Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Address some fallout of the locking rework, this time affecting the
     way the vgic is configured

   - Fix an issue where the page table walker frees a subtree and then
     proceeds with walking what it has just freed...

   - Check that a given PA donated to the guest is actually memory (only
     affecting pKVM)

   - Correctly handle MTE CMOs by Set/Way

   - Fix the reported address of a watchpoint forwarded to userspace

   - Fix the freeing of the root of stage-2 page tables

   - Stop creating spurious PMU events to perform detection of the
     default PMU and use the existing PMU list instead

  x86:

   - Fix a memslot lookup bug in the NX recovery thread that could
     theoretically let userspace bypass the NX hugepage mitigation

   - Fix a s/BLOCKING/PENDING bug in SVM's vNMI support

   - Account exit stats for fastpath VM-Exits that never leave the super
     tight run-loop

   - Fix an out-of-bounds bug in the optimized APIC map code, and add a
     regression test for the race"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: selftests: Add test for race in kvm_recalculate_apic_map()
  KVM: x86: Bail from kvm_recalculate_phys_map() if x2APIC ID is out-of-bounds
  KVM: x86: Account fastpath-only VM-Exits in vCPU stats
  KVM: SVM: vNMI pending bit is V_NMI_PENDING_MASK not V_NMI_BLOCKING_MASK
  KVM: x86/mmu: Grab memslot for correct address space in NX recovery worker
  KVM: arm64: Document default vPMU behavior on heterogeneous systems
  KVM: arm64: Iterate arm_pmus list to probe for default PMU
  KVM: arm64: Drop last page ref in kvm_pgtable_stage2_free_removed()
  KVM: arm64: Populate fault info for watchpoint
  KVM: arm64: Reload PTE after invoking walker callback on preorder traversal
  KVM: arm64: Handle trap of tagged Set/Way CMOs
  arm64: Add missing Set/Way CMO encodings
  KVM: arm64: Prevent unconditional donation of unmapped regions from the host
  KVM: arm64: vgic: Fix a comment
  KVM: arm64: vgic: Fix locking comment
  KVM: arm64: vgic: Wrap vgic_its_create() with config_lock
  KVM: arm64: vgic: Fix a circular locking issue

Author: torvalds

arch/arm64/include/asm/kvm_pgtable.h

@@ -632,9 +632,9 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
  *
  * The walker will walk the page-table entries corresponding to the input
  * address range specified, visiting entries according to the walker flags.
- * Invalid entries are treated as leaf entries. Leaf entries are reloaded
- * after invoking the walker callback, allowing the walker to descend into
- * a newly installed table.
+ * Invalid entries are treated as leaf entries. The visited page table entry is
+ * reloaded after invoking the walker callback, allowing the walker to descend
+ * into a newly installed table.
  *
  * Returning a negative error code from the walker callback function will
  * terminate the walk immediately with the same error code.

arch/arm64/include/asm/sysreg.h

@@ -115,8 +115,14 @@
 #define SB_BARRIER_INSN			__SYS_BARRIER_INSN(0, 7, 31)
 
 #define SYS_DC_ISW			sys_insn(1, 0, 7, 6, 2)
+#define SYS_DC_IGSW			sys_insn(1, 0, 7, 6, 4)
+#define SYS_DC_IGDSW			sys_insn(1, 0, 7, 6, 6)
 #define SYS_DC_CSW			sys_insn(1, 0, 7, 10, 2)
+#define SYS_DC_CGSW			sys_insn(1, 0, 7, 10, 4)
+#define SYS_DC_CGDSW			sys_insn(1, 0, 7, 10, 6)
 #define SYS_DC_CISW			sys_insn(1, 0, 7, 14, 2)
+#define SYS_DC_CIGSW			sys_insn(1, 0, 7, 14, 4)
+#define SYS_DC_CIGDSW			sys_insn(1, 0, 7, 14, 6)
 
 /*
  * Automatically generated definitions for system registers, the

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -412,17 +412,21 @@ static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return false;
 }
 
-static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+static bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	if (!__populate_fault_info(vcpu))
 		return true;
 
 	return false;
 }
+static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+	__alias(kvm_hyp_handle_memory_fault);
+static bool kvm_hyp_handle_watchpt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+	__alias(kvm_hyp_handle_memory_fault);
 
 static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
-	if (!__populate_fault_info(vcpu))
+	if (kvm_hyp_handle_memory_fault(vcpu, exit_code))
 		return true;
 
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {

arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -575,18 +575,15 @@ struct pkvm_mem_donation {
 
 struct check_walk_data {
 	enum pkvm_page_state	desired;
-	enum pkvm_page_state	(*get_page_state)(kvm_pte_t pte);
+	enum pkvm_page_state	(*get_page_state)(kvm_pte_t pte, u64 addr);
 };
 
 static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx,
 				      enum kvm_pgtable_walk_flags visit)
 {
 	struct check_walk_data *d = ctx->arg;
 
-	if (kvm_pte_valid(ctx->old) && !addr_is_allowed_memory(kvm_pte_to_phys(ctx->old)))
-		return -EINVAL;
-
-	return d->get_page_state(ctx->old) == d->desired ? 0 : -EPERM;
+	return d->get_page_state(ctx->old, ctx->addr) == d->desired ? 0 : -EPERM;
 }
 
 static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size,
@@ -601,8 +598,11 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	return kvm_pgtable_walk(pgt, addr, size, &walker);
 }
 
-static enum pkvm_page_state host_get_page_state(kvm_pte_t pte)
+static enum pkvm_page_state host_get_page_state(kvm_pte_t pte, u64 addr)
 {
+	if (!addr_is_allowed_memory(addr))
+		return PKVM_NOPAGE;
+
 	if (!kvm_pte_valid(pte) && pte)
 		return PKVM_NOPAGE;
 
@@ -709,7 +709,7 @@ static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx
 	return host_stage2_set_owner_locked(addr, size, host_id);
 }
 
-static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte)
+static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte, u64 addr)
 {
 	if (!kvm_pte_valid(pte))
 		return PKVM_NOPAGE;

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -186,6 +186,7 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
+	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
 	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
 };
 
@@ -196,6 +197,7 @@ static const exit_handler_fn pvm_exit_handlers[] = {
 	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
+	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
 	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
 };
 

arch/arm64/kvm/hyp/pgtable.c

@@ -209,14 +209,26 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 		.flags	= flags,
 	};
 	int ret = 0;
+	bool reload = false;
 	kvm_pteref_t childp;
 	bool table = kvm_pte_table(ctx.old, level);
 
-	if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE))
+	if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) {
 		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE);
+		reload = true;
+	}
 
 	if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) {
 		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF);
+		reload = true;
+	}
+
+	/*
+	 * Reload the page table after invoking the walker callback for leaf
+	 * entries or after pre-order traversal, to allow the walker to descend
+	 * into a newly installed or replaced table.
+	 */
+	if (reload) {
 		ctx.old = READ_ONCE(*ptep);
 		table = kvm_pte_table(ctx.old, level);
 	}
@@ -1320,4 +1332,7 @@ void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pg
 	};
 
 	WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1));
+
+	WARN_ON(mm_ops->page_count(pgtable) != 1);
+	mm_ops->put_page(pgtable);
 }

arch/arm64/kvm/hyp/vhe/switch.c

@@ -110,6 +110,7 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
+	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
 	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
 };
 

arch/arm64/kvm/pmu-emul.c

@@ -694,45 +694,23 @@ void kvm_host_pmu_init(struct arm_pmu *pmu)
 
 static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 {
-	struct perf_event_attr attr = { };
-	struct perf_event *event;
-	struct arm_pmu *pmu = NULL;
-
-	/*
-	 * Create a dummy event that only counts user cycles. As we'll never
-	 * leave this function with the event being live, it will never
-	 * count anything. But it allows us to probe some of the PMU
-	 * details. Yes, this is terrible.
-	 */
-	attr.type = PERF_TYPE_RAW;
-	attr.size = sizeof(attr);
-	attr.pinned = 1;
-	attr.disabled = 0;
-	attr.exclude_user = 0;
-	attr.exclude_kernel = 1;
-	attr.exclude_hv = 1;
-	attr.exclude_host = 1;
-	attr.config = ARMV8_PMUV3_PERFCTR_CPU_CYCLES;
-	attr.sample_period = GENMASK(63, 0);
+	struct arm_pmu *tmp, *pmu = NULL;
+	struct arm_pmu_entry *entry;
+	int cpu;
 
-	event = perf_event_create_kernel_counter(&attr, -1, current,
-						 kvm_pmu_perf_overflow, &attr);
+	mutex_lock(&arm_pmus_lock);
 
-	if (IS_ERR(event)) {
-		pr_err_once("kvm: pmu event creation failed %ld\n",
-			    PTR_ERR(event));
-		return NULL;
-	}
+	cpu = smp_processor_id();
+	list_for_each_entry(entry, &arm_pmus, entry) {
+		tmp = entry->arm_pmu;
 
-	if (event->pmu) {
-		pmu = to_arm_pmu(event->pmu);
-		if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI ||
-		    pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
-			pmu = NULL;
+		if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) {
+			pmu = tmp;
+			break;
+		}
 	}
 
