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

Pull KVM fixes from Radim Krčmář:
 "ARM:
   - Fix handling of the 32bit cycle counter
   - Fix cycle counter filtering

  x86:
   - Fix a race leading to double unregistering of user notifiers
   - Amend oversight in kvm_arch_set_irq that turned Hyper-V code dead
   - Use SRCU around kvm_lapic_set_vapic_addr
   - Avoid recursive flushing of asynchronous page faults
   - Do not rely on deferred update in KVM_GET_CLOCK, which fixes #GP
   - Let userspace know that KVM_GET_CLOCK is useful with master clock;
     4.9 changed the return value to better match the guest clock, but
     didn't provide means to let guests take advantage of it"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm: x86: merge kvm_arch_set_irq and kvm_arch_set_irq_inatomic
  KVM: x86: fix missed SRCU usage in kvm_lapic_set_vapic_addr
  KVM: async_pf: avoid recursive flushing of work items
  kvm: kvmclock: let KVM_GET_CLOCK return whether the master clock is in use
  KVM: Disable irq while unregistering user notifier
  KVM: x86: do not go through vcpu in __get_kvmclock_ns
  KVM: arm64: Fix the issues when guest PMCCFILTR is configured
  arm64: KVM: pmu: Fix AArch32 cycle counter access

Documentation/virtual/kvm/api.txt

@@ -777,6 +777,17 @@ Gets the current timestamp of kvmclock as seen by the current guest. In
 conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
+When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the
+set of bits that KVM can return in struct kvm_clock_data's flag member.
+
+The only flag defined now is KVM_CLOCK_TSC_STABLE.  If set, the returned
+value is the exact kvmclock value seen by all VCPUs at the instant
+when KVM_GET_CLOCK was called.  If clear, the returned value is simply
+CLOCK_MONOTONIC plus a constant offset; the offset can be modified
+with KVM_SET_CLOCK.  KVM will try to make all VCPUs follow this clock,
+but the exact value read by each VCPU could differ, because the host
+TSC is not stable.
+
 struct kvm_clock_data {
 	__u64 clock;  /* kvmclock current value */
 	__u32 flags;

arch/arm64/include/asm/perf_event.h

@@ -46,7 +46,15 @@
 #define	ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
 #define	ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
 
-#define ARMV8_PMU_EVTYPE_EVENT_SW_INCR	0	/* Software increment event */
+/*
+ * PMUv3 event types: required events
+ */
+#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
+#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
+#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
 
 /*
  * Event filters for PMUv3

arch/arm64/kernel/perf_event.c

@@ -31,17 +31,9 @@
 
 /*
  * ARMv8 PMUv3 Performance Events handling code.
- * Common event types.
+ * Common event types (some are defined in asm/perf_event.h).
  */
 
-/* Required events. */
-#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
-#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
-#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
-#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
-
 /* At least one of the following is required. */
 #define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x08
 #define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x1B

arch/arm64/kvm/sys_regs.c

@@ -597,8 +597,14 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 
 			idx = ARMV8_PMU_CYCLE_IDX;
 		} else {
-			BUG();
+			return false;
 		}
+	} else if (r->CRn == 0 && r->CRm == 9) {
+		/* PMCCNTR */
+		if (pmu_access_event_counter_el0_disabled(vcpu))
+			return false;
+
+		idx = ARMV8_PMU_CYCLE_IDX;
 	} else if (r->CRn == 14 && (r->CRm & 12) == 8) {
 		/* PMEVCNTRn_EL0 */
 		if (pmu_access_event_counter_el0_disabled(vcpu))
@@ -606,7 +612,7 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 
 		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
 	} else {
-		BUG();
+		return false;
 	}
 
 	if (!pmu_counter_idx_valid(vcpu, idx))

arch/x86/kvm/irq_comm.c

@@ -156,6 +156,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 }
 
 
+static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
+		    struct kvm *kvm, int irq_source_id, int level,
+		    bool line_status)
+{
+	if (!level)
+		return -1;
+
+	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
+}
+
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
 			      bool line_status)
@@ -163,18 +173,26 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	struct kvm_lapic_irq irq;
 	int r;
 
