From nobody Wed Dec 17 05:27:02 2025 Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5532222EF4 for ; Tue, 18 Jun 2024 15:12:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=192.198.163.19 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1718723538; cv=none; b=deqDUgWbTsx7FLzV7OArgQkZuryH93BpqOtWrdYtde5pq1nqHQAw5CEV2zDKk/Eu0ld940qWhyu0iOY+SneC4CPSOVESAWe6DOYJVfxmgKfx9TLK1pxcVGNkwgFL4STVTU/cAV9+eJnglpp+hIWIwNUdEfIFHUfCTM5LcWBkoC8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1718723538; c=relaxed/simple; bh=6e0Gvn/nvISRBfHULmLHw55WHOEd0L5UVOFZmVrXNCU=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=kz0k2cwbdFeP3iFSCW/ViBnp1rjMtZNO4veEa64dScdsKKDqFASMuOgkYkx6I+mvZi0Um7KiDQMswKHNQmOL+vm1w4+CTWY7PNfST2EOT6cQrh4ZdwZ7ne8yjeUqTvOEOoS3c2VVeMVSl5RG40tknw+iNVUxHOT/UXNYaczm0Eg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com; spf=none smtp.mailfrom=linux.intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=Ru3tDXr3; arc=none smtp.client-ip=192.198.163.19 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="Ru3tDXr3" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1718723536; x=1750259536; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=6e0Gvn/nvISRBfHULmLHw55WHOEd0L5UVOFZmVrXNCU=; b=Ru3tDXr3JeYIZAUMgpnp/xwprnYlMwESsEJmAvSzillBacAbUQAyMxBe dUu7ereiG9GbXcK18CFaMhxacVZ5dF1xwtj1V9Kck53le7c0qTx5OZGxd zSy6Cnzg9eRjAOsMkiIf69v0svV4d5ir4Wd7S+WWShUCZwttHMU2cGxb0 9agIyufj/qo68DQvUHHFP1MpZ6LhPdc7alcBwW9DZASbxAMihyTsCbysG v5EVl9JBVFQnYLTkCV//XcG7KjOEEaPADhLzE/nhbIj3i0Rk4VNxOVDle cmGhTbY9GbYAi8Y/rpepQ/MaeHgiyKLm6qIgI53wz7/GEqnsyelMFS/LQ Q==; X-CSE-ConnectionGUID: EA+faTH4SziT5NY9zCWzsQ== X-CSE-MsgGUID: T/zEmQv8R++hR7Nuewsl0w== X-IronPort-AV: E=McAfee;i="6700,10204,11107"; a="15374180" X-IronPort-AV: E=Sophos;i="6.08,247,1712646000"; d="scan'208";a="15374180" Received: from fmviesa006.fm.intel.com ([10.60.135.146]) by fmvoesa113.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 18 Jun 2024 08:12:14 -0700 X-CSE-ConnectionGUID: tN1GcXcrQfy5hH+8y+CFrQ== X-CSE-MsgGUID: MUx+NMJ4QO6DyWprHThwrg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.08,247,1712646000"; d="scan'208";a="41426920" Received: from kanliang-dev.jf.intel.com ([10.165.154.102]) by fmviesa006.fm.intel.com with ESMTP; 18 Jun 2024 08:12:14 -0700 From: kan.liang@linux.intel.com To: peterz@infradead.org, mingo@kernel.org, acme@kernel.org, namhyung@kernel.org, irogers@google.com, adrian.hunter@intel.com, alexander.shishkin@linux.intel.com, linux-kernel@vger.kernel.org Cc: ak@linux.intel.com, eranian@google.com, Kan Liang Subject: [RESEND PATCH 01/12] perf/x86/intel: Support the PEBS event mask Date: Tue, 18 Jun 2024 08:10:33 -0700 Message-Id: <20240618151044.1318612-2-kan.liang@linux.intel.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: <20240618151044.1318612-1-kan.liang@linux.intel.com> References: <20240618151044.1318612-1-kan.liang@linux.intel.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Kan Liang The current perf assumes that the counters that support PEBS are contiguous. But it's not guaranteed with the new leaf 0x23 introduced. The counters are enumerated with a counter mask. There may be holes in the counter mask for future platforms or in a virtualization environment. Store the PEBS event mask rather than the maximum number of PEBS counters in the x86 PMU structures. Reviewed-by: Andi Kleen Signed-off-by: Kan Liang --- arch/x86/events/intel/core.c | 8 ++++---- arch/x86/events/intel/ds.c | 14 +++++++------- arch/x86/events/perf_event.h | 4 ++-- arch/x86/include/asm/intel_ds.h | 6 ++++++ 4 files changed, 19 insertions(+), 13 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 38c1b1f1deaa..c27a9f75defb 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4728,7 +4728,7 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hy= brid_pmu *pmu) { intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed, &pmu->intel_ctrl, (1ULL << pmu->num_counters_fixed) - 1); - pmu->max_pebs_events =3D min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counte= rs); + pmu->pebs_events_mask =3D intel_pmu_pebs_mask(GENMASK_ULL(pmu->num_counte= rs - 1, 0)); pmu->unconstrained =3D (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, 0, pmu->num_counters, 0, 0); @@ -6070,7 +6070,7 @@ static __always_inline int intel_pmu_init_hybrid(enum= hybrid_pmu_type pmus) =20 pmu->num_counters =3D x86_pmu.num_counters; pmu->num_counters_fixed =3D x86_pmu.num_counters_fixed; - pmu->max_pebs_events =3D min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_count= ers); + pmu->pebs_events_mask =3D intel_pmu_pebs_mask(GENMASK_ULL(pmu->num_count= ers - 1, 0)); pmu->unconstrained =3D (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, 0, pmu->num_counters, 0, 0); @@ -6193,7 +6193,7 @@ __init int intel_pmu_init(void) x86_pmu.events_maskl =3D ebx.full; x86_pmu.events_mask_len =3D eax.split.mask_length; =20 - x86_pmu.max_pebs_events =3D min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num= _counters); + x86_pmu.pebs_events_mask =3D intel_pmu_pebs_mask(GENMASK_ULL(x86_pmu.num_= counters - 1, 0)); x86_pmu.pebs_capable =3D PEBS_COUNTER_MASK; =20 /* @@ -6822,7 +6822,7 @@ __init int intel_pmu_init(void) pmu->num_counters_fixed =3D x86_pmu.num_counters_fixed; } =20 - pmu->max_pebs_events =3D min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_count= ers); + pmu->pebs_events_mask =3D intel_pmu_pebs_mask(GENMASK_ULL(pmu->num_count= ers - 1, 0)); pmu->unconstrained =3D (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, 0, pmu->num_counters, 0, 0); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index e010bfed8417..a0104c82baed 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1137,7 +1137,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_pmu_= context *pmu_ctx, bool sche static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) { struct debug_store *ds =3D cpuc->ds; - int max_pebs_events =3D hybrid(cpuc->pmu, max_pebs_events); + int max_pebs_events =3D hweight64(hybrid(cpuc->pmu, pebs_events_mask)); int num_counters_fixed =3D hybrid(cpuc->pmu, num_counters_fixed); u64 threshold; int reserved; @@ -2157,6 +2157,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *= iregs, struct perf_sample_d void *base, *at, *top; short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] =3D {}; short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] =3D {}; + int max_pebs_events =3D hweight64(x86_pmu.pebs_events_mask); int bit, i, size; u64 mask; =20 @@ -2168,8 +2169,8 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *= iregs, struct perf_sample_d =20 ds->pebs_index =3D ds->pebs_buffer_base; =20 - mask =3D (1ULL << x86_pmu.max_pebs_events) - 1; - size =3D x86_pmu.max_pebs_events; + mask =3D x86_pmu.pebs_events_mask; + size =3D max_pebs_events; if (x86_pmu.flags & PMU_FL_PEBS_ALL) { mask |=3D ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FI= XED; size =3D INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed; @@ -2208,8 +2209,8 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *= iregs, struct perf_sample_d pebs_status =3D p->status =3D cpuc->pebs_enabled; =20 bit =3D find_first_bit((unsigned long *)&pebs_status, - x86_pmu.max_pebs_events); - if (bit >=3D x86_pmu.max_pebs_events) + max_pebs_events); + if (bit >=3D max_pebs_events) continue; =20 /* @@ -2267,7 +2268,6 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *= iregs, struct perf_sample_d { short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] =3D {}; struct cpu_hw_events *cpuc =3D this_cpu_ptr(&cpu_hw_events); - int max_pebs_events =3D hybrid(cpuc->pmu, max_pebs_events); int num_counters_fixed =3D hybrid(cpuc->pmu, num_counters_fixed); struct debug_store *ds =3D cpuc->ds; struct perf_event *event; @@ -2283,7 +2283,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *= iregs, struct perf_sample_d =20 ds->pebs_index =3D ds->pebs_buffer_base; =20 - mask =3D ((1ULL << max_pebs_events) - 1) | + mask =3D hybrid(cpuc->pmu, pebs_events_mask) | (((1ULL << num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED); size =3D INTEL_PMC_IDX_FIXED + num_counters_fixed; =20 diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 72b022a1e16c..880fe0c4aa68 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -684,7 +684,7 @@ struct x86_hybrid_pmu { cpumask_t supported_cpus; union perf_capabilities intel_cap; u64 intel_ctrl; - int max_pebs_events; + u64 pebs_events_mask; int num_counters; int num_counters_fixed; struct event_constraint unconstrained; @@ -852,7 +852,7 @@ struct x86_pmu { pebs_ept :1; int pebs_record_size; int pebs_buffer_size; - int max_pebs_events; + u64 pebs_events_mask; void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_d= s.h index 2f9eeb5c3069..d11f0f480ccb 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -9,6 +9,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS_FMT4 8 #define MAX_PEBS_EVENTS 32 +#define MAX_PEBS_EVENTS_MASK GENMASK_ULL(MAX_PEBS_EVENTS - 1, 0) #define MAX_FIXED_PEBS_EVENTS 16 =20 /* @@ -35,4 +36,9 @@ struct debug_store_buffers { char pebs_buffer[PEBS_BUFFER_SIZE]; }; =20 +static inline u64 intel_pmu_pebs_mask(u64 cntr_mask) +{ + return MAX_PEBS_EVENTS_MASK & cntr_mask; +} + #endif --=20 2.35.1