From 3d4b2a4cddd783bc5a75585a7cb6189a8a551b22 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Wed, 20 Sep 2023 19:50:35 +0000
Subject: KVM: arm64: Remove unused return value from kvm_reset_vcpu()

Get rid of the return value for kvm_reset_vcpu() as there are no longer
any cases where it returns a nonzero value.

Link: https://lore.kernel.org/r/20230920195036.1169791-8-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 include/kvm/arm_arch_timer.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/kvm')

diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index bb3cb005873e..8adf09dbc473 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -94,7 +94,7 @@ struct arch_timer_cpu {
 
 int __init kvm_timer_hyp_init(bool has_gic);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
-int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_user(struct kvm_vcpu *vcpu);
 bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
-- 
cgit v1.2.3


From 1de10b7d13a971f9ab90c5ed300b76d6e0c0db38 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Wed, 20 Sep 2023 19:50:36 +0000
Subject: KVM: arm64: Get rid of vCPU-scoped feature bitmap

The vCPU-scoped feature bitmap was left in place a couple of releases
ago in case the change to VM-scoped vCPU features broke anyone. Nobody
has complained and the interop between VM and vCPU bitmaps is pretty
gross. Throw it out.

Link: https://lore.kernel.org/r/20230920195036.1169791-9-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_emulate.h | 13 ++++++-------
 arch/arm64/include/asm/kvm_host.h    |  3 ---
 arch/arm64/include/asm/kvm_nested.h  |  3 ++-
 arch/arm64/kvm/arm.c                 |  9 ++++-----
 arch/arm64/kvm/hypercalls.c          |  2 +-
 arch/arm64/kvm/reset.c               |  6 +++---
 include/kvm/arm_pmu.h                |  2 +-
 include/kvm/arm_psci.h               |  2 +-
 8 files changed, 18 insertions(+), 22 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 3d6725ff0bf6..965b4cd8c247 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -54,6 +54,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
 int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
 int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
 
+static inline bool vcpu_has_feature(const struct kvm_vcpu *vcpu, int feature)
+{
+	return test_bit(feature, vcpu->kvm->arch.vcpu_features);
+}
+
 #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
@@ -62,7 +67,7 @@ static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 #else
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
-	return test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features);
+	return vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT);
 }
 #endif
 
@@ -565,12 +570,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 		vcpu_set_flag((v), e);					\
 	} while (0)
 
-
-static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature)
-{
-	return test_bit(feature, vcpu->arch.features);
-}
-
 static __always_inline void kvm_write_cptr_el2(u64 val)
 {
 	if (has_vhe() || has_hvhe())
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index cb2cde7b2682..c3a17888f183 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -574,9 +574,6 @@ struct kvm_vcpu_arch {
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
-	/* feature flags */
-	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
-
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
 	u64 vsesr_el2;
 
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index fa23cc9c2adc..6cec8e9c6c91 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -2,13 +2,14 @@
 #ifndef __ARM64_KVM_NESTED_H
 #define __ARM64_KVM_NESTED_H
 
+#include <asm/kvm_emulate.h>
 #include <linux/kvm_host.h>
 
 static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 {
 	return (!__is_defined(__KVM_NVHE_HYPERVISOR__) &&
 		cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
-		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
+		vcpu_has_feature(vcpu, KVM_ARM_VCPU_HAS_EL2));
 }
 
 extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index ac30c4f3d55c..1bfdd583b261 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -367,7 +367,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	/* Force users to call KVM_ARM_VCPU_INIT */
 	vcpu_clear_flag(vcpu, VCPU_INITIALIZED);
-	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
 
 	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
 
@@ -1263,7 +1262,8 @@ static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu,
 {
 	unsigned long features = init->features[0];
 
-	return !bitmap_equal(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES);
+	return !bitmap_equal(vcpu->kvm->arch.vcpu_features, &features,
+			     KVM_VCPU_MAX_FEATURES);
 }
 
 static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
@@ -1276,15 +1276,14 @@ static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 	mutex_lock(&kvm->arch.config_lock);
 
 	if (test_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags) &&
-	    !bitmap_equal(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES))
+	    kvm_vcpu_init_changed(vcpu, init))
 		goto out_unlock;
 
