[PATCH v4 01/58] perf inject: Fix itrace branch stack synthesis

[Ian Rogers <irogers@google.com>]

When using "perf inject --itrace=L" to synthesize branch stacks from
AUX data, several issues caused failures:

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_deliver_synth_event.

2. The record layout was misaligned because of inconsistent handling
   of PERF_SAMPLE_BRANCH_HW_INDEX. Fixed by explicitly writing nr and
   hw_idx in perf_event__synthesize_sample.

3. 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.

4. 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.

Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
Issues fixed in v2:

1. 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 , as you
   requested.

2. 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.

3. 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 .

4. Unsafe Reads for events lacking HW_INDEX in synthetic-events.c :
   Addressed by using the perf_sample__branch_entries() macro and
   checking sample->no_hw_idx .

5. Size mismatch in perf_event__sample_event_size : Addressed by
   passing branch_sample_type to it and conditioning the hw_idx size on
   PERF_SAMPLE_BRANCH_HW_INDEX .
---
 tools/perf/bench/inject-buildid.c  |  9 ++--
 tools/perf/builtin-inject.c        | 77 ++++++++++++++++++++++++++++--
 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         | 13 +++--
 tools/perf/util/synthetic-events.c | 25 +++++++---
 tools/perf/util/synthetic-events.h |  6 ++-
 10 files changed, 129 insertions(+), 30 deletions(-)

diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.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 *data, struct bench_dso *dso,
 
 	event.header.type = PERF_RECORD_SAMPLE;
 	event.header.misc = PERF_RECORD_MISC_USER;
-	event.header.size = perf_event__sample_event_size(&sample, bench_sample_type, 0);
-
-	perf_event__synthesize_sample(&event, bench_sample_type, 0, &sample);
+	event.header.size = perf_event__sample_event_size(&sample, bench_sample_type,
+							   /*read_format=*/0,
+							   /*branch_sample_type=*/0);
+	perf_event__synthesize_sample(&event, bench_sample_type,
+				      /*read_format=*/0,
+				      /*branch_sample_type=*/0, &sample);
 
 	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..88c0ef4f5ff1 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -375,7 +375,59 @@ static int perf_event__repipe_sample(const struct perf_tool *tool,
 
 	build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 
-	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 = (void *)inject->event_copy;
+		struct branch_stack dummy_bs = { .nr = 0 };
+		int err;
+		size_t sz;
+		u64 orig_type = evsel->core.attr.sample_type;
+		u64 orig_branch_type = evsel->core.attr.branch_sample_type;
+
+		if (event_copy == NULL) {
+			inject->event_copy = malloc(PERF_SAMPLE_MAX_SIZE);
+			if (!inject->event_copy)
+				return -ENOMEM;
+
+			event_copy = (void *)inject->event_copy;
+		}
+
+		if (!sample->branch_stack)
+			sample->branch_stack = &dummy_bs;
+
+		if (inject->itrace_synth_opts.add_last_branch) {
+			/* Temporarily add in type bits for synthesis. */
+			evsel->core.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+			evsel->core.attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+			evsel->core.attr.sample_type &= ~PERF_SAMPLE_AUX;
+		}
+
+		sz = perf_event__sample_event_size(sample, evsel->core.attr.sample_type,
+						   evsel->core.attr.read_format,
+						   evsel->core.attr.branch_sample_type);
+
+		if (sz > PERF_SAMPLE_MAX_SIZE) {
+			pr_err("Sample size %zu exceeds max size %d\n", sz, PERF_SAMPLE_MAX_SIZE);
+			return -EFAULT;
+		}
+
+		event_copy->header.type = PERF_RECORD_SAMPLE;
+		event_copy->header.size = sz;
+
+		err = perf_event__synthesize_sample(event_copy, evsel->core.attr.sample_type,
+						    evsel->core.attr.read_format,
+						    evsel->core.attr.branch_sample_type, sample);
+
+		evsel->core.attr.sample_type = orig_type;
+		evsel->core.attr.branch_sample_type = orig_branch_type;
+
+		if (err) {
+			pr_err("Failed to synthesize sample\n");
+			return err;
+		}
+		event = event_copy;
+	} else if (inject->itrace_synth_opts.set && sample->aux_sample.size) {
 		event = perf_inject__cut_auxtrace_sample(inject, event, sample);
 		if (IS_ERR(event))
 			return PTR_ERR(event);
@@ -464,7 +516,8 @@ static int perf_event__convert_sample_callchain(const struct perf_tool *tool,
 	sample_type &= ~(PERF_SAMPLE_STACK_USER | PERF_SAMPLE_REGS_USER);
 
 	perf_event__synthesize_sample(event_copy, sample_type,
-				      evsel->core.attr.read_format, sample);
+				      evsel->core.attr.read_format,
+				      evsel->core.attr.branch_sample_type, sample);
 	return perf_event__repipe_synth(tool, event_copy);
 }
 
@@ -1100,7 +1153,8 @@ static int perf_inject__sched_stat(const struct perf_tool *tool,
 	sample_sw.period = sample->period;
 	sample_sw.time	 = 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 = perf_event__repipe(tool, event_sw, &sample_sw, machine);
 	perf_sample__exit(&sample_sw);
@@ -2434,12 +2488,25 @@ 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 &= ~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 |= PERF_SAMPLE_BRANCH_STACK;
+					evsel->core.attr.branch_sample_type |=
+						PERF_SAMPLE_BRANCH_HW_INDEX;
+				}
+			}
 		}
 
