perf report: Implement perf.data record decompression

zstd_init(, comp_level = 0) initializes decompression part of API only
hat now consists of zstd_decompress_stream() function.

The perf.data PERF_RECORD_COMPRESSED records are decompressed using
zstd_decompress_stream() function into a linked list of mmaped memory
regions of mmap_comp_len size (struct decomp).

After decompression of one COMPRESSED record its content is iterated and
fetched for usual processing. The mmaped memory regions with
decompressed events are kept in the linked list till the tool process
termination.

When dumping raw records (e.g., perf report -D --header) file offsets of
events from compressed records are printed as zero.

Committer notes:

Since now we have support for processing PERF_RECORD_COMPRESSED, we see
none, in raw form, like we saw in the previous patch commiter notes,
they were decompressed into the usual PERF_RECORD_{FORK,MMAP,COMM,etc}
records, we only see the stats for those PERF_RECORD_COMPRESSED events,
and since I used the file generated in the commiter notes for the
previous patch, there they are, 2 compressed records:

  $ perf report --header-only | grep cmdline
  # cmdline : /home/acme/bin/perf record -z2 sleep 1
  $ perf report -D | grep COMPRESS
        COMPRESSED events:          2
        COMPRESSED events:          0
  $ perf report --stdio
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 15  of event 'cycles:u'
  # Event count (approx.): 962227
  #
  # Overhead  Command  Shared Object     Symbol
  # ........  .......  ................  ...........................
  #
      46.99%  sleep    libc-2.28.so      [.] _dl_addr
      29.24%  sleep    [unknown]         [k] 0xffffffffaea00a67
      16.45%  sleep    libc-2.28.so      [.] __GI__IO_un_link.part.1
       5.92%  sleep    ld-2.28.so        [.] _dl_setup_hash
       1.40%  sleep    libc-2.28.so      [.] __nanosleep
       0.00%  sleep    [unknown]         [k] 0xffffffffaea00163

  #
  # (Tip: To see callchains in a more compact form: perf report -g folded)
  #
  $

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
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/304b0a59-942c-3fe1-da02-aa749f87108b@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 115 insertions, 1 deletions

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ec1dec86d0e1..2310a1752983 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -29,6 +29,61 @@
 #include "stat.h"
 #include "arch/common.h"
 
+#ifdef HAVE_ZSTD_SUPPORT
+static int perf_session__process_compressed_event(struct perf_session *session,
+						  union perf_event *event, u64 file_offset)
+{
+	void *src;
+	size_t decomp_size, src_size;
+	u64 decomp_last_rem = 0;
+	size_t decomp_len = session->header.env.comp_mmap_len;
+	struct decomp *decomp, *decomp_last = session->decomp_last;
+
+	decomp = mmap(NULL, sizeof(struct decomp) + decomp_len, PROT_READ|PROT_WRITE,
+		      MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+	if (decomp == MAP_FAILED) {
+		pr_err("Couldn't allocate memory for decompression\n");
+		return -1;
+	}
+
+	decomp->file_pos = file_offset;
+	decomp->head = 0;
+
+	if (decomp_last) {
+		decomp_last_rem = decomp_last->size - decomp_last->head;
+		memcpy(decomp->data, &(decomp_last->data[decomp_last->head]), decomp_last_rem);
+		decomp->size = decomp_last_rem;
+	}
+
+	src = (void *)event + sizeof(struct compressed_event);
+	src_size = event->pack.header.size - sizeof(struct compressed_event);
+
+	decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size,
+				&(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem);
+	if (!decomp_size) {
+		munmap(decomp, sizeof(struct decomp) + decomp_len);
+		pr_err("Couldn't decompress data\n");
+		return -1;
+	}
+
+	decomp->size += decomp_size;
+
+	if (session->decomp == NULL) {
+		session->decomp = decomp;
+		session->decomp_last = decomp;
+	} else {
+		session->decomp_last->next = decomp;
+		session->decomp_last = decomp;
+	}
+
+	pr_debug("decomp (B): %ld to %ld\n", src_size, decomp_size);
+
+	return 0;
+}
+#else /* !HAVE_ZSTD_SUPPORT */
+#define perf_session__process_compressed_event perf_session__process_compressed_event_stub
+#endif
+
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
@@ -197,6 +252,21 @@ static void perf_session__delete_threads(struct perf_session *session)
 	machine__delete_threads(&session->machines.host);
 }
 
+static void perf_session__release_decomp_events(struct perf_session *session)
+{
+	struct decomp *next, *decomp;
+	size_t decomp_len;
+	next = session->decomp;
+	decomp_len = session->header.env.comp_mmap_len;
+	do {
+		decomp = next;
+		if (decomp == NULL)
+			break;
+		next = decomp->next;
+		munmap(decomp, decomp_len + sizeof(struct decomp));
+	} while (1);
+}
+
 void perf_session__delete(struct perf_session *session)
 {
 	if (session == NULL)
@@ -205,6 +275,7 @@ void perf_session__delete(struct perf_session *session)
 	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
 	perf_session__delete_threads(session);
+	perf_session__release_decomp_events(session);
 	perf_env__exit(&session->header.env);
 	machines__exit(&session->machines);
 	if (session->data)
@@ -439,7 +510,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->feature == NULL)
 		tool->feature = process_event_op2_stub;
 	if (tool->compressed == NULL)
-		tool->compressed = perf_session__process_compressed_event_stub;
+		tool->compressed = perf_session__process_compressed_event;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -1725,6 +1796,8 @@ static int perf_session__flush_thread_stacks(struct perf_session *session)
 
 volatile int session_done;
 
+static int __perf_session__process_decomp_events(struct perf_session *session);
+
 static int __perf_session__process_pipe_events(struct perf_session *session)
 {
 	struct ordered_events *oe = &session->ordered_events;
@@ -1805,6 +1878,10 @@ more:
 	if (skip > 0)
 		head += skip;
 
+	err = __perf_session__process_decomp_events(session);
+	if (err)
+		goto out_err;
+
 	if (!session_done())
 		goto more;
 done:
@@ -1853,6 +1930,39 @@ fetch_mmaped_event(struct perf_session *session,
 	return event;
 }
 
+static int __perf_session__process_decomp_events(struct perf_session *session)
+{
+	s64 skip;
+	u64 size, file_pos = 0;
+	struct decomp *decomp = session->decomp_last;
+
+	if (!decomp)
+		return 0;
+
+	while (decomp->head < decomp->size && !session_done()) {
+		union perf_event *event = fetch_mmaped_event(session, decomp->head, decomp->size, decomp->data);
+
+		if (!event)
+			break;
+
+		size = event->header.size;
+
+		if (size < sizeof(struct perf_event_header) ||
+		    (skip = perf_session__process_event(session, event, file_pos)) < 0) {
+			pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+				decomp->file_pos + decomp->head, event->header.size, event->header.type);
+			return -EINVAL;
+		}
+
+		if (skip)
+			size += skip;
+
+		decomp->head += size;
+	}
+
+	return 0;
+}
+
 /*
  * On 64bit we can mmap the data file in one go. No need for tiny mmap
  * slices. On 32bit we use 32MB.
@@ -1962,6 +2072,10 @@ more:
 	head += size;
 	file_pos += size;
 
+	err = __perf_session__process_decomp_events(session);
+	if (err)
+		goto out;
+
 	ui_progress__update(prog, size);
 
 	if (session_done())