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')

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')

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')

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 b37e6b680e3a4fad40d8c7b92cfe9b2806c6248e Mon Sep 17 00:00:00 2001
From: Tianrui Zhao <zhaotianrui@loongson.cn>
Date: Mon, 2 Oct 2023 10:01:20 +0800
Subject: LoongArch: KVM: Add kvm related header files

Add LoongArch KVM related header files, including kvm.h, kvm_host.h and
kvm_types.h. All of those are about LoongArch virtualization features
and kvm interfaces.

Reviewed-by: Bibo Mao <maobibo@loongson.cn>
Tested-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Tianrui Zhao <zhaotianrui@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/kvm_host.h  | 237 +++++++++++++++++++++++++++++++++
 arch/loongarch/include/asm/kvm_types.h |  11 ++
 arch/loongarch/include/uapi/asm/kvm.h  | 108 +++++++++++++++
 include/uapi/linux/kvm.h               |   9 ++
 4 files changed, 365 insertions(+)
 create mode 100644 arch/loongarch/include/asm/kvm_host.h
 create mode 100644 arch/loongarch/include/asm/kvm_types.h
 create mode 100644 arch/loongarch/include/uapi/asm/kvm.h

(limited to 'include')

diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
new file mode 100644
index 000000000000..11328700d4fa
--- /dev/null
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef __ASM_LOONGARCH_KVM_HOST_H__
+#define __ASM_LOONGARCH_KVM_HOST_H__
+
+#include <linux/cpumask.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/kvm.h>
+#include <linux/kvm_types.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+#include <linux/types.h>
+
+#include <asm/inst.h>
+#include <asm/kvm_mmu.h>
+#include <asm/loongarch.h>
+
+/* Loongarch KVM register ids */
+#define KVM_GET_IOC_CSR_IDX(id)		((id & KVM_CSR_IDX_MASK) >> LOONGARCH_REG_SHIFT)
+#define KVM_GET_IOC_CPUCFG_IDX(id)	((id & KVM_CPUCFG_IDX_MASK) >> LOONGARCH_REG_SHIFT)
+
+#define KVM_MAX_VCPUS			256
+#define KVM_MAX_CPUCFG_REGS		21
+/* memory slots that does not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS		0
+
+#define KVM_HALT_POLL_NS_DEFAULT	500000
+
+struct kvm_vm_stat {
+	struct kvm_vm_stat_generic generic;
+	u64 pages;
+	u64 hugepages;
+};
+
+struct kvm_vcpu_stat {
+	struct kvm_vcpu_stat_generic generic;
+	u64 int_exits;
+	u64 idle_exits;
+	u64 cpucfg_exits;
+	u64 signal_exits;
+};
+
+struct kvm_arch_memory_slot {
+};
+
+struct kvm_context {
+	unsigned long vpid_cache;
+	struct kvm_vcpu *last_vcpu;
+};
+
+struct kvm_world_switch {
+	int (*exc_entry)(void);
+	int (*enter_guest)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+	unsigned long page_order;
+};
+
+#define MAX_PGTABLE_LEVELS	4
+
+struct kvm_arch {
+	/* Guest physical mm */
+	kvm_pte_t *pgd;
+	unsigned long gpa_size;
+	unsigned long invalid_ptes[MAX_PGTABLE_LEVELS];
+	unsigned int  pte_shifts[MAX_PGTABLE_LEVELS];
+	unsigned int  root_level;
+
+	s64 time_offset;
+	struct kvm_context __percpu *vmcs;
+};
+
+#define CSR_MAX_NUMS		0x800
+
+struct loongarch_csrs {
+	unsigned long csrs[CSR_MAX_NUMS];
+};
+
+/* Resume Flags */
+#define RESUME_HOST		0
+#define RESUME_GUEST		1
+
+enum emulation_result {
+	EMULATE_DONE,		/* no further processing */
+	EMULATE_DO_MMIO,	/* kvm_run filled with MMIO request */
+	EMULATE_DO_IOCSR,	/* handle IOCSR request */
+	EMULATE_FAIL,		/* can't emulate this instruction */
+	EMULATE_EXCEPT,		/* A guest exception has been generated */
+};
+
+#define KVM_LARCH_FPU		(0x1 << 0)
+#define KVM_LARCH_SWCSR_LATEST	(0x1 << 1)
+#define KVM_LARCH_HWCSR_USABLE	(0x1 << 2)
+
+struct kvm_vcpu_arch {
+	/*
+	 * Switch pointer-to-function type to unsigned long
+	 * for loading the value into register directly.
+	 */
+	unsigned long host_eentry;