-	bitmap_copy(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES);
+	bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES);
 
 	/* Now we know what it is, we can reset it. */
 	kvm_reset_vcpu(vcpu);
 
-	bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES);
 	set_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags);
 	vcpu_set_flag(vcpu, VCPU_INITIALIZED);
 	ret = 0;
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 7fb4df0456de..1b79219c590c 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -554,7 +554,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	{
 		bool wants_02;
 
-		wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
+		wants_02 = vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2);
 
 		switch (val) {
 		case KVM_ARM_PSCI_0_1:
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 96ef9b7e74d4..5bb4de162cab 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -208,14 +208,14 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		kvm_arch_vcpu_put(vcpu);
 
 	if (!kvm_arm_vcpu_sve_finalized(vcpu)) {
-		if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features))
+		if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE))
 			kvm_vcpu_enable_sve(vcpu);
 	} else {
 		kvm_vcpu_reset_sve(vcpu);
 	}
 
-	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
-	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features))
+	if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) ||
+	    vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC))
 		kvm_vcpu_enable_ptrauth(vcpu);
 
 	if (vcpu_el1_is_32bit(vcpu))
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 31029f4f7be8..3546ebc469ad 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -77,7 +77,7 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
 void kvm_vcpu_pmu_resync_el0(void);
 
 #define kvm_vcpu_has_pmu(vcpu)					\
-	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
+	(vcpu_has_feature(vcpu, KVM_ARM_VCPU_PMU_V3))
 
 /*
  * Updates the vcpu's view of the pmu events for this cpu.
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index 6e55b9283789..e8fb624013d1 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -26,7 +26,7 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu)
 	 * revisions. It is thus safe to return the latest, unless
 	 * userspace has instructed us otherwise.
 	 */
-	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) {
+	if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2)) {
 		if (vcpu->kvm->arch.psci_version)
 			return vcpu->kvm->arch.psci_version;
 
-- 
cgit v1.2.3


From 9a0a75d3ccee20149587ab740a2dee31ba401ada Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 27 Sep 2023 10:09:01 +0100
Subject: KVM: arm64: vgic: Make kvm_vgic_inject_irq() take a vcpu pointer

Passing a vcpu_id to kvm_vgic_inject_irq() is silly for two reasons:

- we often confuse vcpu_id and vcpu_idx
- we eventually have to convert it back to a vcpu
- we can't count

Instead, pass a vcpu pointer, which is unambiguous. A NULL vcpu
is also allowed for interrupts that are not private to a vcpu
(such as SPIs).

Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230927090911.3355209-2-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/arch_timer.c      |  2 +-
 arch/arm64/kvm/arm.c             | 23 ++++++++---------------
 arch/arm64/kvm/pmu-emul.c        |  2 +-
 arch/arm64/kvm/vgic/vgic-irqfd.c |  2 +-
 arch/arm64/kvm/vgic/vgic.c       | 12 +++++-------
 include/kvm/arm_vgic.h           |  4 ++--
 6 files changed, 18 insertions(+), 27 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 6dcdae4d38cb..1f828f3b854c 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -458,7 +458,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 				   timer_ctx->irq.level);
 
 	if (!userspace_irqchip(vcpu->kvm)) {
-		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu,
 					  timer_irq(timer_ctx),
 					  timer_ctx->irq.level,
 					  timer_ctx);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 4866b3f7b4ea..fa21fb15e927 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1134,27 +1134,23 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 			  bool line_status)
 {
 	u32 irq = irq_level->irq;
-	unsigned int irq_type, vcpu_idx, irq_num;
-	int nrcpus = atomic_read(&kvm->online_vcpus);
+	unsigned int irq_type, vcpu_id, irq_num;
 	struct kvm_vcpu *vcpu = NULL;
 	bool level = irq_level->level;
 
 	irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK;
-	vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK;
-	vcpu_idx += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1);
+	vcpu_id = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK;
+	vcpu_id += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1);
 	irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK;
 
