public inbox for linux-perf-users@vger.kernel.org
 help / color / mirror / Atom feed
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Jiri Olsa <jolsa@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>,
	Eranian Stephane <eranian@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>,
	broonie@kernel.org, Ravi Bangoria <ravi.bangoria@amd.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Zide Chen <zide.chen@intel.com>,
	Falcon Thomas <thomas.falcon@intel.com>,
	Dapeng Mi <dapeng1.mi@intel.com>,
	Xudong Hao <xudong.hao@intel.com>,
	Kan Liang <kan.liang@linux.intel.com>,
	Dapeng Mi <dapeng1.mi@linux.intel.com>
Subject: [Patch v7 17/24] perf/x86: Enable OPMASK sampling using sample_simd_pred_reg_* fields
Date: Tue, 24 Mar 2026 08:41:11 +0800	[thread overview]
Message-ID: <20260324004118.3772171-18-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20260324004118.3772171-1-dapeng1.mi@linux.intel.com>

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

This patch adds support for sampling OPAMSK registers via the
sample_simd_pred_reg_* fields.

Each OPMASK register consists of 1 u64 word. Current x86 hardware
supports 8 OPMASK registers. The perf_simd_reg_value() function is
responsible for outputting OPMASK value to userspace.

Additionally, sample_simd_pred_reg_qwords should be set to 1 to indicate
OPMASK sampling.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Co-developed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 arch/x86/events/core.c                |  8 ++++++++
 arch/x86/events/perf_event.h          | 10 ++++++++++
 arch/x86/include/asm/perf_event.h     |  4 ++++
 arch/x86/include/uapi/asm/perf_regs.h |  5 +++++
 arch/x86/kernel/perf_regs.c           | 15 ++++++++++++---
 5 files changed, 39 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e5f5a6971d72..d86a4fbea1ed 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -729,6 +729,9 @@ int x86_pmu_hw_config(struct perf_event *event)
 			if (event_needs_high16_zmm(event) &&
 			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_Hi16_ZMM))
 				return -EINVAL;
+			if (event_needs_opmask(event) &&
+			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_OPMASK))
+				return -EINVAL;
 		}
 	}
 
@@ -1856,6 +1859,7 @@ inline void x86_pmu_clear_perf_regs(struct pt_regs *regs)
 	perf_regs->ymmh_regs = NULL;
 	perf_regs->zmmh_regs = NULL;
 	perf_regs->h16zmm_regs = NULL;
+	perf_regs->opmask_regs = NULL;
 }
 
 static inline void x86_pmu_update_xregs(struct x86_perf_regs *perf_regs,
@@ -1877,6 +1881,8 @@ static inline void x86_pmu_update_xregs(struct x86_perf_regs *perf_regs,
 		perf_regs->zmmh = get_xsave_addr(xsave, XFEATURE_ZMM_Hi256);
 	if (mask & XFEATURE_MASK_Hi16_ZMM)
 		perf_regs->h16zmm = get_xsave_addr(xsave, XFEATURE_Hi16_ZMM);
+	if (mask & XFEATURE_MASK_OPMASK)
+		perf_regs->opmask = get_xsave_addr(xsave, XFEATURE_OPMASK);
 }
 
 /*
@@ -1938,6 +1944,8 @@ static void x86_pmu_sample_xregs(struct perf_event *event,
 		mask |= XFEATURE_MASK_ZMM_Hi256;
 	if (event_needs_high16_zmm(event))
 		mask |= XFEATURE_MASK_Hi16_ZMM;
+	if (event_needs_opmask(event))
+		mask |= XFEATURE_MASK_OPMASK;
 
 	mask &= x86_pmu.ext_regs_mask;
 	if ((sample_type & PERF_SAMPLE_REGS_USER) && data->regs_user.abi)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 841c8880e6fd..00f436f5840b 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -177,6 +177,16 @@ static inline bool event_needs_high16_zmm(struct perf_event *event)
 	return false;
 }
 
