Merge branch kvm-arm64/misc-5.15 into kvmarm-master/next

* kvm-arm64/misc-5.15:
  : Misc improvements for 5.15:
  :
  : - Account the number of VMID-wide TLB invalidations as
  :   remote TLB flushes
  : - Fix comments in the VGIC code
  : - Cleanup the PMU IMPDEF identification
  : - Streamline the TGRAN2 usage
  : - Avoid advertising a 52bit IPA range for non-64KB configs
  : - Avoid spurious signalling when a HW-mapped interrupt is in the
  :   A+P state on entry, and in the P state on exit, but that the
  :   physical line is not pending anymore.
  : - Bunch of minor cleanups
  KVM: arm64: vgic: Resample HW pending state on deactivation
  KVM: arm64: vgic: Drop WARN from vgic_get_irq
  KVM: arm64: Drop unused REQUIRES_VIRT
  KVM: arm64: Drop check_kvm_target_cpu() based percpu probe
  KVM: arm64: Drop init_common_resources()
  KVM: arm64: Use ARM64_MIN_PARANGE_BITS as the minimum supported IPA
  arm64/mm: Add remaining ID_AA64MMFR0_PARANGE_ macros
  KVM: arm64: Restrict IPA size to maximum 48 bits on 4K and 16K page size
  arm64/mm: Define ID_AA64MMFR0_TGRAN_2_SHIFT
  KVM: arm64: perf: Replace '0xf' instances with ID_AA64DFR0_PMUVER_IMP_DEF
  KVM: arm64: Fix comments related to GICv2 PMR reporting
  KVM: arm64: Count VMID-wide TLB invalidations
  arm64/kexec: Test page size support with new TGRAN range values

Signed-off-by: Marc Zyngier <maz@kernel.org>

11 files changed, 72 insertions, 112 deletions

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e9a2b8f27792..d779a29c5607 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -42,10 +42,6 @@
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_psci.h>
 
-#ifdef REQUIRES_VIRT
-__asm__(".arch_extension	virt");
-#endif
-
 static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT;
 DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
 
@@ -1035,7 +1031,7 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			       const struct kvm_vcpu_init *init)
 {
 	unsigned int i, ret;
-	int phys_target = kvm_target_cpu();
+	u32 phys_target = kvm_target_cpu();
 
 	if (init->target != phys_target)
 		return -EINVAL;
@@ -1696,11 +1692,6 @@ static bool init_psci_relay(void)
 	return true;
 }
 
-static int init_common_resources(void)
-{
-	return kvm_set_ipa_limit();
-}
-
 static int init_subsystems(void)
 {
 	int err = 0;
@@ -2015,11 +2006,6 @@ static int finalize_hyp_mode(void)
 	return 0;
 }
 
-static void check_kvm_target_cpu(void *ret)
-{
-	*(int *)ret = kvm_target_cpu();
-}
-
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
 {
 	struct kvm_vcpu *vcpu;
@@ -2079,7 +2065,6 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons)
 int kvm_arch_init(void *opaque)
 {
 	int err;
-	int ret, cpu;
 	bool in_hyp_mode;
 
 	if (!is_hyp_mode_available()) {
@@ -2094,15 +2079,7 @@ int kvm_arch_init(void *opaque)
 		kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \
 			 "Only trusted guests should be used on this system.\n");
 
-	for_each_online_cpu(cpu) {
-		smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
-		if (ret < 0) {
-			kvm_err("Error, CPU %d not supported!\n", cpu);
-			return -ENODEV;
-		}
-	}
-
-	err = init_common_resources();
+	err = kvm_set_ipa_limit();
 	if (err)
 		return err;
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 1dfb83578277..8ce850fa7b49 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -842,7 +842,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int __attribute_const__ kvm_target_cpu(void)
+u32 __attribute_const__ kvm_target_cpu(void)
 {
 	unsigned long implementor = read_cpuid_implementor();
 	unsigned long part_number = read_cpuid_part_number();
@@ -874,7 +874,7 @@ int __attribute_const__ kvm_target_cpu(void)
 
