summaryrefslogtreecommitdiffstats
path: root/arch/sparc
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.com>2016-06-24 14:49:12 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-06-24 17:23:52 -0700
commit2379a23e34b58520dfc8f4909f116a08393138e4 (patch)
treec75c83a3a70479525083511e26fd7818353a76ce /arch/sparc
parenta4135b93898fe38ea4136c6b03b29b746e08c83a (diff)
downloadop-kernel-dev-2379a23e34b58520dfc8f4909f116a08393138e4.zip
op-kernel-dev-2379a23e34b58520dfc8f4909f116a08393138e4.tar.gz
powerpc: get rid of superfluous __GFP_REPEAT
__GFP_REPEAT has a rather weak semantic but since it has been introduced around 2.6.12 it has been ignored for low order allocations. {pud,pmd}_alloc_one are allocating from {PGT,PUD}_CACHE initialized in pgtable_cache_init which doesn't have larger than sizeof(void *) << 12 size and that fits into !costly allocation request size. PGALLOC_GFP is used only in radix__pgd_alloc which uses either order-0 or order-4 requests. The first one doesn't need the flag while the second does. Drop __GFP_REPEAT from PGALLOC_GFP and add it for the order-4 one. This means that this flag has never been actually useful here because it has always been used only for PAGE_ALLOC_COSTLY requests. Link: http://lkml.kernel.org/r/1464599699-30131-12-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'arch/sparc')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud