On Thu, 2012-09-20 at 12:50 +0300, Avi Kivity wrote:
> On 09/20/2012 03:10 AM, Suresh Siddha wrote:
> > diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> > index b06737d..8ff328b 100644
> > --- a/arch/x86/kvm/vmx.c
> > +++ b/arch/x86/kvm/vmx.c
> > @@ -1493,7 +1493,8 @@ static void
On 09/20/2012 03:10 AM, Suresh Siddha wrote:
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index b06737d..8ff328b 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -1493,7 +1493,8 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
> #ifdef CONFIG_X86_64
>
On 09/19/2012 08:26 PM, H. Peter Anvin wrote:
> On 09/19/2012 10:22 AM, Avi Kivity wrote:
>>
>> Note, we could also go in a different direction and make
>> kernel_fpu_begin() use preempt notifiers and thus make its users
>> preemptible. But that's for a separate patchset.
>>
>
> Where would
On 09/19/2012 08:25 PM, Suresh Siddha wrote:
> On Wed, 2012-09-19 at 20:22 +0300, Avi Kivity wrote:
>> On 09/19/2012 08:18 PM, Suresh Siddha wrote:
>>
>> > These routines (kvm_load/put_guest_fpu()) are already called with
>> > preemption disabled but as you mentioned, we don't want the preemption
On 09/19/2012 08:25 PM, Suresh Siddha wrote:
On Wed, 2012-09-19 at 20:22 +0300, Avi Kivity wrote:
On 09/19/2012 08:18 PM, Suresh Siddha wrote:
These routines (kvm_load/put_guest_fpu()) are already called with
preemption disabled but as you mentioned, we don't want the preemption
to be
On 09/19/2012 08:26 PM, H. Peter Anvin wrote:
On 09/19/2012 10:22 AM, Avi Kivity wrote:
Note, we could also go in a different direction and make
kernel_fpu_begin() use preempt notifiers and thus make its users
preemptible. But that's for a separate patchset.
Where would you put the
On 09/20/2012 03:10 AM, Suresh Siddha wrote:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b06737d..8ff328b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1493,7 +1493,8 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
#ifdef CONFIG_X86_64
On Thu, 2012-09-20 at 12:50 +0300, Avi Kivity wrote:
On 09/20/2012 03:10 AM, Suresh Siddha wrote:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b06737d..8ff328b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1493,7 +1493,8 @@ static void
On Wed, 2012-09-19 at 10:18 -0700, Suresh Siddha wrote:
> These routines (kvm_load/put_guest_fpu()) are already called with
> preemption disabled but as you mentioned, we don't want the preemption
> to be disabled completely between the kvm_load_guest_fpu() and
> kvm_put_guest_fpu().
>
> Also KVM
On 09/19/2012 10:22 AM, Avi Kivity wrote:
>
> Note, we could also go in a different direction and make
> kernel_fpu_begin() use preempt notifiers and thus make its users
> preemptible. But that's for a separate patchset.
>
Where would you put the state if you were preempted? You want to
On Wed, 2012-09-19 at 20:22 +0300, Avi Kivity wrote:
> On 09/19/2012 08:18 PM, Suresh Siddha wrote:
>
> > These routines (kvm_load/put_guest_fpu()) are already called with
> > preemption disabled but as you mentioned, we don't want the preemption
> > to be disabled completely between the
On 09/19/2012 08:18 PM, Suresh Siddha wrote:
> These routines (kvm_load/put_guest_fpu()) are already called with
> preemption disabled but as you mentioned, we don't want the preemption
> to be disabled completely between the kvm_load_guest_fpu() and
> kvm_put_guest_fpu().
>
> Also KVM already
On Wed, 2012-09-19 at 13:13 +0300, Avi Kivity wrote:
> On 08/25/2012 12:12 AM, Suresh Siddha wrote:
> > kvm's guest fpu save/restore should be wrapped around
> > kernel_fpu_begin/end(). This will avoid for example taking a DNA
> > in kvm_load_guest_fpu() when it tries to load the fpu immediately
>
On 08/25/2012 12:12 AM, Suresh Siddha wrote:
> kvm's guest fpu save/restore should be wrapped around
> kernel_fpu_begin/end(). This will avoid for example taking a DNA
> in kvm_load_guest_fpu() when it tries to load the fpu immediately
> after doing unlazy_fpu() on the host side.
>
> More
On 08/25/2012 12:12 AM, Suresh Siddha wrote:
kvm's guest fpu save/restore should be wrapped around
kernel_fpu_begin/end(). This will avoid for example taking a DNA
in kvm_load_guest_fpu() when it tries to load the fpu immediately
after doing unlazy_fpu() on the host side.
More importantly
On Wed, 2012-09-19 at 13:13 +0300, Avi Kivity wrote:
On 08/25/2012 12:12 AM, Suresh Siddha wrote:
kvm's guest fpu save/restore should be wrapped around
kernel_fpu_begin/end(). This will avoid for example taking a DNA
in kvm_load_guest_fpu() when it tries to load the fpu immediately
after
On 09/19/2012 08:18 PM, Suresh Siddha wrote:
These routines (kvm_load/put_guest_fpu()) are already called with
preemption disabled but as you mentioned, we don't want the preemption
to be disabled completely between the kvm_load_guest_fpu() and
kvm_put_guest_fpu().
Also KVM already has the
On Wed, 2012-09-19 at 20:22 +0300, Avi Kivity wrote:
On 09/19/2012 08:18 PM, Suresh Siddha wrote:
These routines (kvm_load/put_guest_fpu()) are already called with
preemption disabled but as you mentioned, we don't want the preemption
to be disabled completely between the
On 09/19/2012 10:22 AM, Avi Kivity wrote:
Note, we could also go in a different direction and make
kernel_fpu_begin() use preempt notifiers and thus make its users
preemptible. But that's for a separate patchset.
Where would you put the state if you were preempted? You want to
allocate a
On Wed, 2012-09-19 at 10:18 -0700, Suresh Siddha wrote:
These routines (kvm_load/put_guest_fpu()) are already called with
preemption disabled but as you mentioned, we don't want the preemption
to be disabled completely between the kvm_load_guest_fpu() and
kvm_put_guest_fpu().
Also KVM
kvm's guest fpu save/restore should be wrapped around
kernel_fpu_begin/end(). This will avoid for example taking a DNA
in kvm_load_guest_fpu() when it tries to load the fpu immediately
after doing unlazy_fpu() on the host side.
More importantly this will prevent the host process fpu from being
kvm's guest fpu save/restore should be wrapped around
kernel_fpu_begin/end(). This will avoid for example taking a DNA
in kvm_load_guest_fpu() when it tries to load the fpu immediately
after doing unlazy_fpu() on the host side.
More importantly this will prevent the host process fpu from being
22 matches
Mail list logo