From nobody Tue Jun 16 19:33:18 2026 Received: from mail-pl1-f201.google.com (mail-pl1-f201.google.com [209.85.214.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 0981E41C2F4 for ; Wed, 29 Apr 2026 18:12:10 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777486332; cv=none; b=C9z8JuEVkOEiub9rrvNzR8QGcJ1wzFbeVaBAWJpiT+XOLeQIh2jr0aeel2P8IxmAwtTzVOeMSTee2psbRIueSV3PM68dgxhRxYDoxqzLwrs3yuUiu6Pl1MC3Azz7zxOPYl6Zg2SkjMGXozYIt2l92HGX0yWaaizEnoVtuih3b6M= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777486332; c=relaxed/simple; bh=lAl3czDkD/f+DrcoXOo6L7I6tPLct5f+0+ILlwcgu0c=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=fzLKhVfxzhtyecGJIwGc5GcvRsHGXdwDt6duYK0hedveBxbKRK3TCN+m4VMKpqJkex4NPmjJWGybvDzoJCmyEowR0L6KXHs95lMJ8aXEYQ31FltJhnmcLYl6HOibjzYVoLBthsfa1gnEO049eaCPleyXmnugoJW7314uaWNzB/g= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--irogers.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=gLPm+enX; arc=none smtp.client-ip=209.85.214.201 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--irogers.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="gLPm+enX" Received: by mail-pl1-f201.google.com with SMTP id d9443c01a7336-2b99eb06178so788845ad.2 for ; Wed, 29 Apr 2026 11:12:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20251104; t=1777486330; x=1778091130; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=d/8huAkyQztqOOP4DJuZU1ZW2j6w3MCnFzNy+nKN1Kk=; b=gLPm+enXcv3IW4C1QsFzTPHapcXz2u+dsfRlpBiTpOss/UFYSsw33vzY/UczUQCIpk +P6MKNjWx9Ep3Fnmve7fl7fDeVUsRHBucY9rOSd54+evITDCUoJwZnXk7A+aDScIyQad mUeY6tJWkEWZe0urATlZya+ewA1/V43NBw24UJcHn+d+H/538OBWA1nObzqQSGjicn8H CxEeyB0agi4yrWsThdvDh+DY80Cky7nU2Wbb8UO/c0ptKX4USymkmWMOLnkc1xvu/ucC zen9clr8Ob+YRoYshzpMfruo4NoIh4q6HCCzKjGdssW7lLYZw49FpUUa7bAg+ifr+bZC Bs0Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1777486330; x=1778091130; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=d/8huAkyQztqOOP4DJuZU1ZW2j6w3MCnFzNy+nKN1Kk=; b=NkPxqWaQUIRvfhqbkH2Mc8aF8icRGZ+yZ4MPh9jM9tleahl4Y0YfUbSEflDrv+FYc4 oWpI4w7Uf8kgOaobY5if2qmwvhFCbUysDZ7Dy+aqHQivI0VH+LEZRxhsX0d2qj6v6pgZ p2A1lJ0+V/4LpWHqqADPadjwxVYaS5jvNM3PEJWYLJUt5igwG5T32VQk66KWoV7J2WOB TvvPlRzgmkbxbfEWKmHs1SBSaVRDchALF2tAkzu1l04iWgiyhWDVtbaj59gBzp0Woeqr 1PKa3OuLT/UBnEApIKGEl2WI9uzv9oLxbnsZEooKJ8vuFdrj9dmBRUkzDyaKI+uhivEo f97w== X-Forwarded-Encrypted: i=1; AFNElJ9yqbstVQm1V3kNY9dLPKaQOArP4xJ62XG43yzQydKuzJCOSgdwQMpdV7SmoI931R06gK8pAhaNAghwc4w=@vger.kernel.org X-Gm-Message-State: AOJu0YydWtEucil0wYngLFrb9YKHmh2DNDYtdBkG+TFcN5KTBS2w4aoB Yt69ZC88Pvd2IBNwqiiYKxbqQDS2Gd9bP74XxcuJqjkLXJXZxHaabq9T3P5WviivZGGwu2DQnMl bQAaU9lSVSA== X-Received: from pgam24.prod.google.com ([2002:a05:6a02:2b58:b0:c79:26bb:5541]) (user=irogers job=prod-delivery.src-stubby-dispatcher) by 2002:a05:6a20:3d19:b0:3a2:e089:ae56 with SMTP id adf61e73a8af0-3a39c2c28f2mr9579080637.52.1777486330077; Wed, 29 Apr 2026 11:12:10 -0700 (PDT) Date: Wed, 29 Apr 2026 11:11:35 -0700 In-Reply-To: <20260429181136.2712655-1-irogers@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20260428070328.1880314-1-irogers@google.com> <20260429181136.2712655-1-irogers@google.com> X-Mailer: git-send-email 2.54.0.545.g6539524ca2-goog Message-ID: <20260429181136.2712655-2-irogers@google.com> Subject: [PATCH v2 1/2] perf event: Fix size of synthesized sample with branch stacks From: Ian Rogers To: acme@kernel.org, adrian.hunter@intel.com, dapeng1.mi@linux.intel.com, namhyung@kernel.org, thomas.falcon@intel.com Cc: james.clark@linaro.org, leo.yan@linux.dev, linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, mingo@redhat.com, peterz@infradead.org, ravi.bangoria@amd.com, Ian Rogers Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Synthesizing branch