[PATCH v2 2/4] perf record: bind the AIO user space buffers to nodes

[Alexey Budankov <alexey.budankov@linux.intel.com>]

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@linux.intel.com>
---
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 | 49 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 47 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index e68ba754a8e2..742fa9a8e498 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"
@@ -154,6 +157,46 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb
 }
 
 #ifdef HAVE_AIO_SUPPORT
+
+#ifdef HAVE_LIBNUMA_SUPPORT
+static void perf_mmap__aio_alloc(void **data, size_t len)
+{
+	*data = mmap(NULL, len, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+}
+
+static void perf_mmap__aio_free(void **data, size_t len)
+{
+	munmap(*data, len);
+	*data = NULL;
+}
+
+static void perf_mmap__aio_bind(void *data, size_t len, int cpu, int affinity)
+{
+	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
+		unsigned long node_mask = 1UL << cpu__get_node(cpu);
+		if (mbind(data, len, MPOL_BIND, &node_mask, 1, 0)) {
+			  pr_debug2("failed to bind [%p-%p] to node %d\n",
+				    data, data + len, cpu__get_node(cpu));
+		}
+	}
+}
+#else
+static void perf_mmap__aio_alloc(void **data, size_t len)
+{
+	*data = malloc(len);
+}
+
+static void perf_mmap__aio_free(void **data, size_t len __maybe_unused)
+{
+	zfree(data);
+}
+
+static void perf_mmap__aio_bind(void *data __maybe_unused, size_t len __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;
@@ -177,11 +220,13 @@ 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));
+			size_t mmap_len = perf_mmap__mmap_len(map);
+			perf_mmap__aio_alloc(&(map->aio.data[i]), mmap_len);
 			if (!map->aio.data[i]) {
 				pr_debug2("failed to allocate data buffer area, error %m");
 				return -1;
 			}
+			perf_mmap__aio_bind(map->aio.data[i], mmap_len, map->cpu, mp->affinity);
 			/*
 			 * Use cblock.aio_fildes value different from -1
 			 * to denote started aio write operation on the
@@ -210,7 +255,7 @@ 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->aio.data[i]), perf_mmap__mmap_len(map));
 	if (map->aio.data)
 		zfree(&map->aio.data);
 	zfree(&map->aio.cblocks);