diff mbox series

[V2,7/9] perf/x86/msr: Add Meteor Lake support

Message ID	20230104201349.1451191-7-kan.liang@linux.intel.com
State	New
Headers	Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20; From: kan.liang@linux.intel.com To: peterz@infradead.org, mingo@redhat.com, acme@kernel.org, linux-kernel@vger.kernel.org Cc: ak@linux.intel.com, eranian@google.com, irogers@google.com, Kan Liang <kan.liang@linux.intel.com> Subject: [PATCH V2 7/9] perf/x86/msr: Add Meteor Lake support Date: Wed, 4 Jan 2023 12:13:47 -0800 Message-Id: <20230104201349.1451191-7-kan.liang@linux.intel.com> In-Reply-To: <20230104201349.1451191-1-kan.liang@linux.intel.com> References: <20230104201349.1451191-1-kan.liang@linux.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk
Series	[V2,1/9] perf: Add PMU_FORMAT_ATTR_SHOW \| [V2,1/9] perf: Add PMU_FORMAT_ATTR_SHOW [V2,2/9] perf/x86: Add Meteor Lake support [V2,3/9] perf/x86: Support Retire Latency [V2,4/9] x86/cpufeatures: Add Architectural PerfMon Extension bit [V2,5/9] perf/x86/intel: Support Architectural PerfMon Extension leaf [V2,6/9] perf/x86/cstate: Add Meteor Lake support [V2,7/9] perf/x86/msr: Add Meteor Lake support [V2,8/9] perf report: Support Retire Latency [V2,9/9] perf script: Support Retire Latency

Commit Message

Liang, Kan Jan. 4, 2023, 8:13 p.m. UTC

  From: Kan Liang <kan.liang@linux.intel.com>

Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
are also supported.

Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---

No change since V1

 arch/x86/events/msr.c | 2 ++
 1 file changed, 2 insertions(+)

Comments

Arnaldo Carvalho de Melo Feb. 2, 2023, 1:47 a.m. UTC | #1

Em Wed, Jan 04, 2023 at 12:13:47PM -0800, kan.liang@linux.intel.com escreveu:
> From: Kan Liang <kan.liang@linux.intel.com>
> 
> Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
> are also supported.
> 
> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> ---

Did the kernel bits land upstream?

- Arnaldo
 
> No change since V1
> 
>  arch/x86/events/msr.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
> index ecced3a52668..074150d28fa8 100644
> --- a/arch/x86/events/msr.c
> +++ b/arch/x86/events/msr.c
> @@ -107,6 +107,8 @@ static bool test_intel(int idx, void *data)
>  	case INTEL_FAM6_RAPTORLAKE:
>  	case INTEL_FAM6_RAPTORLAKE_P:
>  	case INTEL_FAM6_RAPTORLAKE_S:
> +	case INTEL_FAM6_METEORLAKE:
> +	case INTEL_FAM6_METEORLAKE_L:
>  		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
>  			return true;
>  		break;
> -- 
> 2.35.1

Liang, Kan Feb. 2, 2023, 2:34 p.m. UTC | #2

Hi Arnaldo,

On 2023-02-01 8:47 p.m., Arnaldo Carvalho de Melo wrote:
> Em Wed, Jan 04, 2023 at 12:13:47PM -0800, kan.liang@linux.intel.com escreveu:
>> From: Kan Liang <kan.liang@linux.intel.com>
>>
>> Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
>> are also supported.
>>
>> Reviewed-by: Andi Kleen <ak@linux.intel.com>
>> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
>> ---
> 
> Did the kernel bits land upstream?
Yes, the kernel part has been merged into the tip.git perf/core branch.

Thanks for checking the status. There are two perf tool patches in this
series, which hasn't been merged. Should I resend them?

