From af22bbe1f4a514c80b89a27252beef033168f4e9 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 16 Jul 2024 13:35:48 +0200
Subject: virtio: create admin queues alongside other virtqueues

Admin virtqueue is just another virtqueue nothing that special about it.
The current implementation treats it somehow separate though in terms
of creation and deletion. Unify the admin virtqueue creation and
deletion flows to be aligned with the rest of virtqueues, creating
it from vp_find_vqs_*() helpers. Let the admin virtqueue to be deleted
by vp_del_vqs() as the rest.

Call vp_find_one_vq_msix() with slow_path argument being "true" to make
sure that in case of limited interrupt vectors the config vector is used
for admin queue.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Message-Id: <20240716113552.80599-10-jiri@resnulli.us>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index ab4b9a3fef6b..169c7d367fac 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -104,8 +104,6 @@ struct virtqueue_info {
  *	Returns 0 on success or error status
  *	If disable_vq_and_reset is set, then enable_vq_after_reset must also be
  *	set.
- * @create_avq: create admin virtqueue resource.
- * @destroy_avq: destroy admin virtqueue resource.
  */
 struct virtio_config_ops {
 	void (*get)(struct virtio_device *vdev, unsigned offset,
@@ -133,8 +131,6 @@ struct virtio_config_ops {
 			       struct virtio_shm_region *region, u8 id);
 	int (*disable_vq_and_reset)(struct virtqueue *vq);
 	int (*enable_vq_after_reset)(struct virtqueue *vq);
-	int (*create_avq)(struct virtio_device *vdev);
-	void (*destroy_avq)(struct virtio_device *vdev);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
-- 
cgit v1.3


From 4c3b54af907e709609d3d8beca92d65e2f0cfd83 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 16 Jul 2024 13:35:51 +0200
Subject: virtio_pci_modern: use completion instead of busy loop to wait on
 admin cmd result

Currently, the code waits in a busy loop on every admin virtqueue issued
command to get a reply. That prevents callers from issuing multiple
commands in parallel.

To overcome this limitation, introduce a virtqueue event callback for
admin virtqueue. For every issued command, use completion mechanism
to wait on a reply. In the event callback, trigger the completion
is done for every incoming reply.

Alongside with that, introduce a spin lock to protect the admin
virtqueue operations.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Message-Id: <20240716113552.80599-13-jiri@resnulli.us>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_common.c | 13 ++++---
 drivers/virtio/virtio_pci_common.h |  3 ++
 drivers/virtio/virtio_pci_modern.c | 74 ++++++++++++++++++++++++++++++++------
 include/linux/virtio.h             |  3 ++
 4 files changed, 77 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 267643bb1cd5..c44d8ba00c02 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -395,6 +395,8 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 			if (vqi->name && vqi->callback)
 				++nvectors;
 		}
+		if (avq_num && vector_policy == VP_VQ_VECTOR_POLICY_EACH)
+			++nvectors;
 	} else {
 		/* Second best: one for change, shared for all vqs. */
 		nvectors = 2;
@@ -425,9 +427,9 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 	if (!avq_num)
 		return 0;
 	sprintf(avq->name, "avq.%u", avq->vq_index);
-	vq = vp_find_one_vq_msix(vdev, avq->vq_index, NULL, avq->name, false,
-				 true, &allocated_vectors, vector_policy,
-				 &vp_dev->admin_vq.info);
+	vq = vp_find_one_vq_msix(vdev, avq->vq_index, vp_modern_avq_done,
+				 avq->name, false, true, &allocated_vectors,
+				 vector_policy, &vp_dev->admin_vq.info);
 	if (IS_ERR(vq)) {
 		err = PTR_ERR(vq);
 		goto error_find;
@@ -486,8 +488,9 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 	if (!avq_num)
 		return 0;
 	sprintf(avq->name, "avq.%u", avq->vq_index);
-	vq = vp_setup_vq(vdev, queue_idx++, NULL, avq->name, false,
-			 VIRTIO_MSI_NO_VECTOR, &vp_dev->admin_vq.info);
+	vq = vp_setup_vq(vdev, queue_idx++, vp_modern_avq_done, avq->name,
+			 false, VIRTIO_MSI_NO_VECTOR,
+			 &vp_dev->admin_vq.info);
 	if (IS_ERR(vq)) {
 		err = PTR_ERR(vq);
 		goto out_del_vqs;
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index de59bb06ec3c..90df381fbbcf 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -47,6 +47,8 @@ struct virtio_pci_admin_vq {
 	struct virtio_pci_vq_info *info;
 	/* serializing admin commands execution. */
 	struct mutex cmd_lock;
+	/* Protects virtqueue access. */
+	spinlock_t lock;
 	u64 supported_cmds;
 	/* Name of the admin queue: avq.$vq_index. */
 	char name[10];
@@ -178,6 +180,7 @@ struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
 #define VIRTIO_ADMIN_CMD_BITMAP 0
 #endif
 
+void vp_modern_avq_done(struct virtqueue *vq);
 int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
 			     struct virtio_admin_cmd *cmd);
 
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 0fd344d1eaf9..608df3263df1 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -53,6 +53,23 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
 	return index == vp_dev->admin_vq.vq_index;
 }
 
+void vp_modern_avq_done(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+	struct virtio_admin_cmd *cmd;
+	unsigned long flags;
+	unsigned int len;
+
+	spin_lock_irqsave(&admin_vq->lock, flags);
+	do {
+		virtqueue_disable_cb(vq);
+		while ((cmd = virtqueue_get_buf(vq, &len)))
+			complete(&cmd->completion);
+	} while (!virtqueue_enable_cb(vq));
+	spin_unlock_irqrestore(&admin_vq->lock, flags);
+}
+
 static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
 				    u16 opcode,
 				    struct scatterlist **sgs,
@@ -61,7 +78,8 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
 				    struct virtio_admin_cmd *cmd)
 {
 	struct virtqueue *vq;
-	int ret, len;
+	unsigned long flags;
+	int ret;
 
 	vq = admin_vq->info->vq;
 	if (!vq)
@@ -72,21 +90,33 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
 	    !((1ULL << opcode) & admin_vq->supported_cmds))
 		return -EOPNOTSUPP;
 
-	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_KERNEL);
-	if (ret < 0)
-		return -EIO;
+	init_completion(&cmd->completion);
 
-	if (unlikely(!virtqueue_kick(vq)))
+again:
+	if (virtqueue_is_broken(vq))
 		return -EIO;
 
-	while (!virtqueue_get_buf(vq, &len) &&
-	       !virtqueue_is_broken(vq))
-		cpu_relax();
+	spin_lock_irqsave(&admin_vq->lock, flags);
+	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_KERNEL);
+	if (ret < 0) {
+		if (ret == -ENOSPC) {
+			spin_unlock_irqrestore(&admin_vq->lock, flags);
+			cpu_relax();
+			goto again;
+		}
+		goto unlock_err;
+	}
+	if (!virtqueue_kick(vq))
+		goto unlock_err;
+	spin_unlock_irqrestore(&admin_vq->lock, flags);
 
-	if (virtqueue_is_broken(vq))
-		return -EIO;
+	wait_for_completion(&cmd->completion);
 
-	return 0;
+	return cmd->ret;
+
+unlock_err:
+	spin_unlock_irqrestore(&admin_vq->lock, flags);
+	return -EIO;
 }
 
 int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
@@ -209,6 +239,25 @@ static void vp_modern_avq_activate(struct virtio_device *vdev)
 	virtio_pci_admin_cmd_list_init(vdev);
 }
 
+static void vp_modern_avq_cleanup(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_admin_cmd *cmd;
+	struct virtqueue *vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	vq = vp_dev->vqs[vp_dev->admin_vq.vq_index]->vq;
+	if (!vq)
+		return;
+
+	while ((cmd = virtqueue_detach_unused_buf(vq))) {
+		cmd->ret = -EIO;
+		complete(&cmd->completion);
+	}
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -403,6 +452,8 @@ static void vp_reset(struct virtio_device *vdev)
 	while (vp_modern_get_status(mdev))
 		msleep(1);
 
+	vp_modern_avq_cleanup(vdev);
+
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
 }
@@ -785,6 +836,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
+	spin_lock_init(&vp_dev->admin_vq.lock);
 	mutex_init(&vp_dev->admin_vq.cmd_lock);
 	return 0;
 }
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 96fea920873b..999ff5934392 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -10,6 +10,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/gfp.h>
 #include <linux/dma-mapping.h>
+#include <linux/completion.h>
 
 /**
  * struct virtqueue - a queue to register buffers for sending or receiving.
@@ -109,6 +110,8 @@ struct virtio_admin_cmd {
 	__le64 group_member_id;
 	struct scatterlist *data_sg;
 	struct scatterlist *result_sg;
+	struct completion completion;
+	int ret;
 };
 
 /**
-- 
cgit v1.3


From 564429a6bd8d26065b2cccffcaa9485359f74de7 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 11 Jul 2024 18:27:47 -0400
Subject: KVM: rename CONFIG_HAVE_KVM_GMEM_* to CONFIG_HAVE_KVM_ARCH_GMEM_*

Add "ARCH" to the symbols; shortly, the "prepare" phase will include both
the arch-independent step to clear out contents left in the page by the
host, and the arch-dependent step enabled by CONFIG_HAVE_KVM_GMEM_PREPARE.
For consistency do the same for CONFIG_HAVE_KVM_GMEM_INVALIDATE as well.

