ping_req  # same req
      # cancel_linger_request is NOT
      # called - handle_reply already
      # unregistered
      request_reinit(req)
        WARN_ON(req->r_kref != 1)  # fires
        request_init(req)
          kref_init(req->r_kref)

                   # req->r_kref == 1 after kref_init

                                              ceph_osdc_put_request(req)
                                                kref_put(req->r_kref)

            # req->r_kref == 0 after kref_put, req is freed

        <further req initialization/use> !!!

This happens because send_linger_ping() always (re)uses the same OSD
request for watch ping requests, relying on cancel_linger_request() to
unregister it from the OSD client and rip its messages out from the
messenger.  send_linger() does the same for watch/notify registration
and watch reconnect requests.  Unfortunately cancel_request() doesn't
guarantee that after it returns the OSD client would be completely done
with the OSD request -- a ref could still be held and the callback (if
specified) could still be invoked too.

The original motivation for request_reinit() was inability to deal with
allocation failures in send_linger() and send_linger_ping().  Switching
to using osdc->req_mempool (currently only used by CephFS) respects that
and allows us to get rid of request_reinit().

Cc: stable@vger.kernel.org
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Acked-by: Jeff Layton <jlayton@kernel.org>
---
 include/linux/ceph/osd_client.h |   3 +
 net/ceph/osd_client.c           | 302 ++++++++++++++++------------------------
 2 files changed, 122 insertions(+), 183 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 3431011f364d..cba8a6ffc329 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -287,6 +287,9 @@ struct ceph_osd_linger_request {
 	rados_watcherrcb_t errcb;
 	void *data;
 
+	struct ceph_pagelist *request_pl;
+	struct page **notify_id_pages;
+
 	struct page ***preply_pages;
 	size_t *preply_len;
 };
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 83eb97c94e83..4b88f2a4a6e2 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -537,43 +537,6 @@ static void request_init(struct ceph_osd_request *req)
 	target_init(&req->r_t);
 }
 
-/*
- * This is ugly, but it allows us to reuse linger registration and ping
- * requests, keeping the structure of the code around send_linger{_ping}()
- * reasonable.  Setting up a min_nr=2 mempool for each linger request
- * and dealing with copying ops (this blasts req only, watch op remains
- * intact) isn't any better.
- */
-static void request_reinit(struct ceph_osd_request *req)
-{
-	struct ceph_osd_client *osdc = req->r_osdc;
-	bool mempool = req->r_mempool;
-	unsigned int num_ops = req->r_num_ops;
-	u64 snapid = req->r_snapid;
-	struct ceph_snap_context *snapc = req->r_snapc;
-	bool linger = req->r_linger;
-	struct ceph_msg *request_msg = req->r_request;
-	struct ceph_msg *reply_msg = req->r_reply;
-
-	dout("%s req %p\n", __func__, req);
-	WARN_ON(kref_read(&req->r_kref) != 1);
-	request_release_checks(req);
-
-	WARN_ON(kref_read(&request_msg->kref) != 1);
-	WARN_ON(kref_read(&reply_msg->kref) != 1);
-	target_destroy(&req->r_t);
-
-	request_init(req);
-	req->r_osdc = osdc;
-	req->r_mempool = mempool;
-	req->r_num_ops = num_ops;
-	req->r_snapid = snapid;
-	req->r_snapc = snapc;
-	req->r_linger = linger;
-	req->r_request = request_msg;
-	req->r_reply = reply_msg;
-}
-
 struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 					       struct ceph_snap_context *snapc,
 					       unsigned int num_ops,
@@ -918,14 +881,30 @@ EXPORT_SYMBOL(osd_req_op_xattr_init);
  * @watch_opcode: CEPH_OSD_WATCH_OP_*
  */
 static void osd_req_op_watch_init(struct ceph_osd_request *req, int which,
-				  u64 cookie, u8 watch_opcode)
+				  u8 watch_opcode, u64 cookie, u32 gen)
 {
 	struct ceph_osd_req_op *op;
 
 	op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
 	op->watch.cookie = cookie;
 	op->watch.op = watch_opcode;
-	op->watch.gen = 0;
+	op->watch.gen = gen;
+}
+
+/*
+ * prot_ver, timeout and notify payload (may be empty) should already be
+ * encoded in @request_pl
+ */
+static void osd_req_op_notify_init(struct ceph_osd_request *req, int which,
+				   u64 cookie, struct ceph_pagelist *request_pl)
+{
+	struct ceph_osd_req_op *op;
+
+	op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
+	op->notify.cookie = cookie;
+
+	ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl);
+	op->indata_len = request_pl->length;
 }
 
 /*
@@ -2731,10 +2710,13 @@ static void linger_release(struct kref *kref)
 	WARN_ON(!list_empty(&lreq->pending_lworks));
 	WARN_ON(lreq->osd);
 
-	if (lreq->reg_req)
-		ceph_osdc_put_request(lreq->reg_req);
-	if (lreq->ping_req)
-		ceph_osdc_put_request(lreq->ping_req);
+	if (lreq->request_pl)
+		ceph_pagelist_release(lreq->request_pl);
+	if (lreq->notify_id_pages)
+		ceph_release_page_vector(lreq->notify_id_pages, 1);
+
+	ceph_osdc_put_request(lreq->reg_req);
+	ceph_osdc_put_request(lreq->ping_req);
 	target_destroy(&lreq->t);
 	kfree(lreq);
 }
@@ -3003,6 +2985,12 @@ static void linger_commit_cb(struct ceph_osd_request *req)
 	struct ceph_osd_linger_request *lreq = req->r_priv;
 
 	mutex_lock(&lreq->lock);
+	if (req != lreq->reg_req) {
+		dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
+		     __func__, lreq, lreq->linger_id, req, lreq->reg_req);
+		goto out;
+	}
+
 	dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq,
 	     lreq->linger_id, req->r_result);
 	linger_reg_commit_complete(lreq, req->r_result);
@@ -3026,6 +3014,7 @@ static void linger_commit_cb(struct ceph_osd_request *req)
 		}
 	}
 
+out:
 	mutex_unlock(&lreq->lock);
 	linger_put(lreq);
 }
@@ -3048,6 +3037,12 @@ static void linger_reconnect_cb(struct ceph_osd_request *req)
 	struct ceph_osd_linger_request *lreq = req->r_priv;
 
 	mutex_lock(&lreq->lock);
+	if (req != lreq->reg_req) {
+		dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
+		     __func__, lreq, lreq->linger_id, req, lreq->reg_req);
+		goto out;
+	}
+
 	dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__,
 	     lreq, lreq->linger_id, req->r_result, lreq->last_error);
 	if (req->r_result < 0) {
@@ -3057,46 +3052,64 @@ static void linger_reconnect_cb(struct ceph_osd_request *req)
 		}
 	}
 
+out:
 	mutex_unlock(&lreq->lock);
 	linger_put(lreq);
 }
 
 static void send_linger(struct ceph_osd_linger_request *lreq)
 {
-	struct ceph_osd_request *req = lreq->reg_req;
-	struct ceph_osd_req_op *op = &req->r_ops[0];
+	struct ceph_osd_client *osdc = lreq->osdc;
+	struct ceph_osd_request *req;
+	int ret;
 
-	verify_osdc_wrlocked(req->r_osdc);
+	verify_osdc_wrlocked(osdc);
+	mutex_lock(&lreq->lock);
 	dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
 
-	if (req->r_osd)
-		cancel_linger_request(req);
+	if (lreq->reg_req) {
+		if (lreq->reg_req->r_osd)
+			cancel_linger_request(lreq->reg_req);
+		ceph_osdc_put_request(lreq->reg_req);
+	}
+
+	req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO);
+	BUG_ON(!req);
 
-	request_reinit(req);
 	target_copy(&req->r_t, &lreq->t);
 	req->r_mtime = lreq->mtime;
 
-	mutex_lock(&lreq->lock);
 	if (lreq->is_watch && lreq->committed) {
-		WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
-			op->watch.cookie != lreq->linger_id);
-		op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT;
-		op->watch.gen = ++lreq->register_gen;
+		osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT,
+				      lreq->linger_id, ++lreq->register_gen);
 		dout("lreq %p reconnect register_gen %u\n", lreq,
-		     op->watch.gen);
+		     req->r_ops[0].watch.gen);
 		req->r_callback = linger_reconnect_cb;
 	} else {
-		if (!lreq->is_watch)
+		if (lreq->is_watch) {
+			osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH,
+					      lreq->linger_id, 0);
+		} else {
 			lreq->notify_id = 0;
-		else
-			WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH);
+
+			refcount_inc(&lreq->request_pl->refcnt);
+			osd_req_op_notify_init(req, 0, lreq->linger_id,
+					       lreq->request_pl);
+			ceph_osd_data_pages_init(
+			    osd_req_op_data(req, 0, notify, response_data),
+			    lreq->notify_id_pages, PAGE_SIZE, 0, false, false);
+		}
 		dout("lreq %p register\n", lreq);
 		req->r_callback = linger_commit_cb;
 	}
-	mutex_unlock(&lreq->lock);
+
+	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+	BUG_ON(ret);
 
 	req->r_priv = linger_get(lreq);
 	req->r_linger = true;
+	lreq->reg_req = req;
+	mutex_unlock(&lreq->lock);
 
 	submit_request(req, true);
 }
@@ -3106,6 +3119,12 @@ static void linger_ping_cb(struct ceph_osd_request *req)
 	struct ceph_osd_linger_request *lreq = req->r_priv;
 
 	mutex_lock(&lreq->lock);
+	if (req != lreq->ping_req) {
+		dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
+		     __func__, lreq, lreq->linger_id, req, lreq->ping_req);
+		goto out;
+	}
+
 	dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n",
 	     __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent,
 	     lreq->last_error);
@@ -3121,6 +3140,7 @@ static void linger_ping_cb(struct ceph_osd_request *req)
 		     lreq->register_gen, req->r_ops[0].watch.gen);
 	}
 
+out:
 	mutex_unlock(&lreq->lock);
 	linger_put(lreq);
 }
@@ -3128,8 +3148,8 @@ static void linger_ping_cb(struct ceph_osd_request *req)
 static void send_linger_ping(struct ceph_osd_linger_request *lreq)
 {
 	struct ceph_osd_client *osdc = lreq->osdc;
-	struct ceph_osd_request *req = lreq->ping_req;
-	struct ceph_osd_req_op *op = &req->r_ops[0];
+	struct ceph_osd_request *req;
+	int ret;
 
 	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
 		dout("%s PAUSERD\n", __func__);
@@ -3141,19 +3161,26 @@ static void send_linger_ping(struct ceph_osd_linger_request *lreq)
 	     __func__, lreq, lreq->linger_id, lreq->ping_sent,
 	     lreq->register_gen);
 
-	if (req->r_osd)
-		cancel_linger_request(req);
+	if (lreq->ping_req) {
+		if (lreq->ping_req->r_osd)
+			cancel_linger_request(lreq->ping_req);
+		ceph_osdc_put_request(lreq->ping_req);
+	}
 
-	request_reinit(req);
-	target_copy(&req->r_t, &lreq->t);
+	req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO);
+	BUG_ON(!req);
 
-	WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
-		op->watch.cookie != lreq->linger_id ||
-		op->watch.op != CEPH_OSD_WATCH_OP_PING);
-	op->watch.gen = lreq->register_gen;
+	target_copy(&req->r_t, &lreq->t);
+	osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id,
+			      lreq->register_gen);
 	req->r_callback = linger_ping_cb;
+
+	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+	BUG_ON(ret);
+
 	req->r_priv = linger_get(lreq);
 	req->r_linger = true;
+	lreq->ping_req = req;
 
 	ceph_osdc_get_request(req);
 	account_request(req);
@@ -3169,12 +3196,6 @@ static void linger_submit(struct ceph_osd_linger_request *lreq)
 
 	down_write(&osdc->lock);
 	linger_register(lreq);
-	if (lreq->is_watch) {
-		lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id;
-		lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id;
-	} else {
-		lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id;
-	}
 
 	calc_target(osdc, &lreq->t, false);
 	osd = lookup_create_osd(osdc, lreq->t.osd, true);
@@ -3206,9 +3227,9 @@ static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq)
  */
 static void __linger_cancel(struct ceph_osd_linger_request *lreq)
 {
-	if (lreq->is_watch && lreq->ping_req->r_osd)
+	if (lreq->ping_req && lreq->ping_req->r_osd)
 		cancel_linger_request(lreq->ping_req);
-	if (lreq->reg_req->r_osd)
+	if (lreq->reg_req && lreq->reg_req->r_osd)
 		cancel_linger_request(lreq->reg_req);
 	cancel_linger_map_check(lreq);
 	unlink_linger(lreq->osd, lreq);
@@ -4657,43 +4678,6 @@ again:
 }
 EXPORT_SYMBOL(ceph_osdc_sync);
 
-static struct ceph_osd_request *
-alloc_linger_request(struct ceph_osd_linger_request *lreq)
-{
-	struct ceph_osd_request *req;
-
-	req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO);
-	if (!req)
-		return NULL;
-
-	ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
-	ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
-	return req;
-}
-
-static struct ceph_osd_request *
-alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode)
-{
-	struct ceph_osd_request *req;
-
-	req = alloc_linger_request(lreq);
-	if (!req)
-		return NULL;
-
-	/*
-	 * Pass 0 for cookie because we don't know it yet, it will be
-	 * filled in by linger_submit().
-	 */
-	osd_req_op_watch_init(req, 0, 0, watch_opcode);
-
-	if (ceph_osdc_alloc_messages(req, GFP_NOIO)) {
-		ceph_osdc_put_request(req);
-		return NULL;
-	}
-
-	return req;
-}
-
 /*
  * Returns a handle, caller owns a ref.
  */
@@ -4723,18 +4707,6 @@ ceph_osdc_watch(struct ceph_osd_client *osdc,
 	lreq->t.flags = CEPH_OSD_FLAG_WRITE;
 	ktime_get_real_ts64(&lreq->mtime);
 
-	lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH);
-	if (!lreq->reg_req) {
-		ret = -ENOMEM;
-		goto err_put_lreq;
-	}
-
-	lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING);
-	if (!lreq->ping_req) {
-		ret = -ENOMEM;
-		goto err_put_lreq;
-	}
-
 	linger_submit(lreq);
 	ret = linger_reg_commit_wait(lreq);
 	if (ret) {
@@ -4772,8 +4744,8 @@ int ceph_osdc_unwatch(struct ceph_osd_client *osdc,
 	ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
 	req->r_flags = CEPH_OSD_FLAG_WRITE;
 	ktime_get_real_ts64(&req->r_mtime);
-	osd_req_op_watch_init(req, 0, lreq->linger_id,
-			      CEPH_OSD_WATCH_OP_UNWATCH);
+	osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH,
+			      lreq->linger_id, 0);
 
 	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
 	if (ret)
@@ -4859,35 +4831,6 @@ out_put_req:
 }
 EXPORT_SYMBOL(ceph_osdc_notify_ack);
 
-static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
-				  u64 cookie, u32 prot_ver, u32 timeout,
-				  void *payload, u32 payload_len)
-{
-	struct ceph_osd_req_op *op;
-	struct ceph_pagelist *pl;
-	int ret;
-
-	op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
-	op->notify.cookie = cookie;
-
-	pl = ceph_pagelist_alloc(GFP_NOIO);
-	if (!pl)
-		return -ENOMEM;
-
-	ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */
-	ret |= ceph_pagelist_encode_32(pl, timeout);
-	ret |= ceph_pagelist_encode_32(pl, payload_len);
-	ret |= ceph_pagelist_append(pl, payload, payload_len);
-	if (ret) {
-		ceph_pagelist_release(pl);
-		return -ENOMEM;
-	}
-
-	ceph_osd_data_pagelist_init(&op->notify.request_data, pl);
-	op->indata_len = pl->length;
-	return 0;
-}
-
 /*
  * @timeout: in seconds
  *
@@ -4906,7 +4849,6 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
 		     size_t *preply_len)
 {
 	struct ceph_osd_linger_request *lreq;
-	struct page **pages;
 	int ret;
 
 	WARN_ON(!timeout);
@@ -4919,41 +4861,35 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
 	if (!lreq)
 		return -ENOMEM;
 
-	lreq->preply_pages = preply_pages;
-	lreq->preply_len = preply_len;
-
-	ceph_oid_copy(&lreq->t.base_oid, oid);
-	ceph_oloc_copy(&lreq->t.base_oloc, oloc);
-	lreq->t.flags = CEPH_OSD_FLAG_READ;
-
-	lreq->reg_req = alloc_linger_request(lreq);
-	if (!lreq->reg_req) {
+	lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO);
+	if (!lreq->request_pl) {
 		ret = -ENOMEM;
 		goto out_put_lreq;
 	}
 
-	/*
-	 * Pass 0 for cookie because we don't know it yet, it will be
-	 * filled in by linger_submit().
-	 */
-	ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout,
-				     payload, payload_len);
-	if (ret)
+	ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */
+	ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout);
+	ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len);
+	ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len);
+	if (ret) {
+		ret = -ENOMEM;
 		goto out_put_lreq;
+	}
 
 	/* for notify_id */
-	pages = ceph_alloc_page_vector(1, GFP_NOIO);
-	if (IS_ERR(pages)) {
-		ret = PTR_ERR(pages);
+	lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO);
+	if (IS_ERR(lreq->notify_id_pages)) {
+		ret = PTR_ERR(lreq->notify_id_pages);
+		lreq->notify_id_pages = NULL;
 		goto out_put_lreq;
 	}
-	ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify,
-						 response_data),
-				 pages, PAGE_SIZE, 0, false, true);
 
-	ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO);
-	if (ret)
-		goto out_put_lreq;
+	lreq->preply_pages = preply_pages;
+	lreq->preply_len = preply_len;
+
+	ceph_oid_copy(&lreq->t.base_oid, oid);
+	ceph_oloc_copy(&lreq->t.base_oloc, oloc);
+	lreq->t.flags = CEPH_OSD_FLAG_READ;
 
 	linger_submit(lreq);
 	ret = linger_reg_commit_wait(lreq);
-- 
cgit v1.2.3


From 3f68e69520d3d52d66a6ad872a75b7d8f2ea7665 Mon Sep 17 00:00:00 2001
From: Sunil V L <sunilvl@ventanamicro.com>
Date: Thu, 19 May 2022 10:45:12 +0530
Subject: riscv/efi_stub: Add support for RISCV_EFI_BOOT_PROTOCOL

Add support for getting the boot hart ID from the Linux EFI stub using
RISCV_EFI_BOOT_PROTOCOL. This method is preferred over the existing DT
based approach since it works irrespective of DT or ACPI.

The specification of the protocol is hosted at:
https://github.com/riscv-non-isa/riscv-uefi

Signed-off-by: Sunil V L <sunilvl@ventanamicro.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Heinrich Schuchardt <heinrich.schuchardt@canonical.com>
Link: https://lore.kernel.org/r/20220519051512.136724-2-sunilvl@ventanamicro.com
[ardb: minor tweaks for coding style and whitespace]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/efistub.h    |  7 +++++++
 drivers/firmware/efi/libstub/riscv-stub.c | 29 +++++++++++++++++++++++------
 include/linux/efi.h                       |  2 ++
 3 files changed, 32 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index a0477afaa55f..b0ae0a454404 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -794,6 +794,13 @@ union efi_tcg2_protocol {
 	} mixed_mode;
 };
 
+struct riscv_efi_boot_protocol {
+	u64 revision;
+
+	efi_status_t (__efiapi *get_boot_hartid)(struct riscv_efi_boot_protocol *,
+						 unsigned long *boot_hartid);
+};
+
 typedef union efi_load_file_protocol efi_load_file_protocol_t;
 typedef union efi_load_file_protocol efi_load_file2_protocol_t;
 
diff --git a/drivers/firmware/efi/libstub/riscv-stub.c b/drivers/firmware/efi/libstub/riscv-stub.c
index eec043873354..9e85e58d1f27 100644
--- a/drivers/firmware/efi/libstub/riscv-stub.c
+++ b/drivers/firmware/efi/libstub/riscv-stub.c
@@ -21,9 +21,9 @@
 #define MIN_KIMG_ALIGN		SZ_4M
 #endif
 
-typedef void __noreturn (*jump_kernel_func)(unsigned int, unsigned long);
+typedef void __noreturn (*jump_kernel_func)(unsigned long, unsigned long);
 
-static u32 hartid;
+static unsigned long hartid;
 
 static int get_boot_hartid_from_fdt(void)
 {
@@ -47,14 +47,31 @@ static int get_boot_hartid_from_fdt(void)
 	return 0;
 }
 
+static efi_status_t get_boot_hartid_from_efi(void)
+{
+	efi_guid_t boot_protocol_guid = RISCV_EFI_BOOT_PROTOCOL_GUID;
+	struct riscv_efi_boot_protocol *boot_protocol;
+	efi_status_t status;
+
+	status = efi_bs_call(locate_protocol, &boot_protocol_guid, NULL,
+			     (void **)&boot_protocol);
+	if (status != EFI_SUCCESS)
+		return status;
+	return efi_call_proto(boot_protocol, get_boot_hartid, &hartid);
+}
+
 efi_status_t check_platform_features(void)
 {
+	efi_status_t status;
 	int ret;
 
-	ret = get_boot_hartid_from_fdt();
-	if (ret) {
-		efi_err("/chosen/boot-hartid missing or invalid!\n");
-		return EFI_UNSUPPORTED;
+	status = get_boot_hartid_from_efi();
+	if (status != EFI_SUCCESS) {
+		ret = get_boot_hartid_from_fdt();
+		if (ret) {
+			efi_err("Failed to get boot hartid!\n");
+			return EFI_UNSUPPORTED;
+		}
 	}
 	return EFI_SUCCESS;
 }
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 580ce607d6f5..0412304ce34e 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -410,6 +410,8 @@ void efi_native_runtime_setup(void);
 #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID	EFI_GUID(0xc451ed2b, 0x9694, 0x45d3,  0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89)
 #define LINUX_EFI_COCO_SECRET_AREA_GUID		EFI_GUID(0xadf956ad, 0xe98c, 0x484c,  0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47)
 
+#define RISCV_EFI_BOOT_PROTOCOL_GUID		EFI_GUID(0xccd15fec, 0x6f73, 0x4eec,  0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf)
+
 /*
  * This GUID may be installed onto the kernel image's handle as a NULL protocol
  * to signal to the stub that the placement of the image should be respected,
-- 
cgit v1.2.3


From 238e34ad7d5ce36939ac1442c98c7cbb7771f4de Mon Sep 17 00:00:00 2001
From: Jishnu Prakash <quic_jprakash@quicinc.com>
Date: Sun, 3 Apr 2022 18:47:47 +0530
Subject: iio: adc: qcom-vadc-common: add reverse scaling for PMIC5 Gen2 ADC_TM

Add reverse scaling function for PMIC5 Gen2 ADC_TM, to convert
temperature to raw ADC code, for setting thresholds for
thermistor channels.

Signed-off-by: Jishnu Prakash <quic_jprakash@quicinc.com>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/1648991869-20899-3-git-send-email-quic_jprakash@quicinc.com
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/iio/adc/qcom-vadc-common.c       | 11 +++++++++++
 include/linux/iio/adc/qcom-vadc-common.h |  2 ++
 2 files changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iio/adc/qcom-vadc-common.c b/drivers/iio/adc/qcom-vadc-common.c
index 6c6aec848f98..d5209f32adb3 100644
--- a/drivers/iio/adc/qcom-vadc-common.c
+++ b/drivers/iio/adc/qcom-vadc-common.c
@@ -677,6 +677,17 @@ u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio,
 }
 EXPORT_SYMBOL(qcom_adc_tm5_temp_volt_scale);
 
+u16 qcom_adc_tm5_gen2_temp_res_scale(int temp)
+{
+	int64_t resistance;
+
+	resistance = qcom_vadc_map_temp_voltage(adcmap7_100k,
+		ARRAY_SIZE(adcmap7_100k), temp);
+
+	return div64_s64(resistance * RATIO_MAX_ADC7, resistance + R_PU_100K);
+}
+EXPORT_SYMBOL(qcom_adc_tm5_gen2_temp_res_scale);
+
 int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype,
 		    unsigned int prescale_ratio,
 		    const struct adc5_data *data,
diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h
index ce78d4804994..aa21b032e861 100644
--- a/include/linux/iio/adc/qcom-vadc-common.h
+++ b/include/linux/iio/adc/qcom-vadc-common.h
@@ -152,6 +152,8 @@ int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype,
 u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio,
 				 u32 full_scale_code_volt, int temp);
 
+u16 qcom_adc_tm5_gen2_temp_res_scale(int temp);
+
 int qcom_adc5_prescaling_from_dt(u32 num, u32 den);
 
 int qcom_adc5_hw_settle_time_from_dt(u32 value, const unsigned int *hw_settle);
-- 
cgit v1.2.3


From bf70c577516b8d9fbe703371aa98bbea13661cec Mon Sep 17 00:00:00 2001
From: Manaf Meethalavalappu Pallikunhi <quic_manafm@quicinc.com>
Date: Wed, 9 Mar 2022 00:56:26 +0530
Subject: thermal/drivers/thermal_of: Add change_mode ops support for
 thermal_of sensor

The sensor driver which register through thermal_of interface doesn't
have an option to get thermal zone mode change notification from
thermal core.

Add support for change_mode ops in thermal_of interface so that sensor
driver can use this ops for mode change notification.

Signed-off-by: Manaf Meethalavalappu Pallikunhi <quic_manafm@quicinc.com>
Link: https://lore.kernel.org/r/1646767586-31908-1-git-send-email-quic_manafm@quicinc.com
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_of.c | 12 ++++++++++++
 include/linux/thermal.h      |  3 +++
 2 files changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 9233f7e74454..da484800906f 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -203,6 +203,14 @@ static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
 	return data->ops->get_trend(data->sensor_data, trip, trend);
 }
 
+static int of_thermal_change_mode(struct thermal_zone_device *tz,
+				enum thermal_device_mode mode)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	return data->ops->change_mode(data->sensor_data, mode);
+}
+
 static int of_thermal_bind(struct thermal_zone_device *thermal,
 			   struct thermal_cooling_device *cdev)
 {
@@ -408,6 +416,9 @@ thermal_zone_of_add_sensor(struct device_node *zone,
 	if (ops->set_emul_temp)
 		tzd->ops->set_emul_temp = of_thermal_set_emul_temp;
 
+	if (ops->change_mode)
+		tzd->ops->change_mode = of_thermal_change_mode;
+
 	mutex_unlock(&tzd->lock);
 
 	return tzd;
@@ -569,6 +580,7 @@ void thermal_zone_of_sensor_unregister(struct device *dev,
 	tzd->ops->get_temp = NULL;
 	tzd->ops->get_trend = NULL;
 	tzd->ops->set_emul_temp = NULL;
+	tzd->ops->change_mode = NULL;
 
 	tz->ops = NULL;
 	tz->sensor_data = NULL;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index c314893970b3..365733b428d8 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -299,6 +299,8 @@ struct thermal_zone_params {
  *		   temperature.
  * @set_trip_temp: a pointer to a function that sets the trip temperature on
  *		   hardware.
+ * @change_mode: a pointer to a function that notifies the thermal zone
+ *		   mode change.
  */
 struct thermal_zone_of_device_ops {
 	int (*get_temp)(void *, int *);
@@ -306,6 +308,7 @@ struct thermal_zone_of_device_ops {
 	int (*set_trips)(void *, int, int);
 	int (*set_emul_temp)(void *, int);
 	int (*set_trip_temp)(void *, int, int);
+	int (*change_mode) (void *, enum thermal_device_mode);
 };
 
 /* Function declarations */
-- 
cgit v1.2.3


From 7782cfeca7d420e8bb707613d4cfb0f7ff29bb3a Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Fri, 13 May 2022 12:29:38 +0200
Subject: random: remove extern from functions in header

Accoriding to the kernel style guide, having `extern` on functions in
headers is old school and deprecated, and doesn't add anything. So remove
them from random.h, and tidy up the file a little bit too.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 include/linux/random.h | 77 ++++++++++++++++++++------------------------------
 1 file changed, 31 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/random.h b/include/linux/random.h
index b52963955a99..97f879ea78a5 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -12,13 +12,12 @@
 
 struct notifier_block;
 
-extern void add_device_randomness(const void *, size_t);
-extern void add_bootloader_randomness(const void *, size_t);
-extern void add_input_randomness(unsigned int type, unsigned int code,
-				 unsigned int value) __latent_entropy;
-extern void add_interrupt_randomness(int irq) __latent_entropy;
-extern void add_hwgenerator_randomness(const void *buffer, size_t count,
-				       size_t entropy);
+void add_device_randomness(const void *, size_t);
+void add_bootloader_randomness(const void *, size_t);
+void add_input_randomness(unsigned int type, unsigned int code,
+			  unsigned int value) __latent_entropy;
+void add_interrupt_randomness(int irq) __latent_entropy;
+void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy);
 
 #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 static inline void add_latent_entropy(void)
@@ -26,30 +25,20 @@ static inline void add_latent_entropy(void)
 	add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy));
 }
 #else
-static inline void add_latent_entropy(void) {}
+static inline void add_latent_entropy(void) { }
 #endif
 
 #if IS_ENABLED(CONFIG_VMGENID)
-extern void add_vmfork_randomness(const void *unique_vm_id, size_t size);
-extern int register_random_vmfork_notifier(struct notifier_block *nb);
-extern int unregister_random_vmfork_notifier(struct notifier_block *nb);
+void add_vmfork_randomness(const void *unique_vm_id, size_t size);
+int register_random_vmfork_notifier(struct notifier_block *nb);
+int unregister_random_vmfork_notifier(struct notifier_block *nb);
 #else
 static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; }
 static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; }
 #endif
 
-extern void get_random_bytes(void *buf, size_t nbytes);
-extern int wait_for_random_bytes(void);
-extern int __init random_init(const char *command_line);
-extern bool rng_is_initialized(void);
-extern int register_random_ready_notifier(struct notifier_block *nb);
-extern int unregister_random_ready_notifier(struct notifier_block *nb);
-extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes);
-
-#ifndef MODULE
-extern const struct file_operations random_fops, urandom_fops;
-#endif
-
+void get_random_bytes(void *buf, size_t nbytes);
+size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes);
 u32 get_random_u32(void);
 u64 get_random_u64(void);
 static inline unsigned int get_random_int(void)
@@ -81,11 +70,17 @@ static inline unsigned long get_random_long(void)
 
 static inline unsigned long get_random_canary(void)
 {
-	unsigned long val = get_random_long();
-
-	return val & CANARY_MASK;
+	return get_random_long() & CANARY_MASK;
 }
 
+unsigned long randomize_page(unsigned long start, unsigned long range);
+
+int __init random_init(const char *command_line);
+bool rng_is_initialized(void);
+int wait_for_random_bytes(void);
+int register_random_ready_notifier(struct notifier_block *nb);
+int unregister_random_ready_notifier(struct notifier_block *nb);
+
 /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes).
  * Returns the result of the call to wait_for_random_bytes. */
 static inline int get_random_bytes_wait(void *buf, size_t nbytes)
@@ -109,8 +104,6 @@ declare_get_random_var_wait(int)
 declare_get_random_var_wait(long)
 #undef declare_get_random_var
 
-unsigned long randomize_page(unsigned long start, unsigned long range);
-
 /*
  * This is designed to be standalone for just prandom
  * users, but for now we include it from <linux/random.h>
@@ -121,22 +114,10 @@ unsigned long randomize_page(unsigned long start, unsigned long range);
 #ifdef CONFIG_ARCH_RANDOM
 # include <asm/archrandom.h>
 #else
-static inline bool __must_check arch_get_random_long(unsigned long *v)
-{
-	return false;
-}
-static inline bool __must_check arch_get_random_int(unsigned int *v)
-{
-	return false;
-}
-static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
-{
-	return false;
-}
-static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
-{
-	return false;
-}
+static inline bool __must_check arch_get_random_long(unsigned long *v) { return false; }
+static inline bool __must_check arch_get_random_int(unsigned int *v) { return false; }
+static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { return false; }
+static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { return false; }
 #endif
 
 /*
@@ -160,8 +141,12 @@ static inline bool __init arch_get_random_long_early(unsigned long *v)
 #endif
 
 #ifdef CONFIG_SMP
-extern int random_prepare_cpu(unsigned int cpu);
-extern int random_online_cpu(unsigned int cpu);
+int random_prepare_cpu(unsigned int cpu);
+int random_online_cpu(unsigned int cpu);
+#endif
+
+#ifndef MODULE
+extern const struct file_operations random_fops, urandom_fops;
 #endif
 
 #endif /* _LINUX_RANDOM_H */
-- 
cgit v1.2.3


From 7c3a8a1db5e03d02cc0abb3357a84b8b326dfac3 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Fri, 13 May 2022 12:32:23 +0200
Subject: random: use proper return types on get_random_{int,long}_wait()

Before these were returning signed values, but the API is intended to be
used with unsigned values.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 include/linux/random.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/random.h b/include/linux/random.h
index 97f879ea78a5..883bf9a23d84 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -90,18 +90,18 @@ static inline int get_random_bytes_wait(void *buf, size_t nbytes)
 	return ret;
 }
 
-#define declare_get_random_var_wait(var) \
-	static inline int get_random_ ## var ## _wait(var *out) { \
+#define declare_get_random_var_wait(name, ret_type) \
+	static inline int get_random_ ## name ## _wait(ret_type *out) { \
 		int ret = wait_for_random_bytes(); \
 		if (unlikely(ret)) \
 			return ret; \
-		*out = get_random_ ## var(); \
+		*out = get_random_ ## name(); \
 		return 0; \
 	}
-declare_get_random_var_wait(u32)
-declare_get_random_var_wait(u64)
-declare_get_random_var_wait(int)
-declare_get_random_var_wait(long)
+declare_get_random_var_wait(u32, u32)
+declare_get_random_var_wait(u64, u32)
+declare_get_random_var_wait(int, unsigned int)
+declare_get_random_var_wait(long, unsigned long)
 #undef declare_get_random_var
 
 /*
-- 
cgit v1.2.3


From a19402634c435a4eae226df53c141cdbb9922e7b Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Fri, 13 May 2022 13:18:46 +0200
Subject: random: make consistent use of buf and len

The current code was a mix of "nbytes", "count", "size", "buffer", "in",
and so forth. Instead, let's clean this up by naming input parameters
"buf" (or "ubuf") and "len", so that you always understand that you're
reading this variety of function argument.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 drivers/char/random.c  | 199 ++++++++++++++++++++++++-------------------------
 include/linux/random.h |  12 +--
 2 files changed, 103 insertions(+), 108 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index b2cfd659bae5..0475ed69aa34 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -209,7 +209,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller)
  *
  * There are a few exported interfaces for use by other drivers:
  *
- *	void get_random_bytes(void *buf, size_t nbytes)
+ *	void get_random_bytes(void *buf, size_t len)
  *	u32 get_random_u32()
  *	u64 get_random_u64()
  *	unsigned int get_random_int()
@@ -250,7 +250,7 @@ static DEFINE_PER_CPU(struct crng, crngs) = {
 };
 
 /* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */
-static void extract_entropy(void *buf, size_t nbytes);
+static void extract_entropy(void *buf, size_t len);
 
 /* This extracts a new crng key from the input pool. */
 static void crng_reseed(void)
@@ -404,24 +404,24 @@ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS],
 	local_unlock_irqrestore(&crngs.lock, flags);
 }
 
-static void _get_random_bytes(void *buf, size_t nbytes)
+static void _get_random_bytes(void *buf, size_t len)
 {
 	u32 chacha_state[CHACHA_STATE_WORDS];
 	u8 tmp[CHACHA_BLOCK_SIZE];
-	size_t len;
+	size_t first_block_len;
 
-	if (!nbytes)
+	if (!len)
 		return;
 
-	len = min_t(size_t, 32, nbytes);
-	crng_make_state(chacha_state, buf, len);
-	nbytes -= len;
-	buf += len;
+	first_block_len = min_t(size_t, 32, len);
+	crng_make_state(chacha_state, buf, first_block_len);
+	len -= first_block_len;
+	buf += first_block_len;
 
-	while (nbytes) {
-		if (nbytes < CHACHA_BLOCK_SIZE) {
+	while (len) {
+		if (len < CHACHA_BLOCK_SIZE) {
 			chacha20_block(chacha_state, tmp);
-			memcpy(buf, tmp, nbytes);
+			memcpy(buf, tmp, len);
 			memzero_explicit(tmp, sizeof(tmp));
 			break;
 		}
@@ -429,7 +429,7 @@ static void _get_random_bytes(void *buf, size_t nbytes)
 		chacha20_block(chacha_state, buf);
 		if (unlikely(chacha_state[12] == 0))
 			++chacha_state[13];
-		nbytes -= CHACHA_BLOCK_SIZE;
+		len -= CHACHA_BLOCK_SIZE;
 		buf += CHACHA_BLOCK_SIZE;
 	}
 
@@ -446,20 +446,20 @@ static void _get_random_bytes(void *buf, size_t nbytes)
  * wait_for_random_bytes() should be called and return 0 at least once
  * at any point prior.
  */
-void get_random_bytes(void *buf, size_t nbytes)
+void get_random_bytes(void *buf, size_t len)
 {
 	warn_unseeded_randomness();
-	_get_random_bytes(buf, nbytes);
+	_get_random_bytes(buf, len);
 }
 EXPORT_SYMBOL(get_random_bytes);
 
-static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
+static ssize_t get_random_bytes_user(void __user *ubuf, size_t len)
 {
-	size_t len, left, ret = 0;
+	size_t block_len, left, ret = 0;
 	u32 chacha_state[CHACHA_STATE_WORDS];
 	u8 output[CHACHA_BLOCK_SIZE];
 
-	if (!nbytes)
+	if (!len)
 		return 0;
 
 	/*
@@ -473,8 +473,8 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
 	 * use chacha_state after, so we can simply return those bytes to
 	 * the user directly.
 	 */
-	if (nbytes <= CHACHA_KEY_SIZE) {
-		ret = nbytes - copy_to_user(buf, &chacha_state[4], nbytes);
+	if (len <= CHACHA_KEY_SIZE) {
+		ret = len - copy_to_user(ubuf, &chacha_state[4], len);
 		goto out_zero_chacha;
 	}
 
@@ -483,17 +483,17 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
 		if (unlikely(chacha_state[12] == 0))
 			++chacha_state[13];
 
-		len = min_t(size_t, nbytes, CHACHA_BLOCK_SIZE);
-		left = copy_to_user(buf, output, len);
+		block_len = min_t(size_t, len, CHACHA_BLOCK_SIZE);
+		left = copy_to_user(ubuf, output, block_len);
 		if (left) {
-			ret += len - left;
+			ret += block_len - left;
 			break;
 		}
 
-		buf += len;
-		ret += len;
-		nbytes -= len;
-		if (!nbytes)
+		ubuf += block_len;
+		ret += block_len;
+		len -= block_len;
+		if (!len)
 			break;
 
 		BUILD_BUG_ON(PAGE_SIZE % CHACHA_BLOCK_SIZE != 0);
@@ -667,24 +667,24 @@ unsigned long randomize_page(unsigned long start, unsigned long range)
  * use. Use get_random_bytes() instead. It returns the number of
  * bytes filled in.
  */
-size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes)
+size_t __must_check get_random_bytes_arch(void *buf, size_t len)
 {
-	size_t left = nbytes;
+	size_t left = len;
 	u8 *p = buf;
 
 	while (left) {
 		unsigned long v;
-		size_t chunk = min_t(size_t, left, sizeof(unsigned long));
+		size_t block_len = min_t(size_t, left, sizeof(unsigned long));
 
 		if (!arch_get_random_long(&v))
 			break;
 
-		memcpy(p, &v, chunk);
-		p += chunk;
-		left -= chunk;
+		memcpy(p, &v, block_len);
+		p += block_len;
+		left -= block_len;
 	}
 
-	return nbytes - left;
+	return len - left;
 }
 EXPORT_SYMBOL(get_random_bytes_arch);
 
@@ -695,15 +695,15 @@ EXPORT_SYMBOL(get_random_bytes_arch);
  *
  * Callers may add entropy via:
  *
- *     static void mix_pool_bytes(const void *in, size_t nbytes)
+ *     static void mix_pool_bytes(const void *buf, size_t len)
  *
  * After which, if added entropy should be credited:
  *
- *     static void credit_init_bits(size_t nbits)
+ *     static void credit_init_bits(size_t bits)
  *
  * Finally, extract entropy via:
  *
- *     static void extract_entropy(void *buf, size_t nbytes)
+ *     static void extract_entropy(void *buf, size_t len)
  *
  **********************************************************************/
 
@@ -725,9 +725,9 @@ static struct {
 	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
 };
 
-static void _mix_pool_bytes(const void *in, size_t nbytes)
+static void _mix_pool_bytes(const void *buf, size_t len)
 {
-	blake2s_update(&input_pool.hash, in, nbytes);
+	blake2s_update(&input_pool.hash, buf, len);
 }
 
 /*
@@ -735,12 +735,12 @@ static void _mix_pool_bytes(const void *in, size_t nbytes)
  * update the initialization bit counter; the caller should call
  * credit_init_bits if this is appropriate.
  */
-static void mix_pool_bytes(const void *in, size_t nbytes)
+static void mix_pool_bytes(const void *buf, size_t len)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&input_pool.lock, flags);
-	_mix_pool_bytes(in, nbytes);
+	_mix_pool_bytes(buf, len);
 	spin_unlock_irqrestore(&input_pool.lock, flags);
 }
 
@@ -748,7 +748,7 @@ static void mix_pool_bytes(const void *in, size_t nbytes)
  * This is an HKDF-like construction for using the hashed collected entropy
  * as a PRF key, that's then expanded block-by-block.
  */
-static void extract_entropy(void *buf, size_t nbytes)
+static void extract_entropy(void *buf, size_t len)
 {
 	unsigned long flags;
 	u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE];
@@ -777,12 +777,12 @@ static void extract_entropy(void *buf, size_t nbytes)
 	spin_unlock_irqrestore(&input_pool.lock, flags);
 	memzero_explicit(next_key, sizeof(next_key));
 
-	while (nbytes) {
-		i = min_t(size_t, nbytes, BLAKE2S_HASH_SIZE);
+	while (len) {
+		i = min_t(size_t, len, BLAKE2S_HASH_SIZE);
 		/* output = HASHPRF(seed, RDSEED || ++counter) */
 		++block.counter;
 		blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed));
-		nbytes -= i;
+		len -= i;
 		buf += i;
 	}
 
@@ -790,16 +790,16 @@ static void extract_entropy(void *buf, size_t nbytes)
 	memzero_explicit(&block, sizeof(block));
 }
 
-static void credit_init_bits(size_t nbits)
+static void credit_init_bits(size_t bits)
 {
 	static struct execute_work set_ready;
 	unsigned int new, orig, add;
 	unsigned long flags;
 
-	if (crng_ready() || !nbits)
+	if (crng_ready() || !bits)
 		return;
 
-	add = min_t(size_t, nbits, POOL_BITS);
+	add = min_t(size_t, bits, POOL_BITS);
 
 	do {
 		orig = READ_ONCE(input_pool.init_bits);
@@ -835,14 +835,12 @@ static void credit_init_bits(size_t nbits)
  * The following exported functions are used for pushing entropy into
  * the above entropy accumulation routines:
  *
- *	void add_device_randomness(const void *buf, size_t size);
- *	void add_hwgenerator_randomness(const void *buffer, size_t count,
- *					size_t entropy);
- *	void add_bootloader_randomness(const void *buf, size_t size);
- *	void add_vmfork_randomness(const void *unique_vm_id, size_t size);
+ *	void add_device_randomness(const void *buf, size_t len);
+ *	void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy);
+ *	void add_bootloader_randomness(const void *buf, size_t len);
+ *	void add_vmfork_randomness(const void *unique_vm_id, size_t len);
  *	void add_interrupt_randomness(int irq);
- *	void add_input_randomness(unsigned int type, unsigned int code,
- *	                          unsigned int value);
+ *	void add_input_randomness(unsigned int type, unsigned int code, unsigned int value);
  *	void add_disk_randomness(struct gendisk *disk);
  *
  * add_device_randomness() adds data to the input pool that
@@ -937,7 +935,7 @@ int __init random_init(const char *command_line)
 {
 	ktime_t now = ktime_get_real();
 	unsigned int i, arch_bytes;
-	unsigned long rv;
+	unsigned long entropy;
 
 #if defined(LATENT_ENTROPY_PLUGIN)
 	static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy;
@@ -945,13 +943,13 @@ int __init random_init(const char *command_line)
 #endif
 
 	for (i = 0, arch_bytes = BLAKE2S_BLOCK_SIZE;
-	     i < BLAKE2S_BLOCK_SIZE; i += sizeof(rv)) {
-		if (!arch_get_random_seed_long_early(&rv) &&
-		    !arch_get_random_long_early(&rv)) {
-			rv = random_get_entropy();
-			arch_bytes -= sizeof(rv);
+	     i < BLAKE2S_BLOCK_SIZE; i += sizeof(entropy)) {
+		if (!arch_get_random_seed_long_early(&entropy) &&
+		    !arch_get_random_long_early(&entropy)) {
+			entropy = random_get_entropy();
+			arch_bytes -= sizeof(entropy);
 		}
-		_mix_pool_bytes(&rv, sizeof(rv));
+		_mix_pool_bytes(&entropy, sizeof(entropy));
 	}
 	_mix_pool_bytes(&now, sizeof(now));
 	_mix_pool_bytes(utsname(), sizeof(*(utsname())));
@@ -978,14 +976,14 @@ int __init random_init(const char *command_line)
  * the entropy pool having similar initial state across largely
  * identical devices.
  */
-void add_device_randomness(const void *buf, size_t size)
+void add_device_randomness(const void *buf, size_t len)
 {
 	unsigned long entropy = random_get_entropy();
 	unsigned long flags;
 
 	spin_lock_irqsave(&input_pool.lock, flags);
 	_mix_pool_bytes(&entropy, sizeof(entropy));
-	_mix_pool_bytes(buf, size);
+	_mix_pool_bytes(buf, len);
 	spin_unlock_irqrestore(&input_pool.lock, flags);
 }
 EXPORT_SYMBOL(add_device_randomness);
@@ -995,10 +993,9 @@ EXPORT_SYMBOL(add_device_randomness);
  * Those devices may produce endless random bits and will be throttled
  * when our pool is full.
  */
-void add_hwgenerator_randomness(const void *buffer, size_t count,
-				size_t entropy)
+void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy)
 {
-	mix_pool_bytes(buffer, count);
+	mix_pool_bytes(buf, len);
 	credit_init_bits(entropy);
 
 	/*
@@ -1014,11 +1011,11 @@ EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);
  * Handle random seed passed by bootloader, and credit it if
  * CONFIG_RANDOM_TRUST_BOOTLOADER is set.
  */
-void add_bootloader_randomness(const void *buf, size_t size)
+void add_bootloader_randomness(const void *buf, size_t len)
 {
-	mix_pool_bytes(buf, size);
+	mix_pool_bytes(buf, len);
 	if (trust_bootloader)
-		credit_init_bits(size * 8);
+		credit_init_bits(len * 8);
 }
 EXPORT_SYMBOL_GPL(add_bootloader_randomness);
 
@@ -1030,9 +1027,9 @@ static BLOCKING_NOTIFIER_HEAD(vmfork_chain);
  * don't credit it, but we do immediately force a reseed after so
  * that it's used by the crng posthaste.
  */
-void add_vmfork_randomness(const void *unique_vm_id, size_t size)
+void add_vmfork_randomness(const void *unique_vm_id, size_t len)
 {
-	add_device_randomness(unique_vm_id, size);
+	add_device_randomness(unique_vm_id, len);
 	if (crng_ready()) {
 		crng_reseed();
 		pr_notice("crng reseeded due to virtual machine fork\n");
@@ -1252,8 +1249,7 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned int nu
 		credit_init_bits(bits);
 }
 
-void add_input_randomness(unsigned int type, unsigned int code,
-			  unsigned int value)
+void add_input_randomness(unsigned int type, unsigned int code, unsigned int value)
 {
 	static unsigned char last_value;
 	static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES };
@@ -1388,8 +1384,7 @@ static void try_to_generate_entropy(void)
  *
  **********************************************************************/
 
-SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int,
-		flags)
+SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags)
 {
 	if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))
 		return -EINVAL;
@@ -1401,8 +1396,8 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int,
 	if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM))
 		return -EINVAL;
 
-	if (count > INT_MAX)
-		count = INT_MAX;
+	if (len > INT_MAX)
+		len = INT_MAX;
 
 	if (!crng_ready() && !(flags & GRND_INSECURE)) {
 		int ret;
@@ -1413,7 +1408,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int,
 		if (unlikely(ret))
 			return ret;
 	}
-	return get_random_bytes_user(buf, count);
+	return get_random_bytes_user(ubuf, len);
 }
 
 static __poll_t random_poll(struct file *file, poll_table *wait)
@@ -1422,21 +1417,21 @@ static __poll_t random_poll(struct file *file, poll_table *wait)
 	return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM;
 }
 
-static int write_pool(const char __user *ubuf, size_t count)
+static int write_pool(const char __user *ubuf, size_t len)
 {
-	size_t len;
+	size_t block_len;
 	int ret = 0;
 	u8 block[BLAKE2S_BLOCK_SIZE];
 
-	while (count) {
-		len = min(count, sizeof(block));
-		if (copy_from_user(block, ubuf, len)) {
+	while (len) {
+		block_len = min(len, sizeof(block));
+		if (copy_from_user(block, ubuf, block_len)) {
 			ret = -EFAULT;
 			goto out;
 		}
-		count -= len;
-		ubuf += len;
-		mix_pool_bytes(block, len);
+		len -= block_len;
+		ubuf += block_len;
+		mix_pool_bytes(block, block_len);
 		cond_resched();
 	}
 
@@ -1445,20 +1440,20 @@ out:
 	return ret;
 }
 
-static ssize_t random_write(struct file *file, const char __user *buffer,
-			    size_t count, loff_t *ppos)
+static ssize_t random_write(struct file *file, const char __user *ubuf,
+			    size_t len, loff_t *ppos)
 {
 	int ret;
 
-	ret = write_pool(buffer, count);
+	ret = write_pool(ubuf, len);
 	if (ret)
 		return ret;
 
-	return (ssize_t)count;
+	return (ssize_t)len;
 }
 
-static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes,
-			    loff_t *ppos)
+static ssize_t urandom_read(struct file *file, char __user *ubuf,
+			    size_t len, loff_t *ppos)
 {
 	static int maxwarn = 10;
 
@@ -1475,22 +1470,22 @@ static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes,
 		else if (ratelimit_disable || __ratelimit(&urandom_warning)) {
 			--maxwarn;
 			pr_notice("%s: uninitialized urandom read (%zd bytes read)\n",
-				  current->comm, nbytes);
+				  current->comm, len);
 		}
 	}
 
-	return get_random_bytes_user(buf, nbytes);
+	return get_random_bytes_user(ubuf, len);
 }
 
-static ssize_t random_read(struct file *file, char __user *buf, size_t nbytes,
-			   loff_t *ppos)
+static ssize_t random_read(struct file *file, char __user *ubuf,
+			   size_t len, loff_t *ppos)
 {
 	int ret;
 
 	ret = wait_for_random_bytes();
 	if (ret != 0)
 		return ret;
-	return get_random_bytes_user(buf, nbytes);
+	return get_random_bytes_user(ubuf, len);
 }
 
 static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
@@ -1615,7 +1610,7 @@ static u8 sysctl_bootid[UUID_SIZE];
  * UUID. The difference is in whether table->data is NULL; if it is,
  * then a new UUID is generated and returned to the user.
  */
-static int proc_do_uuid(struct ctl_table *table, int write, void *buffer,
+static int proc_do_uuid(struct ctl_table *table, int write, void *buf,
 			size_t *lenp, loff_t *ppos)
 {
 	u8 tmp_uuid[UUID_SIZE], *uuid;
@@ -1642,14 +1637,14 @@ static int proc_do_uuid(struct ctl_table *table, int write, void *buffer,
 	}
 
 	snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid);
-	return proc_dostring(&fake_table, 0, buffer, lenp, ppos);
+	return proc_dostring(&fake_table, 0, buf, lenp, ppos);
 }
 
 /* The same as proc_dointvec, but writes don't change anything. */
-static int proc_do_rointvec(struct ctl_table *table, int write, void *buffer,
+static int proc_do_rointvec(struct ctl_table *table, int write, void *buf,
 			    size_t *lenp, loff_t *ppos)
 {
-	return write ? 0 : proc_dointvec(table, 0, buffer, lenp, ppos);
+	return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos);
 }
 
 static struct ctl_table random_table[] = {
diff --git a/include/linux/random.h b/include/linux/random.h
index 883bf9a23d84..fc82f1dc36f1 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -12,12 +12,12 @@
 
 struct notifier_block;
 
-void add_device_randomness(const void *, size_t);
-void add_bootloader_randomness(const void *, size_t);
+void add_device_randomness(const void *buf, size_t len);
+void add_bootloader_randomness(const void *buf, size_t len);
 void add_input_randomness(unsigned int type, unsigned int code,
 			  unsigned int value) __latent_entropy;
 void add_interrupt_randomness(int irq) __latent_entropy;
-void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy);
+void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy);
 
 #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 static inline void add_latent_entropy(void)
@@ -29,7 +29,7 @@ static inline void add_latent_entropy(void) { }
 #endif
 
 #if IS_ENABLED(CONFIG_VMGENID)
-void add_vmfork_randomness(const void *unique_vm_id, size_t size);
+void add_vmfork_randomness(const void *unique_vm_id, size_t len);
 int register_random_vmfork_notifier(struct notifier_block *nb);
 int unregister_random_vmfork_notifier(struct notifier_block *nb);
 #else
@@ -37,8 +37,8 @@ static inline int register_random_vmfork_notifier(struct notifier_block *nb) { r
 static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; }
 #endif
 
-void get_random_bytes(void *buf, size_t nbytes);
-size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes);
+void get_random_bytes(void *buf, size_t len);
+size_t __must_check get_random_bytes_arch(void *buf, size_t len);
 u32 get_random_u32(void);
 u64 get_random_u64(void);
 static inline unsigned int get_random_int(void)
-- 
cgit v1.2.3


From 248561ad25a8ba4ecbc7df42f9a5a82fd5fbb4f6 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sat, 14 May 2022 13:09:17 +0200
Subject: random: remove get_random_bytes_arch() and add rng_has_arch_random()

The RNG incorporates RDRAND into its state at boot and every time it
reseeds, so there's no reason for callers to use it directly. The
hashing that the RNG does on it is preferable to using the bytes raw.

The only current use case of get_random_bytes_arch() is vsprintf's
siphash key for pointer hashing, which uses it to initialize the pointer
secret earlier than usual if RDRAND is available. In order to replace
this narrow use case, just expose whether RDRAND is mixed into the RNG,
with a new function called rng_has_arch_random(). With that taken care
of, there are no users of get_random_bytes_arch() left, so it can be
removed.

Later, if trust_cpu gets turned on by default (as most distros are
doing), this one use of rng_has_arch_random() can probably go away as
well.

Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Acked-by: Petr Mladek <pmladek@suse.com> # for vsprintf.c
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 drivers/char/random.c  | 49 ++++++++++++++++---------------------------------
 include/linux/random.h |  2 +-
 lib/vsprintf.c         |  7 +++----
 3 files changed, 20 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 7ec700683e42..6b8c89378954 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -433,12 +433,9 @@ static void _get_random_bytes(void *buf, size_t len)
 /*
  * This function is the exported kernel interface.  It returns some
  * number of good random numbers, suitable for key generation, seeding
- * TCP sequence numbers, etc.  It does not rely on the hardware random
- * number generator.  For random bytes direct from the hardware RNG
- * (when available), use get_random_bytes_arch(). In order to ensure
- * that the randomness provided by this function is okay, the function
- * wait_for_random_bytes() should be called and return 0 at least once
- * at any point prior.
+ * TCP sequence numbers, etc. In order to ensure that the randomness
+ * by this function is okay, the function wait_for_random_bytes()
+ * should be called and return 0 at least once at any point prior.
  */
 void get_random_bytes(void *buf, size_t len)
 {
@@ -655,33 +652,6 @@ unsigned long randomize_page(unsigned long start, unsigned long range)
 	return start + (get_random_long() % range << PAGE_SHIFT);
 }
 
-/*
- * This function will use the architecture-specific hardware random
- * number generator if it is available. It is not recommended for
- * use. Use get_random_bytes() instead. It returns the number of
- * bytes filled in.
- */
-size_t __must_check get_random_bytes_arch(void *buf, size_t len)
-{
-	size_t left = len;
-	u8 *p = buf;
-
-	while (left) {
-		unsigned long v;
-		size_t block_len = min_t(size_t, left, sizeof(unsigned long));
-
-		if (!arch_get_random_long(&v))
-			break;
-
-		memcpy(p, &v, block_len);
-		p += block_len;
-		left -= block_len;
-	}
-
-	return len - left;
-}
-EXPORT_SYMBOL(get_random_bytes_arch);
-
 
 /**********************************************************************
  *
@@ -879,6 +849,7 @@ static void __cold _credit_init_bits(size_t bits)
  *
  **********************************************************************/
 
+static bool used_arch_random;
 static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
 static bool trust_bootloader __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER);
 static int __init parse_trust_cpu(char *arg)
@@ -956,6 +927,7 @@ int __init random_init(const char *command_line)
 		crng_reseed();
 	else if (trust_cpu)
 		credit_init_bits(arch_bytes * 8);
+	used_arch_random = arch_bytes * 8 >= POOL_READY_BITS;
 
 	WARN_ON(register_pm_notifier(&pm_notifier));
 
@@ -964,6 +936,17 @@ int __init random_init(const char *command_line)
 	return 0;
 }
 
+/*
+ * Returns whether arch randomness has been mixed into the initial
+ * state of the RNG, regardless of whether or not that randomness
+ * was credited. Knowing this is only good for a very limited set
+ * of uses, such as early init printk pointer obfuscation.
+ */
+bool rng_has_arch_random(void)
+{
+	return used_arch_random;
+}
+
 /*
  * Add device- or boot-specific data to the input pool to help
  * initialize it.
diff --git a/include/linux/random.h b/include/linux/random.h
index fc82f1dc36f1..6af130c6edb9 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -38,7 +38,6 @@ static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) {
 #endif
 
 void get_random_bytes(void *buf, size_t len);
-size_t __must_check get_random_bytes_arch(void *buf, size_t len);
 u32 get_random_u32(void);
 u64 get_random_u64(void);
 static inline unsigned int get_random_int(void)
@@ -77,6 +76,7 @@ unsigned long randomize_page(unsigned long start, unsigned long range);
 
 int __init random_init(const char *command_line);
 bool rng_is_initialized(void);
+bool rng_has_arch_random(void);
 int wait_for_random_bytes(void);
 int register_random_ready_notifier(struct notifier_block *nb);
 int unregister_random_ready_notifier(struct notifier_block *nb);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 40d26a07a133..20e9887faaaa 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -776,12 +776,11 @@ static struct notifier_block random_ready = {
 
 static int __init initialize_ptr_random(void)
 {
-	int key_size = sizeof(ptr_key);
 	int ret;
 
-	/* Use hw RNG if available. */
-	if (get_random_bytes_arch(&ptr_key, key_size) == key_size) {
-		static_branch_disable(&not_filled_random_ptr_key);
+	/* Don't bother waiting for RNG to be ready if RDRAND is mixed in already. */
+	if (rng_has_arch_random()) {
+		enable_ptr_key_workfn(&enable_ptr_key_work);
 		return 0;
 	}
 
-- 
cgit v1.2.3


From 6701de6c51c172b5de5633374479503c81fefc0b Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sun, 15 May 2022 15:06:18 +0200
Subject: random: remove mostly unused async readiness notifier

The register_random_ready_notifier() notifier is somewhat complicated,
and was already recently rewritten to use notifier blocks. It is only
used now by one consumer in the kernel, vsprintf.c, for which the async
mechanism is really overly complex for what it actually needs. This
commit removes register_random_ready_notifier() and unregister_random_
ready_notifier(), because it just adds complication with little utility,
and changes vsprintf.c to just check on `!rng_is_initialized() &&
!rng_has_arch_random()`, which will eventually be true. Performance-
wise, that code was already using a static branch, so there's basically
no overhead at all to this change.

Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Acked-by: Petr Mladek <pmladek@suse.com> # for vsprintf.c
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 drivers/char/random.c  | 48 ------------------------------------
 include/linux/random.h |  2 --
 lib/vsprintf.c         | 66 +++++++++++++++++---------------------------------
 3 files changed, 22 insertions(+), 94 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 6b8c89378954..16b39d2dead7 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -84,8 +84,6 @@ static DEFINE_STATIC_KEY_FALSE(crng_is_ready);
 /* Various types of waiters for crng_init->CRNG_READY transition. */
 static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
 static struct fasync_struct *fasync;
-static DEFINE_SPINLOCK(random_ready_chain_lock);
-static RAW_NOTIFIER_HEAD(random_ready_chain);
 
 /* Control how we warn userspace. */
 static struct ratelimit_state urandom_warning =
@@ -142,51 +140,6 @@ int wait_for_random_bytes(void)
 }
 EXPORT_SYMBOL(wait_for_random_bytes);
 
-/*
- * Add a callback function that will be invoked when the input
- * pool is initialised.
- *
- * returns: 0 if callback is successfully added
- *	    -EALREADY if pool is already initialised (callback not called)
- */
-int __cold register_random_ready_notifier(struct notifier_block *nb)
-{
-	unsigned long flags;
-	int ret = -EALREADY;
-
-	if (crng_ready())
-		return ret;
-
-	spin_lock_irqsave(&random_ready_chain_lock, flags);
-	if (!crng_ready())
-		ret = raw_notifier_chain_register(&random_ready_chain, nb);
-	spin_unlock_irqrestore(&random_ready_chain_lock, flags);
-	return ret;
-}
-
-/*
- * Delete a previously registered readiness callback function.
- */
-int __cold unregister_random_ready_notifier(struct notifier_block *nb)
-{
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&random_ready_chain_lock, flags);
-	ret = raw_notifier_chain_unregister(&random_ready_chain, nb);
-	spin_unlock_irqrestore(&random_ready_chain_lock, flags);
-	return ret;
-}
-
-static void __cold process_random_ready_list(void)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&random_ready_chain_lock, flags);
-	raw_notifier_call_chain(&random_ready_chain, 0, NULL);
-	spin_unlock_irqrestore(&random_ready_chain_lock, flags);
-}
-
 #define warn_unseeded_randomness() \
 	if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \
 		printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \
@@ -775,7 +728,6 @@ static void __cold _credit_init_bits(size_t bits)
 	if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) {
 		crng_reseed(); /* Sets crng_init to CRNG_READY under base_crng.lock. */
 		execute_in_process_context(crng_set_ready, &set_ready);
-		process_random_ready_list();
 		wake_up_interruptible(&crng_init_wait);
 		kill_fasync(&fasync, SIGIO, POLL_IN);
 		pr_notice("crng init done\n");
diff --git a/include/linux/random.h b/include/linux/random.h
index 6af130c6edb9..d2360b2825b6 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -78,8 +78,6 @@ int __init random_init(const char *command_line);
 bool rng_is_initialized(void);
 bool rng_has_arch_random(void);
 int wait_for_random_bytes(void);
-int register_random_ready_notifier(struct notifier_block *nb);
-int unregister_random_ready_notifier(struct notifier_block *nb);
 
 /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes).
  * Returns the result of the call to wait_for_random_bytes. */
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 20e9887faaaa..fb77f7bfd126 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -750,60 +750,38 @@ static int __init debug_boot_weak_hash_enable(char *str)
 }
 early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable);
 
-static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key);
-static siphash_key_t ptr_key __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(filled_random_ptr_key);
 
 static void enable_ptr_key_workfn(struct work_struct *work)
 {
-	get_random_bytes(&ptr_key, sizeof(ptr_key));
-	/* Needs to run from preemptible context */
-	static_branch_disable(&not_filled_random_ptr_key);
+	static_branch_enable(&filled_random_ptr_key);
 }
 
-static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
-
-static int fill_random_ptr_key(struct notifier_block *nb,
-			       unsigned long action, void *data)
-{
-	/* This may be in an interrupt handler. */
-	queue_work(system_unbound_wq, &enable_ptr_key_work);
-	return 0;
-}
-
-static struct notifier_block random_ready = {
-	.notifier_call = fill_random_ptr_key
-};
-
-static int __init initialize_ptr_random(void)
-{
-	int ret;
-
-	/* Don't bother waiting for RNG to be ready if RDRAND is mixed in already. */
-	if (rng_has_arch_random()) {
-		enable_ptr_key_workfn(&enable_ptr_key_work);
-		return 0;
-	}
-
-	ret = register_random_ready_notifier(&random_ready);
-	if (!ret) {
-		return 0;
-	} else if (ret == -EALREADY) {
-		/* This is in preemptible context */
-		enable_ptr_key_workfn(&enable_ptr_key_work);
-		return 0;
-	}
-
-	return ret;
-}
-early_initcall(initialize_ptr_random);
-
 /* Maps a pointer to a 32 bit unique identifier. */
 static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out)
 {
+	static siphash_key_t ptr_key __read_mostly;
 	unsigned long hashval;
 
-	if (static_branch_unlikely(&not_filled_random_ptr_key))
-		return -EAGAIN;
+	if (!static_branch_likely(&filled_random_ptr_key)) {
+		static bool filled = false;
+		static DEFINE_SPINLOCK(filling);
+		static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
+		unsigned long flags;
+
+		if (!system_unbound_wq ||
+		    (!rng_is_initialized() && !rng_has_arch_random()) ||
+		    !spin_trylock_irqsave(&filling, flags))
+			return -EAGAIN;
+
+		if (!filled) {
+			get_random_bytes(&ptr_key, sizeof(ptr_key));
+			queue_work(system_unbound_wq, &enable_ptr_key_work);
+			filled = true;
+		}
+		spin_unlock_irqrestore(&filling, flags);
+	}
+
 
 #ifdef CONFIG_64BIT
 	hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key);
-- 
cgit v1.2.3


From 5ad7dd882e45d7fe432c32e896e2aaa0b21746ea Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sat, 14 May 2022 13:59:30 +0200
Subject: random: move randomize_page() into mm where it belongs

randomize_page is an mm function. It is documented like one. It contains
the history of one. It has the naming convention of one. It looks
just like another very similar function in mm, randomize_stack_top().
And it has always been maintained and updated by mm people. There is no
need for it to be in random.c. In the "which shape does not look like
the other ones" test, pointing to randomize_page() is correct.

So move randomize_page() into mm/util.c, right next to the similar
randomize_stack_top() function.

This commit contains no actual code changes.

Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 drivers/char/random.c  | 32 --------------------------------
 include/linux/mm.h     |  1 +
 include/linux/random.h |  2 --
 mm/util.c              | 32 ++++++++++++++++++++++++++++++++
 4 files changed, 33 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 16b39d2dead7..36183b0cf923 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -573,38 +573,6 @@ int __cold random_prepare_cpu(unsigned int cpu)
 }
 #endif
 
-/**
- * randomize_page - Generate a random, page aligned address
- * @start:	The smallest acceptable address the caller will take.
- * @range:	The size of the area, starting at @start, within which the
- *		random address must fall.
- *
- * If @start + @range would overflow, @range is capped.
- *
- * NOTE: Historical use of randomize_range, which this replaces, presumed that
- * @start was already page aligned.  We now align it regardless.
- *
- * Return: A page aligned address within [start, start + range).  On error,
- * @start is returned.
- */
-unsigned long randomize_page(unsigned long start, unsigned long range)
-{
-	if (!PAGE_ALIGNED(start)) {
-		range -= PAGE_ALIGN(start) - start;
-		start = PAGE_ALIGN(start);
-	}
-
-	if (start > ULONG_MAX - range)
-		range = ULONG_MAX - start;
-
-	range >>= PAGE_SHIFT;
-
-	if (range == 0)
-		return start;
-
-	return start + (get_random_long() % range << PAGE_SHIFT);
-}
-
 
 /**********************************************************************
  *
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9f44254af8ce..b0183450e484 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2677,6 +2677,7 @@ extern int install_special_mapping(struct mm_struct *mm,
 				   unsigned long flags, struct page **pages);
 
 unsigned long randomize_stack_top(unsigned long stack_top);
+unsigned long randomize_page(unsigned long start, unsigned long range);
 
 extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 
diff --git a/include/linux/random.h b/include/linux/random.h
index d2360b2825b6..fae0c84027fd 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -72,8 +72,6 @@ static inline unsigned long get_random_canary(void)
 	return get_random_long() & CANARY_MASK;
 }
 
-unsigned long randomize_page(unsigned long start, unsigned long range);
-
 int __init random_init(const char *command_line);
 bool rng_is_initialized(void);
 bool rng_has_arch_random(void);
diff --git a/mm/util.c b/mm/util.c
index 3492a9e81aa3..ac63e5ca8b21 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -343,6 +343,38 @@ unsigned long randomize_stack_top(unsigned long stack_top)
 #endif
 }
 
+/**
+ * randomize_page - Generate a random, page aligned address
+ * @start:	The smallest acceptable address the caller will take.
+ * @range:	The size of the area, starting at @start, within which the
+ *		random address must fall.
+ *
+ * If @start + @range would overflow, @range is capped.
+ *
+ * NOTE: Historical use of randomize_range, which this replaces, presumed that
+ * @start was already page aligned.  We now align it regardless.
+ *
+ * Return: A page aligned address within [start, start + range).  On error,
+ * @start is returned.
+ */
+unsigned long randomize_page(unsigned long start, unsigned long range)
+{
+	if (!PAGE_ALIGNED(start)) {
+		range -= PAGE_ALIGN(start) - start;
+		start = PAGE_ALIGN(start);
+	}
+
+	if (start > ULONG_MAX - range)
+		range = ULONG_MAX - start;
+
+	range >>= PAGE_SHIFT;
+
+	if (range == 0)
+		return start;
+
+	return start + (get_random_long() % range << PAGE_SHIFT);
+}
+
 #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 unsigned long arch_randomize_brk(struct mm_struct *mm)
 {
-- 
cgit v1.2.3


From 135c579d77d066aece83609329150b87fe81e454 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Mon, 2 May 2022 18:25:05 +0900
Subject: tty: serial: samsung_tty: Fix suspend/resume on S5L

We were restoring the IRQ masks then clearing them again, because
ucon_mask wasn't set properly. Adding that makes suspend/resume
work as intended.

Signed-off-by: Hector Martin <marcan@marcan.st>
Link: https://lore.kernel.org/r/20220502092505.30934-1-marcan@marcan.st
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/samsung_tty.c | 1 +
 include/linux/serial_s3c.h       | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c
index 8af5aceb9f4e..d5ca904def34 100644
--- a/drivers/tty/serial/samsung_tty.c
+++ b/drivers/tty/serial/samsung_tty.c
@@ -2826,6 +2826,7 @@ static const struct s3c24xx_serial_drv_data s5l_serial_drv_data = {
 		.num_clks	= 1,
 		.clksel_mask	= 0,
 		.clksel_shift	= 0,
+		.ucon_mask	= APPLE_S5L_UCON_MASK,
 	},
 	.def_cfg = {
 		.ucon		= APPLE_S5L_UCON_DEFAULT,
diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h
index f6c3323fc4c5..dec15f5b3dec 100644
--- a/include/linux/serial_s3c.h
+++ b/include/linux/serial_s3c.h
@@ -256,6 +256,9 @@
 #define APPLE_S5L_UCON_DEFAULT		(S3C2410_UCON_TXIRQMODE | \
 					 S3C2410_UCON_RXIRQMODE | \
 					 S3C2410_UCON_RXFIFO_TOI)
+#define APPLE_S5L_UCON_MASK		(APPLE_S5L_UCON_RXTO_ENA_MSK | \
+					 APPLE_S5L_UCON_RXTHRESH_ENA_MSK | \
+					 APPLE_S5L_UCON_TXTHRESH_ENA_MSK)
 
 #define APPLE_S5L_UTRSTAT_RXTHRESH	(1<<4)
 #define APPLE_S5L_UTRSTAT_TXTHRESH	(1<<5)
-- 
cgit v1.2.3


From 0b6c14bdd908879078ec85d65cfb78472a97e4e7 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 1 Apr 2022 13:10:31 -0400
Subject: SUNRPC: Make cache_req::thread_wait an unsigned long

The second parameter of wait_for_completion_interruptible_timeout()
is a jiffies value whose type is "unsigned long". Avoid an
unnecessary and potentially fraught implicit type conversion at the
wait_for_completion_interruptible_timeout() call site in
cache_wait_req().

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/cache.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index b134b2b3371c..ec5a555df96f 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -121,17 +121,17 @@ struct cache_detail {
 	struct net		*net;
 };
 
-
 /* this must be embedded in any request structure that
  * identifies an object that will want a callback on
  * a cache fill
  */
 struct cache_req {
 	struct cache_deferred_req *(*defer)(struct cache_req *req);
-	int thread_wait;  /* How long (jiffies) we can block the
-			   * current thread to wait for updates.
-			   */
+	unsigned long	thread_wait;	/* How long (jiffies) we can block the
+					 * current thread to wait for updates.
+					 */
 };
+
 /* this must be embedded in a deferred_request that is being
  * delayed awaiting cache-fill
  */
-- 
cgit v1.2.3


From 983084b2672c593959e3148d6a17c8b920797dde Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 6 Apr 2022 14:38:59 -0400
Subject: SUNRPC: Remove svc_rqst::rq_xprt_hlen

Clean up: This field is now always set to zero.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc.h              |  2 --
 include/trace/events/sunrpc.h           |  3 +--
 net/sunrpc/svc_xprt.c                   | 10 ++++------
 net/sunrpc/svcsock.c                    |  2 --
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c |  1 -
 5 files changed, 5 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 217711fc9cac..b73704fbd09b 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -257,7 +257,6 @@ struct svc_rqst {
 	void *			rq_xprt_ctxt;	/* transport specific context ptr */
 	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */
 
-	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
 	struct xdr_stream	rq_arg_stream;
 	struct xdr_stream	rq_res_stream;
@@ -397,7 +396,6 @@ struct svc_deferred_req {
 	size_t			daddrlen;
 	void			*xprt_ctxt;
 	struct cache_deferred_req handle;
-	size_t			xprt_hlen;
 	int			argslen;
 	__be32			args[];
 };
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index ee84e9289707..b61d9c90fa26 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -2020,8 +2020,7 @@ DECLARE_EVENT_CLASS(svc_deferred_event,
 
 	TP_fast_assign(
 		__entry->dr = dr;
-		__entry->xid = be32_to_cpu(*(__be32 *)(dr->args +
-						       (dr->xprt_hlen>>2)));
+		__entry->xid = be32_to_cpu(*(__be32 *)dr->args);
 		__assign_sockaddr(addr, &dr->addr, dr->addrlen);
 	),
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 5b59e2103526..f9d9922f1629 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1230,7 +1230,6 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 		dr->addrlen = rqstp->rq_addrlen;
 		dr->daddr = rqstp->rq_daddr;
 		dr->argslen = rqstp->rq_arg.len >> 2;
-		dr->xprt_hlen = rqstp->rq_xprt_hlen;
 		dr->xprt_ctxt = rqstp->rq_xprt_ctxt;
 		rqstp->rq_xprt_ctxt = NULL;
 
@@ -1258,22 +1257,21 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp)
 	trace_svc_defer_recv(dr);
 
 	/* setup iov_base past transport header */
-	rqstp->rq_arg.head[0].iov_base = dr->args + (dr->xprt_hlen>>2);
+	rqstp->rq_arg.head[0].iov_base = dr->args;
 	/* The iov_len does not include the transport header bytes */
-	rqstp->rq_arg.head[0].iov_len = (dr->argslen<<2) - dr->xprt_hlen;
+	rqstp->rq_arg.head[0].iov_len = dr->argslen << 2;
 	rqstp->rq_arg.page_len = 0;
 	/* The rq_arg.len includes the transport header bytes */
-	rqstp->rq_arg.len     = dr->argslen<<2;
+	rqstp->rq_arg.len     = dr->argslen << 2;
 	rqstp->rq_prot        = dr->prot;
 	memcpy(&rqstp->rq_addr, &dr->addr, dr->addrlen);
 	rqstp->rq_addrlen     = dr->addrlen;
 	/* Save off transport header len in case we get deferred again */
-	rqstp->rq_xprt_hlen   = dr->xprt_hlen;
 	rqstp->rq_daddr       = dr->daddr;
 	rqstp->rq_respages    = rqstp->rq_pages;
 	rqstp->rq_xprt_ctxt   = dr->xprt_ctxt;
 	svc_xprt_received(rqstp->rq_xprt);
-	return (dr->argslen<<2) - dr->xprt_hlen;
+	return dr->argslen << 2;
 }
 
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 68e46d4547b4..05452318afec 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -250,8 +250,6 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen,
 	ssize_t len;
 	size_t t;
 
-	rqstp->rq_xprt_hlen = 0;
-
 	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
 	for (i = 0, t = 0; t < buflen; i++, t += PAGE_SIZE) {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 864131a9fc6e..5242ad121450 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -831,7 +831,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		goto out_err;
 	if (ret == 0)
 		goto out_drop;
-	rqstp->rq_xprt_hlen = 0;
 
 	if (svc_rdma_is_reverse_direction_reply(xprt, ctxt))
 		goto out_backchannel;
-- 
cgit v1.2.3


From 591502c5cb325b1c6ec59ab161927d606b918aa0 Mon Sep 17 00:00:00 2001
From: Dai Ngo <dai.ngo@oracle.com>
Date: Mon, 2 May 2022 14:19:24 -0700
Subject: fs/lock: add helper locks_owner_has_blockers to check for blockers

Add helper locks_owner_has_blockers to check if there is any blockers
for a given lockowner.

Reviewed-by: J. Bruce Fields <bfields@fieldses.org>
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 fs/locks.c         | 28 ++++++++++++++++++++++++++++
 include/linux/fs.h |  7 +++++++
 2 files changed, 35 insertions(+)

(limited to 'include/linux')

diff --git a/fs/locks.c b/fs/locks.c
index 8c6df10cd9ed..c369841ef7d1 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -300,6 +300,34 @@ void locks_release_private(struct file_lock *fl)
 }
 EXPORT_SYMBOL_GPL(locks_release_private);
 
+/**
+ * locks_owner_has_blockers - Check for blocking lock requests
+ * @flctx: file lock context
+ * @owner: lock owner
+ *
+ * Return values:
+ *   %true: @owner has at least one blocker
+ *   %false: @owner has no blockers
+ */
+bool locks_owner_has_blockers(struct file_lock_context *flctx,
+		fl_owner_t owner)
+{
+	struct file_lock *fl;
+
+	spin_lock(&flctx->flc_lock);
+	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+		if (fl->fl_owner != owner)
+			continue;
+		if (!list_empty(&fl->fl_blocked_requests)) {
+			spin_unlock(&flctx->flc_lock);
+			return true;
+		}
+	}
+	spin_unlock(&flctx->flc_lock);
+	return false;
+}
+EXPORT_SYMBOL_GPL(locks_owner_has_blockers);
+
 /* Free a lock which is not in use. */
 void locks_free_lock(struct file_lock *fl)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde95387a23..b8ed7f974fb4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1174,6 +1174,8 @@ extern void lease_unregister_notifier(struct notifier_block *);
 struct files_struct;
 extern void show_fd_locks(struct seq_file *f,
 			 struct file *filp, struct files_struct *files);
+extern bool locks_owner_has_blockers(struct file_lock_context *flctx,
+			fl_owner_t owner);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1309,6 +1311,11 @@ static inline int lease_modify(struct file_lock *fl, int arg,
 struct files_struct;
 static inline void show_fd_locks(struct seq_file *f,
 			struct file *filp, struct files_struct *files) {}
+static inline bool locks_owner_has_blockers(struct file_lock_context *flctx,
+			fl_owner_t owner)
+{
+	return false;
+}
 #endif /* !CONFIG_FILE_LOCKING */
 
 static inline struct inode *file_inode(const struct file *f)
-- 
cgit v1.2.3


From 2443da2259e97688f93d64d17ab69b15f466078a Mon Sep 17 00:00:00 2001
From: Dai Ngo <dai.ngo@oracle.com>
Date: Mon, 2 May 2022 14:19:25 -0700
Subject: fs/lock: add 2 callbacks to lock_manager_operations to resolve
 conflict

Add 2 new callbacks, lm_lock_expirable and lm_expire_lock, to
lock_manager_operations to allow the lock manager to take appropriate
action to resolve the lock conflict if possible.

A new field, lm_mod_owner, is also added to lock_manager_operations.
The lm_mod_owner is used by the fs/lock code to make sure the lock
manager module such as nfsd, is not freed while lock conflict is being
resolved.

lm_lock_expirable checks and returns true to indicate that the lock
conflict can be resolved else return false. This callback must be
called with the flc_lock held so it can not block.

lm_expire_lock is called to resolve the lock conflict if the returned
value from lm_lock_expirable is true. This callback is called without
the flc_lock held since it's allowed to block. Upon returning from
this callback, the lock conflict should be resolved and the caller is
expected to restart the conflict check from the beginnning of the list.

Lock manager, such as NFSv4 courteous server, uses this callback to
resolve conflict by destroying lock owner, or the NFSv4 courtesy client
(client that has expired but allowed to maintains its states) that owns
the lock.

Reviewed-by: J. Bruce Fields <bfields@fieldses.org>
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
---
 Documentation/filesystems/locking.rst |  4 ++++
 fs/locks.c                            | 33 ++++++++++++++++++++++++++++++---
 include/linux/fs.h                    |  3 +++
 3 files changed, 37 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index c26d854275a0..0997a258361a 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -428,6 +428,8 @@ prototypes::
 	void (*lm_break)(struct file_lock *); /* break_lease callback */
 	int (*lm_change)(struct file_lock **, int);
 	bool (*lm_breaker_owns_lease)(struct file_lock *);
+        bool (*lm_lock_expirable)(struct file_lock *);
+        void (*lm_expire_lock)(void);
 
 locking rules:
 
@@ -439,6 +441,8 @@ lm_grant:		no		no			no
 lm_break:		yes		no			no
 lm_change		yes		no			no
 lm_breaker_owns_lease:	yes     	no			no
+lm_lock_expirable	yes		no			no
+lm_expire_lock		no		no			yes
 ======================	=============	=================	=========
 
 buffer_head
diff --git a/fs/locks.c b/fs/locks.c
index c369841ef7d1..ca28e0e50e56 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -902,6 +902,8 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 	struct file_lock *cfl;
 	struct file_lock_context *ctx;
 	struct inode *inode = locks_inode(filp);
+	void *owner;
+	void (*func)(void);
 
 	ctx = smp_load_acquire(&inode->i_flctx);
 	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
@@ -909,12 +911,23 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 		return;
 	}
 
+retry:
 	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
-		if (posix_locks_conflict(fl, cfl)) {
-			locks_copy_conflock(fl, cfl);
-			goto out;
+		if (!posix_locks_conflict(fl, cfl))
+			continue;
+		if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable
+			&& (*cfl->fl_lmops->lm_lock_expirable)(cfl)) {
+			owner = cfl->fl_lmops->lm_mod_owner;
+			func = cfl->fl_lmops->lm_expire_lock;
+			__module_get(owner);
+			spin_unlock(&ctx->flc_lock);
+			(*func)();
+			module_put(owner);
+			goto retry;
 		}
+		locks_copy_conflock(fl, cfl);
+		goto out;
 	}
 	fl->fl_type = F_UNLCK;
 out:
@@ -1088,6 +1101,8 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 	int error;
 	bool added = false;
 	LIST_HEAD(dispose);
+	void *owner;
+	void (*func)(void);
 
 	ctx = locks_get_lock_context(inode, request->fl_type);
 	if (!ctx)
@@ -1106,6 +1121,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 		new_fl2 = locks_alloc_lock();
 	}
 
+retry:
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	/*
@@ -1117,6 +1133,17 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 			if (!posix_locks_conflict(request, fl))
 				continue;
+			if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable
+				&& (*fl->fl_lmops->lm_lock_expirable)(fl)) {
+				owner = fl->fl_lmops->lm_mod_owner;
+				func = fl->fl_lmops->lm_expire_lock;
+				__module_get(owner);
+				spin_unlock(&ctx->flc_lock);
+				percpu_up_read(&file_rwsem);
+				(*func)();
+				module_put(owner);
+				goto retry;
+			}
 			if (conflock)
 				locks_copy_conflock(conflock, fl);
 			error = -EAGAIN;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b8ed7f974fb4..aa6c1bbdb8c4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1029,6 +1029,7 @@ struct file_lock_operations {
 };
 
 struct lock_manager_operations {
+	void *lm_mod_owner;
 	fl_owner_t (*lm_get_owner)(fl_owner_t);
 	void (*lm_put_owner)(fl_owner_t);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
@@ -1037,6 +1038,8 @@ struct lock_manager_operations {
 	int (*lm_change)(struct file_lock *, int, struct list_head *);
 	void (*lm_setup)(struct file_lock *, void **);
 	bool (*lm_breaker_owns_lease)(struct file_lock *);
+	bool (*lm_lock_expirable)(struct file_lock *cfl);
+	void (*lm_expire_lock)(void);
 };
 
 struct lock_manager {
-- 
cgit v1.2.3


From 2059b698a2efcce3c67b0e61eab7d7680bbe10bd Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 10 May 2022 11:45:53 -0400
Subject: SUNRPC: Simplify synopsis of svc_pool_for_cpu()

Clean up: There is one caller. The @cpu argument can be made
implicit now that a get_cpu/put_cpu pair is no longer needed.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc.h |  2 +-
 net/sunrpc/svc.c           | 18 ++++++++++++------
 net/sunrpc/svc_xprt.c      |  2 +-
 3 files changed, 14 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index b73704fbd09b..daecb009c05b 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -504,7 +504,7 @@ int		   svc_register(const struct svc_serv *, struct net *, const int,
 
 void		   svc_wake_up(struct svc_serv *);
 void		   svc_reserve(struct svc_rqst *rqstp, int space);
-struct svc_pool *  svc_pool_for_cpu(struct svc_serv *serv, int cpu);
+struct svc_pool   *svc_pool_for_cpu(struct svc_serv *serv);
 char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
 const char *	   svc_proc_name(const struct svc_rqst *rqstp);
 int		   svc_encode_result_payload(struct svc_rqst *rqstp,
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 557004017548..56bed0a57eea 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -356,15 +356,21 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
 	}
 }
 
-/*
- * Use the mapping mode to choose a pool for a given CPU.
- * Used when enqueueing an incoming RPC.  Always returns
- * a non-NULL pool pointer.
+/**
+ * svc_pool_for_cpu - Select pool to run a thread on this cpu
+ * @serv: An RPC service
+ *
+ * Use the active CPU and the svc_pool_map's mode setting to
+ * select the svc thread pool to use. Once initialized, the
+ * svc_pool_map does not change.
+ *
+ * Return value:
+ *   A pointer to an svc_pool
  */
-struct svc_pool *
-svc_pool_for_cpu(struct svc_serv *serv, int cpu)
+struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv)
 {
 	struct svc_pool_map *m = &svc_pool_map;
+	int cpu = raw_smp_processor_id();
 	unsigned int pidx = 0;
 
 	if (serv->sv_nrpools <= 1)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 66cf720853bb..5df90bca10ed 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -460,7 +460,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags))
 		return;
 
-	pool = svc_pool_for_cpu(xprt->xpt_server, raw_smp_processor_id());
+	pool = svc_pool_for_cpu(xprt->xpt_server);
 
 	atomic_long_inc(&pool->sp_stats.packets);
 
-- 
cgit v1.2.3


From 53c83d6d8e399fad3d3d25df0ea0d54eb0f94f88 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 18 May 2022 15:23:45 +0200
Subject: siphash: add SPDX tags as sole licensing authority

The text "dual BSD/GPLv2 license" is somewhat ambiguous, and moving this
over to SPDX is overdue. This commit adds SPDX tags to the relevant
files and clarifies that it's GPLv2 only and 3-clause BSD. It also
removes the old text, so that the SPDX tags are the only source of the
information.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/siphash.h | 5 ++---
 lib/siphash.c           | 5 ++---
 lib/test_siphash.c      | 7 +++----
 3 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index cce8a9acc76c..9e822311b29e 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -1,6 +1,5 @@
-/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- *
- * This file is provided under a dual BSD/GPLv2 license.
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  *
  * SipHash: a fast short-input PRF
  * https://131002.net/siphash/
diff --git a/lib/siphash.c b/lib/siphash.c
index 72b9068ab57b..f08fd988173b 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -1,6 +1,5 @@
-/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- *
- * This file is provided under a dual BSD/GPLv2 license.
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  *
  * SipHash: a fast short-input PRF
  * https://131002.net/siphash/
diff --git a/lib/test_siphash.c b/lib/test_siphash.c
index a6d854d933bf..a96788d0141d 100644
--- a/lib/test_siphash.c
+++ b/lib/test_siphash.c
@@ -1,8 +1,7 @@
-/* Test cases for siphash.c
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  *
- * Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- *
- * This file is provided under a dual BSD/GPLv2 license.
+ * Test cases for siphash.c
  *
  * SipHash: a fast short-input PRF
  * https://131002.net/siphash/
-- 
cgit v1.2.3


From e6d3c99adf54fc1dcd07729990dc32acd3be874b Mon Sep 17 00:00:00 2001
From: Abhyuday Godhasara <abhyuday.godhasara@xilinx.com>
Date: Wed, 27 Apr 2022 00:48:03 -0700
Subject: driver: soc: xilinx: Update function prototype for
 xlnx_unregister_event

As per the current implementation only single callback data gets saved per
event, driver is throwing an error if try to register multiple callback for
same event. So at time of unregistration of any event required things are
event details and callback handler as parameter of xlnx_unregister_event().

As part of adding support of multiple callbacks for same event also require
change in prototype of xlnx_unregister_event().
During unregistration of any events, now required things are event details,
callback handler and agent's private data as parameter of
xlnx_unregister_event().

Also modify the usage of xlnx_unregister_event() in xilinx/zynqmp_power.c
driver as per new implementation.

Signed-off-by: Abhyuday Godhasara <abhyuday.godhasara@xilinx.com>
Link: https://lore.kernel.org/r/20220427074803.19009-3-abhyuday.godhasara@xilinx.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/soc/xilinx/xlnx_event_manager.c     | 58 +++++++++++++++++++----------
 drivers/soc/xilinx/zynqmp_power.c           |  7 ++--
 include/linux/firmware/xlnx-event-manager.h |  4 +-
 3 files changed, 45 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index f89000dc33a3..5dcb7665fe22 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -41,6 +41,8 @@ static int event_manager_availability = -EACCES;
 static DEFINE_HASHTABLE(reg_driver_map, REGISTERED_DRIVER_MAX_ORDER);
 static int sgi_num = XLNX_EVENT_SGI_NUM;
 
+static bool is_need_to_unregister;
+
 /**
  * struct agent_cb - Registered callback function and private data.
  * @agent_data:		Data passed back to handler function.
@@ -189,6 +191,8 @@ static int xlnx_remove_cb_for_suspend(event_cb_func_t cb_fun)
 	struct agent_cb *cb_pos;
 	struct agent_cb *cb_next;
 
+	is_need_to_unregister = false;
+
 	/* Check for existing entry in hash table for given cb_type */
 	hash_for_each_possible(reg_driver_map, eve_data, hentry, PM_INIT_SUSPEND_CB) {
 		if (eve_data->cb_type == PM_INIT_SUSPEND_CB) {
@@ -203,6 +207,7 @@ static int xlnx_remove_cb_for_suspend(event_cb_func_t cb_fun)
 			/* remove an object from a hashtable */
 			hash_del(&eve_data->hentry);
 			kfree(eve_data);
+			is_need_to_unregister = true;
 		}
 	}
 	if (!is_callback_found) {
@@ -214,7 +219,7 @@ static int xlnx_remove_cb_for_suspend(event_cb_func_t cb_fun)
 }
 
 static int xlnx_remove_cb_for_notify_event(const u32 node_id, const u32 event,
-					   event_cb_func_t cb_fun)
+					   event_cb_func_t cb_fun, void *data)
 {
 	bool is_callback_found = false;
 	struct registered_event_data *eve_data;
@@ -222,20 +227,28 @@ static int xlnx_remove_cb_for_notify_event(const u32 node_id, const u32 event,
 	struct agent_cb *cb_pos;
 	struct agent_cb *cb_next;
 
+	is_need_to_unregister = false;
+
 	/* Check for existing entry in hash table for given key id */
 	hash_for_each_possible(reg_driver_map, eve_data, hentry, key) {
 		if (eve_data->key == key) {
 			/* Delete the list of callback */
 			list_for_each_entry_safe(cb_pos, cb_next, &eve_data->cb_list_head, list) {
-				if (cb_pos->eve_cb == cb_fun) {
+				if (cb_pos->eve_cb == cb_fun &&
+				    cb_pos->agent_data == data) {
 					is_callback_found = true;
 					list_del_init(&cb_pos->list);
 					kfree(cb_pos);
 				}
 			}
-			/* remove an object from a HASH table */
-			hash_del(&eve_data->hentry);
-			kfree(eve_data);
+
+			/* Remove HASH table if callback list is empty */
+			if (list_empty(&eve_data->cb_list_head)) {
+				/* remove an object from a HASH table */
+				hash_del(&eve_data->hentry);
+				kfree(eve_data);
+				is_need_to_unregister = true;
+			}
 		}
 	}
 	if (!is_callback_found) {
@@ -307,7 +320,7 @@ int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, cons
 					eve = event & (1 << pos);
 					if (!eve)
 						continue;
-					xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun);
+					xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun, data);
 				}
 			}
 		}
@@ -329,10 +342,10 @@ int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, cons
 					eve = event & (1 << pos);
 					if (!eve)
 						continue;
-					xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun);
+					xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun, data);
 				}
 			} else {
-				xlnx_remove_cb_for_notify_event(node_id, event, cb_fun);
+				xlnx_remove_cb_for_notify_event(node_id, event, cb_fun, data);
 			}
 			return ret;
 		}
@@ -350,15 +363,18 @@ EXPORT_SYMBOL_GPL(xlnx_register_event);
  * @node_id:	Node-Id related to event.
  * @event:	Event Mask for the Error Event.
  * @cb_fun:	Function pointer of callback function.
+ * @data:	Pointer of agent's private data.
  *
  * Return:	Returns 0 on successful unregistration else error code.
  */
 int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, const u32 event,
-			  event_cb_func_t cb_fun)
+			  event_cb_func_t cb_fun, void *data)
 {
-	int ret;
+	int ret = 0;
 	u32 eve, pos;
 
+	is_need_to_unregister = false;
+
 	if (event_manager_availability)
 		return event_manager_availability;
 
@@ -375,23 +391,26 @@ int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, co
 	} else {
 		/* Remove Node-Id/Event from hash table */
 		if (!xlnx_is_error_event(node_id)) {
-			xlnx_remove_cb_for_notify_event(node_id, event, cb_fun);
+			xlnx_remove_cb_for_notify_event(node_id, event, cb_fun, data);
 		} else {
 			for (pos = 0; pos < MAX_BITS; pos++) {
 				eve = event & (1 << pos);
 				if (!eve)
 					continue;
 
-				xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun);
+				xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun, data);
 			}
 		}
 
-		/* Un-register for Node-Id/Event combination */
-		ret = zynqmp_pm_register_notifier(node_id, event, false, false);
-		if (ret) {
-			pr_err("%s() failed for 0x%x and 0x%x: %d\n",
-			       __func__, node_id, event, ret);
-			return ret;
+		/* Un-register if list is empty */
+		if (is_need_to_unregister) {
+			/* Un-register for Node-Id/Event combination */
+			ret = zynqmp_pm_register_notifier(node_id, event, false, false);
+			if (ret) {
+				pr_err("%s() failed for 0x%x and 0x%x: %d\n",
+				       __func__, node_id, event, ret);
+				return ret;
+			}
 		}
 	}
 
@@ -447,7 +466,8 @@ static void xlnx_call_notify_cb_handler(const u32 *payload)
 							 list) {
 					/* Remove already registered event from hash table */
 					xlnx_remove_cb_for_notify_event(payload[1], payload[2],
-									cb_pos->eve_cb);
+									cb_pos->eve_cb,
+									cb_pos->agent_data);
 				}
 			}
 		}
diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c
index 859dd31b6eff..78a8a7545d1e 100644
--- a/drivers/soc/xilinx/zynqmp_power.c
+++ b/drivers/soc/xilinx/zynqmp_power.c
@@ -208,7 +208,7 @@ static int zynqmp_pm_probe(struct platform_device *pdev)
 							   GFP_KERNEL);
 		if (!zynqmp_pm_init_suspend_work) {
 			xlnx_unregister_event(PM_INIT_SUSPEND_CB, 0, 0,
-					      suspend_event_callback);
+					      suspend_event_callback, NULL);
 			return -ENOMEM;
 		}
 		event_registered = true;
@@ -263,7 +263,8 @@ static int zynqmp_pm_probe(struct platform_device *pdev)
 	ret = sysfs_create_file(&pdev->dev.kobj, &dev_attr_suspend_mode.attr);
 	if (ret) {
 		if (event_registered) {
-			xlnx_unregister_event(PM_INIT_SUSPEND_CB, 0, 0, suspend_event_callback);
+			xlnx_unregister_event(PM_INIT_SUSPEND_CB, 0, 0, suspend_event_callback,
+					      NULL);
 			event_registered = false;
 		}
 		dev_err(&pdev->dev, "unable to create sysfs interface\n");
@@ -277,7 +278,7 @@ static int zynqmp_pm_remove(struct platform_device *pdev)
 {
 	sysfs_remove_file(&pdev->dev.kobj, &dev_attr_suspend_mode.attr);
 	if (event_registered)
-		xlnx_unregister_event(PM_INIT_SUSPEND_CB, 0, 0, suspend_event_callback);
+		xlnx_unregister_event(PM_INIT_SUSPEND_CB, 0, 0, suspend_event_callback, NULL);
 
 	if (!rx_chan)
 		mbox_free_channel(rx_chan);
diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h
index 3f87c4929d21..82e8254b0f80 100644
--- a/include/linux/firmware/xlnx-event-manager.h
+++ b/include/linux/firmware/xlnx-event-manager.h
@@ -17,7 +17,7 @@ int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id,
 			event_cb_func_t cb_fun, void *data);
 
 int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id,
-			  const u32 event, event_cb_func_t cb_fun);
+			  const u32 event, event_cb_func_t cb_fun, void *data);
 #else
 static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id,
 				      const u32 event, const bool wake,
@@ -27,7 +27,7 @@ static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32
 }
 
 static inline int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id,
-					 const u32 event, event_cb_func_t cb_fun)
+					const u32 event, event_cb_func_t cb_fun, void *data)
 {
 	return -ENODEV;
 }
-- 
cgit v1.2.3


From 885525c1e7e27ea6207d648a8db20dfbbd9e4238 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Apr 2022 11:56:48 +0200
Subject: clk: renesas: r9a06g032: Export function to set dmamux

The dmamux register is located within the system controller.

Without syscon, we need an extra helper in order to give write access to
this register to a dmamux driver.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stephen Boyd <sboyd@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20220427095653.91804-5-miquel.raynal@bootlin.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/clk/renesas/r9a06g032-clocks.c        | 35 ++++++++++++++++++++++++++-
 include/linux/soc/renesas/r9a06g032-sysctrl.h | 11 +++++++++
 2 files changed, 45 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/soc/renesas/r9a06g032-sysctrl.h

(limited to 'include/linux')

diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c
index c99942f0e4d4..052d99059981 100644
--- a/drivers/clk/renesas/r9a06g032-clocks.c
+++ b/drivers/clk/renesas/r9a06g032-clocks.c
@@ -20,9 +20,12 @@
 #include <linux/pm_clock.h>
 #include <linux/pm_domain.h>
 #include <linux/slab.h>
+#include <linux/soc/renesas/r9a06g032-sysctrl.h>
 #include <linux/spinlock.h>
 #include <dt-bindings/clock/r9a06g032-sysctrl.h>
 
+#define R9A06G032_SYSCTRL_DMAMUX 0xA0
+
 struct r9a06g032_gate {
 	u16 gate, reset, ready, midle,
 		scon, mirack, mistat;
@@ -315,6 +318,30 @@ struct r9a06g032_priv {
 	void __iomem *reg;
 };
 
+static struct r9a06g032_priv *sysctrl_priv;
+
+/* Exported helper to access the DMAMUX register */
+int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val)
+{
+	unsigned long flags;
+	u32 dmamux;
+
+	if (!sysctrl_priv)
+		return -EPROBE_DEFER;
+
+	spin_lock_irqsave(&sysctrl_priv->lock, flags);
+
+	dmamux = readl(sysctrl_priv->reg + R9A06G032_SYSCTRL_DMAMUX);
+	dmamux &= ~mask;
+	dmamux |= val & mask;
+	writel(dmamux, sysctrl_priv->reg + R9A06G032_SYSCTRL_DMAMUX);
+
+	spin_unlock_irqrestore(&sysctrl_priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(r9a06g032_sysctrl_set_dmamux);
+
 /* register/bit pairs are encoded as an uint16_t */
 static void
 clk_rdesc_set(struct r9a06g032_priv *clocks,
@@ -963,7 +990,13 @@ static int __init r9a06g032_clocks_probe(struct platform_device *pdev)
 	if (error)
 		return error;
 
-	return r9a06g032_add_clk_domain(dev);
+	error = r9a06g032_add_clk_domain(dev);
+	if (error)
+		return error;
+
+	sysctrl_priv = clocks;
+
+	return 0;
 }
 
 static const struct of_device_id r9a06g032_match[] = {
diff --git a/include/linux/soc/renesas/r9a06g032-sysctrl.h b/include/linux/soc/renesas/r9a06g032-sysctrl.h
new file mode 100644
index 000000000000..066dfb15cbdd
--- /dev/null
+++ b/include/linux/soc/renesas/r9a06g032-sysctrl.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__
+#define __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__
+
+#ifdef CONFIG_CLK_R9A06G032
+int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val);
+#else
+static inline int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val) { return -ENODEV; }
+#endif
+
+#endif /* __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ */
-- 
cgit v1.2.3


From 13dfd97a341a5cf9d15f415dd469f45e971ef12a Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Thu, 19 May 2022 14:02:32 +0300
Subject: notifier: Add atomic_notifier_call_chain_is_empty()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add atomic_notifier_call_chain_is_empty() that returns true if given
atomic call chain is empty.

