Merge branch 'v3.1-rc10' into for-3.2/core

Conflicts:
	block/blk-core.c
	include/linux/blkdev.h

Signed-off-by: Jens Axboe <axboe@kernel.dk>

10 files changed, 98 insertions, 276 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d6edf8d14f9..a87da524a4a 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -359,6 +359,17 @@ static unsigned long bdi_longest_inactive(void)
 	return max(5UL * 60 * HZ, interval);
 }
 
+/*
+ * Clear pending bit and wakeup anybody waiting for flusher thread creation or
+ * shutdown
+ */
+static void bdi_clear_pending(struct backing_dev_info *bdi)
+{
+	clear_bit(BDI_pending, &bdi->state);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&bdi->state, BDI_pending);
+}
+
 static int bdi_forker_thread(void *ptr)
 {
 	struct bdi_writeback *me = ptr;
@@ -390,6 +401,13 @@ static int bdi_forker_thread(void *ptr)
 		}
 
 		spin_lock_bh(&bdi_lock);
+		/*
+		 * In the following loop we are going to check whether we have
+		 * some work to do without any synchronization with tasks
+		 * waking us up to do work for them. So we have to set task
+		 * state already here so that we don't miss wakeups coming
+		 * after we verify some condition.
+		 */
 		set_current_state(TASK_INTERRUPTIBLE);
 
 		list_for_each_entry(bdi, &bdi_list, bdi_list) {
@@ -469,11 +487,13 @@ static int bdi_forker_thread(void *ptr)
 				spin_unlock_bh(&bdi->wb_lock);
 				wake_up_process(task);
 			}
+			bdi_clear_pending(bdi);
 			break;
 
 		case KILL_THREAD:
 			__set_current_state(TASK_RUNNING);
 			kthread_stop(task);
+			bdi_clear_pending(bdi);
 			break;
 
 		case NO_ACTION:
@@ -489,16 +509,8 @@ static int bdi_forker_thread(void *ptr)
 			else
 				schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
 			try_to_freeze();
-			/* Back to the main loop */
-			continue;
+			break;
 		}
-
-		/*
-		 * Clear pending bit and wakeup anybody waiting to tear us down.
-		 */
-		clear_bit(BDI_pending, &bdi->state);
-		smp_mb__after_clear_bit();
-		wake_up_bit(&bdi->state, BDI_pending);
 	}
 
 	return 0;
diff --git a/mm/filemap.c b/mm/filemap.c
index 645a080ba4d..7771871fa35 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -827,13 +827,14 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 {
 	unsigned int i;
 	unsigned int ret;
-	unsigned int nr_found;
+	unsigned int nr_found, nr_skip;
 
 	rcu_read_lock();
 restart:
 	nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
 				(void ***)pages, NULL, start, nr_pages);
 	ret = 0;
+	nr_skip = 0;
 	for (i = 0; i < nr_found; i++) {
 		struct page *page;
 repeat:
@@ -856,6 +857,7 @@ repeat:
 			 * here as an exceptional entry: so skip over it -
 			 * we only reach this from invalidate_mapping_pages().
 			 */
+			nr_skip++;
 			continue;
 		}
 
@@ -876,7 +878,7 @@ repeat:
 	 * If all entries were removed before we could secure them,
 	 * try again, because callers stop trying once 0 is returned.
 	 */
-	if (unlikely(!ret && nr_found))
+	if (unlikely(!ret && nr_found > nr_skip))
 		goto restart;
 	rcu_read_unlock();
 	return ret;
diff --git a/mm/highmem.c b/mm/highmem.c
index 693394daa2e..5ef672c07f7 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -326,7 +326,7 @@ static struct page_address_slot {
 	spinlock_t lock;			/* Protect this bucket's list */
 } ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER];
 