+	unsigned long guest_eentry;
+
+	/* Pointers stored here for easy accessing from assembly code */
+	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+
+	/* Host registers preserved across guest mode execution */
+	unsigned long host_sp;
+	unsigned long host_tp;
+	unsigned long host_pgd;
+
+	/* Host CSRs are used when handling exits from guest */
+	unsigned long badi;
+	unsigned long badv;
+	unsigned long host_ecfg;
+	unsigned long host_estat;
+	unsigned long host_percpu;
+
+	/* GPRs */
+	unsigned long gprs[32];
+	unsigned long pc;
+
+	/* Which auxiliary state is loaded (KVM_LARCH_*) */
+	unsigned int aux_inuse;
+
+	/* FPU state */
+	struct loongarch_fpu fpu FPU_ALIGN;
+
+	/* CSR state */
+	struct loongarch_csrs *csr;
+
+	/* GPR used as IO source/target */
+	u32 io_gpr;
+
+	/* KVM register to control count timer */
+	u32 count_ctl;
+	struct hrtimer swtimer;
+
+	/* Bitmask of intr that are pending */
+	unsigned long irq_pending;
+	/* Bitmask of pending intr to be cleared */
+	unsigned long irq_clear;
+
+	/* Bitmask of exceptions that are pending */
+	unsigned long exception_pending;
+	unsigned int  esubcode;
+
+	/* Cache for pages needed inside spinlock regions */
+	struct kvm_mmu_memory_cache mmu_page_cache;
+
+	/* vcpu's vpid */
+	u64 vpid;
+
+	/* Frequency of stable timer in Hz */
+	u64 timer_mhz;
+	ktime_t expire;
+
+	/* Last CPU the vCPU state was loaded on */
+	int last_sched_cpu;
+	/* mp state */
+	struct kvm_mp_state mp_state;
+	/* cpucfg */
+	u32 cpucfg[KVM_MAX_CPUCFG_REGS];
+};
+
+static inline unsigned long readl_sw_gcsr(struct loongarch_csrs *csr, int reg)
+{
+	return csr->csrs[reg];
+}
+
+static inline void writel_sw_gcsr(struct loongarch_csrs *csr, int reg, unsigned long val)
+{
+	csr->csrs[reg] = val;
+}
+
+/* Debug: dump vcpu state */
+int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
+
+/* MMU handling */
+void kvm_flush_tlb_all(void);
+void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa);
+int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write);
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable);
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
+
+static inline void update_pc(struct kvm_vcpu_arch *arch)
+{
+	arch->pc += 4;
+}
+
+/*
+ * kvm_is_ifetch_fault() - Find whether a TLBL exception is due to ifetch fault.
+ * @vcpu:	Virtual CPU.
+ *
+ * Returns:	Whether the TLBL exception was likely due to an instruction
+ *		fetch fault rather than a data load fault.
+ */
+static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *arch)
+{
+	return arch->pc == arch->badv;
+}
+
+/* Misc */
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {}
+void kvm_check_vpid(struct kvm_vcpu *vcpu);
+enum hrtimer_restart kvm_swtimer_wakeup(struct hrtimer *timer);
+void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot);
+void kvm_init_vmcs(struct kvm *kvm);
+void kvm_exc_entry(void);
+int  kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu);
+
+extern unsigned long vpid_mask;
+extern const unsigned long kvm_exception_size;
+extern const unsigned long kvm_enter_guest_size;
+extern struct kvm_world_switch *kvm_loongarch_ops;
+
+#define SW_GCSR		(1 << 0)
+#define HW_GCSR		(1 << 1)
+#define INVALID_GCSR	(1 << 2)
+
+int get_gcsr_flag(int csr);
+void set_hw_gcsr(int csr_id, unsigned long val);
+
+#endif /* __ASM_LOONGARCH_KVM_HOST_H__ */
diff --git a/arch/loongarch/include/asm/kvm_types.h b/arch/loongarch/include/asm/kvm_types.h
new file mode 100644
index 000000000000..2fe1d4bdff66
--- /dev/null
+++ b/arch/loongarch/include/asm/kvm_types.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef _ASM_LOONGARCH_KVM_TYPES_H
+#define _ASM_LOONGARCH_KVM_TYPES_H
+
+#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE	40
+
