1 files changed, 318 insertions, 274 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 5b4a9362d5a..be568b7311d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -14,7 +14,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
@@ -22,11 +22,11 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/kthread.h>
-#include <linux/freezer.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/tracepoint.h>
+#include <linux/device.h>
 #include "internal.h"
 
 /*
@@ -46,17 +46,13 @@ struct wb_writeback_work {
 	unsigned int for_kupdate:1;
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
+	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
 	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
 	struct completion *done;	/* set if the caller waits */
 };
 
-/*
- * We don't actually have pdflush, but this one is exported though /proc...
- */
-int nr_pdflush_threads;
-
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
@@ -68,12 +64,13 @@ int writeback_in_progress(struct backing_dev_info *bdi)
 {
 	return test_bit(BDI_writeback_running, &bdi->state);
 }
+EXPORT_SYMBOL(writeback_in_progress);
 
 static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 
-	if (strcmp(sb->s_type->name, "bdev") == 0)
+	if (sb_is_blkdev_sb(sb))
 		return inode->i_mapping->backing_dev_info;
 
 	return sb->s_bdi;
@@ -92,18 +89,14 @@ static inline struct inode *wb_inode(struct list_head *head)
 #define CREATE_TRACE_POINTS
 #include <trace/events/writeback.h>
 
-/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
-static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
+EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
+
+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
 {
-	if (bdi->wb.task) {
-		wake_up_process(bdi->wb.task);
-	} else {
-		/*
-		 * The bdi thread isn't there, wake up the forker thread which
-		 * will create and run it.
-		 */
-		wake_up_process(default_backing_dev_info.wb.task);
-	}
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void bdi_queue_work(struct backing_dev_info *bdi,
@@ -112,10 +105,14 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 	trace_writeback_queue(bdi, work);
 
 	spin_lock_bh(&bdi->wb_lock);
+	if (!test_bit(BDI_registered, &bdi->state)) {
+		if (work->done)
+			complete(work->done);
+		goto out_unlock;
+	}
 	list_add_tail(&work->list, &bdi->work_list);
-	if (!bdi->wb.task)
-		trace_writeback_nothread(bdi, work);
-	bdi_wakeup_flusher(bdi);
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+out_unlock:
 	spin_unlock_bh(&bdi->wb_lock);
 }
 
@@ -131,10 +128,8 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	 */
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
-		if (bdi->wb.task) {
-			trace_writeback_nowork(bdi);
-			wake_up_process(bdi->wb.task);
-		}
+		trace_writeback_nowork(bdi);
+		bdi_wakeup_thread(bdi);
 		return;
 	}
 
@@ -181,9 +176,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
 	 * writeback as soon as there is no other work to do.
 	 */
 	trace_writeback_wake_background(bdi);
-	spin_lock_bh(&bdi->wb_lock);
-	bdi_wakeup_flusher(bdi);
-	spin_unlock_bh(&bdi->wb_lock);
+	bdi_wakeup_thread(bdi);
 }
 
 /*
@@ -231,11 +224,10 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 
 static void inode_sync_complete(struct inode *inode)
 {
-	/*
-	 * Prevent speculative execution through
-	 * spin_unlock(&wb->list_lock);
-	 */
-
+	inode->i_state &= ~I_SYNC;
+	/* If inode is clean an unused, put it into LRU now... */
+	inode_add_lru(inode);
+	/* Waiters must see I_SYNC cleared before being woken up */
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_SYNC);
 }
@@ -256,7 +248,8 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 }
 
 /*
- * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
+ * Move expired (dirtied before work->older_than_this) dirty inodes from
+ * @delaying_queue to @dispatch_queue.
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
@@ -274,11 +267,13 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 		if (work->older_than_this &&
 		    inode_dirtied_after(inode, *work->older_than_this))
 			break;
+		list_move(&inode->i_wb_list, &tmp);
+		moved++;
+		if (sb_is_blkdev_sb(inode->i_sb))
+			continue;
 		if (sb && sb != inode->i_sb)
 			do_sb_sort = 1;
 		sb = inode->i_sb;
-		list_move(&inode->i_wb_list, &tmp);
-		moved++;
 	}
 
 	/* just one sb in list, splice to dispatch_queue and we're done */
@@ -322,16 +317,24 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
-		return inode->i_sb->s_op->write_inode(inode, wbc);
+	int ret;
+
+	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) {
+		trace_writeback_write_inode_start(inode, wbc);
+		ret = inode->i_sb->s_op->write_inode(inode, wbc);
+		trace_writeback_write_inode(inode, wbc);
+		return ret;
+	}
 	return 0;
 }
 
