1 files changed, 161 insertions, 85 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3c4eb750a199..114c56c3685d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -74,6 +74,7 @@
 #include <asm/div64.h>
 #include "internal.h"
 #include "shuffle.h"
+#include "page_reporting.h"
 
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
@@ -95,7 +96,6 @@ DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key);
  */
 DEFINE_PER_CPU(int, _numa_mem_);		/* Kernel "local memory" node */
 EXPORT_PER_CPU_SYMBOL(_numa_mem_);
-int _node_numa_mem_[MAX_NUMNODES];
 #endif
 
 /* work_structs for global per-cpu drains */
@@ -689,6 +689,8 @@ void prep_compound_page(struct page *page, unsigned int order)
 		set_compound_head(p, page);
 	}
 	atomic_set(compound_mapcount_ptr(page), -1);
+	if (hpage_pincount_available(page))
+		atomic_set(compound_pincount_ptr(page), 0);
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -791,32 +793,25 @@ static inline void set_page_order(struct page *page, unsigned int order)
  *
  * For recording page's order, we use page_private(page).
  */
-static inline int page_is_buddy(struct page *page, struct page *buddy,
+static inline bool page_is_buddy(struct page *page, struct page *buddy,
 							unsigned int order)
 {
-	if (page_is_guard(buddy) && page_order(buddy) == order) {
-		if (page_zone_id(page) != page_zone_id(buddy))
-			return 0;
-
-		VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
+	if (!page_is_guard(buddy) && !PageBuddy(buddy))
+		return false;
 
-		return 1;
-	}
+	if (page_order(buddy) != order)
+		return false;
 
-	if (PageBuddy(buddy) && page_order(buddy) == order) {
-		/*
-		 * zone check is done late to avoid uselessly
-		 * calculating zone/node ids for pages that could
-		 * never merge.
-		 */
-		if (page_zone_id(page) != page_zone_id(buddy))
-			return 0;
+	/*
+	 * zone check is done late to avoid uselessly calculating
+	 * zone/node ids for pages that could never merge.
+	 */
+	if (page_zone_id(page) != page_zone_id(buddy))
+		return false;
 
-		VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
+	VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
 
-		return 1;
-	}
-	return 0;
+	return true;
 }
 
 #ifdef CONFIG_COMPACTION
@@ -870,6 +865,78 @@ compaction_capture(struct capture_control *capc, struct page *page,
 }
 #endif /* CONFIG_COMPACTION */
 
+/* Used for pages not on another list */
+static inline void add_to_free_list(struct page *page, struct zone *zone,
+				    unsigned int order, int migratetype)
+{
+	struct free_area *area = &zone->free_area[order];
+
+	list_add(&page->lru, &area->free_list[migratetype]);
+	area->nr_free++;
+}
+
+/* Used for pages not on another list */
+static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
+					 unsigned int order, int migratetype)
+{
+	struct free_area *area = &zone->free_area[order];
+
+	list_add_tail(&page->lru, &area->free_list[migratetype]);
+	area->nr_free++;
+}
+
+/* Used for pages which are on another list */
+static inline void move_to_free_list(struct page *page, struct zone *zone,
+				     unsigned int order, int migratetype)
+{
+	struct free_area *area = &zone->free_area[order];
+
+	list_move(&page->lru, &area->free_list[migratetype]);
+}
+
+static inline void del_page_from_free_list(struct page *page, struct zone *zone,
+					   unsigned int order)
+{
+	/* clear reported state and update reported page count */
+	if (page_reported(page))
+		__ClearPageReported(page);
+
+	list_del(&page->lru);
+	__ClearPageBuddy(page);
+	set_page_private(page, 0);
+	zone->free_area[order].nr_free--;
+}
+
+/*
+ * If this is not the largest possible page, check if the buddy
+ * of the next-highest order is free. If it is, it's possible
+ * that pages are being freed that will coalesce soon. In case,
+ * that is happening, add the free page to the tail of the list
+ * so it's less likely to be used soon and more likely to be merged
+ * as a higher order page
+ */
+static inline bool
+buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
+		   struct page *page, unsigned int order)
+{
+	struct page *higher_page, *higher_buddy;
+	unsigned long combined_pfn;
+
+	if (order >= MAX_ORDER - 2)
+		return false;
+
+	if (!pfn_valid_within(buddy_pfn))
+		return false;
+
+	combined_pfn = buddy_pfn & pfn;
+	higher_page = page + (combined_pfn - pfn);
+	buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
+	higher_buddy = higher_page + (buddy_pfn - combined_pfn);
+
+	return pfn_valid_within(buddy_pfn) &&
+	       page_is_buddy(higher_page, higher_buddy, order + 1);
+}
+
 /*
  * Freeing function for a buddy system allocator.
  *
@@ -897,13 +964,14 @@ compaction_capture(struct capture_control *capc, struct page *page,
 static inline void __free_one_page(struct page *page,
 		unsigned long pfn,
 		struct zone *zone, unsigned int order,
-		int migratetype)
+		int migratetype, bool report)
 {
-	unsigned long combined_pfn;
+	struct capture_control *capc = task_capc(zone);
 	unsigned long uninitialized_var(buddy_pfn);
-	struct page *buddy;
+	unsigned long combined_pfn;
 	unsigned int max_order;
-	struct capture_control *capc = task_capc(zone);
+	struct page *buddy;
+	bool to_tail;
 
