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 v6 15/22] perf/x86: Enable ZMM sampling using sample_simd_vec_reg_* fields
Date: Mon,  9 Feb 2026 15:20:40 +0800	[thread overview]
Message-ID: <20260209072047.2180332-16-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20260209072047.2180332-1-dapeng1.mi@linux.intel.com>

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

This patch adds support for sampling ZMM registers via the
sample_simd_vec_reg_* fields.

Each ZMM register consists of 8 u64 words. Current x86 hardware supports
up to 32 ZMM registers. For ZMM registers from ZMM0 to ZMM15, they are
assembled from three parts: XMM (the lower 2 u64 words),
YMMH (the middle 2 u64 words), and ZMMH (the upper 4 u64 words). The
perf_simd_reg_value() function is responsible for assembling these three
parts into a complete ZMM register for output to userspace.

For ZMM registers ZMM16 to ZMM31, each register can be read as a whole
and directly outputted to userspace.

Additionally, sample_simd_vec_reg_qwords should be set to 8 to indicate
ZMM 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                | 16 ++++++++++++++++
 arch/x86/events/perf_event.h          | 19 +++++++++++++++++++
 arch/x86/include/asm/perf_event.h     |  8 ++++++++
 arch/x86/include/uapi/asm/perf_regs.h |  8 ++++++--
 arch/x86/kernel/perf_regs.c           | 16 +++++++++++++++-
 5 files changed, 64 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e80a392e30b0..b279dfc1c97f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -723,6 +723,12 @@ int x86_pmu_hw_config(struct perf_event *event)
 			if (event_needs_ymm(event) &&
 			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_YMM))
 				return -EINVAL;
+			if (event_needs_low16_zmm(event) &&
+			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_ZMM_Hi256))
+				return -EINVAL;
+			if (event_needs_high16_zmm(event) &&
+			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_Hi16_ZMM))
+				return -EINVAL;
 		}
 	}
 
@@ -1848,6 +1854,8 @@ inline void x86_pmu_clear_perf_regs(struct pt_regs *regs)
 
 	perf_regs->xmm_regs = NULL;
 	perf_regs->ymmh_regs = NULL;
+	perf_regs->zmmh_regs = NULL;
+	perf_regs->h16zmm_regs = NULL;
 }
 
 static inline void __x86_pmu_sample_ext_regs(u64 mask)
@@ -1875,6 +1883,10 @@ static inline void x86_pmu_update_ext_regs(struct x86_perf_regs *perf_regs,
 		perf_regs->xmm_space = xsave->i387.xmm_space;
 	if (mask & XFEATURE_MASK_YMM)
 		perf_regs->ymmh = get_xsave_addr(xsave, XFEATURE_YMM);
+	if (mask & XFEATURE_MASK_ZMM_Hi256)
+		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);
 }
 
 /*
@@ -1936,6 +1948,10 @@ static void x86_pmu_sample_extended_regs(struct perf_event *event,
 		mask |= XFEATURE_MASK_SSE;
 	if (event_needs_ymm(event))
 		mask |= XFEATURE_MASK_YMM;
+	if (event_needs_low16_zmm(event))
+		mask |= XFEATURE_MASK_ZMM_Hi256;
+	if (event_needs_high16_zmm(event))
+		mask |= XFEATURE_MASK_Hi16_ZMM;
 
 	mask &= x86_pmu.ext_regs_mask;
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 4f18ba6ef0c4..f6379adb8e83 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -158,6 +158,25 @@ static inline bool event_needs_ymm(struct perf_event *event)
 	return false;
 }
 
+static inline bool event_needs_low16_zmm(struct perf_event *event)
+{
+	if (event->attr.sample_simd_regs_enabled &&
+	    event->attr.sample_simd_vec_reg_qwords >= PERF_X86_ZMM_QWORDS)
+		return true;
+
+	return false;
+}
+
+static inline bool event_needs_high16_zmm(struct perf_event *event)
+{
+	if (event->attr.sample_simd_regs_enabled &&
+	    (fls64(event->attr.sample_simd_vec_reg_intr) > PERF_X86_H16ZMM_BASE ||
+	     fls64(event->attr.sample_simd_vec_reg_user) > PERF_X86_H16ZMM_BASE))
+		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 bffe47851676..a57386ae70d9 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -718,6 +718,14 @@ struct x86_perf_regs {
 		u64	*ymmh_regs;
 		struct ymmh_struct *ymmh;
 	};
+	union {
+		u64	*zmmh_regs;
+		struct avx_512_zmm_uppers_state *zmmh;
+	};
+	union {
+		u64	*h16zmm_regs;
+		struct avx_512_hi16_state *h16zmm;
+	};
 };
 