-	trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level);
+	trace_kvm_irq_line(irq_type, vcpu_id, irq_num, irq_level->level);
 
 	switch (irq_type) {
 	case KVM_ARM_IRQ_TYPE_CPU:
 		if (irqchip_in_kernel(kvm))
 			return -ENXIO;
 
-		if (vcpu_idx >= nrcpus)
-			return -EINVAL;
-
-		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
+		vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
 		if (!vcpu)
 			return -EINVAL;
 
@@ -1166,17 +1162,14 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (!irqchip_in_kernel(kvm))
 			return -ENXIO;
 
-		if (vcpu_idx >= nrcpus)
-			return -EINVAL;
-
-		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
+		vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
 		if (!vcpu)
 			return -EINVAL;
 
 		if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
-		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level, NULL);
+		return kvm_vgic_inject_irq(kvm, vcpu, irq_num, level, NULL);
 	case KVM_ARM_IRQ_TYPE_SPI:
 		if (!irqchip_in_kernel(kvm))
 			return -ENXIO;
@@ -1184,7 +1177,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (irq_num < VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
-		return kvm_vgic_inject_irq(kvm, 0, irq_num, level, NULL);
+		return kvm_vgic_inject_irq(kvm, NULL, irq_num, level, NULL);
 	}
 
 	return -EINVAL;
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 6b066e04dc5d..3afb281ed8d2 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -348,7 +348,7 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 	pmu->irq_level = overflow;
 
 	if (likely(irqchip_in_kernel(vcpu->kvm))) {
-		int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+		int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu,
 					      pmu->irq_num, overflow, pmu);
 		WARN_ON(ret);
 	}
diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c
index 475059bacedf..8c711deb25aa 100644
--- a/arch/arm64/kvm/vgic/vgic-irqfd.c
+++ b/arch/arm64/kvm/vgic/vgic-irqfd.c
@@ -23,7 +23,7 @@ static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e,
 
 	if (!vgic_valid_spi(kvm, spi_id))
 		return -EINVAL;
-	return kvm_vgic_inject_irq(kvm, 0, spi_id, level, NULL);
+	return kvm_vgic_inject_irq(kvm, NULL, spi_id, level, NULL);
 }
 
 /**
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 8be4c1ebdec2..db2a95762b1b 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -422,7 +422,7 @@ retry:
 /**
  * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
  * @kvm:     The VM structure pointer
- * @cpuid:   The CPU for PPIs
+ * @vcpu:    The CPU for PPIs or NULL for global interrupts
  * @intid:   The INTID to inject a new state to.
  * @level:   Edge-triggered:  true:  to trigger the interrupt
  *			      false: to ignore the call
@@ -436,24 +436,22 @@ retry:
  * level-sensitive interrupts.  You can think of the level parameter as 1
  * being HIGH and 0 being LOW and all devices being active-HIGH.
  */
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			bool level, void *owner)
+int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
+			unsigned int intid, bool level, void *owner)
 {
-	struct kvm_vcpu *vcpu;
 	struct vgic_irq *irq;
 	unsigned long flags;
 	int ret;
 
-	trace_vgic_update_irq_pending(cpuid, intid, level);
-
 	ret = vgic_lazy_init(kvm);
 	if (ret)
 		return ret;
 
-	vcpu = kvm_get_vcpu(kvm, cpuid);
 	if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS)
 		return -EINVAL;
 
+	trace_vgic_update_irq_pending(vcpu ? vcpu->vcpu_idx : 0, intid, level);
+
 	irq = vgic_get_irq(kvm, vcpu, intid);
 	if (!irq)
 		return -EINVAL;
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 5b27f94d4fad..8cc38e836f54 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -375,8 +375,8 @@ int kvm_vgic_map_resources(struct kvm *kvm);
 int kvm_vgic_hyp_init(void);
 void kvm_vgic_init_cpu_hardware(void);
 
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			bool level, void *owner);
+int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
+			unsigned int intid, bool level, void *owner);
 int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
 			  u32 vintid, struct irq_ops *ops);
 int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid);
-- 
cgit v1.2.3


From bc512d6a9b92390760f0e8c895501c5016539929 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Thu, 19 Oct 2023 18:56:17 +0000
Subject: KVM: arm64: Make PMEVTYPER<n>_EL0.NSH RES0 if EL2 isn't advertised

The NSH bit, which filters event counting at EL2, is required by the
architecture if an implementation has EL2. Even though KVM doesn't
support nested virt yet, it makes no effort to hide the existence of EL2
from the ID registers. Userspace can, however, change the value of PFR0
to hide EL2. Align KVM's sysreg emulation with the architecture and make
NSH RES0 if EL2 isn't advertised. Keep in mind the bit is ignored when
constructing the backing perf event.