The first user of this new notifier API function will be the kernel
power-off core code that will support power-off call chains. The core
code will need to check whether there is a power-off handler registered
at all in order to decide whether to halt machine or power it off.

Reviewed-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/notifier.h |  2 ++
 kernel/notifier.c        | 13 +++++++++++++
 2 files changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 87069b8459af..95e2440037de 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -173,6 +173,8 @@ extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh
 extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
 		unsigned long val_up, unsigned long val_down, void *v);
 
+extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh);
+
 #define NOTIFY_DONE		0x0000		/* Don't care */
 #define NOTIFY_OK		0x0001		/* Suits me */
 #define NOTIFY_STOP_MASK	0x8000		/* Don't call further */
diff --git a/kernel/notifier.c b/kernel/notifier.c
index ba005ebf4730..137b902c985b 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -204,6 +204,19 @@ int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
 EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
 NOKPROBE_SYMBOL(atomic_notifier_call_chain);
 
+/**
+ *	atomic_notifier_call_chain_is_empty - Check whether notifier chain is empty
+ *	@nh: Pointer to head of the atomic notifier chain
+ *
+ *	Checks whether notifier chain is empty.
+ *
+ *	Returns true is notifier chain is empty, false otherwise.
+ */
+bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh)
+{
+	return !rcu_access_pointer(nh->head);
+}
+
 /*
  *	Blocking notifier chain routines.  All access to the chain is
  *	synchronized by an rwsem.
-- 
cgit v1.2.3


From c82f898d873ce10d88f8d60b38c8dd19f1ed7c66 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 10 May 2022 02:32:10 +0300
Subject: notifier: Add blocking/atomic_notifier_chain_register_unique_prio()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add variant of blocking/atomic_notifier_chain_register() functions that
allow registration of a notifier only if it has unique priority, otherwise
-EBUSY error code is returned by the new functions.

Reviewed-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/notifier.h |  5 +++
 kernel/notifier.c        | 88 +++++++++++++++++++++++++++++++++++++-----------
 2 files changed, 74 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 95e2440037de..aef88c2d1173 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -150,6 +150,11 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh,
 extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
 		struct notifier_block *nb);
 
+extern int atomic_notifier_chain_register_unique_prio(
+		struct atomic_notifier_head *nh, struct notifier_block *nb);
+extern int blocking_notifier_chain_register_unique_prio(
+		struct blocking_notifier_head *nh, struct notifier_block *nb);
+
 extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
 		struct notifier_block *nb);
 extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 137b902c985b..0d5bd62c480e 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -20,7 +20,8 @@ BLOCKING_NOTIFIER_HEAD(reboot_notifier_list);
  */
 
 static int notifier_chain_register(struct notifier_block **nl,
-				   struct notifier_block *n)
+				   struct notifier_block *n,
+				   bool unique_priority)
 {
 	while ((*nl) != NULL) {
 		if (unlikely((*nl) == n)) {
@@ -30,6 +31,8 @@ static int notifier_chain_register(struct notifier_block **nl,
 		}
 		if (n->priority > (*nl)->priority)
 			break;
+		if (n->priority == (*nl)->priority && unique_priority)
+			return -EBUSY;
 		nl = &((*nl)->next);
 	}
 	n->next = *nl;
@@ -144,12 +147,35 @@ int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
 	int ret;
 
 	spin_lock_irqsave(&nh->lock, flags);
-	ret = notifier_chain_register(&nh->head, n);
+	ret = notifier_chain_register(&nh->head, n, false);
 	spin_unlock_irqrestore(&nh->lock, flags);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(atomic_notifier_chain_register);
 
+/**
+ *	atomic_notifier_chain_register_unique_prio - Add notifier to an atomic notifier chain
+ *	@nh: Pointer to head of the atomic notifier chain
+ *	@n: New entry in notifier chain
+ *
+ *	Adds a notifier to an atomic notifier chain if there is no other
+ *	notifier registered using the same priority.
+ *
+ *	Returns 0 on success, %-EEXIST or %-EBUSY on error.
+ */
+int atomic_notifier_chain_register_unique_prio(struct atomic_notifier_head *nh,
+					       struct notifier_block *n)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&nh->lock, flags);
+	ret = notifier_chain_register(&nh->head, n, true);
+	spin_unlock_irqrestore(&nh->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(atomic_notifier_chain_register_unique_prio);
+
 /**
  *	atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain
  *	@nh: Pointer to head of the atomic notifier chain
@@ -222,18 +248,9 @@ bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh)
  *	synchronized by an rwsem.
  */
 
-/**
- *	blocking_notifier_chain_register - Add notifier to a blocking notifier chain
- *	@nh: Pointer to head of the blocking notifier chain
- *	@n: New entry in notifier chain
- *
- *	Adds a notifier to a blocking notifier chain.
- *	Must be called in process context.
- *
- *	Returns 0 on success, %-EEXIST on error.
- */
-int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
-		struct notifier_block *n)
+static int __blocking_notifier_chain_register(struct blocking_notifier_head *nh,
+					      struct notifier_block *n,
+					      bool unique_priority)
 {
 	int ret;
 
@@ -243,15 +260,48 @@ int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
 	 * such times we must not call down_write().
 	 */
 	if (unlikely(system_state == SYSTEM_BOOTING))
-		return notifier_chain_register(&nh->head, n);
+		return notifier_chain_register(&nh->head, n, unique_priority);
 
 	down_write(&nh->rwsem);
-	ret = notifier_chain_register(&nh->head, n);
+	ret = notifier_chain_register(&nh->head, n, unique_priority);
 	up_write(&nh->rwsem);
 	return ret;
 }
+
+/**
+ *	blocking_notifier_chain_register - Add notifier to a blocking notifier chain
+ *	@nh: Pointer to head of the blocking notifier chain
+ *	@n: New entry in notifier chain
+ *
+ *	Adds a notifier to a blocking notifier chain.
+ *	Must be called in process context.
+ *
+ *	Returns 0 on success, %-EEXIST on error.
+ */
+int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
+		struct notifier_block *n)
+{
+	return __blocking_notifier_chain_register(nh, n, false);
+}
 EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
 
+/**
+ *	blocking_notifier_chain_register_unique_prio - Add notifier to a blocking notifier chain
+ *	@nh: Pointer to head of the blocking notifier chain
+ *	@n: New entry in notifier chain
+ *
+ *	Adds a notifier to an blocking notifier chain if there is no other
+ *	notifier registered using the same priority.
+ *
+ *	Returns 0 on success, %-EEXIST or %-EBUSY on error.
+ */
+int blocking_notifier_chain_register_unique_prio(struct blocking_notifier_head *nh,
+						 struct notifier_block *n)
+{
+	return __blocking_notifier_chain_register(nh, n, true);
+}
+EXPORT_SYMBOL_GPL(blocking_notifier_chain_register_unique_prio);
+
 /**
  *	blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain
  *	@nh: Pointer to head of the blocking notifier chain
@@ -354,7 +404,7 @@ EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);
 int raw_notifier_chain_register(struct raw_notifier_head *nh,
 		struct notifier_block *n)
 {
-	return notifier_chain_register(&nh->head, n);
+	return notifier_chain_register(&nh->head, n, false);
 }
 EXPORT_SYMBOL_GPL(raw_notifier_chain_register);
 
@@ -433,10 +483,10 @@ int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
 	 * such times we must not call mutex_lock().
 	 */
 	if (unlikely(system_state == SYSTEM_BOOTING))
-		return notifier_chain_register(&nh->head, n);
+		return notifier_chain_register(&nh->head, n, false);
 
 	mutex_lock(&nh->mutex);
-	ret = notifier_chain_register(&nh->head, n);
+	ret = notifier_chain_register(&nh->head, n, false);
 	mutex_unlock(&nh->mutex);
 	return ret;
 }
-- 
cgit v1.2.3


From 232edc2f72f5beda3586360de6254d443820050a Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 10 May 2022 02:32:11 +0300
Subject: kernel/reboot: Introduce sys-off handler API

In order to support power-off chaining we need to get rid of the global
pm_* variables, replacing them with the new kernel API functions that
support chaining.

Introduce new generic sys-off handler API that brings the following
features:

1. Power-off and restart handlers are registered using same API function
   that supports chaining, hence all power-off and restart modes will
   support chaining using this unified function.

2. Prevents notifier priority collisions by disallowing registration of
   multiple handlers at the non-default priority level.

3. Supports passing opaque user argument to callback, which allows us to
   remove global variables from drivers.

This patch adds support of the following sys-off modes:

- SYS_OFF_MODE_POWER_OFF_PREPARE that replaces global pm_power_off_prepare
  variable and provides chaining support for power-off-prepare handlers.

- SYS_OFF_MODE_POWER_OFF that replaces global pm_power_off variable and
  provides chaining support for power-off handlers.

- SYS_OFF_MODE_RESTART that provides a better restart API, removing a need
  from drivers to have a global scratch variable by utilizing the opaque
  callback argument.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/reboot.h |  77 +++++++++++++++++++++
 kernel/reboot.c        | 182 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 259 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index af907a3d68d1..b79f8942ea5f 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -7,6 +7,7 @@
 #include <uapi/linux/reboot.h>
 
 struct device;
+struct sys_off_handler;
 
 #define SYS_DOWN	0x0001	/* Notify of system down */
 #define SYS_RESTART	SYS_DOWN
@@ -62,6 +63,82 @@ extern void machine_shutdown(void);
 struct pt_regs;
 extern void machine_crash_shutdown(struct pt_regs *);
 
+/*
+ * sys-off handler API.
+ */
+
+/*
+ * Standard sys-off priority levels. Users are expected to set priorities
+ * relative to the standard levels.
+ *
+ * SYS_OFF_PRIO_PLATFORM:	Use this for platform-level handlers.
+ *
+ * SYS_OFF_PRIO_LOW:		Use this for handler of last resort.
+ *
+ * SYS_OFF_PRIO_DEFAULT:	Use this for normal handlers.
+ *
+ * SYS_OFF_PRIO_HIGH:		Use this for higher priority handlers.
+ *
+ * SYS_OFF_PRIO_FIRMWARE:	Use this if handler uses firmware call.
+ */
+#define SYS_OFF_PRIO_PLATFORM		-256
+#define SYS_OFF_PRIO_LOW		-128
+#define SYS_OFF_PRIO_DEFAULT		0
+#define SYS_OFF_PRIO_HIGH		192
+#define SYS_OFF_PRIO_FIRMWARE		224
+
+enum sys_off_mode {
+	/**
+	 * @SYS_OFF_MODE_POWER_OFF_PREPARE:
+	 *
+	 * Handlers prepare system to be powered off. Handlers are
+	 * allowed to sleep.
+	 */
+	SYS_OFF_MODE_POWER_OFF_PREPARE,
+
+	/**
+	 * @SYS_OFF_MODE_POWER_OFF:
+	 *
+	 * Handlers power-off system. Handlers are disallowed to sleep.
+	 */
+	SYS_OFF_MODE_POWER_OFF,
+
+	/**
+	 * @SYS_OFF_MODE_RESTART:
+	 *
+	 * Handlers restart system. Handlers are disallowed to sleep.
+	 */
+	SYS_OFF_MODE_RESTART,
+};
+
+/**
+ * struct sys_off_data - sys-off callback argument
+ *
+ * @mode: Mode ID. Currently used only by the sys-off restart mode,
+ *        see enum reboot_mode for the available modes.
+ * @cb_data: User's callback data.
+ * @cmd: Command string. Currently used only by the sys-off restart mode,
+ *       NULL otherwise.
+ */
+struct sys_off_data {
+	int mode;
+	void *cb_data;
+	const char *cmd;
+};
+
+struct sys_off_handler *
+register_sys_off_handler(enum sys_off_mode mode,
+			 int priority,
+			 int (*callback)(struct sys_off_data *data),
+			 void *cb_data);
+void unregister_sys_off_handler(struct sys_off_handler *handler);
+
+int devm_register_sys_off_handler(struct device *dev,
+				  enum sys_off_mode mode,
+				  int priority,
+				  int (*callback)(struct sys_off_data *data),
+				  void *cb_data);
+
 /*
  * Architecture independent implemenations of sys_reboot commands.
  */
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 6bcc5d6a6572..3e6867ee61e0 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -48,6 +48,15 @@ int reboot_cpu;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
+struct sys_off_handler {
+	struct notifier_block nb;
+	int (*sys_off_cb)(struct sys_off_data *data);
+	void *cb_data;
+	enum sys_off_mode mode;
+	bool blocking;
+	void *list;
+};
+
 /*
  * If set, this is used for preparing the system to power off.
  */
@@ -281,6 +290,179 @@ void kernel_halt(void)
 }
 EXPORT_SYMBOL_GPL(kernel_halt);
 
+/*
+ *	Notifier list for kernel code which wants to be called
+ *	to prepare system for power off.
+ */
+static BLOCKING_NOTIFIER_HEAD(power_off_prep_handler_list);
+
+/*
+ *	Notifier list for kernel code which wants to be called
+ *	to power off system.
+ */
+static ATOMIC_NOTIFIER_HEAD(power_off_handler_list);
+
+static int sys_off_notify(struct notifier_block *nb,
+			  unsigned long mode, void *cmd)
+{
+	struct sys_off_handler *handler;
+	struct sys_off_data data = {};
+
+	handler = container_of(nb, struct sys_off_handler, nb);
+	data.cb_data = handler->cb_data;
+	data.mode = mode;
+	data.cmd = cmd;
+
+	return handler->sys_off_cb(&data);
+}
+
+/**
+ *	register_sys_off_handler - Register sys-off handler
+ *	@mode: Sys-off mode
+ *	@priority: Handler priority
+ *	@callback: Callback function
+ *	@cb_data: Callback argument
+ *
+ *	Registers system power-off or restart handler that will be invoked
+ *	at the step corresponding to the given sys-off mode. Handler's callback
+ *	should return NOTIFY_DONE to permit execution of the next handler in
+ *	the call chain or NOTIFY_STOP to break the chain (in error case for
+ *	example).
+ *
+ *	Multiple handlers can be registered at the default priority level.
+ *
+ *	Only one handler can be registered at the non-default priority level,
+ *	otherwise ERR_PTR(-EBUSY) is returned.
+ *
+ *	Returns a new instance of struct sys_off_handler on success, or
+ *	an ERR_PTR()-encoded error code otherwise.
+ */
+struct sys_off_handler *
+register_sys_off_handler(enum sys_off_mode mode,
+			 int priority,
+			 int (*callback)(struct sys_off_data *data),
+			 void *cb_data)
+{
+	struct sys_off_handler *handler;
+	int err;
+
+	handler = kzalloc(sizeof(*handler), GFP_KERNEL);
+	if (!handler)
+		return ERR_PTR(-ENOMEM);
+
+	switch (mode) {
+	case SYS_OFF_MODE_POWER_OFF_PREPARE:
+		handler->list = &power_off_prep_handler_list;
+		handler->blocking = true;
+		break;
+
+	case SYS_OFF_MODE_POWER_OFF:
+		handler->list = &power_off_handler_list;
+		break;
+
+	case SYS_OFF_MODE_RESTART:
+		handler->list = &restart_handler_list;
+		break;
+
+	default:
+		kfree(handler);
+		return ERR_PTR(-EINVAL);
+	}
+
+	handler->nb.notifier_call = sys_off_notify;
+	handler->nb.priority = priority;
+	handler->sys_off_cb = callback;
+	handler->cb_data = cb_data;
+	handler->mode = mode;
+
+	if (handler->blocking) {
+		if (priority == SYS_OFF_PRIO_DEFAULT)
+			err = blocking_notifier_chain_register(handler->list,
+							       &handler->nb);
+		else
+			err = blocking_notifier_chain_register_unique_prio(handler->list,
+									   &handler->nb);
+	} else {
+		if (priority == SYS_OFF_PRIO_DEFAULT)
+			err = atomic_notifier_chain_register(handler->list,
+							     &handler->nb);
+		else
+			err = atomic_notifier_chain_register_unique_prio(handler->list,
+									 &handler->nb);
+	}
+
+	if (err) {
+		kfree(handler);
+		return ERR_PTR(err);
+	}
+
+	return handler;
+}
+EXPORT_SYMBOL_GPL(register_sys_off_handler);
+
+/**
+ *	unregister_sys_off_handler - Unregister sys-off handler
+ *	@handler: Sys-off handler
+ *
+ *	Unregisters given sys-off handler.
+ */
+void unregister_sys_off_handler(struct sys_off_handler *handler)
+{
+	int err;
+
+	if (!handler)
+		return;
+
+	if (handler->blocking)
+		err = blocking_notifier_chain_unregister(handler->list,
+							 &handler->nb);
+	else
+		err = atomic_notifier_chain_unregister(handler->list,
+						       &handler->nb);
+
+	/* sanity check, shall never happen */
+	WARN_ON(err);
+
+	kfree(handler);
+}
+EXPORT_SYMBOL_GPL(unregister_sys_off_handler);
+
+static void devm_unregister_sys_off_handler(void *data)
+{
+	struct sys_off_handler *handler = data;
+
+	unregister_sys_off_handler(handler);
+}
+
+/**
+ *	devm_register_sys_off_handler - Register sys-off handler
+ *	@dev: Device that registers handler
+ *	@mode: Sys-off mode
+ *	@priority: Handler priority
+ *	@callback: Callback function
+ *	@cb_data: Callback argument
+ *
+ *	Registers resource-managed sys-off handler.
+ *
+ *	Returns zero on success, or error code on failure.
+ */
+int devm_register_sys_off_handler(struct device *dev,
+				  enum sys_off_mode mode,
+				  int priority,
+				  int (*callback)(struct sys_off_data *data),
+				  void *cb_data)
+{
+	struct sys_off_handler *handler;
+
+	handler = register_sys_off_handler(mode, priority, callback, cb_data);
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
+
+	return devm_add_action_or_reset(dev, devm_unregister_sys_off_handler,
+					handler);
+}
+EXPORT_SYMBOL_GPL(devm_register_sys_off_handler);
+
 /**
  *	kernel_power_off - power_off the system
  *
-- 
cgit v1.2.3


From 2b6aa7332f8020dfdaffe340ff038aac4df35238 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 10 May 2022 02:32:13 +0300
Subject: kernel/reboot: Add do_kernel_power_off()

Add do_kernel_power_off() helper that will remove open-coded pm_power_off
invocations from the architecture code. This is the first step on the way
to remove the global pm_power_off variable, which will allow us to
implement consistent power-off chaining support.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/reboot.h |  2 ++
 kernel/reboot.c        | 13 +++++++++++++
 2 files changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index b79f8942ea5f..99a9753e77bc 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -63,6 +63,8 @@ extern void machine_shutdown(void);
 struct pt_regs;
 extern void machine_crash_shutdown(struct pt_regs *);
 
+void do_kernel_power_off(void);
+
 /*
  * sys-off handler API.
  */
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 96f681f7b20c..892d25aa12df 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -504,6 +504,19 @@ static void do_kernel_power_off_prepare(void)
 	blocking_notifier_call_chain(&power_off_prep_handler_list, 0, NULL);
 }
 
+/**
+ *	do_kernel_power_off - Execute kernel power-off handler call chain
+ *
+ *	Expected to be called as last step of the power-off sequence.
+ *
+ *	Powers off the system immediately if a power-off handler function has
+ *	been registered. Otherwise does nothing.
+ */
+void do_kernel_power_off(void)
+{
+	atomic_notifier_call_chain(&power_off_handler_list, 0, NULL);
+}
+
 /**
  *	kernel_power_off - power_off the system
  *
-- 
cgit v1.2.3


From 0e2110d2e910e44cc7cf23fce14613e232602602 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 10 May 2022 02:32:15 +0300
Subject: kernel/reboot: Add kernel_can_power_off()

Add kernel_can_power_off() helper that replaces open-coded checks of
the global pm_power_off variable. This is a necessary step towards
supporting chained power-off handlers.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/reboot.h |  1 +
 kernel/reboot.c        | 14 +++++++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 99a9753e77bc..5837c6c2fb40 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -149,6 +149,7 @@ extern void kernel_restart_prepare(char *cmd);
 extern void kernel_restart(char *cmd);
 extern void kernel_halt(void);
 extern void kernel_power_off(void);
+extern bool kernel_can_power_off(void);
 
 extern int C_A_D; /* for sysctl */
 void ctrl_alt_del(void);
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 7723aff4d09b..fb3f49350927 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -523,6 +523,18 @@ void do_kernel_power_off(void)
 	atomic_notifier_call_chain(&power_off_handler_list, 0, NULL);
 }
 
+/**
+ *	kernel_can_power_off - check whether system can be powered off
+ *
+ *	Returns true if power-off handler is registered and system can be
+ *	powered off, false otherwise.
+ */
+bool kernel_can_power_off(void)
+{
+	return !atomic_notifier_call_chain_is_empty(&power_off_handler_list);
+}
+EXPORT_SYMBOL_GPL(kernel_can_power_off);
+
 /**
  *	kernel_power_off - power_off the system
  *
@@ -581,7 +593,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	/* Instead of trying to make the power_off code look like
 	 * halt when pm_power_off is not set do it the easy way.
 	 */
-	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
+	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off())
 		cmd = LINUX_REBOOT_CMD_HALT;
 
 	mutex_lock(&system_transition_mutex);
-- 
cgit v1.2.3


From fb61375ecfba49e153af561402f49f6fe3bebd39 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 10 May 2022 02:32:16 +0300
Subject: kernel/reboot: Add register_platform_power_off()

Add platform-level registration helpers that will ease transition of the
arch/platform power-off callbacks to the new sys-off based API, allowing
us to remove the global pm_power_off variable in the future.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/reboot.h |  3 +++
 kernel/reboot.c        | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 5837c6c2fb40..a8fee1d09c65 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -141,6 +141,9 @@ int devm_register_sys_off_handler(struct device *dev,
 				  int (*callback)(struct sys_off_data *data),
 				  void *cb_data);
 
+int register_platform_power_off(void (*power_off)(void));
+void unregister_platform_power_off(void (*power_off)(void));
+
 /*
  * Architecture independent implemenations of sys_reboot commands.
  */
diff --git a/kernel/reboot.c b/kernel/reboot.c
index fb3f49350927..673d3f54dcad 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -469,6 +469,61 @@ int devm_register_sys_off_handler(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_register_sys_off_handler);
 
+static struct sys_off_handler *platform_power_off_handler;
+
+static int platform_power_off_notify(struct sys_off_data *data)
+{
+	void (*platform_power_power_off_cb)(void) = data->cb_data;
+
+	platform_power_power_off_cb();
+
+	return NOTIFY_DONE;
+}
+
+/**
+ *	register_platform_power_off - Register platform-level power-off callback
+ *	@power_off: Power-off callback
+ *
+ *	Registers power-off callback that will be called as last step
+ *	of the power-off sequence. This callback is expected to be invoked
+ *	for the last resort. Only one platform power-off callback is allowed
+ *	to be registered at a time.
+ *
+ *	Returns zero on success, or error code on failure.
+ */
+int register_platform_power_off(void (*power_off)(void))
+{
+	struct sys_off_handler *handler;
+
+	handler = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+					   SYS_OFF_PRIO_PLATFORM,
+					   platform_power_off_notify,
+					   power_off);
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
+
+	platform_power_off_handler = handler;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_platform_power_off);
+
+/**
+ *	unregister_platform_power_off - Unregister platform-level power-off callback
+ *	@power_off: Power-off callback
+ *
+ *	Unregisters previously registered platform power-off callback.
+ */
+void unregister_platform_power_off(void (*power_off)(void))
+{
+	if (platform_power_off_handler &&
+	    platform_power_off_handler->cb_data == power_off) {
+		unregister_sys_off_handler(platform_power_off_handler);
+		platform_power_off_handler = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(unregister_platform_power_off);
+
 static int legacy_pm_power_off_prepare(struct sys_off_data *data)
 {
 	if (pm_power_off_prepare)
-- 
cgit v1.2.3


From 5b71808eb7c97815fc3b9c386ca0ef6daf2dc053 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 10 May 2022 02:32:32 +0300
Subject: reboot: Remove pm_power_off_prepare()

All pm_power_off_prepare() users were converted to sys-off handler API.
Remove the obsolete global callback variable.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h |  1 -
 kernel/reboot.c    | 19 -------------------
 2 files changed, 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index e65b3ab28377..3786d306dad2 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -21,7 +21,6 @@
  * Callbacks for platform drivers to implement.
  */
 extern void (*pm_power_off)(void);
-extern void (*pm_power_off_prepare)(void);
 
 struct device; /* we have a circular dep with device.h */
 #ifdef CONFIG_VT_CONSOLE_SLEEP
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 673d3f54dcad..88c835167d9e 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -63,13 +63,6 @@ struct sys_off_handler {
  */
 void __weak (*pm_power_off)(void);
 
-/*
- * If set, this is used for preparing the system to power off.
- */
-
-void (*pm_power_off_prepare)(void);
-EXPORT_SYMBOL_GPL(pm_power_off_prepare);
-
 /**
  *	emergency_restart - reboot the system
  *
@@ -524,14 +517,6 @@ void unregister_platform_power_off(void (*power_off)(void))
 }
 EXPORT_SYMBOL_GPL(unregister_platform_power_off);
 
-static int legacy_pm_power_off_prepare(struct sys_off_data *data)
-{
-	if (pm_power_off_prepare)
-		pm_power_off_prepare();
-
-	return NOTIFY_DONE;
-}
-
 static int legacy_pm_power_off(struct sys_off_data *data)
 {
 	if (pm_power_off)
@@ -549,10 +534,6 @@ static int legacy_pm_power_off(struct sys_off_data *data)
  */
 static int __init legacy_pm_init(void)
 {
-	register_sys_off_handler(SYS_OFF_MODE_POWER_OFF_PREPARE,
-				 SYS_OFF_PRIO_DEFAULT,
-				 legacy_pm_power_off_prepare, NULL);
-
 	register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, SYS_OFF_PRIO_DEFAULT,
 				 legacy_pm_power_off, NULL);
 
-- 
cgit v1.2.3


From d2c5415327171e6c1bca2dc4d8a77f450ecf7150 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 10 May 2022 02:32:34 +0300
Subject: kernel/reboot: Add devm_register_power_off_handler()

Add devm_register_power_off_handler() helper that registers sys-off
handler using power-off mode and with a default priority. Most drivers
will want to register power-off handler with a default priority, so this
helper will reduce the boilerplate code and make code easier to read and
follow.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/reboot.h |  4 ++++
 kernel/reboot.c        | 22 ++++++++++++++++++++++
 2 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index a8fee1d09c65..3b063c5b6118 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -141,6 +141,10 @@ int devm_register_sys_off_handler(struct device *dev,
 				  int (*callback)(struct sys_off_data *data),
 				  void *cb_data);
 
+int devm_register_power_off_handler(struct device *dev,
+				    int (*callback)(struct sys_off_data *data),
+				    void *cb_data);
+
 int register_platform_power_off(void (*power_off)(void));
 void unregister_platform_power_off(void (*power_off)(void));
 
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 88c835167d9e..4dbb6e29247a 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -462,6 +462,28 @@ int devm_register_sys_off_handler(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_register_sys_off_handler);
 
+/**
+ *	devm_register_power_off_handler - Register power-off handler
+ *	@dev: Device that registers callback
+ *	@callback: Callback function
+ *	@cb_data: Callback's argument
+ *
+ *	Registers resource-managed sys-off handler with a default priority
+ *	and using power-off mode.
+ *
+ *	Returns zero on success, or error code on failure.
+ */
+int devm_register_power_off_handler(struct device *dev,
+				    int (*callback)(struct sys_off_data *data),
+				    void *cb_data)
+{
+	return devm_register_sys_off_handler(dev,
+					     SYS_OFF_MODE_POWER_OFF,
+					     SYS_OFF_PRIO_DEFAULT,
+					     callback, cb_data);
+}
+EXPORT_SYMBOL_GPL(devm_register_power_off_handler);
+
 static struct sys_off_handler *platform_power_off_handler;
 
 static int platform_power_off_notify(struct sys_off_data *data)
-- 
cgit v1.2.3


From 6779db970bd287bb35b28bd5dc256fd7aef19d1c Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Tue, 10 May 2022 02:32:35 +0300
Subject: kernel/reboot: Add devm_register_restart_handler()

Add devm_register_restart_handler() helper that registers sys-off
handler using restart mode and with a default priority. Most drivers
will want to register restart handler with a default priority, so this
helper will reduce the boilerplate code and make code easier to read and
follow.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/reboot.h |  4 ++++
 kernel/reboot.c        | 22 ++++++++++++++++++++++
 2 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 3b063c5b6118..d29d37a2abb6 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -145,6 +145,10 @@ int devm_register_power_off_handler(struct device *dev,
 				    int (*callback)(struct sys_off_data *data),
 				    void *cb_data);
 
+int devm_register_restart_handler(struct device *dev,
+				  int (*callback)(struct sys_off_data *data),
+				  void *cb_data);
+
 int register_platform_power_off(void (*power_off)(void));
 void unregister_platform_power_off(void (*power_off)(void));
 
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 4dbb6e29247a..bdb635842ec8 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -484,6 +484,28 @@ int devm_register_power_off_handler(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_register_power_off_handler);
 
+/**
+ *	devm_register_restart_handler - Register restart handler
+ *	@dev: Device that registers callback
+ *	@callback: Callback function
+ *	@cb_data: Callback's argument
+ *
+ *	Registers resource-managed sys-off handler with a default priority
+ *	and using restart mode.
+ *
+ *	Returns zero on success, or error code on failure.
+ */
+int devm_register_restart_handler(struct device *dev,
+				  int (*callback)(struct sys_off_data *data),
+				  void *cb_data)
+{
+	return devm_register_sys_off_handler(dev,
+					     SYS_OFF_MODE_RESTART,
+					     SYS_OFF_PRIO_DEFAULT,
+					     callback, cb_data);
+}
+EXPORT_SYMBOL_GPL(devm_register_restart_handler);
+
 static struct sys_off_handler *platform_power_off_handler;
 
 static int platform_power_off_notify(struct sys_off_data *data)
-- 
cgit v1.2.3


From 15f214f9bdb7c1f560b4bf863c5a72ff53b442a4 Mon Sep 17 00:00:00 2001
From: Dietmar Eggemann <dietmar.eggemann@arm.com>
Date: Fri, 13 May 2022 11:34:33 +0200
Subject: topology: Remove unused cpu_cluster_mask()

default_topology[] uses cpu_clustergroup_mask() for the CLS level
(guarded by CONFIG_SCHED_CLUSTER) which is currently provided by x86
(arch/x86/kernel/smpboot.c) and arm64 (drivers/base/arch_topology.c).

Fixes: 778c558f49a2 ("sched: Add cluster scheduler level in core and related Kconfig for ARM64")
Acked-by: Barry Song <baohua@kernel.org>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20220513093433.425163-1-dietmar.eggemann@arm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/topology.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/topology.h b/include/linux/topology.h
index f19bc3626297..4564faafd0e1 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -240,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu)
 }
 #endif
 
-#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask)
-static inline const struct cpumask *cpu_cluster_mask(int cpu)
-{
-	return topology_cluster_cpumask(cpu);
-}
-#endif
-
 static inline const struct cpumask *cpu_cpu_mask(int cpu)
 {
 	return cpumask_of_node(cpu_to_node(cpu));
-- 
cgit v1.2.3


From 0651ab90e4ade17f1d4f4367b70f6120480410f3 Mon Sep 17 00:00:00 2001
From: Pierre Gondois <pierre.gondois@arm.com>
Date: Wed, 18 May 2022 11:08:57 +0200
Subject: ACPI: CPPC: Check _OSC for flexible address space
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ACPI 6.2 Section 6.2.11.2 'Platform-Wide OSPM Capabilities':
  Starting with ACPI Specification 6.2, all _CPC registers can be in
  PCC, System Memory, System IO, or Functional Fixed Hardware address
  spaces. OSPM support for this more flexible register space scheme is
  indicated by the “Flexible Address Space for CPPC Registers” _OSC bit

Otherwise (cf ACPI 6.1, s8.4.7.1.1.X), _CPC registers must be in:
- PCC or Functional Fixed Hardware address space if defined
- SystemMemory address space (NULL register) if not defined

Add the corresponding _OSC bit and check it when parsing _CPC objects.

Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/bus.c       | 18 ++++++++++++++++++
 drivers/acpi/cppc_acpi.c |  9 +++++++++
 include/linux/acpi.h     |  2 ++
 3 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 3e58b613a2c4..9eca43d1d941 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -278,6 +278,20 @@ bool osc_sb_apei_support_acked;
 bool osc_pc_lpi_support_confirmed;
 EXPORT_SYMBOL_GPL(osc_pc_lpi_support_confirmed);
 
+/*
+ * ACPI 6.2 Section 6.2.11.2 'Platform-Wide OSPM Capabilities':
+ *   Starting with ACPI Specification 6.2, all _CPC registers can be in
+ *   PCC, System Memory, System IO, or Functional Fixed Hardware address
+ *   spaces. OSPM support for this more flexible register space scheme is
+ *   indicated by the “Flexible Address Space for CPPC Registers” _OSC bit.
+ *
+ * Otherwise (cf ACPI 6.1, s8.4.7.1.1.X), _CPC registers must be in:
+ * - PCC or Functional Fixed Hardware address space if defined
+ * - SystemMemory address space (NULL register) if not defined
+ */
+bool osc_cpc_flexible_adr_space_confirmed;
+EXPORT_SYMBOL_GPL(osc_cpc_flexible_adr_space_confirmed);
+
 /*
  * ACPI 6.4 Operating System Capabilities for USB.
  */
@@ -321,6 +335,8 @@ static void acpi_bus_osc_negotiate_platform_control(void)
 	}
 #endif
 
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_FLEXIBLE_ADR_SPACE;
+
 	if (IS_ENABLED(CONFIG_SCHED_MC_PRIO))
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_DIVERSE_HIGH_SUPPORT;
 
@@ -366,6 +382,8 @@ static void acpi_bus_osc_negotiate_platform_control(void)
 			capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_PCLPI_SUPPORT;
 		osc_sb_native_usb4_support_confirmed =
 			capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_NATIVE_USB4_SUPPORT;
+		osc_cpc_flexible_adr_space_confirmed =
+			capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_CPC_FLEXIBLE_ADR_SPACE;
 	}
 
 	kfree(context.ret.pointer);
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index bc1454789a06..6f09fe011544 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -736,6 +736,11 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 				if (gas_t->address) {
 					void __iomem *addr;
 
+					if (!osc_cpc_flexible_adr_space_confirmed) {
+						pr_debug("Flexible address space capability not supported\n");
+						goto out_free;
+					}
+
 					addr = ioremap(gas_t->address, gas_t->bit_width/8);
 					if (!addr)
 						goto out_free;
@@ -758,6 +763,10 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 						 gas_t->address);
 					goto out_free;
 				}
+				if (!osc_cpc_flexible_adr_space_confirmed) {
+					pr_debug("Flexible address space capability not supported\n");
+					goto out_free;
+				}
 			} else {
 				if (gas_t->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE || !cpc_ffh_supported()) {
 					/* Support only PCC, SystemMemory, SystemIO, and FFH type regs. */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d7136d13aa44..03465db16b68 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -574,6 +574,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 #define OSC_SB_OSLPI_SUPPORT			0x00000100
 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT		0x00001000
 #define OSC_SB_GENERIC_INITIATOR_SUPPORT	0x00002000
+#define OSC_SB_CPC_FLEXIBLE_ADR_SPACE		0x00004000
 #define OSC_SB_NATIVE_USB4_SUPPORT		0x00040000
 #define OSC_SB_PRM_SUPPORT			0x00200000
 
@@ -581,6 +582,7 @@ extern bool osc_sb_apei_support_acked;
 extern bool osc_pc_lpi_support_confirmed;
 extern bool osc_sb_native_usb4_support_confirmed;
 extern bool osc_sb_cppc_not_supported;
+extern bool osc_cpc_flexible_adr_space_confirmed;
 
 /* USB4 Capabilities */
 #define OSC_USB_USB3_TUNNELING			0x00000001
-- 
cgit v1.2.3


From 66d29d802ef3bf55a49b07568b0048823d4a72a6 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 11 May 2022 16:56:56 +0200
Subject: PM: domains: Allocate gpd_timing_data dynamically based on governor

If a genpd doesn't have an associated governor assigned, there's really no
point to allocate the per device gpd_timing_data, as the data isn't being
used by a governor anyway.

To avoid wasting memory, let's therefore convert the corresponding td
variable in the struct generic_pm_domain_data into a pointer and manage the
allocation of its data dynamically.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c          | 48 +++++++++++++++++++++++++-----------
 drivers/base/power/domain_governor.c |  9 ++++---
 include/linux/pm_domain.h            |  2 +-
 3 files changed, 40 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index a3e727c9a4fa..ca86fb3db901 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -773,13 +773,16 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 	for (;;) {
 		struct generic_pm_domain *genpd;
 		struct pm_domain_data *pdd;
+		struct gpd_timing_data *td;
 
 		spin_lock_irq(&dev->power.lock);
 
 		pdd = dev->power.subsys_data ?
 				dev->power.subsys_data->domain_data : NULL;
 		if (pdd) {
-			to_gpd_data(pdd)->td.constraint_changed = true;
+			td = to_gpd_data(pdd)->td;
+			if (td)
+				td->constraint_changed = true;
 			genpd = dev_to_genpd(dev);
 		} else {
 			genpd = ERR_PTR(-ENODATA);
@@ -875,7 +878,7 @@ static int genpd_runtime_suspend(struct device *dev)
 	struct generic_pm_domain *genpd;
 	bool (*suspend_ok)(struct device *__dev);
 	struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev);
-	struct gpd_timing_data *td = &gpd_data->td;
+	struct gpd_timing_data *td = gpd_data->td;
 	bool runtime_pm = pm_runtime_enabled(dev);
 	ktime_t time_start;
 	s64 elapsed_ns;
@@ -915,7 +918,7 @@ static int genpd_runtime_suspend(struct device *dev)
 	/* Update suspend latency value if the measured time exceeds it. */
 	if (runtime_pm) {
 		elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
-		if (elapsed_ns > td->suspend_latency_ns) {
+		if (td && (elapsed_ns > td->suspend_latency_ns)) {
 			td->suspend_latency_ns = elapsed_ns;
 			dev_dbg(dev, "suspend latency exceeded, %lld ns\n",
 				elapsed_ns);
@@ -951,7 +954,7 @@ static int genpd_runtime_resume(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
 	struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev);
-	struct gpd_timing_data *td = &gpd_data->td;
+	struct gpd_timing_data *td = gpd_data->td;
 	bool runtime_pm = pm_runtime_enabled(dev);
 	ktime_t time_start;
 	s64 elapsed_ns;
@@ -999,7 +1002,7 @@ static int genpd_runtime_resume(struct device *dev)
 	/* Update resume latency value if the measured time exceeds it. */
 	if (timed && runtime_pm) {
 		elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
-		if (elapsed_ns > td->resume_latency_ns) {
+		if (td && (elapsed_ns > td->resume_latency_ns)) {
 			td->resume_latency_ns = elapsed_ns;
 			dev_dbg(dev, "resume latency exceeded, %lld ns\n",
 				elapsed_ns);
@@ -1496,9 +1499,11 @@ EXPORT_SYMBOL_GPL(dev_pm_genpd_resume);
 
 #endif /* CONFIG_PM_SLEEP */
 
-static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev)
+static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
+							   bool has_governor)
 {
 	struct generic_pm_domain_data *gpd_data;
+	struct gpd_timing_data *td;
 	int ret;
 
 	ret = dev_pm_get_subsys_data(dev);
@@ -1512,26 +1517,38 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev)
 	}
 
 	gpd_data->base.dev = dev;
-	gpd_data->td.constraint_changed = true;
-	gpd_data->td.effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
 	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
 	gpd_data->next_wakeup = KTIME_MAX;
 
-	spin_lock_irq(&dev->power.lock);
+	/* Allocate data used by a governor. */
+	if (has_governor) {
+		td = kzalloc(sizeof(*td), GFP_KERNEL);
+		if (!td) {
+			ret = -ENOMEM;
+			goto err_free;
+		}
 
-	if (dev->power.subsys_data->domain_data) {
-		ret = -EINVAL;
-		goto err_free;
+		td->constraint_changed = true;
+		td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
+		gpd_data->td = td;
 	}
 
-	dev->power.subsys_data->domain_data = &gpd_data->base;
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.subsys_data->domain_data)
+		ret = -EINVAL;
+	else
+		dev->power.subsys_data->domain_data = &gpd_data->base;
 
 	spin_unlock_irq(&dev->power.lock);
 
+	if (ret)
+		goto err_free;
+
 	return gpd_data;
 
  err_free:
-	spin_unlock_irq(&dev->power.lock);
+	kfree(gpd_data->td);
 	kfree(gpd_data);
  err_put:
 	dev_pm_put_subsys_data(dev);
@@ -1547,6 +1564,7 @@ static void genpd_free_dev_data(struct device *dev,
 
 	spin_unlock_irq(&dev->power.lock);
 
+	kfree(gpd_data->td);
 	kfree(gpd_data);
 	dev_pm_put_subsys_data(dev);
 }
@@ -1611,7 +1629,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
 		return -EINVAL;
 
-	gpd_data = genpd_alloc_dev_data(dev);
+	gpd_data = genpd_alloc_dev_data(dev, genpd->gov);
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index c13e44823f16..62be9b3f8c90 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -18,6 +18,8 @@ static int dev_update_qos_constraint(struct device *dev, void *data)
 	s64 constraint_ns;
 
 	if (dev->power.subsys_data && dev->power.subsys_data->domain_data) {
+		struct gpd_timing_data *td = dev_gpd_data(dev)->td;
+
 		/*
 		 * Only take suspend-time QoS constraints of devices into
 		 * account, because constraints updated after the device has
@@ -25,7 +27,8 @@ static int dev_update_qos_constraint(struct device *dev, void *data)
 		 * anyway.  In order for them to take effect, the device has to
 		 * be resumed and suspended again.
 		 */
-		constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns;
+		constraint_ns = td ? td->effective_constraint_ns :
+				PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
 	} else {
 		/*
 		 * The child is not in a domain and there's no info on its
@@ -49,7 +52,7 @@ static int dev_update_qos_constraint(struct device *dev, void *data)
  */
 static bool default_suspend_ok(struct device *dev)
 {
-	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
+	struct gpd_timing_data *td = dev_gpd_data(dev)->td;
 	unsigned long flags;
 	s64 constraint_ns;
 
@@ -215,7 +218,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
 		 * domain to turn off and on (that's how much time it will
 		 * have to wait worst case).
 		 */
-		td = &to_gpd_data(pdd)->td;
+		td = to_gpd_data(pdd)->td;
 		constraint_ns = td->effective_constraint_ns;
 		/*
 		 * Zero means "no suspend at all" and this runs only when all
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 043d48e4420a..126a4b9ab215 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -193,7 +193,7 @@ struct pm_domain_data {
 
 struct generic_pm_domain_data {
 	struct pm_domain_data base;
-	struct gpd_timing_data td;
+	struct gpd_timing_data *td;
 	struct notifier_block nb;
 	struct notifier_block *power_nb;
 	int cpu;
-- 
cgit v1.2.3


From 9c74f2ac4801473d03b0e29fab74eb94a9944521 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 11 May 2022 16:56:57 +0200
Subject: PM: domains: Move the next_wakeup variable into the struct
 gpd_timing_data

If the corresponding genpd for the device doesn't use a governor, the
variable next_wakeup within the struct generic_pm_domain_data becomes
superfluous.

To avoid wasting memory, let's move it into the struct gpd_timing_data,
which is already being allocated based upon if there is governor assigned.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c          | 9 +++++----
 drivers/base/power/domain_governor.c | 2 +-
 include/linux/pm_domain.h            | 2 +-
 3 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index ca86fb3db901..4c059a858957 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -478,15 +478,16 @@ EXPORT_SYMBOL_GPL(dev_pm_genpd_set_performance_state);
  */
 void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next)
 {
-	struct generic_pm_domain_data *gpd_data;
 	struct generic_pm_domain *genpd;
+	struct gpd_timing_data *td;
 
 	genpd = dev_to_genpd_safe(dev);
 	if (!genpd)
 		return;
 
-	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-	gpd_data->next_wakeup = next;
+	td = to_gpd_data(dev->power.subsys_data->domain_data)->td;
+	if (td)
+		td->next_wakeup = next;
 }
 EXPORT_SYMBOL_GPL(dev_pm_genpd_set_next_wakeup);
 
@@ -1518,7 +1519,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
 
 	gpd_data->base.dev = dev;
 	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
-	gpd_data->next_wakeup = KTIME_MAX;
 
 	/* Allocate data used by a governor. */
 	if (has_governor) {
@@ -1530,6 +1530,7 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
 
 		td->constraint_changed = true;
 		td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
+		td->next_wakeup = KTIME_MAX;
 		gpd_data->td = td;
 	}
 
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 62be9b3f8c90..599b3909821c 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -139,7 +139,7 @@ static void update_domain_next_wakeup(struct generic_pm_domain *genpd, ktime_t n
 	 * is able to enter its optimal idle state.
 	 */
 	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
-		next_wakeup = to_gpd_data(pdd)->next_wakeup;
+		next_wakeup = to_gpd_data(pdd)->td->next_wakeup;
 		if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now))
 			if (ktime_before(next_wakeup, domain_wakeup))
 				domain_wakeup = next_wakeup;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 126a4b9ab215..1f370f074f30 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -182,6 +182,7 @@ struct gpd_timing_data {
 	s64 suspend_latency_ns;
 	s64 resume_latency_ns;
 	s64 effective_constraint_ns;
+	ktime_t	next_wakeup;
 	bool constraint_changed;
 	bool cached_suspend_ok;
 };
@@ -200,7 +201,6 @@ struct generic_pm_domain_data {
 	unsigned int performance_state;
 	unsigned int default_pstate;
 	unsigned int rpm_pstate;
-	ktime_t	next_wakeup;
 	void *data;
 };
 
-- 
cgit v1.2.3


From f38d1a6d002526a4e8840e9bb19733e9d4ce1a67 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 11 May 2022 16:57:02 +0200
Subject: PM: domains: Allocate governor data dynamically based on a genpd
 governor

If a genpd doesn't have an associated governor assigned, several variables
in the struct generic_pm_domain becomes superfluous.

Rather than wasting memory in allocated genpds, let's move the variables
from the struct generic_pm_domain into a new separate struct. In this way,
we can instead dynamically decide when we need to allocate the
corresponding data for it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c          | 49 ++++++++++++++++++++++++------------
 drivers/base/power/domain_governor.c | 48 ++++++++++++++++++++---------------
 include/linux/pm_domain.h            | 14 +++++++----
 3 files changed, 70 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index ac1eb7d2470b..a7de5fb8f073 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -527,7 +527,8 @@ static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 		goto out;
 
 	genpd->states[state_idx].power_on_latency_ns = elapsed_ns;
-	genpd->max_off_time_changed = true;
+	if (genpd->gd)
+		genpd->gd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "on", elapsed_ns);
 
@@ -576,7 +577,8 @@ static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 		goto out;
 
 	genpd->states[state_idx].power_off_latency_ns = elapsed_ns;
-	genpd->max_off_time_changed = true;
+	if (genpd->gd)
+		genpd->gd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "off", elapsed_ns);
 
@@ -772,7 +774,7 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 	dev = gpd_data->base.dev;
 
 	for (;;) {
-		struct generic_pm_domain *genpd;
+		struct generic_pm_domain *genpd = ERR_PTR(-ENODATA);
 		struct pm_domain_data *pdd;
 		struct gpd_timing_data *td;
 
@@ -782,18 +784,17 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 				dev->power.subsys_data->domain_data : NULL;
 		if (pdd) {
 			td = to_gpd_data(pdd)->td;
-			if (td)
+			if (td) {
 				td->constraint_changed = true;
-			genpd = dev_to_genpd(dev);
-		} else {
-			genpd = ERR_PTR(-ENODATA);
+				genpd = dev_to_genpd(dev);
+			}
 		}
 
 		spin_unlock_irq(&dev->power.lock);
 
 		if (!IS_ERR(genpd)) {
 			genpd_lock(genpd);
-			genpd->max_off_time_changed = true;
+			genpd->gd->max_off_time_changed = true;
 			genpd_unlock(genpd);
 		}
 
@@ -922,7 +923,7 @@ static int genpd_runtime_suspend(struct device *dev)
 			td->suspend_latency_ns = elapsed_ns;
 			dev_dbg(dev, "suspend latency exceeded, %lld ns\n",
 				elapsed_ns);
-			genpd->max_off_time_changed = true;
+			genpd->gd->max_off_time_changed = true;
 			td->constraint_changed = true;
 		}
 	}
@@ -1002,7 +1003,7 @@ static int genpd_runtime_resume(struct device *dev)
 			td->resume_latency_ns = elapsed_ns;
 			dev_dbg(dev, "resume latency exceeded, %lld ns\n",
 				elapsed_ns);
-			genpd->max_off_time_changed = true;
+			genpd->gd->max_off_time_changed = true;
 			td->constraint_changed = true;
 		}
 	}
@@ -1617,6 +1618,7 @@ static int genpd_get_cpu(struct generic_pm_domain *genpd, struct device *dev)
 static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 			    struct device *base_dev)
 {
+	struct genpd_governor_data *gd = genpd->gd;
 	struct generic_pm_domain_data *gpd_data;
 	int ret;
 
@@ -1625,7 +1627,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
 		return -EINVAL;
 
-	gpd_data = genpd_alloc_dev_data(dev, genpd->gov);
+	gpd_data = genpd_alloc_dev_data(dev, gd);
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
@@ -1641,7 +1643,8 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	dev_pm_domain_set(dev, &genpd->domain);
 
 	genpd->device_count++;
-	genpd->max_off_time_changed = true;
+	if (gd)
+		gd->max_off_time_changed = true;
 
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
 
@@ -1695,7 +1698,8 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 	}
 
 	genpd->device_count--;
-	genpd->max_off_time_changed = true;
+	if (genpd->gd)
+		genpd->gd->max_off_time_changed = true;
 
 	genpd_clear_cpumask(genpd, gpd_data->cpu);
 	dev_pm_domain_set(dev, NULL);
@@ -1970,12 +1974,25 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd)
 
 static int genpd_alloc_data(struct generic_pm_domain *genpd)
 {
+	struct genpd_governor_data *gd = NULL;
 	int ret;
 
 	if (genpd_is_cpu_domain(genpd) &&
 	    !zalloc_cpumask_var(&genpd->cpus, GFP_KERNEL))
 		return -ENOMEM;
 
+	if (genpd->gov) {
+		gd = kzalloc(sizeof(*gd), GFP_KERNEL);
+		if (!gd) {
+			ret = -ENOMEM;
+			goto free;
+		}
+
+		gd->max_off_time_ns = -1;
+		gd->max_off_time_changed = true;
+		gd->next_wakeup = KTIME_MAX;
+	}
+
 	/* Use only one "off" state if there were no states declared */
 	if (genpd->state_count == 0) {
 		ret = genpd_set_default_power_state(genpd);
@@ -1983,11 +2000,13 @@ static int genpd_alloc_data(struct generic_pm_domain *genpd)
 			goto free;
 	}
 
+	genpd->gd = gd;
 	return 0;
 
 free:
 	if (genpd_is_cpu_domain(genpd))
 		free_cpumask_var(genpd->cpus);
+	kfree(gd);
 	return ret;
 }
 
@@ -1997,6 +2016,7 @@ static void genpd_free_data(struct generic_pm_domain *genpd)
 		free_cpumask_var(genpd->cpus);
 	if (genpd->free_states)
 		genpd->free_states(genpd->states, genpd->state_count);
+	kfree(genpd->gd);
 }
 
 static void genpd_lock_init(struct generic_pm_domain *genpd)
@@ -2036,9 +2056,6 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	atomic_set(&genpd->sd_count, 0);
 	genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON;
 	genpd->device_count = 0;
-	genpd->max_off_time_ns = -1;
-	genpd->max_off_time_changed = true;
-	genpd->next_wakeup = KTIME_MAX;
 	genpd->provider = NULL;
 	genpd->has_provider = false;
 	genpd->accounting_time = ktime_get_mono_fast_ns();
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 599b3909821c..282a3a135827 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -146,19 +146,21 @@ static void update_domain_next_wakeup(struct generic_pm_domain *genpd, ktime_t n
 	}
 
 	list_for_each_entry(link, &genpd->parent_links, parent_node) {
-		next_wakeup = link->child->next_wakeup;
+		struct genpd_governor_data *cgd = link->child->gd;
+
+		next_wakeup = cgd ? cgd->next_wakeup : KTIME_MAX;
 		if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now))
 			if (ktime_before(next_wakeup, domain_wakeup))
 				domain_wakeup = next_wakeup;
 	}
 
-	genpd->next_wakeup = domain_wakeup;
+	genpd->gd->next_wakeup = domain_wakeup;
 }
 
 static bool next_wakeup_allows_state(struct generic_pm_domain *genpd,
 				     unsigned int state, ktime_t now)
 {
-	ktime_t domain_wakeup = genpd->next_wakeup;
+	ktime_t domain_wakeup = genpd->gd->next_wakeup;
 	s64 idle_time_ns, min_sleep_ns;
 
 	min_sleep_ns = genpd->states[state].power_off_latency_ns +
@@ -188,8 +190,9 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
 	 * All subdomains have been powered off already at this point.
 	 */
 	list_for_each_entry(link, &genpd->parent_links, parent_node) {
-		struct generic_pm_domain *sd = link->child;
-		s64 sd_max_off_ns = sd->max_off_time_ns;
+		struct genpd_governor_data *cgd = link->child->gd;
+
+		s64 sd_max_off_ns = cgd ? cgd->max_off_time_ns : -1;
 
 		if (sd_max_off_ns < 0)
 			continue;
@@ -247,7 +250,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
 	 * time and the time needed to turn the domain on is the maximum
 	 * theoretical time this domain can spend in the "off" state.
 	 */
-	genpd->max_off_time_ns = min_off_time_ns -
+	genpd->gd->max_off_time_ns = min_off_time_ns -
 		genpd->states[state].power_on_latency_ns;
 	return true;
 }
@@ -262,6 +265,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
 static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now)
 {
 	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct genpd_governor_data *gd = genpd->gd;
 	int state_idx = genpd->state_count - 1;
 	struct gpd_link *link;
 
@@ -272,11 +276,11 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now)
 	 * cannot be met.
 	 */
 	update_domain_next_wakeup(genpd, now);
-	if ((genpd->flags & GENPD_FLAG_MIN_RESIDENCY) && (genpd->next_wakeup != KTIME_MAX)) {
+	if ((genpd->flags & GENPD_FLAG_MIN_RESIDENCY) && (gd->next_wakeup != KTIME_MAX)) {
 		/* Let's find out the deepest domain idle state, the devices prefer */
 		while (state_idx >= 0) {
 			if (next_wakeup_allows_state(genpd, state_idx, now)) {
-				genpd->max_off_time_changed = true;
+				gd->max_off_time_changed = true;
 				break;
 			}
 			state_idx--;
@@ -284,14 +288,14 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now)
 
 		if (state_idx < 0) {
 			state_idx = 0;
-			genpd->cached_power_down_ok = false;
+			gd->cached_power_down_ok = false;
 			goto done;
 		}
 	}
 
-	if (!genpd->max_off_time_changed) {
-		genpd->state_idx = genpd->cached_power_down_state_idx;
-		return genpd->cached_power_down_ok;
+	if (!gd->max_off_time_changed) {
+		genpd->state_idx = gd->cached_power_down_state_idx;
+		return gd->cached_power_down_ok;
 	}
 
 	/*
@@ -300,12 +304,16 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now)
 	 * going to be called for any parent until this instance
 	 * returns.
 	 */
-	list_for_each_entry(link, &genpd->child_links, child_node)
-		link->parent->max_off_time_changed = true;
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		struct genpd_governor_data *pgd = link->parent->gd;
+
+		if (pgd)
+			pgd->max_off_time_changed = true;
+	}
 
-	genpd->max_off_time_ns = -1;
-	genpd->max_off_time_changed = false;
-	genpd->cached_power_down_ok = true;
+	gd->max_off_time_ns = -1;
+	gd->max_off_time_changed = false;
+	gd->cached_power_down_ok = true;
 
 	/*
 	 * Find a state to power down to, starting from the state
@@ -313,7 +321,7 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now)
 	 */
 	while (!__default_power_down_ok(pd, state_idx)) {
 		if (state_idx == 0) {
-			genpd->cached_power_down_ok = false;
+			gd->cached_power_down_ok = false;
 			break;
 		}
 		state_idx--;
@@ -321,8 +329,8 @@ static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now)
 
 done:
 	genpd->state_idx = state_idx;
-	genpd->cached_power_down_state_idx = genpd->state_idx;
-	return genpd->cached_power_down_ok;
+	gd->cached_power_down_state_idx = genpd->state_idx;
+	return gd->cached_power_down_ok;
 }
 
 static bool default_power_down_ok(struct dev_pm_domain *pd)
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 1f370f074f30..ebc351698090 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -91,6 +91,14 @@ struct gpd_dev_ops {
 	int (*stop)(struct device *dev);
 };
 
+struct genpd_governor_data {
+	s64 max_off_time_ns;
+	bool max_off_time_changed;
+	ktime_t next_wakeup;
+	bool cached_power_down_ok;
+	bool cached_power_down_state_idx;
+};
+
 struct genpd_power_state {
 	s64 power_off_latency_ns;
 	s64 power_on_latency_ns;
@@ -114,6 +122,7 @@ struct generic_pm_domain {
 	struct list_head child_links;	/* Links with PM domain as a child */
 	struct list_head dev_list;	/* List of devices */
 	struct dev_power_governor *gov;
+	struct genpd_governor_data *gd;	/* Data used by a genpd governor. */
 	struct work_struct power_off_work;
 	struct fwnode_handle *provider;	/* Identity of the domain provider */
 	bool has_provider;
@@ -134,11 +143,6 @@ struct generic_pm_domain {
 	int (*set_performance_state)(struct generic_pm_domain *genpd,
 				     unsigned int state);
 	struct gpd_dev_ops dev_ops;
-	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
-	ktime_t next_wakeup;	/* Maintained by the domain governor */
-	bool max_off_time_changed;
-	bool cached_power_down_ok;
-	bool cached_power_down_state_idx;
 	int (*attach_dev)(struct generic_pm_domain *domain,
 			  struct device *dev);
 	void (*detach_dev)(struct generic_pm_domain *domain,
-- 
cgit v1.2.3


From 4853f68d158ac59b05985a6af5b7da7ccdbc14c8 Mon Sep 17 00:00:00 2001
From: Liao Chang <liaochang1@huawei.com>
Date: Fri, 8 Apr 2022 18:09:09 +0800
Subject: kexec_file: Fix kexec_file.c build error for riscv platform

When CONFIG_KEXEC_FILE is set for riscv platform, the compilation of
kernel/kexec_file.c generate build error:

kernel/kexec_file.c: In function 'crash_prepare_elf64_headers':
./arch/riscv/include/asm/page.h:110:71: error: request for member 'virt_addr' in something not a structure or union
  110 |  ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < kernel_map.virt_addr))
      |                                                                       ^
./arch/riscv/include/asm/page.h:131:2: note: in expansion of macro 'is_linear_mapping'
  131 |  is_linear_mapping(_x) ?       \
      |  ^~~~~~~~~~~~~~~~~
./arch/riscv/include/asm/page.h:140:31: note: in expansion of macro '__va_to_pa_nodebug'
  140 | #define __phys_addr_symbol(x) __va_to_pa_nodebug(x)
      |                               ^~~~~~~~~~~~~~~~~~
./arch/riscv/include/asm/page.h:143:24: note: in expansion of macro '__phys_addr_symbol'
  143 | #define __pa_symbol(x) __phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0))
      |                        ^~~~~~~~~~~~~~~~~~
kernel/kexec_file.c:1327:36: note: in expansion of macro '__pa_symbol'
 1327 |   phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);

This occurs is because the "kernel_map" referenced in macro
is_linear_mapping()  is suppose to be the one of struct kernel_mapping
defined in arch/riscv/mm/init.c, but the 2nd argument of
crash_prepare_elf64_header() has same symbol name, in expansion of macro
is_linear_mapping in function crash_prepare_elf64_header(), "kernel_map"
actually is the local variable.

Signed-off-by: Liao Chang <liaochang1@huawei.com>
Link: https://lore.kernel.org/r/20220408100914.150110-2-lizhengyu3@huawei.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 include/linux/kexec.h | 2 +-
 kernel/kexec_file.c   | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 58d1b58a971e..ebb1bffbf068 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -227,7 +227,7 @@ struct crash_mem {
 extern int crash_exclude_mem_range(struct crash_mem *mem,
 				   unsigned long long mstart,
 				   unsigned long long mend);
-extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
+extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
 				       void **addr, unsigned long *sz);
 #endif /* CONFIG_KEXEC_FILE */
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 8347fc158d2b..331a4f0f10f5 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -1260,7 +1260,7 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 	return 0;
 }
 
-int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
+int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
 			  void **addr, unsigned long *sz)
 {
 	Elf64_Ehdr *ehdr;
@@ -1324,7 +1324,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	phdr++;
 
 	/* Prepare PT_LOAD type program header for kernel text region */
-	if (kernel_map) {
+	if (need_kernel_map) {
 		phdr->p_type = PT_LOAD;
 		phdr->p_flags = PF_R|PF_W|PF_X;
 		phdr->p_vaddr = (unsigned long) _text;
-- 
cgit v1.2.3


From 6c1e423a3c84953edcf91ff03ab97829b287184a Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Wed, 18 May 2022 17:45:27 +0200
Subject: can: can-dev: remove obsolete CAN LED support

Since commit 30f3b42147ba6f ("can: mark led trigger as broken") the
CAN specific LED support was disabled and marked as BROKEN. As the
common LED support with CONFIG_LEDS_TRIGGER_NETDEV should do this work
now the code can be removed as preparation for a CAN netdevice Kconfig
rework.

Link: https://lore.kernel.org/all/20220518154527.29046-1-socketcan@hartkopp.net
Suggested-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
[mkl: remove led.h from MAINTAINERS]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 MAINTAINERS                              |   1 -
 drivers/net/can/Kconfig                  |  17 ----
 drivers/net/can/at91_can.c               |  10 ---
 drivers/net/can/c_can/c_can_main.c       |  16 +---
 drivers/net/can/ctucanfd/ctucanfd_base.c |  10 ---
 drivers/net/can/dev/Makefile             |   2 -
 drivers/net/can/dev/dev.c                |   5 --
 drivers/net/can/dev/rx-offload.c         |   2 -
 drivers/net/can/flexcan/flexcan-core.c   |   7 --
 drivers/net/can/ifi_canfd/ifi_canfd.c    |   9 --
 drivers/net/can/led.c                    | 140 -------------------------------
 drivers/net/can/m_can/m_can.c            |  11 ---
 drivers/net/can/m_can/m_can.h            |   1 -
 drivers/net/can/rcar/rcar_can.c          |   8 --
 drivers/net/can/rcar/rcar_canfd.c        |   7 --
 drivers/net/can/sja1000/sja1000.c        |  11 ---
 drivers/net/can/spi/hi311x.c             |   8 --
 drivers/net/can/spi/mcp251x.c            |  10 ---
 drivers/net/can/sun4i_can.c              |   7 --
 drivers/net/can/ti_hecc.c                |   8 --
 drivers/net/can/usb/mcba_usb.c           |   8 --
 drivers/net/can/usb/usb_8dev.c           |  11 ---
 drivers/net/can/xilinx_can.c             |  10 +--
 include/linux/can/dev.h                  |  10 ---
 include/linux/can/led.h                  |  51 -----------
 25 files changed, 2 insertions(+), 378 deletions(-)
 delete mode 100644 drivers/net/can/led.c
 delete mode 100644 include/linux/can/led.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 3a29bf2452f4..234380c959c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4376,7 +4376,6 @@ F:	drivers/net/can/
 F:	drivers/phy/phy-can-transceiver.c
 F:	include/linux/can/bittiming.h
 F:	include/linux/can/dev.h
-F:	include/linux/can/led.h
 F:	include/linux/can/length.h
 F:	include/linux/can/platform/
 F:	include/linux/can/rx-offload.h
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index ac760fd39282..b2dcc1e5a388 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -71,23 +71,6 @@ config CAN_CALC_BITTIMING
 	  arguments "tq", "prop_seg", "phase_seg1", "phase_seg2" and "sjw".
 	  If unsure, say Y.
 
-config CAN_LEDS
-	bool "Enable LED triggers for Netlink based drivers"
-	depends on LEDS_CLASS
-	# The netdev trigger (LEDS_TRIGGER_NETDEV) should be able to do
-	# everything that this driver is doing. This is marked as broken
-	# because it uses stuff that is intended to be changed or removed.
-	# Please consider switching to the netdev trigger and confirm it
-	# fulfills your needs instead of fixing this driver.
-	depends on BROKEN
-	select LEDS_TRIGGERS
-	help
-	  This option adds two LED triggers for packet receive and transmit
-	  events on each supported CAN device.
-
-	  Say Y here if you are working on a system with led-class supported
-	  LEDs and you want to use them as canbus activity indicators.
-
 config CAN_AT91
 	tristate "Atmel AT91 onchip CAN controller"
 	depends on (ARCH_AT91 || COMPILE_TEST) && HAS_IOMEM
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 953aef8d3978..29ed0d3cd171 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -23,7 +23,6 @@
 
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 
 #define AT91_MB_MASK(i)		((1 << (i)) - 1)
 
@@ -618,8 +617,6 @@ static void at91_read_msg(struct net_device *dev, unsigned int mb)
 		stats->rx_bytes += cf->len;
 
 	netif_receive_skb(skb);
-
-	can_led_event(dev, CAN_LED_EVENT_RX);
 }
 
 /**
@@ -854,7 +851,6 @@ static void at91_irq_tx(struct net_device *dev, u32 reg_sr)
 						 mb - get_mb_tx_first(priv),
 						 NULL);
 			dev->stats.tx_packets++;
-			can_led_event(dev, CAN_LED_EVENT_TX);
 		}
 	}
 
@@ -1101,8 +1097,6 @@ static int at91_open(struct net_device *dev)
 		goto out_close;
 	}
 
-	can_led_event(dev, CAN_LED_EVENT_OPEN);
-
 	/* start chip and queuing */
 	at91_chip_start(dev);
 	napi_enable(&priv->napi);
@@ -1133,8 +1127,6 @@ static int at91_close(struct net_device *dev)
 
 	close_candev(dev);
 
-	can_led_event(dev, CAN_LED_EVENT_STOP);
-
 	return 0;
 }
 
@@ -1331,8 +1323,6 @@ static int at91_can_probe(struct platform_device *pdev)
 		goto exit_free;
 	}
 
-	devm_can_led_init(dev);
-
 	dev_info(&pdev->dev, "device registered (reg_base=%p, irq=%d)\n",
 		 priv->reg_base, dev->irq);
 
diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c
index 2034dbe30958..a7362af0babb 100644
--- a/drivers/net/can/c_can/c_can_main.c
+++ b/drivers/net/can/c_can/c_can_main.c
@@ -40,7 +40,6 @@
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 
 #include "c_can.h"
 
@@ -759,7 +758,6 @@ static void c_can_do_tx(struct net_device *dev)
 
 	stats->tx_bytes += bytes;
 	stats->tx_packets += pkts;
-	can_led_event(dev, CAN_LED_EVENT_TX);
 
 	tail = c_can_get_tx_tail(tx_ring);
 
@@ -906,9 +904,6 @@ static int c_can_do_rx_poll(struct net_device *dev, int quota)
 		quota -= n;
 	}
 
-	if (pkts)
-		can_led_event(dev, CAN_LED_EVENT_RX);
-
 	return pkts;
 }
 
@@ -1182,8 +1177,6 @@ static int c_can_open(struct net_device *dev)
 	if (err)
 		goto exit_start_fail;
 
-	can_led_event(dev, CAN_LED_EVENT_OPEN);
-
 	napi_enable(&priv->napi);
 	/* enable status change, error and module interrupts */
 	c_can_irq_control(priv, true);
@@ -1214,8 +1207,6 @@ static int c_can_close(struct net_device *dev)
 	c_can_reset_ram(priv, false);
 	c_can_pm_runtime_put_sync(priv);
 
-	can_led_event(dev, CAN_LED_EVENT_STOP);
-
 	return 0;
 }
 
@@ -1365,8 +1356,6 @@ static const struct net_device_ops c_can_netdev_ops = {
 
 int register_c_can_dev(struct net_device *dev)
 {
-	int err;
-
 	/* Deactivate pins to prevent DRA7 DCAN IP from being
 	 * stuck in transition when module is disabled.
 	 * Pins are activated in c_can_start() and deactivated
@@ -1378,10 +1367,7 @@ int register_c_can_dev(struct net_device *dev)
 	dev->netdev_ops = &c_can_netdev_ops;
 	c_can_set_ethtool_ops(dev);
 
-	err = register_candev(dev);
-	if (!err)
-		devm_can_led_init(dev);
-	return err;
+	return register_candev(dev);
 }
 EXPORT_SYMBOL_GPL(register_c_can_dev);
 
diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c
index 2ada097d1ede..64990bf20fdc 100644
--- a/drivers/net/can/ctucanfd/ctucanfd_base.c
+++ b/drivers/net/can/ctucanfd/ctucanfd_base.c
@@ -29,7 +29,6 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 #include <linux/pm_runtime.h>
 
 #include "ctucanfd.h"
@@ -957,9 +956,6 @@ static int ctucan_rx_poll(struct napi_struct *napi, int quota)
 		ctucan_write32(priv, CTUCANFD_COMMAND, REG_COMMAND_CDO);
 	}
 
-	if (work_done)
-		can_led_event(ndev, CAN_LED_EVENT_RX);
-
 	if (!framecnt && res != 0) {
 		if (napi_complete_done(napi, work_done)) {
 			/* Clear and enable RBNEI. It is level-triggered, so
@@ -1079,8 +1075,6 @@ clear:
 		}
 	} while (some_buffers_processed);
 
-	can_led_event(ndev, CAN_LED_EVENT_TX);
-
 	spin_lock_irqsave(&priv->tx_lock, flags);
 
 	/* Check if at least one TX buffer is free */
@@ -1236,7 +1230,6 @@ static int ctucan_open(struct net_device *ndev)
 	}
 
 	netdev_info(ndev, "ctu_can_fd device registered\n");
-	can_led_event(ndev, CAN_LED_EVENT_OPEN);
 	napi_enable(&priv->napi);
 	netif_start_queue(ndev);
 
@@ -1269,7 +1262,6 @@ static int ctucan_close(struct net_device *ndev)
 	free_irq(ndev->irq, ndev);
 	close_candev(ndev);
 
-	can_led_event(ndev, CAN_LED_EVENT_STOP);
 	pm_runtime_put(priv->dev);
 
 	return 0;
@@ -1434,8 +1426,6 @@ int ctucan_probe_common(struct device *dev, void __iomem *addr, int irq, unsigne
 		goto err_deviceoff;
 	}
 
-	devm_can_led_init(ndev);
-
 	pm_runtime_put(dev);
 
 	netdev_dbg(ndev, "mem_base=0x%p irq=%d clock=%d, no. of txt buffers:%d\n",
diff --git a/drivers/net/can/dev/Makefile b/drivers/net/can/dev/Makefile
index 3e2e207861fc..af2901db473c 100644
--- a/drivers/net/can/dev/Makefile
+++ b/drivers/net/can/dev/Makefile
@@ -7,5 +7,3 @@ can-dev-y			+= length.o
 can-dev-y			+= netlink.o
 can-dev-y			+= rx-offload.o
 can-dev-y                       += skb.o
-
-can-dev-$(CONFIG_CAN_LEDS)	+= led.o
diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c
index e7ab45f1c43b..96c9d9db00cf 100644
--- a/drivers/net/can/dev/dev.c
+++ b/drivers/net/can/dev/dev.c
@@ -14,7 +14,6 @@
 #include <linux/can/can-ml.h>
 #include <linux/can/dev.h>
 #include <linux/can/skb.h>
-#include <linux/can/led.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of.h>
 
@@ -512,8 +511,6 @@ static __init int can_dev_init(void)
 {
 	int err;
 
-	can_led_notifier_init();
-
 	err = can_netlink_register();
 	if (!err)
 		pr_info(MOD_DESC "\n");
@@ -525,8 +522,6 @@ module_init(can_dev_init);
 static __exit void can_dev_exit(void)
 {
 	can_netlink_unregister();
-
-	can_led_notifier_exit();
 }
 module_exit(can_dev_exit);
 
diff --git a/drivers/net/can/dev/rx-offload.c b/drivers/net/can/dev/rx-offload.c
index 509d21170c8c..a32a01c172d4 100644
--- a/drivers/net/can/dev/rx-offload.c
+++ b/drivers/net/can/dev/rx-offload.c
@@ -70,8 +70,6 @@ static int can_rx_offload_napi_poll(struct napi_struct *napi, int quota)
 			napi_reschedule(&offload->napi);
 	}
 
-	can_led_event(offload->dev, CAN_LED_EVENT_RX);
-
 	return work_done;
 }
 
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index fe9bda0f5ec4..d060088047f1 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -14,7 +14,6 @@
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/firmware/imx/sci.h>
@@ -1081,7 +1080,6 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 			can_rx_offload_get_echo_skb(&priv->offload, 0,
 						    reg_ctrl << 16, NULL);
 		stats->tx_packets++;
-		can_led_event(dev, CAN_LED_EVENT_TX);
 
 		/* after sending a RTR frame MB is in RX mode */
 		priv->write(FLEXCAN_MB_CODE_TX_INACTIVE,
@@ -1738,8 +1736,6 @@ static int flexcan_open(struct net_device *dev)
 
 	flexcan_chip_interrupts_enable(dev);
 
-	can_led_event(dev, CAN_LED_EVENT_OPEN);
-
 	netif_start_queue(dev);
 
 	return 0;
@@ -1785,8 +1781,6 @@ static int flexcan_close(struct net_device *dev)
 
 	pm_runtime_put(priv->dev);
 
-	can_led_event(dev, CAN_LED_EVENT_STOP);
-
 	return 0;
 }
 
@@ -2189,7 +2183,6 @@ static int flexcan_probe(struct platform_device *pdev)
 	}
 
 	of_can_transceiver(dev);
-	devm_can_led_init(dev);
 
 	return 0;
 
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index b0a3473f211d..968ed6d7316b 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -345,9 +345,6 @@ static int ifi_canfd_do_rx_poll(struct net_device *ndev, int quota)
 		rxst = readl(priv->base + IFI_CANFD_RXSTCMD);
 	}
 
-	if (pkts)
-		can_led_event(ndev, CAN_LED_EVENT_RX);
-
 	return pkts;
 }
 
@@ -626,7 +623,6 @@ static irqreturn_t ifi_canfd_isr(int irq, void *dev_id)
 	if (isr & IFI_CANFD_INTERRUPT_TXFIFO_REMOVE) {
 		stats->tx_bytes += can_get_echo_skb(ndev, 0, NULL);
 		stats->tx_packets++;
-		can_led_event(ndev, CAN_LED_EVENT_TX);
 	}
 
 	if (isr & tx_irq_mask)
@@ -830,7 +826,6 @@ static int ifi_canfd_open(struct net_device *ndev)
 
 	ifi_canfd_start(ndev);
 
-	can_led_event(ndev, CAN_LED_EVENT_OPEN);
 	napi_enable(&priv->napi);
 	netif_start_queue(ndev);
 
@@ -853,8 +848,6 @@ static int ifi_canfd_close(struct net_device *ndev)
 
 	close_candev(ndev);
 
-	can_led_event(ndev, CAN_LED_EVENT_STOP);
-
 	return 0;
 }
 
@@ -1004,8 +997,6 @@ static int ifi_canfd_plat_probe(struct platform_device *pdev)
 		goto err_reg;
 	}
 
-	devm_can_led_init(ndev);
-
 	dev_info(dev, "Driver registered: regs=%p, irq=%d, clock=%d\n",
 		 priv->base, ndev->irq, priv->can.clock.freq);
 
diff --git a/drivers/net/can/led.c b/drivers/net/can/led.c
deleted file mode 100644
index db14897f8e16..000000000000
--- a/drivers/net/can/led.c
+++ /dev/null
@@ -1,140 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright 2012, Fabio Baltieri <fabio.baltieri@gmail.com>
- * Copyright 2012, Kurt Van Dijck <kurt.van.dijck@eia.be>
- */
-
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/netdevice.h>
-#include <linux/can/dev.h>
-
-#include <linux/can/led.h>
-
-static unsigned long led_delay = 50;
-module_param(led_delay, ulong, 0644);
-MODULE_PARM_DESC(led_delay,
-		"blink delay time for activity leds (msecs, default: 50).");
-
-/* Trigger a LED event in response to a CAN device event */
-void can_led_event(struct net_device *netdev, enum can_led_event event)
-{
-	struct can_priv *priv = netdev_priv(netdev);
-
-	switch (event) {
-	case CAN_LED_EVENT_OPEN:
-		led_trigger_event(priv->tx_led_trig, LED_FULL);
-		led_trigger_event(priv->rx_led_trig, LED_FULL);
-		led_trigger_event(priv->rxtx_led_trig, LED_FULL);
-		break;
-	case CAN_LED_EVENT_STOP:
-		led_trigger_event(priv->tx_led_trig, LED_OFF);
-		led_trigger_event(priv->rx_led_trig, LED_OFF);
-		led_trigger_event(priv->rxtx_led_trig, LED_OFF);
-		break;
-	case CAN_LED_EVENT_TX:
-		if (led_delay) {
-			led_trigger_blink_oneshot(priv->tx_led_trig,
-						  &led_delay, &led_delay, 1);
-			led_trigger_blink_oneshot(priv->rxtx_led_trig,
-						  &led_delay, &led_delay, 1);
-		}
-		break;
-	case CAN_LED_EVENT_RX:
-		if (led_delay) {
-			led_trigger_blink_oneshot(priv->rx_led_trig,
-						  &led_delay, &led_delay, 1);
-			led_trigger_blink_oneshot(priv->rxtx_led_trig,
-						  &led_delay, &led_delay, 1);
-		}
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(can_led_event);
-
-static void can_led_release(struct device *gendev, void *res)
-{
-	struct can_priv *priv = netdev_priv(to_net_dev(gendev));
-
-	led_trigger_unregister_simple(priv->tx_led_trig);
-	led_trigger_unregister_simple(priv->rx_led_trig);
-	led_trigger_unregister_simple(priv->rxtx_led_trig);
-}
-
-/* Register CAN LED triggers for a CAN device
- *
- * This is normally called from a driver's probe function
- */
-void devm_can_led_init(struct net_device *netdev)
-{
-	struct can_priv *priv = netdev_priv(netdev);
-	void *res;
-
-	res = devres_alloc(can_led_release, 0, GFP_KERNEL);
-	if (!res) {
-		netdev_err(netdev, "cannot register LED triggers\n");
-		return;
-	}
-
-	snprintf(priv->tx_led_trig_name, sizeof(priv->tx_led_trig_name),
-		 "%s-tx", netdev->name);
-	snprintf(priv->rx_led_trig_name, sizeof(priv->rx_led_trig_name),
-		 "%s-rx", netdev->name);
-	snprintf(priv->rxtx_led_trig_name, sizeof(priv->rxtx_led_trig_name),
-		 "%s-rxtx", netdev->name);
-
-	led_trigger_register_simple(priv->tx_led_trig_name,
-				    &priv->tx_led_trig);
-	led_trigger_register_simple(priv->rx_led_trig_name,
-				    &priv->rx_led_trig);
-	led_trigger_register_simple(priv->rxtx_led_trig_name,
-				    &priv->rxtx_led_trig);
-
-	devres_add(&netdev->dev, res);
-}
-EXPORT_SYMBOL_GPL(devm_can_led_init);
-
-/* NETDEV rename notifier to rename the associated led triggers too */
-static int can_led_notifier(struct notifier_block *nb, unsigned long msg,
-			    void *ptr)
-{
-	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
-	struct can_priv *priv = safe_candev_priv(netdev);
-	char name[CAN_LED_NAME_SZ];
-
-	if (!priv)
-		return NOTIFY_DONE;
-
-	if (!priv->tx_led_trig || !priv->rx_led_trig || !priv->rxtx_led_trig)
-		return NOTIFY_DONE;
-
-	if (msg == NETDEV_CHANGENAME) {
-		snprintf(name, sizeof(name), "%s-tx", netdev->name);
-		led_trigger_rename_static(name, priv->tx_led_trig);
-
-		snprintf(name, sizeof(name), "%s-rx", netdev->name);
-		led_trigger_rename_static(name, priv->rx_led_trig);
-
-		snprintf(name, sizeof(name), "%s-rxtx", netdev->name);
-		led_trigger_rename_static(name, priv->rxtx_led_trig);
-	}
-
-	return NOTIFY_DONE;
-}
-
-/* notifier block for netdevice event */
-static struct notifier_block can_netdev_notifier __read_mostly = {
-	.notifier_call = can_led_notifier,
-};
-
-int __init can_led_notifier_init(void)
-{
-	return register_netdevice_notifier(&can_netdev_notifier);
-}
-
-void __exit can_led_notifier_exit(void)
-{
-	unregister_netdevice_notifier(&can_netdev_notifier);
-}
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 7582908e1192..5d0c82d8b9a9 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -565,9 +565,6 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota)
 		rxfs = m_can_read(cdev, M_CAN_RXF0S);
 	}
 
-	if (pkts)
-		can_led_event(dev, CAN_LED_EVENT_RX);
-
 	return pkts;
 }
 
@@ -1087,8 +1084,6 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 			if (cdev->is_peripheral)
 				timestamp = m_can_get_timestamp(cdev);
 			m_can_tx_update_stats(cdev, 0, timestamp);
-
-			can_led_event(dev, CAN_LED_EVENT_TX);
 			netif_wake_queue(dev);
 		}
 	} else  {
@@ -1097,7 +1092,6 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 			if (m_can_echo_tx_event(dev) != 0)
 				goto out_fail;
 
-			can_led_event(dev, CAN_LED_EVENT_TX);
 			if (netif_queue_stopped(dev) &&
 			    !m_can_tx_fifo_full(cdev))
 				netif_wake_queue(dev);
@@ -1562,7 +1556,6 @@ static int m_can_close(struct net_device *dev)
 		can_rx_offload_disable(&cdev->offload);
 
 	close_candev(dev);
-	can_led_event(dev, CAN_LED_EVENT_STOP);
 
 	phy_power_off(cdev->transceiver);
 
@@ -1806,8 +1799,6 @@ static int m_can_open(struct net_device *dev)
 	/* start the m_can controller */
 	m_can_start(dev);
 
-	can_led_event(dev, CAN_LED_EVENT_OPEN);
-
 	if (!cdev->is_peripheral)
 		napi_enable(&cdev->napi);
 
@@ -1995,8 +1986,6 @@ int m_can_class_register(struct m_can_classdev *cdev)
 		goto rx_offload_del;
 	}
 
-	devm_can_led_init(cdev->net);
-
 	of_can_transceiver(cdev->net);
 
 	dev_info(cdev->dev, "%s device registered (irq=%d, version=%d)\n",
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index d18b515e6ccc..4c0267f9f297 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -7,7 +7,6 @@
 #define _CAN_M_CAN_H_
 
 #include <linux/can/core.h>
-#include <linux/can/led.h>
 #include <linux/can/rx-offload.h>
 #include <linux/completion.h>
 #include <linux/device.h>
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 103f1a92eee2..d45762f1cf6b 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -12,7 +12,6 @@
 #include <linux/errno.h>
 #include <linux/netdevice.h>
 #include <linux/platform_device.h>
-#include <linux/can/led.h>
 #include <linux/can/dev.h>
 #include <linux/clk.h>
 #include <linux/of.h>
@@ -389,7 +388,6 @@ static void rcar_can_tx_done(struct net_device *ndev)
 	/* Clear interrupt */
 	isr = readb(&priv->regs->isr);
 	writeb(isr & ~RCAR_CAN_ISR_TXFF, &priv->regs->isr);
-	can_led_event(ndev, CAN_LED_EVENT_TX);
 }
 
 static irqreturn_t rcar_can_interrupt(int irq, void *dev_id)
@@ -531,7 +529,6 @@ static int rcar_can_open(struct net_device *ndev)
 			   ndev->irq, err);
 		goto out_close;
 	}
-	can_led_event(ndev, CAN_LED_EVENT_OPEN);
 	rcar_can_start(ndev);
 	netif_start_queue(ndev);
 	return 0;
@@ -581,7 +578,6 @@ static int rcar_can_close(struct net_device *ndev)
 	clk_disable_unprepare(priv->can_clk);
 	clk_disable_unprepare(priv->clk);
 	close_candev(ndev);
-	can_led_event(ndev, CAN_LED_EVENT_STOP);
 	return 0;
 }
 
@@ -666,8 +662,6 @@ static void rcar_can_rx_pkt(struct rcar_can_priv *priv)
 	}
 	stats->rx_packets++;
 
-	can_led_event(priv->ndev, CAN_LED_EVENT_RX);
-
 	netif_receive_skb(skb);
 }
 
@@ -812,8 +806,6 @@ static int rcar_can_probe(struct platform_device *pdev)
 		goto fail_candev;
 	}
 
-	devm_can_led_init(ndev);
-
 	dev_info(&pdev->dev, "device registered (IRQ%d)\n", ndev->irq);
 
 	return 0;
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index f75ebaa35519..40a11445d021 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -29,7 +29,6 @@
 #include <linux/errno.h>
 #include <linux/netdevice.h>
 #include <linux/platform_device.h>
-#include <linux/can/led.h>
 #include <linux/can/dev.h>
 #include <linux/clk.h>
 #include <linux/of.h>
@@ -1128,7 +1127,6 @@ static void rcar_canfd_tx_done(struct net_device *ndev)
 	/* Clear interrupt */
 	rcar_canfd_write(priv->base, RCANFD_CFSTS(gpriv, ch, RCANFD_CFFIFO_IDX),
 			 sts & ~RCANFD_CFSTS_CFTXIF);
-	can_led_event(ndev, CAN_LED_EVENT_TX);
 }
 
 static void rcar_canfd_handle_global_err(struct rcar_canfd_global *gpriv, u32 ch)
@@ -1419,7 +1417,6 @@ static int rcar_canfd_open(struct net_device *ndev)
 	if (err)
 		goto out_close;
 	netif_start_queue(ndev);
-	can_led_event(ndev, CAN_LED_EVENT_OPEN);
 	return 0;
 out_close:
 	napi_disable(&priv->napi);
@@ -1469,7 +1466,6 @@ static int rcar_canfd_close(struct net_device *ndev)
 	napi_disable(&priv->napi);
 	clk_disable_unprepare(gpriv->can_clk);
 	close_candev(ndev);
-	can_led_event(ndev, CAN_LED_EVENT_STOP);
 	return 0;
 }
 
@@ -1619,8 +1615,6 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 	 */
 	rcar_canfd_write(priv->base, RCANFD_RFPCTR(gpriv, ridx), 0xff);
 
-	can_led_event(priv->ndev, CAN_LED_EVENT_RX);
-
 	if (!(cf->can_id & CAN_RTR_FLAG))
 		stats->rx_bytes += cf->len;
 	stats->rx_packets++;
@@ -1792,7 +1786,6 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 	netif_napi_add_weight(ndev, &priv->napi, rcar_canfd_rx_poll,
 			      RCANFD_NAPI_WEIGHT);
 	spin_lock_init(&priv->tx_lock);
-	devm_can_led_init(ndev);
 	gpriv->ch[priv->channel] = priv;
 	err = register_candev(ndev);
 	if (err) {
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 966316479485..2e7638f98cf1 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -60,7 +60,6 @@
 
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 
 #include "sja1000.h"
 
@@ -383,8 +382,6 @@ static void sja1000_rx(struct net_device *dev)
 	sja1000_write_cmdreg(priv, CMD_RRB);
 
 	netif_rx(skb);
-
-	can_led_event(dev, CAN_LED_EVENT_RX);
 }
 
 static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status)
@@ -531,7 +528,6 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id)
 				stats->tx_packets++;
 			}
 			netif_wake_queue(dev);
-			can_led_event(dev, CAN_LED_EVENT_TX);
 		}
 		if (isrc & IRQ_RI) {
 			/* receive interrupt */
@@ -587,8 +583,6 @@ static int sja1000_open(struct net_device *dev)
 	/* init and start chi */
 	sja1000_start(dev);
 
-	can_led_event(dev, CAN_LED_EVENT_OPEN);
-
 	netif_start_queue(dev);
 
 	return 0;
@@ -606,8 +600,6 @@ static int sja1000_close(struct net_device *dev)
 
 	close_candev(dev);
 
-	can_led_event(dev, CAN_LED_EVENT_STOP);
-
 	return 0;
 }
 
@@ -673,9 +665,6 @@ int register_sja1000dev(struct net_device *dev)
 
 	ret =  register_candev(dev);
 
-	if (!ret)
-		devm_can_led_init(dev);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(register_sja1000dev);
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index a5b2952b8d0f..ebc4ebb44c98 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -16,7 +16,6 @@
 
 #include <linux/can/core.h>
 #include <linux/can/dev.h>
-#include <linux/can/led.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
@@ -354,8 +353,6 @@ static void hi3110_hw_rx(struct spi_device *spi)
 	}
 	priv->net->stats.rx_packets++;
 
-	can_led_event(priv->net, CAN_LED_EVENT_RX);
-
 	netif_rx(skb);
 }
 
@@ -567,8 +564,6 @@ static int hi3110_stop(struct net_device *net)
 
 	mutex_unlock(&priv->hi3110_lock);
 
-	can_led_event(net, CAN_LED_EVENT_STOP);
-
 	return 0;
 }
 
@@ -725,7 +720,6 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
 		if (priv->tx_busy && statf & HI3110_STAT_TXMTY) {
 			net->stats.tx_packets++;
 			net->stats.tx_bytes += can_get_echo_skb(net, 0, NULL);
-			can_led_event(net, CAN_LED_EVENT_TX);
 			priv->tx_busy = false;
 			netif_wake_queue(net);
 		}
@@ -783,7 +777,6 @@ static int hi3110_open(struct net_device *net)
 	if (ret)
 		goto out_free_wq;
 
-	can_led_event(net, CAN_LED_EVENT_OPEN);
 	netif_wake_queue(net);
 	mutex_unlock(&priv->hi3110_lock);
 
@@ -931,7 +924,6 @@ static int hi3110_can_probe(struct spi_device *spi)
 	if (ret)
 		goto error_probe;
 
-	devm_can_led_init(net);
 	netdev_info(net, "%x successfully initialized.\n", priv->model);
 
 	return 0;
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index fc747bff5eeb..666a4505a55a 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -22,7 +22,6 @@
 #include <linux/bitfield.h>
 #include <linux/can/core.h>
 #include <linux/can/dev.h>
-#include <linux/can/led.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
@@ -738,8 +737,6 @@ static void mcp251x_hw_rx(struct spi_device *spi, int buf_idx)
 	}
 	priv->net->stats.rx_packets++;
 
-	can_led_event(priv->net, CAN_LED_EVENT_RX);
-
 	netif_rx(skb);
 }
 
@@ -973,8 +970,6 @@ static int mcp251x_stop(struct net_device *net)
 
 	mutex_unlock(&priv->mcp_lock);
 
-	can_led_event(net, CAN_LED_EVENT_STOP);
-
 	return 0;
 }
 
@@ -1177,7 +1172,6 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id)
 			break;
 
 		if (intf & CANINTF_TX) {
-			can_led_event(net, CAN_LED_EVENT_TX);
 			if (priv->tx_busy) {
 				net->stats.tx_packets++;
 				net->stats.tx_bytes += can_get_echo_skb(net, 0,
@@ -1232,8 +1226,6 @@ static int mcp251x_open(struct net_device *net)
 	if (ret)
 		goto out_free_irq;
 
-	can_led_event(net, CAN_LED_EVENT_OPEN);
-
 	netif_wake_queue(net);
 	mutex_unlock(&priv->mcp_lock);
 
@@ -1403,8 +1395,6 @@ static int mcp251x_can_probe(struct spi_device *spi)
 	if (ret)
 		goto error_probe;
 
-	devm_can_led_init(net);
-
 	ret = mcp251x_gpio_setup(priv);
 	if (ret)
 		goto error_probe;
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 25d6d81ab4f4..155b90f6c767 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -51,7 +51,6 @@
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
@@ -516,8 +515,6 @@ static void sun4i_can_rx(struct net_device *dev)
 	sun4i_can_write_cmdreg(priv, SUN4I_CMD_RELEASE_RBUF);
 
 	netif_rx(skb);
-
-	can_led_event(dev, CAN_LED_EVENT_RX);
 }
 
 static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status)
@@ -664,7 +661,6 @@ static irqreturn_t sun4i_can_interrupt(int irq, void *dev_id)
 			stats->tx_bytes += can_get_echo_skb(dev, 0, NULL);
 			stats->tx_packets++;
 			netif_wake_queue(dev);
-			can_led_event(dev, CAN_LED_EVENT_TX);
 		}
 		if ((isrc & SUN4I_INT_RBUF_VLD) &&
 		    !(isrc & SUN4I_INT_DATA_OR)) {
@@ -729,7 +725,6 @@ static int sun4ican_open(struct net_device *dev)
 		goto exit_can_start;
 	}
 
-	can_led_event(dev, CAN_LED_EVENT_OPEN);
 	netif_start_queue(dev);
 
 	return 0;
@@ -756,7 +751,6 @@ static int sun4ican_close(struct net_device *dev)
 
 	free_irq(dev->irq, dev);
 	close_candev(dev);
-	can_led_event(dev, CAN_LED_EVENT_STOP);
 
 	return 0;
 }
@@ -883,7 +877,6 @@ static int sun4ican_probe(struct platform_device *pdev)
 			DRV_NAME, err);
 		goto exit_free;
 	}
-	devm_can_led_init(dev);
 
 	dev_info(&pdev->dev, "device registered (base=%p, irq=%d)\n",
 		 priv->base, dev->irq);
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index bb3f2e3b004c..debe17bfd0f0 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -34,7 +34,6 @@
 
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 #include <linux/can/rx-offload.h>
 
 #define DRV_NAME "ti_hecc"
@@ -759,7 +758,6 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 				can_rx_offload_get_echo_skb(&priv->offload,
 							    mbxno, stamp, NULL);
 			stats->tx_packets++;
-			can_led_event(ndev, CAN_LED_EVENT_TX);
 			--priv->tx_tail;
 		}
 
@@ -814,8 +812,6 @@ static int ti_hecc_open(struct net_device *ndev)
 		return err;
 	}
 
-	can_led_event(ndev, CAN_LED_EVENT_OPEN);
-
 	ti_hecc_start(ndev);
 	can_rx_offload_enable(&priv->offload);
 	netif_start_queue(ndev);
@@ -834,8 +830,6 @@ static int ti_hecc_close(struct net_device *ndev)
 	close_candev(ndev);
 	ti_hecc_transceiver_switch(priv, 0);
 
-	can_led_event(ndev, CAN_LED_EVENT_STOP);
-
 	return 0;
 }
 
@@ -954,8 +948,6 @@ static int ti_hecc_probe(struct platform_device *pdev)
 		goto probe_exit_offload;
 	}
 
-	devm_can_led_init(ndev);
-
 	dev_info(&pdev->dev, "device registered (reg_base=%p, irq=%u)\n",
 		 priv->base, (u32)ndev->irq);
 
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index c45a814e1de2..792ab9da317d 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -10,7 +10,6 @@
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/signal.h>
@@ -232,8 +231,6 @@ static void mcba_usb_write_bulk_callback(struct urb *urb)
 		netdev->stats.tx_packets++;
 		netdev->stats.tx_bytes += can_get_echo_skb(netdev, ctx->ndx,
 							   NULL);
-
-		can_led_event(netdev, CAN_LED_EVENT_TX);
 	}
 
 	if (urb->status)
@@ -452,7 +449,6 @@ static void mcba_usb_process_can(struct mcba_priv *priv,
 	}
 	stats->rx_packets++;
 
-	can_led_event(priv->netdev, CAN_LED_EVENT_RX);
 	netif_rx(skb);
 }
 
@@ -700,7 +696,6 @@ static int mcba_usb_open(struct net_device *netdev)
 	priv->can_speed_check = true;
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
-	can_led_event(netdev, CAN_LED_EVENT_OPEN);
 	netif_start_queue(netdev);
 
 	return 0;
@@ -732,7 +727,6 @@ static int mcba_usb_close(struct net_device *netdev)
 	mcba_urb_unlink(priv);
 
 	close_candev(netdev);
-	can_led_event(netdev, CAN_LED_EVENT_STOP);
 
 	return 0;
 }
@@ -857,8 +851,6 @@ static int mcba_usb_probe(struct usb_interface *intf,
 	priv->rx_pipe = usb_rcvbulkpipe(priv->udev, in->bEndpointAddress);
 	priv->tx_pipe = usb_sndbulkpipe(priv->udev, out->bEndpointAddress);
 
-	devm_can_led_init(netdev);
-
 	/* Start USB dev only if we have successfully registered CAN device */
 	err = mcba_usb_start(priv);
 	if (err) {
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index b638604bf1ee..f3363575bf32 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -21,7 +21,6 @@
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 
 /* driver constants */
 #define MAX_RX_URBS			20
@@ -480,8 +479,6 @@ static void usb_8dev_rx_can_msg(struct usb_8dev_priv *priv,
 		stats->rx_packets++;
 
 		netif_rx(skb);
-
-		can_led_event(priv->netdev, CAN_LED_EVENT_RX);
 	} else {
 		netdev_warn(priv->netdev, "frame type %d unknown",
 			 msg->type);
@@ -582,8 +579,6 @@ static void usb_8dev_write_bulk_callback(struct urb *urb)
 	netdev->stats.tx_packets++;
 	netdev->stats.tx_bytes += can_get_echo_skb(netdev, context->echo_index, NULL);
 
-	can_led_event(netdev, CAN_LED_EVENT_TX);
-
 	/* Release context */
 	context->echo_index = MAX_TX_URBS;
 
@@ -807,8 +802,6 @@ static int usb_8dev_open(struct net_device *netdev)
 	if (err)
 		return err;
 
-	can_led_event(netdev, CAN_LED_EVENT_OPEN);
-
 	/* finally start device */
 	err = usb_8dev_start(priv);
 	if (err) {
@@ -865,8 +858,6 @@ static int usb_8dev_close(struct net_device *netdev)
 
 	close_candev(netdev);
 
-	can_led_event(netdev, CAN_LED_EVENT_STOP);
-
 	return err;
 }
 
@@ -974,8 +965,6 @@ static int usb_8dev_probe(struct usb_interface *intf,
 			 (version>>8) & 0xff, version & 0xff);
 	}
 
-	devm_can_led_init(netdev);
-
 	return 0;
 
 cleanup_unregister_candev:
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 7f730b471e9f..8a3b7b103ca4 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -26,7 +26,6 @@
 #include <linux/types.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 #include <linux/pm_runtime.h>
 
 #define DRIVER_NAME	"xilinx_can"
@@ -1209,10 +1208,8 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 					XCAN_IXR_RXNEMP_MASK);
 	}
 
-	if (work_done) {
-		can_led_event(ndev, CAN_LED_EVENT_RX);
+	if (work_done)
 		xcan_update_error_state_after_rxtx(ndev);
-	}
 
 	if (work_done < quota) {
 		if (napi_complete_done(napi, work_done)) {
@@ -1298,7 +1295,6 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr)
 
 	spin_unlock_irqrestore(&priv->tx_lock, flags);
 
-	can_led_event(ndev, CAN_LED_EVENT_TX);
 	xcan_update_error_state_after_rxtx(ndev);
 }
 
@@ -1420,7 +1416,6 @@ static int xcan_open(struct net_device *ndev)
 		goto err_candev;
 	}
 
-	can_led_event(ndev, CAN_LED_EVENT_OPEN);
 	napi_enable(&priv->napi);
 	netif_start_queue(ndev);
 
@@ -1452,7 +1447,6 @@ static int xcan_close(struct net_device *ndev)
 	free_irq(ndev->irq, ndev);
 	close_candev(ndev);
 
-	can_led_event(ndev, CAN_LED_EVENT_STOP);
 	pm_runtime_put(priv->dev);
 
 	return 0;
@@ -1812,8 +1806,6 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err_disableclks;
 	}
 
-	devm_can_led_init(ndev);
-
 	pm_runtime_put(&pdev->dev);
 
 	if (priv->devtype.flags & XCAN_FLAG_CANFD_2) {
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index c2ea47f30046..e22dc03c850e 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -17,7 +17,6 @@
 #include <linux/can.h>
 #include <linux/can/bittiming.h>
 #include <linux/can/error.h>
-#include <linux/can/led.h>
 #include <linux/can/length.h>
 #include <linux/can/netlink.h>
 #include <linux/can/skb.h>
@@ -85,15 +84,6 @@ struct can_priv {
 	int (*do_get_berr_counter)(const struct net_device *dev,
 				   struct can_berr_counter *bec);
 	int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv);
-
-#ifdef CONFIG_CAN_LEDS
-	struct led_trigger *tx_led_trig;
-	char tx_led_trig_name[CAN_LED_NAME_SZ];
-	struct led_trigger *rx_led_trig;
-	char rx_led_trig_name[CAN_LED_NAME_SZ];
-	struct led_trigger *rxtx_led_trig;
-	char rxtx_led_trig_name[CAN_LED_NAME_SZ];
-#endif
 };
 
 static inline bool can_tdc_is_enabled(const struct can_priv *priv)
diff --git a/include/linux/can/led.h b/include/linux/can/led.h
deleted file mode 100644
index 7c3cfd798c56..000000000000
--- a/include/linux/can/led.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright 2012, Fabio Baltieri <fabio.baltieri@gmail.com>
- */
-
-#ifndef _CAN_LED_H
-#define _CAN_LED_H
-
-#include <linux/if.h>
-#include <linux/leds.h>
-#include <linux/netdevice.h>
-
-enum can_led_event {
-	CAN_LED_EVENT_OPEN,
-	CAN_LED_EVENT_STOP,
-	CAN_LED_EVENT_TX,
-	CAN_LED_EVENT_RX,
-};
-
-#ifdef CONFIG_CAN_LEDS
-
-/* keep space for interface name + "-tx"/"-rx"/"-rxtx"
- * suffix and null terminator
- */
-#define CAN_LED_NAME_SZ (IFNAMSIZ + 6)
-
-void can_led_event(struct net_device *netdev, enum can_led_event event);
-void devm_can_led_init(struct net_device *netdev);
-int __init can_led_notifier_init(void);
-void __exit can_led_notifier_exit(void);
-
-#else
-
-static inline void can_led_event(struct net_device *netdev,
-				 enum can_led_event event)
-{
-}
-static inline void devm_can_led_init(struct net_device *netdev)
-{
-}
-static inline int can_led_notifier_init(void)
-{
-	return 0;
-}
-static inline void can_led_notifier_exit(void)
-{
-}
-
-#endif
-
-#endif /* !_CAN_LED_H */
-- 
cgit v1.2.3


From b265cdebdfefbee4ef1ae2972af36f7a7cac5148 Mon Sep 17 00:00:00 2001
From: Yang Shi <shy828301@gmail.com>
Date: Thu, 19 May 2022 14:08:48 -0700
Subject: sched: coredump.h: clarify the use of MMF_VM_HUGEPAGE

Patch series "Make khugepaged collapse readonly FS THP more consistent", v4.

