1 files changed, 94 insertions, 115 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f8f3bfc435ee..452513bf02ce 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -63,6 +63,7 @@
 #include <linux/sched/rt.h>
 #include <linux/page_owner.h>
 #include <linux/kthread.h>
+#include <linux/memcontrol.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -286,7 +287,9 @@ static inline void reset_deferred_meminit(pg_data_t *pgdat)
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 {
-	if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn)
+	int nid = early_pfn_to_nid(pfn);
+
+	if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
 		return true;
 
 	return false;
@@ -656,6 +659,9 @@ static inline void set_page_guard(struct zone *zone, struct page *page,
 		return;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
 	INIT_LIST_HEAD(&page->lru);
@@ -673,6 +679,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
 		return;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
 	set_page_private(page, 0);
@@ -998,6 +1007,8 @@ static __always_inline bool free_pages_prepare(struct page *page,
 
 		VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
 
+		if (compound)
+			ClearPageDoubleMap(page);
 		for (i = 1; i < (1 << order); i++) {
 			if (compound)
 				bad += free_tail_pages_check(page, page + i);
@@ -1008,8 +1019,12 @@ static __always_inline bool free_pages_prepare(struct page *page,
 			(page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 		}
 	}
-	if (PageAnonHead(page))
+	if (PageMappingFlags(page))
 		page->mapping = NULL;
+	if (memcg_kmem_enabled() && PageKmemcg(page)) {
+		memcg_kmem_uncharge(page, order);
+		__ClearPageKmemcg(page);
+	}
 	if (check_free)
 		bad += free_pages_check(page);
 	if (bad)
@@ -1267,7 +1282,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
 	spin_lock(&early_pfn_lock);
 	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
 	if (nid < 0)
-		nid = 0;
+		nid = first_online_node;
 	spin_unlock(&early_pfn_lock);
 
 	return nid;
@@ -1716,6 +1731,19 @@ static bool check_new_pages(struct page *page, unsigned int order)
 	return false;
 }
 
+inline void post_alloc_hook(struct page *page, unsigned int order,
+				gfp_t gfp_flags)
+{
+	set_page_private(page, 0);
+	set_page_refcounted(page);
+
+	arch_alloc_page(page, order);
+	kernel_map_pages(page, 1 << order, 1);
+	kernel_poison_pages(page, 1 << order, 1);
+	kasan_alloc_pages(page, order);
+	set_page_owner(page, order, gfp_flags);
+}
+
 static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
 							unsigned int alloc_flags)
 {
@@ -1728,13 +1756,7 @@ static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags
 			poisoned &= page_is_poisoned(p);
 	}
 
-	set_page_private(page, 0);
-	set_page_refcounted(page);
-
-	arch_alloc_page(page, order);
-	kernel_map_pages(page, 1 << order, 1);
-	kernel_poison_pages(page, 1 << order, 1);
-	kasan_alloc_pages(page, order);
+	post_alloc_hook(page, order, gfp_flags);
 
 	if (!free_pages_prezeroed(poisoned) && (gfp_flags & __GFP_ZERO))
 		for (i = 0; i < (1 << order); i++)
@@ -1743,8 +1765,6 @@ static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags
 	if (order && (gfp_flags & __GFP_COMP))
 		prep_compound_page(page, order);
 
-	set_page_owner(page, order, gfp_flags);
-
 	/*
 	 * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
 	 * allocate the page. The expectation is that the caller is taking
@@ -2453,7 +2473,6 @@ void free_hot_cold_page_list(struct list_head *list, bool cold)
 void split_page(struct page *page, unsigned int order)
 {
 	int i;
-	gfp_t gfp_mask;
 
 	VM_BUG_ON_PAGE(PageCompound(page), page);
 	VM_BUG_ON_PAGE(!page_count(page), page);
@@ -2467,12 +2486,9 @@ void split_page(struct page *page, unsigned int order)
 		split_page(virt_to_page(page[0].shadow), order);
 #endif
 
-	gfp_mask = get_page_owner_gfp(page);
-	set_page_owner(page, 0, gfp_mask);
-	for (i = 1; i < (1 << order); i++) {
+	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
-		set_page_owner(page + i, 0, gfp_mask);
-	}
+	split_page_owner(page, order);
 }
 EXPORT_SYMBOL_GPL(split_page);
 
@@ -2501,8 +2517,6 @@ int __isolate_free_page(struct page *page, unsigned int order)
 	zone->free_area[order].nr_free--;
 	rmv_page_order(page);
 
