KVM: x86: Add KVM_GET/SET_VCPU_EVENTS

This new IOCTL exports all yet user-invisible states related to
exceptions, interrupts, and NMIs. Together with appropriate user space
changes, this fixes sporadic problems of vmsave/restore, live migration
and system reset.

[avi: future-proof abi by adding a flags field]

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

7 files changed, 214 insertions, 0 deletions

diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 36594ba57723..e1a114161027 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -653,6 +653,55 @@ struct kvm_clock_data {
         __u32 pad[9];
 };
 
+4.29 KVM_GET_VCPU_EVENTS
+
+Capability: KVM_CAP_VCPU_EVENTS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_vcpu_event (out)
+Returns: 0 on success, -1 on error
+
+Gets currently pending exceptions, interrupts, and NMIs as well as related
+states of the vcpu.
+
+struct kvm_vcpu_events {
+        struct {
+                __u8 injected;
+                __u8 nr;
+                __u8 has_error_code;
+                __u8 pad;
+                __u32 error_code;
+        } exception;
+        struct {
+                __u8 injected;
+                __u8 nr;
+                __u8 soft;
+                __u8 pad;
+        } interrupt;
+        struct {
+                __u8 injected;
+                __u8 pending;
+                __u8 masked;
+                __u8 pad;
+        } nmi;
+        __u32 sipi_vector;
+        __u32 flags;   /* must be zero */
+};
+
+4.30 KVM_SET_VCPU_EVENTS
+
+Capability: KVM_CAP_VCPU_EVENTS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_vcpu_event (in)
+Returns: 0 on success, -1 on error
+
+Set pending exceptions, interrupts, and NMIs as well as related states of the
+vcpu.
+
+See KVM_GET_VCPU_EVENTS for the data structure.
+
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index ef9b4b73cce4..950df434763f 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -20,6 +20,7 @@
 #define __KVM_HAVE_MCE
 #define __KVM_HAVE_PIT_STATE2
 #define __KVM_HAVE_XEN_HVM
+#define __KVM_HAVE_VCPU_EVENTS
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -252,4 +253,31 @@ struct kvm_reinject_control {
         __u8 pit_reinject;
         __u8 reserved[31];
 };
+
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+        struct {
+                __u8 injected;
+                __u8 nr;
+                __u8 has_error_code;
+                __u8 pad;
+                __u32 error_code;
+        } exception;
+        struct {
+                __u8 injected;
+                __u8 nr;
+                __u8 soft;
+                __u8 pad;
+        } interrupt;
+        struct {
+                __u8 injected;
+                __u8 pending;
+                __u8 masked;
+                __u8 pad;
+        } nmi;
+        __u32 sipi_vector;
+        __u32 flags;
+        __u32 reserved[10];
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 26a74b7bb6bc..06e085614dad 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -523,6 +523,8 @@ struct kvm_x86_ops {
                                 bool has_error_code, u32 error_code);
         int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
         int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+        bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
+        void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
         void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
         void (*enable_irq_window)(struct kvm_vcpu *vcpu);
         void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 34b700f9e498..3de0b37ec038 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2499,6 +2499,26 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
                 !(svm->vcpu.arch.hflags & HF_NMI_MASK);
 }
 
+static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+        struct vcpu_svm *svm = to_svm(vcpu);
+
+        return !!(svm->vcpu.arch.hflags & HF_NMI_MASK);
+}
+
+static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+        struct vcpu_svm *svm = to_svm(vcpu);
+
+        if (masked) {
+                svm->vcpu.arch.hflags |= HF_NMI_MASK;
+                svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+        } else {
+                svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
+                svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+        }
+}
+
 static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
         struct vcpu_svm *svm = to_svm(vcpu);
@@ -2946,6 +2966,8 @@ static struct kvm_x86_ops svm_x86_ops = {
         .queue_exception = svm_queue_exception,
         .interrupt_allowed = svm_interrupt_allowed,
         .nmi_allowed = svm_nmi_allowed,
+        .get_nmi_mask = svm_get_nmi_mask,
+        .set_nmi_mask = svm_set_nmi_mask,
         .enable_nmi_window = enable_nmi_window,
         .enable_irq_window = enable_irq_window,
         .update_cr8_intercept = update_cr8_intercept,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 22fcd27a0b58..778f059ae423 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2639,6 +2639,34 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
                                 GUEST_INTR_STATE_NMI));
 }
 
