[PATCH v3 1/4] KVM: VMX: use kvm_event_needs_reinjection

[PATCH v3 1/4] KVM: VMX: use kvm_event_needs_reinjection

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@hotmail.com>

Use kvm_event_needs_reinjection() encapsulation.

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 | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index dd710d3..c5f43ab 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -10988,9 +10988,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (vcpu->arch.exception.pending ||
-		vcpu->arch.nmi_injected ||
-		vcpu->arch.interrupt.pending)
+	if (kvm_event_needs_reinjection(vcpu))
 		return -EBUSY;
 
 	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
-- 
2.7.4

[PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@hotmail.com>

vmx_complete_interrupts() assumes that the exception is always injected, 
so it would be dropped by kvm_clear_exception_queue(). This patch separates 
exception.pending from exception.injected, exception.inject represents the 
exception is injected or the exception should be reinjected due to vmexit 
occurs during event delivery in VMX non-root operation. exception.pending 
represents the exception is queued and will be cleared when injecting the 
exception to the guest. So exception.pending and exception.injected can 
cooperate to guarantee exception will not be lost.

Reported-by: Radim Krčmář <rkrcmar@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
v2 -> v3:
 * the changes to inject_pending_event and adds the WARN_ON
 * combine injected and pending exception for GET/SET_VCPU_EVENTS

 arch/x86/include/asm/kvm_host.h |  2 +-
 arch/x86/kvm/svm.c              |  2 +-
 arch/x86/kvm/vmx.c              |  4 +--
 arch/x86/kvm/x86.c              | 56 ++++++++++++++++++++++++++---------------
 arch/x86/kvm/x86.h              |  4 +--
 5 files changed, 42 insertions(+), 26 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9d90787..6e385ac 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -547,8 +547,8 @@ struct kvm_vcpu_arch {
 
 	struct kvm_queued_exception {
 		bool pending;
+		bool injected;
 		bool has_error_code;
-		bool reinject;
 		u8 nr;
 		u32 error_code;
 		u8 nested_apf;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a2fddce..6a439a1 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -655,7 +655,7 @@ 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;
+	bool reinject = vcpu->arch.exception.injected;
 	u32 error_code = vcpu->arch.exception.error_code;
 
 	/*
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c5f43ab..902b780 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2503,7 +2503,7 @@ 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;
+	bool reinject = vcpu->arch.exception.injected;
 	u32 error_code = vcpu->arch.exception.error_code;
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
@@ -10948,7 +10948,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 	u32 idt_vectoring;
 	unsigned int nr;
 
-	if (vcpu->arch.exception.pending && vcpu->arch.exception.reinject) {
+	if (vcpu->arch.exception.injected) {
 		nr = vcpu->arch.exception.nr;
 		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8f41b88..b698b2f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -389,15 +389,18 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
-	if (!vcpu->arch.exception.pending) {
+	if (!vcpu->arch.exception.pending ||
+		!vcpu->arch.exception.injected) {
 	queue:
 		if (has_error && !is_protmode(vcpu))
 			has_error = false;
-		vcpu->arch.exception.pending = true;
+		if (reinject)
+			vcpu->arch.exception.injected = true;
+		else
+			vcpu->arch.exception.pending = true;
 		vcpu->arch.exception.has_error_code = has_error;
 		vcpu->arch.exception.nr = nr;
 		vcpu->arch.exception.error_code = error_code;
-		vcpu->arch.exception.reinject = reinject;
 		return;
 	}
 
@@ -3069,8 +3072,14 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 					       struct kvm_vcpu_events *events)
 {
 	process_nmi(vcpu);
+	/*
+	 * FIXME: pass injected and pending separately.  This is only
+	 * needed for nested virtualization, whose state cannot be
+	 * migrated yet.  For now we combine them just in case.
+	 */
 	events->exception.injected =
-		vcpu->arch.exception.pending &&
+		(vcpu->arch.exception.pending ||
+		 vcpu->arch.exception.injected) &&
 		!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;
@@ -3125,6 +3134,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	process_nmi(vcpu);
+	vcpu->arch.exception.injected = false;
 	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;
@@ -6350,21 +6360,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	int r;
 
 	/* try to reinject previous events if any */
-	if (vcpu->arch.exception.pending) {
-		trace_kvm_inj_exception(vcpu->arch.exception.nr,
-					vcpu->arch.exception.has_error_code,
-					vcpu->arch.exception.error_code);
-
-		if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
-			__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
-					     X86_EFLAGS_RF);
-
-		if (vcpu->arch.exception.nr == DB_VECTOR &&
-		    (vcpu->arch.dr7 & DR7_GD)) {
-			vcpu->arch.dr7 &= ~DR7_GD;
-			kvm_update_dr7(vcpu);
-		}
-
+	if (vcpu->arch.exception.injected) {
 		kvm_x86_ops->queue_exception(vcpu);
 		return 0;
 	}
@@ -6386,7 +6382,25 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	}
 
 	/* try to inject new event if pending */
-	if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
+	if (vcpu->arch.exception.pending) {
+		trace_kvm_inj_exception(vcpu->arch.exception.nr,
+					vcpu->arch.exception.has_error_code,
+					vcpu->arch.exception.error_code);
+
+		vcpu->arch.exception.pending = false;
+		vcpu->arch.exception.injected = true;
+		kvm_x86_ops->queue_exception(vcpu);
+
+		if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
+			__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
+					     X86_EFLAGS_RF);
+
+		if (vcpu->arch.exception.nr == DB_VECTOR &&
+		    (vcpu->arch.dr7 & DR7_GD)) {
+			vcpu->arch.dr7 &= ~DR7_GD;
+			kvm_update_dr7(vcpu);
+		}
+	} else if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
 		vcpu->arch.smi_pending = false;
 		enter_smm(vcpu);
 	} else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
@@ -6862,6 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 				kvm_x86_ops->enable_nmi_window(vcpu);
 			if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
 				kvm_x86_ops->enable_irq_window(vcpu);
+			WARN_ON(vcpu->arch.exception.pending);
 		}
 
 		if (kvm_lapic_enabled(vcpu)) {
@@ -7738,6 +7753,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vcpu->arch.nmi_injected = false;
 	kvm_clear_interrupt_queue(vcpu);
 	kvm_clear_exception_queue(vcpu);
+	vcpu->arch.exception.pending = false;
 