-	set_page_owner(page, order, __GFP_MOVABLE);
-
 	/* Set the pageblock if the isolated page is at least a pageblock */
 	if (order >= pageblock_order - 1) {
 		struct page *endpage = page + (1 << order) - 1;
@@ -2519,33 +2533,6 @@ int __isolate_free_page(struct page *page, unsigned int order)
 }
 
 /*
- * Similar to split_page except the page is already free. As this is only
- * being used for migration, the migratetype of the block also changes.
- * As this is called with interrupts disabled, the caller is responsible
- * for calling arch_alloc_page() and kernel_map_page() after interrupts
- * are enabled.
- *
- * Note: this is probably too low level an operation for use in drivers.
- * Please consult with lkml before using this in your driver.
- */
-int split_free_page(struct page *page)
-{
-	unsigned int order;
-	int nr_pages;
-
-	order = page_order(page);
-
-	nr_pages = __isolate_free_page(page, order);
-	if (!nr_pages)
-		return 0;
-
-	/* Split into individual pages */
-	set_page_refcounted(page);
-	split_page(page, order);
-	return nr_pages;
-}
-
-/*
  * Update NUMA hit/miss statistics
  *
  * Must be called with interrupts disabled.
@@ -2609,11 +2596,12 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 				page = list_last_entry(list, struct page, lru);
 			else
 				page = list_first_entry(list, struct page, lru);
-		} while (page && check_new_pcp(page));
 
-		__dec_zone_state(zone, NR_ALLOC_BATCH);
-		list_del(&page->lru);
-		pcp->count--;
+			__dec_zone_state(zone, NR_ALLOC_BATCH);
+			list_del(&page->lru);
+			pcp->count--;
+
+		} while (check_new_pcp(page));
 	} else {
 		/*
 		 * We most definitely don't want callers attempting to
@@ -3023,6 +3011,7 @@ reset_fair:
 		apply_fair = false;
 		fair_skipped = false;
 		reset_alloc_batches(ac->preferred_zoneref->zone);
+		z = ac->preferred_zoneref;
 		goto zonelist_scan;
 	}
 
@@ -3095,6 +3084,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	struct oom_control oc = {
 		.zonelist = ac->zonelist,
 		.nodemask = ac->nodemask,
+		.memcg = NULL,
 		.gfp_mask = gfp_mask,
 		.order = order,
 	};
@@ -3596,6 +3586,17 @@ retry:
 	 */
 	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+	/*
+	 * Reset the zonelist iterators if memory policies can be ignored.
+	 * These allocations are high priority and system rather than user
+	 * orientated.
+	 */
+	if ((alloc_flags & ALLOC_NO_WATERMARKS) || !(alloc_flags & ALLOC_CPUSET)) {
+		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
+		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+					ac->high_zoneidx, ac->nodemask);
+	}
+
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, order,
 				alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
@@ -3604,12 +3605,6 @@ retry:
 
 	/* Allocate without watermarks if the context allows */
 	if (alloc_flags & ALLOC_NO_WATERMARKS) {
-		/*
-		 * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
-		 * the allocation is high priority and these type of
-		 * allocations are system rather than user orientated
-		 */
-		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
 		page = get_page_from_freelist(gfp_mask, order,
 						ALLOC_NO_WATERMARKS, ac);
 		if (page)
@@ -3808,7 +3803,11 @@ retry_cpuset:
 	/* Dirty zone balancing only done in the fast path */
 	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
-	/* The preferred zone is used for statistics later */
+	/*
+	 * The preferred zone is used for statistics but crucially it is
+	 * also used as the starting point for the zonelist iterator. It
+	 * may get reset for allocations that ignore memory policies.
+	 */
 	ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
 					ac.high_zoneidx, ac.nodemask);
 	if (!ac.preferred_zoneref) {
@@ -3849,6 +3848,14 @@ no_zone:
 	}
 
 out:
+	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page) {
+		if (unlikely(memcg_kmem_charge(page, gfp_mask, order))) {
+			__free_pages(page, order);
+			page = NULL;
+		} else
+			__SetPageKmemcg(page);
+	}
+
 	if (kmemcheck_enabled && page)
 		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
 
@@ -4004,56 +4011,6 @@ void __free_page_frag(void *addr)
 }
 EXPORT_SYMBOL(__free_page_frag);
 
