perf inject: Fix build ID injection

Build ID injection wasn't inserting a sample ID and aligning events to
64 bytes rather than 8. No sample ID means events are unordered and two
different build_id events for the same path, as happens when a file is
replaced, can't be differentiated.

Add in sample ID insertion for the build_id events alongside some
refactoring. The refactoring better aligns the function arguments for
different use cases, such as synthesizing build_id events without
needing to have a dso. The misc bits are explicitly passed as with
callchains the maps/dsos may span user and kernel land, so using
sample->cpumode isn't good enough.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anne Macedo <retpolanne@posteo.net>
Cc: Casey Chen <cachen@purestorage.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sun Haiyong <sunhaiyong@loongson.cn>
Link: https://lore.kernel.org/r/20240909203740.143492-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

3 files changed, 44 insertions, 16 deletions

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 451d145fa4ed..8982f68e7230 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -277,8 +277,8 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid
 	struct perf_record_header_build_id b;
 	size_t len;
 
-	len = name_len + 1;
-	len = PERF_ALIGN(len, NAME_ALIGN);
+	len = sizeof(b) + name_len + 1;
+	len = PERF_ALIGN(len, sizeof(u64));
 
 	memset(&b, 0, sizeof(b));
 	memcpy(&b.data, bid->data, bid->size);
@@ -286,7 +286,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid
 	misc |= PERF_RECORD_MISC_BUILD_ID_SIZE;
 	b.pid = pid;
 	b.header.misc = misc;
-	b.header.size = sizeof(b) + len;
+	b.header.size = len;
 
 	err = do_write(fd, &b, sizeof(b));
 	if (err < 0)
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 0a7f93ae76fb..6bb62e4e2d5d 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -2225,28 +2225,48 @@ int perf_event__synthesize_tracing_data(const struct perf_tool *tool, int fd, st
 }
 #endif
 
-int perf_event__synthesize_build_id(const struct perf_tool *tool, struct dso *pos, u16 misc,
-				    perf_event__handler_t process, struct machine *machine)
+int perf_event__synthesize_build_id(const struct perf_tool *tool,
+				    struct perf_sample *sample,
+				    struct machine *machine,
+				    perf_event__handler_t process,
+				    const struct evsel *evsel,
+				    __u16 misc,
+				    const struct build_id *bid,
+				    const char *filename)
 {
 	union perf_event ev;
 	size_t len;
 
-	if (!dso__hit(pos))
-		return 0;
+	len = sizeof(ev.build_id) + strlen(filename) + 1;
+	len = PERF_ALIGN(len, sizeof(u64));
 
-	memset(&ev, 0, sizeof(ev));
+	memset(&ev, 0, len);
 
-	len = dso__long_name_len(pos) + 1;
-	len = PERF_ALIGN(len, NAME_ALIGN);
-	ev.build_id.size = min(dso__bid(pos)->size, sizeof(dso__bid(pos)->data));
-	memcpy(&ev.build_id.build_id, dso__bid(pos)->data, ev.build_id.size);
+	ev.build_id.size = min(bid->size, sizeof(ev.build_id.build_id));
+	memcpy(ev.build_id.build_id, bid->data, ev.build_id.size);
 	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
 	ev.build_id.header.misc = misc | PERF_RECORD_MISC_BUILD_ID_SIZE;
 	ev.build_id.pid = machine->pid;
-	ev.build_id.header.size = sizeof(ev.build_id) + len;
-	memcpy(&ev.build_id.filename, dso__long_name(pos), dso__long_name_len(pos));
+	ev.build_id.header.size = len;
+	strcpy(ev.build_id.filename, filename);
+
+	if (evsel) {
+		void *array = &ev;
+		int ret;
 
-	return process(tool, &ev, NULL, machine);
+		array += ev.header.size;
+		ret = perf_event__synthesize_id_sample(array, evsel->core.attr.sample_type, sample);
+		if (ret < 0)
+			return ret;
+
+		if (ret & 7) {
+			pr_err("Bad id sample size %d\n", ret);
+			return -EINVAL;
+		}
+
+		ev.header.size += ret;
+	}
+	return process(tool, &ev, sample, machine);
 }
 
 int perf_event__synthesize_stat_events(struct perf_stat_config *config, const struct perf_tool *tool,
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index 31df7653677f..795bf3e18396 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -9,6 +9,7 @@
 #include <perf/cpumap.h>
 
 struct auxtrace_record;
+struct build_id;
 struct dso;
 struct evlist;
 struct evsel;
@@ -45,7 +46,14 @@ typedef int (*perf_event__handler_t)(const struct perf_tool *tool, union perf_ev
 
 int perf_event__synthesize_attrs(const struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process);
 int perf_event__synthesize_attr(const struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process);
-int perf_event__synthesize_build_id(const struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_build_id(const struct perf_tool *tool,
+				    struct perf_sample *sample,
+				    struct machine *machine,
+				    perf_event__handler_t process,
+				    const struct evsel *evsel,
+				    __u16 misc,
+				    const struct build_id *bid,
+				    const char *filename);
 int perf_event__synthesize_cpu_map(const struct perf_tool *tool, const struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_event_update_cpus(const struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
 int perf_event__synthesize_event_update_name(const struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);