From: "Mi, Dapeng" <dapeng1.mi@linux.intel.com>
To: "Liang, Kan" <kan.liang@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Andi Kleen <ak@linux.intel.com>,
Eranian Stephane <eranian@google.com>
Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
Dapeng Mi <dapeng1.mi@intel.com>
Subject: Re: [Patch v2 13/24] perf/x86/intel: Update dyn_constranit base on PEBS event precise level
Date: Wed, 5 Mar 2025 09:41:27 +0800 [thread overview]
Message-ID: <0496c7b0-098c-4b2f-9c71-a258a398c5a8@linux.intel.com> (raw)
In-Reply-To: <afdc5b07-9795-4049-8941-c2e3d2bbaa87@linux.intel.com>
On 2/27/2025 10:06 PM, Liang, Kan wrote:
>
> On 2025-02-18 10:28 a.m., Dapeng Mi wrote:
>> arch-PEBS provides CPUIDs to enumerate which counters support PEBS
>> sampling and precise distribution PEBS sampling. Thus PEBS constraints
>> should be dynamically configured base on these counter and precise
>> distribution bitmap instead of defining them statically.
>>
>> Update event dyn_constraint base on PEBS event precise level.
>>
>> Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
>> ---
>> arch/x86/events/intel/core.c | 6 ++++++
>> arch/x86/events/intel/ds.c | 1 +
>> 2 files changed, 7 insertions(+)
>>
>> diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
>> index 472366c3db22..c777e0531d40 100644
>> --- a/arch/x86/events/intel/core.c
>> +++ b/arch/x86/events/intel/core.c
>> @@ -4033,6 +4033,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
>> return ret;
>>
>> if (event->attr.precise_ip) {
>> + struct arch_pebs_cap pebs_cap = hybrid(event->pmu, arch_pebs_cap);
>> +
>> if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
>> return -EINVAL;
>>
>> @@ -4046,6 +4048,10 @@ static int intel_pmu_hw_config(struct perf_event *event)
>> }
>> if (x86_pmu.pebs_aliases)
>> x86_pmu.pebs_aliases(event);
>> +
>> + if (x86_pmu.arch_pebs)
>> + event->hw.dyn_constraint = event->attr.precise_ip >= 3 ?
>> + pebs_cap.pdists : pebs_cap.counters;
>> }
> The dyn_constraint is only required when the counter mask is different.
> I think the pebs_cap.counters should be very likely the same as the
> regular counter mask. Maybe something as below (not test).
>
> if (x86_pmu.arch_pebs) {
> u64 cntr_mask = event->attr.precise_ip >= 3 ?
> pebs_cap.pdists : pebs_cap.counters;
> if (cntr_mask != hybrid(event->pmu, intel_ctrl))
> event->hw.dyn_constraint = cntr_mask;
> }
Sure. Thanks.
>
> Thanks,
> Kan
>>
>> if (needs_branch_stack(event)) {
>> diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
>> index 519767fc9180..615aefb4e52e 100644
>> --- a/arch/x86/events/intel/ds.c
>> +++ b/arch/x86/events/intel/ds.c
>> @@ -2948,6 +2948,7 @@ static void __init intel_arch_pebs_init(void)
>> x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
>> x86_pmu.drain_pebs = intel_pmu_drain_arch_pebs;
>> x86_pmu.pebs_capable = ~0ULL;
>> + x86_pmu.flags |= PMU_FL_PEBS_ALL;
>>
>> x86_pmu.pebs_enable = __intel_pmu_pebs_enable;
>> x86_pmu.pebs_disable = __intel_pmu_pebs_disable;
>
next prev parent reply other threads:[~2025-03-05 1:41 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-18 15:27 [Patch v2 00/24] Arch-PEBS and PMU supports for Clearwater Forest and Panther Lake Dapeng Mi
2025-02-18 15:27 ` [Patch v2 01/24] perf/x86: Add dynamic constraint Dapeng Mi
2025-02-18 15:27 ` [Patch v2 02/24] perf/x86/intel: Add Panther Lake support Dapeng Mi
2025-02-18 15:27 ` [Patch v2 03/24] perf/x86/intel: Add PMU support for Clearwater Forest Dapeng Mi
2025-02-18 15:27 ` [Patch v2 04/24] perf/x86/intel: Parse CPUID archPerfmonExt leaves for non-hybrid CPUs Dapeng Mi
