1 files changed, 321 insertions, 408 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 0e8ca034770..1706cbbdf5f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -10,40 +10,46 @@
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
+#include <trace/events/writeback.h>
 
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-EXPORT_SYMBOL(default_unplug_io_fn);
+static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
 struct backing_dev_info default_backing_dev_info = {
 	.name		= "default",
 	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
 	.state		= 0,
 	.capabilities	= BDI_CAP_MAP_COPY,
-	.unplug_io_fn	= default_unplug_io_fn,
 };
 EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
+struct backing_dev_info noop_backing_dev_info = {
+	.name		= "noop",
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+};
+EXPORT_SYMBOL_GPL(noop_backing_dev_info);
+
 static struct class *bdi_class;
 
 /*
- * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as
- * reader side protection for bdi_pending_list. bdi_list has RCU reader side
+ * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side
  * locking.
  */
 DEFINE_SPINLOCK(bdi_lock);
 LIST_HEAD(bdi_list);
-LIST_HEAD(bdi_pending_list);
 
-static struct task_struct *sync_supers_tsk;
-static struct timer_list sync_supers_timer;
+/* bdi_wq serves all asynchronous writeback tasks */
+struct workqueue_struct *bdi_wq;
 
-static int bdi_sync_supers(void *);
-static void sync_supers_timer_fn(unsigned long);
-static void arm_supers_timer(void);
-
-static void bdi_add_default_flusher_task(struct backing_dev_info *bdi);
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+{
+	if (wb1 < wb2) {
+		spin_lock(&wb1->list_lock);
+		spin_lock_nested(&wb2->list_lock, 1);
+	} else {
+		spin_lock(&wb2->list_lock);
+		spin_lock_nested(&wb1->list_lock, 1);
+	}
+}
 
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
@@ -59,54 +65,53 @@ 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;
+	unsigned long nr_dirty, nr_io, nr_more_io;
 	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++;
-	}
-	spin_unlock(&inode_lock);
+	nr_dirty = nr_io = nr_more_io = 0;
+	spin_lock(&wb->list_lock);
+	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
+		nr_dirty++;
+	list_for_each_entry(inode, &wb->b_io, i_wb_list)
+		nr_io++;
+	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
+		nr_more_io++;
+	spin_unlock(&wb->list_lock);
 
-	get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
+	global_dirty_limits(&background_thresh, &dirty_thresh);
+	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
 
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	seq_printf(m,
-		   "BdiWriteback:     %8lu kB\n"
-		   "BdiReclaimable:   %8lu kB\n"
-		   "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_mask:          %8lx\n"
-		   "wb_list:          %8u\n"
-		   "wb_cnt:           %8u\n",
+		   "BdiWriteback:       %10lu kB\n"
+		   "BdiReclaimable:     %10lu kB\n"
+		   "BdiDirtyThresh:     %10lu kB\n"
+		   "DirtyThresh:        %10lu kB\n"
+		   "BackgroundThresh:   %10lu kB\n"
+		   "BdiDirtied:         %10lu kB\n"
+		   "BdiWritten:         %10lu kB\n"
+		   "BdiWriteBandwidth:  %10lu kBps\n"
+		   "b_dirty:            %10lu\n"
+		   "b_io:               %10lu\n"
+		   "b_more_io:          %10lu\n"
+		   "bdi_list:           %10u\n"
+		   "state:              %10lx\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, bdi->wb_mask,
-		   !list_empty(&bdi->wb_list), bdi->wb_cnt);
+		   K(bdi_thresh),
+		   K(dirty_thresh),
+		   K(background_thresh),
+		   (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)),
+		   (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
+		   (unsigned long) K(bdi->write_bandwidth),
+		   nr_dirty,
+		   nr_io,
+		   nr_more_io,
+		   !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 
 	return 0;
@@ -154,16 +159,16 @@ static ssize_t read_ahead_kb_store(struct device *dev,
 				  const char *buf, size_t count)
 {
 	struct backing_dev_info *bdi = dev_get_drvdata(dev);
-	char *end;
 	unsigned long read_ahead_kb;
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
 
-	read_ahead_kb = simple_strtoul(buf, &end, 10);
-	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
-		bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10);
-		ret = count;
-	}
-	return ret;
+	ret = kstrtoul(buf, 10, &read_ahead_kb);
+	if (ret < 0)
+		return ret;
+
+	bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10);
+
+	return count;
 }
 
 #define K(pages) ((pages) << (PAGE_SHIFT - 10))
@@ -175,7 +180,8 @@ static ssize_t name##_show(struct device *dev,				\
 	struct backing_dev_info *bdi = dev_get_drvdata(dev);		\
 									\
 	return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr);	\
-}
+}									\
+static DEVICE_ATTR_RW(name);
 
 BDI_SHOW(read_ahead_kb, K(bdi->ra_pages))
 
@@ -183,16 +189,17 @@ static ssize_t min_ratio_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct backing_dev_info *bdi = dev_get_drvdata(dev);
-	char *end;
 	unsigned int ratio;
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &ratio);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_min_ratio(bdi, ratio);
+	if (!ret)
+		ret = count;
 
-	ratio = simple_strtoul(buf, &end, 10);
-	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
-		ret = bdi_set_min_ratio(bdi, ratio);
-		if (!ret)
-			ret = count;
-	}
 	return ret;
 }
 BDI_SHOW(min_ratio, bdi->min_ratio)
@@ -201,33 +208,48 @@ static ssize_t max_ratio_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct backing_dev_info *bdi = dev_get_drvdata(dev);
-	char *end;
 	unsigned int ratio;
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &ratio);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_max_ratio(bdi, ratio);
+	if (!ret)
+		ret = count;
 
-	ratio = simple_strtoul(buf, &end, 10);
-	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
-		ret = bdi_set_max_ratio(bdi, ratio);
-		if (!ret)
-			ret = count;
-	}
 	return ret;
 }
 BDI_SHOW(max_ratio, bdi->max_ratio)
 
-#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
+static ssize_t stable_pages_required_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *page)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return snprintf(page, PAGE_SIZE-1, "%d\n",
+			bdi_cap_stable_pages_required(bdi) ? 1 : 0);
+}
+static DEVICE_ATTR_RO(stable_pages_required);
 
-static struct device_attribute bdi_dev_attrs[] = {
-	__ATTR_RW(read_ahead_kb),
-	__ATTR_RW(min_ratio),
-	__ATTR_RW(max_ratio),
-	__ATTR_NULL,
+static struct attribute *bdi_dev_attrs[] = {
+	&dev_attr_read_ahead_kb.attr,
+	&dev_attr_min_ratio.attr,
+	&dev_attr_max_ratio.attr,
+	&dev_attr_stable_pages_required.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(bdi_dev);
 
 static __init int bdi_class_init(void)
 {
 	bdi_class = class_create(THIS_MODULE, "bdi");
-	bdi_class->dev_attrs = bdi_dev_attrs;
+	if (IS_ERR(bdi_class))
+		return PTR_ERR(bdi_class);
+
+	bdi_class->dev_groups = bdi_dev_groups;
 	bdi_debug_init();
 	return 0;
 }
@@ -237,280 +259,48 @@ static int __init default_bdi_init(void)
 {
 	int err;
 
-	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);
-	arm_supers_timer();
+	bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE |
+					      WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!bdi_wq)
+		return -ENOMEM;
 
 	err = bdi_init(&default_backing_dev_info);
 	if (!err)
 		bdi_register(&default_backing_dev_info, NULL, "default");
+	err = bdi_init(&noop_backing_dev_info);
 
