1 files changed, 190 insertions, 63 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7990ca154d1..794e6715c22 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -57,6 +57,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/memcontrol.h>
 #include <linux/prefetch.h>
+#include <linux/page-debug-flags.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -96,6 +97,14 @@ EXPORT_SYMBOL(node_states);
 
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
+/*
+ * When calculating the number of globally allowed dirty pages, there
+ * is a certain number of per-zone reserves that should not be
+ * considered dirtyable memory.  This is the sum of those reserves
+ * over all existing zones that contribute dirtyable memory.
+ */
+unsigned long dirty_balance_reserve __read_mostly;
+
 int percpu_pagelist_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
 
@@ -127,6 +136,13 @@ void pm_restrict_gfp_mask(void)
 	saved_gfp_mask = gfp_allowed_mask;
 	gfp_allowed_mask &= ~GFP_IOFS;
 }
+
+bool pm_suspended_storage(void)
+{
+	if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+		return false;
+	return true;
+}
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -381,6 +397,37 @@ static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
 		clear_highpage(page + i);
 }
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
+unsigned int _debug_guardpage_minorder;
+
+static int __init debug_guardpage_minorder_setup(char *buf)
+{
+	unsigned long res;
+
+	if (kstrtoul(buf, 10, &res) < 0 ||  res > MAX_ORDER / 2) {
+		printk(KERN_ERR "Bad debug_guardpage_minorder value\n");
+		return 0;
+	}
+	_debug_guardpage_minorder = res;
+	printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res);
+	return 0;
+}
+__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
+
+static inline void set_page_guard_flag(struct page *page)
+{
+	__set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+
+static inline void clear_page_guard_flag(struct page *page)
+{
+	__clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+#else
+static inline void set_page_guard_flag(struct page *page) { }
+static inline void clear_page_guard_flag(struct page *page) { }
+#endif
+
 static inline void set_page_order(struct page *page, int order)
 {
 	set_page_private(page, order);
@@ -438,6 +485,11 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
 	if (page_zone_id(page) != page_zone_id(buddy))
 		return 0;
 
+	if (page_is_guard(buddy) && page_order(buddy) == order) {
+		VM_BUG_ON(page_count(buddy) != 0);
+		return 1;
+	}
+
 	if (PageBuddy(buddy) && page_order(buddy) == order) {
 		VM_BUG_ON(page_count(buddy) != 0);
 		return 1;
@@ -494,11 +546,19 @@ static inline void __free_one_page(struct page *page,
 		buddy = page + (buddy_idx - page_idx);
 		if (!page_is_buddy(page, buddy, order))
 			break;
-
-		/* Our buddy is free, merge with it and move up one order. */
-		list_del(&buddy->lru);
-		zone->free_area[order].nr_free--;
-		rmv_page_order(buddy);
+		/*
+		 * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
+		 * merge with it and move up one order.
+		 */
+		if (page_is_guard(buddy)) {
+			clear_page_guard_flag(buddy);
+			set_page_private(page, 0);
+			__mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+		} else {
+			list_del(&buddy->lru);
+			zone->free_area[order].nr_free--;
+			rmv_page_order(buddy);
+		}
 		combined_idx = buddy_idx & page_idx;
 		page = page + (combined_idx - page_idx);
 		page_idx = combined_idx;
@@ -632,7 +692,7 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 	int i;
 	int bad = 0;
 
-	trace_mm_page_free_direct(page, order);
+	trace_mm_page_free(page, order);
 	kmemcheck_free_shadow(page, order);
 
 	if (PageAnon(page))
@@ -670,32 +730,23 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	local_irq_restore(flags);
 }
 
-/*
- * permit the bootmem allocator to evade page validation on high-order frees
- */
 void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
 {
-	if (order == 0) {
-		__ClearPageReserved(page);
-		set_page_count(page, 0);
-		set_page_refcounted(page);
-		__free_page(page);
-	} else {
-		int loop;
-
-		prefetchw(page);
-		for (loop = 0; loop < (1 << order); loop++) {
-			struct page *p = &page[loop];
+	unsigned int nr_pages = 1 << order;
+	unsigned int loop;
 
-			if (loop + 1 < (1 << order))
-				prefetchw(p + 1);
-			__ClearPageReserved(p);
-			set_page_count(p, 0);
-		}
+	prefetchw(page);
+	for (loop = 0; loop < nr_pages; loop++) {
+		struct page *p = &page[loop];
 
-		set_page_refcounted(page);
-		__free_pages(page, order);
+		if (loop + 1 < nr_pages)
+			prefetchw(p + 1);
+		__ClearPageReserved(p);
+		set_page_count(p, 0);
 	}
+
+	set_page_refcounted(page);
+	__free_pages(page, order);
 }
 
 
@@ -724,6 +775,23 @@ static inline void expand(struct zone *zone, struct page *page,
 		high--;
 		size >>= 1;
 		VM_BUG_ON(bad_range(zone, &page[size]));
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+		if (high < debug_guardpage_minorder()) {
+			/*
+			 * Mark as guard pages (or page), that will allow to
+			 * merge back to allocator when buddy will be freed.
+			 * Corresponding page table entries will not be touched,
+			 * pages will stay not present in virtual address space
+			 */
+			INIT_LIST_HEAD(&page[size].lru);
+			set_page_guard_flag(&page[size]);
+			set_page_private(&page[size], high);
+			/* Guard pages are not available for any usage */
+			__mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << high));
+			continue;
+		}
+#endif
 		list_add(&page[size].lru, &area->free_list[migratetype]);
 		area->nr_free++;
 		set_page_order(&page[size], high);
@@ -1189,6 +1257,19 @@ out:
 }
 
 /*
+ * Free a list of 0-order pages
+ */
+void free_hot_cold_page_list(struct list_head *list, int cold)
+{
+	struct page *page, *next;
+
+	list_for_each_entry_safe(page, next, list, lru) {
+		trace_mm_page_free_batched(page, cold);
+		free_hot_cold_page(page, cold);
+	}
+}
+
+/*
  * split_page takes a non-compound higher-order page, and splits it into
  * n (1<<order) sub-pages: page[0..n]
  * Each sub-page must be freed individually.
@@ -1435,7 +1516,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	long min = mark;
 	int o;
 
-	free_pages -= (1 << order) + 1;
+	free_pages -= (1 << order) - 1;
 	if (alloc_flags & ALLOC_HIGH)
 		min -= min / 2;
 	if (alloc_flags & ALLOC_HARDER)
@@ -1645,6 +1726,35 @@ zonelist_scan:
 		if ((alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				continue;
+		/*
+		 * When allocating a page cache page for writing, we
+		 * want to get it from a zone that is within its dirty
+		 * limit, such that no single zone holds more than its
+		 * proportional share of globally allowed dirty pages.
+		 * The dirty limits take into account the zone's
+		 * lowmem reserves and high watermark so that kswapd
+		 * should be able to balance it without having to
+		 * write pages from its LRU list.
+		 *
+		 * This may look like it could increase pressure on
+		 * lower zones by failing allocations in higher zones
+		 * before they are full.  But the pages that do spill
+		 * over are limited as the lower zones are protected
+		 * by this very same mechanism.  It should not become
+		 * a practical burden to them.
+		 *
+		 * XXX: For now, allow allocations to potentially
+		 * exceed the per-zone dirty limit in the slowpath
+		 * (ALLOC_WMARK_LOW unset) before going into reclaim,
+		 * which is important when on a NUMA setup the allowed
+		 * zones are together not big enough to reach the
+		 * global limit.  The proper fix for these situations
+		 * will require awareness of zones in the
+		 * dirty-throttling and the flusher threads.
+		 */
+		if ((alloc_flags & ALLOC_WMARK_LOW) &&
+		    (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
+			goto this_zone_full;
 
 		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
 		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
@@ -1734,7 +1844,8 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 {
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
 
-	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) ||
+	    debug_guardpage_minorder() > 0)
 		return;
 
