* [PATCH v5 1/4] KVM: x86: Simple kvm_x86_ops->queue_exception parameter
2017-06-27 1:46 [PATCH v5 0/4] KVM: async_pf: Fix async pf exception injection Wanpeng Li
@ 2017-06-27 1:46 ` Wanpeng Li
2017-06-27 1:46 ` [PATCH v5 2/4] KVM: async_pf: Add L1 guest async_pf #PF vmexit handler Wanpeng Li
` (2 subsequent siblings)
3 siblings, 0 replies; 10+ messages in thread
From: Wanpeng Li @ 2017-06-27 1:46 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: Paolo Bonzini, Radim Krčmář, Wanpeng Li
From: Wanpeng Li <wanpeng.li@hotmail.com>
This patch removes all arguments except the first in kvm_x86_ops->queue_exception
since they can extract the arguments from vcpu->arch.exception themselves, do the
same in nested_{vmx,svm}_check_exception.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
arch/x86/include/asm/kvm_host.h | 4 +---
arch/x86/kvm/svm.c | 8 +++++---
arch/x86/kvm/vmx.c | 8 +++++---
arch/x86/kvm/x86.c | 5 +----
4 files changed, 12 insertions(+), 13 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 695605e..1f01bfb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -948,9 +948,7 @@ struct kvm_x86_ops {
unsigned char *hypercall_addr);
void (*set_irq)(struct kvm_vcpu *vcpu);
void (*set_nmi)(struct kvm_vcpu *vcpu);
- void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code,
- bool reinject);
+ void (*queue_exception)(struct kvm_vcpu *vcpu);
void (*cancel_injection)(struct kvm_vcpu *vcpu);
int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
int (*nmi_allowed)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ba9891a..e1f8e89 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -631,11 +631,13 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
svm_set_interrupt_shadow(vcpu, 0);
}
-static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code,
- bool reinject)
+static void svm_queue_exception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ unsigned nr = vcpu->arch.exception.nr;
+ bool has_error_code = vcpu->arch.exception.has_error_code;
+ bool reinject = vcpu->arch.exception.reinject;
+ u32 error_code = vcpu->arch.exception.error_code;
/*
* If we are within a nested VM we'd better #VMEXIT and let the guest
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ca5d2b9..df825bb 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2431,11 +2431,13 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
return 1;
}
-static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code,
- bool reinject)
+static void vmx_queue_exception(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned nr = vcpu->arch.exception.nr;
+ bool has_error_code = vcpu->arch.exception.has_error_code;
+ bool reinject = vcpu->arch.exception.reinject;
+ u32 error_code = vcpu->arch.exception.error_code;
u32 intr_info = nr | INTR_INFO_VALID_MASK;
if (!reinject && is_guest_mode(vcpu) &&
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 87d3cb9..1b28a31 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6345,10 +6345,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
kvm_update_dr7(vcpu);
}
- kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
- vcpu->arch.exception.has_error_code,
- vcpu->arch.exception.error_code,
- vcpu->arch.exception.reinject);
+ kvm_x86_ops->queue_exception(vcpu);
return 0;
}
--
2.7.4
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH v5 2/4] KVM: async_pf: Add L1 guest async_pf #PF vmexit handler
2017-06-27 1:46 [PATCH v5 0/4] KVM: async_pf: Fix async pf exception injection Wanpeng Li
2017-06-27 1:46 ` [PATCH v5 1/4] KVM: x86: Simple kvm_x86_ops->queue_exception parameter Wanpeng Li
@ 2017-06-27 1:46 ` Wanpeng Li
2017-06-27 13:30 ` Paolo Bonzini
