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 <[email protected]>
Signed-off-by: Jiang Liu <[email protected]>
Reported-by: Petr Tesarik <[email protected]>
Tested-by: Petr Tesarik <[email protected]>
Cc: "Luck, Tony" <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Yinghai Lu <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: David Rientjes <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

arch/ia64/mm/init.c

@@ -637,6 +637,7 @@ mem_init (void)
 
 	high_memory = __va(max_low_pfn * PAGE_SIZE);
 
+	reset_zone_present_pages();
 	for_each_online_pgdat(pgdat)
 		if (pgdat->bdata->node_bootmem_map)
 			totalram_pages += free_all_bootmem_node(pgdat);

include/linux/mm.h

@@ -1684,5 +1684,9 @@ static inline unsigned int debug_guardpage_minorder(void) { return 0; }
 static inline bool page_is_guard(struct page *page) { return false; }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
+extern void reset_zone_present_pages(void);
+extern void fixup_zone_present_pages(int nid, unsigned long start_pfn,
+				unsigned long end_pfn);
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

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);
 

mm/memory_hotplug.c

@@ -106,6 +106,7 @@ static void get_page_bootmem(unsigned long info,  struct page *page,
 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 @@ void __ref put_page_bootmem(struct page *page)
 		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++;
 	}
 
 }

mm/nobootmem.c

@@ -116,6 +116,8 @@ static unsigned long __init __free_memory_core(phys_addr_t start,
 		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 @@ unsigned long __init free_low_memory_core_early(int nodeid)
 	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);
 

mm/page_alloc.c

@@ -6087,3 +6087,37 @@ void dump_page(struct page *page)
 	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);
+	}
+}