-static struct page_address_slot *page_slot(struct page *page)
+static struct page_address_slot *page_slot(const struct page *page)
 {
 	return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
 }
@@ -337,7 +337,7 @@ static struct page_address_slot *page_slot(struct page *page)
  *
  * Returns the page's virtual address.
  */
-void *page_address(struct page *page)
+void *page_address(const struct page *page)
 {
 	unsigned long flags;
 	void *ret;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f4ec4e7ca4c..3508777837c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -204,50 +204,6 @@ struct mem_cgroup_eventfd_list {
 static void mem_cgroup_threshold(struct mem_cgroup *mem);
 static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
 
-enum {
-	SCAN_BY_LIMIT,
-	SCAN_BY_SYSTEM,
-	NR_SCAN_CONTEXT,
-	SCAN_BY_SHRINK,	/* not recorded now */
-};
-
-enum {
-	SCAN,
-	SCAN_ANON,
-	SCAN_FILE,
-	ROTATE,
-	ROTATE_ANON,
-	ROTATE_FILE,
-	FREED,
-	FREED_ANON,
-	FREED_FILE,
-	ELAPSED,
-	NR_SCANSTATS,
-};
-
-struct scanstat {
-	spinlock_t	lock;
-	unsigned long	stats[NR_SCAN_CONTEXT][NR_SCANSTATS];
-	unsigned long	rootstats[NR_SCAN_CONTEXT][NR_SCANSTATS];
-};
-
-const char *scanstat_string[NR_SCANSTATS] = {
-	"scanned_pages",
-	"scanned_anon_pages",
-	"scanned_file_pages",
-	"rotated_pages",
-	"rotated_anon_pages",
-	"rotated_file_pages",
-	"freed_pages",
-	"freed_anon_pages",
-	"freed_file_pages",
-	"elapsed_ns",
-};
-#define SCANSTAT_WORD_LIMIT	"_by_limit"
-#define SCANSTAT_WORD_SYSTEM	"_by_system"
-#define SCANSTAT_WORD_HIERARCHY	"_under_hierarchy"
-
-
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -313,8 +269,7 @@ struct mem_cgroup {
 
 	/* For oom notifier event fd */
 	struct list_head oom_notify;
-	/* For recording LRU-scan statistics */
-	struct scanstat scanstat;
+
 	/*
 	 * Should we move charges of a task when a task is moved into this
 	 * mem_cgroup ? And what type of charges should we move ?
@@ -1678,44 +1633,6 @@ bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
 }
 #endif
 
-static void __mem_cgroup_record_scanstat(unsigned long *stats,
-			   struct memcg_scanrecord *rec)
-{
-
-	stats[SCAN] += rec->nr_scanned[0] + rec->nr_scanned[1];
-	stats[SCAN_ANON] += rec->nr_scanned[0];
-	stats[SCAN_FILE] += rec->nr_scanned[1];
-
-	stats[ROTATE] += rec->nr_rotated[0] + rec->nr_rotated[1];
-	stats[ROTATE_ANON] += rec->nr_rotated[0];
-	stats[ROTATE_FILE] += rec->nr_rotated[1];
-
-	stats[FREED] += rec->nr_freed[0] + rec->nr_freed[1];
-	stats[FREED_ANON] += rec->nr_freed[0];
-	stats[FREED_FILE] += rec->nr_freed[1];
-
-	stats[ELAPSED] += rec->elapsed;
-}
-
-static void mem_cgroup_record_scanstat(struct memcg_scanrecord *rec)
-{
-	struct mem_cgroup *mem;
-	int context = rec->context;
-
-	if (context >= NR_SCAN_CONTEXT)
-		return;
-
-	mem = rec->mem;
-	spin_lock(&mem->scanstat.lock);
-	__mem_cgroup_record_scanstat(mem->scanstat.stats[context], rec);
-	spin_unlock(&mem->scanstat.lock);
-
-	mem = rec->root;
-	spin_lock(&mem->scanstat.lock);
-	__mem_cgroup_record_scanstat(mem->scanstat.rootstats[context], rec);
-	spin_unlock(&mem->scanstat.lock);
-}
-
 /*
  * Scan the hierarchy if needed to reclaim memory. We remember the last child
  * we reclaimed from, so that we don't end up penalizing one child extensively
@@ -1740,9 +1657,8 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP;
 	bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK;
 	bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT;
-	struct memcg_scanrecord rec;
 	unsigned long excess;
-	unsigned long scanned;
+	unsigned long nr_scanned;
 
 	excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
 
@@ -1750,15 +1666,6 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	if (!check_soft && !shrink && root_mem->memsw_is_minimum)
 		noswap = true;
 
