From b57de4ffd7c6d1247fdaef8437450ab7c1dd4ed0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 19 Apr 2022 19:27:48 +0100
Subject: KVM: arm64: Simplify kvm_cpu_has_pending_timer()

kvm_cpu_has_pending_timer() ends up checking all the possible
timers for a wake-up cause. However, we already check for
pending interrupts whenever we try to wake-up a vcpu, including
the timer interrupts.

Obviously, doing the same work twice is once too many. Reduce
this helper to almost nothing, but keep it around, as we are
going to make use of it soon.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220419182755.601427-4-maz@kernel.org
---
 include/kvm/arm_arch_timer.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/kvm')

diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 51c19381108c..cd6d8f260eab 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -76,8 +76,6 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
 int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
 int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
 
-bool kvm_timer_is_pending(struct kvm_vcpu *vcpu);
-
 u64 kvm_phys_timer_read(void);
 
 void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu);
-- 
cgit v1.2.3


From 85fbe08e4da862dc64fc10071c4a03e51b6361d0 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Mon, 2 May 2022 23:38:45 +0000
Subject: KVM: arm64: Factor out firmware register handling from psci.c

Common hypercall firmware register handing is currently employed
by psci.c. Since the upcoming patches add more of these registers,
it's better to move the generic handling to hypercall.c for a
cleaner presentation.

While we are at it, collect all the firmware registers under
fw_reg_ids[] to help implement kvm_arm_get_fw_num_regs() and
kvm_arm_copy_fw_reg_indices() in a generic way. Also, define
KVM_REG_FEATURE_LEVEL_MASK using a GENMASK instead.

No functional change intended.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Oliver Upton <oupton@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
[maz: fixed KVM_REG_FEATURE_LEVEL_MASK]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220502233853.1233742-2-rananta@google.com
---
 arch/arm64/kvm/guest.c       |   2 +-
 arch/arm64/kvm/hypercalls.c  | 184 +++++++++++++++++++++++++++++++++++++++++++
 arch/arm64/kvm/psci.c        | 183 ------------------------------------------
 include/kvm/arm_hypercalls.h |   7 ++
 include/kvm/arm_psci.h       |   7 --
 5 files changed, 192 insertions(+), 191 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 7e15b03fbdf8..0d5cca56cbda 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -18,7 +18,7 @@
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
-#include <kvm/arm_psci.h>
+#include <kvm/arm_hypercalls.h>
 #include <asm/cputype.h>
 #include <linux/uaccess.h>
 #include <asm/fpsimd.h>
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 202b8c455724..dd4e20b8d656 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -158,3 +158,187 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 	smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]);
 	return 1;
 }
+
+static const u64 kvm_arm_fw_reg_ids[] = {
+	KVM_REG_ARM_PSCI_VERSION,
+	KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1,
+	KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2,
+	KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3,
+};
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
+{
+	return ARRAY_SIZE(kvm_arm_fw_reg_ids);
+}
+
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(kvm_arm_fw_reg_ids); i++) {
+		if (put_user(kvm_arm_fw_reg_ids[i], uindices++))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+#define KVM_REG_FEATURE_LEVEL_MASK	GENMASK(3, 0)
+
+/*
+ * Convert the workaround level into an easy-to-compare number, where higher
+ * values mean better protection.
+ */
+static int get_kernel_wa_level(u64 regid)
+{
+	switch (regid) {
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+		switch (arm64_get_spectre_v2_state()) {
+		case SPECTRE_VULNERABLE:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
+		case SPECTRE_MITIGATED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL;
+		case SPECTRE_UNAFFECTED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED;
+		}
+		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+		switch (arm64_get_spectre_v4_state()) {
+		case SPECTRE_MITIGATED:
+			/*
+			 * As for the hypercall discovery, we pretend we
+			 * don't have any FW mitigation if SSBS is there at
+			 * all times.
+			 */
+			if (cpus_have_final_cap(ARM64_SSBS))
+				return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
+			fallthrough;
+		case SPECTRE_UNAFFECTED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
+		case SPECTRE_VULNERABLE:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
+		}
+		break;
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
+		switch (arm64_get_spectre_bhb_state()) {
+		case SPECTRE_VULNERABLE:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
+		case SPECTRE_MITIGATED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL;
+		case SPECTRE_UNAFFECTED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED;
+		}
+		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
+	}
+
+	return -EINVAL;
+}
+
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+
+	switch (reg->id) {
+	case KVM_REG_ARM_PSCI_VERSION:
+		val = kvm_psci_version(vcpu);
+		break;
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
+		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+	int wa_level;
+
+	if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	switch (reg->id) {
+	case KVM_REG_ARM_PSCI_VERSION:
+	{
+		bool wants_02;
+
+		wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
+
+		switch (val) {
+		case KVM_ARM_PSCI_0_1:
+			if (wants_02)
+				return -EINVAL;
+			vcpu->kvm->arch.psci_version = val;
+			return 0;
+		case KVM_ARM_PSCI_0_2:
+		case KVM_ARM_PSCI_1_0:
+		case KVM_ARM_PSCI_1_1:
+			if (!wants_02)
+				return -EINVAL;
+			vcpu->kvm->arch.psci_version = val;
+			return 0;
+		}
+		break;
+	}
+
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
+		if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
+			return -EINVAL;
+
+		if (get_kernel_wa_level(reg->id) < val)
+			return -EINVAL;
+
+		return 0;
+
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+		if (val & ~(KVM_REG_FEATURE_LEVEL_MASK |
+			    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED))
+			return -EINVAL;
+
+		/* The enabled bit must not be set unless the level is AVAIL. */
+		if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) &&
+		    (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL)
+			return -EINVAL;
+
+		/*
+		 * Map all the possible incoming states to the only two we
+		 * really want to deal with.
+		 */
+		switch (val & KVM_REG_FEATURE_LEVEL_MASK) {
+		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL:
+		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN:
+			wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
+			break;
+		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL:
+		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED:
+			wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		/*
+		 * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
+		 * other way around.
+		 */
+		if (get_kernel_wa_level(reg->id) < wa_level)
+			return -EINVAL;
+
+		return 0;
+	default:
+		return -ENOENT;
+	}
+
+	return -EINVAL;
+}
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index baac2b405f23..346535169faa 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -436,186 +436,3 @@ int kvm_psci_call(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 	}
 }
-
-int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
-{
-	return 4;		/* PSCI version and three workaround registers */
-}
-
-int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
-{
-	if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices++))
-		return -EFAULT;
-
-	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, uindices++))
-		return -EFAULT;
-
-	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++))
-		return -EFAULT;
-
-	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, uindices++))
-		return -EFAULT;
-
-	return 0;
-}
-
-#define KVM_REG_FEATURE_LEVEL_WIDTH	4
-#define KVM_REG_FEATURE_LEVEL_MASK	(BIT(KVM_REG_FEATURE_LEVEL_WIDTH) - 1)
-
-/*
- * Convert the workaround level into an easy-to-compare number, where higher
- * values mean better protection.
- */
-static int get_kernel_wa_level(u64 regid)
-{
-	switch (regid) {
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-		switch (arm64_get_spectre_v2_state()) {
-		case SPECTRE_VULNERABLE:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
-		case SPECTRE_MITIGATED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL;
-		case SPECTRE_UNAFFECTED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED;
-		}
-		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
-		switch (arm64_get_spectre_v4_state()) {
-		case SPECTRE_MITIGATED:
-			/*
-			 * As for the hypercall discovery, we pretend we
-			 * don't have any FW mitigation if SSBS is there at
-			 * all times.
-			 */
-			if (cpus_have_final_cap(ARM64_SSBS))
-				return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
-			fallthrough;
-		case SPECTRE_UNAFFECTED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
-		case SPECTRE_VULNERABLE:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
-		}
-		break;
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		switch (arm64_get_spectre_bhb_state()) {
-		case SPECTRE_VULNERABLE:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
-		case SPECTRE_MITIGATED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL;
-		case SPECTRE_UNAFFECTED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED;
-		}
-		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
-	}
-
-	return -EINVAL;
-}
-
-int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
-{
-	void __user *uaddr = (void __user *)(long)reg->addr;
-	u64 val;
-
-	switch (reg->id) {
-	case KVM_REG_ARM_PSCI_VERSION:
-		val = kvm_psci_version(vcpu);
-		break;
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
-		break;
-	default:
-		return -ENOENT;
-	}
-
-	if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	return 0;
-}
-
-int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
-{
-	void __user *uaddr = (void __user *)(long)reg->addr;
-	u64 val;
-	int wa_level;
-
-	if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	switch (reg->id) {
-	case KVM_REG_ARM_PSCI_VERSION:
-	{
-		bool wants_02;
-
-		wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
-
-		switch (val) {
-		case KVM_ARM_PSCI_0_1:
-			if (wants_02)
-				return -EINVAL;
-			vcpu->kvm->arch.psci_version = val;
-			return 0;
-		case KVM_ARM_PSCI_0_2:
-		case KVM_ARM_PSCI_1_0:
-		case KVM_ARM_PSCI_1_1:
-			if (!wants_02)
-				return -EINVAL;
-			vcpu->kvm->arch.psci_version = val;
-			return 0;
-		}
-		break;
-	}
-
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
-			return -EINVAL;
-
-		if (get_kernel_wa_level(reg->id) < val)
-			return -EINVAL;
-
-		return 0;
-
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
-		if (val & ~(KVM_REG_FEATURE_LEVEL_MASK |
-			    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED))
-			return -EINVAL;
-
-		/* The enabled bit must not be set unless the level is AVAIL. */
-		if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) &&
-		    (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL)
-			return -EINVAL;
-
-		/*
-		 * Map all the possible incoming states to the only two we
-		 * really want to deal with.
-		 */
-		switch (val & KVM_REG_FEATURE_LEVEL_MASK) {
-		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL:
-		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN:
-			wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
-			break;
-		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL:
-		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED:
-			wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
-			break;
-		default:
-			return -EINVAL;
-		}
-
-		/*
-		 * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
-		 * other way around.
-		 */
-		if (get_kernel_wa_level(reg->id) < wa_level)
-			return -EINVAL;
-
-		return 0;
-	default:
-		return -ENOENT;
-	}
-
-	return -EINVAL;
-}
diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h
index 0e2509d27910..5d38628a8d04 100644
--- a/include/kvm/arm_hypercalls.h
+++ b/include/kvm/arm_hypercalls.h
@@ -40,4 +40,11 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu,
 	vcpu_set_reg(vcpu, 3, a3);
 }
 
+struct kvm_one_reg;
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+
 #endif
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index 68b96c3826c3..6e55b9283789 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -39,11 +39,4 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu)
 
 int kvm_psci_call(struct kvm_vcpu *vcpu);
 
-struct kvm_one_reg;
-
-int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu);
-int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
-int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
-int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
-
 #endif /* __KVM_ARM_PSCI_H__ */
-- 
cgit v1.2.3


From 05714cab7d63b189894235cf310fae7d6ffc2e9b Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Mon, 2 May 2022 23:38:46 +0000
Subject: KVM: arm64: Setup a framework for hypercall bitmap firmware registers

KVM regularly introduces new hypercall services to the guests without
any consent from the userspace. This means, the guests can observe
hypercall services in and out as they migrate across various host
kernel versions. This could be a major problem if the guest
discovered a hypercall, started using it, and after getting migrated
to an older kernel realizes that it's no longer available. Depending
on how the guest handles the change, there's a potential chance that
the guest would just panic.

As a result, there's a need for the userspace to elect the services
that it wishes the guest to discover. It can elect these services
based on the kernels spread across its (migration) fleet. To remedy
this, extend the existing firmware pseudo-registers, such as
KVM_REG_ARM_PSCI_VERSION, but by creating a new COPROC register space
for all the hypercall services available.

These firmware registers are categorized based on the service call
owners, but unlike the existing firmware pseudo-registers, they hold
the features supported in the form of a bitmap.

During the VM initialization, the registers are set to upper-limit of
the features supported by the corresponding registers. It's expected
that the VMMs discover the features provided by each register via
GET_ONE_REG, and write back the desired values using SET_ONE_REG.
KVM allows this modification only until the VM has started.

Some of the standard features are not mapped to any bits of the
registers. But since they can recreate the original problem of
making it available without userspace's consent, they need to
be explicitly added to the case-list in
kvm_hvc_call_default_allowed(). Any function-id that's not enabled
via the bitmap, or not listed in kvm_hvc_call_default_allowed, will
be returned as SMCCC_RET_NOT_SUPPORTED to the guest.

Older userspace code can simply ignore the feature and the
hypercall services will be exposed unconditionally to the guests,
thus ensuring backward compatibility.

