perf record: Implement compression for AIO trace streaming

Compression is implemented using the functions from zstd.c. As the memory
to operate on the compression uses mmap->aio.data[] buffers. If Zstd
streaming compression API fails for some reason the data to be compressed
are just copied into the memory buffers using plain memcpy().

Compressed trace frame consists of an array of PERF_RECORD_COMPRESSED
records. Each element of the array is not longer that PERF_SAMPLE_MAX_SIZE
and consists of perf_event_header followed by the compressed chunk
that is decompressed on the loading stage.

perf_mmap__aio_push() is replaced by perf_mmap__push() which is now used
in the both serial and AIO streaming cases. perf_mmap__push() is extended
with positive return values to signify absence of data ready for
processing.

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/77db2b2c-5d03-dbb0-aeac-c4dd92129ab9@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 1 insertions, 75 deletions

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index d85e73fc82e2..868c0b0e909c 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -289,80 +289,6 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map)
 	zfree(&map->aio.cblocks);
 	zfree(&map->aio.aiocb);
 }
-
-int perf_mmap__aio_push(struct perf_mmap *md, void *to, int idx,
-			int push(void *to, struct aiocb *cblock, void *buf, size_t size, off_t off),
-			off_t *off)
-{
-	u64 head = perf_mmap__read_head(md);
-	unsigned char *data = md->base + page_size;
-	unsigned long size, size0 = 0;
-	void *buf;
-	int rc = 0;
-
-	rc = perf_mmap__read_init(md);
-	if (rc < 0)
-		return (rc == -EAGAIN) ? 0 : -1;
-
-	/*
-	 * md->base data is copied into md->data[idx] buffer to
-	 * release space in the kernel buffer as fast as possible,
-	 * thru perf_mmap__consume() below.
-	 *
-	 * That lets the kernel to proceed with storing more
-	 * profiling data into the kernel buffer earlier than other
-	 * per-cpu kernel buffers are handled.
-	 *
-	 * Coping can be done in two steps in case the chunk of
-	 * profiling data crosses the upper bound of the kernel buffer.
-	 * In this case we first move part of data from md->start
-	 * till the upper bound and then the reminder from the
-	 * beginning of the kernel buffer till the end of
-	 * the data chunk.
-	 */
-
-	size = md->end - md->start;
-
-	if ((md->start & md->mask) + size != (md->end & md->mask)) {
-		buf = &data[md->start & md->mask];
-		size = md->mask + 1 - (md->start & md->mask);
-		md->start += size;
-		memcpy(md->aio.data[idx], buf, size);
-		size0 = size;
-	}
-
-	buf = &data[md->start & md->mask];
-	size = md->end - md->start;
-	md->start += size;
-	memcpy(md->aio.data[idx] + size0, buf, size);
-
-	/*
-	 * Increment md->refcount to guard md->data[idx] buffer
-	 * from premature deallocation because md object can be
-	 * released earlier than aio write request started
-	 * on mmap->data[idx] is complete.
-	 *
-	 * perf_mmap__put() is done at record__aio_complete()
-	 * after started request completion.
-	 */
-	perf_mmap__get(md);
-
-	md->prev = head;
-	perf_mmap__consume(md);
-
-	rc = push(to, &md->aio.cblocks[idx], md->aio.data[idx], size0 + size, *off);
-	if (!rc) {
-		*off += size0 + size;
-	} else {
-		/*
-		 * Decrement md->refcount back if aio write
-		 * operation failed to start.
-		 */
-		perf_mmap__put(md);
-	}
-
-	return rc;
-}
 #else /* !HAVE_AIO_SUPPORT */
 static int perf_mmap__aio_enabled(struct perf_mmap *map __maybe_unused)
 {
@@ -566,7 +492,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 
 	rc = perf_mmap__read_init(md);
 	if (rc < 0)
-		return (rc == -EAGAIN) ? 0 : -1;
+		return (rc == -EAGAIN) ? 1 : -1;
 
 	size = md->end - md->start;