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>
This commit is contained in:
parent
65ac726404
commit
3cfc3092f4
|
@ -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
|
||||
|
|
|
@ -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 */
|
||||
|
|
|
@ -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);
|
||||
|
|
|
@ -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,
|
||||
|
|
|
@ -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,
|
||||
|
|
|
@ -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;
|
||||
}
|
||||
|
|
|
@ -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)
|
||||
|
||||
|
|
Loading…
Reference in New Issue