1 files changed, 134 insertions, 120 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 89b98e0..a8ae57a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2167,46 +2167,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	struct pi_desc old, new;
 	unsigned int dest;
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	/*
+	 * In case of hot-plug or hot-unplug, we may have to undo
+	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
+	 * always keep PI.NDST up to date for simplicity: it makes the
+	 * code easier, and CPU migration is not a fast path.
+	 */
+	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
+		return;
+
+	/*
+	 * First handle the simple case where no cmpxchg is necessary; just
+	 * allow posting non-urgent interrupts.
+	 *
+	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+	 * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+	 * expects the VCPU to be on the blocked_vcpu_list that matches
+	 * PI.NDST.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+	    vcpu->cpu == cpu) {
+		pi_clear_sn(pi_desc);
 		return;
+	}
 
+	/* The full case.  */
 	do {
 		old.control = new.control = pi_desc->control;
 
-		/*
-		 * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
-		 * are two possible cases:
-		 * 1. After running 'pre_block', context switch
-		 *    happened. For this case, 'sn' was set in
-		 *    vmx_vcpu_put(), so we need to clear it here.
-		 * 2. After running 'pre_block', we were blocked,
-		 *    and woken up by some other guy. For this case,
-		 *    we don't need to do anything, 'pi_post_block'
-		 *    will do everything for us. However, we cannot
-		 *    check whether it is case #1 or case #2 here
-		 *    (maybe, not needed), so we also clear sn here,
-		 *    I think it is not a big deal.
-		 */
-		if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
-			if (vcpu->cpu != cpu) {
-				dest = cpu_physical_id(cpu);
-
-				if (x2apic_enabled())
-					new.ndst = dest;
-				else
-					new.ndst = (dest << 8) & 0xFF00;
-			}
+		dest = cpu_physical_id(cpu);
 
-			/* set 'NV' to 'notification vector' */
-			new.nv = POSTED_INTR_VECTOR;
-		}
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
 
-		/* Allow posting non-urgent interrupts */
 		new.sn = 0;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 }
 
 static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
@@ -2455,7 +2453,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
 	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
-	nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
 			  vmcs_readl(EXIT_QUALIFICATION));
 	return 1;
@@ -2987,7 +2985,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported())
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
@@ -3069,7 +3068,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!kvm_mpx_supported())
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
+			return 1;
+		if (is_noncanonical_address(data & PAGE_MASK) ||
+		    (data & MSR_IA32_BNDCFGS_RSVD))
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
@@ -4756,21 +4759,30 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_SMP
 	if (vcpu->mode == IN_GUEST_MODE) {
-		struct vcpu_vmx *vmx = to_vmx(vcpu);
-
 		/*
-		 * Currently, we don't support urgent interrupt,
-		 * all interrupts are recognized as non-urgent
-		 * interrupt, so we cannot post interrupts when
-		 * 'SN' is set.
+		 * The vector of interrupt to be delivered to vcpu had
+		 * been set in PIR before this function.
+		 *
+		 * Following cases will be reached in this block, and
+		 * we always send a notification event in all cases as
+		 * explained below.
+		 *
+		 * Case 1: vcpu keeps in non-root mode. Sending a
+		 * notification event posts the interrupt to vcpu.
 		 *
-		 * If the vcpu is in guest mode, it means it is
-		 * running instead of being scheduled out and
-		 * waiting in the run queue, and that's the only
-		 * case when 'SN' is set currently, warning if
-		 * 'SN' is set.
+		 * Case 2: vcpu exits to root mode and is still
+		 * runnable. PIR will be synced to vIRR before the
+		 * next vcpu entry. Sending a notification event in
+		 * this case has no effect, as vcpu is not in root
+		 * mode.
+		 *
+		 * Case 3: vcpu exits to root mode and is blocked.
+		 * vcpu_block() has already synced PIR to vIRR and
+		 * never blocks vcpu if vIRR is not cleared. Therefore,
+		 * a blocked vcpu here does not wait for any requested
+		 * interrupts in PIR, and sending a notification event
+		 * which has no effect is safe here.
 		 */
-		WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
 
 		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
 				POSTED_INTR_VECTOR);
@@ -6474,7 +6486,6 @@ static __init int hardware_setup(void)
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
 
 	memcpy(vmx_msr_bitmap_legacy_x2apic,
 			vmx_msr_bitmap_legacy, PAGE_SIZE);
@@ -9183,6 +9194,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
 
+	/*
+	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+	 * or POSTED_INTR_WAKEUP_VECTOR.
+	 */
+	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+	vmx->pi_desc.sn = 1;
+
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -9992,6 +10010,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
 				page_to_phys(vmx->nested.virtual_apic_page));
 		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+	} else {
+#ifdef CONFIG_X86_64
+		exec_control |= CPU_BASED_CR8_LOAD_EXITING |
+				CPU_BASED_CR8_STORE_EXITING;
+#endif
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
@@ -10667,7 +10690,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 * (KVM doesn't change it)- no reason to call set_cr4_guest_host_mask();
 	 */
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
-	kvm_set_cr4(vcpu, vmcs12->host_cr4);
+	vmx_set_cr4(vcpu, vmcs12->host_cr4);
 
 	nested_ept_uninit_mmu_context(vcpu);
 
