[PATCH v6 3/4] KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf

From: Wanpeng Li
Date: Wed Jun 28 2017 - 08:26:20 EST


From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

Add an nested_apf 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 KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
Documentation/virtual/kvm/api.txt | 8 ++++++--
arch/x86/include/asm/kvm_emulate.h | 1 +
arch/x86/include/asm/kvm_host.h | 2 ++
arch/x86/include/uapi/asm/kvm.h | 3 ++-
arch/x86/kvm/svm.c | 16 ++++++++++------
arch/x86/kvm/vmx.c | 17 ++++++++++++++---
arch/x86/kvm/x86.c | 19 +++++++++++++++----
tools/arch/x86/include/uapi/asm/kvm.h | 3 ++-
8 files changed, 52 insertions(+), 17 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 4029943..a991a7c 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -832,7 +832,7 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 has_error_code;
- __u8 pad;
+ __u8 nested_apf;
__u32 error_code;
} exception;
struct {
@@ -857,7 +857,7 @@ struct kvm_vcpu_events {
} smi;
};

-Only two fields are defined in the flags field:
+Only three fields are defined in the flags field:

- KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
interrupt.shadow contains a valid state.
@@ -865,6 +865,9 @@ Only two fields are defined in the flags field:
- KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that
smi contains a valid state.

+- KVM_VCPUEVENT_VALID_ASYNC_PF may be set in the flags field to signal that
+ the exception is an async page fault.
+
4.32 KVM_SET_VCPU_EVENTS

Capability: KVM_CAP_VCPU_EVENTS
@@ -887,6 +890,7 @@ 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
KVM_VCPUEVENT_VALID_SMM - transfer the smi sub-struct.
+KVM_VCPUEVENT_VALID_ASYNC_PF - transfer async page fault

If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
the flags field to signal that interrupt.shadow contains a valid state and
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 722d0e5..fde36f1 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 */
+ u8 async_page_fault;
};

/*
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e20d8a8..71aef4b 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;
+ u8 nested_apf;
} exception;

struct kvm_queued_interrupt {
@@ -646,6 +647,7 @@ struct kvm_vcpu_arch {
u32 id;
bool send_user_only;
u32 host_apf_reason;
+ 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..c9556ec 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
@@ -298,7 +299,7 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 has_error_code;
- __u8 pad;
+ __u8 nested_apf;
__u32 error_code;
} exception;
struct {
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 8f263bf..49cdb8e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2367,15 +2367,19 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
if (!is_guest_mode(&svm->vcpu))
return 0;

+ vmexit = nested_svm_intercept(svm);
+ if (vmexit != NESTED_EXIT_DONE)
+ return 0;
+
svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
svm->vmcb->control.exit_code_hi = 0;
svm->vmcb->control.exit_info_1 = error_code;
- svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
-
- vmexit = nested_svm_intercept(svm);
- if (vmexit == NESTED_EXIT_DONE)
- svm->nested.exit_required = true;
+ if (svm->vcpu.arch.exception.nested_apf)
+ svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
+ else
+ svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;

+ svm->nested.exit_required = true;
return vmexit;
}

@@ -2568,7 +2572,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
vmexit = NESTED_EXIT_DONE;
/* async page fault always cause vmexit */
else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) &&
- svm->vcpu.arch.apf.host_apf_reason != 0)
+ svm->vcpu.arch.exception.nested_apf != 0)
vmexit = NESTED_EXIT_DONE;
break;
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d20f794..8724ea6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2418,13 +2418,24 @@ 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.nested_apf)))
return 0;

+ if (vcpu->arch.exception.nested_apf) {
+ 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));
@@ -2441,7 +2452,7 @@ 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 7511c0a..5756811 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -452,7 +452,12 @@ 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.nested_apf =
+ is_guest_mode(vcpu) && fault->async_page_fault;
+ if (vcpu->arch.exception.nested_apf)
+ 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);
@@ -3072,7 +3077,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
!kvm_exception_is_soft(vcpu->arch.exception.nr);
events->exception.nr = vcpu->arch.exception.nr;
events->exception.has_error_code = vcpu->arch.exception.has_error_code;
- events->exception.pad = 0;
+ events->exception.nested_apf = vcpu->arch.exception.nested_apf;
events->exception.error_code = vcpu->arch.exception.error_code;

events->interrupt.injected =
@@ -3096,7 +3101,8 @@ 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 +3114,8 @@ 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 &&
@@ -3126,6 +3133,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *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;
+ if (events->flags & KVM_VCPUEVENT_VALID_ASYNC_PF)
+ vcpu->arch.exception.nested_apf = events->exception.nested_apf;
vcpu->arch.exception.error_code = events->exception.error_code;

vcpu->arch.interrupt.pending = events->interrupt.injected;
@@ -8573,6 +8582,7 @@ 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);
}
}
@@ -8595,6 +8605,7 @@ 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..c9556ec 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
@@ -298,7 +299,7 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 has_error_code;
- __u8 pad;
+ __u8 nested_apf;
__u32 error_code;
} exception;
struct {
--
2.7.4