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 v5 09/19] perf/x86: Enable YMM sampling using sample_simd_vec_reg_* fields
Date: Wed, 3 Dec 2025 14:54:50 +0800 [thread overview]
Message-ID: <20251203065500.2597594-10-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20251203065500.2597594-1-dapeng1.mi@linux.intel.com>
From: Kan Liang <kan.liang@linux.intel.com>
This patch introduces support for sampling YMM registers via the
sample_simd_vec_reg_* fields.
Each YMM register consists of 4 u64 words, assembled from two halves:
XMM (the lower 2 u64 words) and YMMH (the upper 2 u64 words). Although
both XMM and YMMH data can be retrieved with a single xsaves instruction,
they are stored in separate locations. The perf_simd_reg_value() function
is responsible for assembling these halves into a complete YMM register
for output to userspace.
Additionally, sample_simd_vec_reg_qwords should be set to 4 to indicate
YMM 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 | 9 +++++++++
arch/x86/events/perf_event.h | 9 +++++++++
arch/x86/include/asm/perf_event.h | 4 ++++
arch/x86/include/uapi/asm/perf_regs.h | 8 ++++++--
arch/x86/kernel/perf_regs.c | 8 +++++++-
5 files changed, 35 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f7e7e81daaf..b1e62c061d9e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -423,6 +423,9 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
if (valid_mask & XFEATURE_MASK_SSE)
perf_regs->xmm_space = xsave->i387.xmm_space;
+
+ if (valid_mask & XFEATURE_MASK_YMM)
+ perf_regs->ymmh = get_xsave_addr(xsave, XFEATURE_YMM);
}
static void release_ext_regs_buffers(void)
@@ -735,6 +738,9 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event_needs_xmm(event) &&
!(x86_pmu.ext_regs_mask & XFEATURE_MASK_SSE))
return -EINVAL;
+ if (event_needs_ymm(event) &&
+ !(x86_pmu.ext_regs_mask & XFEATURE_MASK_YMM))
+ return -EINVAL;
}
}
@@ -1814,6 +1820,7 @@ inline void x86_pmu_clear_perf_regs(struct pt_regs *regs)
struct x86_perf_regs *perf_regs = container_of(regs, struct x86_perf_regs, regs);
perf_regs->xmm_regs = NULL;
+ perf_regs->ymmh_regs = NULL;
}
static void x86_pmu_setup_basic_regs_data(struct perf_event *event,
@@ -1883,6 +1890,8 @@ static void x86_pmu_sample_ext_regs(struct perf_event *event,
if (event_needs_xmm(event))
mask |= XFEATURE_MASK_SSE;
+ if (event_needs_ymm(event))
+ mask |= XFEATURE_MASK_YMM;
mask &= ~ignore_mask;
if (mask)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index e5d8ad024553..3d4577a1bb7d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -145,6 +145,15 @@ static inline bool event_needs_xmm(struct perf_event *event)
return false;
}
+static inline bool event_needs_ymm(struct perf_event *event)
+{
+ if (event->attr.sample_simd_regs_enabled &&
+ event->attr.sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS)
+ 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 5d623805bf87..25f5ae60f72f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -709,6 +709,10 @@ struct x86_perf_regs {