2017-06-27 1:47 ` [PATCH v5 3/4] KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf Wanpeng Li
2017-06-27 1:47 ` [PATCH v5 4/4] KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit Wanpeng Li
3 siblings, 1 reply; 10+ messages in thread
From: Wanpeng Li @ 2017-06-27 1:46 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: Paolo Bonzini, Radim Krčmář, Wanpeng Li
From: Wanpeng Li <wanpeng.li@hotmail.com>
This patch adds the L1 guest async page fault #PF vmexit handler, such
#PF is converted into vmexit from L2 to L1 on #PF which is then handled
by L1 similar to ordinary async page fault.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
arch/x86/kvm/vmx.c | 34 ++++++++++++++++++++++++++++------
1 file changed, 28 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index df825bb..f533cc1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -616,6 +616,7 @@ struct vcpu_vmx {
bool emulation_required;
u32 exit_reason;
+ u32 apf_reason;
/* Posted interrupt descriptor */
struct pi_desc pi_desc;
@@ -5648,14 +5649,31 @@ static int handle_exception(struct kvm_vcpu *vcpu)
}
if (is_page_fault(intr_info)) {
- /* EPT won't cause page fault directly */
- BUG_ON(enable_ept);
cr2 = vmcs_readl(EXIT_QUALIFICATION);
- trace_kvm_page_fault(cr2, error_code);
+ switch (vmx->apf_reason) {
+ default:
+ /* EPT won't cause page fault directly */
+ BUG_ON(enable_ept);
+ trace_kvm_page_fault(cr2, error_code);
- if (kvm_event_needs_reinjection(vcpu))
- kvm_mmu_unprotect_page_virt(vcpu, cr2);
- return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
+ if (kvm_event_needs_reinjection(vcpu))
+ kvm_mmu_unprotect_page_virt(vcpu, cr2);
+ return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
+ break;
+ case KVM_PV_REASON_PAGE_NOT_PRESENT:
+ vmx->apf_reason = 0;
+ local_irq_disable();
+ kvm_async_pf_task_wait(cr2);
+ local_irq_enable();
+ break;
+ case KVM_PV_REASON_PAGE_READY:
+ vmx->apf_reason = 0;
+ local_irq_disable();
+ kvm_async_pf_task_wake(cr2);
+ local_irq_enable();
+ break;
+ }
+ return 0;
}
ex_no = intr_info & INTR_INFO_VECTOR_MASK;
@@ -8602,6 +8620,10 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
exit_intr_info = vmx->exit_intr_info;
+ /* if exit due to PF check for async PF */
+ if (is_page_fault(exit_intr_info))
+ vmx->apf_reason = kvm_read_and_reset_pf_reason();
+
/* Handle machine checks before interrupts are enabled */
if (is_machine_check(exit_intr_info))
kvm_machine_check();
--
2.7.4
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [PATCH v5 2/4] KVM: async_pf: Add L1 guest async_pf #PF vmexit handler
2017-06-27 1:46 ` [PATCH v5 2/4] KVM: async_pf: Add L1 guest async_pf #PF vmexit handler Wanpeng Li
@ 2017-06-27 13:30 ` Paolo Bonzini
2017-06-27 22:40 ` Wanpeng Li
0 siblings, 1 reply; 10+ messages in thread
From: Paolo Bonzini @ 2017-06-27 13:30 UTC (permalink / raw)
To: Wanpeng Li, linux-kernel, kvm; +Cc: Radim Krčmář, Wanpeng Li
On 27/06/2017 03:46, Wanpeng Li wrote:
> From: Wanpeng Li <wanpeng.li@hotmail.com>
>
> This patch adds the L1 guest async page fault #PF vmexit handler, such
> #PF is converted into vmexit from L2 to L1 on #PF which is then handled
> by L1 similar to ordinary async page fault.
>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Radim Krčmář <rkrcmar@redhat.com>
> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
> ---
> arch/x86/kvm/vmx.c | 34 ++++++++++++++++++++++++++++------
> 1 file changed, 28 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index df825bb..f533cc1 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -616,6 +616,7 @@ struct vcpu_vmx {
> bool emulation_required;
>
> u32 exit_reason;
> + u32 apf_reason;
Can you instead of move vcpu_svm's apf_reason field to kvm_vcpu_arch?
(e.g. vcpu->arch.apf.host_apf_reason)?
> /* Posted interrupt descriptor */
> struct pi_desc pi_desc;
> @@ -5648,14 +5649,31 @@ static int handle_exception(struct kvm_vcpu *vcpu)
> }
>
> if (is_page_fault(intr_info)) {
> - /* EPT won't cause page fault directly */
> - BUG_ON(enable_ept);
> cr2 = vmcs_readl(EXIT_QUALIFICATION);
> - trace_kvm_page_fault(cr2, error_code);
> + switch (vmx->apf_reason) {
> + default:
> + /* EPT won't cause page fault directly */
> + BUG_ON(enable_ept);
> + trace_kvm_page_fault(cr2, error_code);
>
> - if (kvm_event_needs_reinjection(vcpu))
> - kvm_mmu_unprotect_page_virt(vcpu, cr2);
> - return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
> + if (kvm_event_needs_reinjection(vcpu))
> + kvm_mmu_unprotect_page_virt(vcpu, cr2);
> + return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
> + break;
> + case KVM_PV_REASON_PAGE_NOT_PRESENT:
> + vmx->apf_reason = 0;
> + local_irq_disable();
> + kvm_async_pf_task_wait(cr2);
> + local_irq_enable();
> + break;
> + case KVM_PV_REASON_PAGE_READY:
> + vmx->apf_reason = 0;
> + local_irq_disable();
> + kvm_async_pf_task_wake(cr2);
> + local_irq_enable();
> + break;
> + }
> + return 0;
> }
This code can be moved to a common function
int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
u64 fault_address);
in mmu.c. It can be used by vmx.c here and in svm.c's pf_interception.
You can change "enable_ept" to "tdp_enabled" (but please make that a
WARN_ON_ONCE, too).
Thanks,
Paolo
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v5 2/4] KVM: async_pf: Add L1 guest async_pf #PF vmexit handler
2017-06-27 13:30 ` Paolo Bonzini
@ 2017-06-27 22:40 ` Wanpeng Li
0 siblings, 0 replies; 10+ messages in thread
From: Wanpeng Li @ 2017-06-27 22:40 UTC (permalink / raw)
To: Paolo Bonzini; +Cc: linux-kernel, kvm, Radim Krčmář, Wanpeng Li
2017-06-27 21:30 GMT+08:00 Paolo Bonzini <pbonzini@redhat.com>:
>
>
> On 27/06/2017 03:46, Wanpeng Li wrote:
>> From: Wanpeng Li <wanpeng.li@hotmail.com>
>>
>> This patch adds the L1 guest async page fault #PF vmexit handler, such
>> #PF is converted into vmexit from L2 to L1 on #PF which is then handled
>> by L1 similar to ordinary async page fault.
>>
>> Cc: Paolo Bonzini <pbonzini@redhat.com>
>> Cc: Radim Krčmář <rkrcmar@redhat.com>
>> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
>> ---
>> arch/x86/kvm/vmx.c | 34 ++++++++++++++++++++++++++++------
>> 1 file changed, 28 insertions(+), 6 deletions(-)
>>
>> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
>> index df825bb..f533cc1 100644
>> --- a/arch/x86/kvm/vmx.c
>> +++ b/arch/x86/kvm/vmx.c
>> @@ -616,6 +616,7 @@ struct vcpu_vmx {
>> bool emulation_required;
>>
>> u32 exit_reason;
>> + u32 apf_reason;
>
> Can you instead of move vcpu_svm's apf_reason field to kvm_vcpu_arch?
> (e.g. vcpu->arch.apf.host_apf_reason)?
Agreed.
