1 files changed, 106 insertions, 117 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3e3422f7f0a..be568b7311d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -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"
 
 /*
@@ -46,6 +46,7 @@ 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 */
@@ -69,7 +70,7 @@ 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;
@@ -88,18 +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,
@@ -108,10 +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);
 }
 
@@ -127,10 +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;
 	}
 
@@ -177,9 +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);
 }
 
 /*
@@ -270,11 +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 */
@@ -318,8 +317,14 @@ 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;
 }
 
@@ -450,14 +455,18 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
 	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;
@@ -517,13 +526,16 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	}
 	WARN_ON(inode->i_state & I_SYNC);
 	/*
-	 * Skip inode if it is clean. 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.
+	 * 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))
+	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);
@@ -590,6 +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,
@@ -731,7 +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 = {
@@ -971,7 +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;
@@ -979,12 +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);
 
@@ -1012,66 +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.
@@ -1080,10 +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) {
@@ -1150,8 +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);
 	}
 
 	/*
@@ -1200,6 +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);
@@ -1214,8 +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);
@@ -1332,47 +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_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
@@ -1391,6 +1379,7 @@ void sync_inodes_sb(struct super_block *sb)
 		.range_cyclic	= 0,
 		.done		= &done,
 		.reason		= WB_REASON_SYNC,
+		.for_sync	= 1,
 	};
 
 	/* Nothing to do? */