u64 *xmm_regs;
u32 *xmm_space; /* for xsaves */
};
+ union {
+ u64 *ymmh_regs;
+ struct ymmh_struct *ymmh;
+ };
};
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 c3862e5fdd6d..4fd598785f6d 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -57,19 +57,23 @@ enum perf_event_x86_regs {
enum {
PERF_REG_X86_XMM,
+ PERF_REG_X86_YMM,
PERF_REG_X86_MAX_SIMD_REGS,
};
enum {
PERF_X86_SIMD_XMM_REGS = 16,
- PERF_X86_SIMD_VEC_REGS_MAX = PERF_X86_SIMD_XMM_REGS,
+ PERF_X86_SIMD_YMM_REGS = 16,
+ PERF_X86_SIMD_VEC_REGS_MAX = PERF_X86_SIMD_YMM_REGS,
};
#define PERF_X86_SIMD_VEC_MASK GENMASK_ULL(PERF_X86_SIMD_VEC_REGS_MAX - 1, 0)
enum {
PERF_X86_XMM_QWORDS = 2,
- PERF_X86_SIMD_QWORDS_MAX = PERF_X86_XMM_QWORDS,
+ PERF_X86_YMMH_QWORDS = 2,
+ PERF_X86_YMM_QWORDS = 4,
+ PERF_X86_SIMD_QWORDS_MAX = PERF_X86_YMM_QWORDS,
};
#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 9947a6b5c260..8aa61a18fd71 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -95,6 +95,11 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
return 0;
return perf_regs->xmm_regs[idx * PERF_X86_XMM_QWORDS +
qwords_idx];
+ } else if (qwords_idx < PERF_X86_YMM_QWORDS) {
+ if (!perf_regs->ymmh_regs)
+ return 0;
+ return perf_regs->ymmh_regs[idx * PERF_X86_YMMH_QWORDS +
+ qwords_idx - PERF_X86_XMM_QWORDS];
}
return 0;
@@ -111,7 +116,8 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
if (vec_mask)
return -EINVAL;
} else {
- if (vec_qwords != PERF_X86_XMM_QWORDS)
+ if (vec_qwords != PERF_X86_XMM_QWORDS &&
+ vec_qwords != PERF_X86_YMM_QWORDS)
return -EINVAL;
if (vec_mask & ~PERF_X86_SIMD_VEC_MASK)
return -EINVAL;
--
2.34.1
next prev parent reply other threads:[~2025-12-03 6:58 UTC|newest]
Thread overview: 86+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-12-03 6:54 [Patch v5 00/19] Support SIMD/eGPRs/SSP registers sampling for perf Dapeng Mi
2025-12-03 6:54 ` [Patch v5 01/19] perf: Eliminate duplicate arch-specific functions definations Dapeng Mi
2025-12-03 6:54 ` [Patch v5 02/19] perf/x86: Use x86_perf_regs in the x86 nmi handler Dapeng Mi
2025-12-03 6:54 ` [Patch v5 03/19] perf/x86: Introduce x86-specific x86_pmu_setup_regs_data() Dapeng Mi
2025-12-03 6:54 ` [Patch v5 04/19] x86/fpu/xstate: Add xsaves_nmi() helper Dapeng Mi
2025-12-03 6:54 ` [Patch v5 05/19] perf: Move and rename has_extended_regs() for ARCH-specific use Dapeng Mi
2025-12-03 6:54 ` [Patch v5 06/19] perf/x86: Add support for XMM registers in non-PEBS and REGS_USER Dapeng Mi
2025-12-04 15:17 ` Peter Zijlstra
2025-12-04 15:47 ` Peter Zijlstra
2025-12-05 6:37 ` Mi, Dapeng
2025-12-04 18:59 ` Dave Hansen
2025-12-05 8:42 ` Peter Zijlstra
2025-12-03 6:54 ` [Patch v5 07/19] perf: Add sampling support for SIMD registers Dapeng Mi
2025-12-05 11:07 ` Peter Zijlstra
2025-12-08 5:24 ` Mi, Dapeng
2025-12-05 11:40 ` Peter Zijlstra
2025-12-08 6:00 ` Mi, Dapeng