Reviewed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig     | 4 ++--
 arch/x86/kvm/x86.c       | 4 ++--
 include/linux/kvm_host.h | 4 ++--
 virt/kvm/Kconfig         | 4 ++--
 virt/kvm/guest_memfd.c   | 6 +++---
 5 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 4287a8071a3a..472a1537b7a9 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -141,8 +141,8 @@ config KVM_AMD_SEV
 	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
 	select ARCH_HAS_CC_PLATFORM
 	select KVM_GENERIC_PRIVATE_MEM
-	select HAVE_KVM_GMEM_PREPARE
-	select HAVE_KVM_GMEM_INVALIDATE
+	select HAVE_KVM_ARCH_GMEM_PREPARE
+	select HAVE_KVM_ARCH_GMEM_INVALIDATE
 	help
 	  Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
 	  with Encrypted State (SEV-ES) on AMD processors.
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 52778689cef4..4db18924b2f2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13644,7 +13644,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
-#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 bool kvm_arch_gmem_prepare_needed(struct kvm *kvm)
 {
 	return kvm->arch.vm_type == KVM_X86_SNP_VM;
@@ -13656,7 +13656,7 @@ int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_ord
 }
 #endif
 
-#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
 void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 {
 	kvm_x86_call(gmem_invalidate)(start, end);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 689e8be873a7..344d90771844 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2445,7 +2445,7 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_PRIVATE_MEM */
 
-#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
 bool kvm_arch_gmem_prepare_needed(struct kvm *kvm);
 #endif
@@ -2477,7 +2477,7 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque);
 
-#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
 void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
 #endif
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index b14e14cdbfb9..fd6a3010afa8 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -113,10 +113,10 @@ config KVM_GENERIC_PRIVATE_MEM
        select KVM_PRIVATE_MEM
        bool
 
-config HAVE_KVM_GMEM_PREPARE
+config HAVE_KVM_ARCH_GMEM_PREPARE
        bool
        depends on KVM_PRIVATE_MEM
 
-config HAVE_KVM_GMEM_INVALIDATE
+config HAVE_KVM_ARCH_GMEM_INVALIDATE
        bool
        depends on KVM_PRIVATE_MEM
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 5221b584288f..76139332f2f3 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -27,7 +27,7 @@ static inline kvm_pfn_t folio_file_pfn(struct folio *folio, pgoff_t index)
 
 static int kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct folio *folio)
 {
-#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 	struct list_head *gmem_list = &inode->i_mapping->i_private_list;
 	struct kvm_gmem *gmem;
 
@@ -353,7 +353,7 @@ static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *fol
 	return MF_DELAYED;
 }
 
-#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
 static void kvm_gmem_free_folio(struct folio *folio)
 {
 	struct page *page = folio_page(folio, 0);
@@ -368,7 +368,7 @@ static const struct address_space_operations kvm_gmem_aops = {
 	.dirty_folio = noop_dirty_folio,
 	.migrate_folio	= kvm_gmem_migrate_folio,
 	.error_remove_folio = kvm_gmem_error_folio,
-#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
 	.free_folio = kvm_gmem_free_folio,
 #endif
 };
-- 
cgit v1.3


From 7239ed74677af143857d1a96d402476446a0995a Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 11 Jul 2024 18:27:51 -0400
Subject: KVM: remove kvm_arch_gmem_prepare_needed()

It is enough to return 0 if a guest need not do any preparation.
This is in fact how sev_gmem_prepare() works for non-SNP guests,
and it extends naturally to Intel hosts: the x86 callback for
gmem_prepare is optional and returns 0 if not defined.

Reviewed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c       |  5 -----
 include/linux/kvm_host.h |  1 -
 virt/kvm/guest_memfd.c   | 13 +++----------
 3 files changed, 3 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4db18924b2f2..ef3d3511e4af 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13645,11 +13645,6 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
-bool kvm_arch_gmem_prepare_needed(struct kvm *kvm)
-{
-	return kvm->arch.vm_type == KVM_X86_SNP_VM;
-}
-
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order)
 {
 	return kvm_x86_call(gmem_prepare)(kvm, pfn, gfn, max_order);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 344d90771844..45373d42f314 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2447,7 +2447,6 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
-bool kvm_arch_gmem_prepare_needed(struct kvm *kvm);
 #endif
 
 /**
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 444ded162154..191fd42067c0 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -29,16 +29,9 @@ static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slo
 				    pgoff_t index, struct folio *folio)
 {
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
-	kvm_pfn_t pfn;
-	gfn_t gfn;
-	int rc;
-
-	if (!kvm_arch_gmem_prepare_needed(kvm))
-		return 0;
-
-	pfn = folio_file_pfn(folio, index);
-	gfn = slot->base_gfn + index - slot->gmem.pgoff;
-	rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio));
+	kvm_pfn_t pfn = folio_file_pfn(folio, index);
+	gfn_t gfn = slot->base_gfn + index - slot->gmem.pgoff;
+	int rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio));
 	if (rc) {
 		pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx GFN %llx PFN %llx error %d.\n",
 				    index, gfn, pfn, rc);
-- 
cgit v1.3


From 4b5f67120a88c713b82907d55a767693382e9e9d Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 11 Jul 2024 18:27:54 -0400
Subject: KVM: extend kvm_range_has_memory_attributes() to check subset of
 attributes

While currently there is no other attribute than KVM_MEMORY_ATTRIBUTE_PRIVATE,
KVM code such as kvm_mem_is_private() is written to expect their existence.
Allow using kvm_range_has_memory_attributes() as a multi-page version of
kvm_mem_is_private(), without it breaking later when more attributes are
introduced.

Reviewed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   |  2 +-
 include/linux/kvm_host.h |  2 +-
 virt/kvm/kvm_main.c      | 13 +++++++------
 3 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 26ef5b6ac3c1..43a02891babb 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7513,7 +7513,7 @@ static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
 	const unsigned long end = start + KVM_PAGES_PER_HPAGE(level);
 
 	if (level == PG_LEVEL_2M)
-		return kvm_range_has_memory_attributes(kvm, start, end, attrs);
+		return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs);
 
 	for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) {
 		if (hugepage_test_mixed(slot, gfn, level - 1) ||
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 45373d42f314..c223b97df03e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2414,7 +2414,7 @@ static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn
 }
 
 bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
-				     unsigned long attrs);
+				     unsigned long mask, unsigned long attrs);
 bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range);
 bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 30328ff2d840..92901656a0d4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2408,21 +2408,21 @@ static u64 kvm_supported_mem_attributes(struct kvm *kvm)
 
 /*
  * Returns true if _all_ gfns in the range [@start, @end) have attributes
- * matching @attrs.
+ * such that the bits in @mask match @attrs.
  */
 bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
-				     unsigned long attrs)
+				     unsigned long mask, unsigned long attrs)
 {
 	XA_STATE(xas, &kvm->mem_attr_array, start);
-	unsigned long mask = kvm_supported_mem_attributes(kvm);
 	unsigned long index;
 	void *entry;
 
+	mask &= kvm_supported_mem_attributes(kvm);
 	if (attrs & ~mask)
 		return false;
 
 	if (end == start + 1)
-		return kvm_get_memory_attributes(kvm, start) == attrs;
+		return (kvm_get_memory_attributes(kvm, start) & mask) == attrs;
 
 	guard(rcu)();
 	if (!attrs)
@@ -2433,7 +2433,8 @@ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
 			entry = xas_next(&xas);
 		} while (xas_retry(&xas, entry));
 
-		if (xas.xa_index != index || xa_to_value(entry) != attrs)
+		if (xas.xa_index != index ||
+		    (xa_to_value(entry) & mask) != attrs)
 			return false;
 	}
 
@@ -2532,7 +2533,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
 	mutex_lock(&kvm->slots_lock);
 
 	/* Nothing to do if the entire range as the desired attributes. */
-	if (kvm_range_has_memory_attributes(kvm, start, end, attributes))
+	if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes))
 		goto out_unlock;
 
 	/*
-- 
cgit v1.3


From e4ee5447927377c55777b73fe497a2455a25f948 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 11 Jul 2024 18:27:55 -0400
Subject: KVM: guest_memfd: let kvm_gmem_populate() operate only on private
 gfns

This check is currently performed by sev_gmem_post_populate(), but it
applies to all callers of kvm_gmem_populate(): the point of the function
is that the memory is being encrypted and some work has to be done
on all the gfns in order to encrypt them.