>
>> /* Posted interrupt descriptor */
>> struct pi_desc pi_desc;
>> @@ -5648,14 +5649,31 @@ static int handle_exception(struct kvm_vcpu *vcpu)
>> }
>>
>> if (is_page_fault(intr_info)) {
>> - /* EPT won't cause page fault directly */
>> - BUG_ON(enable_ept);
>> cr2 = vmcs_readl(EXIT_QUALIFICATION);
>> - trace_kvm_page_fault(cr2, error_code);
>> + switch (vmx->apf_reason) {
>> + default:
>> + /* EPT won't cause page fault directly */
>> + BUG_ON(enable_ept);
>> + trace_kvm_page_fault(cr2, error_code);
>>
>> - if (kvm_event_needs_reinjection(vcpu))
>> - kvm_mmu_unprotect_page_virt(vcpu, cr2);
>> - return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
>> + if (kvm_event_needs_reinjection(vcpu))
>> + kvm_mmu_unprotect_page_virt(vcpu, cr2);
>> + return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
>> + break;
>> + case KVM_PV_REASON_PAGE_NOT_PRESENT:
>> + vmx->apf_reason = 0;
>> + local_irq_disable();
>> + kvm_async_pf_task_wait(cr2);
>> + local_irq_enable();
>> + break;
>> + case KVM_PV_REASON_PAGE_READY:
>> + vmx->apf_reason = 0;
>> + local_irq_disable();
>> + kvm_async_pf_task_wake(cr2);
>> + local_irq_enable();
>> + break;
>> + }
>> + return 0;
>> }
>
>
> This code can be moved to a common function
>
> int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
> u64 fault_address);
>
> in mmu.c. It can be used by vmx.c here and in svm.c's pf_interception.
>
> You can change "enable_ept" to "tdp_enabled" (but please make that a
> WARN_ON_ONCE, too).
Agreed. :)
Regards,
Wanpeng Li
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH v5 3/4] KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf
2017-06-27 1:46 [PATCH v5 0/4] KVM: async_pf: Fix async pf exception injection Wanpeng Li
2017-06-27 1:46 ` [PATCH v5 1/4] KVM: x86: Simple kvm_x86_ops->queue_exception parameter Wanpeng Li
2017-06-27 1:46 ` [PATCH v5 2/4] KVM: async_pf: Add L1 guest async_pf #PF vmexit handler Wanpeng Li
@ 2017-06-27 1:47 ` Wanpeng Li
2017-06-27 13:40 ` Paolo Bonzini
2017-06-27 1:47 ` [PATCH v5 4/4] KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit Wanpeng Li
3 siblings, 1 reply; 10+ messages in thread
From: Wanpeng Li @ 2017-06-27 1:47 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: Paolo Bonzini, Radim Krčmář, Wanpeng Li
From: Wanpeng Li <wanpeng.li@hotmail.com>
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@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
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/vmx.c | 17 ++++++++++++++---
arch/x86/kvm/x86.c | 18 ++++++++++++++----
tools/arch/x86/include/uapi/asm/kvm.h | 3 ++-
7 files changed, 41 insertions(+), 11 deletions(-)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 4029943..db32882 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 async_page_fault;
__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 0559626..6d54c8f 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 1f01bfb..2e84cc4 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 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..27b368b 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 async_page_fault;
__u32 error_code;
} exception;
struct {
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..9a2410c 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);
@@ -3072,7 +3076,7 @@ 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.async_page_fault = vcpu->arch.exception.async_page_fault;
events->exception.error_code = vcpu->arch.exception.error_code;
events->interrupt.injected =
@@ -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 &&
@@ -3126,6 +3132,8 @@ 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.async_page_fault = events->exception.async_page_fault;
vcpu->arch.exception.error_code = events->exception.error_code;
vcpu->arch.interrupt.pending = events->interrupt.injected;
@@ -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..27b368b 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 async_page_fault;
__u32 error_code;
} exception;
struct {
--
2.7.4
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [PATCH v5 3/4] KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf
2017-06-27 1:47 ` [PATCH v5 3/4] KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf Wanpeng Li
@ 2017-06-27 13:40 ` Paolo Bonzini
0 siblings, 0 replies; 10+ messages in thread
From: Paolo Bonzini @ 2017-06-27 13:40 UTC (permalink / raw)
To: Wanpeng Li, linux-kernel, kvm; +Cc: Radim Krčmář, Wanpeng Li
On 27/06/2017 03:47, Wanpeng Li wrote:
> -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) {
The corresponding change for svm.c should be:
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 6e3095d1bad4..b92f56b98844 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2391,15 +2391,19 @@ 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;
}
@@ -2592,7 +2596,7 @@ 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->apf_reason != 0)
+ svm->vcpu.arch.exception.nested_apf)
vmexit = NESTED_EXIT_DONE;
break;
}
(where I'm already using the "nested_apf" name I proposed in the other email.