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 1134603..e6ec0de 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -11,7 +11,7 @@
 
 static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.exception.pending = false;
+	vcpu->arch.exception.injected = false;
 }
 
 static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector,
@@ -29,7 +29,7 @@ static inline void kvm_clear_interrupt_queue(struct kvm_vcpu *vcpu)
 
 static inline bool kvm_event_needs_reinjection(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.exception.pending || vcpu->arch.interrupt.pending ||
+	return vcpu->arch.exception.injected || vcpu->arch.interrupt.pending ||
 		vcpu->arch.nmi_injected;
 }
 
-- 
2.7.4

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Wanpeng Li]

2017-08-24 12:21 GMT+08:00 Wanpeng Li <kernellwp@gmail.com>:
> From: Wanpeng Li <wanpeng.li@hotmail.com>
>
> vmx_complete_interrupts() assumes that the exception is always injected,
> so it would be dropped by kvm_clear_exception_queue(). This patch separates
> exception.pending from exception.injected, exception.inject represents the
> exception is injected or the exception should be reinjected due to vmexit
> occurs during event delivery in VMX non-root operation. exception.pending
> represents the exception is queued and will be cleared when injecting the
> exception to the guest. So exception.pending and exception.injected can
> cooperate to guarantee exception will not be lost.
>
> Reported-by: Radim Krčmář <rkrcmar@redhat.com>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Radim Krčmář <rkrcmar@redhat.com>
> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
> ---
> v2 -> v3:
>  * the changes to inject_pending_event and adds the WARN_ON
>  * combine injected and pending exception for GET/SET_VCPU_EVENTS
>
>  arch/x86/include/asm/kvm_host.h |  2 +-
>  arch/x86/kvm/svm.c              |  2 +-
>  arch/x86/kvm/vmx.c              |  4 +--
>  arch/x86/kvm/x86.c              | 56 ++++++++++++++++++++++++++---------------
>  arch/x86/kvm/x86.h              |  4 +--
>  5 files changed, 42 insertions(+), 26 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 9d90787..6e385ac 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -547,8 +547,8 @@ struct kvm_vcpu_arch {
>
>         struct kvm_queued_exception {
>                 bool pending;
> +               bool injected;
>                 bool has_error_code;
> -               bool reinject;
>                 u8 nr;
>                 u32 error_code;
>                 u8 nested_apf;
> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> index a2fddce..6a439a1 100644
> --- a/arch/x86/kvm/svm.c
> +++ b/arch/x86/kvm/svm.c
> @@ -655,7 +655,7 @@ 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;
> +       bool reinject = vcpu->arch.exception.injected;
>         u32 error_code = vcpu->arch.exception.error_code;
>
>         /*
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index c5f43ab..902b780 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -2503,7 +2503,7 @@ 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;
> +       bool reinject = vcpu->arch.exception.injected;
>         u32 error_code = vcpu->arch.exception.error_code;
>         u32 intr_info = nr | INTR_INFO_VALID_MASK;
>
> @@ -10948,7 +10948,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
>         u32 idt_vectoring;
>         unsigned int nr;
>
> -       if (vcpu->arch.exception.pending && vcpu->arch.exception.reinject) {
> +       if (vcpu->arch.exception.injected) {
>                 nr = vcpu->arch.exception.nr;
>                 idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 8f41b88..b698b2f 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -389,15 +389,18 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
>
>         kvm_make_request(KVM_REQ_EVENT, vcpu);
>
> -       if (!vcpu->arch.exception.pending) {
> +       if (!vcpu->arch.exception.pending ||
> +               !vcpu->arch.exception.injected) {
>         queue:
>                 if (has_error && !is_protmode(vcpu))
>                         has_error = false;
> -               vcpu->arch.exception.pending = true;
> +               if (reinject)
> +                       vcpu->arch.exception.injected = true;
> +               else
> +                       vcpu->arch.exception.pending = true;
>                 vcpu->arch.exception.has_error_code = has_error;
>                 vcpu->arch.exception.nr = nr;
>                 vcpu->arch.exception.error_code = error_code;
> -               vcpu->arch.exception.reinject = reinject;
>                 return;
>         }
>
> @@ -3069,8 +3072,14 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
>                                                struct kvm_vcpu_events *events)
>  {
>         process_nmi(vcpu);
> +       /*
> +        * FIXME: pass injected and pending separately.  This is only
> +        * needed for nested virtualization, whose state cannot be
> +        * migrated yet.  For now we combine them just in case.
> +        */
>         events->exception.injected =
> -               vcpu->arch.exception.pending &&
> +               (vcpu->arch.exception.pending ||
> +                vcpu->arch.exception.injected) &&
>                 !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;
> @@ -3125,6 +3134,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
>                 return -EINVAL;
>
>         process_nmi(vcpu);
> +       vcpu->arch.exception.injected = false;
>         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;
> @@ -6350,21 +6360,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
>         int r;
>
>         /* try to reinject previous events if any */
> -       if (vcpu->arch.exception.pending) {
> -               trace_kvm_inj_exception(vcpu->arch.exception.nr,
> -                                       vcpu->arch.exception.has_error_code,
> -                                       vcpu->arch.exception.error_code);
> -
> -               if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
> -                       __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
> -                                            X86_EFLAGS_RF);
> -
> -               if (vcpu->arch.exception.nr == DB_VECTOR &&
> -                   (vcpu->arch.dr7 & DR7_GD)) {
> -                       vcpu->arch.dr7 &= ~DR7_GD;
> -                       kvm_update_dr7(vcpu);
> -               }
> -
> +       if (vcpu->arch.exception.injected) {
>                 kvm_x86_ops->queue_exception(vcpu);
>                 return 0;
>         }
> @@ -6386,7 +6382,25 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
>         }
>
>         /* try to inject new event if pending */
> -       if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
> +       if (vcpu->arch.exception.pending) {
> +               trace_kvm_inj_exception(vcpu->arch.exception.nr,
> +                                       vcpu->arch.exception.has_error_code,
> +                                       vcpu->arch.exception.error_code);
> +
> +               vcpu->arch.exception.pending = false;
> +               vcpu->arch.exception.injected = true;
> +               kvm_x86_ops->queue_exception(vcpu);
> +
> +               if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
> +                       __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
> +                                            X86_EFLAGS_RF);
> +
> +               if (vcpu->arch.exception.nr == DB_VECTOR &&
> +                   (vcpu->arch.dr7 & DR7_GD)) {
> +                       vcpu->arch.dr7 &= ~DR7_GD;
> +                       kvm_update_dr7(vcpu);
> +               }
> +       } else if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
>                 vcpu->arch.smi_pending = false;
>                 enter_smm(vcpu);
>         } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
> @@ -6862,6 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>                                 kvm_x86_ops->enable_nmi_window(vcpu);
>                         if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
>                                 kvm_x86_ops->enable_irq_window(vcpu);
> +                       WARN_ON(vcpu->arch.exception.pending);

This WARN_ON() is suggested during the review of last version,
however, there are many cases in inject_pending_event() can result in
return directly w/ vcpu->arch.exception.pending is true. Actually I
have already catched the warning several times during the testing. I
think we should remove it when committing.