 	max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
 
@@ -938,7 +1006,7 @@ continue_merging:
 		if (page_is_guard(buddy))
 			clear_page_guard(zone, buddy, order, migratetype);
 		else
-			del_page_from_free_area(buddy, &zone->free_area[order]);
+			del_page_from_free_list(buddy, zone, order);
 		combined_pfn = buddy_pfn & pfn;
 		page = page + (combined_pfn - pfn);
 		pfn = combined_pfn;
@@ -972,35 +1040,19 @@ continue_merging:
 done_merging:
 	set_page_order(page, order);
 
-	/*
-	 * If this is not the largest possible page, check if the buddy
-	 * of the next-highest order is free. If it is, it's possible
-	 * that pages are being freed that will coalesce soon. In case,
-	 * that is happening, add the free page to the tail of the list
-	 * so it's less likely to be used soon and more likely to be merged
-	 * as a higher order page
-	 */
-	if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)
-			&& !is_shuffle_order(order)) {
-		struct page *higher_page, *higher_buddy;
-		combined_pfn = buddy_pfn & pfn;
-		higher_page = page + (combined_pfn - pfn);
-		buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
-		higher_buddy = higher_page + (buddy_pfn - combined_pfn);
-		if (pfn_valid_within(buddy_pfn) &&
-		    page_is_buddy(higher_page, higher_buddy, order + 1)) {
-			add_to_free_area_tail(page, &zone->free_area[order],
-					      migratetype);
-			return;
-		}
-	}
-
 	if (is_shuffle_order(order))
-		add_to_free_area_random(page, &zone->free_area[order],
-				migratetype);
+		to_tail = shuffle_pick_tail();
 	else
-		add_to_free_area(page, &zone->free_area[order], migratetype);
+		to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
 
+	if (to_tail)
+		add_to_free_list_tail(page, zone, order, migratetype);
+	else
+		add_to_free_list(page, zone, order, migratetype);
+
+	/* Notify page reporting subsystem of freed page */
+	if (report)
+		page_reporting_notify_free(order);
 }
 
 /*
@@ -1152,7 +1204,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	if (PageMappingFlags(page))
 		page->mapping = NULL;
 	if (memcg_kmem_enabled() && PageKmemcg(page))
-		__memcg_kmem_uncharge(page, order);
+		__memcg_kmem_uncharge_page(page, order);
 	if (check_free)
 		bad += free_pages_check(page);
 	if (bad)
@@ -1317,7 +1369,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 		if (unlikely(isolated_pageblocks))
 			mt = get_pageblock_migratetype(page);
 