-/*
- * alloc_kmem_pages charges newly allocated pages to the kmem resource counter
- * of the current memory cgroup if __GFP_ACCOUNT is set, other than that it is
- * equivalent to alloc_pages.
- *
- * It should be used when the caller would like to use kmalloc, but since the
- * allocation is large, it has to fall back to the page allocator.
- */
-struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order)
-{
-	struct page *page;
-
-	page = alloc_pages(gfp_mask, order);
-	if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) {
-		__free_pages(page, order);
-		page = NULL;
-	}
-	return page;
-}
-
-struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
-{
-	struct page *page;
-
-	page = alloc_pages_node(nid, gfp_mask, order);
-	if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) {
-		__free_pages(page, order);
-		page = NULL;
-	}
-	return page;
-}
-
-/*
- * __free_kmem_pages and free_kmem_pages will free pages allocated with
- * alloc_kmem_pages.
- */
-void __free_kmem_pages(struct page *page, unsigned int order)
-{
-	memcg_kmem_uncharge(page, order);
-	__free_pages(page, order);
-}
-
-void free_kmem_pages(unsigned long addr, unsigned int order)
-{
-	if (addr != 0) {
-		VM_BUG_ON(!virt_addr_valid((void *)addr));
-		__free_kmem_pages(virt_to_page((void *)addr), order);
-	}
-}
-
 static void *make_alloc_exact(unsigned long addr, unsigned int order,
 		size_t size)
 {
@@ -4355,6 +4312,9 @@ void show_free_areas(unsigned int filter)
 		" unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n"
 		" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
 		" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		" anon_thp: %lu shmem_thp: %lu shmem_pmdmapped: %lu\n"
+#endif
 		" free:%lu free_pcp:%lu free_cma:%lu\n",
 		global_page_state(NR_ACTIVE_ANON),
 		global_page_state(NR_INACTIVE_ANON),
@@ -4372,6 +4332,11 @@ void show_free_areas(unsigned int filter)
 		global_page_state(NR_SHMEM),
 		global_page_state(NR_PAGETABLE),
 		global_page_state(NR_BOUNCE),
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR,
+		global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR,
+		global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR,
+#endif
 		global_page_state(NR_FREE_PAGES),
 		free_pcp,
 		global_page_state(NR_FREE_CMA_PAGES));
@@ -4406,6 +4371,11 @@ void show_free_areas(unsigned int filter)
 			" writeback:%lukB"
 			" mapped:%lukB"
 			" shmem:%lukB"
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			" shmem_thp: %lukB"
+			" shmem_pmdmapped: %lukB"
+			" anon_thp: %lukB"
+#endif
 			" slab_reclaimable:%lukB"
 			" slab_unreclaimable:%lukB"
 			" kernel_stack:%lukB"
@@ -4438,6 +4408,12 @@ void show_free_areas(unsigned int filter)
 			K(zone_page_state(zone, NR_WRITEBACK)),
 			K(zone_page_state(zone, NR_FILE_MAPPED)),
 			K(zone_page_state(zone, NR_SHMEM)),
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			K(zone_page_state(zone, NR_SHMEM_THPS) * HPAGE_PMD_NR),
+			K(zone_page_state(zone, NR_SHMEM_PMDMAPPED)
+					* HPAGE_PMD_NR),
+			K(zone_page_state(zone, NR_ANON_THPS) * HPAGE_PMD_NR),
+#endif
 			K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
 			K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
 			zone_page_state(zone, NR_KERNEL_STACK) *
@@ -6448,15 +6424,18 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 				sizeof(arch_zone_lowest_possible_pfn));
 	memset(arch_zone_highest_possible_pfn, 0,
 				sizeof(arch_zone_highest_possible_pfn));
-	arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
-	arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
-	for (i = 1; i < MAX_NR_ZONES; i++) {
+
+	start_pfn = find_min_pfn_with_active_regions();
+
+	for (i = 0; i < MAX_NR_ZONES; i++) {
 		if (i == ZONE_MOVABLE)
 			continue;
-		arch_zone_lowest_possible_pfn[i] =
-			arch_zone_highest_possible_pfn[i-1];
-		arch_zone_highest_possible_pfn[i] =
-			max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
+
+		end_pfn = max(max_zone_pfn[i], start_pfn);
+		arch_zone_lowest_possible_pfn[i] = start_pfn;
+		arch_zone_highest_possible_pfn[i] = end_pfn;
+
+		start_pfn = end_pfn;
 	}
 	arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
 	arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;