1 files changed, 145 insertions, 73 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1521100f1e63..c677c1506d73 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -155,16 +155,17 @@ static inline void set_pcppage_migratetype(struct page *page, int migratetype)
  * The following functions are used by the suspend/hibernate code to temporarily
  * change gfp_allowed_mask in order to avoid using I/O during memory allocations
  * while devices are suspended.  To avoid races with the suspend/hibernate code,
- * they should always be called with pm_mutex held (gfp_allowed_mask also should
- * only be modified with pm_mutex held, unless the suspend/hibernate code is
- * guaranteed not to run in parallel with that modification).
+ * they should always be called with system_transition_mutex held
+ * (gfp_allowed_mask also should only be modified with system_transition_mutex
+ * held, unless the suspend/hibernate code is guaranteed not to run in parallel
+ * with that modification).
  */
 
 static gfp_t saved_gfp_mask;
 
 void pm_restore_gfp_mask(void)
 {
-	WARN_ON(!mutex_is_locked(&pm_mutex));
+	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 	if (saved_gfp_mask) {
 		gfp_allowed_mask = saved_gfp_mask;
 		saved_gfp_mask = 0;
@@ -173,7 +174,7 @@ void pm_restore_gfp_mask(void)
 
 void pm_restrict_gfp_mask(void)
 {
-	WARN_ON(!mutex_is_locked(&pm_mutex));
+	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 	WARN_ON(saved_gfp_mask);
 	saved_gfp_mask = gfp_allowed_mask;
 	gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
@@ -2908,10 +2909,10 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 	if (!static_branch_likely(&vm_numa_stat_key))
 		return;
 
-	if (z->node != numa_node_id())
+	if (zone_to_nid(z) != numa_node_id())
 		local_stat = NUMA_OTHER;
 
-	if (z->node == preferred_zone->node)
+	if (zone_to_nid(z) == zone_to_nid(preferred_zone))
 		__inc_numa_state(z, NUMA_HIT);
 	else {
 		__inc_numa_state(z, NUMA_MISS);
@@ -4164,11 +4165,12 @@ retry:
 		alloc_flags = reserve_flags;
 
 	/*
-	 * Reset the zonelist iterators if memory policies can be ignored.
-	 * These allocations are high priority and system rather than user
-	 * orientated.
+	 * Reset the nodemask and zonelist iterators if memory policies can be
+	 * ignored. These allocations are high priority and system rather than
+	 * user oriented.
 	 */
 	if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
+		ac->nodemask = NULL;
 		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
 					ac->high_zoneidx, ac->nodemask);
 	}
@@ -4402,19 +4404,15 @@ out:
 EXPORT_SYMBOL(__alloc_pages_nodemask);
 
 /*
- * Common helper functions.
+ * Common helper functions. Never use with __GFP_HIGHMEM because the returned
+ * address cannot represent highmem pages. Use alloc_pages and then kmap if
+ * you need to access high mem.
  */
 unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
 {
 	struct page *page;
 
-	/*
-	 * __get_free_pages() returns a virtual address, which cannot represent
-	 * a highmem page
-	 */
-	VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
-
-	page = alloc_pages(gfp_mask, order);
+	page = alloc_pages(gfp_mask & ~__GFP_HIGHMEM, order);
 	if (!page)
 		return 0;
 	return (unsigned long) page_address(page);
@@ -5280,7 +5278,7 @@ int local_memory_node(int node)
 	z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
 				   gfp_zone(GFP_KERNEL),
 				   NULL);
-	return z->zone->node;
+	return zone_to_nid(z->zone);
 }
 #endif
 
@@ -5566,13 +5564,12 @@ static int zone_batchsize(struct zone *zone)
 
 	/*
 	 * The per-cpu-pages pools are set to around 1000th of the
-	 * size of the zone.  But no more than 1/2 of a meg.
-	 *
-	 * OK, so we don't know how big the cache is.  So guess.
+	 * size of the zone.
 	 */
 	batch = zone->managed_pages / 1024;
-	if (batch * PAGE_SIZE > 512 * 1024)
-		batch = (512 * 1024) / PAGE_SIZE;
+	/* But no more than a meg. */
+	if (batch * PAGE_SIZE > 1024 * 1024)
+		batch = (1024 * 1024) / PAGE_SIZE;
 	batch /= 4;		/* We effectively *= 4 below */
 	if (batch < 1)
 		batch = 1;
@@ -6123,7 +6120,7 @@ static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned l
 	return usemapsize / 8;
 }
 
