summaryrefslogtreecommitdiff
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorKAMEZAWA Hiroyuki <kamezawa.hioryu@jp.fujitsu.com>2009-12-15 16:45:33 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-12-16 07:19:57 -0800
commit4365a5676fa3aa1d5ae6c90c22a0044f09ba584e (patch)
tree5b9914ccbdcf2aa695473421e71f6299fbe78cef /mm/page_alloc.c
parent3b4798cbc13dd8d1150aa6377f97f0e11450a67d (diff)
downloadconfigs-4365a5676fa3aa1d5ae6c90c22a0044f09ba584e.tar.gz
oom-kill: fix NUMA constraint check with nodemask
Fix node-oriented allocation handling in oom-kill.c I myself think of this as a bugfix not as an ehnancement. In these days, things are changed as - alloc_pages() eats nodemask as its arguments, __alloc_pages_nodemask(). - mempolicy don't maintain its own private zonelists. (And cpuset doesn't use nodemask for __alloc_pages_nodemask()) So, current oom-killer's check function is wrong. This patch does - check nodemask, if nodemask && nodemask doesn't cover all node_states[N_HIGH_MEMORY], this is CONSTRAINT_MEMORY_POLICY. - Scan all zonelist under nodemask, if it hits cpuset's wall this faiulre is from cpuset. And - modifies the caller of out_of_memory not to call oom if __GFP_THISNODE. This doesn't change "current" behavior. If callers use __GFP_THISNODE it should handle "page allocation failure" by itself. - handle __GFP_NOFAIL+__GFP_THISNODE path. This is something like a FIXME but this gfpmask is not used now. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hioryu@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> 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.c22
1 files changed, 16 insertions, 6 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 59d2e88fb47..850c4a7e2fe 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1654,12 +1654,22 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
if (page)
goto out;
- /* The OOM killer will not help higher order allocs */
- if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_NOFAIL))
- goto out;
-
+ if (!(gfp_mask & __GFP_NOFAIL)) {
+ /* The OOM killer will not help higher order allocs */
+ if (order > PAGE_ALLOC_COSTLY_ORDER)
+ goto out;
+ /*
+ * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
+ * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
+ * The caller should handle page allocation failure by itself if
+ * it specifies __GFP_THISNODE.
+ * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER.
+ */
+ if (gfp_mask & __GFP_THISNODE)
+ goto out;
+ }
/* Exhausted what can be done so it's blamo time */
- out_of_memory(zonelist, gfp_mask, order);
+ out_of_memory(zonelist, gfp_mask, order, nodemask);
out:
clear_zonelist_oom(zonelist, gfp_mask);
@@ -3123,7 +3133,7 @@ static int __cpuinit process_zones(int cpu)
if (percpu_pagelist_fraction)
setup_pagelist_highmark(zone_pcp(zone, cpu),
- (zone->present_pages / percpu_pagelist_fraction));
+ (zone->present_pages / percpu_pagelist_fraction));
}
return 0;