diff mbox

[v3] kvm: svm: Use the hardware provided GPA instead of page walk

Message ID 148044249174.29544.4194514184644021170.stgit@brijesh-build-machine (mailing list archive)
State New, archived
Headers show

Commit Message

Brijesh Singh Nov. 29, 2016, 6:01 p.m. UTC
From: Tom Lendacky <thomas.lendacky@amd.com>

When a guest causes a NPF which requires emulation, KVM sometimes walks
the guest page tables to translate the GVA to a GPA. This is unnecessary
most of the time on AMD hardware since the hardware provides the GPA in
EXITINFO2.

The only exception cases involve string operations involving rep or
operations that use two memory locations. With rep, the GPA will only be
the value of the initial NPF and with dual memory locations we won't know
which memory address was translated into EXITINFO2.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
---
 arch/x86/include/asm/kvm_emulate.h |    1 +
 arch/x86/include/asm/kvm_host.h    |    3 ++
 arch/x86/kvm/emulate.c             |    8 +++++++
 arch/x86/kvm/svm.c                 |    2 ++
 arch/x86/kvm/x86.c                 |   44 ++++++++++++++++++++++++++++--------
 5 files changed, 48 insertions(+), 10 deletions(-)


--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Paolo Bonzini Nov. 29, 2016, 6:10 p.m. UTC | #1
On 29/11/2016 19:01, Brijesh Singh wrote:
> From: Tom Lendacky <thomas.lendacky@amd.com>
> 
> When a guest causes a NPF which requires emulation, KVM sometimes walks
> the guest page tables to translate the GVA to a GPA. This is unnecessary
> most of the time on AMD hardware since the hardware provides the GPA in
> EXITINFO2.
> 
> The only exception cases involve string operations involving rep or
> operations that use two memory locations. With rep, the GPA will only be
> the value of the initial NPF and with dual memory locations we won't know
> which memory address was translated into EXITINFO2.
> 
> Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
> Reviewed-by: Borislav Petkov <bp@suse.de>
> Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
> ---
>  arch/x86/include/asm/kvm_emulate.h |    1 +
>  arch/x86/include/asm/kvm_host.h    |    3 ++
>  arch/x86/kvm/emulate.c             |    8 +++++++
>  arch/x86/kvm/svm.c                 |    2 ++
>  arch/x86/kvm/x86.c                 |   44 ++++++++++++++++++++++++++++--------
>  5 files changed, 48 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
> index e9cd7be..777eea2 100644
> --- a/arch/x86/include/asm/kvm_emulate.h
> +++ b/arch/x86/include/asm/kvm_emulate.h
> @@ -441,5 +441,6 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
>  int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq);
>  void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt);
>  void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt);
> +bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt);
>  
>  #endif /* _ASM_X86_KVM_X86_EMULATE_H */
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 77cb3f9..fd5b1c8 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -668,6 +668,9 @@ struct kvm_vcpu_arch {
>  
>  	int pending_ioapic_eoi;
>  	int pending_external_vector;
> +
> +	/* GPA available (AMD only) */
> +	bool gpa_available;
>  };
>  
>  struct kvm_lpage_info {
> diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
> index a3ce9d2..0ea543e 100644
> --- a/arch/x86/kvm/emulate.c
> +++ b/arch/x86/kvm/emulate.c
> @@ -5483,3 +5483,11 @@ void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt)
>  {
>  	writeback_registers(ctxt);
>  }
> +
> +bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt)
> +{
> +	if (ctxt->d & String)
> +		return true;
> +
> +	return false;
> +}
> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> index 5e64e656..e9b3555 100644
> --- a/arch/x86/kvm/svm.c
> +++ b/arch/x86/kvm/svm.c
> @@ -4188,6 +4188,8 @@ static int handle_exit(struct kvm_vcpu *vcpu)
>  
>  	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
>  
> +	vcpu->arch.gpa_available = (exit_code == SVM_EXIT_NPF);
> +
>  	if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE))
>  		vcpu->arch.cr0 = svm->vmcb->save.cr0;
>  	if (npt_enabled)
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index c30f62dc..507c75c 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -4420,6 +4420,21 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
>  }
>  EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
>  
> +static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
> +			    gpa_t gpa, bool write)
> +{
> +	/* For APIC access vmexit */
> +	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
> +		return 1;
> +
> +	if (vcpu_match_mmio_gpa(vcpu, gpa)) {
> +		trace_vcpu_match_mmio(gva, gpa, write, true);
> +		return 1;
> +	}
> +
> +	return 0;
> +}
> +
>  static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
>  				gpa_t *gpa, struct x86_exception *exception,
>  				bool write)
> @@ -4446,16 +4461,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
>  	if (*gpa == UNMAPPED_GVA)
>  		return -1;
>  
> -	/* For APIC access vmexit */
> -	if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
> -		return 1;
> -
> -	if (vcpu_match_mmio_gpa(vcpu, *gpa)) {
> -		trace_vcpu_match_mmio(gva, *gpa, write, true);
> -		return 1;
> -	}
> -
> -	return 0;
> +	return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write);
>  }
>  
>  int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
> @@ -4552,6 +4558,21 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
>  	int handled, ret;
>  	bool write = ops->write;
>  	struct kvm_mmio_fragment *frag;
> +	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
> +
> +	/*
> +	 * If the exit was due to a NPF we may already have a GPA.
> +	 * If the GPA is present, use it to avoid the GVA to GPA table walk.
> +	 * Note, this cannot be used on string operations since string
> +	 * operation using rep will only have the initial GPA from the NPF
> +	 * occurred.
> +	 */
> +	if (vcpu->arch.gpa_available &&
> +	    !emulator_is_string_op(ctxt) &&
> +	    vcpu_is_mmio_gpa(vcpu, addr, exception->address, write)) {
> +		gpa = exception->address;
> +		goto mmio;
> +	}
>  
>  	ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
>  
> @@ -5563,6 +5584,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
>  	}
>  
>  restart:
> +	/* Save the faulting GPA (cr2) in the address field */
> +	ctxt->exception.address = cr2;
> +
>  	r = x86_emulate_insn(ctxt);
>  
>  	if (r == EMULATION_INTERCEPTED)
> 

