mm: optimize put_mems_allowed() usage
authorMel Gorman <mgorman@suse.de>
Thu, 3 Apr 2014 21:47:24 +0000 (14:47 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Thu, 3 Apr 2014 23:20:58 +0000 (16:20 -0700)
commitd26914d11751b23ca2e8747725f2cae10c2f2c1b
tree020b606fb9223e29292f54922a11111239e3a3f4
parent91ca9186484809c57303b33778d841cc28f696ed
mm: optimize put_mems_allowed() usage

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>
include/linux/cpuset.h
kernel/cpuset.c
mm/filemap.c
mm/hugetlb.c
mm/mempolicy.c
mm/page_alloc.c
mm/slab.c
mm/slub.c