In this patch, the framework adds the register only for ARM's standard
secure services (owner value 4). Currently, this includes support only
for ARM True Random Number Generator (TRNG) service, with bit-0 of the
register representing mandatory features of v1.0. Other services are
momentarily added in the upcoming patches.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
[maz: reduced the scope of some helpers, tidy-up bitmap max values,
 dropped error-only fast path]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220502233853.1233742-3-rananta@google.com
---
 arch/arm64/include/asm/kvm_host.h |  12 +++++
 arch/arm64/include/uapi/asm/kvm.h |  13 +++++
 arch/arm64/kvm/arm.c              |   1 +
 arch/arm64/kvm/guest.c            |   8 ++-
 arch/arm64/kvm/hypercalls.c       | 104 ++++++++++++++++++++++++++++++++++++++
 include/kvm/arm_hypercalls.h      |   1 +
 6 files changed, 137 insertions(+), 2 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 94a27a7520f4..fef597af0beb 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -101,6 +101,15 @@ struct kvm_s2_mmu {
 struct kvm_arch_memory_slot {
 };
 
+/**
+ * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests
+ *
+ * @std_bmap: Bitmap of standard secure service calls
+ */
+struct kvm_smccc_features {
+	unsigned long std_bmap;
+};
+
 struct kvm_arch {
 	struct kvm_s2_mmu mmu;
 
@@ -150,6 +159,9 @@ struct kvm_arch {
 
 	u8 pfr0_csv2;
 	u8 pfr0_csv3;
+
+	/* Hypercall features firmware registers' descriptor */
+	struct kvm_smccc_features smccc_feat;
 };
 
 struct kvm_vcpu_fault_info {
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index c1b6ddc02d2f..b0be5ec196b9 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -332,6 +332,19 @@ struct kvm_arm_copy_mte_tags {
 #define KVM_ARM64_SVE_VLS_WORDS	\
 	((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1)
 
+/* Bitmap feature firmware registers */
+#define KVM_REG_ARM_FW_FEAT_BMAP		(0x0016 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_FEAT_BMAP_REG(r)		(KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+						KVM_REG_ARM_FW_FEAT_BMAP |	\
+						((r) & 0xffff))
+
+#define KVM_REG_ARM_STD_BMAP			KVM_REG_ARM_FW_FEAT_BMAP_REG(0)
+
+enum {
+	KVM_REG_ARM_STD_BIT_TRNG_V1_0	= 0,
+	KVM_REG_ARM_STD_BMAP_BIT_COUNT,
+};
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 523bc934fe2f..a37fadbd617e 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -156,6 +156,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
 
 	set_default_spectre(kvm);
+	kvm_arm_init_hypercalls(kvm);
 
 	return ret;
 out_free_stage2_pgd:
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 0d5cca56cbda..8c607199cad1 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -756,7 +756,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	switch (reg->id & KVM_REG_ARM_COPROC_MASK) {
 	case KVM_REG_ARM_CORE:	return get_core_reg(vcpu, reg);
-	case KVM_REG_ARM_FW:	return kvm_arm_get_fw_reg(vcpu, reg);
+	case KVM_REG_ARM_FW:
+	case KVM_REG_ARM_FW_FEAT_BMAP:
+		return kvm_arm_get_fw_reg(vcpu, reg);
 	case KVM_REG_ARM64_SVE:	return get_sve_reg(vcpu, reg);
 	}
 
@@ -774,7 +776,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	switch (reg->id & KVM_REG_ARM_COPROC_MASK) {
 	case KVM_REG_ARM_CORE:	return set_core_reg(vcpu, reg);
-	case KVM_REG_ARM_FW:	return kvm_arm_set_fw_reg(vcpu, reg);
+	case KVM_REG_ARM_FW:
+	case KVM_REG_ARM_FW_FEAT_BMAP:
+		return kvm_arm_set_fw_reg(vcpu, reg);
 	case KVM_REG_ARM64_SVE:	return set_sve_reg(vcpu, reg);
 	}
 
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index dd4e20b8d656..22f3a919e699 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -9,6 +9,9 @@
 #include <kvm/arm_hypercalls.h>
 #include <kvm/arm_psci.h>
 
+#define KVM_ARM_SMCCC_STD_FEATURES				\
+	GENMASK(KVM_REG_ARM_STD_BMAP_BIT_COUNT - 1, 0)
+
 static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val)
 {
 	struct system_time_snapshot systime_snapshot;
@@ -58,6 +61,56 @@ static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val)
 	val[3] = lower_32_bits(cycles);
 }
 
+static bool kvm_hvc_call_default_allowed(u32 func_id)
+{
+	switch (func_id) {
+	/*
+	 * List of function-ids that are not gated with the bitmapped
+	 * feature firmware registers, and are to be allowed for
+	 * servicing the call by default.
+	 */
+	case ARM_SMCCC_VERSION_FUNC_ID:
+	case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
+	case ARM_SMCCC_HV_PV_TIME_FEATURES:
+	case ARM_SMCCC_HV_PV_TIME_ST:
+	case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID:
+	case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
+	case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID:
+		return true;
+	default:
+		/* PSCI 0.2 and up is in the 0:0x1f range */
+		if (ARM_SMCCC_OWNER_NUM(func_id) == ARM_SMCCC_OWNER_STANDARD &&
+		    ARM_SMCCC_FUNC_NUM(func_id) <= 0x1f)
+			return true;
+
+		/*
+		 * KVM's PSCI 0.1 doesn't comply with SMCCC, and has
+		 * its own function-id base and range
+		 */
+		if (func_id >= KVM_PSCI_FN(0) && func_id <= KVM_PSCI_FN(3))
+			return true;
+
+		return false;
+	}
+}
+
+static bool kvm_hvc_call_allowed(struct kvm_vcpu *vcpu, u32 func_id)
+{
+	struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat;
+
+	switch (func_id) {
+	case ARM_SMCCC_TRNG_VERSION:
+	case ARM_SMCCC_TRNG_FEATURES:
+	case ARM_SMCCC_TRNG_GET_UUID:
+	case ARM_SMCCC_TRNG_RND32:
+	case ARM_SMCCC_TRNG_RND64:
+		return test_bit(KVM_REG_ARM_STD_BIT_TRNG_V1_0,
+				&smccc_feat->std_bmap);
+	default:
+		return kvm_hvc_call_default_allowed(func_id);
+	}
+}
+
 int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 {
 	u32 func_id = smccc_get_function(vcpu);
@@ -65,6 +118,9 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 	u32 feature;
 	gpa_t gpa;
 
