[PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
model when the AMD ZEN based host supports it. This change makes it recognize
this CPUID for guests which use EPYC or EPYC-IBPB CPU model.

Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
---
 target/i386/cpu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 69f518a..55f0691 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
             CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
             CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
             CPUID_EXT3_TOPOEXT,
+        .features[FEAT_8000_0008_EBX] =
+            CPUID_8000_0008_EBX_CLZERO,
         .features[FEAT_7_0_EBX] =
             CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
             CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
-- 
1.9.4

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Paolo Bonzini]

On 18/12/19 10:05, Ani Sinha wrote:
> CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
> model when the AMD ZEN based host supports it. This change makes it recognize
> this CPUID for guests which use EPYC or EPYC-IBPB CPU model.
> 
> Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
> ---
>  target/i386/cpu.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> index 69f518a..55f0691 100644
> --- a/target/i386/cpu.c
> +++ b/target/i386/cpu.c
> @@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
>              CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
>              CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
>              CPUID_EXT3_TOPOEXT,
> +        .features[FEAT_8000_0008_EBX] =
> +            CPUID_8000_0008_EBX_CLZERO,
>          .features[FEAT_7_0_EBX] =
>              CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
>              CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
> 

This needs to be done only for newer machine type (or is it CPU model
versions now? need Eduardo to respond).

Paolo

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Eduardo Habkost]

On Wed, Dec 18, 2019 at 12:53:45PM +0100, Paolo Bonzini wrote:
> On 18/12/19 10:05, Ani Sinha wrote:
> > CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
> > model when the AMD ZEN based host supports it. This change makes it recognize
> > this CPUID for guests which use EPYC or EPYC-IBPB CPU model.

Can you clarify what's the intended use case here?  Why the
"if host supports it" conditional?

If you need host-dependent CPU configuration, "-cpu host" (or the
libvirt "host-model" mode) is the most appropriate solution.

> > 
> > Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
> > ---
> >  target/i386/cpu.c | 2 ++
> >  1 file changed, 2 insertions(+)
> > 
> > diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> > index 69f518a..55f0691 100644
> > --- a/target/i386/cpu.c
> > +++ b/target/i386/cpu.c
> > @@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
> >              CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
> >              CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
> >              CPUID_EXT3_TOPOEXT,
> > +        .features[FEAT_8000_0008_EBX] =
> > +            CPUID_8000_0008_EBX_CLZERO,
> >          .features[FEAT_7_0_EBX] =
> >              CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
> >              CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
> > 
> 
> This needs to be done only for newer machine type (or is it CPU model
> versions now? need Eduardo to respond).

If we want to add it, it has to be done as a new CPU model version.

But I don't know yet if we want to add it.  Do all EPYC CPUs have
CLZERO available?  If not, it's probably not advisable to add it
to EPYC (even if it's just on EPYC-v3).

-- 
Eduardo

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

Ping …

> On Dec 18, 2019, at 5:23 PM, Paolo Bonzini <pbonzini@redhat.com> wrote:
> 
> On 18/12/19 10:05, Ani Sinha wrote:
>> CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
>> model when the AMD ZEN based host supports it. This change makes it recognize
>> this CPUID for guests which use EPYC or EPYC-IBPB CPU model.
>> 
>> Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
>> ---
>> target/i386/cpu.c | 2 ++
>> 1 file changed, 2 insertions(+)
>> 
>> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
>> index 69f518a..55f0691 100644
>> --- a/target/i386/cpu.c
>> +++ b/target/i386/cpu.c
>> @@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
>>             CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
>>             CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
>>             CPUID_EXT3_TOPOEXT,
>> +        .features[FEAT_8000_0008_EBX] =
>> +            CPUID_8000_0008_EBX_CLZERO,
>>         .features[FEAT_7_0_EBX] =
>>             CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
>>             CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
>> 
> 
> This needs to be done only for newer machine type (or is it CPU model
> versions now? need Eduardo to respond).
> 
> Paolo

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Paolo Bonzini]

[-- Attachment #1: Type: text/plain, Size: 1624 bytes --]

Il dom 22 dic 2019, 08:49 Ani Sinha <ani.sinha@nutanix.com> ha scritto:

>
> Ping …
>

Why ping? You got questions from Eduardo, so you need to answer them and/or
send a fixed version of the patch.

