summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.com>2016-01-14 15:19:05 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-14 16:00:49 -0800
commit33d5310306ec244d96533da5f9183e05a7a51106 (patch)
tree7cf5a0493091776b205d7f8ae4288f7d9e05c9e6 /mm
parentfde82aaa731de8a23d817971f6080041a4917d06 (diff)
downloadlinux-33d5310306ec244d96533da5f9183e05a7a51106.tar.gz
linux-33d5310306ec244d96533da5f9183e05a7a51106.tar.bz2
linux-33d5310306ec244d96533da5f9183e05a7a51106.zip
mm/page_alloc.c: do not loop over ALLOC_NO_WATERMARKS without triggering reclaim
__alloc_pages_slowpath is looping over ALLOC_NO_WATERMARKS requests if __GFP_NOFAIL is requested. This is fragile because we are basically relying on somebody else to make the reclaim (be it the direct reclaim or OOM killer) for us. The caller might be holding resources (e.g. locks) which block other other reclaimers from making any progress for example. Remove the retry loop and rely on __alloc_pages_slowpath to invoke all allowed reclaim steps and retry logic. We have to be careful about __GFP_NOFAIL allocations from the PF_MEMALLOC context even though this is a very bad idea to begin with because no progress can be gurateed at all. We shouldn't break the __GFP_NOFAIL semantic here though. It could be argued that this is essentially GFP_NOWAIT context which we do not support but PF_MEMALLOC is much harder to check for existing users because they might happen deep down the code path performed much later after setting the flag so we cannot really rule out there is no kernel path triggering this combination. Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: David Rientjes <rientjes@google.com> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/page_alloc.c32
1 files changed, 18 insertions, 14 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1f3c26992e90..2a6fe377cafc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3020,32 +3020,36 @@ retry:
* allocations are system rather than user orientated
*/
ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
- do {
- page = get_page_from_freelist(gfp_mask, order,
- ALLOC_NO_WATERMARKS, ac);
- if (page)
- goto got_pg;
-
- if (gfp_mask & __GFP_NOFAIL)
- wait_iff_congested(ac->preferred_zone,
- BLK_RW_ASYNC, HZ/50);
- } while (gfp_mask & __GFP_NOFAIL);
+ page = get_page_from_freelist(gfp_mask, order,
+ ALLOC_NO_WATERMARKS, ac);
+ if (page)
+ goto got_pg;
}
/* Caller is not willing to reclaim, we can't balance anything */
if (!can_direct_reclaim) {
/*
- * All existing users of the deprecated __GFP_NOFAIL are
- * blockable, so warn of any new users that actually allow this
- * type of allocation to fail.
+ * All existing users of the __GFP_NOFAIL are blockable, so warn
+ * of any new users that actually allow this type of allocation
+ * to fail.
*/
WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL);
goto nopage;
}
/* Avoid recursion of direct reclaim */
- if (current->flags & PF_MEMALLOC)
+ if (current->flags & PF_MEMALLOC) {
+ /*
+ * __GFP_NOFAIL request from this context is rather bizarre
+ * because we cannot reclaim anything and only can loop waiting
+ * for somebody to do a work for us.
+ */
+ if (WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
+ cond_resched();
+ goto retry;
+ }
goto nopage;
+ }
/* Avoid allocations with no watermarks from looping endlessly */
if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))