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
 {
-	int target = kvm_target_cpu();
+	u32 target = kvm_target_cpu();
 
 	if (target < 0)
 		return -ENODEV;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6e002d30a478..f446f55b6832 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -81,6 +81,7 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
 	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
+	++kvm->stat.generic.remote_tlb_flush;
 }
 
 static bool kvm_is_device_pfn(unsigned long pfn)
diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c
index 151c31fb9860..f9bb3b14130e 100644
--- a/arch/arm64/kvm/perf.c
+++ b/arch/arm64/kvm/perf.c
@@ -50,7 +50,7 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
 
 int kvm_perf_init(void)
 {
-	if (kvm_pmu_probe_pmuver() != 0xf && !is_protected_kvm_enabled())
+	if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled())
 		static_branch_enable(&kvm_arm_pmu_available);
 
 	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index dc65b58dc68f..f5065f23b413 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -745,7 +745,7 @@ int kvm_pmu_probe_pmuver(void)
 	struct perf_event_attr attr = { };
 	struct perf_event *event;
 	struct arm_pmu *pmu;
-	int pmuver = 0xf;
+	int pmuver = ID_AA64DFR0_PMUVER_IMP_DEF;
 
 	/*
 	 * Create a dummy event that only counts user cycles. As we'll never
@@ -770,7 +770,7 @@ int kvm_pmu_probe_pmuver(void)
 	if (IS_ERR(event)) {
 		pr_err_once("kvm: pmu event creation failed %ld\n",
 			    PTR_ERR(event));
-		return 0xf;
+		return ID_AA64DFR0_PMUVER_IMP_DEF;
 	}
 
 	if (event->pmu) {
@@ -923,7 +923,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	if (!vcpu->kvm->arch.pmuver)
 		vcpu->kvm->arch.pmuver = kvm_pmu_probe_pmuver();
 
-	if (vcpu->kvm->arch.pmuver == 0xf)
+	if (vcpu->kvm->arch.pmuver == ID_AA64DFR0_PMUVER_IMP_DEF)
 		return -ENODEV;
 
 	switch (attr->attr) {
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index cba7872d69a8..08fd487d5f95 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -311,31 +311,26 @@ u32 get_kvm_ipa_limit(void)
 
 int kvm_set_ipa_limit(void)
 {
-	unsigned int parange, tgran_2;
+	unsigned int parange;
 	u64 mmfr0;
 
 	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 	parange = cpuid_feature_extract_unsigned_field(mmfr0,
 				ID_AA64MMFR0_PARANGE_SHIFT);
+	/*
+	 * IPA size beyond 48 bits could not be supported
+	 * on either 4K or 16K page size. Hence let's cap
+	 * it to 48 bits, in case it's reported as larger
+	 * on the system.
+	 */
+	if (PAGE_SIZE != SZ_64K)
+		parange = min(parange, (unsigned int)ID_AA64MMFR0_PARANGE_48);
 