Thanks,

Paolo


> > On Dec 18, 2019, at 5:23 PM, Paolo Bonzini <pbonzini@redhat.com> wrote:
> >
> > On 18/12/19 10:05, Ani Sinha wrote:
> >> CLZERO CPUID should be passed on to the guests that use EPYC or
> EPYC-IBPB CPU
> >> model when the AMD ZEN based host supports it. This change makes it
> recognize
> >> this CPUID for guests which use EPYC or EPYC-IBPB CPU model.
> >>
> >> Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
> >> ---
> >> target/i386/cpu.c | 2 ++
> >> 1 file changed, 2 insertions(+)
> >>
> >> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> >> index 69f518a..55f0691 100644
> >> --- a/target/i386/cpu.c
> >> +++ b/target/i386/cpu.c
> >> @@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
> >>             CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
> >>             CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
> >>             CPUID_EXT3_TOPOEXT,
> >> +        .features[FEAT_8000_0008_EBX] =
> >> +            CPUID_8000_0008_EBX_CLZERO,
> >>         .features[FEAT_7_0_EBX] =
> >>             CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 |
> CPUID_7_0_EBX_AVX2 |
> >>             CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 |
> CPUID_7_0_EBX_RDSEED |
> >>
> >
> > This needs to be done only for newer machine type (or is it CPU model
> > versions now? need Eduardo to respond).
> >
> > Paolo
>
>

[-- Attachment #2: Type: text/html, Size: 2661 bytes --]

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

> On Dec 22, 2019, at 1:45 PM, Paolo Bonzini <pbonzini@redhat.com> wrote:
> 
> 
> 
> Il dom 22 dic 2019, 08:49 Ani Sinha <ani.sinha@nutanix.com> ha scritto:
> 
> Ping …
> 
> Why ping? You got questions from Eduardo, so you need to answer them and/or send a fixed version of the patch.
> 


Maybe he responded privately but I did not get any questions from Eduardo.

Ani


> Thanks,
> 
> Paolo
> 
> 
> > On Dec 18, 2019, at 5:23 PM, Paolo Bonzini <pbonzini@redhat.com> wrote:
> > 
> > On 18/12/19 10:05, Ani Sinha wrote:
> >> CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
> >> model when the AMD ZEN based host supports it. This change makes it recognize
> >> this CPUID for guests which use EPYC or EPYC-IBPB CPU model.
> >> 
> >> Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
> >> ---
> >> target/i386/cpu.c | 2 ++
> >> 1 file changed, 2 insertions(+)
> >> 
> >> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> >> index 69f518a..55f0691 100644
> >> --- a/target/i386/cpu.c
> >> +++ b/target/i386/cpu.c
> >> @@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
> >>             CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
> >>             CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
> >>             CPUID_EXT3_TOPOEXT,
> >> +        .features[FEAT_8000_0008_EBX] =
> >> +            CPUID_8000_0008_EBX_CLZERO,
> >>         .features[FEAT_7_0_EBX] =
> >>             CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
> >>             CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
> >> 
> > 
> > This needs to be done only for newer machine type (or is it CPU model
> > versions now? need Eduardo to respond).
> > 
> > Paolo
> 

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

> On Dec 23, 2019, at 1:44 PM, Ani Sinha <ani.sinha@nutanix.com> wrote:
> 
> 
> 
>> On Dec 22, 2019, at 1:45 PM, Paolo Bonzini <pbonzini@redhat.com> wrote:
>> 
>> 
>> 
>> Il dom 22 dic 2019, 08:49 Ani Sinha <ani.sinha@nutanix.com> ha scritto:
>> 
>> Ping …
>> 
>> Why ping? You got questions from Eduardo, so you need to answer them and/or send a fixed version of the patch.
>> 
> 
> 
> Maybe he responded privately but I did not get any questions from Eduardo.
> 

Ok I see his response in the mailing list archives:
https://lists.gnu.org/archive/html/qemu-devel/2019-12/msg03927.html

I generally do not pay attention to emails sent to @qemu-dev and they arrive as a digest and get filtered out. So please do send the responses with me in the CC or To list. That way, I won’t miss them.

thanks
ani
 

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

Sorry Eduardo, it took a little while for me to get to this thread again.

> On Dec 18, 2019, at 8:41 PM, Eduardo Habkost <ehabkost@redhat.com> wrote:
> 
> On Wed, Dec 18, 2019 at 12:53:45PM +0100, Paolo Bonzini wrote:
>> On 18/12/19 10:05, Ani Sinha wrote:
>>> CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
>>> model when the AMD ZEN based host supports it. This change makes it recognize
>>> this CPUID for guests which use EPYC or EPYC-IBPB CPU model.
> 
> Can you clarify what's the intended use case here?  Why the
> "if host supports it" conditional?