While at it, build the event type mask using explicit field definitions
instead of relying on ARMV8_PMU_EVTYPE_MASK. KVM probably should've been
doing this in the first place, as it avoids changes to the
aforementioned mask affecting sysreg emulation.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231019185618.3442949-2-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/pmu-emul.c | 21 ++++++++++++++-------
 arch/arm64/kvm/sys_regs.c |  8 ++++++--
 include/kvm/arm_pmu.h     |  5 +++++
 3 files changed, 25 insertions(+), 9 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 6b066e04dc5d..32d83db9674e 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -60,6 +60,18 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm)
 	return __kvm_pmu_event_mask(pmuver);
 }
 
+u64 kvm_pmu_evtyper_mask(struct kvm *kvm)
+{
+	u64 mask = ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMU_EXCLUDE_EL0 |
+		   kvm_pmu_event_mask(kvm);
+	u64 pfr0 = IDREG(kvm, SYS_ID_AA64PFR0_EL1);
+
+	if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL2, pfr0))
+		mask |= ARMV8_PMU_INCLUDE_EL2;
+
+	return mask;
+}
+
 /**
  * kvm_pmc_is_64bit - determine if counter is 64bit
  * @pmc: counter context
@@ -657,18 +669,13 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 				    u64 select_idx)
 {
 	struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx);
-	u64 reg, mask;
+	u64 reg;
 
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return;
 
-	mask  =  ARMV8_PMU_EVTYPE_MASK;
-	mask &= ~ARMV8_PMU_EVTYPE_EVENT;
-	mask |= kvm_pmu_event_mask(vcpu->kvm);
-
 	reg = counter_index_to_evtreg(pmc->idx);
-
-	__vcpu_sys_reg(vcpu, reg) = data & mask;
+	__vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm);
 
 	kvm_pmu_create_perf_event(pmc);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e92ec810d449..78720c373904 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -746,8 +746,12 @@ static u64 reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 
 static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
+	/* This thing will UNDEF, who cares about the reset value? */
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return 0;
+
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_EVTYPE_MASK;
+	__vcpu_sys_reg(vcpu, r->reg) &= kvm_pmu_evtyper_mask(vcpu->kvm);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
@@ -988,7 +992,7 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		kvm_pmu_set_counter_event_type(vcpu, p->regval, idx);
 		kvm_vcpu_pmu_restore_guest(vcpu);
 	} else {
-		p->regval = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK;
+		p->regval = __vcpu_sys_reg(vcpu, reg);
 	}
 
 	return true;
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 31029f4f7be8..fd0aa8105a5b 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -101,6 +101,7 @@ void kvm_vcpu_pmu_resync_el0(void);
 })
 
 u8 kvm_arm_pmu_get_pmuver_limit(void);
+u64 kvm_pmu_evtyper_mask(struct kvm *kvm);
 
 #else
 struct kvm_pmu {
@@ -172,6 +173,10 @@ static inline u8 kvm_arm_pmu_get_pmuver_limit(void)
 {
 	return 0;
 }
+static inline u64 kvm_pmu_evtyper_mask(struct kvm *kvm)
+{
+	return 0;
+}
 static inline void kvm_vcpu_pmu_resync_el0(void) {}
 
 #endif
-- 
cgit v1.2.3


From 427733579744ef22ee6d0da9907560d79d937458 Mon Sep 17 00:00:00 2001
From: Reiji Watanabe <reijiw@google.com>
Date: Fri, 20 Oct 2023 21:40:42 +0000
Subject: KVM: arm64: Select default PMU in KVM_ARM_VCPU_INIT handler

Future changes to KVM's sysreg emulation will rely on having a valid PMU
instance to determine the number of implemented counters (PMCR_EL0.N).
This is earlier than when userspace is expected to modify the vPMU
device attributes, where the default is selected today.

