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>,
Kan Liang <kan.liang@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,
Dapeng Mi <dapeng1.mi@intel.com>,
Dapeng Mi <dapeng1.mi@linux.intel.com>
Subject: [Patch v4 10/17] perf/x86: Add OPMASK into sample_simd_pred_reg
Date: Thu, 25 Sep 2025 14:12:06 +0800 [thread overview]
Message-ID: <20250925061213.178796-11-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20250925061213.178796-1-dapeng1.mi@linux.intel.com>
From: Kan Liang <kan.liang@linux.intel.com>
The OPMASK is the SIMD's predicate registers. Add them into
sample_simd_pred_reg. The qwords of OPMASK is 1. There are 8 registers.
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 | 9 +++++++++
arch/x86/include/asm/perf_event.h | 4 ++++
arch/x86/include/uapi/asm/perf_regs.h | 8 ++++++++
arch/x86/kernel/perf_regs.c | 19 +++++++++++++++----
5 files changed, 44 insertions(+), 4 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 87572b85d234..c942c6f808ca 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -430,6 +430,8 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
perf_regs->zmmh = get_xsave_addr(xsave, XFEATURE_ZMM_Hi256);
if (valid_mask & XFEATURE_MASK_Hi16_ZMM)
perf_regs->h16zmm = get_xsave_addr(xsave, XFEATURE_Hi16_ZMM);
+ if (valid_mask & XFEATURE_MASK_OPMASK)
+ perf_regs->opmask = get_xsave_addr(xsave, XFEATURE_OPMASK);
}
static void release_ext_regs_buffers(void)
@@ -741,6 +743,9 @@ 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;
}
}
@@ -1900,6 +1905,9 @@ static void x86_pmu_setup_extended_regs_data(struct perf_event *event,
perf_regs->h16zmm_regs = NULL;
if (event_needs_high16_zmm(event))
mask |= XFEATURE_MASK_Hi16_ZMM;
+ perf_regs->opmask_regs = NULL;
+ if (event_needs_opmask(event))
+ mask |= XFEATURE_MASK_OPMASK;
mask &= ~ignore_mask;
if (mask)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 3d6a5739d86e..4584de1c79a3 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -173,6 +173,15 @@ 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 44e89adedc61..d8cac3f9f8df 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -613,6 +613,10 @@ 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 96db454c7923..6f29fd9495a2 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -60,6 +60,9 @@ enum {
PERF_REG_X86_YMM,
PERF_REG_X86_ZMM,
PERF_REG_X86_MAX_SIMD_REGS,
+
+ PERF_REG_X86_OPMASK = 0,
+ PERF_REG_X86_MAX_PRED_REGS = 1,
};
enum {
@@ -68,13 +71,18 @@ enum {
PERF_X86_SIMD_ZMMH_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 PERF_X86_SIMD_ZMMH_REGS
enum {
+ PERF_X86_OPMASK_QWORDS = 1,
PERF_X86_XMM_QWORDS = 2,
PERF_X86_YMMH_QWORDS = 2,
PERF_X86_YMM_QWORDS = 4,
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 8d877b2be957..f6e9cde11ba1 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -83,7 +83,9 @@ void perf_simd_reg_check(struct pt_regs *regs, u64 ignore,
!perf_regs->h16zmm_regs)
*nr_vectors = PERF_X86_H16ZMM_BASE;
- *nr_pred = 0;
+ if (!(ignore & XFEATURE_MASK_OPMASK) &&
+ *nr_pred && !perf_regs->opmask_regs)
+ *nr_pred = 0;
}
u64 perf_reg_value(struct pt_regs *regs, int idx)
@@ -112,8 +114,14 @@ 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);
int index;
- 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))
@@ -162,7 +170,10 @@ 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
next prev parent reply other threads:[~2025-09-25 6:15 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-25 6:11 [Patch v4 00/17] Support vector and more extended registers in perf Dapeng Mi
2025-09-25 6:11 ` [Patch v4 01/17] perf/x86: Use x86_perf_regs in the x86 nmi handler Dapeng Mi
2025-09-25 6:11 ` [Patch v4 02/17] perf/x86: Setup the regs data Dapeng Mi
2025-09-25 6:11 ` [Patch v4 03/17] x86/fpu/xstate: Add xsaves_nmi Dapeng Mi
2025-09-25 15:07 ` Dave Hansen
2025-09-28 5:31 ` Mi, Dapeng
2025-09-29 19:01 ` Dave Hansen
2025-09-30 2:44 ` Mi, Dapeng
2025-09-25 6:12 ` [Patch v4 04/17] perf: Move has_extended_regs() to header file Dapeng Mi
2025-09-25 6:12 ` [Patch v4 05/17] perf/x86: Support XMM register for non-PEBS and REGS_USER Dapeng Mi
2025-09-25 6:12 ` [Patch v4 06/17] perf: Support SIMD registers Dapeng Mi
2025-09-25 6:12 ` [Patch v4 07/17] perf/x86: Move XMM to sample_simd_vec_regs Dapeng Mi
2025-09-25 6:12 ` [Patch v4 08/17] perf/x86: Add YMM into sample_simd_vec_regs Dapeng Mi
2025-09-25 6:12 ` [Patch v4 09/17] perf/x86: Add ZMM " Dapeng Mi
2025-09-25 6:12 ` Dapeng Mi [this message]
2025-09-25 6:12 ` [Patch v4 11/17] perf/x86: Add eGPRs into sample_regs Dapeng Mi
2025-09-25 6:12 ` [Patch v4 12/17] perf/x86: Add SSP " Dapeng Mi
2025-09-25 6:12 ` [Patch v4 13/17] perf/x86/intel: Enable PERF_PMU_CAP_SIMD_REGS Dapeng Mi
2025-09-25 6:12 ` [Patch v4 14/17] perf tools: Only support legacy regs for the PT and PERF_REGS_MASK Dapeng Mi
2025-09-25 6:12 ` [Patch v4 15/17] perf tools: headers: Sync with the kernel sources Dapeng Mi
2025-09-25 6:12 ` [Patch v4 16/17] perf tools: parse-regs: Support the new SIMD format Dapeng Mi
2025-09-25 6:12 ` [Patch v4 17/17] perf tools: regs: Support to dump regs for PERF_SAMPLE_REGS_ABI_SIMD Dapeng Mi
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=20250925061213.178796-11-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 \
/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;
as well as URLs for NNTP newsgroup(s).