Regards,
Wanpeng Li

>                 }
>
>                 if (kvm_lapic_enabled(vcpu)) {
> @@ -7738,6 +7753,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
>         vcpu->arch.nmi_injected = false;
>         kvm_clear_interrupt_queue(vcpu);
>         kvm_clear_exception_queue(vcpu);
> +       vcpu->arch.exception.pending = false;
>
>         memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
>         kvm_update_dr0123(vcpu);
> diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
> index 1134603..e6ec0de 100644
> --- a/arch/x86/kvm/x86.h
> +++ b/arch/x86/kvm/x86.h
> @@ -11,7 +11,7 @@
>
>  static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
>  {
> -       vcpu->arch.exception.pending = false;
> +       vcpu->arch.exception.injected = false;
>  }
>
>  static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector,
> @@ -29,7 +29,7 @@ static inline void kvm_clear_interrupt_queue(struct kvm_vcpu *vcpu)
>
>  static inline bool kvm_event_needs_reinjection(struct kvm_vcpu *vcpu)
>  {
> -       return vcpu->arch.exception.pending || vcpu->arch.interrupt.pending ||
> +       return vcpu->arch.exception.injected || vcpu->arch.interrupt.pending ||
>                 vcpu->arch.nmi_injected;
>  }
>
> --
> 2.7.4
>

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Paolo Bonzini]

On 24/08/2017 08:52, Wanpeng Li wrote:
>> @@ -6862,6 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>>                                 kvm_x86_ops->enable_nmi_window(vcpu);
>>                         if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
>>                                 kvm_x86_ops->enable_irq_window(vcpu);
>> +                       WARN_ON(vcpu->arch.exception.pending);
>
> This WARN_ON() is suggested during the review of last version,
> however, there are many cases in inject_pending_event() can result in
> return directly w/ vcpu->arch.exception.pending is true. Actually I
> have already catched the warning several times during the testing. I
> think we should remove it when committing.

No, it's a good thing that it's failing, because it's finding a bug.  
There's no such thing as an "exception window", so at the very least it 
should set req_immediate_exit to true.

Does this help?

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b698b2f135a2..76d5a192be6c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6365,14 +6365,20 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 		return 0;
 	}
 
-	if (vcpu->arch.nmi_injected) {
-		kvm_x86_ops->set_nmi(vcpu);
-		return 0;
-	}
+	/*
+	 * Exceptions must be injected immediately, or the exception
+	 * frame will have the address of the NMI or interrupt handler.
+	 */
+	if (!vcpu->arch.exception.pending) {
+		if (vcpu->arch.nmi_injected) {
+			kvm_x86_ops->set_nmi(vcpu);
+			return 0;
+		}
 
-	if (vcpu->arch.interrupt.pending) {
-		kvm_x86_ops->set_irq(vcpu);
-		return 0;
+		if (vcpu->arch.interrupt.pending) {
+			kvm_x86_ops->set_irq(vcpu);
+			return 0;
+		}
 	}
 
 	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {

Paolo

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Wanpeng Li]

2017-08-24 16:57 GMT+08:00 Paolo Bonzini <pbonzini@redhat.com>:
> On 24/08/2017 08:52, Wanpeng Li wrote:
>>> @@ -6862,6 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>>>                                 kvm_x86_ops->enable_nmi_window(vcpu);
>>>                         if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
>>>                                 kvm_x86_ops->enable_irq_window(vcpu);
>>> +                       WARN_ON(vcpu->arch.exception.pending);
>>
>> This WARN_ON() is suggested during the review of last version,
>> however, there are many cases in inject_pending_event() can result in
>> return directly w/ vcpu->arch.exception.pending is true. Actually I
>> have already catched the warning several times during the testing. I
>> think we should remove it when committing.
>
> No, it's a good thing that it's failing, because it's finding a bug.
> There's no such thing as an "exception window", so at the very least it

Good point, the code looks good, I will fold it in next version.
However, I still can observe the warning.

Regards,
Wanpeng Li

> should set req_immediate_exit to true.
>
> Does this help?
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index b698b2f135a2..76d5a192be6c 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -6365,14 +6365,20 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
>                 return 0;
>         }
>
> -       if (vcpu->arch.nmi_injected) {
> -               kvm_x86_ops->set_nmi(vcpu);
> -               return 0;
> -       }
> +       /*
> +        * Exceptions must be injected immediately, or the exception
> +        * frame will have the address of the NMI or interrupt handler.
> +        */
> +       if (!vcpu->arch.exception.pending) {
> +               if (vcpu->arch.nmi_injected) {
> +                       kvm_x86_ops->set_nmi(vcpu);
> +                       return 0;
> +               }
>
> -       if (vcpu->arch.interrupt.pending) {
> -               kvm_x86_ops->set_irq(vcpu);
> -               return 0;
> +               if (vcpu->arch.interrupt.pending) {
> +                       kvm_x86_ops->set_irq(vcpu);
> +                       return 0;
> +               }
>         }
>
>         if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
>
> Paolo

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Wanpeng Li]

2017-08-24 17:13 GMT+08:00 Wanpeng Li <kernellwp@gmail.com>:
> 2017-08-24 16:57 GMT+08:00 Paolo Bonzini <pbonzini@redhat.com>:
>> On 24/08/2017 08:52, Wanpeng Li wrote:
>>>> @@ -6862,6 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>>>>                                 kvm_x86_ops->enable_nmi_window(vcpu);
>>>>                         if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
>>>>                                 kvm_x86_ops->enable_irq_window(vcpu);
>>>> +                       WARN_ON(vcpu->arch.exception.pending);
>>>
>>> This WARN_ON() is suggested during the review of last version,
>>> however, there are many cases in inject_pending_event() can result in
>>> return directly w/ vcpu->arch.exception.pending is true. Actually I
>>> have already catched the warning several times during the testing. I
>>> think we should remove it when committing.
>>
>> No, it's a good thing that it's failing, because it's finding a bug.
>> There's no such thing as an "exception window", so at the very least it
>
> Good point, the code looks good, I will fold it in next version.
> However, I still can observe the warning.
>
> Regards,
> Wanpeng Li