-	if (shrink)
-		rec.context = SCAN_BY_SHRINK;
-	else if (check_soft)
-		rec.context = SCAN_BY_SYSTEM;
-	else
-		rec.context = SCAN_BY_LIMIT;
-
-	rec.root = root_mem;
-
 	while (1) {
 		victim = mem_cgroup_select_victim(root_mem);
 		if (victim == root_mem) {
@@ -1799,23 +1706,14 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 			css_put(&victim->css);
 			continue;
 		}
-		rec.mem = victim;
-		rec.nr_scanned[0] = 0;
-		rec.nr_scanned[1] = 0;
-		rec.nr_rotated[0] = 0;
-		rec.nr_rotated[1] = 0;
-		rec.nr_freed[0] = 0;
-		rec.nr_freed[1] = 0;
-		rec.elapsed = 0;
 		/* we use swappiness of local cgroup */
 		if (check_soft) {
 			ret = mem_cgroup_shrink_node_zone(victim, gfp_mask,
-				noswap, zone, &rec, &scanned);
-			*total_scanned += scanned;
+				noswap, zone, &nr_scanned);
+			*total_scanned += nr_scanned;
 		} else
 			ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
-						noswap, &rec);
-		mem_cgroup_record_scanstat(&rec);
+						noswap);
 		css_put(&victim->css);
 		/*
 		 * At shrinking usage, we can't check we should stop here or
@@ -1841,29 +1739,23 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
  */
 static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
 {
-	int lock_count = -1;
 	struct mem_cgroup *iter, *failed = NULL;
 	bool cond = true;
 
 	for_each_mem_cgroup_tree_cond(iter, mem, cond) {
-		bool locked = iter->oom_lock;
-
-		iter->oom_lock = true;
-		if (lock_count == -1)
-			lock_count = iter->oom_lock;
-		else if (lock_count != locked) {
+		if (iter->oom_lock) {
 			/*
 			 * this subtree of our hierarchy is already locked
 			 * so we cannot give a lock.
 			 */
-			lock_count = 0;
 			failed = iter;
 			cond = false;
-		}
+		} else
+			iter->oom_lock = true;
 	}
 
 	if (!failed)
-		goto done;
+		return true;
 
 	/*
 	 * OK, we failed to lock the whole subtree so we have to clean up
@@ -1877,8 +1769,7 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
 		}
 		iter->oom_lock = false;
 	}
-done:
-	return lock_count;
+	return false;
 }
 
 /*
@@ -2091,6 +1982,7 @@ struct memcg_stock_pcp {
 #define FLUSHING_CACHED_CHARGE	(0)
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
+static DEFINE_MUTEX(percpu_charge_mutex);
 
 /*
  * Try to consume stocked charge on this cpu. If success, one page is consumed
@@ -2168,13 +2060,7 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
 
 	/* Notify other cpus that system-wide "drain" is running */
 	get_online_cpus();
-	/*
-	 * Get a hint for avoiding draining charges on the current cpu,
-	 * which must be exhausted by our charging.  It is not required that
-	 * this be a precise check, so we use raw_smp_processor_id() instead of
-	 * getcpu()/putcpu().
-	 */
-	curcpu = raw_smp_processor_id();
+	curcpu = get_cpu();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
 		struct mem_cgroup *mem;
@@ -2191,14 +2077,14 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
 				schedule_work_on(cpu, &stock->work);
 		}
 	}
+	put_cpu();
 
 	if (!sync)
 		goto out;
 
