Merge branch 'akpm' (Andrew's patch-bomb)

Merge misc VM changes from Andrew Morton:
 "The rest of most-of-MM.  The other MM bits await a slab merge.

  This patch includes the addition of a huge zero_page.  Not a
  performance boost but it an save large amounts of physical memory in
  some situations.

  Also a bunch of Fujitsu engineers are working on memory hotplug.
  Which, as it turns out, was badly broken.  About half of their patches
  are included here; the remainder are 3.8 material."

However, this merge disables CONFIG_MOVABLE_NODE, which was totally
broken.  We don't add new features with "default y", nor do we add
Kconfig questions that are incomprehensible to most people without any
help text.  Does the feature even make sense without compaction or
memory hotplug?

* akpm: (54 commits)
  mm/bootmem.c: remove unused wrapper function reserve_bootmem_generic()
  mm/memory.c: remove unused code from do_wp_page()
  asm-generic, mm: pgtable: consolidate zero page helpers
  mm/hugetlb.c: fix warning on freeing hwpoisoned hugepage
  hwpoison, hugetlbfs: fix RSS-counter warning
  hwpoison, hugetlbfs: fix "bad pmd" warning in unmapping hwpoisoned hugepage
  mm: protect against concurrent vma expansion
  memcg: do not check for mm in __mem_cgroup_count_vm_event
  tmpfs: support SEEK_DATA and SEEK_HOLE (reprise)
  mm: provide more accurate estimation of pages occupied by memmap
  fs/buffer.c: remove redundant initialization in alloc_page_buffers()
  fs/buffer.c: do not inline exported function
  writeback: fix a typo in comment
  mm: introduce new field "managed_pages" to struct zone
  mm, oom: remove statically defined arch functions of same name
  mm, oom: remove redundant sleep in pagefault oom handler
  mm, oom: cleanup pagefault oom handler
  memory_hotplug: allow online/offline memory to result movable node
  numa: add CONFIG_MOVABLE_NODE for movable-dedicated node
  mm, memcg: avoid unnecessary function call when memcg is disabled
  ...

1 files changed, 80 insertions, 35 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eee3efa..83637df 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -90,6 +90,9 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
 #ifdef CONFIG_HIGHMEM
 	[N_HIGH_MEMORY] = { { [0] = 1UL } },
 #endif
+#ifdef CONFIG_MOVABLE_NODE
+	[N_MEMORY] = { { [0] = 1UL } },
+#endif
 	[N_CPU] = { { [0] = 1UL } },
 #endif	/* NUMA */
 };
@@ -732,6 +735,13 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	local_irq_restore(flags);
 }
 
+/*
+ * Read access to zone->managed_pages is safe because it's unsigned long,
+ * but we still need to serialize writers. Currently all callers of
+ * __free_pages_bootmem() except put_page_bootmem() should only be used
+ * at boot time. So for shorter boot time, we shift the burden to
+ * put_page_bootmem() to serialize writers.
+ */
 void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
 {
 	unsigned int nr_pages = 1 << order;
@@ -747,6 +757,7 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
 		set_page_count(p, 0);
 	}
 
+	page_zone(page)->managed_pages += 1 << order;
 	set_page_refcounted(page);
 	__free_pages(page, order);
 }
@@ -1695,7 +1706,7 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
  *
  * If the zonelist cache is present in the passed in zonelist, then
  * returns a pointer to the allowed node mask (either the current
- * tasks mems_allowed, or node_states[N_HIGH_MEMORY].)
+ * tasks mems_allowed, or node_states[N_MEMORY].)
  *
  * If the zonelist cache is not available for this zonelist, does
  * nothing and returns NULL.
@@ -1724,7 +1735,7 @@ static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
 
 	allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
 					&cpuset_current_mems_allowed :
-					&node_states[N_HIGH_MEMORY];
+					&node_states[N_MEMORY];
 	return allowednodes;
 }
 