+static inline bool event_needs_opmask(struct perf_event *event)
+{
+	if (event->attr.sample_simd_regs_enabled &&
+	    (event->attr.sample_simd_pred_reg_intr ||
+	     event->attr.sample_simd_pred_reg_user))
+		return true;
+
+	return false;
+}
+
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
 	int refcnt; /* reference count */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 273840bd7b33..7e8b60bddd5a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -743,6 +743,10 @@ struct x86_perf_regs {
 		u64	*h16zmm_regs;
 		struct avx_512_hi16_state *h16zmm;
 	};
+	union {
+		u64	*opmask_regs;
+		struct avx_512_opmask_state *opmask;
+	};
 };
 
 extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index a889fd92f2f0..f4a1630c1928 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -60,14 +60,19 @@ enum {
 	PERF_X86_SIMD_YMM_REGS      = 16,
 	PERF_X86_SIMD_ZMM_REGS      = 32,
 	PERF_X86_SIMD_VEC_REGS_MAX  = PERF_X86_SIMD_ZMM_REGS,
+
+	PERF_X86_SIMD_OPMASK_REGS   = 8,
+	PERF_X86_SIMD_PRED_REGS_MAX = PERF_X86_SIMD_OPMASK_REGS,
 };
 
+#define PERF_X86_SIMD_PRED_MASK	GENMASK(PERF_X86_SIMD_PRED_REGS_MAX - 1, 0)
 #define PERF_X86_SIMD_VEC_MASK	GENMASK_ULL(PERF_X86_SIMD_VEC_REGS_MAX - 1, 0)
 
 #define PERF_X86_H16ZMM_BASE		16
 
 enum {
 	/* 1 qword = 8 bytes */
+	PERF_X86_OPMASK_QWORDS   = 1,
 	PERF_X86_XMM_QWORDS      = 2,
 	PERF_X86_YMM_QWORDS      = 4,
 	PERF_X86_ZMM_QWORDS      = 8,
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index fe4ff4d2de88..2e3c10dffb35 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -86,8 +86,14 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 	struct x86_perf_regs *perf_regs =
 			container_of(regs, struct x86_perf_regs, regs);
 
-	if (pred)
-		return 0;
+	if (pred) {
+		if (WARN_ON_ONCE(idx >= PERF_X86_SIMD_PRED_REGS_MAX ||
+				 qwords_idx >= PERF_X86_OPMASK_QWORDS))
+			return 0;
+		if (!perf_regs->opmask_regs)
+			return 0;
+		return perf_regs->opmask_regs[idx];
+	}
 
 	if (WARN_ON_ONCE(idx >= PERF_X86_SIMD_VEC_REGS_MAX ||
 			 qwords_idx >= PERF_X86_SIMD_QWORDS_MAX))
@@ -138,7 +144,10 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
 		if (vec_mask & ~PERF_X86_SIMD_VEC_MASK)
 			return -EINVAL;
 	}
-	if (pred_mask)
+
+	if (pred_qwords != PERF_X86_OPMASK_QWORDS)
+		return -EINVAL;
+	if (pred_mask & ~PERF_X86_SIMD_PRED_MASK)
 		return -EINVAL;
 