+#endif /* _ASM_LOONGARCH_KVM_TYPES_H */
diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h
new file mode 100644
index 000000000000..c6ad2ee6106c
--- /dev/null
+++ b/arch/loongarch/include/uapi/asm/kvm.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef __UAPI_ASM_LOONGARCH_KVM_H
+#define __UAPI_ASM_LOONGARCH_KVM_H
+
+#include <linux/types.h>
+
+/*
+ * KVM LoongArch specific structures and definitions.
+ *
+ * Some parts derived from the x86 version of this file.
+ */
+
+#define __KVM_HAVE_READONLY_MEM
+
+#define KVM_COALESCED_MMIO_PAGE_OFFSET	1
+#define KVM_DIRTY_LOG_PAGE_OFFSET	64
+
+/*
+ * for KVM_GET_REGS and KVM_SET_REGS
+ */
+struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 gpr[32];
+	__u64 pc;
+};
+
+/*
+ * for KVM_GET_FPU and KVM_SET_FPU
+ */
+struct kvm_fpu {
+	__u32 fcsr;
+	__u64 fcc;    /* 8x8 */
+	struct kvm_fpureg {
+		__u64 val64[4];
+	} fpr[32];
+};
+
+/*
+ * For LoongArch, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access various
+ * registers.  The id field is broken down as follows:
+ *
+ *  bits[63..52] - As per linux/kvm.h
+ *  bits[51..32] - Must be zero.
+ *  bits[31..16] - Register set.
+ *
+ * Register set = 0: GP registers from kvm_regs (see definitions below).
+ *
+ * Register set = 1: CSR registers.
+ *
+ * Register set = 2: KVM specific registers (see definitions below).
+ *
+ * Register set = 3: FPU / SIMD registers (see definitions below).
+ *
+ * Other sets registers may be added in the future.  Each set would
+ * have its own identifier in bits[31..16].
+ */
+
+#define KVM_REG_LOONGARCH_GPR		(KVM_REG_LOONGARCH | 0x00000ULL)
+#define KVM_REG_LOONGARCH_CSR		(KVM_REG_LOONGARCH | 0x10000ULL)
+#define KVM_REG_LOONGARCH_KVM		(KVM_REG_LOONGARCH | 0x20000ULL)
+#define KVM_REG_LOONGARCH_FPSIMD	(KVM_REG_LOONGARCH | 0x30000ULL)
+#define KVM_REG_LOONGARCH_CPUCFG	(KVM_REG_LOONGARCH | 0x40000ULL)
+#define KVM_REG_LOONGARCH_MASK		(KVM_REG_LOONGARCH | 0x70000ULL)
+#define KVM_CSR_IDX_MASK		0x7fff
+#define KVM_CPUCFG_IDX_MASK		0x7fff
+
+/*
+ * KVM_REG_LOONGARCH_KVM - KVM specific control registers.
+ */
+
+#define KVM_REG_LOONGARCH_COUNTER	(KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 1)
+#define KVM_REG_LOONGARCH_VCPU_RESET	(KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 2)
+
+#define LOONGARCH_REG_SHIFT		3
+#define LOONGARCH_REG_64(TYPE, REG)	(TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT))
+#define KVM_IOC_CSRID(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CSR, REG)
+#define KVM_IOC_CPUCFG(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG)
+
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+/* dummy definition */
+struct kvm_sregs {
+};
+
+struct kvm_iocsr_entry {
+	__u32 addr;
+	__u32 pad;
+	__u64 data;
+};
+
+#define KVM_NR_IRQCHIPS		1
+#define KVM_IRQCHIP_NUM_PINS	64
+#define KVM_MAX_CORES		256
+
+#endif /* __UAPI_ASM_LOONGARCH_KVM_H */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 13065dd96132..863f84619a15 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -264,6 +264,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_SBI        35
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
+#define KVM_EXIT_LOONGARCH_IOCSR  38
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -336,6 +337,13 @@ struct kvm_run {
 			__u32 len;
 			__u8  is_write;
 		} mmio;
+		/* KVM_EXIT_LOONGARCH_IOCSR */
+		struct {
+			__u64 phys_addr;
+			__u8  data[8];
+			__u32 len;
+			__u8  is_write;
+		} iocsr_io;
 		/* KVM_EXIT_HYPERCALL */
 		struct {
 			__u64 nr;
@@ -1362,6 +1370,7 @@ struct kvm_dirty_tlb {
 #define KVM_REG_ARM64		0x6000000000000000ULL
 #define KVM_REG_MIPS		0x7000000000000000ULL
 #define KVM_REG_RISCV		0x8000000000000000ULL
+#define KVM_REG_LOONGARCH	0x9000000000000000ULL
 
