1 files changed, 73 insertions, 110 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 905db9d7962f..a790ef4be74e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -705,16 +705,14 @@ static inline void rmv_page_order(struct page *page)
 
 /*
  * This function checks whether a page is free && is the buddy
- * we can do coalesce a page and its buddy if
+ * we can coalesce a page and its buddy if
  * (a) the buddy is not in a hole (check before calling!) &&
  * (b) the buddy is in the buddy system &&
  * (c) a page and its buddy have the same order &&
  * (d) a page and its buddy are in the same zone.
  *
- * For recording whether a page is in the buddy system, we set ->_mapcount
- * PAGE_BUDDY_MAPCOUNT_VALUE.
- * Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is
- * serialized by zone->lock.
+ * For recording whether a page is in the buddy system, we set PageBuddy.
+ * Setting, clearing, and testing PageBuddy is serialized by zone->lock.
  *
  * For recording page's order, we use page_private(page).
  */
@@ -759,9 +757,8 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with _mapcount
- * PAGE_BUDDY_MAPCOUNT_VALUE. Page's order is recorded in page_private(page)
- * field.
+ * free pages of length of (1 << order) and marked with PageBuddy.
+ * Page's order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were
  * free, the remainder of the region must be split into blocks.
@@ -946,7 +943,7 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
 	}
 	switch (page - head_page) {
 	case 1:
-		/* the first tail page: ->mapping is compound_mapcount() */
+		/* the first tail page: ->mapping may be compound_mapcount() */
 		if (unlikely(compound_mapcount(page))) {
 			bad_page(page, "nonzero compound_mapcount", 0);
 			goto out;
@@ -955,7 +952,7 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
 	case 2:
 		/*
 		 * the second tail page: ->mapping is
-		 * page_deferred_list().next -- ignore value.
+		 * deferred_list.next -- ignore value.
 		 */
 		break;
 	default:
@@ -1743,38 +1740,16 @@ void __init page_alloc_init_late(void)
 }
 
 #ifdef CONFIG_CMA
-static void __init adjust_present_page_count(struct page *page, long count)
-{
-	struct zone *zone = page_zone(page);
-
-	/* We don't need to hold a lock since it is boot-up process */
-	zone->present_pages += count;
-}
-
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
 void __init init_cma_reserved_pageblock(struct page *page)
 {
 	unsigned i = pageblock_nr_pages;
-	unsigned long pfn = page_to_pfn(page);
 	struct page *p = page;
-	int nid = page_to_nid(page);
-
-	/*
-	 * ZONE_MOVABLE will steal present pages from other zones by
-	 * changing page links so page_zone() is changed. Before that,
-	 * we need to adjust previous zone's page count first.
-	 */
-	adjust_present_page_count(page, -pageblock_nr_pages);
 
 	do {
 		__ClearPageReserved(p);
 		set_page_count(p, 0);
-
-		/* Steal pages from other zones */
-		set_page_links(p, ZONE_MOVABLE, nid, pfn);
-	} while (++p, ++pfn, --i);
-
-	adjust_present_page_count(page, pageblock_nr_pages);
+	} while (++p, --i);
 
 	set_pageblock_migratetype(page, MIGRATE_CMA);
 
@@ -2889,7 +2864,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 		 * exists.
 		 */
 		watermark = min_wmark_pages(zone) + (1UL << order);
-		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+		if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
 			return 0;
 
 		__mod_zone_freepage_state(zone, -(1UL << order), mt);
@@ -3086,7 +3061,7 @@ static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 
 static int __init fail_page_alloc_debugfs(void)
 {
-	umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+	umode_t mode = S_IFREG | 0600;
 	struct dentry *dir;
 
 	dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
@@ -3165,6 +3140,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 	}
 
 
+#ifdef CONFIG_CMA
+	/* If allocation can't use CMA areas don't use free CMA pages */
+	if (!(alloc_flags & ALLOC_CMA))
+		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
 	/*
 	 * Check watermarks for an order-0 allocation request. If these
 	 * are not met, then a high-order request also cannot go ahead
@@ -3191,8 +3172,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		}
 
 #ifdef CONFIG_CMA
-		if (!list_empty(&area->free_list[MIGRATE_CMA]))
+		if ((alloc_flags & ALLOC_CMA) &&
+		    !list_empty(&area->free_list[MIGRATE_CMA])) {
 			return true;
+		}
 #endif
 		if (alloc_harder &&
 			!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
@@ -3212,6 +3195,13 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 		unsigned long mark, int classzone_idx, unsigned int alloc_flags)
 {
 	long free_pages = zone_page_state(z, NR_FREE_PAGES);
+	long cma_pages = 0;
+
+#ifdef CONFIG_CMA
+	/* If allocation can't use CMA areas don't use free CMA pages */
+	if (!(alloc_flags & ALLOC_CMA))
+		cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
 