2025-12-03 6:54 ` [Patch v5 08/19] perf/x86: Enable XMM sampling using sample_simd_vec_reg_* fields Dapeng Mi
2025-12-05 11:25 ` Peter Zijlstra
2025-12-08 6:10 ` Mi, Dapeng
2025-12-03 6:54 ` Dapeng Mi [this message]
2025-12-03 6:54 ` [Patch v5 10/19] perf/x86: Enable ZMM " Dapeng Mi
2025-12-03 6:54 ` [Patch v5 11/19] perf/x86: Enable OPMASK sampling using sample_simd_pred_reg_* fields Dapeng Mi
2025-12-03 6:54 ` [Patch v5 12/19] perf/x86: Enable eGPRs sampling using sample_regs_* fields Dapeng Mi
2025-12-05 12:16 ` Peter Zijlstra
2025-12-08 6:11 ` Mi, Dapeng
2025-12-03 6:54 ` [Patch v5 13/19] perf/x86: Enable SSP " Dapeng Mi
2025-12-05 12:20 ` Peter Zijlstra
2025-12-08 6:21 ` Mi, Dapeng
2025-12-24 5:45 ` Ravi Bangoria
2025-12-24 6:26 ` Mi, Dapeng
2026-01-06 6:55 ` Mi, Dapeng
2025-12-03 6:54 ` [Patch v5 14/19] perf/x86/intel: Enable PERF_PMU_CAP_SIMD_REGS capability Dapeng Mi
2025-12-03 6:54 ` [Patch v5 15/19] perf/x86/intel: Enable arch-PEBS based SIMD/eGPRs/SSP sampling Dapeng Mi
2025-12-03 6:54 ` [Patch v5 16/19] perf/x86: Activate back-to-back NMI detection for arch-PEBS induced NMIs Dapeng Mi
2025-12-05 12:39 ` Peter Zijlstra
2025-12-07 20:44 ` Andi Kleen
2025-12-08 6:46 ` Mi, Dapeng
2025-12-08 8:50 ` Peter Zijlstra
2025-12-08 8:53 ` Mi, Dapeng
2025-12-03 6:54 ` [Patch v5 17/19] perf headers: Sync with the kernel headers Dapeng Mi
2025-12-03 23:43 ` Ian Rogers
2025-12-04 1:37 ` Mi, Dapeng
2025-12-04 7:28 ` Ian Rogers
2026-01-20 7:01 ` Ian Rogers
2026-01-20 7:25 ` Mi, Dapeng
2026-01-20 7:16 ` Ian Rogers
2026-01-20 7:43 ` Mi, Dapeng
2026-01-20 8:00 ` Ian Rogers
2026-01-20 9:22 ` Mi, Dapeng
2026-01-20 18:11 ` Ian Rogers
2026-01-21 2:03 ` Mi, Dapeng
2025-12-03 6:54 ` [Patch v5 18/19] perf parse-regs: Support new SIMD sampling format Dapeng Mi
2025-12-04 0:17 ` Ian Rogers
2025-12-04 2:58 ` Mi, Dapeng
2025-12-04 7:49 ` Ian Rogers
2025-12-04 9:20 ` Mi, Dapeng
2025-12-04 16:16 ` Ian Rogers
2025-12-05 4:00 ` Mi, Dapeng
2025-12-05 6:38 ` Ian Rogers
2025-12-05 8:10 ` Mi, Dapeng
2025-12-05 16:35 ` Ian Rogers
2025-12-08 4:20 ` Mi, Dapeng
2026-01-06 7:27 ` Mi, Dapeng
2026-01-17 5:50 ` Ian Rogers
2026-01-19 6:55 ` Mi, Dapeng
2026-01-19 20:25 ` Ian Rogers
2026-01-20 3:04 ` Mi, Dapeng
2026-01-20 5:16 ` Ian Rogers
2026-01-20 6:46 ` Mi, Dapeng
2026-01-20 6:56 ` Ian Rogers
2026-01-20 7:39 ` Ian Rogers
2026-01-20 9:04 ` Mi, Dapeng
2026-01-20 18:20 ` Ian Rogers
2026-01-21 5:17 ` Mi, Dapeng
2026-01-21 7:09 ` Ian Rogers
2026-01-21 7:52 ` Mi, Dapeng
2026-01-21 14:48 ` Ian Rogers
2026-01-22 1:49 ` Mi, Dapeng
2026-01-22 7:27 ` Ian Rogers
2026-01-22 8:29 ` Mi, Dapeng
2025-12-03 6:55 ` [Patch v5 19/19] perf regs: Enable dumping of SIMD registers Dapeng Mi
2025-12-04 0:24 ` [Patch v5 00/19] Support SIMD/eGPRs/SSP registers sampling for perf Ian Rogers
2025-12-04 3:28 ` Mi, Dapeng
2025-12-16 4:42 ` Ravi Bangoria
2025-12-16 6:59 ` 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=20251203065500.2597594-10-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