[PATCH v1 01/58] perf inject: Fix itrace branch stack synthesis

[Ian Rogers]

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@xxxxxxxxxx>
---
 tools/perf/builtin-inject.c        | 63 +++++++++++++++++++++++++++++-
 tools/perf/util/intel-pt.c         |  3 +-
 tools/perf/util/synthetic-events.c |  6 +--
 3 files changed, 66 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index f174bc69cec4..9da334740017 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -375,7 +375,52 @@ 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);
+
+		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, 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);
@@ -2434,12 +2479,26 @@ 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);
+
+			evlist__for_each_entry(session->evlist, evsel) {
+				evsel->core.attr.sample_type &= ~PERF_SAMPLE_AUX;
+			}
+
 			if (inject->itrace_synth_opts.last_branch ||
-			    inject->itrace_synth_opts.add_last_branch)
+			    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/util/intel-pt.c b/tools/perf/util/intel-pt.c
index fc9eec8b54b8..b9fcf3b457b0 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2557,7 +2557,8 @@ 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..33b530b73796 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1719,9 +1719,9 @@ 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;
+		*array++ = sample->branch_stack->hw_idx;
+		memcpy(array, sample->branch_stack->entries, sz);
 		array = (void *)array + sz;
 	}
 
-- 
2.54.0.rc1.513.gad8abe7a5a-goog