Merge tag 'kvmarm-fixes-5.8-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-master

KVM/arm fixes for 5.8, take #2

- Make sure a vcpu becoming non-resident doesn't race against the doorbell delivery
- Only advertise pvtime if accounting is enabled
- Return the correct error code if reset fails with SVE
- Make sure that pseudo-NMI functions are annotated as __always_inline

Author: bonzini

arch/arm64/include/asm/arch_gicv3.h

@@ -109,7 +109,7 @@ static inline u32 gic_read_pmr(void)
 	return read_sysreg_s(SYS_ICC_PMR_EL1);
 }
 
-static inline void gic_write_pmr(u32 val)
+static __always_inline void gic_write_pmr(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_PMR_EL1);
 }

arch/arm64/include/asm/cpufeature.h

@@ -675,7 +675,7 @@ static inline bool system_supports_generic_auth(void)
 		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
 }
 
-static inline bool system_uses_irq_prio_masking(void)
+static __always_inline bool system_uses_irq_prio_masking(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);

arch/arm64/kvm/pvtime.c

@@ -3,6 +3,7 @@
 
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
+#include <linux/sched/stat.h>
 
 #include <asm/kvm_mmu.h>
 #include <asm/pvclock-abi.h>
@@ -73,6 +74,11 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
+static bool kvm_arm_pvtime_supported(void)
+{
+	return !!sched_info_on();
+}
+
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr)
 {
@@ -82,7 +88,8 @@ int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 	int ret = 0;
 	int idx;
 
-	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+	if (!kvm_arm_pvtime_supported() ||
+	    attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
 		return -ENXIO;
 
 	if (get_user(ipa, user))
@@ -110,7 +117,8 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
 	u64 __user *user = (u64 __user *)attr->addr;
 	u64 ipa;
 
-	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+	if (!kvm_arm_pvtime_supported() ||
+	    attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
 		return -ENXIO;
 
 	ipa = vcpu->arch.steal.base;
@@ -125,7 +133,8 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 {
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_PVTIME_IPA:
-		return 0;
+		if (kvm_arm_pvtime_supported())
+			return 0;
 	}
 	return -ENXIO;
 }

arch/arm64/kvm/reset.c

@@ -245,7 +245,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
-	int ret = -EINVAL;
+	int ret;
 	bool loaded;
 	u32 pstate;
 
@@ -269,15 +269,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *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))
+		if (kvm_vcpu_enable_ptrauth(vcpu)) {
+			ret = -EINVAL;
 			goto out;
+		}
 	}
 
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
+			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
+				ret = -EINVAL;
 				goto out;
+			}
 			pstate = VCPU_RESET_PSTATE_SVC;
 		} else {
 			pstate = VCPU_RESET_PSTATE_EL1;

arch/arm64/kvm/vgic/vgic-v4.c

@@ -90,7 +90,15 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 	    !irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
 		disable_irq_nosync(irq);
 
+	/*
+	 * The v4.1 doorbell can fire concurrently with the vPE being
+	 * made non-resident. Ensure we only update pending_last
+	 * *after* the non-residency sequence has completed.
+	 */
+	raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
+	raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
+
 	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
 

drivers/irqchip/irq-gic-v3-its.c

@@ -4054,16 +4054,24 @@ static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
 	u64 val;
 
 	if (info->req_db) {
+		unsigned long flags;
+
 		/*
 		 * vPE is going to block: make the vPE non-resident with
 		 * PendingLast clear and DB set. The GIC guarantees that if
 		 * we read-back PendingLast clear, then a doorbell will be
 		 * delivered when an interrupt comes.
+		 *
+		 * Note the locking to deal with the concurrent update of
+		 * pending_last from the doorbell interrupt handler that can
+		 * run concurrently.
 		 */
+		raw_spin_lock_irqsave(&vpe->vpe_lock, flags);
 		val = its_clear_vpend_valid(vlpi_base,
 					    GICR_VPENDBASER_PendingLast,
 					    GICR_VPENDBASER_4_1_DB);
 		vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
+		raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags);
 	} else {
 		/*
 		 * We're not blocking, so just make the vPE non-resident