Select the default PMU when handling KVM_ARM_VCPU_INIT such that it is
available in time for sysreg emulation.

Reviewed-by: Sebastian Ott <sebott@redhat.com>
Co-developed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Link: https://lore.kernel.org/r/20231020214053.2144305-3-rananta@google.com
[Oliver: rewrite changelog]
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/arm.c      | 19 +++++++++++++++++++
 arch/arm64/kvm/pmu-emul.c | 16 ++++------------
 include/kvm/arm_pmu.h     |  6 ++++++
 3 files changed, 29 insertions(+), 12 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 4866b3f7b4ea..0771c42d02e4 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1229,6 +1229,21 @@ static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu,
 	return !bitmap_equal(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES);
 }
 
+static int kvm_setup_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int ret = 0;
+
+	/*
+	 * When the vCPU has a PMU, but no PMU is set for the guest
+	 * yet, set the default one.
+	 */
+	if (kvm_vcpu_has_pmu(vcpu) && !kvm->arch.arm_pmu)
+		ret = kvm_arm_set_default_pmu(kvm);
+
+	return ret;
+}
+
 static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 				 const struct kvm_vcpu_init *init)
 {
@@ -1244,6 +1259,10 @@ static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 
 	bitmap_copy(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES);
 
+	ret = kvm_setup_vcpu(vcpu);
+	if (ret)
+		goto out_unlock;
+
 	/* Now we know what it is, we can reset it. */
 	ret = kvm_reset_vcpu(vcpu);
 	if (ret) {
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index fb9817bdfeb5..1eb02765dd14 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -717,10 +717,9 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 	 * It is still necessary to get a valid cpu, though, to probe for the
 	 * default PMU instance as userspace is not required to specify a PMU
 	 * type. In order to uphold the preexisting behavior KVM selects the
-	 * PMU instance for the core where the first call to the
-	 * KVM_ARM_VCPU_PMU_V3_CTRL attribute group occurs. A dependent use case
-	 * would be a user with disdain of all things big.LITTLE that affines
-	 * the VMM to a particular cluster of cores.
+	 * PMU instance for the core during vcpu init. A dependent use
+	 * case would be a user with disdain of all things big.LITTLE that
+	 * affines the VMM to a particular cluster of cores.
 	 *
 	 * In any case, userspace should just do the sane thing and use the UAPI
 	 * to select a PMU type directly. But, be wary of the baggage being
@@ -893,7 +892,7 @@ static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu)
  * where vCPUs can be scheduled on any core but the guest
  * counters could stop working.
  */
-static int kvm_arm_set_default_pmu(struct kvm *kvm)
+int kvm_arm_set_default_pmu(struct kvm *kvm)
 {
 	struct arm_pmu *arm_pmu = kvm_pmu_probe_armpmu();
 
@@ -946,13 +945,6 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	if (vcpu->arch.pmu.created)
 		return -EBUSY;
 
-	if (!kvm->arch.arm_pmu) {
-		int ret = kvm_arm_set_default_pmu(kvm);
-
-		if (ret)
-			return ret;
-	}
-
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_PMU_V3_IRQ: {
 		int __user *uaddr = (int __user *)(long)attr->addr;
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 31029f4f7be8..b80c75d80886 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -101,6 +101,7 @@ void kvm_vcpu_pmu_resync_el0(void);
 })
 
 u8 kvm_arm_pmu_get_pmuver_limit(void);
+int kvm_arm_set_default_pmu(struct kvm *kvm);
 
 #else
 struct kvm_pmu {
@@ -174,6 +175,11 @@ static inline u8 kvm_arm_pmu_get_pmuver_limit(void)
 }
 static inline void kvm_vcpu_pmu_resync_el0(void) {}
 
+static inline int kvm_arm_set_default_pmu(struct kvm *kvm)
+{
+	return -ENODEV;
+}
+
 #endif
 
 #endif
-- 
cgit v1.2.3


From 57fc267f1b5caa56dfb46f60e20e673cbc4cc4a8 Mon Sep 17 00:00:00 2001
From: Reiji Watanabe <reijiw@google.com>
Date: Fri, 20 Oct 2023 21:40:43 +0000
Subject: KVM: arm64: PMU: Add a helper to read a vCPU's PMCR_EL0

Add a helper to read a vCPU's PMCR_EL0, and use it whenever KVM
reads a vCPU's PMCR_EL0.