@@ -10996,6 +11019,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
 }
 
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	do {
+		old.control = new.control = pi_desc->control;
+		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+		     "Wakeup handler not enabled while the VCPU is blocked\n");
+
+		dest = cpu_physical_id(vcpu->cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'notification vector' */
+		new.nv = POSTED_INTR_VECTOR;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_del(&vcpu->blocked_vcpu_list);
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		vcpu->pre_pcpu = -1;
+	}
+}
+
 /*
  * This routine does the following things for vCPU which is going
  * to be blocked if VT-d PI is enabled.
@@ -11011,7 +11065,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
  */
 static int pi_pre_block(struct kvm_vcpu *vcpu)
 {
-	unsigned long flags;
 	unsigned int dest;
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -11021,34 +11074,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
 		!kvm_vcpu_apicv_active(vcpu))
 		return 0;
 
-	vcpu->pre_pcpu = vcpu->cpu;
-	spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
-			  vcpu->pre_pcpu), flags);
-	list_add_tail(&vcpu->blocked_vcpu_list,
-		      &per_cpu(blocked_vcpu_on_cpu,
-		      vcpu->pre_pcpu));
-	spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
-			       vcpu->pre_pcpu), flags);
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+		vcpu->pre_pcpu = vcpu->cpu;
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_add_tail(&vcpu->blocked_vcpu_list,
+			      &per_cpu(blocked_vcpu_on_cpu,
+				       vcpu->pre_pcpu));
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+	}
 
 	do {
 		old.control = new.control = pi_desc->control;
 
-		/*
-		 * We should not block the vCPU if
-		 * an interrupt is posted for it.
-		 */
-		if (pi_test_on(pi_desc) == 1) {
-			spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
-					  vcpu->pre_pcpu), flags);
-			list_del(&vcpu->blocked_vcpu_list);
-			spin_unlock_irqrestore(
-					&per_cpu(blocked_vcpu_on_cpu_lock,
-					vcpu->pre_pcpu), flags);
-			vcpu->pre_pcpu = -1;
-
-			return 1;
-		}
-
 		WARN((pi_desc->sn == 1),
 		     "Warning: SN field of posted-interrupts "
 		     "is set before blocking\n");
@@ -11070,10 +11109,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
 
 		/* set 'NV' to 'wakeup vector' */
 		new.nv = POSTED_INTR_WAKEUP_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 
-	return 0;
+	/* We should not block the vCPU if an interrupt is posted for it.  */
+	if (pi_test_on(pi_desc) == 1)
+		__pi_post_block(vcpu);
+
+	local_irq_enable();
+	return (vcpu->pre_pcpu == -1);
 }
 
 static int vmx_pre_block(struct kvm_vcpu *vcpu)
@@ -11089,44 +11133,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
 
 static void pi_post_block(struct kvm_vcpu *vcpu)
 {
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-	unsigned long flags;
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (vcpu->pre_pcpu == -1)
 		return;
 
-	do {
-		old.control = new.control = pi_desc->control;
-
-		dest = cpu_physical_id(vcpu->cpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* Allow posting non-urgent interrupts */
-		new.sn = 0;
-
-		/* set 'NV' to 'notification vector' */
-		new.nv = POSTED_INTR_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
-
-	if(vcpu->pre_pcpu != -1) {
-		spin_lock_irqsave(
-			&per_cpu(blocked_vcpu_on_cpu_lock,
-			vcpu->pre_pcpu), flags);
-		list_del(&vcpu->blocked_vcpu_list);
-		spin_unlock_irqrestore(
-			&per_cpu(blocked_vcpu_on_cpu_lock,
-			vcpu->pre_pcpu), flags);
-		vcpu->pre_pcpu = -1;
-	}
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	__pi_post_block(vcpu);
+	local_irq_enable();
 }
 
 static void vmx_post_block(struct kvm_vcpu *vcpu)
@@ -11154,7 +11167,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 	struct kvm_lapic_irq irq;
 	struct kvm_vcpu *vcpu;
 	struct vcpu_data vcpu_info;
-	int idx, ret = -EINVAL;
+	int idx, ret = 0;
 
 	if (!kvm_arch_has_assigned_device(kvm) ||
 		!irq_remapping_cap(IRQ_POSTING_CAP) ||
@@ -11163,7 +11176,12 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	BUG_ON(guest_irq >= irq_rt->nr_rt_entries);
+	if (guest_irq >= irq_rt->nr_rt_entries ||
+	    hlist_empty(&irq_rt->map[guest_irq])) {
+		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+			     guest_irq, irq_rt->nr_rt_entries);
+		goto out;
+	}
 
 	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
 		if (e->type != KVM_IRQ_ROUTING_MSI)
@@ -11206,12 +11224,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 
 		if (set)
 			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else {
-			/* suppress notification event before unposting */
-			pi_set_sn(vcpu_to_pi_desc(vcpu));
+		else
 			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			pi_clear_sn(vcpu_to_pi_desc(vcpu));
-		}
 
 		if (ret < 0) {
 			printk(KERN_INFO "%s: failed to update PI IRTE\n",