@@ -2981,6 +2992,7 @@ void show_free_areas(unsigned int filter)
 			" isolated(anon):%lukB"
 			" isolated(file):%lukB"
 			" present:%lukB"
+			" managed:%lukB"
 			" mlocked:%lukB"
 			" dirty:%lukB"
 			" writeback:%lukB"
@@ -3010,6 +3022,7 @@ void show_free_areas(unsigned int filter)
 			K(zone_page_state(zone, NR_ISOLATED_ANON)),
 			K(zone_page_state(zone, NR_ISOLATED_FILE)),
 			K(zone->present_pages),
+			K(zone->managed_pages),
 			K(zone_page_state(zone, NR_MLOCK)),
 			K(zone_page_state(zone, NR_FILE_DIRTY)),
 			K(zone_page_state(zone, NR_WRITEBACK)),
@@ -3238,7 +3251,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 		return node;
 	}
 
-	for_each_node_state(n, N_HIGH_MEMORY) {
+	for_each_node_state(n, N_MEMORY) {
 
 		/* Don't want a node to appear more than once */
 		if (node_isset(n, *used_node_mask))
@@ -3380,7 +3393,7 @@ static int default_zonelist_order(void)
  	 * local memory, NODE_ORDER may be suitable.
          */
 	average_size = total_size /
-				(nodes_weight(node_states[N_HIGH_MEMORY]) + 1);
+				(nodes_weight(node_states[N_MEMORY]) + 1);
 	for_each_online_node(nid) {
 		low_kmem_size = 0;
 		total_size = 0;
@@ -4476,6 +4489,26 @@ 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)
+{
+	unsigned long pages = spanned_pages;
+
+	/*
+	 * Provide a more accurate estimation if there are holes within
+	 * the zone and SPARSEMEM is in use. If there are holes within the
+	 * zone, each populated memory region may cost us one or two extra
+	 * memmap pages due to alignment because memmap pages for each
+	 * populated regions may not naturally algined on page boundary.
+	 * So the (present_pages >> 4) heuristic is a tradeoff for that.
+	 */
+	if (spanned_pages > present_pages + (present_pages >> 4) &&
+	    IS_ENABLED(CONFIG_SPARSEMEM))
+		pages = present_pages;
+
+	return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
+}
+
 /*
  * Set up the zone data structures:
  *   - mark all pages reserved
@@ -4499,48 +4532,56 @@ 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, memmap_pages;
+		unsigned long size, realsize, freesize, memmap_pages;
 
 		size = zone_spanned_pages_in_node(nid, j, zones_size);
-		realsize = size - zone_absent_pages_in_node(nid, j,
+		realsize = freesize = size - zone_absent_pages_in_node(nid, j,
 								zholes_size);
 
 		/*
-		 * Adjust realsize so that it accounts for how much memory
+		 * 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 =
-			PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
-		if (realsize >= memmap_pages) {
-			realsize -= memmap_pages;
+		memmap_pages = calc_memmap_size(size, realsize);
+		if (freesize >= memmap_pages) {
+			freesize -= memmap_pages;
 			if (memmap_pages)
 				printk(KERN_DEBUG
 				       "  %s zone: %lu pages used for memmap\n",
 				       zone_names[j], memmap_pages);
 		} else
 			printk(KERN_WARNING
-				"  %s zone: %lu pages exceeds realsize %lu\n",
-				zone_names[j], memmap_pages, realsize);
+				"  %s zone: %lu pages exceeds freesize %lu\n",
+				zone_names[j], memmap_pages, freesize);
 