Therefore, check the KVM_MEMORY_ATTRIBUTE_PRIVATE attribute prior
to invoking the callback, and stop the operation if a shared page
is encountered.  Because CONFIG_KVM_PRIVATE_MEM in principle does
not require attributes, this makes kvm_gmem_populate() depend on
CONFIG_KVM_GENERIC_PRIVATE_MEM (which does require them).

Reviewed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c   |  7 -------
 include/linux/kvm_host.h |  2 ++
 virt/kvm/guest_memfd.c   | 12 ++++++++++++
 3 files changed, 14 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 752d2fff0f10..532df12b43c5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2279,13 +2279,6 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf
 		bool assigned;
 		int level;
 
-		if (!kvm_mem_is_private(kvm, gfn)) {
-			pr_debug("%s: Failed to ensure GFN 0x%llx has private memory attribute set\n",
-				 __func__, gfn);
-			ret = -EINVAL;
-			goto err;
-		}
-
 		ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level);
 		if (ret || assigned) {
 			pr_debug("%s: Failed to ensure GFN 0x%llx RMP entry is initial shared state, ret: %d assigned: %d\n",
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c223b97df03e..79a6b1a63027 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2449,6 +2449,7 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
 #endif
 
+#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
 /**
  * kvm_gmem_populate() - Populate/prepare a GPA range with guest data
  *
@@ -2475,6 +2476,7 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 
 long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque);
+#endif
 
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
 void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 319ec491ca47..95e338a29910 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -612,6 +612,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
 
+#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
 long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque)
 {
@@ -665,11 +666,21 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long
 		    (npages - i) < (1 << max_order))
 			max_order = 0;
 
+		ret = -EINVAL;
+		while (!kvm_range_has_memory_attributes(kvm, gfn, gfn + (1 << max_order),
+							KVM_MEMORY_ATTRIBUTE_PRIVATE,
+							KVM_MEMORY_ATTRIBUTE_PRIVATE)) {
+			if (!max_order)
+				goto put_folio_and_exit;
+			max_order--;
+		}
+
 		p = src ? src + i * PAGE_SIZE : NULL;
 		ret = post_populate(kvm, gfn, pfn, p, max_order, opaque);
 		if (!ret)
 			folio_mark_uptodate(folio);
 
+put_folio_and_exit:
 		folio_put(folio);
 		if (ret)
 			break;
@@ -681,3 +692,4 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long
 	return ret && !i ? ret : i;
 }
 EXPORT_SYMBOL_GPL(kvm_gmem_populate);
+#endif
-- 
cgit v1.3


From 1a251f52cfdc417c84411a056bc142cbd77baef4 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 28 Jul 2024 15:49:18 -0700
Subject: minmax: make generic MIN() and MAX() macros available everywhere

This just standardizes the use of MIN() and MAX() macros, with the very
traditional semantics.  The goal is to use these for C constant
expressions and for top-level / static initializers, and so be able to
simplify the min()/max() macros.

These macro names were used by various kernel code - they are very
traditional, after all - and all such users have been fixed up, with a
few different approaches:

 - trivial duplicated macro definitions have been removed

   Note that 'trivial' here means that it's obviously kernel code that
   already included all the major kernel headers, and thus gets the new
   generic MIN/MAX macros automatically.

 - non-trivial duplicated macro definitions are guarded with #ifndef

   This is the "yes, they define their own versions, but no, the include
   situation is not entirely obvious, and maybe they don't get the
   generic version automatically" case.

 - strange use case #1

   A couple of drivers decided that the way they want to describe their
   versioning is with

	#define MAJ 1
	#define MIN 2
	#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN)

   which adds zero value and I just did my Alexander the Great
   impersonation, and rewrote that pointless Gordian knot as

	#define DRV_VERSION "1.2"

   instead.

 - strange use case #2

   A couple of drivers thought that it's a good idea to have a random
   'MIN' or 'MAX' define for a value or index into a table, rather than
   the traditional macro that takes arguments.

   These values were re-written as C enum's instead. The new
   function-line macros only expand when followed by an open
   parenthesis, and thus don't clash with enum use.

Happily, there weren't really all that many of these cases, and a lot of
users already had the pattern of using '#ifndef' guarding (or in one
case just using '#undef MIN') before defining their own private version
that does the same thing. I left such cases alone.

Cc: David Laight <David.Laight@aculab.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/um/drivers/mconsole_user.c                    |  2 ++
 drivers/edac/skx_common.h                          |  1 -
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c    |  2 ++
 .../gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c    |  2 ++
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h | 14 +++++++++----
 drivers/gpu/drm/radeon/evergreen_cs.c              |  2 ++
 drivers/hwmon/adt7475.c                            | 24 +++++++++++-----------
 drivers/media/dvb-frontends/stv0367_priv.h         |  3 +++
 drivers/net/fjes/fjes_main.c                       |  4 +---
 drivers/nfc/pn544/i2c.c                            |  2 --
 drivers/platform/x86/sony-laptop.c                 |  1 -
 drivers/scsi/isci/init.c                           |  6 +-----
 .../pci/hive_isp_css_include/math_support.h        |  5 -----
 include/linux/minmax.h                             |  2 ++
 kernel/trace/preemptirq_delay_test.c               |  2 --
 lib/btree.c                                        |  1 -
 lib/decompress_unlzma.c                            |  2 ++
 mm/zsmalloc.c                                      |  2 --
 tools/testing/selftests/mm/mremap_test.c           |  2 ++
 tools/testing/selftests/seccomp/seccomp_bpf.c      |  2 ++
 20 files changed, 43 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/arch/um/drivers/mconsole_user.c b/arch/um/drivers/mconsole_user.c
index e24298a734be..a04cd13c6315 100644
--- a/arch/um/drivers/mconsole_user.c
+++ b/arch/um/drivers/mconsole_user.c
@@ -71,7 +71,9 @@ static struct mconsole_command *mconsole_parse(struct mc_request *req)
 	return NULL;
 }
 
+#ifndef MIN
 #define MIN(a,b) ((a)<(b) ? (a):(b))
+#endif
 
 #define STRINGX(x) #x
 #define STRING(x) STRINGX(x)
diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
index 11faf1db4fa4..473421ba7a18 100644
--- a/drivers/edac/skx_common.h
+++ b/drivers/edac/skx_common.h
@@ -45,7 +45,6 @@
 #define I10NM_NUM_CHANNELS	MAX(I10NM_NUM_DDR_CHANNELS, I10NM_NUM_HBM_CHANNELS)
 #define I10NM_NUM_DIMMS		MAX(I10NM_NUM_DDR_DIMMS, I10NM_NUM_HBM_DIMMS)
 
-#define MAX(a, b)	((a) > (b) ? (a) : (b))
 #define NUM_IMC		MAX(SKX_NUM_IMC, I10NM_NUM_IMC)
 #define NUM_CHANNELS	MAX(SKX_NUM_CHANNELS, I10NM_NUM_CHANNELS)
 #define NUM_DIMMS	MAX(SKX_NUM_DIMMS, I10NM_NUM_DIMMS)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index be2638c763d7..9a406d74c0dd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -35,8 +35,10 @@
 #include "dc_stream_priv.h"
 
 #define DC_LOGGER dc->ctx->logger
+#ifndef MIN
 #define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
 #define MAX(x, y) ((x > y) ? x : y)
+#endif
 
 /*******************************************************************************
  * Private functions
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
index 7ecf76aea950..6e064e6ae949 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
@@ -25,7 +25,9 @@
 
 #include "hdcp.h"
 
+#ifndef MIN
 #define MIN(a, b) ((a) < (b) ? (a) : (b))
+#endif
 #define HDCP_I2C_ADDR 0x3a	/* 0x74 >> 1*/
 #define KSV_READ_SIZE 0xf	/* 0x6803b - 0x6802c */
 #define HDCP_MAX_AUX_TRANSACTION_SIZE 16
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h
index 6f54c410c2f9..409aeec6baa9 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h
@@ -22,12 +22,18 @@
  */
 #include <asm/div64.h>
 