Currently, the PMCR_EL0 value is tracked per vCPU. The following
patches will make (only) PMCR_EL0.N track per guest. Having the
new helper will be useful to combine the PMCR_EL0.N field
(tracked per guest) and the other fields (tracked per vCPU)
to provide the value of PMCR_EL0.

No functional change intended.

Reviewed-by: Sebastian Ott <sebott@redhat.com>
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231020214053.2144305-4-rananta@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/arm.c      |  3 +--
 arch/arm64/kvm/pmu-emul.c | 21 +++++++++++++++------
 arch/arm64/kvm/sys_regs.c |  6 +++---
 include/kvm/arm_pmu.h     |  6 ++++++
 4 files changed, 25 insertions(+), 11 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 0771c42d02e4..624e62b2345a 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -801,8 +801,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 		}
 
 		if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu))
-			kvm_pmu_handle_pmcr(vcpu,
-					    __vcpu_sys_reg(vcpu, PMCR_EL0));
+			kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu));
 
 		if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu))
 			kvm_vcpu_pmu_restore_guest(vcpu);
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 1eb02765dd14..6337ba6f7941 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -72,7 +72,7 @@ static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc)
 
 static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc)
 {
-	u64 val = __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), PMCR_EL0);
+	u64 val = kvm_vcpu_read_pmcr(kvm_pmc_to_vcpu(pmc));
 
 	return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) ||
 	       (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC));
@@ -250,7 +250,7 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 {
-	u64 val = __vcpu_sys_reg(vcpu, PMCR_EL0) >> ARMV8_PMU_PMCR_N_SHIFT;
+	u64 val = kvm_vcpu_read_pmcr(vcpu) >> ARMV8_PMU_PMCR_N_SHIFT;
 
 	val &= ARMV8_PMU_PMCR_N_MASK;
 	if (val == 0)
@@ -272,7 +272,7 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return;
 
-	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val)
+	if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val)
 		return;
 
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
@@ -324,7 +324,7 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
 {
 	u64 reg = 0;
 
-	if ((__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) {
+	if ((kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) {
 		reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
 		reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
 		reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
@@ -426,7 +426,7 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
 {
 	int i;
 
-	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+	if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E))
 		return;
 
 	/* Weed out disabled counters */
@@ -569,7 +569,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc)
 {
 	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
-	return (__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) &&
+	return (kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) &&
 	       (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx));
 }
 
@@ -1084,3 +1084,12 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
 					      ID_AA64DFR0_EL1_PMUVer_V3P5);
 	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp);
 }
+
+/**
+ * kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU
+ * @vcpu: The vcpu pointer
+ */
+u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
+{
+	return __vcpu_sys_reg(vcpu, PMCR_EL0);
+}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e92ec810d449..d490cd903e2b 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -822,7 +822,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		 * Only update writeable bits of PMCR (continuing into
 		 * kvm_pmu_handle_pmcr() as well)
 		 */
-		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
+		val = kvm_vcpu_read_pmcr(vcpu);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
 		if (!kvm_supports_32bit_el0())
@@ -830,7 +830,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		kvm_pmu_handle_pmcr(vcpu, val);
 	} else {
 		/* PMCR.P & PMCR.C are RAZ */
-		val = __vcpu_sys_reg(vcpu, PMCR_EL0)
+		val = kvm_vcpu_read_pmcr(vcpu)
 		      & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
 		p->regval = val;
 	}
@@ -879,7 +879,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 {
 	u64 pmcr, val;
 
-	pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
+	pmcr = kvm_vcpu_read_pmcr(vcpu);
 	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
 	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
 		kvm_inject_undefined(vcpu);
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index b80c75d80886..c6a5e49b850a 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -103,6 +103,7 @@ void kvm_vcpu_pmu_resync_el0(void);
 u8 kvm_arm_pmu_get_pmuver_limit(void);
 int kvm_arm_set_default_pmu(struct kvm *kvm);
 