 	return err;
 }
 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);
 }
 
-static void bdi_flush_io(struct backing_dev_info *bdi)
-{
-	struct writeback_control wbc = {
-		.bdi			= bdi,
-		.sync_mode		= WB_SYNC_NONE,
-		.older_than_this	= NULL,
-		.range_cyclic		= 1,
-		.nr_to_write		= 1024,
-	};
-
-	writeback_inodes_wbc(&wbc);
-}
-
 /*
- * kupdated() used to do this. We cannot do it from the bdi_forker_task()
- * 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.
- */
-static int bdi_sync_supers(void *unused)
-{
-	set_user_nice(current, 0);
-
-	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule();
-
-		/*
-		 * Do this periodically, like kupdated() did before.
-		 */
-		sync_supers();
-	}
-
-	return 0;
-}
-
-static void arm_supers_timer(void)
-{
-	unsigned long next;
-
-	next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies;
-	mod_timer(&sync_supers_timer, round_jiffies_up(next));
-}
-
-static void sync_supers_timer_fn(unsigned long unused)
-{
-	wake_up_process(sync_supers_tsk);
-	arm_supers_timer();
-}
-
-static int bdi_forker_task(void *ptr)
-{
-	struct bdi_writeback *me = ptr;
-
-	bdi_task_init(me->bdi, me);
-
-	for (;;) {
-		struct backing_dev_info *bdi, *tmp;
-		struct bdi_writeback *wb;
-
-		/*
-		 * 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))
-			wb_do_writeback(me, 0);
-
-		spin_lock_bh(&bdi_lock);
-
-		/*
-		 * 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))
-				continue;
-
-			bdi_add_default_flusher_task(bdi);
-		}
-
-		set_current_state(TASK_INTERRUPTIBLE);
-
-		if (list_empty(&bdi_pending_list)) {
-			unsigned long wait;
-
-			spin_unlock_bh(&bdi_lock);
-			wait = msecs_to_jiffies(dirty_writeback_interval * 10);
-			schedule_timeout(wait);
-			try_to_freeze();
-			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.
-		 */
-		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);
-		}
-	}
-
-	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
+ * 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.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
  */
-void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
+void bdi_wakeup_thread_delayed(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;
-	}
+	unsigned long timeout;
 
-	/*
-	 * 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);
-	}
+	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+	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);
 }
 
 /*
@@ -522,56 +312,35 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	list_del_rcu(&bdi->bdi_list);
 	spin_unlock_bh(&bdi_lock);
 
-	synchronize_rcu();
+	synchronize_rcu_expedited();
 }
 
 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;
 
-	/*
-	 * Just start the forker thread for our default backing_dev_info,
-	 * and add other bdi's to the list. They will get a thread created
-	 * on-demand when they need it.
-	 */
-	if (bdi_cap_flush_forker(bdi)) {
-		struct bdi_writeback *wb = &bdi->wb;
-
-		wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s",
-						dev_name(dev));
-		if (IS_ERR(wb->task)) {
-			wb->task = NULL;
-			ret = -ENOMEM;
-
-			bdi_remove_from_list(bdi);
-			goto exit;
-		}
-	}
-
 	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);
 
@@ -586,32 +355,34 @@ 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 queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	clear_bit(BDI_registered, &bdi->state);
+	spin_unlock_bh(&bdi->wb_lock);
 
 	/*
-	 * Make sure nobody finds us on the bdi_list anymore
+	 * Drain work list and shutdown the delayed_work.  At this point,
+	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
+	 * is dying and its work_list needs to be drained no matter what.
 	 */
-	bdi_remove_from_list(bdi);
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	flush_delayed_work(&bdi->wb.dwork);
+	WARN_ON(!list_empty(&bdi->work_list));
 
 	/*
-	 * Finally, kill the kernel threads. 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.
+	 * This shouldn't be necessary unless @bdi for some reason has
+	 * unflushed dirty IO after work_list is drained.  Do it anyway
+	 * just in case.
 	 */
-	list_for_each_entry(wb, &bdi->wb_list, list) {
-		thaw_process(wb->task);
-		kthread_stop(wb->task);
-	}
+	cancel_delayed_work_sync(&bdi->wb.dwork);
 }
 