2025-02-18 15:27 ` [Patch v2 05/24] perf/x86/intel: Decouple BTS initialization from PEBS initialization Dapeng Mi
2025-02-18 15:28 ` [Patch v2 06/24] perf/x86/intel: Rename x86_pmu.pebs to x86_pmu.ds_pebs Dapeng Mi
2025-02-18 15:28 ` [Patch v2 07/24] perf/x86/intel: Introduce pairs of PEBS static calls Dapeng Mi
2025-02-18 15:28 ` [Patch v2 08/24] perf/x86/intel: Initialize architectural PEBS Dapeng Mi
2025-02-18 15:28 ` [Patch v2 09/24] perf/x86/intel/ds: Factor out common PEBS processing code to functions Dapeng Mi
2025-02-18 15:28 ` [Patch v2 10/24] perf/x86/intel: Process arch-PEBS records or record fragments Dapeng Mi
2025-02-25 10:39 ` Peter Zijlstra
2025-02-25 11:00 ` Peter Zijlstra
2025-02-26 5:20 ` Mi, Dapeng
2025-02-26 9:35 ` Peter Zijlstra
2025-02-26 15:45 ` Liang, Kan
2025-02-27 2:04 ` Mi, Dapeng
2025-02-25 20:42 ` Andi Kleen
2025-02-26 2:54 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 11/24] perf/x86/intel: Factor out common functions to process PEBS groups Dapeng Mi
2025-02-25 11:02 ` Peter Zijlstra
2025-02-26 5:24 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 12/24] perf/x86/intel: Allocate arch-PEBS buffer and initialize PEBS_BASE MSR Dapeng Mi
2025-02-25 11:18 ` Peter Zijlstra
2025-02-26 5:48 ` Mi, Dapeng
2025-02-26 9:46 ` Peter Zijlstra
2025-02-27 2:05 ` Mi, Dapeng
2025-02-25 11:25 ` Peter Zijlstra
2025-02-26 6:19 ` Mi, Dapeng
2025-02-26 9:48 ` Peter Zijlstra
2025-02-27 2:09 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 13/24] perf/x86/intel: Update dyn_constranit base on PEBS event precise level Dapeng Mi
2025-02-27 14:06 ` Liang, Kan
2025-03-05 1:41 ` Mi, Dapeng [this message]
2025-02-18 15:28 ` [Patch v2 14/24] perf/x86/intel: Setup PEBS data configuration and enable legacy groups Dapeng Mi
2025-02-18 15:28 ` [Patch v2 15/24] perf/x86/intel: Add SSP register support for arch-PEBS Dapeng Mi
2025-02-25 11:52 ` Peter Zijlstra
2025-02-26 6:56 ` Mi, Dapeng
2025-02-25 11:54 ` Peter Zijlstra
2025-02-25 20:44 ` Andi Kleen
2025-02-27 6:29 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 16/24] perf/x86/intel: Add counter group " Dapeng Mi
2025-02-18 15:28 ` [Patch v2 17/24] perf/core: Support to capture higher width vector registers Dapeng Mi
2025-02-25 20:32 ` Peter Zijlstra
2025-02-26 7:55 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 18/24] perf/x86/intel: Support arch-PEBS vector registers group capturing Dapeng Mi
2025-02-25 15:32 ` Peter Zijlstra
2025-02-26 8:08 ` Mi, Dapeng
2025-02-27 6:40 ` Mi, Dapeng
2025-03-04 3:08 ` Mi, Dapeng
2025-03-04 16:26 ` Liang, Kan
2025-03-05 1:34 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 19/24] perf tools: Support to show SSP register Dapeng Mi
2025-02-18 15:28 ` [Patch v2 20/24] perf tools: Enhance arch__intr/user_reg_mask() helpers Dapeng Mi
2025-02-18 15:28 ` [Patch v2 21/24] perf tools: Enhance sample_regs_user/intr to capture more registers Dapeng Mi
2025-02-18 15:28 ` [Patch v2 22/24] perf tools: Support to capture more vector registers (x86/Intel) Dapeng Mi
2025-02-18 15:28 ` [Patch v2 23/24] perf tools/tests: Add vector registers PEBS sampling test Dapeng Mi
2025-02-18 15:28 ` [Patch v2 24/24] perf tools: Fix incorrect --user-regs comments Dapeng Mi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=0496c7b0-098c-4b2f-9c71-a258a398c5a8@linux.intel.com \
--to=dapeng1.mi@linux.intel.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=dapeng1.mi@intel.com \
--cc=eranian@google.com \
--cc=irogers@google.com \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®