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>
diff --git a/mm/bootmem.c b/mm/bootmem.c
index f468185..434be4a 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -198,6 +198,8 @@
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 @@
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 @@
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);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f9ac095..ce690a9 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -106,6 +106,7 @@
void __ref put_page_bootmem(struct page *page)
{
unsigned long type;
+ struct zone *zone;
type = (unsigned long) page->lru.next;
BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
@@ -116,6 +117,12 @@
set_page_private(page, 0);
INIT_LIST_HEAD(&page->lru);
__free_pages_bootmem(page, 0);
+
+ zone = page_zone(page);
+ zone_span_writelock(zone);
+ zone->present_pages++;
+ zone_span_writeunlock(zone);
+ totalram_pages++;
}
}
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index bd82f6b..714d5d6 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -116,6 +116,8 @@
return 0;
__free_pages_memory(start_pfn, end_pfn);
+ fixup_zone_present_pages(pfn_to_nid(start >> PAGE_SHIFT),
+ start_pfn, end_pfn);
return end_pfn - start_pfn;
}
@@ -126,6 +128,7 @@
phys_addr_t start, end, size;
u64 i;
+ reset_zone_present_pages();
for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
count += __free_memory_core(start, end);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8ac5938..00750bc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6087,3 +6087,37 @@
dump_page_flags(page->flags);
mem_cgroup_print_bad_page(page);
}
+
+/* reset zone->present_pages */
+void reset_zone_present_pages(void)
+{
+ struct zone *z;
+ int i, nid;
+
+ for_each_node_state(nid, N_HIGH_MEMORY) {
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ z = NODE_DATA(nid)->node_zones + i;
+ z->present_pages = 0;
+ }
+ }
+}
+
+/* calculate zone's present pages in buddy system */
+void fixup_zone_present_pages(int nid, unsigned long start_pfn,
+ unsigned long end_pfn)
+{
+ struct zone *z;
+ unsigned long zone_start_pfn, zone_end_pfn;
+ int i;
+
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ z = NODE_DATA(nid)->node_zones + i;
+ zone_start_pfn = z->zone_start_pfn;
+ zone_end_pfn = zone_start_pfn + z->spanned_pages;
+
+ /* if the two regions intersect */
+ if (!(zone_start_pfn >= end_pfn || zone_end_pfn <= start_pfn))
+ z->present_pages += min(end_pfn, zone_end_pfn) -
+ max(start_pfn, zone_start_pfn);
+ }
+}