+	if (!kvm_hvc_call_allowed(vcpu, func_id))
+		goto out;
+
 	switch (func_id) {
 	case ARM_SMCCC_VERSION_FUNC_ID:
 		val[0] = ARM_SMCCC_VERSION_1_1;
@@ -155,6 +211,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 		return kvm_psci_call(vcpu);
 	}
 
+out:
 	smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]);
 	return 1;
 }
@@ -164,8 +221,16 @@ static const u64 kvm_arm_fw_reg_ids[] = {
 	KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1,
 	KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2,
 	KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3,
+	KVM_REG_ARM_STD_BMAP,
 };
 
+void kvm_arm_init_hypercalls(struct kvm *kvm)
+{
+	struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat;
+
+	smccc_feat->std_bmap = KVM_ARM_SMCCC_STD_FEATURES;
+}
+
 int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
 {
 	return ARRAY_SIZE(kvm_arm_fw_reg_ids);
@@ -236,6 +301,7 @@ static int get_kernel_wa_level(u64 regid)
 
 int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
+	struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat;
 	void __user *uaddr = (void __user *)(long)reg->addr;
 	u64 val;
 
@@ -248,6 +314,9 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
 		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
 		break;
+	case KVM_REG_ARM_STD_BMAP:
+		val = READ_ONCE(smccc_feat->std_bmap);
+		break;
 	default:
 		return -ENOENT;
 	}
@@ -258,6 +327,39 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	return 0;
 }
 
+static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val)
+{
+	int ret = 0;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat;
+	unsigned long *fw_reg_bmap, fw_reg_features;
+
+	switch (reg_id) {
+	case KVM_REG_ARM_STD_BMAP:
+		fw_reg_bmap = &smccc_feat->std_bmap;
+		fw_reg_features = KVM_ARM_SMCCC_STD_FEATURES;
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	/* Check for unsupported bit */
+	if (val & ~fw_reg_features)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	WRITE_ONCE(*fw_reg_bmap, val);
+out:
+	mutex_unlock(&kvm->lock);
+	return ret;
+}
+
 int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	void __user *uaddr = (void __user *)(long)reg->addr;
@@ -336,6 +438,8 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 			return -EINVAL;
 
 		return 0;
+	case KVM_REG_ARM_STD_BMAP:
+		return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val);
 	default:
 		return -ENOENT;
 	}
diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h
index 5d38628a8d04..1188f116cf4e 100644
--- a/include/kvm/arm_hypercalls.h
+++ b/include/kvm/arm_hypercalls.h
@@ -42,6 +42,7 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu,
 
 struct kvm_one_reg;
 
+void kvm_arm_init_hypercalls(struct kvm *kvm);
 int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
 int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
-- 
cgit v1.2.3


From 94828468a6085e6ae148986d300b634b87f86516 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 5 Apr 2022 19:23:25 +0100
Subject: KVM: arm64: vgic-v3: Expose GICR_CTLR.RWP when disabling LPIs

When disabling LPIs, a guest needs to poll GICR_CTLR.RWP in order
to be sure that the write has taken effect. We so far reported it
as 0, as we didn't advertise that LPIs could be turned off the
first place.

Start tracking this state during which LPIs are being disabled,
and expose the 'in progress' state via the RWP bit.

We also take this opportunity to disallow enabling LPIs and programming
GICR_{PEND,PROP}BASER while LPI disabling is in progress, as allowed by
the architecture (UNPRED behaviour).

We don't advertise the feature to the guest yet (which is allowed by
the architecture).

Reviewed-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220405182327.205520-3-maz@kernel.org
---
 arch/arm64/kvm/vgic/vgic-its.c     |  2 +-
 arch/arm64/kvm/vgic/vgic-mmio-v3.c | 36 +++++++++++++++++++++++++++---------
 arch/arm64/kvm/vgic/vgic.h         |  1 +
 include/kvm/arm_vgic.h             |  4 ++--
 4 files changed, 31 insertions(+), 12 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 2e13402be3bd..9d11072964fb 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -683,7 +683,7 @@ int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
 	if (!vcpu)
 		return E_ITS_INT_UNMAPPED_INTERRUPT;
 
-	if (!vcpu->arch.vgic_cpu.lpis_enabled)
+	if (!vgic_lpis_enabled(vcpu))
 		return -EBUSY;
 
 	vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq);
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 58e40b4874f8..b5ef7e15bb66 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -221,6 +221,13 @@ static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu,
 	vgic_put_irq(vcpu->kvm, irq);
 }
 
+bool vgic_lpis_enabled(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	return atomic_read(&vgic_cpu->ctlr) == GICR_CTLR_ENABLE_LPIS;
+}
+
 static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu,
 					     gpa_t addr, unsigned int len)
 {
@@ -229,26 +236,38 @@ static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu,
 	return vgic_cpu->lpis_enabled ? GICR_CTLR_ENABLE_LPIS : 0;
 }
 
-
 static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu,
 				     gpa_t addr, unsigned int len,
 				     unsigned long val)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	bool was_enabled = vgic_cpu->lpis_enabled;
+	u32 ctlr;
 
 	if (!vgic_has_its(vcpu->kvm))
 		return;
 
-	vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS;
+	if (!(val & GICR_CTLR_ENABLE_LPIS)) {
+		/*
+		 * Don't disable if RWP is set, as there already an
+		 * ongoing disable. Funky guest...
+		 */
+		ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr,
+					      GICR_CTLR_ENABLE_LPIS,
+					      GICR_CTLR_RWP);
+		if (ctlr != GICR_CTLR_ENABLE_LPIS)
+			return;
 
-	if (was_enabled && !vgic_cpu->lpis_enabled) {
 		vgic_flush_pending_lpis(vcpu);
 		vgic_its_invalidate_cache(vcpu->kvm);
-	}
+		atomic_set_release(&vgic_cpu->ctlr, 0);
+	} else {
+		ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr, 0,
+					      GICR_CTLR_ENABLE_LPIS);
+		if (ctlr != 0)
+			return;
 
-	if (!was_enabled && vgic_cpu->lpis_enabled)
 		vgic_enable_lpis(vcpu);
+	}
 }
 
 static bool vgic_mmio_vcpu_rdist_is_last(struct kvm_vcpu *vcpu)
@@ -478,11 +497,10 @@ static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu,
 				     unsigned long val)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	u64 old_propbaser, propbaser;
 
