Merge branch 'master' into for-next

Conflicts:
	fs/exofs/inode.c

6 files changed, 333 insertions, 280 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f9fd3dd3916b..08d357522e78 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
+#include <trace/events/writeback.h>
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
@@ -49,8 +50,6 @@ static struct timer_list sync_supers_timer;
 static int bdi_sync_supers(void *);
 static void sync_supers_timer_fn(unsigned long);
 
-static void bdi_add_default_flusher_task(struct backing_dev_info *bdi);
-
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -65,28 +64,21 @@ static void bdi_debug_init(void)
 static int bdi_debug_stats_show(struct seq_file *m, void *v)
 {
 	struct backing_dev_info *bdi = m->private;
-	struct bdi_writeback *wb;
+	struct bdi_writeback *wb = &bdi->wb;
 	unsigned long background_thresh;
 	unsigned long dirty_thresh;
 	unsigned long bdi_thresh;
 	unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
 	struct inode *inode;
 
-	/*
-	 * inode lock is enough here, the bdi->wb_list is protected by
-	 * RCU on the reader side
-	 */
 	nr_wb = nr_dirty = nr_io = nr_more_io = 0;
 	spin_lock(&inode_lock);
-	list_for_each_entry(wb, &bdi->wb_list, list) {
-		nr_wb++;
-		list_for_each_entry(inode, &wb->b_dirty, i_list)
-			nr_dirty++;
-		list_for_each_entry(inode, &wb->b_io, i_list)
-			nr_io++;
-		list_for_each_entry(inode, &wb->b_more_io, i_list)
-			nr_more_io++;
-	}
+	list_for_each_entry(inode, &wb->b_dirty, i_list)
+		nr_dirty++;
+	list_for_each_entry(inode, &wb->b_io, i_list)
+		nr_io++;
+	list_for_each_entry(inode, &wb->b_more_io, i_list)
+		nr_more_io++;
 	spin_unlock(&inode_lock);
 
 	get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
@@ -98,19 +90,16 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   "BdiDirtyThresh:   %8lu kB\n"
 		   "DirtyThresh:      %8lu kB\n"
 		   "BackgroundThresh: %8lu kB\n"
-		   "WritebackThreads: %8lu\n"
 		   "b_dirty:          %8lu\n"
 		   "b_io:             %8lu\n"
 		   "b_more_io:        %8lu\n"
 		   "bdi_list:         %8u\n"
-		   "state:            %8lx\n"
-		   "wb_list:          %8u\n",
+		   "state:            %8lx\n",
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
 		   (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
 		   K(bdi_thresh), K(dirty_thresh),
-		   K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io,
-		   !list_empty(&bdi->bdi_list), bdi->state,
-		   !list_empty(&bdi->wb_list));
+		   K(background_thresh), nr_dirty, nr_io, nr_more_io,
+		   !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 
 	return 0;
@@ -247,7 +236,6 @@ static int __init default_bdi_init(void)
 	sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
 	BUG_ON(IS_ERR(sync_supers_tsk));
 
-	init_timer(&sync_supers_timer);
 	setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
 	bdi_arm_supers_timer();
 
@@ -259,77 +247,6 @@ static int __init default_bdi_init(void)
 }
 subsys_initcall(default_bdi_init);
 
