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

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Correctly save/restore PMUSERNR_EL0 when host userspace is using
     PMU counters directly

   - Fix GICv2 emulation on GICv3 after the locking rework

   - Don't use smp_processor_id() in kvm_pmu_probe_armpmu(), and
     document why

  Generic:

   - Avoid setting page table entries pointing to a deleted memslot if a
     host page table entry is changed concurrently with the deletion"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Avoid illegal stage2 mapping on invalid memory slot
  KVM: arm64: Use raw_smp_processor_id() in kvm_pmu_probe_armpmu()
  KVM: arm64: Restore GICv2-on-GICv3 functionality
  KVM: arm64: PMU: Don't overwrite PMUSERENR with vcpu loaded
  KVM: arm64: PMU: Restore the host's PMUSERENR_EL0

arch/arm/include/asm/arm_pmuv3.h

@@ -222,6 +222,11 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
 	return false;
 }
 
+static inline bool kvm_set_pmuserenr(u64 val)
+{
+	return false;
+}
+
 /* PMU Version in DFR Register */
 #define ARMV8_PMU_DFR_VER_NI        0
 #define ARMV8_PMU_DFR_VER_V3P4      0x5

arch/arm64/include/asm/kvm_host.h

@@ -699,6 +699,8 @@ struct kvm_vcpu_arch {
 #define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(4))
 /* Software step state is Active-pending */
 #define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
+/* PMUSERENR for the guest EL0 is on physical CPU */
+#define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(6))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -1065,9 +1067,14 @@ void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
 void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
 void kvm_clr_pmu_events(u32 clr);
+bool kvm_set_pmuserenr(u64 val);
 #else
 static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
 static inline void kvm_clr_pmu_events(u32 clr) {}
+static inline bool kvm_set_pmuserenr(u64 val)
+{
+	return false;
+}
 #endif
 
 void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);

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

@@ -82,8 +82,14 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	 * EL1 instead of being trapped to EL2.
 	 */
 	if (kvm_arm_support_pmu_v3()) {
+		struct kvm_cpu_context *hctxt;
+
 		write_sysreg(0, pmselr_el0);
+
+		hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+		ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0);
 		write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+		vcpu_set_flag(vcpu, PMUSERENR_ON_CPU);
 	}
 
 	vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
@@ -106,8 +112,13 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 	write_sysreg(vcpu->arch.mdcr_el2_host, mdcr_el2);
 
 	write_sysreg(0, hstr_el2);
-	if (kvm_arm_support_pmu_v3())
-		write_sysreg(0, pmuserenr_el0);
+	if (kvm_arm_support_pmu_v3()) {
+		struct kvm_cpu_context *hctxt;
+
+		hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+		write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0);
+		vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
+	}
 
 	if (cpus_have_final_cap(ARM64_SME)) {
 		sysreg_clear_set_s(SYS_HFGRTR_EL2, 0,

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

@@ -92,14 +92,28 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 }
 NOKPROBE_SYMBOL(__deactivate_traps);
 
+/*
+ * Disable IRQs in {activate,deactivate}_traps_vhe_{load,put}() to
+ * prevent a race condition between context switching of PMUSERENR_EL0
+ * in __{activate,deactivate}_traps_common() and IPIs that attempts to
+ * update PMUSERENR_EL0. See also kvm_set_pmuserenr().
+ */
 void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	__activate_traps_common(vcpu);
+	local_irq_restore(flags);
 }
 
 void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	__deactivate_traps_common(vcpu);
+	local_irq_restore(flags);
 }
 
 static const exit_handler_fn hyp_exit_handlers[] = {

arch/arm64/kvm/pmu-emul.c

@@ -700,7 +700,25 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 
 	mutex_lock(&arm_pmus_lock);
 
-	cpu = smp_processor_id();
+	/*
+	 * It is safe to use a stale cpu to iterate the list of PMUs so long as
+	 * the same value is used for the entirety of the loop. Given this, and
+	 * the fact that no percpu data is used for the lookup there is no need
+	 * to disable preemption.
+	 *
+	 * It is still necessary to get a valid cpu, though, to probe for the
+	 * default PMU instance as userspace is not required to specify a PMU
+	 * type. In order to uphold the preexisting behavior KVM selects the
+	 * PMU instance for the core where the first call to the
+	 * KVM_ARM_VCPU_PMU_V3_CTRL attribute group occurs. A dependent use case
+	 * would be a user with disdain of all things big.LITTLE that affines
+	 * the VMM to a particular cluster of cores.
+	 *
+	 * In any case, userspace should just do the sane thing and use the UAPI
+	 * to select a PMU type directly. But, be wary of the baggage being
+	 * carried here.
+	 */
+	cpu = raw_smp_processor_id();
 	list_for_each_entry(entry, &arm_pmus, entry) {
 		tmp = entry->arm_pmu;
 

