Merge commit 'refs/changes/82/419382/1' of ssh://git-master:12001/linux-3.10 into promotion_build

Change-Id: I9418a05ad5c56b2e902249218bac2fa594d99f56

10 files changed, 61 insertions, 18 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 502517492258..eea1a9dfac38 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -287,13 +287,19 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
  * Note, we wouldn't bother setting up the timer, but this function is on the
  * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
  * by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
  */
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
 {
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
@@ -306,9 +312,6 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	spin_unlock_bh(&bdi_lock);
 
 	synchronize_rcu_expedited();
-
-	/* bdi_list is now unused, clear it to mark @bdi dying */
-	INIT_LIST_HEAD(&bdi->bdi_list);
 }
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -359,6 +362,11 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 */
 	bdi_remove_from_list(bdi);
 
+	/* Make sure nobody queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	clear_bit(BDI_registered, &bdi->state);
+	spin_unlock_bh(&bdi->wb_lock);
+
 	/*
 	 * Drain work list and shutdown the delayed_work.  At this point,
 	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
diff --git a/mm/compaction.c b/mm/compaction.c
index 9a3e351da29b..18a90b4d0bfc 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -252,7 +252,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 {
 	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor, *valid_page = NULL;
-	unsigned long nr_strict_required = end_pfn - blockpfn;
 	unsigned long flags;
 	bool locked = false;
 
@@ -265,11 +264,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		nr_scanned++;
 		if (!pfn_valid_within(blockpfn))
-			continue;
+			goto isolate_fail;
+
 		if (!valid_page)
 			valid_page = page;
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/*
 		 * The zone lock must be held to isolate freepages.
@@ -290,12 +290,10 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
-			continue;
+			goto isolate_fail;
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
-		if (!isolated && strict)
-			break;
 		total_isolated += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
@@ -306,7 +304,15 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		if (isolated) {
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
+			continue;
 		}
+
+isolate_fail:
+		if (strict)
+			break;
+		else
+			continue;
+
 	}
 
 	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -316,7 +322,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	 * pages requested were isolated. If there were any failures, 0 is
 	 * returned and CMA will fail.
 	 */
-	if (strict && nr_strict_required > total_isolated)
+	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
 	if (locked)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index aa3b9a63394b..8a7f27b42131 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1487,6 +1487,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 	while (min_count < persistent_huge_pages(h)) {
 		if (!free_pool_huge_page(h, nodes_allowed, 0))
 			break;
+		cond_resched_lock(&hugetlb_lock);
 	}
 	while (count < persistent_huge_pages(h)) {
 		if (!adjust_pool_surplus(h, nodes_allowed, 1))
diff --git a/mm/ksm.c b/mm/ksm.c
index b6afe0c440d8..784d1e4bc385 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -444,7 +444,7 @@ static void break_cow(struct rmap_item *rmap_item)
 static struct page *page_trans_compound_anon(struct page *page)
 {
 	if (PageTransCompound(page)) {
-		struct page *head = compound_trans_head(page);
+		struct page *head = compound_head(page);
 		/*
 		 * head may actually be splitted and freed from under
 		 * us but it's ok here.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 96f5e2d8390a..7849660665d7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6395,9 +6395,23 @@ static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
 static void mem_cgroup_css_offline(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	struct cgroup *iter;
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
+
+	/*
+	 * This requires that offlining is serialized.  Right now that is
+	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
+	 */
+	rcu_read_lock();
+	cgroup_for_each_descendant_post(iter, cont) {
+		rcu_read_unlock();
+		mem_cgroup_reparent_charges(mem_cgroup_from_cont(iter));
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
 	mem_cgroup_reparent_charges(memcg);
+
 	mem_cgroup_destroy_all_caches(memcg);
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e386beefc994..59c62fa75c5a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1544,7 +1544,7 @@ int soft_offline_page(struct page *page, int flags)
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
-	struct page *hpage = compound_trans_head(page);
+	struct page *hpage = compound_head(page);
 
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
diff --git a/mm/mlock.c b/mm/mlock.c
index 33861c780070..3dcea72277be 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -76,6 +76,7 @@ void clear_page_mlock(struct page *page)
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {
@@ -106,6 +107,7 @@ unsigned int munlock_vma_page(struct page *page)
 {
 	unsigned int page_mask = 0;
 
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 48c90b99a4cb..6e064ceaef69 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -374,9 +374,11 @@ 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;
+		/* Make sure p->first_page is always valid for PageTail() */
+		smp_wmb();
+		__SetPageTail(p);
 	}
 }
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 3f6077461aea..fbf0040a7342 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1390,9 +1390,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		BUG_ON(!page || PageAnon(page));
 
 		if (locked_vma) {
-			mlock_vma_page(page);   /* no-op if already mlocked */
-			if (page == check_page)
+			if (page == check_page) {
+				/* we know we have check_page locked */
+				mlock_vma_page(page);
 				ret = SWAP_MLOCK;
+			} else if (trylock_page(page)) {
+				/*
+				 * If we can lock the page, perform mlock.
+				 * Otherwise leave the page alone, it will be
+				 * eventually encountered again later.
+				 */
+				mlock_vma_page(page);
+				unlock_page(page);
+			}
 			continue;	/* don't unmap */
 		}
 
diff --git a/mm/swap.c b/mm/swap.c
index ea58dbde788e..4e35f3ff0427 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -81,7 +81,7 @@ static void put_compound_page(struct page *page)
 {
 	if (unlikely(PageTail(page))) {
 		/* __split_huge_page_refcount can run under us */
-		struct page *page_head = compound_trans_head(page);
+		struct page *page_head = compound_head(page);
 
 		if (likely(page != page_head &&
 			   get_page_unless_zero(page_head))) {
@@ -219,7 +219,7 @@ bool __get_page_tail(struct page *page)
 	 */
 	unsigned long flags;
 	bool got = false;
-	struct page *page_head = compound_trans_head(page);
+	struct page *page_head = compound_head(page);
 
 	if (likely(page != page_head && get_page_unless_zero(page_head))) {
 		/* Ref to put_compound_page() comment. */