stacks for Intel-PT highlighed an issue where PERF_SAMPLE_BRANCH_HW_INDEX was assumed to always be set in the perf_event_attr branch_sample_type. This caused an incorrect size calculation. Fix the writing of the nr and hw_idx values during sample event synthesis. Assisted-by: Gemini:gemini-3.1-pro-preview Signed-off-by: Ian Rogers Acked-by: Namhyung Kim --- tools/perf/bench/inject-buildid.c | 9 ++++++--- tools/perf/builtin-inject.c | 12 +++++++++--- tools/perf/tests/dlfilter-test.c | 8 ++++++-- tools/perf/tests/sample-parsing.c | 5 +++-- tools/perf/util/arm-spe.c | 7 +++++-- tools/perf/util/cs-etm.c | 6 ++++-- tools/perf/util/intel-bts.c | 3 ++- tools/perf/util/intel-pt.c | 7 +++++-- tools/perf/util/synthetic-events.c | 25 ++++++++++++++++++------- tools/perf/util/synthetic-events.h | 6 ++++-- 10 files changed, 62 insertions(+), 26 deletions(-) diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-bu= ildid.c index aad572a78d7f..bfd2c5ec9488 100644 --- a/tools/perf/bench/inject-buildid.c +++ b/tools/perf/bench/inject-buildid.c @@ -228,9 +228,12 @@ static ssize_t synthesize_sample(struct bench_data *da= ta, struct bench_dso *dso, =20 event.header.type =3D PERF_RECORD_SAMPLE; event.header.misc =3D PERF_RECORD_MISC_USER; - event.header.size =3D perf_event__sample_event_size(&sample, bench_sample= _type, 0); - - perf_event__synthesize_sample(&event, bench_sample_type, 0, &sample); + event.header.size =3D perf_event__sample_event_size(&sample, bench_sample= _type, + /*read_format=3D*/0, + /*branch_sample_type=3D*/0); + perf_event__synthesize_sample(&event, bench_sample_type, + /*read_format=3D*/0, + /*branch_sample_type=3D*/0, &sample); =20 return writen(data->input_pipe[1], &event, event.header.size); } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index f174bc69cec4..0c51cb4250d1 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -463,8 +463,13 @@ static int perf_event__convert_sample_callchain(const = struct perf_tool *tool, /* remove sample_type {STACK,REGS}_USER for synthesize */ sample_type &=3D ~(PERF_SAMPLE_STACK_USER | PERF_SAMPLE_REGS_USER); =20 - perf_event__synthesize_sample(event_copy, sample_type, - evsel->core.attr.read_format, sample); + ret =3D perf_event__synthesize_sample(event_copy, evsel->core.attr.sample= _type, + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type, sample); + if (ret) { + pr_err("Failed to synthesize sample\n"); + return ret; + } return perf_event__repipe_synth(tool, event_copy); } =20 @@ -1100,7 +1105,8 @@ static int perf_inject__sched_stat(const struct perf_= tool *tool, sample_sw.period =3D sample->period; sample_sw.time =3D sample->time; perf_event__synthesize_sample(event_sw, evsel->core.attr.sample_type, - evsel->core.attr.read_format, &sample_sw); + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type, &sample_sw); build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine); ret =3D perf_event__repipe(tool, event_sw, &sample_sw, machine); perf_sample__exit(&sample_sw); diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-t= est.c index e63790c61d53..204663571943 100644 --- a/tools/perf/tests/dlfilter-test.c +++ b/tools/perf/tests/dlfilter-test.c @@ -188,8 +188,12 @@ static int write_sample(struct test_data *td, u64 samp= le_type, u64 id, pid_t pid =20 event->header.type =3D PERF_RECORD_SAMPLE; event->header.misc =3D PERF_RECORD_MISC_USER; - event->header.size =3D perf_event__sample_event_size(&sample, sample_type= , 0); - err =3D perf_event__synthesize_sample(event, sample_type, 0, &sample); + event->header.size =3D perf_event__sample_event_size(&sample, sample_type, + /*read_format=3D*/0, + /*branch_sample_type=3D*/0); + err =3D