Thanks,
Kan
> 
> - Arnaldo
>  
>> No change since V1
>>
>>  arch/x86/events/msr.c | 2 ++
>>  1 file changed, 2 insertions(+)
>>
>> diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
>> index ecced3a52668..074150d28fa8 100644
>> --- a/arch/x86/events/msr.c
>> +++ b/arch/x86/events/msr.c
>> @@ -107,6 +107,8 @@ static bool test_intel(int idx, void *data)
>>  	case INTEL_FAM6_RAPTORLAKE:
>>  	case INTEL_FAM6_RAPTORLAKE_P:
>>  	case INTEL_FAM6_RAPTORLAKE_S:
>> +	case INTEL_FAM6_METEORLAKE:
>> +	case INTEL_FAM6_METEORLAKE_L:
>>  		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
>>  			return true;
>>  		break;
>> -- 
>> 2.35.1
>

Arnaldo Carvalho de Melo Feb. 2, 2023, 2:45 p.m. UTC | #3

On February 2, 2023 11:34:02 AM GMT-03:00, "Liang, Kan" <kan.liang@linux.intel.com> wrote:
>Hi Arnaldo,
>
>On 2023-02-01 8:47 p.m., Arnaldo Carvalho de Melo wrote:
>> Em Wed, Jan 04, 2023 at 12:13:47PM -0800, kan.liang@linux.intel.com escreveu:
>>> From: Kan Liang <kan.liang@linux.intel.com>
>>>
>>> Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
>>> are also supported.
>>>
>>> Reviewed-by: Andi Kleen <ak@linux.intel.com>
>>> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
>>> ---
>> 
>> Did the kernel bits land upstream?
>Yes, the kernel part has been merged into the tip.git perf/core branch.
>
>Thanks for checking the status. There are two perf tool patches in this
>series, which hasn't been merged. Should I resend them?

Please, try rebasing it on the tmp.perf/core in my tree.

- Arnaldo

>
>
>>  
>>> No change since V1
>>>
>>>  arch/x86/events/msr.c | 2 ++
>>>  1 file changed, 2 insertions(+)
>>>
>>> diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
>>> index ecced3a52668..074150d28fa8 100644
>>> --- a/arch/x86/events/msr.c
>>> +++ b/arch/x86/events/msr.c
>>> @@ -107,6 +107,8 @@ static bool test_intel(int idx, void *data)
>>>  	case INTEL_FAM6_RAPTORLAKE:
>>>  	case INTEL_FAM6_RAPTORLAKE_P:
>>>  	case INTEL_FAM6_RAPTORLAKE_S:
>>> +	case INTEL_FAM6_METEORLAKE:
>>> +	case INTEL_FAM6_METEORLAKE_L:
>>>  		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
>>>  			return true;
>>>  		break;
>>> -- 
>>> 2.35.1
>>

Arnaldo Carvalho de Melo Feb. 3, 2023, 8:21 p.m. UTC | #4

Em Thu, Feb 02, 2023 at 09:34:02AM -0500, Liang, Kan escreveu:
> Hi Arnaldo,
> 
> On 2023-02-01 8:47 p.m., Arnaldo Carvalho de Melo wrote:
> > Em Wed, Jan 04, 2023 at 12:13:47PM -0800, kan.liang@linux.intel.com escreveu:
> >> From: Kan Liang <kan.liang@linux.intel.com>
> >>
> >> Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
> >> are also supported.
> >>
> >> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> >> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> >> ---
> > 
> > Did the kernel bits land upstream?
> Yes, the kernel part has been merged into the tip.git perf/core branch.
> 
> Thanks for checking the status. There are two perf tool patches in this
> series, which hasn't been merged. Should I resend them?

Lemme try cherry-picking just the tooling bits from this series.
 
> Thanks,
> Kan
> > 
> > - Arnaldo
> >  
> >> No change since V1
> >>
> >>  arch/x86/events/msr.c | 2 ++
> >>  1 file changed, 2 insertions(+)
> >>
> >> diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
> >> index ecced3a52668..074150d28fa8 100644
> >> --- a/arch/x86/events/msr.c
> >> +++ b/arch/x86/events/msr.c
> >> @@ -107,6 +107,8 @@ static bool test_intel(int idx, void *data)
> >>  	case INTEL_FAM6_RAPTORLAKE:
> >>  	case INTEL_FAM6_RAPTORLAKE_P:
> >>  	case INTEL_FAM6_RAPTORLAKE_S:
> >> +	case INTEL_FAM6_METEORLAKE:
> >> +	case INTEL_FAM6_METEORLAKE_L:
> >>  		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
> >>  			return true;
> >>  		break;
> >> -- 
> >> 2.35.1
> >

