KVM: x86: Extend KVM_SET_VCPU_EVENTS with selective updates

User space may not want to overwrite asynchronously changing VCPU event
states on write-back. So allow to skip nmi.pending and sipi_vector by
setting corresponding bits in the flags field of kvm_vcpu_events.

[avi: advertise the bits in KVM_GET_VCPU_EVENTS]

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

3 files changed, 21 insertions, 5 deletions

diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index e1a11416102..2811e452f75 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -685,7 +685,7 @@ struct kvm_vcpu_events {
                 __u8 pad;
         } nmi;
         __u32 sipi_vector;
-        __u32 flags;   /* must be zero */
+        __u32 flags;
 };
 
 4.30 KVM_SET_VCPU_EVENTS
@@ -701,6 +701,14 @@ vcpu.
 
 See KVM_GET_VCPU_EVENTS for the data structure.
 
+Fields that may be modified asynchronously by running VCPUs can be excluded
+from the update. These fields are nmi.pending and sipi_vector. Keep the
+corresponding bits in the flags field cleared to suppress overwriting the
+current in-kernel state. The bits are:
+
+KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
+KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
+
 
 5. The kvm_run structure
 
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 950df434763..f46b79f6c16 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -254,6 +254,10 @@ struct kvm_reinject_control {
         __u8 reserved[31];
 };
 
+/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
+#define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001
+#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
+
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
         struct {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9d068966fb2..6651dbf5867 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1913,7 +1913,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 
         events->sipi_vector = vcpu->arch.sipi_vector;
 
-        events->flags = 0;
+        events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
+                         | KVM_VCPUEVENT_VALID_SIPI_VECTOR);
 
         vcpu_put(vcpu);
 }
@@ -1921,7 +1922,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
                                               struct kvm_vcpu_events *events)
 {
-        if (events->flags)
+        if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
+                              | KVM_VCPUEVENT_VALID_SIPI_VECTOR))
                 return -EINVAL;
 
         vcpu_load(vcpu);
@@ -1938,10 +1940,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
                 kvm_pic_clear_isr_ack(vcpu->kvm);
 
         vcpu->arch.nmi_injected = events->nmi.injected;
-        vcpu->arch.nmi_pending = events->nmi.pending;
+        if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
+                vcpu->arch.nmi_pending = events->nmi.pending;
         kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
 
-        vcpu->arch.sipi_vector = events->sipi_vector;
+        if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR)
+                vcpu->arch.sipi_vector = events->sipi_vector;
 
         vcpu_put(vcpu);