-#define SHIFT_AMOUNT 16 /* We multiply all original integers with 2^SHIFT_AMOUNT to get the fInt representation */
+enum ppevvmath_constants {
+	/* We multiply all original integers with 2^SHIFT_AMOUNT to get the fInt representation */
+	SHIFT_AMOUNT	= 16,
 
-#define PRECISION 5 /* Change this value to change the number of decimal places in the final output - 5 is a good default */
+	/* Change this value to change the number of decimal places in the final output - 5 is a good default */
+	PRECISION	=  5,
 
-#define SHIFTED_2 (2 << SHIFT_AMOUNT)
-#define MAX (1 << (SHIFT_AMOUNT - 1)) - 1 /* 32767 - Might change in the future */
+	SHIFTED_2	= (2 << SHIFT_AMOUNT),
+
+	/* 32767 - Might change in the future */
+	MAX		= (1 << (SHIFT_AMOUNT - 1)) - 1,
+};
 
 /* -------------------------------------------------------------------------------
  * NEW TYPE - fINT
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 1fe6e0d883c7..e5577d2a19ef 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -33,8 +33,10 @@
 #include "evergreen_reg_safe.h"
 #include "cayman_reg_safe.h"
 
+#ifndef MIN
 #define MAX(a, b)                   (((a) > (b)) ? (a) : (b))
 #define MIN(a, b)                   (((a) < (b)) ? (a) : (b))
+#endif
 
 #define REG_SAFE_BM_SIZE ARRAY_SIZE(evergreen_reg_safe_bm)
 
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index bc186c61a2c0..382a2bb9168a 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -22,23 +22,23 @@
 #include <linux/util_macros.h>
 
 /* Indexes for the sysfs hooks */
-
-#define INPUT		0
-#define MIN		1
-#define MAX		2
-#define CONTROL		3
-#define OFFSET		3
-#define AUTOMIN		4
-#define THERM		5
-#define HYSTERSIS	6
-
+enum adt_sysfs_id {
+	INPUT		= 0,
+	MIN		= 1,
+	MAX		= 2,
+	CONTROL		= 3,
+	OFFSET		= 3,	// Dup
+	AUTOMIN		= 4,
+	THERM		= 5,
+	HYSTERSIS	= 6,
 /*
  * These are unique identifiers for the sysfs functions - unlike the
  * numbers above, these are not also indexes into an array
  */
+	ALARM		= 9,
+	FAULT		= 10,
+};
 
-#define ALARM		9
-#define FAULT		10
 
 /* 7475 Common Registers */
 
diff --git a/drivers/media/dvb-frontends/stv0367_priv.h b/drivers/media/dvb-frontends/stv0367_priv.h
index 617f605947b2..7f056d1cce82 100644
--- a/drivers/media/dvb-frontends/stv0367_priv.h
+++ b/drivers/media/dvb-frontends/stv0367_priv.h
@@ -25,8 +25,11 @@
 #endif
 
 /* MACRO definitions */
+#ifndef MIN
 #define MAX(X, Y) ((X) >= (Y) ? (X) : (Y))
 #define MIN(X, Y) ((X) <= (Y) ? (X) : (Y))
+#endif
+
 #define INRANGE(X, Y, Z) \
 	((((X) <= (Y)) && ((Y) <= (Z))) || \
 	(((Z) <= (Y)) && ((Y) <= (X))) ? 1 : 0)
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index b3ddc9a629d9..fad5b6564464 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -14,9 +14,7 @@
 #include "fjes.h"
 #include "fjes_trace.h"
 
-#define MAJ 1
-#define MIN 2
-#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN)
+#define DRV_VERSION "1.2"
 #define DRV_NAME	"fjes"
 char fjes_driver_name[] = DRV_NAME;
 char fjes_driver_version[] = DRV_VERSION;
diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index 9fe664960b38..e2a6575b9ff7 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -126,8 +126,6 @@ struct pn544_i2c_fw_secure_blob {
 #define PN544_FW_CMD_RESULT_COMMAND_REJECTED 0xE0
 #define PN544_FW_CMD_RESULT_CHUNK_ERROR 0xE6
 
-#define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
-
 #define PN544_FW_WRITE_BUFFER_MAX_LEN 0x9f7
 #define PN544_FW_I2C_MAX_PAYLOAD PN544_HCI_I2C_LLC_MAX_SIZE
 #define PN544_FW_I2C_WRITE_FRAME_HEADER_LEN 8
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index 3e94fdd1ea52..3197aaa69da7 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -757,7 +757,6 @@ static union acpi_object *__call_snc_method(acpi_handle handle, char *method,
 	return result;
 }
 
-#define MIN(a, b)	(a > b ? b : a)
 static int sony_nc_buffer_call(acpi_handle handle, char *name, u64 *value,
 		void *buffer, size_t buflen)
 {
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index d31884f82f2a..73085d2f5c43 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -65,11 +65,7 @@
 #include "task.h"
 #include "probe_roms.h"
 
-#define MAJ 1
-#define MIN 2
-#define BUILD 0
-#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
-	__stringify(BUILD)
+#define DRV_VERSION "1.2.0"
 
 MODULE_VERSION(DRV_VERSION);
 
diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h b/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h
index 7349943bba2b..160c496784b7 100644
--- a/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h
+++ b/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h
@@ -22,11 +22,6 @@
 /* force a value to a lower even value */
 #define EVEN_FLOOR(x)        ((x) & ~1)
 
-/* for preprocessor and array sizing use MIN and MAX
-   otherwise use min and max */
-#define MAX(a, b)            (((a) > (b)) ? (a) : (b))
-#define MIN(a, b)            (((a) < (b)) ? (a) : (b))
-
 #define CEIL_DIV(a, b)       (((b) != 0) ? ((a) + (b) - 1) / (b) : 0)
 #define CEIL_MUL(a, b)       (CEIL_DIV(a, b) * (b))
 #define CEIL_MUL2(a, b)      (((a) + (b) - 1) & ~((b) - 1))
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index 9c2848abc804..fc384714da45 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -277,6 +277,8 @@ static inline bool in_range32(u32 val, u32 start, u32 len)
  * Use these carefully: no type checking, and uses the arguments
  * multiple times. Use for obvious constants only.
  */
+#define MIN(a,b) __cmp(min,a,b)
+#define MAX(a,b) __cmp(max,a,b)
 #define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b))
 #define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b))
 
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
index cb0871fbdb07..314ffc143039 100644
--- a/kernel/trace/preemptirq_delay_test.c
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -34,8 +34,6 @@ MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on");
 
 static struct completion done;
 
-#define MIN(x, y) ((x) < (y) ? (x) : (y))
-
 static void busy_wait(ulong time)
 {
 	u64 start, end;
diff --git a/lib/btree.c b/lib/btree.c
index 49420cae3a83..bb81d3393ac5 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -43,7 +43,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 
-#define MAX(a, b) ((a) > (b) ? (a) : (b))
 #define NODESIZE MAX(L1_CACHE_BYTES, 128)
 
 struct btree_geo {
diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c
index 20a858031f12..9d34d35908da 100644
--- a/lib/decompress_unlzma.c
+++ b/lib/decompress_unlzma.c
@@ -37,7 +37,9 @@
 
 #include <linux/decompress/mm.h>
 
+#ifndef MIN
 #define	MIN(a, b) (((a) < (b)) ? (a) : (b))
+#endif
 
 static long long INIT read_int(unsigned char *ptr, int size)
 {
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 5d6581ab7c07..2d3163e4da96 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -120,8 +120,6 @@
 #define CLASS_BITS	8
 #define MAGIC_VAL_BITS	8
 
-#define MAX(a, b) ((a) >= (b) ? (a) : (b))
-
 #define ZS_MAX_PAGES_PER_ZSPAGE	(_AC(CONFIG_ZSMALLOC_CHAIN_SIZE, UL))
 
 /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index 1b03bcfaefdf..5a3a9bcba640 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -22,8 +22,10 @@
 #define VALIDATION_DEFAULT_THRESHOLD 4	/* 4MB */
 #define VALIDATION_NO_THRESHOLD 0	/* Verify the entire region */
 
+#ifndef MIN
 #define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
 #define MAX(X, Y) ((X) > (Y) ? (X) : (Y))
+#endif
 #define SIZE_MB(m) ((size_t)m * (1024 * 1024))
 #define SIZE_KB(k) ((size_t)k * 1024)
 
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index e3f97f90d8db..8c3a73461475 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -60,7 +60,9 @@
 #define SKIP(s, ...)	XFAIL(s, ##__VA_ARGS__)
 #endif
 
+#ifndef MIN
 #define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
+#endif
 
 #ifndef PR_SET_PTRACER
 # define PR_SET_PTRACER 0x59616d61
-- 
cgit v1.3


From dc1c8034e31b14a2e5e212104ec508aec44ce1b9 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 28 Jul 2024 20:24:12 -0700
Subject: minmax: simplify min()/max()/clamp() implementation

Now that we no longer have any C constant expression contexts (ie array
size declarations or static initializers) that use min() or max(), we
can simpify the implementation by not having to worry about the result
staying as a C constant expression.