+static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+        if (!cpu_has_virtual_nmis())
+                return to_vmx(vcpu)->soft_vnmi_blocked;
+        else
+                return !!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+                          GUEST_INTR_STATE_NMI);
+}
+
+static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+        struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+        if (!cpu_has_virtual_nmis()) {
+                if (vmx->soft_vnmi_blocked != masked) {
+                        vmx->soft_vnmi_blocked = masked;
+                        vmx->vnmi_blocked_time = 0;
+                }
+        } else {
+                if (masked)
+                        vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+                                      GUEST_INTR_STATE_NMI);
+                else
+                        vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+                                        GUEST_INTR_STATE_NMI);
+        }
+}
+
 static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
         return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
@@ -3985,6 +4013,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
         .queue_exception = vmx_queue_exception,
         .interrupt_allowed = vmx_interrupt_allowed,
         .nmi_allowed = vmx_nmi_allowed,
+        .get_nmi_mask = vmx_get_nmi_mask,
+        .set_nmi_mask = vmx_set_nmi_mask,
         .enable_nmi_window = enable_nmi_window,
         .enable_irq_window = enable_irq_window,
         .update_cr8_intercept = update_cr8_intercept,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ba8958dca3c4..35eea30821d6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1342,6 +1342,7 @@ int kvm_dev_ioctl_check_extension(long ext)
         case KVM_CAP_SET_IDENTITY_MAP_ADDR:
         case KVM_CAP_XEN_HVM:
         case KVM_CAP_ADJUST_CLOCK:
+        case KVM_CAP_VCPU_EVENTS:
                 r = 1;
                 break;
         case KVM_CAP_COALESCED_MMIO:
@@ -1883,6 +1884,61 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
         return 0;
 }
 
+static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
+                                               struct kvm_vcpu_events *events)
+{
+        vcpu_load(vcpu);
+
+        events->exception.injected = vcpu->arch.exception.pending;
+        events->exception.nr = vcpu->arch.exception.nr;
+        events->exception.has_error_code = vcpu->arch.exception.has_error_code;
+        events->exception.error_code = vcpu->arch.exception.error_code;
+
+        events->interrupt.injected = vcpu->arch.interrupt.pending;
+        events->interrupt.nr = vcpu->arch.interrupt.nr;
+        events->interrupt.soft = vcpu->arch.interrupt.soft;
+
+        events->nmi.injected = vcpu->arch.nmi_injected;
+        events->nmi.pending = vcpu->arch.nmi_pending;
+        events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
+
+        events->sipi_vector = vcpu->arch.sipi_vector;
+
+        events->flags = 0;
+
+        vcpu_put(vcpu);
+}
+
+static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
+                                              struct kvm_vcpu_events *events)
+{
+        if (events->flags)
+                return -EINVAL;
+
+        vcpu_load(vcpu);
+
+        vcpu->arch.exception.pending = events->exception.injected;
+        vcpu->arch.exception.nr = events->exception.nr;
+        vcpu->arch.exception.has_error_code = events->exception.has_error_code;
+        vcpu->arch.exception.error_code = events->exception.error_code;
+
+        vcpu->arch.interrupt.pending = events->interrupt.injected;
+        vcpu->arch.interrupt.nr = events->interrupt.nr;
+        vcpu->arch.interrupt.soft = events->interrupt.soft;
+        if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
+                kvm_pic_clear_isr_ack(vcpu->kvm);
+
+        vcpu->arch.nmi_injected = events->nmi.injected;
+        vcpu->arch.nmi_pending = events->nmi.pending;
+        kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
+
+        vcpu->arch.sipi_vector = events->sipi_vector;
+
+        vcpu_put(vcpu);
+
+        return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
                          unsigned int ioctl, unsigned long arg)
 {
@@ -2040,6 +2096,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
                 r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
                 break;
         }
+        case KVM_GET_VCPU_EVENTS: {
+                struct kvm_vcpu_events events;
+
+                kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events);
+
+                r = -EFAULT;
+                if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events)))
+                        break;
+                r = 0;
+                break;
+        }
+        case KVM_SET_VCPU_EVENTS: {
+                struct kvm_vcpu_events events;
+
+                r = -EFAULT;
+                if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events)))
+                        break;
+
+                r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
+                break;
+        }
         default:
                 r = -EINVAL;
         }
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 976f4d181858..92045a92d714 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -489,6 +489,9 @@ struct kvm_ioeventfd {
 #endif
 #define KVM_CAP_ADJUST_CLOCK 39
 #define KVM_CAP_INTERNAL_ERROR_DATA 40
+#ifdef __KVM_HAVE_VCPU_EVENTS
+#define KVM_CAP_VCPU_EVENTS 41
+#endif
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -672,6 +675,9 @@ struct kvm_clock_data {
 /* IA64 stack access */
 #define KVM_IA64_VCPU_GET_STACK   _IOR(KVMIO,  0x9a, void *)
 #define KVM_IA64_VCPU_SET_STACK   _IOW(KVMIO,  0x9b, void *)
+/* Available with KVM_CAP_VCPU_EVENTS */
+#define KVM_GET_VCPU_EVENTS       _IOR(KVMIO,  0x9f, struct kvm_vcpu_events)
+#define KVM_SET_VCPU_EVENTS       _IOW(KVMIO,  0xa0, struct kvm_vcpu_events)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU     (1 << 0)