The readonly FS THP relies on khugepaged to collapse THP for suitable
vmas.  But the behavior is inconsistent for "always" mode
(https://lore.kernel.org/linux-mm/00f195d4-d039-3cf2-d3a1-a2c88de397a0@suse.cz/).

The "always" mode means THP allocation should be tried all the time and
khugepaged should try to collapse THP all the time.  Of course the
allocation and collapse may fail due to other factors and conditions.

Currently file THP may not be collapsed by khugepaged even though all the
conditions are met.  That does break the semantics of "always" mode.

So make sure readonly FS vmas are registered to khugepaged to fix the
break.

Register suitable vmas in common mmap path, that could cover both readonly
FS vmas and shmem vmas, so remove the khugepaged calls in shmem.c.

The patch 1-7 are minor bug fixes, clean up and preparation patches.
Patch 8 is the real meat.

Tested with khugepaged test in selftests and the testcase provided by
Vlastimil Babka in
https://lore.kernel.org/lkml/df3b5d1c-a36b-2c73-3e27-99e74983de3a@suse.cz/
by commenting out MADV_HUGEPAGE call.


This patch (of 8):

MMF_VM_HUGEPAGE is set as long as the mm is available for khugepaged by
khugepaged_enter(), not only when VM_HUGEPAGE is set on vma.  Correct the
comment to avoid confusion.

Link: https://lkml.kernel.org/r/20220510203222.24246-1-shy828301@gmail.com
Link: https://lkml.kernel.org/r/20220510203222.24246-2-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Vlastmil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/sched/coredump.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 4d9e3a656875..4d0a5be28b70 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -57,7 +57,8 @@ static inline int get_dumpable(struct mm_struct *mm)
 #endif
 					/* leave room for more dump flags */
 #define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
-#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
+#define MMF_VM_HUGEPAGE		17	/* set when mm is available for
+					   khugepaged */
 /*
  * This one-shot flag is dropped due to necessity of changing exe once again
  * on NFS restore
-- 
cgit v1.2.3


From 78d12c19e02d8151b1c82228ae6bb10f174a68e2 Mon Sep 17 00:00:00 2001
From: Yang Shi <shy828301@gmail.com>
Date: Thu, 19 May 2022 14:08:49 -0700
Subject: mm: thp: only regular file could be THP eligible

Since commit a4aeaa06d45e ("mm: khugepaged: skip huge page collapse for
special files"), khugepaged just collapses THP for regular file which is
the intended usecase for readonly fs THP.  Only show regular file as THP
eligible accordingly.

And make file_thp_enabled() available for khugepaged too in order to
remove duplicate code.

Link: https://lkml.kernel.org/r/20220510203222.24246-5-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Vlastmil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/huge_mm.h | 14 ++++++++++++++
 mm/huge_memory.c        | 11 ++---------
 mm/khugepaged.c         |  9 ++-------
 3 files changed, 18 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fbf36bb1be22..de29821231c9 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -173,6 +173,20 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
 	return false;
 }
 
+static inline bool file_thp_enabled(struct vm_area_struct *vma)
+{
+	struct inode *inode;
+
+	if (!vma->vm_file)
+		return false;
+
+	inode = vma->vm_file->f_inode;
+
+	return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) &&
+	       (vma->vm_flags & VM_EXEC) &&
+	       !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
+}
+
 bool transparent_hugepage_active(struct vm_area_struct *vma);
 
 #define transparent_hugepage_use_zero_page()				\
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c37c870c526f..1a00bdf0f1e8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -69,13 +69,6 @@ static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
 unsigned long huge_zero_pfn __read_mostly = ~0UL;
 
-static inline bool file_thp_enabled(struct vm_area_struct *vma)
-{
-	return transhuge_vma_enabled(vma, vma->vm_flags) && vma->vm_file &&
-	       !inode_is_open_for_write(vma->vm_file->f_inode) &&
-	       (vma->vm_flags & VM_EXEC);
-}
-
 bool transparent_hugepage_active(struct vm_area_struct *vma)
 {
 	/* The addr is used to check if the vma size fits */
@@ -87,8 +80,8 @@ bool transparent_hugepage_active(struct vm_area_struct *vma)
 		return __transparent_hugepage_enabled(vma);
 	if (vma_is_shmem(vma))
 		return shmem_huge_enabled(vma);
-	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS))
-		return file_thp_enabled(vma);
+	if (transhuge_vma_enabled(vma, vma->vm_flags) && file_thp_enabled(vma))
+		return true;
 
 	return false;
 }
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 647efd46b369..1f4822dcc970 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -464,13 +464,8 @@ static bool hugepage_vma_check(struct vm_area_struct *vma,
 		return false;
 
 	/* Only regular file is valid */
-	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file &&
-	    (vm_flags & VM_EXEC)) {
-		struct inode *inode = vma->vm_file->f_inode;
-
-		return !inode_is_open_for_write(inode) &&
-			S_ISREG(inode->i_mode);
-	}
+	if (file_thp_enabled(vma))
+		return true;
 
 	if (!vma->anon_vma || !vma_is_anonymous(vma))
 		return false;
-- 
cgit v1.2.3


From d2081b2bf8195b8239c67fdd61518e077da7cbec Mon Sep 17 00:00:00 2001
From: Yang Shi <shy828301@gmail.com>
Date: Thu, 19 May 2022 14:08:49 -0700
Subject: mm: khugepaged: make khugepaged_enter() void function

The most callers of khugepaged_enter() don't care about the return value.
Only dup_mmap(), anonymous THP page fault and MADV_HUGEPAGE handle the
error by returning -ENOMEM.  Actually it is not harmful for them to ignore
the error case either.  It also sounds overkilling to fail fork() and page
fault early due to khugepaged_enter() error, and MADV_HUGEPAGE does set
VM_HUGEPAGE flag regardless of the error.

Link: https://lkml.kernel.org/r/20220510203222.24246-6-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Vlastmil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/khugepaged.h | 30 ++++++++++++------------------
 kernel/fork.c              |  4 +---
 mm/huge_memory.c           |  4 ++--
 mm/khugepaged.c            | 18 +++++++-----------
 4 files changed, 22 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 2fcc01891b47..0423d3619f26 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -12,10 +12,10 @@ extern struct attribute_group khugepaged_attr_group;
 extern int khugepaged_init(void);
 extern void khugepaged_destroy(void);
 extern int start_stop_khugepaged(void);
-extern int __khugepaged_enter(struct mm_struct *mm);
+extern void __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
-extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
-				      unsigned long vm_flags);
+extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+				       unsigned long vm_flags);
 extern void khugepaged_min_free_kbytes_update(void);
 #ifdef CONFIG_SHMEM
 extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr);
@@ -40,11 +40,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
 	(transparent_hugepage_flags &				\
 	 (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG))
 
-static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
 	if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags))
-		return __khugepaged_enter(mm);
-	return 0;
+		__khugepaged_enter(mm);
 }
 
 static inline void khugepaged_exit(struct mm_struct *mm)
@@ -53,7 +52,7 @@ static inline void khugepaged_exit(struct mm_struct *mm)
 		__khugepaged_exit(mm);
 }
 
-static inline int khugepaged_enter(struct vm_area_struct *vma,
+static inline void khugepaged_enter(struct vm_area_struct *vma,
 				   unsigned long vm_flags)
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags))
@@ -62,27 +61,22 @@ static inline int khugepaged_enter(struct vm_area_struct *vma,
 		     (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) &&
 		    !(vm_flags & VM_NOHUGEPAGE) &&
 		    !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
-			if (__khugepaged_enter(vma->vm_mm))
-				return -ENOMEM;
-	return 0;
+			__khugepaged_enter(vma->vm_mm);
 }
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
-static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	return 0;
 }
 static inline void khugepaged_exit(struct mm_struct *mm)
 {
 }
-static inline int khugepaged_enter(struct vm_area_struct *vma,
-				   unsigned long vm_flags)
+static inline void khugepaged_enter(struct vm_area_struct *vma,
+				    unsigned long vm_flags)
 {
-	return 0;
 }
-static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
-					     unsigned long vm_flags)
+static inline void khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+					      unsigned long vm_flags)
 {
-	return 0;
 }
 static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
 					   unsigned long addr)
diff --git a/kernel/fork.c b/kernel/fork.c
index 9796897560ab..0d13baf86650 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -612,9 +612,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	retval = ksm_fork(mm, oldmm);
 	if (retval)
 		goto out;
-	retval = khugepaged_fork(mm, oldmm);
-	if (retval)
-		goto out;
+	khugepaged_fork(mm, oldmm);
 
 	prev = NULL;
 	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1a00bdf0f1e8..efd06af61fca 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -726,8 +726,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 		return VM_FAULT_FALLBACK;
 	if (unlikely(anon_vma_prepare(vma)))
 		return VM_FAULT_OOM;
-	if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
-		return VM_FAULT_OOM;
+	khugepaged_enter(vma, vma->vm_flags);
+
 	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
 			!mm_forbids_zeropage(vma->vm_mm) &&
 			transparent_hugepage_use_zero_page()) {
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 1f4822dcc970..b43b294ca5f8 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -365,8 +365,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 * register it here without waiting a page fault that
 		 * may not happen any time soon.
 		 */
-		if (khugepaged_enter_vma_merge(vma, *vm_flags))
-			return -ENOMEM;
+		khugepaged_enter_vma_merge(vma, *vm_flags);
 		break;
 	case MADV_NOHUGEPAGE:
 		*vm_flags &= ~VM_HUGEPAGE;
@@ -475,20 +474,20 @@ static bool hugepage_vma_check(struct vm_area_struct *vma,
 	return true;
 }
 
-int __khugepaged_enter(struct mm_struct *mm)
+void __khugepaged_enter(struct mm_struct *mm)
 {
 	struct mm_slot *mm_slot;
 	int wakeup;
 
 	mm_slot = alloc_mm_slot();
 	if (!mm_slot)
-		return -ENOMEM;
+		return;
 
 	/* __khugepaged_exit() must not run from under us */
 	VM_BUG_ON_MM(khugepaged_test_exit(mm), mm);
 	if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
 		free_mm_slot(mm_slot);
-		return 0;
+		return;
 	}
 
 	spin_lock(&khugepaged_mm_lock);
@@ -504,11 +503,9 @@ int __khugepaged_enter(struct mm_struct *mm)
 	mmgrab(mm);
 	if (wakeup)
 		wake_up_interruptible(&khugepaged_wait);
-
-	return 0;
 }
 
-int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+void khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 			       unsigned long vm_flags)
 {
 	unsigned long hstart, hend;
@@ -519,13 +516,12 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 	 * file-private shmem THP is not supported.
 	 */
 	if (!hugepage_vma_check(vma, vm_flags))
-		return 0;
+		return;
 
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
-		return khugepaged_enter(vma, vm_flags);
-	return 0;
+		khugepaged_enter(vma, vm_flags);
 }
 
 void __khugepaged_exit(struct mm_struct *mm)
-- 
cgit v1.2.3


From 2647d11b9e71d495b2d4985ebaf7a734373a4b80 Mon Sep 17 00:00:00 2001
From: Yang Shi <shy828301@gmail.com>
Date: Thu, 19 May 2022 14:08:49 -0700
Subject: mm: khugepaged: make hugepage_vma_check() non-static

The hugepage_vma_check() could be reused by khugepaged_enter() and
khugepaged_enter_vma_merge(), but it is static in khugepaged.c.  Make it
non-static and declare it in khugepaged.h.

Link: https://lkml.kernel.org/r/20220510203222.24246-7-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Song Liu <song@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/khugepaged.h | 14 ++++++--------
 mm/khugepaged.c            | 25 +++++++++----------------
 2 files changed, 15 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 0423d3619f26..c340f6bb39d6 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -3,8 +3,6 @@
 #define _LINUX_KHUGEPAGED_H
 
 #include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */
-#include <linux/shmem_fs.h>
-
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern struct attribute_group khugepaged_attr_group;
@@ -12,6 +10,8 @@ extern struct attribute_group khugepaged_attr_group;
 extern int khugepaged_init(void);
 extern void khugepaged_destroy(void);
 extern int start_stop_khugepaged(void);
+extern bool hugepage_vma_check(struct vm_area_struct *vma,
+			       unsigned long vm_flags);
 extern void __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
 extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma,
@@ -55,13 +55,11 @@ static inline void khugepaged_exit(struct mm_struct *mm)
 static inline void khugepaged_enter(struct vm_area_struct *vma,
 				   unsigned long vm_flags)
 {
-	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags))
-		if ((khugepaged_always() ||
-		     (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) ||
-		     (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) &&
-		    !(vm_flags & VM_NOHUGEPAGE) &&
-		    !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
+	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
+	    khugepaged_enabled()) {
+		if (hugepage_vma_check(vma, vm_flags))
 			__khugepaged_enter(vma->vm_mm);
+	}
 }
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b43b294ca5f8..9ef626e2c750 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -437,8 +437,8 @@ static inline int khugepaged_test_exit(struct mm_struct *mm)
 	return atomic_read(&mm->mm_users) == 0;
 }
 
-static bool hugepage_vma_check(struct vm_area_struct *vma,
-			       unsigned long vm_flags)
+bool hugepage_vma_check(struct vm_area_struct *vma,
+			unsigned long vm_flags)
 {
 	if (!transhuge_vma_enabled(vma, vm_flags))
 		return false;
@@ -508,20 +508,13 @@ void __khugepaged_enter(struct mm_struct *mm)
 void khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 			       unsigned long vm_flags)
 {
-	unsigned long hstart, hend;
-
-	/*
-	 * khugepaged only supports read-only files for non-shmem files.
-	 * khugepaged does not yet work on special mappings. And
-	 * file-private shmem THP is not supported.
-	 */
-	if (!hugepage_vma_check(vma, vm_flags))
-		return;
-
-	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
-	hend = vma->vm_end & HPAGE_PMD_MASK;
-	if (hstart < hend)
-		khugepaged_enter(vma, vm_flags);
+	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
+	    khugepaged_enabled() &&
+	    (((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) <
+	     (vma->vm_end & HPAGE_PMD_MASK))) {
+		if (hugepage_vma_check(vma, vm_flags))
+			__khugepaged_enter(vma->vm_mm);
+	}
 }
 
 void __khugepaged_exit(struct mm_struct *mm)
-- 
cgit v1.2.3


From c791576c60288c89b351ea2d2098f6a872d78fa7 Mon Sep 17 00:00:00 2001
From: Yang Shi <shy828301@gmail.com>
Date: Thu, 19 May 2022 14:08:50 -0700
Subject: mm: khugepaged: introduce khugepaged_enter_vma() helper

The khugepaged_enter_vma_merge() actually does as the same thing as the
khugepaged_enter() section called by shmem_mmap(), so consolidate them
into one helper and rename it to khugepaged_enter_vma().

Link: https://lkml.kernel.org/r/20220510203222.24246-8-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Acked-by: Vlastmil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Song Liu <song@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/khugepaged.h |  8 ++++----
 mm/khugepaged.c            |  6 +++---
 mm/mmap.c                  |  8 ++++----
 mm/shmem.c                 | 12 ++----------
 4 files changed, 13 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index c340f6bb39d6..392d34c3c59a 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -14,8 +14,8 @@ extern bool hugepage_vma_check(struct vm_area_struct *vma,
 			       unsigned long vm_flags);
 extern void __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
-extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma,
-				       unsigned long vm_flags);
+extern void khugepaged_enter_vma(struct vm_area_struct *vma,
+				 unsigned long vm_flags);
 extern void khugepaged_min_free_kbytes_update(void);
 #ifdef CONFIG_SHMEM
 extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr);
@@ -72,8 +72,8 @@ static inline void khugepaged_enter(struct vm_area_struct *vma,
 				    unsigned long vm_flags)
 {
 }
-static inline void khugepaged_enter_vma_merge(struct vm_area_struct *vma,
-					      unsigned long vm_flags)
+static inline void khugepaged_enter_vma(struct vm_area_struct *vma,
+					unsigned long vm_flags)
 {
 }
 static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 9ef626e2c750..16be62d493cd 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -365,7 +365,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 * register it here without waiting a page fault that
 		 * may not happen any time soon.
 		 */
-		khugepaged_enter_vma_merge(vma, *vm_flags);
+		khugepaged_enter_vma(vma, *vm_flags);
 		break;
 	case MADV_NOHUGEPAGE:
 		*vm_flags &= ~VM_HUGEPAGE;
@@ -505,8 +505,8 @@ void __khugepaged_enter(struct mm_struct *mm)
 		wake_up_interruptible(&khugepaged_wait);
 }
 
-void khugepaged_enter_vma_merge(struct vm_area_struct *vma,
-			       unsigned long vm_flags)
+void khugepaged_enter_vma(struct vm_area_struct *vma,
+			  unsigned long vm_flags)
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
 	    khugepaged_enabled() &&
diff --git a/mm/mmap.c b/mm/mmap.c
index 7f7d982721b9..4456bf81e11e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1223,7 +1223,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 					 end, prev->vm_pgoff, NULL, prev);
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(prev, vm_flags);
+		khugepaged_enter_vma(prev, vm_flags);
 		return prev;
 	}
 
@@ -1250,7 +1250,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 		}
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(area, vm_flags);
+		khugepaged_enter_vma(area, vm_flags);
 		return area;
 	}
 
@@ -2450,7 +2450,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		}
 	}
 	anon_vma_unlock_write(vma->anon_vma);
-	khugepaged_enter_vma_merge(vma, vma->vm_flags);
+	khugepaged_enter_vma(vma, vma->vm_flags);
 	validate_mm(mm);
 	return error;
 }
@@ -2528,7 +2528,7 @@ int expand_downwards(struct vm_area_struct *vma,
 		}
 	}
 	anon_vma_unlock_write(vma->anon_vma);
-	khugepaged_enter_vma_merge(vma, vma->vm_flags);
+	khugepaged_enter_vma(vma, vma->vm_flags);
 	validate_mm(mm);
 	return error;
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index 29701be579f8..89f6f4fec3f9 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2232,11 +2232,7 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 
 	file_accessed(file);
 	vma->vm_ops = &shmem_vm_ops;
-	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
-			((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) <
-			(vma->vm_end & HPAGE_PMD_MASK)) {
-		khugepaged_enter(vma, vma->vm_flags);
-	}
+	khugepaged_enter_vma(vma, vma->vm_flags);
 	return 0;
 }
 
@@ -4137,11 +4133,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	vma->vm_file = file;
 	vma->vm_ops = &shmem_vm_ops;
 
-	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
-			((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) <
-			(vma->vm_end & HPAGE_PMD_MASK)) {
-		khugepaged_enter(vma, vma->vm_flags);
-	}
+	khugepaged_enter_vma(vma, vma->vm_flags);
 
 	return 0;
 }
-- 
cgit v1.2.3


From bc4a68adb151f08b50822158c7767f5726346370 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 19 May 2022 14:08:50 -0700
Subject: mm/swap: remove unneeded return value of free_swap_slot

The return value of free_swap_slot is always 0 and also ignored now.
Remove it to clean up the code.

Link: https://lkml.kernel.org/r/20220509131416.17553-5-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap_slots.h | 2 +-
 mm/swap_slots.c            | 4 +---
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h
index 347f1a304190..15adfb8c813a 100644
--- a/include/linux/swap_slots.h
+++ b/include/linux/swap_slots.h
@@ -24,7 +24,7 @@ struct swap_slots_cache {
 void disable_swap_slots_cache_lock(void);
 void reenable_swap_slots_cache_unlock(void);
 void enable_swap_slots_cache(void);
-int free_swap_slot(swp_entry_t entry);
+void free_swap_slot(swp_entry_t entry);
 
 extern bool swap_slot_cache_enabled;
 
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 0218ec1cd24c..2f877e6f87d7 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -269,7 +269,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
 	return cache->nr;
 }
 
-int free_swap_slot(swp_entry_t entry)
+void free_swap_slot(swp_entry_t entry)
 {
 	struct swap_slots_cache *cache;
 
@@ -297,8 +297,6 @@ int free_swap_slot(swp_entry_t entry)
 direct_free:
 		swapcache_free_entries(&entry, 1);
 	}
-
-	return 0;
 }
 
 swp_entry_t folio_alloc_swap(struct folio *folio)
-- 
cgit v1.2.3


From 3db3264d8a5f4816c022eb9052694ce51e657bfc Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 19 May 2022 14:08:51 -0700
Subject: mm/swap: make page_swapcount and __lru_add_drain_all static

Make page_swapcount and __lru_add_drain_all static.  They are only used
within the file now.

Link: https://lkml.kernel.org/r/20220509131416.17553-9-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h | 7 -------
 mm/swap.c            | 2 +-
 mm/swapfile.c        | 2 +-
 3 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 6bf1506e5080..0ff887cad383 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -485,7 +485,6 @@ int swap_type_of(dev_t device, sector_t offset);
 int find_first_swap(dev_t *device);
 extern unsigned int count_swap_pages(int, int);
 extern sector_t swapdev_block(int, pgoff_t);
-extern int page_swapcount(struct page *);
 extern int __swap_count(swp_entry_t entry);
 extern int __swp_swapcount(swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
@@ -557,12 +556,6 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp)
 {
 }
 
-
-static inline int page_swapcount(struct page *page)
-{
-	return 0;
-}
-
 static inline int __swap_count(swp_entry_t entry)
 {
 	return 0;
diff --git a/mm/swap.c b/mm/swap.c
index 7e320ec08c6a..6d2c37f781f8 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -748,7 +748,7 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
  * Calling this function with cpu hotplug locks held can actually lead
  * to obscure indirect dependencies via WQ context.
  */
-inline void __lru_add_drain_all(bool force_all_cpus)
+static inline void __lru_add_drain_all(bool force_all_cpus)
 {
 	/*
 	 * lru_drain_gen - Global pages generation number
diff --git a/mm/swapfile.c b/mm/swapfile.c
index e67addac61e2..f64b298f1034 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1429,7 +1429,7 @@ void swapcache_free_entries(swp_entry_t *entries, int n)
  * This does not give an exact answer when swap count is continued,
  * but does include the high COUNT_CONTINUED flag to allow for that.
  */
-int page_swapcount(struct page *page)
+static int page_swapcount(struct page *page)
 {
 	int count = 0;
 	struct swap_info_struct *p;
-- 
cgit v1.2.3


From a930c210c42dec32b031ad7645bd6904701b5297 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 19 May 2022 14:08:52 -0700
Subject: mm/swap: fix the obsolete comment for SWP_TYPE_SHIFT

Since commit 3159f943aafd ("xarray: Replace exceptional entries"), there
is only one bit of 'type' can be shifted up.  Update the corresponding
comment.

Link: https://lkml.kernel.org/r/20220509131416.17553-13-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swapops.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 09945342bf76..fe220df499f1 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -13,10 +13,10 @@
  * get good packing density in that tree, so the index should be dense in
  * the low-order bits.
  *
- * We arrange the `type' and `offset' fields so that `type' is at the seven
+ * We arrange the `type' and `offset' fields so that `type' is at the six
  * high-order bits of the swp_entry_t and `offset' is right-aligned in the
  * remaining bits.  Although `type' itself needs only five bits, we allow for
- * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry().
+ * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry().
  *
  * swp_entry_t's are *never* stored anywhere in their arch-dependent format.
  */
-- 
cgit v1.2.3


From ff351f4bb9606a6c9a1f3fcdd918635b51514779 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 19 May 2022 14:08:52 -0700
Subject: mm/swap: fix comment about swap extent

Since commit 4efaceb1c5f8 ("mm, swap: use rbtree for swap_extent"), rbtree
is used for swap extent.  Also curr_swap_extent is removed at that time.
Update the corresponding comment.

Link: https://lkml.kernel.org/r/20220509131416.17553-16-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h |  4 ++--
 mm/swapfile.c        | 15 ++++++---------
 2 files changed, 8 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0ff887cad383..04c0713c1d6e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -168,8 +168,8 @@ struct zone;
 
 /*
  * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of
- * disk blocks.  A list of swap extents maps the entire swapfile.  (Where the
- * term `swapfile' refers to either a blockdevice or an IS_REG file.  Apart
+ * disk blocks.  A rbtree of swap extents maps the entire swapfile (Where the
+ * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart
  * from setup, they're handled identically.
  *
  * We always assume that blocks are of size PAGE_SIZE.
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0535afc897ab..a0eb690d9926 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2208,8 +2208,8 @@ EXPORT_SYMBOL_GPL(add_swap_extent);
 
 /*
  * A `swap extent' is a simple thing which maps a contiguous range of pages
- * onto a contiguous range of disk blocks.  An ordered list of swap extents
- * is built at swapon time and is then used at swap_writepage/swap_readpage
+ * onto a contiguous range of disk blocks.  A rbtree of swap extents is
+ * built at swapon time and is then used at swap_writepage/swap_readpage
  * time for locating where on disk a page belongs.
  *
  * If the swapfile is an S_ISBLK block device, a single extent is installed.
@@ -2217,12 +2217,12 @@ EXPORT_SYMBOL_GPL(add_swap_extent);
  * swap files identically.
  *
  * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap
- * extent list operates in PAGE_SIZE disk blocks.  Both S_ISREG and S_ISBLK
+ * extent rbtree operates in PAGE_SIZE disk blocks.  Both S_ISREG and S_ISBLK
  * swapfiles are handled *identically* after swapon time.
  *
  * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks
- * and will parse them into an ordered extent list, in PAGE_SIZE chunks.  If
- * some stray blocks are found which do not fall within the PAGE_SIZE alignment
+ * and will parse them into a rbtree, in PAGE_SIZE chunks.  If some stray
+ * blocks are found which do not fall within the PAGE_SIZE alignment
  * requirements, they are simply tossed out - we will never use those blocks
  * for swapping.
  *
@@ -2231,10 +2231,7 @@ EXPORT_SYMBOL_GPL(add_swap_extent);
  *
  * The amount of disk space which a single swap extent represents varies.
  * Typically it is in the 1-4 megabyte range.  So we can have hundreds of
- * extents in the list.  To avoid much list walking, we cache the previous
- * search location in `curr_swap_extent', and start new searches from there.
- * This is extremely effective.  The average number of iterations in
- * map_swap_page() has been measured at about 0.3 per page.  - akpm.
+ * extents in the rbtree. - akpm.
  */
 static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 {
-- 
cgit v1.2.3


From f6498b776d280b30a4614d8261840961e993c2c8 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 19 May 2022 14:08:53 -0700
Subject: mm: zswap: add basic meminfo and vmstat coverage

Currently it requires poking at debugfs to figure out the size and
population of the zswap cache on a host.  There are no counters for reads
and writes against the cache.  As a result, it's difficult to understand
zswap behavior on production systems.

Print zswap memory consumption and how many pages are zswapped out in
/proc/meminfo.  Count zswapouts and zswapins in /proc/vmstat.

Link: https://lkml.kernel.org/r/20220510152847.230957-6-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/filesystems/proc.rst |  6 ++++++
 fs/proc/meminfo.c                  |  7 +++++++
 include/linux/swap.h               |  5 +++++
 include/linux/vm_event_item.h      |  4 ++++
 mm/vmstat.c                        |  4 ++++
 mm/zswap.c                         | 13 ++++++-------
 6 files changed, 32 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 5e9791457876..cfec3cab0f9a 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -964,6 +964,8 @@ Example output. You may not have all of these fields.
     Mlocked:               0 kB
     SwapTotal:             0 kB
     SwapFree:              0 kB
+    Zswap:              1904 kB
+    Zswapped:           7792 kB
     Dirty:                12 kB
     Writeback:             0 kB
     AnonPages:       4654780 kB
@@ -1055,6 +1057,10 @@ SwapTotal
 SwapFree
               Memory which has been evicted from RAM, and is temporarily
               on the disk
+Zswap
+              Memory consumed by the zswap backend (compressed size)
+Zswapped
+              Amount of anonymous memory stored in zswap (original size)
 Dirty
               Memory which is waiting to get written back to the disk
 Writeback
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 6fa761c9cc78..6e89f0e2fd20 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -86,6 +86,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 
 	show_val_kb(m, "SwapTotal:      ", i.totalswap);
 	show_val_kb(m, "SwapFree:       ", i.freeswap);
+#ifdef CONFIG_ZSWAP
+	seq_printf(m,  "Zswap:          %8lu kB\n",
+		   (unsigned long)(zswap_pool_total_size >> 10));
+	seq_printf(m,  "Zswapped:       %8lu kB\n",
+		   (unsigned long)atomic_read(&zswap_stored_pages) <<
+		   (PAGE_SHIFT - 10));
+#endif
 	show_val_kb(m, "Dirty:          ",
 		    global_node_page_state(NR_FILE_DIRTY));
 	show_val_kb(m, "Writeback:      ",
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 04c0713c1d6e..f3ae17b43f20 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -620,6 +620,11 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 }
 #endif
 
+#ifdef CONFIG_ZSWAP
+extern u64 zswap_pool_total_size;
+extern atomic_t zswap_stored_pages;
+#endif
+
 #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
 extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask);
 static inline  void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index e83967e4c20e..404024486fa5 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -136,6 +136,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_KSM
 		COW_KSM,
 #endif
+#ifdef CONFIG_ZSWAP
+		ZSWPIN,
+		ZSWPOUT,
+#endif
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
 		DIRECT_MAP_LEVEL3_SPLIT,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b94a2e4723ff..da525bfb6f4a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1396,6 +1396,10 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_KSM
 	"cow_ksm",
 #endif
+#ifdef CONFIG_ZSWAP
+	"zswpin",
+	"zswpout",
+#endif
 #ifdef CONFIG_X86
 	"direct_map_level2_splits",
 	"direct_map_level3_splits",
diff --git a/mm/zswap.c b/mm/zswap.c
index 2c5db4cbedea..e3c16a70f533 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -42,9 +42,9 @@
 * statistics
 **********************************/
 /* Total bytes used by the compressed storage */
-static u64 zswap_pool_total_size;
+u64 zswap_pool_total_size;
 /* The number of compressed pages currently stored in zswap */
-static atomic_t zswap_stored_pages = ATOMIC_INIT(0);
+atomic_t zswap_stored_pages = ATOMIC_INIT(0);
 /* The number of same-value filled pages currently stored in zswap */
 static atomic_t zswap_same_filled_pages = ATOMIC_INIT(0);
 
@@ -1243,6 +1243,7 @@ insert_entry:
 	/* update stats */
 	atomic_inc(&zswap_stored_pages);
 	zswap_update_total_size();
+	count_vm_event(ZSWPOUT);
 
 	return 0;
 
@@ -1285,11 +1286,10 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 		zswap_fill_page(dst, entry->value);
 		kunmap_atomic(dst);
 		ret = 0;
-		goto freeentry;
+		goto stats;
 	}
 
 	if (!zpool_can_sleep_mapped(entry->pool->zpool)) {
-
 		tmp = kmalloc(entry->length, GFP_ATOMIC);
 		if (!tmp) {
 			ret = -ENOMEM;
@@ -1304,10 +1304,8 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 		src += sizeof(struct zswap_header);
 
 	if (!zpool_can_sleep_mapped(entry->pool->zpool)) {
-
 		memcpy(tmp, src, entry->length);
 		src = tmp;
-
 		zpool_unmap_handle(entry->pool->zpool, entry->handle);
 	}
 
@@ -1326,7 +1324,8 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 		kfree(tmp);
 
 	BUG_ON(ret);
-
+stats:
+	count_vm_event(ZSWPIN);
 freeentry:
 	spin_lock(&tree->lock);
 	zswap_entry_put(tree, entry);
-- 
cgit v1.2.3


From f4840ccfca25db225b3371a8f7b5770febee87c5 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 19 May 2022 14:08:53 -0700
Subject: zswap: memcg accounting

Applications can currently escape their cgroup memory containment when
zswap is enabled.  This patch adds per-cgroup tracking and limiting of
zswap backend memory to rectify this.

The existing cgroup2 memory.stat file is extended to show zswap statistics
analogous to what's in meminfo and vmstat.  Furthermore, two new control
files, memory.zswap.current and memory.zswap.max, are added to allow
tuning zswap usage on a per-workload basis.  This is important since not
all workloads benefit from zswap equally; some even suffer compared to
disk swap when memory contents don't compress well.  The optimal size of
the zswap pool, and the threshold for writeback, also depends on the size
of the workload's warm set.

The implementation doesn't use a traditional page_counter transaction.
zswap is unconventional as a memory consumer in that we only know the
amount of memory to charge once expensive compression has occurred.  If
zwap is disabled or the limit is already exceeded we obviously don't want
to compress page upon page only to reject them all.  Instead, the limit is
checked against current usage, then we compress and charge.  This allows
some limit overrun, but not enough to matter in practice.

[hannes@cmpxchg.org: fix for CONFIG_SLOB builds]
  Link: https://lkml.kernel.org/r/YnwD14zxYjUJPc2w@cmpxchg.org
[hannes@cmpxchg.org: opt out of cgroups v1]
  Link: https://lkml.kernel.org/r/Yn6it9mBYFA+/lTb@cmpxchg.org
Link: https://lkml.kernel.org/r/20220510152847.230957-7-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v2.rst |  21 ++++
 include/linux/memcontrol.h              |  54 +++++++++
 mm/memcontrol.c                         | 205 ++++++++++++++++++++++++++++++--
 mm/zswap.c                              |  37 ++++--
 4 files changed, 302 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 07ef3bf1448e..08ae8189e6cb 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1354,6 +1354,12 @@ PAGE_SIZE multiple when read back.
 		Amount of cached filesystem data that is swap-backed,
 		such as tmpfs, shm segments, shared anonymous mmap()s
 
+	  zswap
+		Amount of memory consumed by the zswap compression backend.
+
+	  zswapped
+		Amount of application memory swapped out to zswap.
+
 	  file_mapped
 		Amount of cached filesystem data mapped with mmap()
 
@@ -1544,6 +1550,21 @@ PAGE_SIZE multiple when read back.
 	higher than the limit for an extended period of time.  This
 	reduces the impact on the workload and memory management.
 
+  memory.zswap.current
+	A read-only single value file which exists on non-root
+	cgroups.
+
+	The total amount of memory consumed by the zswap compression
+	backend.
+
+  memory.zswap.max
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Zswap usage hard limit. If a cgroup's zswap pool reaches this
+	limit, it will refuse to take any more stores before existing
+	entries fault back in or are written out to disk.
+
   memory.pressure
 	A read-only nested-keyed file.
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8ea4b541c31e..9ecead1042b9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -35,6 +35,8 @@ enum memcg_stat_item {
 	MEMCG_PERCPU_B,
 	MEMCG_VMALLOC,
 	MEMCG_KMEM,
+	MEMCG_ZSWAP_B,
+	MEMCG_ZSWAPPED,
 	MEMCG_NR_STAT,
 };
 
@@ -252,6 +254,10 @@ struct mem_cgroup {
 	/* Range enforcement for interrupt charges */
 	struct work_struct high_work;
 
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+	unsigned long zswap_max;
+#endif
+
 	unsigned long soft_limit;
 
 	/* vmpressure notifications */
@@ -1273,6 +1279,10 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css)
 	return NULL;
 }
 
+static inline void obj_cgroup_put(struct obj_cgroup *objcg)
+{
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
@@ -1694,6 +1704,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
 
 struct obj_cgroup *get_obj_cgroup_from_current(void);
+struct obj_cgroup *get_obj_cgroup_from_page(struct page *page);
 
 int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
 void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
@@ -1730,6 +1741,20 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 
 struct mem_cgroup *mem_cgroup_from_obj(void *p);
 
+static inline void count_objcg_event(struct obj_cgroup *objcg,
+				     enum vm_event_item idx)
+{
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_kmem_disabled())
+		return;
+
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	count_memcg_events(memcg, idx, 1);
+	rcu_read_unlock();
+}
+
 #else
 static inline bool mem_cgroup_kmem_disabled(void)
 {
@@ -1756,6 +1781,11 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order)
 {
 }
 
+static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page)
+{
+	return NULL;
+}
+
 static inline bool memcg_kmem_enabled(void)
 {
 	return false;
@@ -1771,6 +1801,30 @@ static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
        return NULL;
 }
 
+static inline void count_objcg_event(struct obj_cgroup *objcg,
+				     enum vm_event_item idx)
+{
+}
+
 #endif /* CONFIG_MEMCG_KMEM */
 
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
+void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
+void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size);
+#else
+static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
+{
+	return true;
+}
+static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg,
+					   size_t size)
+{
+}
+static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
+					     size_t size)
+{
+}
+#endif
+
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ef76df7c6d12..abec50f31fe6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1398,6 +1398,10 @@ static const struct memory_stat memory_stats[] = {
 	{ "sock",			MEMCG_SOCK			},
 	{ "vmalloc",			MEMCG_VMALLOC			},
 	{ "shmem",			NR_SHMEM			},
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+	{ "zswap",			MEMCG_ZSWAP_B			},
+	{ "zswapped",			MEMCG_ZSWAPPED			},
+#endif
 	{ "file_mapped",		NR_FILE_MAPPED			},
 	{ "file_dirty",			NR_FILE_DIRTY			},
 	{ "file_writeback",		NR_WRITEBACK			},
@@ -1432,6 +1436,7 @@ static int memcg_page_state_unit(int item)
 {
 	switch (item) {
 	case MEMCG_PERCPU_B:
+	case MEMCG_ZSWAP_B:
 	case NR_SLAB_RECLAIMABLE_B:
 	case NR_SLAB_UNRECLAIMABLE_B:
 	case WORKINGSET_REFAULT_ANON:
@@ -1512,6 +1517,13 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 	seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED),
 		       memcg_events(memcg, PGLAZYFREED));
 
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+	seq_buf_printf(&s, "%s %lu\n", vm_event_name(ZSWPIN),
+		       memcg_events(memcg, ZSWPIN));
+	seq_buf_printf(&s, "%s %lu\n", vm_event_name(ZSWPOUT),
+		       memcg_events(memcg, ZSWPOUT));
+#endif
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC),
 		       memcg_events(memcg, THP_FAULT_ALLOC));
@@ -2883,6 +2895,19 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 	return page_memcg_check(folio_page(folio, 0));
 }
 
+static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
+{
+	struct obj_cgroup *objcg = NULL;
+
+	for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
+		objcg = rcu_dereference(memcg->objcg);
+		if (objcg && obj_cgroup_tryget(objcg))
+			break;
+		objcg = NULL;
+	}
+	return objcg;
+}
+
 __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 {
 	struct obj_cgroup *objcg = NULL;
@@ -2896,15 +2921,32 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 		memcg = active_memcg();
 	else
 		memcg = mem_cgroup_from_task(current);
-
-	for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
-		objcg = rcu_dereference(memcg->objcg);
-		if (objcg && obj_cgroup_tryget(objcg))
-			break;
-		objcg = NULL;
-	}
+	objcg = __get_obj_cgroup_from_memcg(memcg);
 	rcu_read_unlock();
+	return objcg;
+}
+
+struct obj_cgroup *get_obj_cgroup_from_page(struct page *page)
+{
+	struct obj_cgroup *objcg;
+
+	if (!memcg_kmem_enabled() || memcg_kmem_bypass())
+		return NULL;
+
+	if (PageMemcgKmem(page)) {
+		objcg = __folio_objcg(page_folio(page));
+		obj_cgroup_get(objcg);
+	} else {
+		struct mem_cgroup *memcg;
 
+		rcu_read_lock();
+		memcg = __folio_memcg(page_folio(page));
+		if (memcg)
+			objcg = __get_obj_cgroup_from_memcg(memcg);
+		else
+			objcg = NULL;
+		rcu_read_unlock();
+	}
 	return objcg;
 }
 
@@ -5142,6 +5184,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
 	memcg->soft_limit = PAGE_COUNTER_MAX;
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+	memcg->zswap_max = PAGE_COUNTER_MAX;
+#endif
 	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 	if (parent) {
 		memcg->swappiness = mem_cgroup_swappiness(parent);
@@ -7421,6 +7466,148 @@ static struct cftype memsw_files[] = {
 	{ },	/* terminate */
 };
 
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+/**
+ * obj_cgroup_may_zswap - check if this cgroup can zswap
+ * @objcg: the object cgroup
+ *
+ * Check if the hierarchical zswap limit has been reached.
+ *
+ * This doesn't check for specific headroom, and it is not atomic
+ * either. But with zswap, the size of the allocation is only known
+ * once compression has occured, and this optimistic pre-check avoids
+ * spending cycles on compression when there is already no room left
+ * or zswap is disabled altogether somewhere in the hierarchy.
+ */
+bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
+{
+	struct mem_cgroup *memcg, *original_memcg;
+	bool ret = true;
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return true;
+
+	original_memcg = get_mem_cgroup_from_objcg(objcg);
+	for (memcg = original_memcg; memcg != root_mem_cgroup;
+	     memcg = parent_mem_cgroup(memcg)) {
+		unsigned long max = READ_ONCE(memcg->zswap_max);
+		unsigned long pages;
+
+		if (max == PAGE_COUNTER_MAX)
+			continue;
+		if (max == 0) {
+			ret = false;
+			break;
+		}
+
+		cgroup_rstat_flush(memcg->css.cgroup);
+		pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE;
+		if (pages < max)
+			continue;
+		ret = false;
+		break;
+	}
+	mem_cgroup_put(original_memcg);
+	return ret;
+}
+
+/**
+ * obj_cgroup_charge_zswap - charge compression backend memory
+ * @objcg: the object cgroup
+ * @size: size of compressed object
+ *
+ * This forces the charge after obj_cgroup_may_swap() allowed
+ * compression and storage in zwap for this cgroup to go ahead.
+ */
+void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size)
+{
+	struct mem_cgroup *memcg;
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return;
+
+	VM_WARN_ON_ONCE(!(current->flags & PF_MEMALLOC));
+
+	/* PF_MEMALLOC context, charging must succeed */
+	if (obj_cgroup_charge(objcg, GFP_KERNEL, size))
+		VM_WARN_ON_ONCE(1);
+
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	mod_memcg_state(memcg, MEMCG_ZSWAP_B, size);
+	mod_memcg_state(memcg, MEMCG_ZSWAPPED, 1);
+	rcu_read_unlock();
+}
+
+/**
+ * obj_cgroup_uncharge_zswap - uncharge compression backend memory
+ * @objcg: the object cgroup
+ * @size: size of compressed object
+ *
+ * Uncharges zswap memory on page in.
+ */
+void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
+{
+	struct mem_cgroup *memcg;
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return;
+
+	obj_cgroup_uncharge(objcg, size);
+
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	mod_memcg_state(memcg, MEMCG_ZSWAP_B, -size);
+	mod_memcg_state(memcg, MEMCG_ZSWAPPED, -1);
+	rcu_read_unlock();
+}
+
+static u64 zswap_current_read(struct cgroup_subsys_state *css,
+			      struct cftype *cft)
+{
+	cgroup_rstat_flush(css->cgroup);
+	return memcg_page_state(mem_cgroup_from_css(css), MEMCG_ZSWAP_B);
+}
+
+static int zswap_max_show(struct seq_file *m, void *v)
+{
+	return seq_puts_memcg_tunable(m,
+		READ_ONCE(mem_cgroup_from_seq(m)->zswap_max));
+}
+
+static ssize_t zswap_max_write(struct kernfs_open_file *of,
+			       char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	unsigned long max;
+	int err;
+
+	buf = strstrip(buf);
+	err = page_counter_memparse(buf, "max", &max);
+	if (err)
+		return err;
+
+	xchg(&memcg->zswap_max, max);
+
+	return nbytes;
+}
+
+static struct cftype zswap_files[] = {
+	{
+		.name = "zswap.current",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = zswap_current_read,
+	},
+	{
+		.name = "zswap.max",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = zswap_max_show,
+		.write = zswap_max_write,
+	},
+	{ }	/* terminate */
+};
+#endif /* CONFIG_MEMCG_KMEM && CONFIG_ZSWAP */
+
 /*
  * If mem_cgroup_swap_init() is implemented as a subsys_initcall()
  * instead of a core_initcall(), this could mean cgroup_memory_noswap still
@@ -7439,7 +7626,9 @@ static int __init mem_cgroup_swap_init(void)
 
 	WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, swap_files));
 	WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_files));
-
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+	WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, zswap_files));
+#endif
 	return 0;
 }
 core_initcall(mem_cgroup_swap_init);
diff --git a/mm/zswap.c b/mm/zswap.c
index e3c16a70f533..104835b379ec 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -188,6 +188,7 @@ struct zswap_entry {
 		unsigned long handle;
 		unsigned long value;
 	};
+	struct obj_cgroup *objcg;
 };
 
 struct zswap_header {
@@ -359,6 +360,10 @@ static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
  */
 static void zswap_free_entry(struct zswap_entry *entry)
 {
+	if (entry->objcg) {
+		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
+		obj_cgroup_put(entry->objcg);
+	}
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
@@ -1096,6 +1101,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	struct zswap_entry *entry, *dupentry;
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
+	struct obj_cgroup *objcg = NULL;
+	struct zswap_pool *pool;
 	int ret;
 	unsigned int hlen, dlen = PAGE_SIZE;
 	unsigned long handle, value;
@@ -1115,17 +1122,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 		goto reject;
 	}
 
+	objcg = get_obj_cgroup_from_page(page);
+	if (objcg && !obj_cgroup_may_zswap(objcg))
+		goto shrink;
+
 	/* reclaim space if needed */
 	if (zswap_is_full()) {
-		struct zswap_pool *pool;
-
 		zswap_pool_limit_hit++;
 		zswap_pool_reached_full = true;
-		pool = zswap_pool_last_get();
-		if (pool)
-			queue_work(shrink_wq, &pool->shrink_work);
-		ret = -ENOMEM;
-		goto reject;
+		goto shrink;
 	}
 
 	if (zswap_pool_reached_full) {
@@ -1227,6 +1232,13 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	entry->length = dlen;
 
 insert_entry:
+	entry->objcg = objcg;
+	if (objcg) {
+		obj_cgroup_charge_zswap(objcg, entry->length);
+		/* Account before objcg ref is moved to tree */
+		count_objcg_event(objcg, ZSWPOUT);
+	}
+
 	/* map */
 	spin_lock(&tree->lock);
 	do {
@@ -1253,7 +1265,16 @@ put_dstmem:
 freepage:
 	zswap_entry_cache_free(entry);
 reject:
+	if (objcg)
+		obj_cgroup_put(objcg);
 	return ret;
+
+shrink:
+	pool = zswap_pool_last_get();
+	if (pool)
+		queue_work(shrink_wq, &pool->shrink_work);
+	ret = -ENOMEM;
+	goto reject;
 }
 
 /*
@@ -1326,6 +1347,8 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	BUG_ON(ret);
 stats:
 	count_vm_event(ZSWPIN);
+	if (entry->objcg)
+		count_objcg_event(entry->objcg, ZSWPIN);
 freeentry:
 	spin_lock(&tree->lock);
 	zswap_entry_put(tree, entry);
-- 
cgit v1.2.3


From 6d4675e601357834dadd2ba1d803f6484596015c Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Thu, 19 May 2022 14:08:54 -0700
Subject: mm: don't be stuck to rmap lock on reclaim path

The rmap locks(i_mmap_rwsem and anon_vma->root->rwsem) could be contended
under memory pressure if processes keep working on their vmas(e.g., fork,
mmap, munmap).  It makes reclaim path stuck.  In our real workload traces,
we see kswapd is waiting the lock for 300ms+(worst case, a sec) and it
makes other processes entering direct reclaim, which were also stuck on
the lock.

This patch makes lru aging path try_lock mode like shink_page_list so the
reclaim context will keep working with next lru pages without being stuck.
if it found the rmap lock contended, it rotates the page back to head of
lru in both active/inactive lrus to make them consistent behavior, which
is basic starting point rather than adding more heristic.

Since this patch introduces a new "contended" field as out-param along
with try_lock in-param in rmap_walk_control, it's not immutable any longer
if the try_lock is set so remove const keywords on rmap related functions.
Since rmap walking is already expensive operation, I doubt the const
would help sizable benefit( And we didn't have it until 5.17).

In a heavy app workload in Android, trace shows following statistics.  It
almost removes rmap lock contention from reclaim path.

Martin Liu reported:

Before:

   max_dur(ms)  min_dur(ms)  max-min(dur)ms  avg_dur(ms)  sum_dur(ms)  count blocked_function
         1632            0            1631   151.542173        31672    209  page_lock_anon_vma_read
          601            0             601   145.544681        28817    198  rmap_walk_file

After:

   max_dur(ms)  min_dur(ms)  max-min(dur)ms  avg_dur(ms)  sum_dur(ms)  count blocked_function
          NaN          NaN              NaN          NaN          NaN    0.0             NaN
            0            0                0     0.127645            1     12  rmap_walk_file

[minchan@kernel.org: add comment, per Matthew]
  Link: https://lkml.kernel.org/r/YnNqeB5tUf6LZ57b@google.com
Link: https://lkml.kernel.org/r/20220510215423.164547-1-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: John Dias <joaodias@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Martin Liu <liumartin@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/fs.h   |  5 +++++
 include/linux/ksm.h  |  4 ++--
 include/linux/rmap.h | 28 ++++++++++++++++++++--------
 mm/ksm.c             | 10 ++++++++--
 mm/memory-failure.c  |  2 +-
 mm/page_idle.c       |  7 ++++---
 mm/rmap.c            | 52 +++++++++++++++++++++++++++++++++++++++++-----------
 mm/vmscan.c          |  7 ++++++-
 8 files changed, 87 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index b81cacc51d2f..044b67f8d861 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -477,6 +477,11 @@ static inline void i_mmap_unlock_write(struct address_space *mapping)
 	up_write(&mapping->i_mmap_rwsem);
 }
 
+static inline int i_mmap_trylock_read(struct address_space *mapping)
+{
+	return down_read_trylock(&mapping->i_mmap_rwsem);
+}
+
 static inline void i_mmap_lock_read(struct address_space *mapping)
 {
 	down_read(&mapping->i_mmap_rwsem);
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 0630e545f4cb..0b4f17418f64 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm)
 struct page *ksm_might_need_to_copy(struct page *page,
 			struct vm_area_struct *vma, unsigned long address);
 
-void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc);
+void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
 void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
 
 #else  /* !CONFIG_KSM */
@@ -79,7 +79,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page,
 }
 
 static inline void rmap_walk_ksm(struct folio *folio,
-			const struct rmap_walk_control *rwc)
+			struct rmap_walk_control *rwc)
 {
 }
 
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index cbe279a6f0de..9ec23138e410 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -128,6 +128,11 @@ static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
 	down_read(&anon_vma->root->rwsem);
 }
 
+static inline int anon_vma_trylock_read(struct anon_vma *anon_vma)
+{
+	return down_read_trylock(&anon_vma->root->rwsem);
+}
+
 static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
 {
 	up_read(&anon_vma->root->rwsem);
@@ -366,17 +371,14 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
 
 void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked);
 
-/*
- * Called by memory-failure.c to kill processes.
- */
-struct anon_vma *folio_lock_anon_vma_read(struct folio *folio);
-void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
 int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
 
 /*
  * rmap_walk_control: To control rmap traversing for specific needs
  *
  * arg: passed to rmap_one() and invalid_vma()
+ * try_lock: bail out if the rmap lock is contended
+ * contended: indicate the rmap traversal bailed out due to lock contention
  * rmap_one: executed on each vma where page is mapped
  * done: for checking traversing termination condition
  * anon_lock: for getting anon_lock by optimized way rather than default
@@ -384,6 +386,8 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
  */
 struct rmap_walk_control {
 	void *arg;
+	bool try_lock;
+	bool contended;
 	/*
 	 * Return false if page table scanning in rmap_walk should be stopped.
 	 * Otherwise, return true.
@@ -391,12 +395,20 @@ struct rmap_walk_control {
 	bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma,
 					unsigned long addr, void *arg);
 	int (*done)(struct folio *folio);
-	struct anon_vma *(*anon_lock)(struct folio *folio);
+	struct anon_vma *(*anon_lock)(struct folio *folio,
+				      struct rmap_walk_control *rwc);
 	bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
 };
 
-void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc);
-void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc);
+void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc);
+void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc);
+
+/*
+ * Called by memory-failure.c to kill processes.
+ */
+struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
+					  struct rmap_walk_control *rwc);
+void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
 
 #else	/* !CONFIG_MMU */
 
diff --git a/mm/ksm.c b/mm/ksm.c
index 38360285497a..9ee82c9bce94 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2610,7 +2610,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
 	return new_page;
 }
 
-void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc)
+void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc)
 {
 	struct stable_node *stable_node;
 	struct rmap_item *rmap_item;
@@ -2634,7 +2634,13 @@ again:
 		struct vm_area_struct *vma;
 
 		cond_resched();
-		anon_vma_lock_read(anon_vma);
+		if (!anon_vma_trylock_read(anon_vma)) {
+			if (rwc->try_lock) {
+				rwc->contended = true;
+				return;
+			}
+			anon_vma_lock_read(anon_vma);
+		}
 		anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
 					       0, ULONG_MAX) {
 			unsigned long addr;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 01f8b63d3621..a934ee8124dd 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -485,7 +485,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	struct anon_vma *av;
 	pgoff_t pgoff;
 
-	av = folio_lock_anon_vma_read(folio);
+	av = folio_lock_anon_vma_read(folio, NULL);
 	if (av == NULL)	/* Not actually mapped anymore */
 		return;
 
diff --git a/mm/page_idle.c b/mm/page_idle.c
index fc0435abf909..bc08332a609c 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -86,11 +86,12 @@ static bool page_idle_clear_pte_refs_one(struct folio *folio,
 static void page_idle_clear_pte_refs(struct page *page)
 {
 	struct folio *folio = page_folio(page);
+
 	/*
-	 * Since rwc.arg is unused, rwc is effectively immutable, so we
-	 * can make it static const to save some cycles and stack.
+	 * Since rwc.try_lock is unused, rwc is effectively immutable, so we
+	 * can make it static to save some cycles and stack.
 	 */
-	static const struct rmap_walk_control rwc = {
+	static struct rmap_walk_control rwc = {
 		.rmap_one = page_idle_clear_pte_refs_one,
 		.anon_lock = folio_lock_anon_vma_read,
 	};
diff --git a/mm/rmap.c b/mm/rmap.c
index 219e287a83d2..5bcb334cd6f2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -527,9 +527,11 @@ out:
  *
  * Its a little more complex as it tries to keep the fast path to a single
  * atomic op -- the trylock. If we fail the trylock, we fall back to getting a
- * reference like with page_get_anon_vma() and then block on the mutex.
+ * reference like with page_get_anon_vma() and then block on the mutex
+ * on !rwc->try_lock case.
  */
-struct anon_vma *folio_lock_anon_vma_read(struct folio *folio)
+struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
+					  struct rmap_walk_control *rwc)
 {
 	struct anon_vma *anon_vma = NULL;
 	struct anon_vma *root_anon_vma;
@@ -557,6 +559,12 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio)
 		goto out;
 	}
 
+	if (rwc && rwc->try_lock) {
+		anon_vma = NULL;
+		rwc->contended = true;
+		goto out;
+	}
+
 	/* trylock failed, we got to sleep */
 	if (!atomic_inc_not_zero(&anon_vma->refcount)) {
 		anon_vma = NULL;
@@ -883,7 +891,8 @@ static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg)
  *
  * Quick test_and_clear_referenced for all mappings of a folio,
  *
- * Return: The number of mappings which referenced the folio.
+ * Return: The number of mappings which referenced the folio. Return -1 if
+ * the function bailed out due to rmap lock contention.
  */
 int folio_referenced(struct folio *folio, int is_locked,
 		     struct mem_cgroup *memcg, unsigned long *vm_flags)
@@ -897,6 +906,7 @@ int folio_referenced(struct folio *folio, int is_locked,
 		.rmap_one = folio_referenced_one,
 		.arg = (void *)&pra,
 		.anon_lock = folio_lock_anon_vma_read,
+		.try_lock = true,
 	};
 
 	*vm_flags = 0;
@@ -927,7 +937,7 @@ int folio_referenced(struct folio *folio, int is_locked,
 	if (we_locked)
 		folio_unlock(folio);
 
-	return pra.referenced;
+	return rwc.contended ? -1 : pra.referenced;
 }
 
 static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
@@ -2336,12 +2346,12 @@ void __put_anon_vma(struct anon_vma *anon_vma)
 }
 
 static struct anon_vma *rmap_walk_anon_lock(struct folio *folio,
-					const struct rmap_walk_control *rwc)
+					    struct rmap_walk_control *rwc)
 {
 	struct anon_vma *anon_vma;
 
 	if (rwc->anon_lock)
-		return rwc->anon_lock(folio);
+		return rwc->anon_lock(folio, rwc);
 
 	/*
 	 * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read()
@@ -2353,7 +2363,17 @@ static struct anon_vma *rmap_walk_anon_lock(struct folio *folio,
 	if (!anon_vma)
 		return NULL;
 
+	if (anon_vma_trylock_read(anon_vma))
+		goto out;
+
+	if (rwc->try_lock) {
+		anon_vma = NULL;
+		rwc->contended = true;
+		goto out;
+	}
+
 	anon_vma_lock_read(anon_vma);
+out:
 	return anon_vma;
 }
 
@@ -2367,7 +2387,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct folio *folio,
  * contained in the anon_vma struct it points to.
  */
 static void rmap_walk_anon(struct folio *folio,
-		const struct rmap_walk_control *rwc, bool locked)
+		struct rmap_walk_control *rwc, bool locked)
 {
 	struct anon_vma *anon_vma;
 	pgoff_t pgoff_start, pgoff_end;
@@ -2415,7 +2435,7 @@ static void rmap_walk_anon(struct folio *folio,
  * contained in the address_space struct it points to.
  */
 static void rmap_walk_file(struct folio *folio,
-		const struct rmap_walk_control *rwc, bool locked)
+		struct rmap_walk_control *rwc, bool locked)
 {
 	struct address_space *mapping = folio_mapping(folio);
 	pgoff_t pgoff_start, pgoff_end;
@@ -2434,8 +2454,18 @@ static void rmap_walk_file(struct folio *folio,
 
 	pgoff_start = folio_pgoff(folio);
 	pgoff_end = pgoff_start + folio_nr_pages(folio) - 1;
-	if (!locked)
+	if (!locked) {
+		if (i_mmap_trylock_read(mapping))
+			goto lookup;
+
+		if (rwc->try_lock) {
+			rwc->contended = true;
+			return;
+		}
+
 		i_mmap_lock_read(mapping);
+	}
+lookup:
 	vma_interval_tree_foreach(vma, &mapping->i_mmap,
 			pgoff_start, pgoff_end) {
 		unsigned long address = vma_address(&folio->page, vma);
@@ -2457,7 +2487,7 @@ done:
 		i_mmap_unlock_read(mapping);
 }
 
-void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc)
+void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc)
 {
 	if (unlikely(folio_test_ksm(folio)))
 		rmap_walk_ksm(folio, rwc);
@@ -2468,7 +2498,7 @@ void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc)
 }
 
 /* Like rmap_walk, but caller holds relevant rmap lock */
-void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc)
+void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc)
 {
 	/* no ksm support for now */
 	VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 24dbe04520cb..887edcd93a40 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1391,6 +1391,10 @@ static enum page_references folio_check_references(struct folio *folio,
 	if (vm_flags & VM_LOCKED)
 		return PAGEREF_ACTIVATE;
 
+	/* rmap lock contention: rotate */
+	if (referenced_ptes == -1)
+		return PAGEREF_KEEP;
+
 	if (referenced_ptes) {
 		/*
 		 * All mapped folios start out with page table
@@ -2499,8 +2503,9 @@ static void shrink_active_list(unsigned long nr_to_scan,
 			}
 		}
 
+		/* Referenced or rmap lock contention: rotate */
 		if (folio_referenced(folio, 0, sc->target_mem_cgroup,
-				     &vm_flags)) {
+				     &vm_flags) != 0) {
 			/*
 			 * Identify referenced, file-backed active pages and
 			 * give them one more trip around the active list. So
-- 
cgit v1.2.3


From 3f913fc5f9745613088d3c569778c9813ab9c129 Mon Sep 17 00:00:00 2001
From: Qi Zheng <zhengqi.arch@bytedance.com>
Date: Thu, 19 May 2022 14:08:55 -0700
Subject: mm: fix missing handler for __GFP_NOWARN

We expect no warnings to be issued when we specify __GFP_NOWARN, but
currently in paths like alloc_pages() and kmalloc(), there are still some
warnings printed, fix it.

But for some warnings that report usage problems, we don't deal with them.
If such warnings are printed, then we should fix the usage problems.
Such as the following case:

	WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));

[zhengqi.arch@bytedance.com: v2]
 Link: https://lkml.kernel.org/r/20220511061951.1114-1-zhengqi.arch@bytedance.com
Link: https://lkml.kernel.org/r/20220510113809.80626-1-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/fault-inject.h |  2 ++
 lib/fault-inject.c           |  3 +++
 mm/failslab.c                |  3 +++
 mm/internal.h                | 15 +++++++++++++++
 mm/page_alloc.c              | 18 ++++++++++--------
 5 files changed, 33 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index 2d04f6448cde..9f6e25467844 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -20,6 +20,7 @@ struct fault_attr {
 	atomic_t space;
 	unsigned long verbose;
 	bool task_filter;
+	bool no_warn;
 	unsigned long stacktrace_depth;
 	unsigned long require_start;
 	unsigned long require_end;
@@ -39,6 +40,7 @@ struct fault_attr {
 		.ratelimit_state = RATELIMIT_STATE_INIT_DISABLED,	\
 		.verbose = 2,						\
 		.dname = NULL,						\
+		.no_warn = false,					\
 	}
 
 #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index ce12621b4275..423784d9c058 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -41,6 +41,9 @@ EXPORT_SYMBOL_GPL(setup_fault_attr);
 
 static void fail_dump(struct fault_attr *attr)
 {
+	if (attr->no_warn)
+		return;
+
 	if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) {
 		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n"
 		       "name %pd, interval %lu, probability %lu, "
diff --git a/mm/failslab.c b/mm/failslab.c
index f92fed91ac23..58df9789f1d2 100644
--- a/mm/failslab.c
+++ b/mm/failslab.c
@@ -30,6 +30,9 @@ bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 	if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB))
 		return false;
 
+	if (gfpflags & __GFP_NOWARN)
+		failslab.attr.no_warn = true;
+
 	return should_fail(&failslab.attr, s->object_size);
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 6d188161b20e..64e61b032dac 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -35,6 +35,21 @@ struct folio_batch;
 /* Do not use these with a slab allocator */
 #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
 
+/*
+ * Different from WARN_ON_ONCE(), no warning will be issued
+ * when we specify __GFP_NOWARN.
+ */
+#define WARN_ON_ONCE_GFP(cond, gfp)	({				\
+	static bool __section(".data.once") __warned;			\
+	int __ret_warn_once = !!(cond);					\
+									\
+	if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \
+		__warned = true;					\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn_once);					\
+})
+
 void page_writeback_init(void);
 
 static inline void *folio_raw_mapping(struct folio *folio)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 10305b10fe93..267599dd9706 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3786,6 +3786,9 @@ static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 			(gfp_mask & __GFP_DIRECT_RECLAIM))
 		return false;
 
+	if (gfp_mask & __GFP_NOWARN)
+		fail_page_alloc.attr.no_warn = true;
+
 	return should_fail(&fail_page_alloc.attr, 1 << order);
 }
 
@@ -4334,7 +4337,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	 */
 
 	/* Exhausted what can be done so it's blame time */
-	if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
+	if (out_of_memory(&oc) ||
+	    WARN_ON_ONCE_GFP(gfp_mask & __GFP_NOFAIL, gfp_mask)) {
 		*did_some_progress = 1;
 
 		/*
@@ -5108,7 +5112,7 @@ nopage:
 		 * All existing users of the __GFP_NOFAIL are blockable, so warn
 		 * of any new users that actually require GFP_NOWAIT
 		 */
-		if (WARN_ON_ONCE(!can_direct_reclaim))
+		if (WARN_ON_ONCE_GFP(!can_direct_reclaim, gfp_mask))
 			goto fail;
 
 		/*
@@ -5116,7 +5120,7 @@ nopage:
 		 * because we cannot reclaim anything and only can loop waiting
 		 * for somebody to do a work for us
 		 */
-		WARN_ON_ONCE(current->flags & PF_MEMALLOC);
+		WARN_ON_ONCE_GFP(current->flags & PF_MEMALLOC, gfp_mask);
 
 		/*
 		 * non failing costly orders are a hard requirement which we
@@ -5124,7 +5128,7 @@ nopage:
 		 * so that we can identify them and convert them to something
 		 * else.
 		 */
-		WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER);
+		WARN_ON_ONCE_GFP(order > PAGE_ALLOC_COSTLY_ORDER, gfp_mask);
 
 		/*
 		 * Help non-failing allocations by giving them access to memory
@@ -5370,10 +5374,8 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
 	 * There are several places where we assume that the order value is sane
 	 * so bail out early if the request is out of bound.
 	 */
-	if (unlikely(order >= MAX_ORDER)) {
-		WARN_ON_ONCE(!(gfp & __GFP_NOWARN));
+	if (WARN_ON_ONCE_GFP(order >= MAX_ORDER, gfp))
 		return NULL;
-	}
 
 	gfp &= gfp_allowed_mask;
 	/*
@@ -9025,7 +9027,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 
 	lru_cache_enable();
 	if (ret < 0) {
-		if (ret == -EBUSY)
+		if (!(cc->gfp_mask & __GFP_NOWARN) && ret == -EBUSY)
 			alloc_contig_dump_pages(&cc->migratepages);
 		putback_movable_pages(&cc->migratepages);
 		return ret;
-- 
cgit v1.2.3


From 37462a920392cb86541650a6f4121155f11f1199 Mon Sep 17 00:00:00 2001
From: Christophe de Dinechin <dinechin@redhat.com>
Date: Thu, 14 Apr 2022 17:08:54 +0200
Subject: nodemask.h: fix compilation error with GCC12

With gcc version 12.0.1 20220401 (Red Hat 12.0.1-0), building with
defconfig results in the following compilation error:

|   CC      mm/swapfile.o
| mm/swapfile.c: In function `setup_swap_info':
| mm/swapfile.c:2291:47: error: array subscript -1 is below array bounds
|  of `struct plist_node[]' [-Werror=array-bounds]
|  2291 |                                 p->avail_lists[i].prio = 1;
|       |                                 ~~~~~~~~~~~~~~^~~
| In file included from mm/swapfile.c:16:
| ./include/linux/swap.h:292:27: note: while referencing `avail_lists'
|   292 |         struct plist_node avail_lists[]; /*
|       |                           ^~~~~~~~~~~

This is due to the compiler detecting that the mask in
node_states[__state] could theoretically be zero, which would lead to
first_node() returning -1 through find_first_bit.

I believe that the warning/error is legitimate.  I first tried adding a
test to check that the node mask is not emtpy, since a similar test exists
in the case where MAX_NUMNODES == 1.

However, adding the if statement causes other warnings to appear in
for_each_cpu_node_but, because it introduces a dangling else ambiguity.
And unfortunately, GCC is not smart enough to detect that the added test
makes the case where (node) == -1 impossible, so it still complains with
the same message.

This is why I settled on replacing that with a harmless, but relatively
useless (node) >= 0 test.  Based on the warning for the dangling else, I
also decided to fix the case where MAX_NUMNODES == 1 by moving the
condition inside the for loop.  It will still only be tested once.  This
ensures that the meaning of an else following for_each_node_mask or
derivatives would not silently have a different meaning depending on the
configuration.

Link: https://lkml.kernel.org/r/20220414150855.2407137-3-dinechin@redhat.com
Signed-off-by: Christophe de Dinechin <christophe@dinechin.org>
Signed-off-by: Christophe de Dinechin <dinechin@redhat.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Ben Segall <bsegall@google.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/nodemask.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 567c3ddba2c4..c6199dbe2591 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -375,14 +375,13 @@ static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
 }
 
 #if MAX_NUMNODES > 1
-#define for_each_node_mask(node, mask)			\
-	for ((node) = first_node(mask);			\
-		(node) < MAX_NUMNODES;			\
-		(node) = next_node((node), (mask)))
+#define for_each_node_mask(node, mask)				    \
+	for ((node) = first_node(mask);				    \
+	     (node >= 0) && (node) < MAX_NUMNODES;		    \
+	     (node) = next_node((node), (mask)))
 #else /* MAX_NUMNODES == 1 */
-#define for_each_node_mask(node, mask)			\
-	if (!nodes_empty(mask))				\
-		for ((node) = 0; (node) < 1; (node)++)
+#define for_each_node_mask(node, mask)                                  \
+	for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++)
 #endif /* MAX_NUMNODES */
 
 /*
-- 
cgit v1.2.3


From 991d8d8142cad94f9c5c05db25e67fa83d6f772a Mon Sep 17 00:00:00 2001
From: Dietmar Eggemann <dietmar.eggemann@arm.com>
Date: Fri, 13 May 2022 11:34:33 +0200
Subject: topology: Remove unused cpu_cluster_mask()

default_topology[] uses cpu_clustergroup_mask() for the CLS level
(guarded by CONFIG_SCHED_CLUSTER) which is currently provided by x86
(arch/x86/kernel/smpboot.c) and arm64 (drivers/base/arch_topology.c).

Fixes: 778c558f49a2c ("sched: Add cluster scheduler level in core and
related Kconfig for ARM64")

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Barry Song <baohua@kernel.org>
Link: https://lore.kernel.org/r/20220513093433.425163-1-dietmar.eggemann@arm.com
---
 include/linux/topology.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/topology.h b/include/linux/topology.h
index f19bc3626297..4564faafd0e1 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -240,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu)
 }
 #endif
 
-#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask)
-static inline const struct cpumask *cpu_cluster_mask(int cpu)
-{
-	return topology_cluster_cpumask(cpu);
-}
-#endif
-
 static inline const struct cpumask *cpu_cpu_mask(int cpu)
 {
 	return cpumask_of_node(cpu_to_node(cpu));
-- 
cgit v1.2.3


From 5cebb40bc9554aafcc492431181f43c6231b0459 Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Wed, 18 May 2022 22:37:56 +0530
Subject: net: macb: Fix PTP one step sync support

PTP one step sync packets cannot have CSUM padding and insertion in
SW since time stamp is inserted on the fly by HW.
In addition, ptp4l version 3.0 and above report an error when skb
timestamps are reported for packets that not processed for TX TS
after transmission.
Add a helper to identify PTP one step sync and fix the above two
errors. Add a common mask for PTP header flag field "twoStepflag".
Also reset ptp OSS bit when one step is not selected.

Fixes: ab91f0a9b5f4 ("net: macb: Add hardware PTP support")
Fixes: 653e92a9175e ("net: macb: add support for padding and fcs computation")
Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Reviewed-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Reviewed-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/20220518170756.7752-1-harini.katakam@xilinx.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 40 ++++++++++++++++++++++++++++----
 drivers/net/ethernet/cadence/macb_ptp.c  |  4 +++-
 include/linux/ptp_classify.h             |  3 +++
 3 files changed, 42 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 61284baa0496..3a1b5ac48ca5 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -36,6 +36,7 @@
 #include <linux/iopoll.h>
 #include <linux/phy/phy.h>
 #include <linux/pm_runtime.h>
+#include <linux/ptp_classify.h>
 #include <linux/reset.h>
 #include "macb.h"
 
@@ -1124,6 +1125,36 @@ static void macb_tx_error_task(struct work_struct *work)
 	spin_unlock_irqrestore(&bp->lock, flags);
 }
 
+static bool ptp_one_step_sync(struct sk_buff *skb)
+{
+	struct ptp_header *hdr;
+	unsigned int ptp_class;
+	u8 msgtype;
+
+	/* No need to parse packet if PTP TS is not involved */
+	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
+		goto not_oss;
+
+	/* Identify and return whether PTP one step sync is being processed */
+	ptp_class = ptp_classify_raw(skb);
+	if (ptp_class == PTP_CLASS_NONE)
+		goto not_oss;
+
+	hdr = ptp_parse_header(skb, ptp_class);
+	if (!hdr)
+		goto not_oss;
+
+	if (hdr->flag_field[0] & PTP_FLAG_TWOSTEP)
+		goto not_oss;
+
+	msgtype = ptp_get_msgtype(hdr, ptp_class);
+	if (msgtype == PTP_MSGTYPE_SYNC)
+		return true;
+
+not_oss:
+	return false;
+}
+
 static void macb_tx_interrupt(struct macb_queue *queue)
 {
 	unsigned int tail;
@@ -1168,8 +1199,8 @@ static void macb_tx_interrupt(struct macb_queue *queue)
 
 			/* First, update TX stats if needed */
 			if (skb) {
-				if (unlikely(skb_shinfo(skb)->tx_flags &
-					     SKBTX_HW_TSTAMP) &&
+				if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+				    !ptp_one_step_sync(skb) &&
 				    gem_ptp_do_txstamp(queue, skb, desc) == 0) {
 					/* skb now belongs to timestamp buffer
 					 * and will be removed later
@@ -1999,7 +2030,8 @@ static unsigned int macb_tx_map(struct macb *bp,
 			ctrl |= MACB_BF(TX_LSO, lso_ctrl);
 			ctrl |= MACB_BF(TX_TCP_SEQ_SRC, seq_ctrl);
 			if ((bp->dev->features & NETIF_F_HW_CSUM) &&
-			    skb->ip_summed != CHECKSUM_PARTIAL && !lso_ctrl)
+			    skb->ip_summed != CHECKSUM_PARTIAL && !lso_ctrl &&
+			    !ptp_one_step_sync(skb))
 				ctrl |= MACB_BIT(TX_NOCRC);
 		} else
 			/* Only set MSS/MFS on payload descriptors
@@ -2097,7 +2129,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
 
 	if (!(ndev->features & NETIF_F_HW_CSUM) ||
 	    !((*skb)->ip_summed != CHECKSUM_PARTIAL) ||
-	    skb_shinfo(*skb)->gso_size)	/* Not available for GSO */
+	    skb_shinfo(*skb)->gso_size || ptp_one_step_sync(*skb))
 		return 0;
 
 	if (padlen <= 0) {
diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index fb6b27f46b15..9559c16078f9 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -470,8 +470,10 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case HWTSTAMP_TX_ONESTEP_SYNC:
 		if (gem_ptp_set_one_step_sync(bp, 1) != 0)
 			return -ERANGE;
-		fallthrough;
+		tx_bd_control = TSTAMP_ALL_FRAMES;
+		break;
 	case HWTSTAMP_TX_ON:
+		gem_ptp_set_one_step_sync(bp, 0);
 		tx_bd_control = TSTAMP_ALL_FRAMES;
 		break;
 	default:
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index fefa7790dc46..2b6ea36ad162 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -43,6 +43,9 @@
 #define OFF_PTP_SOURCE_UUID	22 /* PTPv1 only */
 #define OFF_PTP_SEQUENCE_ID	30
 
+/* PTP header flag fields */
+#define PTP_FLAG_TWOSTEP	BIT(1)
+
 /* Below defines should actually be removed at some point in time. */
 #define IP6_HLEN	40
 #define UDP_HLEN	8
-- 
cgit v1.2.3


From 827fc630e4c8087df5a8e8ee013b686bd6f13736 Mon Sep 17 00:00:00 2001
From: Muneendra Kumar <muneendra.kumar@broadcom.com>
Date: Thu, 19 May 2022 05:31:07 -0700
Subject: scsi: nvme-fc: Add new routine nvme_fc_io_getuuid()

Add nvme_fc_io_getuuid() to the nvme-fc transport. The routine is invoked
by the FC LLDD on a per-I/O request basis.  The routine translates from the
FC-specific request structure to the bio and the cgroup structure in order
to obtain the FC appid stored in the cgroup structure. If a value is not
set or a bio is not found, a NULL appid (aka uuid) will be returned to the
LLDD.

Link: https://lore.kernel.org/r/20220519123110.17361-2-jsmart2021@gmail.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Muneendra Kumar <muneendra.kumar@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/nvme/host/fc.c         | 18 ++++++++++++++++++
 include/linux/nvme-fc-driver.h | 14 ++++++++++++++
 2 files changed, 32 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 080f85f4105f..05f9da251758 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1899,6 +1899,24 @@ nvme_fc_ctrl_ioerr_work(struct work_struct *work)
 	nvme_fc_error_recovery(ctrl, "transport detected io error");
 }
 
+/*
+ * nvme_fc_io_getuuid - Routine called to get the appid field
+ * associated with request by the lldd
+ * @req:IO request from nvme fc to driver
+ * Returns: UUID if there is an appid associated with VM or
+ * NULL if the user/libvirt has not set the appid to VM
+ */
+char *nvme_fc_io_getuuid(struct nvmefc_fcp_req *req)
+{
+	struct nvme_fc_fcp_op *op = fcp_req_to_fcp_op(req);
+	struct request *rq = op->rq;
+
+	if (!IS_ENABLED(CONFIG_BLK_CGROUP_FC_APPID) || !rq->bio)
+		return NULL;
+	return blkcg_get_fc_appid(rq->bio);
+}
+EXPORT_SYMBOL_GPL(nvme_fc_io_getuuid);
+
 static void
 nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 {
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 5358a5facdee..fa092b9be2fd 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -564,6 +564,15 @@ int nvme_fc_rcv_ls_req(struct nvme_fc_remote_port *remoteport,
 			void *lsreqbuf, u32 lsreqbuf_len);
 
 
+/*
+ * Routine called to get the appid field associated with request by the lldd
+ *
+ * If the return value is NULL : the user/libvirt has not set the appid to VM
+ * If the return value is non-zero: Returns the appid associated with VM
+ *
+ * @req: IO request from nvme fc to driver
+ */
+char *nvme_fc_io_getuuid(struct nvmefc_fcp_req *req);
 
 /*
  * ***************  LLDD FC-NVME Target/Subsystem API ***************
@@ -1048,5 +1057,10 @@ int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport,
 
 void nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *tgtport,
 			struct nvmefc_tgt_fcp_req *fcpreq);
+/*
+ * add a define, visible to the compiler, that indicates support
+ * for feature. Allows for conditional compilation in LLDDs.
+ */
+#define NVME_FC_FEAT_UUID	0x0001
 
 #endif /* _NVME_FC_DRIVER_H */
-- 
cgit v1.2.3


From 59df85d5fbae17175c391d89ad03e9e7a01b7a55 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 1 Mar 2022 19:56:53 -0500
Subject: linux/mount.h: trim includes

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/mount.h | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mount.h b/include/linux/mount.h
index 7f18a7555dff..b3b149dcbf96 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -11,17 +11,15 @@
 #define _LINUX_MOUNT_H
 
 #include <linux/types.h>
-#include <linux/list.h>
-#include <linux/nodemask.h>
-#include <linux/spinlock.h>
-#include <linux/seqlock.h>
-#include <linux/atomic.h>
+#include <asm/barrier.h>
 
 struct super_block;
-struct vfsmount;
 struct dentry;
-struct mnt_namespace;
+struct user_namespace;
+struct file_system_type;
 struct fs_context;
+struct file;
+struct path;
 
 #define MNT_NOSUID	0x01
 #define MNT_NODEV	0x02
@@ -81,9 +79,6 @@ static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt)
 	return smp_load_acquire(&mnt->mnt_userns);
 }
 
-struct file; /* forward dec */
-struct path;
-
 extern int mnt_want_write(struct vfsmount *mnt);
 extern int mnt_want_write_file(struct file *file);
 extern void mnt_drop_write(struct vfsmount *mnt);
@@ -94,12 +89,10 @@ extern struct vfsmount *mnt_clone_internal(const struct path *path);
 extern bool __mnt_is_readonly(struct vfsmount *mnt);
 extern bool mnt_may_suid(struct vfsmount *mnt);
 
-struct path;
 extern struct vfsmount *clone_private_mount(const struct path *path);
 extern int __mnt_want_write(struct vfsmount *);
 extern void __mnt_drop_write(struct vfsmount *);
 
-struct file_system_type;
 extern struct vfsmount *fc_mount(struct fs_context *fc);
 extern struct vfsmount *vfs_create_mount(struct fs_context *fc);
 extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
-- 
cgit v1.2.3


From 70f8d9c5750bbb0ca4ef7e23d6abcb05e6061138 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 2 Mar 2022 17:49:09 -0500
Subject: move mount-related externs from fs.h to mount.h

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/kernel/osf_sys.c |  1 +
 include/linux/fs.h          | 11 -----------
 include/linux/mount.h       | 12 ++++++++++++
 security/smack/smackfs.c    |  1 +
 4 files changed, 14 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 8bbeebb73cf0..d257293401e2 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -36,6 +36,7 @@
 #include <linux/types.h>
 #include <linux/ipc.h>
 #include <linux/namei.h>
+#include <linux/mount.h>
 #include <linux/uio.h>
 #include <linux/vfs.h>
 #include <linux/rcupdate.h>
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbde95387a23..14df7c049b43 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2461,22 +2461,11 @@ struct super_block *sget(struct file_system_type *type,
 
 extern int register_filesystem(struct file_system_type *);
 extern int unregister_filesystem(struct file_system_type *);
-extern struct vfsmount *kern_mount(struct file_system_type *);
-extern void kern_unmount(struct vfsmount *mnt);
-extern int may_umount_tree(struct vfsmount *);
-extern int may_umount(struct vfsmount *);
-extern long do_mount(const char *, const char __user *,
-		     const char *, unsigned long, void *);
-extern struct vfsmount *collect_mounts(const struct path *);
-extern void drop_collected_mounts(struct vfsmount *);
-extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
-			  struct vfsmount *);
 extern int vfs_statfs(const struct path *, struct kstatfs *);
 extern int user_statfs(const char __user *, struct kstatfs *);
 extern int fd_statfs(int, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
-extern bool our_mnt(struct vfsmount *mnt);
 extern __printf(2, 3)
 int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
 extern int super_setup_bdi(struct super_block *sb);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index b3b149dcbf96..55a4abaf6715 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -108,6 +108,18 @@ extern void mark_mounts_for_expiry(struct list_head *mounts);
 extern dev_t name_to_dev_t(const char *name);
 extern bool path_is_mountpoint(const struct path *path);
 
+extern bool our_mnt(struct vfsmount *mnt);
+
+extern struct vfsmount *kern_mount(struct file_system_type *);
+extern void kern_unmount(struct vfsmount *mnt);
+extern int may_umount_tree(struct vfsmount *);
+extern int may_umount(struct vfsmount *);
+extern long do_mount(const char *, const char __user *,
+		     const char *, unsigned long, void *);
+extern struct vfsmount *collect_mounts(const struct path *);
+extern void drop_collected_mounts(struct vfsmount *);
+extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
+			  struct vfsmount *);
 extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);
 
 #endif /* _LINUX_MOUNT_H */
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index 658eab05599e..192f33cc601e 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -23,6 +23,7 @@
 #include <linux/ctype.h>
 #include <linux/audit.h>
 #include <linux/magic.h>
+#include <linux/mount.h>
 #include <linux/fs_context.h>
 #include "smack.h"
 
-- 
cgit v1.2.3


From 3bc253c2e652cf5f12cd8c00d80d8ec55d67d1a7 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Thu, 19 May 2022 16:30:10 -0700
Subject: bpf: Add bpf_skc_to_mptcp_sock_proto

This patch implements a new struct bpf_func_proto, named
bpf_skc_to_mptcp_sock_proto. Define a new bpf_id BTF_SOCK_TYPE_MPTCP,
and a new helper bpf_skc_to_mptcp_sock(), which invokes another new
helper bpf_mptcp_sock_from_subflow() in net/mptcp/bpf.c to get struct
mptcp_sock from a given subflow socket.

v2: Emit BTF type, add func_id checks in verifier.c and bpf_trace.c,
remove build check for CONFIG_BPF_JIT
v5: Drop EXPORT_SYMBOL (Martin)

Co-developed-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220519233016.105670-2-mathew.j.martineau@linux.intel.com
---
 include/linux/bpf.h            |  1 +
 include/linux/btf_ids.h        |  3 ++-
 include/net/mptcp.h            |  6 ++++++
 include/uapi/linux/bpf.h       |  7 +++++++
 kernel/bpf/verifier.c          |  1 +
 kernel/trace/bpf_trace.c       |  2 ++
 net/core/filter.c              | 18 ++++++++++++++++++
 net/mptcp/Makefile             |  2 ++
 net/mptcp/bpf.c                | 21 +++++++++++++++++++++
 scripts/bpf_doc.py             |  2 ++
 tools/include/uapi/linux/bpf.h |  7 +++++++
 11 files changed, 69 insertions(+), 1 deletion(-)
 create mode 100644 net/mptcp/bpf.c

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c107392b0ba7..a3ef078401cf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2231,6 +2231,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_snprintf_proto;
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index bc5d9cc34e4c..335a19092368 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -178,7 +178,8 @@ extern struct btf_id_set name;
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock)			\
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock)
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock)
 
 enum {
 #define BTF_SOCK_TYPE(name, str) name,
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 8b1afd6f5cc4..2ba09de955c7 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -284,4 +284,10 @@ static inline int mptcpv6_init(void) { return 0; }
 static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { }
 #endif
 
+#if defined(CONFIG_MPTCP) && defined(CONFIG_BPF_SYSCALL)
+struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk);
+#else
+static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; }
+#endif
+
 #endif /* __NET_MPTCP_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0210f85131b3..56688bee20d9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5172,6 +5172,12 @@ union bpf_attr {
  * 	Return
  * 		Map value associated to *key* on *cpu*, or **NULL** if no entry
  * 		was found or *cpu* is invalid.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or **NULL** otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5370,6 +5376,7 @@ union bpf_attr {
 	FN(ima_file_hash),		\
 	FN(kptr_xchg),			\
 	FN(map_lookup_percpu_elem),     \
+	FN(skc_to_mptcp_sock),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9b59581026f8..14e8c17d3d8d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -509,6 +509,7 @@ static bool is_ptr_cast_function(enum bpf_func_id func_id)
 		func_id == BPF_FUNC_skc_to_tcp_sock ||
 		func_id == BPF_FUNC_skc_to_tcp6_sock ||
 		func_id == BPF_FUNC_skc_to_udp6_sock ||
+		func_id == BPF_FUNC_skc_to_mptcp_sock ||
 		func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||
 		func_id == BPF_FUNC_skc_to_tcp_request_sock;
 }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7141ca8a1c2d..10b157a6d73e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1705,6 +1705,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_to_udp6_sock_proto;
 	case BPF_FUNC_skc_to_unix_sock:
 		return &bpf_skc_to_unix_sock_proto;
+	case BPF_FUNC_skc_to_mptcp_sock:
+		return &bpf_skc_to_mptcp_sock_proto;
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_tracing_proto;
 	case BPF_FUNC_sk_storage_delete:
diff --git a/net/core/filter.c b/net/core/filter.c
index fe0da529d00f..5af58eb48587 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -78,6 +78,7 @@
 #include <linux/btf_ids.h>
 #include <net/tls.h>
 #include <net/xdp.h>
+#include <net/mptcp.h>
 
 static const struct bpf_func_proto *
 bpf_sk_base_func_proto(enum bpf_func_id func_id);
@@ -11281,6 +11282,20 @@ const struct bpf_func_proto bpf_skc_to_unix_sock_proto = {
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UNIX],
 };
 
+BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk)
+{
+	BTF_TYPE_EMIT(struct mptcp_sock);
+	return (unsigned long)bpf_mptcp_sock_from_subflow(sk);
+}
+
+const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = {
+	.func		= bpf_skc_to_mptcp_sock,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.ret_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_MPTCP],
+};
+
 BPF_CALL_1(bpf_sock_from_file, struct file *, file)
 {
 	return (unsigned long)sock_from_file(file);
@@ -11323,6 +11338,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_skc_to_unix_sock:
 		func = &bpf_skc_to_unix_sock_proto;
 		break;
+	case BPF_FUNC_skc_to_mptcp_sock:
+		func = &bpf_skc_to_mptcp_sock_proto;
+		break;
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
index e54daceac58b..99dddf08ca73 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -10,3 +10,5 @@ obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
 mptcp_crypto_test-objs := crypto_test.o
 mptcp_token_test-objs := token_test.o
 obj-$(CONFIG_MPTCP_KUNIT_TEST) += mptcp_crypto_test.o mptcp_token_test.o
+
+obj-$(CONFIG_BPF_SYSCALL) += bpf.o
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
new file mode 100644
index 000000000000..5a0a84ad94af
--- /dev/null
+++ b/net/mptcp/bpf.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2020, Tessares SA.
+ * Copyright (c) 2022, SUSE.
+ *
+ * Author: Nicolas Rybowski <nicolas.rybowski@tessares.net>
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/bpf.h>
+#include "protocol.h"
+
+struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk)
+{
+	if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk_is_mptcp(sk))
+		return mptcp_sk(mptcp_subflow_ctx(sk)->conn);
+
+	return NULL;
+}
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index 096625242475..d5452f7eb996 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -633,6 +633,7 @@ class PrinterHelpers(Printer):
             'struct socket',
             'struct file',
             'struct bpf_timer',
+            'struct mptcp_sock',
     ]
     known_types = {
             '...',
@@ -682,6 +683,7 @@ class PrinterHelpers(Printer):
             'struct socket',
             'struct file',
             'struct bpf_timer',
+            'struct mptcp_sock',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0210f85131b3..56688bee20d9 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5172,6 +5172,12 @@ union bpf_attr {
  * 	Return
  * 		Map value associated to *key* on *cpu*, or **NULL** if no entry
  * 		was found or *cpu* is invalid.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or **NULL** otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5370,6 +5376,7 @@ union bpf_attr {
 	FN(ima_file_hash),		\
 	FN(kptr_xchg),			\
 	FN(map_lookup_percpu_elem),     \
+	FN(skc_to_mptcp_sock),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From b23316aabffa835ecc516cb81daeef5b9155e8a5 Mon Sep 17 00:00:00 2001
From: Yuntao Wang <ytcoode@gmail.com>
Date: Thu, 19 May 2022 23:06:10 +0800
Subject: selftests/bpf: Add missing trampoline program type to
 trampoline_count test

Currently the trampoline_count test doesn't include any fmod_ret bpf
programs, fix it to make the test cover all possible trampoline program
types.

Since fmod_ret bpf programs can't be attached to __set_task_comm function,
as it's neither whitelisted for error injection nor a security hook, change
it to bpf_modify_return_test.

This patch also does some other cleanups such as removing duplicate code,
dropping inconsistent comments, etc.

Signed-off-by: Yuntao Wang <ytcoode@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20220519150610.601313-1-ytcoode@gmail.com
---
 include/linux/bpf.h                                |   2 +-
 .../selftests/bpf/prog_tests/trampoline_count.c    | 134 ++++++++-------------
 .../selftests/bpf/progs/test_trampoline_count.c    |  16 +--
 3 files changed, 61 insertions(+), 91 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a3ef078401cf..cc4d5e394031 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -724,7 +724,7 @@ struct btf_func_model {
 #define BPF_TRAMP_F_RET_FENTRY_RET	BIT(4)
 
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
- * bytes on x86.  Pick a number to fit into BPF_IMAGE_SIZE / 2
+ * bytes on x86.
  */
 #define BPF_MAX_TRAMP_LINKS 38
 
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index 9c795ee52b7b..b0acbda6dbf5 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -1,126 +1,94 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #define _GNU_SOURCE
-#include <sched.h>
-#include <sys/prctl.h>
 #include <test_progs.h>
 
 #define MAX_TRAMP_PROGS 38
 
 struct inst {
 	struct bpf_object *obj;
-	struct bpf_link   *link_fentry;
-	struct bpf_link   *link_fexit;
+	struct bpf_link   *link;
 };
 
-static int test_task_rename(void)
-{
-	int fd, duration = 0, err;
-	char buf[] = "test_overhead";
-
-	fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
-	if (CHECK(fd < 0, "open /proc", "err %d", errno))
-		return -1;
-	err = write(fd, buf, sizeof(buf));
-	if (err < 0) {
-		CHECK(err < 0, "task rename", "err %d", errno);
-		close(fd);
-		return -1;
-	}
-	close(fd);
-	return 0;
-}
-
-static struct bpf_link *load(struct bpf_object *obj, const char *name)
+static struct bpf_program *load_prog(char *file, char *name, struct inst *inst)
 {
+	struct bpf_object *obj;
 	struct bpf_program *prog;
-	int duration = 0;
+	int err;
+
+	obj = bpf_object__open_file(file, NULL);
+	if (!ASSERT_OK_PTR(obj, "obj_open_file"))
+		return NULL;
+
+	inst->obj = obj;
+
+	err = bpf_object__load(obj);
+	if (!ASSERT_OK(err, "obj_load"))
+		return NULL;
 
 	prog = bpf_object__find_program_by_name(obj, name);
-	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", name))
-		return ERR_PTR(-EINVAL);
-	return bpf_program__attach_trace(prog);
+	if (!ASSERT_OK_PTR(prog, "obj_find_prog"))
+		return NULL;
+
+	return prog;
 }
 
 /* TODO: use different target function to run in concurrent mode */
 void serial_test_trampoline_count(void)
 {
-	const char *fentry_name = "prog1";
-	const char *fexit_name = "prog2";
-	const char *object = "test_trampoline_count.o";
-	struct inst inst[MAX_TRAMP_PROGS] = {};
-	int err, i = 0, duration = 0;
-	struct bpf_object *obj;
+	char *file = "test_trampoline_count.o";
+	char *const progs[] = { "fentry_test", "fmod_ret_test", "fexit_test" };
+	struct inst inst[MAX_TRAMP_PROGS + 1] = {};
+	struct bpf_program *prog;
 	struct bpf_link *link;
-	char comm[16] = {};
+	int prog_fd, err, i;
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
 
 	/* attach 'allowed' trampoline programs */
 	for (i = 0; i < MAX_TRAMP_PROGS; i++) {
-		obj = bpf_object__open_file(object, NULL);
-		if (!ASSERT_OK_PTR(obj, "obj_open_file")) {
-			obj = NULL;
+		prog = load_prog(file, progs[i % ARRAY_SIZE(progs)], &inst[i]);
+		if (!prog)
 			goto cleanup;
-		}
 
-		err = bpf_object__load(obj);
-		if (CHECK(err, "obj_load", "err %d\n", err))
+		link = bpf_program__attach(prog);
+		if (!ASSERT_OK_PTR(link, "attach_prog"))
 			goto cleanup;
-		inst[i].obj = obj;
-		obj = NULL;
-
-		if (rand() % 2) {
-			link = load(inst[i].obj, fentry_name);
-			if (!ASSERT_OK_PTR(link, "attach_prog")) {
-				link = NULL;
-				goto cleanup;
-			}
-			inst[i].link_fentry = link;
-		} else {
-			link = load(inst[i].obj, fexit_name);
-			if (!ASSERT_OK_PTR(link, "attach_prog")) {
-				link = NULL;
-				goto cleanup;
-			}
-			inst[i].link_fexit = link;
-		}
+
+		inst[i].link = link;
 	}
 
 	/* and try 1 extra.. */
-	obj = bpf_object__open_file(object, NULL);
-	if (!ASSERT_OK_PTR(obj, "obj_open_file")) {
-		obj = NULL;
+	prog = load_prog(file, "fmod_ret_test", &inst[i]);
+	if (!prog)
 		goto cleanup;
-	}
-
-	err = bpf_object__load(obj);
-	if (CHECK(err, "obj_load", "err %d\n", err))
-		goto cleanup_extra;
 
 	/* ..that needs to fail */
-	link = load(obj, fentry_name);
-	err = libbpf_get_error(link);
-	if (!ASSERT_ERR_PTR(link, "cannot attach over the limit")) {
-		bpf_link__destroy(link);
-		goto cleanup_extra;
+	link = bpf_program__attach(prog);
+	if (!ASSERT_ERR_PTR(link, "attach_prog")) {
+		inst[i].link = link;
+		goto cleanup;
 	}
 
 	/* with E2BIG error */
-	ASSERT_EQ(err, -E2BIG, "proper error check");
-	ASSERT_EQ(link, NULL, "ptr_is_null");
+	if (!ASSERT_EQ(libbpf_get_error(link), -E2BIG, "E2BIG"))
+		goto cleanup;
+	if (!ASSERT_EQ(link, NULL, "ptr_is_null"))
+		goto cleanup;
 
 	/* and finaly execute the probe */
-	if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L)))
-		goto cleanup_extra;
-	CHECK_FAIL(test_task_rename());
-	CHECK_FAIL(prctl(PR_SET_NAME, comm, 0L, 0L, 0L));
+	prog_fd = bpf_program__fd(prog);
+	if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd"))
+		goto cleanup;
+
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+		goto cleanup;
+
+	ASSERT_EQ(opts.retval & 0xffff, 4, "bpf_modify_return_test.result");
+	ASSERT_EQ(opts.retval >> 16, 1, "bpf_modify_return_test.side_effect");
 
-cleanup_extra:
-	bpf_object__close(obj);
 cleanup:
-	if (i >= MAX_TRAMP_PROGS)
-		i = MAX_TRAMP_PROGS - 1;
 	for (; i >= 0; i--) {
-		bpf_link__destroy(inst[i].link_fentry);
-		bpf_link__destroy(inst[i].link_fexit);
+		bpf_link__destroy(inst[i].link);
 		bpf_object__close(inst[i].obj);
 	}
 }
diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
index f030e469d05b..7765720da7d5 100644
--- a/tools/testing/selftests/bpf/progs/test_trampoline_count.c
+++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
@@ -1,20 +1,22 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <stdbool.h>
-#include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-struct task_struct;
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(fentry_test, int a, int *b)
+{
+	return 0;
+}
 
-SEC("fentry/__set_task_comm")
-int BPF_PROG(prog1, struct task_struct *tsk, const char *buf, bool exec)
+SEC("fmod_ret/bpf_modify_return_test")
+int BPF_PROG(fmod_ret_test, int a, int *b, int ret)
 {
 	return 0;
 }
 
-SEC("fexit/__set_task_comm")
-int BPF_PROG(prog2, struct task_struct *tsk, const char *buf, bool exec)
+SEC("fexit/bpf_modify_return_test")
+int BPF_PROG(fexit_test, int a, int *b, int ret)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From bb12dd42d20f5513a8d1da225232af0a0743fd79 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Date: Fri, 24 Sep 2021 12:56:53 +0200
Subject: powerpc/powermac: constify device_node in of_irq_parse_oldworld()

The of_irq_parse_oldworld() does not modify passed device_node so make
it a pointer to const for safety.  Drop the extern while modifying the
line.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210924105653.46963-2-krzysztof.kozlowski@canonical.com
---
 arch/powerpc/platforms/powermac/pic.c | 2 +-
 include/linux/of_irq.h                | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 71a3f62d9b5f..8c8d8e0a7d13 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -384,7 +384,7 @@ static void __init pmac_pic_probe_oldstyle(void)
 #endif
 }
 
-int of_irq_parse_oldworld(struct device_node *device, int index,
+int of_irq_parse_oldworld(const struct device_node *device, int index,
 			struct of_phandle_args *out_irq)
 {
 	const u32 *ints = NULL;
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index aaf219bd0354..83fccd0c9bba 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -20,12 +20,12 @@ typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *);
 #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 extern unsigned int of_irq_workarounds;
 extern struct device_node *of_irq_dflt_pic;
-extern int of_irq_parse_oldworld(struct device_node *device, int index,
-			       struct of_phandle_args *out_irq);
+int of_irq_parse_oldworld(const struct device_node *device, int index,
+			  struct of_phandle_args *out_irq);
 #else /* CONFIG_PPC32 && CONFIG_PPC_PMAC */
 #define of_irq_workarounds (0)
 #define of_irq_dflt_pic (NULL)
-static inline int of_irq_parse_oldworld(struct device_node *device, int index,
+static inline int of_irq_parse_oldworld(const struct device_node *device, int index,
 				      struct of_phandle_args *out_irq)
 {
 	return -EINVAL;
-- 
cgit v1.2.3


From cd705ea857fdd859a9df09e8adda4cb4c906e8a2 Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Fri, 1 Apr 2022 23:40:29 +0200
Subject: lib: add generic polynomial calculation

Some temperature and voltage sensors use a polynomial to convert between
raw data points and actual temperature or voltage. The polynomial is
usually the result of a curve fitting of the diode characteristic.

