1 files changed, 137 insertions, 47 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00462bd63129..f53f5b13c677 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -951,7 +951,7 @@ static u32 msrs_to_save[] = {
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
-	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS
+	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
 };
 
 static unsigned num_msrs_to_save;
@@ -966,6 +966,8 @@ static u32 emulated_msrs[] = {
 	HV_X64_MSR_RESET,
 	HV_X64_MSR_VP_INDEX,
 	HV_X64_MSR_VP_RUNTIME,
+	HV_X64_MSR_SCONTROL,
+	HV_X64_MSR_STIMER0_CONFIG,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
 	MSR_KVM_PV_EOI_EN,
 
@@ -1167,7 +1169,8 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 
 	++version;
 
-	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
+	if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version)))
+		return;
 
 	/*
 	 * The guest calculates current wall clock time by adding
@@ -1683,6 +1686,11 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
 #endif
 }
 
+void kvm_make_mclock_inprogress_request(struct kvm *kvm)
+{
+	kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
+}
+
 static void kvm_gen_update_masterclock(struct kvm *kvm)
 {
 #ifdef CONFIG_X86_64
@@ -2198,6 +2206,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
 	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 	case HV_X64_MSR_CRASH_CTL:
+	case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
 		return kvm_hv_set_msr_common(vcpu, msr, data,
 					     msr_info->host_initiated);
 	case MSR_IA32_BBL_CR_CTL3:
@@ -2402,6 +2411,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
 	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
 	case HV_X64_MSR_CRASH_CTL:
+	case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
 		return kvm_hv_get_msr_common(vcpu,
 					     msr_info->index, &msr_info->data);
 		break;
@@ -2541,6 +2551,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
 	case KVM_CAP_HYPERV_SPIN:
+	case KVM_CAP_HYPERV_SYNIC:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -2693,6 +2704,11 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 	return kvm_arch_has_noncoherent_dma(vcpu->kvm);
 }
 
+static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
+{
+	set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Address WBINVD may be executed by guest */
@@ -2748,7 +2764,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	kvm_x86_ops->sync_pir_to_irr(vcpu);
+	if (vcpu->arch.apicv_active)
+		kvm_x86_ops->sync_pir_to_irr(vcpu);
+
 	memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);
 
 	return 0;
@@ -2763,6 +2781,26 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
+{
+	return (!lapic_in_kernel(vcpu) ||
+		kvm_apic_accept_pic_intr(vcpu));
+}
+
+/*
+ * if userspace requested an interrupt window, check that the
+ * interrupt window is open.
+ *
+ * No need to exit to userspace if we already have an interrupt queued.
+ */
+static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
+{
+	return kvm_arch_interrupt_allowed(vcpu) &&
+		!kvm_cpu_has_interrupt(vcpu) &&
+		!kvm_event_needs_reinjection(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu);
+}
+
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 				    struct kvm_interrupt *irq)
 {
@@ -2786,6 +2824,7 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 		return -EEXIST;
 
 	vcpu->arch.pending_external_vector = irq->irq;
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	return 0;
 }
 
@@ -3170,6 +3209,20 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
+				     struct kvm_enable_cap *cap)
+{
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_HYPERV_SYNIC:
+		return kvm_hv_activate_synic(vcpu);
+	default:
+		return -EINVAL;
+	}
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -3434,6 +3487,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_set_guest_paused(vcpu);
 		goto out;
 	}
+	case KVM_ENABLE_CAP: {
+		struct kvm_enable_cap cap;
+
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			goto out;
+		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -3551,9 +3613,11 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 
 static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
+	int i;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
-	kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0);
+	for (i = 0; i < 3; i++)
+		kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -3572,6 +3636,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 {
 	int start = 0;
+	int i;
 	u32 prev_legacy, cur_legacy;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
@@ -3581,7 +3646,9 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 	memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
 	       sizeof(kvm->arch.vpit->pit_state.channels));
 	kvm->arch.vpit->pit_state.flags = ps->flags;
-	kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
+	for (i = 0; i < 3; i++)
+		kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count,
+				   start && i == 0);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -3980,16 +4047,17 @@ static void kvm_init_msr_list(void)
 
 		/*
 		 * Even MSRs that are valid in the host may not be exposed
-		 * to the guests in some cases.  We could work around this
-		 * in VMX with the generic MSR save/load machinery, but it
-		 * is not really worthwhile since it will really only
-		 * happen with nested virtualization.
+		 * to the guests in some cases.
 		 */
 		switch (msrs_to_save[i]) {
 		case MSR_IA32_BNDCFGS:
 			if (!kvm_x86_ops->mpx_supported())
 				continue;
 			break;
+		case MSR_TSC_AUX:
+			if (!kvm_x86_ops->rdtscp_supported())
+				continue;
+			break;
 		default:
 			break;
 		}
@@ -5846,6 +5914,12 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 	kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
 }
 
+void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.apicv_active = false;
+	kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu);
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
@@ -5910,23 +5984,10 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
 	return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
 }
 
