Merge branch 'master' into percpu

Conflicts:
	arch/powerpc/platforms/pseries/hvCall.S
	include/linux/percpu.h

1 files changed, 99 insertions, 27 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bf720550b44d..4e9f5cc5fb59 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,6 +48,7 @@
 #include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
+#include <linux/memory.h>
 #include <trace/events/kmem.h>
 
 #include <asm/tlbflush.h>
@@ -486,7 +487,6 @@ static inline void __free_one_page(struct page *page,
 	zone->free_area[order].nr_free++;
 }
 
-#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
 /*
  * free_page_mlock() -- clean up attempts to free and mlocked() page.
  * Page should not be on lru, so no need to fix that up.
@@ -497,9 +497,6 @@ static inline void free_page_mlock(struct page *page)
 	__dec_zone_page_state(page, NR_MLOCK);
 	__count_vm_event(UNEVICTABLE_MLOCKFREED);
 }
-#else
-static void free_page_mlock(struct page *page) { }
-#endif
 
 static inline int free_pages_check(struct page *page)
 {
@@ -1658,12 +1655,22 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	if (page)
 		goto out;
 
-	/* The OOM killer will not help higher order allocs */
-	if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_NOFAIL))
-		goto out;
-
+	if (!(gfp_mask & __GFP_NOFAIL)) {
+		/* The OOM killer will not help higher order allocs */
+		if (order > PAGE_ALLOC_COSTLY_ORDER)
+			goto out;
+		/*
+		 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
+		 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
+		 * The caller should handle page allocation failure by itself if
+		 * it specifies __GFP_THISNODE.
+		 * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER.
+		 */
+		if (gfp_mask & __GFP_THISNODE)
+			goto out;
+	}
 	/* Exhausted what can be done so it's blamo time */
-	out_of_memory(zonelist, gfp_mask, order);
+	out_of_memory(zonelist, gfp_mask, order, nodemask);
 
 out:
 	clear_zonelist_oom(zonelist, gfp_mask);
@@ -1769,7 +1776,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
-	} else if (unlikely(rt_task(p)))
+	} else if (unlikely(rt_task(p)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
 	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
@@ -1817,9 +1824,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
+restart:
 	wake_all_kswapd(order, zonelist, high_zoneidx);
 
-restart:
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
 	 * reclaim. Now things get more complex, so set up alloc_flags according
@@ -2183,7 +2190,7 @@ void show_free_areas(void)
 	printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
 		" active_file:%lu inactive_file:%lu isolated_file:%lu\n"
 		" unevictable:%lu"
-		" dirty:%lu writeback:%lu unstable:%lu buffer:%lu\n"
+		" dirty:%lu writeback:%lu unstable:%lu\n"
 		" free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n"
 		" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n",
 		global_page_state(NR_ACTIVE_ANON),
@@ -2196,7 +2203,6 @@ void show_free_areas(void)
 		global_page_state(NR_FILE_DIRTY),
 		global_page_state(NR_WRITEBACK),
 		global_page_state(NR_UNSTABLE_NFS),
-		nr_blockdev_pages(),
 		global_page_state(NR_FREE_PAGES),
 		global_page_state(NR_SLAB_RECLAIMABLE),
 		global_page_state(NR_SLAB_UNRECLAIMABLE),
@@ -2396,13 +2402,14 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 {
 	char saved_string[NUMA_ZONELIST_ORDER_LEN];
 	int ret;
+	static DEFINE_MUTEX(zl_order_mutex);
 
+	mutex_lock(&zl_order_mutex);
 	if (write)
-		strncpy(saved_string, (char*)table->data,
-			NUMA_ZONELIST_ORDER_LEN);
+		strcpy(saved_string, (char*)table->data);
 	ret = proc_dostring(table, write, buffer, length, ppos);
 	if (ret)
-		return ret;
+		goto out;
 	if (write) {
 		int oldval = user_zonelist_order;
 		if (__parse_numa_zonelist_order((char*)table->data)) {
@@ -2415,7 +2422,9 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 		} else if (oldval != user_zonelist_order)
 			build_all_zonelists();
 	}
-	return 0;
+out:
+	mutex_unlock(&zl_order_mutex);
+	return ret;
 }
 
 
@@ -3128,7 +3137,7 @@ static int __cpuinit process_zones(int cpu)
 
 		if (percpu_pagelist_fraction)
 			setup_pagelist_highmark(zone_pcp(zone, cpu),
-			 	(zone->present_pages / percpu_pagelist_fraction));
+			    (zone->present_pages / percpu_pagelist_fraction));
 	}
 
 	return 0;
@@ -3574,7 +3583,7 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
  * Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
  * then all holes in the requested range will be accounted for.
  */
-static unsigned long __meminit __absent_pages_in_range(int nid,
+unsigned long __meminit __absent_pages_in_range(int nid,
 				unsigned long range_start_pfn,
 				unsigned long range_end_pfn)
 {
@@ -4103,7 +4112,7 @@ static int __init cmp_node_active_region(const void *a, const void *b)
 }
 
 /* sort the node_map by start_pfn */
-static void __init sort_node_map(void)
+void __init sort_node_map(void)
 {
 	sort(early_node_map, (size_t)nr_nodemap_entries,
 			sizeof(struct node_active_region),
@@ -5003,23 +5012,65 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
 int set_migratetype_isolate(struct page *page)
 {
 	struct zone *zone;
-	unsigned long flags;
+	struct page *curr_page;
+	unsigned long flags, pfn, iter;
+	unsigned long immobile = 0;
+	struct memory_isolate_notify arg;
+	int notifier_ret;
 	int ret = -EBUSY;
 	int zone_idx;
 
 	zone = page_zone(page);
 	zone_idx = zone_idx(zone);
+
 	spin_lock_irqsave(&zone->lock, flags);
+	if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE ||
+	    zone_idx == ZONE_MOVABLE) {
+		ret = 0;
+		goto out;
+	}
+
+	pfn = page_to_pfn(page);
+	arg.start_pfn = pfn;
+	arg.nr_pages = pageblock_nr_pages;
+	arg.pages_found = 0;
+
 	/*
-	 * In future, more migrate types will be able to be isolation target.
+	 * It may be possible to isolate a pageblock even if the
+	 * migratetype is not MIGRATE_MOVABLE. The memory isolation
+	 * notifier chain is used by balloon drivers to return the
+	 * number of pages in a range that are held by the balloon
+	 * driver to shrink memory. If all the pages are accounted for
+	 * by balloons, are free, or on the LRU, isolation can continue.
+	 * Later, for example, when memory hotplug notifier runs, these
+	 * pages reported as "can be isolated" should be isolated(freed)
+	 * by the balloon driver through the memory notifier chain.
 	 */
-	if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE &&
-	    zone_idx != ZONE_MOVABLE)
+	notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
+	notifier_ret = notifier_to_errno(notifier_ret);
+	if (notifier_ret || !arg.pages_found)
 		goto out;
-	set_pageblock_migratetype(page, MIGRATE_ISOLATE);
-	move_freepages_block(zone, page, MIGRATE_ISOLATE);
-	ret = 0;
+
+	for (iter = pfn; iter < (pfn + pageblock_nr_pages); iter++) {
+		if (!pfn_valid_within(pfn))
+			continue;
+
+		curr_page = pfn_to_page(iter);
+		if (!page_count(curr_page) || PageLRU(curr_page))
+			continue;
+
+		immobile++;
+	}
+
+	if (arg.pages_found == immobile)
+		ret = 0;
+
 out:
+	if (!ret) {
+		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+		move_freepages_block(zone, page, MIGRATE_ISOLATE);
+	}
+
 	spin_unlock_irqrestore(&zone->lock, flags);
 	if (!ret)
 		drain_all_pages();
@@ -5086,3 +5137,24 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
 #endif
+
+#ifdef CONFIG_MEMORY_FAILURE
+bool is_free_buddy_page(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long flags;
+	int order;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	for (order = 0; order < MAX_ORDER; order++) {
+		struct page *page_head = page - (pfn & ((1 << order) - 1));
+
+		if (PageBuddy(page_head) && page_order(page_head) >= order)
+			break;
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+
+	return order < MAX_ORDER;
+}
+#endif