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 17/17] perf tools: regs: Support to dump regs for PERF_SAMPLE_REGS_ABI_SIMD
Date: Thu, 25 Sep 2025 14:12:13 +0800 [thread overview]
Message-ID: <20250925061213.178796-18-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>
Support the new PERF_SAMPLE_REGS_ABI_SIMD ABI. Dump the data to
perf report -D. Only the superset of the vector registers is displayed
for now.
Example:
$perf record -e cycles:p -IXMM,YMM,OPMASK,SSP ./test
$perf report -D
... ...
237538985992962 0x454d0 [0x480]: PERF_RECORD_SAMPLE(IP, 0x1):
179370/179370: 0xffffffff969627fc period: 124999 addr: 0
... intr regs: mask 0x20000000000 ABI 64-bit
.... SSP 0x0000000000000000
... SIMD ABI nr_vectors 32 vector_qwords 4 nr_pred 8 pred_qwords 1
.... YMM [0] 0x0000000000004000
.... YMM [0] 0x000055e828695270
.... YMM [0] 0x0000000000000000
.... YMM [0] 0x0000000000000000
.... YMM [1] 0x000055e8286990e0
.... YMM [1] 0x000055e828698dd0
.... YMM [1] 0x0000000000000000
.... YMM [1] 0x0000000000000000
... ...
.... YMM [31] 0x0000000000000000
.... YMM [31] 0x0000000000000000
.... YMM [31] 0x0000000000000000
.... YMM [31] 0x0000000000000000
.... OPMASK[0] 0x0000000000100221
.... OPMASK[1] 0x0000000000000020
.... OPMASK[2] 0x000000007fffffff
.... OPMASK[3] 0x0000000000000000
.... OPMASK[4] 0x0000000000000000
.... OPMASK[5] 0x0000000000000000
.... OPMASK[6] 0x0000000000000000
.... OPMASK[7] 0x0000000000000000
... ...
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>
---
tools/perf/util/evsel.c | 20 +++++
.../perf/util/perf-regs-arch/perf_regs_x86.c | 43 ++++++++++
tools/perf/util/sample.h | 10 +++
tools/perf/util/session.c | 78 +++++++++++++++++--
4 files changed, 143 insertions(+), 8 deletions(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 98996e672794..e7404b2e1e24 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3259,6 +3259,16 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
regs->mask = mask;
regs->regs = (u64 *)array;
array = (void *)array + sz;
+
+ if (regs->abi & PERF_SAMPLE_REGS_ABI_SIMD) {
+ regs->config = *(u64 *)array;
+ array = (void *)array + sizeof(u64);
+ regs->data = (u64 *)array;
+ sz = (regs->nr_vectors * regs->vector_qwords +
+ regs->nr_pred * regs->pred_qwords) * sizeof(u64);
+ OVERFLOW_CHECK(array, sz, max_size);
+ array = (void *)array + sz;
+ }
}
}
@@ -3316,6 +3326,16 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
regs->mask = mask;
regs->regs = (u64 *)array;
array = (void *)array + sz;
+
+ if (regs->abi & PERF_SAMPLE_REGS_ABI_SIMD) {
+ regs->config = *(u64 *)array;
+ array = (void *)array + sizeof(u64);
+ regs->data = (u64 *)array;
+ sz = (regs->nr_vectors * regs->vector_qwords +
+ regs->nr_pred * regs->pred_qwords) * sizeof(u64);
+ OVERFLOW_CHECK(array, sz, max_size);
+ array = (void *)array + sz;
+ }
}
}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_x86.c b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
index 708954a9d35d..32dac438b12d 100644
--- a/tools/perf/util/perf-regs-arch/perf_regs_x86.c
+++ b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
@@ -5,6 +5,49 @@
const char *__perf_reg_name_x86(int id)
{
+ if (id > PERF_REG_X86_R15 && arch__intr_simd_reg_mask()) {
+ switch (id) {
+ case PERF_REG_X86_R16:
+ return "R16";
+ case PERF_REG_X86_R17:
+ return "R17";
+ case PERF_REG_X86_R18:
+ return "R18";
+ case PERF_REG_X86_R19:
+ return "R19";
+ case PERF_REG_X86_R20:
+ return "R20";
+ case PERF_REG_X86_R21:
+ return "R21";
+ case PERF_REG_X86_R22:
+ return "R22";
+ case PERF_REG_X86_R23:
+ return "R23";
+ case PERF_REG_X86_R24:
+ return "R24";
+ case PERF_REG_X86_R25:
+ return "R25";
+ case PERF_REG_X86_R26:
+ return "R26";
+ case PERF_REG_X86_R27:
+ return "R27";
+ case PERF_REG_X86_R28:
+ return "R28";
+ case PERF_REG_X86_R29:
+ return "R29";
+ case PERF_REG_X86_R30:
+ return "R30";
+ case PERF_REG_X86_R31:
