summaryrefslogtreecommitdiffstats
path: root/mm/bootmem.c
diff options
context:
space:
mode:
authorJianguo Wu <wujianguo@huawei.com>2012-10-08 16:33:06 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-10-09 16:22:54 +0900
commit7f1290f2f2a4d2c3f1b7ce8e87256e052ca23125 (patch)
tree10328fcb468647ba678e022911d5c2005080f309 /mm/bootmem.c
parent05106e6a54aed321191b4bb5c9ee09538cbad3b1 (diff)
downloadlinux-7f1290f2f2a4d2c3f1b7ce8e87256e052ca23125.tar.bz2
mm: fix-up zone present pages
I think zone->present_pages indicates pages that buddy system can management, it should be: zone->present_pages = spanned pages - absent pages - bootmem pages, but is now: zone->present_pages = spanned pages - absent pages - memmap pages. spanned pages: total size, including holes. absent pages: holes. bootmem pages: pages used in system boot, managed by bootmem allocator. memmap pages: pages used by page structs. This may cause zone->present_pages less than it should be. For example, numa node 1 has ZONE_NORMAL and ZONE_MOVABLE, it's memmap and other bootmem will be allocated from ZONE_MOVABLE, so ZONE_NORMAL's present_pages should be spanned pages - absent pages, but now it also minus memmap pages(free_area_init_core), which are actually allocated from ZONE_MOVABLE. When offlining all memory of a zone, this will cause zone->present_pages less than 0, because present_pages is unsigned long type, it is actually a very large integer, it indirectly caused zone->watermark[WMARK_MIN] becomes a large integer(setup_per_zone_wmarks()), than cause totalreserve_pages become a large integer(calculate_totalreserve_pages()), and finally cause memory allocating failure when fork process(__vm_enough_memory()). [root@localhost ~]# dmesg -bash: fork: Cannot allocate memory I think the bug described in http://marc.info/?l=linux-mm&m=134502182714186&w=2 is also caused by wrong zone present pages. This patch intends to fix-up zone->present_pages when memory are freed to buddy system on x86_64 and IA64 platforms. Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Reported-by: Petr Tesarik <ptesarik@suse.cz> Tested-by: Petr Tesarik <ptesarik@suse.cz> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/bootmem.c')
-rw-r--r--mm/bootmem.c10
1 files changed, 9 insertions, 1 deletions
diff --git a/mm/bootmem.c b/mm/bootmem.c
index f468185b3b28..434be4ae7a04 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -198,6 +198,8 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
int order = ilog2(BITS_PER_LONG);
__free_pages_bootmem(pfn_to_page(start), order);
+ fixup_zone_present_pages(page_to_nid(pfn_to_page(start)),
+ start, start + BITS_PER_LONG);
count += BITS_PER_LONG;
start += BITS_PER_LONG;
} else {
@@ -208,6 +210,9 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
if (vec & 1) {
page = pfn_to_page(start + off);
__free_pages_bootmem(page, 0);
+ fixup_zone_present_pages(
+ page_to_nid(page),
+ start + off, start + off + 1);
count++;
}
vec >>= 1;
@@ -221,8 +226,11 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
pages = bdata->node_low_pfn - bdata->node_min_pfn;
pages = bootmem_bootmap_pages(pages);
count += pages;
- while (pages--)
+ while (pages--) {
+ fixup_zone_present_pages(page_to_nid(page),
+ page_to_pfn(page), page_to_pfn(page) + 1);
__free_pages_bootmem(page++, 0);
+ }
bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);