Merge tag 'kvmarm-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 5.19

- Add support for the ARMv8.6 WFxT extension

- Guard pages for the EL2 stacks

- Trap and emulate AArch32 ID registers to hide unsupported features

- Ability to select and save/restore the set of hypercalls exposed
  to the guest

- Support for PSCI-initiated suspend in collaboration with userspace

- GICv3 register-based LPI invalidation support

- Move host PMU event merging into the vcpu data structure

- GICv3 ITS save/restore fixes

- The usual set of small-scale cleanups and fixes

[Due to the conflict, KVM_SYSTEM_EVENT_SEV_TERM is relocated
 from 4 to 6. - Paolo]

1 files changed, 42 insertions, 206 deletions

diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 708d80e8e60d..7fbc4c1b9df0 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -51,13 +51,6 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 	return PSCI_RET_SUCCESS;
 }
 
-static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.power_off = true;
-	kvm_make_request(KVM_REQ_SLEEP, vcpu);
-	kvm_vcpu_kick(vcpu);
-}
-
 static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu,
 					   unsigned long affinity)
 {
@@ -83,7 +76,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 */
 	if (!vcpu)
 		return PSCI_RET_INVALID_PARAMS;
-	if (!vcpu->arch.power_off) {
+	if (!kvm_arm_vcpu_stopped(vcpu)) {
 		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
 			return PSCI_RET_ALREADY_ON;
 		else
@@ -107,12 +100,12 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	kvm_make_request(KVM_REQ_VCPU_RESET, vcpu);
 
 	/*
-	 * Make sure the reset request is observed if the change to
-	 * power_off is observed.
+	 * Make sure the reset request is observed if the RUNNABLE mp_state is
+	 * observed.
 	 */
 	smp_wmb();
 
-	vcpu->arch.power_off = false;
+	vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE;
 	kvm_vcpu_wake_up(vcpu);
 
 	return PSCI_RET_SUCCESS;
@@ -150,7 +143,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 		mpidr = kvm_vcpu_get_mpidr_aff(tmp);
 		if ((mpidr & target_affinity_mask) == target_affinity) {
 			matching_cpus++;
-			if (!tmp->arch.power_off)
+			if (!kvm_arm_vcpu_stopped(tmp))
 				return PSCI_0_2_AFFINITY_LEVEL_ON;
 		}
 	}
@@ -176,7 +169,7 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags)
 	 * re-initialized.
 	 */
 	kvm_for_each_vcpu(i, tmp, vcpu->kvm)
-		tmp->arch.power_off = true;
+		tmp->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED;
 	kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
 
 	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
@@ -202,6 +195,15 @@ static void kvm_psci_system_reset2(struct kvm_vcpu *vcpu)
 				 KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2);
 }
 
+static void kvm_psci_system_suspend(struct kvm_vcpu *vcpu)
+{
+	struct kvm_run *run = vcpu->run;
+
+	memset(&run->system_event, 0, sizeof(vcpu->run->system_event));
+	run->system_event.type = KVM_SYSTEM_EVENT_SUSPEND;
+	run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+}
+
 static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu)
 {
 	int i;
@@ -245,7 +247,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		val = kvm_psci_vcpu_suspend(vcpu);
 		break;
 	case PSCI_0_2_FN_CPU_OFF:
-		kvm_psci_vcpu_off(vcpu);
+		kvm_arm_vcpu_power_off(vcpu);
 		val = PSCI_RET_SUCCESS;
 		break;
 	case PSCI_0_2_FN_CPU_ON:
@@ -305,9 +307,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 
 static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 {
+	unsigned long val = PSCI_RET_NOT_SUPPORTED;
 	u32 psci_fn = smccc_get_function(vcpu);
+	struct kvm *kvm = vcpu->kvm;
 	u32 arg;
-	unsigned long val;
 	int ret = 1;
 
 	switch(psci_fn) {
@@ -320,6 +323,8 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 		if (val)
 			break;
 