So now we can unconditionally just use temporary variables of the right
type, and get rid of the excessive expansion that used to come from the
use of

   __builtin_choose_expr(__is_constexpr(...), ..

to pick the specialized code for constant expressions.

Another expansion simplification is to pass the temporary variables (in
addition to the original expression) to our __types_ok() macro.  That
may superficially look like it complicates the macro, but when we only
want the type of the expression, expanding the temporary variable names
is much simpler and smaller than expanding the potentially complicated
original expression.

As a result, on my machine, doing a

  $ time make drivers/staging/media/atomisp/pci/isp/kernels/ynr/ynr_1.0/ia_css_ynr.host.i

goes from

	real	0m16.621s
	user	0m15.360s
	sys	0m1.221s

to

	real	0m2.532s
	user	0m2.091s
	sys	0m0.452s

because the token expansion goes down dramatically.

In particular, the longest line expansion (which was line 71 of that
'ia_css_ynr.host.c' file) shrinks from 23,338kB (yes, 23MB for one
single line) to "just" 1,444kB (now "only" 1.4MB).

And yes, that line is still the line from hell, because it's doing
multiple levels of "min()/max()" expansion thanks to some of them being
hidden inside the uDIGIT_FITTING() macro.

Lorenzo has a nice cleanup patch that makes that driver use inline
functions instead of macros for sDIGIT_FITTING() and uDIGIT_FITTING(),
which will fix that line once and for all, but the 16-fold reduction in
this case does show why we need to simplify these helpers.

Cc: David Laight <David.Laight@aculab.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/minmax.h | 43 ++++++++++++++++++++-----------------------
 1 file changed, 20 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index fc384714da45..e3e4353df983 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -35,10 +35,10 @@
 #define __is_noneg_int(x)	\
 	(__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0)
 
-#define __types_ok(x, y) 					\
-	(__is_signed(x) == __is_signed(y) ||			\
-		__is_signed((x) + 0) == __is_signed((y) + 0) ||	\
-		__is_noneg_int(x) || __is_noneg_int(y))
+#define __types_ok(x, y, ux, uy) 				\
+	(__is_signed(ux) == __is_signed(uy) ||			\
+	 __is_signed((ux) + 0) == __is_signed((uy) + 0) ||	\
+	 __is_noneg_int(x) || __is_noneg_int(y))
 
 #define __cmp_op_min <
 #define __cmp_op_max >
@@ -51,34 +51,31 @@
 #define __cmp_once(op, type, x, y) \
 	__cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_))
 
-#define __careful_cmp_once(op, x, y) ({			\
-	static_assert(__types_ok(x, y),			\
+#define __careful_cmp_once(op, x, y, ux, uy) ({		\
+	__auto_type ux = (x); __auto_type uy = (y);	\
+	static_assert(__types_ok(x, y, ux, uy),		\
 		#op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \
-	__cmp_once(op, __auto_type, x, y); })
+	__cmp(op, ux, uy); })
 
-#define __careful_cmp(op, x, y)					\
-	__builtin_choose_expr(__is_constexpr((x) - (y)),	\
-		__cmp(op, x, y), __careful_cmp_once(op, x, y))
+#define __careful_cmp(op, x, y) \
+	__careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_))
 
 #define __clamp(val, lo, hi)	\
 	((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val)))
 
-#define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({		\
-	typeof(val) unique_val = (val);						\
-	typeof(lo) unique_lo = (lo);						\
-	typeof(hi) unique_hi = (hi);						\
+#define __clamp_once(val, lo, hi, uval, ulo, uhi) ({				\
+	__auto_type uval = (val);						\
+	__auto_type ulo = (lo);							\
+	__auto_type uhi = (hi);							\
 	static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), 	\
 			(lo) <= (hi), true),					\
 		"clamp() low limit " #lo " greater than high limit " #hi);	\
-	static_assert(__types_ok(val, lo), "clamp() 'lo' signedness error");	\
-	static_assert(__types_ok(val, hi), "clamp() 'hi' signedness error");	\
-	__clamp(unique_val, unique_lo, unique_hi); })
-
-#define __careful_clamp(val, lo, hi) ({					\
-	__builtin_choose_expr(__is_constexpr((val) - (lo) + (hi)),	\
-		__clamp(val, lo, hi),					\
-		__clamp_once(val, lo, hi, __UNIQUE_ID(__val),		\
-			     __UNIQUE_ID(__lo), __UNIQUE_ID(__hi))); })
+	static_assert(__types_ok(uval, lo, uval, ulo), "clamp() 'lo' signedness error");	\
+	static_assert(__types_ok(uval, hi, uval, uhi), "clamp() 'hi' signedness error");	\
+	__clamp(uval, ulo, uhi); })
+
+#define __careful_clamp(val, lo, hi) \
+	__clamp_once(val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_))
 
 /**
  * min - return minimum of two values of the same or compatible types
-- 
cgit v1.3


From 2accfdb7eff65f390c4308b0e9cb7c3fe48ad63c Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 29 Jul 2024 10:58:28 -0700
Subject: profiling: attempt to remove per-cpu profile flip buffer

This is the really old legacy kernel profiling code, which has long
since been obviated by "real profiling" (ie 'prof' and company), and
mainly remains as a source of syzbot reports.

There are anecdotal reports that people still use it for boot-time
profiling, but it's unlikely that such use would care about the old NUMA
optimizations in this code from 2004 (commit ad02973d42: "profile: 512x
Altix timer interrupt livelock fix" in the BK import archive at [1])

So in order to head off future syzbot reports, let's try to simplify
this code and get rid of the per-cpu profile buffers that are quite a
large portion of the complexity footprint of this thing (including CPU
hotplug callbacks etc).

It's unlikely anybody will actually notice, or possibly, as Thomas put
it: "Only people who indulge in nostalgia will notice :)".

That said, if it turns out that this code is actually actively used by
somebody, we can always revert this removal.  Thus the "attempt" in the
summary line.

[ Note: in a small nod to "the profiling code can cause NUMA problems",
  this also removes the "increment the last entry in the profiling array
  on any unknown hits" logic. That would account any program counter in
  a module to that single counter location, and might exacerbate any
  NUMA cacheline bouncing issues ]