perf_event__synthesize_sample(event, sample_type, + /*read_format=3D*/0, + /*branch_sample_type=3D*/0, &sample); if (err) return test_result("perf_event__synthesize_sample() failed", TEST_FAIL); =20 diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-pa= rsing.c index a7327c942ca2..55f0b73ca20e 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -310,7 +310,8 @@ static int do_test(u64 sample_type, u64 sample_regs, u6= 4 read_format) sample.read.one.lost =3D 1; } =20 - sz =3D perf_event__sample_event_size(&sample, sample_type, read_format); + sz =3D perf_event__sample_event_size(&sample, sample_type, read_format, + evsel.core.attr.branch_sample_type); bufsz =3D sz + 4096; /* Add a bit for overrun checking */ event =3D malloc(bufsz); if (!event) { @@ -324,7 +325,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u6= 4 read_format) event->header.size =3D sz; =20 err =3D perf_event__synthesize_sample(event, sample_type, read_format, - &sample); + evsel.core.attr.branch_sample_type, &sample); if (err) { pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", "perf_event__synthesize_sample", sample_type, err); diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index e5835042acdf..c4ed9f10e731 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -484,8 +484,11 @@ static void arm_spe__prep_branch_stack(struct arm_spe_= queue *speq) =20 static int arm_spe__inject_event(union perf_event *event, struct perf_samp= le *sample, u64 type) { - event->header.size =3D perf_event__sample_event_size(sample, type, 0); - return perf_event__synthesize_sample(event, type, 0, sample); + event->header.type =3D PERF_RECORD_SAMPLE; + event->header.size =3D perf_event__sample_event_size(sample, type, /*read= _format=3D*/0, + /*branch_sample_type=3D*/0); + return perf_event__synthesize_sample(event, type, /*read_format=3D*/0, + /*branch_sample_type=3D*/0, sample); } =20 static inline int diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 8a639d2e51a4..1ebc1a6a5e75 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1425,8 +1425,10 @@ static void cs_etm__update_last_branch_rb(struct cs_= etm_queue *etmq, static int cs_etm__inject_event(union perf_event *event, struct perf_sample *sample, u64 type) { - event->header.size =3D perf_event__sample_event_size(sample, type, 0); - return perf_event__synthesize_sample(event, type, 0, sample); + event->header.size =3D perf_event__sample_event_size(sample, type, /*read= _format=3D*/0, + /*branch_sample_type=3D*/0); + return perf_event__synthesize_sample(event, type, /*read_format=3D*/0, + /*branch_sample_type=3D*/0, sample); } =20 =20 diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 382255393fb3..0b18ebd13f7c 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -303,7 +303,8 @@ static int intel_bts_synth_branch_sample(struct intel_b= ts_queue *btsq, event.sample.header.size =3D bts->branches_event_size; ret =3D perf_event__synthesize_sample(&event, bts->branches_sample_type, - 0, &sample); + /*read_format=3D*/0, /*branch_sample_type=3D*/0, + &sample); if (ret) return ret; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index fc9eec8b54b8..5142983e3243 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1731,8 +1731,11 @@ static void intel_pt_prep_b_sample(struct intel_pt *= pt, static int intel_pt_inject_event(union perf_event *event, struct perf_sample *sample, u64 type) { - event->header.size =3D perf_event__sample_event_size(sample, type, 0); - return perf_event__synthesize_sample(event, type, 0, sample); + event->header.size =3D perf_event__sample_event_size(sample, type, /*read= _format=3D*/0, + /*branch_sample_type=3D*/0); + + return perf_event__synthesize_sample(event, type, /*read_format=3D*/0, + /*branch_sample_type=3D*/0, sample); } =20 