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>

Thanks!

Paolo
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Thomas Gleixner Nov. 29, 2016, 6:20 p.m. UTC | #2
On Tue, 29 Nov 2016, Brijesh Singh wrote:
> --- a/arch/x86/kvm/emulate.c
> +++ b/arch/x86/kvm/emulate.c
> @@ -5483,3 +5483,11 @@ void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt)
>  {
>  	writeback_registers(ctxt);
>  }
> +
> +bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt)
> +{
> +	if (ctxt->d & String)
> +		return true;
> +
> +	return false;
> +}

Do we really need a full function call for this simple thing? Just because
this horrible CamelCase constant is in emulate.c?

What's wrong with moving that thing into a header and make it a trivial
inline:

#define INS_STRING		(1 << 13)

static inline bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt)
{
	return ctxt->d & INS_STRING;
}

Hmm?

	tglx
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Brijesh Singh Nov. 29, 2016, 7:38 p.m. UTC | #3
On 11/29/2016 12:20 PM, Thomas Gleixner wrote:
> On Tue, 29 Nov 2016, Brijesh Singh wrote:
>> --- a/arch/x86/kvm/emulate.c
>> +++ b/arch/x86/kvm/emulate.c
>> @@ -5483,3 +5483,11 @@ void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt)
>>  {
>>  	writeback_registers(ctxt);
>>  }
>> +
>> +bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt)
>> +{
>> +	if (ctxt->d & String)
>> +		return true;
>> +
>> +	return false;
>> +}
>
> Do we really need a full function call for this simple thing? Just because
> this horrible CamelCase constant is in emulate.c?
>
> What's wrong with moving that thing into a header and make it a trivial
> inline:
>
> #define INS_STRING		(1 << 13)
>
> static inline bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt)
> {
> 	return ctxt->d & INS_STRING;
> }
>
> Hmm?

One of the recommendation from previous review feedback was to move the 
check inside emulator.c. I am fine with inlining it into kvm_emulate.h

Hi Paolo,

Do you want me to spin a new version ?