 	/* Storing a value with LPIs already enabled is undefined */
-	if (vgic_cpu->lpis_enabled)
+	if (vgic_lpis_enabled(vcpu))
 		return;
 
 	do {
@@ -513,7 +531,7 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu,
 	u64 old_pendbaser, pendbaser;
 
 	/* Storing a value with LPIs already enabled is undefined */
-	if (vgic_cpu->lpis_enabled)
+	if (vgic_lpis_enabled(vcpu))
 		return;
 
 	do {
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 3fd6c86a7ef3..a21e9b602ff2 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -308,6 +308,7 @@ static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size)
 		(base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE);
 }
 
+bool vgic_lpis_enabled(struct kvm_vcpu *vcpu);
 int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr);
 int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
 			 u32 devid, u32 eventid, struct vgic_irq **irq);
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index bb30a6803d9f..fdf1c2c322e5 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -347,8 +347,8 @@ struct vgic_cpu {
 
 	/* Contains the attributes and gpa of the LPI pending tables. */
 	u64 pendbaser;
-
-	bool lpis_enabled;
+	/* GICR_CTLR.{ENABLE_LPIS,RWP} */
+	atomic_t ctlr;
 
 	/* Cache guest priority bits */
 	u32 num_pri_bits;
-- 
cgit v1.2.3


From 4645d11f4a5538ec1221f36e397cfb0115718ffe Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 5 Apr 2022 19:23:26 +0100
Subject: KVM: arm64: vgic-v3: Implement MMIO-based LPI invalidation

Since GICv4.1, it has become legal for an implementation to advertise
GICR_{INVLPIR,INVALLR,SYNCR} while having an ITS, allowing for a more
efficient invalidation scheme (no guest command queue contention when
multiple CPUs are generating invalidations).

Provide the invalidation registers as a primitive to their ITS
counterpart. Note that we don't advertise them to the guest yet
(the architecture allows an implementation to do this).

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Oliver Upton <oupton@google.com>
Link: https://lore.kernel.org/r/20220405182327.205520-4-maz@kernel.org
---
 arch/arm64/kvm/vgic/vgic-its.c     | 62 +++++++++++++++++++++++------------
 arch/arm64/kvm/vgic/vgic-mmio-v3.c | 66 ++++++++++++++++++++++++++++++++++++++
 arch/arm64/kvm/vgic/vgic.h         |  4 +++
 include/kvm/arm_vgic.h             |  1 +
 4 files changed, 112 insertions(+), 21 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 9d11072964fb..292ca5bb8a50 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -1272,6 +1272,11 @@ static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its,
 	return 0;
 }
 
+int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq)
+{
+	return update_lpi_config(kvm, irq, NULL, true);
+}
+
 /*
  * The INV command syncs the configuration bits from the memory table.
  * Must be called with the its_lock mutex held.
@@ -1288,7 +1293,41 @@ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
 	if (!ite)
 		return E_ITS_INV_UNMAPPED_INTERRUPT;
 
-	return update_lpi_config(kvm, ite->irq, NULL, true);
+	return vgic_its_inv_lpi(kvm, ite->irq);
+}
+
+/**
+ * vgic_its_invall - invalidate all LPIs targetting a given vcpu
+ * @vcpu: the vcpu for which the RD is targetted by an invalidation
+ *
+ * Contrary to the INVALL command, this targets a RD instead of a
+ * collection, and we don't need to hold the its_lock, since no ITS is
+ * involved here.
+ */
+int vgic_its_invall(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int irq_count, i = 0;
+	u32 *intids;
+
+	irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids);
+	if (irq_count < 0)
+		return irq_count;
+
+	for (i = 0; i < irq_count; i++) {
+		struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
+		update_lpi_config(kvm, irq, vcpu, false);
+		vgic_put_irq(kvm, irq);
+	}
+
+	kfree(intids);
+
+	if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm)
+		its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe);
+
+	return 0;
 }
 
 /*
@@ -1305,32 +1344,13 @@ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its,
 	u32 coll_id = its_cmd_get_collection(its_cmd);
 	struct its_collection *collection;
 	struct kvm_vcpu *vcpu;
-	struct vgic_irq *irq;
-	u32 *intids;
-	int irq_count, i;
 
 	collection = find_collection(its, coll_id);
 	if (!its_is_collection_mapped(collection))
 		return E_ITS_INVALL_UNMAPPED_COLLECTION;
 
 	vcpu = kvm_get_vcpu(kvm, collection->target_addr);
-
-	irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids);
-	if (irq_count < 0)
-		return irq_count;
-
-	for (i = 0; i < irq_count; i++) {
-		irq = vgic_get_irq(kvm, NULL, intids[i]);
-		if (!irq)
-			continue;
-		update_lpi_config(kvm, irq, vcpu, false);
-		vgic_put_irq(kvm, irq);
-	}
-
-	kfree(intids);
-
-	if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm)
-		its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe);
+	vgic_its_invall(vcpu);
 
 	return 0;
 }
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index b5ef7e15bb66..9824c773427d 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -543,6 +543,63 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu,
 			   pendbaser) != old_pendbaser);
 }
 