static inline int intel_pt_opt_inject(struct intel_pt *pt, diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic= -events.c index 85bee747f4cd..2461f25a4d7d 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1455,7 +1455,8 @@ int perf_event__synthesize_stat_round(const struct pe= rf_tool *tool, return process(tool, (union perf_event *) &event, NULL, machine); } =20 -size_t perf_event__sample_event_size(const struct perf_sample *sample, u64= type, u64 read_format) +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64= type, u64 read_format, + u64 branch_sample_type) { size_t sz, result =3D sizeof(struct perf_record_sample); =20 @@ -1515,8 +1516,10 @@ size_t perf_event__sample_event_size(const struct pe= rf_sample *sample, u64 type, =20 if (type & PERF_SAMPLE_BRANCH_STACK) { sz =3D sample->branch_stack->nr * sizeof(struct branch_entry); - /* nr, hw_idx */ - sz +=3D 2 * sizeof(u64); + /* nr */ + sz +=3D sizeof(u64); + if (branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX) + sz +=3D sizeof(u64); result +=3D sz; } =20 @@ -1605,7 +1608,7 @@ static __u64 *copy_read_group_values(__u64 *array, __= u64 read_format, } =20 int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 r= ead_format, - const struct perf_sample *sample) + u64 branch_sample_type, const struct perf_sample *sample) { __u64 *array; size_t sz; @@ -1719,9 +1722,17 @@ int perf_event__synthesize_sample(union perf_event *= event, u64 type, u64 read_fo =20 if (type & PERF_SAMPLE_BRANCH_STACK) { sz =3D sample->branch_stack->nr * sizeof(struct branch_entry); - /* nr, hw_idx */ - sz +=3D 2 * sizeof(u64); - memcpy(array, sample->branch_stack, sz); + + *array++ =3D sample->branch_stack->nr; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX) { + if (sample->no_hw_idx) + *array++ =3D 0; + else + *array++ =3D sample->branch_stack->hw_idx; + } + + memcpy(array, perf_sample__branch_entries((struct perf_sample *)sample),= sz); array =3D (void *)array + sz; } =20 diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic= -events.h index b0edad0c3100..8c7f49f9ccf5 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -81,7 +81,8 @@ int perf_event__synthesize_mmap_events(const struct perf_= tool *tool, union perf_ int perf_event__synthesize_modules(const struct perf_tool *tool, perf_even= t__handler_t process, struct machine *machine); int perf_event__synthesize_namespaces(const struct perf_tool *tool, union = perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, st= ruct machine *machine); int perf_event__synthesize_cgroups(const struct perf_tool *tool, perf_even= t__handler_t process, struct machine *machine); -int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 r= ead_format, const struct perf_sample *sample); +int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 r= ead_format, + u64 branch_sample_type, const struct perf_sample *sample); int perf_event__synthesize_stat_config(const struct perf_tool *tool, struc= t perf_stat_config *config, perf_event__handler_t process, struct machine *= machine); int perf_event__synthesize_stat_events(struct perf_stat_config *config, co= nst struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t pr= ocess, bool attrs); int perf_event__synthesize_stat_round(const struct perf_tool *tool, u64 ti= me, u64 type, perf_event__handler_t process, struct machine *machine); @@ -97,7 +98,8 @@ void perf_event__synthesize_final_bpf_metadata(struct per= f_session *session, =20 int perf_tool__process_synth_event(const struct perf_tool *tool, union per= f_event *event, struct machine *machine, perf_event__handler_t process); =20 -size_t perf_event__sample_event_size(const