perf record: Add 8-byte aligned event type PERF_RECORD_COMPRESSED2

The original PERF_RECORD_COMPRESS is not 8-byte aligned, which can cause
asan runtime error:

  # Build with asan
  $ make -C tools/perf O=/tmp/perf DEBUG=1 EXTRA_CFLAGS="-O0 -g -fno-omit-frame-pointer -fsanitize=undefined"
  # Test success with many asan runtime errors:
  $ /tmp/perf/perf test "Zstd perf.data compression/decompression" -vv
   83: Zstd perf.data compression/decompression:
  ...
  util/session.c:1959:13: runtime error: member access within misaligned address 0x7f69e3f99653 for type 'union perf_event', which requires 13 byte alignment
  0x7f69e3f99653: note: pointer points here
   d0  3a 50 69 44 00 00 00 00  00 08 00 bb 07 00 00 00  00 00 00 44 00 00 00 00  00 00 00 ff 07 00 00
                ^
  util/session.c:2163:22: runtime error: member access within misaligned address 0x7f69e3f99653 for type 'union perf_event', which requires 8 byte alignment
  0x7f69e3f99653: note: pointer points here
   d0  3a 50 69 44 00 00 00 00  00 08 00 bb 07 00 00 00  00 00 00 44 00 00 00 00  00 00 00 ff 07 00 00
                ^
  ...

Since there is no way to align compressed data in zstd compression, this
patch add a new event type `PERF_RECORD_COMPRESSED2`, which adds a field
`data_size` to specify the actual compressed data size.

The `header.size` contains the total record size, including the padding
at the end to make it 8-byte aligned.

Tested with `Zstd perf.data compression/decompression`

Signed-off-by: Chun-Tse Shao <ctshao@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303183646.327510-1-ctshao@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 51 insertions, 13 deletions

diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index 010a4edcd384..cd95ba09f727 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -370,7 +370,7 @@ struct {
 	u32	mmap_len;
 };
 
-Indicates that trace contains records of PERF_RECORD_COMPRESSED type
+Indicates that trace contains records of PERF_RECORD_COMPRESSED2 type
 that have perf_events records in compressed form.
 
 	HEADER_CPU_PMU_CAPS = 28,
@@ -602,7 +602,14 @@ struct auxtrace_error_event {
 Describes a header feature. These are records used in pipe-mode that
 contain information that otherwise would be in perf.data file's header.
 
-	PERF_RECORD_COMPRESSED 			= 81,
+	PERF_RECORD_COMPRESSED 			= 81, /* deprecated */
+
+The header is followed by compressed data frame that can be decompressed
+into array of perf trace records. The size of the entire compressed event
+record including the header is limited by the max value of header.size.
+
+It is deprecated and new files should use PERF_RECORD_COMPRESSED2 to gurantee
+8-byte alignment.
 
 struct compressed_event {
 	struct perf_event_header	header;
@@ -618,10 +625,17 @@ This is used, for instance, to 'perf inject' events after init and before
 regular events, those emitted by the kernel, to support combining guest and
 host records.
 
+	PERF_RECORD_COMPRESSED2			= 83,
 
-The header is followed by compressed data frame that can be decompressed
-into array of perf trace records. The size of the entire compressed event
-record including the header is limited by the max value of header.size.
+8-byte aligned version of `PERF_RECORD_COMPRESSED`. `header.size` indicates the
+total record size, including padding for 8-byte alignment, and `data_size`
+specifies the actual size of the compressed data.
+
+struct perf_record_compressed2 {
+	struct perf_event_header	header;
+	__u64				data_size;
+	char				data[];
+};
 
 Event types
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 94d9c97af7b7..136c0172799a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -650,14 +650,27 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
+		struct perf_record_compressed2 *event = map->data;
+		size_t padding = 0;
+		u8 pad[8] = {0};
 		ssize_t compressed = zstd_compress(rec->session, map, map->data,
 						   mmap__mmap_len(map), bf, size);
 
 		if (compressed < 0)
 			return (int)compressed;
 
