summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorDavid Rientjes <rientjes@google.com>2010-08-09 17:18:54 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-08-09 20:44:56 -0700
commit03668b3ceb0c7a95e09f1b6169f5270ffc1a19f6 (patch)
tree755ea207b968af12e195f6fb3e3b52b4d68e8630 /mm/page_alloc.c
parentad915c432eccb482427c1bbd77c74e6f7bfe60b3 (diff)
downloadlinux-03668b3ceb0c7a95e09f1b6169f5270ffc1a19f6.tar.gz
linux-03668b3ceb0c7a95e09f1b6169f5270ffc1a19f6.tar.bz2
linux-03668b3ceb0c7a95e09f1b6169f5270ffc1a19f6.zip
oom: avoid oom killer for lowmem allocations
If memory has been depleted in lowmem zones even with the protection afforded to it by /proc/sys/vm/lowmem_reserve_ratio, it is unlikely that killing current users will help. The memory is either reclaimable (or migratable) already, in which case we should not invoke the oom killer at all, or it is pinned by an application for I/O. Killing such an application may leave the hardware in an unspecified state and there is no guarantee that it will be able to make a timely exit. Lowmem allocations are now failed in oom conditions when __GFP_NOFAIL is not used so that the task can perhaps recover or try again later. Previously, the heuristic provided some protection for those tasks with CAP_SYS_RAWIO, but this is no longer necessary since we will not be killing tasks for the purposes of ISA allocations. high_zoneidx is gfp_zone(gfp_flags), meaning that ZONE_NORMAL will be the default for all allocations that are not __GFP_DMA, __GFP_DMA32, __GFP_HIGHMEM, and __GFP_MOVABLE on kernels configured to support those flags. Testing for high_zoneidx being less than ZONE_NORMAL will only return true for allocations that have either __GFP_DMA or __GFP_DMA32. Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: David Rientjes <rientjes@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c29
1 files changed, 20 insertions, 9 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9bd339eb04c6..527f73e4c63f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1759,6 +1759,9 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
/* The OOM killer will not help higher order allocs */
if (order > PAGE_ALLOC_COSTLY_ORDER)
goto out;
+ /* The OOM killer does not needlessly kill tasks for lowmem */
+ if (high_zoneidx < ZONE_NORMAL)
+ goto out;
/*
* GFP_THISNODE contains __GFP_NORETRY and we never hit this.
* Sanity check for bare calls of __GFP_THISNODE, not real OOM.
@@ -2052,15 +2055,23 @@ rebalance:
if (page)
goto got_pg;
- /*
- * The OOM killer does not trigger for high-order
- * ~__GFP_NOFAIL allocations so if no progress is being
- * made, there are no other options and retrying is
- * unlikely to help.
- */
- if (order > PAGE_ALLOC_COSTLY_ORDER &&
- !(gfp_mask & __GFP_NOFAIL))
- goto nopage;
+ if (!(gfp_mask & __GFP_NOFAIL)) {
+ /*
+ * The oom killer is not called for high-order
+ * allocations that may fail, so if no progress
+ * is being made, there are no other options and
+ * retrying is unlikely to help.
+ */
+ if (order > PAGE_ALLOC_COSTLY_ORDER)
+ goto nopage;
+ /*
+ * The oom killer is not called for lowmem
+ * allocations to prevent needlessly killing
+ * innocent tasks.
+ */
+ if (high_zoneidx < ZONE_NORMAL)
+ goto nopage;
+ }
goto restart;
}