diff options
author | Miao Xie <miaox@cn.fujitsu.com> | 2010-05-24 17:32:08 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-05-25 11:06:57 -0400 |
commit | c0ff7453bb5c7c98e0885fb94279f2571946f280 (patch) | |
tree | 8bb2b169a5145f0496575dbd2f48bb4b1c83f819 /mm/hugetlb.c | |
parent | 708c1bbc9d0c3e57f40501794d9b0eed29d10fce (diff) |
cpuset,mm: fix no node to alloc memory when changing cpuset's mems
Before applying this patch, cpuset updates task->mems_allowed and
mempolicy by setting all new bits in the nodemask first, and clearing all
old unallowed bits later. But in the way, the allocator may find that
there is no node to alloc memory.
The reason is that cpuset rebinds the task's mempolicy, it cleans the
nodes which the allocater can alloc pages on, for example:
(mpol: mempolicy)
task1 task1's mpol task2
alloc page 1
alloc on node0? NO 1
1 change mems from 1 to 0
1 rebind task1's mpol
0-1 set new bits
0 clear disallowed bits
alloc on node1? NO 0
...
can't alloc page
goto oom
This patch fixes this problem by expanding the nodes range first(set newly
allowed bits) and shrink it lazily(clear newly disallowed bits). So we
use a variable to tell the write-side task that read-side task is reading
nodemask, and the write-side task clears newly disallowed nodes after
read-side task ends the current memory allocation.
[akpm@linux-foundation.org: fix spello]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Paul Menage <menage@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r-- | mm/hugetlb.c | 12 |
1 files changed, 8 insertions, 4 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4c9e6bbf377..54d42b009db 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c | |||
@@ -465,11 +465,13 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, | |||
465 | struct page *page = NULL; | 465 | struct page *page = NULL; |
466 | struct mempolicy *mpol; | 466 | struct mempolicy *mpol; |
467 | nodemask_t *nodemask; | 467 | nodemask_t *nodemask; |
468 | struct zonelist *zonelist = huge_zonelist(vma, address, | 468 | struct zonelist *zonelist; |
469 | htlb_alloc_mask, &mpol, &nodemask); | ||
470 | struct zone *zone; | 469 | struct zone *zone; |
471 | struct zoneref *z; | 470 | struct zoneref *z; |
472 | 471 | ||
472 | get_mems_allowed(); | ||
473 | zonelist = huge_zonelist(vma, address, | ||
474 | htlb_alloc_mask, &mpol, &nodemask); | ||
473 | /* | 475 | /* |
474 | * A child process with MAP_PRIVATE mappings created by their parent | 476 | * A child process with MAP_PRIVATE mappings created by their parent |
475 | * have no page reserves. This check ensures that reservations are | 477 | * have no page reserves. This check ensures that reservations are |
@@ -477,11 +479,11 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, | |||
477 | */ | 479 | */ |
478 | if (!vma_has_reserves(vma) && | 480 | if (!vma_has_reserves(vma) && |
479 | h->free_huge_pages - h->resv_huge_pages == 0) | 481 | h->free_huge_pages - h->resv_huge_pages == 0) |
480 | return NULL; | 482 | goto err; |
481 | 483 | ||
482 | /* If reserves cannot be used, ensure enough pages are in the pool */ | 484 | /* If reserves cannot be used, ensure enough pages are in the pool */ |
483 | if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) | 485 | if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) |
484 | return NULL; | 486 | goto err;; |
485 | 487 | ||
486 | for_each_zone_zonelist_nodemask(zone, z, zonelist, | 488 | for_each_zone_zonelist_nodemask(zone, z, zonelist, |
487 | MAX_NR_ZONES - 1, nodemask) { | 489 | MAX_NR_ZONES - 1, nodemask) { |
@@ -500,7 +502,9 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, | |||
500 | break; | 502 | break; |
501 | } | 503 | } |
502 | } | 504 | } |
505 | err: | ||
503 | mpol_cond_put(mpol); | 506 | mpol_cond_put(mpol); |
507 | put_mems_allowed(); | ||
504 | return page; | 508 | return page; |
505 | } | 509 | } |
506 | 510 | ||