 /*
@@ -624,25 +395,50 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 	spin_lock(&sb_lock);
 	list_for_each_entry(sb, &super_blocks, s_list) {
 		if (sb->s_bdi == bdi)
-			sb->s_bdi = NULL;
+			sb->s_bdi = &default_backing_dev_info;
 	}
 	spin_unlock(&sb_lock);
 }
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-	if (bdi->dev) {
+	struct device *dev = bdi->dev;
+
+	if (dev) {
+		bdi_set_min_ratio(bdi, 0);
+		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 
-		if (!bdi_cap_flush_forker(bdi))
-			bdi_wb_shutdown(bdi);
+		bdi_wb_shutdown(bdi);
 		bdi_debug_unregister(bdi);
-		device_unregister(bdi->dev);
+
+		spin_lock_bh(&bdi->wb_lock);
 		bdi->dev = NULL;
+		spin_unlock_bh(&bdi->wb_lock);
+
+		device_unregister(dev);
 	}
 }
 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);
+	spin_lock_init(&wb->list_lock);
+	INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
+}
+
+/*
+ * Initial write bandwidth: 100 MB/s
+ */
+#define INIT_BW		(100 << (20 - PAGE_SHIFT))
+
 int bdi_init(struct backing_dev_info *bdi)
 {
 	int i, err;
@@ -651,21 +447,13 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	bdi->min_ratio = 0;
 	bdi->max_ratio = 100;
-	bdi->max_prop_frac = PROP_FRAC_BASE;
+	bdi->max_prop_frac = FPROP_FRAC_BASE;
 	spin_lock_init(&bdi->wb_lock);
-	INIT_RCU_HEAD(&bdi->rcu_head);
 	INIT_LIST_HEAD(&bdi->bdi_list);
-	INIT_LIST_HEAD(&bdi->wb_list);
 	INIT_LIST_HEAD(&bdi->work_list);
 
 	bdi_wb_init(&bdi->wb, bdi);
 
-	/*
-	 * Just one thread support for now, hard code mask and count
-	 */
-	bdi->wb_mask = 1;
-	bdi->wb_cnt = 1;
-
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
 		if (err)
@@ -673,7 +461,16 @@ int bdi_init(struct backing_dev_info *bdi)
 	}
 
 	bdi->dirty_exceeded = 0;
-	err = prop_local_init_percpu(&bdi->completions);
+
+	bdi->bw_time_stamp = jiffies;
+	bdi->written_stamp = 0;
+
+	bdi->balanced_dirty_ratelimit = INIT_BW;
+	bdi->dirty_ratelimit = INIT_BW;
+	bdi->write_bandwidth = INIT_BW;
+	bdi->avg_write_bandwidth = INIT_BW;
+
+	err = fprop_local_init_percpu(&bdi->completions);
 
 	if (err) {
 err:
@@ -696,26 +493,61 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	if (bdi_has_dirty_io(bdi)) {
 		struct bdi_writeback *dst = &default_backing_dev_info.wb;
 
-		spin_lock(&inode_lock);
+		bdi_lock_two(&bdi->wb, dst);
 		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
 		list_splice(&bdi->wb.b_io, &dst->b_io);
 		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-		spin_unlock(&inode_lock);
+		spin_unlock(&bdi->wb.list_lock);
+		spin_unlock(&dst->list_lock);
 	}
 
 	bdi_unregister(bdi);
 
+	/*
+	 * If bdi_unregister() had already been called earlier, the dwork
+	 * could still be pending because bdi_prune_sb() can race with the
+	 * bdi_wakeup_thread_delayed() calls from __mark_inode_dirty().
+	 */
+	cancel_delayed_work_sync(&bdi->wb.dwork);
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
 
-	prop_local_destroy_percpu(&bdi->completions);
+	fprop_local_destroy_percpu(&bdi->completions);
 }
 EXPORT_SYMBOL(bdi_destroy);
 