-static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
-{
-	memset(wb, 0, sizeof(*wb));
-
-	wb->bdi = bdi;
-	wb->last_old_flush = jiffies;
-	INIT_LIST_HEAD(&wb->b_dirty);
-	INIT_LIST_HEAD(&wb->b_io);
-	INIT_LIST_HEAD(&wb->b_more_io);
-}
-
-static void bdi_task_init(struct backing_dev_info *bdi,
-			  struct bdi_writeback *wb)
-{
-	struct task_struct *tsk = current;
-
-	spin_lock(&bdi->wb_lock);
-	list_add_tail_rcu(&wb->list, &bdi->wb_list);
-	spin_unlock(&bdi->wb_lock);
-
-	tsk->flags |= PF_FLUSHER | PF_SWAPWRITE;
-	set_freezable();
-
-	/*
-	 * Our parent may run at a different priority, just set us to normal
-	 */
-	set_user_nice(tsk, 0);
-}
-
-static int bdi_start_fn(void *ptr)
-{
-	struct bdi_writeback *wb = ptr;
-	struct backing_dev_info *bdi = wb->bdi;
-	int ret;
-
-	/*
-	 * Add us to the active bdi_list
-	 */
-	spin_lock_bh(&bdi_lock);
-	list_add_rcu(&bdi->bdi_list, &bdi_list);
-	spin_unlock_bh(&bdi_lock);
-
-	bdi_task_init(bdi, wb);
-
-	/*
-	 * 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);
-
-	ret = bdi_writeback_task(wb);
-
-	/*
-	 * Remove us from the list
-	 */
-	spin_lock(&bdi->wb_lock);
-	list_del_rcu(&wb->list);
-	spin_unlock(&bdi->wb_lock);
-
-	/*
-	 * Flush any work that raced with us exiting. No new work
-	 * will be added, since this bdi isn't discoverable anymore.
-	 */
-	if (!list_empty(&bdi->work_list))
-		wb_do_writeback(wb, 1);
-
-	wb->task = NULL;
-	return ret;
-}
-
 int bdi_has_dirty_io(struct backing_dev_info *bdi)
 {
 	return wb_has_dirty_io(&bdi->wb);
@@ -348,10 +265,10 @@ static void bdi_flush_io(struct backing_dev_info *bdi)
 }
 
 /*
- * kupdated() used to do this. We cannot do it from the bdi_forker_task()
+ * kupdated() used to do this. We cannot do it from the bdi_forker_thread()
  * or we risk deadlocking on ->s_umount. The longer term solution would be
  * to implement sync_supers_bdi() or similar and simply do it from the
- * bdi writeback tasks individually.
+ * bdi writeback thread individually.
  */
 static int bdi_sync_supers(void *unused)
 {
@@ -387,144 +304,198 @@ static void sync_supers_timer_fn(unsigned long unused)
 	bdi_arm_supers_timer();
 }
 
-static int bdi_forker_task(void *ptr)
+static void wakeup_timer_fn(unsigned long data)
+{
+	struct backing_dev_info *bdi = (struct backing_dev_info *)data;
+
+	spin_lock_bh(&bdi->wb_lock);
+	if (bdi->wb.task) {
+		trace_writeback_wake_thread(bdi);
+		wake_up_process(bdi->wb.task);
+	} else {
+		/*
+		 * When bdi tasks are inactive for long time, they are killed.
+		 * In this case we have to wake-up the forker thread which
+		 * should create and run the bdi thread.
+		 */
+		trace_writeback_wake_forker_thread(bdi);
+		wake_up_process(default_backing_dev_info.wb.task);
+	}
+	spin_unlock_bh(&bdi->wb_lock);
+}
+
+/*
+ * This function is used when the first inode for this bdi is marked dirty. It
+ * wakes-up the corresponding bdi thread which should then take care of the
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * 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.
+ */
+void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
+{
+	unsigned long timeout;
+
+	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+	mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout);
+}
+
+/*
+ * Calculate the longest interval (jiffies) bdi threads are allowed to be
+ * inactive.
+ */
+static unsigned long bdi_longest_inactive(void)
+{
+	unsigned long interval;
+
+	interval = msecs_to_jiffies(dirty_writeback_interval * 10);
+	return max(5UL * 60 * HZ, interval);
+}
+
+static int bdi_forker_thread(void *ptr)
 {
 	struct bdi_writeback *me = ptr;
 
-	bdi_task_init(me->bdi, me);
+	current->flags |= PF_FLUSHER | PF_SWAPWRITE;
+	set_freezable();
+
+	/*
+	 * Our parent may run at a different priority, just set us to normal
+	 */
+	set_user_nice(current, 0);
 
 	for (;;) {
-		struct backing_dev_info *bdi, *tmp;
-		struct bdi_writeback *wb;
+		struct task_struct *task = NULL;
+		struct backing_dev_info *bdi;
+		enum {
+			NO_ACTION,   /* Nothing to do */
+			FORK_THREAD, /* Fork bdi thread */
+			KILL_THREAD, /* Kill inactive bdi thread */
+		} action = NO_ACTION;
 
 		/*
 		 * Temporary measure, we want to make sure we don't see
 		 * dirty data on the default backing_dev_info
 		 */
-		if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
+		if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) {
+			del_timer(&me->wakeup_timer);
 			wb_do_writeback(me, 0);
+		}
 
 		spin_lock_bh(&bdi_lock);
+		set_current_state(TASK_INTERRUPTIBLE);
 
-		/*
-		 * Check if any existing bdi's have dirty data without
-		 * a thread registered. If so, set that up.
-		 */
-		list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) {
-			if (bdi->wb.task)
-				continue;
-			if (list_empty(&bdi->work_list) &&
-			    !bdi_has_dirty_io(bdi))
+		list_for_each_entry(bdi, &bdi_list, bdi_list) {
+			bool have_dirty_io;
+
+			if (!bdi_cap_writeback_dirty(bdi) ||
+			     bdi_cap_flush_forker(bdi))
 				continue;
 
-			bdi_add_default_flusher_task(bdi);
-		}
+			WARN(!test_bit(BDI_registered, &bdi->state),
+			     "bdi %p/%s is not registered!\n", bdi, bdi->name);
 
-		set_current_state(TASK_INTERRUPTIBLE);
+			have_dirty_io = !list_empty(&bdi->work_list) ||
+					wb_has_dirty_io(&bdi->wb);
 
-		if (list_empty(&bdi_pending_list)) {
-			unsigned long wait;
+			/*
+			 * If the bdi has work to do, but the thread does not
+			 * exist - create it.
+			 */
+			if (!bdi->wb.task && have_dirty_io) {
+				/*
+				 * Set the pending bit - if someone will try to
+				 * unregister this bdi - it'll wait on this bit.
+				 */
+				set_bit(BDI_pending, &bdi->state);
+				action = FORK_THREAD;
+				break;
+			}
+
+			spin_lock(&bdi->wb_lock);
+
+			/*
+			 * If there is no work to do and the bdi thread was
+			 * inactive long enough - kill it. The wb_lock is taken
+			 * to make sure no-one adds more work to this bdi and
+			 * wakes the bdi thread up.
+			 */
+			if (bdi->wb.task && !have_dirty_io &&
+			    time_after(jiffies, bdi->wb.last_active +
+						bdi_longest_inactive())) {
+				task = bdi->wb.task;
+				bdi->wb.task = NULL;
+				spin_unlock(&bdi->wb_lock);
+				set_bit(BDI_pending, &bdi->state);
+				action = KILL_THREAD;
+				break;
+			}
+			spin_unlock(&bdi->wb_lock);
+		}
+		spin_unlock_bh(&bdi_lock);
 
-			spin_unlock_bh(&bdi_lock);
-			wait = msecs_to_jiffies(dirty_writeback_interval * 10);
-			if (wait)
-				schedule_timeout(wait);
+		/* Keep working if default bdi still has things to do */
+		if (!list_empty(&me->bdi->work_list))
+			__set_current_state(TASK_RUNNING);
+
+		switch (action) {
+		case FORK_THREAD:
+			__set_current_state(TASK_RUNNING);
+			task = kthread_run(bdi_writeback_thread, &bdi->wb, "flush-%s",
+					   dev_name(bdi->dev));
+			if (IS_ERR(task)) {
+				/*
+				 * If thread creation fails, force writeout of
+				 * the bdi from the thread.
+				 */
+				bdi_flush_io(bdi);
+			} else {
+				/*
+				 * The spinlock makes sure we do not lose
+				 * wake-ups when racing with 'bdi_queue_work()'.
+				 */
+				spin_lock_bh(&bdi->wb_lock);
+				bdi->wb.task = task;
+				spin_unlock_bh(&bdi->wb_lock);
+			}
+			break;
+
+		case KILL_THREAD:
+			__set_current_state(TASK_RUNNING);
+			kthread_stop(task);
+			break;
+
+		case NO_ACTION:
+			if (!wb_has_dirty_io(me) || !dirty_writeback_interval)
+				/*
+				 * There are no dirty data. The only thing we
+				 * should now care about is checking for
+				 * inactive bdi threads and killing them. Thus,
+				 * let's sleep for longer time, save energy and
+				 * be friendly for battery-driven devices.
+				 */
+				schedule_timeout(bdi_longest_inactive());
 			else
-				schedule();
+				schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
 			try_to_freeze();
+			/* Back to the main loop */
 			continue;
 		}
 
-		__set_current_state(TASK_RUNNING);
-
-		/*
-		 * This is our real job - check for pending entries in
-		 * bdi_pending_list, and create the tasks that got added
-		 */
-		bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
-				 bdi_list);
-		list_del_init(&bdi->bdi_list);
-		spin_unlock_bh(&bdi_lock);
-
-		wb = &bdi->wb;
-		wb->task = kthread_run(bdi_start_fn, wb, "flush-%s",
-					dev_name(bdi->dev));
 		/*
-		 * If task creation fails, then readd the bdi to
-		 * the pending list and force writeout of the bdi
-		 * from this forker thread. That will free some memory
-		 * and we can try again.
+		 * Clear pending bit and wakeup anybody waiting to tear us down.
 		 */
-		if (IS_ERR(wb->task)) {
-			wb->task = NULL;
-
-			/*
-			 * Add this 'bdi' to the back, so we get
-			 * a chance to flush other bdi's to free
-			 * memory.
-			 */
-			spin_lock_bh(&bdi_lock);
-			list_add_tail(&bdi->bdi_list, &bdi_pending_list);
-			spin_unlock_bh(&bdi_lock);
-
-			bdi_flush_io(bdi);
-		}
+		clear_bit(BDI_pending, &bdi->state);
+		smp_mb__after_clear_bit();
+		wake_up_bit(&bdi->state, BDI_pending);
 	}
 
 	return 0;
 }
 
-static void bdi_add_to_pending(struct rcu_head *head)
-{
-	struct backing_dev_info *bdi;
-
-	bdi = container_of(head, struct backing_dev_info, rcu_head);
-	INIT_LIST_HEAD(&bdi->bdi_list);
-
-	spin_lock(&bdi_lock);
-	list_add_tail(&bdi->bdi_list, &bdi_pending_list);
-	spin_unlock(&bdi_lock);
-
-	/*
-	 * We are now on the pending list, wake up bdi_forker_task()
-	 * to finish the job and add us back to the active bdi_list
-	 */
-	wake_up_process(default_backing_dev_info.wb.task);
-}
-
-/*
- * Add the default flusher task that gets created for any bdi
- * that has dirty data pending writeout
- */
-void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
-{
-	if (!bdi_cap_writeback_dirty(bdi))
-		return;
-
-	if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) {
-		printk(KERN_ERR "bdi %p/%s is not registered!\n",
-							bdi, bdi->name);
-		return;
-	}
-
-	/*
-	 * Check with the helper whether to proceed adding a task. Will only
-	 * abort if we two or more simultanous calls to
-	 * bdi_add_default_flusher_task() occured, further additions will block
-	 * waiting for previous additions to finish.
-	 */
-	if (!test_and_set_bit(BDI_pending, &bdi->state)) {
-		list_del_rcu(&bdi->bdi_list);
-
-		/*
-		 * We must wait for the current RCU period to end before
-		 * moving to the pending list. So schedule that operation
-		 * from an RCU callback.
-		 */
-		call_rcu(&bdi->rcu_head, bdi_add_to_pending);
-	}
-}
-
 /*
  * Remove bdi from bdi_list, and ensure that it is no longer visible
  */
@@ -541,23 +512,16 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...)
 {
 	va_list args;
-	int ret = 0;
 	struct device *dev;
 
 	if (bdi->dev)	/* The driver needs to use separate queues per device */
-		goto exit;
+		return 0;
 
 	va_start(args, fmt);
 	dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
 	va_end(args);
-	if (IS_ERR(dev)) {
-		ret = PTR_ERR(dev);
-		goto exit;
-	}
-
-	spin_lock_bh(&bdi_lock);
-	list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
-	spin_unlock_bh(&bdi_lock);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
 
 	bdi->dev = dev;
 
@@ -569,21 +533,21 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 	if (bdi_cap_flush_forker(bdi)) {
 		struct bdi_writeback *wb = &bdi->wb;
 
-		wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s",
+		wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s",
 						dev_name(dev));
-		if (IS_ERR(wb->task)) {
-			wb->task = NULL;
-			ret = -ENOMEM;
-
-			bdi_remove_from_list(bdi);
-			goto exit;
-		}
+		if (IS_ERR(wb->task))
+			return PTR_ERR(wb->task);
 	}
 
 	bdi_debug_register(bdi, dev_name(dev));
 	set_bit(BDI_registered, &bdi->state);
-exit:
-	return ret;
+
+	spin_lock_bh(&bdi_lock);
+	list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
+	spin_unlock_bh(&bdi_lock);
+
+	trace_writeback_bdi_register(bdi);
+	return 0;
 }
 EXPORT_SYMBOL(bdi_register);
 
@@ -598,31 +562,29 @@ EXPORT_SYMBOL(bdi_register_dev);
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
-	struct bdi_writeback *wb;
-
 	if (!bdi_cap_writeback_dirty(bdi))
 		return;
 
 	/*
-	 * If setup is pending, wait for that to complete first
+	 * Make sure nobody finds us on the bdi_list anymore
 	 */
-	wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
-			TASK_UNINTERRUPTIBLE);
+	bdi_remove_from_list(bdi);
 
 	/*
-	 * Make sure nobody finds us on the bdi_list anymore
+	 * If setup is pending, wait for that to complete first
 	 */
-	bdi_remove_from_list(bdi);
+	wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
+			TASK_UNINTERRUPTIBLE);
 
 	/*
-	 * Finally, kill the kernel threads. We don't need to be RCU
+	 * Finally, kill the kernel thread. We don't need to be RCU
 	 * safe anymore, since the bdi is gone from visibility. Force
 	 * unfreeze of the thread before calling kthread_stop(), otherwise
 	 * it would never exet if it is currently stuck in the refrigerator.
 	 */
-	list_for_each_entry(wb, &bdi->wb_list, list) {
-		thaw_process(wb->task);
-		kthread_stop(wb->task);
+	if (bdi->wb.task) {
+		thaw_process(bdi->wb.task);
+		kthread_stop(bdi->wb.task);
 	}
 }
 
@@ -644,7 +606,9 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
+		del_timer_sync(&bdi->wb.wakeup_timer);
 
 		if (!bdi_cap_flush_forker(bdi))
 			bdi_wb_shutdown(bdi);
@@ -655,6 +619,18 @@ void bdi_unregister(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_unregister);
 
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+	memset(wb, 0, sizeof(*wb));
+
+	wb->bdi = bdi;
+	wb->last_old_flush = jiffies;
+	INIT_LIST_HEAD(&wb->b_dirty);
+	INIT_LIST_HEAD(&wb->b_io);
+	INIT_LIST_HEAD(&wb->b_more_io);
+	setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
+}
+
 int bdi_init(struct backing_dev_info *bdi)
 {
 	int i, err;
@@ -666,7 +642,6 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->max_prop_frac = PROP_FRAC_BASE;
 	spin_lock_init(&bdi->wb_lock);
 	INIT_LIST_HEAD(&bdi->bdi_list);
-	INIT_LIST_HEAD(&bdi->wb_list);
 	INIT_LIST_HEAD(&bdi->work_list);
 
 	bdi_wb_init(&bdi->wb, bdi);
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 2c0d032ac898..bd9bc214091b 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -211,6 +211,9 @@ static signed long jiffies_scan_wait;
 static int kmemleak_stack_scan = 1;
 /* protects the memory scanning, parameters and debug/kmemleak file access */
 static DEFINE_MUTEX(scan_mutex);
+/* setting kmemleak=on, will set this var, skipping the disable */
+static int kmemleak_skip_disable;
+
 
 /*
  * Early object allocation/freeing logging. Kmemleak is initialized after the
@@ -398,7 +401,9 @@ static struct kmemleak_object *lookup_object(unsigned long ptr, int alias)
 		object = prio_tree_entry(node, struct kmemleak_object,
 					 tree_node);
 		if (!alias && object->pointer != ptr) {
-			kmemleak_warn("Found object by alias");
+			pr_warning("Found object by alias at 0x%08lx\n", ptr);
+			dump_stack();
+			dump_object_info(object);
 			object = NULL;
 		}
 	} else
@@ -695,7 +700,7 @@ static void paint_ptr(unsigned long ptr, int color)
 }
 
 /*
- * Make a object permanently as gray-colored so that it can no longer be
+ * Mark an object permanently as gray-colored so that it can no longer be
  * reported as a leak. This is used in general to mark a false positive.
  */
 static void make_gray_object(unsigned long ptr)
@@ -838,10 +843,19 @@ out:
 	rcu_read_unlock();
 }
 
-/*
- * Memory allocation function callback. This function is called from the
- * kernel allocators when a new block is allocated (kmem_cache_alloc, kmalloc,
- * vmalloc etc.).
+/**
+ * kmemleak_alloc - register a newly allocated object
+ * @ptr:	pointer to beginning of the object
+ * @size:	size of the object
+ * @min_count:	minimum number of references to this object. If during memory
+ *		scanning a number of references less than @min_count is found,
+ *		the object is reported as a memory leak. If @min_count is 0,
+ *		the object is never reported as a leak. If @min_count is -1,
+ *		the object is ignored (not scanned and not reported as a leak)
+ * @gfp:	kmalloc() flags used for kmemleak internal memory allocations
+ *
+ * This function is called from the kernel allocators when a new object
+ * (memory block) is allocated (kmem_cache_alloc, kmalloc, vmalloc etc.).
  */
 void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			  gfp_t gfp)
@@ -855,9 +869,12 @@ void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count,
 }
 EXPORT_SYMBOL_GPL(kmemleak_alloc);
 
-/*
- * Memory freeing function callback. This function is called from the kernel
- * allocators when a block is freed (kmem_cache_free, kfree, vfree etc.).
+/**
+ * kmemleak_free - unregister a previously registered object
+ * @ptr:	pointer to beginning of the object
+ *
+ * This function is called from the kernel allocators when an object (memory
+ * block) is freed (kmem_cache_free, kfree, vfree etc.).
  */
 void __ref kmemleak_free(const void *ptr)
 {
@@ -870,9 +887,14 @@ void __ref kmemleak_free(const void *ptr)
 }
 EXPORT_SYMBOL_GPL(kmemleak_free);
 
-/*
- * Partial memory freeing function callback. This function is usually called
- * from bootmem allocator when (part of) a memory block is freed.
+/**
+ * kmemleak_free_part - partially unregister a previously registered object
+ * @ptr:	pointer to the beginning or inside the object. This also
+ *		represents the start of the range to be freed
+ * @size:	size to be unregistered
+ *
+ * This function is called when only a part of a memory block is freed
+ * (usually from the bootmem allocator).
  */
 void __ref kmemleak_free_part(const void *ptr, size_t size)
 {
@@ -885,9 +907,12 @@ void __ref kmemleak_free_part(const void *ptr, size_t size)
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_part);
 
-/*
- * Mark an already allocated memory block as a false positive. This will cause
- * the block to no longer be reported as leak and always be scanned.
+/**
+ * kmemleak_not_leak - mark an allocated object as false positive
+ * @ptr:	pointer to beginning of the object
+ *
+ * Calling this function on an object will cause the memory block to no longer
+ * be reported as leak and always be scanned.
  */
 void __ref kmemleak_not_leak(const void *ptr)
 {
@@ -900,10 +925,14 @@ void __ref kmemleak_not_leak(const void *ptr)
 }
 EXPORT_SYMBOL(kmemleak_not_leak);
 
-/*
- * Ignore a memory block. This is usually done when it is known that the
- * corresponding block is not a leak and does not contain any references to
- * other allocated memory blocks.
+/**
+ * kmemleak_ignore - ignore an allocated object
+ * @ptr:	pointer to beginning of the object
+ *
+ * Calling this function on an object will cause the memory block to be
+ * ignored (not scanned and not reported as a leak). This is usually done when
+ * it is known that the corresponding block is not a leak and does not contain
+ * any references to other allocated memory blocks.
  */
 void __ref kmemleak_ignore(const void *ptr)
 {
@@ -916,8 +945,16 @@ void __ref kmemleak_ignore(const void *ptr)
 }
 EXPORT_SYMBOL(kmemleak_ignore);
 
-/*
- * Limit the range to be scanned in an allocated memory block.
+/**
+ * kmemleak_scan_area - limit the range to be scanned in an allocated object
+ * @ptr:	pointer to beginning or inside the object. This also
+ *		represents the start of the scan area
+ * @size:	size of the scan area
+ * @gfp:	kmalloc() flags used for kmemleak internal memory allocations
+ *
+ * This function is used when it is known that only certain parts of an object
+ * contain references to other objects. Kmemleak will only scan these areas
+ * reducing the number false negatives.
  */
 void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
 {
@@ -930,8 +967,14 @@ void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
 }
 EXPORT_SYMBOL(kmemleak_scan_area);
 
-/*
- * Inform kmemleak not to scan the given memory block.
+/**
+ * kmemleak_no_scan - do not scan an allocated object
+ * @ptr:	pointer to beginning of the object
+ *
+ * This function notifies kmemleak not to scan the given memory block. Useful
+ * in situations where it is known that the given object does not contain any
+ * references to other objects. Kmemleak will not scan such objects reducing
+ * the number of false negatives.
  */
 void __ref kmemleak_no_scan(const void *ptr)
 {
@@ -1602,7 +1645,9 @@ static int kmemleak_boot_config(char *str)
 		return -EINVAL;
 	if (strcmp(str, "off") == 0)
 		kmemleak_disable();
-	else if (strcmp(str, "on") != 0)
+	else if (strcmp(str, "on") == 0)
+		kmemleak_skip_disable = 1;
+	else
 		return -EINVAL;
 	return 0;
 }
@@ -1616,6 +1661,13 @@ void __init kmemleak_init(void)
 	int i;
 	unsigned long flags;
 
+#ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
+	if (!kmemleak_skip_disable) {
+		kmemleak_disable();
+		return;
+	}
+#endif
+
 	jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
 	jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index df8202ebc7b8..0c6258bd1ba3 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -34,6 +34,7 @@
 #include <linux/syscalls.h>
 #include <linux/buffer_head.h>
 #include <linux/pagevec.h>
+#include <trace/events/writeback.h>
 
 /*
  * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
@@ -535,11 +536,13 @@ static void balance_dirty_pages(struct address_space *mapping,
 		 * threshold otherwise wait until the disk writes catch
 		 * up.
 		 */
+		trace_wbc_balance_dirty_start(&wbc, bdi);
 		if (bdi_nr_reclaimable > bdi_thresh) {
 			writeback_inodes_wb(&bdi->wb, &wbc);
 			pages_written += write_chunk - wbc.nr_to_write;
 			get_dirty_limits(&background_thresh, &dirty_thresh,
 				       &bdi_thresh, bdi);
+			trace_wbc_balance_dirty_written(&wbc, bdi);
 		}
 
 		/*
@@ -565,6 +568,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 		if (pages_written >= write_chunk)
 			break;		/* We've done our duty */
 
+		trace_wbc_balance_dirty_wait(&wbc, bdi);
 		__set_current_state(TASK_INTERRUPTIBLE);
 		io_schedule_timeout(pause);
 
@@ -962,6 +966,7 @@ continue_unlock:
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
+			trace_wbc_writepage(wbc, mapping->backing_dev_info);
 			ret = (*writepage)(page, wbc, data);
 			if (unlikely(ret)) {
 				if (ret == AOP_WRITEPAGE_ACTIVATE) {
diff --git a/mm/page_io.c b/mm/page_io.c
index 31a3b962230a..2dee975bf469 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -106,7 +106,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		goto out;
 	}
 	if (wbc->sync_mode == WB_SYNC_ALL)
-		rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG);
+		rw |= REQ_SYNC | REQ_UNPLUG;
 	count_vm_event(PSWPOUT);
 	set_page_writeback(page);
 	unlock_page(page);
diff --git a/mm/shmem.c b/mm/shmem.c
index 566f9a481e64..dfaa0f4e9789 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -766,6 +766,10 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
 	loff_t newsize = attr->ia_size;
 	int error;
 