-static void __init setup_usemap(struct pglist_data *pgdat,
+static void __ref setup_usemap(struct pglist_data *pgdat,
 				struct zone *zone,
 				unsigned long zone_start_pfn,
 				unsigned long zonesize)
@@ -6143,7 +6140,7 @@ static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
-void __paginginit set_pageblock_order(void)
+void __init set_pageblock_order(void)
 {
 	unsigned int order;
 
@@ -6171,14 +6168,14 @@ void __paginginit set_pageblock_order(void)
  * include/linux/pageblock-flags.h for the values of pageblock_order based on
  * the kernel config
  */
-void __paginginit set_pageblock_order(void)
+void __init set_pageblock_order(void)
 {
 }
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
-static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages,
-						   unsigned long present_pages)
+static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
+						unsigned long present_pages)
 {
 	unsigned long pages = spanned_pages;
 
@@ -6197,39 +6194,99 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages,
 	return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
 }
 
-/*
- * Set up the zone data structures:
- *   - mark all pages reserved
- *   - mark all memory queues empty
- *   - clear the memory bitmaps
- *
- * NOTE: pgdat should get zeroed by caller.
- */
-static void __paginginit free_area_init_core(struct pglist_data *pgdat)
-{
-	enum zone_type j;
-	int nid = pgdat->node_id;
-
-	pgdat_resize_init(pgdat);
 #ifdef CONFIG_NUMA_BALANCING
+static void pgdat_init_numabalancing(struct pglist_data *pgdat)
+{
 	spin_lock_init(&pgdat->numabalancing_migrate_lock);
 	pgdat->numabalancing_migrate_nr_pages = 0;
 	pgdat->numabalancing_migrate_next_window = jiffies;
+}
+#else
+static void pgdat_init_numabalancing(struct pglist_data *pgdat) {}
 #endif
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void pgdat_init_split_queue(struct pglist_data *pgdat)
+{
 	spin_lock_init(&pgdat->split_queue_lock);
 	INIT_LIST_HEAD(&pgdat->split_queue);
 	pgdat->split_queue_len = 0;
+}
+#else
+static void pgdat_init_split_queue(struct pglist_data *pgdat) {}
 #endif
-	init_waitqueue_head(&pgdat->kswapd_wait);
-	init_waitqueue_head(&pgdat->pfmemalloc_wait);
+
 #ifdef CONFIG_COMPACTION
+static void pgdat_init_kcompactd(struct pglist_data *pgdat)
+{
 	init_waitqueue_head(&pgdat->kcompactd_wait);
+}
+#else
+static void pgdat_init_kcompactd(struct pglist_data *pgdat) {}
 #endif
+
+static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
+{
+	pgdat_resize_init(pgdat);
+
+	pgdat_init_numabalancing(pgdat);
+	pgdat_init_split_queue(pgdat);
+	pgdat_init_kcompactd(pgdat);
+
+	init_waitqueue_head(&pgdat->kswapd_wait);
+	init_waitqueue_head(&pgdat->pfmemalloc_wait);
+
 	pgdat_page_ext_init(pgdat);
 	spin_lock_init(&pgdat->lru_lock);
 	lruvec_init(node_lruvec(pgdat));
+}
+
+static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
+							unsigned long remaining_pages)
+{
+	zone->managed_pages = remaining_pages;
+	zone_set_nid(zone, nid);
+	zone->name = zone_names[idx];
+	zone->zone_pgdat = NODE_DATA(nid);
+	spin_lock_init(&zone->lock);
+	zone_seqlock_init(zone);
+	zone_pcp_init(zone);
+}
+
+/*
+ * Set up the zone data structures
+ * - init pgdat internals
+ * - init all zones belonging to this node
+ *
+ * NOTE: this function is only called during memory hotplug
+ */
+#ifdef CONFIG_MEMORY_HOTPLUG
+void __ref free_area_init_core_hotplug(int nid)
+{
+	enum zone_type z;
+	pg_data_t *pgdat = NODE_DATA(nid);
+
+	pgdat_init_internals(pgdat);
+	for (z = 0; z < MAX_NR_ZONES; z++)
+		zone_init_internals(&pgdat->node_zones[z], z, nid, 0);
+}
+#endif
+
+/*
+ * Set up the zone data structures:
+ *   - mark all pages reserved
+ *   - mark all memory queues empty
+ *   - clear the memory bitmaps
+ *
+ * NOTE: pgdat should get zeroed by caller.
+ * NOTE: this function is only called during early init.
+ */
+static void __init free_area_init_core(struct pglist_data *pgdat)
+{
+	enum zone_type j;
+	int nid = pgdat->node_id;
 