struct perf_sample *sample, u64= type, u64 read_format); +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64= type, + u64 read_format, u64 branch_sample_type); =20 int __machine__synthesize_threads(struct machine *machine, const struct pe= rf_tool *tool, struct target *target, struct perf_thread_map *threads, --=20 2.54.0.545.g6539524ca2-goog From nobody Tue Jun 16 19:33:18 2026 Received: from mail-dl1-f74.google.com (mail-dl1-f74.google.com [74.125.82.74]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A3B423FE358 for ; Wed, 29 Apr 2026 18:12:13 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.82.74 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777486336; cv=none; b=Z4fIXjzzy/nIJMd/n6DrupMkxmegqvHsd//exqdDAGjQHmkVx0pVedsmufPpeOiMmsYvC3OyNHKMHT7/BRgdUJ3iJGku+AiDfojyyr72+dVtPHVKoko0s2ZjAWt6dcWQP1SNVaMUoZcGHqKlHUjOw7nN1Q7U9M7hfjy3PwdCOX4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777486336; c=relaxed/simple; bh=iUDtWJ9GZFgc8/2/kgSqLcPy8fgN1HhdljG4tGQ0xXg=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=P+/24Ba6hlEu2sYEDAPpOPeOtOHVCFtnH4DUfih6z+gSy9VJWKzJ8a0Lb2L/sus4ePSj7RFXbIk3EQkZfENXsYDcY6rKUhmJ9kP+wNGktBkAmox+5qQ/AmcDtT/VlMBQiSIh6+xgBGFOKFHY/PDPd9eYK0g3qK99Ff6o+dG/V24= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--irogers.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=aL5dM99h; arc=none smtp.client-ip=74.125.82.74 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--irogers.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="aL5dM99h" Received: by mail-dl1-f74.google.com with SMTP id a92af1059eb24-12c20d5d7f4so110866c88.1 for ; Wed, 29 Apr 2026 11:12:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20251104; t=1777486333; x=1778091133; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=CC+WVhu74Qgg75vUJAa5DPRZl7RZuRZuq+lVZf+PXJw=; b=aL5dM99hYzyO7EUBfGFJuqNNRXnMYqBbmGa+i8eCosVzJedSss/ELefolz2YZR+fB2 xcve/P90HOtxsYy1Fk9DRnFOWN+zscGVcnWZKtf5wPimpSwxqqUUqmcyLl7105DSxMhX CZe+gmbT9FgdOFJUzsjwrkjAGCNZ7+7qSQyYT0ApFrdFcZHzSUJF+WjMaOG+mpxk0Evq rvWoE1aR55sFMG8JBc2FpSwl2tPjuIAMu2K2gREdxO2gDDDeaK0qfO5RIrIJhhM5MK2h tS5qA9HswpsAzy47DFWlETtj1GU+WdRfiyQ8/QeQaF1xTGsZHWDcxdmn63rcI+SEBdHj oV1A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1777486333; x=1778091133; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=CC+WVhu74Qgg75vUJAa5DPRZl7RZuRZuq+lVZf+PXJw=; b=jzgTqoddFs/f7/UZu6MFZi0VngQ8hPwvu41oFZ+EIR78lr28PtPH6MtZcDlHrPTik4 O9JBHRDx/l/WbdiNGp99re5Ulc+efhUI3EmeqJF5UAosP4tWy+46mxsZeTY6sgzJFHnt Eo0X4k0JebCuo4bk108vU3rGptM6wvL7p+RXy1vP14cU07AOU9G0D35K3EGdzDNpW7WF OaqPDwjGxigspAZCZ8H7x3DF8+PJ5uTJ3Z9Qx5sPmHgv8d3ZAyc7ABYpmV38BhGg9dNu Mv7qTrOP6PkzRmAYl+f5/NjqHXHRTDcyQdtclp33GsjKl2VtpXo62TETPrkbbSoxLxH/ +0BQ== X-Forwarded-Encrypted: i=1; AFNElJ+wPgTAstDdw4YXSjsI9E0OMr+i/RcOvaRfzXl9VSZB1P2EsGxgzGmgsHcz63NOeLqkq+E6hvAfE+ruivA=@vger.kernel.org X-Gm-Message-State: AOJu0YxSdW/pqoF1mX7FuukGLcUPql4VMKKOSGP0C2NfbnzhPuNGgNie gKz/V0ZSvzkL0IJA4iT7ieL86xV+CKTzwS7MEYafQ9PgzfVw0hwf2hoF1IQ899olO1T2XY44Ouy 2XtettnlRyA== X-Received: from dlad13.prod.google.com ([2002:a05:701b:220d:b0:12c:34da:e06e]) (user=irogers job=prod-delivery.src-stubby-dispatcher) by 2002:a05:7022:418e:b0:123:34e8:aec2 with SMTP id a92af1059eb24-12de29f9b90mr2122644c88.1.1777486332662; Wed, 29 Apr 2026 11:12:12 -0700 (PDT) Date: Wed, 29 Apr 2026 11:11:36 -0700 In-Reply-To: <20260429181136.2712655-1-irogers@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20260428070328.1880314-1-irogers@google.com> <20260429181136.2712655-1-irogers@google.com> X-Mailer: git-send-email 2.54.0.545.g6539524ca2-goog Message-ID: <20260429181136.2712655-3-irogers@google.com> Subject: [PATCH v2 2/2] perf inject: Fix itrace branch stack