 #define KVM_REG_SIZE_SHIFT	52
 #define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
-- 
cgit v1.2.3


From 3f9cd0ca848413fd368278310d2cdd6c2bef48b2 Mon Sep 17 00:00:00 2001
From: Jing Zhang <jingzhangos@google.com>
Date: Tue, 3 Oct 2023 23:03:57 +0000
Subject: KVM: arm64: Allow userspace to get the writable masks for feature ID
 registers

While the Feature ID range is well defined and pretty large, it isn't
inconceivable that the architecture will eventually grow some other
ranges that will need to similarly be described to userspace.

Add a VM ioctl to allow userspace to get writable masks for feature ID
registers in below system register space:
op0 = 3, op1 = {0, 1, 3}, CRn = 0, CRm = {0 - 7}, op2 = {0 - 7}
This is used to support mix-and-match userspace and kernels for writable
ID registers, where userspace may want to know upfront whether it can
actually tweak the contents of an idreg or not.

Add a new capability (KVM_CAP_ARM_SUPPORTED_FEATURE_ID_RANGES) that
returns a bitmap of the valid ranges, which can subsequently be
retrieved, one at a time by setting the index of the set bit as the
range identifier.

Suggested-by: Marc Zyngier <maz@kernel.org>
Suggested-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20231003230408.3405722-2-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_host.h |  2 ++
 arch/arm64/include/uapi/asm/kvm.h | 32 +++++++++++++++++++
 arch/arm64/kvm/arm.c              | 10 ++++++
 arch/arm64/kvm/sys_regs.c         | 66 +++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/kvm.h          |  2 ++
 5 files changed, 112 insertions(+)

(limited to 'include')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index af06ccb7ee34..5e3f778f81db 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1078,6 +1078,8 @@ int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
 			       struct kvm_arm_copy_mte_tags *copy_tags);
 int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
 				    struct kvm_arm_counter_offset *offset);
+int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm,
+					struct reg_mask_range *range);
 
 /* Guest/host FPSIMD coordination helpers */
 int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index f7ddd73a8c0f..89d2fc872d9f 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -505,6 +505,38 @@ struct kvm_smccc_filter {
 #define KVM_HYPERCALL_EXIT_SMC		(1U << 0)
 #define KVM_HYPERCALL_EXIT_16BIT	(1U << 1)
 
+/*
+ * Get feature ID registers userspace writable mask.
+ *
+ * From DDI0487J.a, D19.2.66 ("ID_AA64MMFR2_EL1, AArch64 Memory Model
+ * Feature Register 2"):
+ *
+ * "The Feature ID space is defined as the System register space in
+ * AArch64 with op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7},
+ * op2=={0-7}."
+ *
+ * This covers all currently known R/O registers that indicate
+ * anything useful feature wise, including the ID registers.
+ *
+ * If we ever need to introduce a new range, it will be described as
+ * such in the range field.
+ */
+#define KVM_ARM_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)		\
+	({								\
+		__u64 __op1 = (op1) & 3;				\
+		__op1 -= (__op1 == 3);					\
+		(__op1 << 6 | ((crm) & 7) << 3 | (op2));		\
+	})
+
+#define KVM_ARM_FEATURE_ID_RANGE	0
+#define KVM_ARM_FEATURE_ID_RANGE_SIZE	(3 * 8 * 8)
+
+struct reg_mask_range {
+	__u64 addr;		/* Pointer to mask array */
+	__u32 range;		/* Requested range */
+	__u32 reserved[13];
+};
+
 #endif
 