 		/* Account for reserved pages */
-		if (j == 0 && realsize > dma_reserve) {
-			realsize -= dma_reserve;
+		if (j == 0 && freesize > dma_reserve) {
+			freesize -= dma_reserve;
 			printk(KERN_DEBUG "  %s zone: %lu pages reserved\n",
 					zone_names[0], dma_reserve);
 		}
 
 		if (!is_highmem_idx(j))
-			nr_kernel_pages += realsize;
-		nr_all_pages += realsize;
+			nr_kernel_pages += freesize;
+		/* Charge for highmem memmap if there are enough kernel pages */
+		else if (nr_kernel_pages > memmap_pages * 2)
+			nr_kernel_pages -= memmap_pages;
+		nr_all_pages += freesize;
 
 		zone->spanned_pages = size;
-		zone->present_pages = realsize;
+		zone->present_pages = freesize;
+		/*
+		 * Set an approximate value for lowmem here, it will be adjusted
+		 * 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;
 #ifdef CONFIG_NUMA
 		zone->node = nid;
-		zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio)
+		zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio)
 						/ 100;
-		zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100;
+		zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100;
 #endif
 		zone->name = zone_names[j];
 		spin_lock_init(&zone->lock);
@@ -4731,7 +4772,7 @@ unsigned long __init find_min_pfn_with_active_regions(void)
 /*
  * early_calculate_totalpages()
  * Sum pages in active regions for movable zone.
- * Populate N_HIGH_MEMORY for calculating usable_nodes.
+ * Populate N_MEMORY for calculating usable_nodes.
  */
 static unsigned long __init early_calculate_totalpages(void)
 {
@@ -4744,7 +4785,7 @@ static unsigned long __init early_calculate_totalpages(void)
 
 		totalpages += pages;
 		if (pages)
-			node_set_state(nid, N_HIGH_MEMORY);
+			node_set_state(nid, N_MEMORY);
 	}
   	return totalpages;
 }
@@ -4761,9 +4802,9 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	unsigned long usable_startpfn;
 	unsigned long kernelcore_node, kernelcore_remaining;
 	/* save the state before borrow the nodemask */
-	nodemask_t saved_node_state = node_states[N_HIGH_MEMORY];
+	nodemask_t saved_node_state = node_states[N_MEMORY];
 	unsigned long totalpages = early_calculate_totalpages();
-	int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
+	int usable_nodes = nodes_weight(node_states[N_MEMORY]);
 
 	/*
 	 * If movablecore was specified, calculate what size of
@@ -4798,7 +4839,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 restart:
 	/* Spread kernelcore memory as evenly as possible throughout nodes */
 	kernelcore_node = required_kernelcore / usable_nodes;
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		unsigned long start_pfn, end_pfn;
 
 		/*
@@ -4890,23 +4931,27 @@ restart:
 
 out:
 	/* restore the node_state */
-	node_states[N_HIGH_MEMORY] = saved_node_state;
+	node_states[N_MEMORY] = saved_node_state;
 }
 
-/* Any regular memory on that node ? */
-static void __init check_for_regular_memory(pg_data_t *pgdat)
+/* Any regular or high memory on that node ? */
+static void check_for_memory(pg_data_t *pgdat, int nid)
 {
-#ifdef CONFIG_HIGHMEM
 	enum zone_type zone_type;
 
-	for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
+	if (N_MEMORY == N_NORMAL_MEMORY)
+		return;
+
+	for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
 		struct zone *zone = &pgdat->node_zones[zone_type];
 		if (zone->present_pages) {
-			node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+			node_set_state(nid, N_HIGH_MEMORY);
+			if (N_NORMAL_MEMORY != N_HIGH_MEMORY &&
+			    zone_type <= ZONE_NORMAL)
+				node_set_state(nid, N_NORMAL_MEMORY);
 			break;
 		}
 	}
-#endif
 }
 
 /**
@@ -4989,8 +5034,8 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 
 		/* Any memory on that node */
 		if (pgdat->node_present_pages)
-			node_set_state(nid, N_HIGH_MEMORY);
-		check_for_regular_memory(pgdat);
+			node_set_state(nid, N_MEMORY);
+		check_for_memory(pgdat, nid);
 	}
 }
 
@@ -5727,7 +5772,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 	unsigned int tries = 0;
 	int ret = 0;
 
-	migrate_prep_local();
+	migrate_prep();
 
 	while (pfn < end || !list_empty(&cc->migratepages)) {
 		if (fatal_signal_pending(current)) {