 /*
- * Wait for writeback on an inode to complete.
+ * Wait for writeback on an inode to complete. Called with i_lock held.
+ * Caller must make sure inode cannot go away when we drop i_lock.
  */
-static void inode_wait_for_writeback(struct inode *inode,
-				     struct bdi_writeback *wb)
+static void __inode_wait_for_writeback(struct inode *inode)
+	__releases(inode->i_lock)
+	__acquires(inode->i_lock)
 {
 	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
 	wait_queue_head_t *wqh;
@@ -339,79 +342,131 @@ static void inode_wait_for_writeback(struct inode *inode,
 	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
 	while (inode->i_state & I_SYNC) {
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&wb->list_lock);
 		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
-		spin_lock(&wb->list_lock);
 		spin_lock(&inode->i_lock);
 	}
 }
 
 /*
- * Write out an inode's dirty pages.  Called under wb->list_lock and
- * inode->i_lock.  Either the caller has an active reference on the inode or
- * the inode has I_WILL_FREE set.
- *
- * If `wait' is set, wait on the writeout.
- *
- * The whole writeout design is quite complex and fragile.  We want to avoid
- * starvation of particular inodes when others are being redirtied, prevent
- * livelocks, etc.
+ * Wait for writeback on an inode to complete. Caller must have inode pinned.
  */
-static int
-writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
-		       struct writeback_control *wbc)
+void inode_wait_for_writeback(struct inode *inode)
 {
-	struct address_space *mapping = inode->i_mapping;
-	long nr_to_write = wbc->nr_to_write;
-	unsigned dirty;
-	int ret;
+	spin_lock(&inode->i_lock);
+	__inode_wait_for_writeback(inode);
+	spin_unlock(&inode->i_lock);
+}
 
-	assert_spin_locked(&wb->list_lock);
-	assert_spin_locked(&inode->i_lock);
+/*
+ * Sleep until I_SYNC is cleared. This function must be called with i_lock
+ * held and drops it. It is aimed for callers not holding any inode reference
+ * so once i_lock is dropped, inode can go away.
+ */
+static void inode_sleep_on_writeback(struct inode *inode)
+	__releases(inode->i_lock)
+{
+	DEFINE_WAIT(wait);
+	wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
+	int sleep;
 
-	if (!atomic_read(&inode->i_count))
-		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
-	else
-		WARN_ON(inode->i_state & I_WILL_FREE);
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	sleep = inode->i_state & I_SYNC;
+	spin_unlock(&inode->i_lock);
+	if (sleep)
+		schedule();
+	finish_wait(wqh, &wait);
+}
 
-	if (inode->i_state & I_SYNC) {
+/*
+ * Find proper writeback list for the inode depending on its current state and
+ * possibly also change of its state while we were doing writeback.  Here we
+ * handle things such as livelock prevention or fairness of writeback among
+ * inodes. This function can be called only by flusher thread - noone else
+ * processes all inodes in writeback lists and requeueing inodes behind flusher
+ * thread's back can have unexpected consequences.
+ */
+static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
+			  struct writeback_control *wbc)
+{
+	if (inode->i_state & I_FREEING)
+		return;
+
+	/*
+	 * Sync livelock prevention. Each inode is tagged and synced in one
+	 * shot. If still dirty, it will be redirty_tail()'ed below.  Update
+	 * the dirty time to prevent enqueue and sync it again.
+	 */
+	if ((inode->i_state & I_DIRTY) &&
+	    (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
+		inode->dirtied_when = jiffies;
+
+	if (wbc->pages_skipped) {
 		/*
-		 * If this inode is locked for writeback and we are not doing
-		 * writeback-for-data-integrity, move it to b_more_io so that
-		 * writeback can proceed with the other inodes on s_io.
-		 *
-		 * We'll have another go at writing back this inode when we
-		 * completed a full scan of b_io.
+		 * writeback is not making progress due to locked
+		 * buffers. Skip this inode for now.
+		 */
+		redirty_tail(inode, wb);
+		return;
+	}
+
+	if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
+		/*
+		 * We didn't write back all the pages.  nfs_writepages()
+		 * sometimes bales out without doing anything.
 		 */
-		if (wbc->sync_mode != WB_SYNC_ALL) {
+		if (wbc->nr_to_write <= 0) {
+			/* Slice used up. Queue for next turn. */
 			requeue_io(inode, wb);
-			trace_writeback_single_inode_requeue(inode, wbc,
-							     nr_to_write);
-			return 0;
+		} else {
+			/*
+			 * Writeback blocked by something other than
+			 * congestion. Delay the inode for some time to
+			 * avoid spinning on the CPU (100% iowait)
+			 * retrying writeback of the dirty page/inode
+			 * that cannot be performed immediately.
+			 */
+			redirty_tail(inode, wb);
 		}
-
+	} else if (inode->i_state & I_DIRTY) {
 		/*
-		 * It's a data-integrity sync.  We must wait.
+		 * Filesystems can dirty the inode during writeback operations,
+		 * such as delayed allocation during submission or metadata
+		 * updates after data IO completion.
 		 */
-		inode_wait_for_writeback(inode, wb);
+		redirty_tail(inode, wb);
+	} else {
+		/* The inode is clean. Remove from writeback lists. */
+		list_del_init(&inode->i_wb_list);
 	}
+}
 