 	/*
 	 * Fast check for order-0 only. If this fails then the reserves
@@ -3220,7 +3210,7 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	 * the caller is !atomic then it'll uselessly search the free
 	 * list. That corner case is then slower but it is harmless.
 	 */
-	if (!order && free_pages > mark + z->lowmem_reserve[classzone_idx])
+	if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
 		return true;
 
 	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
@@ -3708,7 +3698,7 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
 #endif /* CONFIG_COMPACTION */
 
 #ifdef CONFIG_LOCKDEP
-struct lockdep_map __fs_reclaim_map =
+static struct lockdep_map __fs_reclaim_map =
 	STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
 
 static bool __need_fs_reclaim(gfp_t gfp_mask)
@@ -3733,17 +3723,27 @@ static bool __need_fs_reclaim(gfp_t gfp_mask)
 	return true;
 }
 
+void __fs_reclaim_acquire(void)
+{
+	lock_map_acquire(&__fs_reclaim_map);
+}
+
+void __fs_reclaim_release(void)
+{
+	lock_map_release(&__fs_reclaim_map);
+}
+
 void fs_reclaim_acquire(gfp_t gfp_mask)
 {
 	if (__need_fs_reclaim(gfp_mask))
-		lock_map_acquire(&__fs_reclaim_map);
+		__fs_reclaim_acquire();
 }
 EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
 
 void fs_reclaim_release(gfp_t gfp_mask)
 {
 	if (__need_fs_reclaim(gfp_mask))
-		lock_map_release(&__fs_reclaim_map);
+		__fs_reclaim_release();
 }
 EXPORT_SYMBOL_GPL(fs_reclaim_release);
 #endif
@@ -3761,8 +3761,8 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 
 	/* We now go into synchronous reclaim */
 	cpuset_memory_pressure_bump();
-	noreclaim_flag = memalloc_noreclaim_save();
 	fs_reclaim_acquire(gfp_mask);
+	noreclaim_flag = memalloc_noreclaim_save();
 	reclaim_state.reclaimed_slab = 0;
 	current->reclaim_state = &reclaim_state;
 
@@ -3770,8 +3770,8 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 								ac->nodemask);
 
 	current->reclaim_state = NULL;
-	fs_reclaim_release(gfp_mask);
 	memalloc_noreclaim_restore(noreclaim_flag);
+	fs_reclaim_release(gfp_mask);
 
 	cond_resched();
 
@@ -3856,6 +3856,10 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
+#ifdef CONFIG_CMA
+	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+		alloc_flags |= ALLOC_CMA;
+#endif
 	return alloc_flags;
 }
 
@@ -4165,7 +4169,6 @@ retry:
 	 * orientated.
 	 */
 	if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
-		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
 		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
 					ac->high_zoneidx, ac->nodemask);
 	}
@@ -4322,12 +4325,14 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 	if (should_fail_alloc_page(gfp_mask, order))
 		return false;
 
+	if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
+		*alloc_flags |= ALLOC_CMA;
+
 	return true;
 }
 
 /* Determine whether to spread dirty pages and what the first usable zone */
-static inline void finalise_ac(gfp_t gfp_mask,
-		unsigned int order, struct alloc_context *ac)
+static inline void finalise_ac(gfp_t gfp_mask, struct alloc_context *ac)
 {
 	/* Dirty zone balancing only done in the fast path */
 	ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE);
@@ -4358,7 +4363,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
 	if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags))
 		return NULL;
 
-	finalise_ac(gfp_mask, order, &ac);
+	finalise_ac(gfp_mask, &ac);
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
@@ -6204,7 +6209,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 {
 	enum zone_type j;
 	int nid = pgdat->node_id;
-	unsigned long node_end_pfn = 0;
 
 	pgdat_resize_init(pgdat);
 #ifdef CONFIG_NUMA_BALANCING
@@ -6230,22 +6234,18 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
-		unsigned long size, realsize, freesize, memmap_pages;
+		unsigned long size, freesize, memmap_pages;
 		unsigned long zone_start_pfn = zone->zone_start_pfn;
-		unsigned long movable_size = 0;
 
 		size = zone->spanned_pages;
-		realsize = freesize = zone->present_pages;
-		if (zone_end_pfn(zone) > node_end_pfn)
-			node_end_pfn = zone_end_pfn(zone);
-
+		freesize = zone->present_pages;
 
 		/*
 		 * Adjust freesize so that it accounts for how much memory
 		 * is used by this zone for memmap. This affects the watermark
 		 * and per-cpu initialisations
 		 */
-		memmap_pages = calc_memmap_size(size, realsize);
+		memmap_pages = calc_memmap_size(size, freesize);
 		if (!is_highmem_idx(j)) {
 			if (freesize >= memmap_pages) {
 				freesize -= memmap_pages;
@@ -6277,7 +6277,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		 * when the bootmem allocator frees pages into the buddy system.
 		 * And all highmem pages will be managed by the buddy system.
 		 */
-		zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
+		zone->managed_pages = freesize;
 #ifdef CONFIG_NUMA
 		zone->node = nid;
 #endif
@@ -6287,30 +6287,12 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		zone_seqlock_init(zone);
 		zone_pcp_init(zone);
 
