From: "Mi, Dapeng" <dapeng1.mi@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: 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>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
Dapeng Mi <dapeng1.mi@intel.com>
Subject: Re: [Patch v8 05/12] perf/x86/intel: Initialize architectural PEBS
Date: Wed, 22 Oct 2025 13:27:31 +0800 [thread overview]
Message-ID: <ba31c391-e703-4ff6-9742-4518d36bffa6@linux.intel.com> (raw)
In-Reply-To: <20251021154349.GR3245006@noisy.programming.kicks-ass.net>
On 10/21/2025 11:43 PM, Peter Zijlstra wrote:
> On Wed, Oct 15, 2025 at 02:44:15PM +0800, Dapeng Mi wrote:
>> diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
>> index c88bcd5d2bc4..bfb123ff7c9a 100644
>> --- a/arch/x86/events/intel/core.c
>> +++ b/arch/x86/events/intel/core.c
>> @@ -5273,34 +5273,58 @@ static inline bool intel_pmu_broken_perf_cap(void)
>>
>> static void update_pmu_cap(struct pmu *pmu)
>> {
>> - unsigned int cntr, fixed_cntr, ecx, edx;
>> - union cpuid35_eax eax;
>> - union cpuid35_ebx ebx;
>> + unsigned int eax, ebx, ecx, edx;
>> + union cpuid35_eax eax_0;
>> + union cpuid35_ebx ebx_0;
>> + u64 cntrs_mask = 0;
>> + u64 pebs_mask = 0;
>> + u64 pdists_mask = 0;
>>
>> - cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx);
>> + cpuid(ARCH_PERFMON_EXT_LEAF, &eax_0.full, &ebx_0.full, &ecx, &edx);
>>
>> - if (ebx.split.umask2)
>> + if (ebx_0.split.umask2)
>> hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_UMASK2;
>> - if (ebx.split.eq)
>> + if (ebx_0.split.eq)
>> hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_EQ;
>>
>> - if (eax.split.cntr_subleaf) {
>> + if (eax_0.split.cntr_subleaf) {
>> cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
>> - &cntr, &fixed_cntr, &ecx, &edx);
>> - hybrid(pmu, cntr_mask64) = cntr;
>> - hybrid(pmu, fixed_cntr_mask64) = fixed_cntr;
>> + &eax, &ebx, &ecx, &edx);
>> + hybrid(pmu, cntr_mask64) = eax;
>> + hybrid(pmu, fixed_cntr_mask64) = ebx;
>> + cntrs_mask = (u64)ebx << INTEL_PMC_IDX_FIXED | eax;
>> }
>>
>> - if (eax.split.acr_subleaf) {
>> + if (eax_0.split.acr_subleaf) {
>> cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
>> - &cntr, &fixed_cntr, &ecx, &edx);
>> + &eax, &ebx, &ecx, &edx);
>> /* The mask of the counters which can be reloaded */
>> - hybrid(pmu, acr_cntr_mask64) = cntr | ((u64)fixed_cntr << INTEL_PMC_IDX_FIXED);
>> + hybrid(pmu, acr_cntr_mask64) = eax | ((u64)ebx << INTEL_PMC_IDX_FIXED);
>>
>> /* The mask of the counters which can cause a reload of reloadable counters */
>> hybrid(pmu, acr_cause_mask64) = ecx | ((u64)edx << INTEL_PMC_IDX_FIXED);
>> }
>>
>> + /* Bits[5:4] should be set simultaneously if arch-PEBS is supported */
>> + if (eax_0.split.pebs_caps_subleaf && eax_0.split.pebs_cnts_subleaf) {
>> + cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_PEBS_CAP_LEAF,
>> + &eax, &ebx, &ecx, &edx);
>> + hybrid(pmu, arch_pebs_cap).caps = (u64)ebx << 32;
>> +
>> + cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_PEBS_COUNTER_LEAF,
>> + &eax, &ebx, &ecx, &edx);
>> + pebs_mask = ((u64)ecx << INTEL_PMC_IDX_FIXED) | eax;
>> + pdists_mask = ((u64)edx << INTEL_PMC_IDX_FIXED) | ebx;
>> + hybrid(pmu, arch_pebs_cap).counters = pebs_mask;
>> + hybrid(pmu, arch_pebs_cap).pdists = pdists_mask;
>> +
>> + if (WARN_ON((pebs_mask | pdists_mask) & ~cntrs_mask))
>> + x86_pmu.arch_pebs = 0;
>> + } else {
>> + WARN_ON(x86_pmu.arch_pebs == 1);
>> + x86_pmu.arch_pebs = 0;
>> + }
>> +
>> if (!intel_pmu_broken_perf_cap()) {
>> /* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
>> rdmsrq(MSR_IA32_PERF_CAPABILITIES, hybrid(pmu, intel_cap).capabilities);
> I've stuck this on top.