-	BUG_ON(inode->i_state & I_SYNC);
+/*
+ * Write out an inode and its dirty pages. Do not update the writeback list
+ * linkage. That is left to the caller. The caller is also responsible for
+ * setting I_SYNC flag and calling inode_sync_complete() to clear it.
+ */
+static int
+__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
+{
+	struct address_space *mapping = inode->i_mapping;
+	long nr_to_write = wbc->nr_to_write;
+	unsigned dirty;
+	int ret;
 
-	/* Set I_SYNC, reset I_DIRTY_PAGES */
-	inode->i_state |= I_SYNC;
-	inode->i_state &= ~I_DIRTY_PAGES;
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&wb->list_lock);
+	WARN_ON(!(inode->i_state & I_SYNC));
+
+	trace_writeback_single_inode_start(inode, wbc, nr_to_write);
 
 	ret = do_writepages(mapping, wbc);
 
 	/*
 	 * Make sure to wait on the data before writing out the metadata.
 	 * This is important for filesystems that modify metadata on data
-	 * I/O completion.
+	 * I/O completion. We don't do it for sync(2) writeback because it has a
+	 * separate, external IO completion path and ->sync_fs for guaranteeing
+	 * inode metadata is written back correctly.
 	 */
-	if (wbc->sync_mode == WB_SYNC_ALL) {
+	if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) {
 		int err = filemap_fdatawait(mapping);
 		if (ret == 0)
 			ret = err;
@@ -423,6 +478,9 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * write_inode()
 	 */
 	spin_lock(&inode->i_lock);
+	/* Clear I_DIRTY_PAGES if we've written out all dirty pages */
+	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+		inode->i_state &= ~I_DIRTY_PAGES;
 	dirty = inode->i_state & I_DIRTY;
 	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
 	spin_unlock(&inode->i_lock);
@@ -432,60 +490,70 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 		if (ret == 0)
 			ret = err;
 	}
+	trace_writeback_single_inode(inode, wbc, nr_to_write);
+	return ret;
+}
+
+/*
+ * Write out an inode's dirty pages. Either the caller has an active reference
+ * on the inode or the inode has I_WILL_FREE set.
+ *
+ * This function is designed to be called for writing back one inode which
+ * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode()
+ * and does more profound writeback list handling in writeback_sb_inodes().
+ */
+static int
+writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
+		       struct writeback_control *wbc)
+{
+	int ret = 0;
 
-	spin_lock(&wb->list_lock);
 	spin_lock(&inode->i_lock);
-	inode->i_state &= ~I_SYNC;
-	if (!(inode->i_state & I_FREEING)) {
+	if (!atomic_read(&inode->i_count))
+		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
+	else
+		WARN_ON(inode->i_state & I_WILL_FREE);
+
+	if (inode->i_state & I_SYNC) {
+		if (wbc->sync_mode != WB_SYNC_ALL)
+			goto out;
 		/*
-		 * Sync livelock prevention. Each inode is tagged and synced in
-		 * one shot. If still dirty, it will be redirty_tail()'ed below.
-		 * Update the dirty time to prevent enqueue and sync it again.
+		 * It's a data-integrity sync. We must wait. Since callers hold
+		 * inode reference or inode has I_WILL_FREE set, it cannot go
+		 * away under us.
 		 */
-		if ((inode->i_state & I_DIRTY) &&
-		    (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
-			inode->dirtied_when = jiffies;
-
-		if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-			/*
-			 * We didn't write back all the pages.  nfs_writepages()
-			 * sometimes bales out without doing anything.
-			 */
-			inode->i_state |= I_DIRTY_PAGES;
-			if (wbc->nr_to_write <= 0) {
-				/*
-				 * slice used up: queue for next turn
-				 */
-				requeue_io(inode, wb);
-			} else {
-				/*
-				 * Writeback blocked by something other than
-				 * congestion. Delay the inode for some time to
-				 * avoid spinning on the CPU (100% iowait)
-				 * retrying writeback of the dirty page/inode
-				 * that cannot be performed immediately.
-				 */
-				redirty_tail(inode, wb);
-			}
-		} else if (inode->i_state & I_DIRTY) {
-			/*
-			 * Filesystems can dirty the inode during writeback
-			 * operations, such as delayed allocation during
-			 * submission or metadata updates after data IO
-			 * completion.
-			 */
-			redirty_tail(inode, wb);
-		} else {
-			/*
-			 * The inode is clean.  At this point we either have
-			 * a reference to the inode or it's on it's way out.
-			 * No need to add it back to the LRU.
-			 */
-			list_del_init(&inode->i_wb_list);
-		}
+		__inode_wait_for_writeback(inode);
 	}
+	WARN_ON(inode->i_state & I_SYNC);
+	/*
+	 * Skip inode if it is clean and we have no outstanding writeback in
+	 * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this
+	 * function since flusher thread may be doing for example sync in
+	 * parallel and if we move the inode, it could get skipped. So here we
+	 * make sure inode is on some writeback list and leave it there unless
+	 * we have completely cleaned the inode.
+	 */
+	if (!(inode->i_state & I_DIRTY) &&
+	    (wbc->sync_mode != WB_SYNC_ALL ||
+	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
+		goto out;
+	inode->i_state |= I_SYNC;
+	spin_unlock(&inode->i_lock);
+
+	ret = __writeback_single_inode(inode, wbc);
+
+	spin_lock(&wb->list_lock);
+	spin_lock(&inode->i_lock);
+	/*
+	 * If inode is clean, remove it from writeback lists. Otherwise don't
+	 * touch it. See comment above for explanation.
+	 */
+	if (!(inode->i_state & I_DIRTY))
+		list_del_init(&inode->i_wb_list);
+	spin_unlock(&wb->list_lock);
 	inode_sync_complete(inode);
-	trace_writeback_single_inode(inode, wbc, nr_to_write);
+out:
+	spin_unlock(&inode->i_lock);
 	return ret;
 }
 
@@ -523,10 +591,6 @@ static long writeback_chunk_size(struct backing_dev_info *bdi,
 /*
  * Write a portion of b_io inodes which belong to @sb.
  *
- * If @only_this_sb is true, then find and write all such
- * inodes. Otherwise write only ones which go sequentially
- * in reverse order.
- *
  * Return the number of pages and/or inodes written.
  */
 static long writeback_sb_inodes(struct super_block *sb,
@@ -538,6 +602,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		.tagged_writepages	= work->tagged_writepages,
 		.for_kupdate		= work->for_kupdate,
 		.for_background		= work->for_background,
+		.for_sync		= work->for_sync,
 		.range_cyclic		= work->range_cyclic,
 		.range_start		= 0,
 		.range_end		= LLONG_MAX,
@@ -569,8 +634,8 @@ static long writeback_sb_inodes(struct super_block *sb,
 		}
 
 		/*
-		 * Don't bother with new inodes or inodes beeing freed, first
-		 * kind does not need peridic writeout yet, and for the latter
+		 * Don't bother with new inodes or inodes being freed, first
+		 * kind does not need periodic writeout yet, and for the latter
 		 * kind writeout is handled by the freer.
 		 */
 		spin_lock(&inode->i_lock);
@@ -579,29 +644,58 @@ static long writeback_sb_inodes(struct super_block *sb,
 			redirty_tail(inode, wb);
 			continue;
 		}
-		__iget(inode);
+		if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
+			/*
+			 * If this inode is locked for writeback and we are not
+			 * doing writeback-for-data-integrity, move it to
+			 * b_more_io so that writeback can proceed with the
+			 * other inodes on s_io.
+			 *
+			 * We'll have another go at writing back this inode
+			 * when we completed a full scan of b_io.
+			 */
+			spin_unlock(&inode->i_lock);
+			requeue_io(inode, wb);
+			trace_writeback_sb_inodes_requeue(inode);
+			continue;
+		}
+		spin_unlock(&wb->list_lock);
+
+		/*
+		 * We already requeued the inode if it had I_SYNC set and we
+		 * are doing WB_SYNC_NONE writeback. So this catches only the
+		 * WB_SYNC_ALL case.
+		 */
+		if (inode->i_state & I_SYNC) {
+			/* Wait for I_SYNC. This function drops i_lock... */
+			inode_sleep_on_writeback(inode);
+			/* Inode may be gone, start again */
+			spin_lock(&wb->list_lock);
+			continue;
+		}
+		inode->i_state |= I_SYNC;
+		spin_unlock(&inode->i_lock);
+
 		write_chunk = writeback_chunk_size(wb->bdi, work);
 		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
 
-		writeback_single_inode(inode, wb, &wbc);
+		/*
+		 * We use I_SYNC to pin the inode in memory. While it is set
+		 * evict_inode() will wait so the inode cannot be freed.
+		 */
+		__writeback_single_inode(inode, &wbc);
 
 		work->nr_pages -= write_chunk - wbc.nr_to_write;
 		wrote += write_chunk - wbc.nr_to_write;
+		spin_lock(&wb->list_lock);
+		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY))
 			wrote++;
-		if (wbc.pages_skipped) {
-			/*
-			 * writeback is not making progress due to locked
-			 * buffers.  Skip this inode for now.
-			 */
-			redirty_tail(inode, wb);
-		}
+		requeue_inode(inode, wb, &wbc);
+		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&wb->list_lock);
-		iput(inode);
-		cond_resched();
-		spin_lock(&wb->list_lock);
+		cond_resched_lock(&wb->list_lock);
 		/*
 		 * bail out to wb_writeback() often enough to check
 		 * background threshold and other termination conditions.
@@ -650,7 +744,7 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb,
 	return wrote;
 }
 
-long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
+static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 				enum wb_reason reason)
 {
 	struct wb_writeback_work work = {
@@ -795,8 +889,10 @@ static long wb_writeback(struct bdi_writeback *wb,
 			trace_writeback_wait(wb->bdi, work);
 			inode = wb_inode(wb->b_more_io.prev);
 			spin_lock(&inode->i_lock);
-			inode_wait_for_writeback(inode, wb);
-			spin_unlock(&inode->i_lock);
+			spin_unlock(&wb->list_lock);
+			/* This function drops i_lock... */
+			inode_sleep_on_writeback(inode);
+			spin_lock(&wb->list_lock);
 		}
 	}
 	spin_unlock(&wb->list_lock);
@@ -888,7 +984,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
 /*
  * Retrieve work items and do the writeback they describe
  */
-long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
+static long wb_do_writeback(struct bdi_writeback *wb)
 {
 	struct backing_dev_info *bdi = wb->bdi;
 	struct wb_writeback_work *work;
@@ -896,12 +992,6 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 
 	set_bit(BDI_writeback_running, &wb->bdi->state);
 	while ((work = get_next_work_item(bdi)) != NULL) {
-		/*
-		 * Override sync mode, in case we must wait for completion
-		 * because this thread is exiting now.
-		 */
-		if (force_wait)
-			work->sync_mode = WB_SYNC_ALL;
 
 		trace_writeback_exec(bdi, work);
 
@@ -929,66 +1019,49 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 
 /*
  * Handle writeback of dirty data for the device backed by this bdi. Also
- * wakes up periodically and does kupdated style flushing.
+ * reschedules periodically and does kupdated style flushing.
  */
-int bdi_writeback_thread(void *data)
+void bdi_writeback_workfn(struct work_struct *work)
 {
-	struct bdi_writeback *wb = data;
+	struct bdi_writeback *wb = container_of(to_delayed_work(work),
+						struct bdi_writeback, dwork);
 	struct backing_dev_info *bdi = wb->bdi;
 	long pages_written;
 
+	set_worker_desc("flush-%s", dev_name(bdi->dev));
 	current->flags |= PF_SWAPWRITE;
-	set_freezable();
-	wb->last_active = jiffies;
-
-	/*
-	 * Our parent may run at a different priority, just set us to normal
-	 */
-	set_user_nice(current, 0);
 
-	trace_writeback_thread_start(bdi);
-
-	while (!kthread_freezable_should_stop(NULL)) {
+	if (likely(!current_is_workqueue_rescuer() ||
+		   !test_bit(BDI_registered, &bdi->state))) {
 		/*
-		 * Remove own delayed wake-up timer, since we are already awake
-		 * and we'll take care of the preriodic write-back.
+		 * The normal path.  Keep writing back @bdi until its
+		 * work_list is empty.  Note that this path is also taken
+		 * if @bdi is shutting down even when we're running off the
+		 * rescuer as work_list needs to be drained.
 		 */
-		del_timer(&wb->wakeup_timer);
-
-		pages_written = wb_do_writeback(wb, 0);
-
+		do {
+			pages_written = wb_do_writeback(wb);
+			trace_writeback_pages_written(pages_written);
+		} while (!list_empty(&bdi->work_list));
+	} else {
+		/*
+		 * bdi_wq can't get enough workers and we're running off
+		 * the emergency worker.  Don't hog it.  Hopefully, 1024 is
+		 * enough for efficient IO.
+		 */
+		pages_written = writeback_inodes_wb(&bdi->wb, 1024,
+						    WB_REASON_FORKER_THREAD);
 		trace_writeback_pages_written(pages_written);
-
-		if (pages_written)
-			wb->last_active = jiffies;
-
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (!list_empty(&bdi->work_list) || kthread_should_stop()) {
-			__set_current_state(TASK_RUNNING);
-			continue;
-		}
-
-		if (wb_has_dirty_io(wb) && dirty_writeback_interval)
-			schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
-		else {
-			/*
-			 * We have nothing to do, so can go sleep without any
-			 * timeout and save power. When a work is queued or
-			 * something is made dirty - we will be woken up.
-			 */
-			schedule();
-		}
 	}
 
-	/* Flush any work that raced with us exiting */
 	if (!list_empty(&bdi->work_list))
-		wb_do_writeback(wb, 1);
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
+		bdi_wakeup_thread_delayed(bdi);
 
-	trace_writeback_thread_stop(bdi);
-	return 0;
+	current->flags &= ~PF_SWAPWRITE;
 }
 
-
 /*
  * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
  * the whole world.
@@ -997,10 +1070,8 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
 {
 	struct backing_dev_info *bdi;
 
-	if (!nr_pages) {
-		nr_pages = global_page_state(NR_FILE_DIRTY) +
-				global_page_state(NR_UNSTABLE_NFS);
-	}
+	if (!nr_pages)
+		nr_pages = get_nr_dirty_pages();
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
@@ -1067,8 +1138,12 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	 * dirty the inode itself
 	 */
 	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+		trace_writeback_dirty_inode_start(inode, flags);
+
 		if (sb->s_op->dirty_inode)
 			sb->s_op->dirty_inode(inode, flags);
+
+		trace_writeback_dirty_inode(inode, flags);
 	}
 
 	/*
@@ -1117,6 +1192,8 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			bool wakeup_bdi = false;
 			bdi = inode_to_bdi(inode);
 
+			spin_unlock(&inode->i_lock);
+			spin_lock(&bdi->wb.list_lock);
 			if (bdi_cap_writeback_dirty(bdi)) {
 				WARN(!test_bit(BDI_registered, &bdi->state),
 				     "bdi-%s not registered\n", bdi->name);
@@ -1131,8 +1208,6 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 					wakeup_bdi = true;
 			}
 
-			spin_unlock(&inode->i_lock);
-			spin_lock(&bdi->wb.list_lock);
 			inode->dirtied_when = jiffies;
 			list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
 			spin_unlock(&bdi->wb.list_lock);
@@ -1148,23 +1223,6 @@ out_unlock_inode:
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
-/*
- * Write out a superblock's list of dirty inodes.  A wait will be performed
- * upon no inodes, all inodes or the final one, depending upon sync_mode.
- *
- * If older_than_this is non-NULL, then only write out inodes which
- * had their first dirtying at a time earlier than *older_than_this.
- *
- * If `bdi' is non-zero then we're being asked to writeback a specific queue.
- * This function assumes that the blockdev superblock's inodes are backed by
- * a variety of queues, so all inodes are searched.  For other superblocks,
- * assume that all inodes are backed by the same queue.
- *
- * The inodes to be written are parked on bdi->b_io.  They are moved back onto
- * bdi->b_dirty as they are selected for writing.  This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
- */
 static void wait_sb_inodes(struct super_block *sb)
 {
 	struct inode *inode, *old_inode = NULL;
@@ -1242,6 +1300,8 @@ void writeback_inodes_sb_nr(struct super_block *sb,
 		.reason			= reason,
 	};
 