Arnaldo Carvalho de Melo Feb. 3, 2023, 8:28 p.m. UTC | #5

Em Fri, Feb 03, 2023 at 05:21:15PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Thu, Feb 02, 2023 at 09:34:02AM -0500, Liang, Kan escreveu:
> > Hi Arnaldo,
> > 
> > On 2023-02-01 8:47 p.m., Arnaldo Carvalho de Melo wrote:
> > > Em Wed, Jan 04, 2023 at 12:13:47PM -0800, kan.liang@linux.intel.com escreveu:
> > >> From: Kan Liang <kan.liang@linux.intel.com>
> > >>
> > >> Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
> > >> are also supported.
> > >>
> > >> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> > >> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> > >> ---
> > > 
> > > Did the kernel bits land upstream?
> > Yes, the kernel part has been merged into the tip.git perf/core branch.
> > 
> > Thanks for checking the status. There are two perf tool patches in this
> > series, which hasn't been merged. Should I resend them?
> 
> Lemme try cherry-picking just the tooling bits from this series.

There was a clash with:

commit 3fd7a168bf51497909dbfb7347af28b5c57e74a6
Author: Namhyung Kim <namhyung@kernel.org>
Date:   Thu Jan 26 13:36:10 2023 -0800

    perf script: Add 'cgroup' field for output

And a minor fuzz on the first patch, I applied manually and resolved the
conflict,

Thanks,

- Arnaldo
  
> > Thanks,
> > Kan
> > > 
> > > - Arnaldo
> > >  
> > >> No change since V1
> > >>
> > >>  arch/x86/events/msr.c | 2 ++
> > >>  1 file changed, 2 insertions(+)
> > >>
> > >> diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
> > >> index ecced3a52668..074150d28fa8 100644
> > >> --- a/arch/x86/events/msr.c
> > >> +++ b/arch/x86/events/msr.c
> > >> @@ -107,6 +107,8 @@ static bool test_intel(int idx, void *data)
> > >>  	case INTEL_FAM6_RAPTORLAKE:
> > >>  	case INTEL_FAM6_RAPTORLAKE_P:
> > >>  	case INTEL_FAM6_RAPTORLAKE_S:
> > >> +	case INTEL_FAM6_METEORLAKE:
> > >> +	case INTEL_FAM6_METEORLAKE_L:
> > >>  		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
> > >>  			return true;
> > >>  		break;
> > >> -- 
> > >> 2.35.1
> > > 
> 
> -- 
> 
> - Arnaldo

Liang, Kan Feb. 6, 2023, 2:32 p.m. UTC | #6

On 2023-02-03 3:28 p.m., Arnaldo Carvalho de Melo wrote:
> Em Fri, Feb 03, 2023 at 05:21:15PM -0300, Arnaldo Carvalho de Melo escreveu:
>> Em Thu, Feb 02, 2023 at 09:34:02AM -0500, Liang, Kan escreveu:
>>> Hi Arnaldo,
>>>
>>> On 2023-02-01 8:47 p.m., Arnaldo Carvalho de Melo wrote:
>>>> Em Wed, Jan 04, 2023 at 12:13:47PM -0800, kan.liang@linux.intel.com escreveu:
>>>>> From: Kan Liang <kan.liang@linux.intel.com>
>>>>>
>>>>> Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
>>>>> are also supported.
>>>>>
>>>>> Reviewed-by: Andi Kleen <ak@linux.intel.com>
>>>>> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
>>>>> ---
>>>>
>>>> Did the kernel bits land upstream?
>>> Yes, the kernel part has been merged into the tip.git perf/core branch.
>>>
>>> Thanks for checking the status. There are two perf tool patches in this
>>> series, which hasn't been merged. Should I resend them?
>>
>> Lemme try cherry-picking just the tooling bits from this series.
>

Sorry, I forgot to mention it in this thread.
I sent V3 with only perf tool patches.

https://lore.kernel.org/lkml/20230202192209.1795329-1-kan.liang@linux.intel.com/


> There was a clash with:
> 
> commit 3fd7a168bf51497909dbfb7347af28b5c57e74a6
> Author: Namhyung Kim <namhyung@kernel.org>
> Date:   Thu Jan 26 13:36:10 2023 -0800
> 
>     perf script: Add 'cgroup' field for output
> 
> And a minor fuzz on the first patch, I applied manually and resolved the
> conflict,

The V3 add a perf test case for the new field. Could you please apply it
as well?

