1 files changed, 108 insertions, 61 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 30ac305..2f76c4a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -26,15 +26,9 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
+#include <linux/tracepoint.h>
 #include "internal.h"
 
-#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
-
-/*
- * We don't actually have pdflush, but this one is exported though /proc...
- */
-int nr_pdflush_threads;
-
 /*
  * Passed into wb_writeback(), essentially a subset of writeback_control
  */
@@ -50,6 +44,21 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
+/*
+ * Include the creation of the trace points after defining the
+ * wb_writeback_work structure so that the definition remains local to this
+ * file.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/writeback.h>
+
+#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
+
+/*
+ * 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.
@@ -65,22 +74,21 @@ int writeback_in_progress(struct backing_dev_info *bdi)
 static void bdi_queue_work(struct backing_dev_info *bdi,
 		struct wb_writeback_work *work)
 {
-	spin_lock(&bdi->wb_lock);
-	list_add_tail(&work->list, &bdi->work_list);
-	spin_unlock(&bdi->wb_lock);
+	trace_writeback_queue(bdi, work);
 
-	/*
-	 * If the default thread isn't there, make sure we add it. When
-	 * it gets created and wakes up, we'll run this work.
-	 */
-	if (unlikely(list_empty_careful(&bdi->wb_list)))
+	spin_lock_bh(&bdi->wb_lock);
+	list_add_tail(&work->list, &bdi->work_list);
+	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.
+		 */
+		trace_writeback_nothread(bdi, work);
 		wake_up_process(default_backing_dev_info.wb.task);
-	else {
-		struct bdi_writeback *wb = &bdi->wb;
-
-		if (wb->task)
-			wake_up_process(wb->task);
 	}
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
@@ -95,8 +103,10 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	 */
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
-		if (bdi->wb.task)
+		if (bdi->wb.task) {
+			trace_writeback_nowork(bdi);
 			wake_up_process(bdi->wb.task);
+		}
 		return;
 	}
 
@@ -352,7 +362,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
 	spin_lock(&inode_lock);
 	inode->i_state &= ~I_SYNC;
-	if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
+	if (!(inode->i_state & I_FREEING)) {
 		if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
 			/*
 			 * More pages get dirtied by a fast dirtier.
@@ -499,7 +509,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 		if (inode_dirtied_after(inode, wbc->wb_start))
 			return 1;
 
-		BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
+		BUG_ON(inode->i_state & I_FREEING);
 		__iget(inode);
 		pages_skipped = wbc->pages_skipped;
 		writeback_single_inode(inode, wbc);
@@ -643,10 +653,14 @@ static long wb_writeback(struct bdi_writeback *wb,
 		wbc.more_io = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		wbc.pages_skipped = 0;
+
+		trace_wbc_writeback_start(&wbc, wb->bdi);
 		if (work->sb)
 			__writeback_inodes_sb(work->sb, wb, &wbc);
 		else
 			writeback_inodes_wb(wb, &wbc);
+		trace_wbc_writeback_written(&wbc, wb->bdi);
+
 		work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 		wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 
@@ -674,6 +688,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		if (!list_empty(&wb->b_more_io))  {
 			inode = list_entry(wb->b_more_io.prev,
 						struct inode, i_list);
+			trace_wbc_writeback_wait(&wbc, wb->bdi);
 			inode_wait_for_writeback(inode);
 		}
 		spin_unlock(&inode_lock);
@@ -686,17 +701,17 @@ static long wb_writeback(struct bdi_writeback *wb,
  * Return the next wb_writeback_work struct that hasn't been processed yet.
  */
 static struct wb_writeback_work *
-get_next_work_item(struct backing_dev_info *bdi, struct bdi_writeback *wb)
+get_next_work_item(struct backing_dev_info *bdi)
 {
 	struct wb_writeback_work *work = NULL;
 
-	spin_lock(&bdi->wb_lock);
+	spin_lock_bh(&bdi->wb_lock);
 	if (!list_empty(&bdi->work_list)) {
 		work = list_entry(bdi->work_list.next,
 				  struct wb_writeback_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock(&bdi->wb_lock);
+	spin_unlock_bh(&bdi->wb_lock);
 	return work;
 }
 