+		val = PSCI_RET_NOT_SUPPORTED;
+
 		switch(arg) {
 		case PSCI_0_2_FN_PSCI_VERSION:
 		case PSCI_0_2_FN_CPU_SUSPEND:
@@ -336,18 +341,32 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 		case ARM_SMCCC_VERSION_FUNC_ID:
 			val = 0;
 			break;
+		case PSCI_1_0_FN_SYSTEM_SUSPEND:
+		case PSCI_1_0_FN64_SYSTEM_SUSPEND:
+			if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags))
+				val = 0;
+			break;
 		case PSCI_1_1_FN_SYSTEM_RESET2:
 		case PSCI_1_1_FN64_SYSTEM_RESET2:
-			if (minor >= 1) {
+			if (minor >= 1)
 				val = 0;
-				break;
-			}
-			fallthrough;
-		default:
-			val = PSCI_RET_NOT_SUPPORTED;
 			break;
 		}
 		break;
+	case PSCI_1_0_FN_SYSTEM_SUSPEND:
+		kvm_psci_narrow_to_32bit(vcpu);
+		fallthrough;
+	case PSCI_1_0_FN64_SYSTEM_SUSPEND:
+		/*
+		 * Return directly to userspace without changing the vCPU's
+		 * registers. Userspace depends on reading the SMCCC parameters
+		 * to implement SYSTEM_SUSPEND.
+		 */
+		if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) {
+			kvm_psci_system_suspend(vcpu);
+			return 0;
+		}
+		break;
 	case PSCI_1_1_FN_SYSTEM_RESET2:
 		kvm_psci_narrow_to_32bit(vcpu);
 		fallthrough;
@@ -365,7 +384,7 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 			val = PSCI_RET_INVALID_PARAMS;
 			break;
 		}
-		fallthrough;
+		break;
 	default:
 		return kvm_psci_0_2_call(vcpu);
 	}
@@ -382,7 +401,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 
 	switch (psci_fn) {
 	case KVM_PSCI_FN_CPU_OFF:
-		kvm_psci_vcpu_off(vcpu);
+		kvm_arm_vcpu_power_off(vcpu);
 		val = PSCI_RET_SUCCESS;
 		break;
 	case KVM_PSCI_FN_CPU_ON:
@@ -437,186 +456,3 @@ int kvm_psci_call(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 	}
 }
-
-int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
-{
-	return 4;		/* PSCI version and three workaround registers */
-}
-
-int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
-{
-	if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices++))
-		return -EFAULT;
-
-	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, uindices++))
-		return -EFAULT;
-
-	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++))
-		return -EFAULT;
-
-	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, uindices++))
-		return -EFAULT;
-
-	return 0;
-}
-
-#define KVM_REG_FEATURE_LEVEL_WIDTH	4
-#define KVM_REG_FEATURE_LEVEL_MASK	(BIT(KVM_REG_FEATURE_LEVEL_WIDTH) - 1)
-
-/*
- * Convert the workaround level into an easy-to-compare number, where higher
- * values mean better protection.
- */
-static int get_kernel_wa_level(u64 regid)
-{
-	switch (regid) {
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-		switch (arm64_get_spectre_v2_state()) {
-		case SPECTRE_VULNERABLE:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
-		case SPECTRE_MITIGATED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL;
-		case SPECTRE_UNAFFECTED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED;
-		}
-		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL;
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
-		switch (arm64_get_spectre_v4_state()) {
-		case SPECTRE_MITIGATED:
-			/*
-			 * As for the hypercall discovery, we pretend we
-			 * don't have any FW mitigation if SSBS is there at
-			 * all times.
-			 */
-			if (cpus_have_final_cap(ARM64_SSBS))
-				return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
-			fallthrough;
-		case SPECTRE_UNAFFECTED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
-		case SPECTRE_VULNERABLE:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
-		}
-		break;
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		switch (arm64_get_spectre_bhb_state()) {
-		case SPECTRE_VULNERABLE:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
-		case SPECTRE_MITIGATED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL;
-		case SPECTRE_UNAFFECTED:
-			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED;
-		}
-		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
-	}
-
-	return -EINVAL;
-}
-
-int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
-{
-	void __user *uaddr = (void __user *)(long)reg->addr;
-	u64 val;
-
-	switch (reg->id) {
-	case KVM_REG_ARM_PSCI_VERSION:
-		val = kvm_psci_version(vcpu);
-		break;
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
-		break;
-	default:
-		return -ENOENT;
-	}
-
-	if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	return 0;
-}
-
-int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
-{
-	void __user *uaddr = (void __user *)(long)reg->addr;
-	u64 val;
-	int wa_level;
-
-	if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
-		return -EFAULT;
-
-	switch (reg->id) {
-	case KVM_REG_ARM_PSCI_VERSION:
-	{
-		bool wants_02;
-
-		wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
-
-		switch (val) {
-		case KVM_ARM_PSCI_0_1:
-			if (wants_02)
-				return -EINVAL;
-			vcpu->kvm->arch.psci_version = val;
-			return 0;
-		case KVM_ARM_PSCI_0_2:
-		case KVM_ARM_PSCI_1_0:
-		case KVM_ARM_PSCI_1_1:
-			if (!wants_02)
-				return -EINVAL;
-			vcpu->kvm->arch.psci_version = val;
-			return 0;
-		}
-		break;
-	}
-
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
-			return -EINVAL;
-
-		if (get_kernel_wa_level(reg->id) < val)
-			return -EINVAL;
-
-		return 0;
-
-	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
-		if (val & ~(KVM_REG_FEATURE_LEVEL_MASK |
-			    KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED))
-			return -EINVAL;
-
-		/* The enabled bit must not be set unless the level is AVAIL. */
-		if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) &&
-		    (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL)
-			return -EINVAL;
-
-		/*
-		 * Map all the possible incoming states to the only two we
-		 * really want to deal with.
-		 */
-		switch (val & KVM_REG_FEATURE_LEVEL_MASK) {
-		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL:
-		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN:
-			wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
-			break;
-		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL:
-		case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED:
-			wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED;
-			break;
-		default:
-			return -EINVAL;
-		}
-
-		/*
-		 * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
-		 * other way around.
-		 */
-		if (get_kernel_wa_level(reg->id) < wa_level)
-			return -EINVAL;
-
-		return 0;
-	default:
-		return -ENOENT;
-	}
-
-	return -EINVAL;
-}