-		__free_one_page(page, page_to_pfn(page), zone, 0, mt);
+		__free_one_page(page, page_to_pfn(page), zone, 0, mt, true);
 		trace_mm_page_pcpu_drain(page, 0, mt);
 	}
 	spin_unlock(&zone->lock);
@@ -1333,7 +1385,7 @@ static void free_one_page(struct zone *zone,
 		is_migrate_isolate(migratetype))) {
 		migratetype = get_pfnblock_migratetype(page, pfn);
 	}
-	__free_one_page(page, pfn, zone, order, migratetype);
+	__free_one_page(page, pfn, zone, order, migratetype, true);
 	spin_unlock(&zone->lock);
 }
 
@@ -2014,13 +2066,11 @@ void __init init_cma_reserved_pageblock(struct page *page)
  * -- nyc
  */
 static inline void expand(struct zone *zone, struct page *page,
-	int low, int high, struct free_area *area,
-	int migratetype)
+	int low, int high, int migratetype)
 {
 	unsigned long size = 1 << high;
 
 	while (high > low) {
-		area--;
 		high--;
 		size >>= 1;
 		VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
@@ -2034,7 +2084,7 @@ static inline void expand(struct zone *zone, struct page *page,
 		if (set_page_guard(zone, &page[size], high, migratetype))
 			continue;
 
-		add_to_free_area(&page[size], area, migratetype);
+		add_to_free_list(&page[size], zone, high, migratetype);
 		set_page_order(&page[size], high);
 	}
 }
@@ -2192,8 +2242,8 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		page = get_page_from_free_area(area, migratetype);
 		if (!page)
 			continue;
-		del_page_from_free_area(page, area);
-		expand(zone, page, order, current_order, area, migratetype);
+		del_page_from_free_list(page, zone, current_order);
+		expand(zone, page, order, current_order, migratetype);
 		set_pcppage_migratetype(page, migratetype);
 		return page;
 	}
@@ -2267,7 +2317,7 @@ static int move_freepages(struct zone *zone,
 		VM_BUG_ON_PAGE(page_zone(page) != zone, page);
 
 		order = page_order(page);
-		move_to_free_area(page, &zone->free_area[order], migratetype);
+		move_to_free_list(page, zone, order, migratetype);
 		page += 1 << order;
 		pages_moved += 1 << order;
 	}
@@ -2383,7 +2433,6 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page,
 		unsigned int alloc_flags, int start_type, bool whole_block)
 {
 	unsigned int current_order = page_order(page);
-	struct free_area *area;
 	int free_pages, movable_pages, alike_pages;
 	int old_block_type;
 
@@ -2454,8 +2503,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page,
 	return;
 
 single_page:
-	area = &zone->free_area[current_order];
-	move_to_free_area(page, area, start_type);
+	move_to_free_list(page, zone, current_order, start_type);
 }
 
 /*
@@ -3126,7 +3174,6 @@ EXPORT_SYMBOL_GPL(split_page);
 
 int __isolate_free_page(struct page *page, unsigned int order)
 {
-	struct free_area *area = &page_zone(page)->free_area[order];
 	unsigned long watermark;
 	struct zone *zone;
 	int mt;
@@ -3152,7 +3199,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 
 	/* Remove page from free list */
 
-	del_page_from_free_area(page, area);
+	del_page_from_free_list(page, zone, order);
 
 	/*
 	 * Set the pageblock if the isolated page is at least half of a
@@ -3173,6 +3220,25 @@ int __isolate_free_page(struct page *page, unsigned int order)
 	return 1UL << order;
 }
 
+/**
+ * __putback_isolated_page - Return a now-isolated page back where we got it
+ * @page: Page that was isolated
+ * @order: Order of the isolated page
+ *
+ * This function is meant to return a page pulled from the free lists via
+ * __isolate_free_page back to the free lists they were pulled from.
+ */
+void __putback_isolated_page(struct page *page, unsigned int order, int mt)
+{
+	struct zone *zone = page_zone(page);
+
+	/* zone lock should be held when this function is called */
+	lockdep_assert_held(&zone->lock);
+
+	/* Return isolated page to tail of freelist. */
+	__free_one_page(page, page_to_pfn(page), zone, order, mt, false);
+}
+
 /*
  * Update NUMA hit/miss statistics
  *
@@ -3459,8 +3525,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 			return true;
 		}
 #endif
-		if (alloc_harder &&
-			!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+		if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC))
 			return true;
 	}
 	return false;
@@ -3535,10 +3600,13 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 static inline unsigned int
 alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 {
-	unsigned int alloc_flags = 0;
+	unsigned int alloc_flags;
 