 	/*
 	 * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
 	 * Stage-2. If not, things will stop very quickly.
 	 */
-	switch (PAGE_SIZE) {
-	default:
-	case SZ_4K:
-		tgran_2 = ID_AA64MMFR0_TGRAN4_2_SHIFT;
-		break;
-	case SZ_16K:
-		tgran_2 = ID_AA64MMFR0_TGRAN16_2_SHIFT;
-		break;
-	case SZ_64K:
-		tgran_2 = ID_AA64MMFR0_TGRAN64_2_SHIFT;
-		break;
-	}
-
-	switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
+	switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN_2_SHIFT)) {
 	case ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE:
 		kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
 		return -EINVAL;
@@ -369,7 +364,7 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 	phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
 	if (phys_shift) {
 		if (phys_shift > kvm_ipa_limit ||
-		    phys_shift < 32)
+		    phys_shift < ARM64_MIN_PARANGE_BITS)
 			return -EINVAL;
 	} else {
 		phys_shift = KVM_PHYS_SHIFT;
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
index a016f07adc28..5f9014ae595b 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
@@ -282,7 +282,7 @@ static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu,
 	case GIC_CPU_PRIMASK:
 		/*
 		 * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
-		 * the PMR field as GICH_VMCR.VMPriMask rather than
+		 * PMR field as GICH_VMCR.VMPriMask rather than
 		 * GICC_PMR.Priority, so we expose the upper five bits of
 		 * priority mask to userspace using the lower bits in the
 		 * unsigned long.
@@ -329,7 +329,7 @@ static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu,
 	case GIC_CPU_PRIMASK:
 		/*
 		 * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
-		 * the PMR field as GICH_VMCR.VMPriMask rather than
+		 * PMR field as GICH_VMCR.VMPriMask rather than
 		 * GICC_PMR.Priority, so we expose the upper five bits of
 		 * priority mask to userspace using the lower bits in the
 		 * unsigned long.
diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c
index 2c580204f1dc..95a18cec14a3 100644
--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -60,6 +60,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 		u32 val = cpuif->vgic_lr[lr];
 		u32 cpuid, intid = val & GICH_LR_VIRTUALID;
 		struct vgic_irq *irq;
+		bool deactivated;
 
 		/* Extract the source vCPU id from the LR */
 		cpuid = val & GICH_LR_PHYSID_CPUID;
@@ -75,7 +76,8 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 
 		raw_spin_lock(&irq->irq_lock);
 
-		/* Always preserve the active bit */
+		/* Always preserve the active bit, note deactivation */
+		deactivated = irq->active && !(val & GICH_LR_ACTIVE_BIT);
 		irq->active = !!(val & GICH_LR_ACTIVE_BIT);
 
 		if (irq->active && vgic_irq_is_sgi(intid))
@@ -96,36 +98,8 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 		if (irq->config == VGIC_CONFIG_LEVEL && !(val & GICH_LR_STATE))
 			irq->pending_latch = false;
 
-		/*
-		 * Level-triggered mapped IRQs are special because we only
-		 * observe rising edges as input to the VGIC.
-		 *
-		 * If the guest never acked the interrupt we have to sample
-		 * the physical line and set the line level, because the
-		 * device state could have changed or we simply need to
-		 * process the still pending interrupt later.
-		 *
-		 * If this causes us to lower the level, we have to also clear
-		 * the physical active state, since we will otherwise never be
-		 * told when the interrupt becomes asserted again.
-		 *
-		 * Another case is when the interrupt requires a helping hand
-		 * on deactivation (no HW deactivation, for example).
-		 */
-		if (vgic_irq_is_mapped_level(irq)) {
-			bool resample = false;
-
-			if (val & GICH_LR_PENDING_BIT) {
-				irq->line_level = vgic_get_phys_line_level(irq);
-				resample = !irq->line_level;
-			} else if (vgic_irq_needs_resampling(irq) &&
-				   !(irq->active || irq->pending_latch)) {
-				resample = true;
-			}
-
-			if (resample)
-				vgic_irq_set_phys_active(irq, false);
-		}
+		/* Handle resampling for mapped interrupts if required */
+		vgic_irq_handle_resampling(irq, deactivated, val & GICH_LR_PENDING_BIT);
 
 		raw_spin_unlock(&irq->irq_lock);
 		vgic_put_irq(vcpu->kvm, irq);
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 66004f61cd83..21a6207fb2ee 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -46,6 +46,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 		u32 intid, cpuid;
 		struct vgic_irq *irq;
 		bool is_v2_sgi = false;
+		bool deactivated;
 
 		cpuid = val & GICH_LR_PHYSID_CPUID;
 		cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
@@ -68,7 +69,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 
 		raw_spin_lock(&irq->irq_lock);
 