Paolo
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH v5 4/4] KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit
2017-06-27 1:46 [PATCH v5 0/4] KVM: async_pf: Fix async pf exception injection Wanpeng Li
` (2 preceding siblings ...)
2017-06-27 1:47 ` [PATCH v5 3/4] KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf Wanpeng Li
@ 2017-06-27 1:47 ` Wanpeng Li
2017-06-27 13:19 ` Paolo Bonzini
3 siblings, 1 reply; 10+ messages in thread
From: Wanpeng Li @ 2017-06-27 1:47 UTC (permalink / raw)
To: linux-kernel, kvm; +Cc: Paolo Bonzini, Radim Krčmář, Wanpeng Li
From: Wanpeng Li <wanpeng.li@hotmail.com>
Adds another flag bit (bit 2) to MSR_KVM_ASYNC_PF_EN. If bit 2 is 1, async
page faults are delivered to L1 as #PF vmexits; if bit 2 is 0, kvm_can_do_async_pf
returns 0 if in guest mode.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
Documentation/virtual/kvm/msr.txt | 5 +++--
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/include/uapi/asm/kvm_para.h | 1 +
arch/x86/kernel/kvm.c | 3 ++-
arch/x86/kvm/mmu.c | 2 +-
arch/x86/kvm/vmx.c | 2 +-
arch/x86/kvm/x86.c | 5 +++--
7 files changed, 12 insertions(+), 7 deletions(-)
diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index 0a9ea51..1ebecc1 100644
--- a/Documentation/virtual/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
@@ -166,10 +166,11 @@ MSR_KVM_SYSTEM_TIME: 0x12
MSR_KVM_ASYNC_PF_EN: 0x4b564d02
data: Bits 63-6 hold 64-byte aligned physical address of a
64 byte memory area which must be in guest RAM and must be
- zeroed. Bits 5-2 are reserved and should be zero. Bit 0 is 1
+ zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1
when asynchronous page faults are enabled on the vcpu 0 when
disabled. Bit 1 is 1 if asynchronous page faults can be injected
- when vcpu is in cpl == 0.
+ when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
+ are delivered to L1 as #PF vmexits.