+static unsigned long vgic_mmio_read_sync(struct kvm_vcpu *vcpu,
+					 gpa_t addr, unsigned int len)
+{
+	return !!atomic_read(&vcpu->arch.vgic_cpu.syncr_busy);
+}
+
+static void vgic_set_rdist_busy(struct kvm_vcpu *vcpu, bool busy)
+{
+	if (busy) {
+		atomic_inc(&vcpu->arch.vgic_cpu.syncr_busy);
+		smp_mb__after_atomic();
+	} else {
+		smp_mb__before_atomic();
+		atomic_dec(&vcpu->arch.vgic_cpu.syncr_busy);
+	}
+}
+
+static void vgic_mmio_write_invlpi(struct kvm_vcpu *vcpu,
+				   gpa_t addr, unsigned int len,
+				   unsigned long val)
+{
+	struct vgic_irq *irq;
+
+	/*
+	 * If the guest wrote only to the upper 32bit part of the
+	 * register, drop the write on the floor, as it is only for
+	 * vPEs (which we don't support for obvious reasons).
+	 *
+	 * Also discard the access if LPIs are not enabled.
+	 */
+	if ((addr & 4) || !vgic_lpis_enabled(vcpu))
+		return;
+
+	vgic_set_rdist_busy(vcpu, true);
+
+	irq = vgic_get_irq(vcpu->kvm, NULL, lower_32_bits(val));
+	if (irq) {
+		vgic_its_inv_lpi(vcpu->kvm, irq);
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	vgic_set_rdist_busy(vcpu, false);
+}
+
+static void vgic_mmio_write_invall(struct kvm_vcpu *vcpu,
+				   gpa_t addr, unsigned int len,
+				   unsigned long val)
+{
+	/* See vgic_mmio_write_invlpi() for the early return rationale */
+	if ((addr & 4) || !vgic_lpis_enabled(vcpu))
+		return;
+
+	vgic_set_rdist_busy(vcpu, true);
+	vgic_its_invall(vcpu);
+	vgic_set_rdist_busy(vcpu, false);
+}
+
 /*
  * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the
  * redistributors, while SPIs are covered by registers in the distributor
@@ -648,6 +705,15 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = {
 	REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER,
 		vgic_mmio_read_pendbase, vgic_mmio_write_pendbase, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICR_INVLPIR,
+		vgic_mmio_read_raz, vgic_mmio_write_invlpi, 8,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICR_INVALLR,
+		vgic_mmio_read_raz, vgic_mmio_write_invall, 8,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_DESC_WITH_LENGTH(GICR_SYNCR,
+		vgic_mmio_read_sync, vgic_mmio_write_wi, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_IDREGS,
 		vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48,
 		VGIC_ACCESS_32bit),
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index a21e9b602ff2..1d04a900f3e3 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -318,6 +318,10 @@ void vgic_lpi_translation_cache_init(struct kvm *kvm);
 void vgic_lpi_translation_cache_destroy(struct kvm *kvm);
 void vgic_its_invalidate_cache(struct kvm *kvm);
 
+/* GICv4.1 MMIO interface */
+int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq);
+int vgic_its_invall(struct kvm_vcpu *vcpu);
+
 bool vgic_supports_direct_msis(struct kvm *kvm);
 int vgic_v4_init(struct kvm *kvm);
 void vgic_v4_teardown(struct kvm *kvm);
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index fdf1c2c322e5..401236f97cf2 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -344,6 +344,7 @@ struct vgic_cpu {
 	struct vgic_io_device	rd_iodev;
 	struct vgic_redist_region *rdreg;
 	u32 rdreg_index;
+	atomic_t syncr_busy;
 
 	/* Contains the attributes and gpa of the LPI pending tables. */
 	u64 pendbaser;
-- 
cgit v1.2.3


From 49a1a2c70a7fd820fe60a65a3e38ab9095082dc9 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 5 Apr 2022 19:23:27 +0100
Subject: KVM: arm64: vgic-v3: Advertise GICR_CTLR.{IR, CES} as a new GICD_IIDR
 revision

Since adversising GICR_CTLR.{IC,CES} is directly observable from
a guest, we need to make it selectable from userspace.

For that, bump the default GICD_IIDR revision and let userspace
downgrade it to the previous default. For GICv2, the two distributor
revisions are strictly equivalent.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220405182327.205520-5-maz@kernel.org
---
 arch/arm64/kvm/vgic/vgic-init.c    |  7 ++++++-
 arch/arm64/kvm/vgic/vgic-mmio-v2.c | 18 +++++++++++++++---
 arch/arm64/kvm/vgic/vgic-mmio-v3.c | 23 +++++++++++++++++++++--
 arch/arm64/kvm/vgic/vgic.h         |  5 +++++
 include/kvm/arm_vgic.h             |  3 +++
 5 files changed, 50 insertions(+), 6 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index fc00304fe7d8..f84e04f334c6 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -319,7 +319,12 @@ int vgic_init(struct kvm *kvm)
 
 	vgic_debug_init(kvm);
 
-	dist->implementation_rev = 2;
+	/*
+	 * If userspace didn't set the GIC implementation revision,
+	 * default to the latest and greatest. You know want it.
+	 */
+	if (!dist->implementation_rev)
+		dist->implementation_rev = KVM_VGIC_IMP_REV_LATEST;
 	dist->initialized = true;
 
 out:
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
index 12e4c223e6b8..77a67e9d3d14 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
@@ -73,9 +73,13 @@ static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu,
 					   gpa_t addr, unsigned int len,
 					   unsigned long val)
 {
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	u32 reg;
+
 	switch (addr & 0x0c) {
 	case GIC_DIST_IIDR:
-		if (val != vgic_mmio_read_v2_misc(vcpu, addr, len))
+		reg = vgic_mmio_read_v2_misc(vcpu, addr, len);
+		if ((reg ^ val) & ~GICD_IIDR_REVISION_MASK)
 			return -EINVAL;
 
 		/*
@@ -87,8 +91,16 @@ static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu,
 		 * migration from old kernels to new kernels with legacy
 		 * userspace.
 		 */
-		vcpu->kvm->arch.vgic.v2_groups_user_writable = true;
-		return 0;
+		reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg);
+		switch (reg) {
+		case KVM_VGIC_IMP_REV_2:
+		case KVM_VGIC_IMP_REV_3:
+			vcpu->kvm->arch.vgic.v2_groups_user_writable = true;
+			dist->implementation_rev = reg;
+			return 0;
+		default:
+			return -EINVAL;
+		}
 	}
 
 	vgic_mmio_write_v2_misc(vcpu, addr, len, val);
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 9824c773427d..f7aa7bcd6fb8 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -155,13 +155,27 @@ static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu,
 					   unsigned long val)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	u32 reg;
 
 	switch (addr & 0x0c) {
 	case GICD_TYPER2:
-	case GICD_IIDR:
 		if (val != vgic_mmio_read_v3_misc(vcpu, addr, len))
 			return -EINVAL;
 		return 0;
+	case GICD_IIDR:
+		reg = vgic_mmio_read_v3_misc(vcpu, addr, len);
+		if ((reg ^ val) & ~GICD_IIDR_REVISION_MASK)
+			return -EINVAL;
+
+		reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg);
+		switch (reg) {
+		case KVM_VGIC_IMP_REV_2:
+		case KVM_VGIC_IMP_REV_3:
+			dist->implementation_rev = reg;
+			return 0;
+		default:
+			return -EINVAL;
+		}
 	case GICD_CTLR:
 		/* Not a GICv4.1? No HW SGIs */
 		if (!kvm_vgic_global_state.has_gicv4_1)
@@ -232,8 +246,13 @@ static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu,
 					     gpa_t addr, unsigned int len)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	unsigned long val;
+
+	val = atomic_read(&vgic_cpu->ctlr);
+	if (vgic_get_implementation_rev(vcpu) >= KVM_VGIC_IMP_REV_3)
+		val |= GICR_CTLR_IR | GICR_CTLR_CES;
 