 	/*
@@ -1773,12 +1884,25 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 
 static inline int
 should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+				unsigned long did_some_progress,
 				unsigned long pages_reclaimed)
 {
 	/* Do not loop if specifically requested */
 	if (gfp_mask & __GFP_NORETRY)
 		return 0;
 
+	/* Always retry if specifically requested */
+	if (gfp_mask & __GFP_NOFAIL)
+		return 1;
+
+	/*
+	 * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim
+	 * making forward progress without invoking OOM. Suspend also disables
+	 * storage devices so kswapd will not help. Bail if we are suspending.
+	 */
+	if (!did_some_progress && pm_suspended_storage())
+		return 0;
+
 	/*
 	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
 	 * means __GFP_NOFAIL, but that may not be true in other
@@ -1797,13 +1921,6 @@ should_alloc_retry(gfp_t gfp_mask, unsigned int order,
 	if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
 		return 1;
 
-	/*
-	 * Don't let big-order allocations loop unless the caller
-	 * explicitly requests that.
-	 */
-	if (gfp_mask & __GFP_NOFAIL)
-		return 1;
-
 	return 0;
 }
 
@@ -2196,7 +2313,8 @@ rebalance:
 
 	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
-	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+	if (should_alloc_retry(gfp_mask, order, did_some_progress,
+						pages_reclaimed)) {
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
@@ -2306,16 +2424,6 @@ unsigned long get_zeroed_page(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(get_zeroed_page);
 
-void __pagevec_free(struct pagevec *pvec)
-{
-	int i = pagevec_count(pvec);
-
-	while (--i >= 0) {
-		trace_mm_pagevec_free(pvec->pages[i], pvec->cold);
-		free_hot_cold_page(pvec->pages[i], pvec->cold);
-	}
-}
-
 void __free_pages(struct page *page, unsigned int order)
 {
 	if (put_page_testzero(page)) {
@@ -3385,25 +3493,33 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 		if (page_to_nid(page) != zone_to_nid(zone))
 			continue;
 
-		/* Blocks with reserved pages will never free, skip them. */
-		block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
-		if (pageblock_is_reserved(pfn, block_end_pfn))
-			continue;
-
 		block_migratetype = get_pageblock_migratetype(page);
 
-		/* If this block is reserved, account for it */
-		if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
-			reserve--;
-			continue;
-		}
+		/* Only test what is necessary when the reserves are not met */
+		if (reserve > 0) {
+			/*
+			 * Blocks with reserved pages will never free, skip
+			 * them.
+			 */
+			block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+			if (pageblock_is_reserved(pfn, block_end_pfn))
+				continue;
 
-		/* Suitable for reserving if this block is movable */
-		if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
-			set_pageblock_migratetype(page, MIGRATE_RESERVE);
-			move_freepages_block(zone, page, MIGRATE_RESERVE);
-			reserve--;
-			continue;
+			/* If this block is reserved, account for it */
+			if (block_migratetype == MIGRATE_RESERVE) {
+				reserve--;
+				continue;
+			}
+
+			/* Suitable for reserving if this block is movable */
+			if (block_migratetype == MIGRATE_MOVABLE) {
+				set_pageblock_migratetype(page,
+							MIGRATE_RESERVE);
+				move_freepages_block(zone, page,
+							MIGRATE_RESERVE);
+				reserve--;
+				continue;
+			}
 		}
 
 		/*
@@ -4734,8 +4850,19 @@ static void calculate_totalreserve_pages(void)
 			if (max > zone->present_pages)
 				max = zone->present_pages;
 			reserve_pages += max;
+			/*
+			 * Lowmem reserves are not available to
+			 * GFP_HIGHUSER page cache allocations and
+			 * kswapd tries to balance zones to their high
+			 * watermark.  As a result, neither should be
+			 * regarded as dirtyable memory, to prevent a
+			 * situation where reclaim has to clean pages
+			 * in order to balance the zones.
+			 */
+			zone->dirty_balance_reserve = max;
 		}
 	}
+	dirty_balance_reserve = reserve_pages;
 	totalreserve_pages = reserve_pages;
 }