Link: https://lore.kernel.org/all/CAHk-=wgs52BxT4Zjmjz8aNvHWKxf5_ThBY4bYL1Y6CTaNL2dTw@mail.gmail.com/
Link:  https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git [1]
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cpuhotplug.h |   1 -
 kernel/profile.c           | 183 +--------------------------------------------
 2 files changed, 2 insertions(+), 182 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 51ba681b915a..affdd890899e 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -100,7 +100,6 @@ enum cpuhp_state {
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-	CPUHP_PROFILE_PREPARE,
 	CPUHP_X2APIC_PREPARE,
 	CPUHP_SMPCFD_PREPARE,
 	CPUHP_RELAY_PREPARE,
diff --git a/kernel/profile.c b/kernel/profile.c
index 4654c6cd984e..2dfb0f4e755c 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -129,180 +129,13 @@ int __ref profile_init(void)
 	return -ENOMEM;
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS)
-/*
- * Each cpu has a pair of open-addressed hashtables for pending
- * profile hits. read_profile() IPI's all cpus to request them
- * to flip buffers and flushes their contents to prof_buffer itself.
- * Flip requests are serialized by the profile_flip_mutex. The sole
- * use of having a second hashtable is for avoiding cacheline
- * contention that would otherwise happen during flushes of pending
- * profile hits required for the accuracy of reported profile hits
- * and so resurrect the interrupt livelock issue.
- *
- * The open-addressed hashtables are indexed by profile buffer slot
- * and hold the number of pending hits to that profile buffer slot on
- * a cpu in an entry. When the hashtable overflows, all pending hits
- * are accounted to their corresponding profile buffer slots with
- * atomic_add() and the hashtable emptied. As numerous pending hits
- * may be accounted to a profile buffer slot in a hashtable entry,
- * this amortizes a number of atomic profile buffer increments likely
- * to be far larger than the number of entries in the hashtable,
- * particularly given that the number of distinct profile buffer
- * positions to which hits are accounted during short intervals (e.g.
- * several seconds) is usually very small. Exclusion from buffer
- * flipping is provided by interrupt disablement (note that for
- * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from
- * process context).
- * The hash function is meant to be lightweight as opposed to strong,
- * and was vaguely inspired by ppc64 firmware-supported inverted
- * pagetable hash functions, but uses a full hashtable full of finite
- * collision chains, not just pairs of them.
- *
- * -- nyc
- */
-static void __profile_flip_buffers(void *unused)
-{
-	int cpu = smp_processor_id();
-
-	per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu);
-}
-
-static void profile_flip_buffers(void)
-{
-	int i, j, cpu;
-
-	mutex_lock(&profile_flip_mutex);
-	j = per_cpu(cpu_profile_flip, get_cpu());
-	put_cpu();
-	on_each_cpu(__profile_flip_buffers, NULL, 1);
-	for_each_online_cpu(cpu) {
-		struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j];
-		for (i = 0; i < NR_PROFILE_HIT; ++i) {
-			if (!hits[i].hits) {
-				if (hits[i].pc)
-					hits[i].pc = 0;
-				continue;
-			}
-			atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]);
-			hits[i].hits = hits[i].pc = 0;
-		}
-	}
-	mutex_unlock(&profile_flip_mutex);
-}
-
-static void profile_discard_flip_buffers(void)
-{
-	int i, cpu;
-
-	mutex_lock(&profile_flip_mutex);
-	i = per_cpu(cpu_profile_flip, get_cpu());
-	put_cpu();
-	on_each_cpu(__profile_flip_buffers, NULL, 1);
-	for_each_online_cpu(cpu) {
-		struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i];
-		memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit));
-	}
-	mutex_unlock(&profile_flip_mutex);
-}
-
-static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
-{
-	unsigned long primary, secondary, flags, pc = (unsigned long)__pc;
-	int i, j, cpu;
-	struct profile_hit *hits;
-
-	pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1);
-	i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
-	secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
-	cpu = get_cpu();
-	hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)];
-	if (!hits) {
-		put_cpu();
-		return;
-	}
-	/*
-	 * We buffer the global profiler buffer into a per-CPU
-	 * queue and thus reduce the number of global (and possibly
-	 * NUMA-alien) accesses. The write-queue is self-coalescing:
-	 */
-	local_irq_save(flags);
-	do {
-		for (j = 0; j < PROFILE_GRPSZ; ++j) {
-			if (hits[i + j].pc == pc) {
-				hits[i + j].hits += nr_hits;
-				goto out;
-			} else if (!hits[i + j].hits) {
-				hits[i + j].pc = pc;
-				hits[i + j].hits = nr_hits;
-				goto out;
-			}
-		}
-		i = (i + secondary) & (NR_PROFILE_HIT - 1);
-	} while (i != primary);
-
-	/*
-	 * Add the current hit(s) and flush the write-queue out
-	 * to the global buffer:
-	 */
-	atomic_add(nr_hits, &prof_buffer[pc]);
-	for (i = 0; i < NR_PROFILE_HIT; ++i) {
-		atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]);
-		hits[i].pc = hits[i].hits = 0;
-	}
-out:
-	local_irq_restore(flags);
-	put_cpu();
-}
-
-static int profile_dead_cpu(unsigned int cpu)
-{
-	struct page *page;
-	int i;
-
-	for (i = 0; i < 2; i++) {
-		if (per_cpu(cpu_profile_hits, cpu)[i]) {
-			page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]);
-			per_cpu(cpu_profile_hits, cpu)[i] = NULL;
-			__free_page(page);
-		}
-	}
-	return 0;
-}
-
-static int profile_prepare_cpu(unsigned int cpu)
-{
-	int i, node = cpu_to_mem(cpu);
-	struct page *page;
-
-	per_cpu(cpu_profile_flip, cpu) = 0;
-
-	for (i = 0; i < 2; i++) {
-		if (per_cpu(cpu_profile_hits, cpu)[i])
-			continue;
-
-		page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
-		if (!page) {
-			profile_dead_cpu(cpu);
-			return -ENOMEM;
-		}
-		per_cpu(cpu_profile_hits, cpu)[i] = page_address(page);
-
-	}
-	return 0;
-}
-
-#else /* !CONFIG_SMP */
-#define profile_flip_buffers()		do { } while (0)
-#define profile_discard_flip_buffers()	do { } while (0)
-
 static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
 {
 	unsigned long pc;
 	pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift;
-	atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]);
+	if (pc < prof_len)
+		atomic_add(nr_hits, &prof_buffer[pc]);
 }
-#endif /* !CONFIG_SMP */
 
 void profile_hits(int type, void *__pc, unsigned int nr_hits)
 {
@@ -340,7 +173,6 @@ read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	char *pnt;
 	unsigned long sample_step = 1UL << prof_shift;
 
-	profile_flip_buffers();
 	if (p >= (prof_len+1)*sizeof(unsigned int))
 		return 0;
 	if (count > (prof_len+1)*sizeof(unsigned int) - p)
@@ -386,7 +218,6 @@ static ssize_t write_profile(struct file *file, const char __user *buf,
 			return -EINVAL;
 	}
 #endif
-	profile_discard_flip_buffers();
 	memset(prof_buffer, 0, prof_len * sizeof(atomic_t));
 	return count;
 }
@@ -404,20 +235,10 @@ int __ref create_proc_profile(void)
 
 	if (!prof_on)
 		return 0;
-#ifdef CONFIG_SMP
-	err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE",
-				profile_prepare_cpu, profile_dead_cpu);
-	if (err)
-		return err;
-#endif
 	entry = proc_create("profile", S_IWUSR | S_IRUGO,
 			    NULL, &profile_proc_ops);
 	if (entry)
 		proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));
-#ifdef CONFIG_SMP
-	else
-		cpuhp_remove_state(CPUHP_PROFILE_PREPARE);
-#endif
 	return err;
 }
 subsys_initcall(create_proc_profile);
-- 
cgit v1.3


From 22f5468731491e53356ba7c028f0fdea20b18e2c Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 30 Jul 2024 10:36:47 -0700
Subject: minmax: improve macro expansion and type checking

This clarifies the rules for min()/max()/clamp() type checking and makes
them a much more efficient macro expansion.

In particular, we now look at the type and range of the inputs to see
whether they work together, generating a mask of acceptable comparisons,
and then just verifying that the inputs have a shared case:

 - an expression with a signed type can be used for
    (1) signed comparisons
    (2) unsigned comparisons if it is statically known to have a
        non-negative value

 - an expression with an unsigned type can be used for
    (3) unsigned comparison
    (4) signed comparisons if the type is smaller than 'int' and thus
        the C integer promotion rules will make it signed anyway

Here rule (1) and (3) are obvious, and rule (2) is important in order to
allow obvious trivial constants to be used together with unsigned
values.

Rule (4) is not necessarily a good idea, but matches what we used to do,
and we have extant cases of this situation in the kernel.  Notably with
bcachefs having an expression like

	min(bch2_bucket_sectors_dirty(a), ca->mi.bucket_size)

where bch2_bucket_sectors_dirty() returns an 's64', and
'ca->mi.bucket_size' is of type 'u16'.

Technically that bcachefs comparison is clearly sensible on a C type
level, because the 'u16' will go through the normal C integer promotion,
and become 'int', and then we're comparing two signed values and
everything looks sane.

However, it's not entirely clear that a 'min(s64,u16)' operation makes a
lot of conceptual sense, and it's possible that we will remove rule (4).
After all, the _reason_ we have these complicated type checks is exactly
that the C type promotion rules are not very intuitive.

But at least for now the rule is in place for backwards compatibility.

Also note that rule (2) existed before, but is hugely relaxed by this
commit.  It used to be true only for the simplest compile-time
non-negative integer constants.  The new macro model will allow cases
where the compiler can trivially see that an expression is non-negative
even if it isn't necessarily a constant.

For example, the amdgpu driver does

	min_t(size_t, sizeof(fru_info->serial), pia[addr] & 0x3F));

because our old 'min()' macro would see that 'pia[addr] & 0x3F' is of
type 'int' and clearly not a C constant expression, so doing a 'min()'
with a 'size_t' is a signedness violation.

Our new 'min()' macro still sees that 'pia[addr] & 0x3F' is of type
'int', but is smart enough to also see that it is clearly non-negative,
and thus would allow that case without any complaints.

