1 files changed, 89 insertions, 121 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 41a3ccff18d8..68851ff2fd41 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -22,7 +22,6 @@
 #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>
@@ -46,17 +45,13 @@ 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.
@@ -68,6 +63,7 @@ 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)
 {
@@ -92,20 +88,6 @@ 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)
-{
-	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);
-	}
-}
-
 static void bdi_queue_work(struct backing_dev_info *bdi,
 			   struct wb_writeback_work *work)
 {
@@ -113,10 +95,9 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 
 	spin_lock_bh(&bdi->wb_lock);
 	list_add_tail(&work->list, &bdi->work_list);
-	if (!bdi->wb.task)
-		trace_writeback_nothread(bdi, work);
-	bdi_wakeup_flusher(bdi);
 	spin_unlock_bh(&bdi->wb_lock);
+
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 }
 
 static void
@@ -131,10 +112,8 @@ __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);
+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 		return;
 	}
 
@@ -181,9 +160,7 @@ 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);
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 }
 
 /*
@@ -232,6 +209,8 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 static void inode_sync_complete(struct inode *inode)
 {
 	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);
@@ -253,7 +232,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 }
 
 /*
- * Move expired (dirtied after work->older_than_this) dirty inodes from
+ * 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,
@@ -320,8 +299,14 @@ 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;
 }
 
@@ -443,8 +428,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
  * setting I_SYNC flag and calling inode_sync_complete() to clear it.
  */
 static int
-__writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
-			 struct writeback_control *wbc)
+__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;
@@ -453,14 +437,18 @@ __writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 
 	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;
@@ -531,7 +519,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	inode->i_state |= I_SYNC;
 	spin_unlock(&inode->i_lock);
 
-	ret = __writeback_single_inode(inode, wb, wbc);
+	ret = __writeback_single_inode(inode, wbc);
 
 	spin_lock(&wb->list_lock);
 	spin_lock(&inode->i_lock);
@@ -582,10 +570,6 @@ 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,
@@ -597,6 +581,7 @@ 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,
@@ -628,8 +613,8 @@ 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);
@@ -678,7 +663,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		 * 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, wb, &wbc);
+		__writeback_single_inode(inode, &wbc);
 
 		work->nr_pages -= write_chunk - wbc.nr_to_write;
 		wrote += write_chunk - wbc.nr_to_write;
@@ -978,7 +963,7 @@ 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;
@@ -986,12 +971,6 @@ 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);
 
@@ -1019,66 +998,49 @@ 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() ||
+		   list_empty(&bdi->bdi_list))) {
 		/*
-		 * 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);
+	if (!list_empty(&bdi->work_list) ||
+	    (wb_has_dirty_io(wb) && dirty_writeback_interval))
+		queue_delayed_work(bdi_wq, &wb->dwork,
+			msecs_to_jiffies(dirty_writeback_interval * 10));
 
-	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.
@@ -1157,8 +1119,12 @@ 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);
 	}
 
 	/*
@@ -1315,6 +1281,8 @@ 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);
@@ -1337,47 +1305,43 @@ 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_nr_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
@@ -1396,8 +1360,12 @@ 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);