Looking at https://www.amd.com/system/files/TechDocs/24594.pdf , it says :

"The CLZERO instruction is supported if the feature flag CPUID Fn8000_0008_EBX[CLZERO] is set.”

This I interpreted to mean that not all AMD Zen architectures supports it. So when the host does support it, this CPUID should be passed on to the guest as well.


> 
> If you need host-dependent CPU configuration, "-cpu host" (or the
> libvirt "host-model" mode) is the most appropriate solution.

Yes that is an option but we are going to use EPYC-IBPB model for now. 


> 
>>> 
>>> Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
>>> ---
>>> target/i386/cpu.c | 2 ++
>>> 1 file changed, 2 insertions(+)
>>> 
>>> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
>>> index 69f518a..55f0691 100644
>>> --- a/target/i386/cpu.c
>>> +++ b/target/i386/cpu.c
>>> @@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
>>>             CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
>>>             CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
>>>             CPUID_EXT3_TOPOEXT,
>>> +        .features[FEAT_8000_0008_EBX] =
>>> +            CPUID_8000_0008_EBX_CLZERO,
>>>         .features[FEAT_7_0_EBX] =
>>>             CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
>>>             CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
>>> 
>> 
>> This needs to be done only for newer machine type (or is it CPU model
>> versions now? need Eduardo to respond).
> 
> If we want to add it, it has to be done as a new CPU model version.

I see what you mean. 

> 
> But I don't know yet if we want to add it.  Do all EPYC CPUs have
> CLZERO available?  If not, it's probably not advisable to add it
> to EPYC (even if it's just on EPYC-v3).

Ok so I think we need to get this clarified from AMD if all their EPYC platforms supports this CPUID or not. Is there any contact point within AMD where we can get this information?

For our use case, I just verified that even without this patch, if we pass CLZERO through libvirt CPU definition xml, like " <feature policy='require' name='clzero’/>”, it gets passed on to the guest. So this patch is not super critical for us.

Thanks,
Ani


> 
> -- 
> Eduardo

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Eduardo Habkost]

Hi,

Sorry for the delayed reply.  I was away from work for the whole
month of January.

On Mon, Jan 20, 2020 at 10:56:43AM +0000, Ani Sinha wrote:
> Sorry Eduardo, it took a little while for me to get to this thread again.
> 
> > On Dec 18, 2019, at 8:41 PM, Eduardo Habkost <ehabkost@redhat.com> wrote:
> > 
> > On Wed, Dec 18, 2019 at 12:53:45PM +0100, Paolo Bonzini wrote:
> >> On 18/12/19 10:05, Ani Sinha wrote:
> >>> CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
> >>> model when the AMD ZEN based host supports it. This change makes it recognize
> >>> this CPUID for guests which use EPYC or EPYC-IBPB CPU model.
> > 
> > Can you clarify what's the intended use case here?  Why the
> > "if host supports it" conditional?
> 
> Looking at https://www.amd.com/system/files/TechDocs/24594.pdf , it says :
> 
> "The CLZERO instruction is supported if the feature flag CPUID Fn8000_0008_EBX[CLZERO] is set.”
> 
> This I interpreted to mean that not all AMD Zen architectures
> supports it. So when the host does support it, this CPUID
> should be passed on to the guest as well.

This is not a supported use case of named CPU models.  Named CPU
models should expose the same guest ABI on all hosts.  This means
CPUID should be the same on all hosts if using the same CPU
model (and same machine type).

If you need features to be automatically enabled/disabled
depending on host capabilities, I advise you to use "-cpu host"
or libvirt's mode=host-model.

> 
> 
> > 
> > If you need host-dependent CPU configuration, "-cpu host" (or the
> > libvirt "host-model" mode) is the most appropriate solution.
> 
> Yes that is an option but we are going to use EPYC-IBPB model for now. 
> 
> 
> > 
> >>> 
> >>> Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
> >>> ---
> >>> target/i386/cpu.c | 2 ++
> >>> 1 file changed, 2 insertions(+)
> >>> 
> >>> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> >>> index 69f518a..55f0691 100644
> >>> --- a/target/i386/cpu.c
> >>> +++ b/target/i386/cpu.c
> >>> @@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
> >>>             CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
> >>>             CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
> >>>             CPUID_EXT3_TOPOEXT,
> >>> +        .features[FEAT_8000_0008_EBX] =
> >>> +            CPUID_8000_0008_EBX_CLZERO,
> >>>         .features[FEAT_7_0_EBX] =
> >>>             CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
> >>>             CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
> >>> 
> >> 
> >> This needs to be done only for newer machine type (or is it CPU model
> >> versions now? need Eduardo to respond).
> > 
> > If we want to add it, it has to be done as a new CPU model version.
> 
> I see what you mean. 
> 
> > 
> > But I don't know yet if we want to add it.  Do all EPYC CPUs have
> > CLZERO available?  If not, it's probably not advisable to add it
> > to EPYC (even if it's just on EPYC-v3).
> 
> Ok so I think we need to get this clarified from AMD if all
> their EPYC platforms supports this CPUID or not. Is there any
> contact point within AMD where we can get this information?