The BT1 PVT hwmon driver already uses such a polynonmial calculation
which is rather generic. Move it to lib/ so other drivers can reuse it.

Signed-off-by: Michael Walle <michael@walle.cc>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20220401214032.3738095-2-michael@walle.cc
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 include/linux/polynomial.h |  35 +++++++++++++++
 lib/Kconfig                |   3 ++
 lib/Makefile               |   2 +
 lib/polynomial.c           | 108 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 148 insertions(+)
 create mode 100644 include/linux/polynomial.h
 create mode 100644 lib/polynomial.c

(limited to 'include/linux')

diff --git a/include/linux/polynomial.h b/include/linux/polynomial.h
new file mode 100644
index 000000000000..9e074a0bb6fa
--- /dev/null
+++ b/include/linux/polynomial.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC
+ */
+
+#ifndef _POLYNOMIAL_H
+#define _POLYNOMIAL_H
+
+/*
+ * struct polynomial_term - one term descriptor of a polynomial
+ * @deg: degree of the term.
+ * @coef: multiplication factor of the term.
+ * @divider: distributed divider per each degree.
+ * @divider_leftover: divider leftover, which couldn't be redistributed.
+ */
+struct polynomial_term {
+	unsigned int deg;
+	long coef;
+	long divider;
+	long divider_leftover;
+};
+
+/*
+ * struct polynomial - a polynomial descriptor
+ * @total_divider: total data divider.
+ * @terms: polynomial terms, last term must have degree of 0
+ */
+struct polynomial {
+	long total_divider;
+	struct polynomial_term terms[];
+};
+
+long polynomial_calc(const struct polynomial *poly, long data);
+
+#endif
diff --git a/lib/Kconfig b/lib/Kconfig
index 087e06b4cdfd..6a843639814f 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -737,3 +737,6 @@ config PLDMFW
 
 config ASN1_ENCODER
        tristate
+
+config POLYNOMIAL
+       tristate
diff --git a/lib/Makefile b/lib/Makefile
index 6b9ffc1bd1ee..89fcae891361 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -263,6 +263,8 @@ obj-$(CONFIG_MEMREGION) += memregion.o
 obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
 obj-$(CONFIG_IRQ_POLL) += irq_poll.o
 
+obj-$(CONFIG_POLYNOMIAL) += polynomial.o
+
 # stackdepot.c should not be instrumented or call instrumented functions.
 # Prevent the compiler from calling builtins like memcmp() or bcmp() from this
 # file.
diff --git a/lib/polynomial.c b/lib/polynomial.c
new file mode 100644
index 000000000000..66d383445fec
--- /dev/null
+++ b/lib/polynomial.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Generic polynomial calculation using integer coefficients.
+ *
+ * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC
+ *
+ * Authors:
+ *   Maxim Kaurkin <maxim.kaurkin@baikalelectronics.ru>
+ *   Serge Semin <Sergey.Semin@baikalelectronics.ru>
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/polynomial.h>
+
+/*
+ * Originally this was part of drivers/hwmon/bt1-pvt.c.
+ * There the following conversion is used and should serve as an example here:
+ *
+ * The original translation formulae of the temperature (in degrees of Celsius)
+ * to PVT data and vice-versa are following:
+ *
+ * N = 1.8322e-8*(T^4) + 2.343e-5*(T^3) + 8.7018e-3*(T^2) + 3.9269*(T^1) +
+ *     1.7204e2
+ * T = -1.6743e-11*(N^4) + 8.1542e-8*(N^3) + -1.8201e-4*(N^2) +
+ *     3.1020e-1*(N^1) - 4.838e1
+ *
+ * where T = [-48.380, 147.438]C and N = [0, 1023].
+ *
+ * They must be accordingly altered to be suitable for the integer arithmetics.
+ * The technique is called 'factor redistribution', which just makes sure the
+ * multiplications and divisions are made so to have a result of the operations
+ * within the integer numbers limit. In addition we need to translate the
+ * formulae to accept millidegrees of Celsius. Here what they look like after
+ * the alterations:
+ *
+ * N = (18322e-20*(T^4) + 2343e-13*(T^3) + 87018e-9*(T^2) + 39269e-3*T +
+ *     17204e2) / 1e4
+ * T = -16743e-12*(D^4) + 81542e-9*(D^3) - 182010e-6*(D^2) + 310200e-3*D -
+ *     48380
+ * where T = [-48380, 147438] mC and N = [0, 1023].
+ *
+ * static const struct polynomial poly_temp_to_N = {
+ *         .total_divider = 10000,
+ *         .terms = {
+ *                 {4, 18322, 10000, 10000},
+ *                 {3, 2343, 10000, 10},
+ *                 {2, 87018, 10000, 10},
+ *                 {1, 39269, 1000, 1},
+ *                 {0, 1720400, 1, 1}
+ *         }
+ * };
+ *
+ * static const struct polynomial poly_N_to_temp = {
+ *         .total_divider = 1,
+ *         .terms = {
+ *                 {4, -16743, 1000, 1},
+ *                 {3, 81542, 1000, 1},
+ *                 {2, -182010, 1000, 1},
+ *                 {1, 310200, 1000, 1},
+ *                 {0, -48380, 1, 1}
+ *         }
+ * };
+ */
+
+/**
+ * polynomial_calc - calculate a polynomial using integer arithmetic
+ *
+ * @poly: pointer to the descriptor of the polynomial
+ * @data: input value of the polynimal
+ *
+ * Calculate the result of a polynomial using only integer arithmetic. For
+ * this to work without too much loss of precision the coefficients has to
+ * be altered. This is called factor redistribution.
+ *
+ * Returns the result of the polynomial calculation.
+ */
+long polynomial_calc(const struct polynomial *poly, long data)
+{
+	const struct polynomial_term *term = poly->terms;
+	long total_divider = poly->total_divider ?: 1;
+	long tmp, ret = 0;
+	int deg;
+
+	/*
+	 * Here is the polynomial calculation function, which performs the
+	 * redistributed terms calculations. It's pretty straightforward.
+	 * We walk over each degree term up to the free one, and perform
+	 * the redistributed multiplication of the term coefficient, its
+	 * divider (as for the rationale fraction representation), data
+	 * power and the rational fraction divider leftover. Then all of
+	 * this is collected in a total sum variable, which value is
+	 * normalized by the total divider before being returned.
+	 */
+	do {
+		tmp = term->coef;
+		for (deg = 0; deg < term->deg; ++deg)
+			tmp = mult_frac(tmp, data, term->divider);
+		ret += tmp / term->divider_leftover;
+	} while ((term++)->deg);
+
+	return ret / total_divider;
+}
+EXPORT_SYMBOL_GPL(polynomial_calc);
+
+MODULE_DESCRIPTION("Generic polynomial calculations");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From e5d21072054fbadf41cd56062a3a14e447e8c22b Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 11 May 2022 06:29:59 -0700
Subject: hwmon: Introduce hwmon_device_register_for_thermal

The thermal subsystem registers a hwmon driver without providing
chip or sysfs group information. This is for legacy reasons and
would be difficult to change. At the same time, we want to enforce
that chip information is provided when registering a hwmon device
using hwmon_device_register_with_info(). To enable this, introduce
a special API for use only by the thermal subsystem.

Acked-by: Rafael J . Wysocki <rafael@kernel.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/hwmon.c | 25 +++++++++++++++++++++++++
 include/linux/hwmon.h |  3 +++
 2 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 5915ccfdb7d9..13053a4edc9e 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -916,6 +916,31 @@ hwmon_device_register_with_info(struct device *dev, const char *name,
 }
 EXPORT_SYMBOL_GPL(hwmon_device_register_with_info);
 
+/**
+ * hwmon_device_register_for_thermal - register hwmon device for thermal subsystem
+ * @dev: the parent device
+ * @name: hwmon name attribute
+ * @drvdata: driver data to attach to created device
+ *
+ * The use of this function is restricted. It is provided for legacy reasons
+ * and must only be called from the thermal subsystem.
+ *
+ * hwmon_device_unregister() must be called when the device is no
+ * longer needed.
+ *
+ * Returns the pointer to the new device.
+ */
+struct device *
+hwmon_device_register_for_thermal(struct device *dev, const char *name,
+				  void *drvdata)
+{
+	if (!name || !dev)
+		return ERR_PTR(-EINVAL);
+
+	return __hwmon_device_register(dev, name, drvdata, NULL, NULL);
+}
+EXPORT_SYMBOL_NS_GPL(hwmon_device_register_for_thermal, HWMON_THERMAL);
+
 /**
  * hwmon_device_register - register w/ hwmon
  * @dev: the device to register
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 4efaf06fd2b8..14325f93c6b2 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -450,6 +450,9 @@ hwmon_device_register_with_info(struct device *dev,
 				const struct hwmon_chip_info *info,
 				const struct attribute_group **extra_groups);
 struct device *
+hwmon_device_register_for_thermal(struct device *dev, const char *name,
+				  void *drvdata);
+struct device *
 devm_hwmon_device_register_with_info(struct device *dev,
 				const char *name, void *drvdata,
 				const struct hwmon_chip_info *info,
-- 
cgit v1.2.3


From cc4e7fa549cb69c18bc2ba7209df373ca06749e3 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Sat, 21 May 2022 13:10:53 +0200
Subject: net: qed: fix typos in comments

Spelling mistakes (triple letters) in comments.
Detected with the help of Coccinelle.

Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/qed/qed_fcoe_if.h    | 4 ++--
 include/linux/qed/qed_iscsi_if.h   | 4 ++--
 include/linux/qed/qed_nvmetcp_if.h | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h
index 16752eca5cbd..90e3045b2dcb 100644
--- a/include/linux/qed/qed_fcoe_if.h
+++ b/include/linux/qed/qed_fcoe_if.h
@@ -76,7 +76,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev,
  * @fill_dev_info:	fills FCoE specific information
  *			@param cdev
  *			@param info
- *			@return 0 on sucesss, otherwise error value.
+ *			@return 0 on success, otherwise error value.
  * @register_ops:	register FCoE operations
  *			@param cdev
  *			@param ops - specified using qed_iscsi_cb_ops
@@ -96,7 +96,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev,
  *				connection.
  *			@param p_doorbell - qed will fill the address of the
  *				doorbell.
- *			return 0 on sucesss, otherwise error value.
+ *			return 0 on success, otherwise error value.
  * @release_conn:	release a previously acquired fcoe connection
  *			@param cdev
  *			@param handle - the connection handle.
diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h
index 494cdc3cd840..fbf7973ae9ba 100644
--- a/include/linux/qed/qed_iscsi_if.h
+++ b/include/linux/qed/qed_iscsi_if.h
@@ -133,7 +133,7 @@ struct qed_iscsi_cb_ops {
  * @fill_dev_info:	fills iSCSI specific information
  *			@param cdev
  *			@param info
- *			@return 0 on sucesss, otherwise error value.
+ *			@return 0 on success, otherwise error value.
  * @register_ops:	register iscsi operations
  *			@param cdev
  *			@param ops - specified using qed_iscsi_cb_ops
@@ -152,7 +152,7 @@ struct qed_iscsi_cb_ops {
  *				connection.
  *			@param p_doorbell - qed will fill the address of the
  *				doorbell.
- *			@return 0 on sucesss, otherwise error value.
+ *			@return 0 on success, otherwise error value.
  * @release_conn:	release a previously acquired iscsi connection
  *			@param cdev
  *			@param handle - the connection handle.
diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h
index 1d51df347560..bbfbfba51f37 100644
--- a/include/linux/qed/qed_nvmetcp_if.h
+++ b/include/linux/qed/qed_nvmetcp_if.h
@@ -132,7 +132,7 @@ struct nvmetcp_task_params {
  *				connection.
  *			@param p_doorbell - qed will fill the address of the
  *				doorbell.
- *			@return 0 on sucesss, otherwise error value.
+ *			@return 0 on success, otherwise error value.
  * @release_conn:	release a previously acquired nvmetcp connection
  *			@param cdev
  *			@param handle - the connection handle.
-- 
cgit v1.2.3


From ad25f5cb39872ca14bcbe00816ae65c22fe04b89 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 21 May 2022 08:45:28 +0100
Subject: rxrpc: Fix locking issue

There's a locking issue with the per-netns list of calls in rxrpc.  The
pieces of code that add and remove a call from the list use write_lock()
and the calls procfile uses read_lock() to access it.  However, the timer
callback function may trigger a removal by trying to queue a call for
processing and finding that it's already queued - at which point it has a
spare refcount that it has to do something with.  Unfortunately, if it puts
the call and this reduces the refcount to 0, the call will be removed from
the list.  Unfortunately, since the _bh variants of the locking functions
aren't used, this can deadlock.

================================
WARNING: inconsistent lock state
5.18.0-rc3-build4+ #10 Not tainted
--------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
ksoftirqd/2/25 [HC0[0]:SC1[1]:HE1:SE0] takes:
ffff888107ac4038 (&rxnet->call_lock){+.?.}-{2:2}, at: rxrpc_put_call+0x103/0x14b
{SOFTIRQ-ON-W} state was registered at:
...
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&rxnet->call_lock);
  <Interrupt>
    lock(&rxnet->call_lock);

 *** DEADLOCK ***

1 lock held by ksoftirqd/2/25:
 #0: ffff8881008ffdb0 ((&call->timer)){+.-.}-{0:0}, at: call_timer_fn+0x5/0x23d

Changes
=======
ver #2)
 - Changed to using list_next_rcu() rather than rcu_dereference() directly.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/seq_file.c            | 32 ++++++++++++++++++++++++++++++++
 include/linux/list.h     | 10 ++++++++++
 include/linux/seq_file.h |  4 ++++
 net/rxrpc/ar-internal.h  |  2 +-
 net/rxrpc/call_accept.c  |  6 +++---
 net/rxrpc/call_object.c  | 18 +++++++++---------
 net/rxrpc/net_ns.c       |  2 +-
 net/rxrpc/proc.c         | 10 ++--------
 8 files changed, 62 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/fs/seq_file.c b/fs/seq_file.c
index 7ab8a58c29b6..9456a2032224 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -931,6 +931,38 @@ struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos)
 }
 EXPORT_SYMBOL(seq_list_next);
 
+struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos)
+{
+	struct list_head *lh;
+
+	list_for_each_rcu(lh, head)
+		if (pos-- == 0)
+			return lh;
+
+	return NULL;
+}
+EXPORT_SYMBOL(seq_list_start_rcu);
+
+struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos)
+{
+	if (!pos)
+		return head;
+
+	return seq_list_start_rcu(head, pos - 1);
+}
+EXPORT_SYMBOL(seq_list_start_head_rcu);
+
+struct list_head *seq_list_next_rcu(void *v, struct list_head *head,
+				    loff_t *ppos)
+{
+	struct list_head *lh;
+
+	lh = list_next_rcu((struct list_head *)v);
+	++*ppos;
+	return lh == head ? NULL : lh;
+}
+EXPORT_SYMBOL(seq_list_next_rcu);
+
 /**
  * seq_hlist_start - start an iteration of a hlist
  * @head: the head of the hlist
diff --git a/include/linux/list.h b/include/linux/list.h
index c147eeb2d39d..57e8b559cdf6 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -605,6 +605,16 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_for_each(pos, head) \
 	for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next)
 
+/**
+ * list_for_each_rcu - Iterate over a list in an RCU-safe fashion
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ */
+#define list_for_each_rcu(pos, head)		  \
+	for (pos = rcu_dereference((head)->next); \
+	     !list_is_head(pos, (head)); \
+	     pos = rcu_dereference(pos->next))
+
 /**
  * list_for_each_continue - continue iteration over a list
  * @pos:	the &struct list_head to use as a loop cursor.
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 60820ab511d2..bd023dd38ae6 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -277,6 +277,10 @@ extern struct list_head *seq_list_start_head(struct list_head *head,
 extern struct list_head *seq_list_next(void *v, struct list_head *head,
 		loff_t *ppos);
 
+extern struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos);
+extern struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos);
+extern struct list_head *seq_list_next_rcu(void *v, struct list_head *head, loff_t *ppos);
+
 /*
  * Helpers for iteration over hlist_head-s in seq_files
  */
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 52a23d03d694..dcc0ec0bf3de 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -60,7 +60,7 @@ struct rxrpc_net {
 	struct proc_dir_entry	*proc_net;	/* Subdir in /proc/net */
 	u32			epoch;		/* Local epoch for detecting local-end reset */
 	struct list_head	calls;		/* List of calls active in this namespace */
-	rwlock_t		call_lock;	/* Lock for ->calls */
+	spinlock_t		call_lock;	/* Lock for ->calls */
 	atomic_t		nr_calls;	/* Count of allocated calls */
 
 	atomic_t		nr_conns;
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 8ae59edc2551..99e10eea3732 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -140,9 +140,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 	write_unlock(&rx->call_lock);
 
 	rxnet = call->rxnet;
-	write_lock(&rxnet->call_lock);
-	list_add_tail(&call->link, &rxnet->calls);
-	write_unlock(&rxnet->call_lock);
+	spin_lock_bh(&rxnet->call_lock);
+	list_add_tail_rcu(&call->link, &rxnet->calls);
+	spin_unlock_bh(&rxnet->call_lock);
 
 	b->call_backlog[call_head] = call;
 	smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1));
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 8764a4f19c03..84d0a4109645 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -337,9 +337,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	write_unlock(&rx->call_lock);
 
 	rxnet = call->rxnet;
-	write_lock(&rxnet->call_lock);
-	list_add_tail(&call->link, &rxnet->calls);
-	write_unlock(&rxnet->call_lock);
+	spin_lock_bh(&rxnet->call_lock);
+	list_add_tail_rcu(&call->link, &rxnet->calls);
+	spin_unlock_bh(&rxnet->call_lock);
 
 	/* From this point on, the call is protected by its own lock. */
 	release_sock(&rx->sk);
@@ -633,9 +633,9 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
 		ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
 
 		if (!list_empty(&call->link)) {
-			write_lock(&rxnet->call_lock);
+			spin_lock_bh(&rxnet->call_lock);
 			list_del_init(&call->link);
-			write_unlock(&rxnet->call_lock);
+			spin_unlock_bh(&rxnet->call_lock);
 		}
 
 		rxrpc_cleanup_call(call);
@@ -707,7 +707,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 	_enter("");
 
 	if (!list_empty(&rxnet->calls)) {
-		write_lock(&rxnet->call_lock);
+		spin_lock_bh(&rxnet->call_lock);
 
 		while (!list_empty(&rxnet->calls)) {
 			call = list_entry(rxnet->calls.next,
@@ -722,12 +722,12 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 			       rxrpc_call_states[call->state],
 			       call->flags, call->events);
 
-			write_unlock(&rxnet->call_lock);
+			spin_unlock_bh(&rxnet->call_lock);
 			cond_resched();
-			write_lock(&rxnet->call_lock);
+			spin_lock_bh(&rxnet->call_lock);
 		}
 
-		write_unlock(&rxnet->call_lock);
+		spin_unlock_bh(&rxnet->call_lock);
 	}
 
 	atomic_dec(&rxnet->nr_calls);
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 34f389975a7d..bb4c25d6df64 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -50,7 +50,7 @@ static __net_init int rxrpc_init_net(struct net *net)
 	rxnet->epoch |= RXRPC_RANDOM_EPOCH;
 
 	INIT_LIST_HEAD(&rxnet->calls);
-	rwlock_init(&rxnet->call_lock);
+	spin_lock_init(&rxnet->call_lock);
 	atomic_set(&rxnet->nr_calls, 1);
 
 	atomic_set(&rxnet->nr_conns, 1);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 8967201fd8e5..245418943e01 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -26,29 +26,23 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
  */
 static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos)
 	__acquires(rcu)
-	__acquires(rxnet->call_lock)
 {
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
 
 	rcu_read_lock();
-	read_lock(&rxnet->call_lock);
-	return seq_list_start_head(&rxnet->calls, *_pos);
+	return seq_list_start_head_rcu(&rxnet->calls, *_pos);
 }
 
 static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
 
-	return seq_list_next(v, &rxnet->calls, pos);
+	return seq_list_next_rcu(v, &rxnet->calls, pos);
 }
 
 static void rxrpc_call_seq_stop(struct seq_file *seq, void *v)
-	__releases(rxnet->call_lock)
 	__releases(rcu)
 {
-	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
-
-	read_unlock(&rxnet->call_lock);
 	rcu_read_unlock();
 }
 
-- 
cgit v1.2.3


From c304eddcecfe2513ff98ce3ae97d1c196d82ba08 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 19 May 2022 13:20:54 -0700
Subject: net: wrap the wireless pointers in struct net_device in an ifdef

Most protocol-specific pointers in struct net_device are under
a respective ifdef. Wireless is the notable exception. Since
there's a sizable number of custom-built kernels for datacenter
workloads which don't build wireless it seems reasonable to
ifdefy those pointers as well.

While at it move IPv4 and IPv6 pointers up, those are special
for obvious reasons.

Acked-by: Johannes Berg <johannes@sipsolutions.net>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org> # ieee802154
Acked-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h       |  8 ++++++--
 include/net/cfg80211.h          |  2 ++
 include/net/cfg802154.h         |  2 ++
 net/batman-adv/hard-interface.c |  2 ++
 net/core/net-sysfs.c            | 21 +++++++++++++--------
 5 files changed, 25 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1ce91cb8074a..f615a66c89e9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2119,6 +2119,8 @@ struct net_device {
 
 	/* Protocol-specific pointers */
 
+	struct in_device __rcu	*ip_ptr;
+	struct inet6_dev __rcu	*ip6_ptr;
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	struct vlan_info __rcu	*vlan_info;
 #endif
@@ -2131,16 +2133,18 @@ struct net_device {
 #if IS_ENABLED(CONFIG_ATALK)
 	void 			*atalk_ptr;
 #endif
-	struct in_device __rcu	*ip_ptr;
 #if IS_ENABLED(CONFIG_DECNET)
 	struct dn_dev __rcu     *dn_ptr;
 #endif
-	struct inet6_dev __rcu	*ip6_ptr;
 #if IS_ENABLED(CONFIG_AX25)
 	void			*ax25_ptr;
 #endif
+#if IS_ENABLED(CONFIG_CFG80211)
 	struct wireless_dev	*ieee80211_ptr;
+#endif
+#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN)
 	struct wpan_dev		*ieee802154_ptr;
+#endif
 #if IS_ENABLED(CONFIG_MPLS_ROUTING)
 	struct mpls_dev __rcu	*mpls_ptr;
 #endif
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cc8a9880b9d6..6d02e12e4702 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -8006,7 +8006,9 @@ int cfg80211_register_netdevice(struct net_device *dev);
  */
 static inline void cfg80211_unregister_netdevice(struct net_device *dev)
 {
+#if IS_ENABLED(CONFIG_CFG80211)
 	cfg80211_unregister_wdev(dev->ieee80211_ptr);
+#endif
 }
 
 /**
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 85f9e8417688..d8d8719315fd 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -373,6 +373,7 @@ struct wpan_dev {
 
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
 
+#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN)
 static inline int
 wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 		     const struct ieee802154_addr *daddr,
@@ -383,6 +384,7 @@ wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 
 	return wpan_dev->header_ops->create(skb, dev, daddr, saddr, len);
 }
+#endif
 
 struct wpan_phy *
 wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size);
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 83fb51b6e299..b8f8da7ee3de 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -307,9 +307,11 @@ static bool batadv_is_cfg80211_netdev(struct net_device *net_device)
 	if (!net_device)
 		return false;
 
+#if IS_ENABLED(CONFIG_CFG80211)
 	/* cfg80211 drivers have to set ieee80211_ptr */
 	if (net_device->ieee80211_ptr)
 		return true;
+#endif
 
 	return false;
 }
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 4980c3a50475..e319e242dddf 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -746,7 +746,6 @@ static const struct attribute_group netstat_group = {
 	.attrs  = netstat_attrs,
 };
 
-#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211)
 static struct attribute *wireless_attrs[] = {
 	NULL
 };
@@ -755,7 +754,19 @@ static const struct attribute_group wireless_group = {
 	.name = "wireless",
 	.attrs = wireless_attrs,
 };
+
+static bool wireless_group_needed(struct net_device *ndev)
+{
+#if IS_ENABLED(CONFIG_CFG80211)
+	if (ndev->ieee80211_ptr)
+		return true;
 #endif
+#if IS_ENABLED(CONFIG_WIRELESS_EXT)
+	if (ndev->wireless_handlers)
+		return true;
+#endif
+	return false;
+}
 
 #else /* CONFIG_SYSFS */
 #define net_class_groups	NULL
@@ -1996,14 +2007,8 @@ int netdev_register_kobject(struct net_device *ndev)
 
 	*groups++ = &netstat_group;
 
-#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211)
-	if (ndev->ieee80211_ptr)
-		*groups++ = &wireless_group;
-#if IS_ENABLED(CONFIG_WIRELESS_EXT)
-	else if (ndev->wireless_handlers)
+	if (wireless_group_needed(ndev))
 		*groups++ = &wireless_group;
-#endif
-#endif
 #endif /* CONFIG_SYSFS */
 
 	error = device_add(dev);
-- 
cgit v1.2.3


From 97d6fb1b48f5e6f6d58028593defe8a23641b0b4 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Tue, 12 Apr 2022 12:23:10 +0900
Subject: block: add sync_blockdev_range()

sync_blockdev_range() is to support syncing multiple sectors
with as few block device requests as possible, it is helpful
to make the block device to give full play to its performance.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Andy Wu <Andy.Wu@sony.com>
Reviewed-by: Aoyama Wataru <wataru.aoyama@sony.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Acked-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 block/bdev.c           | 7 +++++++
 include/linux/blkdev.h | 1 +
 2 files changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/block/bdev.c b/block/bdev.c
index 13de871fa816..8b549b071bd6 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -200,6 +200,13 @@ int sync_blockdev(struct block_device *bdev)
 }
 EXPORT_SYMBOL(sync_blockdev);
 
+int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend)
+{
+	return filemap_write_and_wait_range(bdev->bd_inode->i_mapping,
+			lstart, lend);
+}
+EXPORT_SYMBOL(sync_blockdev_range);
+
 /*
  * Write out and wait upon all dirty data associated with this
  * device.   Filesystem data as well as the underlying block
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 60d016138997..331cc6918ee9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1547,6 +1547,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
 int sync_blockdev(struct block_device *bdev);
+int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
 int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
 void printk_all_partitions(void);
-- 
cgit v1.2.3


From 100f59d964050020285f0c8264ce520f0c406c13 Mon Sep 17 00:00:00 2001
From: Mickaël Salaün <mic@digikod.net>
Date: Fri, 6 May 2022 18:10:56 +0200
Subject: LSM: Remove double path_rename hook calls for RENAME_EXCHANGE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to be able to identify a file exchange with renameat2(2) and
RENAME_EXCHANGE, which will be useful for Landlock [1], propagate the
rename flags to LSMs.  This may also improve performance because of the
switch from two set of LSM hook calls to only one, and because LSMs
using this hook may optimize the double check (e.g. only one lock,
reduce the number of path walks).

AppArmor, Landlock and Tomoyo are updated to leverage this change.  This
should not change the current behavior (same check order), except
(different level of) speed boosts.

[1] https://lore.kernel.org/r/20220221212522.320243-1-mic@digikod.net

Cc: James Morris <jmorris@namei.org>
Cc: Kentaro Takeda <takedakn@nttdata.co.jp>
Cc: Serge E. Hallyn <serge@hallyn.com>
Acked-by: John Johansen <john.johansen@canonical.com>
Acked-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Mickaël Salaün <mic@digikod.net>
Link: https://lore.kernel.org/r/20220506161102.525323-7-mic@digikod.net
---
 include/linux/lsm_hook_defs.h |  2 +-
 include/linux/lsm_hooks.h     |  1 +
 security/apparmor/lsm.c       | 30 +++++++++++++++++++++++++-----
 security/landlock/fs.c        | 11 ++++++++++-
 security/security.c           |  9 +--------
 security/tomoyo/tomoyo.c      | 11 ++++++++++-
 6 files changed, 48 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index db924fe379c9..eafa1d2489fd 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -100,7 +100,7 @@ LSM_HOOK(int, 0, path_link, struct dentry *old_dentry,
 	 const struct path *new_dir, struct dentry *new_dentry)
 LSM_HOOK(int, 0, path_rename, const struct path *old_dir,
 	 struct dentry *old_dentry, const struct path *new_dir,
-	 struct dentry *new_dentry)
+	 struct dentry *new_dentry, unsigned int flags)
 LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode)
 LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid)
 LSM_HOOK(int, 0, path_chroot, const struct path *path)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 419b5febc3ca..9acf5e368d73 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -358,6 +358,7 @@
  *	@old_dentry contains the dentry structure of the old link.
  *	@new_dir contains the path structure for parent of the new link.
  *	@new_dentry contains the dentry structure of the new link.
+ *	@flags may contain rename options such as RENAME_EXCHANGE.
  *	Return 0 if permission is granted.
  * @path_chmod:
  *	Check for permission to change a mode of the file @path. The new
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 4f0eecb67dde..900bc540656a 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -354,13 +354,16 @@ static int apparmor_path_link(struct dentry *old_dentry, const struct path *new_
 }
 
 static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_dentry,
-				const struct path *new_dir, struct dentry *new_dentry)
+				const struct path *new_dir, struct dentry *new_dentry,
+				const unsigned int flags)
 {
 	struct aa_label *label;
 	int error = 0;
 
 	if (!path_mediated_fs(old_dentry))
 		return 0;
+	if ((flags & RENAME_EXCHANGE) && !path_mediated_fs(new_dentry))
+		return 0;
 
 	label = begin_current_label_crit_section();
 	if (!unconfined(label)) {
@@ -374,10 +377,27 @@ static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_d
 			d_backing_inode(old_dentry)->i_mode
 		};
 
-		error = aa_path_perm(OP_RENAME_SRC, label, &old_path, 0,
-				     MAY_READ | AA_MAY_GETATTR | MAY_WRITE |
-				     AA_MAY_SETATTR | AA_MAY_DELETE,
-				     &cond);
+		if (flags & RENAME_EXCHANGE) {
+			struct path_cond cond_exchange = {
+				i_uid_into_mnt(mnt_userns, d_backing_inode(new_dentry)),
+				d_backing_inode(new_dentry)->i_mode
+			};
+
+			error = aa_path_perm(OP_RENAME_SRC, label, &new_path, 0,
+					     MAY_READ | AA_MAY_GETATTR | MAY_WRITE |
+					     AA_MAY_SETATTR | AA_MAY_DELETE,
+					     &cond_exchange);
+			if (!error)
+				error = aa_path_perm(OP_RENAME_DEST, label, &old_path,
+						     0, MAY_WRITE | AA_MAY_SETATTR |
+						     AA_MAY_CREATE, &cond_exchange);
+		}
+
+		if (!error)
+			error = aa_path_perm(OP_RENAME_SRC, label, &old_path, 0,
+					     MAY_READ | AA_MAY_GETATTR | MAY_WRITE |
+					     AA_MAY_SETATTR | AA_MAY_DELETE,
+					     &cond);
 		if (!error)
 			error = aa_path_perm(OP_RENAME_DEST, label, &new_path,
 					     0, MAY_WRITE | AA_MAY_SETATTR |
diff --git a/security/landlock/fs.c b/security/landlock/fs.c
index 7b7860039a08..30b42cdee52e 100644
--- a/security/landlock/fs.c
+++ b/security/landlock/fs.c
@@ -622,10 +622,12 @@ static int hook_path_link(struct dentry *const old_dentry,
 static int hook_path_rename(const struct path *const old_dir,
 			    struct dentry *const old_dentry,
 			    const struct path *const new_dir,
-			    struct dentry *const new_dentry)
+			    struct dentry *const new_dentry,
+			    const unsigned int flags)
 {
 	const struct landlock_ruleset *const dom =
 		landlock_get_current_domain();
+	u32 exchange_access = 0;
 
 	if (!dom)
 		return 0;
@@ -633,12 +635,19 @@ static int hook_path_rename(const struct path *const old_dir,
 	if (old_dir->dentry != new_dir->dentry)
 		/* Gracefully forbids reparenting. */
 		return -EXDEV;
+	if (flags & RENAME_EXCHANGE) {
+		if (unlikely(d_is_negative(new_dentry)))
+			return -ENOENT;
+		exchange_access =
+			get_mode_access(d_backing_inode(new_dentry)->i_mode);
+	}
 	if (unlikely(d_is_negative(old_dentry)))
 		return -ENOENT;
 	/* RENAME_EXCHANGE is handled because directories are the same. */
 	return check_access_path(
 		dom, old_dir,
 		maybe_remove(old_dentry) | maybe_remove(new_dentry) |
+			exchange_access |
 			get_mode_access(d_backing_inode(old_dentry)->i_mode));
 }
 
diff --git a/security/security.c b/security/security.c
index b7cf5cbfdc67..c9bfc0b70b28 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1197,15 +1197,8 @@ int security_path_rename(const struct path *old_dir, struct dentry *old_dentry,
 		     (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry)))))
 		return 0;
 
-	if (flags & RENAME_EXCHANGE) {
-		int err = call_int_hook(path_rename, 0, new_dir, new_dentry,
-					old_dir, old_dentry);
-		if (err)
-			return err;
-	}
-
 	return call_int_hook(path_rename, 0, old_dir, old_dentry, new_dir,
-				new_dentry);
+				new_dentry, flags);
 }
 EXPORT_SYMBOL(security_path_rename);
 
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index b6a31901f289..71e82d855ebf 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -264,17 +264,26 @@ static int tomoyo_path_link(struct dentry *old_dentry, const struct path *new_di
  * @old_dentry: Pointer to "struct dentry".
  * @new_parent: Pointer to "struct path".
  * @new_dentry: Pointer to "struct dentry".
+ * @flags: Rename options.
  *
  * Returns 0 on success, negative value otherwise.
  */
 static int tomoyo_path_rename(const struct path *old_parent,
 			      struct dentry *old_dentry,
 			      const struct path *new_parent,
-			      struct dentry *new_dentry)
+			      struct dentry *new_dentry,
+			      const unsigned int flags)
 {
 	struct path path1 = { .mnt = old_parent->mnt, .dentry = old_dentry };
 	struct path path2 = { .mnt = new_parent->mnt, .dentry = new_dentry };
 
+	if (flags & RENAME_EXCHANGE) {
+		const int err = tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path2,
+				&path1);
+
+		if (err)
+			return err;
+	}
 	return tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path1, &path2);
 }
 
-- 
cgit v1.2.3


From fb70bf124b051d4ded4ce57511dfec6d3ebf2b43 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 30 Mar 2022 10:30:54 -0400
Subject: NFSD: Instantiate a struct file when creating a regular NFSv4 file

There have been reports of races that cause NFSv4 OPEN(CREATE) to
return an error even though the requested file was created. NFSv4
does not provide a status code for this case.

To mitigate some of these problems, reorganize the NFSv4
OPEN(CREATE) logic to allocate resources before the file is actually
created, and open the new file while the parent directory is still
locked.

Two new APIs are added:

+ Add an API that works like nfsd_file_acquire() but does not open
the underlying file. The OPEN(CREATE) path can use this API when it
already has an open file.

+ Add an API that is kin to dentry_open(). NFSD needs to create a
file and grab an open "struct file *" atomically. The
alloc_empty_file() has to be done before the inode create. If it
fails (for example, because the NFS server has exceeded its
max_files limit), we avoid creating the file and can still return
an error to the NFS client.

BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=382
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: JianHong Yin <jiyin@redhat.com>
---
 fs/nfsd/filecache.c | 51 ++++++++++++++++++++++++++++++++++++++++++++-------
 fs/nfsd/filecache.h |  2 ++
 fs/nfsd/nfs4proc.c  | 43 +++++++++++++++++++++++++++++++++++++++----
 fs/nfsd/nfs4state.c | 16 +++++++++++++---
 fs/nfsd/xdr4.h      |  1 +
 fs/open.c           | 42 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h  |  2 ++
 7 files changed, 143 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 781bef7e42d9..24772f246461 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -897,9 +897,9 @@ nfsd_file_is_cached(struct inode *inode)
 	return ret;
 }
 
-__be32
-nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		  unsigned int may_flags, struct nfsd_file **pnf)
+static __be32
+nfsd_do_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		     unsigned int may_flags, struct nfsd_file **pnf, bool open)
 {
 	__be32	status;
 	struct net *net = SVC_NET(rqstp);
@@ -994,10 +994,13 @@ open_file:
 		nfsd_file_gc();
 
 	nf->nf_mark = nfsd_file_mark_find_or_create(nf);
-	if (nf->nf_mark)
-		status = nfsd_open_verified(rqstp, fhp, may_flags,
-					    &nf->nf_file);
-	else
+	if (nf->nf_mark) {
+		if (open)
+			status = nfsd_open_verified(rqstp, fhp, may_flags,
+						    &nf->nf_file);
+		else
+			status = nfs_ok;
+	} else
 		status = nfserr_jukebox;
 	/*
 	 * If construction failed, or we raced with a call to unlink()
@@ -1017,6 +1020,40 @@ open_file:
 	goto out;
 }
 
+/**
+ * nfsd_file_acquire - Get a struct nfsd_file with an open file
+ * @rqstp: the RPC transaction being executed
+ * @fhp: the NFS filehandle of the file to be opened
+ * @may_flags: NFSD_MAY_ settings for the file
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
+ * network byte order is returned.
+ */
+__be32
+nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **pnf)
+{
+	return nfsd_do_file_acquire(rqstp, fhp, may_flags, pnf, true);
+}
+
+/**
+ * nfsd_file_create - Get a struct nfsd_file, do not open
+ * @rqstp: the RPC transaction being executed
+ * @fhp: the NFS filehandle of the file just created
+ * @may_flags: NFSD_MAY_ settings for the file
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
+ * network byte order is returned.
+ */
+__be32
+nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		 unsigned int may_flags, struct nfsd_file **pnf)
+{
+	return nfsd_do_file_acquire(rqstp, fhp, may_flags, pnf, false);
+}
+
 /*
  * Note that fields may be added, removed or reordered in the future. Programs
  * scraping this file for info should test the labels to ensure they're
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 435ceab27897..1da0c79a5580 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -59,5 +59,7 @@ void nfsd_file_close_inode_sync(struct inode *inode);
 bool nfsd_file_is_cached(struct inode *inode);
 __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **nfp);
+__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **nfp);
 int	nfsd_file_cache_stats_open(struct inode *, struct file *);
 #endif /* _FS_NFSD_FILECACHE_H */
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 99c0485a29e9..28bae84d7809 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -243,6 +243,37 @@ static inline bool nfsd4_create_is_exclusive(int createmode)
 		createmode == NFS4_CREATE_EXCLUSIVE4_1;
 }
 
+static __be32
+nfsd4_vfs_create(struct svc_fh *fhp, struct dentry *child,
+		 struct nfsd4_open *open)
+{
+	struct file *filp;
+	struct path path;
+	int oflags;
+
+	oflags = O_CREAT | O_LARGEFILE;
+	switch (open->op_share_access & NFS4_SHARE_ACCESS_BOTH) {
+	case NFS4_SHARE_ACCESS_WRITE:
+		oflags |= O_WRONLY;
+		break;
+	case NFS4_SHARE_ACCESS_BOTH:
+		oflags |= O_RDWR;
+		break;
+	default:
+		oflags |= O_RDONLY;
+	}
+
+	path.mnt = fhp->fh_export->ex_path.mnt;
+	path.dentry = child;
+	filp = dentry_create(&path, oflags, open->op_iattr.ia_mode,
+			     current_cred());
+	if (IS_ERR(filp))
+		return nfserrno(PTR_ERR(filp));
+
+	open->op_filp = filp;
+	return nfs_ok;
+}
+
 /*
  * Implement NFSv4's unchecked, guarded, and exclusive create
  * semantics for regular files. Open state for this new file is
@@ -355,11 +386,9 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (!IS_POSIXACL(inode))
 		iap->ia_mode &= ~current_umask();
 
-	host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true);
-	if (host_err < 0) {
-		status = nfserrno(host_err);
+	status = nfsd4_vfs_create(fhp, child, open);
+	if (status != nfs_ok)
 		goto out;
-	}
 	open->op_created = true;
 
 	/* A newly created file already has a file size of zero. */
@@ -517,6 +546,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		(int)open->op_fnamelen, open->op_fname,
 		open->op_openowner);
 
+	open->op_filp = NULL;
+
 	/* This check required by spec. */
 	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
 		return nfserr_inval;
@@ -613,6 +644,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (reclaim && !status)
 		nn->somebody_reclaimed = true;
 out:
+	if (open->op_filp) {
+		fput(open->op_filp);
+		open->op_filp = NULL;
+	}
 	if (resfh && resfh != &cstate->current_fh) {
 		fh_dup2(&cstate->current_fh, resfh);
 		fh_put(resfh);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 231e5c19cdb7..131102cba06b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5093,9 +5093,19 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
 
 	if (!fp->fi_fds[oflag]) {
 		spin_unlock(&fp->fi_lock);
-		status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
-		if (status)
-			goto out_put_access;
+
+		if (!open->op_filp) {
+			status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
+			if (status != nfs_ok)
+				goto out_put_access;
+		} else {
+			status = nfsd_file_create(rqstp, cur_fh, access, &nf);
+			if (status != nfs_ok)
+				goto out_put_access;
+			nf->nf_file = open->op_filp;
+			open->op_filp = NULL;
+		}
+
 		spin_lock(&fp->fi_lock);
 		if (!fp->fi_fds[oflag]) {
 			fp->fi_fds[oflag] = nf;
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 846ab6df9d48..7b744011f2d3 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -273,6 +273,7 @@ struct nfsd4_open {
 	bool		op_truncate;        /* used during processing */
 	bool		op_created;         /* used during processing */
 	struct nfs4_openowner *op_openowner; /* used during processing */
+	struct file	*op_filp;           /* used during processing */
 	struct nfs4_file *op_file;          /* used during processing */
 	struct nfs4_ol_stateid *op_stp;	    /* used during processing */
 	struct nfs4_clnt_odstate *op_odstate; /* used during processing */
diff --git a/fs/open.c b/fs/open.c
index 1315253e0247..117355ae6bd5 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -981,6 +981,48 @@ struct file *dentry_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(dentry_open);
 
+/**
+ * dentry_create - Create and open a file
+ * @path: path to create
+ * @flags: O_ flags
+ * @mode: mode bits for new file
+ * @cred: credentials to use
+ *
+ * Caller must hold the parent directory's lock, and have prepared
+ * a negative dentry, placed in @path->dentry, for the new file.
+ *
+ * Caller sets @path->mnt to the vfsmount of the filesystem where
+ * the new file is to be created. The parent directory and the
+ * negative dentry must reside on the same filesystem instance.
+ *
+ * On success, returns a "struct file *". Otherwise a ERR_PTR
+ * is returned.
+ */
+struct file *dentry_create(const struct path *path, int flags, umode_t mode,
+			   const struct cred *cred)
+{
+	struct file *f;
+	int error;
+
+	validate_creds(cred);
+	f = alloc_empty_file(flags, cred);
+	if (IS_ERR(f))
+		return f;
+
+	error = vfs_create(mnt_user_ns(path->mnt),
+			   d_inode(path->dentry->d_parent),
+			   path->dentry, mode, true);
+	if (!error)
+		error = vfs_open(path, f);
+
+	if (unlikely(error)) {
+		fput(f);
+		return ERR_PTR(error);
+	}
+	return f;
+}
+EXPORT_SYMBOL(dentry_create);
+
 struct file *open_with_fake_path(const struct path *path, int flags,
 				struct inode *inode, const struct cred *cred)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index aa6c1bbdb8c4..b848355b5e6c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2640,6 +2640,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
 			      name, flags, mode);
 }
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
+extern struct file *dentry_create(const struct path *path, int flags,
+				  umode_t mode, const struct cred *cred);
 extern struct file * open_with_fake_path(const struct path *, int,
 					 struct inode*, const struct cred *);
 static inline struct file *file_clone_open(struct file *file)
-- 
cgit v1.2.3


From bca1a1004615efe141fd78f360ecc48c60bc4ad5 Mon Sep 17 00:00:00 2001
From: Björn Ardö <bjorn.ardo@axis.com>
Date: Thu, 31 Mar 2022 09:01:15 +0200
Subject: mailbox: forward the hrtimer if not queued and under a lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit c7dacf5b0f32957b24ef29df1207dc2cd8307743,
"mailbox: avoid timer start from callback"

The previous commit was reverted since it lead to a race that
caused the hrtimer to not be started at all. The check for
hrtimer_active() in msg_submit() will return true if the
callback function txdone_hrtimer() is currently running. This
function could return HRTIMER_NORESTART and then the timer
will not be restarted, and also msg_submit() will not start
the timer. This will lead to a message actually being submitted
but no timer will start to check for its compleation.

The original fix that added checking hrtimer_active() was added to
avoid a warning with hrtimer_forward. Looking in the kernel
another solution to avoid this warning is to check hrtimer_is_queued()
before calling hrtimer_forward_now() instead. This however requires a
lock so the timer is not started by msg_submit() inbetween this check
and the hrtimer_forward() call.

Fixes: c7dacf5b0f32 ("mailbox: avoid timer start from callback")
Signed-off-by: Björn Ardö <bjorn.ardo@axis.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mailbox.c          | 19 +++++++++++++------
 include/linux/mailbox_controller.h |  1 +
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index 3e7d4b20ab34..4229b9b5da98 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -82,11 +82,11 @@ static void msg_submit(struct mbox_chan *chan)
 exit:
 	spin_unlock_irqrestore(&chan->lock, flags);
 
-	/* kick start the timer immediately to avoid delays */
 	if (!err && (chan->txdone_method & TXDONE_BY_POLL)) {
-		/* but only if not already active */
-		if (!hrtimer_active(&chan->mbox->poll_hrt))
-			hrtimer_start(&chan->mbox->poll_hrt, 0, HRTIMER_MODE_REL);
+		/* kick start the timer immediately to avoid delays */
+		spin_lock_irqsave(&chan->mbox->poll_hrt_lock, flags);
+		hrtimer_start(&chan->mbox->poll_hrt, 0, HRTIMER_MODE_REL);
+		spin_unlock_irqrestore(&chan->mbox->poll_hrt_lock, flags);
 	}
 }
 
@@ -120,20 +120,26 @@ static enum hrtimer_restart txdone_hrtimer(struct hrtimer *hrtimer)
 		container_of(hrtimer, struct mbox_controller, poll_hrt);
 	bool txdone, resched = false;
 	int i;
+	unsigned long flags;
 
 	for (i = 0; i < mbox->num_chans; i++) {
 		struct mbox_chan *chan = &mbox->chans[i];
 
 		if (chan->active_req && chan->cl) {
-			resched = true;
 			txdone = chan->mbox->ops->last_tx_done(chan);
 			if (txdone)
 				tx_tick(chan, 0);
+			else
+				resched = true;
 		}
 	}
 
 	if (resched) {
-		hrtimer_forward_now(hrtimer, ms_to_ktime(mbox->txpoll_period));
+		spin_lock_irqsave(&mbox->poll_hrt_lock, flags);
+		if (!hrtimer_is_queued(hrtimer))
+			hrtimer_forward_now(hrtimer, ms_to_ktime(mbox->txpoll_period));
+		spin_unlock_irqrestore(&mbox->poll_hrt_lock, flags);
+
 		return HRTIMER_RESTART;
 	}
 	return HRTIMER_NORESTART;
@@ -500,6 +506,7 @@ int mbox_controller_register(struct mbox_controller *mbox)
 		hrtimer_init(&mbox->poll_hrt, CLOCK_MONOTONIC,
 			     HRTIMER_MODE_REL);
 		mbox->poll_hrt.function = txdone_hrtimer;
+		spin_lock_init(&mbox->poll_hrt_lock);
 	}
 
 	for (i = 0; i < mbox->num_chans; i++) {
diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h
index 36d6ce673503..6fee33cb52f5 100644
--- a/include/linux/mailbox_controller.h
+++ b/include/linux/mailbox_controller.h
@@ -83,6 +83,7 @@ struct mbox_controller {
 				      const struct of_phandle_args *sp);
 	/* Internal to API */
 	struct hrtimer poll_hrt;
+	spinlock_t poll_hrt_lock;
 	struct list_head node;
 };
 
-- 
cgit v1.2.3


From fe736565efb775620dbcf3c459c1cd80d3e868da Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Fri, 20 May 2022 16:57:53 -0700
Subject: bpf: Introduce bpf_arch_text_invalidate for bpf_prog_pack

Introduce bpf_arch_text_invalidate and use it to fill unused part of the
bpf_prog_pack with illegal instructions when a BPF program is freed.

Fixes: 57631054fae6 ("bpf: Introduce bpf_prog_pack allocator")
Fixes: 33c9805860e5 ("bpf: Introduce bpf_jit_binary_pack_[alloc|finalize|free]")
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220520235758.1858153-4-song@kernel.org
---
 arch/x86/net/bpf_jit_comp.c | 5 +++++
 include/linux/bpf.h         | 1 +
 kernel/bpf/core.c           | 8 ++++++++
 3 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a2b6d197c226..f298b18a9a3d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -228,6 +228,11 @@ static void jit_fill_hole(void *area, unsigned int size)
 	memset(area, 0xcc, size);
 }
 
+int bpf_arch_text_invalidate(void *dst, size_t len)
+{
+	return IS_ERR_OR_NULL(text_poke_set(dst, 0xcc, len));
+}
+
 struct jit_context {
 	int cleanup_addr; /* Epilogue code offset */
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cc4d5e394031..a9b1875212f6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2365,6 +2365,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
 void *bpf_arch_text_copy(void *dst, void *src, size_t len);
+int bpf_arch_text_invalidate(void *dst, size_t len);
 
 struct btf_id_set;
 bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2d0c9d4696ad..cacd8684c3c4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -968,6 +968,9 @@ static void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 	nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size);
 	pos = ((unsigned long)hdr - (unsigned long)pack_ptr) >> BPF_PROG_CHUNK_SHIFT;
 
+	WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size),
+		  "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n");
+
 	bitmap_clear(pack->bitmap, pos, nbits);
 	if (bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0,
 				       bpf_prog_chunk_count(), 0) == 0) {
@@ -2740,6 +2743,11 @@ void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len)
 	return ERR_PTR(-ENOTSUPP);
 }
 
+int __weak bpf_arch_text_invalidate(void *dst, size_t len)
+{
+	return -ENOTSUPP;
+}
+
 DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 EXPORT_SYMBOL(bpf_stats_enabled_key);
 
-- 
cgit v1.2.3


From 97e03f521050c092919591e668107b3d69c5f426 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Mon, 23 May 2022 14:07:07 -0700
Subject: bpf: Add verifier support for dynptrs

This patch adds the bulk of the verifier work for supporting dynamic
pointers (dynptrs) in bpf.

A bpf_dynptr is opaque to the bpf program. It is a 16-byte structure
defined internally as:

struct bpf_dynptr_kern {
    void *data;
    u32 size;
    u32 offset;
} __aligned(8);

The upper 8 bits of *size* is reserved (it contains extra metadata about
read-only status and dynptr type). Consequently, a dynptr only supports
memory less than 16 MB.

There are different types of dynptrs (eg malloc, ringbuf, ...). In this
patchset, the most basic one, dynptrs to a bpf program's local memory,
is added. For now only local memory that is of reg type PTR_TO_MAP_VALUE
is supported.

In the verifier, dynptr state information will be tracked in stack
slots. When the program passes in an uninitialized dynptr
(ARG_PTR_TO_DYNPTR | MEM_UNINIT), the stack slots corresponding
to the frame pointer where the dynptr resides at are marked
STACK_DYNPTR. For helper functions that take in initialized dynptrs (eg
bpf_dynptr_read + bpf_dynptr_write which are added later in this
patchset), the verifier enforces that the dynptr has been initialized
properly by checking that their corresponding stack slots have been
marked as STACK_DYNPTR.

The 6th patch in this patchset adds test cases that the verifier should
successfully reject, such as for example attempting to use a dynptr
after doing a direct write into it inside the bpf program.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/bpf/20220523210712.3641569-2-joannelkoong@gmail.com
---
 include/linux/bpf.h            |  28 ++++++
 include/linux/bpf_verifier.h   |  18 ++++
 include/uapi/linux/bpf.h       |   5 ++
 kernel/bpf/verifier.c          | 188 ++++++++++++++++++++++++++++++++++++++++-
 scripts/bpf_doc.py             |   2 +
 tools/include/uapi/linux/bpf.h |   5 ++
 6 files changed, 243 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a9b1875212f6..b26c8176b9e0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -392,10 +392,15 @@ enum bpf_type_flag {
 
 	MEM_UNINIT		= BIT(7 + BPF_BASE_TYPE_BITS),
 
+	/* DYNPTR points to memory local to the bpf program. */
+	DYNPTR_TYPE_LOCAL	= BIT(8 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
 
+#define DYNPTR_TYPE_FLAG_MASK	DYNPTR_TYPE_LOCAL
+
 /* Max number of base types. */
 #define BPF_BASE_TYPE_LIMIT	(1UL << BPF_BASE_TYPE_BITS)
 
@@ -438,6 +443,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
 	ARG_PTR_TO_TIMER,	/* pointer to bpf_timer */
 	ARG_PTR_TO_KPTR,	/* pointer to referenced kptr */
+	ARG_PTR_TO_DYNPTR,      /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */
 	__BPF_ARG_TYPE_MAX,
 
 	/* Extended arg_types. */
@@ -2376,4 +2382,26 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 **bin_buf, u32 num_args);
 void bpf_bprintf_cleanup(void);
 
+/* the implementation of the opaque uapi struct bpf_dynptr */
+struct bpf_dynptr_kern {
+	void *data;
+	/* Size represents the number of usable bytes of dynptr data.
+	 * If for example the offset is at 4 for a local dynptr whose data is
+	 * of type u64, the number of usable bytes is 4.
+	 *
+	 * The upper 8 bits are reserved. It is as follows:
+	 * Bits 0 - 23 = size
+	 * Bits 24 - 30 = dynptr type
+	 * Bit 31 = whether dynptr is read-only
+	 */
+	u32 size;
+	u32 offset;
+} __aligned(8);
+
+enum bpf_dynptr_type {
+	BPF_DYNPTR_TYPE_INVALID,
+	/* Points to memory that is local to the bpf program */
+	BPF_DYNPTR_TYPE_LOCAL,
+};
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 1f1e7f2ea967..af5b2135215e 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -72,6 +72,18 @@ struct bpf_reg_state {
 
 		u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */
 
+		/* For dynptr stack slots */
+		struct {
+			enum bpf_dynptr_type type;
+			/* A dynptr is 16 bytes so it takes up 2 stack slots.
+			 * We need to track which slot is the first slot
+			 * to protect against cases where the user may try to
+			 * pass in an address starting at the second slot of the
+			 * dynptr.
+			 */
+			bool first_slot;
+		} dynptr;
+
 		/* Max size from any of the above. */
 		struct {
 			unsigned long raw1;
@@ -174,9 +186,15 @@ enum bpf_stack_slot_type {
 	STACK_SPILL,      /* register spilled into stack */
 	STACK_MISC,	  /* BPF program wrote some data into this slot */
 	STACK_ZERO,	  /* BPF program wrote constant zero */
+	/* A dynptr is stored in this stack slot. The type of dynptr
+	 * is stored in bpf_stack_state->spilled_ptr.dynptr.type
+	 */
+	STACK_DYNPTR,
 };
 
 #define BPF_REG_SIZE 8	/* size of eBPF register in bytes */
+#define BPF_DYNPTR_SIZE		sizeof(struct bpf_dynptr_kern)
+#define BPF_DYNPTR_NR_SLOTS		(BPF_DYNPTR_SIZE / BPF_REG_SIZE)
 
 struct bpf_stack_state {
 	struct bpf_reg_state spilled_ptr;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 56688bee20d9..610944cb3389 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6528,6 +6528,11 @@ struct bpf_timer {
 	__u64 :64;
 } __attribute__((aligned(8)));
 
+struct bpf_dynptr {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
 struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 45153cbc2bd6..1fd0b81c3fec 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -259,6 +259,7 @@ struct bpf_call_arg_meta {
 	u32 ret_btf_id;
 	u32 subprogno;
 	struct bpf_map_value_off_desc *kptr_off_desc;
+	u8 uninit_dynptr_regno;
 };
 
 struct btf *btf_vmlinux;
@@ -581,6 +582,7 @@ static char slot_type_char[] = {
 	[STACK_SPILL]	= 'r',
 	[STACK_MISC]	= 'm',
 	[STACK_ZERO]	= '0',
+	[STACK_DYNPTR]	= 'd',
 };
 
 static void print_liveness(struct bpf_verifier_env *env,
@@ -596,6 +598,25 @@ static void print_liveness(struct bpf_verifier_env *env,
 		verbose(env, "D");
 }
 
+static int get_spi(s32 off)
+{
+	return (-off - 1) / BPF_REG_SIZE;
+}
+
+static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots)
+{
+	int allocated_slots = state->allocated_stack / BPF_REG_SIZE;
+
+	/* We need to check that slots between [spi - nr_slots + 1, spi] are
+	 * within [0, allocated_stack).
+	 *
+	 * Please note that the spi grows downwards. For example, a dynptr
+	 * takes the size of two stack slots; the first slot will be at
+	 * spi and the second slot will be at spi - 1.
+	 */
+	return spi - nr_slots + 1 >= 0 && spi < allocated_slots;
+}
+
 static struct bpf_func_state *func(struct bpf_verifier_env *env,
 				   const struct bpf_reg_state *reg)
 {
@@ -647,6 +668,108 @@ static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
 	env->scratched_stack_slots = ~0ULL;
 }
 
+static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
+{
+	switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
+	case DYNPTR_TYPE_LOCAL:
+		return BPF_DYNPTR_TYPE_LOCAL;
+	default:
+		return BPF_DYNPTR_TYPE_INVALID;
+	}
+}
+
+static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+				   enum bpf_arg_type arg_type, int insn_idx)
+{
+	struct bpf_func_state *state = func(env, reg);
+	enum bpf_dynptr_type type;
+	int spi, i;
+
+	spi = get_spi(reg->off);
+
+	if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS))
+		return -EINVAL;
+
+	for (i = 0; i < BPF_REG_SIZE; i++) {
+		state->stack[spi].slot_type[i] = STACK_DYNPTR;
+		state->stack[spi - 1].slot_type[i] = STACK_DYNPTR;
+	}
+
+	type = arg_to_dynptr_type(arg_type);
+	if (type == BPF_DYNPTR_TYPE_INVALID)
+		return -EINVAL;
+
+	state->stack[spi].spilled_ptr.dynptr.first_slot = true;
+	state->stack[spi].spilled_ptr.dynptr.type = type;
+	state->stack[spi - 1].spilled_ptr.dynptr.type = type;
+
+	return 0;
+}
+
+static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi, i;
+
+	spi = get_spi(reg->off);
+
+	if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS))
+		return -EINVAL;
+
+	for (i = 0; i < BPF_REG_SIZE; i++) {
+		state->stack[spi].slot_type[i] = STACK_INVALID;
+		state->stack[spi - 1].slot_type[i] = STACK_INVALID;
+	}
+
+	state->stack[spi].spilled_ptr.dynptr.first_slot = false;
+	state->stack[spi].spilled_ptr.dynptr.type = 0;
+	state->stack[spi - 1].spilled_ptr.dynptr.type = 0;
+
+	return 0;
+}
+
+static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi = get_spi(reg->off);
+	int i;
+
+	if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS))
+		return true;
+
+	for (i = 0; i < BPF_REG_SIZE; i++) {
+		if (state->stack[spi].slot_type[i] == STACK_DYNPTR ||
+		    state->stack[spi - 1].slot_type[i] == STACK_DYNPTR)
+			return false;
+	}
+
+	return true;
+}
+
+static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+				     enum bpf_arg_type arg_type)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi = get_spi(reg->off);
+	int i;
+
+	if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) ||
+	    !state->stack[spi].spilled_ptr.dynptr.first_slot)
+		return false;
+
+	for (i = 0; i < BPF_REG_SIZE; i++) {
+		if (state->stack[spi].slot_type[i] != STACK_DYNPTR ||
+		    state->stack[spi - 1].slot_type[i] != STACK_DYNPTR)
+			return false;
+	}
+
+	/* ARG_PTR_TO_DYNPTR takes any type of dynptr */
+	if (arg_type == ARG_PTR_TO_DYNPTR)
+		return true;
+
+	return state->stack[spi].spilled_ptr.dynptr.type == arg_to_dynptr_type(arg_type);
+}
+
 /* The reg state of a pointer or a bounded scalar was saved when
  * it was spilled to the stack.
  */
@@ -5400,6 +5523,11 @@ static bool arg_type_is_release(enum bpf_arg_type type)
 	return type & OBJ_RELEASE;
 }
 
+static bool arg_type_is_dynptr(enum bpf_arg_type type)
+{
+	return base_type(type) == ARG_PTR_TO_DYNPTR;
+}
+
 static int int_ptr_type_to_size(enum bpf_arg_type type)
 {
 	if (type == ARG_PTR_TO_INT)
@@ -5539,6 +5667,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
 	[ARG_PTR_TO_TIMER]		= &timer_types,
 	[ARG_PTR_TO_KPTR]		= &kptr_types,
+	[ARG_PTR_TO_DYNPTR]		= &stack_ptr_types,
 };
 
 static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
@@ -5628,8 +5757,13 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	bool fixed_off_ok = false;
 
 	switch ((u32)type) {
-	case SCALAR_VALUE:
 	/* Pointer types where reg offset is explicitly allowed: */
+	case PTR_TO_STACK:
+		if (arg_type_is_dynptr(arg_type) && reg->off % BPF_REG_SIZE) {
+			verbose(env, "cannot pass in dynptr at an offset\n");
+			return -EINVAL;
+		}
+		fallthrough;
 	case PTR_TO_PACKET:
 	case PTR_TO_PACKET_META:
 	case PTR_TO_MAP_KEY:
@@ -5639,7 +5773,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	case PTR_TO_MEM | MEM_ALLOC:
 	case PTR_TO_BUF:
 	case PTR_TO_BUF | MEM_RDONLY:
-	case PTR_TO_STACK:
+	case SCALAR_VALUE:
 		/* Some of the argument types nevertheless require a
 		 * zero register offset.
 		 */
@@ -5837,6 +5971,36 @@ skip_type_check:
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
 
 		err = check_mem_size_reg(env, reg, regno, zero_size_allowed, meta);
+	} else if (arg_type_is_dynptr(arg_type)) {
+		if (arg_type & MEM_UNINIT) {
+			if (!is_dynptr_reg_valid_uninit(env, reg)) {
+				verbose(env, "Dynptr has to be an uninitialized dynptr\n");
+				return -EINVAL;
+			}
+
+			/* We only support one dynptr being uninitialized at the moment,
+			 * which is sufficient for the helper functions we have right now.
+			 */
+			if (meta->uninit_dynptr_regno) {
+				verbose(env, "verifier internal error: multiple uninitialized dynptr args\n");
+				return -EFAULT;
+			}
+
+			meta->uninit_dynptr_regno = regno;
+		} else if (!is_dynptr_reg_valid_init(env, reg, arg_type)) {
+			const char *err_extra = "";
+
+			switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
+			case DYNPTR_TYPE_LOCAL:
+				err_extra = "local ";
+				break;
+			default:
+				break;
+			}
+			verbose(env, "Expected an initialized %sdynptr as arg #%d\n",
+				err_extra, arg + 1);
+			return -EINVAL;
+		}
 	} else if (arg_type_is_alloc_size(arg_type)) {
 		if (!tnum_is_const(reg->var_off)) {
 			verbose(env, "R%d is not a known constant'\n",
@@ -6970,9 +7134,27 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 	regs = cur_regs(env);
 
+	if (meta.uninit_dynptr_regno) {
+		/* we write BPF_DW bits (8 bytes) at a time */
+		for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) {
+			err = check_mem_access(env, insn_idx, meta.uninit_dynptr_regno,
+					       i, BPF_DW, BPF_WRITE, -1, false);
+			if (err)
+				return err;
+		}
+
+		err = mark_stack_slots_dynptr(env, &regs[meta.uninit_dynptr_regno],
+					      fn->arg_type[meta.uninit_dynptr_regno - BPF_REG_1],
+					      insn_idx);
+		if (err)
+			return err;
+	}
+
 	if (meta.release_regno) {
 		err = -EINVAL;
-		if (meta.ref_obj_id)
+		if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1]))
+			err = unmark_stack_slots_dynptr(env, &regs[meta.release_regno]);
+		else if (meta.ref_obj_id)
 			err = release_reference(env, meta.ref_obj_id);
 		/* meta.ref_obj_id can only be 0 if register that is meant to be
 		 * released is NULL, which must be > R0.
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index d5452f7eb996..855b937e7585 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -634,6 +634,7 @@ class PrinterHelpers(Printer):
             'struct file',
             'struct bpf_timer',
             'struct mptcp_sock',
+            'struct bpf_dynptr',
     ]
     known_types = {
             '...',
@@ -684,6 +685,7 @@ class PrinterHelpers(Printer):
             'struct file',
             'struct bpf_timer',
             'struct mptcp_sock',
+            'struct bpf_dynptr',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 56688bee20d9..610944cb3389 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6528,6 +6528,11 @@ struct bpf_timer {
 	__u64 :64;
 } __attribute__((aligned(8)));
 
+struct bpf_dynptr {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
 struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.
-- 
cgit v1.2.3


From bc34dee65a65e9c920c420005b8a43f2a721a458 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Mon, 23 May 2022 14:07:09 -0700
Subject: bpf: Dynptr support for ring buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, our only way of writing dynamically-sized data into a ring
buffer is through bpf_ringbuf_output but this incurs an extra memcpy
cost. bpf_ringbuf_reserve + bpf_ringbuf_commit avoids this extra
memcpy, but it can only safely support reservation sizes that are
statically known since the verifier cannot guarantee that the bpf
program won’t access memory outside the reserved space.

The bpf_dynptr abstraction allows for dynamically-sized ring buffer
reservations without the extra memcpy.

There are 3 new APIs:

long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr);
void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags);
void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags);

These closely follow the functionalities of the original ringbuf APIs.
For example, all ringbuffer dynptrs that have been reserved must be
either submitted or discarded before the program exits.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: David Vernet <void@manifault.com>
Link: https://lore.kernel.org/bpf/20220523210712.3641569-4-joannelkoong@gmail.com
---
 include/linux/bpf.h            | 15 +++++++-
 include/linux/bpf_verifier.h   |  2 ++
 include/uapi/linux/bpf.h       | 35 +++++++++++++++++++
 kernel/bpf/helpers.c           | 14 +++++---
 kernel/bpf/ringbuf.c           | 78 ++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c          | 52 ++++++++++++++++++++++++++--
 tools/include/uapi/linux/bpf.h | 35 +++++++++++++++++++
 7 files changed, 223 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b26c8176b9e0..c72321b6f306 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -395,11 +395,14 @@ enum bpf_type_flag {
 	/* DYNPTR points to memory local to the bpf program. */
 	DYNPTR_TYPE_LOCAL	= BIT(8 + BPF_BASE_TYPE_BITS),
 
+	/* DYNPTR points to a ringbuf record. */
+	DYNPTR_TYPE_RINGBUF	= BIT(9 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
 
-#define DYNPTR_TYPE_FLAG_MASK	DYNPTR_TYPE_LOCAL
+#define DYNPTR_TYPE_FLAG_MASK	(DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF)
 
 /* Max number of base types. */
 #define BPF_BASE_TYPE_LIMIT	(1UL << BPF_BASE_TYPE_BITS)
@@ -2231,6 +2234,9 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
 extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
 extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
 extern const struct bpf_func_proto bpf_ringbuf_query_proto;
+extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto;
+extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto;
+extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
@@ -2402,6 +2408,13 @@ enum bpf_dynptr_type {
 	BPF_DYNPTR_TYPE_INVALID,
 	/* Points to memory that is local to the bpf program */
 	BPF_DYNPTR_TYPE_LOCAL,
+	/* Underlying data is a ringbuf record */
+	BPF_DYNPTR_TYPE_RINGBUF,
 };
 
+void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
+		     enum bpf_dynptr_type type, u32 offset, u32 size);
+void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
+int bpf_dynptr_check_size(u32 size);
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index af5b2135215e..e8439f6cbe57 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -100,6 +100,8 @@ struct bpf_reg_state {
 	 * for the purpose of tracking that it's freed.
 	 * For PTR_TO_SOCKET this is used to share which pointers retain the
 	 * same reference to the socket, to determine proper reference freeing.
+	 * For stack slots that are dynptrs, this is used to track references to
+	 * the dynptr to determine proper reference freeing.
 	 */
 	u32 id;
 	/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9be3644457dd..081a55540aa5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5189,6 +5189,38 @@ union bpf_attr {
  *	Return
  *		0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
  *		-EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ *	Description
+ *		Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ *		through the dynptr interface. *flags* must be 0.
+ *
+ *		Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ *		bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ *		reservation fails. This is enforced by the verifier.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Submit reserved ring buffer sample, pointed to by *data*,
+ *		through the dynptr interface. This is a no-op if the dynptr is
+ *		invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_submit'.
+ *	Return
+ *		Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Discard reserved ring buffer sample through the dynptr
+ *		interface. This is a no-op if the dynptr is invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_discard'.
+ *	Return
+ *		Nothing. Always succeeds.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5389,6 +5421,9 @@ union bpf_attr {
 	FN(map_lookup_percpu_elem),     \
 	FN(skc_to_mptcp_sock),		\
 	FN(dynptr_from_mem),		\
+	FN(ringbuf_reserve_dynptr),	\
+	FN(ringbuf_submit_dynptr),	\
+	FN(ringbuf_discard_dynptr),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index d3e935c2e25e..abb08999ff56 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1423,13 +1423,13 @@ static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_typ
 	ptr->size |= type << DYNPTR_TYPE_SHIFT;
 }
 
-static int bpf_dynptr_check_size(u32 size)
+int bpf_dynptr_check_size(u32 size)
 {
 	return size > DYNPTR_MAX_SIZE ? -E2BIG : 0;
 }
 
-static void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
-			    enum bpf_dynptr_type type, u32 offset, u32 size)
+void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
+		     enum bpf_dynptr_type type, u32 offset, u32 size)
 {
 	ptr->data = data;
 	ptr->offset = offset;
@@ -1437,7 +1437,7 @@ static void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
 	bpf_dynptr_set_type(ptr, type);
 }
 
-static void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
+void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
 {
 	memset(ptr, 0, sizeof(*ptr));
 }
@@ -1523,6 +1523,12 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ringbuf_discard_proto;
 	case BPF_FUNC_ringbuf_query:
 		return &bpf_ringbuf_query_proto;
+	case BPF_FUNC_ringbuf_reserve_dynptr:
+		return &bpf_ringbuf_reserve_dynptr_proto;
+	case BPF_FUNC_ringbuf_submit_dynptr:
+		return &bpf_ringbuf_submit_dynptr_proto;
+	case BPF_FUNC_ringbuf_discard_dynptr:
+		return &bpf_ringbuf_discard_dynptr_proto;
 	case BPF_FUNC_for_each_map_elem:
 		return &bpf_for_each_map_elem_proto;
 	case BPF_FUNC_loop:
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 311264ab80c4..ded4faeca192 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -475,3 +475,81 @@ const struct bpf_func_proto bpf_ringbuf_query_proto = {
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_ANYTHING,
 };
+
+BPF_CALL_4(bpf_ringbuf_reserve_dynptr, struct bpf_map *, map, u32, size, u64, flags,
+	   struct bpf_dynptr_kern *, ptr)
+{
+	struct bpf_ringbuf_map *rb_map;
+	void *sample;
+	int err;
+
+	if (unlikely(flags)) {
+		bpf_dynptr_set_null(ptr);
+		return -EINVAL;
+	}
+
+	err = bpf_dynptr_check_size(size);
+	if (err) {
+		bpf_dynptr_set_null(ptr);
+		return err;
+	}
+
+	rb_map = container_of(map, struct bpf_ringbuf_map, map);
+
+	sample = __bpf_ringbuf_reserve(rb_map->rb, size);
+	if (!sample) {
+		bpf_dynptr_set_null(ptr);
+		return -EINVAL;
+	}
+
+	bpf_dynptr_init(ptr, sample, BPF_DYNPTR_TYPE_RINGBUF, 0, size);
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = {
+	.func		= bpf_ringbuf_reserve_dynptr,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT,
+};
+
+BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags)
+{
+	if (!ptr->data)
+		return 0;
+
+	bpf_ringbuf_commit(ptr->data, flags, false /* discard */);
+
+	bpf_dynptr_set_null(ptr);
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto = {
+	.func		= bpf_ringbuf_submit_dynptr,
+	.ret_type	= RET_VOID,
+	.arg1_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE,
+	.arg2_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_ringbuf_discard_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags)
+{
+	if (!ptr->data)
+		return 0;
+
+	bpf_ringbuf_commit(ptr->data, flags, true /* discard */);
+
+	bpf_dynptr_set_null(ptr);
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = {
+	.func		= bpf_ringbuf_discard_dynptr,
+	.ret_type	= RET_VOID,
+	.arg1_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE,
+	.arg2_type	= ARG_ANYTHING,
+};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b657d46f886e..8be140351966 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -187,6 +187,9 @@ struct bpf_verifier_stack_elem {
 					  POISON_POINTER_DELTA))
 #define BPF_MAP_PTR(X)		((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
 
+static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx);
+static int release_reference(struct bpf_verifier_env *env, int ref_obj_id);
+
 static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
 {
 	return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON;
@@ -673,17 +676,24 @@ static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
 	switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
 	case DYNPTR_TYPE_LOCAL:
 		return BPF_DYNPTR_TYPE_LOCAL;
+	case DYNPTR_TYPE_RINGBUF:
+		return BPF_DYNPTR_TYPE_RINGBUF;
 	default:
 		return BPF_DYNPTR_TYPE_INVALID;
 	}
 }
 
+static bool dynptr_type_refcounted(enum bpf_dynptr_type type)
+{
+	return type == BPF_DYNPTR_TYPE_RINGBUF;
+}
+
 static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 				   enum bpf_arg_type arg_type, int insn_idx)
 {
 	struct bpf_func_state *state = func(env, reg);
 	enum bpf_dynptr_type type;
-	int spi, i;
+	int spi, i, id;
 
 	spi = get_spi(reg->off);
 
@@ -703,6 +713,16 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_
 	state->stack[spi].spilled_ptr.dynptr.type = type;
 	state->stack[spi - 1].spilled_ptr.dynptr.type = type;
 
+	if (dynptr_type_refcounted(type)) {
+		/* The id is used to track proper releasing */
+		id = acquire_reference_state(env, insn_idx);
+		if (id < 0)
+			return id;
+
+		state->stack[spi].spilled_ptr.id = id;
+		state->stack[spi - 1].spilled_ptr.id = id;
+	}
+
 	return 0;
 }
 
@@ -721,6 +741,13 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re
 		state->stack[spi - 1].slot_type[i] = STACK_INVALID;
 	}
 
+	/* Invalidate any slices associated with this dynptr */
+	if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) {
+		release_reference(env, state->stack[spi].spilled_ptr.id);
+		state->stack[spi].spilled_ptr.id = 0;
+		state->stack[spi - 1].spilled_ptr.id = 0;
+	}
+
 	state->stack[spi].spilled_ptr.dynptr.first_slot = false;
 	state->stack[spi].spilled_ptr.dynptr.type = 0;
 	state->stack[spi - 1].spilled_ptr.dynptr.type = 0;
@@ -5859,7 +5886,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 
 skip_type_check:
 	if (arg_type_is_release(arg_type)) {
-		if (!reg->ref_obj_id && !register_is_null(reg)) {
+		if (arg_type_is_dynptr(arg_type)) {
+			struct bpf_func_state *state = func(env, reg);
+			int spi = get_spi(reg->off);
+
+			if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) ||
+			    !state->stack[spi].spilled_ptr.id) {
+				verbose(env, "arg %d is an unacquired reference\n", regno);
+				return -EINVAL;
+			}
+		} else if (!reg->ref_obj_id && !register_is_null(reg)) {
 			verbose(env, "R%d must be referenced when passed to release function\n",
 				regno);
 			return -EINVAL;
@@ -5994,9 +6030,13 @@ skip_type_check:
 			case DYNPTR_TYPE_LOCAL:
 				err_extra = "local ";
 				break;
+			case DYNPTR_TYPE_RINGBUF:
+				err_extra = "ringbuf ";
+				break;
 			default:
 				break;
 			}
+
 			verbose(env, "Expected an initialized %sdynptr as arg #%d\n",
 				err_extra, arg + 1);
 			return -EINVAL;
@@ -6122,7 +6162,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_RINGBUF:
 		if (func_id != BPF_FUNC_ringbuf_output &&
 		    func_id != BPF_FUNC_ringbuf_reserve &&
-		    func_id != BPF_FUNC_ringbuf_query)
+		    func_id != BPF_FUNC_ringbuf_query &&
+		    func_id != BPF_FUNC_ringbuf_reserve_dynptr &&
+		    func_id != BPF_FUNC_ringbuf_submit_dynptr &&
+		    func_id != BPF_FUNC_ringbuf_discard_dynptr)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -6238,6 +6281,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_ringbuf_output:
 	case BPF_FUNC_ringbuf_reserve:
 	case BPF_FUNC_ringbuf_query:
+	case BPF_FUNC_ringbuf_reserve_dynptr:
+	case BPF_FUNC_ringbuf_submit_dynptr:
+	case BPF_FUNC_ringbuf_discard_dynptr:
 		if (map->map_type != BPF_MAP_TYPE_RINGBUF)
 			goto error;
 		break;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9be3644457dd..081a55540aa5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5189,6 +5189,38 @@ union bpf_attr {
  *	Return
  *		0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
  *		-EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ *	Description
+ *		Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ *		through the dynptr interface. *flags* must be 0.
+ *
+ *		Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ *		bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ *		reservation fails. This is enforced by the verifier.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Submit reserved ring buffer sample, pointed to by *data*,
+ *		through the dynptr interface. This is a no-op if the dynptr is
+ *		invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_submit'.
+ *	Return
+ *		Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Discard reserved ring buffer sample through the dynptr
+ *		interface. This is a no-op if the dynptr is invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_discard'.
+ *	Return
+ *		Nothing. Always succeeds.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5389,6 +5421,9 @@ union bpf_attr {
 	FN(map_lookup_percpu_elem),     \
 	FN(skc_to_mptcp_sock),		\
 	FN(dynptr_from_mem),		\
+	FN(ringbuf_reserve_dynptr),	\
+	FN(ringbuf_submit_dynptr),	\
+	FN(ringbuf_discard_dynptr),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 34d4ef5775f776ec4b0d53a02d588bf3195cada6 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Mon, 23 May 2022 14:07:11 -0700
Subject: bpf: Add dynptr data slices

This patch adds a new helper function

void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len);

which returns a pointer to the underlying data of a dynptr. *len*
must be a statically known value. The bpf program may access the returned
data slice as a normal buffer (eg can do direct reads and writes), since
the verifier associates the length with the returned pointer, and
enforces that no out of bounds accesses occur.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20220523210712.3641569-6-joannelkoong@gmail.com
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       | 12 ++++++++++++
 kernel/bpf/helpers.c           | 28 ++++++++++++++++++++++++++++
 kernel/bpf/verifier.c          | 23 +++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h | 12 ++++++++++++
 5 files changed, 76 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c72321b6f306..a7080c86fa76 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -488,6 +488,7 @@ enum bpf_return_type {
 	RET_PTR_TO_TCP_SOCK_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
 	RET_PTR_TO_SOCK_COMMON_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
 	RET_PTR_TO_ALLOC_MEM_OR_NULL	= PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM,
+	RET_PTR_TO_DYNPTR_MEM_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM,
 	RET_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index efe2505650e6..f4009dbdf62d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5238,6 +5238,17 @@ union bpf_attr {
  *		0 on success, -E2BIG if *offset* + *len* exceeds the length
  *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
  *		is a read-only dynptr.
+ *
+ * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ *	Description
+ *		Get a pointer to the underlying dynptr data.
+ *
+ *		*len* must be a statically known value. The returned data slice
+ *		is invalidated whenever the dynptr is invalidated.
+ *	Return
+ *		Pointer to the underlying dynptr data, NULL if the dynptr is
+ *		read-only, if the dynptr is invalid, or if the offset and length
+ *		is out of bounds.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5443,6 +5454,7 @@ union bpf_attr {
 	FN(ringbuf_discard_dynptr),	\
 	FN(dynptr_read),		\
 	FN(dynptr_write),		\
+	FN(dynptr_data),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 8cef3fb0d143..225806a02efb 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1549,6 +1549,32 @@ const struct bpf_func_proto bpf_dynptr_write_proto = {
 	.arg4_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
+BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len)
+{
+	int err;
+
+	if (!ptr->data)
+		return 0;
+
+	err = bpf_dynptr_check_off_len(ptr, offset, len);
+	if (err)
+		return 0;
+
+	if (bpf_dynptr_is_rdonly(ptr))
+		return 0;
+
+	return (unsigned long)(ptr->data + ptr->offset + offset);
+}
+
+const struct bpf_func_proto bpf_dynptr_data_proto = {
+	.func		= bpf_dynptr_data,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_DYNPTR_MEM_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_DYNPTR,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_CONST_ALLOC_SIZE_OR_ZERO,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_get_current_task_btf_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
@@ -1615,6 +1641,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_dynptr_read_proto;
 	case BPF_FUNC_dynptr_write:
 		return &bpf_dynptr_write_proto;
+	case BPF_FUNC_dynptr_data:
+		return &bpf_dynptr_data_proto;
 	default:
 		break;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8be140351966..aedac2ac02b9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5832,6 +5832,14 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	return __check_ptr_off_reg(env, reg, regno, fixed_off_ok);
 }
 
+static u32 stack_slot_get_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi = get_spi(reg->off);
+
+	return state->stack[spi].spilled_ptr.id;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn)
@@ -7384,6 +7392,21 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		regs[BPF_REG_0].id = id;
 		/* For release_reference() */
 		regs[BPF_REG_0].ref_obj_id = id;
+	} else if (func_id == BPF_FUNC_dynptr_data) {
+		int dynptr_id = 0, i;
+
+		/* Find the id of the dynptr we're acquiring a reference to */
+		for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
+			if (arg_type_is_dynptr(fn->arg_type[i])) {
+				if (dynptr_id) {
+					verbose(env, "verifier internal error: multiple dynptr args in func\n");
+					return -EFAULT;
+				}
+				dynptr_id = stack_slot_get_id(env, &regs[BPF_REG_1 + i]);
+			}
+		}
+		/* For release_reference() */
+		regs[BPF_REG_0].ref_obj_id = dynptr_id;
 	}
 
 	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index efe2505650e6..f4009dbdf62d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5238,6 +5238,17 @@ union bpf_attr {
  *		0 on success, -E2BIG if *offset* + *len* exceeds the length
  *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
  *		is a read-only dynptr.
+ *
+ * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ *	Description
+ *		Get a pointer to the underlying dynptr data.
+ *
+ *		*len* must be a statically known value. The returned data slice
+ *		is invalidated whenever the dynptr is invalidated.
+ *	Return
+ *		Pointer to the underlying dynptr data, NULL if the dynptr is
+ *		read-only, if the dynptr is invalid, or if the offset and length
+ *		is out of bounds.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5443,6 +5454,7 @@ union bpf_attr {
 	FN(ringbuf_discard_dynptr),	\
 	FN(dynptr_read),		\
 	FN(dynptr_write),		\
+	FN(dynptr_data),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 5d7c854593a460706dacf8e1b16c9bdcb1c2d7bb Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Mon, 28 Mar 2022 08:26:48 +0200
Subject: livepatch: Remove klp_arch_set_pc() and asm/livepatch.h

All three versions of klp_arch_set_pc() do exactly the same: they
call ftrace_instruction_pointer_set().

Call ftrace_instruction_pointer_set() directly and remove
klp_arch_set_pc().

As klp_arch_set_pc() was the only thing remaining in asm/livepatch.h
on x86 and s390, remove asm/livepatch.h

livepatch.h remains on powerpc but its content is exclusively used
by powerpc specific code.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Petr Mladek <pmladek@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 MAINTAINERS                          |  2 --
 arch/powerpc/include/asm/livepatch.h | 10 +---------
 arch/powerpc/kernel/irq.c            |  1 -
 arch/powerpc/kernel/setup_64.c       |  2 +-
 arch/s390/include/asm/livepatch.h    | 22 ----------------------
 arch/x86/include/asm/livepatch.h     | 20 --------------------
 include/linux/livepatch.h            |  2 --
 kernel/livepatch/patch.c             |  2 +-
 8 files changed, 3 insertions(+), 58 deletions(-)
 delete mode 100644 arch/s390/include/asm/livepatch.h
 delete mode 100644 arch/x86/include/asm/livepatch.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 741825cff43c..589c61412e3b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11338,8 +11338,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/livepatching/livepatching.g
 F:	Documentation/ABI/testing/sysfs-kernel-livepatch
 F:	Documentation/livepatch/
 F:	arch/powerpc/include/asm/livepatch.h
-F:	arch/s390/include/asm/livepatch.h
-F:	arch/x86/include/asm/livepatch.h
 F:	include/linux/livepatch.h
 F:	kernel/livepatch/
 F:	lib/livepatch/
diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h
index 1c60094ea0cd..d044a1fd4f44 100644
--- a/arch/powerpc/include/asm/livepatch.h
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -7,17 +7,9 @@
 #ifndef _ASM_POWERPC_LIVEPATCH_H
 #define _ASM_POWERPC_LIVEPATCH_H
 
-#include <linux/module.h>
-#include <linux/ftrace.h>
+#include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 
-#ifdef CONFIG_LIVEPATCH
-static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip)
-{
-	ftrace_instruction_pointer_set(fregs, ip);
-}
-#endif /* CONFIG_LIVEPATCH */
-
 #ifdef CONFIG_LIVEPATCH_64
 static inline void klp_init_thread_info(struct task_struct *p)
 {
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 752fb182eacb..fb99e3fa034d 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -63,7 +63,6 @@
 #include <asm/machdep.h>
 #include <asm/udbg.h>
 #include <asm/smp.h>
-#include <asm/livepatch.h>
 #include <asm/hw_irq.h>
 #include <asm/softirq_stack.h>
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index e547066a06aa..2c1e9a5ac6ca 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -59,7 +59,7 @@
 #include <asm/udbg.h>
 #include <asm/kexec.h>
 #include <asm/code-patching.h>
-#include <asm/livepatch.h>
+#include <asm/ftrace.h>
 #include <asm/opal.h>
 #include <asm/cputhreads.h>
 #include <asm/hw_irq.h>
diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h
deleted file mode 100644
index 5209f223331a..000000000000
--- a/arch/s390/include/asm/livepatch.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
-/*
- * livepatch.h - s390-specific Kernel Live Patching Core
- *
- *  Copyright (c) 2013-2015 SUSE
- *   Authors: Jiri Kosina
- *	      Vojtech Pavlik
- *	      Jiri Slaby
- */
-
-#ifndef ASM_LIVEPATCH_H
-#define ASM_LIVEPATCH_H
-
-#include <linux/ftrace.h>
-#include <asm/ptrace.h>
-
-static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip)
-{
-	ftrace_instruction_pointer_set(fregs, ip);
-}
-
-#endif
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
deleted file mode 100644
index 7c5cc6660e4b..000000000000
--- a/arch/x86/include/asm/livepatch.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * livepatch.h - x86-specific Kernel Live Patching Core
- *
- * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
- * Copyright (C) 2014 SUSE
- */
-
-#ifndef _ASM_X86_LIVEPATCH_H
-#define _ASM_X86_LIVEPATCH_H
-
-#include <asm/setup.h>
-#include <linux/ftrace.h>
-
-static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip)
-{
-	ftrace_instruction_pointer_set(fregs, ip);
-}
-
-#endif /* _ASM_X86_LIVEPATCH_H */
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index 2614247a9781..293e29960c6e 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -16,8 +16,6 @@
 
 #if IS_ENABLED(CONFIG_LIVEPATCH)
 
-#include <asm/livepatch.h>
-
 /* task patch states */
 #define KLP_UNDEFINED	-1
 #define KLP_UNPATCHED	 0
diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
index c172bf92b576..4c4f5a776d80 100644
--- a/kernel/livepatch/patch.c
+++ b/kernel/livepatch/patch.c
@@ -118,7 +118,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
 	if (func->nop)
 		goto unlock;
 
-	klp_arch_set_pc(fregs, (unsigned long)func->new_func);
+	ftrace_instruction_pointer_set(fregs, (unsigned long)func->new_func);
 
 unlock:
 	ftrace_test_recursion_unlock(bit);
-- 
cgit v1.2.3


From 7b4537199a4a8480b8c3ba37a2d44765ce76cd9b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Fri, 13 May 2022 20:39:22 +0900
Subject: kbuild: link symbol CRCs at final link, removing
 CONFIG_MODULE_REL_CRCS

include/{linux,asm-generic}/export.h defines a weak symbol, __crc_*
as a placeholder.

Genksyms writes the version CRCs into the linker script, which will be
used for filling the __crc_* symbols. The linker script format depends
on CONFIG_MODULE_REL_CRCS. If it is enabled, __crc_* holds the offset
to the reference of CRC.

It is time to get rid of this complexity.

Now that modpost parses text files (.*.cmd) to collect all the CRCs,
it can generate C code that will be linked to the vmlinux or modules.

Generate a new C file, .vmlinux.export.c, which contains the CRCs of
symbols exported by vmlinux. It is compiled and linked to vmlinux in
scripts/link-vmlinux.sh.

Put the CRCs of symbols exported by modules into the existing *.mod.c
files. No additional build step is needed for modules. As before,
*.mod.c are compiled and linked to *.ko in scripts/Makefile.modfinal.

No linker magic is used here. The new C implementation works in the
same way, whether CONFIG_RELOCATABLE is enabled or not.
CONFIG_MODULE_REL_CRCS is no longer needed.

Previously, Kbuild invoked additional $(LD) to update the CRCs in
objects, but this step is unneeded too.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nicolas Schier <nicolas@fjasle.eu>
Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com> # LLVM-14 (x86-64)
---
 arch/m68k/include/asm/Kbuild    |  1 +
 arch/m68k/include/asm/export.h  |  2 --
 arch/powerpc/Kconfig            |  1 -
 arch/s390/Kconfig               |  1 -
 arch/um/Kconfig                 |  1 -
 include/asm-generic/export.h    | 22 ++++++++--------------
 include/linux/export-internal.h | 17 +++++++++++++++++
 include/linux/export.h          | 30 ++++++++----------------------
 init/Kconfig                    |  4 ----
 kernel/module.c                 | 10 +---------
 scripts/Makefile.build          | 27 ++++-----------------------
 scripts/Makefile.vmlinux        | 32 ++++++++++++++++++++++++++++++++
 scripts/genksyms/genksyms.c     | 18 ++++--------------
 scripts/link-vmlinux.sh         | 10 +++++++++-
 scripts/mod/modpost.c           | 28 ++++++++++++++++++++++++----
 15 files changed, 108 insertions(+), 96 deletions(-)
 delete mode 100644 arch/m68k/include/asm/export.h
 create mode 100644 include/linux/export-internal.h
 create mode 100644 scripts/Makefile.vmlinux

(limited to 'include/linux')

diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 0dbf9c5c6fae..1b720299deb1 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 generated-y += syscall_table.h
+generic-y += export.h
 generic-y += extable.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
diff --git a/arch/m68k/include/asm/export.h b/arch/m68k/include/asm/export.h
deleted file mode 100644
index b53008b67ce1..000000000000
--- a/arch/m68k/include/asm/export.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#define KCRC_ALIGN 2
-#include <asm-generic/export.h>
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 174edabb74fa..a4e8dd889e29 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -566,7 +566,6 @@ config RELOCATABLE
 	bool "Build a relocatable kernel"
 	depends on PPC64 || (FLATMEM && (44x || FSL_BOOKE))
 	select NONSTATIC_KERNEL
-	select MODULE_REL_CRCS if MODVERSIONS
 	help
 	  This builds a kernel image that is capable of running at the
 	  location the kernel is loaded at. For ppc32, there is no any
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 77b5a03de13a..aa5848004c76 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -567,7 +567,6 @@ endchoice
 
 config RELOCATABLE
 	bool "Build a relocatable kernel"
-	select MODULE_REL_CRCS if MODVERSIONS
 	default y
 	help
 	  This builds a kernel image that retains relocation information
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 4d398b80aea8..e8983d098e73 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -106,7 +106,6 @@ config LD_SCRIPT_DYN
 	bool
 	default y
 	depends on !LD_SCRIPT_STATIC
-	select MODULE_REL_CRCS if MODVERSIONS
 
 config LD_SCRIPT_DYN_RPATH
 	bool "set rpath in the binary" if EXPERT
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index 07a36a874dca..5e4b1f2369d2 100644
--- a/include/asm-generic/export.h
+++ b/include/asm-generic/export.h
@@ -2,6 +2,14 @@
 #ifndef __ASM_GENERIC_EXPORT_H
 #define __ASM_GENERIC_EXPORT_H
 
+/*
+ * This comment block is used by fixdep. Please do not remove.
+ *
+ * When CONFIG_MODVERSIONS is changed from n to y, all source files having
+ * EXPORT_SYMBOL variants must be re-compiled because genksyms is run as a
+ * side effect of the *.o build rule.
+ */
+
 #ifndef KSYM_FUNC
 #define KSYM_FUNC(x) x
 #endif
@@ -12,9 +20,6 @@
 #else
 #define KSYM_ALIGN 4
 #endif
-#ifndef KCRC_ALIGN
-#define KCRC_ALIGN 4
-#endif
 
 .macro __put, val, name
 #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
@@ -43,17 +48,6 @@ __ksymtab_\name:
 __kstrtab_\name:
 	.asciz "\name"
 	.previous
-#ifdef CONFIG_MODVERSIONS
-	.section ___kcrctab\sec+\name,"a"
-	.balign KCRC_ALIGN
-#if defined(CONFIG_MODULE_REL_CRCS)
-	.long __crc_\name - .
-#else
-	.long __crc_\name
-#endif
-	.weak __crc_\name
-	.previous
-#endif
 #endif
 .endm
 
diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h
new file mode 100644
index 000000000000..c2b1d4fd5987
--- /dev/null
+++ b/include/linux/export-internal.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Please do not include this explicitly.
+ * This is used by C files generated by modpost.
+ */
+
+#ifndef __LINUX_EXPORT_INTERNAL_H__
+#define __LINUX_EXPORT_INTERNAL_H__
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+/* __used is needed to keep __crc_* for LTO */
+#define SYMBOL_CRC(sym, crc, sec)   \
+	u32 __section("___kcrctab" sec "+" #sym) __used __crc_##sym = crc
+
+#endif /* __LINUX_EXPORT_INTERNAL_H__ */
diff --git a/include/linux/export.h b/include/linux/export.h
index 27d848712b90..565c5ffcb26f 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -11,6 +11,14 @@
  * hackers place grumpy comments in header files.
  */
 
+/*
+ * This comment block is used by fixdep. Please do not remove.
+ *
+ * When CONFIG_MODVERSIONS is changed from n to y, all source files having
+ * EXPORT_SYMBOL variants must be re-compiled because genksyms is run as a
+ * side effect of the *.o build rule.
+ */
+
 #ifndef __ASSEMBLY__
 #ifdef MODULE
 extern struct module __this_module;
@@ -19,26 +27,6 @@ extern struct module __this_module;
 #define THIS_MODULE ((struct module *)0)
 #endif
 
-#ifdef CONFIG_MODVERSIONS
-/* Mark the CRC weak since genksyms apparently decides not to
- * generate a checksums for some symbols */
-#if defined(CONFIG_MODULE_REL_CRCS)
-#define __CRC_SYMBOL(sym, sec)						\
-	asm("	.section \"___kcrctab" sec "+" #sym "\", \"a\"	\n"	\
-	    "	.weak	__crc_" #sym "				\n"	\
-	    "	.long	__crc_" #sym " - .			\n"	\
-	    "	.previous					\n")
-#else
-#define __CRC_SYMBOL(sym, sec)						\
-	asm("	.section \"___kcrctab" sec "+" #sym "\", \"a\"	\n"	\
-	    "	.weak	__crc_" #sym "				\n"	\
-	    "	.long	__crc_" #sym "				\n"	\
-	    "	.previous					\n")
-#endif
-#else
-#define __CRC_SYMBOL(sym, sec)
-#endif
-
 #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
 #include <linux/compiler.h>
 /*
@@ -85,7 +73,6 @@ struct kernel_symbol {
 /*
  * For every exported symbol, do the following:
  *
- * - If applicable, place a CRC entry in the __kcrctab section.
  * - Put the name of the symbol and namespace (empty string "" for none) in
  *   __ksymtab_strings.
  * - Place a struct kernel_symbol entry in the __ksymtab section.
@@ -98,7 +85,6 @@ struct kernel_symbol {
 	extern typeof(sym) sym;							\
 	extern const char __kstrtab_##sym[];					\
 	extern const char __kstrtabns_##sym[];					\
-	__CRC_SYMBOL(sym, sec);							\
 	asm("	.section \"__ksymtab_strings\",\"aMS\",%progbits,1	\n"	\
 	    "__kstrtab_" #sym ":					\n"	\
 	    "	.asciz 	\"" #sym "\"					\n"	\
diff --git a/init/Kconfig b/init/Kconfig
index ddcbefe535e9..f5b14318dfcb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2136,10 +2136,6 @@ config ASM_MODVERSIONS
 	  assembly. This can be enabled only when the target architecture
 	  supports it.
 
-config MODULE_REL_CRCS
-	bool
-	depends on MODVERSIONS
-
 config MODULE_SRCVERSION_ALL
 	bool "Source checksum for all modules"
 	help
diff --git a/kernel/module.c b/kernel/module.c
index 6cea788fd965..c9e2342da28e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1231,11 +1231,6 @@ static int try_to_force_load(struct module *mod, const char *reason)
 
 #ifdef CONFIG_MODVERSIONS
 
-static u32 resolve_rel_crc(const s32 *crc)
-{
-	return *(u32 *)((void *)crc + *crc);
-}
-
 static int check_version(const struct load_info *info,
 			 const char *symname,
 			 struct module *mod,
@@ -1264,10 +1259,7 @@ static int check_version(const struct load_info *info,
 		if (strcmp(versions[i].name, symname) != 0)
 			continue;
 
-		if (IS_ENABLED(CONFIG_MODULE_REL_CRCS))
-			crcval = resolve_rel_crc(crc);
-		else
-			crcval = *crc;
+		crcval = *crc;
 		if (versions[i].crc == crcval)
 			return 1;
 		pr_debug("Found checksum %X vs module %lX\n",
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index a1023868775f..ddd9080fc028 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -128,7 +128,6 @@ $(obj)/%.i: $(src)/%.c FORCE
 
 genksyms = scripts/genksyms/genksyms		\
 	$(if $(1), -T $(2))			\
-	$(if $(CONFIG_MODULE_REL_CRCS), -R)	\
 	$(if $(KBUILD_PRESERVE), -p)		\
 	-r $(or $(wildcard $(2:.symtypes=.symref)), /dev/null)
 
@@ -162,19 +161,11 @@ ifdef CONFIG_MODVERSIONS
 # o if <file>.o doesn't contain a __ksymtab version, i.e. does
 #   not export symbols, it's done.
 # o otherwise, we calculate symbol versions using the good old
-#   genksyms on the preprocessed source and postprocess them in a way
-#   that they are usable as a linker script
-# o generate .tmp_<file>.o from <file>.o using the linker to
-#   replace the unresolved symbols __crc_exported_symbol with
-#   the actual value of the checksum generated by genksyms
-# o remove .tmp_<file>.o to <file>.o
+#   genksyms on the preprocessed source and dump them into the .cmd file.
+# o modpost will extract versions from that file and create *.c files that will
+#   be compiled and linked to the kernel and/or modules.
 
