diff options
| author | Mel Gorman <mgorman@suse.de> | 2014-08-28 19:34:44 +0100 |
|---|---|---|
| committer | Jiri Slaby <jslaby@suse.cz> | 2014-09-26 11:51:56 +0200 |
| commit | 337c9823cf0b93c8f4d1c4654bd93cf24e5b837b (patch) | |
| tree | 76c04b196afd4d715011190e8ecffac1a9f05eaf /mm/slub.c | |
| parent | 8010da4957163cce03a9a27b7f3dbeb5a77a3954 (diff) | |
| download | lwn-337c9823cf0b93c8f4d1c4654bd93cf24e5b837b.tar.gz lwn-337c9823cf0b93c8f4d1c4654bd93cf24e5b837b.zip | |
mm: optimize put_mems_allowed() usage
commit d26914d11751b23ca2e8747725f2cae10c2f2c1b upstream.
Since put_mems_allowed() is strictly optional, its a seqcount retry, we
don't need to evaluate the function if the allocation was in fact
successful, saving a smp_rmb some loads and comparisons on some relative
fast-paths.
Since the naming, get/put_mems_allowed() does suggest a mandatory
pairing, rename the interface, as suggested by Mel, to resemble the
seqcount interface.
This gives us: read_mems_allowed_begin() and read_mems_allowed_retry(),
where it is important to note that the return value of the latter call
is inverted from its previous incarnation.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Diffstat (limited to 'mm/slub.c')
| -rw-r--r-- | mm/slub.c | 16 |
1 files changed, 7 insertions, 9 deletions
diff --git a/mm/slub.c b/mm/slub.c index 5c1343a391d0..a88d94cfee20 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1635,7 +1635,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, return NULL; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1647,19 +1647,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, object = get_partial_node(s, n, c, flags); if (object) { /* - * Return the object even if - * put_mems_allowed indicated that - * the cpuset mems_allowed was - * updated in parallel. It's a - * harmless race between the alloc - * and the cpuset update. + * Don't check read_mems_allowed_retry() + * here - if mems_allowed was updated in + * parallel, that was a harmless race + * between allocation and the cpuset + * update */ - put_mems_allowed(cpuset_mems_cookie); return object; } } } - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); #endif return NULL; } |