+ return "R31";
+ case PERF_REG_X86_SSP:
+ return "SSP";
+ default:
+ return NULL;
+ }
+
+ return NULL;
+ }
+
switch (id) {
case PERF_REG_X86_AX:
return "AX";
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index fae834144ef4..3b247e0e8242 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -12,6 +12,16 @@ struct regs_dump {
u64 abi;
u64 mask;
u64 *regs;
+ union {
+ u64 config;
+ struct {
+ u16 nr_vectors;
+ u16 vector_qwords;
+ u16 nr_pred;
+ u16 pred_qwords;
+ };
+ };
+ u64 *data;
/* Cached values/mask filled by first register access. */
u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE];
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 26ae078278cd..4cf6afa37d79 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -927,18 +927,78 @@ static void regs_dump__printf(u64 mask, u64 *regs, const char *arch)
}
}
-static const char *regs_abi[] = {
- [PERF_SAMPLE_REGS_ABI_NONE] = "none",
- [PERF_SAMPLE_REGS_ABI_32] = "32-bit",
- [PERF_SAMPLE_REGS_ABI_64] = "64-bit",
-};
+static void simd_regs_dump__printf(struct regs_dump *regs, bool intr)
+{
+ const char *name = "unknown";
+ const struct sample_reg *r;
+ int i, idx = 0;
+ u16 qwords;
+ int reg_idx;
+
+ if (!(regs->abi & PERF_SAMPLE_REGS_ABI_SIMD))
+ return;
+
+ printf("... SIMD ABI nr_vectors %d vector_qwords %d nr_pred %d pred_qwords %d\n",
+ regs->nr_vectors, regs->vector_qwords,
+ regs->nr_pred, regs->pred_qwords);
+
+ for (r = arch__sample_simd_reg_masks(); r->name; r++) {
+ if (!fls64(r->mask))
+ continue;
+ reg_idx = fls64(r->mask) - 1;
+ if (intr)
+ arch__intr_simd_reg_bitmap_qwords(reg_idx, &qwords);
+ else
+ arch__user_simd_reg_bitmap_qwords(reg_idx, &qwords);
+ if (regs->vector_qwords == qwords) {
+ name = r->name;
+ break;
+ }
+ }
+
+ for (i = 0; i < regs->nr_vectors; i++) {
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+ if (regs->vector_qwords > 2) {
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+ }
+ if (regs->vector_qwords > 4) {
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+ }
+ }
+
+ name = "unknown";
+ for (r = arch__sample_pred_reg_masks(); r->name; r++) {
+ if (!fls64(r->mask))
+ continue;
+ reg_idx = fls64(r->mask) - 1;
+ if (intr)
+ arch__intr_pred_reg_bitmap_qwords(reg_idx, &qwords);
+ else
+ arch__user_pred_reg_bitmap_qwords(reg_idx, &qwords);
+ if (regs->pred_qwords == qwords) {
+ name = r->name;
+ break;
+ }
+ }
+ for (i = 0; i < regs->nr_pred; i++)
+ printf(".... %-5s[%d] 0x%016" PRIx64 "\n", name, i, regs->data[idx++]);
+}
static inline const char *regs_dump_abi(struct regs_dump *d)
{
- if (d->abi > PERF_SAMPLE_REGS_ABI_64)
- return "unknown";
+ if (!d->abi)
+ return "none";
+ if (d->abi & PERF_SAMPLE_REGS_ABI_32)
+ return "32-bit";
+ else if (d->abi & PERF_SAMPLE_REGS_ABI_64)
+ return "64-bit";
- return regs_abi[d->abi];
+ return "unknown";
}
static void regs__printf(const char *type, struct regs_dump *regs, const char *arch)
@@ -964,6 +1024,7 @@ static void regs_user__printf(struct perf_sample *sample, const char *arch)
if (user_regs->regs)
regs__printf("user", user_regs, arch);
+ simd_regs_dump__printf(user_regs, false);
}
static void regs_intr__printf(struct perf_sample *sample, const char *arch)
@@ -977,6 +1038,7 @@ static void regs_intr__printf(struct perf_sample *sample, const char *arch)
if (intr_regs->regs)
regs__printf("intr", intr_regs, arch);
+ simd_regs_dump__printf(intr_regs, true);
}
static void stack_user__printf(struct stack_dump *dump)
--
2.34.1
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 ` [Patch v4 10/17] perf/x86: Add OPMASK into sample_simd_pred_reg Dapeng Mi
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 ` Dapeng Mi [this message]
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=20250925061213.178796-18-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 \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.