Cc: Arnd Bergmann <arnd@kernel.org>
Cc: David Laight <David.Laight@aculab.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler.h |  9 ++++++
 include/linux/minmax.h   | 74 ++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 68 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 2594553bb30b..2df665fa2964 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -296,6 +296,15 @@ static inline void *offset_to_ptr(const int *off)
 #define is_signed_type(type) (((type)(-1)) < (__force type)1)
 #define is_unsigned_type(type) (!is_signed_type(type))
 
+/*
+ * Useful shorthand for "is this condition known at compile-time?"
+ *
+ * Note that the condition may involve non-constant values,
+ * but the compiler may know enough about the details of the
+ * values to determine that the condition is statically true.
+ */
+#define statically_true(x) (__builtin_constant_p(x) && (x))
+
 /*
  * This is needed in functions which generate the stack canary, see
  * arch/x86/kernel/smpboot.c::start_secondary() for an example.
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index e3e4353df983..41da6f85a407 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -26,19 +26,63 @@
 #define __typecheck(x, y) \
 	(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
 
-/* is_signed_type() isn't a constexpr for pointer types */
-#define __is_signed(x) 								\
-	__builtin_choose_expr(__is_constexpr(is_signed_type(typeof(x))),	\
-		is_signed_type(typeof(x)), 0)
+/*
+ * __sign_use for integer expressions:
+ *   bit #0 set if ok for unsigned comparisons
+ *   bit #1 set if ok for signed comparisons
+ *
+ * In particular, statically non-negative signed integer
+ * expressions are ok for both.
+ *
+ * NOTE! Unsigned types smaller than 'int' are implicitly
+ * converted to 'int' in expressions, and are accepted for
+ * signed conversions for now. This is debatable.
+ *
+ * Note that 'x' is the original expression, and 'ux' is
+ * the unique variable that contains the value.
+ *
+ * We use 'ux' for pure type checking, and 'x' for when
+ * we need to look at the value (but without evaluating
+ * it for side effects! Careful to only ever evaluate it
+ * with sizeof() or __builtin_constant_p() etc).
+ *
+ * Pointers end up being checked by the normal C type
+ * rules at the actual comparison, and these expressions
+ * only need to be careful to not cause warnings for
+ * pointer use.
+ */
+#define __signed_type_use(x,ux) (2+__is_nonneg(x,ux))
+#define __unsigned_type_use(x,ux) (1+2*(sizeof(ux)<4))
+#define __sign_use(x,ux) (is_signed_type(typeof(ux))? \
+	__signed_type_use(x,ux):__unsigned_type_use(x,ux))
+
+/*
+ * To avoid warnings about casting pointers to integers
+ * of different sizes, we need that special sign type.
+ *
+ * On 64-bit we can just always use 'long', since any
+ * integer or pointer type can just be cast to that.
+ *
+ * This does not work for 128-bit signed integers since
+ * the cast would truncate them, but we do not use s128
+ * types in the kernel (we do use 'u128', but they will
+ * be handled by the !is_signed_type() case).
+ *
+ * NOTE! The cast is there only to avoid any warnings
+ * from when values that aren't signed integer types.
+ */
+#ifdef CONFIG_64BIT
+  #define __signed_type(ux) long
+#else
+  #define __signed_type(ux) typeof(__builtin_choose_expr(sizeof(ux)>4,1LL,1L))
+#endif
+#define __is_nonneg(x,ux) statically_true((__signed_type(ux))(x)>=0)
 
-/* True for a non-negative signed int constant */
-#define __is_noneg_int(x)	\
-	(__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0)
+#define __types_ok(x,y,ux,uy) \
+	(__sign_use(x,ux) & __sign_use(y,uy))
 
-#define __types_ok(x, y, ux, uy) 				\
-	(__is_signed(ux) == __is_signed(uy) ||			\
-	 __is_signed((ux) + 0) == __is_signed((uy) + 0) ||	\
-	 __is_noneg_int(x) || __is_noneg_int(y))
+#define __types_ok3(x,y,z,ux,uy,uz) \
+	(__sign_use(x,ux) & __sign_use(y,uy) & __sign_use(z,uz))
 
 #define __cmp_op_min <
 #define __cmp_op_max >
@@ -53,8 +97,8 @@
 
 #define __careful_cmp_once(op, x, y, ux, uy) ({		\
 	__auto_type ux = (x); __auto_type uy = (y);	\
-	static_assert(__types_ok(x, y, ux, uy),		\
-		#op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \
+	BUILD_BUG_ON_MSG(!__types_ok(x,y,ux,uy),	\
+		#op"("#x", "#y") signedness error");	\
 	__cmp(op, ux, uy); })
 
 #define __careful_cmp(op, x, y) \
@@ -70,8 +114,8 @@
 	static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), 	\
 			(lo) <= (hi), true),					\
 		"clamp() low limit " #lo " greater than high limit " #hi);	\
-	static_assert(__types_ok(uval, lo, uval, ulo), "clamp() 'lo' signedness error");	\
-	static_assert(__types_ok(uval, hi, uval, uhi), "clamp() 'hi' signedness error");	\
+	BUILD_BUG_ON_MSG(!__types_ok3(val,lo,hi,uval,ulo,uhi),			\
+		"clamp("#val", "#lo", "#hi") signedness error");		\
 	__clamp(uval, ulo, uhi); })
 
 #define __careful_clamp(val, lo, hi) \
-- 
cgit v1.3


From 89add40066f9ed9abe5f7f886fe5789ff7e0c50e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 29 Jul 2024 16:10:12 -0400
Subject: net: drop bad gso csum_start and offset in virtio_net_hdr

Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb
for GSO packets.

The function already checks that a checksum requested with
VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets
this might not hold for segs after segmentation.

Syzkaller demonstrated to reach this warning in skb_checksum_help

	offset = skb_checksum_start_offset(skb);
	ret = -EINVAL;
	if (WARN_ON_ONCE(offset >= skb_headlen(skb)))

By injecting a TSO packet:

WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0
 ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774
 ip_finish_output_gso net/ipv4/ip_output.c:279 [inline]
 __ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301
 iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82
 ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813
 __gre_xmit net/ipv4/ip_gre.c:469 [inline]
 ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661
 __netdev_start_xmit include/linux/netdevice.h:4850 [inline]
 netdev_start_xmit include/linux/netdevice.h:4864 [inline]
 xmit_one net/core/dev.c:3595 [inline]
 dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611
 __dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261
 packet_snd net/packet/af_packet.c:3073 [inline]

The geometry of the bad input packet at tcp_gso_segment:

[   52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0
[   52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244
[   52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0))
[   52.003050][ T8403] csum(0x60000c7 start=199 offset=1536
ip_summed=3 complete_sw=0 valid=0 level=0)

Mitigate with stricter input validation.

csum_offset: for GSO packets, deduce the correct value from gso_type.
This is already done for USO. Extend it to TSO. Let UFO be:
udp[46]_ufo_fragment ignores these fields and always computes the
checksum in software.

csum_start: finding the real offset requires parsing to the transport
header. Do not add a parser, use existing segmentation parsing. Thanks
to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded.
Again test both TSO and USO. Do not test UFO for the above reason, and
do not test UDP tunnel offload.

GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be
CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit
from devices with no checksum offload"), but then still these fields
are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no
need to test for ip_summed == CHECKSUM_PARTIAL first.

This revises an existing fix mentioned in the Fixes tag, which broke
small packets with GSO offload, as detected by kselftests.

Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871
Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org
Fixes: e269d79c7d35 ("net: missing check virtio")
Cc: stable@vger.kernel.org
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240729201108.1615114-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/virtio_net.h | 16 +++++-----------
 net/ipv4/tcp_offload.c     |  3 +++
 net/ipv4/udp_offload.c     |  4 ++++
 3 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index d1d7825318c3..6c395a2600e8 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 	unsigned int thlen = 0;
 	unsigned int p_off = 0;
 	unsigned int ip_proto;
-	u64 ret, remainder, gso_size;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
 		u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
 
-		if (hdr->gso_size) {
-			gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
-			ret = div64_u64_rem(skb->len, gso_size, &remainder);
-			if (!(ret && (hdr->gso_size > needed) &&
-						((remainder > needed) || (remainder == 0)))) {
-				return -EINVAL;
-			}
-			skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG;
-		}
-
 		if (!pskb_may_pull(skb, needed))
 			return -EINVAL;
 
@@ -182,6 +171,11 @@ retry:
 			if (gso_type != SKB_GSO_UDP_L4)
 				return -EINVAL;
 			break;
+		case SKB_GSO_TCPV4:
+		case SKB_GSO_TCPV6:
+			if (skb->csum_offset != offsetof(struct tcphdr, check))
+				return -EINVAL;
+			break;
 		}
 
 		/* Kernel has a special handling for GSO_BY_FRAGS. */
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 4b791e74529e..e4ad3311e148 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	if (thlen < sizeof(*th))
 		goto out;
 
+	if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb)))
+		goto out;
+
 	if (!pskb_may_pull(skb, thlen))
 		goto out;
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index aa2e0a28ca61..bc8a9da750fe 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 	if (gso_skb->len <= sizeof(*uh) + mss)
 		return ERR_PTR(-EINVAL);
 
+	if (unlikely(skb_checksum_start(gso_skb) !=
+		     skb_transport_header(gso_skb)))
+		return ERR_PTR(-EINVAL);
+
 	if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
 		/* Packet is from an untrusted source, reset gso_segs. */
 		skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
-- 
cgit v1.3


From 21b136cc63d2a9ddd60d4699552b69c214b32964 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 30 Jul 2024 15:44:16 -0700
Subject: minmax: fix up min3() and max3() too

David Laight pointed out that we should deal with the min3() and max3()
mess too, which still does excessive expansion.

And our current macros are actually rather broken.

In particular, the macros did this:

  #define min3(x, y, z) min((typeof(x))min(x, y), z)
  #define max3(x, y, z) max((typeof(x))max(x, y), z)

and that not only is a nested expansion of possibly very complex
arguments with all that involves, the typing with that "typeof()" cast
is completely wrong.

For example, imagine what happens in max3() if 'x' happens to be a
'unsigned char', but 'y' and 'z' are 'unsigned long'.  The types are
compatible, and there's no warning - but the result is just random
garbage.

No, I don't think we've ever hit that issue in practice, but since we
now have sane infrastructure for doing this right, let's just use it.
It fixes any excessive expansion, and also avoids these kinds of broken
type issues.

Requested-by: David Laight <David.Laight@aculab.com>
Acked-by: Arnd Bergmann <arnd@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/minmax.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index 41da6f85a407..98008dd92153 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -152,13 +152,20 @@
 #define umax(x, y)	\
 	__careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull)
 
+#define __careful_op3(op, x, y, z, ux, uy, uz) ({			\
+	__auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\
+	BUILD_BUG_ON_MSG(!__types_ok3(x,y,z,ux,uy,uz),			\
+		#op"3("#x", "#y", "#z") signedness error");		\
+	__cmp(op, ux, __cmp(op, uy, uz)); })
+
 /**
  * min3 - return minimum of three values
  * @x: first value
  * @y: second value
  * @z: third value
  */
-#define min3(x, y, z) min((typeof(x))min(x, y), z)
+#define min3(x, y, z) \
+	__careful_op3(min, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_))
 
 /**
  * max3 - return maximum of three values
@@ -166,7 +173,8 @@
  * @y: second value
  * @z: third value
  */
-#define max3(x, y, z) max((typeof(x))max(x, y), z)
+#define max3(x, y, z) \
+	__careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_))
 
 /**
  * min_not_zero - return the minimum that is _not_ zero, unless both are zero
-- 
cgit v1.3


From 3908ba2e0b2476e2ec13e15967bf6a37e449f2af Mon Sep 17 00:00:00 2001
From: Nick Hu <nick.hu@sifive.com>
Date: Wed, 17 Jul 2024 11:17:14 +0800
Subject: RISC-V: Enable the IPI before workqueue_online_cpu()

Sometimes the hotplug cpu stalls at the arch_cpu_idle() for a while after
workqueue_online_cpu(). When cpu stalls at the idle loop, the reschedule
IPI is pending. However the enable bit is not enabled yet so the cpu stalls
at WFI until watchdog timeout. Therefore enable the IPI before the
workqueue_online_cpu() to fix the issue.

Fixes: 63c5484e7495 ("workqueue: Add multiple affinity scopes and interface to select them")
Signed-off-by: Nick Hu <nick.hu@sifive.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20240717031714.1946036-1-nick.hu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/sbi-ipi.c | 2 +-
 include/linux/cpuhotplug.h  | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/riscv/kernel/sbi-ipi.c b/arch/riscv/kernel/sbi-ipi.c
index 1026e22955cc..0cc5559c08d8 100644
--- a/arch/riscv/kernel/sbi-ipi.c
+++ b/arch/riscv/kernel/sbi-ipi.c
@@ -71,7 +71,7 @@ void __init sbi_ipi_init(void)
 	 * the masking/unmasking of virtual IPIs is done
 	 * via generic IPI-Mux
 	 */
-	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+	cpuhp_setup_state(CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING,
 			  "irqchip/sbi-ipi:starting",
 			  sbi_ipi_starting_cpu, NULL);
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 51ba681b915a..e30d93b807d5 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -148,6 +148,7 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_LOONGARCH_STARTING,
 	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
 	CPUHP_AP_IRQ_RISCV_IMSIC_STARTING,
+	CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
-- 
cgit v1.3


From b88f55389ad27f05ed84af9e1026aa64dbfabc9a Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Sun, 4 Aug 2024 18:48:10 +0900
Subject: profiling: remove profile=sleep support

The kernel sleep profile is no longer working due to a recursive locking
bug introduced by commit 42a20f86dc19 ("sched: Add wrapper for get_wchan()
to keep task blocked")

Booting with the 'profile=sleep' kernel command line option added or
executing

  # echo -n sleep > /sys/kernel/profiling

after boot causes the system to lock up.

Lockdep reports

  kthreadd/3 is trying to acquire lock:
  ffff93ac82e08d58 (&p->pi_lock){....}-{2:2}, at: get_wchan+0x32/0x70

  but task is already holding lock:
  ffff93ac82e08d58 (&p->pi_lock){....}-{2:2}, at: try_to_wake_up+0x53/0x370

with the call trace being

   lock_acquire+0xc8/0x2f0
   get_wchan+0x32/0x70
   __update_stats_enqueue_sleeper+0x151/0x430
   enqueue_entity+0x4b0/0x520
   enqueue_task_fair+0x92/0x6b0
   ttwu_do_activate+0x73/0x140
   try_to_wake_up+0x213/0x370
   swake_up_locked+0x20/0x50
   complete+0x2f/0x40
   kthread+0xfb/0x180

However, since nobody noticed this regression for more than two years,
let's remove 'profile=sleep' support based on the assumption that nobody
needs this functionality.

Fixes: 42a20f86dc19 ("sched: Add wrapper for get_wchan() to keep task blocked")
Cc: stable@vger.kernel.org # v5.16+
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  4 +---
 include/linux/profile.h                         |  1 -
 kernel/profile.c                                | 11 +----------
 kernel/sched/stats.c                            | 10 ----------
 4 files changed, 2 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f1384c7b59c9..09126bb8cc9f 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4798,11 +4798,9 @@
 
 	profile=	[KNL] Enable kernel profiling via /proc/profile
 			Format: [<profiletype>,]<number>
-			Param: <profiletype>: "schedule", "sleep", or "kvm"
+			Param: <profiletype>: "schedule" or "kvm"
 				[defaults to kernel profiling]
 			Param: "schedule" - profile schedule points.
-			Param: "sleep" - profile D-state sleeping (millisecs).
-				Requires CONFIG_SCHEDSTATS
 			Param: "kvm" - profile VM exits.
 			Param: <number> - step/bucket size as a power of 2 for
 				statistical time based profiling.
diff --git a/include/linux/profile.h b/include/linux/profile.h
index 2fb487f61d12..3f53cdb0c27c 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -10,7 +10,6 @@
 
 #define CPU_PROFILING	1
 #define SCHED_PROFILING	2
-#define SLEEP_PROFILING	3
 #define KVM_PROFILING	4
 
 struct proc_dir_entry;
diff --git a/kernel/profile.c b/kernel/profile.c
index ff68d3816182..1fcf1adcf4eb 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -50,20 +50,11 @@ EXPORT_SYMBOL_GPL(prof_on);
 int profile_setup(char *str)
 {
 	static const char schedstr[] = "schedule";
-	static const char sleepstr[] = "sleep";
 	static const char kvmstr[] = "kvm";
 	const char *select = NULL;
 	int par;
 
-	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
-#ifdef CONFIG_SCHEDSTATS
-		force_schedstat_enabled();
-		prof_on = SLEEP_PROFILING;
-		select = sleepstr;
-#else
-		pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
-#endif /* CONFIG_SCHEDSTATS */
-	} else if (!strncmp(str, schedstr, strlen(schedstr))) {
+	if (!strncmp(str, schedstr, strlen(schedstr))) {
 		prof_on = SCHED_PROFILING;
 		select = schedstr;
 	} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 78e48f5426ee..eb0cdcd4d921 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -92,16 +92,6 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
 
 			trace_sched_stat_blocked(p, delta);
 
-			/*
-			 * Blocking time is in units of nanosecs, so shift by
-			 * 20 to get a milliseconds-range estimation of the
-			 * amount of time that the task spent sleeping:
-			 */
-			if (unlikely(prof_on == SLEEP_PROFILING)) {
-				profile_hits(SLEEP_PROFILING,
-					     (void *)get_wchan(p),
-					     delta >> 20);
-			}
 			account_scheduler_latency(p, delta >> 10, 0);
 		}
 	}
-- 
cgit v1.3