 #endif /* __ARM_KVM_H__ */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 4866b3f7b4ea..f48430ed5b8b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -317,6 +317,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES:
 		r = kvm_supported_block_sizes();
 		break;
+	case KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES:
+		r = BIT(0);
+		break;
 	default:
 		r = 0;
 	}
@@ -1629,6 +1632,13 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 
 		return kvm_vm_set_attr(kvm, &attr);
 	}
+	case KVM_ARM_GET_REG_WRITABLE_MASKS: {
+		struct reg_mask_range range;
+
+		if (copy_from_user(&range, argp, sizeof(range)))
+			return -EFAULT;
+		return kvm_vm_ioctl_get_reg_writable_masks(kvm, &range);
+	}
 	default:
 		return -EINVAL;
 	}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e92ec810d449..5b0e94367f74 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1373,6 +1373,13 @@ static inline bool is_id_reg(u32 id)
 		sys_reg_CRm(id) < 8);
 }
 
+static inline bool is_aa32_id_reg(u32 id)
+{
+	return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 &&
+		sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 &&
+		sys_reg_CRm(id) <= 3);
+}
+
 static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
 				  const struct sys_reg_desc *r)
 {
@@ -3572,6 +3579,65 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 	return write_demux_regids(uindices);
 }
 
+#define KVM_ARM_FEATURE_ID_RANGE_INDEX(r)			\
+	KVM_ARM_FEATURE_ID_RANGE_IDX(sys_reg_Op0(r),		\
+		sys_reg_Op1(r),					\
+		sys_reg_CRn(r),					\
+		sys_reg_CRm(r),					\
+		sys_reg_Op2(r))
+
+static bool is_feature_id_reg(u32 encoding)
+{
+	return (sys_reg_Op0(encoding) == 3 &&
+		(sys_reg_Op1(encoding) < 2 || sys_reg_Op1(encoding) == 3) &&
+		sys_reg_CRn(encoding) == 0 &&
+		sys_reg_CRm(encoding) <= 7);
+}
+
+int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *range)
+{
+	const void *zero_page = page_to_virt(ZERO_PAGE(0));
+	u64 __user *masks = (u64 __user *)range->addr;
+
+	/* Only feature id range is supported, reserved[13] must be zero. */
+	if (range->range ||
+	    memcmp(range->reserved, zero_page, sizeof(range->reserved)))
+		return -EINVAL;
+
+	/* Wipe the whole thing first */
+	if (clear_user(masks, KVM_ARM_FEATURE_ID_RANGE_SIZE * sizeof(__u64)))
+		return -EFAULT;
+
+	for (int i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) {
+		const struct sys_reg_desc *reg = &sys_reg_descs[i];
+		u32 encoding = reg_to_encoding(reg);
+		u64 val;
+
+		if (!is_feature_id_reg(encoding) || !reg->set_user)
+			continue;
+
+		/*
+		 * For ID registers, we return the writable mask. Other feature
+		 * registers return a full 64bit mask. That's not necessary
+		 * compliant with a given revision of the architecture, but the
+		 * RES0/RES1 definitions allow us to do that.
+		 */
+		if (is_id_reg(encoding)) {
+			if (!reg->val ||
+			    (is_aa32_id_reg(encoding) && !kvm_supports_32bit_el0()))
+				continue;
+			val = reg->val;
+		} else {
+			val = ~0UL;
+		}
+
+		if (put_user(val, (masks + KVM_ARM_FEATURE_ID_RANGE_INDEX(encoding))))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
 int __init kvm_sys_reg_table_init(void)
 {
 	struct sys_reg_params params;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 13065dd96132..f49c84487200 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1192,6 +1192,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_COUNTER_OFFSET 227
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
+#define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1562,6 +1563,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
 /* Available with KVM_CAP_COUNTER_OFFSET */
 #define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO,  0xb5, struct kvm_arm_counter_offset)
+#define KVM_ARM_GET_REG_WRITABLE_MASKS _IOR(KVMIO,  0xb6, struct reg_mask_range)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
-- 
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')

