[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251021154349.GR3245006@noisy.programming.kicks-ass.net>
Date: Tue, 21 Oct 2025 17:43:49 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Dapeng Mi <dapeng1.mi@...ux.intel.com>
Cc: Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Namhyung Kim <namhyung@...nel.org>, Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Andi Kleen <ak@...ux.intel.com>,
Eranian Stephane <eranian@...gle.com>, linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org, Dapeng Mi <dapeng1.mi@...el.com>
Subject: Re: [Patch v8 05/12] perf/x86/intel: Initialize architectural PEBS
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;
Powered by blists - more mailing lists