+u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu);
 #else
 struct kvm_pmu {
 };
@@ -180,6 +181,11 @@ static inline int kvm_arm_set_default_pmu(struct kvm *kvm)
 	return -ENODEV;
 }
 
+static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
 #endif
 
 #endif
-- 
cgit v1.2.3


From 4d20debf9ca160720a0b01ba4f2dc3d62296c4d1 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 20 Oct 2023 21:40:44 +0000
Subject: KVM: arm64: PMU: Set PMCR_EL0.N for vCPU based on the associated PMU

The number of PMU event counters is indicated in PMCR_EL0.N.
For a vCPU with PMUv3 configured, the value is set to the same
value as the current PE on every vCPU reset.  Unless the vCPU is
pinned to PEs that has the PMU associated to the guest from the
initial vCPU reset, the value might be different from the PMU's
PMCR_EL0.N on heterogeneous PMU systems.

Fix this by setting the vCPU's PMCR_EL0.N to the PMU's PMCR_EL0.N
value. Track the PMCR_EL0.N per guest, as only one PMU can be set
for the guest (PMCR_EL0.N must be the same for all vCPUs of the
guest), and it is convenient for updating the value.

To achieve this, the patch introduces a helper,
kvm_arm_pmu_get_max_counters(), that reads the maximum number of
counters from the arm_pmu associated to the VM. Make the function
global as upcoming patches will be interested to know the value
while setting the PMCR.N of the guest from userspace.

KVM does not yet support userspace modifying PMCR_EL0.N.
The following patch will add support for that.

Reviewed-by: Sebastian Ott <sebott@redhat.com>
Co-developed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Link: https://lore.kernel.org/r/20231020214053.2144305-5-rananta@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_host.h |  3 +++
 arch/arm64/kvm/pmu-emul.c         | 21 ++++++++++++++++++++-
 arch/arm64/kvm/sys_regs.c         | 28 ++++++++++++++--------------
 include/kvm/arm_pmu.h             |  6 ++++++
 4 files changed, 43 insertions(+), 15 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index af06ccb7ee34..0fe9cc9dc836 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -257,6 +257,9 @@ struct kvm_arch {
 
 	cpumask_var_t supported_cpus;
 
+	/* PMCR_EL0.N value for the guest */
+	u8 pmcr_n;
+
 	/* Hypercall features firmware registers' descriptor */
 	struct kvm_smccc_features smccc_feat;
 	struct maple_tree smccc_filter;
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 6337ba6f7941..6d4763d7308f 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -873,11 +873,27 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq)
 	return true;
 }
 
+/**
+ * kvm_arm_pmu_get_max_counters - Return the max number of PMU counters.
+ * @kvm: The kvm pointer
+ */
+u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
+{
+	struct arm_pmu *arm_pmu = kvm->arch.arm_pmu;
+
+	/*
+	 * The arm_pmu->num_events considers the cycle counter as well.
+	 * Ignore that and return only the general-purpose counters.
+	 */
+	return arm_pmu->num_events - 1;
+}
+
 static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu)
 {
 	lockdep_assert_held(&kvm->arch.config_lock);
 
 	kvm->arch.arm_pmu = arm_pmu;
+	kvm->arch.pmcr_n = kvm_arm_pmu_get_max_counters(kvm);
 }
 
 /**
@@ -1091,5 +1107,8 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
  */
 u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
 {
-	return __vcpu_sys_reg(vcpu, PMCR_EL0);
+	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0) &
+			~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
+
+	return pmcr | ((u64)vcpu->kvm->arch.pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d490cd903e2b..6dcfac15fe49 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -721,12 +721,7 @@ static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 n, mask = BIT(ARMV8_PMU_CYCLE_IDX);
 
-	/* No PMU available, any PMU reg may UNDEF... */
-	if (!kvm_arm_support_pmu_v3())
-		return 0;
-
-	n = read_sysreg(pmcr_el0) >> ARMV8_PMU_PMCR_N_SHIFT;
-	n &= ARMV8_PMU_PMCR_N_MASK;
+	n = vcpu->kvm->arch.pmcr_n;
 	if (n)
 		mask |= GENMASK(n - 1, 0);
 