-		/* Always preserve the active bit */
+		/* Always preserve the active bit, note deactivation */
+		deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT);
 		irq->active = !!(val & ICH_LR_ACTIVE_BIT);
 
 		if (irq->active && is_v2_sgi)
@@ -89,36 +91,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 		if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE))
 			irq->pending_latch = false;
 
-		/*
-		 * Level-triggered mapped IRQs are special because we only
-		 * observe rising edges as input to the VGIC.
-		 *
-		 * If the guest never acked the interrupt we have to sample
-		 * the physical line and set the line level, because the
-		 * device state could have changed or we simply need to
-		 * process the still pending interrupt later.
-		 *
-		 * If this causes us to lower the level, we have to also clear
-		 * the physical active state, since we will otherwise never be
-		 * told when the interrupt becomes asserted again.
-		 *
-		 * Another case is when the interrupt requires a helping hand
-		 * on deactivation (no HW deactivation, for example).
-		 */
-		if (vgic_irq_is_mapped_level(irq)) {
-			bool resample = false;
-
-			if (val & ICH_LR_PENDING_BIT) {
-				irq->line_level = vgic_get_phys_line_level(irq);
-				resample = !irq->line_level;
-			} else if (vgic_irq_needs_resampling(irq) &&
-				   !(irq->active || irq->pending_latch)) {
-				resample = true;
-			}
-
-			if (resample)
-				vgic_irq_set_phys_active(irq, false);
-		}
+		/* Handle resampling for mapped interrupts if required */
+		vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT);
 
 		raw_spin_unlock(&irq->irq_lock);
 		vgic_put_irq(vcpu->kvm, irq);
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 111bff47e471..5dad4996cfb2 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -106,7 +106,6 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	if (intid >= VGIC_MIN_LPI)
 		return vgic_get_lpi(kvm, intid);
 
-	WARN(1, "Looking up struct vgic_irq for reserved INTID");
 	return NULL;
 }
 
@@ -1022,3 +1021,41 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid)
 
 	return map_is_active;
 }
+
+/*
+ * Level-triggered mapped IRQs are special because we only observe rising
+ * edges as input to the VGIC.
+ *
+ * If the guest never acked the interrupt we have to sample the physical
+ * line and set the line level, because the device state could have changed
+ * or we simply need to process the still pending interrupt later.
+ *
+ * We could also have entered the guest with the interrupt active+pending.
+ * On the next exit, we need to re-evaluate the pending state, as it could
+ * otherwise result in a spurious interrupt by injecting a now potentially
+ * stale pending state.
+ *
+ * If this causes us to lower the level, we have to also clear the physical
+ * active state, since we will otherwise never be told when the interrupt
+ * becomes asserted again.
+ *
+ * Another case is when the interrupt requires a helping hand on
+ * deactivation (no HW deactivation, for example).
+ */
+void vgic_irq_handle_resampling(struct vgic_irq *irq,
+				bool lr_deactivated, bool lr_pending)
+{
+	if (vgic_irq_is_mapped_level(irq)) {
+		bool resample = false;
+
+		if (unlikely(vgic_irq_needs_resampling(irq))) {
+			resample = !(irq->active || irq->pending_latch);
+		} else if (lr_pending || (lr_deactivated && irq->line_level)) {
+			irq->line_level = vgic_get_phys_line_level(irq);
+			resample = !irq->line_level;
+		}
+
+		if (resample)
+			vgic_irq_set_phys_active(irq, false);
+	}
+}
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index dc1f3d1657ee..14a9218641f5 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -169,6 +169,8 @@ void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active);
 bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
 			   unsigned long flags);
 void vgic_kick_vcpus(struct kvm *kvm);
+void vgic_irq_handle_resampling(struct vgic_irq *irq,
+				bool lr_deactivated, bool lr_pending);
 
 int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
 		      phys_addr_t addr, phys_addr_t alignment);