I observed sometimes both vcpu->arch.exception.pending and
vcpu->arch.expception.injected are true before executing below codes:

if (vcpu->arch.exception.injected) {
    kvm_x86_ops->queue_exception(vcpu);
    return 0;
}

Regards,
Wanpeng Li

>
>> should set req_immediate_exit to true.
>>
>> Does this help?
>>
>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>> index b698b2f135a2..76d5a192be6c 100644
>> --- a/arch/x86/kvm/x86.c
>> +++ b/arch/x86/kvm/x86.c
>> @@ -6365,14 +6365,20 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
>>                 return 0;
>>         }
>>
>> -       if (vcpu->arch.nmi_injected) {
>> -               kvm_x86_ops->set_nmi(vcpu);
>> -               return 0;
>> -       }
>> +       /*
>> +        * Exceptions must be injected immediately, or the exception
>> +        * frame will have the address of the NMI or interrupt handler.
>> +        */
>> +       if (!vcpu->arch.exception.pending) {
>> +               if (vcpu->arch.nmi_injected) {
>> +                       kvm_x86_ops->set_nmi(vcpu);
>> +                       return 0;
>> +               }
>>
>> -       if (vcpu->arch.interrupt.pending) {
>> -               kvm_x86_ops->set_irq(vcpu);
>> -               return 0;
>> +               if (vcpu->arch.interrupt.pending) {
>> +                       kvm_x86_ops->set_irq(vcpu);
>> +                       return 0;
>> +               }
>>         }
>>
>>         if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
>>
>> Paolo

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Paolo Bonzini]

On 24/08/2017 11:34, Wanpeng Li wrote:
> 2017-08-24 17:13 GMT+08:00 Wanpeng Li <kernellwp@gmail.com>:
>> 2017-08-24 16:57 GMT+08:00 Paolo Bonzini <pbonzini@redhat.com>:
>>> On 24/08/2017 08:52, Wanpeng Li wrote:
>>>>> @@ -6862,6 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>>>>>                                 kvm_x86_ops->enable_nmi_window(vcpu);
>>>>>                         if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
>>>>>                                 kvm_x86_ops->enable_irq_window(vcpu);
>>>>> +                       WARN_ON(vcpu->arch.exception.pending);
>>>>
>>>> This WARN_ON() is suggested during the review of last version,
>>>> however, there are many cases in inject_pending_event() can result in
>>>> return directly w/ vcpu->arch.exception.pending is true. Actually I
>>>> have already catched the warning several times during the testing. I
>>>> think we should remove it when committing.
>>>
>>> No, it's a good thing that it's failing, because it's finding a bug.
>>> There's no such thing as an "exception window", so at the very least it
>>
>> Good point, the code looks good, I will fold it in next version.
>> However, I still can observe the warning.
>>
>> Regards,
>> Wanpeng Li
> 
> I observed sometimes both vcpu->arch.exception.pending and
> vcpu->arch.expception.injected are true before executing below codes:
> 
> if (vcpu->arch.exception.injected) {
>     kvm_x86_ops->queue_exception(vcpu);
>     return 0;
> }

More missing pieces:

1) kvm_x86_ops->queue_exception must be called in the
vcpu->arch.exception.pending case.  Compare it with the others, which
are calling enter_smm, kvm_x86_ops->set_irq, kvm_x86_ops->set_nmi.
	
2) here:

        if (!vcpu->arch.exception.pending ||
                !vcpu->arch.exception.injected) {
        queue:
                if (has_error && !is_protmode(vcpu))
                        has_error = false;
                if (reinject)
                        vcpu->arch.exception.injected = true;
                else
                        vcpu->arch.exception.pending = true;

you need to reset the other field, because you can get here from the
double-fault case.  Likewise below:

        if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY)
                || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
                /* generate double fault per SDM Table 5-5 */
                vcpu->arch.exception.pending = true;

injected must be cleared.

> Regards,
> Wanpeng Li
> 
>>
>>> should set req_immediate_exit to true.
>>>
>>> Does this help?
>>>
>>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>>> index b698b2f135a2..76d5a192be6c 100644
>>> --- a/arch/x86/kvm/x86.c
>>> +++ b/arch/x86/kvm/x86.c
>>> @@ -6365,14 +6365,20 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
>>>                 return 0;
>>>         }
>>>
>>> -       if (vcpu->arch.nmi_injected) {
>>> -               kvm_x86_ops->set_nmi(vcpu);
>>> -               return 0;
>>> -       }
>>> +       /*
>>> +        * Exceptions must be injected immediately, or the exception
>>> +        * frame will have the address of the NMI or interrupt handler.
>>> +        */
>>> +       if (!vcpu->arch.exception.pending) {
>>> +               if (vcpu->arch.nmi_injected) {
>>> +                       kvm_x86_ops->set_nmi(vcpu);
>>> +                       return 0;
>>> +               }
>>>
>>> -       if (vcpu->arch.interrupt.pending) {
>>> -               kvm_x86_ops->set_irq(vcpu);
>>> -               return 0;
>>> +               if (vcpu->arch.interrupt.pending) {
>>> +                       kvm_x86_ops->set_irq(vcpu);
>>> +                       return 0;
>>> +               }
>>>         }
>>>
>>>         if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
>>>
>>> Paolo

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Paolo Bonzini]

On 24/08/2017 11:13, Wanpeng Li wrote:
> 2017-08-24 16:57 GMT+08:00 Paolo Bonzini <pbonzini@redhat.com>:
>> On 24/08/2017 08:52, Wanpeng Li wrote:
>>>> @@ -6862,6 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>>>>                                 kvm_x86_ops->enable_nmi_window(vcpu);
>>>>                         if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
>>>>                                 kvm_x86_ops->enable_irq_window(vcpu);
>>>> +                       WARN_ON(vcpu->arch.exception.pending);
>>>
>>> This WARN_ON() is suggested during the review of last version,
>>> however, there are many cases in inject_pending_event() can result in
>>> return directly w/ vcpu->arch.exception.pending is true. Actually I
>>> have already catched the warning several times during the testing. I
>>> think we should remove it when committing.
>>
>> No, it's a good thing that it's failing, because it's finding a bug.
>> There's no such thing as an "exception window", so at the very least it
> 
> Good point, the code looks good, I will fold it in next version.
> However, I still can observe the warning.

In patch 4, vmx_check_nested_events must clear vcpu->ex.pending.

Paolo

> Regards,
> Wanpeng Li
> 
>> should set req_immediate_exit to true.
>>
>> Does this help?
>>
>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>> index b698b2f135a2..76d5a192be6c 100644
>> --- a/arch/x86/kvm/x86.c
>> +++ b/arch/x86/kvm/x86.c
>> @@ -6365,14 +6365,20 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
>>                 return 0;
>>         }
>>
>> -       if (vcpu->arch.nmi_injected) {
>> -               kvm_x86_ops->set_nmi(vcpu);
>> -               return 0;
>> -       }
>> +       /*
>> +        * Exceptions must be injected immediately, or the exception
>> +        * frame will have the address of the NMI or interrupt handler.
>> +        */
>> +       if (!vcpu->arch.exception.pending) {
>> +               if (vcpu->arch.nmi_injected) {
>> +                       kvm_x86_ops->set_nmi(vcpu);
>> +                       return 0;
>> +               }
>>
>> -       if (vcpu->arch.interrupt.pending) {
>> -               kvm_x86_ops->set_irq(vcpu);
>> -               return 0;
>> +               if (vcpu->arch.interrupt.pending) {
>> +                       kvm_x86_ops->set_irq(vcpu);
>> +                       return 0;
>> +               }
>>         }
>>
>>         if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
>>
>> Paolo

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Wanpeng Li]

2017-08-24 17:35 GMT+08:00 Paolo Bonzini <pbonzini@redhat.com>:
> On 24/08/2017 11:13, Wanpeng Li wrote:
>> 2017-08-24 16:57 GMT+08:00 Paolo Bonzini <pbonzini@redhat.com>:
>>> On 24/08/2017 08:52, Wanpeng Li wrote:
>>>>> @@ -6862,6 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>>>>>                                 kvm_x86_ops->enable_nmi_window(vcpu);
>>>>>                         if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
>>>>>                                 kvm_x86_ops->enable_irq_window(vcpu);
>>>>> +                       WARN_ON(vcpu->arch.exception.pending);
>>>>
>>>> This WARN_ON() is suggested during the review of last version,
>>>> however, there are many cases in inject_pending_event() can result in
>>>> return directly w/ vcpu->arch.exception.pending is true. Actually I
>>>> have already catched the warning several times during the testing. I
>>>> think we should remove it when committing.
>>>
>>> No, it's a good thing that it's failing, because it's finding a bug.
>>> There's no such thing as an "exception window", so at the very least it
>>
>> Good point, the code looks good, I will fold it in next version.
>> However, I still can observe the warning.
>
> In patch 4, vmx_check_nested_events must clear vcpu->ex.pending.

It is true, but I can still observe the warning.


diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6f88a79..4f97c4f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -10990,6 +10990,8 @@ static int vmx_check_nested_events(struct
kvm_vcpu *vcpu, bool external_intr)
         if (vmx->nested.nested_run_pending)
             return -EBUSY;

+        vcpu->arch.exception.pending = false;
+        vcpu->arch.exception.injected = true;
         nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
         return 0;
     }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b698b2f..77e3031 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6365,14 +6365,20 @@ static int inject_pending_event(struct
kvm_vcpu *vcpu, bool req_int_win)
         return 0;
     }

-    if (vcpu->arch.nmi_injected) {
-        kvm_x86_ops->set_nmi(vcpu);
-        return 0;
-    }
+    /*
+     * Exceptions must be injected immediately, or the exception
+     * frame will have the address of the NMI or interrupt handler.
+     */
+    if (!vcpu->arch.exception.pending) {
+        if (vcpu->arch.nmi_injected) {
+            kvm_x86_ops->set_nmi(vcpu);
+            return 0;
+        }

-    if (vcpu->arch.interrupt.pending) {
-        kvm_x86_ops->set_irq(vcpu);
-        return 0;
+        if (vcpu->arch.interrupt.pending) {
+            kvm_x86_ops->set_irq(vcpu);
+            return 0;
+        }
     }

     if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Ross Zwisler]

On Wed, Aug 23, 2017 at 10:21 PM, Wanpeng Li <kernellwp@gmail.com> wrote:
> From: Wanpeng Li <wanpeng.li@hotmail.com>
>
> vmx_complete_interrupts() assumes that the exception is always injected,
> so it would be dropped by kvm_clear_exception_queue(). This patch separates
> exception.pending from exception.injected, exception.inject represents the
> exception is injected or the exception should be reinjected due to vmexit
> occurs during event delivery in VMX non-root operation. exception.pending
> represents the exception is queued and will be cleared when injecting the
> exception to the guest. So exception.pending and exception.injected can
> cooperate to guarantee exception will not be lost.
>
> Reported-by: Radim Krčmář <rkrcmar@redhat.com>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Radim Krčmář <rkrcmar@redhat.com>
> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
> ---

I'm seeing a regression in my QEMU based NVDIMM testing system, and I
bisected it to this commit.

The behavior I'm seeing is that heavy I/O to simulated NVDIMMs in
multiple virtual machines causes the QEMU guests to receive double
faults, crashing them.  Here's an example backtrace:

[ 1042.653816] PANIC: double fault, error_code: 0x0
[ 1042.654398] CPU: 2 PID: 30257 Comm: fsstress Not tainted 4.15.0-rc5 #1
[ 1042.655169] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.10.2-2.fc27 04/01/2014
[ 1042.656121] RIP: 0010:memcpy_flushcache+0x4d/0x180
[ 1042.656631] RSP: 0018:ffffac098c7d3808 EFLAGS: 00010286
[ 1042.657245] RAX: ffffac0d18ca8000 RBX: 0000000000000fe0 RCX: ffffac0d18ca8000
[ 1042.658085] RDX: ffff921aaa5df000 RSI: ffff921aaa5e0000 RDI: 000019f26e6c9000
[ 1042.658802] RBP: 0000000000001000 R08: 0000000000000000 R09: 0000000000000000
[ 1042.659503] R10: 0000000000000000 R11: 0000000000000000 R12: ffff921aaa5df020
[ 1042.660306] R13: ffffac0d18ca8000 R14: fffff4c102a977c0 R15: 0000000000001000
[ 1042.661132] FS:  00007f71530b90c0(0000) GS:ffff921b3b280000(0000)
knlGS:0000000000000000
[ 1042.662051] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1042.662528] CR2: 0000000001156002 CR3: 000000012a936000 CR4: 00000000000006e0
[ 1042.663093] Call Trace:
[ 1042.663329]  write_pmem+0x6c/0xa0 [nd_pmem]
[ 1042.663668]  pmem_do_bvec+0x15f/0x330 [nd_pmem]
[ 1042.664056]  ? kmem_alloc+0x61/0xe0 [xfs]
[ 1042.664393]  pmem_make_request+0xdd/0x220 [nd_pmem]
[ 1042.664781]  generic_make_request+0x11f/0x300
[ 1042.665135]  ? submit_bio+0x6c/0x140
[ 1042.665436]  submit_bio+0x6c/0x140
[ 1042.665754]  ? next_bio+0x18/0x40
[ 1042.666025]  ? _cond_resched+0x15/0x40
[ 1042.666341]  submit_bio_wait+0x53/0x80
[ 1042.666804]  blkdev_issue_zeroout+0xdc/0x210
[ 1042.667336]  ? __dax_zero_page_range+0xb5/0x140
[ 1042.667810]  __dax_zero_page_range+0xb5/0x140
[ 1042.668197]  ? xfs_file_iomap_begin+0x2bd/0x8e0 [xfs]
[ 1042.668611]  iomap_zero_range_actor+0x7c/0x1b0
[ 1042.668974]  ? iomap_write_actor+0x170/0x170
[ 1042.669318]  iomap_apply+0xa4/0x110
[ 1042.669616]  ? iomap_write_actor+0x170/0x170
[ 1042.669958]  iomap_zero_range+0x52/0x80
[ 1042.670255]  ? iomap_write_actor+0x170/0x170
[ 1042.670616]  xfs_setattr_size+0xd4/0x330 [xfs]
[ 1042.670995]  xfs_ioc_space+0x27e/0x2f0 [xfs]
[ 1042.671332]  ? terminate_walk+0x87/0xf0
[ 1042.671662]  xfs_file_ioctl+0x862/0xa40 [xfs]
[ 1042.672035]  ? _copy_to_user+0x22/0x30
[ 1042.672346]  ? cp_new_stat+0x150/0x180
[ 1042.672663]  do_vfs_ioctl+0xa1/0x610
[ 1042.672960]  ? SYSC_newfstat+0x3c/0x60
[ 1042.673264]  SyS_ioctl+0x74/0x80
[ 1042.673661]  entry_SYSCALL_64_fastpath+0x1a/0x7d
[ 1042.674239] RIP: 0033:0x7f71525a2dc7
[ 1042.674681] RSP: 002b:00007ffef97aa778 EFLAGS: 00000246 ORIG_RAX:
0000000000000010
[ 1042.675664] RAX: ffffffffffffffda RBX: 00000000000112bc RCX: 00007f71525a2dc7
[ 1042.676592] RDX: 00007ffef97aa7a0 RSI: 0000000040305825 RDI: 0000000000000003
[ 1042.677520] RBP: 0000000000000009 R08: 0000000000000045 R09: 00007ffef97aa78c
[ 1042.678442] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003
[ 1042.679330] R13: 0000000000019e38 R14: 00000000000fcca7 R15: 0000000000000016
[ 1042.680216] Code: 48 8d 5d e0 4c 8d 62 20 48 89 cf 48 29 d7 48 89
de 48 83 e6 e0 4c 01 e6 48 8d 04 17 4c 8b 02 4c 8b 4a 08 4c 8b 52 10
4c 8b 5a 18 <4c> 0f c3 00 4c 0f c3 48 08 4c 0f c3 50 10 4c 0f c3 58 18
48 83

This appears to be independent of both the guest kernel version (this
backtrace has v4.15.0-rc5, but I've seen it with other kernels) as
well as independent of the host QMEU version (mine happens to be
qemu-2.10.1-2.fc27 in Fedora 27).

The new behavior is due to this commit being present in the host OS
kernel.  Prior to this commit I could fire up 4 VMs and run xfstests
on my simulated NVDIMMs, but after this commit such testing results in
multiple of my VMs crashing almost immediately.

Reproduction is very simple, at least on my development box.  All you
need are a pair of VMs (I just did it with clean installs of Fedora
27) with NVDIMMs.  Here's a sample QEMU command to get one of these:

# qemu-system-x86_64 /home/rzwisler/vms/Fedora27.qcow2 -m
4G,slots=3,maxmem=512G -smp 12 -machine pc,accel=kvm,nvdimm
-enable-kvm -object
memory-backend-file,id=mem1,share,mem-path=/home/rzwisler/nvdimms/nvdimm-1,size=17G
-device nvdimm,memdev=mem1,id=nv1

In my setup my NVDIMMs backing files (/home/rzwisler/nvdimms/nvdimm-1)
are being created on a filesystem on an SSD.

After these two qemu guests are up, run write I/Os to the resulting
/dev/pmem0 devices.   I've done this with xfstests and fio to get the
error, but the simplest way is just:

# dd if=/dev/zero of=/dev/pmem0

The double fault should happen in under a minute, definitely before
the DDs run out of space on their /dev/pmem0 devices.

I've reproduced this on multiple development boxes, so I'm pretty sure
it's not related to a flakey hardware setup.

Thanks,
- Ross

Re: [PATCH v3 2/4] KVM: X86: Fix loss of exception which has not yet injected

[Haozhong Zhang]

On 01/07/18 00:26 -0700, Ross Zwisler wrote:
> On Wed, Aug 23, 2017 at 10:21 PM, Wanpeng Li <kernellwp@gmail.com> wrote:
> > From: Wanpeng Li <wanpeng.li@hotmail.com>
> >
> > vmx_complete_interrupts() assumes that the exception is always injected,
> > so it would be dropped by kvm_clear_exception_queue(). This patch separates
> > exception.pending from exception.injected, exception.inject represents the
> > exception is injected or the exception should be reinjected due to vmexit
> > occurs during event delivery in VMX non-root operation. exception.pending
> > represents the exception is queued and will be cleared when injecting the
> > exception to the guest. So exception.pending and exception.injected can
> > cooperate to guarantee exception will not be lost.
> >
> > Reported-by: Radim Krčmář <rkrcmar@redhat.com>
> > Cc: Paolo Bonzini <pbonzini@redhat.com>
> > Cc: Radim Krčmář <rkrcmar@redhat.com>
> > Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
> > ---
> 
> I'm seeing a regression in my QEMU based NVDIMM testing system, and I
> bisected it to this commit.
> 
> The behavior I'm seeing is that heavy I/O to simulated NVDIMMs in
> multiple virtual machines causes the QEMU guests to receive double
> faults, crashing them.  Here's an example backtrace:
> 
> [ 1042.653816] PANIC: double fault, error_code: 0x0
> [ 1042.654398] CPU: 2 PID: 30257 Comm: fsstress Not tainted 4.15.0-rc5 #1
> [ 1042.655169] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
> BIOS 1.10.2-2.fc27 04/01/2014
> [ 1042.656121] RIP: 0010:memcpy_flushcache+0x4d/0x180
> [ 1042.656631] RSP: 0018:ffffac098c7d3808 EFLAGS: 00010286
> [ 1042.657245] RAX: ffffac0d18ca8000 RBX: 0000000000000fe0 RCX: ffffac0d18ca8000
> [ 1042.658085] RDX: ffff921aaa5df000 RSI: ffff921aaa5e0000 RDI: 000019f26e6c9000
> [ 1042.658802] RBP: 0000000000001000 R08: 0000000000000000 R09: 0000000000000000
> [ 1042.659503] R10: 0000000000000000 R11: 0000000000000000 R12: ffff921aaa5df020
> [ 1042.660306] R13: ffffac0d18ca8000 R14: fffff4c102a977c0 R15: 0000000000001000
> [ 1042.661132] FS:  00007f71530b90c0(0000) GS:ffff921b3b280000(0000)
> knlGS:0000000000000000
> [ 1042.662051] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 1042.662528] CR2: 0000000001156002 CR3: 000000012a936000 CR4: 00000000000006e0
> [ 1042.663093] Call Trace:
> [ 1042.663329]  write_pmem+0x6c/0xa0 [nd_pmem]
> [ 1042.663668]  pmem_do_bvec+0x15f/0x330 [nd_pmem]
> [ 1042.664056]  ? kmem_alloc+0x61/0xe0 [xfs]
> [ 1042.664393]  pmem_make_request+0xdd/0x220 [nd_pmem]
> [ 1042.664781]  generic_make_request+0x11f/0x300
> [ 1042.665135]  ? submit_bio+0x6c/0x140
> [ 1042.665436]  submit_bio+0x6c/0x140
> [ 1042.665754]  ? next_bio+0x18/0x40
> [ 1042.666025]  ? _cond_resched+0x15/0x40
> [ 1042.666341]  submit_bio_wait+0x53/0x80
> [ 1042.666804]  blkdev_issue_zeroout+0xdc/0x210
> [ 1042.667336]  ? __dax_zero_page_range+0xb5/0x140
> [ 1042.667810]  __dax_zero_page_range+0xb5/0x140
> [ 1042.668197]  ? xfs_file_iomap_begin+0x2bd/0x8e0 [xfs]
> [ 1042.668611]  iomap_zero_range_actor+0x7c/0x1b0
> [ 1042.668974]  ? iomap_write_actor+0x170/0x170
> [ 1042.669318]  iomap_apply+0xa4/0x110
> [ 1042.669616]  ? iomap_write_actor+0x170/0x170
> [ 1042.669958]  iomap_zero_range+0x52/0x80
> [ 1042.670255]  ? iomap_write_actor+0x170/0x170
> [ 1042.670616]  xfs_setattr_size+0xd4/0x330 [xfs]
> [ 1042.670995]  xfs_ioc_space+0x27e/0x2f0 [xfs]
> [ 1042.671332]  ? terminate_walk+0x87/0xf0
> [ 1042.671662]  xfs_file_ioctl+0x862/0xa40 [xfs]
> [ 1042.672035]  ? _copy_to_user+0x22/0x30
> [ 1042.672346]  ? cp_new_stat+0x150/0x180
> [ 1042.672663]  do_vfs_ioctl+0xa1/0x610
> [ 1042.672960]  ? SYSC_newfstat+0x3c/0x60
> [ 1042.673264]  SyS_ioctl+0x74/0x80
> [ 1042.673661]  entry_SYSCALL_64_fastpath+0x1a/0x7d
> [ 1042.674239] RIP: 0033:0x7f71525a2dc7
> [ 1042.674681] RSP: 002b:00007ffef97aa778 EFLAGS: 00000246 ORIG_RAX:
> 0000000000000010
> [ 1042.675664] RAX: ffffffffffffffda RBX: 00000000000112bc RCX: 00007f71525a2dc7
> [ 1042.676592] RDX: 00007ffef97aa7a0 RSI: 0000000040305825 RDI: 0000000000000003
> [ 1042.677520] RBP: 0000000000000009 R08: 0000000000000045 R09: 00007ffef97aa78c
> [ 1042.678442] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003
> [ 1042.679330] R13: 0000000000019e38 R14: 00000000000fcca7 R15: 0000000000000016
> [ 1042.680216] Code: 48 8d 5d e0 4c 8d 62 20 48 89 cf 48 29 d7 48 89
> de 48 83 e6 e0 4c 01 e6 48 8d 04 17 4c 8b 02 4c 8b 4a 08 4c 8b 52 10
> 4c 8b 5a 18 <4c> 0f c3 00 4c 0f c3 48 08 4c 0f c3 50 10 4c 0f c3 58 18
> 48 83
> 
> This appears to be independent of both the guest kernel version (this
> backtrace has v4.15.0-rc5, but I've seen it with other kernels) as
> well as independent of the host QMEU version (mine happens to be
> qemu-2.10.1-2.fc27 in Fedora 27).
> 
> The new behavior is due to this commit being present in the host OS
> kernel.  Prior to this commit I could fire up 4 VMs and run xfstests
> on my simulated NVDIMMs, but after this commit such testing results in
> multiple of my VMs crashing almost immediately.
> 
> Reproduction is very simple, at least on my development box.  All you
> need are a pair of VMs (I just did it with clean installs of Fedora
> 27) with NVDIMMs.  Here's a sample QEMU command to get one of these:
> 
> # qemu-system-x86_64 /home/rzwisler/vms/Fedora27.qcow2 -m
> 4G,slots=3,maxmem=512G -smp 12 -machine pc,accel=kvm,nvdimm
> -enable-kvm -object
> memory-backend-file,id=mem1,share,mem-path=/home/rzwisler/nvdimms/nvdimm-1,size=17G
> -device nvdimm,memdev=mem1,id=nv1
> 
> In my setup my NVDIMMs backing files (/home/rzwisler/nvdimms/nvdimm-1)
> are being created on a filesystem on an SSD.
> 
> After these two qemu guests are up, run write I/Os to the resulting
> /dev/pmem0 devices.   I've done this with xfstests and fio to get the
> error, but the simplest way is just:
> 
> # dd if=/dev/zero of=/dev/pmem0
> 
> The double fault should happen in under a minute, definitely before
> the DDs run out of space on their /dev/pmem0 devices.
> 
> I've reproduced this on multiple development boxes, so I'm pretty sure
> it's not related to a flakey hardware setup.
> 

Thanks for reporting this issue. I'll look into this issue.

Haozhong

[PATCH v3 3/4] KVM: VMX: Move the nested_vmx_inject_exception_vmexit call from nested_vmx_check_exception to vmx_queue_exception

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@hotmail.com>

Move the nested_vmx_inject_exception_vmexit call from nested_vmx_check_exception 
to vmx_queue_exception. 

Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
 arch/x86/kvm/vmx.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 902b780..21760b8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2459,15 +2459,14 @@ static void nested_vmx_inject_exception_vmexit(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)
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	unsigned int nr = vcpu->arch.exception.nr;
 
 	if (nr == PF_VECTOR) {
 		if (vcpu->arch.exception.nested_apf) {
-			nested_vmx_inject_exception_vmexit(vcpu,
-							   vcpu->arch.apf.nested_apf_token);
+			*exit_qual = vcpu->arch.apf.nested_apf_token;
 			return 1;
 		}
 		/*
@@ -2481,16 +2480,15 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
 		 */
 		if (nested_vmx_is_page_fault_vmexit(vmcs12,
 						    vcpu->arch.exception.error_code)) {
-			nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2);
+			*exit_qual = vcpu->arch.cr2;
 			return 1;
 		}
 	} else {
-		unsigned long exit_qual = 0;
-		if (nr == DB_VECTOR)
-			exit_qual = vcpu->arch.dr6;
-
 		if (vmcs12->exception_bitmap & (1u << nr)) {
-			nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+			if (nr == DB_VECTOR)
+				*exit_qual = vcpu->arch.dr6;
+			else
+				*exit_qual = 0;
 			return 1;
 		}
 	}
@@ -2506,10 +2504,13 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 	bool reinject = vcpu->arch.exception.injected;
 	u32 error_code = vcpu->arch.exception.error_code;
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
+	unsigned long exit_qual;
 
 	if (!reinject && is_guest_mode(vcpu) &&
-	    nested_vmx_check_exception(vcpu))
+	    nested_vmx_check_exception(vcpu, &exit_qual)) {
+		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
 		return;
+	}
 
 	if (has_error_code) {
 		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
-- 
2.7.4

[PATCH v3 4/4] KVM: nVMX: Fix trying to cancel vmlauch/vmresume

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@hotmail.com>

------------[ cut here ]------------
WARNING: CPU: 7 PID: 3861 at /home/kernel/ssd/kvm/arch/x86/kvm//vmx.c:11299 nested_vmx_vmexit+0x176e/0x1980 [kvm_intel]
CPU: 7 PID: 3861 Comm: qemu-system-x86 Tainted: G        W  OE   4.13.0-rc4+ #11
RIP: 0010:nested_vmx_vmexit+0x176e/0x1980 [kvm_intel]
Call Trace:
 ? kvm_multiple_exception+0x149/0x170 [kvm]
 ? handle_emulation_failure+0x79/0x230 [kvm]
 ? load_vmcs12_host_state+0xa80/0xa80 [kvm_intel]
 ? check_chain_key+0x137/0x1e0
 ? reexecute_instruction.part.168+0x130/0x130 [kvm]
 nested_vmx_inject_exception_vmexit+0xb7/0x100 [kvm_intel]
 ? nested_vmx_inject_exception_vmexit+0xb7/0x100 [kvm_intel]
 vmx_queue_exception+0x197/0x300 [kvm_intel]
 kvm_arch_vcpu_ioctl_run+0x1b0c/0x2c90 [kvm]
 ? kvm_arch_vcpu_runnable+0x220/0x220 [kvm]
 ? preempt_count_sub+0x18/0xc0
 ? restart_apic_timer+0x17d/0x300 [kvm]
 ? kvm_lapic_restart_hv_timer+0x37/0x50 [kvm]
 ? kvm_arch_vcpu_load+0x1d8/0x350 [kvm]
 kvm_vcpu_ioctl+0x4e4/0x910 [kvm]
 ? kvm_vcpu_ioctl+0x4e4/0x910 [kvm]
 ? kvm_dev_ioctl+0xbe0/0xbe0 [kvm]

The flag "nested_run_pending", which can override the decision of which should run 
next, L1 or L2. nested_run_pending=1 means that we *must* run L2 next, not L1. This 
is necessary in particular when L1 did a VMLAUNCH of L2 and therefore expects L2 to 
be run (and perhaps be injected with an event it specified, etc.). Nested_run_pending 
is especially intended to avoid switching  to L1 in the injection decision-point.

I catch this in the queue exception path, this patch fixes it by requesting 
an immediate VM exit from L2 and keeping the exception for L1 pending for a 
subsequent nested VM exit.

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 | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 21760b8..6f88a79 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2501,16 +2501,8 @@ 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.injected;
 	u32 error_code = vcpu->arch.exception.error_code;
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
-	unsigned long exit_qual;
-
-	if (!reinject && is_guest_mode(vcpu) &&
-	    nested_vmx_check_exception(vcpu, &exit_qual)) {
-		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
-		return;
-	}
 
 	if (has_error_code) {
 		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
@@ -10988,10 +10980,20 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long exit_qual;
 
 	if (kvm_event_needs_reinjection(vcpu))
 		return -EBUSY;
 
+	if (vcpu->arch.exception.pending &&
+		nested_vmx_check_exception(vcpu, &exit_qual)) {
+		if (vmx->nested.nested_run_pending)
+			return -EBUSY;
+
+		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+		return 0;
+    }
+
 	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
 	    vmx->nested.preemption_timer_expired) {
 		if (vmx->nested.nested_run_pending)
-- 
2.7.4