-		size = compressed;
-		bf   = map->data;
+		bf = event;
+		thread->samples++;
+
+		/*
+		 * The record from `zstd_compress` is not 8 bytes aligned, which would cause asan
+		 * error. We make it aligned here.
+		 */
+		event->data_size = compressed - sizeof(struct perf_record_compressed2);
+		event->header.size = PERF_ALIGN(compressed, sizeof(u64));
+		padding = event->header.size - compressed;
+		return record__write(rec, map, bf, compressed) ||
+		       record__write(rec, map, &pad, padding);
 	}
 
 	thread->samples++;
@@ -1536,7 +1549,7 @@ static void record__adjust_affinity(struct record *rec, struct mmap *map)
 
 static size_t process_comp_header(void *record, size_t increment)
 {
-	struct perf_record_compressed *event = record;
+	struct perf_record_compressed2 *event = record;
 	size_t size = sizeof(*event);
 
 	if (increment) {
@@ -1544,7 +1557,7 @@ static size_t process_comp_header(void *record, size_t increment)
 		return increment;
 	}
 
-	event->header.type = PERF_RECORD_COMPRESSED;
+	event->header.type = PERF_RECORD_COMPRESSED2;
 	event->header.size = size;
 
 	return size;
@@ -1554,7 +1567,7 @@ static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size)
 {
 	ssize_t compressed;
-	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
+	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed2) - 1;
 	struct zstd_data *zstd_data = &session->zstd_data;
 
 	if (map && map->file)
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index c23b77f8f854..80c9ea682413 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -77,6 +77,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_HEADER_FEATURE]		= "FEATURE",
 	[PERF_RECORD_COMPRESSED]		= "COMPRESSED",
 	[PERF_RECORD_FINISHED_INIT]		= "FINISHED_INIT",
+	[PERF_RECORD_COMPRESSED2]		= "COMPRESSED2",
 };
 
 const char *perf_event__name(unsigned int id)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 81cc56503a2d..a320672c264e 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1400,7 +1400,9 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	int err;
 
 	perf_sample__init(&sample, /*all=*/true);
-	if (event->header.type != PERF_RECORD_COMPRESSED || perf_tool__compressed_is_stub(tool))
+	if ((event->header.type != PERF_RECORD_COMPRESSED &&
+	     event->header.type != PERF_RECORD_COMPRESSED2) ||
+	    perf_tool__compressed_is_stub(tool))
 		dump_event(session->evlist, event, file_offset, &sample, file_path);
 
 	/* These events are processed right away */
@@ -1481,6 +1483,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		err = tool->feature(session, event);
 		break;
 	case PERF_RECORD_COMPRESSED:
+	case PERF_RECORD_COMPRESSED2:
 		err = tool->compressed(session, event, file_offset, file_path);
 		if (err)
 			dump_event(session->evlist, event, file_offset, &sample, file_path);
diff --git a/tools/perf/util/tool.c b/tools/perf/util/tool.c
index 3b7f390f26eb..37bd8ac63b01 100644
--- a/tools/perf/util/tool.c
+++ b/tools/perf/util/tool.c
@@ -43,8 +43,15 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 		decomp->size = decomp_last_rem;
 	}
 
-	src = (void *)event + sizeof(struct perf_record_compressed);
-	src_size = event->pack.header.size - sizeof(struct perf_record_compressed);
+	if (event->header.type == PERF_RECORD_COMPRESSED) {
+		src = (void *)event + sizeof(struct perf_record_compressed);
+		src_size = event->pack.header.size - sizeof(struct perf_record_compressed);
+	} else if (event->header.type == PERF_RECORD_COMPRESSED2) {
+		src = (void *)event + sizeof(struct perf_record_compressed2);
+		src_size = event->pack2.data_size;
+	} else {
+		return -1;
+	}
 
 	decomp_size = zstd_decompress_stream(session->active_decomp->zstd_decomp, src, src_size,
 				&(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem);