Merge commit 'v3.3-rc1' into stable/for-linus-fixes-3.3

* commit 'v3.3-rc1': (9775 commits)
  Linux 3.3-rc1
  x86, syscall: Need __ARCH_WANT_SYS_IPC for 32 bits
  qnx4: don't leak ->BitMap on late failure exits
  qnx4: reduce the insane nesting in qnx4_checkroot()
  qnx4: di_fname is an array, for crying out loud...
  KEYS: Permit key_serial() to be called with a const key pointer
  keys: fix user_defined key sparse messages
  ima: fix cred sparse warning
  uml: fix compile for x86-64
  MPILIB: Add a missing ENOMEM check
  tpm: fix (ACPI S3) suspend regression
  nvme: fix merge error due to change of 'make_request_fn' fn type
  xen: using EXPORT_SYMBOL requires including export.h
  gpio: tps65910: Use correct offset for gpio initialization
  acpi/apei/einj: Add extensions to EINJ from rev 5.0 of acpi spec
  intel_idle: Split up and provide per CPU initialization func
  ACPI processor: Remove unneeded variable passed by acpi_processor_hotadd_init V2
  tg3: Fix single-vector MSI-X code
  openvswitch: Fix multipart datapath dumps.
  ipv6: fix per device IP snmp counters
  ...

1 files changed, 260 insertions, 323 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6ce27331834c..0027d8f4a1bb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -57,6 +57,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/memcontrol.h>
 #include <linux/prefetch.h>
+#include <linux/page-debug-flags.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -96,6 +97,14 @@ EXPORT_SYMBOL(node_states);
 
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
+/*
+ * When calculating the number of globally allowed dirty pages, there
+ * is a certain number of per-zone reserves that should not be
+ * considered dirtyable memory.  This is the sum of those reserves
+ * over all existing zones that contribute dirtyable memory.
+ */
+unsigned long dirty_balance_reserve __read_mostly;
+
 int percpu_pagelist_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
 
@@ -127,6 +136,13 @@ void pm_restrict_gfp_mask(void)
 	saved_gfp_mask = gfp_allowed_mask;
 	gfp_allowed_mask &= ~GFP_IOFS;
 }
+
+bool pm_suspended_storage(void)
+{
+	if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+		return false;
+	return true;
+}
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -181,42 +197,17 @@ static unsigned long __meminitdata nr_kernel_pages;
 static unsigned long __meminitdata nr_all_pages;
 static unsigned long __meminitdata dma_reserve;
 
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
-  #ifndef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-    /*
-     * MAX_ACTIVE_REGIONS determines the maximum number of distinct ranges
-     * of memory (RAM) that may be registered with add_active_range().
-     * Ranges passed to add_active_range() will be merged if possible so
-     * the number of times add_active_range() can be called is related to
-     * the number of nodes and the number of holes
-     */
-    #ifdef CONFIG_MAX_ACTIVE_REGIONS
-      /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */
-      #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS
-    #else
-      #if MAX_NUMNODES >= 32
-        /* If there can be many nodes, allow up to 50 holes per node */
-        #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50)
-      #else
-        /* By default, allow up to 256 distinct regions */
-        #define MAX_ACTIVE_REGIONS 256
-      #endif
-    #endif
-
-    static struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS];
-    static int __meminitdata nr_nodemap_entries;
-#endif /* !CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
-  static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
-  static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
-  static unsigned long __initdata required_kernelcore;
-  static unsigned long __initdata required_movablecore;
-  static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
-
-  /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
-  int movable_zone;
-  EXPORT_SYMBOL(movable_zone);
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
+static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
+static unsigned long __initdata required_kernelcore;
+static unsigned long __initdata required_movablecore;
+static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
+
+/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
+int movable_zone;
+EXPORT_SYMBOL(movable_zone);
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 #if MAX_NUMNODES > 1
 int nr_node_ids __read_mostly = MAX_NUMNODES;
@@ -336,8 +327,8 @@ out:
  *
  * The remaining PAGE_SIZE pages are called "tail pages".
  *
- * All pages have PG_compound set.  All pages have their ->private pointing at
- * the head page (even the head page has this).
+ * All pages have PG_compound set.  All tail pages have their ->first_page
+ * pointing at the head page.
  *
  * The first tail page's ->lru.next holds the address of the compound page's
  * put_page() function.  Its ->lru.prev holds the order of allocation.
@@ -359,8 +350,8 @@ void prep_compound_page(struct page *page, unsigned long order)
 	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
-
 		__SetPageTail(p);
+		set_page_count(p, 0);
 		p->first_page = page;
 	}
 }
@@ -406,6 +397,37 @@ static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
 		clear_highpage(page + i);
 }
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
+unsigned int _debug_guardpage_minorder;
+
+static int __init debug_guardpage_minorder_setup(char *buf)
+{
+	unsigned long res;
+
+	if (kstrtoul(buf, 10, &res) < 0 ||  res > MAX_ORDER / 2) {
+		printk(KERN_ERR "Bad debug_guardpage_minorder value\n");
+		return 0;
+	}
+	_debug_guardpage_minorder = res;
+	printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res);
+	return 0;
+}
+__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
+
+static inline void set_page_guard_flag(struct page *page)
+{
+	__set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+
+static inline void clear_page_guard_flag(struct page *page)
+{
+	__clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+#else
+static inline void set_page_guard_flag(struct page *page) { }
+static inline void clear_page_guard_flag(struct page *page) { }
+#endif
+
 static inline void set_page_order(struct page *page, int order)
 {
 	set_page_private(page, order);
@@ -463,6 +485,11 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
 	if (page_zone_id(page) != page_zone_id(buddy))
 		return 0;
 
+	if (page_is_guard(buddy) && page_order(buddy) == order) {
+		VM_BUG_ON(page_count(buddy) != 0);
+		return 1;
+	}
+
 	if (PageBuddy(buddy) && page_order(buddy) == order) {
 		VM_BUG_ON(page_count(buddy) != 0);
 		return 1;
@@ -519,11 +546,19 @@ static inline void __free_one_page(struct page *page,
 		buddy = page + (buddy_idx - page_idx);
 		if (!page_is_buddy(page, buddy, order))
 			break;
-
-		/* Our buddy is free, merge with it and move up one order. */
-		list_del(&buddy->lru);
-		zone->free_area[order].nr_free--;
-		rmv_page_order(buddy);
+		/*
+		 * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
+		 * merge with it and move up one order.
+		 */
+		if (page_is_guard(buddy)) {
+			clear_page_guard_flag(buddy);
+			set_page_private(page, 0);
+			__mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+		} else {
+			list_del(&buddy->lru);
+			zone->free_area[order].nr_free--;
+			rmv_page_order(buddy);
+		}
 		combined_idx = buddy_idx & page_idx;
 		page = page + (combined_idx - page_idx);
 		page_idx = combined_idx;
@@ -657,7 +692,7 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 	int i;
 	int bad = 0;
 
-	trace_mm_page_free_direct(page, order);
+	trace_mm_page_free(page, order);
 	kmemcheck_free_shadow(page, order);
 
 	if (PageAnon(page))
@@ -695,32 +730,23 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	local_irq_restore(flags);
 }
 
-/*
- * permit the bootmem allocator to evade page validation on high-order frees
- */
 void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
 {
-	if (order == 0) {
-		__ClearPageReserved(page);
-		set_page_count(page, 0);
-		set_page_refcounted(page);
-		__free_page(page);
-	} else {
-		int loop;
+	unsigned int nr_pages = 1 << order;
+	unsigned int loop;
 
-		prefetchw(page);
-		for (loop = 0; loop < (1 << order); loop++) {
-			struct page *p = &page[loop];
+	prefetchw(page);
+	for (loop = 0; loop < nr_pages; loop++) {
+		struct page *p = &page[loop];
 
-			if (loop + 1 < (1 << order))
-				prefetchw(p + 1);
-			__ClearPageReserved(p);
-			set_page_count(p, 0);
-		}
-
-		set_page_refcounted(page);
-		__free_pages(page, order);
+		if (loop + 1 < nr_pages)
+			prefetchw(p + 1);
+		__ClearPageReserved(p);
+		set_page_count(p, 0);
 	}
+
+	set_page_refcounted(page);
+	__free_pages(page, order);
 }
 
 
@@ -749,6 +775,23 @@ static inline void expand(struct zone *zone, struct page *page,
 		high--;
 		size >>= 1;
 		VM_BUG_ON(bad_range(zone, &page[size]));
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+		if (high < debug_guardpage_minorder()) {
+			/*
+			 * Mark as guard pages (or page), that will allow to
+			 * merge back to allocator when buddy will be freed.
+			 * Corresponding page table entries will not be touched,
+			 * pages will stay not present in virtual address space
+			 */
+			INIT_LIST_HEAD(&page[size].lru);
+			set_page_guard_flag(&page[size]);
+			set_page_private(&page[size], high);
+			/* Guard pages are not available for any usage */
+			__mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << high));
+			continue;
+		}
+#endif
 		list_add(&page[size].lru, &area->free_list[migratetype]);
 		area->nr_free++;
 		set_page_order(&page[size], high);
@@ -1214,6 +1257,19 @@ out:
 }
 
 /*
+ * Free a list of 0-order pages
+ */
+void free_hot_cold_page_list(struct list_head *list, int cold)
+{
+	struct page *page, *next;
+
+	list_for_each_entry_safe(page, next, list, lru) {
+		trace_mm_page_free_batched(page, cold);
+		free_hot_cold_page(page, cold);
+	}
+}
+
+/*
  * split_page takes a non-compound higher-order page, and splits it into
  * n (1<<order) sub-pages: page[0..n]
  * Each sub-page must be freed individually.
@@ -1411,7 +1467,7 @@ static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 
 static int __init fail_page_alloc_debugfs(void)
 {
-	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+	umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
 	struct dentry *dir;
 
 	dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
@@ -1460,7 +1516,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	long min = mark;
 	int o;
 
-	free_pages -= (1 << order) + 1;
+	free_pages -= (1 << order) - 1;
 	if (alloc_flags & ALLOC_HIGH)
 		min -= min / 2;
 	if (alloc_flags & ALLOC_HARDER)
@@ -1670,6 +1726,35 @@ zonelist_scan:
 		if ((alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				continue;
+		/*
+		 * When allocating a page cache page for writing, we
+		 * want to get it from a zone that is within its dirty
+		 * limit, such that no single zone holds more than its
+		 * proportional share of globally allowed dirty pages.
+		 * The dirty limits take into account the zone's
+		 * lowmem reserves and high watermark so that kswapd
+		 * should be able to balance it without having to
+		 * write pages from its LRU list.
+		 *
+		 * This may look like it could increase pressure on
+		 * lower zones by failing allocations in higher zones
+		 * before they are full.  But the pages that do spill
+		 * over are limited as the lower zones are protected
+		 * by this very same mechanism.  It should not become
+		 * a practical burden to them.
+		 *
+		 * XXX: For now, allow allocations to potentially
+		 * exceed the per-zone dirty limit in the slowpath
+		 * (ALLOC_WMARK_LOW unset) before going into reclaim,
+		 * which is important when on a NUMA setup the allowed
+		 * zones are together not big enough to reach the
+		 * global limit.  The proper fix for these situations
+		 * will require awareness of zones in the
+		 * dirty-throttling and the flusher threads.
+		 */
+		if ((alloc_flags & ALLOC_WMARK_LOW) &&
+		    (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
+			goto this_zone_full;
 
 		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
 		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
@@ -1759,7 +1844,8 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 {
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
 
-	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) ||
+	    debug_guardpage_minorder() > 0)
 		return;
 
 	/*
@@ -1798,12 +1884,25 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 
 static inline int
 should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+				unsigned long did_some_progress,
 				unsigned long pages_reclaimed)
 {
 	/* Do not loop if specifically requested */
 	if (gfp_mask & __GFP_NORETRY)
 		return 0;
 
+	/* Always retry if specifically requested */
+	if (gfp_mask & __GFP_NOFAIL)
+		return 1;
+
+	/*
+	 * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim
+	 * making forward progress without invoking OOM. Suspend also disables
+	 * storage devices so kswapd will not help. Bail if we are suspending.
+	 */
+	if (!did_some_progress && pm_suspended_storage())
+		return 0;
+
 	/*
 	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
 	 * means __GFP_NOFAIL, but that may not be true in other
@@ -1822,13 +1921,6 @@ should_alloc_retry(gfp_t gfp_mask, unsigned int order,
 	if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
 		return 1;
 
-	/*
-	 * Don't let big-order allocations loop unless the caller
-	 * explicitly requests that.
-	 */
-	if (gfp_mask & __GFP_NOFAIL)
-		return 1;
-
 	return 0;
 }
 
@@ -1889,13 +1981,19 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress,
-	bool sync_migration)
+	int migratetype, bool sync_migration,
+	bool *deferred_compaction,
+	unsigned long *did_some_progress)
 {
 	struct page *page;
 
-	if (!order || compaction_deferred(preferred_zone))
+	if (!order)
+		return NULL;
+
+	if (compaction_deferred(preferred_zone)) {
+		*deferred_compaction = true;
 		return NULL;
+	}
 
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
@@ -1924,7 +2022,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 * but not enough to satisfy watermarks.
 		 */
 		count_vm_event(COMPACTFAIL);
-		defer_compaction(preferred_zone);
+
+		/*
+		 * As async compaction considers a subset of pageblocks, only
+		 * defer if the failure was a sync compaction failure.
+		 */
+		if (sync_migration)
+			defer_compaction(preferred_zone);
 
 		cond_resched();
 	}
@@ -1936,8 +2040,9 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress,
-	bool sync_migration)
+	int migratetype, bool sync_migration,
+	bool *deferred_compaction,
+	unsigned long *did_some_progress)
 {
 	return NULL;
 }
@@ -2087,6 +2192,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long pages_reclaimed = 0;
 	unsigned long did_some_progress;
 	bool sync_migration = false;
+	bool deferred_compaction = false;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2167,12 +2273,22 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress,
-					sync_migration);
+					migratetype, sync_migration,
+					&deferred_compaction,
+					&did_some_progress);
 	if (page)
 		goto got_pg;
 	sync_migration = true;
 
+	/*
+	 * If compaction is deferred for high-order allocations, it is because
+	 * sync compaction recently failed. In this is the case and the caller
+	 * has requested the system not be heavily disrupted, fail the
+	 * allocation now instead of entering direct reclaim
+	 */
+	if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+		goto nopage;
+
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
 					zonelist, high_zoneidx,
@@ -2221,7 +2337,8 @@ rebalance:
 
 	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
-	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+	if (should_alloc_retry(gfp_mask, order, did_some_progress,
+						pages_reclaimed)) {
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
@@ -2235,8 +2352,9 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress,
-					sync_migration);
+					migratetype, sync_migration,
+					&deferred_compaction,
+					&did_some_progress);
 		if (page)
 			goto got_pg;
 	}
@@ -2331,16 +2449,6 @@ unsigned long get_zeroed_page(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(get_zeroed_page);
 
-void __pagevec_free(struct pagevec *pvec)
-{
-	int i = pagevec_count(pvec);
-
-	while (--i >= 0) {
-		trace_mm_pagevec_free(pvec->pages[i], pvec->cold);
-		free_hot_cold_page(pvec->pages[i], pvec->cold);
-	}
-}
-
 void __free_pages(struct page *page, unsigned int order)
 {
 	if (put_page_testzero(page)) {
@@ -3380,9 +3488,15 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 	unsigned long block_migratetype;
 	int reserve;
 
-	/* Get the start pfn, end pfn and the number of blocks to reserve */
+	/*
+	 * Get the start pfn, end pfn and the number of blocks to reserve
+	 * We have to be careful to be aligned to pageblock_nr_pages to
+	 * make sure that we always check pfn_valid for the first page in
+	 * the block.
+	 */
 	start_pfn = zone->zone_start_pfn;
 	end_pfn = start_pfn + zone->spanned_pages;
+	start_pfn = roundup(start_pfn, pageblock_nr_pages);
 	reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
 							pageblock_order;
 
@@ -3404,25 +3518,33 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 		if (page_to_nid(page) != zone_to_nid(zone))
 			continue;
 
-		/* Blocks with reserved pages will never free, skip them. */
-		block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
-		if (pageblock_is_reserved(pfn, block_end_pfn))
-			continue;
-
 		block_migratetype = get_pageblock_migratetype(page);
 
-		/* If this block is reserved, account for it */
-		if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
-			reserve--;
-			continue;
-		}
+		/* Only test what is necessary when the reserves are not met */
+		if (reserve > 0) {
+			/*
+			 * Blocks with reserved pages will never free, skip
+			 * them.
+			 */
+			block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+			if (pageblock_is_reserved(pfn, block_end_pfn))
+				continue;
 
-		/* Suitable for reserving if this block is movable */
-		if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
-			set_pageblock_migratetype(page, MIGRATE_RESERVE);
-			move_freepages_block(zone, page, MIGRATE_RESERVE);
-			reserve--;
-			continue;
+			/* If this block is reserved, account for it */
+			if (block_migratetype == MIGRATE_RESERVE) {
+				reserve--;
+				continue;
+			}
+
+			/* Suitable for reserving if this block is movable */
+			if (block_migratetype == MIGRATE_MOVABLE) {
+				set_pageblock_migratetype(page,
+							MIGRATE_RESERVE);
+				move_freepages_block(zone, page,
+							MIGRATE_RESERVE);
+				reserve--;
+				continue;
+			}
 		}
 
 		/*
@@ -3734,7 +3856,7 @@ __meminit int init_currently_empty_zone(struct zone *zone,
 	return 0;
 }
 
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
 /*
  * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
@@ -4002,7 +4124,7 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
 }
 
-#else
+#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
 					unsigned long zone_type,
 					unsigned long *zones_size)
@@ -4020,7 +4142,7 @@ static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
 	return zholes_size[zone_type];
 }
 
-#endif
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
 		unsigned long *zones_size, unsigned long *zholes_size)
@@ -4140,7 +4262,7 @@ 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;
-		enum lru_list l;
+		enum lru_list lru;
 
 		size = zone_spanned_pages_in_node(nid, j, zones_size);
 		realsize = size - zone_absent_pages_in_node(nid, j,
@@ -4190,8 +4312,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		zone->zone_pgdat = pgdat;
 
 		zone_pcp_init(zone);
-		for_each_lru(l)
-			INIT_LIST_HEAD(&zone->lru[l].list);
+		for_each_lru(lru)
+			INIT_LIST_HEAD(&zone->lruvec.lists[lru]);
 		zone->reclaim_stat.recent_rotated[0] = 0;
 		zone->reclaim_stat.recent_rotated[1] = 0;
 		zone->reclaim_stat.recent_scanned[0] = 0;
@@ -4243,10 +4365,10 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 	 */
 	if (pgdat == NODE_DATA(0)) {
 		mem_map = NODE_DATA(0)->node_mem_map;
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 		if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
 			mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET);
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 	}
 #endif
 #endif /* CONFIG_FLAT_NODE_MEM_MAP */
@@ -4271,7 +4393,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	free_area_init_core(pgdat, zones_size, zholes_size);
 }
 
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 
 #if MAX_NUMNODES > 1
 /*
@@ -4292,201 +4414,6 @@ static inline void setup_nr_node_ids(void)
 }
 #endif
 
-#ifndef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-/*
- * Common iterator interface used to define for_each_mem_pfn_range().
- */
-void __meminit __next_mem_pfn_range(int *idx, int nid,
-				    unsigned long *out_start_pfn,
-				    unsigned long *out_end_pfn, int *out_nid)
-{
-	struct node_active_region *r = NULL;
-
-	while (++*idx < nr_nodemap_entries) {
-		if (nid == MAX_NUMNODES || nid == early_node_map[*idx].nid) {
-			r = &early_node_map[*idx];
-			break;
-		}
-	}
-	if (!r) {
-		*idx = -1;
-		return;
-	}
-
-	if (out_start_pfn)
-		*out_start_pfn = r->start_pfn;
-	if (out_end_pfn)
-		*out_end_pfn = r->end_pfn;
-	if (out_nid)
-		*out_nid = r->nid;
-}
-
-/**
- * add_active_range - Register a range of PFNs backed by physical memory
- * @nid: The node ID the range resides on
- * @start_pfn: The start PFN of the available physical memory
- * @end_pfn: The end PFN of the available physical memory
- *
- * These ranges are stored in an early_node_map[] and later used by
- * free_area_init_nodes() to calculate zone sizes and holes. If the
- * range spans a memory hole, it is up to the architecture to ensure
- * the memory is not freed by the bootmem allocator. If possible
- * the range being registered will be merged with existing ranges.
- */
-void __init add_active_range(unsigned int nid, unsigned long start_pfn,
-						unsigned long end_pfn)
-{
-	int i;
-
-	mminit_dprintk(MMINIT_TRACE, "memory_register",
-			"Entering add_active_range(%d, %#lx, %#lx) "
-			"%d entries of %d used\n",
-			nid, start_pfn, end_pfn,
-			nr_nodemap_entries, MAX_ACTIVE_REGIONS);
-
-	mminit_validate_memmodel_limits(&start_pfn, &end_pfn);
-
-	/* Merge with existing active regions if possible */
-	for (i = 0; i < nr_nodemap_entries; i++) {
-		if (early_node_map[i].nid != nid)
-			continue;
-
-		/* Skip if an existing region covers this new one */
-		if (start_pfn >= early_node_map[i].start_pfn &&
-				end_pfn <= early_node_map[i].end_pfn)
-			return;
-
-		/* Merge forward if suitable */
-		if (start_pfn <= early_node_map[i].end_pfn &&
-				end_pfn > early_node_map[i].end_pfn) {
-			early_node_map[i].end_pfn = end_pfn;
-			return;
-		}
-
-		/* Merge backward if suitable */
-		if (start_pfn < early_node_map[i].start_pfn &&
-				end_pfn >= early_node_map[i].start_pfn) {
-			early_node_map[i].start_pfn = start_pfn;
-			return;
-		}
-	}
-
-	/* Check that early_node_map is large enough */
-	if (i >= MAX_ACTIVE_REGIONS) {
-		printk(KERN_CRIT "More than %d memory regions, truncating\n",
-							MAX_ACTIVE_REGIONS);
-		return;
-	}
-
-	early_node_map[i].nid = nid;
-	early_node_map[i].start_pfn = start_pfn;
-	early_node_map[i].end_pfn = end_pfn;
-	nr_nodemap_entries = i + 1;
-}
-
-/**
- * remove_active_range - Shrink an existing registered range of PFNs
- * @nid: The node id the range is on that should be shrunk
- * @start_pfn: The new PFN of the range
- * @end_pfn: The new PFN of the range
- *
- * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
- * The map is kept near the end physical page range that has already been
- * registered. This function allows an arch to shrink an existing registered
- * range.
- */
-void __init remove_active_range(unsigned int nid, unsigned long start_pfn,
-				unsigned long end_pfn)
-{
-	unsigned long this_start_pfn, this_end_pfn;
-	int i, j;
-	int removed = 0;
-
-	printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n",
-			  nid, start_pfn, end_pfn);
-
-	/* Find the old active region end and shrink */
-	for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) {
-		if (this_start_pfn >= start_pfn && this_end_pfn <= end_pfn) {
-			/* clear it */
-			early_node_map[i].start_pfn = 0;
-			early_node_map[i].end_pfn = 0;
-			removed = 1;
-			continue;
-		}
-		if (this_start_pfn < start_pfn && this_end_pfn > start_pfn) {
-			early_node_map[i].end_pfn = start_pfn;
-			if (this_end_pfn > end_pfn)
-				add_active_range(nid, end_pfn, this_end_pfn);
-			continue;
-		}
-		if (this_start_pfn >= start_pfn && this_end_pfn > end_pfn &&
-		    this_start_pfn < end_pfn) {
-			early_node_map[i].start_pfn = end_pfn;
-			continue;
-		}
-	}
-
-	if (!removed)
-		return;
-
-	/* remove the blank ones */
-	for (i = nr_nodemap_entries - 1; i > 0; i--) {
-		if (early_node_map[i].nid != nid)
-			continue;
-		if (early_node_map[i].end_pfn)
-			continue;
-		/* we found it, get rid of it */
-		for (j = i; j < nr_nodemap_entries - 1; j++)
-			memcpy(&early_node_map[j], &early_node_map[j+1],
-				sizeof(early_node_map[j]));
-		j = nr_nodemap_entries - 1;
-		memset(&early_node_map[j], 0, sizeof(early_node_map[j]));
-		nr_nodemap_entries--;
-	}
-}
-
-/**
- * remove_all_active_ranges - Remove all currently registered regions
- *
- * During discovery, it may be found that a table like SRAT is invalid
- * and an alternative discovery method must be used. This function removes
- * all currently registered regions.
- */
-void __init remove_all_active_ranges(void)
-{
-	memset(early_node_map, 0, sizeof(early_node_map));
-	nr_nodemap_entries = 0;
-}
-
-/* Compare two active node_active_regions */
-static int __init cmp_node_active_region(const void *a, const void *b)
-{
-	struct node_active_region *arange = (struct node_active_region *)a;
-	struct node_active_region *brange = (struct node_active_region *)b;
-
-	/* Done this way to avoid overflows */
-	if (arange->start_pfn > brange->start_pfn)
-		return 1;
-	if (arange->start_pfn < brange->start_pfn)
-		return -1;
-
-	return 0;
-}
-
-/* sort the node_map by start_pfn */
-void __init sort_node_map(void)
-{
-	sort(early_node_map, (size_t)nr_nodemap_entries,
-			sizeof(struct node_active_region),
-			cmp_node_active_region, NULL);
-}
-#else /* !CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-static inline void sort_node_map(void)
-{
-}
-#endif
-
 /**
  * node_map_pfn_alignment - determine the maximum internode alignment
  *
@@ -4740,8 +4667,10 @@ static void check_for_regular_memory(pg_data_t *pgdat)
 