-# Generate .o.symversions files for each .o with exported symbols, and link these
-# to the kernel and/or modules at the end.
-
-genksyms_format_rel_crc := [^_]*__crc_\([^ ]*\) = \.; LONG(\([^)]*\)).*
-genksyms_format_normal := __crc_\(.*\) = \(.*\);
-genksyms_format := $(if $(CONFIG_MODULE_REL_CRCS),$(genksyms_format_rel_crc),$(genksyms_format_normal))
+genksyms_format := __crc_\(.*\) = \(.*\);
 
 gen_symversions =								\
 	if $(NM) $@ 2>/dev/null | grep -q __ksymtab; then			\
@@ -188,12 +179,6 @@ gen_symversions =								\
 
 cmd_gen_symversions_c =	$(call gen_symversions,c)
 
-cmd_modversions =								\
-	if [ -r $@.symversions ]; then						\
-		$(LD) $(KBUILD_LDFLAGS) -r -o $(@D)/.tmp_$(@F) $@ 		\
-			-T $@.symversions;					\
-		mv -f $(@D)/.tmp_$(@F) $@;					\
-	fi
 endif
 
 ifdef CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
@@ -273,7 +258,6 @@ define rule_cc_o_c
 	$(call cmd,checkdoc)
 	$(call cmd,gen_objtooldep)
 	$(call cmd,gen_symversions_c)
-	$(if $(CONFIG_LTO_CLANG),,$(call cmd,modversions))
 	$(call cmd,record_mcount)
 endef
 
@@ -282,7 +266,6 @@ define rule_as_o_S
 	$(call cmd,gen_ksymdeps)
 	$(call cmd,gen_objtooldep)
 	$(call cmd,gen_symversions_S)
-	$(call cmd,modversions)
 endef
 
 # Built-in and composite module parts
@@ -296,8 +279,6 @@ ifneq ($(CONFIG_LTO_CLANG)$(CONFIG_X86_KERNEL_IBT),)
 quiet_cmd_cc_prelink_modules = LD [M]  $@
       cmd_cc_prelink_modules =						\
 	$(LD) $(ld_flags) -r -o $@					\
-               $(shell [ -s $(@:.prelink.o=.o.symversions) ] &&		\
-                       echo -T $(@:.prelink.o=.o.symversions))		\
 		--whole-archive $(filter-out FORCE,$^)			\
 		$(cmd_objtool)
 
diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
new file mode 100644
index 000000000000..7a63abf22399
--- /dev/null
+++ b/scripts/Makefile.vmlinux
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+include include/config/auto.conf
+include $(srctree)/scripts/Kbuild.include
+
+# for c_flags
+include $(srctree)/scripts/Makefile.lib
+
+quiet_cmd_cc_o_c = CC      $@
+      cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $<
+
+%.o: %.c FORCE
+	$(call if_changed_dep,cc_o_c)
+
+targets := $(MAKECMDGOALS)
+
+# Add FORCE to the prequisites of a target to force it to be always rebuilt.
+# ---------------------------------------------------------------------------
+
+PHONY += FORCE
+FORCE:
+
+# Read all saved command lines and dependencies for the $(targets) we
+# may be building above, using $(if_changed{,_dep}). As an
+# optimization, we don't need to read them if the target does not
+# exist, we will rebuild anyway in that case.
+
+existing-targets := $(wildcard $(sort $(targets)))
+
+-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd)
+
+.PHONY: $(PHONY)
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index 4827c5abe5b7..67b23cc0df0f 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -33,7 +33,7 @@ char *cur_filename;
 int in_source_file;
 
 static int flag_debug, flag_dump_defs, flag_reference, flag_dump_types,
-	   flag_preserve, flag_warnings, flag_rel_crcs;
+	   flag_preserve, flag_warnings;
 
 static int errors;
 static int nsyms;
@@ -680,11 +680,7 @@ void export_symbol(const char *name)
 		if (flag_dump_defs)
 			fputs(">\n", debugfile);
 
-		/* Used as a linker script. */
-		printf(!flag_rel_crcs ? "__crc_%s = 0x%08lx;\n" :
-		       "SECTIONS { .rodata : ALIGN(4) { "
-		       "__crc_%s = .; LONG(0x%08lx); } }\n",
-		       name, crc);
+		printf("__crc_%s = 0x%08lx;\n", name, crc);
 	}
 }
 
@@ -733,7 +729,6 @@ static void genksyms_usage(void)
 	      "  -q, --quiet           Disable warnings (default)\n"
 	      "  -h, --help            Print this message\n"
 	      "  -V, --version         Print the release version\n"
-	      "  -R, --relative-crc    Emit section relative symbol CRCs\n"
 #else				/* __GNU_LIBRARY__ */
 	      "  -s                    Select symbol prefix\n"
 	      "  -d                    Increment the debug level (repeatable)\n"
@@ -745,7 +740,6 @@ static void genksyms_usage(void)
 	      "  -q                    Disable warnings (default)\n"
 	      "  -h                    Print this message\n"
 	      "  -V                    Print the release version\n"
-	      "  -R                    Emit section relative symbol CRCs\n"
 #endif				/* __GNU_LIBRARY__ */
 	      , stderr);
 }
@@ -766,14 +760,13 @@ int main(int argc, char **argv)
 		{"preserve", 0, 0, 'p'},
 		{"version", 0, 0, 'V'},
 		{"help", 0, 0, 'h'},
-		{"relative-crc", 0, 0, 'R'},
 		{0, 0, 0, 0}
 	};
 
-	while ((o = getopt_long(argc, argv, "s:dwqVDr:T:phR",
+	while ((o = getopt_long(argc, argv, "s:dwqVDr:T:ph",
 				&long_opts[0], NULL)) != EOF)
 #else				/* __GNU_LIBRARY__ */
-	while ((o = getopt(argc, argv, "s:dwqVDr:T:phR")) != EOF)
+	while ((o = getopt(argc, argv, "s:dwqVDr:T:ph")) != EOF)
 #endif				/* __GNU_LIBRARY__ */
 		switch (o) {
 		case 'd':
@@ -813,9 +806,6 @@ int main(int argc, char **argv)
 		case 'h':
 			genksyms_usage();
 			return 0;
-		case 'R':
-			flag_rel_crcs = 1;
-			break;
 		default:
 			genksyms_usage();
 			return 1;
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index eceb3ee7ec06..db34dc3163ae 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -90,7 +90,6 @@ modpost_link()
 
 		if is_enabled CONFIG_MODVERSIONS; then
 			gen_symversions
-			lds="${lds} -T .tmp_symversions.lds"
 		fi
 
 		# This might take a while, so indicate that we're doing
@@ -183,6 +182,10 @@ vmlinux_link()
 		libs="${KBUILD_VMLINUX_LIBS}"
 	fi
 
+	if is_enabled CONFIG_MODULES; then
+		objs="${objs} .vmlinux.export.o"
+	fi
+
 	if [ "${SRCARCH}" = "um" ]; then
 		wl=-Wl,
 		ld="${CC}"
@@ -312,6 +315,7 @@ cleanup()
 	rm -f vmlinux.o
 	rm -f .vmlinux.d
 	rm -f .vmlinux.objs
+	rm -f .vmlinux.export.c
 }
 
 # Use "make V=1" to debug this script
@@ -363,6 +367,10 @@ info GEN modules.builtin
 tr '\0' '\n' < modules.builtin.modinfo | sed -n 's/^[[:alnum:]:_]*\.file=//p' |
 	tr ' ' '\n' | uniq | sed -e 's:^:kernel/:' -e 's/$/.ko/' > modules.builtin
 
+if is_enabled CONFIG_MODULES; then
+	${MAKE} -f "${srctree}/scripts/Makefile.vmlinux" .vmlinux.export.o
+fi
+
 btf_vmlinux_bin_o=""
 if is_enabled CONFIG_DEBUG_INFO_BTF; then
 	btf_vmlinux_bin_o=.btf.vmlinux.bin.o
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 1e2949775e1b..42e949cbc255 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -2234,6 +2234,7 @@ static void add_header(struct buffer *b, struct module *mod)
 	buf_printf(b, "#define INCLUDE_VERMAGIC\n");
 	buf_printf(b, "#include <linux/build-salt.h>\n");
 	buf_printf(b, "#include <linux/elfnote-lto.h>\n");
+	buf_printf(b, "#include <linux/export-internal.h>\n");
 	buf_printf(b, "#include <linux/vermagic.h>\n");
 	buf_printf(b, "#include <linux/compiler.h>\n");
 	buf_printf(b, "\n");
@@ -2268,20 +2269,26 @@ static void add_header(struct buffer *b, struct module *mod)
 		buf_printf(b, "\nMODULE_INFO(staging, \"Y\");\n");
 }
 
-static void check_symversions(struct module *mod)
+static void add_exported_symbols(struct buffer *buf, struct module *mod)
 {
 	struct symbol *sym;
 
 	if (!modversions)
 		return;
 
+	/* record CRCs for exported symbols */
+	buf_printf(buf, "\n");
 	list_for_each_entry(sym, &mod->exported_symbols, list) {
 		if (!sym->crc_valid) {
 			warn("EXPORT symbol \"%s\" [%s%s] version generation failed, symbol will not be versioned.\n"
 			     "Is \"%s\" prototyped in <asm/asm-prototypes.h>?\n",
 			     sym->name, mod->name, mod->is_vmlinux ? "" : ".ko",
 			     sym->name);
+			continue;
 		}
+
+		buf_printf(buf, "SYMBOL_CRC(%s, 0x%08x, \"%s\");\n",
+			   sym->name, sym->crc, sym->is_gpl_only ? "_gpl" : "");
 	}
 }
 
@@ -2418,6 +2425,18 @@ static void write_if_changed(struct buffer *b, const char *fname)
 	write_buf(b, fname);
 }
 
+static void write_vmlinux_export_c_file(struct module *mod)
+{
+	struct buffer buf = { };
+
+	buf_printf(&buf,
+		   "#include <linux/export-internal.h>\n");
+
+	add_exported_symbols(&buf, mod);
+	write_if_changed(&buf, ".vmlinux.export.c");
+	free(buf.p);
+}
+
 /* do sanity checks, and generate *.mod.c file */
 static void write_mod_c_file(struct module *mod)
 {
@@ -2429,6 +2448,7 @@ static void write_mod_c_file(struct module *mod)
 	check_exports(mod);
 
 	add_header(&buf, mod);
+	add_exported_symbols(&buf, mod);
 	add_versions(&buf, mod);
 	add_depends(&buf, mod);
 	add_moddevtable(&buf, mod);
@@ -2626,9 +2646,9 @@ int main(int argc, char **argv)
 		if (mod->from_dump)
 			continue;
 
-		check_symversions(mod);
-
-		if (!mod->is_vmlinux)
+		if (mod->is_vmlinux)
+			write_vmlinux_export_c_file(mod);
+		else
 			write_mod_c_file(mod);
 	}
 
-- 
cgit v1.2.3


From 421cfe6596f6cb316991c02bf30a93bd81092853 Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Thu, 19 May 2022 14:33:11 -0400
Subject: vfio: remove VFIO_GROUP_NOTIFY_SET_KVM

Rather than relying on a notifier for associating the KVM with
the group, let's assume that the association has already been
made prior to device_open.  The first time a device is opened
associate the group KVM with the device.

This fixes a user-triggerable oops in GVT.

Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Zhi Wang <zhi.a.wang@intel.com>
Link: https://lore.kernel.org/r/20220519183311.582380-2-mjrosato@linux.ibm.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c        |  4 +-
 drivers/gpu/drm/i915/gvt/gvt.h        |  3 --
 drivers/gpu/drm/i915/gvt/kvmgt.c      | 82 ++++++++--------------------------
 drivers/s390/crypto/vfio_ap_ops.c     | 35 +++------------
 drivers/s390/crypto/vfio_ap_private.h |  3 --
 drivers/vfio/vfio.c                   | 83 ++++++++++++-----------------------
 include/linux/vfio.h                  |  6 +--
 7 files changed, 57 insertions(+), 159 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 9c5cc2800975..b4f69364f9a1 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -51,7 +51,7 @@ static int preallocated_oos_pages = 8192;
 
 static bool intel_gvt_is_valid_gfn(struct intel_vgpu *vgpu, unsigned long gfn)
 {
-	struct kvm *kvm = vgpu->kvm;
+	struct kvm *kvm = vgpu->vfio_device.kvm;
 	int idx;
 	bool ret;
 
@@ -1185,7 +1185,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
 
 	if (!vgpu->attached)
 		return -EINVAL;
-	pfn = gfn_to_pfn(vgpu->kvm, ops->get_pfn(entry));
+	pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
 	return PageTransHuge(pfn_to_page(pfn));
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 2af4c83e733c..aee1a45da74b 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -227,9 +227,6 @@ struct intel_vgpu {
 	struct mutex cache_lock;
 
 	struct notifier_block iommu_notifier;
-	struct notifier_block group_notifier;
-	struct kvm *kvm;
-	struct work_struct release_work;
 	atomic_t released;
 
 	struct kvm_page_track_notifier_node track_node;
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 7655ffa97d51..e2f6c56ab342 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -228,8 +228,6 @@ static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt)
 	}
 }
 
-static void intel_vgpu_release_work(struct work_struct *work);
-
 static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 		unsigned long size)
 {
@@ -761,23 +759,6 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static int intel_vgpu_group_notifier(struct notifier_block *nb,
-				     unsigned long action, void *data)
-{
-	struct intel_vgpu *vgpu =
-		container_of(nb, struct intel_vgpu, group_notifier);
-
-	/* the only action we care about */
-	if (action == VFIO_GROUP_NOTIFY_SET_KVM) {
-		vgpu->kvm = data;
-
-		if (!data)
-			schedule_work(&vgpu->release_work);
-	}
-
-	return NOTIFY_OK;
-}
-
 static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)
 {
 	struct intel_vgpu *itr;
@@ -789,7 +770,7 @@ static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)
 		if (!itr->attached)
 			continue;
 
-		if (vgpu->kvm == itr->kvm) {
+		if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) {
 			ret = true;
 			goto out;
 		}
@@ -806,7 +787,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 	int ret;
 
 	vgpu->iommu_notifier.notifier_call = intel_vgpu_iommu_notifier;
-	vgpu->group_notifier.notifier_call = intel_vgpu_group_notifier;
 
 	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
 	ret = vfio_register_notifier(vfio_dev, VFIO_IOMMU_NOTIFY, &events,
@@ -817,38 +797,32 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 		goto out;
 	}
 
-	events = VFIO_GROUP_NOTIFY_SET_KVM;
-	ret = vfio_register_notifier(vfio_dev, VFIO_GROUP_NOTIFY, &events,
-				     &vgpu->group_notifier);
-	if (ret != 0) {
-		gvt_vgpu_err("vfio_register_notifier for group failed: %d\n",
-			ret);
-		goto undo_iommu;
-	}
-
 	ret = -EEXIST;
 	if (vgpu->attached)
-		goto undo_register;
+		goto undo_iommu;
 
 	ret = -ESRCH;
-	if (!vgpu->kvm || vgpu->kvm->mm != current->mm) {
+	if (!vgpu->vfio_device.kvm ||
+	    vgpu->vfio_device.kvm->mm != current->mm) {
 		gvt_vgpu_err("KVM is required to use Intel vGPU\n");
-		goto undo_register;
+		goto undo_iommu;
 	}
 
+	kvm_get_kvm(vgpu->vfio_device.kvm);
+
 	ret = -EEXIST;
 	if (__kvmgt_vgpu_exist(vgpu))
-		goto undo_register;
+		goto undo_iommu;
 
 	vgpu->attached = true;
-	kvm_get_kvm(vgpu->kvm);
 
 	kvmgt_protect_table_init(vgpu);
 	gvt_cache_init(vgpu);
 
 	vgpu->track_node.track_write = kvmgt_page_track_write;
 	vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
-	kvm_page_track_register_notifier(vgpu->kvm, &vgpu->track_node);
+	kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
+					 &vgpu->track_node);
 
 	debugfs_create_ulong(KVMGT_DEBUGFS_FILENAME, 0444, vgpu->debugfs,
 			     &vgpu->nr_cache_entries);
@@ -858,10 +832,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
 	atomic_set(&vgpu->released, 0);
 	return 0;
 
-undo_register:
-	vfio_unregister_notifier(vfio_dev, VFIO_GROUP_NOTIFY,
-				 &vgpu->group_notifier);
-
 undo_iommu:
 	vfio_unregister_notifier(vfio_dev, VFIO_IOMMU_NOTIFY,
 				 &vgpu->iommu_notifier);
@@ -880,8 +850,9 @@ static void intel_vgpu_release_msi_eventfd_ctx(struct intel_vgpu *vgpu)
 	}
 }
 
-static void __intel_vgpu_release(struct intel_vgpu *vgpu)
+static void intel_vgpu_close_device(struct vfio_device *vfio_dev)
 {
+	struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
 	struct drm_i915_private *i915 = vgpu->gvt->gt->i915;
 	int ret;
 
@@ -898,35 +869,19 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)
 	drm_WARN(&i915->drm, ret,
 		 "vfio_unregister_notifier for iommu failed: %d\n", ret);
 
-	ret = vfio_unregister_notifier(&vgpu->vfio_device, VFIO_GROUP_NOTIFY,
-				       &vgpu->group_notifier);
-	drm_WARN(&i915->drm, ret,
-		 "vfio_unregister_notifier for group failed: %d\n", ret);
-
 	debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs));
 
-	kvm_page_track_unregister_notifier(vgpu->kvm, &vgpu->track_node);
-	kvm_put_kvm(vgpu->kvm);
+	kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm,
+					   &vgpu->track_node);
 	kvmgt_protect_table_destroy(vgpu);
 	gvt_cache_destroy(vgpu);
 
 	intel_vgpu_release_msi_eventfd_ctx(vgpu);
 
-	vgpu->kvm = NULL;
 	vgpu->attached = false;
-}
-
-static void intel_vgpu_close_device(struct vfio_device *vfio_dev)
-{
-	__intel_vgpu_release(vfio_dev_to_vgpu(vfio_dev));
-}
-
-static void intel_vgpu_release_work(struct work_struct *work)
-{
-	struct intel_vgpu *vgpu =
-		container_of(work, struct intel_vgpu, release_work);
 
-	__intel_vgpu_release(vgpu);
+	if (vgpu->vfio_device.kvm)
+		kvm_put_kvm(vgpu->vfio_device.kvm);
 }
 
 static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
@@ -1675,7 +1630,6 @@ static int intel_vgpu_probe(struct mdev_device *mdev)
 		return PTR_ERR(vgpu);
 	}
 
-	INIT_WORK(&vgpu->release_work, intel_vgpu_release_work);
 	vfio_init_group_dev(&vgpu->vfio_device, &mdev->dev,
 			    &intel_vgpu_dev_ops);
 
@@ -1713,7 +1667,7 @@ static struct mdev_driver intel_vgpu_mdev_driver = {
 
 int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 {
-	struct kvm *kvm = info->kvm;
+	struct kvm *kvm = info->vfio_device.kvm;
 	struct kvm_memory_slot *slot;
 	int idx;
 
@@ -1743,7 +1697,7 @@ out:
 
 int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 {
-	struct kvm *kvm = info->kvm;
+	struct kvm *kvm = info->vfio_device.kvm;
 	struct kvm_memory_slot *slot;
 	int idx;
 
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index e8914024f5b1..a7d2a95796d3 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -1284,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 	}
 }
 
-static int vfio_ap_mdev_group_notifier(struct notifier_block *nb,
-				       unsigned long action, void *data)
-{
-	int notify_rc = NOTIFY_OK;
-	struct ap_matrix_mdev *matrix_mdev;
-
-	if (action != VFIO_GROUP_NOTIFY_SET_KVM)
-		return NOTIFY_OK;
-
-	matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier);
-
-	if (!data)
-		vfio_ap_mdev_unset_kvm(matrix_mdev);
-	else if (vfio_ap_mdev_set_kvm(matrix_mdev, data))
-		notify_rc = NOTIFY_DONE;
-
-	return notify_rc;
-}
-
 static struct vfio_ap_queue *vfio_ap_find_queue(int apqn)
 {
 	struct device *dev;
@@ -1402,11 +1383,10 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)
 	unsigned long events;
 	int ret;
 
-	matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier;
-	events = VFIO_GROUP_NOTIFY_SET_KVM;
+	if (!vdev->kvm)
+		return -EINVAL;
 
-	ret = vfio_register_notifier(vdev, VFIO_GROUP_NOTIFY, &events,
-				     &matrix_mdev->group_notifier);
+	ret = vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm);
 	if (ret)
 		return ret;
 
@@ -1415,12 +1395,11 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)
 	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY, &events,
 				     &matrix_mdev->iommu_notifier);
 	if (ret)
-		goto out_unregister_group;
+		goto err_kvm;
 	return 0;
 
-out_unregister_group:
-	vfio_unregister_notifier(vdev, VFIO_GROUP_NOTIFY,
-				 &matrix_mdev->group_notifier);
+err_kvm:
+	vfio_ap_mdev_unset_kvm(matrix_mdev);
 	return ret;
 }
 
@@ -1431,8 +1410,6 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev)
 
 	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY,
 				 &matrix_mdev->iommu_notifier);
-	vfio_unregister_notifier(vdev, VFIO_GROUP_NOTIFY,
-				 &matrix_mdev->group_notifier);
 	vfio_ap_mdev_unset_kvm(matrix_mdev);
 }
 
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index 648fcaf8104a..a26efd804d0d 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -81,8 +81,6 @@ struct ap_matrix {
  * @node:	allows the ap_matrix_mdev struct to be added to a list
  * @matrix:	the adapters, usage domains and control domains assigned to the
  *		mediated matrix device.
- * @group_notifier: notifier block used for specifying callback function for
- *		    handling the VFIO_GROUP_NOTIFY_SET_KVM event
  * @iommu_notifier: notifier block used for specifying callback function for
  *		    handling the VFIO_IOMMU_NOTIFY_DMA_UNMAP even
  * @kvm:	the struct holding guest's state
@@ -94,7 +92,6 @@ struct ap_matrix_mdev {
 	struct vfio_device vdev;
 	struct list_head node;
 	struct ap_matrix matrix;
-	struct notifier_block group_notifier;
 	struct notifier_block iommu_notifier;
 	struct kvm *kvm;
 	crypto_hook pqap_hook;
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index f5ed03897210..e22be13e6771 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1088,10 +1088,21 @@ static struct file *vfio_device_open(struct vfio_device *device)
 
 	mutex_lock(&device->dev_set->lock);
 	device->open_count++;
-	if (device->open_count == 1 && device->ops->open_device) {
-		ret = device->ops->open_device(device);
-		if (ret)
-			goto err_undo_count;
+	if (device->open_count == 1) {
+		/*
+		 * Here we pass the KVM pointer with the group under the read
+		 * lock.  If the device driver will use it, it must obtain a
+		 * reference and release it during close_device.
+		 */
+		down_read(&device->group->group_rwsem);
+		device->kvm = device->group->kvm;
+
+		if (device->ops->open_device) {
+			ret = device->ops->open_device(device);
+			if (ret)
+				goto err_undo_count;
+		}
+		up_read(&device->group->group_rwsem);
 	}
 	mutex_unlock(&device->dev_set->lock);
 
@@ -1124,10 +1135,14 @@ static struct file *vfio_device_open(struct vfio_device *device)
 
 err_close_device:
 	mutex_lock(&device->dev_set->lock);
+	down_read(&device->group->group_rwsem);
 	if (device->open_count == 1 && device->ops->close_device)
 		device->ops->close_device(device);
 err_undo_count:
 	device->open_count--;
+	if (device->open_count == 0 && device->kvm)
+		device->kvm = NULL;
+	up_read(&device->group->group_rwsem);
 	mutex_unlock(&device->dev_set->lock);
 	module_put(device->dev->driver->owner);
 err_unassign_container:
@@ -1320,9 +1335,13 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep)
 
 	mutex_lock(&device->dev_set->lock);
 	vfio_assert_device_open(device);
+	down_read(&device->group->group_rwsem);
 	if (device->open_count == 1 && device->ops->close_device)
 		device->ops->close_device(device);
+	up_read(&device->group->group_rwsem);
 	device->open_count--;
+	if (device->open_count == 0)
+		device->kvm = NULL;
 	mutex_unlock(&device->dev_set->lock);
 
 	module_put(device->dev->driver->owner);
@@ -1731,8 +1750,8 @@ EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);
  * @file: VFIO group file
  * @kvm: KVM to link
  *
- * The kvm pointer will be forwarded to all the vfio_device's attached to the
- * VFIO file via the VFIO_GROUP_NOTIFY_SET_KVM notifier.
+ * When a VFIO device is first opened the KVM will be available in
+ * device->kvm if one was associated with the group.
  */
 void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
 {
@@ -1743,8 +1762,6 @@ void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
 
 	down_write(&group->group_rwsem);
 	group->kvm = kvm;
-	blocking_notifier_call_chain(&group->notifier,
-				     VFIO_GROUP_NOTIFY_SET_KVM, kvm);
 	up_write(&group->group_rwsem);
 }
 EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
@@ -2011,7 +2028,8 @@ static int vfio_register_iommu_notifier(struct vfio_group *group,
 	struct vfio_iommu_driver *driver;
 	int ret;
 
-	down_read(&group->group_rwsem);
+	lockdep_assert_held_read(&group->group_rwsem);
+
 	container = group->container;
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->register_notifier))
@@ -2019,7 +2037,6 @@ static int vfio_register_iommu_notifier(struct vfio_group *group,
 						     events, nb);
 	else
 		ret = -ENOTTY;
-	up_read(&group->group_rwsem);
 
 	return ret;
 }
@@ -2031,7 +2048,8 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group,
 	struct vfio_iommu_driver *driver;
 	int ret;
 
-	down_read(&group->group_rwsem);
+	lockdep_assert_held_read(&group->group_rwsem);
+
 	container = group->container;
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->unregister_notifier))
@@ -2039,47 +2057,10 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group,
 						       nb);
 	else
 		ret = -ENOTTY;
-	up_read(&group->group_rwsem);
 
 	return ret;
 }
 
-static int vfio_register_group_notifier(struct vfio_group *group,
-					unsigned long *events,
-					struct notifier_block *nb)
-{
-	int ret;
-	bool set_kvm = false;
-
-	if (*events & VFIO_GROUP_NOTIFY_SET_KVM)
-		set_kvm = true;
-
-	/* clear known events */
-	*events &= ~VFIO_GROUP_NOTIFY_SET_KVM;
-
-	/* refuse to continue if still events remaining */
-	if (*events)
-		return -EINVAL;
-
-	ret = blocking_notifier_chain_register(&group->notifier, nb);
-	if (ret)
-		return ret;
-
-	/*
-	 * The attaching of kvm and vfio_group might already happen, so
-	 * here we replay once upon registration.
-	 */
-	if (set_kvm) {
-		down_read(&group->group_rwsem);
-		if (group->kvm)
-			blocking_notifier_call_chain(&group->notifier,
-						     VFIO_GROUP_NOTIFY_SET_KVM,
-						     group->kvm);
-		up_read(&group->group_rwsem);
-	}
-	return 0;
-}
-
 int vfio_register_notifier(struct vfio_device *device,
 			   enum vfio_notify_type type, unsigned long *events,
 			   struct notifier_block *nb)
@@ -2095,9 +2076,6 @@ int vfio_register_notifier(struct vfio_device *device,
 	case VFIO_IOMMU_NOTIFY:
 		ret = vfio_register_iommu_notifier(group, events, nb);
 		break;
-	case VFIO_GROUP_NOTIFY:
-		ret = vfio_register_group_notifier(group, events, nb);
-		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -2119,9 +2097,6 @@ int vfio_unregister_notifier(struct vfio_device *device,
 	case VFIO_IOMMU_NOTIFY:
 		ret = vfio_unregister_iommu_notifier(group, nb);
 		break;
-	case VFIO_GROUP_NOTIFY:
-		ret = blocking_notifier_chain_unregister(&group->notifier, nb);
-		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 45b287826ce6..aa888cc51757 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -36,6 +36,8 @@ struct vfio_device {
 	struct vfio_device_set *dev_set;
 	struct list_head dev_set_list;
 	unsigned int migration_flags;
+	/* Driver must reference the kvm during open_device or never touch it */
+	struct kvm *kvm;
 
 	/* Members below here are private, not for driver use */
 	refcount_t refcount;
@@ -155,15 +157,11 @@ extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova,
 /* each type has independent events */
 enum vfio_notify_type {
 	VFIO_IOMMU_NOTIFY = 0,
-	VFIO_GROUP_NOTIFY = 1,
 };
 
 /* events for VFIO_IOMMU_NOTIFY */
 #define VFIO_IOMMU_NOTIFY_DMA_UNMAP	BIT(0)
 
-/* events for VFIO_GROUP_NOTIFY */
-#define VFIO_GROUP_NOTIFY_SET_KVM	BIT(0)
-
 extern int vfio_register_notifier(struct vfio_device *device,
 				  enum vfio_notify_type type,
 				  unsigned long *required_events,
-- 
cgit v1.2.3


From eadb2f47a3ced5c64b23b90fd2a3463f63726066 Mon Sep 17 00:00:00 2001
From: Daniel Thompson <daniel.thompson@linaro.org>
Date: Mon, 23 May 2022 19:11:02 +0100
Subject: lockdown: also lock down previous kgdb use

KGDB and KDB allow read and write access to kernel memory, and thus
should be restricted during lockdown.  An attacker with access to a
serial port (for example, via a hypervisor console, which some cloud
vendors provide over the network) could trigger the debugger so it is
important that the debugger respect the lockdown mode when/if it is
triggered.

Fix this by integrating lockdown into kdb's existing permissions
mechanism.  Unfortunately kgdb does not have any permissions mechanism
(although it certainly could be added later) so, for now, kgdb is simply
and brutally disabled by immediately exiting the gdb stub without taking
any action.

For lockdowns established early in the boot (e.g. the normal case) then
this should be fine but on systems where kgdb has set breakpoints before
the lockdown is enacted than "bad things" will happen.

CVE: CVE-2022-21499
Co-developed-by: Stephen Brennan <stephen.s.brennan@oracle.com>
Signed-off-by: Stephen Brennan <stephen.s.brennan@oracle.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/security.h    |  2 ++
 kernel/debug/debug_core.c   | 24 ++++++++++++++++++
 kernel/debug/kdb/kdb_main.c | 62 ++++++++++++++++++++++++++++++++++++++++++---
 security/security.c         |  2 ++
 4 files changed, 87 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/security.h b/include/linux/security.h
index 25b3ef71f495..7fc4e9f49f54 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -121,10 +121,12 @@ enum lockdown_reason {
 	LOCKDOWN_DEBUGFS,
 	LOCKDOWN_XMON_WR,
 	LOCKDOWN_BPF_WRITE_USER,
+	LOCKDOWN_DBG_WRITE_KERNEL,
 	LOCKDOWN_INTEGRITY_MAX,
 	LOCKDOWN_KCORE,
 	LOCKDOWN_KPROBES,
 	LOCKDOWN_BPF_READ_KERNEL,
+	LOCKDOWN_DBG_READ_KERNEL,
 	LOCKDOWN_PERF,
 	LOCKDOWN_TRACEFS,
 	LOCKDOWN_XMON_RW,
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index da06a5553835..7beceb447211 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -53,6 +53,7 @@
 #include <linux/vmacache.h>
 #include <linux/rcupdate.h>
 #include <linux/irq.h>
+#include <linux/security.h>
 
 #include <asm/cacheflush.h>
 #include <asm/byteorder.h>
@@ -752,6 +753,29 @@ cpu_master_loop:
 				continue;
 			kgdb_connected = 0;
 		} else {
+			/*
+			 * This is a brutal way to interfere with the debugger
+			 * and prevent gdb being used to poke at kernel memory.
+			 * This could cause trouble if lockdown is applied when
+			 * there is already an active gdb session. For now the
+			 * answer is simply "don't do that". Typically lockdown
+			 * *will* be applied before the debug core gets started
+			 * so only developers using kgdb for fairly advanced
+			 * early kernel debug can be biten by this. Hopefully
+			 * they are sophisticated enough to take care of
+			 * themselves, especially with help from the lockdown
+			 * message printed on the console!
+			 */
+			if (security_locked_down(LOCKDOWN_DBG_WRITE_KERNEL)) {
+				if (IS_ENABLED(CONFIG_KGDB_KDB)) {
+					/* Switch back to kdb if possible... */
+					dbg_kdb_mode = 1;
+					continue;
+				} else {
+					/* ... otherwise just bail */
+					break;
+				}
+			}
 			error = gdb_serial_stub(ks);
 		}
 
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 0852a537dad4..ead4da947127 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -45,6 +45,7 @@
 #include <linux/proc_fs.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
+#include <linux/security.h>
 #include "kdb_private.h"
 
 #undef	MODULE_PARAM_PREFIX
@@ -166,10 +167,62 @@ struct task_struct *kdb_curr_task(int cpu)
 }
 
 /*
- * Check whether the flags of the current command and the permissions
- * of the kdb console has allow a command to be run.
+ * Update the permissions flags (kdb_cmd_enabled) to match the
+ * current lockdown state.
+ *
+ * Within this function the calls to security_locked_down() are "lazy". We
+ * avoid calling them if the current value of kdb_cmd_enabled already excludes
+ * flags that might be subject to lockdown. Additionally we deliberately check
+ * the lockdown flags independently (even though read lockdown implies write
+ * lockdown) since that results in both simpler code and clearer messages to
+ * the user on first-time debugger entry.
+ *
+ * The permission masks during a read+write lockdown permits the following
+ * flags: INSPECT, SIGNAL, REBOOT (and ALWAYS_SAFE).
+ *
+ * The INSPECT commands are not blocked during lockdown because they are
+ * not arbitrary memory reads. INSPECT covers the backtrace family (sometimes
+ * forcing them to have no arguments) and lsmod. These commands do expose
+ * some kernel state but do not allow the developer seated at the console to
+ * choose what state is reported. SIGNAL and REBOOT should not be controversial,
+ * given these are allowed for root during lockdown already.
+ */
+static void kdb_check_for_lockdown(void)
+{
+	const int write_flags = KDB_ENABLE_MEM_WRITE |
+				KDB_ENABLE_REG_WRITE |
+				KDB_ENABLE_FLOW_CTRL;
+	const int read_flags = KDB_ENABLE_MEM_READ |
+			       KDB_ENABLE_REG_READ;
+
+	bool need_to_lockdown_write = false;
+	bool need_to_lockdown_read = false;
+
+	if (kdb_cmd_enabled & (KDB_ENABLE_ALL | write_flags))
+		need_to_lockdown_write =
+			security_locked_down(LOCKDOWN_DBG_WRITE_KERNEL);
+
+	if (kdb_cmd_enabled & (KDB_ENABLE_ALL | read_flags))
+		need_to_lockdown_read =
+			security_locked_down(LOCKDOWN_DBG_READ_KERNEL);
+
+	/* De-compose KDB_ENABLE_ALL if required */
+	if (need_to_lockdown_write || need_to_lockdown_read)
+		if (kdb_cmd_enabled & KDB_ENABLE_ALL)
+			kdb_cmd_enabled = KDB_ENABLE_MASK & ~KDB_ENABLE_ALL;
+
+	if (need_to_lockdown_write)
+		kdb_cmd_enabled &= ~write_flags;
+
+	if (need_to_lockdown_read)
+		kdb_cmd_enabled &= ~read_flags;
+}
+
+/*
+ * Check whether the flags of the current command, the permissions of the kdb
+ * console and the lockdown state allow a command to be run.
  */
-static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions,
+static bool kdb_check_flags(kdb_cmdflags_t flags, int permissions,
 				   bool no_args)
 {
 	/* permissions comes from userspace so needs massaging slightly */
@@ -1180,6 +1233,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 		kdb_curr_task(raw_smp_processor_id());
 
 	KDB_DEBUG_STATE("kdb_local 1", reason);
+
+	kdb_check_for_lockdown();
+
 	kdb_go_count = 0;
 	if (reason == KDB_REASON_DEBUG) {
 		/* special case below */
diff --git a/security/security.c b/security/security.c
index b7cf5cbfdc67..aaf6566deb9f 100644
--- a/security/security.c
+++ b/security/security.c
@@ -59,10 +59,12 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = {
 	[LOCKDOWN_DEBUGFS] = "debugfs access",
 	[LOCKDOWN_XMON_WR] = "xmon write access",
 	[LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM",
+	[LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM",
 	[LOCKDOWN_INTEGRITY_MAX] = "integrity",
 	[LOCKDOWN_KCORE] = "/proc/kcore access",
 	[LOCKDOWN_KPROBES] = "use of kprobes",
 	[LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM",
+	[LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM",
 	[LOCKDOWN_PERF] = "unsafe use of perf",
 	[LOCKDOWN_TRACEFS] = "use of tracefs",
 	[LOCKDOWN_XMON_RW] = "xmon read and write access",
-- 
cgit v1.2.3


From 43994049180704fd1faf78623fabd9a5cd443708 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 4 May 2022 12:36:31 +0900
Subject: kprobes: Fix build errors with CONFIG_KRETPROBES=n
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Max Filippov reported:

When building kernel with CONFIG_KRETPROBES=n kernel/kprobes.c
compilation fails with the following messages:

  kernel/kprobes.c: In function ‘recycle_rp_inst’:
  kernel/kprobes.c:1273:32: error: implicit declaration of function
                                   ‘get_kretprobe’

  kernel/kprobes.c: In function ‘kprobe_flush_task’:
  kernel/kprobes.c:1299:35: error: ‘struct task_struct’ has no member
                                   named ‘kretprobe_instances’

This came from the commit d741bf41d7c7 ("kprobes: Remove
kretprobe hash") which introduced get_kretprobe() and
kretprobe_instances member in task_struct when CONFIG_KRETPROBES=y,
but did not make recycle_rp_inst() and kprobe_flush_task()
depending on CONFIG_KRETPORBES.

Since those functions are only used for kretprobe, move those
functions into #ifdef CONFIG_KRETPROBE area.

Link: https://lkml.kernel.org/r/165163539094.74407.3838114721073251225.stgit@devnote2

Reported-by: Max Filippov <jcmvbkbc@gmail.com>
Fixes: d741bf41d7c7 ("kprobes: Remove kretprobe hash")
Cc: "Naveen N . Rao" <naveen.n.rao@linux.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: "David S . Miller" <davem@davemloft.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Tested-by: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/kprobes.h |   2 +-
 kernel/kprobes.c        | 144 ++++++++++++++++++++++++------------------------
 2 files changed, 72 insertions(+), 74 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 157168769fc2..55041d2f884d 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -424,7 +424,7 @@ void unregister_kretprobe(struct kretprobe *rp);
 int register_kretprobes(struct kretprobe **rps, int num);
 void unregister_kretprobes(struct kretprobe **rps, int num);
 
-#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+#if defined(CONFIG_KRETPROBE_ON_RETHOOK) || !defined(CONFIG_KRETPROBES)
 #define kprobe_flush_task(tk)	do {} while (0)
 #else
 void kprobe_flush_task(struct task_struct *tk);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index dbe57df2e199..172ba75a4a49 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1257,79 +1257,6 @@ void kprobe_busy_end(void)
 	preempt_enable();
 }
 
-#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
-static void free_rp_inst_rcu(struct rcu_head *head)
-{
-	struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
-
-	if (refcount_dec_and_test(&ri->rph->ref))
-		kfree(ri->rph);
-	kfree(ri);
-}
-NOKPROBE_SYMBOL(free_rp_inst_rcu);
-
-static void recycle_rp_inst(struct kretprobe_instance *ri)
-{
-	struct kretprobe *rp = get_kretprobe(ri);
-
-	if (likely(rp))
-		freelist_add(&ri->freelist, &rp->freelist);
-	else
-		call_rcu(&ri->rcu, free_rp_inst_rcu);
-}
-NOKPROBE_SYMBOL(recycle_rp_inst);
-
-/*
- * This function is called from delayed_put_task_struct() when a task is
- * dead and cleaned up to recycle any kretprobe instances associated with
- * this task. These left over instances represent probed functions that
- * have been called but will never return.
- */
-void kprobe_flush_task(struct task_struct *tk)
-{
-	struct kretprobe_instance *ri;
-	struct llist_node *node;
-
-	/* Early boot, not yet initialized. */
-	if (unlikely(!kprobes_initialized))
-		return;
-
-	kprobe_busy_begin();
-
-	node = __llist_del_all(&tk->kretprobe_instances);
-	while (node) {
-		ri = container_of(node, struct kretprobe_instance, llist);
-		node = node->next;
-
-		recycle_rp_inst(ri);
-	}
-
-	kprobe_busy_end();
-}
-NOKPROBE_SYMBOL(kprobe_flush_task);
-
-static inline void free_rp_inst(struct kretprobe *rp)
-{
-	struct kretprobe_instance *ri;
-	struct freelist_node *node;
-	int count = 0;
-
-	node = rp->freelist.head;
-	while (node) {
-		ri = container_of(node, struct kretprobe_instance, freelist);
-		node = node->next;
-
-		kfree(ri);
-		count++;
-	}
-
-	if (refcount_sub_and_test(count, &rp->rph->ref)) {
-		kfree(rp->rph);
-		rp->rph = NULL;
-	}
-}
-#endif	/* !CONFIG_KRETPROBE_ON_RETHOOK */
-
 /* Add the new probe to 'ap->list'. */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
@@ -1928,6 +1855,77 @@ static struct notifier_block kprobe_exceptions_nb = {
 #ifdef CONFIG_KRETPROBES
 
 #if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
+static void free_rp_inst_rcu(struct rcu_head *head)
+{
+	struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
+
+	if (refcount_dec_and_test(&ri->rph->ref))
+		kfree(ri->rph);
+	kfree(ri);
+}
+NOKPROBE_SYMBOL(free_rp_inst_rcu);
+
+static void recycle_rp_inst(struct kretprobe_instance *ri)
+{
+	struct kretprobe *rp = get_kretprobe(ri);
+
+	if (likely(rp))
+		freelist_add(&ri->freelist, &rp->freelist);
+	else
+		call_rcu(&ri->rcu, free_rp_inst_rcu);
+}
+NOKPROBE_SYMBOL(recycle_rp_inst);
+
+/*
+ * This function is called from delayed_put_task_struct() when a task is
+ * dead and cleaned up to recycle any kretprobe instances associated with
+ * this task. These left over instances represent probed functions that
+ * have been called but will never return.
+ */
+void kprobe_flush_task(struct task_struct *tk)
+{
+	struct kretprobe_instance *ri;
+	struct llist_node *node;
+
+	/* Early boot, not yet initialized. */
+	if (unlikely(!kprobes_initialized))
+		return;
+
+	kprobe_busy_begin();
+
+	node = __llist_del_all(&tk->kretprobe_instances);
+	while (node) {
+		ri = container_of(node, struct kretprobe_instance, llist);
+		node = node->next;
+
+		recycle_rp_inst(ri);
+	}
+
+	kprobe_busy_end();
+}
+NOKPROBE_SYMBOL(kprobe_flush_task);
+
+static inline void free_rp_inst(struct kretprobe *rp)
+{
+	struct kretprobe_instance *ri;
+	struct freelist_node *node;
+	int count = 0;
+
+	node = rp->freelist.head;
+	while (node) {
+		ri = container_of(node, struct kretprobe_instance, freelist);
+		node = node->next;
+
+		kfree(ri);
+		count++;
+	}
+
+	if (refcount_sub_and_test(count, &rp->rph->ref)) {
+		kfree(rp->rph);
+		rp->rph = NULL;
+	}
+}
+
 /* This assumes the 'tsk' is the current task or the is not running. */
 static kprobe_opcode_t *__kretprobe_find_ret_addr(struct task_struct *tsk,
 						  struct llist_node **cur)
-- 
cgit v1.2.3


From 3a2bfec0b02f2226ff3376a5d2ff604d799bd7ea Mon Sep 17 00:00:00 2001
From: Li kunyu <kunyu@nfschina.com>
Date: Wed, 18 May 2022 10:36:40 +0800
Subject: ftrace: Remove return value of ftrace_arch_modify_*()

All instances of the function ftrace_arch_modify_prepare() and
  ftrace_arch_modify_post_process() return zero. There's no point in
  checking their return value. Just have them be void functions.

Link: https://lkml.kernel.org/r/20220518023639.4065-1-kunyu@nfschina.com

Signed-off-by: Li kunyu <kunyu@nfschina.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 arch/arm/kernel/ftrace.c   |  6 ++----
 arch/riscv/kernel/ftrace.c |  6 ++----
 arch/s390/kernel/ftrace.c  |  3 +--
 arch/x86/kernel/ftrace.c   |  6 ++----
 include/linux/ftrace.h     |  4 ++--
 kernel/trace/ftrace.c      | 16 ++++------------
 6 files changed, 13 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 83cc068586bc..a0b6d1e3812f 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -79,16 +79,14 @@ static unsigned long __ref adjust_address(struct dyn_ftrace *rec,
 	return (unsigned long)&ftrace_regs_caller_from_init;
 }
 
-int ftrace_arch_code_modify_prepare(void)
+void ftrace_arch_code_modify_prepare(void)
 {
-	return 0;
 }
 
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
 {
 	/* Make sure any TLB misses during machine stop are cleared. */
 	flush_tlb_all();
-	return 0;
 }
 
 static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr,
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 4716f4cdc038..2086f6585773 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -12,16 +12,14 @@
 #include <asm/patch.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
+void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
 {
 	mutex_lock(&text_mutex);
-	return 0;
 }
 
-int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
+void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
 {
 	mutex_unlock(&text_mutex);
-	return 0;
 }
 
 static int ftrace_check_current_call(unsigned long hook_pos,
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 1852d46babb1..416b5a94353d 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -225,14 +225,13 @@ void arch_ftrace_update_code(int command)
 	ftrace_modify_all_code(command);
 }
 
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
 {
 	/*
 	 * Flush any pre-fetched instructions on all
 	 * CPUs to make the new code visible.
 	 */
 	text_poke_sync_lock();
-	return 0;
 }
 
 #ifdef CONFIG_MODULES
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1e31c7d21597..73d2719ed12c 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -37,7 +37,7 @@
 
 static int ftrace_poke_late = 0;
 
-int ftrace_arch_code_modify_prepare(void)
+void ftrace_arch_code_modify_prepare(void)
     __acquires(&text_mutex)
 {
 	/*
@@ -47,10 +47,9 @@ int ftrace_arch_code_modify_prepare(void)
 	 */
 	mutex_lock(&text_mutex);
 	ftrace_poke_late = 1;
-	return 0;
 }
 
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
     __releases(&text_mutex)
 {
 	/*
@@ -61,7 +60,6 @@ int ftrace_arch_code_modify_post_process(void)
 	text_poke_finish();
 	ftrace_poke_late = 0;
 	mutex_unlock(&text_mutex);
-	return 0;
 }
 
 static const char *ftrace_nop_replace(void)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4816b7e11047..a5f74f6e7e4e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -449,8 +449,8 @@ static inline void stack_tracer_enable(void) { }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
-int ftrace_arch_code_modify_prepare(void);
-int ftrace_arch_code_modify_post_process(void);
+void ftrace_arch_code_modify_prepare(void);
+void ftrace_arch_code_modify_post_process(void);
 
 enum ftrace_bug_type {
 	FTRACE_BUG_UNKNOWN,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 737e895e2aad..852c731cbd9a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2704,18 +2704,16 @@ ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec)
  * archs can override this function if they must do something
  * before the modifying code is performed.
  */
-int __weak ftrace_arch_code_modify_prepare(void)
+void __weak ftrace_arch_code_modify_prepare(void)
 {
-	return 0;
 }
 
 /*
  * archs can override this function if they must do something
  * after the modifying code is performed.
  */
-int __weak ftrace_arch_code_modify_post_process(void)
+void __weak ftrace_arch_code_modify_post_process(void)
 {
-	return 0;
 }
 
 void ftrace_modify_all_code(int command)
@@ -2801,12 +2799,7 @@ void __weak arch_ftrace_update_code(int command)
 
 static void ftrace_run_update_code(int command)
 {
-	int ret;
-
-	ret = ftrace_arch_code_modify_prepare();
-	FTRACE_WARN_ON(ret);
-	if (ret)
-		return;
+	ftrace_arch_code_modify_prepare();
 
 	/*
 	 * By default we use stop_machine() to modify the code.
@@ -2816,8 +2809,7 @@ static void ftrace_run_update_code(int command)
 	 */
 	arch_ftrace_update_code(command);
 
-	ret = ftrace_arch_code_modify_post_process();
-	FTRACE_WARN_ON(ret);
+	ftrace_arch_code_modify_post_process();
 }
 
 static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
-- 
cgit v1.2.3


From 656d054e0a15ec327bd82801ccd58201e59f6896 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 2 May 2022 12:30:20 +0200
Subject: jump_label,noinstr: Avoid instrumentation for JUMP_LABEL=n builds

When building x86_64 with JUMP_LABEL=n it's possible for
instrumentation to sneak into noinstr:

vmlinux.o: warning: objtool: exit_to_user_mode+0x14: call to static_key_count.constprop.0() leaves .noinstr.text section
vmlinux.o: warning: objtool: syscall_exit_to_user_mode+0x2d: call to static_key_count.constprop.0() leaves .noinstr.text section
vmlinux.o: warning: objtool: irqentry_exit_to_user_mode+0x1b: call to static_key_count.constprop.0() leaves .noinstr.text section

Switch to arch_ prefixed atomic to avoid the explicit instrumentation.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/jump_label.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 107751cc047b..bf1eef337a07 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -256,9 +256,9 @@ extern void static_key_disable_cpuslocked(struct static_key *key);
 #include <linux/atomic.h>
 #include <linux/bug.h>
 
-static inline int static_key_count(struct static_key *key)
+static __always_inline int static_key_count(struct static_key *key)
 {
-	return atomic_read(&key->enabled);
+	return arch_atomic_read(&key->enabled);
 }
 
 static __always_inline void jump_label_init(void)
-- 
cgit v1.2.3


From 620f8d3bd3d5e82dff8cc591c831827d4beeae2e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 7 May 2022 13:35:37 +0200
Subject: context_tracking: Always inline empty stubs

Because GCC is seriously challenged..

vmlinux.o: warning: objtool: enter_from_user_mode+0x85: call to context_tracking_enabled() leaves .noinstr.text section
vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x8f: call to context_tracking_enabled() leaves .noinstr.text section
vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0x85: call to context_tracking_enabled() leaves .noinstr.text section
vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0x85: call to context_tracking_enabled() leaves .noinstr.text section

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lkml.kernel.org/r/20220526105958.134113388@infradead.org
---
 include/linux/context_tracking_state.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index 65a60d3313b0..ae1e63e26947 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -46,10 +46,10 @@ static __always_inline bool context_tracking_in_user(void)
 	return __this_cpu_read(context_tracking.state) == CONTEXT_USER;
 }
 #else
-static inline bool context_tracking_in_user(void) { return false; }
-static inline bool context_tracking_enabled(void) { return false; }
-static inline bool context_tracking_enabled_cpu(int cpu) { return false; }
-static inline bool context_tracking_enabled_this_cpu(void) { return false; }
+static __always_inline bool context_tracking_in_user(void) { return false; }
+static __always_inline bool context_tracking_enabled(void) { return false; }
+static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; }
+static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; }
 #endif /* CONFIG_CONTEXT_TRACKING */
 
 #endif
-- 
cgit v1.2.3


From b9684a71fca793213378dd410cd11675d973eaa1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 27 May 2022 07:58:06 +0200
Subject: block, loop: support partitions without scanning

Historically we did distinguish between a flag that surpressed partition
scanning, and a combinations of the minors variable and another flag if
any partitions were supported.  This was generally confusing and doesn't
make much sense, but some corner case uses of the loop driver actually
do want to support manually added partitions on a device that does not
actively scan for partitions.  To make things worsee the loop driver
also wants to dynamically toggle the scanning for partitions on a live
gendisk, which makes the disk->flags updates non-atomic.

Introduce a new GD_SUPPRESS_PART_SCAN bit in disk->state that disables
just scanning for partitions, and toggle that instead of GENHD_FL_NO_PART
in the loop driver.

Fixes: 1ebe2e5f9d68 ("block: remove GENHD_FL_EXT_DEVT")
Reported-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20220527055806.1972352-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c          | 2 ++
 drivers/block/loop.c   | 8 ++++----
 include/linux/blkdev.h | 1 +
 3 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 36532b931841..27205ae47d59 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -385,6 +385,8 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 
 	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
 		return -EINVAL;
+	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+		return -EINVAL;
 	if (disk->open_partitions)
 		return -EBUSY;
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 01b4e257016a..121f96dfc23e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1102,7 +1102,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
 	if (partscan)
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART;
+		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 
 	loop_global_unlock(lo, is_loop);
 	if (partscan)
@@ -1198,7 +1198,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 	 */
 	lo->lo_flags = 0;
 	if (!part_shift)
-		lo->lo_disk->flags |= GENHD_FL_NO_PART;
+		set_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 	mutex_lock(&lo->lo_mutex);
 	lo->lo_state = Lo_unbound;
 	mutex_unlock(&lo->lo_mutex);
@@ -1308,7 +1308,7 @@ out_unfreeze:
 
 	if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) &&
 	     !(prev_lo_flags & LO_FLAGS_PARTSCAN)) {
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART;
+		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 		partscan = true;
 	}
 out_unlock:
@@ -2009,7 +2009,7 @@ static int loop_add(int i)
 	 * userspace tools. Parameters like this in general should be avoided.
 	 */
 	if (!part_shift)
-		disk->flags |= GENHD_FL_NO_PART;
+		set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 	mutex_init(&lo->lo_mutex);
 	lo->lo_number		= i;
 	spin_lock_init(&lo->lo_lock);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index afad3d1d0dac..691b4c15b8ce 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -147,6 +147,7 @@ struct gendisk {
 #define GD_DEAD				2
 #define GD_NATIVE_CAPACITY		3
 #define GD_ADDED			4
+#define GD_SUPPRESS_PART_SCAN		5
 
 	struct mutex open_mutex;	/* open/close mutex */
 	unsigned open_partitions;	/* number of open partitions */
-- 
cgit v1.2.3


From 3e35142ef99fe6b4fe5d834ad43ee13cca10a2dc Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Thu, 19 May 2022 14:42:37 +0530
Subject: kexec_file: drop weak attribute from
 arch_kexec_apply_relocations[_add]

Since commit d1bcae833b32f1 ("ELF: Don't generate unused section
symbols") [1], binutils (v2.36+) started dropping section symbols that
it thought were unused.  This isn't an issue in general, but with
kexec_file.c, gcc is placing kexec_arch_apply_relocations[_add] into a
separate .text.unlikely section and the section symbol ".text.unlikely"
is being dropped. Due to this, recordmcount is unable to find a non-weak
symbol in .text.unlikely to generate a relocation record against.

Address this by dropping the weak attribute from these functions.
Instead, follow the existing pattern of having architectures #define the
name of the function they want to override in their headers.

[1] https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=d1bcae833b32f1

[akpm@linux-foundation.org: arch/s390/include/asm/kexec.h needs linux/module.h]
Link: https://lkml.kernel.org/r/20220519091237.676736-1-naveen.n.rao@linux.vnet.ibm.com
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/s390/include/asm/kexec.h | 10 ++++++++++
 arch/x86/include/asm/kexec.h  |  8 ++++++++
 include/linux/kexec.h         | 46 +++++++++++++++++++++++++++++++++++--------
 kernel/kexec_file.c           | 34 --------------------------------
 4 files changed, 56 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 7f3c9ac34bd8..63098df81c9f 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -9,6 +9,8 @@
 #ifndef _S390_KEXEC_H
 #define _S390_KEXEC_H
 
+#include <linux/module.h>
+
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/setup.h>
@@ -83,4 +85,12 @@ struct kimage_arch {
 extern const struct kexec_file_ops s390_kexec_image_ops;
 extern const struct kexec_file_ops s390_kexec_elf_ops;
 
+#ifdef CONFIG_KEXEC_FILE
+struct purgatory_info;
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+				     Elf_Shdr *section,
+				     const Elf_Shdr *relsec,
+				     const Elf_Shdr *symtab);
+#define arch_kexec_apply_relocations_add arch_kexec_apply_relocations_add
+#endif
 #endif /*_S390_KEXEC_H */
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 11b7c06e2828..6ad8d946cd3e 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -186,6 +186,14 @@ extern int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages,
 extern void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages);
 #define arch_kexec_pre_free_pages arch_kexec_pre_free_pages
 
+#ifdef CONFIG_KEXEC_FILE
+struct purgatory_info;
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+				     Elf_Shdr *section,
+				     const Elf_Shdr *relsec,
+				     const Elf_Shdr *symtab);
+#define arch_kexec_apply_relocations_add arch_kexec_apply_relocations_add
+#endif
 #endif
 
 typedef void crash_vmclear_fn(void);
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 58d1b58a971e..fcd5035209f1 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -193,14 +193,6 @@ void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name);
 int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
 				  unsigned long buf_len);
 void *arch_kexec_kernel_image_load(struct kimage *image);
-int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
-				     Elf_Shdr *section,
-				     const Elf_Shdr *relsec,
-				     const Elf_Shdr *symtab);
-int arch_kexec_apply_relocations(struct purgatory_info *pi,
-				 Elf_Shdr *section,
-				 const Elf_Shdr *relsec,
-				 const Elf_Shdr *symtab);
 int arch_kimage_file_post_load_cleanup(struct kimage *image);
 #ifdef CONFIG_KEXEC_SIG
 int arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
@@ -229,6 +221,44 @@ extern int crash_exclude_mem_range(struct crash_mem *mem,
 				   unsigned long long mend);
 extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 				       void **addr, unsigned long *sz);
+
+#ifndef arch_kexec_apply_relocations_add
+/*
+ * arch_kexec_apply_relocations_add - apply relocations of type RELA
+ * @pi:		Purgatory to be relocated.
+ * @section:	Section relocations applying to.
+ * @relsec:	Section containing RELAs.
+ * @symtab:	Corresponding symtab.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+static inline int
+arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section,
+				 const Elf_Shdr *relsec, const Elf_Shdr *symtab)
+{
+	pr_err("RELA relocation unsupported.\n");
+	return -ENOEXEC;
+}
+#endif
+
+#ifndef arch_kexec_apply_relocations
+/*
+ * arch_kexec_apply_relocations - apply relocations of type REL
+ * @pi:		Purgatory to be relocated.
+ * @section:	Section relocations applying to.
+ * @relsec:	Section containing RELs.
+ * @symtab:	Corresponding symtab.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+static inline int
+arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section,
+			     const Elf_Shdr *relsec, const Elf_Shdr *symtab)
+{
+	pr_err("REL relocation unsupported.\n");
+	return -ENOEXEC;
+}
+#endif
 #endif /* CONFIG_KEXEC_FILE */
 
 #ifdef CONFIG_KEXEC_ELF
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 8347fc158d2b..c108a2a88754 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -108,40 +108,6 @@ int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
 }
 #endif
 
-/*
- * arch_kexec_apply_relocations_add - apply relocations of type RELA
- * @pi:		Purgatory to be relocated.
- * @section:	Section relocations applying to.
- * @relsec:	Section containing RELAs.
- * @symtab:	Corresponding symtab.
- *
- * Return: 0 on success, negative errno on error.
- */
-int __weak
-arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section,
-				 const Elf_Shdr *relsec, const Elf_Shdr *symtab)
-{
-	pr_err("RELA relocation unsupported.\n");
-	return -ENOEXEC;
-}
-
-/*
- * arch_kexec_apply_relocations - apply relocations of type REL
- * @pi:		Purgatory to be relocated.
- * @section:	Section relocations applying to.
- * @relsec:	Section containing RELs.
- * @symtab:	Corresponding symtab.
- *
- * Return: 0 on success, negative errno on error.
- */
-int __weak
-arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section,
-			     const Elf_Shdr *relsec, const Elf_Shdr *symtab)
-{
-	pr_err("REL relocation unsupported.\n");
-	return -ENOEXEC;
-}
-
 /*
  * Free up memory used by kernel, initrd, and command line. This is temporary
  * memory allocation which is not needed any more after these buffers have
-- 
cgit v1.2.3


From 9f186f9e5fa9ebdaef909fd45f825a6ce281f13c Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 19 May 2022 20:50:26 +0800
Subject: mm/swapfile: unuse_pte can map random data if swap read fails

Patch series "A few fixup patches for mm", v4.

This series contains a few patches to avoid mapping random data if swap
read fails and fix lost swap bits in unuse_pte.  Also we free hwpoison and
swapin error entry in madvise_free_pte_range and so on.  More details can
be found in the respective changelogs.


This patch (of 5):

There is a bug in unuse_pte(): when swap page happens to be unreadable,
page filled with random data is mapped into user address space.  In case
of error, a special swap entry indicating swap read fails is set to the
page table.  So the swapcache page can be freed and the user won't end up
with a permanently mounted swap because a sector is bad.  And if the page
is accessed later, the user process will be killed so that corrupted data
is never consumed.  On the other hand, if the page is never accessed, the
user won't even notice it.

Link: https://lkml.kernel.org/r/20220519125030.21486-1-linmiaohe@huawei.com
Link: https://lkml.kernel.org/r/20220519125030.21486-2-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Howells <dhowells@redhat.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h    |  7 ++++++-
 include/linux/swapops.h | 10 ++++++++++
 mm/memory.c             |  5 ++++-
 mm/swapfile.c           | 11 +++++++++++
 4 files changed, 31 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index f3ae17b43f20..0c0fed1b348f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -55,6 +55,10 @@ static inline int current_is_kswapd(void)
  * actions on faults.
  */
 
+#define SWP_SWAPIN_ERROR_NUM 1
+#define SWP_SWAPIN_ERROR     (MAX_SWAPFILES + SWP_HWPOISON_NUM + \
+			     SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \
+			     SWP_PTE_MARKER_NUM)
 /*
  * PTE markers are used to persist information onto PTEs that are mapped with
  * file-backed memories.  As its name "PTE" hints, it should only be applied to
@@ -120,7 +124,8 @@ static inline int current_is_kswapd(void)
 
 #define MAX_SWAPFILES \
 	((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \
-	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM)
+	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \
+	SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM)
 
 /*
  * Magic header for a swap area. The first part of the union is
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index fe220df499f1..f24775b41880 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -108,6 +108,16 @@ static inline void *swp_to_radix_entry(swp_entry_t entry)
 	return xa_mk_value(entry.val);
 }
 
+static inline swp_entry_t make_swapin_error_entry(struct page *page)
+{
+	return swp_entry(SWP_SWAPIN_ERROR, page_to_pfn(page));
+}
+
+static inline int is_swapin_error_entry(swp_entry_t entry)
+{
+	return swp_type(entry) == SWP_SWAPIN_ERROR;
+}
+
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
 static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
 {
diff --git a/mm/memory.c b/mm/memory.c
index 2bf5bca39567..54d106e0c999 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1487,7 +1487,8 @@ again:
 			/* Only drop the uffd-wp marker if explicitly requested */
 			if (!zap_drop_file_uffd_wp(details))
 				continue;
-		} else if (is_hwpoison_entry(entry)) {
+		} else if (is_hwpoison_entry(entry) ||
+			   is_swapin_error_entry(entry)) {
 			if (!should_zap_cows(details))
 				continue;
 		} else {
@@ -3727,6 +3728,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
+		} else if (is_swapin_error_entry(entry)) {
+			ret = VM_FAULT_SIGBUS;
 		} else if (is_pte_marker_entry(entry)) {
 			ret = handle_pte_marker(vmf);
 		} else {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a0eb690d9926..b86d1cc8d00b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1788,6 +1788,17 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		goto out;
 	}
 
+	if (unlikely(!PageUptodate(page))) {
+		pte_t pteval;
+
+		dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
+		pteval = swp_entry_to_pte(make_swapin_error_entry(page));
+		set_pte_at(vma->vm_mm, addr, pte, pteval);
+		swap_free(entry);
+		ret = 0;
+		goto out;
+	}
+
 	/* See do_swap_page() */
 	BUG_ON(!PageAnon(page) && PageMappedToDisk(page));
 	BUG_ON(PageAnon(page) && PageAnonExclusive(page));
-- 
cgit v1.2.3


From 1c563432588dbffa71e67ca6e37c826f9fa86e04 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Tue, 24 May 2022 10:15:25 -0700
Subject: mm: fix is_pinnable_page against a cma page

Pages in the CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA so
the current is_pinnable_page() could miss CMA pages which have
MIGRATE_ISOLATE.  It ends up pinning CMA pages as longterm for the
pin_user_pages() API so CMA allocations keep failing until the pin is
released.

     CPU 0                                   CPU 1 - Task B

cma_alloc
alloc_contig_range
                                        pin_user_pages_fast(FOLL_LONGTERM)
change pageblock as MIGRATE_ISOLATE
                                        internal_get_user_pages_fast
                                        lockless_pages_from_mm
                                        gup_pte_range
                                        try_grab_folio
                                        is_pinnable_page
                                          return true;
                                        So, pinned the page successfully.
page migration failure with pinned page
                                        ..
                                        .. After 30 sec
                                        unpin_user_page(page)

CMA allocation succeeded after 30 sec.

The CMA allocation path protects the migration type change race using
zone->lock but what GUP path need to know is just whether the page is on
CMA area or not rather than exact migration type.  Thus, we don't need
zone->lock but just checks migration type in either of (MIGRATE_ISOLATE
and MIGRATE_CMA).

Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause rejecting
of pinning pages on MIGRATE_ISOLATE pageblocks even though it's neither
CMA nor movable zone if the page is temporarily unmovable.  However, such
a migration failure by unexpected temporal refcount holding is general
issue, not only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also
transient state like other temporal elevated refcount problem.

Link: https://lkml.kernel.org/r/20220524171525.976723-1-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 9 +++++++--
 mm/page_alloc.c    | 8 ++++++--
 2 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index de32c0383387..93a46ff33dc2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1594,8 +1594,13 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 #ifdef CONFIG_MIGRATION
 static inline bool is_pinnable_page(struct page *page)
 {
-	return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) ||
-		is_zero_pfn(page_to_pfn(page));
+#ifdef CONFIG_CMA
+	int mt = get_pageblock_migratetype(page);
+
+	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
+		return false;
+#endif
+	return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page)));
 }
 #else
 static inline bool is_pinnable_page(struct page *page)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6f6e4649ac21..56b3a5d67325 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -482,8 +482,12 @@ unsigned long __get_pfnblock_flags_mask(const struct page *page,
 	bitidx = pfn_to_bitidx(page, pfn);
 	word_bitidx = bitidx / BITS_PER_LONG;
 	bitidx &= (BITS_PER_LONG-1);
-
-	word = bitmap[word_bitidx];
+	/*
+	 * This races, without locks, with set_pfnblock_flags_mask(). Ensure
+	 * a consistent read of the memory array, so that results, even though
+	 * racy, are not corrupted.
+	 */
+	word = READ_ONCE(bitmap[word_bitidx]);
 	return (word >> bitidx) & mask;
 }
 
-- 
cgit v1.2.3


From 98d40e76652e9aeb3aec4065f600d633ed335e94 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Tue, 24 May 2022 07:56:30 +0200
Subject: block: document BLK_STS_AGAIN usage

BLK_STS_AGAIN should only be used if RQF_NOWAIT is set and the bio
would block. So we'd better document that to avoid accidental misuse.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220524055631.85480-2-hare@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 40e815400611..8b38367d1bc7 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -105,6 +105,10 @@ typedef u16 blk_short_t;
 /* hack for device mapper, don't use elsewhere: */
 #define BLK_STS_DM_REQUEUE    ((__force blk_status_t)11)
 
+/*
+ * BLK_STS_AGAIN should only be returned if RQF_NOWAIT is set
+ * and the bio would block (cf bio_wouldblock_error())
+ */
 #define BLK_STS_AGAIN		((__force blk_status_t)12)
 
 /*
-- 
cgit v1.2.3


From e2e530867245d051dc7800b0d07193b3e581f5b9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 May 2022 14:15:30 +0200
Subject: blk-mq: remove the done argument to blk_execute_rq_nowait

Let the caller set it together with the end_io_data instead of passing
a pointless argument.  Note the the target code did in fact already
set it and then just overrode it again by calling blk_execute_rq_nowait.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220524121530.943123-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c                     |  5 +----
 drivers/block/sx8.c                |  4 ++--
 drivers/nvme/host/core.c           |  3 ++-
 drivers/nvme/host/ioctl.c          |  3 ++-
 drivers/nvme/host/pci.c            | 10 +++++++---
 drivers/nvme/target/passthru.c     |  3 ++-
 drivers/scsi/scsi_error.c          |  5 +++--
 drivers/scsi/sg.c                  |  3 ++-
 drivers/scsi/st.c                  |  3 ++-
 drivers/scsi/ufs/ufshpb.c          |  6 ++++--
 drivers/target/target_core_pscsi.c |  3 +--
 include/linux/blk-mq.h             |  3 +--
 12 files changed, 29 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 28b3e6db9849..8e7860268f61 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1189,7 +1189,6 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  * blk_execute_rq_nowait - insert a request to I/O scheduler for execution
  * @rq:		request to insert
  * @at_head:    insert request at head or tail of queue
- * @done:	I/O completion handler
  *
  * Description:
  *    Insert a fully prepared request at the back of the I/O scheduler queue
@@ -1198,13 +1197,11 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  * Note:
  *    This function will invoke @done directly if the queue is dead.
  */
-void blk_execute_rq_nowait(struct request *rq, bool at_head, rq_end_io_fn *done)
+void blk_execute_rq_nowait(struct request *rq, bool at_head)
 {
 	WARN_ON(irqs_disabled());
 	WARN_ON(!blk_rq_is_passthrough(rq));
 
-	rq->end_io = done;
-
 	blk_account_io_start(rq);
 	if (current->plug)
 		blk_add_rq_to_plug(current->plug, rq);
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index b361583944b9..63b4f6431d2e 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -540,7 +540,7 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx)
 	spin_unlock_irq(&host->lock);
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag);
-	blk_execute_rq_nowait(rq, true, NULL);
+	blk_execute_rq_nowait(rq, true);
 
 	return 0;
 
@@ -579,7 +579,7 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func)
 	crq->msg_bucket = (u32) rc;
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag);
-	blk_execute_rq_nowait(rq, true, NULL);
+	blk_execute_rq_nowait(rq, true);
 
 	return 0;
 }
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 72f7c955c707..727c12cbe327 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1206,9 +1206,10 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	nvme_init_request(rq, &ctrl->ka_cmd);
 
 	rq->timeout = ctrl->kato * HZ;
+	rq->end_io = nvme_keep_alive_end_io;
 	rq->end_io_data = ctrl;
 	rq->rq_flags |= RQF_QUIET;
-	blk_execute_rq_nowait(rq, false, nvme_keep_alive_end_io);
+	blk_execute_rq_nowait(rq, false);
 }
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 096b1b47d750..a2e89db1cd63 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -453,6 +453,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			blk_flags);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
+	req->end_io = nvme_uring_cmd_end_io;
 	req->end_io_data = ioucmd;
 
 	/* to free bio on completion, as req->bio will be null at that time */
@@ -461,7 +462,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	pdu->meta_buffer = nvme_to_user_ptr(d.metadata);
 	pdu->meta_len = d.metadata_len;
 
-	blk_execute_rq_nowait(req, 0, nvme_uring_cmd_end_io);
+	blk_execute_rq_nowait(req, false);
 	return -EIOCBQUEUED;
 }
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5a98a7de0964..0403b6d10bb4 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1438,9 +1438,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	}
 	nvme_init_request(abort_req, &cmd);
 
+	abort_req->end_io = abort_endio;
 	abort_req->end_io_data = NULL;
 	abort_req->rq_flags |= RQF_QUIET;
-	blk_execute_rq_nowait(abort_req, false, abort_endio);
+	blk_execute_rq_nowait(abort_req, false);
 
 	/*
 	 * The aborted req will be completed on receiving the abort req.
@@ -2485,12 +2486,15 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 		return PTR_ERR(req);
 	nvme_init_request(req, &cmd);
 
+	if (opcode == nvme_admin_delete_cq)
+		req->end_io = nvme_del_cq_end;
+	else
+		req->end_io = nvme_del_queue_end;
 	req->end_io_data = nvmeq;
 
 	init_completion(&nvmeq->delete_done);
 	req->rq_flags |= RQF_QUIET;
-	blk_execute_rq_nowait(req, false, opcode == nvme_admin_delete_cq ?
-			nvme_del_cq_end : nvme_del_queue_end);
+	blk_execute_rq_nowait(req, false);
 	return 0;
 }
 
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 5247c24538eb..3cc4d6709c93 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -285,8 +285,9 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 		req->p.rq = rq;
 		queue_work(nvmet_wq, &req->p.work);
 	} else {
+		rq->end_io = nvmet_passthru_req_done;
 		rq->end_io_data = req;
-		blk_execute_rq_nowait(rq, false, nvmet_passthru_req_done);
+		blk_execute_rq_nowait(rq, false);
 	}
 
 	if (ns)
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index cdaca13ac1f1..49ef864df581 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2039,12 +2039,13 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 	scmd->cmnd[4] = SCSI_REMOVAL_PREVENT;
 	scmd->cmnd[5] = 0;
 	scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]);
+	scmd->allowed = 5;
 
 	req->rq_flags |= RQF_QUIET;
 	req->timeout = 10 * HZ;
-	scmd->allowed = 5;
+	req->end_io = eh_lock_door_done;
 
-	blk_execute_rq_nowait(req, true, eh_lock_door_done);
+	blk_execute_rq_nowait(req, true);
 }
 
 /**
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index cbffa712b9f3..118c7b4a8af2 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -831,7 +831,8 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
 
 	srp->rq->timeout = timeout;
 	kref_get(&sfp->f_ref); /* sg_rq_end_io() does kref_put(). */
-	blk_execute_rq_nowait(srp->rq, at_head, sg_rq_end_io);
+	srp->rq->end_io = sg_rq_end_io;
+	blk_execute_rq_nowait(srp->rq, at_head);
 	return 0;
 }
 
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 56a093a90b92..850172a2b8f1 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -579,9 +579,10 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 	memcpy(scmd->cmnd, cmd, scmd->cmd_len);
 	req->timeout = timeout;
 	scmd->allowed = retries;
+	req->end_io = st_scsi_execute_end;
 	req->end_io_data = SRpnt;
 
-	blk_execute_rq_nowait(req, true, st_scsi_execute_end);
+	blk_execute_rq_nowait(req, true);
 	return 0;
 }
 
diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
index 8882b47f76d3..002c19c2b31f 100644
--- a/drivers/scsi/ufs/ufshpb.c
+++ b/drivers/scsi/ufs/ufshpb.c
@@ -671,11 +671,12 @@ static void ufshpb_execute_umap_req(struct ufshpb_lu *hpb,
 
 	req->timeout = 0;
 	req->end_io_data = umap_req;
+	req->end_io = ufshpb_umap_req_compl_fn;
 
 	ufshpb_set_unmap_cmd(scmd->cmnd, rgn);
 	scmd->cmd_len = HPB_WRITE_BUFFER_CMD_LENGTH;
 
-	blk_execute_rq_nowait(req, true, ufshpb_umap_req_compl_fn);
+	blk_execute_rq_nowait(req, true);
 
 	hpb->stats.umap_req_cnt++;
 }
@@ -707,6 +708,7 @@ static int ufshpb_execute_map_req(struct ufshpb_lu *hpb,
 	blk_rq_append_bio(req, map_req->bio);
 
 	req->end_io_data = map_req;
+	req->end_io = ufshpb_map_req_compl_fn;
 
 	if (unlikely(last))
 		mem_size = hpb->last_srgn_entries * HPB_ENTRY_SIZE;
@@ -716,7 +718,7 @@ static int ufshpb_execute_map_req(struct ufshpb_lu *hpb,
 				map_req->rb.srgn_idx, mem_size);
 	scmd->cmd_len = HPB_READ_BUFFER_CMD_LENGTH;
 
-	blk_execute_rq_nowait(req, true, ufshpb_map_req_compl_fn);
+	blk_execute_rq_nowait(req, true);
 
 	hpb->stats.map_req_cnt++;
 	return 0;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index bb3fb18b2316..e6a967ddc08c 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -972,8 +972,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 
 	cmd->priv = scmd->cmnd;
 
-	blk_execute_rq_nowait(req, cmd->sam_task_attr == TCM_HEAD_TAG,
-			pscsi_req_done);
+	blk_execute_rq_nowait(req, cmd->sam_task_attr == TCM_HEAD_TAG);
 
 	return 0;
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 9f07061418db..e2d9daf7e8dd 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -969,8 +969,7 @@ int blk_rq_unmap_user(struct bio *);
 int blk_rq_map_kern(struct request_queue *, struct request *, void *,
 		unsigned int, gfp_t);
 int blk_rq_append_bio(struct request *rq, struct bio *bio);
-void blk_execute_rq_nowait(struct request *rq, bool at_head,
-		rq_end_io_fn *end_io);
+void blk_execute_rq_nowait(struct request *rq, bool at_head);
 blk_status_t blk_execute_rq(struct request *rq, bool at_head);
 
 struct req_iterator {
-- 
cgit v1.2.3


From 3e0b8f529c10037ae0b369fc892e524eae5a5485 Mon Sep 17 00:00:00 2001
From: Arun Ajith S <aajith@arista.com>
Date: Mon, 30 May 2022 10:14:14 +0000
Subject: net/ipv6: Expand and rename accept_unsolicited_na to
 accept_untracked_na

RFC 9131 changes default behaviour of handling RX of NA messages when the
corresponding entry is absent in the neighbour cache. The current
implementation is limited to accept just unsolicited NAs. However, the
RFC is more generic where it also accepts solicited NAs. Both types
should result in adding a STALE entry for this case.

Expand accept_untracked_na behaviour to also accept solicited NAs to
be compliant with the RFC and rename the sysctl knob to
accept_untracked_na.

Fixes: f9a2fb73318e ("net/ipv6: Introduce accept_unsolicited_na knob to implement router-side changes for RFC9131")
Signed-off-by: Arun Ajith S <aajith@arista.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20220530101414.65439-1-aajith@arista.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/ip-sysctl.rst             | 23 +++++-------
 include/linux/ipv6.h                               |  2 +-
 include/uapi/linux/ipv6.h                          |  2 +-
 net/ipv6/addrconf.c                                |  6 ++--
 net/ipv6/ndisc.c                                   | 42 +++++++++++++---------
 .../selftests/net/ndisc_unsolicited_na_test.sh     | 23 ++++++------
 6 files changed, 50 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index b882d4238581..04216564a03c 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2474,21 +2474,16 @@ drop_unsolicited_na - BOOLEAN
 
 	By default this is turned off.
 
-accept_unsolicited_na - BOOLEAN
-	Add a new neighbour cache entry in STALE state for routers on receiving an
-	unsolicited neighbour advertisement with target link-layer address option
-	specified. This is as per router-side behavior documented in RFC9131.
-	This has lower precedence than drop_unsolicited_na.
+accept_untracked_na - BOOLEAN
+	Add a new neighbour cache entry in STALE state for routers on receiving a
+	neighbour advertisement (either solicited or unsolicited) with target
+	link-layer address option specified if no neighbour entry is already
+	present for the advertised IPv6 address. Without this knob, NAs received
+	for untracked addresses (absent in neighbour cache) are silently ignored.
+
+	This is as per router-side behaviour documented in RFC9131.
 
-	 ====   ======  ======  ==============================================
-	 drop   accept  fwding                   behaviour
-	 ----   ------  ------  ----------------------------------------------
-	    1        X       X  Drop NA packet and don't pass up the stack
-	    0        0       X  Pass NA packet up the stack, don't update NC
-	    0        1       0  Pass NA packet up the stack, don't update NC
-	    0        1       1  Pass NA packet up the stack, and add a STALE
-	                        NC entry
-	 ====   ======  ======  ==============================================
+	This has lower precedence than drop_unsolicited_na.
 
 	This will optimize the return path for the initial off-link communication
 	that is initiated by a directly connected host, by ensuring that
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 38c8203d52cb..37dfdcfcdd54 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -61,7 +61,7 @@ struct ipv6_devconf {
 	__s32		suppress_frag_ndisc;
 	__s32		accept_ra_mtu;
 	__s32		drop_unsolicited_na;
-	__s32		accept_unsolicited_na;
+	__s32		accept_untracked_na;
 	struct ipv6_stable_secret {
 		bool initialized;
 		struct in6_addr secret;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 549ddeaf788b..03cdbe798fe3 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -194,7 +194,7 @@ enum {
 	DEVCONF_IOAM6_ID,
 	DEVCONF_IOAM6_ID_WIDE,
 	DEVCONF_NDISC_EVICT_NOCARRIER,
-	DEVCONF_ACCEPT_UNSOLICITED_NA,
+	DEVCONF_ACCEPT_UNTRACKED_NA,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ca0aa744593e..1b1932502e9e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5586,7 +5586,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_IOAM6_ID] = cnf->ioam6_id;
 	array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide;
 	array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier;
-	array[DEVCONF_ACCEPT_UNSOLICITED_NA] = cnf->accept_unsolicited_na;
+	array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -7038,8 +7038,8 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.extra2		= (void *)SYSCTL_ONE,
 	},
 	{
-		.procname	= "accept_unsolicited_na",
-		.data		= &ipv6_devconf.accept_unsolicited_na,
+		.procname	= "accept_untracked_na",
+		.data		= &ipv6_devconf.accept_untracked_na,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 254addad0dd3..b0dfe97ea4ee 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -979,7 +979,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	struct inet6_ifaddr *ifp;
 	struct neighbour *neigh;
-	bool create_neigh;
+	u8 new_state;
 
 	if (skb->len < sizeof(struct nd_msg)) {
 		ND_PRINTK(2, warn, "NA: packet too short\n");
@@ -1000,7 +1000,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 	/* For some 802.11 wireless deployments (and possibly other networks),
 	 * there will be a NA proxy and unsolicitd packets are attacks
 	 * and thus should not be accepted.
-	 * drop_unsolicited_na takes precedence over accept_unsolicited_na
+	 * drop_unsolicited_na takes precedence over accept_untracked_na
 	 */
 	if (!msg->icmph.icmp6_solicited && idev &&
 	    idev->cnf.drop_unsolicited_na)
@@ -1041,25 +1041,33 @@ static void ndisc_recv_na(struct sk_buff *skb)
 		in6_ifa_put(ifp);
 		return;
 	}
+
+	neigh = neigh_lookup(&nd_tbl, &msg->target, dev);
+
 	/* RFC 9131 updates original Neighbour Discovery RFC 4861.
-	 * An unsolicited NA can now create a neighbour cache entry
-	 * on routers if it has Target LL Address option.
+	 * NAs with Target LL Address option without a corresponding
+	 * entry in the neighbour cache can now create a STALE neighbour
+	 * cache entry on routers.
+	 *
+	 *   entry accept  fwding  solicited        behaviour
+	 * ------- ------  ------  ---------    ----------------------
+	 * present      X       X         0     Set state to STALE
+	 * present      X       X         1     Set state to REACHABLE
+	 *  absent      0       X         X     Do nothing
+	 *  absent      1       0         X     Do nothing
+	 *  absent      1       1         X     Add a new STALE entry
 	 *
-	 * drop   accept  fwding                   behaviour
-	 * ----   ------  ------  ----------------------------------------------
-	 *    1        X       X  Drop NA packet and don't pass up the stack
-	 *    0        0       X  Pass NA packet up the stack, don't update NC
-	 *    0        1       0  Pass NA packet up the stack, don't update NC
-	 *    0        1       1  Pass NA packet up the stack, and add a STALE
-	 *                          NC entry
 	 * Note that we don't do a (daddr == all-routers-mcast) check.
 	 */
-	create_neigh = !msg->icmph.icmp6_solicited && lladdr &&
-		       idev && idev->cnf.forwarding &&
-		       idev->cnf.accept_unsolicited_na;
-	neigh = __neigh_lookup(&nd_tbl, &msg->target, dev, create_neigh);
+	new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE;
+	if (!neigh && lladdr &&
+	    idev && idev->cnf.forwarding &&
+	    idev->cnf.accept_untracked_na) {
+		neigh = neigh_create(&nd_tbl, &msg->target, dev);
+		new_state = NUD_STALE;
+	}
 
-	if (neigh) {
+	if (neigh && !IS_ERR(neigh)) {
 		u8 old_flags = neigh->flags;
 		struct net *net = dev_net(dev);
 
@@ -1079,7 +1087,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 		}
 
 		ndisc_update(dev, neigh, lladdr,
-			     msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
+			     new_state,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 			     (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
 			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
diff --git a/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh b/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
index f508657ee126..86e621b7b9c7 100755
--- a/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
+++ b/tools/testing/selftests/net/ndisc_unsolicited_na_test.sh
@@ -1,15 +1,14 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-# This test is for the accept_unsolicited_na feature to
+# This test is for the accept_untracked_na feature to
 # enable RFC9131 behaviour. The following is the test-matrix.
 # drop   accept  fwding                   behaviour
 # ----   ------  ------  ----------------------------------------------
-#    1        X       X  Drop NA packet and don't pass up the stack
-#    0        0       X  Pass NA packet up the stack, don't update NC
-#    0        1       0  Pass NA packet up the stack, don't update NC
-#    0        1       1  Pass NA packet up the stack, and add a STALE
-#                           NC entry
+#    1        X       X  Don't update NC
+#    0        0       X  Don't update NC
+#    0        1       0  Don't update NC
+#    0        1       1  Add a STALE NC entry
 
 ret=0
 # Kselftest framework requirement - SKIP code is 4.
@@ -72,7 +71,7 @@ setup()
 	set -e
 
 	local drop_unsolicited_na=$1
-	local accept_unsolicited_na=$2
+	local accept_untracked_na=$2
 	local forwarding=$3
 
 	# Setup two namespaces and a veth tunnel across them.
@@ -93,7 +92,7 @@ setup()
 	${IP_ROUTER_EXEC} sysctl -qw \
                 ${ROUTER_CONF}.drop_unsolicited_na=${drop_unsolicited_na}
 	${IP_ROUTER_EXEC} sysctl -qw \
-                ${ROUTER_CONF}.accept_unsolicited_na=${accept_unsolicited_na}
+                ${ROUTER_CONF}.accept_untracked_na=${accept_untracked_na}
 	${IP_ROUTER_EXEC} sysctl -qw ${ROUTER_CONF}.disable_ipv6=0
 	${IP_ROUTER} addr add ${ROUTER_ADDR_WITH_MASK} dev ${ROUTER_INTF}
 
@@ -144,13 +143,13 @@ link_up() {
 
 verify_ndisc() {
 	local drop_unsolicited_na=$1
-	local accept_unsolicited_na=$2
+	local accept_untracked_na=$2
 	local forwarding=$3
 
 	neigh_show_output=$(${IP_ROUTER} neigh show \
                 to ${HOST_ADDR} dev ${ROUTER_INTF} nud stale)
 	if [ ${drop_unsolicited_na} -eq 0 ] && \
-			[ ${accept_unsolicited_na} -eq 1 ] && \
+			[ ${accept_untracked_na} -eq 1 ] && \
 			[ ${forwarding} -eq 1 ]; then
 		# Neighbour entry expected to be present for 011 case
 		[[ ${neigh_show_output} ]]
@@ -179,14 +178,14 @@ test_unsolicited_na_combination() {
 	test_unsolicited_na_common $1 $2 $3
 	test_msg=("test_unsolicited_na: "
 		"drop_unsolicited_na=$1 "
-		"accept_unsolicited_na=$2 "
+		"accept_untracked_na=$2 "
 		"forwarding=$3")
 	log_test $? 0 "${test_msg[*]}"
 	cleanup
 }
 
 test_unsolicited_na_combinations() {
-	# Args: drop_unsolicited_na accept_unsolicited_na forwarding
+	# Args: drop_unsolicited_na accept_untracked_na forwarding
 
 	# Expect entry
 	test_unsolicited_na_combination 0 1 1
-- 
cgit v1.2.3


From 13b00b135665c92065a27c0c39dd97e0f380bd4f Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Wed, 18 May 2022 16:38:00 +0300
Subject: vdpa: Add support for querying vendor statistics

Allows to read vendor statistics of a vdpa device. The specific
statistics data are received from the upstream driver in the form of an
(attribute name, attribute value) pairs.

An example of statistics for mlx5_vdpa device are:

received_desc - number of descriptors received by the virtqueue
completed_desc - number of descriptors completed by the virtqueue

A descriptor using indirect buffers is still counted as 1. In addition,
N chained descriptors are counted correctly N times as one would expect.

A new callback was added to vdpa_config_ops which provides the means for
the vdpa driver to return statistics results.

The interface allows for reading all the supported virtqueues, including
the control virtqueue if it exists.

Below are some examples taken from mlx5_vdpa which are introduced in the
following patch:

1. Read statistics for the virtqueue at index 1

$ vdpa dev vstats show vdpa-a qidx 1
vdpa-a:
queue_type tx queue_index 1 received_desc 3844836 completed_desc 3844836

2. Read statistics for the virtqueue at index 32
$ vdpa dev vstats show vdpa-a qidx 32
vdpa-a:
queue_type control_vq queue_index 32 received_desc 62 completed_desc 62

3. Read statisitics for the virtqueue at index 0 with json output
$ vdpa -j dev vstats show vdpa-a qidx 0
{"vstats":{"vdpa-a":{
"queue_type":"rx","queue_index":0,"name":"received_desc","value":417776,\
 "name":"completed_desc","value":417548}}}

4. Read statistics for the virtqueue at index 0 with preety json output
$ vdpa -jp dev vstats show vdpa-a qidx 0
{
    "vstats": {
        "vdpa-a": {

            "queue_type": "rx",
            "queue_index": 0,
            "name": "received_desc",
            "value": 417776,
            "name": "completed_desc",
            "value": 417548
        }
    }
}

Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20220518133804.1075129-3-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/vdpa.c       | 162 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/vdpa.h      |   3 +
 include/uapi/linux/vdpa.h |   6 ++
 3 files changed, 171 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index fac89a0d8178..31b5eb2c0778 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -914,6 +914,108 @@ out:
 	return err;
 }
 
+static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg,
+			       struct genl_info *info, u32 index)
+{
+	struct virtio_net_config config = {};
+	u64 features;
+	u16 max_vqp;
+	u8 status;
+	int err;
+
+	status = vdev->config->get_status(vdev);
+	if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
+		NL_SET_ERR_MSG_MOD(info->extack, "feature negotiation not complete");
+		return -EAGAIN;
+	}
+	vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
+
+	max_vqp = le16_to_cpu(config.max_virtqueue_pairs);
+	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp))
+		return -EMSGSIZE;
+
+	features = vdev->config->get_driver_features(vdev);
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES,
+			      features, VDPA_ATTR_PAD))
+		return -EMSGSIZE;
+
+	if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index))
+		return -EMSGSIZE;
+
+	err = vdev->config->get_vendor_vq_stats(vdev, index, msg, info->extack);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int vendor_stats_fill(struct vdpa_device *vdev, struct sk_buff *msg,
+			     struct genl_info *info, u32 index)
+{
+	int err;
+
+	mutex_lock(&vdev->cf_mutex);
+	if (!vdev->config->get_vendor_vq_stats) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	err = vdpa_fill_stats_rec(vdev, msg, info, index);
+out:
+	mutex_unlock(&vdev->cf_mutex);
+	return err;
+}
+
+static int vdpa_dev_vendor_stats_fill(struct vdpa_device *vdev,
+				      struct sk_buff *msg,
+				      struct genl_info *info, u32 index)
+{
+	u32 device_id;
+	void *hdr;
+	int err;
+	u32 portid = info->snd_portid;
+	u32 seq = info->snd_seq;
+	u32 flags = 0;
+
+	hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags,
+			  VDPA_CMD_DEV_VSTATS_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) {
+		err = -EMSGSIZE;
+		goto undo_msg;
+	}
+
+	device_id = vdev->config->get_device_id(vdev);
+	if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) {
+		err = -EMSGSIZE;
+		goto undo_msg;
+	}
+
+	switch (device_id) {
+	case VIRTIO_ID_NET:
+		if (index > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX) {
+			NL_SET_ERR_MSG_MOD(info->extack, "queue index excceeds max value");
+			err = -ERANGE;
+			break;
+		}
+
+		err = vendor_stats_fill(vdev, msg, info, index);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+	genlmsg_end(msg, hdr);
+
+	return err;
+
+undo_msg:
+	genlmsg_cancel(msg, hdr);
+	return err;
+}
+
 static int vdpa_nl_cmd_dev_config_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct vdpa_device *vdev;
@@ -995,6 +1097,60 @@ vdpa_nl_cmd_dev_config_get_dumpit(struct sk_buff *msg, struct netlink_callback *
 	return msg->len;
 }
 
+static int vdpa_nl_cmd_dev_stats_get_doit(struct sk_buff *skb,
+					  struct genl_info *info)
+{
+	struct vdpa_device *vdev;
+	struct sk_buff *msg;
+	const char *devname;
+	struct device *dev;
+	u32 index;
+	int err;
+
+	if (!info->attrs[VDPA_ATTR_DEV_NAME])
+		return -EINVAL;
+
+	if (!info->attrs[VDPA_ATTR_DEV_QUEUE_INDEX])
+		return -EINVAL;
+
+	devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]);
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	index = nla_get_u32(info->attrs[VDPA_ATTR_DEV_QUEUE_INDEX]);
+	mutex_lock(&vdpa_dev_mutex);
+	dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match);
+	if (!dev) {
+		NL_SET_ERR_MSG_MOD(info->extack, "device not found");
+		err = -ENODEV;
+		goto dev_err;
+	}
+	vdev = container_of(dev, struct vdpa_device, dev);
+	if (!vdev->mdev) {
+		NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device");
+		err = -EINVAL;
+		goto mdev_err;
+	}
+	err = vdpa_dev_vendor_stats_fill(vdev, msg, info, index);
+	if (err)
+		goto mdev_err;
+
+	err = genlmsg_reply(msg, info);
+
+	put_device(dev);
+	mutex_unlock(&vdpa_dev_mutex);
+
+	return err;
+
+mdev_err:
+	put_device(dev);
+dev_err:
+	nlmsg_free(msg);
+	mutex_unlock(&vdpa_dev_mutex);
+	return err;
+}
+
 static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = {
 	[VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING },
@@ -1035,6 +1191,12 @@ static const struct genl_ops vdpa_nl_ops[] = {
 		.doit = vdpa_nl_cmd_dev_config_get_doit,
 		.dumpit = vdpa_nl_cmd_dev_config_get_dumpit,
 	},
+	{
+		.cmd = VDPA_CMD_DEV_VSTATS_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = vdpa_nl_cmd_dev_stats_get_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
 };
 
 static struct genl_family vdpa_nl_family __ro_after_init = {
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 8943a209202e..2ae8443331e1 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -276,6 +276,9 @@ struct vdpa_config_ops {
 			    const struct vdpa_vq_state *state);
 	int (*get_vq_state)(struct vdpa_device *vdev, u16 idx,
 			    struct vdpa_vq_state *state);
+	int (*get_vendor_vq_stats)(struct vdpa_device *vdev, u16 idx,
+				   struct sk_buff *msg,
+				   struct netlink_ext_ack *extack);
 	struct vdpa_notification_area
 	(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
 	/* vq irq is not expected to be changed once DRIVER_OK is set */
diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h
index 1061d8d2d09d..25c55cab3d7c 100644
--- a/include/uapi/linux/vdpa.h
+++ b/include/uapi/linux/vdpa.h
@@ -18,6 +18,7 @@ enum vdpa_command {
 	VDPA_CMD_DEV_DEL,
 	VDPA_CMD_DEV_GET,		/* can dump */
 	VDPA_CMD_DEV_CONFIG_GET,	/* can dump */
+	VDPA_CMD_DEV_VSTATS_GET,
 };
 
 enum vdpa_attr {
@@ -46,6 +47,11 @@ enum vdpa_attr {
 	VDPA_ATTR_DEV_NEGOTIATED_FEATURES,	/* u64 */
 	VDPA_ATTR_DEV_MGMTDEV_MAX_VQS,		/* u32 */
 	VDPA_ATTR_DEV_SUPPORTED_FEATURES,	/* u64 */
+
+	VDPA_ATTR_DEV_QUEUE_INDEX,              /* u32 */
+	VDPA_ATTR_DEV_VENDOR_ATTR_NAME,		/* string */
+	VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,        /* u64 */
+
 	/* new attributes must be added above here */
 	VDPA_ATTR_MAX,
 };
-- 
cgit v1.2.3


From a6a51adc6e8aafebfe0c4beb80e99694ea562b40 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Wed, 18 May 2022 16:38:02 +0300
Subject: net/vdpa: Use readers/writers semaphore instead of cf_mutex

Replace cf_mutex with rw_semaphore to reflect the fact that some calls
could be called concurrently but can suffice with read lock.

Suggested-by: Si-Wei Liu <si-wei.liu@oracle.com>
Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20220518133804.1075129-5-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/vdpa.c  | 25 ++++++++++++-------------
 include/linux/vdpa.h | 12 ++++++------
 2 files changed, 18 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 2ff7de5e6b2f..9d3534a0bc5f 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -23,9 +23,9 @@ static DEFINE_IDA(vdpa_index_ida);
 
 void vdpa_set_status(struct vdpa_device *vdev, u8 status)
 {
-	mutex_lock(&vdev->cf_mutex);
+	down_write(&vdev->cf_lock);
 	vdev->config->set_status(vdev, status);
-	mutex_unlock(&vdev->cf_mutex);
+	up_write(&vdev->cf_lock);
 }
 EXPORT_SYMBOL(vdpa_set_status);
 
@@ -148,7 +148,6 @@ static void vdpa_release_dev(struct device *d)
 		ops->free(vdev);
 
 	ida_simple_remove(&vdpa_index_ida, vdev->index);
-	mutex_destroy(&vdev->cf_mutex);
 	kfree(vdev->driver_override);
 	kfree(vdev);
 }
@@ -211,7 +210,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	if (err)
 		goto err_name;
 
-	mutex_init(&vdev->cf_mutex);
+	init_rwsem(&vdev->cf_lock);
 	device_initialize(&vdev->dev);
 
 	return vdev;
@@ -407,9 +406,9 @@ static void vdpa_get_config_unlocked(struct vdpa_device *vdev,
 void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset,
 		     void *buf, unsigned int len)
 {
-	mutex_lock(&vdev->cf_mutex);
+	down_read(&vdev->cf_lock);
 	vdpa_get_config_unlocked(vdev, offset, buf, len);
-	mutex_unlock(&vdev->cf_mutex);
+	up_read(&vdev->cf_lock);
 }
 EXPORT_SYMBOL_GPL(vdpa_get_config);
 
@@ -423,9 +422,9 @@ EXPORT_SYMBOL_GPL(vdpa_get_config);
 void vdpa_set_config(struct vdpa_device *vdev, unsigned int offset,
 		     const void *buf, unsigned int length)
 {
-	mutex_lock(&vdev->cf_mutex);
+	down_write(&vdev->cf_lock);
 	vdev->config->set_config(vdev, offset, buf, length);
-	mutex_unlock(&vdev->cf_mutex);
+	up_write(&vdev->cf_lock);
 }
 EXPORT_SYMBOL_GPL(vdpa_set_config);
 
@@ -866,7 +865,7 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid,
 	u8 status;
 	int err;
 
-	mutex_lock(&vdev->cf_mutex);
+	down_read(&vdev->cf_lock);
 	status = vdev->config->get_status(vdev);
 	if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
 		NL_SET_ERR_MSG_MOD(extack, "Features negotiation not completed");
@@ -903,14 +902,14 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid,
 	if (err)
 		goto msg_err;
 
-	mutex_unlock(&vdev->cf_mutex);
+	up_read(&vdev->cf_lock);
 	genlmsg_end(msg, hdr);
 	return 0;
 
 msg_err:
 	genlmsg_cancel(msg, hdr);
 out:
-	mutex_unlock(&vdev->cf_mutex);
+	up_read(&vdev->cf_lock);
 	return err;
 }
 
@@ -954,7 +953,7 @@ static int vendor_stats_fill(struct vdpa_device *vdev, struct sk_buff *msg,
 {
 	int err;
 
-	mutex_lock(&vdev->cf_mutex);
+	down_read(&vdev->cf_lock);
 	if (!vdev->config->get_vendor_vq_stats) {
 		err = -EOPNOTSUPP;
 		goto out;
@@ -962,7 +961,7 @@ static int vendor_stats_fill(struct vdpa_device *vdev, struct sk_buff *msg,
 
 	err = vdpa_fill_stats_rec(vdev, msg, info, index);
 out:
-	mutex_unlock(&vdev->cf_mutex);
+	up_read(&vdev->cf_lock);
 	return err;
 }
 
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 2ae8443331e1..2cb14847831e 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -66,7 +66,7 @@ struct vdpa_mgmt_dev;
  * @dma_dev: the actual device that is performing DMA
  * @driver_override: driver name to force a match
  * @config: the configuration ops for this device.
- * @cf_mutex: Protects get and set access to configuration layout.
+ * @cf_lock: Protects get and set access to configuration layout.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
  * @use_va: indicate whether virtual address must be used by this device
@@ -79,7 +79,7 @@ struct vdpa_device {
 	struct device *dma_dev;
 	const char *driver_override;
 	const struct vdpa_config_ops *config;
-	struct mutex cf_mutex; /* Protects get/set config */
+	struct rw_semaphore cf_lock; /* Protects get/set config */
 	unsigned int index;
 	bool features_valid;
 	bool use_va;
@@ -398,10 +398,10 @@ static inline int vdpa_reset(struct vdpa_device *vdev)
 	const struct vdpa_config_ops *ops = vdev->config;
 	int ret;
 
-	mutex_lock(&vdev->cf_mutex);
+	down_write(&vdev->cf_lock);
 	vdev->features_valid = false;
 	ret = ops->reset(vdev);
-	mutex_unlock(&vdev->cf_mutex);
+	up_write(&vdev->cf_lock);
 	return ret;
 }
 
@@ -420,9 +420,9 @@ static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
 {
 	int ret;
 
-	mutex_lock(&vdev->cf_mutex);
+	down_write(&vdev->cf_lock);
 	ret = vdpa_set_features_unlocked(vdev, features);
-	mutex_unlock(&vdev->cf_mutex);
+	up_write(&vdev->cf_lock);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 1892a3d425bf525ac98d6d3534035e6ed2bfab50 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Wed, 18 May 2022 16:38:03 +0300
Subject: vdpa/mlx5: Add support for reading descriptor statistics

Implement the get_vq_stats calback of vdpa_config_ops to return the
statistics for a virtqueue.

The statistics are provided as vendor specific statistics where the
driver provides a pair of attribute name and attribute value.

Currently supported are received descriptors and completed descriptors.

Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20220518133804.1075129-6-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/core/mlx5_vdpa.h |   2 +
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 149 +++++++++++++++++++++++++++++++++++++
 include/linux/mlx5/mlx5_ifc.h      |   1 +
 include/linux/mlx5/mlx5_ifc_vdpa.h |  39 ++++++++++
 4 files changed, 191 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index daaf7b503677..44104093163b 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -61,6 +61,8 @@ struct mlx5_control_vq {
 	struct vringh_kiov riov;
 	struct vringh_kiov wiov;
 	unsigned short head;
+	unsigned int received_desc;
+	unsigned int completed_desc;
 };
 
 struct mlx5_vdpa_wq_ent {
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index e0de44000d92..2b815ef850c8 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -119,6 +119,7 @@ struct mlx5_vdpa_virtqueue {
 	struct mlx5_vdpa_umem umem2;
 	struct mlx5_vdpa_umem umem3;
 
+	u32 counter_set_id;
 	bool initialized;
 	int index;
 	u32 virtq_id;
@@ -818,6 +819,12 @@ static u16 get_features_12_3(u64 features)
 	       (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_CSUM)) << 6);
 }
 
+static bool counters_supported(const struct mlx5_vdpa_dev *mvdev)
+{
+	return MLX5_CAP_GEN_64(mvdev->mdev, general_obj_types) &
+	       BIT_ULL(MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS);
+}
+
 static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_virtio_net_q_in);
@@ -872,6 +879,8 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	MLX5_SET(virtio_q, vq_ctx, umem_3_id, mvq->umem3.id);
 	MLX5_SET(virtio_q, vq_ctx, umem_3_size, mvq->umem3.size);
 	MLX5_SET(virtio_q, vq_ctx, pd, ndev->mvdev.res.pdn);
+	if (counters_supported(&ndev->mvdev))
+		MLX5_SET(virtio_q, vq_ctx, counter_set_id, mvq->counter_set_id);
 
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	if (err)
@@ -1135,6 +1144,47 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	return err;
 }
 
+static int counter_set_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+	u32 in[MLX5_ST_SZ_DW(create_virtio_q_counters_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(create_virtio_q_counters_out)] = {};
+	void *cmd_hdr;
+	int err;
+
+	if (!counters_supported(&ndev->mvdev))
+		return 0;
+
+	cmd_hdr = MLX5_ADDR_OF(create_virtio_q_counters_in, in, hdr);
+
+	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS);
+	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
+
+	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	mvq->counter_set_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+
+	return 0;
+}
+
+static void counter_set_dealloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_virtio_q_counters_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(destroy_virtio_q_counters_out)] = {};
+
+	if (!counters_supported(&ndev->mvdev))
+		return;
+
+	MLX5_SET(destroy_virtio_q_counters_in, in, hdr.opcode, MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+	MLX5_SET(destroy_virtio_q_counters_in, in, hdr.obj_id, mvq->counter_set_id);
+	MLX5_SET(destroy_virtio_q_counters_in, in, hdr.uid, ndev->mvdev.res.uid);
+	MLX5_SET(destroy_virtio_q_counters_in, in, hdr.obj_type, MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS);
+	if (mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, sizeof(out)))
+		mlx5_vdpa_warn(&ndev->mvdev, "dealloc counter set 0x%x\n", mvq->counter_set_id);
+}
+
 static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	u16 idx = mvq->index;
@@ -1162,6 +1212,10 @@ static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 	if (err)
 		goto err_connect;
 
+	err = counter_set_alloc(ndev, mvq);
+	if (err)
+		goto err_counter;
+
 	err = create_virtqueue(ndev, mvq);
 	if (err)
 		goto err_connect;
@@ -1179,6 +1233,8 @@ static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 	return 0;
 
 err_connect:
+	counter_set_dealloc(ndev, mvq);
+err_counter:
 	qp_destroy(ndev, &mvq->vqqp);
 err_vqqp:
 	qp_destroy(ndev, &mvq->fwqp);
@@ -1223,6 +1279,7 @@ static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *
 
 	suspend_vq(ndev, mvq);
 	destroy_virtqueue(ndev, mvq);
+	counter_set_dealloc(ndev, mvq);
 	qp_destroy(ndev, &mvq->vqqp);
 	qp_destroy(ndev, &mvq->fwqp);
 	cq_destroy(ndev, mvq->index);
@@ -1659,6 +1716,7 @@ static void mlx5_cvq_kick_handler(struct work_struct *work)
 		if (read != sizeof(ctrl))
 			break;
 
+		cvq->received_desc++;
 		switch (ctrl.class) {
 		case VIRTIO_NET_CTRL_MAC:
 			status = handle_ctrl_mac(mvdev, ctrl.cmd);
@@ -1682,6 +1740,7 @@ static void mlx5_cvq_kick_handler(struct work_struct *work)
 		if (vringh_need_notify_iotlb(&cvq->vring))
 			vringh_notify(&cvq->vring);
 
+		cvq->completed_desc++;
 		queue_work(mvdev->wq, &wqent->work);
 		break;
 	}
@@ -2303,6 +2362,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	mlx5_vdpa_destroy_mr(&ndev->mvdev);
 	ndev->mvdev.status = 0;
 	ndev->cur_num_vqs = 0;
+	ndev->mvdev.cvq.received_desc = 0;
+	ndev->mvdev.cvq.completed_desc = 0;
 	memset(ndev->event_cbs, 0, sizeof(*ndev->event_cbs) * (mvdev->max_vqs + 1));
 	ndev->mvdev.actual_features = 0;
 	++mvdev->generation;
@@ -2422,6 +2483,93 @@ static u64 mlx5_vdpa_get_driver_features(struct vdpa_device *vdev)
 	return mvdev->actual_features;
 }
 
+static int counter_set_query(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq,
+			     u64 *received_desc, u64 *completed_desc)
+{
+	u32 in[MLX5_ST_SZ_DW(query_virtio_q_counters_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(query_virtio_q_counters_out)] = {};
+	void *cmd_hdr;
+	void *ctx;
+	int err;
+
+	if (!counters_supported(&ndev->mvdev))
+		return -EOPNOTSUPP;
+
+	if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
+		return -EAGAIN;
+
+	cmd_hdr = MLX5_ADDR_OF(query_virtio_q_counters_in, in, hdr);
+
+	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_QUERY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS);
+	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
+	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_id, mvq->counter_set_id);
+
+	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	ctx = MLX5_ADDR_OF(query_virtio_q_counters_out, out, counters);
+	*received_desc = MLX5_GET64(virtio_q_counters, ctx, received_desc);
+	*completed_desc = MLX5_GET64(virtio_q_counters, ctx, completed_desc);
+	return 0;
+}
+
+static int mlx5_vdpa_get_vendor_vq_stats(struct vdpa_device *vdev, u16 idx,
+					 struct sk_buff *msg,
+					 struct netlink_ext_ack *extack)
+{
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	struct mlx5_vdpa_virtqueue *mvq;
+	struct mlx5_control_vq *cvq;
+	u64 received_desc;
+	u64 completed_desc;
+	int err = 0;
+
+	mutex_lock(&ndev->reslock);
+	if (!is_index_valid(mvdev, idx)) {
+		NL_SET_ERR_MSG_MOD(extack, "virtqueue index is not valid");
+		err = -EINVAL;
+		goto out_err;
+	}
+
+	if (idx == ctrl_vq_idx(mvdev)) {
+		cvq = &mvdev->cvq;
+		received_desc = cvq->received_desc;
+		completed_desc = cvq->completed_desc;
+		goto out;
+	}
+
+	mvq = &ndev->vqs[idx];
+	err = counter_set_query(ndev, mvq, &received_desc, &completed_desc);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "failed to query hardware");
+		goto out_err;
+	}
+
+out:
+	err = -EMSGSIZE;
+	if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME, "received_desc"))
+		goto out_err;
+
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, received_desc,
+			      VDPA_ATTR_PAD))
+		goto out_err;
+
+	if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME, "completed_desc"))
+		goto out_err;
+
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, completed_desc,
+			      VDPA_ATTR_PAD))
+		goto out_err;
+
+	err = 0;
+out_err:
+	mutex_unlock(&ndev->reslock);
+	return err;
+}
+
 static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.set_vq_address = mlx5_vdpa_set_vq_address,
 	.set_vq_num = mlx5_vdpa_set_vq_num,
@@ -2431,6 +2579,7 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.get_vq_ready = mlx5_vdpa_get_vq_ready,
 	.set_vq_state = mlx5_vdpa_set_vq_state,
 	.get_vq_state = mlx5_vdpa_get_vq_state,
+	.get_vendor_vq_stats = mlx5_vdpa_get_vendor_vq_stats,
 	.get_vq_notification = mlx5_get_vq_notification,
 	.get_vq_irq = mlx5_get_vq_irq,
 	.get_vq_align = mlx5_vdpa_get_vq_align,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 78b3d3465dd7..2a8334bb5f82 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -87,6 +87,7 @@ enum {
 enum {
 	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
 	MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d,
+	MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c,
 	MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018,
 	MLX5_OBJ_TYPE_MKEY = 0xff01,
 	MLX5_OBJ_TYPE_QP = 0xff02,
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 1a9c9d94cb59..4414ed5b6ed2 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -165,4 +165,43 @@ struct mlx5_ifc_modify_virtio_net_q_out_bits {
 	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
 };
 
+struct mlx5_ifc_virtio_q_counters_bits {
+	u8    modify_field_select[0x40];
+	u8    reserved_at_40[0x40];
+	u8    received_desc[0x40];
+	u8    completed_desc[0x40];
+	u8    error_cqes[0x20];
+	u8    bad_desc_errors[0x20];
+	u8    exceed_max_chain[0x20];
+	u8    invalid_buffer[0x20];
+	u8    reserved_at_180[0x280];
+};
+
+struct mlx5_ifc_create_virtio_q_counters_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_virtio_q_counters_bits virtio_q_counters;
+};
+
+struct mlx5_ifc_create_virtio_q_counters_out_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_virtio_q_counters_bits virtio_q_counters;
+};
+
+struct mlx5_ifc_destroy_virtio_q_counters_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+};
+
+struct mlx5_ifc_destroy_virtio_q_counters_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits hdr;
+};
+
+struct mlx5_ifc_query_virtio_q_counters_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+};
+
+struct mlx5_ifc_query_virtio_q_counters_out_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_virtio_q_counters_bits counters;
+};
+
 #endif /* __MLX5_IFC_VDPA_H_ */
-- 
cgit v1.2.3


From d4821902e43453b85b31329441a9f6ac071228a8 Mon Sep 17 00:00:00 2001
From: Gautam Dawar <gautam.dawar@xilinx.com>
Date: Wed, 30 Mar 2022 23:33:45 +0530
Subject: vdpa: introduce virtqueue groups

This patch introduces virtqueue groups to vDPA device. The virtqueue
group is the minimal set of virtqueues that must share an address
space. And the address space identifier could only be attached to
a specific virtqueue group.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Gautam Dawar <gdawar@xilinx.com>
Message-Id: <20220330180436.24644-6-gdawar@xilinx.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/alibaba/eni_vdpa.c    |  2 +-
 drivers/vdpa/ifcvf/ifcvf_main.c    |  8 +++++++-
 drivers/vdpa/mlx5/net/mlx5_vnet.c  |  8 +++++++-
 drivers/vdpa/vdpa.c                |  3 +++
 drivers/vdpa/vdpa_sim/vdpa_sim.c   |  9 ++++++++-
 drivers/vdpa/vdpa_sim/vdpa_sim.h   |  1 +
 drivers/vdpa/vdpa_user/vduse_dev.c |  2 +-
 drivers/vdpa/virtio_pci/vp_vdpa.c  |  2 +-
 include/linux/vdpa.h               | 16 ++++++++++++----
 9 files changed, 41 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c
index f480d54f308c..3e93c5eb0cf9 100644
--- a/drivers/vdpa/alibaba/eni_vdpa.c
+++ b/drivers/vdpa/alibaba/eni_vdpa.c
@@ -470,7 +470,7 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 
 	eni_vdpa = vdpa_alloc_device(struct eni_vdpa, vdpa,
-				     dev, &eni_vdpa_ops, NULL, false);
+				     dev, &eni_vdpa_ops, 1, NULL, false);
 	if (IS_ERR(eni_vdpa)) {
 		ENI_ERR(pdev, "failed to allocate vDPA structure\n");
 		return PTR_ERR(eni_vdpa);
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 4366320fb68d..fde33e143246 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -626,6 +626,11 @@ static size_t ifcvf_vdpa_get_config_size(struct vdpa_device *vdpa_dev)
 	return  vf->config_size;
 }
 
+static u32 ifcvf_vdpa_get_vq_group(struct vdpa_device *vdpa, u16 idx)
+{
+	return 0;
+}
+
 static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev,
 				  unsigned int offset,
 				  void *buf, unsigned int len)
@@ -704,6 +709,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = {
 	.get_device_id	= ifcvf_vdpa_get_device_id,
 	.get_vendor_id	= ifcvf_vdpa_get_vendor_id,
 	.get_vq_align	= ifcvf_vdpa_get_vq_align,
+	.get_vq_group	= ifcvf_vdpa_get_vq_group,
 	.get_config_size	= ifcvf_vdpa_get_config_size,
 	.get_config	= ifcvf_vdpa_get_config,
 	.set_config	= ifcvf_vdpa_set_config,
@@ -758,7 +764,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	pdev = ifcvf_mgmt_dev->pdev;
 	dev = &pdev->dev;
 	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
-				    dev, &ifc_vdpa_ops, name, false);
+				    dev, &ifc_vdpa_ops, 1, name, false);
 	if (IS_ERR(adapter)) {
 		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
 		return PTR_ERR(adapter);
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 57cfc64248b7..5647e12056d8 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1947,6 +1947,11 @@ static u32 mlx5_vdpa_get_vq_align(struct vdpa_device *vdev)
 	return PAGE_SIZE;
 }
 
+static u32 mlx5_vdpa_get_vq_group(struct vdpa_device *vdpa, u16 idx)
+{
+	return 0;
+}
+
 enum { MLX5_VIRTIO_NET_F_GUEST_CSUM = 1 << 9,
 	MLX5_VIRTIO_NET_F_CSUM = 1 << 10,
 	MLX5_VIRTIO_NET_F_HOST_TSO6 = 1 << 11,
@@ -2582,6 +2587,7 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.get_vq_notification = mlx5_get_vq_notification,
 	.get_vq_irq = mlx5_get_vq_irq,
 	.get_vq_align = mlx5_vdpa_get_vq_align,
+	.get_vq_group = mlx5_vdpa_get_vq_group,
 	.get_device_features = mlx5_vdpa_get_device_features,
 	.set_driver_features = mlx5_vdpa_set_driver_features,
 	.get_driver_features = mlx5_vdpa_get_driver_features,
@@ -2817,7 +2823,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	}
 
 	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
-				 name, false);
+				 1, name, false);
 	if (IS_ERR(ndev))
 		return PTR_ERR(ndev);
 
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 9d3534a0bc5f..4ca54779be2c 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -158,6 +158,7 @@ static void vdpa_release_dev(struct device *d)
  * initialized but before registered.
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
+ * @ngroups: number of groups supported by this device
  * @size: size of the parent structure that contains private data
  * @name: name of the vdpa device; optional.
  * @use_va: indicate whether virtual address must be used by this device
@@ -170,6 +171,7 @@ static void vdpa_release_dev(struct device *d)
  */
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
+					unsigned int ngroups,
 					size_t size, const char *name,
 					bool use_va)
 {
@@ -202,6 +204,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	vdev->config = config;
 	vdev->features_valid = false;
 	vdev->use_va = use_va;
+	vdev->ngroups = ngroups;
 
 	if (name)
 		err = dev_set_name(&vdev->dev, "%s", name);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index ddbe142af09a..c98cb1f869fa 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -250,7 +250,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
 	else
 		ops = &vdpasim_config_ops;
 
-	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
+	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1,
 				    dev_attr->name, false);
 	if (IS_ERR(vdpasim)) {
 		ret = PTR_ERR(vdpasim);
@@ -399,6 +399,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
 	return VDPASIM_QUEUE_ALIGN;
 }
 
+static u32 vdpasim_get_vq_group(struct vdpa_device *vdpa, u16 idx)
+{
+	return 0;
+}
+
 static u64 vdpasim_get_device_features(struct vdpa_device *vdpa)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -620,6 +625,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
 	.set_vq_state           = vdpasim_set_vq_state,
 	.get_vq_state           = vdpasim_get_vq_state,
 	.get_vq_align           = vdpasim_get_vq_align,
+	.get_vq_group           = vdpasim_get_vq_group,
 	.get_device_features    = vdpasim_get_device_features,
 	.set_driver_features    = vdpasim_set_driver_features,
 	.get_driver_features    = vdpasim_get_driver_features,
@@ -650,6 +656,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.set_vq_state           = vdpasim_set_vq_state,
 	.get_vq_state           = vdpasim_get_vq_state,
 	.get_vq_align           = vdpasim_get_vq_align,
+	.get_vq_group           = vdpasim_get_vq_group,
 	.get_device_features    = vdpasim_get_device_features,
 	.set_driver_features    = vdpasim_set_driver_features,
 	.get_driver_features    = vdpasim_get_driver_features,
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h
index cd58e888bcf3..0be7c1e7ef80 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.h
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h
@@ -63,6 +63,7 @@ struct vdpasim {
 	u32 status;
 	u32 generation;
 	u64 features;
+	u32 groups;
 	/* spinlock to synchronize iommu table */
 	spinlock_t iommu_lock;
 };
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index f85d1a08ed87..4ee6850b9a68 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -1495,7 +1495,7 @@ static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name)
 		return -EEXIST;
 
 	vdev = vdpa_alloc_device(struct vduse_vdpa, vdpa, dev->dev,
-				 &vduse_vdpa_config_ops, name, true);
+				 &vduse_vdpa_config_ops, 1, name, true);
 	if (IS_ERR(vdev))
 		return PTR_ERR(vdev);
 
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index cce101e6a940..e18dfe993901 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -466,7 +466,7 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 
 	vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa,
-				    dev, &vp_vdpa_ops, NULL, false);
+				    dev, &vp_vdpa_ops, 1, NULL, false);
 	if (IS_ERR(vp_vdpa)) {
 		dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n");
 		return PTR_ERR(vp_vdpa);
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 2cb14847831e..e4e53574183e 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -85,6 +85,7 @@ struct vdpa_device {
 	bool use_va;
 	u32 nvqs;
 	struct vdpa_mgmt_dev *mdev;
+	unsigned int ngroups;
 };
 
 /**
@@ -172,6 +173,10 @@ struct vdpa_map_file {
  *				for the device
  *				@vdev: vdpa device
  *				Returns virtqueue algin requirement
+ * @get_vq_group:		Get the group id for a specific virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				Returns u32: group id for this virtqueue
  * @get_device_features:	Get virtio features supported by the device
  *				@vdev: vdpa device
  *				Returns the virtio features support by the
@@ -286,6 +291,7 @@ struct vdpa_config_ops {
 
 	/* Device ops */
 	u32 (*get_vq_align)(struct vdpa_device *vdev);
+	u32 (*get_vq_group)(struct vdpa_device *vdev, u16 idx);
 	u64 (*get_device_features)(struct vdpa_device *vdev);
 	int (*set_driver_features)(struct vdpa_device *vdev, u64 features);
 	u64 (*get_driver_features)(struct vdpa_device *vdev);
@@ -318,6 +324,7 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
+					unsigned int ngroups,
 					size_t size, const char *name,
 					bool use_va);
 
@@ -328,17 +335,18 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
  * @member: the name of struct vdpa_device within the @dev_struct
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
+ * @ngroups: the number of virtqueue groups supported by this device
  * @name: name of the vdpa device
  * @use_va: indicate whether virtual address must be used by this device
  *
  * Return allocated data structure or ERR_PTR upon error
  */
-#define vdpa_alloc_device(dev_struct, member, parent, config, name, use_va)   \
-			  container_of(__vdpa_alloc_device( \
-				       parent, config, \
+#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, name, use_va)   \
+			  container_of((__vdpa_alloc_device( \
+				       parent, config, ngroups, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
-				       dev_struct, member)), name, use_va), \
+				       dev_struct, member)), name, use_va)), \
 				       dev_struct, member)
 
 int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs);
-- 
cgit v1.2.3


From db9adcbf4286ad1c1fca091a870db6e49bb0df07 Mon Sep 17 00:00:00 2001
From: Gautam Dawar <gautam.dawar@xilinx.com>
Date: Wed, 30 Mar 2022 23:33:46 +0530
Subject: vdpa: multiple address spaces support

This patches introduces the multiple address spaces support for vDPA
device. This idea is to identify a specific address space via an
dedicated identifier - ASID.

During vDPA device allocation, vDPA device driver needs to report the
number of address spaces supported by the device then the DMA mapping
ops of the vDPA device needs to be extended to support ASID.

This helps to isolate the environments for the virtqueue that will not
be assigned directly. E.g in the case of virtio-net, the control
virtqueue will not be assigned directly to guest.

As a start, simply claim 1 virtqueue groups and 1 address spaces for
all vDPA devices. And vhost-vDPA will simply reject the device with
more than 1 virtqueue groups or address spaces.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Gautam Dawar <gdawar@xilinx.com>
Message-Id: <20220330180436.24644-7-gdawar@xilinx.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/alibaba/eni_vdpa.c    |  2 +-
 drivers/vdpa/ifcvf/ifcvf_main.c    |  2 +-
 drivers/vdpa/mlx5/net/mlx5_vnet.c  |  5 +++--
 drivers/vdpa/vdpa.c                |  4 +++-
 drivers/vdpa/vdpa_sim/vdpa_sim.c   | 10 ++++++----
 drivers/vdpa/vdpa_user/vduse_dev.c |  3 ++-
 drivers/vdpa/virtio_pci/vp_vdpa.c  |  2 +-
 drivers/vhost/vdpa.c               | 14 +++++++++-----
 include/linux/vdpa.h               | 28 +++++++++++++++++++---------
 9 files changed, 45 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c
index 3e93c5eb0cf9..5a09a09cca70 100644
--- a/drivers/vdpa/alibaba/eni_vdpa.c
+++ b/drivers/vdpa/alibaba/eni_vdpa.c
@@ -470,7 +470,7 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 
 	eni_vdpa = vdpa_alloc_device(struct eni_vdpa, vdpa,
-				     dev, &eni_vdpa_ops, 1, NULL, false);
+				     dev, &eni_vdpa_ops, 1, 1, NULL, false);
 	if (IS_ERR(eni_vdpa)) {
 		ENI_ERR(pdev, "failed to allocate vDPA structure\n");
 		return PTR_ERR(eni_vdpa);
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index fde33e143246..c1767a0ce630 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -764,7 +764,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	pdev = ifcvf_mgmt_dev->pdev;
 	dev = &pdev->dev;
 	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
-				    dev, &ifc_vdpa_ops, 1, name, false);
+				    dev, &ifc_vdpa_ops, 1, 1, name, false);
 	if (IS_ERR(adapter)) {
 		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
 		return PTR_ERR(adapter);
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 5647e12056d8..dcca782c698e 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2409,7 +2409,8 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev)
 	return mvdev->generation;
 }
 
-static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb)
+static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid,
+			     struct vhost_iotlb *iotlb)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
@@ -2823,7 +2824,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	}
 
 	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
-				 1, name, false);
+				 1, 1, name, false);
 	if (IS_ERR(ndev))
 		return PTR_ERR(ndev);
 
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 4ca54779be2c..f15fb11010a8 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -159,6 +159,7 @@ static void vdpa_release_dev(struct device *d)
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
  * @ngroups: number of groups supported by this device
+ * @nas: number of address spaces supported by this device
  * @size: size of the parent structure that contains private data
  * @name: name of the vdpa device; optional.
  * @use_va: indicate whether virtual address must be used by this device
@@ -171,7 +172,7 @@ static void vdpa_release_dev(struct device *d)
  */
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					unsigned int ngroups,
+					unsigned int ngroups, unsigned int nas,
 					size_t size, const char *name,
 					bool use_va)
 {
@@ -205,6 +206,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	vdev->features_valid = false;
 	vdev->use_va = use_va;
 	vdev->ngroups = ngroups;
+	vdev->nas = nas;
 
 	if (name)
 		err = dev_set_name(&vdev->dev, "%s", name);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index c98cb1f869fa..659e2e2e4b0c 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -251,7 +251,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
 		ops = &vdpasim_config_ops;
 
 	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1,
-				    dev_attr->name, false);
+				    1, dev_attr->name, false);
 	if (IS_ERR(vdpasim)) {
 		ret = PTR_ERR(vdpasim);
 		goto err_alloc;
@@ -539,7 +539,7 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)
 	return range;
 }
 
-static int vdpasim_set_map(struct vdpa_device *vdpa,
+static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,
 			   struct vhost_iotlb *iotlb)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -566,7 +566,8 @@ err:
 	return ret;
 }
 
-static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,
+static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,
+			   u64 iova, u64 size,
 			   u64 pa, u32 perm, void *opaque)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -580,7 +581,8 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,
 	return ret;
 }
 
-static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size)
+static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid,
+			     u64 iova, u64 size)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 4ee6850b9a68..d503848b3b6e 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -693,6 +693,7 @@ static u32 vduse_vdpa_get_generation(struct vdpa_device *vdpa)
 }
 
 static int vduse_vdpa_set_map(struct vdpa_device *vdpa,
+				unsigned int asid,
 				struct vhost_iotlb *iotlb)
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
@@ -1495,7 +1496,7 @@ static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name)
 		return -EEXIST;
 
 	vdev = vdpa_alloc_device(struct vduse_vdpa, vdpa, dev->dev,
-				 &vduse_vdpa_config_ops, 1, name, true);
+				 &vduse_vdpa_config_ops, 1, 1, name, true);
 	if (IS_ERR(vdev))
 		return PTR_ERR(vdev);
 
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index e18dfe993901..35acba0e8d6d 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -466,7 +466,7 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 
 	vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa,
-				    dev, &vp_vdpa_ops, 1, NULL, false);
+				    dev, &vp_vdpa_ops, 1, 1, NULL, false);
 	if (IS_ERR(vp_vdpa)) {
 		dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n");
 		return PTR_ERR(vp_vdpa);
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 632c43eb5ecf..9202ff97ddb5 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -633,10 +633,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
 		return r;
 
 	if (ops->dma_map) {
-		r = ops->dma_map(vdpa, iova, size, pa, perm, opaque);
+		r = ops->dma_map(vdpa, 0, iova, size, pa, perm, opaque);
 	} else if (ops->set_map) {
 		if (!v->in_batch)
-			r = ops->set_map(vdpa, iotlb);
+			r = ops->set_map(vdpa, 0, iotlb);
 	} else {
 		r = iommu_map(v->domain, iova, pa, size,
 			      perm_to_iommu_flags(perm));
@@ -662,10 +662,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,
 	vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
 
 	if (ops->dma_map) {
-		ops->dma_unmap(vdpa, iova, size);
+		ops->dma_unmap(vdpa, 0, iova, size);
 	} else if (ops->set_map) {
 		if (!v->in_batch)
-			ops->set_map(vdpa, iotlb);
+			ops->set_map(vdpa, 0, iotlb);
 	} else {
 		iommu_unmap(v->domain, iova, size);
 	}
@@ -897,7 +897,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
 		break;
 	case VHOST_IOTLB_BATCH_END:
 		if (v->in_batch && ops->set_map)
-			ops->set_map(vdpa, iotlb);
+			ops->set_map(vdpa, 0, iotlb);
 		v->in_batch = false;
 		break;
 	default:
@@ -1163,6 +1163,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 	int minor;
 	int r;
 
+	/* Only support 1 address space and 1 groups */
+	if (vdpa->ngroups != 1 || vdpa->nas != 1)
+		return -EOPNOTSUPP;
+
 	v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!v)
 		return -ENOMEM;
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index e4e53574183e..1515748e84ff 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -69,6 +69,8 @@ struct vdpa_mgmt_dev;
  * @cf_lock: Protects get and set access to configuration layout.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
+ * @ngroups: the number of virtqueue groups
+ * @nas: the number of address spaces
  * @use_va: indicate whether virtual address must be used by this device
  * @nvqs: maximum number of supported virtqueues
  * @mdev: management device pointer; caller must setup when registering device as part
@@ -86,6 +88,7 @@ struct vdpa_device {
 	u32 nvqs;
 	struct vdpa_mgmt_dev *mdev;
 	unsigned int ngroups;
+	unsigned int nas;
 };
 
 /**
@@ -241,6 +244,7 @@ struct vdpa_map_file {
  *				Needed for device that using device
  *				specific DMA translation (on-chip IOMMU)
  *				@vdev: vdpa device
+ *				@asid: address space identifier
  *				@iotlb: vhost memory mapping to be
  *				used by the vDPA
  *				Returns integer: success (0) or error (< 0)
@@ -249,6 +253,7 @@ struct vdpa_map_file {
  *				specific DMA translation (on-chip IOMMU)
  *				and preferring incremental map.
  *				@vdev: vdpa device
+ *				@asid: address space identifier
  *				@iova: iova to be mapped
  *				@size: size of the area
  *				@pa: physical address for the map
@@ -260,6 +265,7 @@ struct vdpa_map_file {
  *				specific DMA translation (on-chip IOMMU)
  *				and preferring incremental unmap.
  *				@vdev: vdpa device
+ *				@asid: address space identifier
  *				@iova: iova to be unmapped
  *				@size: size of the area
  *				Returns integer: success (0) or error (< 0)
@@ -313,10 +319,12 @@ struct vdpa_config_ops {
 	struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev);
 
 	/* DMA ops */
-	int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
-	int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size,
-		       u64 pa, u32 perm, void *opaque);
-	int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size);
+	int (*set_map)(struct vdpa_device *vdev, unsigned int asid,
+		       struct vhost_iotlb *iotlb);
+	int (*dma_map)(struct vdpa_device *vdev, unsigned int asid,
+		       u64 iova, u64 size, u64 pa, u32 perm, void *opaque);
+	int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid,
+			 u64 iova, u64 size);
 
 	/* Free device resources */
 	void (*free)(struct vdpa_device *vdev);
@@ -324,7 +332,7 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					unsigned int ngroups,
+					unsigned int ngroups, unsigned int nas,
 					size_t size, const char *name,
 					bool use_va);
 
@@ -336,17 +344,19 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
  * @ngroups: the number of virtqueue groups supported by this device
+ * @nas: the number of address spaces
  * @name: name of the vdpa device
  * @use_va: indicate whether virtual address must be used by this device
  *
  * Return allocated data structure or ERR_PTR upon error
  */
-#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, name, use_va)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, nas, \
+			  name, use_va) \
 			  container_of((__vdpa_alloc_device( \
-				       parent, config, ngroups, \
-				       sizeof(dev_struct) + \
+				       parent, config, ngroups, nas, \
+				       (sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
-				       dev_struct, member)), name, use_va)), \
+				       dev_struct, member))), name, use_va)), \
 				       dev_struct, member)
 
 int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs);
-- 
cgit v1.2.3


From 46d554b1bcd19133401d2d5c0728b85e7bfd1358 Mon Sep 17 00:00:00 2001
From: Gautam Dawar <gautam.dawar@xilinx.com>
Date: Wed, 30 Mar 2022 23:33:47 +0530
Subject: vdpa: introduce config operations for associating ASID to a virtqueue
 group

This patch introduces a new bus operation to allow the vDPA bus driver
to associate an ASID to a virtqueue group.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Gautam Dawar <gdawar@xilinx.com>
Message-Id: <20220330180436.24644-8-gdawar@xilinx.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/vdpa.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 1515748e84ff..f336d253db3d 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -240,6 +240,12 @@ struct vdpa_map_file {
  *				@vdev: vdpa device
  *				Returns the iova range supported by
  *				the device.
+ * @set_group_asid:		Set address space identifier for a
+ *				virtqueue group
+ *				@vdev: vdpa device
+ *				@group: virtqueue group
+ *				@asid: address space id for this group
+ *				Returns integer: success (0) or error (< 0)
  * @set_map:			Set device memory mapping (optional)
  *				Needed for device that using device
  *				specific DMA translation (on-chip IOMMU)
@@ -325,6 +331,8 @@ struct vdpa_config_ops {
 		       u64 iova, u64 size, u64 pa, u32 perm, void *opaque);
 	int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid,
 			 u64 iova, u64 size);
+	int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group,
+			      unsigned int asid);
 
 	/* Free device resources */
 	void (*free)(struct vdpa_device *vdev);
-- 
cgit v1.2.3


From 1cb108994c6830cc6a6e066ad7d9a22ef59fa167 Mon Sep 17 00:00:00 2001
From: Gautam Dawar <gautam.dawar@xilinx.com>
Date: Wed, 30 Mar 2022 23:33:48 +0530
Subject: vhost_iotlb: split out IOTLB initialization

This patch splits out IOTLB initialization to make sure it could be
reused by external modules.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Gautam Dawar <gdawar@xilinx.com>
Message-Id: <20220330180436.24644-9-gdawar@xilinx.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/iotlb.c       | 23 ++++++++++++++++++-----
 include/linux/vhost_iotlb.h |  2 ++
 2 files changed, 20 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c
index 5829cf2d0552..ea61330a3431 100644
--- a/drivers/vhost/iotlb.c
+++ b/drivers/vhost/iotlb.c
@@ -125,6 +125,23 @@ void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last)
 }
 EXPORT_SYMBOL_GPL(vhost_iotlb_del_range);
 
+/**
+ * vhost_iotlb_init - initialize a vhost IOTLB
+ * @iotlb: the IOTLB that needs to be initialized
+ * @limit: maximum number of IOTLB entries
+ * @flags: VHOST_IOTLB_FLAG_XXX
+ */
+void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit,
+		      unsigned int flags)
+{
+	iotlb->root = RB_ROOT_CACHED;
+	iotlb->limit = limit;
+	iotlb->nmaps = 0;
+	iotlb->flags = flags;
+	INIT_LIST_HEAD(&iotlb->list);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_init);
+
 /**
  * vhost_iotlb_alloc - add a new vhost IOTLB
  * @limit: maximum number of IOTLB entries
@@ -139,11 +156,7 @@ struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags)
 	if (!iotlb)
 		return NULL;
 
-	iotlb->root = RB_ROOT_CACHED;
-	iotlb->limit = limit;
-	iotlb->nmaps = 0;
-	iotlb->flags = flags;
-	INIT_LIST_HEAD(&iotlb->list);
+	vhost_iotlb_init(iotlb, limit, flags);
 
 	return iotlb;
 }
diff --git a/include/linux/vhost_iotlb.h b/include/linux/vhost_iotlb.h
index 2d0e2f52f938..e79a40838998 100644
--- a/include/linux/vhost_iotlb.h
+++ b/include/linux/vhost_iotlb.h
@@ -36,6 +36,8 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last,
 			  u64 addr, unsigned int perm);
 void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last);
 
+void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit,
+		      unsigned int flags);
 struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags);
 void vhost_iotlb_free(struct vhost_iotlb *iotlb);
 void vhost_iotlb_reset(struct vhost_iotlb *iotlb);
-- 
cgit v1.2.3


From ffbda8e9df10d1784d5427ec199e7d8308e3763f Mon Sep 17 00:00:00 2001
From: Cindy Lu <lulu@redhat.com>
Date: Fri, 29 Apr 2022 17:10:30 +0800
Subject: vdpa/vp_vdpa : add vdpa tool support in vp_vdpa

this patch is to add the support for vdpa tool in vp_vdpa
here is the example steps

modprobe vp_vdpa
modprobe vhost_vdpa
echo 0000:00:06.0>/sys/bus/pci/drivers/virtio-pci/unbind
echo 1af4 1041 > /sys/bus/pci/drivers/vp-vdpa/new_id

vdpa dev add name vdpa1 mgmtdev pci/0000:00:06.0

Signed-off-by: Cindy Lu <lulu@redhat.com>
Message-Id: <20220429091030.547434-1-lulu@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/virtio_pci/vp_vdpa.c | 161 ++++++++++++++++++++++++++++++--------
 include/linux/vdpa.h              |   2 +-
 2 files changed, 130 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index 35acba0e8d6d..04522077735b 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -32,7 +32,7 @@ struct vp_vring {
 
 struct vp_vdpa {
 	struct vdpa_device vdpa;
-	struct virtio_pci_modern_device mdev;
+	struct virtio_pci_modern_device *mdev;
 	struct vp_vring *vring;
 	struct vdpa_callback config_cb;
 	char msix_name[VP_VDPA_NAME_SIZE];
@@ -41,6 +41,12 @@ struct vp_vdpa {
 	int vectors;
 };
 
+struct vp_vdpa_mgmtdev {
+	struct vdpa_mgmt_dev mgtdev;
+	struct virtio_pci_modern_device *mdev;
+	struct vp_vdpa *vp_vdpa;
+};
+
 static struct vp_vdpa *vdpa_to_vp(struct vdpa_device *vdpa)
 {
 	return container_of(vdpa, struct vp_vdpa, vdpa);
@@ -50,7 +56,12 @@ static struct virtio_pci_modern_device *vdpa_to_mdev(struct vdpa_device *vdpa)
 {
 	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
 
-	return &vp_vdpa->mdev;
+	return vp_vdpa->mdev;
+}
+
+static struct virtio_pci_modern_device *vp_vdpa_to_mdev(struct vp_vdpa *vp_vdpa)
+{
+	return vp_vdpa->mdev;
 }
 
 static u64 vp_vdpa_get_device_features(struct vdpa_device *vdpa)
@@ -96,7 +107,7 @@ static int vp_vdpa_get_vq_irq(struct vdpa_device *vdpa, u16 idx)
 
 static void vp_vdpa_free_irq(struct vp_vdpa *vp_vdpa)
 {
-	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa);
 	struct pci_dev *pdev = mdev->pci_dev;
 	int i;
 
@@ -143,7 +154,7 @@ static irqreturn_t vp_vdpa_config_handler(int irq, void *arg)
 
 static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa)
 {
-	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa);
 	struct pci_dev *pdev = mdev->pci_dev;
 	int i, ret, irq;
 	int queues = vp_vdpa->queues;
@@ -198,7 +209,7 @@ err:
 static void vp_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
 {
 	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
-	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa);
 	u8 s = vp_vdpa_get_status(vdpa);
 
 	if (status & VIRTIO_CONFIG_S_DRIVER_OK &&
@@ -212,7 +223,7 @@ static void vp_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
 static int vp_vdpa_reset(struct vdpa_device *vdpa)
 {
 	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
-	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa);
 	u8 s = vp_vdpa_get_status(vdpa);
 
 	vp_modern_set_status(mdev, 0);
@@ -372,7 +383,7 @@ static void vp_vdpa_get_config(struct vdpa_device *vdpa,
 			       void *buf, unsigned int len)
 {
 	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
-	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa);
 	u8 old, new;
 	u8 *p;
 	int i;
@@ -392,7 +403,7 @@ static void vp_vdpa_set_config(struct vdpa_device *vdpa,
 			       unsigned int len)
 {
 	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
-	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa);
 	const u8 *p = buf;
 	int i;
 
@@ -412,7 +423,7 @@ static struct vdpa_notification_area
 vp_vdpa_get_vq_notification(struct vdpa_device *vdpa, u16 qid)
 {
 	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
-	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa);
 	struct vdpa_notification_area notify;
 
 	notify.addr = vp_vdpa->vring[qid].notify_pa;
@@ -454,38 +465,31 @@ static void vp_vdpa_free_irq_vectors(void *data)
 	pci_free_irq_vectors(data);
 }
 
-static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+static int vp_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
+			   const struct vdpa_dev_set_config *add_config)
 {
-	struct virtio_pci_modern_device *mdev;
+	struct vp_vdpa_mgmtdev *vp_vdpa_mgtdev =
+		container_of(v_mdev, struct vp_vdpa_mgmtdev, mgtdev);
+
+	struct virtio_pci_modern_device *mdev = vp_vdpa_mgtdev->mdev;
+	struct pci_dev *pdev = mdev->pci_dev;
 	struct device *dev = &pdev->dev;
-	struct vp_vdpa *vp_vdpa;
+	struct vp_vdpa *vp_vdpa = NULL;
 	int ret, i;
 
-	ret = pcim_enable_device(pdev);
-	if (ret)
-		return ret;
-
 	vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa,
-				    dev, &vp_vdpa_ops, 1, 1, NULL, false);
+				    dev, &vp_vdpa_ops, 1, 1, name, false);
+
 	if (IS_ERR(vp_vdpa)) {
 		dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n");
 		return PTR_ERR(vp_vdpa);
 	}
 
-	mdev = &vp_vdpa->mdev;
-	mdev->pci_dev = pdev;
-
-	ret = vp_modern_probe(mdev);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to probe modern PCI device\n");
-		goto err;
-	}
-
-	pci_set_master(pdev);
-	pci_set_drvdata(pdev, vp_vdpa);
+	vp_vdpa_mgtdev->vp_vdpa = vp_vdpa;
 
 	vp_vdpa->vdpa.dma_dev = &pdev->dev;
 	vp_vdpa->queues = vp_modern_get_num_queues(mdev);
+	vp_vdpa->mdev = mdev;
 
 	ret = devm_add_action_or_reset(dev, vp_vdpa_free_irq_vectors, pdev);
 	if (ret) {
@@ -516,7 +520,8 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 	vp_vdpa->config_irq = VIRTIO_MSI_NO_VECTOR;
 
-	ret = vdpa_register_device(&vp_vdpa->vdpa, vp_vdpa->queues);
+	vp_vdpa->vdpa.mdev = &vp_vdpa_mgtdev->mgtdev;
+	ret = _vdpa_register_device(&vp_vdpa->vdpa, vp_vdpa->queues);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to register to vdpa bus\n");
 		goto err;
@@ -529,12 +534,104 @@ err:
 	return ret;
 }
 
+static void vp_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev,
+			    struct vdpa_device *dev)
+{
+	struct vp_vdpa_mgmtdev *vp_vdpa_mgtdev =
+		container_of(v_mdev, struct vp_vdpa_mgmtdev, mgtdev);
+
+	struct vp_vdpa *vp_vdpa = vp_vdpa_mgtdev->vp_vdpa;
+
+	_vdpa_unregister_device(&vp_vdpa->vdpa);
+	vp_vdpa_mgtdev->vp_vdpa = NULL;
+}
+
+static const struct vdpa_mgmtdev_ops vp_vdpa_mdev_ops = {
+	.dev_add = vp_vdpa_dev_add,
+	.dev_del = vp_vdpa_dev_del,
+};
+
+static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct vp_vdpa_mgmtdev *vp_vdpa_mgtdev = NULL;
+	struct vdpa_mgmt_dev *mgtdev;
+	struct device *dev = &pdev->dev;
+	struct virtio_pci_modern_device *mdev = NULL;
+	struct virtio_device_id *mdev_id = NULL;
+	int err;
+
+	vp_vdpa_mgtdev = kzalloc(sizeof(*vp_vdpa_mgtdev), GFP_KERNEL);
+	if (!vp_vdpa_mgtdev)
+		return -ENOMEM;
+
+	mgtdev = &vp_vdpa_mgtdev->mgtdev;
+	mgtdev->ops = &vp_vdpa_mdev_ops;
+	mgtdev->device = dev;
+
+	mdev = kzalloc(sizeof(struct virtio_pci_modern_device), GFP_KERNEL);
+	if (!mdev) {
+		err = -ENOMEM;
+		goto mdev_err;
+	}
+
+	mdev_id = kzalloc(sizeof(struct virtio_device_id), GFP_KERNEL);
+	if (!mdev_id) {
+		err = -ENOMEM;
+		goto mdev_id_err;
+	}
+
+	vp_vdpa_mgtdev->mdev = mdev;
+	mdev->pci_dev = pdev;
+
+	err = pcim_enable_device(pdev);
+	if (err) {
+		goto probe_err;
+	}
+
+	err = vp_modern_probe(mdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to probe modern PCI device\n");
+		goto probe_err;
+	}
+
+	mdev_id->device = mdev->id.device;
+	mdev_id->vendor = mdev->id.vendor;
+	mgtdev->id_table = mdev_id;
+	mgtdev->max_supported_vqs = vp_modern_get_num_queues(mdev);
+	mgtdev->supported_features = vp_modern_get_features(mdev);
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, vp_vdpa_mgtdev);
+
+	err = vdpa_mgmtdev_register(mgtdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to register vdpa mgmtdev device\n");
+		goto register_err;
+	}
+
+	return 0;
+
+register_err:
+	vp_modern_remove(vp_vdpa_mgtdev->mdev);
+probe_err:
+	kfree(mdev_id);
+mdev_id_err:
+	kfree(mdev);
+mdev_err:
+	kfree(vp_vdpa_mgtdev);
+	return err;
+}
+
 static void vp_vdpa_remove(struct pci_dev *pdev)
 {
-	struct vp_vdpa *vp_vdpa = pci_get_drvdata(pdev);
+	struct vp_vdpa_mgmtdev *vp_vdpa_mgtdev = pci_get_drvdata(pdev);
+	struct virtio_pci_modern_device *mdev = NULL;
 
-	vp_modern_remove(&vp_vdpa->mdev);
-	vdpa_unregister_device(&vp_vdpa->vdpa);
+	mdev = vp_vdpa_mgtdev->mdev;
+	vp_modern_remove(mdev);
+	vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev);
+	kfree(&vp_vdpa_mgtdev->mgtdev.id_table);
+	kfree(mdev);
+	kfree(vp_vdpa_mgtdev);
 }
 
 static struct pci_driver vp_vdpa_driver = {
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index f336d253db3d..15af802d41c4 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -492,7 +492,7 @@ struct vdpa_mgmtdev_ops {
 struct vdpa_mgmt_dev {
 	struct device *device;
 	const struct vdpa_mgmtdev_ops *ops;
-	const struct virtio_device_id *id_table;
+	struct virtio_device_id *id_table;
 	u64 config_attr_mask;
 	struct list_head list;
 	u64 supported_features;
-- 
cgit v1.2.3


From 48b69959a8559db5df78661d9c6d5138c2f20871 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 27 May 2022 14:01:14 +0800
Subject: virtio: introduce config op to synchronize vring callbacks

This patch introduces new virtio config op to vring
callbacks. Transport specific method is required to make sure the
write before this function is visible to the vring_interrupt() that is
called after the return of this function. For the transport that
doesn't provide synchronize_vqs(), use synchornize_rcu() which
synchronize with IRQ implicitly as a fallback.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Halil Pasic <pasic@linux.ibm.com>
Cc: Cornelia Huck <cohuck@redhat.com>
Cc: Vineeth Vijayan <vneethv@linux.ibm.com>
Cc: Peter Oberparleiter <oberpar@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220527060120.20964-4-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
---
 include/linux/virtio_config.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index b341dd62aa4d..25be018810a7 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -57,6 +57,11 @@ struct virtio_shm_region {
  *		include a NULL entry for vqs unused by driver
  *	Returns 0 on success or error status
  * @del_vqs: free virtqueues found by find_vqs().
+ * @synchronize_cbs: synchronize with the virtqueue callbacks (optional)
+ *      The function guarantees that all memory operations on the
+ *      queue before it are visible to the vring_interrupt() that is
+ *      called after it.
+ *      vdev: the virtio_device
  * @get_features: get the array of feature bits for this device.
  *	vdev: the virtio_device
  *	Returns the first 64 feature bits (all we currently need).
@@ -89,6 +94,7 @@ struct virtio_config_ops {
 			const char * const names[], const bool *ctx,
 			struct irq_affinity *desc);
 	void (*del_vqs)(struct virtio_device *);
+	void (*synchronize_cbs)(struct virtio_device *);
 	u64 (*get_features)(struct virtio_device *vdev);
 	int (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
@@ -217,6 +223,25 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs,
 				      desc);
 }
 
+/**
+ * virtio_synchronize_cbs - synchronize with virtqueue callbacks
+ * @vdev: the device
+ */
+static inline
+void virtio_synchronize_cbs(struct virtio_device *dev)
+{
+	if (dev->config->synchronize_cbs) {
+		dev->config->synchronize_cbs(dev);
+	} else {
+		/*
+		 * A best effort fallback to synchronize with
+		 * interrupts, preemption and softirq disabled
+		 * regions. See comment above synchronize_rcu().
+		 */
+		synchronize_rcu();
+	}
+}
+
 /**
  * virtio_device_ready - enable vq use in probe function
  * @vdev: the device
-- 
cgit v1.2.3


From be83f04d2529e8dc4273efdd1ccf7b7502741071 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 27 May 2022 14:01:18 +0800
Subject: virtio: allow to unbreak virtqueue

This patch allows the new introduced __virtio_break_device() to
unbreak the virtqueue.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Halil Pasic <pasic@linux.ibm.com>
Cc: Cornelia Huck <cohuck@redhat.com>
Cc: Vineeth Vijayan <vneethv@linux.ibm.com>
Cc: Peter Oberparleiter <oberpar@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220527060120.20964-8-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
 drivers/virtio/virtio_ring.c | 22 ++++++++++++++++++++++
 include/linux/virtio.h       |  1 +
 2 files changed, 23 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 9d0bae4293be..9c231e1fded7 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2395,6 +2395,28 @@ void virtio_break_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(virtio_break_device);
 
+/*
+ * This should allow the device to be used by the driver. You may
+ * need to grab appropriate locks to flush the write to
+ * vq->broken. This should only be used in some specific case e.g
+ * (probing and restoring). This function should only be called by the
+ * core, not directly by the driver.
+ */
+void __virtio_unbreak_device(struct virtio_device *dev)
+{
+	struct virtqueue *_vq;
+
+	spin_lock(&dev->vqs_list_lock);
+	list_for_each_entry(_vq, &dev->vqs, list) {
+		struct vring_virtqueue *vq = to_vvq(_vq);
+
+		/* Pairs with READ_ONCE() in virtqueue_is_broken(). */
+		WRITE_ONCE(vq->broken, false);
+	}
+	spin_unlock(&dev->vqs_list_lock);
+}
+EXPORT_SYMBOL_GPL(__virtio_unbreak_device);
+
 dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 5464f398912a..d8fdf170637c 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -131,6 +131,7 @@ void unregister_virtio_device(struct virtio_device *dev);
 bool is_virtio_device(struct device *dev);
 
 void virtio_break_device(struct virtio_device *dev);
+void __virtio_unbreak_device(struct virtio_device *dev);
 
 void virtio_config_changed(struct virtio_device *dev);
 #ifdef CONFIG_PM_SLEEP
-- 
cgit v1.2.3


From 8b4ec69d7e098a7ddf832e1e7840de53ed474c77 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 27 May 2022 14:01:19 +0800
Subject: virtio: harden vring IRQ

This is a rework on the previous IRQ hardening that is done for
virtio-pci where several drawbacks were found and were reverted:

1) try to use IRQF_NO_AUTOEN which is not friendly to affinity managed IRQ
   that is used by some device such as virtio-blk
2) done only for PCI transport

The vq->broken is re-used in this patch for implementing the IRQ
hardening. The vq->broken is set to true during both initialization
and reset. And the vq->broken is set to false in
virtio_device_ready(). Then vring_interrupt() can check and return
when vq->broken is true. And in this case, switch to return IRQ_NONE
to let the interrupt core aware of such invalid interrupt to prevent
IRQ storm.

The reason of using a per queue variable instead of a per device one
is that we may need it for per queue reset hardening in the future.

Note that the hardening is only done for vring interrupt since the
config interrupt hardening is already done in commit 22b7050a024d7
("virtio: defer config changed notifications"). But the method that is
used by config interrupt can't be reused by the vring interrupt
handler because it uses spinlock to do the synchronization which is
expensive.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Halil Pasic <pasic@linux.ibm.com>
Cc: Cornelia Huck <cohuck@redhat.com>
Cc: Vineeth Vijayan <vneethv@linux.ibm.com>
Cc: Peter Oberparleiter <oberpar@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220527060120.20964-9-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
 drivers/s390/virtio/virtio_ccw.c       |  4 ++++
 drivers/virtio/virtio.c                | 15 ++++++++++++---
 drivers/virtio/virtio_mmio.c           |  5 +++++
 drivers/virtio/virtio_pci_modern_dev.c |  5 +++++
 drivers/virtio/virtio_ring.c           | 11 +++++++----
 include/linux/virtio_config.h          | 20 ++++++++++++++++++++
 6 files changed, 53 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index c188e4f20ca3..97e51c34e6cf 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -971,6 +971,10 @@ static void virtio_ccw_set_status(struct virtio_device *vdev, u8 status)
 	ccw->flags = 0;
 	ccw->count = sizeof(status);
 	ccw->cda = (__u32)(unsigned long)&vcdev->dma_area->status;
+	/* We use ssch for setting the status which is a serializing
+	 * instruction that guarantees the memory writes have
+	 * completed before ssch.
+	 */
 	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_STATUS);
 	/* Write failed? We assume status is unchanged. */
 	if (ret)
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index aa1eb5132767..95fac4c97c8b 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -220,6 +220,15 @@ static int virtio_features_ok(struct virtio_device *dev)
  * */
 void virtio_reset_device(struct virtio_device *dev)
 {
+	/*
+	 * The below virtio_synchronize_cbs() guarantees that any
+	 * interrupt for this line arriving after
+	 * virtio_synchronize_vqs() has completed is guaranteed to see
+	 * vq->broken as true.
+	 */
+	virtio_break_device(dev);
+	virtio_synchronize_cbs(dev);
+
 	dev->config->reset(dev);
 }
 EXPORT_SYMBOL_GPL(virtio_reset_device);
@@ -428,6 +437,9 @@ int register_virtio_device(struct virtio_device *dev)
 	dev->config_enabled = false;
 	dev->config_change_pending = false;
 
+	INIT_LIST_HEAD(&dev->vqs);
+	spin_lock_init(&dev->vqs_list_lock);
+
 	/* We always start by resetting the device, in case a previous
 	 * driver messed it up.  This also tests that code path a little. */
 	virtio_reset_device(dev);
@@ -435,9 +447,6 @@ int register_virtio_device(struct virtio_device *dev)
 	/* Acknowledge that we've seen the device. */
 	virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
 
-	INIT_LIST_HEAD(&dev->vqs);
-	spin_lock_init(&dev->vqs_list_lock);
-
 	/*
 	 * device_add() causes the bus infrastructure to look for a matching
 	 * driver.
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index c9699a59f93c..f9a36bc7ac27 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -253,6 +253,11 @@ static void vm_set_status(struct virtio_device *vdev, u8 status)
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
 
+	/*
+	 * Per memory-barriers.txt, wmb() is not needed to guarantee
+	 * that the the cache coherent memory writes have completed
+	 * before writing to the MMIO region.
+	 */
 	writel(status, vm_dev->base + VIRTIO_MMIO_STATUS);
 }
 
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index 4093f9cca7a6..a0fa14f28a7f 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -467,6 +467,11 @@ void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
+	/*
+	 * Per memory-barriers.txt, wmb() is not needed to guarantee
+	 * that the the cache coherent memory writes have completed
+	 * before writing to the MMIO region.
+	 */
 	vp_iowrite8(status, &cfg->device_status);
 }
 EXPORT_SYMBOL_GPL(vp_modern_set_status);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 9c231e1fded7..13a7348cedff 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1688,7 +1688,7 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	vq->we_own_ring = true;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
-	vq->broken = false;
+	vq->broken = true;
 	vq->last_used_idx = 0;
 	vq->event_triggered = false;
 	vq->num_added = 0;
@@ -2134,8 +2134,11 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 		return IRQ_NONE;
 	}
 
-	if (unlikely(vq->broken))
-		return IRQ_HANDLED;
+	if (unlikely(vq->broken)) {
+		dev_warn_once(&vq->vq.vdev->dev,
+			      "virtio vring IRQ raised before DRIVER_OK");
+		return IRQ_NONE;
+	}
 
 	/* Just a hint for performance: so it's ok that this can be racy! */
 	if (vq->event)
@@ -2177,7 +2180,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	vq->we_own_ring = false;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
-	vq->broken = false;
+	vq->broken = true;
 	vq->last_used_idx = 0;
 	vq->event_triggered = false;
 	vq->num_added = 0;
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 25be018810a7..d4edfd7d91bb 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -256,6 +256,26 @@ void virtio_device_ready(struct virtio_device *dev)
 	unsigned status = dev->config->get_status(dev);
 
 	BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
+
+	/*
+	 * The virtio_synchronize_cbs() makes sure vring_interrupt()
+	 * will see the driver specific setup if it sees vq->broken
+	 * as false (even if the notifications come before DRIVER_OK).
+	 */
+	virtio_synchronize_cbs(dev);
+	__virtio_unbreak_device(dev);
+	/*
+	 * The transport should ensure the visibility of vq->broken
+	 * before setting DRIVER_OK. See the comments for the transport
+	 * specific set_status() method.
+	 *
+	 * A well behaved device will only notify a virtqueue after
+	 * DRIVER_OK, this means the device should "see" the coherenct
+	 * memory write that set vq->broken as false which is done by
+	 * the driver when it sees DRIVER_OK, then the following
+	 * driver's vring_interrupt() will see vq->broken as false so
+	 * we won't lose any notification.
+	 */
 	dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK);
 }
 
-- 
cgit v1.2.3


From 619e9e14ba3c97a80776c0b5a68a01caa41dd148 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 27 May 2022 14:01:20 +0800
Subject: virtio: use WARN_ON() to warning illegal status value

We used to use BUG_ON() in virtio_device_ready() to detect illegal
status value, this seems sub-optimal since the value is under the
control of the device. Switch to use WARN_ON() instead.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Halil Pasic <pasic@linux.ibm.com>
Cc: Cornelia Huck <cohuck@redhat.com>
Cc: Vineeth Vijayan <vneethv@linux.ibm.com>
Cc: Peter Oberparleiter <oberpar@linux.ibm.com>
Cc: linux-s390@vger.kernel.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220527060120.20964-10-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
 include/linux/virtio_config.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index d4edfd7d91bb..9a36051ceb76 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -255,7 +255,7 @@ void virtio_device_ready(struct virtio_device *dev)
 {
 	unsigned status = dev->config->get_status(dev);
 
-	BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
+	WARN_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
 
 	/*
 	 * The virtio_synchronize_cbs() makes sure vring_interrupt()
-- 
cgit v1.2.3


From 3fc2a9e89b3508a5cc0c324f26d7b4740ba8c456 Mon Sep 17 00:00:00 2001
From: Changcheng Liu <jerrliu@nvidia.com>
Date: Tue, 26 Apr 2022 21:28:14 +0800
Subject: net/mlx5: correct ECE offset in query qp output

ECE field should be after opt_param_mask in query qp output.

Fixes: 6b646a7e4af6 ("net/mlx5: Add ability to read and write ECE options")
Signed-off-by: Changcheng Liu <jerrliu@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 78b3d3465dd7..2cd7d611e7b3 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -5176,12 +5176,11 @@ struct mlx5_ifc_query_qp_out_bits {
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x20];
-	u8         ece[0x20];
+	u8         reserved_at_40[0x40];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_at_a0[0x20];
+	u8         ece[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-- 
cgit v1.2.3


From c3ed222745d9ad7b69299b349a64ba533c64a34f Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Sat, 14 May 2022 07:05:13 -0400
Subject: NFSv4: Fix free of uninitialized nfs4_label on referral lookup.

Send along the already-allocated fattr along with nfs4_fs_locations, and
drop the memcpy of fattr.  We end up growing two more allocations, but this
fixes up a crash as:

PID: 790    TASK: ffff88811b43c000  CPU: 0   COMMAND: "ls"
 #0 [ffffc90000857920] panic at ffffffff81b9bfde
 #1 [ffffc900008579c0] do_trap at ffffffff81023a9b
 #2 [ffffc90000857a10] do_error_trap at ffffffff81023b78
 #3 [ffffc90000857a58] exc_stack_segment at ffffffff81be1f45
 #4 [ffffc90000857a80] asm_exc_stack_segment at ffffffff81c009de
 #5 [ffffc90000857b08] nfs_lookup at ffffffffa0302322 [nfs]
 #6 [ffffc90000857b70] __lookup_slow at ffffffff813a4a5f
 #7 [ffffc90000857c60] walk_component at ffffffff813a86c4
 #8 [ffffc90000857cb8] path_lookupat at ffffffff813a9553
 #9 [ffffc90000857cf0] filename_lookup at ffffffff813ab86b

Suggested-by: Trond Myklebust <trondmy@hammerspace.com>
Fixes: 9558a007dbc3 ("NFS: Remove the label from the nfs4_lookup_res struct")
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4namespace.c  |  9 +++++++--
 fs/nfs/nfs4proc.c       | 15 +++++++--------
 fs/nfs/nfs4state.c      |  9 ++++++++-
 fs/nfs/nfs4xdr.c        |  4 ++--
 include/linux/nfs_xdr.h |  2 +-
 5 files changed, 25 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 3680c8da510c..f2dbf904c598 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -417,6 +417,9 @@ static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client)
 	fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
 	if (!fs_locations)
 		goto out_free;
+	fs_locations->fattr = nfs_alloc_fattr();
+	if (!fs_locations->fattr)
+		goto out_free_2;
 
 	/* Get locations */
 	dentry = ctx->clone_data.dentry;
@@ -427,14 +430,16 @@ static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client)
 	err = nfs4_proc_fs_locations(client, d_inode(parent), &dentry->d_name, fs_locations, page);
 	dput(parent);
 	if (err != 0)
-		goto out_free_2;
+		goto out_free_3;
 
 	err = -ENOENT;
 	if (fs_locations->nlocations <= 0 ||
 	    fs_locations->fs_path.ncomponents <= 0)
-		goto out_free_2;
+		goto out_free_3;
 
 	err = nfs_follow_referral(fc, fs_locations);
+out_free_3:
+	kfree(fs_locations->fattr);
 out_free_2:
 	kfree(fs_locations);
 out_free:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0dfdbb406f96..337609befd17 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4247,6 +4247,8 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir,
 	if (locations == NULL)
 		goto out;
 
+	locations->fattr = fattr;
+
 	status = nfs4_proc_fs_locations(client, dir, name, locations, page);
 	if (status != 0)
 		goto out;
@@ -4256,17 +4258,14 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir,
 	 * referral.  Cause us to drop into the exception handler, which
 	 * will kick off migration recovery.
 	 */
-	if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) {
+	if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &fattr->fsid)) {
 		dprintk("%s: server did not return a different fsid for"
 			" a referral at %s\n", __func__, name->name);
 		status = -NFS4ERR_MOVED;
 		goto out;
 	}
 	/* Fixup attributes for the nfs_lookup() call to nfs_fhget() */
-	nfs_fixup_referral_attributes(&locations->fattr);
-
-	/* replace the lookup nfs_fattr with the locations nfs_fattr */
-	memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr));
+	nfs_fixup_referral_attributes(fattr);
 	memset(fhandle, 0, sizeof(struct nfs_fh));
 out:
 	if (page)
@@ -7979,7 +7978,7 @@ static int _nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir,
 	else
 		bitmask[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
 
-	nfs_fattr_init(&fs_locations->fattr);
+	nfs_fattr_init(fs_locations->fattr);
 	fs_locations->server = server;
 	fs_locations->nlocations = 0;
 	status = nfs4_call_sync(client, server, &msg, &args.seq_args, &res.seq_res, 0);
@@ -8044,7 +8043,7 @@ static int _nfs40_proc_get_locations(struct nfs_server *server,
 	unsigned long now = jiffies;
 	int status;
 
-	nfs_fattr_init(&locations->fattr);
+	nfs_fattr_init(locations->fattr);
 	locations->server = server;
 	locations->nlocations = 0;
 
@@ -8109,7 +8108,7 @@ static int _nfs41_proc_get_locations(struct nfs_server *server,
 	};
 	int status;
 
-	nfs_fattr_init(&locations->fattr);
+	nfs_fattr_init(locations->fattr);
 	locations->server = server;
 	locations->nlocations = 0;
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 775c58def32c..2540b35ec187 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2116,6 +2116,11 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
 		dprintk("<-- %s: no memory\n", __func__);
 		goto out;
 	}
+	locations->fattr = nfs_alloc_fattr();
+	if (locations->fattr == NULL) {
+		dprintk("<-- %s: no memory\n", __func__);
+		goto out;
+	}
 
 	inode = d_inode(server->super->s_root);
 	result = nfs4_proc_get_locations(server, NFS_FH(inode), locations,
@@ -2130,7 +2135,7 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
 	if (!locations->nlocations)
 		goto out;
 
-	if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
+	if (!(locations->fattr->valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
 		dprintk("<-- %s: No fs_locations data, migration skipped\n",
 			__func__);
 		goto out;
@@ -2155,6 +2160,8 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
 out:
 	if (page != NULL)
 		__free_page(page);
+	if (locations != NULL)
+		kfree(locations->fattr);
 	kfree(locations);
 	if (result) {
 		pr_err("NFS: migration recovery failed (server %s)\n",
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 0b41e00e754f..acfe5f4bda48 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7080,7 +7080,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
 	if (res->migration) {
 		xdr_enter_page(xdr, PAGE_SIZE);
 		status = decode_getfattr_generic(xdr,
-					&res->fs_locations->fattr,
+					res->fs_locations->fattr,
 					 NULL, res->fs_locations,
 					 res->fs_locations->server);
 		if (status)
@@ -7093,7 +7093,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
 			goto out;
 		xdr_enter_page(xdr, PAGE_SIZE);
 		status = decode_getfattr_generic(xdr,
-					&res->fs_locations->fattr,
+					res->fs_locations->fattr,
 					 NULL, res->fs_locations,
 					 res->fs_locations->server);
 	}
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 4a8ba84f848e..0e3aa0f5f324 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1222,7 +1222,7 @@ struct nfs4_fs_location {
 
 #define NFS4_FS_LOCATIONS_MAXENTRIES 10
 struct nfs4_fs_locations {
-	struct nfs_fattr fattr;
+	struct nfs_fattr *fattr;
 	const struct nfs_server *server;
 	struct nfs4_pathname fs_path;
 	int nlocations;
-- 
cgit v1.2.3


From 118f09eda21d392e1eeb9f8a4bee044958cccf20 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@netapp.com>
Date: Wed, 25 May 2022 12:12:59 -0400
Subject: NFSv4.1 mark qualified async operations as MOVEABLE tasks

Mark async operations such as RENAME, REMOVE, COMMIT MOVEABLE
for the nfsv4.1+ sessions.

Fixes: 85e39feead948 ("NFSv4.1 identify and mark RPC tasks that can move between transports")
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c         | 26 ++++++++++++++------------
 fs/nfs/pagelist.c         |  3 +++
 fs/nfs/unlink.c           |  8 ++++++++
 fs/nfs/write.c            |  4 ++++
 include/linux/nfs_fs_sb.h |  1 +
 5 files changed, 30 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 337609befd17..c0fdcf8c0032 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1162,7 +1162,7 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 {
 	unsigned short task_flags = 0;
 
-	if (server->nfs_client->cl_minorversion)
+	if (server->caps & NFS_CAP_MOVEABLE)
 		task_flags = RPC_TASK_MOVEABLE;
 	return nfs4_do_call_sync(clnt, server, msg, args, res, task_flags);
 }
@@ -2568,7 +2568,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data,
 	};
 	int status;
 
-	if (server->nfs_client->cl_minorversion)
+	if (nfs_server_capable(dir, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
 	kref_get(&data->kref);
@@ -3737,7 +3737,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
 	};
 	int status = -ENOMEM;
 
-	if (server->nfs_client->cl_minorversion)
+	if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
 	nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP,
@@ -4407,7 +4407,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
 	};
 	unsigned short task_flags = 0;
 
-	if (server->nfs_client->cl_minorversion)
+	if (nfs_server_capable(dir, NFS_CAP_MOVEABLE))
 		task_flags = RPC_TASK_MOVEABLE;
 
 	/* Is this is an attribute revalidation, subject to softreval? */
@@ -6639,10 +6639,13 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 		.rpc_client = server->client,
 		.rpc_message = &msg,
 		.callback_ops = &nfs4_delegreturn_ops,
-		.flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT | RPC_TASK_MOVEABLE,
+		.flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
 	};
 	int status = 0;
 
+	if (nfs_server_capable(inode, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (data == NULL)
 		return -ENOMEM;
@@ -6956,10 +6959,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
 		.workqueue = nfsiod_workqueue,
 		.flags = RPC_TASK_ASYNC,
 	};
-	struct nfs_client *client =
-		NFS_SERVER(lsp->ls_state->inode)->nfs_client;
 
-	if (client->cl_minorversion)
+	if (nfs_server_capable(lsp->ls_state->inode, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
 	nfs4_state_protect(NFS_SERVER(lsp->ls_state->inode)->nfs_client,
@@ -7230,9 +7231,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 		.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF,
 	};
 	int ret;
-	struct nfs_client *client = NFS_SERVER(state->inode)->nfs_client;
 
-	if (client->cl_minorversion)
+	if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
 	data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file),
@@ -10467,7 +10467,8 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
-		| NFS_CAP_LGOPEN,
+		| NFS_CAP_LGOPEN
+		| NFS_CAP_MOVEABLE,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
@@ -10502,7 +10503,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_LAYOUTSTATS
 		| NFS_CAP_CLONE
 		| NFS_CAP_LAYOUTERROR
-		| NFS_CAP_READ_PLUS,
+		| NFS_CAP_READ_PLUS
+		| NFS_CAP_MOVEABLE,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 9157dd19b8b4..317cedfa52bf 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -767,6 +767,9 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 		.flags = RPC_TASK_ASYNC | flags,
 	};
 
+	if (nfs_server_capable(hdr->inode, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
 
 	dprintk("NFS: initiated pgio call "
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 6f325e10056c..9697cd5d2561 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -102,6 +102,10 @@ static void nfs_do_call_unlink(struct inode *inode, struct nfs_unlinkdata *data)
 	};
 	struct rpc_task *task;
 	struct inode *dir = d_inode(data->dentry->d_parent);
+
+	if (nfs_server_capable(inode, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	nfs_sb_active(dir->i_sb);
 	data->args.fh = NFS_FH(dir);
 	nfs_fattr_init(data->res.dir_attr);
@@ -344,6 +348,10 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
 		.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF,
 	};
 
+	if (nfs_server_capable(old_dir, NFS_CAP_MOVEABLE) &&
+	    nfs_server_capable(new_dir, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (data == NULL)
 		return ERR_PTR(-ENOMEM);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 2f41659e232e..1c706465d090 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1709,6 +1709,10 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 		.flags = RPC_TASK_ASYNC | flags,
 		.priority = priority,
 	};
+
+	if (nfs_server_capable(data->inode, NFS_CAP_MOVEABLE))
+		task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
 	/* Set up the initial task struct.  */
 	nfs_ops->commit_setup(data, &msg, &task_setup_data.rpc_client);
 	trace_nfs_initiate_commit(data);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 157d2bd6b241..ea2f7e6b1b0b 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -287,4 +287,5 @@ struct nfs_server {
 #define NFS_CAP_XATTR		(1U << 28)
 #define NFS_CAP_READ_PLUS	(1U << 29)
 #define NFS_CAP_FS_LOCATIONS	(1U << 30)
+#define NFS_CAP_MOVEABLE	(1U << 31)
 #endif
-- 
cgit v1.2.3


From 597b89d30b42dcc8e6b262e6876b42dde66f97f0 Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Mon, 16 May 2022 11:52:51 +0300
Subject: gpu: host1x: Add context bus

The context bus is a "dummy" bus that contains struct devices that
correspond to IOMMU contexts assigned through Host1x to processes.

Even when host1x itself is built as a module, the bus is registered
in built-in code so that the built-in ARM SMMU driver is able to
reference it.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/Makefile               |  3 +--
 drivers/gpu/host1x/Kconfig         |  5 +++++
 drivers/gpu/host1x/Makefile        |  1 +
 drivers/gpu/host1x/context_bus.c   | 31 +++++++++++++++++++++++++++++++
 include/linux/host1x_context_bus.h | 15 +++++++++++++++
 5 files changed, 53 insertions(+), 2 deletions(-)
 create mode 100644 drivers/gpu/host1x/context_bus.c
 create mode 100644 include/linux/host1x_context_bus.h

(limited to 'include/linux')

diff --git a/drivers/gpu/Makefile b/drivers/gpu/Makefile
index 835c88318cec..8997f0096545 100644
--- a/drivers/gpu/Makefile
+++ b/drivers/gpu/Makefile
@@ -2,7 +2,6 @@
 # drm/tegra depends on host1x, so if both drivers are built-in care must be
 # taken to initialize them in the correct order. Link order is the only way
 # to ensure this currently.
-obj-$(CONFIG_TEGRA_HOST1X)	+= host1x/
-obj-y			+= drm/ vga/
+obj-y			+= host1x/ drm/ vga/
 obj-$(CONFIG_IMX_IPUV3_CORE)	+= ipu-v3/
 obj-$(CONFIG_TRACE_GPU_MEM)		+= trace/
diff --git a/drivers/gpu/host1x/Kconfig b/drivers/gpu/host1x/Kconfig
index 6815b4db17c1..1861a8180d3f 100644
--- a/drivers/gpu/host1x/Kconfig
+++ b/drivers/gpu/host1x/Kconfig
@@ -1,8 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0-only
+
+config TEGRA_HOST1X_CONTEXT_BUS
+	bool
+
 config TEGRA_HOST1X
 	tristate "NVIDIA Tegra host1x driver"
 	depends on ARCH_TEGRA || (ARM && COMPILE_TEST)
 	select DMA_SHARED_BUFFER
+	select TEGRA_HOST1X_CONTEXT_BUS
 	select IOMMU_IOVA
 	help
 	  Driver for the NVIDIA Tegra host1x hardware.
diff --git a/drivers/gpu/host1x/Makefile b/drivers/gpu/host1x/Makefile
index d2b6f7de0498..c891a3e33844 100644
--- a/drivers/gpu/host1x/Makefile
+++ b/drivers/gpu/host1x/Makefile
@@ -18,3 +18,4 @@ host1x-y = \
 	hw/host1x07.o
 
 obj-$(CONFIG_TEGRA_HOST1X) += host1x.o
+obj-$(CONFIG_TEGRA_HOST1X_CONTEXT_BUS) += context_bus.o
diff --git a/drivers/gpu/host1x/context_bus.c b/drivers/gpu/host1x/context_bus.c
new file mode 100644
index 000000000000..b0d35b2bbe89
--- /dev/null
+++ b/drivers/gpu/host1x/context_bus.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, NVIDIA Corporation.
+ */
+
+#include <linux/device.h>
+#include <linux/of.h>
+
+struct bus_type host1x_context_device_bus_type = {
+	.name = "host1x-context",
+};
+EXPORT_SYMBOL_GPL(host1x_context_device_bus_type);
+
+static int __init host1x_context_device_bus_init(void)
+{
+	int err;
+
+	if (!of_machine_is_compatible("nvidia,tegra186") &&
+	    !of_machine_is_compatible("nvidia,tegra194") &&
+	    !of_machine_is_compatible("nvidia,tegra234"))
+		return 0;
+
+	err = bus_register(&host1x_context_device_bus_type);
+	if (err < 0) {
+		pr_err("bus type registration failed: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+postcore_initcall(host1x_context_device_bus_init);
diff --git a/include/linux/host1x_context_bus.h b/include/linux/host1x_context_bus.h
new file mode 100644
index 000000000000..72462737a6db
--- /dev/null
+++ b/include/linux/host1x_context_bus.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2021, NVIDIA Corporation. All rights reserved.
+ */
+
+#ifndef __LINUX_HOST1X_CONTEXT_BUS_H
+#define __LINUX_HOST1X_CONTEXT_BUS_H
+
+#include <linux/device.h>
+
+#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS
+extern struct bus_type host1x_context_device_bus_type;
+#endif
+
+#endif
-- 
cgit v1.2.3


From 662ce1dc9caf493c309200edbe38d186f1ea20d0 Mon Sep 17 00:00:00 2001
From: Yang Yang <yang.yang29@zte.com.cn>
Date: Wed, 1 Jun 2022 15:55:25 -0700
Subject: delayacct: track delays from write-protect copy

Delay accounting does not track the delay of write-protect copy.  When
tasks trigger many write-protect copys(include COW and unsharing of
anonymous pages[1]), it may spend a amount of time waiting for them.  To
get the delay of tasks in write-protect copy, could help users to evaluate
the impact of using KSM or fork() or GUP.

Also update tools/accounting/getdelays.c:

    / # ./getdelays -dl -p 231
    print delayacct stats ON
    listen forever
    PID     231

    CPU             count     real total  virtual total    delay total  delay average
                     6247     1859000000     2154070021     1674255063          0.268ms
    IO              count    delay total  delay average
                        0              0              0ms
    SWAP            count    delay total  delay average
                        0              0              0ms
    RECLAIM         count    delay total  delay average
                        0              0              0ms
    THRASHING       count    delay total  delay average
                        0              0              0ms
    COMPACT         count    delay total  delay average
                        3          72758              0ms
    WPCOPY          count    delay total  delay average
                     3635      271567604              0ms

[1] commit 31cc5bc4af70("mm: support GUP-triggered unsharing of anonymous pages")

Link: https://lkml.kernel.org/r/20220409014342.2505532-1-yang.yang29@zte.com.cn
Signed-off-by: Yang Yang <yang.yang29@zte.com.cn>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Jiang Xuexin <jiang.xuexin@zte.com.cn>
Reviewed-by: Ran Xiaokai <ran.xiaokai@zte.com.cn>
Reviewed-by: wangyong <wang.yong12@zte.com.cn>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/accounting/delay-accounting.rst |  5 ++++-
 include/linux/delayacct.h                     | 28 +++++++++++++++++++++++++++
 include/uapi/linux/taskstats.h                |  6 +++++-
 kernel/delayacct.c                            | 16 +++++++++++++++
 mm/hugetlb.c                                  |  8 ++++++++
 mm/memory.c                                   |  8 ++++++++
 tools/accounting/getdelays.c                  |  8 +++++++-
 7 files changed, 76 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst
index 197fe319cbec..241d1a87f2cd 100644
--- a/Documentation/accounting/delay-accounting.rst
+++ b/Documentation/accounting/delay-accounting.rst
@@ -15,6 +15,7 @@ c) swapping in pages
 d) memory reclaim
 e) thrashing page cache
 f) direct compact
+g) write-protect copy
 
 and makes these statistics available to userspace through
 the taskstats interface.
@@ -48,7 +49,7 @@ this structure. See
 for a description of the fields pertaining to delay accounting.
 It will generally be in the form of counters returning the cumulative
 delay seen for cpu, sync block I/O, swapin, memory reclaim, thrash page
-cache, direct compact etc.
+cache, direct compact, write-protect copy etc.
 
 Taking the difference of two successive readings of a given
 counter (say cpu_delay_total) for a task will give the delay
@@ -117,6 +118,8 @@ Get sum of delays, since system boot, for all pids with tgid 5::
 	                    0              0              0ms
 	COMPACT         count    delay total  delay average
 	                    0              0              0ms
+        WPCOPY          count    delay total  delay average
+                            0              0              0ms
 
 Get IO accounting for pid 1, it works only with -p::
 
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 6b16a6930a19..58aea2d7385c 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -45,9 +45,13 @@ struct task_delay_info {
 	u64 compact_start;
 	u64 compact_delay;	/* wait for memory compact */
 
+	u64 wpcopy_start;
+	u64 wpcopy_delay;	/* wait for write-protect copy */
+
 	u32 freepages_count;	/* total count of memory reclaim */
 	u32 thrashing_count;	/* total count of thrash waits */
 	u32 compact_count;	/* total count of memory compact */
+	u32 wpcopy_count;	/* total count of write-protect copy */
 };
 #endif
 
@@ -75,6 +79,8 @@ extern void __delayacct_swapin_start(void);
 extern void __delayacct_swapin_end(void);
 extern void __delayacct_compact_start(void);
 extern void __delayacct_compact_end(void);
+extern void __delayacct_wpcopy_start(void);
+extern void __delayacct_wpcopy_end(void);
 
 static inline void delayacct_tsk_init(struct task_struct *tsk)
 {
@@ -191,6 +197,24 @@ static inline void delayacct_compact_end(void)
 		__delayacct_compact_end();
 }
 
+static inline void delayacct_wpcopy_start(void)
+{
+	if (!static_branch_unlikely(&delayacct_key))
+		return;
+
+	if (current->delays)
+		__delayacct_wpcopy_start();
+}
+
+static inline void delayacct_wpcopy_end(void)
+{
+	if (!static_branch_unlikely(&delayacct_key))
+		return;
+
+	if (current->delays)
+		__delayacct_wpcopy_end();
+}
+
 #else
 static inline void delayacct_init(void)
 {}
@@ -225,6 +249,10 @@ static inline void delayacct_compact_start(void)
 {}
 static inline void delayacct_compact_end(void)
 {}
+static inline void delayacct_wpcopy_start(void)
+{}
+static inline void delayacct_wpcopy_end(void)
+{}
 
 #endif /* CONFIG_TASK_DELAY_ACCT */
 
diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h
index 736154171489..a7f5b11a8f1b 100644
--- a/include/uapi/linux/taskstats.h
+++ b/include/uapi/linux/taskstats.h
@@ -34,7 +34,7 @@
  */
 
 
-#define TASKSTATS_VERSION	12
+#define TASKSTATS_VERSION	13
 #define TS_COMM_LEN		32	/* should be >= TASK_COMM_LEN
 					 * in linux/sched.h */
 
@@ -194,6 +194,10 @@ struct taskstats {
 	__u64   ac_exe_dev;     /* program binary device ID */
 	__u64   ac_exe_inode;   /* program binary inode number */
 	/* v12 end */
+
+	/* v13: Delay waiting for write-protect copy */
+	__u64    wpcopy_count;
+	__u64    wpcopy_delay_total;
 };
 
 
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 2c1e18f7c5cf..164ed9ef77a3 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -177,11 +177,14 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
 	tmp = d->compact_delay_total + tsk->delays->compact_delay;
 	d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp;
+	tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay;
+	d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp;
 	d->blkio_count += tsk->delays->blkio_count;
 	d->swapin_count += tsk->delays->swapin_count;
 	d->freepages_count += tsk->delays->freepages_count;
 	d->thrashing_count += tsk->delays->thrashing_count;
 	d->compact_count += tsk->delays->compact_count;
+	d->wpcopy_count += tsk->delays->wpcopy_count;
 	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 	return 0;
@@ -249,3 +252,16 @@ void __delayacct_compact_end(void)
 		      &current->delays->compact_delay,
 		      &current->delays->compact_count);
 }
+
+void __delayacct_wpcopy_start(void)
+{
+	current->delays->wpcopy_start = local_clock();
+}
+
+void __delayacct_wpcopy_end(void)
+{
+	delayacct_end(&current->delays->lock,
+		      &current->delays->wpcopy_start,
+		      &current->delays->wpcopy_delay,
+		      &current->delays->wpcopy_count);
+}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7c468ac1d069..a57e1be41401 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -32,6 +32,7 @@
 #include <linux/cma.h>
 #include <linux/migrate.h>
 #include <linux/nospec.h>
+#include <linux/delayacct.h>
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
@@ -5230,6 +5231,8 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte = huge_ptep_get(ptep);
 	old_page = pte_page(pte);
 
+	delayacct_wpcopy_start();
+
 retry_avoidcopy:
 	/*
 	 * If no-one else is actually using this page, we're the exclusive
@@ -5240,6 +5243,8 @@ retry_avoidcopy:
 			page_move_anon_rmap(old_page, vma);
 		if (likely(!unshare))
 			set_huge_ptep_writable(vma, haddr, ptep);
+
+		delayacct_wpcopy_end();
 		return 0;
 	}
 	VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page),
@@ -5309,6 +5314,7 @@ retry_avoidcopy:
 			 * race occurs while re-acquiring page table
 			 * lock, and our job is done.
 			 */
+			delayacct_wpcopy_end();
 			return 0;
 		}
 
@@ -5367,6 +5373,8 @@ out_release_old:
 	put_page(old_page);
 
 	spin_lock(ptl); /* Caller expects lock to be held */
+
+	delayacct_wpcopy_end();
 	return ret;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 21dadf03f089..7a089145cad4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3090,6 +3090,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	int page_copied = 0;
 	struct mmu_notifier_range range;
 
+	delayacct_wpcopy_start();
+
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
 
@@ -3114,6 +3116,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			put_page(new_page);
 			if (old_page)
 				put_page(old_page);
+
+			delayacct_wpcopy_end();
 			return 0;
 		}
 	}
@@ -3220,12 +3224,16 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			free_swap_cache(old_page);
 		put_page(old_page);
 	}
+
+	delayacct_wpcopy_end();
 	return (page_copied && !unshare) ? VM_FAULT_WRITE : 0;
 oom_free_new:
 	put_page(new_page);
 oom:
 	if (old_page)
 		put_page(old_page);
+
+	delayacct_wpcopy_end();
 	return VM_FAULT_OOM;
 }
 
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 11e86739456d..e83e6e47a21e 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -207,6 +207,8 @@ static void print_delayacct(struct taskstats *t)
 	       "THRASHING%12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n"
 	       "COMPACT  %12s%15s%15s\n"
+	       "      %15llu%15llu%15llums\n"
+	       "WPCOPY   %12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n",
 	       "count", "real total", "virtual total",
 	       "delay total", "delay average",
@@ -234,7 +236,11 @@ static void print_delayacct(struct taskstats *t)
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->compact_count,
 	       (unsigned long long)t->compact_delay_total,
-	       average_ms(t->compact_delay_total, t->compact_count));
+	       average_ms(t->compact_delay_total, t->compact_count),
+	       "count", "delay total", "delay average",
+	       (unsigned long long)t->wpcopy_count,
+	       (unsigned long long)t->wpcopy_delay_total,
+	       average_ms(t->wpcopy_delay_total, t->wpcopy_count));
 }
 
 static void task_context_switch_counts(struct taskstats *t)
-- 
cgit v1.2.3


From 22296a5c0cd35aaf62e1af3266f82cdf6b0b9b78 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Jun 2022 09:18:58 -0700
Subject: net: add debug info to __skb_pull()

While analyzing yet another syzbot report, I found the following
patch very useful. It allows to better understand what went wrong.

This debug info is only enabled if CONFIG_DEBUG_NET=y,
which is the case for syzbot builds.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index da96f0d3e753..d3d10556f0fa 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2696,7 +2696,14 @@ void *skb_pull(struct sk_buff *skb, unsigned int len);
 static inline void *__skb_pull(struct sk_buff *skb, unsigned int len)
 {
 	skb->len -= len;
-	BUG_ON(skb->len < skb->data_len);
+	if (unlikely(skb->len < skb->data_len)) {
+#if defined(CONFIG_DEBUG_NET)
+		skb->len += len;
+		pr_err("__skb_pull(len=%u)\n", len);
+		skb_dump(KERN_ERR, skb, false);
+#endif
+		BUG();
+	}
 	return skb->data += len;
 }
 
-- 
cgit v1.2.3


From 46859ac8af52ae599e1b51992ddef3eb43f295fc Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 31 May 2022 18:04:12 +0800
Subject: LoongArch: Add multi-processor (SMP) support

LoongArch-based procesors have 4, 8 or 16 cores per package. This patch
adds multi-processor (SMP) support for LoongArch.

Reviewed-by: WANG Xuerui <git@xen0n.name>
Reviewed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig                  |  40 +-
 arch/loongarch/include/asm/atomic.h     |   4 +
 arch/loongarch/include/asm/barrier.h    | 108 +++++
 arch/loongarch/include/asm/cmpxchg.h    |   1 +
 arch/loongarch/include/asm/futex.h      |   1 +
 arch/loongarch/include/asm/hardirq.h    |   2 +
 arch/loongarch/include/asm/irq.h        |   2 +
 arch/loongarch/include/asm/percpu.h     | 194 +++++++++
 arch/loongarch/include/asm/pgtable.h    |  21 +
 arch/loongarch/include/asm/smp.h        | 124 ++++++
 arch/loongarch/include/asm/stackframe.h |  17 +-
 arch/loongarch/include/asm/tlbflush.h   |  13 +
 arch/loongarch/include/asm/topology.h   |   7 +-
 arch/loongarch/kernel/Makefile          |   2 +
 arch/loongarch/kernel/acpi.c            |  69 +++
 arch/loongarch/kernel/asm-offsets.c     |  10 +
 arch/loongarch/kernel/head.S            |  30 ++
 arch/loongarch/kernel/irq.c             |  13 +-
 arch/loongarch/kernel/proc.c            |   5 +
 arch/loongarch/kernel/process.c         |   7 +
 arch/loongarch/kernel/reset.c           |  12 +
 arch/loongarch/kernel/setup.c           |  26 ++
 arch/loongarch/kernel/smp.c             | 735 ++++++++++++++++++++++++++++++++
 arch/loongarch/kernel/topology.c        |  43 +-
 arch/loongarch/kernel/vmlinux.lds.S     |   4 +
 arch/loongarch/mm/tlbex.S               |  69 +++
 include/linux/cpuhotplug.h              |   1 +
 27 files changed, 1550 insertions(+), 10 deletions(-)
 create mode 100644 arch/loongarch/include/asm/smp.h
 create mode 100644 arch/loongarch/kernel/smp.c

(limited to 'include/linux')

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 03d9b74eb2a9..85ef258d36d2 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -64,6 +64,7 @@ config LOONGARCH
 	select GENERIC_LIB_UCMPDI2
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
+	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GPIOLIB
 	select HAVE_ARCH_AUDITSYSCALL
@@ -92,7 +93,7 @@ config LOONGARCH
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_TIF_NOHZ
-	select HAVE_VIRT_CPU_ACCOUNTING_GEN
+	select HAVE_VIRT_CPU_ACCOUNTING_GEN if !SMP
 	select IRQ_FORCED_THREADING
 	select IRQ_LOONGARCH_CPU
 	select MODULES_USE_ELF_RELA if MODULES
@@ -297,6 +298,43 @@ config EFI
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).
 
