perf mmap: Lazily initialize zstd streams to save memory when not using it

Zstd streams create dictionaries that can require significant RAM,
especially when there is one per-CPU. Tools like 'perf record' won't use
the streams without the -z option, and so the creation of the streams
is pure overhead. Switch to creating the streams on first use.

Committer notes:

ssize_t comes from sys/types.h, size_t from stddef.h. This worked on
glibc as stdlib.h includes both, but not on musl libc. So do what 'man
size_t' says and include sys/types.h and stddef.h instead of stdlib.h

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Li Dong <lidong@vivo.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Vincent Whitchurch <vincent.whitchurch@axis.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20231102175735.2272696-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 19 insertions, 7 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8ec818568662..9b4f3805ca92 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -270,7 +270,7 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 
 static int record__aio_enabled(struct record *rec);
 static int record__comp_enabled(struct record *rec);
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size);
 
 #ifdef HAVE_AIO_SUPPORT
@@ -405,9 +405,13 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size
 	 */
 
 	if (record__comp_enabled(aio->rec)) {
-		size = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
-				     mmap__mmap_len(map) - aio->size,
-				     buf, size);
+		ssize_t compressed = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
+						   mmap__mmap_len(map) - aio->size,
+						   buf, size);
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 	} else {
 		memcpy(aio->data + aio->size, buf, size);
 	}
@@ -633,7 +637,13 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
-		size = zstd_compress(rec->session, map, map->data, mmap__mmap_len(map), bf, size);
+		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;
 	}
 
@@ -1527,10 +1537,10 @@ static size_t process_comp_header(void *record, size_t increment)
 	return size;
 }
 
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size)
 {
-	size_t compressed;
+	ssize_t compressed;
 	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
 	struct zstd_data *zstd_data = &session->zstd_data;
 
@@ -1539,6 +1549,8 @@ static size_t zstd_compress(struct perf_session *session, struct mmap *map,
 
 	compressed = zstd_compress_stream_to_records(zstd_data, dst, dst_size, src, src_size,
 						     max_record_size, process_comp_header);
+	if (compressed < 0)
+		return compressed;
 
 	if (map && map->file) {
 		thread->bytes_transferred += src_size;