 	return 0;
-- 
2.34.1


  parent reply	other threads:[~2026-03-24  0:47 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-24  0:40 [Patch v7 00/24] Support SIMD/eGPRs/SSP registers sampling for perf Dapeng Mi
2026-03-24  0:40 ` [Patch v7 01/24] perf/x86: Move hybrid PMU initialization before x86_pmu_starting_cpu() Dapeng Mi
2026-03-24  0:40 ` [Patch v7 02/24] perf/x86/intel: Avoid PEBS event on fixed counters without extended PEBS Dapeng Mi
2026-03-24  0:40 ` [Patch v7 03/24] perf/x86/intel: Enable large PEBS sampling for XMMs Dapeng Mi
2026-03-24  0:40 ` [Patch v7 04/24] perf/x86/intel: Convert x86_perf_regs to per-cpu variables Dapeng Mi
2026-03-24  0:40 ` [Patch v7 05/24] perf: Eliminate duplicate arch-specific functions definations Dapeng Mi
2026-03-24  0:41 ` [Patch v7 06/24] perf/x86: Use x86_perf_regs in the x86 nmi handler Dapeng Mi
2026-03-24  0:41 ` [Patch v7 07/24] perf/x86: Introduce x86-specific x86_pmu_setup_regs_data() Dapeng Mi
2026-03-25  5:18   ` Mi, Dapeng
2026-03-24  0:41 ` [Patch v7 08/24] x86/fpu/xstate: Add xsaves_nmi() helper Dapeng Mi
2026-03-24  0:41 ` [Patch v7 09/24] x86/fpu: Ensure TIF_NEED_FPU_LOAD is set after saving FPU state Dapeng Mi
2026-03-24  0:41 ` [Patch v7 10/24] perf: Move and rename has_extended_regs() for ARCH-specific use Dapeng Mi
2026-03-24  0:41 ` [Patch v7 11/24] perf/x86: Enable XMM Register Sampling for Non-PEBS Events Dapeng Mi
2026-03-25  7:30   ` Mi, Dapeng
2026-03-24  0:41 ` [Patch v7 12/24] perf/x86: Enable XMM register sampling for REGS_USER case Dapeng Mi
2026-03-25  7:58   ` Mi, Dapeng
2026-03-24  0:41 ` [Patch v7 13/24] perf: Add sampling support for SIMD registers Dapeng Mi
2026-03-25  8:44   ` Mi, Dapeng
2026-03-24  0:41 ` [Patch v7 14/24] perf/x86: Enable XMM sampling using sample_simd_vec_reg_* fields Dapeng Mi
2026-03-25  9:01   ` Mi, Dapeng
2026-03-24  0:41 ` [Patch v7 15/24] perf/x86: Enable YMM " Dapeng Mi
2026-03-24  0:41 ` [Patch v7 16/24] perf/x86: Enable ZMM " Dapeng Mi
2026-03-24  0:41 ` Dapeng Mi [this message]
2026-03-24  0:41 ` [Patch v7 18/24] perf: Enhance perf_reg_validate() with simd_enabled argument Dapeng Mi
2026-03-24  0:41 ` [Patch v7 19/24] perf/x86: Enable eGPRs sampling using sample_regs_* fields Dapeng Mi
2026-03-24  0:41 ` [Patch v7 20/24] perf/x86: Enable SSP " Dapeng Mi
2026-03-25  9:25   ` Mi, Dapeng
2026-03-24  0:41 ` [Patch v7 21/24] perf/x86/intel: Enable PERF_PMU_CAP_SIMD_REGS capability Dapeng Mi
2026-03-24  0:41 ` [Patch v7 22/24] perf/x86/intel: Enable arch-PEBS based SIMD/eGPRs/SSP sampling Dapeng Mi
2026-03-24  0:41 ` [Patch v7 23/24] perf/x86: Activate back-to-back NMI detection for arch-PEBS induced NMIs Dapeng Mi
2026-03-24  0:41 ` [Patch v7 24/24] perf/x86/intel: Add sanity check for PEBS fragment size Dapeng Mi
2026-03-24  1:08 ` [Patch v7 00/24] Support SIMD/eGPRs/SSP registers sampling for perf Mi, Dapeng
2026-03-25  9:41 ` Mi, Dapeng

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=20260324004118.3772171-18-dapeng1.mi@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=broonie@kernel.org \
    --cc=dapeng1.mi@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=ravi.bangoria@amd.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.falcon@intel.com \
    --cc=xudong.hao@intel.com \
    --cc=zide.chen@intel.com \
    /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