arch/arm64/kvm/pmu.c

@@ -209,3 +209,30 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu)
 	kvm_vcpu_pmu_enable_el0(events_host);
 	kvm_vcpu_pmu_disable_el0(events_guest);
 }
+
+/*
+ * With VHE, keep track of the PMUSERENR_EL0 value for the host EL0 on the pCPU
+ * where PMUSERENR_EL0 for the guest is loaded, since PMUSERENR_EL0 is switched
+ * to the value for the guest on vcpu_load().  The value for the host EL0
+ * will be restored on vcpu_put(), before returning to userspace.
+ * This isn't necessary for nVHE, as the register is context switched for
+ * every guest enter/exit.
+ *
+ * Return true if KVM takes care of the register. Otherwise return false.
+ */
+bool kvm_set_pmuserenr(u64 val)
+{
+	struct kvm_cpu_context *hctxt;
+	struct kvm_vcpu *vcpu;
+
+	if (!kvm_arm_support_pmu_v3() || !has_vhe())
+		return false;
+
+	vcpu = kvm_get_running_vcpu();
+	if (!vcpu || !vcpu_get_flag(vcpu, PMUSERENR_ON_CPU))
+		return false;
+
+	hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	ctxt_sys_reg(hctxt, PMUSERENR_EL0) = val;
+	return true;
+}

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

@@ -446,6 +446,7 @@ int vgic_lazy_init(struct kvm *kvm)
 int kvm_vgic_map_resources(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
+	enum vgic_type type;
 	gpa_t dist_base;
 	int ret = 0;
 
@@ -460,10 +461,13 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 	if (!irqchip_in_kernel(kvm))
 		goto out;
 
-	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2)
+	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) {
 		ret = vgic_v2_map_resources(kvm);
-	else
+		type = VGIC_V2;
+	} else {
 		ret = vgic_v3_map_resources(kvm);
+		type = VGIC_V3;
+	}
 
 	if (ret) {
 		__kvm_vgic_destroy(kvm);
@@ -473,8 +477,7 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 	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);
+	ret = vgic_register_dist_iodev(kvm, dist_base, type);
 	if (ret) {
 		kvm_err("Unable to register VGIC dist MMIO regions\n");
 		kvm_vgic_destroy(kvm);

drivers/perf/arm_pmuv3.c

@@ -677,9 +677,25 @@ static inline u32 armv8pmu_getreset_flags(void)
 	return value;
 }
 
+static void update_pmuserenr(u64 val)
+{
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * The current PMUSERENR_EL0 value might be the value for the guest.
+	 * If that's the case, have KVM keep tracking of the register value
+	 * for the host EL0 so that KVM can restore it before returning to
+	 * the host EL0. Otherwise, update the register now.
+	 */
+	if (kvm_set_pmuserenr(val))
+		return;
+
+	write_pmuserenr(val);
+}
+
 static void armv8pmu_disable_user_access(void)
 {
-	write_pmuserenr(0);
+	update_pmuserenr(0);
 }
 
 static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
@@ -695,8 +711,7 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
 			armv8pmu_write_evcntr(i, 0);
 	}
 
-	write_pmuserenr(0);
-	write_pmuserenr(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR);
+	update_pmuserenr(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR);
 }
 
 static void armv8pmu_enable_event(struct perf_event *event)

virt/kvm/kvm_main.c

@@ -686,6 +686,24 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 
 	return __kvm_handle_hva_range(kvm, &range);
 }
+
+static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	/*
+	 * Skipping invalid memslots is correct if and only change_pte() is
+	 * surrounded by invalidate_range_{start,end}(), which is currently
+	 * guaranteed by the primary MMU.  If that ever changes, KVM needs to
+	 * unmap the memslot instead of skipping the memslot to ensure that KVM
+	 * doesn't hold references to the old PFN.
+	 */
+	WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
+
+	if (range->slot->flags & KVM_MEMSLOT_INVALID)
+		return false;
+
+	return kvm_set_spte_gfn(kvm, range);
+}
+
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					struct mm_struct *mm,
 					unsigned long address,
@@ -707,7 +725,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
 		return;
 
-	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
+	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_change_spte_gfn);
 }
 
 void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,