-	if (unlikely(e->type != KVM_IRQ_ROUTING_MSI))
-		return -EWOULDBLOCK;
+	switch (e->type) {
+	case KVM_IRQ_ROUTING_HV_SINT:
+		return kvm_hv_set_sint(e, kvm, irq_source_id, level,
+				       line_status);
 
-	if (kvm_msi_route_invalid(kvm, e))
-		return -EINVAL;
+	case KVM_IRQ_ROUTING_MSI:
+		if (kvm_msi_route_invalid(kvm, e))
+			return -EINVAL;
 
-	kvm_set_msi_irq(kvm, e, &irq);
+		kvm_set_msi_irq(kvm, e, &irq);
 
-	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
-		return r;
-	else
-		return -EWOULDBLOCK;
+		if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+			return r;
+		break;
+
+	default:
+		break;
+	}
+
+	return -EWOULDBLOCK;
 }
 
 int kvm_request_irq_source_id(struct kvm *kvm)
@@ -254,16 +272,6 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
-		    struct kvm *kvm, int irq_source_id, int level,
-		    bool line_status)
-{
-	if (!level)
-		return -1;
-
-	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
-}
-
 int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
@@ -423,18 +431,6 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm,
-		     int irq_source_id, int level, bool line_status)
-{
-	switch (irq->type) {
-	case KVM_IRQ_ROUTING_HV_SINT:
-		return kvm_hv_set_sint(irq, kvm, irq_source_id, level,
-				       line_status);
-	default:
-		return -EWOULDBLOCK;
-	}
-}
-
 void kvm_arch_irq_routing_update(struct kvm *kvm)
 {
 	kvm_hv_irq_routing_update(kvm);

arch/x86/kvm/x86.c

@@ -210,7 +210,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	struct kvm_shared_msrs *locals
 		= container_of(urn, struct kvm_shared_msrs, urn);
 	struct kvm_shared_msr_values *values;
+	unsigned long flags;
 
+	/*
+	 * Disabling irqs at this point since the following code could be
+	 * interrupted and executed through kvm_arch_hardware_disable()
+	 */
+	local_irq_save(flags);
+	if (locals->registered) {
+		locals->registered = false;
+		user_return_notifier_unregister(urn);
+	}
+	local_irq_restore(flags);
 	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
 		values = &locals->values[slot];
 		if (values->host != values->curr) {
@@ -218,8 +229,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 			values->curr = values->host;
 		}
 	}
-	locals->registered = false;
-	user_return_notifier_unregister(urn);
 }
 
 static void shared_msr_update(unsigned slot, u32 msr)
@@ -1724,18 +1733,23 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 
 static u64 __get_kvmclock_ns(struct kvm *kvm)
 {
-	struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
 	struct kvm_arch *ka = &kvm->arch;
-	s64 ns;
+	struct pvclock_vcpu_time_info hv_clock;
 
-	if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
-		u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-		ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
-	} else {
-		ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+	spin_lock(&ka->pvclock_gtod_sync_lock);
+	if (!ka->use_master_clock) {
+		spin_unlock(&ka->pvclock_gtod_sync_lock);
+		return ktime_get_boot_ns() + ka->kvmclock_offset;
 	}
 
-	return ns;
+	hv_clock.tsc_timestamp = ka->master_cycle_now;
+	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+			   &hv_clock.tsc_shift,
+			   &hv_clock.tsc_to_system_mul);
+	return __pvclock_read_cycles(&hv_clock, rdtsc());
 }
 
 u64 get_kvmclock_ns(struct kvm *kvm)
@@ -2596,7 +2610,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_XEN_HVM:
-	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
@@ -2623,6 +2636,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 		r = 1;
 		break;
+	case KVM_CAP_ADJUST_CLOCK:
+		r = KVM_CLOCK_TSC_STABLE;
+		break;
 	case KVM_CAP_X86_SMM:
 		/* SMBASE is usually relocated above 1M on modern chipsets,
 		 * and SMM handlers might indeed rely on 4G segment limits,
@@ -3415,6 +3431,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	};
 	case KVM_SET_VAPIC_ADDR: {
 		struct kvm_vapic_addr va;
+		int idx;
 
 		r = -EINVAL;
 		if (!lapic_in_kernel(vcpu))
@@ -3422,7 +3439,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -4103,9 +4122,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
 