-	return vgic_cpu->lpis_enabled ? GICR_CTLR_ENABLE_LPIS : 0;
+	return val;
 }
 
 static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 1d04a900f3e3..4c6bdd321faa 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -98,6 +98,11 @@
 #define DEBUG_SPINLOCK_BUG_ON(p)
 #endif
 
+static inline u32 vgic_get_implementation_rev(struct kvm_vcpu *vcpu)
+{
+	return vcpu->kvm->arch.vgic.implementation_rev;
+}
+
 /* Requires the irq_lock to be held by the caller. */
 static inline bool irq_is_pending(struct vgic_irq *irq)
 {
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 401236f97cf2..2d8f2e90edc2 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -231,6 +231,9 @@ struct vgic_dist {
 
 	/* Implementation revision as reported in the GICD_IIDR */
 	u32			implementation_rev;
+#define KVM_VGIC_IMP_REV_2	2 /* GICv2 restorable groups */
+#define KVM_VGIC_IMP_REV_3	3 /* GICv3 GICR_CTLR.{IW,CES,RWP} */
+#define KVM_VGIC_IMP_REV_LATEST	KVM_VGIC_IMP_REV_3
 
 	/* Userspace can write to GICv2 IGROUPR */
 	bool			v2_groups_user_writable;
-- 
cgit v1.2.3


From e987a4c60f9755b2f7a19bf1b5ef2eb74c90579b Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Tue, 10 May 2022 09:57:08 +0000
Subject: KVM: arm64: Repack struct kvm_pmu to reduce size

struct kvm_pmu has 2 holes using 10 bytes. This is instantiated
in all vcpus, so it adds up. Repack the structures to remove the
holes.

No functional change intended.

Reviewed-by: Oliver Upton <oupton@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220510095710.148178-3-tabba@google.com
---
 include/kvm/arm_pmu.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/kvm')

diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 20193416d214..eaa8290b116f 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -21,12 +21,12 @@ struct kvm_pmc {
 };
 
 struct kvm_pmu {
-	int irq_num;
+	struct irq_work overflow_work;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
 	DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
+	int irq_num;
 	bool created;
 	bool irq_level;
-	struct irq_work overflow_work;
 };
 
 struct arm_pmu_entry {
-- 
cgit v1.2.3


From 84d751a019a9792f5b4884e1d598b603c360ec22 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Tue, 10 May 2022 09:57:09 +0000
Subject: KVM: arm64: Pass pmu events to hyp via vcpu

Instead of the host accessing hyp data directly, pass the pmu
events of the current cpu to hyp via the vcpu.

This adds 64 bits (in two fields) to the vcpu that need to be
synced before every vcpu run in nvhe and protected modes.
However, it isolates the hypervisor from the host, which allows
us to use pmu in protected mode in a subsequent patch.

No visible side effects in behavior intended.

Signed-off-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220510095710.148178-4-tabba@google.com
---
 arch/arm64/include/asm/kvm_host.h |  7 +------
 arch/arm64/kvm/arm.c              | 15 +++++++++++++++
 arch/arm64/kvm/hyp/nvhe/switch.c  | 20 ++++++--------------
 arch/arm64/kvm/pmu.c              | 12 ++++--------
 include/kvm/arm_pmu.h             |  6 ++++++
 5 files changed, 32 insertions(+), 28 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 94a27a7520f4..efca5a63bdaf 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -254,14 +254,8 @@ struct kvm_cpu_context {
 	struct kvm_vcpu *__hyp_running_vcpu;
 };
 
-struct kvm_pmu_events {
-	u32 events_host;
-	u32 events_guest;
-};
-
 struct kvm_host_data {
 	struct kvm_cpu_context host_ctxt;
-	struct kvm_pmu_events pmu_events;
 };
 
 struct kvm_host_psci_config {
@@ -796,6 +790,7 @@ void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
 void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
 void kvm_clr_pmu_events(u32 clr);
 
+struct kvm_pmu_events *kvm_get_pmu_events(void);
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
 void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
 #else
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 523bc934fe2f..aa1b15e9d5d9 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -751,6 +751,19 @@ static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+/*
+ * Updates the vcpu's view of the pmu events for this cpu.
+ * Must be called before every vcpu run after disabling interrupts, to ensure
+ * that an interrupt cannot fire and update the structure.
+ */
+static void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu)
+{
+	if (has_vhe() || !kvm_vcpu_has_pmu(vcpu))
+		return;
+
+	vcpu->arch.pmu.events = *kvm_get_pmu_events();
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -815,6 +828,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 		kvm_vgic_flush_hwstate(vcpu);
 
+		kvm_pmu_update_vcpu_events(vcpu);
+
 		/*
 		 * Ensure we set mode to IN_GUEST_MODE after we disable
 		 * interrupts and before the final VCPU requests check.
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 6410d21d8695..ff7b29fb9787 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -123,13 +123,9 @@ static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 /**
  * Disable host events, enable guest events
  */
-static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+static bool __pmu_switch_to_guest(struct kvm_vcpu *vcpu)
 {
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
+	struct kvm_pmu_events *pmu = &vcpu->arch.pmu.events;
 
 	if (pmu->events_host)
 		write_sysreg(pmu->events_host, pmcntenclr_el0);
@@ -143,13 +139,9 @@ static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
 /**
  * Disable guest events, enable host events
  */
-static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+static void __pmu_switch_to_host(struct kvm_vcpu *vcpu)
 {
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
+	struct kvm_pmu_events *pmu = &vcpu->arch.pmu.events;
 
 	if (pmu->events_guest)
 		write_sysreg(pmu->events_guest, pmcntenclr_el0);
@@ -274,7 +266,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	host_ctxt->__hyp_running_vcpu = vcpu;
 	guest_ctxt = &vcpu->arch.ctxt;
 
-	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
+	pmu_switch_needed = __pmu_switch_to_guest(vcpu);
 