I'm CCing Brijesh Singh and Babu Moger, who works on the EPYC CPU
model recently.

> 
> For our use case, I just verified that even without this patch,
> if we pass CLZERO through libvirt CPU definition xml, like "
> <feature policy='require' name='clzero’/>”, it gets passed on
> to the guest. So this patch is not super critical for us.

Note that this is done automatically by libvirt if using
mode=host-model.

-- 
Eduardo

RE: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Moger, Babu]

[AMD Official Use Only - Internal Distribution Only]

> -----Original Message-----
> From: Eduardo Habkost <ehabkost@redhat.com>
> Sent: Wednesday, February 5, 2020 4:38 PM
> To: Ani Sinha <ani.sinha@nutanix.com>
> Cc: Paolo Bonzini <pbonzini@redhat.com>; rth@twiddle.net; qemu-
> devel@nongnu.org; Singh, Brijesh <brijesh.singh@amd.com>; Moger, Babu
> <Babu.Moger@amd.com>
> Subject: Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on
> AMD ZEN platform
> 
> Hi,
> 
> Sorry for the delayed reply.  I was away from work for the whole
> month of January.
> 
> On Mon, Jan 20, 2020 at 10:56:43AM +0000, Ani Sinha wrote:
> > Sorry Eduardo, it took a little while for me to get to this thread again.
> >
> > > On Dec 18, 2019, at 8:41 PM, Eduardo Habkost <ehabkost@redhat.com>
> wrote:
> > >
> > > On Wed, Dec 18, 2019 at 12:53:45PM +0100, Paolo Bonzini wrote:
> > >> On 18/12/19 10:05, Ani Sinha wrote:
> > >>> CLZERO CPUID should be passed on to the guests that use EPYC or
> EPYC-IBPB CPU
> > >>> model when the AMD ZEN based host supports it. This change makes it
> recognize
> > >>> this CPUID for guests which use EPYC or EPYC-IBPB CPU model.
> > >
> > > Can you clarify what's the intended use case here?  Why the
> > > "if host supports it" conditional?
> >
> > Looking at
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fww
> w.amd.com%2Fsystem%2Ffiles%2FTechDocs%2F24594.pdf&amp;data=02%7
> C01%7Cbabu.moger%40amd.com%7C4d00819020cb4892d50608d7aa8c016b%
> 7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637165391335697450
> &amp;sdata=3%2FFGZeeZoz387eeayAbjQJj9qGhemgw0xC0byr%2F0YJk%3D
> &amp;reserved=0 , it says :
> >
> > "The CLZERO instruction is supported if the feature flag CPUID
> Fn8000_0008_EBX[CLZERO] is set.”
> >
> > This I interpreted to mean that not all AMD Zen architectures
> > supports it. So when the host does support it, this CPUID
> > should be passed on to the guest as well.
> 
> This is not a supported use case of named CPU models.  Named CPU
> models should expose the same guest ABI on all hosts.  This means
> CPUID should be the same on all hosts if using the same CPU
> model (and same machine type).
> 
> If you need features to be automatically enabled/disabled
> depending on host capabilities, I advise you to use "-cpu host"
> or libvirt's mode=host-model.
> 
> >
> >
> > >
> > > If you need host-dependent CPU configuration, "-cpu host" (or the
> > > libvirt "host-model" mode) is the most appropriate solution.
> >
> > Yes that is an option but we are going to use EPYC-IBPB model for now.
> >
> >
> > >
> > >>>
> > >>> Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
> > >>> ---
> > >>> target/i386/cpu.c | 2 ++
> > >>> 1 file changed, 2 insertions(+)
> > >>>
> > >>> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> > >>> index 69f518a..55f0691 100644
> > >>> --- a/target/i386/cpu.c
> > >>> +++ b/target/i386/cpu.c
> > >>> @@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
> > >>>             CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A |
> CPUID_EXT3_ABM |
> > >>>             CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM |
> CPUID_EXT3_LAHF_LM |
> > >>>             CPUID_EXT3_TOPOEXT,
> > >>> +        .features[FEAT_8000_0008_EBX] =
> > >>> +            CPUID_8000_0008_EBX_CLZERO,
> > >>>         .features[FEAT_7_0_EBX] =
> > >>>             CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 |
> CPUID_7_0_EBX_AVX2 |
> > >>>             CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 |
> CPUID_7_0_EBX_RDSEED |
> > >>>
> > >>
> > >> This needs to be done only for newer machine type (or is it CPU model
> > >> versions now? need Eduardo to respond).
> > >
> > > If we want to add it, it has to be done as a new CPU model version.
> >
> > I see what you mean.
> >
> > >
> > > But I don't know yet if we want to add it.  Do all EPYC CPUs have
> > > CLZERO available?  If not, it's probably not advisable to add it
> > > to EPYC (even if it's just on EPYC-v3).
> >
> > Ok so I think we need to get this clarified from AMD if all
> > their EPYC platforms supports this CPUID or not. Is there any
> > contact point within AMD where we can get this information?
> 
> I'm CCing Brijesh Singh and Babu Moger, who works on the EPYC CPU
> model recently.

