[PATCH v4 05/10] perf mmap: implement dedicated memory buffer for data compression

[Alexey Budankov]

Implemented mmap data buffer that is used as the memory to operate
on when compressing sampling data in case of serial trace streaming.

In case of AIO trace streaming AIO buffers are used to implement
sampling data compression.

Signed-off-by: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
---
 tools/perf/builtin-record.c |  6 +++++-
 tools/perf/util/evlist.c    |  8 +++++---
 tools/perf/util/evlist.h    |  2 +-
 tools/perf/util/mmap.c      | 25 +++++++++++++++++++++++++
 tools/perf/util/mmap.h      |  4 +++-
 5 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4e992f51e914..1c0d68d27360 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -572,7 +572,7 @@ static int record__mmap_evlist(struct record *rec,
 				 opts->auxtrace_mmap_pages,
 				 opts->auxtrace_snapshot_mode,
 				 opts->nr_cblocks, opts->affinity,
-				 opts->mmap_flush) < 0) {
+				 opts->mmap_flush, opts->comp_level) < 0) {
 		if (errno == EPERM) {
 			pr_err("Permission error mapping pages.\n"
 			       "Consider increasing "
@@ -2241,6 +2241,10 @@ int cmd_record(int argc, const char **argv)
 	pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
 	pr_debug("mmap flush: %d\n", rec->opts.mmap_flush);
 
+	if (rec->opts.comp_level > 22)
+		rec->opts.comp_level = 0;
+	pr_debug("comp level: %d\n", rec->opts.comp_level);
+
 	err = __cmd_record(&record, argc, argv);
 out:
 	perf_evlist__delete(rec->evlist);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 937039faac59..a13458b43dc1 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1022,7 +1022,8 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush)
+			 bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush,
+			 int comp_level)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
@@ -1032,7 +1033,8 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	 * Its value is decided by evsel's write_backward.
 	 * So &mp should not be passed through const pointer.
 	 */
-	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush };
+	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush,
+				  .comp_level = comp_level };
 
 	if (!evlist->mmap)
 		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1064,7 +1066,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1);
+	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index edf18811e39f..77c11dac4a63 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -166,7 +166,7 @@ unsigned long perf_event_mlock_kb_in_pages(void);
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
 			 bool auxtrace_overwrite, int nr_cblocks,
-			 int affinity, int flush);
+			 int affinity, int flush, int comp_level);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index ef3d79b2c90b..08fd846df604 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -159,6 +159,10 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb
 #ifdef HAVE_AIO_SUPPORT
 
 #ifdef HAVE_LIBNUMA_SUPPORT
+static int perf_mmap__aio_enabled(struct perf_mmap *map)
+{
+	return map->aio.nr_cblocks > 0;
+}
 static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx)
 {
 	map->aio.data[idx] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
@@ -199,6 +203,10 @@ static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affi
 	return 0;
 }
 #else
+static int perf_mmap__aio_enabled(struct perf_mmap *map __maybe_unused)
+{
+	return 0;
+}
 static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx)
 {
 	map->aio.data[idx] = malloc(perf_mmap__mmap_len(map));
@@ -374,6 +382,10 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map __maybe_unused)
 void perf_mmap__munmap(struct perf_mmap *map)
 {
 	perf_mmap__aio_munmap(map);
+	if (map->data != NULL) {
+		munmap(map->data, perf_mmap__mmap_len(map));
+		map->data = NULL;
+	}
 	if (map->base != NULL) {
 		munmap(map->base, perf_mmap__mmap_len(map));
 		map->base = NULL;
@@ -442,6 +454,19 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c
 
 	map->flush = mp->flush;
 
+	map->comp_level = mp->comp_level;
+
+	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
+		map->data = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+		if (map->data == MAP_FAILED) {
+			pr_debug2("failed to mmap data buffer, error %d\n",
+					errno);
+			map->data = NULL;
+			return -1;
+		}
+	}
+
 	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
 				&mp->auxtrace_mp, map->base, fd))
 		return -1;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index b82f8c2d55c4..a02427d609c0 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -40,6 +40,8 @@ struct perf_mmap {
 #endif
 	cpu_set_t	affinity_mask;
 	u64		flush;
+	void 		*data;
+	int		comp_level;
 };
 
 /*
@@ -71,7 +73,7 @@ enum bkw_mmap_state {
 };
 
 struct mmap_params {
-	int			    prot, mask, nr_cblocks, affinity, flush;
+	int prot, mask, nr_cblocks, affinity, flush, comp_level;
 	struct auxtrace_mmap_params auxtrace_mp;
 };