Re: [RFC PATCH v1 02/28] kvm: svm: Add kvm_fast_pio_in support

[Borislav Petkov]

On Mon, Aug 22, 2016 at 07:23:54PM -0400, Brijesh Singh wrote:
> From: Tom Lendacky 
> 
> Update the I/O interception support to add the kvm_fast_pio_in function
> to speed up the in instruction similar to the out instruction.
> 
> Signed-off-by: Tom Lendacky 
> ---
>  arch/x86/include/asm/kvm_host.h |1 +
>  arch/x86/kvm/svm.c  |5 +++--
>  arch/x86/kvm/x86.c  |   43 
> +++
>  3 files changed, 47 insertions(+), 2 deletions(-)

FWIW: Reviewed-by: Borislav Petkov 

-- 
Regards/Gruss,
Boris.

SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard, Graham Norton, HRB 21284 
(AG Nürnberg)
-- 

Re: [RFC PATCH v1 02/28] kvm: svm: Add kvm_fast_pio_in support

[Borislav Petkov]

On Mon, Aug 22, 2016 at 07:23:54PM -0400, Brijesh Singh wrote:
> From: Tom Lendacky 
> 
> Update the I/O interception support to add the kvm_fast_pio_in function
> to speed up the in instruction similar to the out instruction.
> 
> Signed-off-by: Tom Lendacky 
> ---
>  arch/x86/include/asm/kvm_host.h |1 +
>  arch/x86/kvm/svm.c  |5 +++--
>  arch/x86/kvm/x86.c  |   43 
> +++
>  3 files changed, 47 insertions(+), 2 deletions(-)

FWIW: Reviewed-by: Borislav Petkov 

-- 
Regards/Gruss,
Boris.

SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard, Graham Norton, HRB 21284 
(AG Nürnberg)
-- 

[RFC PATCH v1 02/28] kvm: svm: Add kvm_fast_pio_in support

[Brijesh Singh]

From: Tom Lendacky 

Update the I/O interception support to add the kvm_fast_pio_in function
to speed up the in instruction similar to the out instruction.

Signed-off-by: Tom Lendacky 
---
 arch/x86/include/asm/kvm_host.h |1 +
 arch/x86/kvm/svm.c  |5 +++--
 arch/x86/kvm/x86.c  |   43 +++
 3 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3f05d36..c38f878 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1133,6 +1133,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data 
*msr);
 struct x86_emulate_ctxt;
 
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d8b9c8c..fd5a9a8 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2131,7 +2131,7 @@ static int io_interception(struct vcpu_svm *svm)
++svm->vcpu.stat.io_exits;
string = (io_info & SVM_IOIO_STR_MASK) != 0;
in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
-   if (string || in)
+   if (string)
return emulate_instruction(vcpu, 0) == EMULATE_DONE;
 
port = io_info >> 16;
@@ -2139,7 +2139,8 @@ static int io_interception(struct vcpu_svm *svm)
svm->next_rip = svm->vmcb->control.exit_info_2;
skip_emulated_instruction(>vcpu);
 
-   return kvm_fast_pio_out(vcpu, size, port);
+   return in ? kvm_fast_pio_in(vcpu, size, port)
+ : kvm_fast_pio_out(vcpu, size, port);
 }
 
 static int nmi_interception(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d432894..78295b0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5579,6 +5579,49 @@ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, 
unsigned short port)
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
+static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
+{
+   unsigned long val;
+
+   /* We should only ever be called with arch.pio.count equal to 1 */
+   BUG_ON(vcpu->arch.pio.count != 1);
+
+   /* For size less than 4 we merge, else we zero extend */
+   val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
+   : 0;
+
+   /*
+* Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform
+* the copy and tracing
+*/
+   emulator_pio_in_emulated(>arch.emulate_ctxt, vcpu->arch.pio.size,
+vcpu->arch.pio.port, , 1);
+   kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+
+   return 1;
+}
+
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port)
+{
+   unsigned long val;
+   int ret;
+
+   /* For size less than 4 we merge, else we zero extend */
+   val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0;
+
+   ret = emulator_pio_in_emulated(>arch.emulate_ctxt, size, port,
+  , 1);
+   if (ret) {
+   kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+   return ret;
+   }
+
+   vcpu->arch.complete_userspace_io = complete_fast_pio_in;
+
+   return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_fast_pio_in);
+
 static int kvmclock_cpu_down_prep(unsigned int cpu)
 {
__this_cpu_write(cpu_tsc_khz, 0);

[RFC PATCH v1 02/28] kvm: svm: Add kvm_fast_pio_in support

[Brijesh Singh]

From: Tom Lendacky 

Update the I/O interception support to add the kvm_fast_pio_in function
to speed up the in instruction similar to the out instruction.

Signed-off-by: Tom Lendacky 
---
 arch/x86/include/asm/kvm_host.h |1 +
 arch/x86/kvm/svm.c  |5 +++--
 arch/x86/kvm/x86.c  |   43 +++
 3 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3f05d36..c38f878 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1133,6 +1133,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data 
*msr);
 struct x86_emulate_ctxt;
 
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d8b9c8c..fd5a9a8 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2131,7 +2131,7 @@ static int io_interception(struct vcpu_svm *svm)
++svm->vcpu.stat.io_exits;
string = (io_info & SVM_IOIO_STR_MASK) != 0;
in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
-   if (string || in)
+   if (string)
return emulate_instruction(vcpu, 0) == EMULATE_DONE;
 
port = io_info >> 16;
@@ -2139,7 +2139,8 @@ static int io_interception(struct vcpu_svm *svm)
svm->next_rip = svm->vmcb->control.exit_info_2;
skip_emulated_instruction(>vcpu);
 
-   return kvm_fast_pio_out(vcpu, size, port);
+   return in ? kvm_fast_pio_in(vcpu, size, port)
+ : kvm_fast_pio_out(vcpu, size, port);
 }
 
 static int nmi_interception(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d432894..78295b0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5579,6 +5579,49 @@ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, 
unsigned short port)
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
+static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
+{
+   unsigned long val;
+
+   /* We should only ever be called with arch.pio.count equal to 1 */
+   BUG_ON(vcpu->arch.pio.count != 1);
+
+   /* For size less than 4 we merge, else we zero extend */
+   val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
+   : 0;
+
+   /*
+* Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform
+* the copy and tracing
+*/
+   emulator_pio_in_emulated(>arch.emulate_ctxt, vcpu->arch.pio.size,
+vcpu->arch.pio.port, , 1);
+   kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+
+   return 1;
+}
+
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port)
+{
+   unsigned long val;
+   int ret;
+
+   /* For size less than 4 we merge, else we zero extend */
+   val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0;
+
+   ret = emulator_pio_in_emulated(>arch.emulate_ctxt, size, port,
+  , 1);
+   if (ret) {
+   kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+   return ret;
+   }
+
+   vcpu->arch.complete_userspace_io = complete_fast_pio_in;
+
+   return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_fast_pio_in);
+
 static int kvmclock_cpu_down_prep(unsigned int cpu)
 {
__this_cpu_write(cpu_tsc_khz, 0);