 	__sysreg_save_state_nvhe(host_ctxt);
 	/*
@@ -336,7 +328,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	__debug_restore_host_buffers_nvhe(vcpu);
 
 	if (pmu_switch_needed)
-		__pmu_switch_to_host(host_ctxt);
+		__pmu_switch_to_host(vcpu);
 
 	/* Returning to host will clear PSR.I, remask PMR if needed */
 	if (system_uses_irq_prio_masking())
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 4bd38ff34221..7887133d15f0 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -5,7 +5,8 @@
  */
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
-#include <asm/kvm_hyp.h>
+
+static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events);
 
 /*
  * Given the perf event attributes and system type, determine
@@ -25,14 +26,9 @@ static bool kvm_pmu_switch_needed(struct perf_event_attr *attr)
 	return (attr->exclude_host != attr->exclude_guest);
 }
 
-static struct kvm_pmu_events *kvm_get_pmu_events(void)
+struct kvm_pmu_events *kvm_get_pmu_events(void)
 {
-	struct kvm_host_data *ctx = this_cpu_ptr_hyp_sym(kvm_host_data);
-
-	if (!ctx)
-		return NULL;
-
-	return &ctx->pmu_events;
+	return this_cpu_ptr(&kvm_pmu_events);
 }
 
 /*
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index eaa8290b116f..35a0903cae32 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -20,8 +20,14 @@ struct kvm_pmc {
 	struct perf_event *perf_event;
 };
 
+struct kvm_pmu_events {
+	u32 events_host;
+	u32 events_guest;
+};
+
 struct kvm_pmu {
 	struct irq_work overflow_work;
+	struct kvm_pmu_events events;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
 	DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
 	int irq_num;
-- 
cgit v1.2.3


From 20492a62b99bd4367b79a76ca288d018f11980db Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Mon, 16 May 2022 13:02:24 +0100
Subject: KVM: arm64: pmu: Restore compilation when HW_PERF_EVENTS isn't
 selected

Moving kvm_pmu_events into the vcpu (and refering to it) broke the
somewhat unusual case where the kernel has no support for a PMU
at all.

In order to solve this, move things around a bit so that we can
easily avoid refering to the pmu structure outside of PMU-aware
code. As a bonus, pmu.c isn't compiled in when HW_PERF_EVENTS
isn't selected.

Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/202205161814.KQHpOzsJ-lkp@intel.com
---
 arch/arm64/include/asm/kvm_host.h |  6 ------
 arch/arm64/kvm/Makefile           |  4 ++--
 arch/arm64/kvm/arm.c              | 13 -------------
 arch/arm64/kvm/hyp/nvhe/switch.c  |  5 +++++
 include/kvm/arm_pmu.h             | 24 ++++++++++++++++++++++++
 5 files changed, 31 insertions(+), 21 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index efca5a63bdaf..ef774b8955bc 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -789,10 +789,6 @@ void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
 void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
 void kvm_clr_pmu_events(u32 clr);
-
-struct kvm_pmu_events *kvm_get_pmu_events(void);
-void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
-void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
 #else
 static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
 static inline void kvm_clr_pmu_events(u32 clr) {}
@@ -824,8 +820,6 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_has_mte(kvm)					\
 	(system_supports_mte() &&				\
 	 test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags))
-#define kvm_vcpu_has_pmu(vcpu)					\
-	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
 
 int kvm_trng_call(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 261644b1a6bb..aa127ae9f675 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_KVM) += hyp/
 kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 	 inject_fault.o va_layout.o handle_exit.o \
 	 guest.o debug.o reset.o sys_regs.o \
-	 vgic-sys-reg-v3.o fpsimd.o pmu.o pkvm.o \
+	 vgic-sys-reg-v3.o fpsimd.o pkvm.o \
 	 arch_timer.o trng.o vmid.o \
 	 vgic/vgic.o vgic/vgic-init.o \
 	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
@@ -22,7 +22,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
 	 vgic/vgic-its.o vgic/vgic-debug.o
 
-kvm-$(CONFIG_HW_PERF_EVENTS)  += pmu-emul.o
+kvm-$(CONFIG_HW_PERF_EVENTS)  += pmu-emul.o pmu.o
 
 always-y := hyp_constants.h hyp-constants.s
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index aa1b15e9d5d9..b3821c430ec9 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -751,19 +751,6 @@ static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-/*
- * Updates the vcpu's view of the pmu events for this cpu.
- * Must be called before every vcpu run after disabling interrupts, to ensure
- * that an interrupt cannot fire and update the structure.
- */
-static void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu)
-{
-	if (has_vhe() || !kvm_vcpu_has_pmu(vcpu))
-		return;
-
-	vcpu->arch.pmu.events = *kvm_get_pmu_events();
-}
-
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index ff7b29fb9787..c7cd2036a75e 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -123,6 +123,7 @@ static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 /**
  * Disable host events, enable guest events
  */
+#ifdef CONFIG_HW_PERF_EVENTS
 static bool __pmu_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu_events *pmu = &vcpu->arch.pmu.events;
@@ -149,6 +150,10 @@ static void __pmu_switch_to_host(struct kvm_vcpu *vcpu)
 	if (pmu->events_host)
 		write_sysreg(pmu->events_host, pmcntenset_el0);
 }
+#else
+#define __pmu_switch_to_guest(v)	({ false; })
+#define __pmu_switch_to_host(v)		do {} while (0)
+#endif
 
 /**
  * Handler for protected VM MSR, MRS or System instruction execution in AArch64.
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 35a0903cae32..c0b868ce6a8f 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -72,6 +72,25 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
 int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
+
+struct kvm_pmu_events *kvm_get_pmu_events(void);
+void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
+void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
+
+#define kvm_vcpu_has_pmu(vcpu)					\
+	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
+
+/*
+ * Updates the vcpu's view of the pmu events for this cpu.
+ * Must be called before every vcpu run after disabling interrupts, to ensure
+ * that an interrupt cannot fire and update the structure.
+ */
+#define kvm_pmu_update_vcpu_events(vcpu)				\
+	do {								\
+		if (!has_vhe() && kvm_vcpu_has_pmu(vcpu))		\
+			vcpu->arch.pmu.events = *kvm_get_pmu_events();	\
+	} while (0)
+
 #else
 struct kvm_pmu {
 };
@@ -133,6 +152,11 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	return 0;
 }
 
+#define kvm_vcpu_has_pmu(vcpu)		({ false; })
+static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {}
+static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {}
+static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {}
+
 #endif
 
 #endif
-- 
cgit v1.2.3