-		now_ns = get_kvmclock_ns(kvm);
+		local_irq_disable();
+		now_ns = __get_kvmclock_ns(kvm);
 		user_ns.clock = now_ns;
-		user_ns.flags = 0;
+		user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0;
+		local_irq_enable();
 		memset(&user_ns.pad, 0, sizeof(user_ns.pad));
 
 		r = -EFAULT;

include/uapi/linux/kvm.h

@@ -972,12 +972,19 @@ struct kvm_irqfd {
 	__u8  pad[16];
 };
 
+/* For KVM_CAP_ADJUST_CLOCK */
+
+/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags.  */
+#define KVM_CLOCK_TSC_STABLE		2
+
 struct kvm_clock_data {
 	__u64 clock;
 	__u32 flags;
 	__u32 pad[9];
 };
 
+/* For KVM_CAP_SW_TLB */
+
 #define KVM_MMU_FSL_BOOKE_NOHV		0
 #define KVM_MMU_FSL_BOOKE_HV		1
 

virt/kvm/arm/pmu.c

@@ -305,7 +305,7 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 		type = vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i)
 		       & ARMV8_PMU_EVTYPE_EVENT;
-		if ((type == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		if ((type == ARMV8_PMUV3_PERFCTR_SW_INCR)
 		    && (enable & BIT(i))) {
 			reg = vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
 			reg = lower_32_bits(reg);
@@ -379,7 +379,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	eventsel = data & ARMV8_PMU_EVTYPE_EVENT;
 
 	/* Software increment event does't need to be backed by a perf event */
-	if (eventsel == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR &&
+	    select_idx != ARMV8_PMU_CYCLE_IDX)
 		return;
 
 	memset(&attr, 0, sizeof(struct perf_event_attr));
@@ -391,7 +392,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
-	attr.config = eventsel;
+	attr.config = (select_idx == ARMV8_PMU_CYCLE_IDX) ?
+		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel;
 
 	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
 	/* The initial sample period (overflow count) of an event. */

virt/kvm/async_pf.c

@@ -91,6 +91,7 @@ static void async_pf_execute(struct work_struct *work)
 
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
+	apf->vcpu = NULL;
 	spin_unlock(&vcpu->async_pf.lock);
 
 	/*
@@ -113,6 +114,8 @@ static void async_pf_execute(struct work_struct *work)
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 {
+	spin_lock(&vcpu->async_pf.lock);
+
 	/* cancel outstanding work queue item */
 	while (!list_empty(&vcpu->async_pf.queue)) {
 		struct kvm_async_pf *work =
@@ -120,6 +123,14 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 					 typeof(*work), queue);
 		list_del(&work->queue);
 
+		/*
+		 * We know it's present in vcpu->async_pf.done, do
+		 * nothing here.
+		 */
+		if (!work->vcpu)
+			continue;
+
+		spin_unlock(&vcpu->async_pf.lock);
 #ifdef CONFIG_KVM_ASYNC_PF_SYNC
 		flush_work(&work->work);
 #else
@@ -129,9 +140,9 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 			kmem_cache_free(async_pf_cache, work);
 		}
 #endif
+		spin_lock(&vcpu->async_pf.lock);
 	}
 
-	spin_lock(&vcpu->async_pf.lock);
 	while (!list_empty(&vcpu->async_pf.done)) {
 		struct kvm_async_pf *work =
 			list_first_entry(&vcpu->async_pf.done,