Ani, I am already working on it.

Eduardo,  I am still waiting for your feedback on this series.
https://lore.kernel.org/qemu-devel/abd39b75-0a12-5198-5815-dd51a3d5c901@amd.com/

I have added all the missing feature bits for EPYC models(as EPYC-v3) and also added EPYC-Rome model.

> 
> >
> > For our use case, I just verified that even without this patch,
> > if we pass CLZERO through libvirt CPU definition xml, like "
> > <feature policy='require' name='clzero’/>”, it gets passed on
> > to the guest. So this patch is not super critical for us.
> 
> Note that this is done automatically by libvirt if using
> mode=host-model.
> 
> --
> Eduardo

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

> On Feb 6, 2020, at 5:30 AM, Moger, Babu <Babu.Moger@amd.com> wrote:
> 
> Ani, I am already working on it.

Wow, I see a whole new AMD-Rome CPU model with it’s own cache info data : 

https://lore.kernel.org/qemu-devel/157314966312.23828.17684821666338093910.stgit@naples-babu.amd.com/

Thanks!

ani

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

> On Feb 6, 2020, at 11:16 AM, Ani Sinha <ani.sinha@nutanix.com> wrote:
> 
> 
> 
>> On Feb 6, 2020, at 5:30 AM, Moger, Babu <Babu.Moger@amd.com> wrote:
>> 
>> Ani, I am already working on it.
> 
> Wow, I see a whole new AMD-Rome CPU model with it’s own cache info data : 
> 
> https://lore.kernel.org/qemu-devel/157314966312.23828.17684821666338093910.stgit@naples-babu.amd.com/

Do you think the ROME specific guest cpu cache data will have significant impact on performance?

> 
> Thanks!
> 
> ani
> 

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Babu Moger]

On 2/5/20 11:53 PM, Ani Sinha wrote:
> 
> 
>> On Feb 6, 2020, at 11:16 AM, Ani Sinha <ani.sinha@nutanix.com> wrote:
>>
>>
>>
>>> On Feb 6, 2020, at 5:30 AM, Moger, Babu <Babu.Moger@amd.com> wrote:
>>>
>>> Ani, I am already working on it.
>>
>> Wow, I see a whole new AMD-Rome CPU model with it’s own cache info data : 
>>
>> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flore.kernel.org%2Fqemu-devel%2F157314966312.23828.17684821666338093910.stgit%40naples-babu.amd.com%2F&amp;data=02%7C01%7CBabu.Moger%40amd.com%7Cc566dc5cf3cc407b5ee608d7aac8d9bc%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637165651955089264&amp;sdata=tlafWD6m5%2BZ12cqd4vqJcWh0%2FIgly%2FPVMgAbjxK5Mog%3D&amp;reserved=0
> 
> Do you think the ROME specific guest cpu cache data will have significant impact on performance?

I have not done performance benchmarks myself. Yes. Rome is expected to
perform better than its previous generations.

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Eduardo Habkost]

On Thu, Feb 06, 2020 at 12:00:04AM +0000, Moger, Babu wrote:
> [AMD Official Use Only - Internal Distribution Only]

Considering that this was posted to qemu-devel, I'm assuming this
notice was added by accident.