-/*
- * Check if userspace requested an interrupt window, and that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm))
-		return false;
-
-	if (kvm_cpu_has_interrupt(vcpu))
-		return false;
-
-	return (irqchip_split(vcpu->kvm)
-		? kvm_apic_accept_pic_intr(vcpu)
-		: kvm_arch_interrupt_allowed(vcpu));
+	return vcpu->run->request_interrupt_window &&
+		likely(!pic_in_kernel(vcpu->kvm));
 }
 
 static void post_kvm_run_save(struct kvm_vcpu *vcpu)
@@ -5937,17 +5998,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 	kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
-	if (!irqchip_in_kernel(vcpu->kvm))
-		kvm_run->ready_for_interrupt_injection =
-			kvm_arch_interrupt_allowed(vcpu) &&
-			!kvm_cpu_has_interrupt(vcpu) &&
-			!kvm_event_needs_reinjection(vcpu);
-	else if (!pic_in_kernel(vcpu->kvm))
-		kvm_run->ready_for_interrupt_injection =
-			kvm_apic_accept_pic_intr(vcpu) &&
-			!kvm_cpu_has_interrupt(vcpu);
-	else
-		kvm_run->ready_for_interrupt_injection = 1;
+	kvm_run->ready_for_interrupt_injection =
+		pic_in_kernel(vcpu->kvm) ||
+		kvm_vcpu_ready_for_interrupt_injection(vcpu);
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -5960,6 +6013,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 	if (!vcpu->arch.apic)
 		return;
 
+	if (vcpu->arch.apicv_active)
+		return;
+
 	if (!vcpu->arch.apic->vapic_addr)
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
 	else
@@ -6296,20 +6352,30 @@ static void process_smi(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 }
 
+void kvm_make_scan_ioapic_request(struct kvm *kvm)
+{
+	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
+}
+
 static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 {
+	u64 eoi_exit_bitmap[4];
+
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		return;
 
-	memset(vcpu->arch.eoi_exit_bitmap, 0, 256 / 8);
+	bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);
 
 	if (irqchip_split(vcpu->kvm))
-		kvm_scan_ioapic_routes(vcpu, vcpu->arch.eoi_exit_bitmap);
+		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
 	else {
-		kvm_x86_ops->sync_pir_to_irr(vcpu);
-		kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap);
+		if (vcpu->arch.apicv_active)
+			kvm_x86_ops->sync_pir_to_irr(vcpu);
+		kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
-	kvm_x86_ops->load_eoi_exitmap(vcpu);
+	bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors,
+		  vcpu_to_synic(vcpu)->vec_bitmap, 256);
+	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
@@ -6360,8 +6426,10 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
-	bool req_int_win = !lapic_in_kernel(vcpu) &&
-		vcpu->run->request_interrupt_window;
+	bool req_int_win =
+		dm_request_for_irq_injection(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu);
+
 	bool req_immediate_exit = false;
 
 	if (vcpu->requests) {
@@ -6415,7 +6483,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) {
 			BUG_ON(vcpu->arch.pending_ioapic_eoi > 255);
 			if (test_bit(vcpu->arch.pending_ioapic_eoi,
-				     (void *) vcpu->arch.eoi_exit_bitmap)) {
+				     vcpu->arch.ioapic_handled_vectors)) {
 				vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI;
 				vcpu->run->eoi.vector =
 						vcpu->arch.pending_ioapic_eoi;
@@ -6439,6 +6507,20 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
+		if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) {
+			vcpu->run->exit_reason = KVM_EXIT_HYPERV;
+			vcpu->run->hyperv = vcpu->arch.hyperv.exit;
+			r = 0;
+			goto out;
+		}
+
+		/*
+		 * KVM_REQ_HV_STIMER has to be processed after
+		 * KVM_REQ_CLOCK_UPDATE, because Hyper-V SynIC timers
+		 * depend on the guest clock being up-to-date
+		 */
+		if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu))
+			kvm_hv_process_stimers(vcpu);
 	}
 
 	/*
@@ -6450,7 +6532,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		 * Update architecture specific hints for APIC
 		 * virtual interrupt delivery.
 		 */
-		if (kvm_x86_ops->hwapic_irr_update)
+		if (vcpu->arch.apicv_active)
 			kvm_x86_ops->hwapic_irr_update(vcpu,
 				kvm_lapic_find_highest_irr(vcpu));
 	}
@@ -6513,6 +6595,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
+	trace_kvm_entry(vcpu->vcpu_id);
+	wait_lapic_expire(vcpu);
 	__kvm_guest_enter();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
@@ -6525,8 +6609,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
 	}
 
-	trace_kvm_entry(vcpu->vcpu_id);
-	wait_lapic_expire(vcpu);
 	kvm_x86_ops->run(vcpu);
 
 	/*
@@ -6663,7 +6745,8 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 		if (kvm_cpu_has_pending_timer(vcpu))
 			kvm_inject_pending_timer_irqs(vcpu);
 
-		if (dm_request_for_irq_injection(vcpu)) {
+		if (dm_request_for_irq_injection(vcpu) &&
+			kvm_vcpu_ready_for_interrupt_injection(vcpu)) {
 			r = 0;
 			vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
 			++vcpu->stat.request_irq_exits;
@@ -7520,6 +7603,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	BUG_ON(vcpu->kvm == NULL);
 	kvm = vcpu->kvm;
 
+	vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv();
 	vcpu->arch.pv.pv_unhalted = false;
 	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
 	if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu))
@@ -7577,6 +7661,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.pending_external_vector = -1;
 
+	kvm_hv_vcpu_init(vcpu);
+
 	return 0;
 
 fail_free_mce_banks:
@@ -7595,6 +7681,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
+	kvm_hv_vcpu_uninit(vcpu);
 	kvm_pmu_destroy(vcpu);
 	kfree(vcpu->arch.mce_banks);
 	kvm_free_lapic(vcpu);
@@ -7989,6 +8076,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 	    kvm_cpu_has_interrupt(vcpu))
 		return true;
 
+	if (kvm_hv_has_stimer_pending(vcpu))
+		return true;
+
 	return false;
 }