 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 eac11a29fce6..d6362bc8d125 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -58,15 +58,19 @@ enum perf_event_x86_regs {
 enum {
 	PERF_X86_SIMD_XMM_REGS      = 16,
 	PERF_X86_SIMD_YMM_REGS      = 16,
-	PERF_X86_SIMD_VEC_REGS_MAX  = PERF_X86_SIMD_YMM_REGS,
+	PERF_X86_SIMD_ZMM_REGS      = 32,
+	PERF_X86_SIMD_VEC_REGS_MAX  = PERF_X86_SIMD_ZMM_REGS,
 };
 
 #define PERF_X86_SIMD_VEC_MASK	GENMASK_ULL(PERF_X86_SIMD_VEC_REGS_MAX - 1, 0)
 
+#define PERF_X86_H16ZMM_BASE		16
+
 enum {
 	PERF_X86_XMM_QWORDS      = 2,
 	PERF_X86_YMM_QWORDS      = 4,
-	PERF_X86_SIMD_QWORDS_MAX = PERF_X86_YMM_QWORDS,
+	PERF_X86_ZMM_QWORDS      = 8,
+	PERF_X86_SIMD_QWORDS_MAX = PERF_X86_ZMM_QWORDS,
 };
 
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 4062a679cc5b..fe4ff4d2de88 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 }
 
 #define PERF_X86_YMMH_QWORDS	(PERF_X86_YMM_QWORDS / 2)
+#define PERF_X86_ZMMH_QWORDS	(PERF_X86_ZMM_QWORDS / 2)
 
 u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 			u16 qwords_idx, bool pred)
@@ -92,6 +93,13 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 			 qwords_idx >= PERF_X86_SIMD_QWORDS_MAX))
 		return 0;
 
+	if (idx >= PERF_X86_H16ZMM_BASE) {
+		if (!perf_regs->h16zmm_regs)
+			return 0;
+		return perf_regs->h16zmm_regs[(idx - PERF_X86_H16ZMM_BASE) *
+					PERF_X86_ZMM_QWORDS + qwords_idx];
+	}
+
 	if (qwords_idx < PERF_X86_XMM_QWORDS) {
 		if (!perf_regs->xmm_regs)
 			return 0;
@@ -102,6 +110,11 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 			return 0;
 		return perf_regs->ymmh_regs[idx * PERF_X86_YMMH_QWORDS +
 					    qwords_idx - PERF_X86_XMM_QWORDS];
+	} else if (qwords_idx < PERF_X86_ZMM_QWORDS) {
+		if (!perf_regs->zmmh_regs)
+			return 0;
+		return perf_regs->zmmh_regs[idx * PERF_X86_ZMMH_QWORDS +
+					    qwords_idx - PERF_X86_YMM_QWORDS];
 	}
 
 	return 0;
@@ -119,7 +132,8 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
 			return -EINVAL;
 	} else {
 		if (vec_qwords != PERF_X86_XMM_QWORDS &&
-		    vec_qwords != PERF_X86_YMM_QWORDS)
+		    vec_qwords != PERF_X86_YMM_QWORDS &&
+		    vec_qwords != PERF_X86_ZMM_QWORDS)
 			return -EINVAL;
 		if (vec_mask & ~PERF_X86_SIMD_VEC_MASK)
 			return -EINVAL;
-- 
2.34.1


