perf tools: Introduce Zstd streaming based compression API

Implemented functions are based on Zstd streaming compression API.

The functions are used in runtime to compress data that come from mmaped
kernel buffer. zstd_init(), zstd_fini() are used for initialization and
finalization to allocate and deallocate internal zstd objects.
zstd_compress_stream_to_records() is used to convert parts of mmaped
kernel buffer into an array of PERF_RECORD_COMPRESSED records.

Signed-off-by: Alexey Budankov <[email protected]>
Reviewed-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

tools/perf/util/Build

@@ -145,6 +145,8 @@ perf-y += scripting-engines/
 
 perf-$(CONFIG_ZLIB) += zlib.o
 perf-$(CONFIG_LZMA) += lzma.o
+perf-$(CONFIG_ZSTD) += zstd.o
+
 perf-y += demangle-java.o
 perf-y += demangle-rust.o
 

tools/perf/util/compress.h

@@ -2,6 +2,11 @@
 #ifndef PERF_COMPRESS_H
 #define PERF_COMPRESS_H
 
+#include <stdbool.h>
+#ifdef HAVE_ZSTD_SUPPORT
+#include <zstd.h>
+#endif
+
 #ifdef HAVE_ZLIB_SUPPORT
 int gzip_decompress_to_file(const char *input, int output_fd);
 bool gzip_is_compressed(const char *input);
@@ -12,4 +17,41 @@ int lzma_decompress_to_file(const char *input, int output_fd);
 bool lzma_is_compressed(const char *input);
 #endif
 
+struct zstd_data {
+#ifdef HAVE_ZSTD_SUPPORT
+	ZSTD_CStream	*cstream;
+#endif
+};
+
+#ifdef HAVE_ZSTD_SUPPORT
+
+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,
+				       void *src, size_t src_size, size_t max_record_size,
+				       size_t process_header(void *record, size_t increment));
+#else /* !HAVE_ZSTD_SUPPORT */
+
+static inline int zstd_init(struct zstd_data *data __maybe_unused, int level __maybe_unused)
+{
+	return 0;
+}
+
+static inline int zstd_fini(struct zstd_data *data __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+size_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,
+				       size_t process_header(void *record, size_t increment) __maybe_unused)
+{
+	return 0;
+}
+#endif
+
 #endif /* PERF_COMPRESS_H */

tools/perf/util/zstd.c

@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include "util/compress.h"
+#include "util/debug.h"
+
+int zstd_init(struct zstd_data *data, int level)
+{
+	size_t ret;
+
+	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;
+	}
+
+	return 0;
+}
+
+int zstd_fini(struct zstd_data *data)
+{
+	if (data->cstream) {
+		ZSTD_freeCStream(data->cstream);
+		data->cstream = NULL;
+	}
+
+	return 0;
+}
+
+size_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))
+{
+	size_t ret, size, compressed = 0;
+	ZSTD_inBuffer input = { src, src_size, 0 };
+	ZSTD_outBuffer output;
+	void *record;
+
+	while (input.pos < input.size) {
+		record = dst;
+		size = process_header(record, 0);
+		compressed += size;
+		dst += size;
+		dst_size -= size;
+		output = (ZSTD_outBuffer){ dst, (dst_size > max_record_size) ?
+						max_record_size : dst_size, 0 };
+		ret = ZSTD_compressStream(data->cstream, &output, &input);
+		ZSTD_flushStream(data->cstream, &output);
+		if (ZSTD_isError(ret)) {
+			pr_err("failed to compress %ld bytes: %s\n",
+				(long)src_size, ZSTD_getErrorName(ret));
+			memcpy(dst, src, src_size);
+			return src_size;
+		}
+		size = output.pos;
+		size = process_header(record, size);
+		compressed += size;
+		dst += size;
+		dst_size -= size;
+	}
+
+	return compressed;
+}