+	if (sb->s_bdi == &noop_backing_dev_info)
+		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 	bdi_queue_work(sb->s_bdi, &work);
 	wait_for_completion(&done);
@@ -1264,47 +1324,43 @@ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
 EXPORT_SYMBOL(writeback_inodes_sb);
 
 /**
- * writeback_inodes_sb_if_idle	-	start writeback if none underway
+ * try_to_writeback_inodes_sb_nr - try to start writeback if none underway
  * @sb: the superblock
- * @reason: reason why some writeback work was initiated
+ * @nr: the number of pages to write
+ * @reason: the reason of writeback
  *
- * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Invoke writeback_inodes_sb_nr if no writeback is currently underway.
  * Returns 1 if writeback was started, 0 if not.
  */
-int writeback_inodes_sb_if_idle(struct super_block *sb, enum wb_reason reason)
+int try_to_writeback_inodes_sb_nr(struct super_block *sb,
+				  unsigned long nr,
+				  enum wb_reason reason)
 {
-	if (!writeback_in_progress(sb->s_bdi)) {
-		down_read(&sb->s_umount);
-		writeback_inodes_sb(sb, reason);
-		up_read(&sb->s_umount);
+	if (writeback_in_progress(sb->s_bdi))
 		return 1;
-	} else
+
+	if (!down_read_trylock(&sb->s_umount))
 		return 0;
+
+	writeback_inodes_sb_nr(sb, nr, reason);
+	up_read(&sb->s_umount);
+	return 1;
 }
-EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
+EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr);
 
 /**
- * writeback_inodes_sb_if_idle	-	start writeback if none underway
+ * try_to_writeback_inodes_sb - try to start writeback if none underway
  * @sb: the superblock
- * @nr: the number of pages to write
  * @reason: reason why some writeback work was initiated
  *
- * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Implement by try_to_writeback_inodes_sb_nr()
  * Returns 1 if writeback was started, 0 if not.
  */
-int writeback_inodes_sb_nr_if_idle(struct super_block *sb,
-				   unsigned long nr,
-				   enum wb_reason reason)
+int try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
 {
-	if (!writeback_in_progress(sb->s_bdi)) {
-		down_read(&sb->s_umount);
-		writeback_inodes_sb_nr(sb, nr, reason);
-		up_read(&sb->s_umount);
-		return 1;
-	} else
-		return 0;
+	return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
 }
-EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle);
+EXPORT_SYMBOL(try_to_writeback_inodes_sb);
 
 /**
  * sync_inodes_sb	-	sync sb inode pages
@@ -1323,8 +1379,12 @@ void sync_inodes_sb(struct super_block *sb)
 		.range_cyclic	= 0,
 		.done		= &done,
 		.reason		= WB_REASON_SYNC,
+		.for_sync	= 1,
 	};
 
+	/* Nothing to do? */
+	if (sb->s_bdi == &noop_backing_dev_info)
+		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
 	bdi_queue_work(sb->s_bdi, &work);
@@ -1347,7 +1407,6 @@ EXPORT_SYMBOL(sync_inodes_sb);
 int write_inode_now(struct inode *inode, int sync)
 {
 	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
-	int ret;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
 		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
@@ -1359,14 +1418,7 @@ int write_inode_now(struct inode *inode, int sync)
 		wbc.nr_to_write = 0;
 
 	might_sleep();
-	spin_lock(&wb->list_lock);
-	spin_lock(&inode->i_lock);
-	ret = writeback_single_inode(inode, wb, &wbc);
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&wb->list_lock);
-	if (sync)
-		inode_sync_wait(inode);
-	return ret;
+	return writeback_single_inode(inode, wb, &wbc);
 }
 EXPORT_SYMBOL(write_inode_now);
 
@@ -1383,15 +1435,7 @@ EXPORT_SYMBOL(write_inode_now);
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
-	int ret;
-
-	spin_lock(&wb->list_lock);
-	spin_lock(&inode->i_lock);
-	ret = writeback_single_inode(inode, wb, wbc);
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&wb->list_lock);
-	return ret;
+	return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc);
 }
 EXPORT_SYMBOL(sync_inode);