  parent reply	other threads:[~2026-02-09  7:26 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-09  7:20 [Patch v6 00/22] Support SIMD/eGPRs/SSP registers sampling for perf Dapeng Mi
2026-02-09  7:20 ` [Patch v6 01/22] perf/x86/intel: Restrict PEBS_ENABLE writes to PEBS-capable counters Dapeng Mi
2026-02-10 15:36   ` Peter Zijlstra
2026-02-11  5:47     ` Mi, Dapeng
2026-02-09  7:20 ` [Patch v6 02/22] perf/x86/intel: Enable large PEBS sampling for XMMs Dapeng Mi
2026-02-09  7:20 ` [Patch v6 03/22] perf/x86/intel: Convert x86_perf_regs to per-cpu variables Dapeng Mi
2026-02-09  7:20 ` [Patch v6 04/22] perf: Eliminate duplicate arch-specific functions definations Dapeng Mi
2026-02-09  7:20 ` [Patch v6 05/22] perf/x86: Use x86_perf_regs in the x86 nmi handler Dapeng Mi
2026-02-10 18:40   ` Peter Zijlstra
2026-02-11  6:26     ` Mi, Dapeng
2026-02-09  7:20 ` [Patch v6 06/22] perf/x86: Introduce x86-specific x86_pmu_setup_regs_data() Dapeng Mi
2026-02-09  7:20 ` [Patch v6 07/22] x86/fpu/xstate: Add xsaves_nmi() helper Dapeng Mi
2026-02-09  7:20 ` [Patch v6 08/22] x86/fpu: Ensure TIF_NEED_FPU_LOAD is set after saving FPU state Dapeng Mi
2026-02-11 19:39   ` Chang S. Bae
2026-02-11 19:55     ` Dave Hansen
2026-02-24  6:50       ` Mi, Dapeng
2026-02-25 13:02       ` Peter Zijlstra
2026-02-24  5:35     ` Mi, Dapeng
2026-02-24 19:13       ` Chang S. Bae
2026-02-25  0:35         ` Mi, Dapeng
2026-02-09  7:20 ` [Patch v6 09/22] perf: Move and rename has_extended_regs() for ARCH-specific use Dapeng Mi
2026-02-09  7:20 ` [Patch v6 10/22] perf/x86: Enable XMM Register Sampling for Non-PEBS Events Dapeng Mi
2026-02-15 23:58   ` Chang S. Bae
2026-02-24  7:11     ` Mi, Dapeng
2026-02-24 19:13       ` Chang S. Bae
2026-02-25  0:55         ` Mi, Dapeng
2026-02-25  1:11           ` Chang S. Bae
2026-02-25  1:36             ` Mi, Dapeng
2026-02-25  3:14               ` Chang S. Bae
2026-02-25  6:13                 ` Mi, Dapeng
2026-02-09  7:20 ` [Patch v6 11/22] perf/x86: Enable XMM register sampling for REGS_USER case Dapeng Mi
2026-02-09  7:20 ` [Patch v6 12/22] perf: Add sampling support for SIMD registers Dapeng Mi
2026-02-10 20:04   ` Peter Zijlstra
2026-02-11  6:56     ` Mi, Dapeng
2026-02-09  7:20 ` [Patch v6 13/22] perf/x86: Enable XMM sampling using sample_simd_vec_reg_* fields Dapeng Mi
2026-02-09  7:20 ` [Patch v6 14/22] perf/x86: Enable YMM " Dapeng Mi
2026-02-09  7:20 ` Dapeng Mi [this message]
2026-02-09  7:20 ` [Patch v6 16/22] perf/x86: Enable OPMASK sampling using sample_simd_pred_reg_* fields Dapeng Mi
2026-02-09  7:20 ` [Patch v6 17/22] perf: Enhance perf_reg_validate() with simd_enabled argument Dapeng Mi
2026-02-09  7:20 ` [Patch v6 18/22] perf/x86: Enable eGPRs sampling using sample_regs_* fields Dapeng Mi
2026-02-09  7:20 ` [Patch v6 19/22] perf/x86: Enable SSP " Dapeng Mi
2026-02-09  7:20 ` [Patch v6 20/22] perf/x86/intel: Enable PERF_PMU_CAP_SIMD_REGS capability Dapeng Mi
2026-02-09  7:20 ` [Patch v6 21/22] perf/x86/intel: Enable arch-PEBS based SIMD/eGPRs/SSP sampling Dapeng Mi
2026-02-09  7:20 ` [Patch v6 22/22] perf/x86: Activate back-to-back NMI detection for arch-PEBS induced NMIs Dapeng Mi
2026-02-09  8:48 ` [Patch v6 00/22] Support SIMD/eGPRs/SSP registers sampling for perf 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=20260209072047.2180332-16-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