+/*
+ * For use from filesystems to quickly init and register a bdi associated
+ * with dirty writeback
+ */
+int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
+			   unsigned int cap)
+{
+	int err;
+
+	bdi->name = name;
+	bdi->capabilities = cap;
+	err = bdi_init(bdi);
+	if (err)
+		return err;
+
+	err = bdi_register(bdi, NULL, "%.28s-%ld", name,
+			   atomic_long_inc_return(&bdi_seq));
+	if (err) {
+		bdi_destroy(bdi);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(bdi_setup_and_register);
+
 static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
 	};
+static atomic_t nr_bdi_congested[2];
 
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
@@ -723,8 +555,9 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	clear_bit(bit, &bdi->state);
-	smp_mb__after_clear_bit();
+	if (test_and_clear_bit(bit, &bdi->state))
+		atomic_dec(&nr_bdi_congested[sync]);
+	smp_mb__after_atomic();
 	if (waitqueue_active(wqh))
 		wake_up(wqh);
 }
@@ -735,7 +568,8 @@ void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 	enum bdi_state bit;
 
 	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	set_bit(bit, &bdi->state);
+	if (!test_and_set_bit(bit, &bdi->state))
+		atomic_inc(&nr_bdi_congested[sync]);
 }
 EXPORT_SYMBOL(set_bdi_congested);
 
@@ -751,13 +585,92 @@ EXPORT_SYMBOL(set_bdi_congested);
 long congestion_wait(int sync, long timeout)
 {
 	long ret;
+	unsigned long start = jiffies;
 	DEFINE_WAIT(wait);
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
 	ret = io_schedule_timeout(timeout);
 	finish_wait(wqh, &wait);
+
+	trace_writeback_congestion_wait(jiffies_to_usecs(timeout),
+					jiffies_to_usecs(jiffies - start));
+
 	return ret;
 }
 EXPORT_SYMBOL(congestion_wait);
 
+/**
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
+ * @zone: A zone to check if it is heavily congested
+ * @sync: SYNC or ASYNC IO
+ * @timeout: timeout in jiffies
+ *
+ * In the event of a congested backing_dev (any backing_dev) and the given
+ * @zone has experienced recent congestion, this waits for up to @timeout
+ * jiffies for either a BDI to exit congestion of the given @sync queue
+ * or a write to complete.
+ *
+ * In the absence of zone congestion, cond_resched() is called to yield
+ * the processor if necessary but otherwise does not sleep.
+ *
+ * The return value is 0 if the sleep is for the full timeout. Otherwise,
+ * it is the number of jiffies that were still remaining when the function
+ * returned. return_value == timeout implies the function did not sleep.
+ */
+long wait_iff_congested(struct zone *zone, int sync, long timeout)
+{
+	long ret;
+	unsigned long start = jiffies;
+	DEFINE_WAIT(wait);
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+	/*
+	 * If there is no congestion, or heavy congestion is not being
+	 * encountered in the current zone, yield if necessary instead
+	 * of sleeping on the congestion queue
+	 */
+	if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
+			!zone_is_reclaim_congested(zone)) {
+		cond_resched();
+
+		/* In case we scheduled, work out time remaining */
+		ret = timeout - (jiffies - start);
+		if (ret < 0)
+			ret = 0;
+
+		goto out;
+	}
+
+	/* Sleep until uncongested or a write happens */
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	ret = io_schedule_timeout(timeout);
+	finish_wait(wqh, &wait);
+
+out:
+	trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
+					jiffies_to_usecs(jiffies - start));
+
+	return ret;
+}
+EXPORT_SYMBOL(wait_iff_congested);
+
+int pdflush_proc_obsolete(struct ctl_table *table, int write,
+			void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	char kbuf[] = "0\n";
+
+	if (*ppos || *lenp < sizeof(kbuf)) {
+		*lenp = 0;
+		return 0;
+	}
+
+	if (copy_to_user(buffer, kbuf, sizeof(kbuf)))
+		return -EFAULT;
+	printk_once(KERN_WARNING "%s exported in /proc is scheduled for removal\n",
+			table->procname);
+
+	*lenp = 2;
+	*ppos += *lenp;
+	return 2;
+}