Sorry for the inconvenience.

Thanks,
Kan
> 
> Thanks,
> 
> - Arnaldo
>   
>>> Thanks,
>>> Kan
>>>>
>>>> - Arnaldo
>>>>  
>>>>> No change since V1
>>>>>
>>>>>  arch/x86/events/msr.c | 2 ++
>>>>>  1 file changed, 2 insertions(+)
>>>>>
>>>>> diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
>>>>> index ecced3a52668..074150d28fa8 100644
>>>>> --- a/arch/x86/events/msr.c
>>>>> +++ b/arch/x86/events/msr.c
>>>>> @@ -107,6 +107,8 @@ static bool test_intel(int idx, void *data)
>>>>>  	case INTEL_FAM6_RAPTORLAKE:
>>>>>  	case INTEL_FAM6_RAPTORLAKE_P:
>>>>>  	case INTEL_FAM6_RAPTORLAKE_S:
>>>>> +	case INTEL_FAM6_METEORLAKE:
>>>>> +	case INTEL_FAM6_METEORLAKE_L:
>>>>>  		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
>>>>>  			return true;
>>>>>  		break;
>>>>> -- 
>>>>> 2.35.1
>>>>
>>
>> -- 
>>
>> - Arnaldo
>

Arnaldo Carvalho de Melo Feb. 6, 2023, 2:51 p.m. UTC | #7

Em Mon, Feb 06, 2023 at 09:32:00AM -0500, Liang, Kan escreveu:
> 
> 
> On 2023-02-03 3:28 p.m., Arnaldo Carvalho de Melo wrote:
> > Em Fri, Feb 03, 2023 at 05:21:15PM -0300, Arnaldo Carvalho de Melo escreveu:
> >> Em Thu, Feb 02, 2023 at 09:34:02AM -0500, Liang, Kan escreveu:
> >>> Hi Arnaldo,
> >>>
> >>> On 2023-02-01 8:47 p.m., Arnaldo Carvalho de Melo wrote:
> >>>> Em Wed, Jan 04, 2023 at 12:13:47PM -0800, kan.liang@linux.intel.com escreveu:
> >>>>> From: Kan Liang <kan.liang@linux.intel.com>
> >>>>>
> >>>>> Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
> >>>>> are also supported.
> >>>>>
> >>>>> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> >>>>> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> >>>>> ---
> >>>>
> >>>> Did the kernel bits land upstream?
> >>> Yes, the kernel part has been merged into the tip.git perf/core branch.
> >>>
> >>> Thanks for checking the status. There are two perf tool patches in this
> >>> series, which hasn't been merged. Should I resend them?
> >>
> >> Lemme try cherry-picking just the tooling bits from this series.
> >
> 
> Sorry, I forgot to mention it in this thread.
> I sent V3 with only perf tool patches.
> 
> https://lore.kernel.org/lkml/20230202192209.1795329-1-kan.liang@linux.intel.com/

> 
> > There was a clash with:
> > 
> > commit 3fd7a168bf51497909dbfb7347af28b5c57e74a6
> > Author: Namhyung Kim <namhyung@kernel.org>
> > Date:   Thu Jan 26 13:36:10 2023 -0800
> > 
> >     perf script: Add 'cgroup' field for output
> > 
> > And a minor fuzz on the first patch, I applied manually and resolved the
> > conflict,
> 
> The V3 add a perf test case for the new field. Could you please apply it
> as well?
> 
> Sorry for the inconvenience.

np, I'll pick the test and apply it as well,

Thanks for letting me know,

- Arnaldo

diff mbox series

Patch

diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index ecced3a52668..074150d28fa8 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -107,6 +107,8 @@  static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 	case INTEL_FAM6_RAPTORLAKE_S:
+	case INTEL_FAM6_METEORLAKE:
+	case INTEL_FAM6_METEORLAKE_L:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;