 	for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
 		struct zone *zone = &pgdat->node_zones[zone_type];
-		if (zone->present_pages)
+		if (zone->present_pages) {
 			node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+			break;
+		}
 	}
 #endif
 }
@@ -4764,9 +4693,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	unsigned long start_pfn, end_pfn;
 	int i, nid;
 
-	/* Sort early_node_map as initialisation assumes it is sorted */
-	sort_node_map();
-
 	/* Record where the zone boundaries are */
 	memset(arch_zone_lowest_possible_pfn, 0,
 				sizeof(arch_zone_lowest_possible_pfn));
@@ -4867,7 +4793,7 @@ static int __init cmdline_parse_movablecore(char *p)
 early_param("kernelcore", cmdline_parse_kernelcore);
 early_param("movablecore", cmdline_parse_movablecore);
 
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 /**
  * set_dma_reserve - set the specified number of pages reserved in the first zone
@@ -4951,8 +4877,19 @@ static void calculate_totalreserve_pages(void)
 			if (max > zone->present_pages)
 				max = zone->present_pages;
 			reserve_pages += max;
+			/*
+			 * Lowmem reserves are not available to
+			 * GFP_HIGHUSER page cache allocations and
+			 * kswapd tries to balance zones to their high
+			 * watermark.  As a result, neither should be
+			 * regarded as dirtyable memory, to prevent a
+			 * situation where reclaim has to clean pages
+			 * in order to balance the zones.
+			 */
+			zone->dirty_balance_reserve = max;
 		}
 	}
+	dirty_balance_reserve = reserve_pages;
 	totalreserve_pages = reserve_pages;
 }