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
-		if (mem_cgroup_same_or_subtree(root_mem, stock->cached) &&
-				test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
+		if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
 			flush_work(&stock->work);
 	}
 out:
@@ -2213,14 +2099,22 @@ out:
  */
 static void drain_all_stock_async(struct mem_cgroup *root_mem)
 {
+	/*
+	 * If someone calls draining, avoid adding more kworker runs.
+	 */
+	if (!mutex_trylock(&percpu_charge_mutex))
+		return;
 	drain_all_stock(root_mem, false);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /* This is a synchronous drain interface. */
 static void drain_all_stock_sync(struct mem_cgroup *root_mem)
 {
 	/* called when force_empty is called */
+	mutex_lock(&percpu_charge_mutex);
 	drain_all_stock(root_mem, true);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /*
@@ -3858,18 +3752,14 @@ try_to_free:
 	/* try to free all pages in this cgroup */
 	shrink = 1;
 	while (nr_retries && mem->res.usage > 0) {
-		struct memcg_scanrecord rec;
 		int progress;
 
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			goto out;
 		}
-		rec.context = SCAN_BY_SHRINK;
-		rec.mem = mem;
-		rec.root = mem;
 		progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
-						false, &rec);
+						false);
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */
@@ -4713,54 +4603,6 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
 }
 #endif /* CONFIG_NUMA */
 
-static int mem_cgroup_vmscan_stat_read(struct cgroup *cgrp,
-				struct cftype *cft,
-				struct cgroup_map_cb *cb)
-{
-	struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
-	char string[64];
-	int i;
-
-	for (i = 0; i < NR_SCANSTATS; i++) {
-		strcpy(string, scanstat_string[i]);
-		strcat(string, SCANSTAT_WORD_LIMIT);
-		cb->fill(cb, string,  mem->scanstat.stats[SCAN_BY_LIMIT][i]);
-	}
-
-	for (i = 0; i < NR_SCANSTATS; i++) {
-		strcpy(string, scanstat_string[i]);
-		strcat(string, SCANSTAT_WORD_SYSTEM);
-		cb->fill(cb, string,  mem->scanstat.stats[SCAN_BY_SYSTEM][i]);
-	}
-
-	for (i = 0; i < NR_SCANSTATS; i++) {
-		strcpy(string, scanstat_string[i]);
-		strcat(string, SCANSTAT_WORD_LIMIT);
-		strcat(string, SCANSTAT_WORD_HIERARCHY);
-		cb->fill(cb, string,  mem->scanstat.rootstats[SCAN_BY_LIMIT][i]);
-	}
-	for (i = 0; i < NR_SCANSTATS; i++) {
-		strcpy(string, scanstat_string[i]);
-		strcat(string, SCANSTAT_WORD_SYSTEM);
-		strcat(string, SCANSTAT_WORD_HIERARCHY);
-		cb->fill(cb, string,  mem->scanstat.rootstats[SCAN_BY_SYSTEM][i]);
-	}
-	return 0;
-}
-
-static int mem_cgroup_reset_vmscan_stat(struct cgroup *cgrp,
-				unsigned int event)
-{
-	struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
-
-	spin_lock(&mem->scanstat.lock);
-	memset(&mem->scanstat.stats, 0, sizeof(mem->scanstat.stats));
-	memset(&mem->scanstat.rootstats, 0, sizeof(mem->scanstat.rootstats));
-	spin_unlock(&mem->scanstat.lock);
-	return 0;
-}
-
-
 static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
@@ -4831,11 +4673,6 @@ static struct cftype mem_cgroup_files[] = {
 		.mode = S_IRUGO,
 	},
 #endif
-	{
-		.name = "vmscan_stat",
-		.read_map = mem_cgroup_vmscan_stat_read,
-		.trigger = mem_cgroup_reset_vmscan_stat,
-	},
 };
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
@@ -5099,7 +4936,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	atomic_set(&mem->refcnt, 1);
 	mem->move_charge_at_immigrate = 0;
 	mutex_init(&mem->thresholds_lock);
-	spin_lock_init(&mem->scanstat.lock);
 	return &mem->css;
 free_out:
 	__mem_cgroup_free(mem);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 8b57173c1dd..9c51f9f58ca 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -636,7 +636,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 	struct vm_area_struct *prev;
 	struct vm_area_struct *vma;
 	int err = 0;
-	pgoff_t pgoff;
 	unsigned long vmstart;
 	unsigned long vmend;
 
@@ -649,9 +648,9 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 		vmstart = max(start, vma->vm_start);
 		vmend   = min(end, vma->vm_end);
 
-		pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 		prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
-				  vma->anon_vma, vma->vm_file, pgoff, new_pol);
+				  vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+				  new_pol);
 		if (prev) {
 			vma = prev;
 			next = vma->vm_next;
@@ -1412,7 +1411,9 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy,
 	err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);
 
 	if (!err && nmask) {
-		err = copy_from_user(bm, nm, alloc_size);
+		unsigned long copy_size;
+		copy_size = min_t(unsigned long, sizeof(bm), alloc_size);
+		err = copy_from_user(bm, nm, copy_size);
 		/* ensure entire bitmap is zeroed */
 		err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
 		err |= compat_put_bitmap(nmask, bm, nr_bits);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d1960744f88..0e309cd1b5b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -754,21 +754,10 @@ static void balance_dirty_pages(struct address_space *mapping,
 		 * 200ms is typically more than enough to curb heavy dirtiers;
 		 * (b) the pause time limit makes the dirtiers more responsive.
 		 */
-		if (nr_dirty < dirty_thresh +
-			       dirty_thresh / DIRTY_MAXPAUSE_AREA &&
+		if (nr_dirty < dirty_thresh &&
+		    bdi_dirty < (task_bdi_thresh + bdi_thresh) / 2 &&
 		    time_after(jiffies, start_time + MAX_PAUSE))
 			break;
-		/*
-		 * pass-good area. When some bdi gets blocked (eg. NFS server
-		 * not responding), or write bandwidth dropped dramatically due
-		 * to concurrent reads, or dirty threshold suddenly dropped and
-		 * the dirty pages cannot be brought down anytime soon (eg. on
-		 * slow USB stick), at least let go of the good bdi's.
-		 */
-		if (nr_dirty < dirty_thresh +
-			       dirty_thresh / DIRTY_PASSGOOD_AREA &&
-		    bdi_dirty < bdi_thresh)
-			break;
 
 		/*
 		 * Increase the delay for each loop, up to our previous
diff --git a/mm/slub.c b/mm/slub.c
index eb5a8f93338..7c54fe83a90 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -701,7 +701,7 @@ static u8 *check_bytes(u8 *start, u8 value, unsigned int bytes)
 		return check_bytes8(start, value, bytes);
 
 	value64 = value | value << 8 | value << 16 | value << 24;
-	value64 = value64 | value64 << 32;
+	value64 = (value64 & 0xffffffff) | value64 << 32;
 	prefix = 8 - ((unsigned long)start) % 8;
 
 	if (prefix) {
@@ -1854,7 +1854,7 @@ redo:
 
 	new.frozen = 0;
 
-	if (!new.inuse && n->nr_partial < s->min_partial)
+	if (!new.inuse && n->nr_partial > s->min_partial)
 		m = M_FREE;
 	else if (new.freelist) {
 		m = M_PARTIAL;
@@ -2377,7 +2377,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		 */
 		if (unlikely(!prior)) {
 			remove_full(s, page);
-			add_partial(n, page, 0);
+			add_partial(n, page, 1);
 			stat(s, FREE_ADD_PARTIAL);
 		}
 	}
@@ -2387,11 +2387,13 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 slab_empty:
 	if (prior) {
 		/*
-		 * Slab still on the partial list.
+		 * Slab on the partial list.
 		 */
 		remove_partial(n, page);
 		stat(s, FREE_REMOVE_PARTIAL);
-	}
+	} else
+		/* Slab must be on the full list */
+		remove_full(s, page);
 
 	spin_unlock_irqrestore(&n->list_lock, flags);
 	stat(s, FREE_SLAB);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 464621d18eb..5016f19e166 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -725,9 +725,10 @@ static void free_unmap_vmap_area_addr(unsigned long addr)
 #define VMAP_BBMAP_BITS_MIN	(VMAP_MAX_ALLOC*2)
 #define VMAP_MIN(x, y)		((x) < (y) ? (x) : (y)) /* can't use min() */
 #define VMAP_MAX(x, y)		((x) > (y) ? (x) : (y)) /* can't use max() */
-#define VMAP_BBMAP_BITS		VMAP_MIN(VMAP_BBMAP_BITS_MAX,		\
-					VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
-						VMALLOC_PAGES / NR_CPUS / 16))
+#define VMAP_BBMAP_BITS		\
+		VMAP_MIN(VMAP_BBMAP_BITS_MAX,	\
+		VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
+			VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))
 
 #define VMAP_BLOCK_SIZE		(VMAP_BBMAP_BITS * PAGE_SIZE)
 
@@ -2139,6 +2140,14 @@ struct vm_struct *alloc_vm_area(size_t size)
 		return NULL;
 	}
 
+	/*
+	 * If the allocated address space is passed to a hypercall
+	 * before being used then we cannot rely on a page fault to
+	 * trigger an update of the page tables.  So sync all the page
+	 * tables here.
+	 */
+	vmalloc_sync_all();
+
 	return area;
 }
 EXPORT_SYMBOL_GPL(alloc_vm_area);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7ef69124fa3..b55699cd906 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -105,7 +105,6 @@ struct scan_control {
 
 	/* Which cgroup do we reclaim from */
 	struct mem_cgroup *mem_cgroup;
-	struct memcg_scanrecord *memcg_record;
 
 	/*
 	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
@@ -1349,8 +1348,6 @@ putback_lru_pages(struct zone *zone, struct scan_control *sc,
 			int file = is_file_lru(lru);
 			int numpages = hpage_nr_pages(page);
 			reclaim_stat->recent_rotated[file] += numpages;
-			if (!scanning_global_lru(sc))
-				sc->memcg_record->nr_rotated[file] += numpages;
 		}
 		if (!pagevec_add(&pvec, page)) {
 			spin_unlock_irq(&zone->lru_lock);
@@ -1394,10 +1391,6 @@ static noinline_for_stack void update_isolated_counts(struct zone *zone,
 
 	reclaim_stat->recent_scanned[0] += *nr_anon;
 	reclaim_stat->recent_scanned[1] += *nr_file;
-	if (!scanning_global_lru(sc)) {
-		sc->memcg_record->nr_scanned[0] += *nr_anon;
-		sc->memcg_record->nr_scanned[1] += *nr_file;
-	}
 }
 
 /*
@@ -1511,9 +1504,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 		nr_reclaimed += shrink_page_list(&page_list, zone, sc);
 	}
 
-	if (!scanning_global_lru(sc))
-		sc->memcg_record->nr_freed[file] += nr_reclaimed;
-
 	local_irq_disable();
 	if (current_is_kswapd())
 		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
@@ -1613,8 +1603,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	}
 
 	reclaim_stat->recent_scanned[file] += nr_taken;
-	if (!scanning_global_lru(sc))
-		sc->memcg_record->nr_scanned[file] += nr_taken;
 
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	if (file)
@@ -1666,8 +1654,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * get_scan_ratio.
 	 */
 	reclaim_stat->recent_rotated[file] += nr_rotated;
-	if (!scanning_global_lru(sc))
-		sc->memcg_record->nr_rotated[file] += nr_rotated;
 
 	move_active_pages_to_lru(zone, &l_active,
 						LRU_ACTIVE + file * LRU_FILE);
@@ -1808,23 +1794,15 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	u64 fraction[2], denominator;
 	enum lru_list l;
 	int noswap = 0;
-	int force_scan = 0;
+	bool force_scan = false;
 	unsigned long nr_force_scan[2];
 