@@ -762,17 +757,15 @@ static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 
 static u64 reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	u64 pmcr;
+	u64 pmcr = 0;
 
-	/* No PMU available, PMCR_EL0 may UNDEF... */
-	if (!kvm_arm_support_pmu_v3())
-		return 0;
-
-	/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
-	pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
 	if (!kvm_supports_32bit_el0())
 		pmcr |= ARMV8_PMU_PMCR_LC;
 
+	/*
+	 * The value of PMCR.N field is included when the
+	 * vCPU register is read via kvm_vcpu_read_pmcr().
+	 */
 	__vcpu_sys_reg(vcpu, r->reg) = pmcr;
 
 	return __vcpu_sys_reg(vcpu, r->reg);
@@ -1103,6 +1096,13 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
+		    u64 *val)
+{
+	*val = kvm_vcpu_read_pmcr(vcpu);
+	return 0;
+}
+
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	{ SYS_DESC(SYS_DBGBVRn_EL1(n)),					\
@@ -2167,7 +2167,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_SVCR), undef_access },
 
 	{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr,
-	  .reset = reset_pmcr, .reg = PMCR_EL0 },
+	  .reset = reset_pmcr, .reg = PMCR_EL0, .get_user = get_pmcr },
 	{ PMU_SYS_REG(PMCNTENSET_EL0),
 	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
 	{ PMU_SYS_REG(PMCNTENCLR_EL0),
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index c6a5e49b850a..96e15f4bb18c 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -102,6 +102,7 @@ void kvm_vcpu_pmu_resync_el0(void);
 
 u8 kvm_arm_pmu_get_pmuver_limit(void);
 int kvm_arm_set_default_pmu(struct kvm *kvm);
+u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm);
 
 u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu);
 #else
@@ -181,6 +182,11 @@ static inline int kvm_arm_set_default_pmu(struct kvm *kvm)
 	return -ENODEV;
 }
 
+static inline u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
+{
+	return 0;
+}
+
 static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
 {
 	return 0;
-- 
cgit v1.2.3


From 27131b199f9fdc0e15baa0ff9d1695b54a96e39c Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Fri, 20 Oct 2023 21:40:46 +0000
Subject: KVM: arm64: Sanitize PM{C,I}NTEN{SET,CLR}, PMOVS{SET,CLR} before
 first run

For unimplemented counters, the registers PM{C,I}NTEN{SET,CLR}
and PMOVS{SET,CLR} are expected to have the corresponding bits RAZ.
Hence to ensure correct KVM's PMU emulation, mask out the RES0 bits.
Defer this work to the point that userspace can no longer change the
number of advertised PMCs.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231020214053.2144305-7-rananta@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/arm.c      |  2 +-
 arch/arm64/kvm/pmu-emul.c | 11 +++++++++++
 include/kvm/arm_pmu.h     |  3 ++-
 3 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include/kvm')

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 624e62b2345a..f6307afc5036 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -801,7 +801,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 		}
 
 		if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu))
-			kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu));
+			kvm_vcpu_reload_pmu(vcpu);
 
 		if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu))
 			kvm_vcpu_pmu_restore_guest(vcpu);
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 6d4763d7308f..6b271c542409 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -785,6 +785,17 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	return val & mask;
 }
 
+void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu)
+{
+	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
+
+	kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu));
+
+	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask;
+	__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask;
+	__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask;
+}
+
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
 	if (!kvm_vcpu_has_pmu(vcpu))
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 96e15f4bb18c..abb1e8215ca8 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -13,7 +13,6 @@
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
 
 #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM)
-
 struct kvm_pmc {
 	u8 idx;	/* index into the pmu->pmc array */
 	struct perf_event *perf_event;
@@ -63,6 +62,7 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 				    u64 select_idx);
+void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu);
 int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
@@ -171,6 +171,7 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 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) {}
+static inline void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) {}
 static inline u8 kvm_arm_pmu_get_pmuver_limit(void)
 {
 	return 0;
-- 
cgit v1.2.3