synthesis From: Ian Rogers To: acme@kernel.org, adrian.hunter@intel.com, dapeng1.mi@linux.intel.com, namhyung@kernel.org, thomas.falcon@intel.com Cc: james.clark@linaro.org, leo.yan@linux.dev, linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org, mingo@redhat.com, peterz@infradead.org, ravi.bangoria@amd.com, Ian Rogers Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" When using "perf inject --itrace=3DL" to synthesize branch stacks from AUX data, several issues caused failures with the generated file: 1. The synthesized samples were delivered without the PERF_SAMPLE_BRANCH_STACK flag if it was not in the original event's sample_type. Fixed by using sample_type | evsel->synth_sample_type in intel_pt_do_synth_pebs_sample. 2. Modifying evsel->core.attr.sample_type early in __cmd_inject caused parse failures for subsequent records in the input file. Fixed by moving this modification to just before writing the header. 3. perf_event__repipe_sample was narrowed to only synthesize samples when branch stack injection was requested, and restored the use of perf_inject__cut_auxtrace_sample as a fallback to preserve functionality. 4. Potential Heap Overflow in perf_event__repipe_sample: Addressed by adding a check that prints an error and returns -EFAULT if the calculated event size exceeds PERF_SAMPLE_MAX_SIZE. 5. Header vs Payload Mismatch in __cmd_inject: Addressed by narrowing the condition so that HEADER_BRANCH_STACK is only set in the file header if add_last_branch was true. 6. NULL Pointer Dereference in intel-pt.c: Addressed by updating the condition in intel_pt_do_synth_pebs_sample to fill sample. branch_stack if it was synthesized, even if not in the original sample_type. 7. Modifying event attributes in perf_event__repipe_attr early caused downstream parser breakage in pipe mode. Fixed by clearing PERF_SAMPLE_AUX when itrace_synth_opts.set is true to ensure the headers match the stripped payload. Also added a size check against struct perf_record_header_attr to prevent out-of-bounds writes. 8. Potential dangling pointer vulnerability in perf_event__repipe_sample: Addressed by restoring the original sample->branch_stack pointer before returning. 9. Off-by-one error in sample size check in perf_event__repipe_sample: Fixed by checking if sz >=3D PERF_SAMPLE_MAX_SIZE instead of >. 10. Unadvertised size field left in payload by cut_auxtrace_sample: Addressed by excluding the 8-byte size field from the copied payload to correctly match the cleared PERF_SAMPLE_AUX bit. 11. Silent data corruption in convert_sample_callchain: Addressed by restoring the error check for perf_event__synthesize_sample to prevent writing malformed or uninitialized memory. 12. Omission of hw_idx in PEBS synthesis: Fixed by passing the correct evsel->core.attr.branch_sample_type instead of 0 in intel-pt.c. Assisted-by: Gemini:gemini-3.1-pro-preview Signed-off-by: Ian Rogers --- v2: - Fix error handling in callchain conversion by keeping the error check. - Fix header advertise issues in pipe mode by clearing PERF_SAMPLE_AUX. - Prevent out-of-bounds writes in attribute repiping with size checks. - Fix sample payload misalignment by cutting the unadvertised AUX size fiel= d. - Fix off-by-one check in sample size overflow to correctly use >=3D. - Avoid dangling pointer vulnerability by restoring the branch_stack pointe= r. - Pass evsel's branch_sample_type to synthesized samples to prevent hw_idx = omission. --- tools/perf/builtin-inject.c | 97 ++++++++++++++++++++++++++++++++++--- tools/perf/util/intel-pt.c | 23 ++++++--- 2 files changed, 106 insertions(+), 14 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 0c51cb4250d1..13fb1f05ceb2 