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>

4 files changed, 40 insertions, 36 deletions

diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
index 0cd3369af2a4..b29109cd3609 100644
--- a/tools/perf/util/compress.h
+++ b/tools/perf/util/compress.h
@@ -3,6 +3,8 @@
 #define PERF_COMPRESS_H
 
 #include <stdbool.h>
+#include <stddef.h>
+#include <sys/types.h>
 #ifdef HAVE_ZSTD_SUPPORT
 #include <zstd.h>
 #endif
@@ -21,6 +23,7 @@ struct zstd_data {
 #ifdef HAVE_ZSTD_SUPPORT
 	ZSTD_CStream	*cstream;
 	ZSTD_DStream	*dstream;
+	int comp_level;
 #endif
 };
 
@@ -29,7 +32,7 @@ struct zstd_data {
 int zstd_init(struct zstd_data *data, int level);
 int zstd_fini(struct zstd_data *data);
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment));
 
@@ -48,7 +51,7 @@ static inline int zstd_fini(struct zstd_data *data __maybe_unused)
 }
 
 static inline
-size_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
 				       void *dst __maybe_unused, size_t dst_size __maybe_unused,
 				       void *src __maybe_unused, size_t src_size __maybe_unused,
 				       size_t max_record_size __maybe_unused,
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 49093b21ee2d..122ee198a86e 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -295,15 +295,14 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu
 
 	map->core.flush = mp->flush;
 
-	map->comp_level = mp->comp_level;
 #ifndef PYTHON_PERF
-	if (zstd_init(&map->zstd_data, map->comp_level)) {
+	if (zstd_init(&map->zstd_data, mp->comp_level)) {
 		pr_debug2("failed to init mmap compressor, error %d\n", errno);
 		return -1;
 	}
 #endif
 
-	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
+	if (mp->comp_level && !perf_mmap__aio_enabled(map)) {
 		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
 				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
 		if (map->data == MAP_FAILED) {
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index f944c3cd5efa..0df6e1621c7e 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -39,7 +39,6 @@ struct mmap {
 #endif
 	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
-	int		comp_level;
 	struct perf_data_file *file;
 	struct zstd_data      zstd_data;
 };
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index 48dd2b018c47..57027e0ac7b6 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -7,35 +7,9 @@
 
 int zstd_init(struct zstd_data *data, int level)
 {
-	size_t ret;
-
-	data->dstream = ZSTD_createDStream();
-	if (data->dstream == NULL) {
-		pr_err("Couldn't create decompression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initDStream(data->dstream);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize decompression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
-	if (!level)
-		return 0;
-
-	data->cstream = ZSTD_createCStream();
-	if (data->cstream == NULL) {
-		pr_err("Couldn't create compression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initCStream(data->cstream, level);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize compression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
+	data->comp_level = level;
+	data->dstream = NULL;
+	data->cstream = NULL;
 	return 0;
 }
 
@@ -54,7 +28,7 @@ int zstd_fini(struct zstd_data *data)
 	return 0;
 }
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment))
 {
@@ -63,6 +37,21 @@ size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t
 	ZSTD_outBuffer output;
 	void *record;
 
+	if (!data->cstream) {
+		data->cstream = ZSTD_createCStream();
+		if (data->cstream == NULL) {
+			pr_err("Couldn't create compression stream.\n");
+			return -1;
+		}
+
+		ret = ZSTD_initCStream(data->cstream, data->comp_level);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize compression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return -1;
+		}
+	}
+
 	while (input.pos < input.size) {
 		record = dst;
 		size = process_header(record, 0);
@@ -96,6 +85,20 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size
 	ZSTD_inBuffer input = { src, src_size, 0 };
 	ZSTD_outBuffer output = { dst, dst_size, 0 };
 
+	if (!data->dstream) {
+		data->dstream = ZSTD_createDStream();
+		if (data->dstream == NULL) {
+			pr_err("Couldn't create decompression stream.\n");
+			return 0;
+		}
+
+		ret = ZSTD_initDStream(data->dstream);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize decompression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return 0;
+		}
+	}
 	while (input.pos < input.size) {
 		ret = ZSTD_decompressStream(data->dstream, &output, &input);
 		if (ZSTD_isError(ret)) {