-Brijesh
>
> 	tglx
>
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Paolo Bonzini Dec. 8, 2016, 2:53 p.m. UTC | #4
On 29/11/2016 20:38, Brijesh Singh wrote:
> 
> 
> On 11/29/2016 12:20 PM, Thomas Gleixner wrote:
>> On Tue, 29 Nov 2016, Brijesh Singh wrote:
>>> --- a/arch/x86/kvm/emulate.c
>>> +++ b/arch/x86/kvm/emulate.c
>>> @@ -5483,3 +5483,11 @@ void emulator_writeback_register_cache(struct
>>> x86_emulate_ctxt *ctxt)
>>>  {
>>>      writeback_registers(ctxt);
>>>  }
>>> +
>>> +bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt)
>>> +{
>>> +    if (ctxt->d & String)
>>> +        return true;
>>> +
>>> +    return false;
>>> +}
>>
>> Do we really need a full function call for this simple thing? Just
>> because
>> this horrible CamelCase constant is in emulate.c?
>>
>> What's wrong with moving that thing into a header and make it a trivial
>> inline:
>>
>> #define INS_STRING        (1 << 13)
>>
>> static inline bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt)
>> {
>>     return ctxt->d & INS_STRING;
>> }
>>
>> Hmm?
> 
> One of the recommendation from previous review feedback was to move the
> check inside emulator.c. I am fine with inlining it into kvm_emulate.h
> 
> Hi Paolo,
> 
> Do you want me to spin a new version ?

No, it's not that much of a fast path, so it wouldn't change anything in
practice.

Paolo
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index e9cd7be..777eea2 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -441,5 +441,6 @@  int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq);
 void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt);
 void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt);
+bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt);
 
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 77cb3f9..fd5b1c8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -668,6 +668,9 @@  struct kvm_vcpu_arch {
 
 	int pending_ioapic_eoi;
 	int pending_external_vector;
+
+	/* GPA available (AMD only) */
+	bool gpa_available;
 };
 
 struct kvm_lpage_info {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a3ce9d2..0ea543e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5483,3 +5483,11 @@  void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt)
 {
 	writeback_registers(ctxt);
 }
+
+bool emulator_is_string_op(struct x86_emulate_ctxt *ctxt)
+{
+	if (ctxt->d & String)
+		return true;
+
+	return false;
+}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 5e64e656..e9b3555 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -4188,6 +4188,8 @@  static int handle_exit(struct kvm_vcpu *vcpu)
 
 	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
 
+	vcpu->arch.gpa_available = (exit_code == SVM_EXIT_NPF);
+
 	if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE))
 		vcpu->arch.cr0 = svm->vmcb->save.cr0;
 	if (npt_enabled)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c30f62dc..507c75c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4420,6 +4420,21 @@  int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
 
+static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
+			    gpa_t gpa, bool write)
+{
+	/* For APIC access vmexit */
+	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
+		return 1;
+
+	if (vcpu_match_mmio_gpa(vcpu, gpa)) {
+		trace_vcpu_match_mmio(gva, gpa, write, true);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
 				gpa_t *gpa, struct x86_exception *exception,
 				bool write)
@@ -4446,16 +4461,7 @@  static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
 	if (*gpa == UNMAPPED_GVA)
 		return -1;
 
-	/* For APIC access vmexit */
-	if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
-		return 1;
-
-	if (vcpu_match_mmio_gpa(vcpu, *gpa)) {
-		trace_vcpu_match_mmio(gva, *gpa, write, true);
-		return 1;
-	}
-
-	return 0;
+	return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write);
 }
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
@@ -4552,6 +4558,21 @@  static int emulator_read_write_onepage(unsigned long addr, void *val,
 	int handled, ret;
 	bool write = ops->write;
 	struct kvm_mmio_fragment *frag;
+	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+
+	/*
+	 * If the exit was due to a NPF we may already have a GPA.
+	 * If the GPA is present, use it to avoid the GVA to GPA table walk.
+	 * Note, this cannot be used on string operations since string
+	 * operation using rep will only have the initial GPA from the NPF
+	 * occurred.
+	 */
+	if (vcpu->arch.gpa_available &&
+	    !emulator_is_string_op(ctxt) &&
+	    vcpu_is_mmio_gpa(vcpu, addr, exception->address, write)) {
+		gpa = exception->address;
+		goto mmio;
+	}
 
 	ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
 
@@ -5563,6 +5584,9 @@  int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 	}
 
 restart:
+	/* Save the faulting GPA (cr2) in the address field */
+	ctxt->exception.address = cr2;
+
 	r = x86_emulate_insn(ctxt);
 
 	if (r == EMULATION_INTERCEPTED)