-
-	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
-	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
-
-	if (((anon + file) >> priority) < SWAP_CLUSTER_MAX) {
-		/* kswapd does zone balancing and need to scan this zone */
-		if (scanning_global_lru(sc) && current_is_kswapd())
-			force_scan = 1;
-		/* memcg may have small limit and need to avoid priority drop */
-		if (!scanning_global_lru(sc))
-			force_scan = 1;
-	}
+	/* kswapd does zone balancing and needs to scan this zone */
+	if (scanning_global_lru(sc) && current_is_kswapd())
+		force_scan = true;
+	/* memcg may have small limit and need to avoid priority drop */
+	if (!scanning_global_lru(sc))
+		force_scan = true;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (!sc->may_swap || (nr_swap_pages <= 0)) {
@@ -1837,6 +1815,11 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 		goto out;
 	}
 
+	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
+	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+
 	if (scanning_global_lru(sc)) {
 		free  = zone_page_state(zone, NR_FREE_PAGES);
 		/* If we have very few page cache pages,
@@ -2268,10 +2251,9 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
 unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
-					gfp_t gfp_mask, bool noswap,
-					struct zone *zone,
-					struct memcg_scanrecord *rec,
-					unsigned long *scanned)
+						gfp_t gfp_mask, bool noswap,
+						struct zone *zone,
+						unsigned long *nr_scanned)
 {
 	struct scan_control sc = {
 		.nr_scanned = 0,
@@ -2281,9 +2263,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 		.may_swap = !noswap,
 		.order = 0,
 		.mem_cgroup = mem,
-		.memcg_record = rec,
 	};
-	unsigned long start, end;
 
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -2292,7 +2272,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 						      sc.may_writepage,
 						      sc.gfp_mask);
 
-	start = sched_clock();
 	/*
 	 * NOTE: Although we can get the priority field, using it
 	 * here is not a good idea, since it limits the pages we can scan.
@@ -2301,25 +2280,19 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 	 * the priority and make it zero.
 	 */
 	shrink_zone(0, zone, &sc);
-	end = sched_clock();
-
-	if (rec)
-		rec->elapsed += end - start;
-	*scanned = sc.nr_scanned;
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
+	*nr_scanned = sc.nr_scanned;
 	return sc.nr_reclaimed;
 }
 
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 					   gfp_t gfp_mask,
-					   bool noswap,
-					   struct memcg_scanrecord *rec)
+					   bool noswap)
 {
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;
-	unsigned long start, end;
 	int nid;
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
@@ -2328,7 +2301,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.order = 0,
 		.mem_cgroup = mem_cont,
-		.memcg_record = rec,
 		.nodemask = NULL, /* we don't care the placement */
 		.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
@@ -2337,7 +2309,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.gfp_mask = sc.gfp_mask,
 	};
 
-	start = sched_clock();
 	/*
 	 * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
 	 * take care of from where we get pages. So the node where we start the
@@ -2352,9 +2323,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 					    sc.gfp_mask);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
-	end = sched_clock();
-	if (rec)
-		rec->elapsed += end - start;
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -2529,6 +2497,9 @@ loop_again:
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;
+			} else {
+				/* If balanced, clear the congested flag */
+				zone_clear_flag(zone, ZONE_CONGESTED);
 			}
 		}
 		if (i < 0)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 20c18b7694b..d52b13d28e8 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -659,7 +659,7 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 }
 #endif
 
-#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS)
+#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA)
 #ifdef CONFIG_ZONE_DMA
 #define TEXT_FOR_DMA(xx) xx "_dma",
 #else
@@ -788,7 +788,7 @@ const char * const vmstat_text[] = {
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };
-#endif /* CONFIG_PROC_FS || CONFIG_SYSFS */
+#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */
 
 
 #ifdef CONFIG_PROC_FS