-	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
-		alloc_flags |= ALLOC_KSWAPD;
+	/*
+	 * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
+	 * to save a branch.
+	 */
+	alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM);
 
 #ifdef CONFIG_ZONE_DMA32
 	if (!zone)
@@ -4174,8 +4242,13 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 {
 	unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
 
-	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
+	/*
+	 * __GFP_HIGH is assumed to be the same as ALLOC_HIGH
+	 * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
+	 * to save two branches.
+	 */
 	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
+	BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD);
 
 	/*
 	 * The caller may dip into page reserves a bit more if the caller
@@ -4183,7 +4256,8 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
 	 * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
 	 */
-	alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
+	alloc_flags |= (__force int)
+		(gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
 
 	if (gfp_mask & __GFP_ATOMIC) {
 		/*
@@ -4200,9 +4274,6 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
-	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
-		alloc_flags |= ALLOC_KSWAPD;
-
 #ifdef CONFIG_CMA
 	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
@@ -4745,14 +4816,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
 	 * Restore the original nodemask if it was potentially replaced with
 	 * &cpuset_current_mems_allowed to optimize the fast-path attempt.
 	 */
-	if (unlikely(ac.nodemask != nodemask))
-		ac.nodemask = nodemask;
+	ac.nodemask = nodemask;
 
 	page = __alloc_pages_slowpath(alloc_mask, order, &ac);
 
 out:
 	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
-	    unlikely(__memcg_kmem_charge(page, gfp_mask, order) != 0)) {
+	    unlikely(__memcg_kmem_charge_page(page, gfp_mask, order) != 0)) {
 		__free_pages(page, order);
 		page = NULL;
 	}
@@ -7867,8 +7937,8 @@ int __meminit init_per_zone_wmark_min(void)
 		min_free_kbytes = new_min_free_kbytes;
 		if (min_free_kbytes < 128)
 			min_free_kbytes = 128;
-		if (min_free_kbytes > 65536)
-			min_free_kbytes = 65536;
+		if (min_free_kbytes > 262144)
+			min_free_kbytes = 262144;
 	} else {
 		pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
 				new_min_free_kbytes, user_min_free_kbytes);
@@ -8253,15 +8323,20 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 
 		/*
 		 * Hugepages are not in LRU lists, but they're movable.
+		 * THPs are on the LRU, but need to be counted as #small pages.
 		 * We need not scan over tail pages because we don't
 		 * handle each tail page individually in migration.
 		 */
-		if (PageHuge(page)) {
+		if (PageHuge(page) || PageTransCompound(page)) {
 			struct page *head = compound_head(page);
 			unsigned int skip_pages;
 
-			if (!hugepage_migration_supported(page_hstate(head)))
+			if (PageHuge(page)) {
+				if (!hugepage_migration_supported(page_hstate(head)))
+					return page;
+			} else if (!PageLRU(head) && !__PageMovable(head)) {
 				return page;
+			}
 
 			skip_pages = compound_nr(head) - (page - head);
 			iter += skip_pages - 1;
@@ -8402,6 +8477,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		.ignore_skip_hint = true,
 		.no_set_skip_hint = true,
 		.gfp_mask = current_gfp_context(gfp_mask),
+		.alloc_contig = true,
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
 
@@ -8709,7 +8785,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		BUG_ON(!PageBuddy(page));
 		order = page_order(page);
 		offlined_pages += 1 << order;
-		del_page_from_free_area(page, &zone->free_area[order]);
+		del_page_from_free_list(page, zone, order);
 		pfn += (1 << order);
 	}
 	spin_unlock_irqrestore(&zone->lock, flags);