-	perf_event_disable(event);
-	perf_event_release_kernel(event);
+	mutex_unlock(&arm_pmus_lock);
 
 	return pmu;
 }
@@ -912,7 +890,17 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		return -EBUSY;
 
 	if (!kvm->arch.arm_pmu) {
-		/* No PMU set, get the default one */
+		/*
+		 * No PMU set, get the default one.
+		 *
+		 * The observant among you will notice that the supported_cpus
+		 * mask does not get updated for the default PMU even though it
+		 * is quite possible the selected instance supports only a
+		 * subset of cores in the system. This is intentional, and
+		 * upholds the preexisting behavior on heterogeneous systems
+		 * where vCPUs can be scheduled on any core but the guest
+		 * counters could stop working.
+		 */
 		kvm->arch.arm_pmu = kvm_pmu_probe_armpmu();
 		if (!kvm->arch.arm_pmu)
 			return -ENODEV;

arch/arm64/kvm/sys_regs.c

@@ -211,6 +211,19 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_dcgsw(struct kvm_vcpu *vcpu,
+			 struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (!kvm_has_mte(vcpu->kvm)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	/* Treat MTE S/W ops as we treat the classic ones: with contempt */
+	return access_dcsw(vcpu, p, r);
+}
+
 static void get_access_mask(const struct sys_reg_desc *r, u64 *mask, u64 *shift)
 {
 	switch (r->aarch32_map) {
@@ -1756,8 +1769,14 @@ static bool access_spsr(struct kvm_vcpu *vcpu,
  */
 static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_DC_ISW), access_dcsw },
+	{ SYS_DESC(SYS_DC_IGSW), access_dcgsw },
+	{ SYS_DESC(SYS_DC_IGDSW), access_dcgsw },
 	{ SYS_DESC(SYS_DC_CSW), access_dcsw },
+	{ SYS_DESC(SYS_DC_CGSW), access_dcgsw },
+	{ SYS_DESC(SYS_DC_CGDSW), access_dcgsw },
 	{ SYS_DESC(SYS_DC_CISW), access_dcsw },
+	{ SYS_DESC(SYS_DC_CIGSW), access_dcgsw },
+	{ SYS_DESC(SYS_DC_CIGDSW), access_dcgsw },
 
 	DBG_BCR_BVR_WCR_WVR_EL1(0),
 	DBG_BCR_BVR_WCR_WVR_EL1(1),

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

@@ -235,9 +235,9 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	 * KVM io device for the redistributor that belongs to this VCPU.
 	 */
 	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
-		mutex_lock(&vcpu->kvm->arch.config_lock);
+		mutex_lock(&vcpu->kvm->slots_lock);
 		ret = vgic_register_redist_iodev(vcpu);
-		mutex_unlock(&vcpu->kvm->arch.config_lock);
+		mutex_unlock(&vcpu->kvm->slots_lock);
 	}
 	return ret;
 }
@@ -406,7 +406,7 @@ void kvm_vgic_destroy(struct kvm *kvm)
 
 /**
  * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest
- * is a GICv2. A GICv3 must be explicitly initialized by the guest using the
+ * is a GICv2. A GICv3 must be explicitly initialized by userspace using the
  * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group.
  * @kvm: kvm struct pointer
  */
@@ -446,11 +446,13 @@ int vgic_lazy_init(struct kvm *kvm)
 int kvm_vgic_map_resources(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	gpa_t dist_base;
 	int ret = 0;
 
 	if (likely(vgic_ready(kvm)))
 		return 0;
 
+	mutex_lock(&kvm->slots_lock);
 	mutex_lock(&kvm->arch.config_lock);
 	if (vgic_ready(kvm))
 		goto out;
@@ -463,13 +465,26 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 	else
 		ret = vgic_v3_map_resources(kvm);
 
-	if (ret)
+	if (ret) {
 		__kvm_vgic_destroy(kvm);
-	else
-		dist->ready = true;
+		goto out;
+	}
+	dist->ready = true;
+	dist_base = dist->vgic_dist_base;
+	mutex_unlock(&kvm->arch.config_lock);
+
+	ret = vgic_register_dist_iodev(kvm, dist_base,
+				       kvm_vgic_global_state.type);
+	if (ret) {
+		kvm_err("Unable to register VGIC dist MMIO regions\n");
+		kvm_vgic_destroy(kvm);
+	}
+	mutex_unlock(&kvm->slots_lock);
+	return ret;
 
 out:
 	mutex_unlock(&kvm->arch.config_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return ret;
 }