> 
[...]
> Eduardo,  I am still waiting for your feedback on this series.
> https://lore.kernel.org/qemu-devel/abd39b75-0a12-5198-5815-dd51a3d5c901@amd.com/
> 
> I have added all the missing feature bits for EPYC models(as
> EPYC-v3) and also added EPYC-Rome model.

I'm still catching up on email and my review queue, but this is
on my list.  Sorry for the long delay!

-- 
Eduardo

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Babu Moger]

On 2/6/20 9:52 AM, Eduardo Habkost wrote:
> On Thu, Feb 06, 2020 at 12:00:04AM +0000, Moger, Babu wrote:
>> [AMD Official Use Only - Internal Distribution Only]
> 
> Considering that this was posted to qemu-devel, I'm assuming this
> notice was added by accident.

Yes. I noticed that after sending out the email. Please ignore that line.

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Eduardo Habkost]

On Thu, Feb 06, 2020 at 09:30:11AM -0600, Babu Moger wrote:
> 
> 
> On 2/5/20 11:53 PM, Ani Sinha wrote:
> > 
> > 
> >> On Feb 6, 2020, at 11:16 AM, Ani Sinha <ani.sinha@nutanix.com> wrote:
> >>
> >>
> >>
> >>> On Feb 6, 2020, at 5:30 AM, Moger, Babu <Babu.Moger@amd.com> wrote:
> >>>
> >>> Ani, I am already working on it.
> >>
> >> Wow, I see a whole new AMD-Rome CPU model with it’s own cache info data : 
> >>
> >> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flore.kernel.org%2Fqemu-devel%2F157314966312.23828.17684821666338093910.stgit%40naples-babu.amd.com%2F&amp;data=02%7C01%7CBabu.Moger%40amd.com%7Cc566dc5cf3cc407b5ee608d7aac8d9bc%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637165651955089264&amp;sdata=tlafWD6m5%2BZ12cqd4vqJcWh0%2FIgly%2FPVMgAbjxK5Mog%3D&amp;reserved=0
> > 
> > Do you think the ROME specific guest cpu cache data will have significant impact on performance?
> 
> I have not done performance benchmarks myself. Yes. Rome is expected to
> perform better than its previous generations.

Note that virtual cache information on CPUID doesn't affect host
software or hardware behavior in any way.  In the exceptional
cases it affects performance, it's solely because guest software
behavior changed depending on the cache information it sees.

-- 
Eduardo

Re: [PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

[-- Attachment #1: Type: text/plain, Size: 1059 bytes --]

Hi :

Can I get some love for this patch?

thanks
ani

On Dec 4, 2019, 3:06 PM +0530, Ani Sinha <ani.sinha@nutanix.com>, wrote:
CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
model when the AMD ZEN based host supports it. This change makes it recognize
this CPUID for guests which use EPYC or EPYC-IBPB CPU model.

Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
---
target/i386/cpu.c | 2 ++
1 file changed, 2 insertions(+)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 69f518a..55f0691 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
CPUID_EXT3_TOPOEXT,
+ .features[FEAT_8000_0008_EBX] =
+ CPUID_8000_0008_EBX_CLZERO,
.features[FEAT_7_0_EBX] =
CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
--
1.9.4


[-- Attachment #2: Type: text/html, Size: 1858 bytes --]

[PATCH] i386: pass CLZERO to guests with EPYC CPU model on AMD ZEN platform

[Ani Sinha]

CLZERO CPUID should be passed on to the guests that use EPYC or EPYC-IBPB CPU
model when the AMD ZEN based host supports it. This change makes it recognize
this CPUID for guests which use EPYC or EPYC-IBPB CPU model.

Signed-off-by: Ani Sinha <ani.sinha@nutanix.com>
---
 target/i386/cpu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 69f518a..55f0691 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -3813,6 +3813,8 @@ static X86CPUDefinition builtin_x86_defs[] = {
             CPUID_EXT3_MISALIGNSSE | CPUID_EXT3_SSE4A | CPUID_EXT3_ABM |
             CPUID_EXT3_CR8LEG | CPUID_EXT3_SVM | CPUID_EXT3_LAHF_LM |
             CPUID_EXT3_TOPOEXT,
+        .features[FEAT_8000_0008_EBX] =
+            CPUID_8000_0008_EBX_CLZERO,
         .features[FEAT_7_0_EBX] =
             CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 |
             CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED |
-- 
1.9.4