+	pgdat_init_internals(pgdat);
 	pgdat->per_cpu_nodestats = &boot_nodestats;
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
@@ -6277,15 +6334,7 @@ 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 = freesize;
-#ifdef CONFIG_NUMA
-		zone->node = nid;
-#endif
-		zone->name = zone_names[j];
-		zone->zone_pgdat = pgdat;
-		spin_lock_init(&zone->lock);
-		zone_seqlock_init(zone);
-		zone_pcp_init(zone);
+		zone_init_internals(zone, j, nid, freesize);
 
 		if (!size)
 			continue;
@@ -6345,8 +6394,24 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { }
 #endif /* CONFIG_FLAT_NODE_MEM_MAP */
 
-void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
-		unsigned long node_start_pfn, unsigned long *zholes_size)
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+static inline void pgdat_set_deferred_range(pg_data_t *pgdat)
+{
+	/*
+	 * We start only with one section of pages, more pages are added as
+	 * needed until the rest of deferred pages are initialized.
+	 */
+	pgdat->static_init_pgcnt = min_t(unsigned long, PAGES_PER_SECTION,
+						pgdat->node_spanned_pages);
+	pgdat->first_deferred_pfn = ULONG_MAX;
+}
+#else
+static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}
+#endif
+
+void __init free_area_init_node(int nid, unsigned long *zones_size,
+				   unsigned long node_start_pfn,
+				   unsigned long *zholes_size)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
 	unsigned long start_pfn = 0;
@@ -6370,20 +6435,12 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 				  zones_size, zholes_size);
 
 	alloc_node_mem_map(pgdat);
+	pgdat_set_deferred_range(pgdat);
 
-#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-	/*
-	 * We start only with one section of pages, more pages are added as
-	 * needed until the rest of deferred pages are initialized.
-	 */
-	pgdat->static_init_pgcnt = min_t(unsigned long, PAGES_PER_SECTION,
-					 pgdat->node_spanned_pages);
-	pgdat->first_deferred_pfn = ULONG_MAX;
-#endif
 	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
@@ -6391,7 +6448,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
  * may be accessed (for example page_to_pfn() on some configuration accesses
  * flags). We must explicitly zero those struct pages.
  */
-void __paginginit zero_resv_unavail(void)
+void __init zero_resv_unavail(void)
 {
 	phys_addr_t start, end;
 	unsigned long pfn;
@@ -6404,8 +6461,11 @@ void __paginginit zero_resv_unavail(void)
 	pgcnt = 0;
 	for_each_resv_unavail_range(i, &start, &end) {
 		for (pfn = PFN_DOWN(start); pfn < PFN_UP(end); pfn++) {
-			if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages)))
+			if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
+				pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
+					+ pageblock_nr_pages - 1;
 				continue;
+			}
 			mm_zero_struct_page(pfn_to_page(pfn));
 			pgcnt++;
 		}
@@ -6421,7 +6481,7 @@ 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
 
@@ -6847,6 +6907,7 @@ 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,
@@ -6857,7 +6918,6 @@ 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,
@@ -6939,9 +6999,21 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
 	start = (void *)PAGE_ALIGN((unsigned long)start);
 	end = (void *)((unsigned long)end & PAGE_MASK);
 	for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
+		struct page *page = virt_to_page(pos);
+		void *direct_map_addr;
+
+		/*
+		 * 'direct_map_addr' might be different from 'pos'
+		 * because some architectures' virt_to_page()
+		 * work with aliases.  Getting the direct map
+		 * address ensures that we get a _writeable_
+		 * alias for the memset().
+		 */
+		direct_map_addr = page_address(page);
 		if ((unsigned int)poison <= 0xFF)
-			memset(pos, poison, PAGE_SIZE);
-		free_reserved_page(virt_to_page(pos));
+			memset(direct_map_addr, poison, PAGE_SIZE);
+
+		free_reserved_page(page);
 	}
 
 	if (pages && s)
@@ -7033,9 +7105,9 @@ 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)