[PATCH v3 2/4] perf record: bind the AIO user space buffers to nodes

[Alexey Budankov]

Allocate and bind AIO user space buffers to the memory nodes
that mmap kernel buffers are bound to.

Signed-off-by: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
---
Changes in v3:
- corrected code style issues
- adjusted __aio_alloc,__aio_bind,__aio_free() implementation
Changes in v2:
- implemented perf_mmap__aio_alloc, perf_mmap__aio_free, perf_mmap__aio_bind 
  and put HAVE_LIBNUMA_SUPPORT #ifdefs in there
---
 tools/perf/util/mmap.c | 71 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 67 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index e68ba754a8e2..e5220790f1fb 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -10,6 +10,9 @@
 #include <sys/mman.h>
 #include <inttypes.h>
 #include <asm/bug.h>
+#ifdef HAVE_LIBNUMA_SUPPORT
+#include <numaif.h>
+#endif
 #include "debug.h"
 #include "event.h"
 #include "mmap.h"
@@ -154,9 +157,68 @@ 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_alloc(struct perf_mmap *map, int index)
+{
+	map->aio.data[index] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+				    MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+	if (map->aio.data[index] == MAP_FAILED) {
+		map->aio.data[index] = NULL;
+		return -1;
+	}
+
+	return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int index)
+{
+	if (map->aio.data[index]) {
+		munmap(map->aio.data[index], perf_mmap__mmap_len(map));
+		map->aio.data[index] = NULL;
+	}
+}
+
+static void perf_mmap__aio_bind(struct perf_mmap *map, int index, int cpu, int affinity)
+{
+	void *data;
+	size_t mmap_len;
+	unsigned long node_mask;
+
+	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
+		data = map->aio.data[index];
+		mmap_len = perf_mmap__mmap_len(map);
+		node_mask = 1UL << cpu__get_node(cpu);
+		if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
+			pr_warn("failed to bind [%p-%p] to node %d\n",
+				data, data + mmap_len, cpu__get_node(cpu));
+		}
+	}
+}
+#else
+static int perf_mmap__aio_alloc(struct perf_mmap *map, int index)
+{
+	map->aio.data[index] = malloc(perf_mmap__mmap_len(map));
+	if (map->aio.data[index] == NULL)
+		return -1;
+
+	return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int index)
+{
+	zfree(&(map->aio.data[index]));
+}
+
+static void perf_mmap__aio_bind(struct perf_mmap *map __maybe_unused, int index __maybe_unused,
+		int cpu __maybe_unused, int affinity __maybe_unused)
+{
+}
+#endif
+
 static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
 {
-	int delta_max, i, prio;
+	int delta_max, i, prio, ret;
 
 	map->aio.nr_cblocks = mp->nr_cblocks;
 	if (map->aio.nr_cblocks) {
@@ -177,11 +239,12 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
 		}
 		delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
 		for (i = 0; i < map->aio.nr_cblocks; ++i) {
-			map->aio.data[i] = malloc(perf_mmap__mmap_len(map));
-			if (!map->aio.data[i]) {
+			ret = perf_mmap__aio_alloc(map, i);
+			if (ret == -1) {
 				pr_debug2("failed to allocate data buffer area, error %m");
 				return -1;
 			}
+			perf_mmap__aio_bind(map, i, map->cpu, mp->affinity);
 			/*
 			 * Use cblock.aio_fildes value different from -1
 			 * to denote started aio write operation on the
@@ -210,7 +273,7 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map)
 	int i;
 
 	for (i = 0; i < map->aio.nr_cblocks; ++i)
-		zfree(&map->aio.data[i]);
+		perf_mmap__aio_free(map, i);
 	if (map->aio.data)
 		zfree(&map->aio.data);
 	zfree(&map->aio.cblocks);