 		/*
diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.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 sample_type, u64 id, pid_t pid
 
 	event->header.type = PERF_RECORD_SAMPLE;
 	event->header.misc = PERF_RECORD_MISC_USER;
-	event->header.size = perf_event__sample_event_size(&sample, sample_type, 0);
-	err = perf_event__synthesize_sample(event, sample_type, 0, &sample);
+	event->header.size = perf_event__sample_event_size(&sample, sample_type,
+							   /*read_format=*/0,
+							   /*branch_sample_type=*/0);
+	err = perf_event__synthesize_sample(event, sample_type,
+					    /*read_format=*/0,
+					    /*branch_sample_type=*/0, &sample);
 	if (err)
 		return test_result("perf_event__synthesize_sample() failed", TEST_FAIL);
 
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.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, u64 read_format)
 		sample.read.one.lost  = 1;
 	}
 
-	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
+	sz = perf_event__sample_event_size(&sample, sample_type, read_format,
+					   evsel.core.attr.branch_sample_type);
 	bufsz = sz + 4096; /* Add a bit for overrun checking */
 	event = malloc(bufsz);
 	if (!event) {
@@ -324,7 +325,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 	event->header.size = sz;
 
 	err = 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)
 
 static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type)
 {
-	event->header.size = perf_event__sample_event_size(sample, type, 0);
-	return perf_event__synthesize_sample(event, type, 0, sample);
+	event->header.type = PERF_RECORD_SAMPLE;
+	event->header.size = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+							   /*branch_sample_type=*/0);
+	return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+					     /*branch_sample_type=*/0, sample);
 }
 
 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 = perf_event__sample_event_size(sample, type, 0);
-	return perf_event__synthesize_sample(event, type, 0, sample);
+	event->header.size = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+							   /*branch_sample_type=*/0);
+	return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+					     /*branch_sample_type=*/0, sample);
 }
 
 
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_bts_queue *btsq,
 		event.sample.header.size = bts->branches_event_size;
 		ret = perf_event__synthesize_sample(&event,
 						    bts->branches_sample_type,
-						    0, &sample);
+						    /*read_format=*/0, /*branch_sample_type=*/0,
+						    &sample);
 		if (ret)
 			return ret;
 	}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index fc9eec8b54b8..2dce6106c038 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1731,8 +1731,12 @@ 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 = perf_event__sample_event_size(sample, type, 0);
-	return perf_event__synthesize_sample(event, type, 0, sample);
+	event->header.type = PERF_RECORD_SAMPLE;
+	event->header.size = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+							   /*branch_sample_type=*/0);
+
+	return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+					     /*branch_sample_type=*/0, sample);
 }
 
 static inline int intel_pt_opt_inject(struct intel_pt *pt,
@@ -2486,7 +2490,7 @@ 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);
 	}
 
-	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]) {
@@ -2557,7 +2561,8 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
 		sample.transaction = txn;
 	}
 
-	ret = intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
+	ret = intel_pt_deliver_synth_event(pt, event, &sample,
+					   sample_type | evsel->synth_sample_type);
 	perf_sample__exit(&sample);
 	return ret;
 }
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 perf_tool *tool,
 	return process(tool, (union perf_event *) &event, NULL, machine);
 }
 
-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 = sizeof(struct perf_record_sample);
 
@@ -1515,8 +1516,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		/* nr, hw_idx */
-		sz += 2 * sizeof(u64);
+		/* nr */
+		sz += sizeof(u64);
+		if (branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)
+			sz += sizeof(u64);
 		result += sz;
 	}
 
@@ -1605,7 +1608,7 @@ static __u64 *copy_read_group_values(__u64 *array, __u64 read_format,
 }
 
 int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_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
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		/* nr, hw_idx */
-		sz += 2 * sizeof(u64);
-		memcpy(array, sample->branch_stack, sz);
+
+		*array++ = sample->branch_stack->nr;
+
+		if (branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX) {
+			if (sample->no_hw_idx)
+				*array++ = 0;
+			else
+				*array++ = sample->branch_stack->hw_idx;
+		}
+
+		memcpy(array, perf_sample__branch_entries((struct perf_sample *)sample), sz);
 		array = (void *)array + sz;
 	}
 
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_event__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, struct machine *machine);
 int perf_event__synthesize_cgroups(const struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample);
+int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
+				  u64 branch_sample_type, const struct perf_sample *sample);
 int perf_event__synthesize_stat_config(const struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_stat_events(struct perf_stat_config *config, const struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);
 int perf_event__synthesize_stat_round(const struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
@@ -97,7 +98,8 @@ void perf_event__synthesize_final_bpf_metadata(struct perf_session *session,
 
 int perf_tool__process_synth_event(const struct perf_tool *tool, union perf_event *event, struct machine *machine, perf_event__handler_t process);
 
-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);
 
 int __machine__synthesize_threads(struct machine *machine, const struct perf_tool *tool,
 				  struct target *target, struct perf_thread_map *threads,
-- 
2.54.0.rc2.533.g4f5dca5207-goog