From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
Add an async_page_fault field to vcpu->arch.exception to identify an async
page fault, and constructs the expected vm-exit information fields. Force
a nested VM exit from nested_vmx_check_exception() if the injected #PF
is async page fault. Extending the userspace interface KVM_GET_VCPU_EVENTS
and KVM_SET_VCPU_EVENTS for live migration.
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim Krčmář <rkrcmar@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
arch/x86/include/asm/kvm_emulate.h | 1 +
arch/x86/include/asm/kvm_host.h | 2 ++
arch/x86/include/uapi/asm/kvm.h | 2 ++
arch/x86/kvm/vmx.c | 17 ++++++++++++++---
arch/x86/kvm/x86.c | 16 +++++++++++++---
tools/arch/x86/include/uapi/asm/kvm.h | 2 ++
6 files changed, 34 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 0559626..b5bcad9 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -23,6 +23,7 @@ struct x86_exception {
u16 error_code;
bool nested_page_fault;
u64 address; /* cr2 or nested page fault gpa */
+ bool async_page_fault;
};
/*
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1f01bfb..100ad9a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -545,6 +545,7 @@ struct kvm_vcpu_arch {
bool reinject;
u8 nr;
u32 error_code;
+ bool async_page_fault;
} exception;
struct kvm_queued_interrupt {
@@ -645,6 +646,7 @@ struct kvm_vcpu_arch {
u64 msr_val;
u32 id;
bool send_user_only;
+ unsigned long nested_apf_token;
} apf;
/* OSVW MSRs (AMD only) */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index c2824d0..435f03f 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -287,6 +287,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
+#define KVM_VCPUEVENT_VALID_ASYNC_PF 0x00000010
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -300,6 +301,7 @@ struct kvm_vcpu_events {
__u8 has_error_code;
__u8 pad;
__u32 error_code;
+ bool async_page_fault;
} exception;
struct {
__u8 injected;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f533cc1..e7b9844 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2419,13 +2419,24 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
* KVM wants to inject page-faults which it got to the guest. This function
* checks whether in a nested guest, we need to inject them to L1 or L2.
*/
-static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ unsigned int nr = vcpu->arch.exception.nr;
- if (!(vmcs12->exception_bitmap & (1u << nr)))
+ if (!((vmcs12->exception_bitmap & (1u << nr)) ||
+ (nr == PF_VECTOR && vcpu->arch.exception.async_page_fault)))
return 0;
+ if (vcpu->arch.exception.async_page_fault) {
+ vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code);
+ nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+ PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+ INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+ vcpu->arch.apf.nested_apf_token);
+ return 1;
+ }
+
nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
vmcs_read32(VM_EXIT_INTR_INFO),
vmcs_readl(EXIT_QUALIFICATION));
@@ -2442,7 +2453,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
u32 intr_info = nr | INTR_INFO_VALID_MASK;
if (!reinject && is_guest_mode(vcpu) &&
- nested_vmx_check_exception(vcpu, nr))
+ nested_vmx_check_exception(vcpu))
return;
if (has_error_code) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1b28a31..0c201eb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -452,7 +452,11 @@ EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
++vcpu->stat.pf_guest;
- vcpu->arch.cr2 = fault->address;
+ vcpu->arch.exception.async_page_fault = fault->async_page_fault;
+ if (is_guest_mode(vcpu) && vcpu->arch.exception.async_page_fault)
+ vcpu->arch.apf.nested_apf_token = fault->address;
+ else
+ vcpu->arch.cr2 = fault->address;
kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
@@ -3096,7 +3100,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SHADOW
- | KVM_VCPUEVENT_VALID_SMM);
+ | KVM_VCPUEVENT_VALID_SMM
+ | KVM_VCPUEVENT_VALID_ASYNC_PF);
memset(&events->reserved, 0, sizeof(events->reserved));
}
@@ -3108,7 +3113,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SIPI_VECTOR
| KVM_VCPUEVENT_VALID_SHADOW
- | KVM_VCPUEVENT_VALID_SMM))
+ | KVM_VCPUEVENT_VALID_SMM
+ | KVM_VCPUEVENT_VALID_ASYNC_PF))
return -EINVAL;
if (events->exception.injected &&
@@ -3127,6 +3133,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
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;
+ if (events->flags & KVM_VCPUEVENT_VALID_ASYNC_PF)
+ vcpu->arch.exception.async_page_fault = events->exception.async_page_fault;
vcpu->arch.interrupt.pending = events->interrupt.injected;
vcpu->arch.interrupt.nr = events->interrupt.nr;
@@ -8571,6 +8579,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
fault.error_code = 0;
fault.nested_page_fault = false;
fault.address = work->arch.token;
+ fault.async_page_fault = true;
kvm_inject_page_fault(vcpu, &fault);
}
}
@@ -8593,6 +8602,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
fault.error_code = 0;
fault.nested_page_fault = false;
fault.address = work->arch.token;
+ fault.async_page_fault = true;
kvm_inject_page_fault(vcpu, &fault);
}
vcpu->arch.apf.halted = false;
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index c2824d0..435f03f 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -287,6 +287,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
+#define KVM_VCPUEVENT_VALID_ASYNC_PF 0x00000010
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -300,6 +301,7 @@ struct kvm_vcpu_events {
__u8 has_error_code;
__u8 pad;
__u32 error_code;
+ bool async_page_fault;
} exception;
struct {
__u8 injected;
--
2.7.4