+config SMP
+	bool "Multi-Processing support"
+	help
+	  This enables support for systems with more than one CPU. If you have
+	  a system with only one CPU, say N. If you have a system with more
+	  than one CPU, say Y.
+
+	  If you say N here, the kernel will run on uni- and multiprocessor
+	  machines, but will use only one CPU of a multiprocessor machine. If
+	  you say Y here, the kernel will run on many, but not all,
+	  uniprocessor machines. On a uniprocessor machine, the kernel
+	  will run faster if you say N here.
+
+	  See also the SMP-HOWTO available at <http://www.tldp.org/docs.html#howto>.
+
+	  If you don't know what to do here, say N.
+
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP
+	select GENERIC_IRQ_MIGRATION
+	help
+	  Say Y here to allow turning CPUs off and on. CPUs can be
+	  controlled through /sys/devices/system/cpu.
+	  (Note: power management support will enable this option
+	    automatically on SMP systems. )
+	  Say N if you want to disable CPU hotplug.
+
+config NR_CPUS
+	int "Maximum number of CPUs (2-256)"
+	range 2 256
+	depends on SMP
+	default "64"
+	help
+	  This allows you to specify the maximum number of CPUs which this
+	  kernel will support.
+
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
 	range 14 64 if PAGE_SIZE_64KB
diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h
index 932352342b12..979367ad4e2c 100644
--- a/arch/loongarch/include/asm/atomic.h
+++ b/arch/loongarch/include/asm/atomic.h
@@ -162,6 +162,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 		"	sc.w	%1, %2					\n"
 		"	beq	$zero, %1, 1b				\n"
 		"2:							\n"
+		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "I" (-i));
@@ -174,6 +175,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 		"	sc.w	%1, %2					\n"
 		"	beq	$zero, %1, 1b				\n"
 		"2:							\n"
+		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "r" (i));
@@ -323,6 +325,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v)
 		"	sc.d	%1, %2					\n"
 		"	beq	%1, $zero, 1b				\n"
 		"2:							\n"
+		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "I" (-i));
@@ -335,6 +338,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v)
 		"	sc.d	%1, %2					\n"
 		"	beq	%1, $zero, 1b				\n"
 		"2:							\n"
+		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "r" (i));
diff --git a/arch/loongarch/include/asm/barrier.h b/arch/loongarch/include/asm/barrier.h
index e57571bcaf4f..b6517eeeb141 100644
--- a/arch/loongarch/include/asm/barrier.h
+++ b/arch/loongarch/include/asm/barrier.h
@@ -18,6 +18,19 @@
 #define mb()		fast_mb()
 #define iob()		fast_iob()
 
+#define __smp_mb()	__asm__ __volatile__("dbar 0" : : : "memory")
+#define __smp_rmb()	__asm__ __volatile__("dbar 0" : : : "memory")
+#define __smp_wmb()	__asm__ __volatile__("dbar 0" : : : "memory")
+
+#ifdef CONFIG_SMP
+#define __WEAK_LLSC_MB		"	dbar 0  \n"
+#else
+#define __WEAK_LLSC_MB		"		\n"
+#endif
+
+#define __smp_mb__before_atomic()	barrier()
+#define __smp_mb__after_atomic()	barrier()
+
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
  * @index: array element index
@@ -46,6 +59,101 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 	return mask;
 }
 
+#define __smp_load_acquire(p)							\
+({										\
+	union { typeof(*p) __val; char __c[1]; } __u;				\
+	unsigned long __tmp = 0;							\
+	compiletime_assert_atomic_type(*p);					\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		*(__u8 *)__u.__c = *(volatile __u8 *)p;				\
+		__smp_mb();							\
+		break;								\
+	case 2:									\
+		*(__u16 *)__u.__c = *(volatile __u16 *)p;			\
+		__smp_mb();							\
+		break;								\
+	case 4:									\
+		__asm__ __volatile__(						\
+		"amor_db.w %[val], %[tmp], %[mem]	\n"				\
+		: [val] "=&r" (*(__u32 *)__u.__c)				\
+		: [mem] "ZB" (*(u32 *) p), [tmp] "r" (__tmp)			\
+		: "memory");							\
+		break;								\
+	case 8:									\
+		__asm__ __volatile__(						\
+		"amor_db.d %[val], %[tmp], %[mem]	\n"				\
+		: [val] "=&r" (*(__u64 *)__u.__c)				\
+		: [mem] "ZB" (*(u64 *) p), [tmp] "r" (__tmp)			\
+		: "memory");							\
+		break;								\
+	}									\
+	(typeof(*p))__u.__val;								\
+})
+
+#define __smp_store_release(p, v)						\
+do {										\
+	union { typeof(*p) __val; char __c[1]; } __u =				\
+		{ .__val = (__force typeof(*p)) (v) };				\
+	unsigned long __tmp;							\
+	compiletime_assert_atomic_type(*p);					\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		__smp_mb();							\
+		*(volatile __u8 *)p = *(__u8 *)__u.__c;				\
+		break;								\
+	case 2:									\
+		__smp_mb();							\
+		*(volatile __u16 *)p = *(__u16 *)__u.__c;			\
+		break;								\
+	case 4:									\
+		__asm__ __volatile__(						\
+		"amswap_db.w %[tmp], %[val], %[mem]	\n"			\
+		: [mem] "+ZB" (*(u32 *)p), [tmp] "=&r" (__tmp)			\
+		: [val] "r" (*(__u32 *)__u.__c)					\
+		: );								\
+		break;								\
+	case 8:									\
+		__asm__ __volatile__(						\
+		"amswap_db.d %[tmp], %[val], %[mem]	\n"			\
+		: [mem] "+ZB" (*(u64 *)p), [tmp] "=&r" (__tmp)			\
+		: [val] "r" (*(__u64 *)__u.__c)					\
+		: );								\
+		break;								\
+	}									\
+} while (0)
+
+#define __smp_store_mb(p, v)							\
+do {										\
+	union { typeof(p) __val; char __c[1]; } __u =				\
+		{ .__val = (__force typeof(p)) (v) };				\
+	unsigned long __tmp;							\
+	switch (sizeof(p)) {							\
+	case 1:									\
+		*(volatile __u8 *)&p = *(__u8 *)__u.__c;			\
+		__smp_mb();							\
+		break;								\
+	case 2:									\
+		*(volatile __u16 *)&p = *(__u16 *)__u.__c;			\
+		__smp_mb();							\
+		break;								\
+	case 4:									\
+		__asm__ __volatile__(						\
+		"amswap_db.w %[tmp], %[val], %[mem]	\n"			\
+		: [mem] "+ZB" (*(u32 *)&p), [tmp] "=&r" (__tmp)			\
+		: [val] "r" (*(__u32 *)__u.__c)					\
+		: );								\
+		break;								\
+	case 8:									\
+		__asm__ __volatile__(						\
+		"amswap_db.d %[tmp], %[val], %[mem]	\n"			\
+		: [mem] "+ZB" (*(u64 *)&p), [tmp] "=&r" (__tmp)			\
+		: [val] "r" (*(__u64 *)__u.__c)					\
+		: );								\
+		break;								\
+	}									\
+} while (0)
+
 #include <asm-generic/barrier.h>
 
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h
index 48613b872bc8..75b3a4478652 100644
--- a/arch/loongarch/include/asm/cmpxchg.h
+++ b/arch/loongarch/include/asm/cmpxchg.h
@@ -59,6 +59,7 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
 	"	" st "	$t0, %1				\n"		\
 	"	beq	$zero, $t0, 1b			\n"		\
 	"2:						\n"		\
+	__WEAK_LLSC_MB							\
 	: "=&r" (__ret), "=ZB"(*m)					\
 	: "ZB"(*m), "Jr" (old), "Jr" (new)				\
 	: "t0", "memory");						\
diff --git a/arch/loongarch/include/asm/futex.h b/arch/loongarch/include/asm/futex.h
index b27d55f92db7..9de8231694ec 100644
--- a/arch/loongarch/include/asm/futex.h
+++ b/arch/loongarch/include/asm/futex.h
@@ -86,6 +86,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv
 	"2:	sc.w	$t0, %2					\n"
 	"	beq	$zero, $t0, 1b				\n"
 	"3:							\n"
+	__WEAK_LLSC_MB
 	"	.section .fixup,\"ax\"				\n"
 	"4:	li.d	%0, %6					\n"
 	"	b	3b					\n"
diff --git a/arch/loongarch/include/asm/hardirq.h b/arch/loongarch/include/asm/hardirq.h
index d32f83938880..befe8184aa08 100644
--- a/arch/loongarch/include/asm/hardirq.h
+++ b/arch/loongarch/include/asm/hardirq.h
@@ -21,4 +21,6 @@ typedef struct {
 
 DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);
 
+#define __ARCH_IRQ_STAT
+
 #endif /* _ASM_HARDIRQ_H */
diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h
index f3f1baf7027c..ace3ea6da72e 100644
--- a/arch/loongarch/include/asm/irq.h
+++ b/arch/loongarch/include/asm/irq.h
@@ -125,6 +125,8 @@ extern struct irq_domain *pch_lpc_domain;
 extern struct irq_domain *pch_msi_domain[MAX_IO_PICS];
 extern struct irq_domain *pch_pic_domain[MAX_IO_PICS];
 
+extern irqreturn_t loongson3_ipi_interrupt(int irq, void *dev);
+
 #include <asm-generic/irq.h>
 
 #endif /* _ASM_IRQ_H */
diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index b03d8f8b9fd3..34f15a6fb1e7 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -5,6 +5,8 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#include <asm/cmpxchg.h>
+
 /* Use r21 for fast access */
 register unsigned long __my_cpu_offset __asm__("$r21");
 
@@ -15,6 +17,198 @@ static inline void set_my_cpu_offset(unsigned long off)
 }
 #define __my_cpu_offset __my_cpu_offset
 
+#define PERCPU_OP(op, asm_op, c_op)					\
+static inline unsigned long __percpu_##op(void *ptr,			\
+			unsigned long val, int size)			\
+{									\
+	unsigned long ret;						\
+									\
+	switch (size) {							\
+	case 4:								\
+		__asm__ __volatile__(					\
+		"am"#asm_op".w"	" %[ret], %[val], %[ptr]	\n"		\
+		: [ret] "=&r" (ret), [ptr] "+ZB"(*(u32 *)ptr)		\
+		: [val] "r" (val));					\
+		break;							\
+	case 8:								\
+		__asm__ __volatile__(					\
+		"am"#asm_op".d" " %[ret], %[val], %[ptr]	\n"		\
+		: [ret] "=&r" (ret), [ptr] "+ZB"(*(u64 *)ptr)		\
+		: [val] "r" (val));					\
+		break;							\
+	default:							\
+		ret = 0;						\
+		BUILD_BUG();						\
+	}								\
+									\
+	return ret c_op val;						\
+}
+
+PERCPU_OP(add, add, +)
+PERCPU_OP(and, and, &)
+PERCPU_OP(or, or, |)
+#undef PERCPU_OP
+
+static inline unsigned long __percpu_read(void *ptr, int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+	case 1:
+		__asm__ __volatile__ ("ldx.b %[ret], $r21, %[ptr]	\n"
+		: [ret] "=&r"(ret)
+		: [ptr] "r"(ptr)
+		: "memory");
+		break;
+	case 2:
+		__asm__ __volatile__ ("ldx.h %[ret], $r21, %[ptr]	\n"
+		: [ret] "=&r"(ret)
+		: [ptr] "r"(ptr)
+		: "memory");
+		break;
+	case 4:
+		__asm__ __volatile__ ("ldx.w %[ret], $r21, %[ptr]	\n"
+		: [ret] "=&r"(ret)
+		: [ptr] "r"(ptr)
+		: "memory");
+		break;
+	case 8:
+		__asm__ __volatile__ ("ldx.d %[ret], $r21, %[ptr]	\n"
+		: [ret] "=&r"(ret)
+		: [ptr] "r"(ptr)
+		: "memory");
+		break;
+	default:
+		ret = 0;
+		BUILD_BUG();
+	}
+
+	return ret;
+}
+
+static inline void __percpu_write(void *ptr, unsigned long val, int size)
+{
+	switch (size) {
+	case 1:
+		__asm__ __volatile__("stx.b %[val], $r21, %[ptr]	\n"
+		:
+		: [val] "r" (val), [ptr] "r" (ptr)
+		: "memory");
+		break;
+	case 2:
+		__asm__ __volatile__("stx.h %[val], $r21, %[ptr]	\n"
+		:
+		: [val] "r" (val), [ptr] "r" (ptr)
+		: "memory");
+		break;
+	case 4:
+		__asm__ __volatile__("stx.w %[val], $r21, %[ptr]	\n"
+		:
+		: [val] "r" (val), [ptr] "r" (ptr)
+		: "memory");
+		break;
+	case 8:
+		__asm__ __volatile__("stx.d %[val], $r21, %[ptr]	\n"
+		:
+		: [val] "r" (val), [ptr] "r" (ptr)
+		: "memory");
+		break;
+	default:
+		BUILD_BUG();
+	}
+}
+
+static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
+						int size)
+{
+	switch (size) {
+	case 4:
+		return __xchg_asm("amswap.w", (volatile u32 *)ptr, (u32)val);
+
+	case 8:
+		return __xchg_asm("amswap.d", (volatile u64 *)ptr, (u64)val);
+
+	default:
+		BUILD_BUG();
+	}
+
+	return 0;
+}
+
+/* this_cpu_cmpxchg */
+#define _protect_cmpxchg_local(pcp, o, n)			\
+({								\
+	typeof(*raw_cpu_ptr(&(pcp))) __ret;			\
+	preempt_disable_notrace();				\
+	__ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n);	\
+	preempt_enable_notrace();				\
+	__ret;							\
+})
+
+#define _percpu_read(pcp)						\
+({									\
+	typeof(pcp) __retval;						\
+	__retval = (typeof(pcp))__percpu_read(&(pcp), sizeof(pcp));	\
+	__retval;							\
+})
+
+#define _percpu_write(pcp, val)						\
+do {									\
+	__percpu_write(&(pcp), (unsigned long)(val), sizeof(pcp));	\
+} while (0)								\
+
+#define _pcp_protect(operation, pcp, val)			\
+({								\
+	typeof(pcp) __retval;					\
+	preempt_disable_notrace();				\
+	__retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)),	\
+					  (val), sizeof(pcp));	\
+	preempt_enable_notrace();				\
+	__retval;						\
+})
+
+#define _percpu_add(pcp, val) \
+	_pcp_protect(__percpu_add, pcp, val)
+
+#define _percpu_add_return(pcp, val) _percpu_add(pcp, val)
+
+#define _percpu_and(pcp, val) \
+	_pcp_protect(__percpu_and, pcp, val)
+
+#define _percpu_or(pcp, val) \
+	_pcp_protect(__percpu_or, pcp, val)
+
+#define _percpu_xchg(pcp, val) ((typeof(pcp)) \
+	_pcp_protect(__percpu_xchg, pcp, (unsigned long)(val)))
+
+#define this_cpu_add_4(pcp, val) _percpu_add(pcp, val)
+#define this_cpu_add_8(pcp, val) _percpu_add(pcp, val)
+
+#define this_cpu_add_return_4(pcp, val) _percpu_add_return(pcp, val)
+#define this_cpu_add_return_8(pcp, val) _percpu_add_return(pcp, val)
+
+#define this_cpu_and_4(pcp, val) _percpu_and(pcp, val)
+#define this_cpu_and_8(pcp, val) _percpu_and(pcp, val)
+
+#define this_cpu_or_4(pcp, val) _percpu_or(pcp, val)
+#define this_cpu_or_8(pcp, val) _percpu_or(pcp, val)
+
+#define this_cpu_read_1(pcp) _percpu_read(pcp)
+#define this_cpu_read_2(pcp) _percpu_read(pcp)
+#define this_cpu_read_4(pcp) _percpu_read(pcp)
+#define this_cpu_read_8(pcp) _percpu_read(pcp)
+
+#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val)
+
+#define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val)
+#define this_cpu_xchg_8(pcp, val) _percpu_xchg(pcp, val)
+
+#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+
 #include <asm-generic/percpu.h>
 
 #endif /* __ASM_PERCPU_H */
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 8920dd8b297b..5e33987d0a13 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -279,8 +279,29 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 		 * Make sure the buddy is global too (if it's !none,
 		 * it better already be global)
 		 */
+#ifdef CONFIG_SMP
+		/*
+		 * For SMP, multiple CPUs can race, so we need to do
+		 * this atomically.
+		 */
+		unsigned long page_global = _PAGE_GLOBAL;
+		unsigned long tmp;
+
+		__asm__ __volatile__ (
+		"1:"	__LL	"%[tmp], %[buddy]		\n"
+		"	bnez	%[tmp], 2f			\n"
+		"	 or	%[tmp], %[tmp], %[global]	\n"
+			__SC	"%[tmp], %[buddy]		\n"
+		"	beqz	%[tmp], 1b			\n"
+		"	nop					\n"
+		"2:						\n"
+		__WEAK_LLSC_MB
+		: [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
+		: [global] "r" (page_global));
+#else /* !CONFIG_SMP */
 		if (pte_none(*buddy))
 			pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
+#endif /* CONFIG_SMP */
 	}
 }
 
diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h
new file mode 100644
index 000000000000..551e1f37c705
--- /dev/null
+++ b/arch/loongarch/include/asm/smp.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Huacai Chen <chenhuacai@loongson.cn>
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/linkage.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+
+void loongson3_smp_setup(void);
+void loongson3_prepare_cpus(unsigned int max_cpus);
+void loongson3_boot_secondary(int cpu, struct task_struct *idle);
+void loongson3_init_secondary(void);
+void loongson3_smp_finish(void);
+void loongson3_send_ipi_single(int cpu, unsigned int action);
+void loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action);
+#ifdef CONFIG_HOTPLUG_CPU
+int loongson3_cpu_disable(void);
+void loongson3_cpu_die(unsigned int cpu);
+#endif
+
+#ifdef CONFIG_SMP
+
+static inline void plat_smp_setup(void)
+{
+	loongson3_smp_setup();
+}
+
+#else /* !CONFIG_SMP */
+
+static inline void plat_smp_setup(void) { }
+
+#endif /* !CONFIG_SMP */
+
+extern int smp_num_siblings;
+extern int num_processors;
+extern int disabled_cpus;
+extern cpumask_t cpu_sibling_map[];
+extern cpumask_t cpu_core_map[];
+extern cpumask_t cpu_foreign_map[];
+
+static inline int raw_smp_processor_id(void)
+{
+#if defined(__VDSO__)
+	extern int vdso_smp_processor_id(void)
+		__compiletime_error("VDSO should not call smp_processor_id()");
+	return vdso_smp_processor_id();
+#else
+	return current_thread_info()->cpu;
+#endif
+}
+#define raw_smp_processor_id raw_smp_processor_id
+
+/* Map from cpu id to sequential logical cpu number.  This will only
+ * not be idempotent when cpus failed to come on-line.	*/
+extern int __cpu_number_map[NR_CPUS];
+#define cpu_number_map(cpu)  __cpu_number_map[cpu]
+
+/* The reverse map from sequential logical cpu number to cpu id.  */
+extern int __cpu_logical_map[NR_CPUS];
+#define cpu_logical_map(cpu)  __cpu_logical_map[cpu]
+
+#define cpu_physical_id(cpu)	cpu_logical_map(cpu)
+
+#define SMP_BOOT_CPU		0x1
+#define SMP_RESCHEDULE		0x2
+#define SMP_CALL_FUNCTION	0x4
+
+struct secondary_data {
+	unsigned long stack;
+	unsigned long thread_info;
+};
+extern struct secondary_data cpuboot_data;
+
+extern asmlinkage void smpboot_entry(void);
+
+extern void calculate_cpu_foreign_map(void);
+
+/*
+ * Generate IPI list text
+ */
+extern void show_ipi_list(struct seq_file *p, int prec);
+
+/*
+ * This function sends a 'reschedule' IPI to another CPU.
+ * it goes straight through and wastes no time serializing
+ * anything. Worst case is that we lose a reschedule ...
+ */
+static inline void smp_send_reschedule(int cpu)
+{
+	loongson3_send_ipi_single(cpu, SMP_RESCHEDULE);
+}
+
+static inline void arch_send_call_function_single_ipi(int cpu)
+{
+	loongson3_send_ipi_single(cpu, SMP_CALL_FUNCTION);
+}
+
+static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
+{
+	loongson3_send_ipi_mask(mask, SMP_CALL_FUNCTION);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static inline int __cpu_disable(void)
+{
+	return loongson3_cpu_disable();
+}
+
+static inline void __cpu_die(unsigned int cpu)
+{
+	loongson3_cpu_die(cpu);
+}
+
+extern void play_dead(void);
+#endif
+
+#endif /* __ASM_SMP_H */
diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index 44151b878d00..4ca953062b5b 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -77,17 +77,24 @@
  * new value in sp.
  */
 	.macro	get_saved_sp docfi=0
-	la.abs	t1, kernelsp
-	move	t0, sp
+	la.abs	  t1, kernelsp
+#ifdef CONFIG_SMP
+	csrrd	  t0, PERCPU_BASE_KS
+	LONG_ADD  t1, t1, t0
+#endif
+	move	  t0, sp
 	.if \docfi
 	.cfi_register sp, t0
 	.endif
-	LONG_L	sp, t1, 0
+	LONG_L	  sp, t1, 0
 	.endm
 
 	.macro	set_saved_sp stackp temp temp2
-	la.abs	\temp, kernelsp
-	LONG_S	\stackp, \temp, 0
+	la.abs	  \temp, kernelsp
+#ifdef CONFIG_SMP
+	LONG_ADD  \temp, \temp, u0
+#endif
+	LONG_S	  \stackp, \temp, 0
 	.endm
 
 	.macro	SAVE_SOME docfi=0
diff --git a/arch/loongarch/include/asm/tlbflush.h b/arch/loongarch/include/asm/tlbflush.h
index 36bd6d11dc2d..a0785e590681 100644
--- a/arch/loongarch/include/asm/tlbflush.h
+++ b/arch/loongarch/include/asm/tlbflush.h
@@ -25,6 +25,17 @@ extern void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
 extern void local_flush_tlb_one(unsigned long vaddr);
 
+#ifdef CONFIG_SMP
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long, unsigned long);
+extern void flush_tlb_kernel_range(unsigned long, unsigned long);
+extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+extern void flush_tlb_one(unsigned long vaddr);
+
+#else /* CONFIG_SMP */
+
 #define flush_tlb_all()			local_flush_tlb_all()
 #define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
 #define flush_tlb_range(vma, vmaddr, end)	local_flush_tlb_range(vma, vmaddr, end)
@@ -32,4 +43,6 @@ extern void local_flush_tlb_one(unsigned long vaddr);
 #define flush_tlb_page(vma, page)	local_flush_tlb_page(vma, page)
 #define flush_tlb_one(vaddr)		local_flush_tlb_one(vaddr)
 
+#endif /* CONFIG_SMP */
+
 #endif /* __ASM_TLBFLUSH_H */
diff --git a/arch/loongarch/include/asm/topology.h b/arch/loongarch/include/asm/topology.h
index 9ac71a25207a..da135841e5b1 100644
--- a/arch/loongarch/include/asm/topology.h
+++ b/arch/loongarch/include/asm/topology.h
@@ -7,7 +7,12 @@
 
 #include <linux/smp.h>
 
-#define cpu_logical_map(cpu)  0
+#ifdef CONFIG_SMP
+#define topology_physical_package_id(cpu)	(cpu_data[cpu].package)
+#define topology_core_id(cpu)			(cpu_data[cpu].core)
+#define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
+#define topology_sibling_cpumask(cpu)		(&cpu_sibling_map[cpu])
+#endif
 
 #include <asm-generic/topology.h>
 
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index e5a3b2fb9961..2cb6f698716a 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -18,4 +18,6 @@ obj-$(CONFIG_MODULES)		+= module.o module-sections.o
 
 obj-$(CONFIG_PROC_FS)		+= proc.o
 
+obj-$(CONFIG_SMP)		+= smp.o
+
 CPPFLAGS_vmlinux.lds		:= $(KBUILD_CFLAGS)
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index a644220bb426..181c59493b63 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -137,8 +137,44 @@ void __init acpi_boot_table_init(void)
 	}
 }
 
+static int set_processor_mask(u32 id, u32 flags)
+{
+
+	int cpu, cpuid = id;
+
+	if (num_processors >= nr_cpu_ids) {
+		pr_warn(PREFIX "nr_cpus/possible_cpus limit of %i reached."
+			" processor 0x%x ignored.\n", nr_cpu_ids, cpuid);
+
+		return -ENODEV;
+
+	}
+	if (cpuid == loongson_sysconf.boot_cpu_id)
+		cpu = 0;
+	else
+		cpu = cpumask_next_zero(-1, cpu_present_mask);
+
+	if (flags & ACPI_MADT_ENABLED) {
+		num_processors++;
+		set_cpu_possible(cpu, true);
+		set_cpu_present(cpu, true);
+		__cpu_number_map[cpuid] = cpu;
+		__cpu_logical_map[cpu] = cpuid;
+	} else
+		disabled_cpus++;
+
+	return cpu;
+}
+
 static void __init acpi_process_madt(void)
 {
+	int i;
+
+	for (i = 0; i < NR_CPUS; i++) {
+		__cpu_number_map[i] = -1;
+		__cpu_logical_map[i] = -1;
+	}
+
 	loongson_sysconf.nr_cpus = num_processors;
 }
 
@@ -167,3 +203,36 @@ void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size)
 {
 	memblock_reserve(addr, size);
 }
+
+#ifdef CONFIG_ACPI_HOTPLUG_CPU
+
+#include <acpi/processor.h>
+
+int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu)
+{
+	int cpu;
+
+	cpu = set_processor_mask(physid, ACPI_MADT_ENABLED);
+	if (cpu < 0) {
+		pr_info(PREFIX "Unable to map lapic to logical cpu number\n");
+		return cpu;
+	}
+
+	*pcpu = cpu;
+
+	return 0;
+}
+EXPORT_SYMBOL(acpi_map_cpu);
+
+int acpi_unmap_cpu(int cpu)
+{
+	set_cpu_present(cpu, false);
+	num_processors--;
+
+	pr_info("cpu%d hot remove!\n", cpu);
+
+	return 0;
+}
+EXPORT_SYMBOL(acpi_unmap_cpu);
+
+#endif /* CONFIG_ACPI_HOTPLUG_CPU */
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 3531e3c60a6e..bfb65eb2844f 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -252,3 +252,13 @@ void output_signal_defines(void)
 	DEFINE(_SIGXFSZ, SIGXFSZ);
 	BLANK();
 }
+
+#ifdef CONFIG_SMP
+void output_smpboot_defines(void)
+{
+	COMMENT("Linux smp cpu boot offsets.");
+	OFFSET(CPU_BOOT_STACK, secondary_data, stack);
+	OFFSET(CPU_BOOT_TINFO, secondary_data, thread_info);
+	BLANK();
+}
+#endif
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 57dabb699bb7..e596dfcd924b 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -65,4 +65,34 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 
 SYM_CODE_END(kernel_entry)
 
+#ifdef CONFIG_SMP
+
+/*
+ * SMP slave cpus entry point.	Board specific code for bootstrap calls this
+ * function after setting up the stack and tp registers.
+ */
+SYM_CODE_START(smpboot_entry)
+	li.d		t0, CSR_DMW0_INIT	# UC, PLV0
+	csrwr		t0, LOONGARCH_CSR_DMWIN0
+	li.d		t0, CSR_DMW1_INIT	# CA, PLV0
+	csrwr		t0, LOONGARCH_CSR_DMWIN1
+	li.w		t0, 0xb0		# PLV=0, IE=0, PG=1
+	csrwr		t0, LOONGARCH_CSR_CRMD
+	li.w		t0, 0x04		# PLV=0, PIE=1, PWE=0
+	csrwr		t0, LOONGARCH_CSR_PRMD
+	li.w		t0, 0x00		# FPE=0, SXE=0, ASXE=0, BTE=0
+	csrwr		t0, LOONGARCH_CSR_EUEN
+
+	la.abs		t0, cpuboot_data
+	ld.d		sp, t0, CPU_BOOT_STACK
+	ld.d		tp, t0, CPU_BOOT_TINFO
+
+	la.abs	t0, 0f
+	jirl	zero, t0, 0
+0:
+	bl		start_secondary
+SYM_CODE_END(smpboot_entry)
+
+#endif /* CONFIG_SMP */
+
 SYM_ENTRY(kernel_entry_end, SYM_L_GLOBAL, SYM_A_NONE)
diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c
index 9bd07edf0bce..4b671d305ede 100644
--- a/arch/loongarch/kernel/irq.c
+++ b/arch/loongarch/kernel/irq.c
@@ -47,13 +47,17 @@ asmlinkage void spurious_interrupt(void)
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
+#ifdef CONFIG_SMP
+	show_ipi_list(p, prec);
+#endif
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
 	return 0;
 }
 
 void __init init_IRQ(void)
 {
-	int i;
+	int i, r, ipi_irq;
+	static int ipi_dummy_dev;
 	unsigned int order = get_order(IRQ_STACK_SIZE);
 	struct page *page;
 
@@ -61,6 +65,13 @@ void __init init_IRQ(void)
 	clear_csr_estat(ESTATF_IP);
 
 	irqchip_init();
+#ifdef CONFIG_SMP
+	ipi_irq = EXCCODE_IPI - EXCCODE_INT_START;
+	irq_set_percpu_devid(ipi_irq);
+	r = request_percpu_irq(ipi_irq, loongson3_ipi_interrupt, "IPI", &ipi_dummy_dev);
+	if (r < 0)
+		panic("IPI IRQ request failed\n");
+#endif
 
 	for (i = 0; i < NR_IRQS; i++)
 		irq_set_noprobe(i);
diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c
index d25592a29196..1effc73850fe 100644
--- a/arch/loongarch/kernel/proc.c
+++ b/arch/loongarch/kernel/proc.c
@@ -35,6 +35,11 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	unsigned int fp_version = cpu_data[n].fpu_vers;
 	struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args;
 
+#ifdef CONFIG_SMP
+	if (!cpu_online(n))
+		return 0;
+#endif
+
 	/*
 	 * For the first processor also print the system type
 	 */
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 54020223068f..6d944d65f600 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -53,6 +53,13 @@
 unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
 EXPORT_SYMBOL(boot_option_idle_override);
 
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
+{
+	play_dead();
+}
+#endif
+
 asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c
index ef484ce43c5c..2b86469e4718 100644
--- a/arch/loongarch/kernel/reset.c
+++ b/arch/loongarch/kernel/reset.c
@@ -65,16 +65,28 @@ EXPORT_SYMBOL(pm_power_off);
 
 void machine_halt(void)
 {
+#ifdef CONFIG_SMP
+	preempt_disable();
+	smp_send_stop();
+#endif
 	default_halt();
 }
 
 void machine_power_off(void)
 {
+#ifdef CONFIG_SMP
+	preempt_disable();
+	smp_send_stop();
+#endif
 	pm_power_off();
 }
 
 void machine_restart(char *command)
 {
+#ifdef CONFIG_SMP
+	preempt_disable();
+	smp_send_stop();
+#endif
 	do_kernel_restart(command);
 	pm_restart();
 }
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 29f3b82cd0a5..34a3011f679e 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -38,6 +38,7 @@
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/smp.h>
 #include <asm/time.h>
 
 #define SMBIOS_BIOSSIZE_OFFSET		0x09
@@ -322,6 +323,29 @@ static int __init reserve_memblock_reserved_regions(void)
 }
 arch_initcall(reserve_memblock_reserved_regions);
 
+#ifdef CONFIG_SMP
+static void __init prefill_possible_map(void)
+{
+	int i, possible;
+
+	possible = num_processors + disabled_cpus;
+	if (possible > nr_cpu_ids)
+		possible = nr_cpu_ids;
+
+	pr_info("SMP: Allowing %d CPUs, %d hotplug CPUs\n",
+			possible, max((possible - num_processors), 0));
+
+	for (i = 0; i < possible; i++)
+		set_cpu_possible(i, true);
+	for (; i < NR_CPUS; i++)
+		set_cpu_possible(i, false);
+
+	nr_cpu_ids = possible;
+}
+#else
+static inline void prefill_possible_map(void) {}
+#endif
+
 void __init setup_arch(char **cmdline_p)
 {
 	cpu_probe();
@@ -336,6 +360,8 @@ void __init setup_arch(char **cmdline_p)
 	arch_mem_init(cmdline_p);
 
 	resource_init();
+	plat_smp_setup();
+	prefill_possible_map();
 
 	paging_init();
 }
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
new file mode 100644
index 000000000000..99ba7a56edf9
--- /dev/null
+++ b/arch/loongarch/kernel/smp.c
@@ -0,0 +1,735 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ *
+ * Derived from MIPS:
+ * Copyright (C) 2000, 2001 Kanoj Sarcar
+ * Copyright (C) 2000, 2001 Ralf Baechle
+ * Copyright (C) 2000, 2001 Silicon Graphics, Inc.
+ * Copyright (C) 2000, 2001, 2003 Broadcom Corporation
+ */
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+#include <linux/export.h>
+#include <linux/time.h>
+#include <linux/tracepoint.h>
+#include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/cpu.h>
+#include <asm/idle.h>
+#include <asm/loongson.h>
+#include <asm/mmu_context.h>
+#include <asm/processor.h>
+#include <asm/setup.h>
+#include <asm/time.h>
+
+int __cpu_number_map[NR_CPUS];   /* Map physical to logical */
+EXPORT_SYMBOL(__cpu_number_map);
+
+int __cpu_logical_map[NR_CPUS];		/* Map logical to physical */
+EXPORT_SYMBOL(__cpu_logical_map);
+
+/* Number of threads (siblings) per CPU core */
+int smp_num_siblings = 1;
+EXPORT_SYMBOL(smp_num_siblings);
+
+/* Representing the threads (siblings) of each logical CPU */
+cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(cpu_sibling_map);
+
+/* Representing the core map of multi-core chips of each logical CPU */
+cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(cpu_core_map);
+
+static DECLARE_COMPLETION(cpu_starting);
+static DECLARE_COMPLETION(cpu_running);
+
+/*
+ * A logcal cpu mask containing only one VPE per core to
+ * reduce the number of IPIs on large MT systems.
+ */
+cpumask_t cpu_foreign_map[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(cpu_foreign_map);
+
+/* representing cpus for which sibling maps can be computed */
+static cpumask_t cpu_sibling_setup_map;
+
+/* representing cpus for which core maps can be computed */
+static cpumask_t cpu_core_setup_map;
+
+struct secondary_data cpuboot_data;
+static DEFINE_PER_CPU(int, cpu_state);
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+enum ipi_msg_type {
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNCTION,
+};
+
+static const char *ipi_types[NR_IPI] __tracepoint_string = {
+	[IPI_RESCHEDULE] = "Rescheduling interrupts",
+	[IPI_CALL_FUNCTION] = "Function call interrupts",
+};
+
+void show_ipi_list(struct seq_file *p, int prec)
+{
+	unsigned int cpu, i;
+
+	for (i = 0; i < NR_IPI; i++) {
+		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : "");
+		for_each_online_cpu(cpu)
+			seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).ipi_irqs[i]);
+		seq_printf(p, " LoongArch  %d  %s\n", i + 1, ipi_types[i]);
+	}
+}
+
+/* Send mailbox buffer via Mail_Send */
+static void csr_mail_send(uint64_t data, int cpu, int mailbox)
+{
+	uint64_t val;
+
+	/* Send high 32 bits */
+	val = IOCSR_MBUF_SEND_BLOCKING;
+	val |= (IOCSR_MBUF_SEND_BOX_HI(mailbox) << IOCSR_MBUF_SEND_BOX_SHIFT);
+	val |= (cpu << IOCSR_MBUF_SEND_CPU_SHIFT);
+	val |= (data & IOCSR_MBUF_SEND_H32_MASK);
+	iocsr_write64(val, LOONGARCH_IOCSR_MBUF_SEND);
+
+	/* Send low 32 bits */
+	val = IOCSR_MBUF_SEND_BLOCKING;
+	val |= (IOCSR_MBUF_SEND_BOX_LO(mailbox) << IOCSR_MBUF_SEND_BOX_SHIFT);
+	val |= (cpu << IOCSR_MBUF_SEND_CPU_SHIFT);
+	val |= (data << IOCSR_MBUF_SEND_BUF_SHIFT);
+	iocsr_write64(val, LOONGARCH_IOCSR_MBUF_SEND);
+};
+
+static u32 ipi_read_clear(int cpu)
+{
+	u32 action;
+
+	/* Load the ipi register to figure out what we're supposed to do */
+	action = iocsr_read32(LOONGARCH_IOCSR_IPI_STATUS);
+	/* Clear the ipi register to clear the interrupt */
+	iocsr_write32(action, LOONGARCH_IOCSR_IPI_CLEAR);
+	smp_mb();
+
+	return action;
+}
+
+static void ipi_write_action(int cpu, u32 action)
+{
+	unsigned int irq = 0;
+
+	while ((irq = ffs(action))) {
+		uint32_t val = IOCSR_IPI_SEND_BLOCKING;
+
+		val |= (irq - 1);
+		val |= (cpu << IOCSR_IPI_SEND_CPU_SHIFT);
+		iocsr_write32(val, LOONGARCH_IOCSR_IPI_SEND);
+		action &= ~BIT(irq - 1);
+	}
+}
+
+void loongson3_send_ipi_single(int cpu, unsigned int action)
+{
+	ipi_write_action(cpu_logical_map(cpu), (u32)action);
+}
+
+void loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+{
+	unsigned int i;
+
+	for_each_cpu(i, mask)
+		ipi_write_action(cpu_logical_map(i), (u32)action);
+}
+
+irqreturn_t loongson3_ipi_interrupt(int irq, void *dev)
+{
+	unsigned int action;
+	unsigned int cpu = smp_processor_id();
+
+	action = ipi_read_clear(cpu_logical_map(cpu));
+
+	if (action & SMP_RESCHEDULE) {
+		scheduler_ipi();
+		per_cpu(irq_stat, cpu).ipi_irqs[IPI_RESCHEDULE]++;
+	}
+
+	if (action & SMP_CALL_FUNCTION) {
+		generic_smp_call_function_interrupt();
+		per_cpu(irq_stat, cpu).ipi_irqs[IPI_CALL_FUNCTION]++;
+	}
+
+	return IRQ_HANDLED;
+}
+
+void __init loongson3_smp_setup(void)
+{
+	cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package;
+	cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package;
+
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN);
+	pr_info("Detected %i available CPU(s)\n", loongson_sysconf.nr_cpus);
+}
+
+void __init loongson3_prepare_cpus(unsigned int max_cpus)
+{
+	int i = 0;
+
+	for (i = 0; i < loongson_sysconf.nr_cpus; i++) {
+		set_cpu_present(i, true);
+		csr_mail_send(0, __cpu_logical_map[i], 0);
+	}
+
+	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
+}
+
+/*
+ * Setup the PC, SP, and TP of a secondary processor and start it running!
+ */
+void loongson3_boot_secondary(int cpu, struct task_struct *idle)
+{
+	unsigned long entry;
+
+	pr_info("Booting CPU#%d...\n", cpu);
+
+	entry = __pa_symbol((unsigned long)&smpboot_entry);
+	cpuboot_data.stack = (unsigned long)__KSTK_TOS(idle);
+	cpuboot_data.thread_info = (unsigned long)task_thread_info(idle);
+
+	csr_mail_send(entry, cpu_logical_map(cpu), 0);
+
+	loongson3_send_ipi_single(cpu, SMP_BOOT_CPU);
+}
+
+/*
+ * SMP init and finish on secondary CPUs
+ */
+void loongson3_init_secondary(void)
+{
+	unsigned int cpu = smp_processor_id();
+	unsigned int imask = ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 |
+			     ECFGF_IPI | ECFGF_PMC | ECFGF_TIMER;
+
+	change_csr_ecfg(ECFG0_IM, imask);
+
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN);
+
+	per_cpu(cpu_state, cpu) = CPU_ONLINE;
+	cpu_data[cpu].core =
+		     cpu_logical_map(cpu) % loongson_sysconf.cores_per_package;
+	cpu_data[cpu].package =
+		     cpu_logical_map(cpu) / loongson_sysconf.cores_per_package;
+}
+
+void loongson3_smp_finish(void)
+{
+	local_irq_enable();
+	iocsr_write64(0, LOONGARCH_IOCSR_MBUF0);
+	pr_info("CPU#%d finished\n", smp_processor_id());
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static bool io_master(int cpu)
+{
+	if (cpu == 0)
+		return true;
+
+	return false;
+}
+
+int loongson3_cpu_disable(void)
+{
+	unsigned long flags;
+	unsigned int cpu = smp_processor_id();
+
+	if (io_master(cpu))
+		return -EBUSY;
+
+	set_cpu_online(cpu, false);
+	calculate_cpu_foreign_map();
+	local_irq_save(flags);
+	irq_migrate_all_off_this_cpu();
+	clear_csr_ecfg(ECFG0_IM);
+	local_irq_restore(flags);
+	local_flush_tlb_all();
+
+	return 0;
+}
+
+void loongson3_cpu_die(unsigned int cpu)
+{
+	while (per_cpu(cpu_state, cpu) != CPU_DEAD)
+		cpu_relax();
+
+	mb();
+}
+
+/*
+ * The target CPU should go to XKPRANGE (uncached area) and flush
+ * ICache/DCache/VCache before the control CPU can safely disable its clock.
+ */
+static void loongson3_play_dead(int *state_addr)
+{
+	register int val;
+	register void *addr;
+	register void (*init_fn)(void);
+
+	__asm__ __volatile__(
+		"   li.d %[addr], 0x8000000000000000\n"
+		"1: cacop 0x8, %[addr], 0           \n" /* flush ICache */
+		"   cacop 0x8, %[addr], 1           \n"
+		"   cacop 0x8, %[addr], 2           \n"
+		"   cacop 0x8, %[addr], 3           \n"
+		"   cacop 0x9, %[addr], 0           \n" /* flush DCache */
+		"   cacop 0x9, %[addr], 1           \n"
+		"   cacop 0x9, %[addr], 2           \n"
+		"   cacop 0x9, %[addr], 3           \n"
+		"   addi.w %[sets], %[sets], -1     \n"
+		"   addi.d %[addr], %[addr], 0x40   \n"
+		"   bnez %[sets], 1b                \n"
+		"   li.d %[addr], 0x8000000000000000\n"
+		"2: cacop 0xa, %[addr], 0           \n" /* flush VCache */
+		"   cacop 0xa, %[addr], 1           \n"
+		"   cacop 0xa, %[addr], 2           \n"
+		"   cacop 0xa, %[addr], 3           \n"
+		"   cacop 0xa, %[addr], 4           \n"
+		"   cacop 0xa, %[addr], 5           \n"
+		"   cacop 0xa, %[addr], 6           \n"
+		"   cacop 0xa, %[addr], 7           \n"
+		"   cacop 0xa, %[addr], 8           \n"
+		"   cacop 0xa, %[addr], 9           \n"
+		"   cacop 0xa, %[addr], 10          \n"
+		"   cacop 0xa, %[addr], 11          \n"
+		"   cacop 0xa, %[addr], 12          \n"
+		"   cacop 0xa, %[addr], 13          \n"
+		"   cacop 0xa, %[addr], 14          \n"
+		"   cacop 0xa, %[addr], 15          \n"
+		"   addi.w %[vsets], %[vsets], -1   \n"
+		"   addi.d %[addr], %[addr], 0x40   \n"
+		"   bnez   %[vsets], 2b             \n"
+		"   li.w   %[val], 0x7              \n" /* *state_addr = CPU_DEAD; */
+		"   st.w   %[val], %[state_addr], 0 \n"
+		"   dbar 0                          \n"
+		"   cacop 0x11, %[state_addr], 0    \n" /* flush entry of *state_addr */
+		: [addr] "=&r" (addr), [val] "=&r" (val)
+		: [state_addr] "r" (state_addr),
+		  [sets] "r" (cpu_data[smp_processor_id()].dcache.sets),
+		  [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets));
+
+	local_irq_enable();
+	change_csr_ecfg(ECFG0_IM, ECFGF_IPI);
+
+	__asm__ __volatile__(
+		"   idle      0			    \n"
+		"   li.w      $t0, 0x1020	    \n"
+		"   iocsrrd.d %[init_fn], $t0	    \n" /* Get init PC */
+		: [init_fn] "=&r" (addr)
+		: /* No Input */
+		: "a0");
+	init_fn = __va(addr);
+
+	init_fn();
+	unreachable();
+}
+
+void play_dead(void)
+{
+	int *state_addr;
+	unsigned int cpu = smp_processor_id();
+	void (*play_dead_uncached)(int *s);
+
+	idle_task_exit();
+	play_dead_uncached = (void *)TO_UNCACHE(__pa((unsigned long)loongson3_play_dead));
+	state_addr = &per_cpu(cpu_state, cpu);
+	mb();
+	play_dead_uncached(state_addr);
+}
+
+static int loongson3_enable_clock(unsigned int cpu)
+{
+	uint64_t core_id = cpu_data[cpu].core;
+	uint64_t package_id = cpu_data[cpu].package;
+
+	LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3);
+
+	return 0;
+}
+
+static int loongson3_disable_clock(unsigned int cpu)
+{
+	uint64_t core_id = cpu_data[cpu].core;
+	uint64_t package_id = cpu_data[cpu].package;
+
+	LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3));
+
+	return 0;
+}
+
+static int register_loongson3_notifier(void)
+{
+	return cpuhp_setup_state_nocalls(CPUHP_LOONGARCH_SOC_PREPARE,
+					 "loongarch/loongson:prepare",
+					 loongson3_enable_clock,
+					 loongson3_disable_clock);
+}
+early_initcall(register_loongson3_notifier);
+
+#endif
+
+/*
+ * Power management
+ */
+#ifdef CONFIG_PM
+
+static int loongson3_ipi_suspend(void)
+{
+	return 0;
+}
+
+static void loongson3_ipi_resume(void)
+{
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN);
+}
+
+static struct syscore_ops loongson3_ipi_syscore_ops = {
+	.resume         = loongson3_ipi_resume,
+	.suspend        = loongson3_ipi_suspend,
+};
+
+/*
+ * Enable boot cpu ipi before enabling nonboot cpus
+ * during syscore_resume.
+ */
+static int __init ipi_pm_init(void)
+{
+	register_syscore_ops(&loongson3_ipi_syscore_ops);
+	return 0;
+}
+
+core_initcall(ipi_pm_init);
+#endif
+
+static inline void set_cpu_sibling_map(int cpu)
+{
+	int i;
+
+	cpumask_set_cpu(cpu, &cpu_sibling_setup_map);
+
+	if (smp_num_siblings <= 1)
+		cpumask_set_cpu(cpu, &cpu_sibling_map[cpu]);
+	else {
+		for_each_cpu(i, &cpu_sibling_setup_map) {
+			if (cpus_are_siblings(cpu, i)) {
+				cpumask_set_cpu(i, &cpu_sibling_map[cpu]);
+				cpumask_set_cpu(cpu, &cpu_sibling_map[i]);
+			}
+		}
+	}
+}
+
+static inline void set_cpu_core_map(int cpu)
+{
+	int i;
+
+	cpumask_set_cpu(cpu, &cpu_core_setup_map);
+
+	for_each_cpu(i, &cpu_core_setup_map) {
+		if (cpu_data[cpu].package == cpu_data[i].package) {
+			cpumask_set_cpu(i, &cpu_core_map[cpu]);
+			cpumask_set_cpu(cpu, &cpu_core_map[i]);
+		}
+	}
+}
+
+/*
+ * Calculate a new cpu_foreign_map mask whenever a
+ * new cpu appears or disappears.
+ */
+void calculate_cpu_foreign_map(void)
+{
+	int i, k, core_present;
+	cpumask_t temp_foreign_map;
+
+	/* Re-calculate the mask */
+	cpumask_clear(&temp_foreign_map);
+	for_each_online_cpu(i) {
+		core_present = 0;
+		for_each_cpu(k, &temp_foreign_map)
+			if (cpus_are_siblings(i, k))
+				core_present = 1;
+		if (!core_present)
+			cpumask_set_cpu(i, &temp_foreign_map);
+	}
+
+	for_each_online_cpu(i)
+		cpumask_andnot(&cpu_foreign_map[i],
+			       &temp_foreign_map, &cpu_sibling_map[i]);
+}
+
+/* Preload SMP state for boot cpu */
+void smp_prepare_boot_cpu(void)
+{
+	unsigned int cpu;
+
+	set_cpu_possible(0, true);
+	set_cpu_online(0, true);
+	set_my_cpu_offset(per_cpu_offset(0));
+
+	for_each_possible_cpu(cpu)
+		set_cpu_numa_node(cpu, 0);
+}
+
+/* called from main before smp_init() */
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	init_new_context(current, &init_mm);
+	current_thread_info()->cpu = 0;
+	loongson3_prepare_cpus(max_cpus);
+	set_cpu_sibling_map(0);
+	set_cpu_core_map(0);
+	calculate_cpu_foreign_map();
+#ifndef CONFIG_HOTPLUG_CPU
+	init_cpu_present(cpu_possible_mask);
+#endif
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+	loongson3_boot_secondary(cpu, tidle);
+
+	/* Wait for CPU to start and be ready to sync counters */
+	if (!wait_for_completion_timeout(&cpu_starting,
+					 msecs_to_jiffies(5000))) {
+		pr_crit("CPU%u: failed to start\n", cpu);
+		return -EIO;
+	}
+
+	/* Wait for CPU to finish startup & mark itself online before return */
+	wait_for_completion(&cpu_running);
+
+	return 0;
+}
+
+/*
+ * First C code run on the secondary CPUs after being started up by
+ * the master.
+ */
+asmlinkage void start_secondary(void)
+{
+	unsigned int cpu;
+
+	sync_counter();
+	cpu = smp_processor_id();
+	set_my_cpu_offset(per_cpu_offset(cpu));
+
+	cpu_probe();
+	constant_clockevent_init();
+	loongson3_init_secondary();
+
+	set_cpu_sibling_map(cpu);
+	set_cpu_core_map(cpu);
+
+	notify_cpu_starting(cpu);
+
+	/* Notify boot CPU that we're starting */
+	complete(&cpu_starting);
+
+	/* The CPU is running, now mark it online */
+	set_cpu_online(cpu, true);
+
+	calculate_cpu_foreign_map();
+
+	/*
+	 * Notify boot CPU that we're up & online and it can safely return
+	 * from __cpu_up()
+	 */
+	complete(&cpu_running);
+
+	/*
+	 * irq will be enabled in loongson3_smp_finish(), enabling it too
+	 * early is dangerous.
+	 */
+	WARN_ON_ONCE(!irqs_disabled());
+	loongson3_smp_finish();
+
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+static void stop_this_cpu(void *dummy)
+{
+	set_cpu_online(smp_processor_id(), false);
+	calculate_cpu_foreign_map();
+	local_irq_disable();
+	while (true);
+}
+
+void smp_send_stop(void)
+{
+	smp_call_function(stop_this_cpu, NULL, 0);
+}
+
+int setup_profiling_timer(unsigned int multiplier)
+{
+	return 0;
+}
+
+static void flush_tlb_all_ipi(void *info)
+{
+	local_flush_tlb_all();
+}
+
+void flush_tlb_all(void)
+{
+	on_each_cpu(flush_tlb_all_ipi, NULL, 1);
+}
+
+static void flush_tlb_mm_ipi(void *mm)
+{
+	local_flush_tlb_mm((struct mm_struct *)mm);
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	if (atomic_read(&mm->mm_users) == 0)
+		return;		/* happens as a result of exit_mmap() */
+
+	preempt_disable();
+
+	if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) {
+		on_each_cpu_mask(mm_cpumask(mm), flush_tlb_mm_ipi, mm, 1);
+	} else {
+		unsigned int cpu;
+
+		for_each_online_cpu(cpu) {
+			if (cpu != smp_processor_id() && cpu_context(cpu, mm))
+				cpu_context(cpu, mm) = 0;
+		}
+		local_flush_tlb_mm(mm);
+	}
+
+	preempt_enable();
+}
+
+struct flush_tlb_data {
+	struct vm_area_struct *vma;
+	unsigned long addr1;
+	unsigned long addr2;
+};
+
+static void flush_tlb_range_ipi(void *info)
+{
+	struct flush_tlb_data *fd = info;
+
+	local_flush_tlb_range(fd->vma, fd->addr1, fd->addr2);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	preempt_disable();
+	if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) {
+		struct flush_tlb_data fd = {
+			.vma = vma,
+			.addr1 = start,
+			.addr2 = end,
+		};
+
+		on_each_cpu_mask(mm_cpumask(mm), flush_tlb_range_ipi, &fd, 1);
+	} else {
+		unsigned int cpu;
+		int exec = vma->vm_flags & VM_EXEC;
+
+		for_each_online_cpu(cpu) {
+			/*
+			 * flush_cache_range() will only fully flush icache if
+			 * the VMA is executable, otherwise we must invalidate
+			 * ASID without it appearing to has_valid_asid() as if
+			 * mm has been completely unused by that CPU.
+			 */
+			if (cpu != smp_processor_id() && cpu_context(cpu, mm))
+				cpu_context(cpu, mm) = !exec;
+		}
+		local_flush_tlb_range(vma, start, end);
+	}
+	preempt_enable();
+}
+
+static void flush_tlb_kernel_range_ipi(void *info)
+{
+	struct flush_tlb_data *fd = info;
+
+	local_flush_tlb_kernel_range(fd->addr1, fd->addr2);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	struct flush_tlb_data fd = {
+		.addr1 = start,
+		.addr2 = end,
+	};
+
+	on_each_cpu(flush_tlb_kernel_range_ipi, &fd, 1);
+}
+
+static void flush_tlb_page_ipi(void *info)
+{
+	struct flush_tlb_data *fd = info;
+
+	local_flush_tlb_page(fd->vma, fd->addr1);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
+{
+	preempt_disable();
+	if ((atomic_read(&vma->vm_mm->mm_users) != 1) || (current->mm != vma->vm_mm)) {
+		struct flush_tlb_data fd = {
+			.vma = vma,
+			.addr1 = page,
+		};
+
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), flush_tlb_page_ipi, &fd, 1);
+	} else {
+		unsigned int cpu;
+
+		for_each_online_cpu(cpu) {
+			/*
+			 * flush_cache_page() only does partial flushes, so
+			 * invalidate ASID without it appearing to
+			 * has_valid_asid() as if mm has been completely unused
+			 * by that CPU.
+			 */
+			if (cpu != smp_processor_id() && cpu_context(cpu, vma->vm_mm))
+				cpu_context(cpu, vma->vm_mm) = 1;
+		}
+		local_flush_tlb_page(vma, page);
+	}
+	preempt_enable();
+}
+EXPORT_SYMBOL(flush_tlb_page);
+
+static void flush_tlb_one_ipi(void *info)
+{
+	unsigned long vaddr = (unsigned long) info;
+
+	local_flush_tlb_one(vaddr);
+}
+
+void flush_tlb_one(unsigned long vaddr)
+{
+	on_each_cpu(flush_tlb_one_ipi, (void *)vaddr, 1);
+}
+EXPORT_SYMBOL(flush_tlb_one);
diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c
index 3b2cbb95875b..ab1a75c0b5a6 100644
--- a/arch/loongarch/kernel/topology.c
+++ b/arch/loongarch/kernel/topology.c
@@ -1,13 +1,52 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/cpu.h>
+#include <linux/cpumask.h>
 #include <linux/init.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
 #include <linux/percpu.h>
 
-static struct cpu cpu_device;
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+#ifdef CONFIG_HOTPLUG_CPU
+int arch_register_cpu(int cpu)
+{
+	int ret;
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+	c->hotpluggable = 1;
+	ret = register_cpu(c, cpu);
+	if (ret < 0)
+		pr_warn("register_cpu %d failed (%d)\n", cpu, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL(arch_register_cpu);
+
+void arch_unregister_cpu(int cpu)
+{
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+	c->hotpluggable = 0;
+	unregister_cpu(c);
+}
+EXPORT_SYMBOL(arch_unregister_cpu);
+#endif
 
 static int __init topology_init(void)
 {
-	return register_cpu(&cpu_device, 0);
+	int i, ret;
+
+	for_each_present_cpu(i) {
+		struct cpu *c = &per_cpu(cpu_devices, i);
+
+		c->hotpluggable = !!i;
+		ret = register_cpu(c, i);
+		if (ret < 0)
+			pr_warn("topology_init: register_cpu %d failed (%d)\n", i, ret);
+	}
+
+	return 0;
 }
 
 subsys_initcall(topology_init);
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index f6ce24f403c2..9d508158fe1a 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -72,6 +72,10 @@ SECTIONS
 		EXIT_DATA
 	}
 
+#ifdef CONFIG_SMP
+	PERCPU_SECTION(1 << CONFIG_L1_CACHE_SHIFT)
+#endif
+
 	.init.bss : {
 		*(.init.bss)
 	}
diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S
index bef740710a3b..7eee40271577 100644
--- a/arch/loongarch/mm/tlbex.S
+++ b/arch/loongarch/mm/tlbex.S
@@ -88,7 +88,14 @@ vmalloc_done_load:
 	slli.d	t0, t0, _PTE_T_LOG2
 	add.d	t1, ra, t0
 
+#ifdef CONFIG_SMP
+smp_pgtable_change_load:
+#endif
+#ifdef CONFIG_SMP
+	ll.d	t0, t1, 0
+#else
 	ld.d	t0, t1, 0
+#endif
 	tlbsrch
 
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
@@ -96,7 +103,12 @@ vmalloc_done_load:
 	beq	ra, $r0, nopage_tlb_load
 
 	ori	t0, t0, _PAGE_VALID
+#ifdef CONFIG_SMP
+	sc.d	t0, t1, 0
+	beq	t0, $r0, smp_pgtable_change_load
+#else
 	st.d	t0, t1, 0
+#endif
 	ori	t1, t1, 8
 	xori	t1, t1, 8
 	ld.d	t0, t1, 0
@@ -120,14 +132,24 @@ vmalloc_load:
 	 * spots a huge page.
 	 */
 tlb_huge_update_load:
+#ifdef CONFIG_SMP
+	ll.d	t0, t1, 0
+#else
 	ld.d	t0, t1, 0
+#endif
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, 1
 	beq	ra, $r0, nopage_tlb_load
 	tlbsrch
 
 	ori	t0, t0, _PAGE_VALID
+#ifdef CONFIG_SMP
+	sc.d	t0, t1, 0
+	beq	t0, $r0, tlb_huge_update_load
+	ld.d	t0, t1, 0
+#else
 	st.d	t0, t1, 0
+#endif
 	addu16i.d	t1, $r0, -(CSR_TLBIDX_EHINV >> 16)
 	addi.d	ra, t1, 0
 	csrxchg	ra, t1, LOONGARCH_CSR_TLBIDX
@@ -173,6 +195,7 @@ tlb_huge_update_load:
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
 nopage_tlb_load:
+	dbar	0
 	csrrd	ra, EXCEPTION_KS2
 	la.abs	t0, tlb_do_page_fault_0
 	jirl	$r0, t0, 0
@@ -229,7 +252,14 @@ vmalloc_done_store:
 	slli.d	t0, t0, _PTE_T_LOG2
 	add.d	t1, ra, t0
 
+#ifdef CONFIG_SMP
+smp_pgtable_change_store:
+#endif
+#ifdef CONFIG_SMP
+	ll.d	t0, t1, 0
+#else
 	ld.d	t0, t1, 0
+#endif
 	tlbsrch
 
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
@@ -238,7 +268,12 @@ vmalloc_done_store:
 	bne	ra, $r0, nopage_tlb_store
 
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+#ifdef CONFIG_SMP
+	sc.d	t0, t1, 0
+	beq	t0, $r0, smp_pgtable_change_store
+#else
 	st.d	t0, t1, 0
+#endif
 
 	ori	t1, t1, 8
 	xori	t1, t1, 8
@@ -263,7 +298,11 @@ vmalloc_store:
 	 * spots a huge page.
 	 */
 tlb_huge_update_store:
+#ifdef CONFIG_SMP
+	ll.d	t0, t1, 0
+#else
 	ld.d	t0, t1, 0
+#endif
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
 	xori	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
@@ -272,7 +311,13 @@ tlb_huge_update_store:
 	tlbsrch
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 
+#ifdef CONFIG_SMP
+	sc.d	t0, t1, 0
+	beq	t0, $r0, tlb_huge_update_store
+	ld.d	t0, t1, 0
+#else
 	st.d	t0, t1, 0
+#endif
 	addu16i.d	t1, $r0, -(CSR_TLBIDX_EHINV >> 16)
 	addi.d	ra, t1, 0
 	csrxchg	ra, t1, LOONGARCH_CSR_TLBIDX
@@ -318,6 +363,7 @@ tlb_huge_update_store:
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
 nopage_tlb_store:
+	dbar	0
 	csrrd	ra, EXCEPTION_KS2
 	la.abs	t0, tlb_do_page_fault_1
 	jirl	$r0, t0, 0
@@ -373,7 +419,14 @@ vmalloc_done_modify:
 	slli.d	t0, t0, _PTE_T_LOG2
 	add.d	t1, ra, t0
 
+#ifdef CONFIG_SMP
+smp_pgtable_change_modify:
+#endif
+#ifdef CONFIG_SMP
+	ll.d	t0, t1, 0
+#else
 	ld.d	t0, t1, 0
+#endif
 	tlbsrch
 
 	srli.d	ra, t0, _PAGE_WRITE_SHIFT
@@ -381,7 +434,12 @@ vmalloc_done_modify:
 	beq	ra, $r0, nopage_tlb_modify
 
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
+#ifdef CONFIG_SMP
+	sc.d	t0, t1, 0
+	beq	t0, $r0, smp_pgtable_change_modify
+#else
 	st.d	t0, t1, 0
+#endif
 	ori	t1, t1, 8
 	xori	t1, t1, 8
 	ld.d	t0, t1, 0
@@ -405,7 +463,11 @@ vmalloc_modify:
 	 * build_tlbchange_handler_head spots a huge page.
 	 */
 tlb_huge_update_modify:
+#ifdef CONFIG_SMP
+	ll.d	t0, t1, 0
+#else
 	ld.d	t0, t1, 0
+#endif
 
 	srli.d	ra, t0, _PAGE_WRITE_SHIFT
 	andi	ra, ra, 1
@@ -414,7 +476,13 @@ tlb_huge_update_modify:
 	tlbsrch
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 
+#ifdef CONFIG_SMP
+	sc.d	t0, t1, 0
+	beq	t0, $r0, tlb_huge_update_modify
+	ld.d	t0, t1, 0
+#else
 	st.d	t0, t1, 0
+#endif
 	/*
 	 * A huge PTE describes an area the size of the
 	 * configured huge page size. This is twice the
@@ -454,6 +522,7 @@ tlb_huge_update_modify:
 	csrxchg	t1, t0, LOONGARCH_CSR_TLBIDX
 
 nopage_tlb_modify:
+	dbar	0
 	csrrd	ra, EXCEPTION_KS2
 	la.abs	t0, tlb_do_page_fault_1
 	jirl	$r0, t0, 0
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index b66c5f389159..19f0dbfdd7fe 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -130,6 +130,7 @@ enum cpuhp_state {
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
+	CPUHP_LOONGARCH_SOC_PREPARE,
 	CPUHP_BP_PREPARE_DYN,
 	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,
 	CPUHP_BRINGUP_CPU,
-- 
cgit v1.2.3


From 6d7131bd52b3e0dd068a0067e5584b3f36cf17eb Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 11 Apr 2022 17:05:55 +0200
Subject: include/linux/find: Fix documentation

The order of the arguments in function documentation doesn't fit the
implementation. Change the documentation so that it corresponds to the
code. This prevent people to get confused when reading the documentation.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/find.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/find.h b/include/linux/find.h
index 5bb6db213bcb..424ef67d4a42 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -21,8 +21,8 @@ extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long siz
 /**
  * find_next_bit - find the next set bit in a memory region
  * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
  * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
  *
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
@@ -50,8 +50,8 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
  * find_next_and_bit - find the next set bit in both memory regions
  * @addr1: The first address to base the search on
  * @addr2: The second address to base the search on
- * @offset: The bitnumber to start searching at
  * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
  *
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
@@ -79,8 +79,8 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
 /**
  * find_next_zero_bit - find the next cleared bit in a memory region
  * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
  * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
  *
  * Returns the bit number of the next zero bit
  * If no bits are zero, returns @size.
-- 
cgit v1.2.3


From e041e0ac53dd52d2d201aa87edc3adaca1085299 Mon Sep 17 00:00:00 2001
From: Yury Norov <yury.norov@gmail.com>
Date: Thu, 28 Apr 2022 13:51:12 -0700
Subject: lib/bitmap: extend comment for bitmap_(from,to)_arr32()

On LE systems bitmaps are naturally ordered, therefore we can potentially
use bitmap_copy routines when converting from 32-bit arrays, even if host
system is 64-bit. But it may lead to out-of-bond access due to unsafe
typecast, and the bitmap_(from,to)_arr32 comment doesn't explain that
clearly

CC: Alexander Gordeev <agordeev@linux.ibm.com>
CC: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
CC: Christian Borntraeger <borntraeger@linux.ibm.com>
CC: Claudio Imbrenda <imbrenda@linux.ibm.com>
CC: David Hildenbrand <david@redhat.com>
CC: Heiko Carstens <hca@linux.ibm.com>
CC: Janosch Frank <frankja@linux.ibm.com>
CC: Rasmus Villemoes <linux@rasmusvillemoes.dk>
CC: Sven Schnelle <svens@linux.ibm.com>
CC: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/bitmap.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 7dba0847510c..afcf7b8dddd1 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -264,8 +264,12 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst,
 }
 
 /*
- * On 32-bit systems bitmaps are represented as u32 arrays internally, and
- * therefore conversion is not needed when copying data from/to arrays of u32.
+ * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
+ * machines the order of hi and lo parts of numbers match the bitmap structure.
+ * In both cases conversion is not needed when copying data from/to arrays of
+ * u32. But in LE64 case, typecast in bitmap_copy_clear_tail() may lead
+ * to out-of-bound access. To avoid that, both LE and BE variants of 64-bit
+ * architectures are not using bitmap_copy_clear_tail().
  */
 #if BITS_PER_LONG == 64
 void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf,
-- 
cgit v1.2.3


From 0a97953fd2210d0ac8eb5c76f8bd08fb53b6d3d6 Mon Sep 17 00:00:00 2001
From: Yury Norov <yury.norov@gmail.com>
Date: Thu, 28 Apr 2022 13:51:13 -0700
Subject: lib: add bitmap_{from,to}_arr64

Manipulating 64-bit arrays with bitmap functions is potentially dangerous
because on 32-bit BE machines the order of halfwords doesn't match.
Another issue is that compiler may throw a warning about out-of-boundary
access.

This patch adds bitmap_{from,to}_arr64 functions in addition to existing
bitmap_{from,to}_arr32.

CC: Alexander Gordeev <agordeev@linux.ibm.com>
CC: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
CC: Christian Borntraeger <borntraeger@linux.ibm.com>
CC: Claudio Imbrenda <imbrenda@linux.ibm.com>
CC: David Hildenbrand <david@redhat.com>
CC: Heiko Carstens <hca@linux.ibm.com>
CC: Janosch Frank <frankja@linux.ibm.com>
CC: Rasmus Villemoes <linux@rasmusvillemoes.dk>
CC: Sven Schnelle <svens@linux.ibm.com>
CC: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/bitmap.h | 23 +++++++++++++++++----
 lib/bitmap.c           | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 73 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index afcf7b8dddd1..71147b7d721b 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -72,6 +72,8 @@ struct device;
  *  bitmap_allocate_region(bitmap, pos, order)  Allocate specified bit region
  *  bitmap_from_arr32(dst, buf, nbits)          Copy nbits from u32[] buf to dst
  *  bitmap_to_arr32(buf, src, nbits)            Copy nbits from buf to u32[] dst
+ *  bitmap_to_arr64(buf, src, nbits)            Copy nbits from buf to u64[] dst
+ *  bitmap_to_arr64(buf, src, nbits)            Copy nbits from buf to u64[] dst
  *  bitmap_get_value8(map, start)               Get 8bit value from map at start
  *  bitmap_set_value8(map, value, start)        Set 8bit value to map at start
  *
@@ -285,6 +287,22 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap,
 			(const unsigned long *) (bitmap), (nbits))
 #endif
 
+/*
+ * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32
+ * machines the order of hi and lo parts of numbers match the bitmap structure.
+ * In both cases conversion is not needed when copying data from/to arrays of
+ * u64.
+ */
+#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits);
+void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
+#else
+#define bitmap_from_arr64(bitmap, buf, nbits)			\
+	bitmap_copy_clear_tail((unsigned long *)(bitmap), (const unsigned long *)(buf), (nbits))
+#define bitmap_to_arr64(buf, bitmap, nbits)			\
+	bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits))
+#endif
+
 static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
 			const unsigned long *src2, unsigned int nbits)
 {
@@ -518,10 +536,7 @@ static inline void bitmap_next_set_region(unsigned long *bitmap,
  */
 static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
 {
-	dst[0] = mask & ULONG_MAX;
-
-	if (sizeof(mask) > sizeof(unsigned long))
-		dst[1] = mask >> 32;
+	bitmap_from_arr64(dst, &mask, 64);
 }
 
 /**
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 8ebe508580ea..4061a5dd2bc6 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -1512,5 +1512,59 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits)
 		buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31));
 }
 EXPORT_SYMBOL(bitmap_to_arr32);
+#endif
+
+#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+/**
+ * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap
+ *	@bitmap: array of unsigned longs, the destination bitmap
+ *	@buf: array of u64 (in host byte order), the source bitmap
+ *	@nbits: number of bits in @bitmap
+ */
+void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits)
+{
+	int n;
+
+	for (n = nbits; n > 0; n -= 64) {
+		u64 val = *buf++;
+
+		*bitmap++ = val;
+		if (n > 32)
+			*bitmap++ = val >> 32;
+	}
+
+	/*
+	 * Clear tail bits in the last word beyond nbits.
+	 *
+	 * Negative index is OK because here we point to the word next
+	 * to the last word of the bitmap, except for nbits == 0, which
+	 * is tested implicitly.
+	 */
+	if (nbits % BITS_PER_LONG)
+		bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits);
+}
+EXPORT_SYMBOL(bitmap_from_arr64);
+
+/**
+ * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits
+ *	@buf: array of u64 (in host byte order), the dest bitmap
+ *	@bitmap: array of unsigned longs, the source bitmap
+ *	@nbits: number of bits in @bitmap
+ */
+void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
+{
+	const unsigned long *end = bitmap + BITS_TO_LONGS(nbits);
 
+	while (bitmap < end) {
+		*buf = *bitmap++;
+		if (bitmap < end)
+			*buf |= (u64)(*bitmap++) << 32;
+		buf++;
+	}
+
+	/* Clear tail bits in the last element of array beyond nbits. */
+	if (nbits % 64)
+		buf[-1] &= GENMASK_ULL(nbits % 64, 0);
+}
+EXPORT_SYMBOL(bitmap_to_arr64);
 #endif
-- 
cgit v1.2.3


From 005f17007f47495dbbb659aa5db7e581065d16e7 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 18 May 2022 13:52:22 -0700
Subject: bitmap: Fix return values to be unsigned

Both nodemask and bitmap routines had mixed return values that provided
potentially signed return values that could never happen. This was
leading to the compiler getting confusing about the range of possible
return values (it was thinking things could be negative where they could
not be). In preparation for fixing nodemask, fix all the bitmap routines
that should be returning unsigned (or bool) values.

Cc: Yury Norov <yury.norov@gmail.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Christophe de Dinechin <dinechin@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/bitmap.h       | 25 +++++++++++++------------
 lib/bitmap.c                 | 30 +++++++++++++++---------------
 tools/include/linux/bitmap.h | 17 +++++++++--------
 tools/lib/bitmap.c           | 20 ++++++++++----------
 4 files changed, 47 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 71147b7d721b..2e6cd5681040 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -134,8 +134,8 @@ unsigned long *devm_bitmap_zalloc(struct device *dev,
  * lib/bitmap.c provides these functions:
  */
 
-int __bitmap_equal(const unsigned long *bitmap1,
-		   const unsigned long *bitmap2, unsigned int nbits);
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int nbits);
 bool __pure __bitmap_or_equal(const unsigned long *src1,
 			      const unsigned long *src2,
 			      const unsigned long *src3,
@@ -159,10 +159,10 @@ int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
 void __bitmap_replace(unsigned long *dst,
 		      const unsigned long *old, const unsigned long *new,
 		      const unsigned long *mask, unsigned int nbits);
-int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, unsigned int nbits);
-int __bitmap_subset(const unsigned long *bitmap1,
-		    const unsigned long *bitmap2, unsigned int nbits);
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int nbits);
+bool __bitmap_subset(const unsigned long *bitmap1,
+		     const unsigned long *bitmap2, unsigned int nbits);
 int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
 void __bitmap_set(unsigned long *map, unsigned int start, int len);
 void __bitmap_clear(unsigned long *map, unsigned int start, int len);
@@ -353,8 +353,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr
 #endif
 #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
 
-static inline int bitmap_equal(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_equal(const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
@@ -384,8 +384,9 @@ static inline bool bitmap_or_equal(const unsigned long *src1,
 	return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits));
 }
 
-static inline int bitmap_intersects(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_intersects(const unsigned long *src1,
+				     const unsigned long *src2,
+				     unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
@@ -393,8 +394,8 @@ static inline int bitmap_intersects(const unsigned long *src1,
 		return __bitmap_intersects(src1, src2, nbits);
 }
 
-static inline int bitmap_subset(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_subset(const unsigned long *src1,
+				 const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 4061a5dd2bc6..b18e31ea6e66 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -45,19 +45,19 @@
  * for the best explanations of this ordering.
  */
 
-int __bitmap_equal(const unsigned long *bitmap1,
-		const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] != bitmap2[k])
-			return 0;
+			return false;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 0;
+			return false;
 
-	return 1;
+	return true;
 }
 EXPORT_SYMBOL(__bitmap_equal);
 
@@ -303,33 +303,33 @@ void __bitmap_replace(unsigned long *dst,
 }
 EXPORT_SYMBOL(__bitmap_replace);
 
-int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] & bitmap2[k])
-			return 1;
+			return true;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 1;
-	return 0;
+			return true;
+	return false;
 }
 EXPORT_SYMBOL(__bitmap_intersects);
 
-int __bitmap_subset(const unsigned long *bitmap1,
-		    const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_subset(const unsigned long *bitmap1,
+		     const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] & ~bitmap2[k])
-			return 0;
+			return false;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 0;
-	return 1;
+			return false;
+	return true;
 }
 EXPORT_SYMBOL(__bitmap_subset);
 
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index ea97804d04d4..afdf93bebaaf 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -16,11 +16,11 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
 int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int bits);
-int __bitmap_equal(const unsigned long *bitmap1,
-		   const unsigned long *bitmap2, unsigned int bits);
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int bits);
 void bitmap_clear(unsigned long *map, unsigned int start, int len);
-int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, unsigned int bits);
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int bits);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
@@ -162,8 +162,8 @@ static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
 #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
 #define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0)
 
-static inline int bitmap_equal(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_equal(const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
@@ -173,8 +173,9 @@ static inline int bitmap_equal(const unsigned long *src1,
 	return __bitmap_equal(src1, src2, nbits);
 }
 
-static inline int bitmap_intersects(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_intersects(const unsigned long *src1,
+				     const unsigned long *src2,
+				     unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index db466ef7be9d..354f8cdc0880 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -72,31 +72,31 @@ int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 	return result != 0;
 }
 
-int __bitmap_equal(const unsigned long *bitmap1,
-		const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] != bitmap2[k])
-			return 0;
+			return false;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 0;
+			return false;
 
-	return 1;
+	return true;
 }
 
-int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] & bitmap2[k])
-			return 1;
+			return true;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 1;
-	return 0;
+			return true;
+	return false;
 }
-- 
cgit v1.2.3


From 0dfe54071d7c828a02917b595456bfde1afdddc9 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 18 May 2022 13:52:23 -0700
Subject: nodemask: Fix return values to be unsigned
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The nodemask routines had mixed return values that provided potentially
signed return values that could never happen. This was leading to the
compiler getting confusing about the range of possible return values
(it was thinking things could be negative where they could not be). Fix
all the nodemask routines that should be returning unsigned
(or bool) values. Silences:

 mm/swapfile.c: In function ‘setup_swap_info’:
 mm/swapfile.c:2291:47: error: array subscript -1 is below array bounds of ‘struct plist_node[]’ [-Werror=array-bounds]
  2291 |                                 p->avail_lists[i].prio = 1;
       |                                 ~~~~~~~~~~~~~~^~~
 In file included from mm/swapfile.c:16:
 ./include/linux/swap.h:292:27: note: while referencing ‘avail_lists’
   292 |         struct plist_node avail_lists[]; /*
       |                           ^~~~~~~~~~~

Reported-by: Christophe de Dinechin <dinechin@redhat.com>
Link: https://lore.kernel.org/lkml/20220414150855.2407137-3-dinechin@redhat.com/
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Yury Norov <yury.norov@gmail.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/nodemask.h | 38 +++++++++++++++++++-------------------
 lib/nodemask.c           |  4 ++--
 2 files changed, 21 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 567c3ddba2c4..2c39663c3407 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -42,11 +42,11 @@
  * void nodes_shift_right(dst, src, n)	Shift right
  * void nodes_shift_left(dst, src, n)	Shift left
  *
- * int first_node(mask)			Number lowest set bit, or MAX_NUMNODES
- * int next_node(node, mask)		Next node past 'node', or MAX_NUMNODES
- * int next_node_in(node, mask)		Next node past 'node', or wrap to first,
+ * unsigned int first_node(mask)	Number lowest set bit, or MAX_NUMNODES
+ * unsigend int next_node(node, mask)	Next node past 'node', or MAX_NUMNODES
+ * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first,
  *					or MAX_NUMNODES
- * int first_unset_node(mask)		First node not set in mask, or 
+ * unsigned int first_unset_node(mask)	First node not set in mask, or
  *					MAX_NUMNODES
  *
  * nodemask_t nodemask_of_node(node)	Return nodemask with bit 'node' set
@@ -153,7 +153,7 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 
 #define node_test_and_set(node, nodemask) \
 			__node_test_and_set((node), &(nodemask))
-static inline int __node_test_and_set(int node, nodemask_t *addr)
+static inline bool __node_test_and_set(int node, nodemask_t *addr)
 {
 	return test_and_set_bit(node, addr->bits);
 }
@@ -200,7 +200,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
 
 #define nodes_equal(src1, src2) \
 			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_equal(const nodemask_t *src1p,
+static inline bool __nodes_equal(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
@@ -208,7 +208,7 @@ static inline int __nodes_equal(const nodemask_t *src1p,
 
 #define nodes_intersects(src1, src2) \
 			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_intersects(const nodemask_t *src1p,
+static inline bool __nodes_intersects(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
@@ -216,20 +216,20 @@ static inline int __nodes_intersects(const nodemask_t *src1p,
 
 #define nodes_subset(src1, src2) \
 			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_subset(const nodemask_t *src1p,
+static inline bool __nodes_subset(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
+static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits)
+static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_full(srcp->bits, nbits);
 }
@@ -260,15 +260,15 @@ static inline void __nodes_shift_left(nodemask_t *dstp,
           > MAX_NUMNODES, then the silly min_ts could be dropped. */
 
 #define first_node(src) __first_node(&(src))
-static inline int __first_node(const nodemask_t *srcp)
+static inline unsigned int __first_node(const nodemask_t *srcp)
 {
-	return min_t(int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
+	return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
 }
 
 #define next_node(n, src) __next_node((n), &(src))
-static inline int __next_node(int n, const nodemask_t *srcp)
+static inline unsigned int __next_node(int n, const nodemask_t *srcp)
 {
-	return min_t(int,MAX_NUMNODES,find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
+	return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
 }
 
 /*
@@ -276,7 +276,7 @@ static inline int __next_node(int n, const nodemask_t *srcp)
  * the first node in src if needed.  Returns MAX_NUMNODES if src is empty.
  */
 #define next_node_in(n, src) __next_node_in((n), &(src))
-int __next_node_in(int node, const nodemask_t *srcp);
+unsigned int __next_node_in(int node, const nodemask_t *srcp);
 
 static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 {
@@ -296,9 +296,9 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 })
 
 #define first_unset_node(mask) __first_unset_node(&(mask))
-static inline int __first_unset_node(const nodemask_t *maskp)
+static inline unsigned int __first_unset_node(const nodemask_t *maskp)
 {
-	return min_t(int,MAX_NUMNODES,
+	return min_t(unsigned int, MAX_NUMNODES,
 			find_first_zero_bit(maskp->bits, MAX_NUMNODES));
 }
 
@@ -436,11 +436,11 @@ static inline int num_node_state(enum node_states state)
 
 #define first_online_node	first_node(node_states[N_ONLINE])
 #define first_memory_node	first_node(node_states[N_MEMORY])
-static inline int next_online_node(int nid)
+static inline unsigned int next_online_node(int nid)
 {
 	return next_node(nid, node_states[N_ONLINE]);
 }
-static inline int next_memory_node(int nid)
+static inline unsigned int next_memory_node(int nid)
 {
 	return next_node(nid, node_states[N_MEMORY]);
 }
diff --git a/lib/nodemask.c b/lib/nodemask.c
index 3aa454c54c0d..e22647f5181b 100644
--- a/lib/nodemask.c
+++ b/lib/nodemask.c
@@ -3,9 +3,9 @@
 #include <linux/module.h>
 #include <linux/random.h>
 
-int __next_node_in(int node, const nodemask_t *srcp)
+unsigned int __next_node_in(int node, const nodemask_t *srcp)
 {
-	int ret = __next_node(node, srcp);
+	unsigned int ret = __next_node(node, srcp);
 
 	if (ret == MAX_NUMNODES)
 		ret = __first_node(srcp);
-- 
cgit v1.2.3


From a734510fa8b4e61e6a37176f0da01f4c55fa52de Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 25 May 2022 13:49:42 +0200
Subject: ata: libata: drop 'sas_last_tag'

Unused now.

Fixes: 4f1a22ee7b57 ("libata: Improve ATA queued command allocation")
Cc: John Garry <john.garry@huawei.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
 include/linux/libata.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/libata.h b/include/linux/libata.h
index 732de9014626..0f2a59c9c735 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -822,7 +822,6 @@ struct ata_port {
 	struct ata_queued_cmd	qcmd[ATA_MAX_QUEUE + 1];
 	u64			qc_active;
 	int			nr_active_links; /* #links with active qcs */
-	unsigned int		sas_last_tag;	/* track next tag hw expects */
 
 	struct ata_link		link;		/* host default link */
 	struct ata_link		*slave_link;	/* see ata_slave_link_init() */
-- 
cgit v1.2.3


From 2130a790ca49763f724ec45cf93b9dd765e2023e Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Thu, 2 Jun 2022 15:05:26 +0200
Subject: kernel: add platform_has() infrastructure

Add a simple infrastructure for setting, resetting and querying
platform feature flags.

Flags can be either global or architecture specific.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Tested-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> # Arm64 only
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 MAINTAINERS                            |  8 ++++++++
 include/asm-generic/Kbuild             |  1 +
 include/asm-generic/platform-feature.h |  8 ++++++++
 include/linux/platform-feature.h       | 15 +++++++++++++++
 kernel/Makefile                        |  2 +-
 kernel/platform-feature.c              | 27 +++++++++++++++++++++++++++
 6 files changed, 60 insertions(+), 1 deletion(-)
 create mode 100644 include/asm-generic/platform-feature.h
 create mode 100644 include/linux/platform-feature.h
 create mode 100644 kernel/platform-feature.c

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index a6d3bd9d2a8d..06678abc22ca 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15824,6 +15824,14 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/iio/chemical/plantower,pms7003.yaml
 F:	drivers/iio/chemical/pms7003.c
 
+PLATFORM FEATURE INFRASTRUCTURE
+M:	Juergen Gross <jgross@suse.com>
+S:	Maintained
+F:	arch/*/include/asm/platform-feature.h
+F:	include/asm-generic/platform-feature.h
+F:	include/linux/platform-feature.h
+F:	kernel/platform-feature.c
+
 PLDMFW LIBRARY
 M:	Jacob Keller <jacob.e.keller@intel.com>
 S:	Maintained
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 302506bbc2a4..8e47d483b524 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -44,6 +44,7 @@ mandatory-y += msi.h
 mandatory-y += pci.h
 mandatory-y += percpu.h
 mandatory-y += pgalloc.h
+mandatory-y += platform-feature.h
 mandatory-y += preempt.h
 mandatory-y += rwonce.h
 mandatory-y += sections.h
diff --git a/include/asm-generic/platform-feature.h b/include/asm-generic/platform-feature.h
new file mode 100644
index 000000000000..4b0af3d51588
--- /dev/null
+++ b/include/asm-generic/platform-feature.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_PLATFORM_FEATURE_H
+#define _ASM_GENERIC_PLATFORM_FEATURE_H
+
+/* Number of arch specific feature flags. */
+#define PLATFORM_ARCH_FEAT_N	0
+
+#endif /* _ASM_GENERIC_PLATFORM_FEATURE_H */
diff --git a/include/linux/platform-feature.h b/include/linux/platform-feature.h
new file mode 100644
index 000000000000..6ed859928b97
--- /dev/null
+++ b/include/linux/platform-feature.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PLATFORM_FEATURE_H
+#define _PLATFORM_FEATURE_H
+
+#include <linux/bitops.h>
+#include <asm/platform-feature.h>
+
+/* The platform features are starting with the architecture specific ones. */
+#define PLATFORM_FEAT_N				(0 + PLATFORM_ARCH_FEAT_N)
+
+void platform_set(unsigned int feature);
+void platform_clear(unsigned int feature);
+bool platform_has(unsigned int feature);
+
+#endif /* _PLATFORM_FEATURE_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index 318789c728d3..a7e1f49ab2b3 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -7,7 +7,7 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    cpu.o exit.o softirq.o resource.o \
 	    sysctl.o capability.o ptrace.o user.o \
 	    signal.o sys.o umh.o workqueue.o pid.o task_work.o \
-	    extable.o params.o \
+	    extable.o params.o platform-feature.o \
 	    kthread.o sys_ni.o nsproxy.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
 	    async.o range.o smpboot.o ucount.o regset.o
diff --git a/kernel/platform-feature.c b/kernel/platform-feature.c
new file mode 100644
index 000000000000..cb6a6c3e4fed
--- /dev/null
+++ b/kernel/platform-feature.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitops.h>
+#include <linux/cache.h>
+#include <linux/export.h>
+#include <linux/platform-feature.h>
+
+#define PLATFORM_FEAT_ARRAY_SZ  BITS_TO_LONGS(PLATFORM_FEAT_N)
+static unsigned long __read_mostly platform_features[PLATFORM_FEAT_ARRAY_SZ];
+
+void platform_set(unsigned int feature)
+{
+	set_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_set);
+
+void platform_clear(unsigned int feature)
+{
+	clear_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_clear);
+
+bool platform_has(unsigned int feature)
+{
+	return test_bit(feature, platform_features);
+}
+EXPORT_SYMBOL_GPL(platform_has);
-- 
cgit v1.2.3


From 3f9dfbebdc48cebfbda738f6f3d1dbf6d7232f90 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Mon, 6 Jun 2022 08:09:16 +0200
Subject: virtio: replace arch_has_restricted_virtio_memory_access()

Instead of using arch_has_restricted_virtio_memory_access() together
with CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS, replace those
with platform_has() and a new platform feature
PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Tested-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> # Arm64 only
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Borislav Petkov <bp@suse.de>
---
 arch/s390/Kconfig                |  1 -
 arch/s390/mm/init.c              | 13 +++----------
 arch/x86/Kconfig                 |  1 -
 arch/x86/mm/mem_encrypt.c        |  7 -------
 arch/x86/mm/mem_encrypt_amd.c    |  4 ++++
 drivers/virtio/Kconfig           |  6 ------
 drivers/virtio/virtio.c          |  5 ++---
 include/linux/platform-feature.h |  6 +++++-
 include/linux/virtio_config.h    |  9 ---------
 9 files changed, 14 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b1a88f6cc349..bf253628c136 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -768,7 +768,6 @@ menu "Virtualization"
 config PROTECTED_VIRTUALIZATION_GUEST
 	def_bool n
 	prompt "Protected virtualization guest support"
-	select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
 	help
 	  Select this option, if you want to be able to run this
 	  kernel as a protected virtualization KVM guest.
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 6fb6bf64326f..6a0ac00d5a42 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -31,6 +31,7 @@
 #include <linux/cma.h>
 #include <linux/gfp.h>
 #include <linux/dma-direct.h>
+#include <linux/platform-feature.h>
 #include <asm/processor.h>
 #include <linux/uaccess.h>
 #include <asm/pgalloc.h>
@@ -168,22 +169,14 @@ bool force_dma_unencrypted(struct device *dev)
 	return is_prot_virt_guest();
 }
 
-#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
-
-int arch_has_restricted_virtio_memory_access(void)
-{
-	return is_prot_virt_guest();
-}
-EXPORT_SYMBOL(arch_has_restricted_virtio_memory_access);
-
-#endif
-
 /* protected virtualization */
 static void pv_init(void)
 {
 	if (!is_prot_virt_guest())
 		return;
 
+	platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS);
+
 	/* make sure bounce buffers are shared */
 	swiotlb_init(true, SWIOTLB_FORCE | SWIOTLB_VERBOSE);
 	swiotlb_update_mem_attributes();
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9783ebc4e021..be0b95e51df6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1542,7 +1542,6 @@ config X86_CPA_STATISTICS
 config X86_MEM_ENCRYPT
 	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	select DYNAMIC_PHYSICAL_MASK
-	select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
 	def_bool n
 
 config AMD_MEM_ENCRYPT
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 11350e2fd736..9f27e14e185f 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -12,7 +12,6 @@
 #include <linux/swiotlb.h>
 #include <linux/cc_platform.h>
 #include <linux/mem_encrypt.h>
-#include <linux/virtio_config.h>
 
 /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 bool force_dma_unencrypted(struct device *dev)
@@ -87,9 +86,3 @@ void __init mem_encrypt_init(void)
 
 	print_mem_encrypt_feature_info();
 }
-
-int arch_has_restricted_virtio_memory_access(void)
-{
-	return cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT);
-}
-EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access);
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index e8f7953fda83..f6d038e2cd8e 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -21,6 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/virtio_config.h>
 #include <linux/cc_platform.h>
+#include <linux/platform-feature.h>
 
 #include <asm/tlbflush.h>
 #include <asm/fixmap.h>
@@ -242,6 +243,9 @@ void __init sev_setup_arch(void)
 	size = total_mem * 6 / 100;
 	size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
 	swiotlb_adjust_size(size);
+
+	/* Set restricted memory access for virtio. */
+	platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS);
 }
 
 static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index b5adf6abd241..a6dc8b5846fe 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -6,12 +6,6 @@ config VIRTIO
 	  bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG
 	  or CONFIG_S390_GUEST.
 
-config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
-	bool
-	help
-	  This option is selected if the architecture may need to enforce
-	  VIRTIO_F_ACCESS_PLATFORM
-
 config VIRTIO_PCI_LIB
 	tristate
 	help
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index ef04a96942bf..6bace84ae37e 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/idr.h>
 #include <linux/of.h>
+#include <linux/platform-feature.h>
 #include <uapi/linux/virtio_ids.h>
 
 /* Unique numbering for virtio devices. */
@@ -170,12 +171,10 @@ EXPORT_SYMBOL_GPL(virtio_add_status);
 static int virtio_features_ok(struct virtio_device *dev)
 {
 	unsigned int status;
-	int ret;
 
 	might_sleep();
 
-	ret = arch_has_restricted_virtio_memory_access();
-	if (ret) {
+	if (platform_has(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS)) {
 		if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
 			dev_warn(&dev->dev,
 				 "device must provide VIRTIO_F_VERSION_1\n");
diff --git a/include/linux/platform-feature.h b/include/linux/platform-feature.h
index 6ed859928b97..b2f48be999fa 100644
--- a/include/linux/platform-feature.h
+++ b/include/linux/platform-feature.h
@@ -6,7 +6,11 @@
 #include <asm/platform-feature.h>
 
 /* The platform features are starting with the architecture specific ones. */
-#define PLATFORM_FEAT_N				(0 + PLATFORM_ARCH_FEAT_N)
+
+/* Used to enable platform specific DMA handling for virtio devices. */
+#define PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS	(0 + PLATFORM_ARCH_FEAT_N)
+
+#define PLATFORM_FEAT_N				(1 + PLATFORM_ARCH_FEAT_N)
 
 void platform_set(unsigned int feature);
 void platform_clear(unsigned int feature);
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 9a36051ceb76..49c7c32815f1 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -604,13 +604,4 @@ static inline void virtio_cwrite64(struct virtio_device *vdev,
 		_r;							\
 	})
 
-#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
-int arch_has_restricted_virtio_memory_access(void);
-#else
-static inline int arch_has_restricted_virtio_memory_access(void)
-{
-	return 0;
-}
-#endif /* CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS */
-
 #endif /* _LINUX_VIRTIO_CONFIG_H */
-- 
cgit v1.2.3


From 77991645952c21962a095910c51fe0f73d35bf91 Mon Sep 17 00:00:00 2001
From: Roger Knecht <roger@norberthealth.com>
Date: Sat, 21 May 2022 14:47:45 +0200
Subject: crc-itu-t: fix typo in CRC ITU-T polynomial comment

The code comment says that the polynomial is x^16 + x^12 + x^15 + 1, but
the correct polynomial is x^16 + x^12 + x^5 + 1. Quoting from page 2 in
the ITU-T V.41 specification [1]:

  2 Encoding and checking process

  The service bits and information bits, taken in conjunction,
  correspond to the coefficients of a message polynomial having terms
  from x^(n-1) (n = total number of bits in a block or sequence) down to
  x^16. This polynomial is divided, modulo 2, by the generating
  polynomial x^16 + x^12 + x^5 + 1.

The hex (truncated) polynomial 0x1021 and CRC code implementation are
correct, however.

[1] https://www.itu.int/rec/T-REC-V.41-198811-I/en

Signed-off-by: Roger Knecht <roger@norberthealth.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 include/linux/crc-itu-t.h | 2 +-
 lib/crc-itu-t.c           | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/crc-itu-t.h b/include/linux/crc-itu-t.h
index a4367051e192..2f991a427ade 100644
--- a/include/linux/crc-itu-t.h
+++ b/include/linux/crc-itu-t.h
@@ -4,7 +4,7 @@
  *
  * Implements the standard CRC ITU-T V.41:
  *   Width 16
- *   Poly  0x1021 (x^16 + x^12 + x^15 + 1)
+ *   Poly  0x1021 (x^16 + x^12 + x^5 + 1)
  *   Init  0
  */
 
diff --git a/lib/crc-itu-t.c b/lib/crc-itu-t.c
index 1974b355c148..1d26a1647da5 100644
--- a/lib/crc-itu-t.c
+++ b/lib/crc-itu-t.c
@@ -7,7 +7,7 @@
 #include <linux/module.h>
 #include <linux/crc-itu-t.h>
 
-/** CRC table for the CRC ITU-T V.41 0x1021 (x^16 + x^12 + x^15 + 1) */
+/* CRC table for the CRC ITU-T V.41 0x1021 (x^16 + x^12 + x^5 + 1) */
 const u16 crc_itu_t_table[256] = {
 	0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50a5, 0x60c6, 0x70e7,
 	0x8108, 0x9129, 0xa14a, 0xb16b, 0xc18c, 0xd1ad, 0xe1ce, 0xf1ef,
-- 
cgit v1.2.3


From c4f135d643823a869becfa87539f7820ef9d5bfa Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Wed, 1 Jun 2022 16:32:47 +0900
Subject: workqueue: Wrap flush_workqueue() using a macro

Since flush operation synchronously waits for completion, flushing
system-wide WQs (e.g. system_wq) might introduce possibility of deadlock
due to unexpected locking dependency. Tejun Heo commented at [1] that it
makes no sense at all to call flush_workqueue() on the shared WQs as the
caller has no idea what it's gonna end up waiting for.

Although there is flush_scheduled_work() which flushes system_wq WQ with
"Think twice before calling this function! It's very easy to get into
trouble if you don't take great care." warning message, syzbot found a
circular locking dependency caused by flushing system_wq WQ [2].

Therefore, let's change the direction to that developers had better use
their local WQs if flush_scheduled_work()/flush_workqueue(system_*_wq) is
inevitable.

Steps for converting system-wide WQs into local WQs are explained at [3],
and a conversion to stop flushing system-wide WQs is in progress. Now we
want some mechanism for preventing developers who are not aware of this
conversion from again start flushing system-wide WQs.

Since I found that WARN_ON() is complete but awkward approach for teaching
developers about this problem, let's use __compiletime_warning() for
incomplete but handy approach. For completeness, we will also insert
WARN_ON() into __flush_workqueue() after all in-tree users stopped calling
flush_scheduled_work().

Link: https://lore.kernel.org/all/YgnQGZWT%2Fn3VAITX@slm.duckdns.org/ [1]
Link: https://syzkaller.appspot.com/bug?extid=bde0f89deacca7c765b8 [2]
Link: https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp [3]
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/workqueue.h | 64 +++++++++++++++++++++++++++++++++++++++++------
 kernel/workqueue.c        | 16 +++++++++---
 2 files changed, 68 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 7fee9b6cfede..e1f1c8b1121b 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -445,7 +445,7 @@ extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
 			struct delayed_work *dwork, unsigned long delay);
 extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork);
 
-extern void flush_workqueue(struct workqueue_struct *wq);
+extern void __flush_workqueue(struct workqueue_struct *wq);
 extern void drain_workqueue(struct workqueue_struct *wq);
 
 extern int schedule_on_each_cpu(work_func_t func);
@@ -563,15 +563,23 @@ static inline bool schedule_work(struct work_struct *work)
 	return queue_work(system_wq, work);
 }
 
+/*
+ * Detect attempt to flush system-wide workqueues at compile time when possible.
+ *
+ * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp
+ * for reasons and steps for converting system-wide workqueues into local workqueues.
+ */
+extern void __warn_flushing_systemwide_wq(void)
+	__compiletime_warning("Please avoid flushing system-wide workqueues.");
+
 /**
  * flush_scheduled_work - ensure that any scheduled work has run to completion.
  *
  * Forces execution of the kernel-global workqueue and blocks until its
  * completion.
  *
- * Think twice before calling this function!  It's very easy to get into
- * trouble if you don't take great care.  Either of the following situations
- * will lead to deadlock:
+ * It's very easy to get into trouble if you don't take great care.
+ * Either of the following situations will lead to deadlock:
  *
  *	One of the work items currently on the workqueue needs to acquire
  *	a lock held by your code or its caller.
@@ -586,11 +594,51 @@ static inline bool schedule_work(struct work_struct *work)
  * need to know that a particular work item isn't queued and isn't running.
  * In such cases you should use cancel_delayed_work_sync() or
  * cancel_work_sync() instead.
+ *
+ * Please stop calling this function! A conversion to stop flushing system-wide
+ * workqueues is in progress. This function will be removed after all in-tree
+ * users stopped calling this function.
  */
-static inline void flush_scheduled_work(void)
-{
-	flush_workqueue(system_wq);
-}
+/*
+ * The background of commit 771c035372a036f8 ("deprecate the
+ * '__deprecated' attribute warnings entirely and for good") is that,
+ * since Linus builds all modules between every single pull he does,
+ * the standard kernel build needs to be _clean_ in order to be able to
+ * notice when new problems happen. Therefore, don't emit warning while
+ * there are in-tree users.
+ */
+#define flush_scheduled_work()						\
+({									\
+	if (0)								\
+		__warn_flushing_systemwide_wq();			\
+	__flush_workqueue(system_wq);					\
+})
+
+/*
+ * Although there is no longer in-tree caller, for now just emit warning
+ * in order to give out-of-tree callers time to update.
+ */
+#define flush_workqueue(wq)						\
+({									\
+	struct workqueue_struct *_wq = (wq);				\
+									\
+	if ((__builtin_constant_p(_wq == system_wq) &&			\
+	     _wq == system_wq) ||					\
+	    (__builtin_constant_p(_wq == system_highpri_wq) &&		\
+	     _wq == system_highpri_wq) ||				\
+	    (__builtin_constant_p(_wq == system_long_wq) &&		\
+	     _wq == system_long_wq) ||					\
+	    (__builtin_constant_p(_wq == system_unbound_wq) &&		\
+	     _wq == system_unbound_wq) ||				\
+	    (__builtin_constant_p(_wq == system_freezable_wq) &&	\
+	     _wq == system_freezable_wq) ||				\
+	    (__builtin_constant_p(_wq == system_power_efficient_wq) &&	\
+	     _wq == system_power_efficient_wq) ||			\
+	    (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \
+	     _wq == system_freezable_power_efficient_wq))		\
+		__warn_flushing_systemwide_wq();			\
+	__flush_workqueue(_wq);						\
+})
 
 /**
  * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4056f2a3f9d5..1ea50f6be843 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2788,13 +2788,13 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
 }
 
 /**
- * flush_workqueue - ensure that any scheduled work has run to completion.
+ * __flush_workqueue - ensure that any scheduled work has run to completion.
  * @wq: workqueue to flush
  *
  * This function sleeps until all work items which were queued on entry
  * have finished execution, but it is not livelocked by new incoming ones.
  */
-void flush_workqueue(struct workqueue_struct *wq)
+void __flush_workqueue(struct workqueue_struct *wq)
 {
 	struct wq_flusher this_flusher = {
 		.list = LIST_HEAD_INIT(this_flusher.list),
@@ -2943,7 +2943,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 out_unlock:
 	mutex_unlock(&wq->mutex);
 }
-EXPORT_SYMBOL(flush_workqueue);
+EXPORT_SYMBOL(__flush_workqueue);
 
 /**
  * drain_workqueue - drain a workqueue
@@ -2971,7 +2971,7 @@ void drain_workqueue(struct workqueue_struct *wq)
 		wq->flags |= __WQ_DRAINING;
 	mutex_unlock(&wq->mutex);
 reflush:
-	flush_workqueue(wq);
+	__flush_workqueue(wq);
 
 	mutex_lock(&wq->mutex);
 
@@ -6111,3 +6111,11 @@ void __init workqueue_init(void)
 	wq_online = true;
 	wq_watchdog_init();
 }
+
+/*
+ * Despite the naming, this is a no-op function which is here only for avoiding
+ * link error. Since compile-time warning may fail to catch, we will need to
+ * emit run-time warning from __flush_workqueue().
+ */
+void __warn_flushing_systemwide_wq(void) { }
+EXPORT_SYMBOL(__warn_flushing_systemwide_wq);
-- 
cgit v1.2.3


From 62ed448cc53b654036f7d7f3c99f299d79ad14c3 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 7 Jun 2022 16:47:58 -0400
Subject: SUNRPC: Optimize xdr_reserve_space()

Transitioning between encode buffers is quite infrequent. It happens
about 1 time in 400 calls to xdr_reserve_space(), measured on NFSD
with a typical build/test workload.

Force the compiler to remove that code from xdr_reserve_space(),
which is a hot path on both the server and the client. This change
reduces the size of xdr_reserve_space() from 10 cache lines to 2
when compiled with -Os.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: J. Bruce Fields <bfields@fieldses.org>
---
 include/linux/sunrpc/xdr.h | 16 +++++++++++++++-
 net/sunrpc/xdr.c           | 17 ++++++++++-------
 2 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 4417f667c757..5860f32e3958 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -243,7 +243,7 @@ extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
 extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec,
 		size_t nbytes);
-extern void xdr_commit_encode(struct xdr_stream *xdr);
+extern void __xdr_commit_encode(struct xdr_stream *xdr);
 extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len);
 extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
@@ -306,6 +306,20 @@ xdr_reset_scratch_buffer(struct xdr_stream *xdr)
 	xdr_set_scratch_buffer(xdr, NULL, 0);
 }
 
+/**
+ * xdr_commit_encode - Ensure all data is written to xdr->buf
+ * @xdr: pointer to xdr_stream
+ *
+ * Handle encoding across page boundaries by giving the caller a
+ * temporary location to write to, then later copying the data into
+ * place. __xdr_commit_encode() does that copying.
+ */
+static inline void xdr_commit_encode(struct xdr_stream *xdr)
+{
+	if (unlikely(xdr->scratch.iov_len))
+		__xdr_commit_encode(xdr);
+}
+
 /**
  * xdr_stream_remaining - Return the number of bytes remaining in the stream
  * @xdr: pointer to struct xdr_stream
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index b57cf9df4de8..1ad8b4ef14de 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -919,7 +919,7 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
 EXPORT_SYMBOL_GPL(xdr_init_encode);
 
 /**
- * xdr_commit_encode - Ensure all data is written to buffer
+ * __xdr_commit_encode - Ensure all data is written to buffer
  * @xdr: pointer to xdr_stream
  *
  * We handle encoding across page boundaries by giving the caller a
@@ -931,22 +931,25 @@ EXPORT_SYMBOL_GPL(xdr_init_encode);
  * required at the end of encoding, or any other time when the xdr_buf
  * data might be read.
  */
-inline void xdr_commit_encode(struct xdr_stream *xdr)
+void __xdr_commit_encode(struct xdr_stream *xdr)
 {
 	int shift = xdr->scratch.iov_len;
 	void *page;
 
-	if (shift == 0)
-		return;
 	page = page_address(*xdr->page_ptr);
 	memcpy(xdr->scratch.iov_base, page, shift);
 	memmove(page, page + shift, (void *)xdr->p - page);
 	xdr_reset_scratch_buffer(xdr);
 }
-EXPORT_SYMBOL_GPL(xdr_commit_encode);
+EXPORT_SYMBOL_GPL(__xdr_commit_encode);
 
-static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
-		size_t nbytes)
+/*
+ * The buffer space to be reserved crosses the boundary between
+ * xdr->buf->head and xdr->buf->pages, or between two pages
+ * in xdr->buf->pages.
+ */
+static noinline __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
+						   size_t nbytes)
 {
 	__be32 *p;
 	int space_left;
-- 
cgit v1.2.3


From d5a37b19983725d2045588cfa3a4699f5b39ae26 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 8 Jun 2022 08:34:07 +0200
Subject: block: remove bioset_init_from_src

Unused now, and the interface never really made a whole lot of sense to
start with.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
 block/bio.c         | 20 --------------------
 include/linux/bio.h |  1 -
 2 files changed, 21 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index f92d0223247b..51c99f2c5c90 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1747,26 +1747,6 @@ bad:
 }
 EXPORT_SYMBOL(bioset_init);
 
-/*
- * Initialize and setup a new bio_set, based on the settings from
- * another bio_set.
- */
-int bioset_init_from_src(struct bio_set *bs, struct bio_set *src)
-{
-	int flags;
-
-	flags = 0;
-	if (src->bvec_pool.min_nr)
-		flags |= BIOSET_NEED_BVECS;
-	if (src->rescue_workqueue)
-		flags |= BIOSET_NEED_RESCUER;
-	if (src->cache)
-		flags |= BIOSET_PERCPU_CACHE;
-
-	return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags);
-}
-EXPORT_SYMBOL(bioset_init_from_src);
-
 static int __init init_bio(void)
 {
 	int i;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1cf3738ef1ea..992ee987f273 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -403,7 +403,6 @@ enum {
 extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags);
 extern void bioset_exit(struct bio_set *);
 extern int biovec_init_pool(mempool_t *pool, int pool_entries);
-extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src);
 
 struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
 			     unsigned int opf, gfp_t gfp_mask,
-- 
cgit v1.2.3


From 00d1f546470d89e072dd3cda12b5c794341e7268 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 9 Jun 2022 12:19:01 +0800
Subject: vdpa: make get_vq_group and set_group_asid optional

This patch makes get_vq_group and set_group_asid optional. This is
needed to unbreak the vDPA parent that doesn't support multiple
address spaces.

Cc: Gautam Dawar <gautam.dawar@xilinx.com>
Fixes: aaca8373c4b1 ("vhost-vdpa: support ASID based IOTLB API")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220609041901.2029-1-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vdpa.c | 2 ++
 include/linux/vdpa.h | 5 +++--
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 935a1d0ddb97..5ad2596c6e8a 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -499,6 +499,8 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 		ops->set_vq_ready(vdpa, idx, s.num);
 		return 0;
 	case VHOST_VDPA_GET_VRING_GROUP:
+		if (!ops->get_vq_group)
+			return -EOPNOTSUPP;
 		s.index = idx;
 		s.num = ops->get_vq_group(vdpa, idx);
 		if (s.num >= vdpa->ngroups)
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 4700a88a28f6..7b4a13d3bd91 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -178,7 +178,8 @@ struct vdpa_map_file {
  *				for the device
  *				@vdev: vdpa device
  *				Returns virtqueue algin requirement
- * @get_vq_group:		Get the group id for a specific virtqueue
+ * @get_vq_group:		Get the group id for a specific
+ *				virtqueue (optional)
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns u32: group id for this virtqueue
@@ -243,7 +244,7 @@ struct vdpa_map_file {
  *				Returns the iova range supported by
  *				the device.
  * @set_group_asid:		Set address space identifier for a
- *				virtqueue group
+ *				virtqueue group (optional)
  *				@vdev: vdpa device
  *				@group: virtqueue group
  *				@asid: address space id for this group
-- 
cgit v1.2.3


From 69a37a8ba1b408a1c7616494aa7018e4b3844cbe Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 8 Jun 2022 15:18:34 -0400
Subject: mm/huge_memory: Fix xarray node memory leak

If xas_split_alloc() fails to allocate the necessary nodes to complete the
xarray entry split, it sets the xa_state to -ENOMEM, which xas_nomem()
then interprets as "Please allocate more memory", not as "Please free
any unnecessary memory" (which was the intended outcome).  It's confusing
to use xas_nomem() to free memory in this context, so call xas_destroy()
instead.

Reported-by: syzbot+9e27a75a8c24f3fe75c1@syzkaller.appspotmail.com
Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h | 1 +
 lib/xarray.c           | 5 +++--
 mm/huge_memory.c       | 3 +--
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 72feab5ea8d4..c29e11b2c073 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1508,6 +1508,7 @@ void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t);
 void xas_init_marks(const struct xa_state *);
 
 bool xas_nomem(struct xa_state *, gfp_t);
+void xas_destroy(struct xa_state *);
 void xas_pause(struct xa_state *);
 
 void xas_create_range(struct xa_state *);
diff --git a/lib/xarray.c b/lib/xarray.c
index 54e646e8e6ee..ea9ce1f0b386 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -264,9 +264,10 @@ static void xa_node_free(struct xa_node *node)
  * xas_destroy() - Free any resources allocated during the XArray operation.
  * @xas: XArray operation state.
  *
- * This function is now internal-only.
+ * Most users will not need to call this function; it is called for you
+ * by xas_nomem().
  */
-static void xas_destroy(struct xa_state *xas)
+void xas_destroy(struct xa_state *xas)
 {
 	struct xa_node *next, *node = xas->xa_alloc;
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a77c78a2b6b5..f7248002dad9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2672,8 +2672,7 @@ out_unlock:
 	if (mapping)
 		i_mmap_unlock_read(mapping);
 out:
-	/* Free any memory we didn't use */
-	xas_nomem(&xas, 0);
+	xas_destroy(&xas);
 	count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
 	return ret;
 }
-- 
cgit v1.2.3


From 334f6f53abcf57782bd2fe81da1cbd893e4ef05c Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 9 Jun 2022 09:13:57 -0400
Subject: mm: Add kernel-doc for folio->mlock_count

Fix "./include/linux/mm_types.h:279: warning: Function parameter or member
'mlock_count' not described in 'folio'".  Also neaten the html by hiding
the anon struct.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/mm_types.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index b34ff2cdbc4f..c29ab4c0cd5c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -227,6 +227,7 @@ struct page {
  * struct folio - Represents a contiguous set of bytes.
  * @flags: Identical to the page flags.
  * @lru: Least Recently Used list; tracks how recently this folio was used.
+ * @mlock_count: Number of times this folio has been pinned by mlock().
  * @mapping: The file this page belongs to, or refers to the anon_vma for
  *    anonymous memory.
  * @index: Offset within the file, in units of pages.  For anonymous memory,
@@ -255,10 +256,14 @@ struct folio {
 			unsigned long flags;
 			union {
 				struct list_head lru;
+	/* private: avoid cluttering the output */
 				struct {
 					void *__filler;
+	/* public: */
 					unsigned int mlock_count;
+	/* private: */
 				};
+	/* public: */
 			};
 			struct address_space *mapping;
 			pgoff_t index;
-- 
cgit v1.2.3


From 874c8ca1e60b2c564a48f7e7acc40d328d5c8733 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 9 Jun 2022 21:46:04 +0100
Subject: netfs: Fix gcc-12 warning by embedding vfs inode in netfs_i_context

While randstruct was satisfied with using an open-coded "void *" offset
cast for the netfs_i_context <-> inode casting, __builtin_object_size() as
used by FORTIFY_SOURCE was not as easily fooled.  This was causing the
following complaint[1] from gcc v12:

  In file included from include/linux/string.h:253,
                   from include/linux/ceph/ceph_debug.h:7,
                   from fs/ceph/inode.c:2:
  In function 'fortify_memset_chk',
      inlined from 'netfs_i_context_init' at include/linux/netfs.h:326:2,
      inlined from 'ceph_alloc_inode' at fs/ceph/inode.c:463:2:
  include/linux/fortify-string.h:242:25: warning: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Wattribute-warning]
    242 |                         __write_overflow_field(p_size_field, size);
        |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Fix this by embedding a struct inode into struct netfs_i_context (which
should perhaps be renamed to struct netfs_inode).  The struct inode
vfs_inode fields are then removed from the 9p, afs, ceph and cifs inode
structs and vfs_inode is then simply changed to "netfs.inode" in those
filesystems.

Further, rename netfs_i_context to netfs_inode, get rid of the
netfs_inode() function that converted a netfs_i_context pointer to an
inode pointer (that can now be done with &ctx->inode) and rename the
netfs_i_context() function to netfs_inode() (which is now a wrapper
around container_of()).

Most of the changes were done with:

  perl -p -i -e 's/vfs_inode/netfs.inode/'g \
        `git grep -l 'vfs_inode' -- fs/{9p,afs,ceph,cifs}/*.[ch]`

Kees suggested doing it with a pair structure[2] and a special
declarator to insert that into the network filesystem's inode
wrapper[3], but I think it's cleaner to embed it - and then it doesn't
matter if struct randomisation reorders things.

Dave Chinner suggested using a filesystem-specific VFS_I() function in
each filesystem to convert that filesystem's own inode wrapper struct
into the VFS inode struct[4].

Version #2:
 - Fix a couple of missed name changes due to a disabled cifs option.
 - Rename nfs_i_context to nfs_inode
 - Use "netfs" instead of "nic" as the member name in per-fs inode wrapper
   structs.

