Skip to contentSkip to conversation

KVM: x86: Add KVM_GET/SET_VCPU_EVENTS

PATCH In review Jan Kiszka 3 participants 4 messages Nov 12, 2009 – Mar 17, 2010

Subsystems (4)
Documentation x86 KVM KVM x86
lore
Share & tools
lore

Jan Kiszka

author
#0 lore raw

PATCH 1/1 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.

Signed-off-by Jan Kiszka <[email protected]>

---

 Documentation/kvm/api.txt       |   48 ++++++++++++++++++++++++++
 arch/x86/include/asm/kvm.h      |   26 ++++++++++++++
 arch/x86/include/asm/kvm_host.h |    2 +
 arch/x86/kvm/svm.c              |   22 ++++++++++++
 arch/x86/kvm/vmx.c              |   30 ++++++++++++++++
 arch/x86/kvm/x86.c              |   72 +++++++++++++++++++++++++++++++++++++++
 include/linux/kvm.h             |    6 +++
 7 files changed, 206 insertions(+), 0 deletions(-)
Documentation/kvm/api.txt +48 -0
index 36594ba..fa3e59e 100644
@@ -653,6 +653,54 @@ 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;
+};
+
+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
arch/x86/include/asm/kvm.h +26 -0
index ef9b4b7..03fd136 100644
@@ -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 +253,29 @@ 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;
+};
+
 #endif /* _ASM_X86_KVM_H */
arch/x86/include/asm/kvm_host.h +2 -0
index 26a74b7..06e0856 100644
@@ -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);
arch/x86/kvm/svm.c +22 -0
index 34b700f..3de0b37 100644
@@ -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,
arch/x86/kvm/vmx.c +30 -0
index b923f2a..63e4a50 100644
@@ -2633,6 +2633,34 @@ 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) &&

@@ -3973,6 +4001,8 @@ 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,
arch/x86/kvm/x86.c +72 -0

90 lines not on this page · raw message

include/linux/kvm.h +6 -0
index ca62b8e..9049dc3 100644
@@ -484,6 +484,9 @@ struct kvm_ioeventfd {
 #define KVM_CAP_XEN_HVM 38
 #endif
 #define KVM_CAP_ADJUST_CLOCK 39
+#ifdef __KVM_HAVE_VCPU_EVENTS
+#define KVM_CAP_VCPU_EVENTS 40
+#endif
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

@@ -667,6 +670,9 @@ 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)
#1 lore raw
Quoted 6 lines · Jan Kiszka

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.

Applied, thanks. I added a flags field to the structure in case we discover a new bit that needs to fit in there. Please take a look (separate commit in kvm-next).

Signature · 1 line
error compiling committee.c: too many arguments to function
author
#2 lore raw
Quoted 8 lines · Avi Kivity
Quoted 6 lines · Jan Kiszka

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.

Quoted 4 lines

Applied, thanks. I added a flags field to the structure in case we discover a new bit that needs to fit in there. Please take a look (separate commit in kvm-next).

Looks ok.

Jan

#3 lore raw
In reply to Avi Kivity
Quoted 8 lines · Avi Kivity
Quoted 6 lines · Jan Kiszka

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.

Quoted 4 lines

Applied, thanks. I added a flags field to the structure in case we discover a new bit that needs to fit in there. Please take a look (separate commit in kvm-next).

So without this patch migration fails? Sounds like a stable candidate to me. Same goes for the follow-up that adds the shadow field.

Alex