>
> --- a/arch/x86/events/intel/core.c
> +++ b/arch/x86/events/intel/core.c
> @@ -5271,6 +5271,8 @@ static inline bool intel_pmu_broken_perf
> return false;
> }
>
> +#define counter_mask(_gp, _fixed) ((_gp) | ((u64)(_fixed) << INTEL_PMC_IDX_FIXED))
> +
> static void update_pmu_cap(struct pmu *pmu)
> {
> unsigned int eax, ebx, ecx, edx;
> @@ -5292,17 +5294,16 @@ static void update_pmu_cap(struct pmu *p
> &eax, &ebx, &ecx, &edx);
> hybrid(pmu, cntr_mask64) = eax;
> hybrid(pmu, fixed_cntr_mask64) = ebx;
> - cntrs_mask = (u64)ebx << INTEL_PMC_IDX_FIXED | eax;
> + cntrs_mask = counter_mask(eax, ebx);
> }
>
> if (eax_0.split.acr_subleaf) {
> cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
> &eax, &ebx, &ecx, &edx);
> /* The mask of the counters which can be reloaded */
> - hybrid(pmu, acr_cntr_mask64) = eax | ((u64)ebx << INTEL_PMC_IDX_FIXED);
> -
> + hybrid(pmu, acr_cntr_mask64) = counter_mask(eax, ebx);
> /* The mask of the counters which can cause a reload of reloadable counters */
> - hybrid(pmu, acr_cause_mask64) = ecx | ((u64)edx << INTEL_PMC_IDX_FIXED);
> + hybrid(pmu, acr_cause_mask64) = counter_mask(ecx, edx);
> }
>
> /* Bits[5:4] should be set simultaneously if arch-PEBS is supported */
> @@ -5313,8 +5314,8 @@ static void update_pmu_cap(struct pmu *p
>
> cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_PEBS_COUNTER_LEAF,
> &eax, &ebx, &ecx, &edx);
> - pebs_mask = ((u64)ecx << INTEL_PMC_IDX_FIXED) | eax;
> - pdists_mask = ((u64)edx << INTEL_PMC_IDX_FIXED) | ebx;
> + pebs_mask = counter_mask(eax, ecx);
> + pdists_mask = counter_mask(ebx, edx);
> hybrid(pmu, arch_pebs_cap).counters = pebs_mask;
> hybrid(pmu, arch_pebs_cap).pdists = pdists_mask;
Nice suggestion. Would do. Thanks.
>
next prev parent reply other threads:[~2025-10-22 5:27 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-15 6:44 [Patch v8 00/12] arch-PEBS enabling for Intel platforms Dapeng Mi
2025-10-15 6:44 ` [Patch v8 01/12] perf/x86: Remove redundant is_x86_event() prototype Dapeng Mi
2025-10-15 6:44 ` [Patch v8 02/12] perf/x86/intel: Fix NULL event access and potential PEBS record loss Dapeng Mi
2025-10-22 8:12 ` Mi, Dapeng
2025-10-22 11:24 ` Peter Zijlstra
2025-10-23 2:29 ` Mi, Dapeng
2025-10-15 6:44 ` [Patch v8 03/12] perf/x86/intel: Replace x86_pmu.drain_pebs calling with static call Dapeng Mi
2025-10-15 6:44 ` [Patch v8 04/12] perf/x86/intel: Correct large PEBS flag check Dapeng Mi
2025-10-15 6:44 ` [Patch v8 05/12] perf/x86/intel: Initialize architectural PEBS Dapeng Mi
2025-10-21 15:43 ` Peter Zijlstra
2025-10-22 5:27 ` Mi, Dapeng [this message]
2025-10-15 6:44 ` [Patch v8 06/12] perf/x86/intel/ds: Factor out PEBS record processing code to functions Dapeng Mi
2025-10-21 15:49 ` Peter Zijlstra
2025-10-22 5:32 ` Mi, Dapeng
2025-10-22 11:49 ` Peter Zijlstra
2025-10-23 1:06 ` Mi, Dapeng
2025-10-15 6:44 ` [Patch v8 07/12] perf/x86/intel/ds: Factor out PEBS group " Dapeng Mi
2025-10-15 6:44 ` [Patch v8 08/12] perf/x86/intel: Process arch-PEBS records or record fragments Dapeng Mi
2025-10-15 6:44 ` [Patch v8 09/12] perf/x86/intel: Allocate arch-PEBS buffer and initialize PEBS_BASE MSR Dapeng Mi
2025-10-15 6:44 ` [Patch v8 10/12] perf/x86/intel: Update dyn_constranit base on PEBS event precise level Dapeng Mi
2025-10-15 6:44 ` [Patch v8 11/12] perf/x86/intel: Setup PEBS data configuration and enable legacy groups Dapeng Mi
2025-10-15 6:44 ` [Patch v8 12/12] perf/x86/intel: Add counter group support for arch-PEBS 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=ba31c391-e703-4ff6-9742-4518d36bffa6@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=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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.