First 4 byte of 64 byte memory location will be written to by
the hypervisor at the time of asynchronous page fault (APF)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2e84cc4..05d7de9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -647,6 +647,7 @@ struct kvm_vcpu_arch {
u32 id;
bool send_user_only;
unsigned long nested_apf_token;
+ bool delivery_as_pf_vmexit;
} apf;
/* OSVW MSRs (AMD only) */
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index cff0bb6..a965e5b 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -67,6 +67,7 @@ struct kvm_clock_pairing {
#define KVM_ASYNC_PF_ENABLED (1 << 0)
#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
+#define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT (1 << 2)
/* Operations for KVM_HC_MMU_OP */
#define KVM_MMU_OP_WRITE_PTE 1
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 43e10d6..6d55441 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -330,7 +330,8 @@ static void kvm_guest_cpu_init(void)
#ifdef CONFIG_PREEMPT
pa |= KVM_ASYNC_PF_SEND_ALWAYS;
#endif
- wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
+ pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT | KVM_ASYNC_PF_ENABLED;
+ wrmsr_safe(MSR_KVM_ASYNC_PF_EN, pa & 0xffffffff, pa >> 32);
__this_cpu_write(apf_reason.enabled, 1);
printk(KERN_INFO"KVM setup async PF for cpu %d\n",
smp_processor_id());
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index cb82259..c49aecd 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3704,7 +3704,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
kvm_event_needs_reinjection(vcpu)))
return false;
- if (is_guest_mode(vcpu))
+ if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
return false;
return kvm_x86_ops->interrupt_allowed(vcpu);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e7b9844..2e906cf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8025,7 +8025,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
if (is_nmi(intr_info))
return false;
else if (is_page_fault(intr_info))
- return enable_ept;
+ return !vmx->apf_reason && enable_ept;
else if (is_no_device(intr_info) &&
!(vmcs12->guest_cr0 & X86_CR0_TS))
return false;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a2410c..fdaa429 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2064,8 +2064,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
{
gpa_t gpa = data & ~0x3f;
- /* Bits 2:5 are reserved, Should be zero */
- if (data & 0x3c)
+ /* Bits 3:5 are reserved, Should be zero */
+ if (data & 0x38)
return 1;
vcpu->arch.apf.msr_val = data;
@@ -2081,6 +2081,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
return 1;
vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+ vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
kvm_async_pf_wakeup_all(vcpu);
return 0;
}
--
2.7.4
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [PATCH v5 4/4] KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit
2017-06-27 1:47 ` [PATCH v5 4/4] KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit Wanpeng Li
@ 2017-06-27 13:19 ` Paolo Bonzini
2017-06-27 22:49 ` Wanpeng Li
0 siblings, 1 reply; 10+ messages in thread
From: Paolo Bonzini @ 2017-06-27 13:19 UTC (permalink / raw)
To: Wanpeng Li, linux-kernel, kvm; +Cc: Radim Krčmář, Wanpeng Li
On 27/06/2017 03:47, Wanpeng Li wrote:
> - wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
> + pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT | KVM_ASYNC_PF_ENABLED;
> + wrmsr_safe(MSR_KVM_ASYNC_PF_EN, pa & 0xffffffff, pa >> 32);
> __this_cpu_write(apf_reason.enabled, 1);
Better:
pa |= KVM_ASYNC_PF_ENABLED;
/* Async page fault support for L1 hypervisor is optional. */
if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN,
pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) < 0)
wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
Thanks,
Paolo
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v5 4/4] KVM: async_pf: Let host know whether the guest support delivery async_pf as #PF vmexit
2017-06-27 13:19 ` Paolo Bonzini
@ 2017-06-27 22:49 ` Wanpeng Li
0 siblings, 0 replies; 10+ messages in thread
From: Wanpeng Li @ 2017-06-27 22:49 UTC (permalink / raw)
To: Paolo Bonzini; +Cc: linux-kernel, kvm, Radim Krčmář, Wanpeng Li
2017-06-27 21:19 GMT+08:00 Paolo Bonzini <pbonzini@redhat.com>:
>
>
> On 27/06/2017 03:47, Wanpeng Li wrote:
>> - wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
>> + pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT | KVM_ASYNC_PF_ENABLED;
>> + wrmsr_safe(MSR_KVM_ASYNC_PF_EN, pa & 0xffffffff, pa >> 32);
>> __this_cpu_write(apf_reason.enabled, 1);
>
> Better:
>
> pa |= KVM_ASYNC_PF_ENABLED;
>
> /* Async page fault support for L1 hypervisor is optional. */
> if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN,
> pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) < 0)
> wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
Good point. :)
Regards,
Wanpeng Li
^ permalink raw reply [flat|nested] 10+ messages in thread