+	error = inode_change_ok(inode, attr);
+	if (error)
+		return error;
+
 	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)
 					&& newsize != inode->i_size) {
 		struct page *page = NULL;
@@ -800,25 +804,22 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
 			}
 		}
 
-		error = simple_setsize(inode, newsize);
+		/* XXX(truncate): truncate_setsize should be called last */
+		truncate_setsize(inode, newsize);
 		if (page)
 			page_cache_release(page);
-		if (error)
-			return error;
 		shmem_truncate_range(inode, newsize, (loff_t)-1);
 	}
 
-	error = inode_change_ok(inode, attr);
-	if (!error)
-		generic_setattr(inode, attr);
+	setattr_copy(inode, attr);
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	if (!error && (attr->ia_valid & ATTR_MODE))
+	if (attr->ia_valid & ATTR_MODE)
 		error = generic_acl_chmod(inode);
 #endif
 	return error;
 }
 
-static void shmem_delete_inode(struct inode *inode)
+static void shmem_evict_inode(struct inode *inode)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
 
@@ -835,7 +836,7 @@ static void shmem_delete_inode(struct inode *inode)
 	}
 	BUG_ON(inode->i_blocks);
 	shmem_free_inode(inode->i_sb);
-	clear_inode(inode);
+	end_writeback(inode);
 }
 
 static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir)
@@ -932,7 +933,7 @@ found:
 
 	/*
 	 * Move _head_ to start search for next from here.
-	 * But be careful: shmem_delete_inode checks list_empty without taking
+	 * But be careful: shmem_evict_inode checks list_empty without taking
 	 * mutex, and there's an instant in list_move_tail when info->swaplist
 	 * would appear empty, if it were the only one on shmem_swaplist.  We
 	 * could avoid doing it if inode NULL; or use this minor optimization.
@@ -2518,7 +2519,7 @@ static const struct super_operations shmem_ops = {
 	.remount_fs	= shmem_remount_fs,
 	.show_options	= shmem_show_options,
 #endif
-	.delete_inode	= shmem_delete_inode,
+	.evict_inode	= shmem_evict_inode,
 	.drop_inode	= generic_delete_inode,
 	.put_super	= shmem_put_super,
 };
diff --git a/mm/truncate.c b/mm/truncate.c
index 937571b8b233..ba887bff48c5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -541,28 +541,48 @@ void truncate_pagecache(struct inode *inode, loff_t old, loff_t new)
 EXPORT_SYMBOL(truncate_pagecache);
 
 /**
+ * truncate_setsize - update inode and pagecache for a new file size
+ * @inode: inode
+ * @newsize: new file size
+ *
+ * truncate_setsize updastes i_size update and performs pagecache
+ * truncation (if necessary) for a file size updates. It will be
+ * typically be called from the filesystem's setattr function when
+ * ATTR_SIZE is passed in.
+ *
+ * Must be called with inode_mutex held and after all filesystem
+ * specific block truncation has been performed.
+ */
+void truncate_setsize(struct inode *inode, loff_t newsize)
+{
+	loff_t oldsize;
+
+	oldsize = inode->i_size;
+	i_size_write(inode, newsize);
+
+	truncate_pagecache(inode, oldsize, newsize);
+}
+EXPORT_SYMBOL(truncate_setsize);
+
+/**
  * vmtruncate - unmap mappings "freed" by truncate() syscall
  * @inode: inode of the file used
  * @offset: file offset to start truncating
  *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page.  Ugly, but necessary.
- *
- * This function is deprecated and simple_setsize or truncate_pagecache
- * should be used instead.
+ * This function is deprecated and truncate_setsize or truncate_pagecache
+ * should be used instead, together with filesystem specific block truncation.
  */
 int vmtruncate(struct inode *inode, loff_t offset)
 {
 	int error;
 
-	error = simple_setsize(inode, offset);
+	error = inode_newsize_ok(inode, offset);
 	if (error)
 		return error;
 
+	truncate_setsize(inode, offset);
 	if (inode->i_op->truncate)
 		inode->i_op->truncate(inode);
-
-	return error;
+	return 0;
 }
 EXPORT_SYMBOL(vmtruncate);