[ This also undoes commit 507160f46c55 ("netfs: gcc-12: temporarily
  disable '-Wattribute-warning' for now") that is no longer needed ]

Fixes: bc899ee1c898 ("netfs: Add a netfs inode context")
Reported-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
cc: Jonathan Corbet <corbet@lwn.net>
cc: Eric Van Hensbergen <ericvh@gmail.com>
cc: Latchesar Ionkov <lucho@ionkov.net>
cc: Dominique Martinet <asmadeus@codewreck.org>
cc: Christian Schoenebeck <linux_oss@crudebyte.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: Steve French <smfrench@gmail.com>
cc: William Kucharski <william.kucharski@oracle.com>
cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
cc: Dave Chinner <david@fromorbit.com>
cc: linux-doc@vger.kernel.org
cc: v9fs-developer@lists.sourceforge.net
cc: linux-afs@lists.infradead.org
cc: ceph-devel@vger.kernel.org
cc: linux-cifs@vger.kernel.org
cc: samba-technical@lists.samba.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-hardening@vger.kernel.org
Link: https://lore.kernel.org/r/d2ad3a3d7bdd794c6efb562d2f2b655fb67756b9.camel@kernel.org/ [1]
Link: https://lore.kernel.org/r/20220517210230.864239-1-keescook@chromium.org/ [2]
Link: https://lore.kernel.org/r/20220518202212.2322058-1-keescook@chromium.org/ [3]
Link: https://lore.kernel.org/r/20220524101205.GI2306852@dread.disaster.area/ [4]
Link: https://lore.kernel.org/r/165296786831.3591209.12111293034669289733.stgit@warthog.procyon.org.uk/ # v1
Link: https://lore.kernel.org/r/165305805651.4094995.7763502506786714216.stgit@warthog.procyon.org.uk # v2
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/netfs_library.rst |  37 +++++-----
 fs/9p/cache.c                               |   4 +-
 fs/9p/v9fs.c                                |   2 +-
 fs/9p/v9fs.h                                |  10 +--
 fs/9p/vfs_addr.c                            |   2 +-
 fs/9p/vfs_inode.c                           |   4 +-
 fs/afs/callback.c                           |   2 +-
 fs/afs/dir.c                                |  32 ++++-----
 fs/afs/dir_edit.c                           |  10 +--
 fs/afs/dir_silly.c                          |   4 +-
 fs/afs/dynroot.c                            |   2 +-
 fs/afs/file.c                               |   4 +-
 fs/afs/fs_operation.c                       |   6 +-
 fs/afs/inode.c                              |  41 +++++------
 fs/afs/internal.h                           |  23 +++---
 fs/afs/super.c                              |   6 +-
 fs/afs/write.c                              |  21 +++---
 fs/ceph/addr.c                              |   4 +-
 fs/ceph/cache.c                             |   4 +-
 fs/ceph/cache.h                             |   2 +-
 fs/ceph/caps.c                              | 104 ++++++++++++++--------------
 fs/ceph/file.c                              |   2 +-
 fs/ceph/inode.c                             |  13 ++--
 fs/ceph/mds_client.c                        |   4 +-
 fs/ceph/snap.c                              |   8 +--
 fs/ceph/super.c                             |   2 +-
 fs/ceph/super.h                             |  10 +--
 fs/ceph/xattr.c                             |  14 ++--
 fs/cifs/cifsfs.c                            |   8 +--
 fs/cifs/cifsglob.h                          |  12 ++--
 fs/cifs/file.c                              |   8 +--
 fs/cifs/fscache.c                           |   8 +--
 fs/cifs/fscache.h                           |   8 +--
 fs/cifs/inode.c                             |   4 +-
 fs/cifs/misc.c                              |   4 +-
 fs/cifs/smb2ops.c                           |   8 +--
 fs/netfs/buffered_read.c                    |   6 +-
 fs/netfs/internal.h                         |   2 +-
 fs/netfs/objects.c                          |   2 +-
 include/linux/netfs.h                       |  41 +++++------
 40 files changed, 227 insertions(+), 261 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index a80a59941d2f..3276c3d55142 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -37,30 +37,31 @@ The network filesystem helper library needs a place to store a bit of state for
 its use on each netfs inode it is helping to manage.  To this end, a context
 structure is defined::
 
-	struct netfs_i_context {
+	struct netfs_inode {
+		struct inode inode;
 		const struct netfs_request_ops *ops;
-		struct fscache_cookie	*cache;
+		struct fscache_cookie *cache;
 	};
 
-A network filesystem that wants to use netfs lib must place one of these
-directly after the VFS ``struct inode`` it allocates, usually as part of its
-own struct.  This can be done in a way similar to the following::
+A network filesystem that wants to use netfs lib must place one of these in its
+inode wrapper struct instead of the VFS ``struct inode``.  This can be done in
+a way similar to the following::
 
 	struct my_inode {
-		struct {
-			/* These must be contiguous */
-			struct inode		vfs_inode;
-			struct netfs_i_context  netfs_ctx;
-		};
+		struct netfs_inode netfs; /* Netfslib context and vfs inode */
 		...
 	};
 
-This allows netfslib to find its state by simple offset from the inode pointer,
-thereby allowing the netfslib helper functions to be pointed to directly by the
-VFS/VM operation tables.
+This allows netfslib to find its state by using ``container_of()`` from the
+inode pointer, thereby allowing the netfslib helper functions to be pointed to
+directly by the VFS/VM operation tables.
 
 The structure contains the following fields:
 
+ * ``inode``
+
+   The VFS inode structure.
+
  * ``ops``
 
    The set of operations provided by the network filesystem to netfslib.
@@ -78,14 +79,12 @@ To help deal with the per-inode context, a number helper functions are
 provided.  Firstly, a function to perform basic initialisation on a context and
 set the operations table pointer::
 
-	void netfs_i_context_init(struct inode *inode,
-				  const struct netfs_request_ops *ops);
+	void netfs_inode_init(struct inode *inode,
+			      const struct netfs_request_ops *ops);
 
-then two functions to cast between the VFS inode structure and the netfs
-context::
+then a function to cast from the VFS inode structure to the netfs context::
 
-	struct netfs_i_context *netfs_i_context(struct inode *inode);
-	struct inode *netfs_inode(struct netfs_i_context *ctx);
+	struct netfs_inode *netfs_node(struct inode *inode);
 
 and finally, a function to get the cache cookie pointer from the context
 attached to an inode (or NULL if fscache is disabled)::
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index 1c8dc696d516..cebba4eaa0b5 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -62,12 +62,12 @@ void v9fs_cache_inode_get_cookie(struct inode *inode)
 	version = cpu_to_le32(v9inode->qid.version);
 	path = cpu_to_le64(v9inode->qid.path);
 	v9ses = v9fs_inode2v9ses(inode);
-	v9inode->netfs_ctx.cache =
+	v9inode->netfs.cache =
 		fscache_acquire_cookie(v9fs_session_cache(v9ses),
 				       0,
 				       &path, sizeof(path),
 				       &version, sizeof(version),
-				       i_size_read(&v9inode->vfs_inode));
+				       i_size_read(&v9inode->netfs.inode));
 
 	p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
 		 inode, v9fs_inode_cookie(v9inode));
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index e28ddf763b3b..0129de2ea31a 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -625,7 +625,7 @@ static void v9fs_inode_init_once(void *foo)
 	struct v9fs_inode *v9inode = (struct v9fs_inode *)foo;
 
 	memset(&v9inode->qid, 0, sizeof(v9inode->qid));
-	inode_init_once(&v9inode->vfs_inode);
+	inode_init_once(&v9inode->netfs.inode);
 }
 
 /**
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index ec0e8df3b2eb..1b219c21d15e 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -109,11 +109,7 @@ struct v9fs_session_info {
 #define V9FS_INO_INVALID_ATTR 0x01
 
 struct v9fs_inode {
-	struct {
-		/* These must be contiguous */
-		struct inode	vfs_inode;	/* the VFS's inode record */
-		struct netfs_i_context netfs_ctx; /* Netfslib context */
-	};
+	struct netfs_inode netfs; /* Netfslib context and vfs inode */
 	struct p9_qid qid;
 	unsigned int cache_validity;
 	struct p9_fid *writeback_fid;
@@ -122,13 +118,13 @@ struct v9fs_inode {
 
 static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
 {
-	return container_of(inode, struct v9fs_inode, vfs_inode);
+	return container_of(inode, struct v9fs_inode, netfs.inode);
 }
 
 static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inode)
 {
 #ifdef CONFIG_9P_FSCACHE
-	return netfs_i_cookie(&v9inode->vfs_inode);
+	return netfs_i_cookie(&v9inode->netfs.inode);
 #else
 	return NULL;
 #endif
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 8ce82ff1e40a..90c6c1ba03ab 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -140,7 +140,7 @@ static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
 	    transferred_or_error != -ENOBUFS) {
 		version = cpu_to_le32(v9inode->qid.version);
 		fscache_invalidate(v9fs_inode_cookie(v9inode), &version,
-				   i_size_read(&v9inode->vfs_inode), 0);
+				   i_size_read(&v9inode->netfs.inode), 0);
 	}
 }
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 55367ecb9442..e660c6348b9d 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -234,7 +234,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb)
 	v9inode->writeback_fid = NULL;
 	v9inode->cache_validity = 0;
 	mutex_init(&v9inode->v_mutex);
-	return &v9inode->vfs_inode;
+	return &v9inode->netfs.inode;
 }
 
 /**
@@ -252,7 +252,7 @@ void v9fs_free_inode(struct inode *inode)
  */
 static void v9fs_set_netfs_context(struct inode *inode)
 {
-	netfs_i_context_init(inode, &v9fs_req_ops);
+	netfs_inode_init(inode, &v9fs_req_ops);
 }
 
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 1b4d5809808d..a484fa642808 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -30,7 +30,7 @@ void afs_invalidate_mmap_work(struct work_struct *work)
 {
 	struct afs_vnode *vnode = container_of(work, struct afs_vnode, cb_work);
 
-	unmap_mapping_pages(vnode->vfs_inode.i_mapping, 0, 0, false);
+	unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false);
 }
 
 void afs_server_init_callback_work(struct work_struct *work)
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 79f6b74336d2..56ae5cd5184f 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -109,7 +109,7 @@ struct afs_lookup_cookie {
  */
 static void afs_dir_read_cleanup(struct afs_read *req)
 {
-	struct address_space *mapping = req->vnode->vfs_inode.i_mapping;
+	struct address_space *mapping = req->vnode->netfs.inode.i_mapping;
 	struct folio *folio;
 	pgoff_t last = req->nr_pages - 1;
 
@@ -153,7 +153,7 @@ static bool afs_dir_check_folio(struct afs_vnode *dvnode, struct folio *folio,
 		block = kmap_local_folio(folio, offset);
 		if (block->hdr.magic != AFS_DIR_MAGIC) {
 			printk("kAFS: %s(%lx): [%llx] bad magic %zx/%zx is %04hx\n",
-			       __func__, dvnode->vfs_inode.i_ino,
+			       __func__, dvnode->netfs.inode.i_ino,
 			       pos, offset, size, ntohs(block->hdr.magic));
 			trace_afs_dir_check_failed(dvnode, pos + offset, i_size);
 			kunmap_local(block);
@@ -183,7 +183,7 @@ error:
 static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
 {
 	union afs_xdr_dir_block *block;
-	struct address_space *mapping = dvnode->vfs_inode.i_mapping;
+	struct address_space *mapping = dvnode->netfs.inode.i_mapping;
 	struct folio *folio;
 	pgoff_t last = req->nr_pages - 1;
 	size_t offset, size;
@@ -217,7 +217,7 @@ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
  */
 static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req)
 {
-	struct address_space *mapping = dvnode->vfs_inode.i_mapping;
+	struct address_space *mapping = dvnode->netfs.inode.i_mapping;
 	struct folio *folio;
 	pgoff_t last = req->nr_pages - 1;
 	int ret = 0;
@@ -269,7 +269,7 @@ static int afs_dir_open(struct inode *inode, struct file *file)
 static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
 	__acquires(&dvnode->validate_lock)
 {
-	struct address_space *mapping = dvnode->vfs_inode.i_mapping;
+	struct address_space *mapping = dvnode->netfs.inode.i_mapping;
 	struct afs_read *req;
 	loff_t i_size;
 	int nr_pages, i;
@@ -287,7 +287,7 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
 	req->cleanup = afs_dir_read_cleanup;
 
 expand:
-	i_size = i_size_read(&dvnode->vfs_inode);
+	i_size = i_size_read(&dvnode->netfs.inode);
 	if (i_size < 2048) {
 		ret = afs_bad(dvnode, afs_file_error_dir_small);
 		goto error;
@@ -305,7 +305,7 @@ expand:
 	req->actual_len = i_size; /* May change */
 	req->len = nr_pages * PAGE_SIZE; /* We can ask for more than there is */
 	req->data_version = dvnode->status.data_version; /* May change */
-	iov_iter_xarray(&req->def_iter, READ, &dvnode->vfs_inode.i_mapping->i_pages,
+	iov_iter_xarray(&req->def_iter, READ, &dvnode->netfs.inode.i_mapping->i_pages,
 			0, i_size);
 	req->iter = &req->def_iter;
 
@@ -897,7 +897,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 
 out_op:
 	if (op->error == 0) {
-		inode = &op->file[1].vnode->vfs_inode;
+		inode = &op->file[1].vnode->netfs.inode;
 		op->file[1].vnode = NULL;
 	}
 
@@ -1139,7 +1139,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	afs_stat_v(dir, n_reval);
 
 	/* search the directory for this vnode */
-	ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key, &dir_version);
+	ret = afs_do_lookup_one(&dir->netfs.inode, dentry, &fid, key, &dir_version);
 	switch (ret) {
 	case 0:
 		/* the filename maps to something */
@@ -1170,7 +1170,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 			_debug("%pd: file deleted (uq %u -> %u I:%u)",
 			       dentry, fid.unique,
 			       vnode->fid.unique,
-			       vnode->vfs_inode.i_generation);
+			       vnode->netfs.inode.i_generation);
 			goto not_found;
 		}
 		goto out_valid;
@@ -1368,7 +1368,7 @@ static void afs_dir_remove_subdir(struct dentry *dentry)
 	if (d_really_is_positive(dentry)) {
 		struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
 
-		clear_nlink(&vnode->vfs_inode);
+		clear_nlink(&vnode->netfs.inode);
 		set_bit(AFS_VNODE_DELETED, &vnode->flags);
 		clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
 		clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
@@ -1487,8 +1487,8 @@ static void afs_dir_remove_link(struct afs_operation *op)
 		/* Already done */
 	} else if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
 		write_seqlock(&vnode->cb_lock);
-		drop_nlink(&vnode->vfs_inode);
-		if (vnode->vfs_inode.i_nlink == 0) {
+		drop_nlink(&vnode->netfs.inode);
+		if (vnode->netfs.inode.i_nlink == 0) {
 			set_bit(AFS_VNODE_DELETED, &vnode->flags);
 			__afs_break_callback(vnode, afs_cb_break_for_unlink);
 		}
@@ -1504,7 +1504,7 @@ static void afs_dir_remove_link(struct afs_operation *op)
 			op->error = ret;
 	}
 
-	_debug("nlink %d [val %d]", vnode->vfs_inode.i_nlink, op->error);
+	_debug("nlink %d [val %d]", vnode->netfs.inode.i_nlink, op->error);
 }
 
 static void afs_unlink_success(struct afs_operation *op)
@@ -1680,8 +1680,8 @@ static void afs_link_success(struct afs_operation *op)
 	afs_update_dentry_version(op, dvp, op->dentry);
 	if (op->dentry_2->d_parent == op->dentry->d_parent)
 		afs_update_dentry_version(op, dvp, op->dentry_2);
-	ihold(&vp->vnode->vfs_inode);
-	d_instantiate(op->dentry, &vp->vnode->vfs_inode);
+	ihold(&vp->vnode->netfs.inode);
+	d_instantiate(op->dentry, &vp->vnode->netfs.inode);
 }
 
 static void afs_link_put(struct afs_operation *op)
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index d98e109ecee9..0ab7752d1b75 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -109,7 +109,7 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block,
  */
 static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index)
 {
-	struct address_space *mapping = vnode->vfs_inode.i_mapping;
+	struct address_space *mapping = vnode->netfs.inode.i_mapping;
 	struct folio *folio;
 
 	folio = __filemap_get_folio(mapping, index,
@@ -216,7 +216,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
 
 	_enter(",,{%d,%s},", name->len, name->name);
 
-	i_size = i_size_read(&vnode->vfs_inode);
+	i_size = i_size_read(&vnode->netfs.inode);
 	if (i_size > AFS_DIR_BLOCK_SIZE * AFS_DIR_MAX_BLOCKS ||
 	    (i_size & (AFS_DIR_BLOCK_SIZE - 1))) {
 		clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
@@ -336,7 +336,7 @@ found_space:
 	if (b < AFS_DIR_BLOCKS_WITH_CTR)
 		meta->meta.alloc_ctrs[b] -= need_slots;
 
-	inode_inc_iversion_raw(&vnode->vfs_inode);
+	inode_inc_iversion_raw(&vnode->netfs.inode);
 	afs_stat_v(vnode, n_dir_cr);
 	_debug("Insert %s in %u[%u]", name->name, b, slot);
 
@@ -383,7 +383,7 @@ void afs_edit_dir_remove(struct afs_vnode *vnode,
 
 	_enter(",,{%d,%s},", name->len, name->name);
 
-	i_size = i_size_read(&vnode->vfs_inode);
+	i_size = i_size_read(&vnode->netfs.inode);
 	if (i_size < AFS_DIR_BLOCK_SIZE ||
 	    i_size > AFS_DIR_BLOCK_SIZE * AFS_DIR_MAX_BLOCKS ||
 	    (i_size & (AFS_DIR_BLOCK_SIZE - 1))) {
@@ -463,7 +463,7 @@ found_dirent:
 	if (b < AFS_DIR_BLOCKS_WITH_CTR)
 		meta->meta.alloc_ctrs[b] += need_slots;
 
-	inode_set_iversion_raw(&vnode->vfs_inode, vnode->status.data_version);
+	inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version);
 	afs_stat_v(vnode, n_dir_rm);
 	_debug("Remove %s from %u[%u]", name->name, b, slot);
 
diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c
index 45cfd50a9521..bb5807e87fa4 100644
--- a/fs/afs/dir_silly.c
+++ b/fs/afs/dir_silly.c
@@ -131,7 +131,7 @@ int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode,
 			goto out;
 	} while (!d_is_negative(sdentry));
 
-	ihold(&vnode->vfs_inode);
+	ihold(&vnode->netfs.inode);
 
 	ret = afs_do_silly_rename(dvnode, vnode, dentry, sdentry, key);
 	switch (ret) {
@@ -148,7 +148,7 @@ int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode,
 		d_drop(sdentry);
 	}
 
-	iput(&vnode->vfs_inode);
+	iput(&vnode->netfs.inode);
 	dput(sdentry);
 out:
 	_leave(" = %d", ret);
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index f120bcb8bf73..3a5bbffdf053 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -76,7 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
 	/* there shouldn't be an existing inode */
 	BUG_ON(!(inode->i_state & I_NEW));
 
-	netfs_i_context_init(inode, NULL);
+	netfs_inode_init(inode, NULL);
 	inode->i_size		= 0;
 	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
 	if (root) {
diff --git a/fs/afs/file.c b/fs/afs/file.c
index a8e8832179e4..4de7af7c2f09 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -194,7 +194,7 @@ int afs_release(struct inode *inode, struct file *file)
 		afs_put_wb_key(af->wb);
 
 	if ((file->f_mode & FMODE_WRITE)) {
-		i_size = i_size_read(&vnode->vfs_inode);
+		i_size = i_size_read(&vnode->netfs.inode);
 		afs_set_cache_aux(vnode, &aux);
 		fscache_unuse_cookie(afs_vnode_cache(vnode), &aux, &i_size);
 	} else {
@@ -325,7 +325,7 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq)
 	fsreq->iter	= &fsreq->def_iter;
 
 	iov_iter_xarray(&fsreq->def_iter, READ,
-			&fsreq->vnode->vfs_inode.i_mapping->i_pages,
+			&fsreq->vnode->netfs.inode.i_mapping->i_pages,
 			fsreq->pos, fsreq->len);
 
 	afs_fetch_data(fsreq->vnode, fsreq);
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index d222dfbe976b..7a3803ce3a22 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -232,14 +232,14 @@ int afs_put_operation(struct afs_operation *op)
 	if (op->file[1].modification && op->file[1].vnode != op->file[0].vnode)
 		clear_bit(AFS_VNODE_MODIFYING, &op->file[1].vnode->flags);
 	if (op->file[0].put_vnode)
-		iput(&op->file[0].vnode->vfs_inode);
+		iput(&op->file[0].vnode->netfs.inode);
 	if (op->file[1].put_vnode)
-		iput(&op->file[1].vnode->vfs_inode);
+		iput(&op->file[1].vnode->netfs.inode);
 
 	if (op->more_files) {
 		for (i = 0; i < op->nr_files - 2; i++)
 			if (op->more_files[i].put_vnode)
-				iput(&op->more_files[i].vnode->vfs_inode);
+				iput(&op->more_files[i].vnode->netfs.inode);
 		kfree(op->more_files);
 	}
 
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 65b439cd53d2..22811e9eacf5 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -25,9 +25,6 @@
 #include "internal.h"
 #include "afs_fs.h"
 
-// Temporary: netfs does disgusting things with inode pointers
-#pragma GCC diagnostic ignored "-Wattribute-warning"
-
 static const struct inode_operations afs_symlink_inode_operations = {
 	.get_link	= page_get_link,
 };
@@ -61,7 +58,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
  */
 static void afs_set_netfs_context(struct afs_vnode *vnode)
 {
-	netfs_i_context_init(&vnode->vfs_inode, &afs_req_ops);
+	netfs_inode_init(&vnode->netfs.inode, &afs_req_ops);
 }
 
 /*
@@ -99,7 +96,7 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 	inode->i_flags |= S_NOATIME;
 	inode->i_uid = make_kuid(&init_user_ns, status->owner);
 	inode->i_gid = make_kgid(&init_user_ns, status->group);
-	set_nlink(&vnode->vfs_inode, status->nlink);
+	set_nlink(&vnode->netfs.inode, status->nlink);
 
 	switch (status->type) {
 	case AFS_FTYPE_FILE:
@@ -142,7 +139,7 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 	afs_set_netfs_context(vnode);
 
 	vnode->invalid_before	= status->data_version;
-	inode_set_iversion_raw(&vnode->vfs_inode, status->data_version);
+	inode_set_iversion_raw(&vnode->netfs.inode, status->data_version);
 
 	if (!vp->scb.have_cb) {
 		/* it's a symlink we just created (the fileserver
@@ -166,7 +163,7 @@ static void afs_apply_status(struct afs_operation *op,
 {
 	struct afs_file_status *status = &vp->scb.status;
 	struct afs_vnode *vnode = vp->vnode;
-	struct inode *inode = &vnode->vfs_inode;
+	struct inode *inode = &vnode->netfs.inode;
 	struct timespec64 t;
 	umode_t mode;
 	bool data_changed = false;
@@ -249,7 +246,7 @@ static void afs_apply_status(struct afs_operation *op,
 		 * idea of what the size should be that's not the same as
 		 * what's on the server.
 		 */
-		vnode->netfs_ctx.remote_i_size = status->size;
+		vnode->netfs.remote_i_size = status->size;
 		if (change_size) {
 			afs_set_i_size(vnode, status->size);
 			inode->i_ctime = t;
@@ -292,7 +289,7 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v
 		 */
 		if (vp->scb.status.abort_code == VNOVNODE) {
 			set_bit(AFS_VNODE_DELETED, &vnode->flags);
-			clear_nlink(&vnode->vfs_inode);
+			clear_nlink(&vnode->netfs.inode);
 			__afs_break_callback(vnode, afs_cb_break_for_deleted);
 			op->flags &= ~AFS_OPERATION_DIR_CONFLICT;
 		}
@@ -309,8 +306,8 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v
 		if (vp->scb.have_cb)
 			afs_apply_callback(op, vp);
 	} else if (vp->op_unlinked && !(op->flags & AFS_OPERATION_DIR_CONFLICT)) {
-		drop_nlink(&vnode->vfs_inode);
-		if (vnode->vfs_inode.i_nlink == 0) {
+		drop_nlink(&vnode->netfs.inode);
+		if (vnode->netfs.inode.i_nlink == 0) {
 			set_bit(AFS_VNODE_DELETED, &vnode->flags);
 			__afs_break_callback(vnode, afs_cb_break_for_deleted);
 		}
@@ -329,7 +326,7 @@ static void afs_fetch_status_success(struct afs_operation *op)
 	struct afs_vnode *vnode = vp->vnode;
 	int ret;
 
-	if (vnode->vfs_inode.i_state & I_NEW) {
+	if (vnode->netfs.inode.i_state & I_NEW) {
 		ret = afs_inode_init_from_status(op, vp, vnode);
 		op->error = ret;
 		if (ret == 0)
@@ -433,7 +430,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode)
 	struct afs_vnode_cache_aux aux;
 
 	if (vnode->status.type != AFS_FTYPE_FILE) {
-		vnode->netfs_ctx.cache = NULL;
+		vnode->netfs.cache = NULL;
 		return;
 	}
 
@@ -460,7 +457,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode)
 struct inode *afs_iget(struct afs_operation *op, struct afs_vnode_param *vp)
 {
 	struct afs_vnode_param *dvp = &op->file[0];
-	struct super_block *sb = dvp->vnode->vfs_inode.i_sb;
+	struct super_block *sb = dvp->vnode->netfs.inode.i_sb;
 	struct afs_vnode *vnode;
 	struct inode *inode;
 	int ret;
@@ -585,10 +582,10 @@ static void afs_zap_data(struct afs_vnode *vnode)
 	/* nuke all the non-dirty pages that aren't locked, mapped or being
 	 * written back in a regular file and completely discard the pages in a
 	 * directory or symlink */
-	if (S_ISREG(vnode->vfs_inode.i_mode))
-		invalidate_remote_inode(&vnode->vfs_inode);
+	if (S_ISREG(vnode->netfs.inode.i_mode))
+		invalidate_remote_inode(&vnode->netfs.inode);
 	else
-		invalidate_inode_pages2(vnode->vfs_inode.i_mapping);
+		invalidate_inode_pages2(vnode->netfs.inode.i_mapping);
 }
 
 /*
@@ -686,8 +683,8 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 	       key_serial(key));
 
 	if (unlikely(test_bit(AFS_VNODE_DELETED, &vnode->flags))) {
-		if (vnode->vfs_inode.i_nlink)
-			clear_nlink(&vnode->vfs_inode);
+		if (vnode->netfs.inode.i_nlink)
+			clear_nlink(&vnode->netfs.inode);
 		goto valid;
 	}
 
@@ -829,7 +826,7 @@ void afs_evict_inode(struct inode *inode)
 static void afs_setattr_success(struct afs_operation *op)
 {
 	struct afs_vnode_param *vp = &op->file[0];
-	struct inode *inode = &vp->vnode->vfs_inode;
+	struct inode *inode = &vp->vnode->netfs.inode;
 	loff_t old_i_size = i_size_read(inode);
 
 	op->setattr.old_i_size = old_i_size;
@@ -846,7 +843,7 @@ static void afs_setattr_success(struct afs_operation *op)
 static void afs_setattr_edit_file(struct afs_operation *op)
 {
 	struct afs_vnode_param *vp = &op->file[0];
-	struct inode *inode = &vp->vnode->vfs_inode;
+	struct inode *inode = &vp->vnode->netfs.inode;
 
 	if (op->setattr.attr->ia_valid & ATTR_SIZE) {
 		loff_t size = op->setattr.attr->ia_size;
@@ -878,7 +875,7 @@ int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET | ATTR_TOUCH;
 	struct afs_operation *op;
 	struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
-	struct inode *inode = &vnode->vfs_inode;
+	struct inode *inode = &vnode->netfs.inode;
 	loff_t i_size;
 	int ret;
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index a30995901266..984b113a9107 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -619,12 +619,7 @@ enum afs_lock_state {
  * leak from one inode to another.
  */
 struct afs_vnode {
-	struct {
-		/* These must be contiguous */
-		struct inode	vfs_inode;	/* the VFS's inode record */
-		struct netfs_i_context netfs_ctx; /* Netfslib context */
-	};
-
+	struct netfs_inode	netfs;		/* Netfslib context and vfs inode */
 	struct afs_volume	*volume;	/* volume on which vnode resides */
 	struct afs_fid		fid;		/* the file identifier for this inode */
 	struct afs_file_status	status;		/* AFS status info for this file */
@@ -675,7 +670,7 @@ struct afs_vnode {
 static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode)
 {
 #ifdef CONFIG_AFS_FSCACHE
-	return netfs_i_cookie(&vnode->vfs_inode);
+	return netfs_i_cookie(&vnode->netfs.inode);
 #else
 	return NULL;
 #endif
@@ -685,7 +680,7 @@ static inline void afs_vnode_set_cache(struct afs_vnode *vnode,
 				       struct fscache_cookie *cookie)
 {
 #ifdef CONFIG_AFS_FSCACHE
-	vnode->netfs_ctx.cache = cookie;
+	vnode->netfs.cache = cookie;
 #endif
 }
 
@@ -892,7 +887,7 @@ static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int fl
 
 	afs_set_cache_aux(vnode, &aux);
 	fscache_invalidate(afs_vnode_cache(vnode), &aux,
-			   i_size_read(&vnode->vfs_inode), flags);
+			   i_size_read(&vnode->netfs.inode), flags);
 }
 
 /*
@@ -1217,7 +1212,7 @@ static inline struct afs_net *afs_i2net(struct inode *inode)
 
 static inline struct afs_net *afs_v2net(struct afs_vnode *vnode)
 {
-	return afs_i2net(&vnode->vfs_inode);
+	return afs_i2net(&vnode->netfs.inode);
 }
 
 static inline struct afs_net *afs_sock2net(struct sock *sk)
@@ -1593,12 +1588,12 @@ extern void yfs_fs_store_opaque_acl2(struct afs_operation *);
  */
 static inline struct afs_vnode *AFS_FS_I(struct inode *inode)
 {
-	return container_of(inode, struct afs_vnode, vfs_inode);
+	return container_of(inode, struct afs_vnode, netfs.inode);
 }
 
 static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode)
 {
-	return &vnode->vfs_inode;
+	return &vnode->netfs.inode;
 }
 
 /*
@@ -1621,8 +1616,8 @@ static inline void afs_update_dentry_version(struct afs_operation *op,
  */
 static inline void afs_set_i_size(struct afs_vnode *vnode, u64 size)
 {
-	i_size_write(&vnode->vfs_inode, size);
-	vnode->vfs_inode.i_blocks = ((size + 1023) >> 10) << 1;
+	i_size_write(&vnode->netfs.inode, size);
+	vnode->netfs.inode.i_blocks = ((size + 1023) >> 10) << 1;
 }
 
 /*
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 1fea195b0b27..95d713074dc8 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -659,7 +659,7 @@ static void afs_i_init_once(void *_vnode)
 	struct afs_vnode *vnode = _vnode;
 
 	memset(vnode, 0, sizeof(*vnode));
-	inode_init_once(&vnode->vfs_inode);
+	inode_init_once(&vnode->netfs.inode);
 	mutex_init(&vnode->io_lock);
 	init_rwsem(&vnode->validate_lock);
 	spin_lock_init(&vnode->wb_lock);
@@ -700,8 +700,8 @@ static struct inode *afs_alloc_inode(struct super_block *sb)
 	init_rwsem(&vnode->rmdir_lock);
 	INIT_WORK(&vnode->cb_work, afs_invalidate_mmap_work);
 
-	_leave(" = %p", &vnode->vfs_inode);
-	return &vnode->vfs_inode;
+	_leave(" = %p", &vnode->netfs.inode);
+	return &vnode->netfs.inode;
 }
 
 static void afs_free_inode(struct inode *inode)
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 2236b2165e37..f80a6096d91c 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -146,10 +146,10 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 
 	write_end_pos = pos + copied;
 
-	i_size = i_size_read(&vnode->vfs_inode);
+	i_size = i_size_read(&vnode->netfs.inode);
 	if (write_end_pos > i_size) {
 		write_seqlock(&vnode->cb_lock);
-		i_size = i_size_read(&vnode->vfs_inode);
+		i_size = i_size_read(&vnode->netfs.inode);
 		if (write_end_pos > i_size)
 			afs_set_i_size(vnode, write_end_pos);
 		write_sequnlock(&vnode->cb_lock);
@@ -257,7 +257,7 @@ static void afs_redirty_pages(struct writeback_control *wbc,
  */
 static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len)
 {
-	struct address_space *mapping = vnode->vfs_inode.i_mapping;
+	struct address_space *mapping = vnode->netfs.inode.i_mapping;
 	struct folio *folio;
 	pgoff_t end;
 
@@ -354,7 +354,6 @@ static const struct afs_operation_ops afs_store_data_operation = {
 static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t pos,
 			  bool laundering)
 {
-	struct netfs_i_context *ictx = &vnode->netfs_ctx;
 	struct afs_operation *op;
 	struct afs_wb_key *wbk = NULL;
 	loff_t size = iov_iter_count(iter);
@@ -385,9 +384,9 @@ static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t
 	op->store.write_iter = iter;
 	op->store.pos = pos;
 	op->store.size = size;
-	op->store.i_size = max(pos + size, ictx->remote_i_size);
+	op->store.i_size = max(pos + size, vnode->netfs.remote_i_size);
 	op->store.laundering = laundering;
-	op->mtime = vnode->vfs_inode.i_mtime;
+	op->mtime = vnode->netfs.inode.i_mtime;
 	op->flags |= AFS_OPERATION_UNINTR;
 	op->ops = &afs_store_data_operation;
 
@@ -554,7 +553,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 	struct iov_iter iter;
 	unsigned long priv;
 	unsigned int offset, to, len, max_len;
-	loff_t i_size = i_size_read(&vnode->vfs_inode);
+	loff_t i_size = i_size_read(&vnode->netfs.inode);
 	bool new_content = test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
 	bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode));
 	long count = wbc->nr_to_write;
@@ -845,7 +844,7 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	_enter("{%llx:%llu},{%zu},",
 	       vnode->fid.vid, vnode->fid.vnode, count);
 
-	if (IS_SWAPFILE(&vnode->vfs_inode)) {
+	if (IS_SWAPFILE(&vnode->netfs.inode)) {
 		printk(KERN_INFO
 		       "AFS: Attempt to write to active swap file!\n");
 		return -EBUSY;
@@ -958,8 +957,8 @@ void afs_prune_wb_keys(struct afs_vnode *vnode)
 	/* Discard unused keys */
 	spin_lock(&vnode->wb_lock);
 
-	if (!mapping_tagged(&vnode->vfs_inode.i_data, PAGECACHE_TAG_WRITEBACK) &&
-	    !mapping_tagged(&vnode->vfs_inode.i_data, PAGECACHE_TAG_DIRTY)) {
+	if (!mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_WRITEBACK) &&
+	    !mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_DIRTY)) {
 		list_for_each_entry_safe(wbk, tmp, &vnode->wb_keys, vnode_link) {
 			if (refcount_read(&wbk->usage) == 1)
 				list_move(&wbk->vnode_link, &graveyard);
@@ -1034,6 +1033,6 @@ static void afs_write_to_cache(struct afs_vnode *vnode,
 			       bool caching)
 {
 	fscache_write_to_cache(afs_vnode_cache(vnode),
-			       vnode->vfs_inode.i_mapping, start, len, i_size,
+			       vnode->netfs.inode.i_mapping, start, len, i_size,
 			       afs_write_to_cache_done, vnode, caching);
 }
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e5221be6eb55..f5f116ed1b9e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1798,7 +1798,7 @@ enum {
 static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 				s64 pool, struct ceph_string *pool_ns)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->netfs.inode);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_osd_request *rd_req = NULL, *wr_req = NULL;
 	struct rb_node **p, *parent;
@@ -1913,7 +1913,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 				     0, false, true);
 	err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
 
-	wr_req->r_mtime = ci->vfs_inode.i_mtime;
+	wr_req->r_mtime = ci->netfs.inode.i_mtime;
 	err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
 
 	if (!err)
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index ddea99922073..177d8e8d73fe 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -29,9 +29,9 @@ void ceph_fscache_register_inode_cookie(struct inode *inode)
 	if (!(inode->i_state & I_NEW))
 		return;
 
-	WARN_ON_ONCE(ci->netfs_ctx.cache);
+	WARN_ON_ONCE(ci->netfs.cache);
 
-	ci->netfs_ctx.cache =
+	ci->netfs.cache =
 		fscache_acquire_cookie(fsc->fscache, 0,
 				       &ci->i_vino, sizeof(ci->i_vino),
 				       &ci->i_version, sizeof(ci->i_version),
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 7255b790a4c1..26c6ae06e2f4 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -28,7 +28,7 @@ void ceph_fscache_invalidate(struct inode *inode, bool dio_write);
 
 static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci)
 {
-	return netfs_i_cookie(&ci->vfs_inode);
+	return netfs_i_cookie(&ci->netfs.inode);
 }
 
 static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index bf2e94005598..38c930384d41 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -492,7 +492,7 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
 	struct ceph_mount_options *opt = mdsc->fsc->mount_options;
 	ci->i_hold_caps_max = round_jiffies(jiffies +
 					    opt->caps_wanted_delay_max * HZ);
-	dout("__cap_set_timeouts %p %lu\n", &ci->vfs_inode,
+	dout("__cap_set_timeouts %p %lu\n", &ci->netfs.inode,
 	     ci->i_hold_caps_max - jiffies);
 }
 
@@ -507,7 +507,7 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
 static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
 				struct ceph_inode_info *ci)
 {
-	dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->vfs_inode,
+	dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->netfs.inode,
 	     ci->i_ceph_flags, ci->i_hold_caps_max);
 	if (!mdsc->stopping) {
 		spin_lock(&mdsc->cap_delay_lock);
@@ -531,7 +531,7 @@ no_change:
 static void __cap_delay_requeue_front(struct ceph_mds_client *mdsc,
 				      struct ceph_inode_info *ci)
 {
-	dout("__cap_delay_requeue_front %p\n", &ci->vfs_inode);
+	dout("__cap_delay_requeue_front %p\n", &ci->netfs.inode);
 	spin_lock(&mdsc->cap_delay_lock);
 	ci->i_ceph_flags |= CEPH_I_FLUSH;
 	if (!list_empty(&ci->i_cap_delay_list))
@@ -548,7 +548,7 @@ static void __cap_delay_requeue_front(struct ceph_mds_client *mdsc,
 static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
 			       struct ceph_inode_info *ci)
 {
-	dout("__cap_delay_cancel %p\n", &ci->vfs_inode);
+	dout("__cap_delay_cancel %p\n", &ci->netfs.inode);
 	if (list_empty(&ci->i_cap_delay_list))
 		return;
 	spin_lock(&mdsc->cap_delay_lock);
@@ -568,7 +568,7 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
 	 * Each time we receive FILE_CACHE anew, we increment
 	 * i_rdcache_gen.
 	 */
-	if (S_ISREG(ci->vfs_inode.i_mode) &&
+	if (S_ISREG(ci->netfs.inode.i_mode) &&
 	    (issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
 	    (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) {
 		ci->i_rdcache_gen++;
@@ -583,14 +583,14 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
 	if ((issued & CEPH_CAP_FILE_SHARED) != (had & CEPH_CAP_FILE_SHARED)) {
 		if (issued & CEPH_CAP_FILE_SHARED)
 			atomic_inc(&ci->i_shared_gen);
-		if (S_ISDIR(ci->vfs_inode.i_mode)) {
-			dout(" marking %p NOT complete\n", &ci->vfs_inode);
+		if (S_ISDIR(ci->netfs.inode.i_mode)) {
+			dout(" marking %p NOT complete\n", &ci->netfs.inode);
 			__ceph_dir_clear_complete(ci);
 		}
 	}
 
 	/* Wipe saved layout if we're losing DIR_CREATE caps */
-	if (S_ISDIR(ci->vfs_inode.i_mode) && (had & CEPH_CAP_DIR_CREATE) &&
+	if (S_ISDIR(ci->netfs.inode.i_mode) && (had & CEPH_CAP_DIR_CREATE) &&
 		!(issued & CEPH_CAP_DIR_CREATE)) {
 	     ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns));
 	     memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
@@ -771,7 +771,7 @@ static int __cap_is_valid(struct ceph_cap *cap)
 
 	if (cap->cap_gen < gen || time_after_eq(jiffies, ttl)) {
 		dout("__cap_is_valid %p cap %p issued %s "
-		     "but STALE (gen %u vs %u)\n", &cap->ci->vfs_inode,
+		     "but STALE (gen %u vs %u)\n", &cap->ci->netfs.inode,
 		     cap, ceph_cap_string(cap->issued), cap->cap_gen, gen);
 		return 0;
 	}
@@ -797,7 +797,7 @@ int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
 		if (!__cap_is_valid(cap))
 			continue;
 		dout("__ceph_caps_issued %p cap %p issued %s\n",
-		     &ci->vfs_inode, cap, ceph_cap_string(cap->issued));
+		     &ci->netfs.inode, cap, ceph_cap_string(cap->issued));
 		have |= cap->issued;
 		if (implemented)
 			*implemented |= cap->implemented;
@@ -844,12 +844,12 @@ static void __touch_cap(struct ceph_cap *cap)
 
 	spin_lock(&s->s_cap_lock);
 	if (!s->s_cap_iterator) {
-		dout("__touch_cap %p cap %p mds%d\n", &cap->ci->vfs_inode, cap,
+		dout("__touch_cap %p cap %p mds%d\n", &cap->ci->netfs.inode, cap,
 		     s->s_mds);
 		list_move_tail(&cap->session_caps, &s->s_caps);
 	} else {
 		dout("__touch_cap %p cap %p mds%d NOP, iterating over caps\n",
-		     &cap->ci->vfs_inode, cap, s->s_mds);
+		     &cap->ci->netfs.inode, cap, s->s_mds);
 	}
 	spin_unlock(&s->s_cap_lock);
 }
@@ -867,7 +867,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 
 	if ((have & mask) == mask) {
 		dout("__ceph_caps_issued_mask ino 0x%llx snap issued %s"
-		     " (mask %s)\n", ceph_ino(&ci->vfs_inode),
+		     " (mask %s)\n", ceph_ino(&ci->netfs.inode),
 		     ceph_cap_string(have),
 		     ceph_cap_string(mask));
 		return 1;
@@ -879,7 +879,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 			continue;
 		if ((cap->issued & mask) == mask) {
 			dout("__ceph_caps_issued_mask ino 0x%llx cap %p issued %s"
-			     " (mask %s)\n", ceph_ino(&ci->vfs_inode), cap,
+			     " (mask %s)\n", ceph_ino(&ci->netfs.inode), cap,
 			     ceph_cap_string(cap->issued),
 			     ceph_cap_string(mask));
 			if (touch)
@@ -891,7 +891,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 		have |= cap->issued;
 		if ((have & mask) == mask) {
 			dout("__ceph_caps_issued_mask ino 0x%llx combo issued %s"
-			     " (mask %s)\n", ceph_ino(&ci->vfs_inode),
+			     " (mask %s)\n", ceph_ino(&ci->netfs.inode),
 			     ceph_cap_string(cap->issued),
 			     ceph_cap_string(mask));
 			if (touch) {
@@ -919,7 +919,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 int __ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, int mask,
 				   int touch)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
 	int r;
 
 	r = __ceph_caps_issued_mask(ci, mask, touch);
@@ -950,7 +950,7 @@ int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
 
 int ceph_caps_revoking(struct ceph_inode_info *ci, int mask)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	int ret;
 
 	spin_lock(&ci->i_ceph_lock);
@@ -969,8 +969,8 @@ int __ceph_caps_used(struct ceph_inode_info *ci)
 	if (ci->i_rd_ref)
 		used |= CEPH_CAP_FILE_RD;
 	if (ci->i_rdcache_ref ||
-	    (S_ISREG(ci->vfs_inode.i_mode) &&
-	     ci->vfs_inode.i_data.nrpages))
+	    (S_ISREG(ci->netfs.inode.i_mode) &&
+	     ci->netfs.inode.i_data.nrpages))
 		used |= CEPH_CAP_FILE_CACHE;
 	if (ci->i_wr_ref)
 		used |= CEPH_CAP_FILE_WR;
@@ -993,11 +993,11 @@ int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
 	const int WR_SHIFT = ffs(CEPH_FILE_MODE_WR);
 	const int LAZY_SHIFT = ffs(CEPH_FILE_MODE_LAZY);
 	struct ceph_mount_options *opt =
-		ceph_inode_to_client(&ci->vfs_inode)->mount_options;
+		ceph_inode_to_client(&ci->netfs.inode)->mount_options;
 	unsigned long used_cutoff = jiffies - opt->caps_wanted_delay_max * HZ;
 	unsigned long idle_cutoff = jiffies - opt->caps_wanted_delay_min * HZ;
 
-	if (S_ISDIR(ci->vfs_inode.i_mode)) {
+	if (S_ISDIR(ci->netfs.inode.i_mode)) {
 		int want = 0;
 
 		/* use used_cutoff here, to keep dir's wanted caps longer */
@@ -1050,7 +1050,7 @@ int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
 int __ceph_caps_wanted(struct ceph_inode_info *ci)
 {
 	int w = __ceph_caps_file_wanted(ci) | __ceph_caps_used(ci);
-	if (S_ISDIR(ci->vfs_inode.i_mode)) {
+	if (S_ISDIR(ci->netfs.inode.i_mode)) {
 		/* we want EXCL if holding caps of dir ops */
 		if (w & CEPH_CAP_ANY_DIR_OPS)
 			w |= CEPH_CAP_FILE_EXCL;
@@ -1116,9 +1116,9 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
+	dout("__ceph_remove_cap %p from %p\n", cap, &ci->netfs.inode);
 
-	mdsc = ceph_inode_to_client(&ci->vfs_inode)->mdsc;
+	mdsc = ceph_inode_to_client(&ci->netfs.inode)->mdsc;
 
 	/* remove from inode's cap rbtree, and clear auth cap */
 	rb_erase(&cap->ci_node, &ci->i_caps);
@@ -1169,7 +1169,7 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 		 * keep i_snap_realm.
 		 */
 		if (ci->i_wr_ref == 0 && ci->i_snap_realm)
-			ceph_change_snap_realm(&ci->vfs_inode, NULL);
+			ceph_change_snap_realm(&ci->netfs.inode, NULL);
 
 		__cap_delay_cancel(mdsc, ci);
 	}
@@ -1188,11 +1188,11 @@ void ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	fsc = ceph_inode_to_client(&ci->vfs_inode);
+	fsc = ceph_inode_to_client(&ci->netfs.inode);
 	WARN_ON_ONCE(ci->i_auth_cap == cap &&
 		     !list_empty(&ci->i_dirty_item) &&
 		     !fsc->blocklisted &&
-		     !ceph_inode_is_shutdown(&ci->vfs_inode));
+		     !ceph_inode_is_shutdown(&ci->netfs.inode));
 
 	__ceph_remove_cap(cap, queue_release);
 }
@@ -1343,7 +1343,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 		       int flushing, u64 flush_tid, u64 oldest_flush_tid)
 {
 	struct ceph_inode_info *ci = cap->ci;
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	int held, revoking;
 
 	lockdep_assert_held(&ci->i_ceph_lock);
@@ -1440,7 +1440,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
 {
 	struct ceph_msg *msg;
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, CAP_MSG_SIZE, GFP_NOFS, false);
 	if (!msg) {
@@ -1528,7 +1528,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 		__releases(ci->i_ceph_lock)
 		__acquires(ci->i_ceph_lock)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mds_client *mdsc = session->s_mdsc;
 	struct ceph_cap_snap *capsnap;
 	u64 oldest_flush_tid = 0;
@@ -1622,7 +1622,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 void ceph_flush_snaps(struct ceph_inode_info *ci,
 		      struct ceph_mds_session **psession)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_mds_session *session = NULL;
 	int mds;
@@ -1682,8 +1682,8 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
 			   struct ceph_cap_flush **pcf)
 {
 	struct ceph_mds_client *mdsc =
-		ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
-	struct inode *inode = &ci->vfs_inode;
+		ceph_sb_to_client(ci->netfs.inode.i_sb)->mdsc;
+	struct inode *inode = &ci->netfs.inode;
 	int was = ci->i_dirty_caps;
 	int dirty = 0;
 
@@ -1696,7 +1696,7 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
 		return 0;
 	}
 
-	dout("__mark_dirty_caps %p %s dirty %s -> %s\n", &ci->vfs_inode,
+	dout("__mark_dirty_caps %p %s dirty %s -> %s\n", &ci->netfs.inode,
 	     ceph_cap_string(mask), ceph_cap_string(was),
 	     ceph_cap_string(was | mask));
 	ci->i_dirty_caps |= mask;
@@ -1712,7 +1712,7 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
 				ci->i_snap_realm->cached_context);
 		}
 		dout(" inode %p now dirty snapc %p auth cap %p\n",
-		     &ci->vfs_inode, ci->i_head_snapc, ci->i_auth_cap);
+		     &ci->netfs.inode, ci->i_head_snapc, ci->i_auth_cap);
 		BUG_ON(!list_empty(&ci->i_dirty_item));
 		spin_lock(&mdsc->cap_dirty_lock);
 		list_add(&ci->i_dirty_item, &session->s_cap_dirty);
@@ -1875,7 +1875,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
 
 bool __ceph_should_report_size(struct ceph_inode_info *ci)
 {
-	loff_t size = i_size_read(&ci->vfs_inode);
+	loff_t size = i_size_read(&ci->netfs.inode);
 	/* mds will adjust max size according to the reported size */
 	if (ci->i_flushing_caps & CEPH_CAP_FILE_WR)
 		return false;
@@ -1900,7 +1900,7 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci)
 void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 		     struct ceph_mds_session *session)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 	struct ceph_cap *cap;
 	u64 flush_tid, oldest_flush_tid;
@@ -2467,7 +2467,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 	__releases(ci->i_ceph_lock)
 	__acquires(ci->i_ceph_lock)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_cap *cap;
 	struct ceph_cap_flush *cf;
 	int ret;
@@ -2560,7 +2560,7 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 		cap = ci->i_auth_cap;
 		if (!(cap && cap->session == session)) {
 			pr_err("%p auth cap %p not mds%d ???\n",
-				&ci->vfs_inode, cap, session->s_mds);
+				&ci->netfs.inode, cap, session->s_mds);
 			spin_unlock(&ci->i_ceph_lock);
 			continue;
 		}
@@ -2610,7 +2610,7 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 		cap = ci->i_auth_cap;
 		if (!(cap && cap->session == session)) {
 			pr_err("%p auth cap %p not mds%d ???\n",
-				&ci->vfs_inode, cap, session->s_mds);
+				&ci->netfs.inode, cap, session->s_mds);
 			spin_unlock(&ci->i_ceph_lock);
 			continue;
 		}
@@ -2630,7 +2630,7 @@ void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session,
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	dout("%s %p flushing %s\n", __func__, &ci->vfs_inode,
+	dout("%s %p flushing %s\n", __func__, &ci->netfs.inode,
 	     ceph_cap_string(ci->i_flushing_caps));
 
 	if (!list_empty(&ci->i_cap_flush_list)) {
@@ -2673,10 +2673,10 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got,
 	}
 	if (got & CEPH_CAP_FILE_BUFFER) {
 		if (ci->i_wb_ref == 0)
-			ihold(&ci->vfs_inode);
+			ihold(&ci->netfs.inode);
 		ci->i_wb_ref++;
 		dout("%s %p wb %d -> %d (?)\n", __func__,
-		     &ci->vfs_inode, ci->i_wb_ref-1, ci->i_wb_ref);
+		     &ci->netfs.inode, ci->i_wb_ref-1, ci->i_wb_ref);
 	}
 }
 
@@ -3004,7 +3004,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 			return ret;
 		}
 
-		if (S_ISREG(ci->vfs_inode.i_mode) &&
+		if (S_ISREG(ci->netfs.inode.i_mode) &&
 		    ci->i_inline_version != CEPH_INLINE_NONE &&
 		    (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
 		    i_size_read(inode) > 0) {
@@ -3094,7 +3094,7 @@ enum put_cap_refs_mode {
 static void __ceph_put_cap_refs(struct ceph_inode_info *ci, int had,
 				enum put_cap_refs_mode mode)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	int last = 0, put = 0, flushsnaps = 0, wake = 0;
 	bool check_flushsnaps = false;
 
@@ -3202,7 +3202,7 @@ void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, int had)
 void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				struct ceph_snap_context *snapc)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_cap_snap *capsnap = NULL, *iter;
 	int put = 0;
 	bool last = false;
@@ -3698,7 +3698,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 				     session->s_mds,
 				     &list_first_entry(&session->s_cap_flushing,
 						struct ceph_inode_info,
-						i_flushing_item)->vfs_inode);
+						i_flushing_item)->netfs.inode);
 			}
 		}
 		mdsc->num_cap_flushing--;
@@ -4345,7 +4345,7 @@ unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 			break;
 		list_del_init(&ci->i_cap_delay_list);
 
-		inode = igrab(&ci->vfs_inode);
+		inode = igrab(&ci->netfs.inode);
 		if (inode) {
 			spin_unlock(&mdsc->cap_delay_lock);
 			dout("check_delayed_caps on %p\n", inode);
@@ -4373,7 +4373,7 @@ static void flush_dirty_session_caps(struct ceph_mds_session *s)
 	while (!list_empty(&s->s_cap_dirty)) {
 		ci = list_first_entry(&s->s_cap_dirty, struct ceph_inode_info,
 				      i_dirty_item);
-		inode = &ci->vfs_inode;
+		inode = &ci->netfs.inode;
 		ihold(inode);
 		dout("flush_dirty_caps %llx.%llx\n", ceph_vinop(inode));
 		spin_unlock(&mdsc->cap_dirty_lock);
@@ -4407,7 +4407,7 @@ void __ceph_touch_fmode(struct ceph_inode_info *ci,
 
 void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
 {
-	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb);
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->netfs.inode.i_sb);
 	int bits = (fmode << 1) | 1;
 	bool already_opened = false;
 	int i;
@@ -4441,7 +4441,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
  */
 void ceph_put_fmode(struct ceph_inode_info *ci, int fmode, int count)
 {
-	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb);
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->netfs.inode.i_sb);
 	int bits = (fmode << 1) | 1;
 	bool is_closed = true;
 	int i;
@@ -4656,7 +4656,7 @@ int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invali
 	lockdep_assert_held(&ci->i_ceph_lock);
 
 	dout("removing cap %p, ci is %p, inode is %p\n",
-	     cap, ci, &ci->vfs_inode);
+	     cap, ci, &ci->netfs.inode);
 
 	is_auth = (cap == ci->i_auth_cap);
 	__ceph_remove_cap(cap, false);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 8c8226c0feac..da59e836a06e 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -205,7 +205,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mount_options *opt =
-		ceph_inode_to_client(&ci->vfs_inode)->mount_options;
+		ceph_inode_to_client(&ci->netfs.inode)->mount_options;
 	struct ceph_file_info *fi;
 	int ret;
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 5f1cc2b4ed06..650746b3ba99 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -20,9 +20,6 @@
 #include "cache.h"
 #include <linux/ceph/decode.h>
 
-// Temporary: netfs does disgusting things with inode pointers
-#pragma GCC diagnostic ignored "-Wattribute-warning"
-
 /*
  * Ceph inode operations
  *
@@ -179,7 +176,7 @@ static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci,
 	rb_insert_color(&frag->node, &ci->i_fragtree);
 
 	dout("get_or_create_frag added %llx.%llx frag %x\n",
-	     ceph_vinop(&ci->vfs_inode), f);
+	     ceph_vinop(&ci->netfs.inode), f);
 	return frag;
 }
 
@@ -460,10 +457,10 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	if (!ci)
 		return NULL;
 
-	dout("alloc_inode %p\n", &ci->vfs_inode);
+	dout("alloc_inode %p\n", &ci->netfs.inode);
 
 	/* Set parameters for the netfs library */
-	netfs_i_context_init(&ci->vfs_inode, &ceph_netfs_ops);
+	netfs_inode_init(&ci->netfs.inode, &ceph_netfs_ops);
 
 	spin_lock_init(&ci->i_ceph_lock);
 
@@ -550,7 +547,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	INIT_WORK(&ci->i_work, ceph_inode_work);
 	ci->i_work_mask = 0;
 	memset(&ci->i_btime, '\0', sizeof(ci->i_btime));
-	return &ci->vfs_inode;
+	return &ci->netfs.inode;
 }
 
 void ceph_free_inode(struct inode *inode)
@@ -1981,7 +1978,7 @@ static void ceph_inode_work(struct work_struct *work)
 {
 	struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
 						 i_work);
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 
 	if (test_and_clear_bit(CEPH_I_WORK_WRITEBACK, &ci->i_work_mask)) {
 		dout("writeback %p\n", inode);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f5d110d90b77..33f517d549ce 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1564,7 +1564,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session,
 	p = session->s_caps.next;
 	while (p != &session->s_caps) {
 		cap = list_entry(p, struct ceph_cap, session_caps);
-		inode = igrab(&cap->ci->vfs_inode);
+		inode = igrab(&cap->ci->netfs.inode);
 		if (!inode) {
 			p = p->next;
 			continue;
@@ -1622,7 +1622,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	int iputs;
 
 	dout("removing cap %p, ci is %p, inode is %p\n",
-	     cap, ci, &ci->vfs_inode);
+	     cap, ci, &ci->netfs.inode);
 	spin_lock(&ci->i_ceph_lock);
 	iputs = ceph_purge_inode_cap(inode, cap, &invalidate);
 	spin_unlock(&ci->i_ceph_lock);
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 322ee5add942..864cdaa0d2bd 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -521,7 +521,7 @@ static bool has_new_snaps(struct ceph_snap_context *o,
 static void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 				struct ceph_cap_snap **pcapsnap)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_snap_context *old_snapc, *new_snapc;
 	struct ceph_cap_snap *capsnap = *pcapsnap;
 	struct ceph_buffer *old_blob = NULL;
@@ -652,7 +652,7 @@ update_snapc:
 int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 			    struct ceph_cap_snap *capsnap)
 {
-	struct inode *inode = &ci->vfs_inode;
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 
 	BUG_ON(capsnap->writing);
@@ -712,7 +712,7 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
 
 	spin_lock(&realm->inodes_with_caps_lock);
 	list_for_each_entry(ci, &realm->inodes_with_caps, i_snap_realm_item) {
-		struct inode *inode = igrab(&ci->vfs_inode);
+		struct inode *inode = igrab(&ci->netfs.inode);
 		if (!inode)
 			continue;
 		spin_unlock(&realm->inodes_with_caps_lock);
@@ -904,7 +904,7 @@ static void flush_snaps(struct ceph_mds_client *mdsc)
 	while (!list_empty(&mdsc->snap_flush_list)) {
 		ci = list_first_entry(&mdsc->snap_flush_list,
 				struct ceph_inode_info, i_snap_flush_item);
-		inode = &ci->vfs_inode;
+		inode = &ci->netfs.inode;
 		ihold(inode);
 		spin_unlock(&mdsc->snap_flush_lock);
 		ceph_flush_snaps(ci, &session);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index b73b4f75462c..40140805bdcf 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -876,7 +876,7 @@ mempool_t *ceph_wb_pagevec_pool;
 static void ceph_inode_init_once(void *foo)
 {
 	struct ceph_inode_info *ci = foo;
-	inode_init_once(&ci->vfs_inode);
+	inode_init_once(&ci->netfs.inode);
 }
 
 static int __init init_caches(void)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index dd7dac0f984a..f59dac66955b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -316,11 +316,7 @@ struct ceph_inode_xattrs_info {
  * Ceph inode.
  */
 struct ceph_inode_info {
-	struct {
-		/* These must be contiguous */
-		struct inode vfs_inode;
-		struct netfs_i_context netfs_ctx; /* Netfslib context */
-	};
+	struct netfs_inode netfs; /* Netfslib context and vfs inode */
 	struct ceph_vino i_vino;   /* ceph ino + snap */
 
 	spinlock_t i_ceph_lock;
@@ -436,7 +432,7 @@ struct ceph_inode_info {
 static inline struct ceph_inode_info *
 ceph_inode(const struct inode *inode)
 {
-	return container_of(inode, struct ceph_inode_info, vfs_inode);
+	return container_of(inode, struct ceph_inode_info, netfs.inode);
 }
 
 static inline struct ceph_fs_client *
@@ -1316,7 +1312,7 @@ static inline void __ceph_update_quota(struct ceph_inode_info *ci,
 	has_quota = __ceph_has_quota(ci, QUOTA_GET_ANY);
 
 	if (had_quota != has_quota)
-		ceph_adjust_quota_realms_count(&ci->vfs_inode, has_quota);
+		ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota);
 }
 
 extern void ceph_handle_quota(struct ceph_mds_client *mdsc,
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 8c2dc2c762a4..f141f5246163 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -57,7 +57,7 @@ static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
 static ssize_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 				    size_t size)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_string *pool_ns;
 	s64 pool = ci->i_layout.pool_id;
@@ -69,7 +69,7 @@ static ssize_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 
 	pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
 
-	dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
+	dout("ceph_vxattrcb_layout %p\n", &ci->netfs.inode);
 	down_read(&osdc->lock);
 	pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
 	if (pool_name) {
@@ -161,7 +161,7 @@ static ssize_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
 					 char *val, size_t size)
 {
 	ssize_t ret;
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	s64 pool = ci->i_layout.pool_id;
 	const char *pool_name;
@@ -313,7 +313,7 @@ static ssize_t ceph_vxattrcb_snap_btime(struct ceph_inode_info *ci, char *val,
 static ssize_t ceph_vxattrcb_cluster_fsid(struct ceph_inode_info *ci,
 					  char *val, size_t size)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
 
 	return ceph_fmt_xattr(val, size, "%pU", &fsc->client->fsid);
 }
@@ -321,7 +321,7 @@ static ssize_t ceph_vxattrcb_cluster_fsid(struct ceph_inode_info *ci,
 static ssize_t ceph_vxattrcb_client_id(struct ceph_inode_info *ci,
 				       char *val, size_t size)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
 
 	return ceph_fmt_xattr(val, size, "client%lld",
 			      ceph_client_gid(fsc->client));
@@ -629,7 +629,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
 	}
 
 	dout("__set_xattr_val added %llx.%llx xattr %p %.*s=%.*s\n",
-	     ceph_vinop(&ci->vfs_inode), xattr, name_len, name, val_len, val);
+	     ceph_vinop(&ci->netfs.inode), xattr, name_len, name, val_len, val);
 
 	return 0;
 }
@@ -871,7 +871,7 @@ struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 	struct ceph_buffer *old_blob = NULL;
 	void *dest;
 
-	dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
+	dout("__build_xattrs_blob %p\n", &ci->netfs.inode);
 	if (ci->i_xattrs.dirty) {
 		int need = __get_required_blob_size(ci, 0, 0);
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 12c872800326..c85d9a378325 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -377,7 +377,7 @@ cifs_alloc_inode(struct super_block *sb)
 	cifs_inode->flags = 0;
 	spin_lock_init(&cifs_inode->writers_lock);
 	cifs_inode->writers = 0;
-	cifs_inode->vfs_inode.i_blkbits = 14;  /* 2**14 = CIFS_MAX_MSGSIZE */
+	cifs_inode->netfs.inode.i_blkbits = 14;  /* 2**14 = CIFS_MAX_MSGSIZE */
 	cifs_inode->server_eof = 0;
 	cifs_inode->uniqueid = 0;
 	cifs_inode->createtime = 0;
@@ -389,12 +389,12 @@ cifs_alloc_inode(struct super_block *sb)
 	 * Can not set i_flags here - they get immediately overwritten to zero
 	 * by the VFS.
 	 */
-	/* cifs_inode->vfs_inode.i_flags = S_NOATIME | S_NOCMTIME; */
+	/* cifs_inode->netfs.inode.i_flags = S_NOATIME | S_NOCMTIME; */
 	INIT_LIST_HEAD(&cifs_inode->openFileList);
 	INIT_LIST_HEAD(&cifs_inode->llist);
 	INIT_LIST_HEAD(&cifs_inode->deferred_closes);
 	spin_lock_init(&cifs_inode->deferred_lock);
-	return &cifs_inode->vfs_inode;
+	return &cifs_inode->netfs.inode;
 }
 
 static void
@@ -1418,7 +1418,7 @@ cifs_init_once(void *inode)
 {
 	struct cifsInodeInfo *cifsi = inode;
 
-	inode_init_once(&cifsi->vfs_inode);
+	inode_init_once(&cifsi->netfs.inode);
 	init_rwsem(&cifsi->lock_sem);
 }
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index f873379066c7..e7737166e5b8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1479,20 +1479,16 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
 #define CIFS_CACHE_RW_FLG	(CIFS_CACHE_READ_FLG | CIFS_CACHE_WRITE_FLG)
 #define CIFS_CACHE_RHW_FLG	(CIFS_CACHE_RW_FLG | CIFS_CACHE_HANDLE_FLG)
 
-#define CIFS_CACHE_READ(cinode) ((cinode->oplock & CIFS_CACHE_READ_FLG) || (CIFS_SB(cinode->vfs_inode.i_sb)->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE))
+#define CIFS_CACHE_READ(cinode) ((cinode->oplock & CIFS_CACHE_READ_FLG) || (CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE))
 #define CIFS_CACHE_HANDLE(cinode) (cinode->oplock & CIFS_CACHE_HANDLE_FLG)
-#define CIFS_CACHE_WRITE(cinode) ((cinode->oplock & CIFS_CACHE_WRITE_FLG) || (CIFS_SB(cinode->vfs_inode.i_sb)->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE))
+#define CIFS_CACHE_WRITE(cinode) ((cinode->oplock & CIFS_CACHE_WRITE_FLG) || (CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE))
 
 /*
  * One of these for each file inode
  */
 
 struct cifsInodeInfo {
-	struct {
-		/* These must be contiguous */
-		struct inode	vfs_inode;	/* the VFS's inode record */
-		struct netfs_i_context netfs_ctx; /* Netfslib context */
-	};
+	struct netfs_inode netfs; /* Netfslib context and vfs inode */
 	bool can_cache_brlcks;
 	struct list_head llist;	/* locks helb by this inode */
 	/*
@@ -1531,7 +1527,7 @@ struct cifsInodeInfo {
 static inline struct cifsInodeInfo *
 CIFS_I(struct inode *inode)
 {
-	return container_of(inode, struct cifsInodeInfo, vfs_inode);
+	return container_of(inode, struct cifsInodeInfo, netfs.inode);
 }
 
 static inline struct cifs_sb_info *
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 1618e0537d58..e64cda7a7610 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2004,7 +2004,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 					bool fsuid_only)
 {
 	struct cifsFileInfo *open_file = NULL;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
 
 	/* only filter by fsuid on multiuser mounts */
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
@@ -2060,7 +2060,7 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
 		return rc;
 	}
 
-	cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
+	cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
 
 	/* only filter by fsuid on multiuser mounts */
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
@@ -4669,14 +4669,14 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file)
 		/* This inode is open for write at least once */
 		struct cifs_sb_info *cifs_sb;
 
-		cifs_sb = CIFS_SB(cifsInode->vfs_inode.i_sb);
+		cifs_sb = CIFS_SB(cifsInode->netfs.inode.i_sb);
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
 			/* since no page cache to corrupt on directio
 			we can change size safely */
 			return true;
 		}
 
-		if (i_size_read(&cifsInode->vfs_inode) < end_of_file)
+		if (i_size_read(&cifsInode->netfs.inode) < end_of_file)
 			return true;
 
 		return false;
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index a638b29e9062..23ef56f55ce5 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -101,13 +101,13 @@ void cifs_fscache_get_inode_cookie(struct inode *inode)
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
-	cifs_fscache_fill_coherency(&cifsi->vfs_inode, &cd);
+	cifs_fscache_fill_coherency(&cifsi->netfs.inode, &cd);
 
-	cifsi->netfs_ctx.cache =
+	cifsi->netfs.cache =
 		fscache_acquire_cookie(tcon->fscache, 0,
 				       &cifsi->uniqueid, sizeof(cifsi->uniqueid),
 				       &cd, sizeof(cd),
-				       i_size_read(&cifsi->vfs_inode));
+				       i_size_read(&cifsi->netfs.inode));
 }
 
 void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update)
@@ -131,7 +131,7 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
 	if (cookie) {
 		cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cookie);
 		fscache_relinquish_cookie(cookie, false);
-		cifsi->netfs_ctx.cache = NULL;
+		cifsi->netfs.cache = NULL;
 	}
 }
 
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index 52355c0912ae..ab9a51d0125c 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -52,10 +52,10 @@ void cifs_fscache_fill_coherency(struct inode *inode,
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 
 	memset(cd, 0, sizeof(*cd));
-	cd->last_write_time_sec   = cpu_to_le64(cifsi->vfs_inode.i_mtime.tv_sec);
-	cd->last_write_time_nsec  = cpu_to_le32(cifsi->vfs_inode.i_mtime.tv_nsec);
-	cd->last_change_time_sec  = cpu_to_le64(cifsi->vfs_inode.i_ctime.tv_sec);
-	cd->last_change_time_nsec = cpu_to_le32(cifsi->vfs_inode.i_ctime.tv_nsec);
+	cd->last_write_time_sec   = cpu_to_le64(cifsi->netfs.inode.i_mtime.tv_sec);
+	cd->last_write_time_nsec  = cpu_to_le32(cifsi->netfs.inode.i_mtime.tv_nsec);
+	cd->last_change_time_sec  = cpu_to_le64(cifsi->netfs.inode.i_ctime.tv_sec);
+	cd->last_change_time_nsec = cpu_to_le32(cifsi->netfs.inode.i_ctime.tv_nsec);
 }
 
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 2f9e7d2f81b6..81da81e18553 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -115,7 +115,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 		 __func__, cifs_i->uniqueid);
 	set_bit(CIFS_INO_INVALID_MAPPING, &cifs_i->flags);
 	/* Invalidate fscache cookie */
-	cifs_fscache_fill_coherency(&cifs_i->vfs_inode, &cd);
+	cifs_fscache_fill_coherency(&cifs_i->netfs.inode, &cd);
 	fscache_invalidate(cifs_inode_cookie(inode), &cd, i_size_read(inode), 0);
 }
 
@@ -2499,7 +2499,7 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start,
 		u64 len)
 {
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_i->vfs_inode.i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_i->netfs.inode.i_sb);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifsFileInfo *cfile;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 35962a1a23b9..cbc3b433f502 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -537,11 +537,11 @@ void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock)
 	if (oplock == OPLOCK_EXCLUSIVE) {
 		cinode->oplock = CIFS_CACHE_WRITE_FLG | CIFS_CACHE_READ_FLG;
 		cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n",
-			 &cinode->vfs_inode);
+			 &cinode->netfs.inode);
 	} else if (oplock == OPLOCK_READ) {
 		cinode->oplock = CIFS_CACHE_READ_FLG;
 		cifs_dbg(FYI, "Level II Oplock granted on inode %p\n",
-			 &cinode->vfs_inode);
+			 &cinode->netfs.inode);
 	} else
 		cinode->oplock = 0;
 }
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 98a76fa791c0..8543cafdfd34 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -4260,15 +4260,15 @@ smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
 	if (oplock == SMB2_OPLOCK_LEVEL_BATCH) {
 		cinode->oplock = CIFS_CACHE_RHW_FLG;
 		cifs_dbg(FYI, "Batch Oplock granted on inode %p\n",
-			 &cinode->vfs_inode);
+			 &cinode->netfs.inode);
 	} else if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE) {
 		cinode->oplock = CIFS_CACHE_RW_FLG;
 		cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n",
-			 &cinode->vfs_inode);
+			 &cinode->netfs.inode);
 	} else if (oplock == SMB2_OPLOCK_LEVEL_II) {
 		cinode->oplock = CIFS_CACHE_READ_FLG;
 		cifs_dbg(FYI, "Level II Oplock granted on inode %p\n",
-			 &cinode->vfs_inode);
+			 &cinode->netfs.inode);
 	} else
 		cinode->oplock = 0;
 }
@@ -4307,7 +4307,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
 
 	cinode->oplock = new_oplock;
 	cifs_dbg(FYI, "%s Lease granted on inode %p\n", message,
-		 &cinode->vfs_inode);
+		 &cinode->netfs.inode);
 }
 
 static void
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 8742d22dfd2b..d37e012386f3 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -155,7 +155,7 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq,
 void netfs_readahead(struct readahead_control *ractl)
 {
 	struct netfs_io_request *rreq;
-	struct netfs_i_context *ctx = netfs_i_context(ractl->mapping->host);
+	struct netfs_inode *ctx = netfs_inode(ractl->mapping->host);
 	int ret;
 
 	_enter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
@@ -215,7 +215,7 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 {
 	struct address_space *mapping = folio_file_mapping(folio);
 	struct netfs_io_request *rreq;
-	struct netfs_i_context *ctx = netfs_i_context(mapping->host);
+	struct netfs_inode *ctx = netfs_inode(mapping->host);
 	int ret;
 
 	_enter("%lx", folio_index(folio));
@@ -331,7 +331,7 @@ int netfs_write_begin(struct file *file, struct address_space *mapping,
 		      void **_fsdata)
 {
 	struct netfs_io_request *rreq;
-	struct netfs_i_context *ctx = netfs_i_context(file_inode(file ));
+	struct netfs_inode *ctx = netfs_inode(file_inode(file ));
 	struct folio *folio;
 	unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
 	pgoff_t index = pos >> PAGE_SHIFT;
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index b7b0e3d18d9e..43fac1b14e40 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -91,7 +91,7 @@ static inline void netfs_stat_d(atomic_t *stat)
 /*
  * Miscellaneous functions.
  */
-static inline bool netfs_is_cache_enabled(struct netfs_i_context *ctx)
+static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx)
 {
 #if IS_ENABLED(CONFIG_FSCACHE)
 	struct fscache_cookie *cookie = ctx->cache;
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index e86107b30ba4..c6afa605b63b 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -18,7 +18,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 {
 	static atomic_t debug_ids;
 	struct inode *inode = file ? file_inode(file) : mapping->host;
-	struct netfs_i_context *ctx = netfs_i_context(inode);
+	struct netfs_inode *ctx = netfs_inode(inode);
 	struct netfs_io_request *rreq;
 	int ret;
 
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 77fa6a61706a..6dbb4c9ce50d 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -119,9 +119,10 @@ typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error,
 				      bool was_async);
 
 /*
- * Per-inode description.  This must be directly after the inode struct.
+ * Per-inode context.  This wraps the VFS inode.
  */
-struct netfs_i_context {
+struct netfs_inode {
+	struct inode		inode;		/* The VFS inode */
 	const struct netfs_request_ops *ops;
 #if IS_ENABLED(CONFIG_FSCACHE)
 	struct fscache_cookie	*cache;
@@ -256,7 +257,7 @@ struct netfs_cache_ops {
 	 * boundary as appropriate.
 	 */
 	enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq,
-					       loff_t i_size);
+					     loff_t i_size);
 
 	/* Prepare a write operation, working out what part of the write we can
 	 * actually do.
@@ -288,45 +289,35 @@ extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 extern void netfs_stats_show(struct seq_file *);
 
 /**
- * netfs_i_context - Get the netfs inode context from the inode
+ * netfs_inode - Get the netfs inode context from the inode
  * @inode: The inode to query
  *
  * Get the netfs lib inode context from the network filesystem's inode.  The
  * context struct is expected to directly follow on from the VFS inode struct.
  */
-static inline struct netfs_i_context *netfs_i_context(struct inode *inode)
+static inline struct netfs_inode *netfs_inode(struct inode *inode)
 {
-	return (void *)inode + sizeof(*inode);
+	return container_of(inode, struct netfs_inode, inode);
 }
 
 /**
- * netfs_inode - Get the netfs inode from the inode context
- * @ctx: The context to query
- *
- * Get the netfs inode from the netfs library's inode context.  The VFS inode
- * is expected to directly precede the context struct.
- */
-static inline struct inode *netfs_inode(struct netfs_i_context *ctx)
-{
-	return (void *)ctx - sizeof(struct inode);
-}
-
-/**
- * netfs_i_context_init - Initialise a netfs lib context
+ * netfs_inode_init - Initialise a netfslib inode context
  * @inode: The inode with which the context is associated
  * @ops: The netfs's operations list
  *
  * Initialise the netfs library context struct.  This is expected to follow on
  * directly from the VFS inode struct.
  */
-static inline void netfs_i_context_init(struct inode *inode,
-					const struct netfs_request_ops *ops)
+static inline void netfs_inode_init(struct inode *inode,
+				    const struct netfs_request_ops *ops)
 {
-	struct netfs_i_context *ctx = netfs_i_context(inode);
+	struct netfs_inode *ctx = netfs_inode(inode);
 
-	memset(ctx, 0, sizeof(*ctx));
 	ctx->ops = ops;
 	ctx->remote_i_size = i_size_read(inode);
+#if IS_ENABLED(CONFIG_FSCACHE)
+	ctx->cache = NULL;
+#endif
 }
 
 /**
@@ -338,7 +329,7 @@ static inline void netfs_i_context_init(struct inode *inode,
  */
 static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size)
 {
-	struct netfs_i_context *ctx = netfs_i_context(inode);
+	struct netfs_inode *ctx = netfs_inode(inode);
 
 	ctx->remote_i_size = new_i_size;
 }
@@ -352,7 +343,7 @@ static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size)
 static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode)
 {
 #if IS_ENABLED(CONFIG_FSCACHE)
-	struct netfs_i_context *ctx = netfs_i_context(inode);
+	struct netfs_inode *ctx = netfs_inode(inode);
 	return ctx->cache;
 #else
 	return NULL;
-- 
cgit v1.2.3


From 39e0f991a62ed5efabd20711a7b6e7da92603170 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 7 Jun 2022 17:00:16 +0200
Subject: random: mark bootloader randomness code as __init

add_bootloader_randomness() and the variables it touches are only used
during __init and not after, so mark these as __init. At the same time,
unexport this, since it's only called by other __init code that's
built-in.

Cc: stable@vger.kernel.org
Fixes: 428826f5358c ("fdt: add support for rng-seed")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 drivers/char/random.c  | 7 +++----
 include/linux/random.h | 2 +-
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 4862d4d3ec49..0d6fb3eaf609 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -725,8 +725,8 @@ static void __cold _credit_init_bits(size_t bits)
  **********************************************************************/
 
 static bool used_arch_random;
-static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
-static bool trust_bootloader __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER);
+static bool trust_cpu __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
+static bool trust_bootloader __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER);
 static int __init parse_trust_cpu(char *arg)
 {
 	return kstrtobool(arg, &trust_cpu);
@@ -865,13 +865,12 @@ EXPORT_SYMBOL_GPL(add_hwgenerator_randomness);
  * Handle random seed passed by bootloader, and credit it if
  * CONFIG_RANDOM_TRUST_BOOTLOADER is set.
  */
-void __cold add_bootloader_randomness(const void *buf, size_t len)
+void __init add_bootloader_randomness(const void *buf, size_t len)
 {
 	mix_pool_bytes(buf, len);
 	if (trust_bootloader)
 		credit_init_bits(len * 8);
 }
-EXPORT_SYMBOL_GPL(add_bootloader_randomness);
 
 #if IS_ENABLED(CONFIG_VMGENID)
 static BLOCKING_NOTIFIER_HEAD(vmfork_chain);
diff --git a/include/linux/random.h b/include/linux/random.h
index fae0c84027fd..223b4bd584e7 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -13,7 +13,7 @@
 struct notifier_block;
 
 void add_device_randomness(const void *buf, size_t len);
-void add_bootloader_randomness(const void *buf, size_t len);
+void __init add_bootloader_randomness(const void *buf, size_t len);
 void add_input_randomness(unsigned int type, unsigned int code,
 			  unsigned int value) __latent_entropy;
 void add_interrupt_randomness(int irq) __latent_entropy;
-- 
cgit v1.2.3


From e052a478a7daeca67664f7addd308ff51dd40654 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 8 Jun 2022 10:31:25 +0200
Subject: random: remove rng_has_arch_random()

With arch randomness being used by every distro and enabled in
defconfigs, the distinction between rng_has_arch_random() and
rng_is_initialized() is now rather small. In fact, the places where they
differ are now places where paranoid users and system builders really
don't want arch randomness to be used, in which case we should respect
that choice, or places where arch randomness is known to be broken, in
which case that choice is all the more important. So this commit just
removes the function and its one user.

Reviewed-by: Petr Mladek <pmladek@suse.com> # for vsprintf.c
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 drivers/char/random.c  | 13 -------------
 include/linux/random.h |  1 -
 lib/vsprintf.c         |  3 +--
 3 files changed, 1 insertion(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 0b78b9c4acf5..655e327d425e 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -725,7 +725,6 @@ static void __cold _credit_init_bits(size_t bits)
  *
  **********************************************************************/
 
-static bool used_arch_random;
 static bool trust_cpu __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
 static bool trust_bootloader __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER);
 static int __init parse_trust_cpu(char *arg)
@@ -811,7 +810,6 @@ int __init random_init(const char *command_line)
 		crng_reseed();
 	else if (trust_cpu)
 		_credit_init_bits(arch_bits);
-	used_arch_random = arch_bits >= POOL_READY_BITS;
 
 	WARN_ON(register_pm_notifier(&pm_notifier));
 
@@ -820,17 +818,6 @@ int __init random_init(const char *command_line)
 	return 0;
 }
 
-/*
- * Returns whether arch randomness has been mixed into the initial
- * state of the RNG, regardless of whether or not that randomness
- * was credited. Knowing this is only good for a very limited set
- * of uses, such as early init printk pointer obfuscation.
- */
-bool rng_has_arch_random(void)
-{
-	return used_arch_random;
-}
-
 /*
  * Add device- or boot-specific data to the input pool to help
  * initialize it.
diff --git a/include/linux/random.h b/include/linux/random.h
index 223b4bd584e7..20e389a14e5c 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -74,7 +74,6 @@ static inline unsigned long get_random_canary(void)
 
 int __init random_init(const char *command_line);
 bool rng_is_initialized(void);
-bool rng_has_arch_random(void);
 int wait_for_random_bytes(void);
 
 /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes).
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index fb77f7bfd126..3c1853a9d1c0 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -769,8 +769,7 @@ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out)
 		static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
 		unsigned long flags;
 
-		if (!system_unbound_wq ||
-		    (!rng_is_initialized() && !rng_has_arch_random()) ||
+		if (!system_unbound_wq || !rng_is_initialized() ||
 		    !spin_trylock_irqsave(&filling, flags))
 			return -EAGAIN;
 
-- 
cgit v1.2.3


From e81fb4198e27925b151aad1450e0fd607d6733f8 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 9 Jun 2022 15:04:01 -0700
Subject: netfs: Further cleanups after struct netfs_inode wrapper introduced

Change the signature of netfs helper functions to take a struct netfs_inode
pointer rather than a struct inode pointer where appropriate, thereby
relieving the need for the network filesystem to convert its internal inode
format down to the VFS inode only for netfslib to bounce it back up.  For
type safety, it's better not to do that (and it's less typing too).

Give netfs_write_begin() an extra argument to pass in a pointer to the
netfs_inode struct rather than deriving it internally from the file
pointer.  Note that the ->write_begin() and ->write_end() ops are intended
to be replaced in the future by netfslib code that manages this without the
need to call in twice for each page.

netfs_readpage() and similar are intended to be pointed at directly by the
address_space_operations table, so must stick to the signature dictated by
the function pointers there.

Changes
=======
- Updated the kerneldoc comments and documentation [DH].

Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-cachefs@redhat.com
Link: https://lore.kernel.org/r/CAHk-=wgkwKyNmNdKpQkqZ6DnmUL-x9hp0YBnUGjaPFEAdxDTbw@mail.gmail.com/
---
 Documentation/filesystems/netfs_library.rst |  9 +++++----
 fs/9p/v9fs.h                                |  2 +-
 fs/9p/vfs_addr.c                            |  2 +-
 fs/9p/vfs_inode.c                           |  3 ++-
 fs/afs/dynroot.c                            |  2 +-
 fs/afs/inode.c                              |  2 +-
 fs/afs/internal.h                           |  2 +-
 fs/afs/write.c                              |  2 +-
 fs/ceph/addr.c                              |  3 ++-
 fs/ceph/cache.h                             |  2 +-
 fs/ceph/inode.c                             |  2 +-
 fs/cifs/fscache.h                           |  2 +-
 fs/netfs/buffered_read.c                    |  5 +++--
 include/linux/netfs.h                       | 22 +++++++++-------------
 14 files changed, 30 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 3276c3d55142..9332f66373ee 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -79,7 +79,7 @@ To help deal with the per-inode context, a number helper functions are
 provided.  Firstly, a function to perform basic initialisation on a context and
 set the operations table pointer::
 
-	void netfs_inode_init(struct inode *inode,
+	void netfs_inode_init(struct netfs_inode *ctx,
 			      const struct netfs_request_ops *ops);
 
 then a function to cast from the VFS inode structure to the netfs context::
@@ -89,7 +89,7 @@ then a function to cast from the VFS inode structure to the netfs context::
 and finally, a function to get the cache cookie pointer from the context
 attached to an inode (or NULL if fscache is disabled)::
 
-	struct fscache_cookie *netfs_i_cookie(struct inode *inode);
+	struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx);
 
 
 Buffered Read Helpers
@@ -136,8 +136,9 @@ Three read helpers are provided::
 
 	void netfs_readahead(struct readahead_control *ractl);
 	int netfs_read_folio(struct file *file,
-			   struct folio *folio);
-	int netfs_write_begin(struct file *file,
+			     struct folio *folio);
+	int netfs_write_begin(struct netfs_inode *ctx,
+			      struct file *file,
 			      struct address_space *mapping,
 			      loff_t pos,
 			      unsigned int len,
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 1b219c21d15e..6acabc2e7dc9 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -124,7 +124,7 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
 static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inode)
 {
 #ifdef CONFIG_9P_FSCACHE
-	return netfs_i_cookie(&v9inode->netfs.inode);
+	return netfs_i_cookie(&v9inode->netfs);
 #else
 	return NULL;
 #endif
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 90c6c1ba03ab..c004b9a73a92 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -274,7 +274,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
 	 * file.  We need to do this before we get a lock on the page in case
 	 * there's more than one writer competing for the same cache block.
 	 */
-	retval = netfs_write_begin(filp, mapping, pos, len, &folio, fsdata);
+	retval = netfs_write_begin(&v9inode->netfs, filp, mapping, pos, len, &folio, fsdata);
 	if (retval < 0)
 		return retval;
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index e660c6348b9d..419d2f3cf2c2 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -252,7 +252,8 @@ void v9fs_free_inode(struct inode *inode)
  */
 static void v9fs_set_netfs_context(struct inode *inode)
 {
-	netfs_inode_init(inode, &v9fs_req_ops);
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	netfs_inode_init(&v9inode->netfs, &v9fs_req_ops);
 }
 
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 3a5bbffdf053..d7d9402ff718 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -76,7 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
 	/* there shouldn't be an existing inode */
 	BUG_ON(!(inode->i_state & I_NEW));
 
-	netfs_inode_init(inode, NULL);
+	netfs_inode_init(&vnode->netfs, NULL);
 	inode->i_size		= 0;
 	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
 	if (root) {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 22811e9eacf5..89630acbc2cc 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -58,7 +58,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
  */
 static void afs_set_netfs_context(struct afs_vnode *vnode)
 {
-	netfs_inode_init(&vnode->netfs.inode, &afs_req_ops);
+	netfs_inode_init(&vnode->netfs, &afs_req_ops);
 }
 
 /*
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 984b113a9107..a6f25d9e75b5 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -670,7 +670,7 @@ struct afs_vnode {
 static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode)
 {
 #ifdef CONFIG_AFS_FSCACHE
-	return netfs_i_cookie(&vnode->netfs.inode);
+	return netfs_i_cookie(&vnode->netfs);
 #else
 	return NULL;
 #endif
diff --git a/fs/afs/write.c b/fs/afs/write.c
index f80a6096d91c..2c885b22de34 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -60,7 +60,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	 * file.  We need to do this before we get a lock on the page in case
 	 * there's more than one writer competing for the same cache block.
 	 */
-	ret = netfs_write_begin(file, mapping, pos, len, &folio, fsdata);
+	ret = netfs_write_begin(&vnode->netfs, file, mapping, pos, len, &folio, fsdata);
 	if (ret < 0)
 		return ret;
 
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index f5f116ed1b9e..9763e7ea8148 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1322,10 +1322,11 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = file_inode(file);
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct folio *folio = NULL;
 	int r;
 
-	r = netfs_write_begin(file, inode->i_mapping, pos, len, &folio, NULL);
+	r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
 	if (r == 0)
 		folio_wait_fscache(folio);
 	if (r < 0) {
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 26c6ae06e2f4..dc502daac49a 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -28,7 +28,7 @@ void ceph_fscache_invalidate(struct inode *inode, bool dio_write);
 
 static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci)
 {
-	return netfs_i_cookie(&ci->netfs.inode);
+	return netfs_i_cookie(&ci->netfs);
 }
 
 static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 650746b3ba99..56c53ab3618e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -460,7 +460,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	dout("alloc_inode %p\n", &ci->netfs.inode);
 
 	/* Set parameters for the netfs library */
-	netfs_inode_init(&ci->netfs.inode, &ceph_netfs_ops);
+	netfs_inode_init(&ci->netfs, &ceph_netfs_ops);
 
 	spin_lock_init(&ci->i_ceph_lock);
 
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index ab9a51d0125c..aa3b941a5555 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -61,7 +61,7 @@ void cifs_fscache_fill_coherency(struct inode *inode,
 
 static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode)
 {
-	return netfs_i_cookie(inode);
+	return netfs_i_cookie(&CIFS_I(inode)->netfs);
 }
 
 static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags)
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index d37e012386f3..42f892c5712e 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -297,6 +297,7 @@ zero_out:
 
 /**
  * netfs_write_begin - Helper to prepare for writing
+ * @ctx: The netfs context
  * @file: The file to read from
  * @mapping: The mapping to read from
  * @pos: File position at which the write will begin
@@ -326,12 +327,12 @@ zero_out:
  *
  * This is usable whether or not caching is enabled.
  */
-int netfs_write_begin(struct file *file, struct address_space *mapping,
+int netfs_write_begin(struct netfs_inode *ctx,
+		      struct file *file, struct address_space *mapping,
 		      loff_t pos, unsigned int len, struct folio **_folio,
 		      void **_fsdata)
 {
 	struct netfs_io_request *rreq;
-	struct netfs_inode *ctx = netfs_inode(file_inode(file ));
 	struct folio *folio;
 	unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
 	pgoff_t index = pos >> PAGE_SHIFT;
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 6dbb4c9ce50d..a62739f3726b 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -277,7 +277,8 @@ struct netfs_cache_ops {
 struct readahead_control;
 extern void netfs_readahead(struct readahead_control *);
 int netfs_read_folio(struct file *, struct folio *);
-extern int netfs_write_begin(struct file *, struct address_space *,
+extern int netfs_write_begin(struct netfs_inode *,
+			     struct file *, struct address_space *,
 			     loff_t, unsigned int, struct folio **,
 			     void **);
 
@@ -302,19 +303,17 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode)
 
 /**
  * netfs_inode_init - Initialise a netfslib inode context
- * @inode: The inode with which the context is associated
+ * @inode: The netfs inode to initialise
  * @ops: The netfs's operations list
  *
  * Initialise the netfs library context struct.  This is expected to follow on
  * directly from the VFS inode struct.
  */
-static inline void netfs_inode_init(struct inode *inode,
+static inline void netfs_inode_init(struct netfs_inode *ctx,
 				    const struct netfs_request_ops *ops)
 {
-	struct netfs_inode *ctx = netfs_inode(inode);
-
 	ctx->ops = ops;
-	ctx->remote_i_size = i_size_read(inode);
+	ctx->remote_i_size = i_size_read(&ctx->inode);
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
@@ -322,28 +321,25 @@ static inline void netfs_inode_init(struct inode *inode,
 
 /**
  * netfs_resize_file - Note that a file got resized
- * @inode: The inode being resized
+ * @ctx: The netfs inode being resized
  * @new_i_size: The new file size
  *
  * Inform the netfs lib that a file got resized so that it can adjust its state.
  */
-static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size)
+static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size)
 {
-	struct netfs_inode *ctx = netfs_inode(inode);
-
 	ctx->remote_i_size = new_i_size;
 }
 
 /**
  * netfs_i_cookie - Get the cache cookie from the inode
- * @inode: The inode to query
+ * @ctx: The netfs inode to query
  *
  * Get the caching cookie (if enabled) from the network filesystem's inode.
  */
-static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode)
+static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx)
 {
 #if IS_ENABLED(CONFIG_FSCACHE)
-	struct netfs_inode *ctx = netfs_inode(inode);
 	return ctx->cache;
 #else
 	return NULL;
-- 
cgit v1.2.3


From 40a81101202300df7db273f77dda9fbe6271b1d2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 25 Feb 2022 11:19:14 +0000
Subject: netfs: Rename the netfs_io_request cleanup op and give it an op
 pointer

The netfs_io_request cleanup op is now always in a position to be given a
pointer to a netfs_io_request struct, so this can be passed in instead of
the mapping and private data arguments (both of which are included in the
struct).

So rename the ->cleanup op to ->free_request (to match ->init_request) and
pass in the I/O pointer.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
---
 Documentation/filesystems/netfs_library.rst | 24 ++++++++++++------------
 fs/9p/vfs_addr.c                            | 11 +++++------
 fs/afs/file.c                               |  6 +++---
 fs/ceph/addr.c                              |  9 ++++-----
 fs/netfs/objects.c                          |  6 +++---
 include/linux/netfs.h                       |  3 ++-
 6 files changed, 29 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 9332f66373ee..4d19b19bcc08 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -158,9 +158,10 @@ The helpers manage the read request, calling back into the network filesystem
 through the suppplied table of operations.  Waits will be performed as
 necessary before returning for helpers that are meant to be synchronous.
 
-If an error occurs and netfs_priv is non-NULL, ops->cleanup() will be called to
-deal with it.  If some parts of the request are in progress when an error
-occurs, the request will get partially completed if sufficient data is read.
+If an error occurs, the ->free_request() will be called to clean up the
+netfs_io_request struct allocated.  If some parts of the request are in
+progress when an error occurs, the request will get partially completed if
+sufficient data is read.
 
 Additionally, there is::
 
@@ -208,8 +209,7 @@ The above fields are the ones the netfs can use.  They are:
  * ``netfs_priv``
 
    The network filesystem's private data.  The value for this can be passed in
-   to the helper functions or set during the request.  The ->cleanup() op will
-   be called if this is non-NULL at the end.
+   to the helper functions or set during the request.
 
  * ``start``
  * ``len``
@@ -294,6 +294,7 @@ through which it can issue requests and negotiate::
 
 	struct netfs_request_ops {
 		void (*init_request)(struct netfs_io_request *rreq, struct file *file);
+		void (*free_request)(struct netfs_io_request *rreq);
 		int (*begin_cache_operation)(struct netfs_io_request *rreq);
 		void (*expand_readahead)(struct netfs_io_request *rreq);
 		bool (*clamp_length)(struct netfs_io_subrequest *subreq);
@@ -302,7 +303,6 @@ through which it can issue requests and negotiate::
 		int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
 					 struct folio *folio, void **_fsdata);
 		void (*done)(struct netfs_io_request *rreq);
-		void (*cleanup)(struct address_space *mapping, void *netfs_priv);
 	};
 
 The operations are as follows:
@@ -310,7 +310,12 @@ The operations are as follows:
  * ``init_request()``
 
    [Optional] This is called to initialise the request structure.  It is given
-   the file for reference and can modify the ->netfs_priv value.
+   the file for reference.
+
+ * ``free_request()``
+
+   [Optional] This is called as the request is being deallocated so that the
+   filesystem can clean up any state it has attached there.
 
  * ``begin_cache_operation()``
 
@@ -384,11 +389,6 @@ The operations are as follows:
    [Optional] This is called after the folios in the request have all been
    unlocked (and marked uptodate if applicable).
 
- * ``cleanup``
-
-   [Optional] This is called as the request is being deallocated so that the
-   filesystem can clean up ->netfs_priv.
-
 
 
 Read Helper Procedure
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index c004b9a73a92..a8f512b44a85 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -66,13 +66,12 @@ static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file)
 }
 
 /**
- * v9fs_req_cleanup - Cleanup request initialized by v9fs_init_request
- * @mapping: unused mapping of request to cleanup
- * @priv: private data to cleanup, a fid, guaranted non-null.
+ * v9fs_free_request - Cleanup request initialized by v9fs_init_rreq
+ * @rreq: The I/O request to clean up
  */
-static void v9fs_req_cleanup(struct address_space *mapping, void *priv)
+static void v9fs_free_request(struct netfs_io_request *rreq)
 {
-	struct p9_fid *fid = priv;
+	struct p9_fid *fid = rreq->netfs_priv;
 
 	p9_client_clunk(fid);
 }
@@ -94,9 +93,9 @@ static int v9fs_begin_cache_operation(struct netfs_io_request *rreq)
 
 const struct netfs_request_ops v9fs_req_ops = {
 	.init_request		= v9fs_init_request,
+	.free_request		= v9fs_free_request,
 	.begin_cache_operation	= v9fs_begin_cache_operation,
 	.issue_read		= v9fs_issue_read,
-	.cleanup		= v9fs_req_cleanup,
 };
 
 /**
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 4de7af7c2f09..42118a4f3383 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -382,17 +382,17 @@ static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len,
 	return test_bit(AFS_VNODE_DELETED, &vnode->flags) ? -ESTALE : 0;
 }
 
-static void afs_priv_cleanup(struct address_space *mapping, void *netfs_priv)
+static void afs_free_request(struct netfs_io_request *rreq)
 {
-	key_put(netfs_priv);
+	key_put(rreq->netfs_priv);
 }
 
 const struct netfs_request_ops afs_req_ops = {
 	.init_request		= afs_init_request,
+	.free_request		= afs_free_request,
 	.begin_cache_operation	= afs_begin_cache_operation,
 	.check_write_begin	= afs_check_write_begin,
 	.issue_read		= afs_issue_read,
-	.cleanup		= afs_priv_cleanup,
 };
 
 int afs_write_inode(struct inode *inode, struct writeback_control *wbc)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 9763e7ea8148..6dee88815491 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -394,11 +394,10 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 	return 0;
 }
 
-static void ceph_readahead_cleanup(struct address_space *mapping, void *priv)
+static void ceph_netfs_free_request(struct netfs_io_request *rreq)
 {
-	struct inode *inode = mapping->host;
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	int got = (uintptr_t)priv;
+	struct ceph_inode_info *ci = ceph_inode(rreq->inode);
+	int got = (uintptr_t)rreq->netfs_priv;
 
 	if (got)
 		ceph_put_cap_refs(ci, got);
@@ -406,12 +405,12 @@ static void ceph_readahead_cleanup(struct address_space *mapping, void *priv)
 
 const struct netfs_request_ops ceph_netfs_ops = {
 	.init_request		= ceph_init_request,
+	.free_request		= ceph_netfs_free_request,
 	.begin_cache_operation	= ceph_begin_cache_operation,
 	.issue_read		= ceph_netfs_issue_read,
 	.expand_readahead	= ceph_netfs_expand_readahead,
 	.clamp_length		= ceph_netfs_clamp_length,
 	.check_write_begin	= ceph_netfs_check_write_begin,
-	.cleanup		= ceph_readahead_cleanup,
 };
 
 #ifdef CONFIG_CEPH_FSCACHE
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index c6afa605b63b..e17cdf53f6a7 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -75,10 +75,10 @@ static void netfs_free_request(struct work_struct *work)
 	struct netfs_io_request *rreq =
 		container_of(work, struct netfs_io_request, work);
 
-	netfs_clear_subrequests(rreq, false);
-	if (rreq->netfs_priv)
-		rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv);
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
+	netfs_clear_subrequests(rreq, false);
+	if (rreq->netfs_ops->free_request)
+		rreq->netfs_ops->free_request(rreq);
 	if (rreq->cache_resources.ops)
 		rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
 	kfree(rreq);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index a62739f3726b..097cdd644665 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -206,7 +206,9 @@ struct netfs_io_request {
  */
 struct netfs_request_ops {
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
+	void (*free_request)(struct netfs_io_request *rreq);
 	int (*begin_cache_operation)(struct netfs_io_request *rreq);
+
 	void (*expand_readahead)(struct netfs_io_request *rreq);
 	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
 	void (*issue_read)(struct netfs_io_subrequest *subreq);
@@ -214,7 +216,6 @@ struct netfs_request_ops {
 	int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
 				 struct folio *folio, void **_fsdata);
 	void (*done)(struct netfs_io_request *rreq);
-	void (*cleanup)(struct address_space *mapping, void *netfs_priv);
 };
 
 /*
-- 
cgit v1.2.3


From 8bee9dd953b69c634d1c9a3241a8b357469ad4aa Mon Sep 17 00:00:00 2001
From: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Date: Fri, 10 Jun 2022 01:41:10 +0200
Subject: workqueue: Switch to new kerneldoc syntax for named variable macro
 argument
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The syntax without dots is available since commit 43756e347f21
("scripts/kernel-doc: Add support for named variable macro arguments").

The same HTML output is produced with and without this patch.

Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/workqueue.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index e1f1c8b1121b..62e75dd40d9a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -406,7 +406,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
  * alloc_ordered_workqueue - allocate an ordered workqueue
  * @fmt: printf format for the name of the workqueue
  * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
- * @args...: args for @fmt
+ * @args: args for @fmt
  *
  * Allocate an ordered workqueue.  An ordered workqueue executes at
  * most one work item at any given time in the queued order.  They are
-- 
cgit v1.2.3