-		/*
-		 * The size of the CMA area is unknown now so we need to
-		 * prepare the memory for the usemap at maximum.
-		 */
-		if (IS_ENABLED(CONFIG_CMA) && j == ZONE_MOVABLE &&
-			pgdat->node_spanned_pages) {
-			movable_size = node_end_pfn - pgdat->node_start_pfn;
-		}
-
-		if (!size && !movable_size)
+		if (!size)
 			continue;
 
 		set_pageblock_order();
-		if (movable_size) {
-			zone->zone_start_pfn = pgdat->node_start_pfn;
-			zone->spanned_pages = movable_size;
-			setup_usemap(pgdat, zone,
-				pgdat->node_start_pfn, movable_size);
-			init_currently_empty_zone(zone,
-				pgdat->node_start_pfn, movable_size);
-		} else {
-			setup_usemap(pgdat, zone, zone_start_pfn, size);
-			init_currently_empty_zone(zone, zone_start_pfn, size);
-		}
+		setup_usemap(pgdat, zone, zone_start_pfn, size);
+		init_currently_empty_zone(zone, zone_start_pfn, size);
 		memmap_init(size, nid, j, zone_start_pfn);
 	}
 }
@@ -6401,7 +6383,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	free_area_init_core(pgdat);
 }
 
-#ifdef CONFIG_HAVE_MEMBLOCK
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
 /*
  * Only struct pages that are backed by physical memory are zeroed and
  * initialized by going through __init_single_page(). But, there are some
@@ -6439,7 +6421,7 @@ void __paginginit zero_resv_unavail(void)
 	if (pgcnt)
 		pr_info("Reserved but unavailable: %lld pages", pgcnt);
 }
-#endif /* CONFIG_HAVE_MEMBLOCK */
+#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 
@@ -6865,6 +6847,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();
+	zero_resv_unavail();
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid, NULL,
@@ -6875,7 +6858,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 			node_set_state(nid, N_MEMORY);
 		check_for_memory(pgdat, nid);
 	}
-	zero_resv_unavail();
 }
 
 static int __init cmdline_parse_core(char *p, unsigned long *core,
@@ -7051,9 +7033,9 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 
 void __init free_area_init(unsigned long *zones_size)
 {
+	zero_resv_unavail();
 	free_area_init_node(0, zones_size,
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
-	zero_resv_unavail();
 }
 
 static int page_alloc_cpu_dead(unsigned int cpu)
@@ -7621,11 +7603,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 	unsigned long pfn, iter, found;
 
 	/*
-	 * For avoiding noise data, lru_add_drain_all() should be called
-	 * If ZONE_MOVABLE, the zone never contains unmovable pages
+	 * TODO we could make this much more efficient by not checking every
+	 * page in the range if we know all of them are in MOVABLE_ZONE and
+	 * that the movable zone guarantees that pages are migratable but
+	 * the later is not the case right now unfortunatelly. E.g. movablecore
+	 * can still lead to having bootmem allocations in zone_movable.
 	 */
-	if (zone_idx(zone) == ZONE_MOVABLE)
-		return false;
 
 	/*
 	 * CMA allocations (alloc_contig_range) really need to mark isolate
@@ -7646,7 +7629,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		page = pfn_to_page(check);
 
 		if (PageReserved(page))
-			return true;
+			goto unmovable;
 
 		/*
 		 * Hugepages are not in LRU lists, but they're movable.
@@ -7696,32 +7679,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		 * page at boot.
 		 */
 		if (found > count)
-			return true;
+			goto unmovable;
 	}
 	return false;
-}
-
-bool is_pageblock_removable_nolock(struct page *page)
-{
-	struct zone *zone;
-	unsigned long pfn;
-
-	/*
-	 * We have to be careful here because we are iterating over memory
-	 * sections which are not zone aware so we might end up outside of
-	 * the zone but still within the section.
-	 * We have to take care about the node as well. If the node is offline
-	 * its NODE_DATA will be NULL - see page_zone.
-	 */
-	if (!node_online(page_to_nid(page)))
-		return false;
-
-	zone = page_zone(page);
-	pfn = page_to_pfn(page);
-	if (!zone_spans_pfn(zone, pfn))
-		return false;
-
-	return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, true);
+unmovable:
+	WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
+	return true;
 }
 
 #if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
@@ -7951,7 +7914,7 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 }
 #endif
 
-#if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * The zone indicated has a new number of managed_pages; batch sizes and percpu
  * page high values need to be recalulated.