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 ae8d3522e5b7208d238c893a00957864536983dc Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Thu, 19 Oct 2023 18:56:18 +0000
Subject: KVM: arm64: Add PMU event filter bits required if EL3 is implemented

Suzuki noticed that KVM's PMU emulation is oblivious to the NSU and NSK
event filter bits. On systems that have EL3 these bits modify the
filter behavior in non-secure EL0 and EL1, respectively. Even though the
kernel doesn't use these bits, it is entirely possible some other guest
OS does. Additionally, it would appear that these and the M bit are
required by the architecture if EL3 is implemented.

Allow the EL3 event filter bits to be set if EL3 is advertised in the
guest's ID register. Implement the behavior of NSU and NSK according to
the pseudocode, and entirely ignore the M bit for perf event creation.

Reported-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20231019185618.3442949-3-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/pmu-emul.c      | 15 +++++++++++++--
 include/linux/perf/arm_pmuv3.h |  9 ++++++---
 2 files changed, 19 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 32d83db9674e..e6be14e38cee 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -69,6 +69,11 @@ u64 kvm_pmu_evtyper_mask(struct kvm *kvm)
 	if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL2, pfr0))
 		mask |= ARMV8_PMU_INCLUDE_EL2;
 
+	if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL3, pfr0))
+		mask |= ARMV8_PMU_EXCLUDE_NS_EL0 |
+			ARMV8_PMU_EXCLUDE_NS_EL1 |
+			ARMV8_PMU_EXCLUDE_EL3;
+
 	return mask;
 }
 
@@ -596,6 +601,7 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc)
 	struct perf_event *event;
 	struct perf_event_attr attr;
 	u64 eventsel, reg, data;
+	bool p, u, nsk, nsu;
 
 	reg = counter_index_to_evtreg(pmc->idx);
 	data = __vcpu_sys_reg(vcpu, reg);
@@ -622,13 +628,18 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc)
 	    !test_bit(eventsel, vcpu->kvm->arch.pmu_filter))
 		return;
 
+	p = data & ARMV8_PMU_EXCLUDE_EL1;
+	u = data & ARMV8_PMU_EXCLUDE_EL0;
+	nsk = data & ARMV8_PMU_EXCLUDE_NS_EL1;
+	nsu = data & ARMV8_PMU_EXCLUDE_NS_EL0;
+
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.type = arm_pmu->pmu.type;
 	attr.size = sizeof(attr);
 	attr.pinned = 1;
 	attr.disabled = !kvm_pmu_counter_is_enabled(pmc);
-	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
-	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
+	attr.exclude_user = (u != nsu);
+	attr.exclude_kernel = (p != nsk);
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
 	attr.config = eventsel;
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index e3899bd77f5c..9c226adf938a 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -234,9 +234,12 @@
 /*
  * Event filters for PMUv3
  */
-#define ARMV8_PMU_EXCLUDE_EL1	(1U << 31)
-#define ARMV8_PMU_EXCLUDE_EL0	(1U << 30)
-#define ARMV8_PMU_INCLUDE_EL2	(1U << 27)
+#define ARMV8_PMU_EXCLUDE_EL1		(1U << 31)
+#define ARMV8_PMU_EXCLUDE_EL0		(1U << 30)
+#define ARMV8_PMU_EXCLUDE_NS_EL1	(1U << 29)
+#define ARMV8_PMU_EXCLUDE_NS_EL0	(1U << 28)
+#define ARMV8_PMU_INCLUDE_EL2		(1U << 27)
+#define ARMV8_PMU_EXCLUDE_EL3		(1U << 26)
 
 /*
  * PMUSERENR: user enable reg
-- 
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')

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')

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')

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')

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