Merge branch kvm-arm64/feature-flag-refactor into kvmarm/next

* kvm-arm64/feature-flag-refactor:
  : vCPU feature flag cleanup
  :
  : Clean up KVM's handling of vCPU feature flags to get rid of the
  : vCPU-scoped bitmaps and remove failure paths from kvm_reset_vcpu().
  KVM: arm64: Get rid of vCPU-scoped feature bitmap
  KVM: arm64: Remove unused return value from kvm_reset_vcpu()
  KVM: arm64: Hoist NV+SVE check into KVM_ARM_VCPU_INIT ioctl handler
  KVM: arm64: Prevent NV feature flag on systems w/o nested virt
  KVM: arm64: Hoist PAuth checks into KVM_ARM_VCPU_INIT ioctl
  KVM: arm64: Hoist SVE check into KVM_ARM_VCPU_INIT ioctl handler
  KVM: arm64: Hoist PMUv3 check into KVM_ARM_VCPU_INIT ioctl handler
  KVM: arm64: Add generic check for system-supported vCPU features
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

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())

arch/arm64/include/asm/kvm_host.h

@@ -78,7 +78,7 @@ extern unsigned int __ro_after_init kvm_sve_max_vl;
 int __init kvm_arm_init_sve(void);
 
 u32 __attribute_const__ kvm_target_cpu(void);
-int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
+void kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
 
 struct kvm_hyp_memcache {
@@ -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;
 

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);

arch/arm64/kvm/arch_timer.c

@@ -943,7 +943,7 @@ void kvm_timer_sync_user(struct kvm_vcpu *vcpu)
 		unmask_vtimer_irq_user(vcpu);
 }
 
-int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
+void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
 	struct timer_map map;
@@ -987,8 +987,6 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 		soft_timer_cancel(&map.emul_vtimer->hrtimer);
 	if (map.emul_ptimer)
 		soft_timer_cancel(&map.emul_ptimer->hrtimer);
-
-	return 0;
 }
 
 static void timer_context_init(struct kvm_vcpu *vcpu, int timerid)

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;
 
@@ -1190,6 +1189,30 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 	return -EINVAL;
 }
 
+static unsigned long system_supported_vcpu_features(void)
+{
+	unsigned long features = KVM_VCPU_VALID_FEATURES;
+
+	if (!cpus_have_final_cap(ARM64_HAS_32BIT_EL1))
+		clear_bit(KVM_ARM_VCPU_EL1_32BIT, &features);
+
+	if (!kvm_arm_support_pmu_v3())
+		clear_bit(KVM_ARM_VCPU_PMU_V3, &features);
+
+	if (!system_supports_sve())
+		clear_bit(KVM_ARM_VCPU_SVE, &features);
+
+	if (!system_has_full_ptr_auth()) {
+		clear_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features);
+		clear_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features);
+	}
+
+	if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
+		clear_bit(KVM_ARM_VCPU_HAS_EL2, &features);
+
+	return features;
+}
+
 static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu,
 					const struct kvm_vcpu_init *init)
 {
@@ -1204,12 +1227,25 @@ static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu,
 			return -ENOENT;
 	}
 
-	if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features))
-		return 0;
+	if (features & ~system_supported_vcpu_features())
+		return -EINVAL;
 
-	if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
+	/*
+	 * For now make sure that both address/generic pointer authentication
+	 * features are requested by the userspace together.
+	 */
+	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features) !=
+	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features))
+		return -EINVAL;
+
+	/* Disallow NV+SVE for the time being */
+	if (test_bit(KVM_ARM_VCPU_HAS_EL2, &features) &&
+	    test_bit(KVM_ARM_VCPU_SVE, &features))
 		return -EINVAL;
 
+	if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features))
+		return 0;
+
 	/* MTE is incompatible with AArch32 */
 	if (kvm_has_mte(vcpu->kvm))
 		return -EINVAL;
@@ -1226,7 +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,
@@ -1239,21 +1276,17 @@ 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. */
-	ret = kvm_reset_vcpu(vcpu);
-	if (ret) {
-		bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
-		goto out_unlock;
-	}
+	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;
 out_unlock:
 	mutex_unlock(&kvm->arch.config_lock);
 	return ret;
@@ -1278,7 +1311,8 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 	if (kvm_vcpu_init_changed(vcpu, init))
 		return -EINVAL;
 
-	return kvm_reset_vcpu(vcpu);
+	kvm_reset_vcpu(vcpu);
+	return 0;
 }
 
 static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,

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:

arch/arm64/kvm/reset.c

@@ -73,11 +73,8 @@ int __init kvm_arm_init_sve(void)
 	return 0;
 }
 
-static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
+static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
 {
-	if (!system_supports_sve())
-		return -EINVAL;
-
 	vcpu->arch.sve_max_vl = kvm_sve_max_vl;
 
 	/*
@@ -86,8 +83,6 @@ static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
 	 * kvm_arm_vcpu_finalize(), which freezes the configuration.
 	 */
 	vcpu_set_flag(vcpu, GUEST_HAS_SVE);
-
-	return 0;
 }
 
 /*
@@ -170,20 +165,9 @@ static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
 		memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu));
 }
 
-static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
+static void kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * For now make sure that both address/generic pointer authentication
-	 * features are requested by the userspace together and the system
-	 * supports these capabilities.
-	 */
-	if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
-	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) ||
-	    !system_has_full_ptr_auth())
-		return -EINVAL;
-
 	vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH);
-	return 0;
 }
 
 /**
@@ -204,10 +188,9 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
  * disable preemption around the vcpu reset as we would otherwise race with
  * preempt notifiers which also call put/load.
  */
-int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
+void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_reset_state reset_state;
-	int ret;
 	bool loaded;
 	u32 pstate;
 
@@ -224,29 +207,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	if (loaded)
 		kvm_arch_vcpu_put(vcpu);
 
-	/* Disallow NV+SVE for the time being */
-	if (vcpu_has_nv(vcpu) && vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	if (!kvm_arm_vcpu_sve_finalized(vcpu)) {
-		if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) {
-			ret = kvm_vcpu_enable_sve(vcpu);
-			if (ret)
-				goto out;
-		}
+		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 (kvm_vcpu_enable_ptrauth(vcpu)) {
-			ret = -EINVAL;
-			goto out;
-		}
-	}
+	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))
 		pstate = VCPU_RESET_PSTATE_SVC;
@@ -255,11 +225,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	else
 		pstate = VCPU_RESET_PSTATE_EL1;
 
-	if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	/* Reset core registers */
 	memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
 	memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs));
@@ -294,12 +259,11 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	}
 
 	/* Reset timer */
-	ret = kvm_timer_vcpu_reset(vcpu);
-out:
+	kvm_timer_vcpu_reset(vcpu);
+
 	if (loaded)
 		kvm_arch_vcpu_load(vcpu, smp_processor_id());
 	preempt_enable();
-	return ret;
 }
 
 u32 get_kvm_ipa_limit(void)

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);

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.

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;