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -223,6 +223,19 @@ static int perf_event__repipe_attr(const struct perf_t= ool *tool, tool); int ret; =20 + if (event->header.size < sizeof(struct perf_record_header_attr)) { + pr_err("Attribute event size %u is too small\n", event->header.size); + return -EINVAL; + } + + if (inject->itrace_synth_opts.set) + event->attr.attr.sample_type &=3D ~PERF_SAMPLE_AUX; + + if (inject->itrace_synth_opts.add_last_branch) { + event->attr.attr.sample_type |=3D PERF_SAMPLE_BRANCH_STACK; + event->attr.attr.branch_sample_type |=3D PERF_SAMPLE_BRANCH_HW_INDEX; + } + ret =3D perf_event__process_attr(tool, event, pevlist); if (ret) return ret; @@ -330,8 +343,8 @@ perf_inject__cut_auxtrace_sample(struct perf_inject *in= ject, union perf_event *event, struct perf_sample *sample) { - size_t sz1 =3D sample->aux_sample.data - (void *)event; - size_t sz2 =3D event->header.size - sample->aux_sample.size - sz1; + size_t sz1 =3D sample->aux_sample.data - (void *)event - sizeof(u64); + size_t sz2 =3D event->header.size - sample->aux_sample.size - (sz1 + size= of(u64)); union perf_event *ev; =20 if (inject->event_copy =3D=3D NULL) { @@ -342,13 +355,12 @@ perf_inject__cut_auxtrace_sample(struct perf_inject *= inject, ev =3D (union perf_event *)inject->event_copy; if (sz1 > event->header.size || sz2 > event->header.size || sz1 + sz2 > event->header.size || - sz1 < sizeof(struct perf_event_header) + sizeof(u64)) + sz1 < sizeof(struct perf_event_header)) return event; =20 memcpy(ev, event, sz1); memcpy((void *)ev + sz1, (void *)event + event->header.size - sz2, sz2); ev->header.size =3D sz1 + sz2; - ((u64 *)((void *)ev + sz1))[-1] =3D 0; =20 return ev; } @@ -375,7 +387,63 @@ static int perf_event__repipe_sample(const struct perf= _tool *tool, =20 build_id__mark_dso_hit(tool, event, sample, evsel, machine); =20 - if (inject->itrace_synth_opts.set && sample->aux_sample.size) { + if (inject->itrace_synth_opts.set && + (inject->itrace_synth_opts.last_branch || + inject->itrace_synth_opts.add_last_branch)) { + union perf_event *event_copy =3D (void *)inject->event_copy; + struct branch_stack dummy_bs =3D { .nr =3D 0, .hw_idx =3D 0 }; + int err; + size_t sz; + u64 orig_type =3D evsel->core.attr.sample_type; + u64 orig_branch_type =3D evsel->core.attr.branch_sample_type; + + struct branch_stack *orig_bs =3D sample->branch_stack; + + if (event_copy =3D=3D NULL) { + inject->event_copy =3D malloc(PERF_SAMPLE_MAX_SIZE); + if (!inject->event_copy) + return -ENOMEM; + + event_copy =3D (void *)inject->event_copy; + } + + if (!sample->branch_stack) + sample->branch_stack =3D &dummy_bs; + + if (inject->itrace_synth_opts.add_last_branch) { + /* Temporarily add in type bits for synthesis. */ + evsel->core.attr.sample_type |=3D PERF_SAMPLE_BRANCH_STACK; + evsel->core.attr.branch_sample_type |=3D PERF_SAMPLE_BRANCH_HW_INDEX; + } + evsel->core.attr.sample_type &=3D ~PERF_SAMPLE_AUX; + + sz =3D perf_event__sample_event_size(sample, evsel->core.attr.sample_typ= e, + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type); + + if (sz >=3D PERF_SAMPLE_MAX_SIZE) { + pr_err("Sample size %zu exceeds max size %d\n", sz, PERF_SAMPLE_MAX_SIZ= E); + return -EFAULT; + } + + event_copy->header.type =3D PERF_RECORD_SAMPLE; + event_copy->header.misc =3D event->header.misc; + event_copy->header.size =3D sz; + + err =3D perf_event__synthesize_sample(event_copy, evsel->core.attr.sampl= e_type, + evsel->core.attr.read_format, + evsel->core.attr.branch_sample_type, sample); + + evsel->core.attr.sample_type =3D orig_type; + evsel->core.attr.branch_sample_type =3D orig_branch_type; + sample->branch_stack =3D orig_bs; + + if (err) { + pr_err("Failed to synthesize sample\n"); + return err; + } + event =3D event_copy; + } else if (inject->itrace_synth_opts.set && sample->aux_sample.size) { event =3D perf_inject__cut_auxtrace_sample(inject, event, sample); if (IS_ERR(event)) return PTR_ERR(event); @@ -463,7 +531,7 @@ static int perf_event__convert_sample_callchain(const s= truct perf_tool *tool, /* remove sample_type {STACK,REGS}_USER for synthesize */ sample_type &=3D ~(PERF_SAMPLE_STACK_USER | PERF_SAMPLE_REGS_USER); =20 - ret =3D perf_event__synthesize_sample(event_copy, evsel->core.attr.sample= _type, + ret =3D perf_event__synthesize_sample(event_copy, sample_type, evsel->core.attr.read_format, evsel->core.attr.branch_sample_type, sample); if (ret) { @@ -2440,12 +2508,25 @@ static int __cmd_inject(struct perf_inject *inject) * synthesized hardware events, so clear the feature flag. */ if (inject->itrace_synth_opts.set) { + struct evsel *evsel; + perf_header__clear_feat(&session->header, HEADER_AUXTRACE); - if (inject->itrace_synth_opts.last_branch || - inject->itrace_synth_opts.add_last_branch) + + evlist__for_each_entry(session->evlist, evsel) { + evsel->core.attr.sample_type &=3D ~PERF_SAMPLE_AUX; + } + + if (inject->itrace_synth_opts.add_last_branch) { perf_header__set_feat(&session->header, HEADER_BRANCH_STACK); + + evlist__for_each_entry(session->evlist, evsel) { + evsel->core.attr.sample_type |=3D PERF_SAMPLE_BRANCH_STACK; + evsel->core.attr.branch_sample_type |=3D + PERF_SAMPLE_BRANCH_HW_INDEX; + } + } } =20 /* diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 5142983e3243..f45dbdd4d323 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1728,14 +1728,24 @@ static void intel_pt_prep_b_sample(struct intel_pt = *pt, event->sample.header.misc =3D sample->cpumode; } =20 -static int intel_pt_inject_event(union perf_event *event, +static int intel_pt_inject_event(struct intel_pt *pt, union perf_event *ev= ent, struct perf_sample *sample, u64 type) { + struct evsel *evsel =3D NULL; + u64 branch_sample_type =3D 0; + + if (pt->session && pt->session->evlist) + evsel =3D evlist__id2evsel(pt->session->evlist, sample->id); + + if (evsel) + branch_sample_type =3D evsel->core.attr.branch_sample_type; + + event->header.type =3D PERF_RECORD_SAMPLE; event->header.size =3D perf_event__sample_event_size(sample, type, /*read= _format=3D*/0, - /*branch_sample_type=3D*/0); + branch_sample_type); =20 return perf_event__synthesize_sample(event, type, /*read_format=3D*/0, - /*branch_sample_type=3D*/0, sample); + branch_sample_type, sample); } =20 static inline int intel_pt_opt_inject(struct intel_pt *pt, @@ -1745,7 +1755,7 @@ static inline int intel_pt_opt_inject(struct intel_pt= *pt, if (!pt->synth_opts.inject) return 0; =20 - return intel_pt_inject_event(event, sample, type); + return intel_pt_inject_event(pt, event, sample, type); } =20 static int intel_pt_deliver_synth_event(struct intel_pt *pt, @@ -2489,7 +2499,7 @@ static int intel_pt_do_synth_pebs_sample(struct intel= _pt_queue *ptq, struct evse intel_pt_add_xmm(intr_regs, pos, items, regs_mask); } =20 - if (sample_type & PERF_SAMPLE_BRANCH_STACK) { + if ((sample_type | evsel->synth_sample_type) & PERF_SAMPLE_BRANCH_STACK) { if (items->mask[INTEL_PT_LBR_0_POS] || items->mask[INTEL_PT_LBR_1_POS] || items->mask[INTEL_PT_LBR_2_POS]) { @@ -2560,7 +2570,8 @@ static int intel_pt_do_synth_pebs_sample(struct intel= _pt_queue *ptq, struct evse sample.transaction =3D txn; } =20 - ret =3D intel_pt_deliver_synth_event(pt, event, &sample, sample_type); + ret =3D intel_pt_deliver_synth_event(pt, event, &sample, + sample_type | evsel->synth_sample_type); perf_sample__exit(&sample); return ret; } --=20 2.54.0.545.g6539524ca2-goog