@@ -744,7 +759,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 	struct wb_writeback_work *work;
 	long wrote = 0;
 
-	while ((work = get_next_work_item(bdi, wb)) != NULL) {
+	while ((work = get_next_work_item(bdi)) != NULL) {
 		/*
 		 * Override sync mode, in case we must wait for completion
 		 * because this thread is exiting now.
@@ -752,6 +767,8 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 		if (force_wait)
 			work->sync_mode = WB_SYNC_ALL;
 
+		trace_writeback_exec(bdi, work);
+
 		wrote += wb_writeback(wb, work);
 
 		/*
@@ -776,47 +793,66 @@ 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.
  */
-int bdi_writeback_task(struct bdi_writeback *wb)
+int bdi_writeback_thread(void *data)
 {
-	unsigned long last_active = jiffies;
-	unsigned long wait_jiffies = -1UL;
+	struct bdi_writeback *wb = data;
+	struct backing_dev_info *bdi = wb->bdi;
 	long pages_written;
 
+	current->flags |= PF_FLUSHER | 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_should_stop()) {
+		/*
+		 * Remove own delayed wake-up timer, since we are already awake
+		 * and we'll take care of the preriodic write-back.
+		 */
+		del_timer(&wb->wakeup_timer);
+
 		pages_written = wb_do_writeback(wb, 0);
 
+		trace_writeback_pages_written(pages_written);
+
 		if (pages_written)
-			last_active = jiffies;
-		else if (wait_jiffies != -1UL) {
-			unsigned long max_idle;
+			wb->last_active = jiffies;
 
-			/*
-			 * Longest period of inactivity that we tolerate. If we
-			 * see dirty data again later, the task will get
-			 * recreated automatically.
-			 */
-			max_idle = max(5UL * 60 * HZ, wait_jiffies);
-			if (time_after(jiffies, max_idle + last_active))
-				break;
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!list_empty(&bdi->work_list)) {
+			__set_current_state(TASK_RUNNING);
+			continue;
 		}
 
-		if (dirty_writeback_interval) {
-			wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
-			schedule_timeout_interruptible(wait_jiffies);
-		} else {
-			set_current_state(TASK_INTERRUPTIBLE);
-			if (list_empty_careful(&wb->bdi->work_list) &&
-			    !kthread_should_stop())
-				schedule();
-			__set_current_state(TASK_RUNNING);
+		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();
 		}
 
 		try_to_freeze();
 	}
 
+	/* Flush any work that raced with us exiting */
+	if (!list_empty(&bdi->work_list))
+		wb_do_writeback(wb, 1);
+
+	trace_writeback_thread_stop(bdi);
 	return 0;
 }
 
+
 /*
  * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
  * the whole world.
@@ -891,6 +927,8 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct super_block *sb = inode->i_sb;
+	struct backing_dev_info *bdi = NULL;
+	bool wakeup_bdi = false;
 
 	/*
 	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
@@ -936,7 +974,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			if (hlist_unhashed(&inode->i_hash))
 				goto out;
 		}
-		if (inode->i_state & (I_FREEING|I_CLEAR))
+		if (inode->i_state & I_FREEING)
 			goto out;
 
 		/*
@@ -944,22 +982,31 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 * reposition it (that would break b_dirty time-ordering).
 		 */
 		if (!was_dirty) {
-			struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
-			struct backing_dev_info *bdi = wb->bdi;
-
-			if (bdi_cap_writeback_dirty(bdi) &&
-			    !test_bit(BDI_registered, &bdi->state)) {
-				WARN_ON(1);
-				printk(KERN_ERR "bdi-%s not registered\n",
-								bdi->name);
+			bdi = inode_to_bdi(inode);
+
+			if (bdi_cap_writeback_dirty(bdi)) {
+				WARN(!test_bit(BDI_registered, &bdi->state),
+				     "bdi-%s not registered\n", bdi->name);
+
+				/*
+				 * If this is the first dirty inode for this
+				 * bdi, we have to wake-up the corresponding
+				 * bdi thread to make sure background
+				 * write-back happens later.
+				 */
+				if (!wb_has_dirty_io(&bdi->wb))
+					wakeup_bdi = true;
 			}
 
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_list, &wb->b_dirty);
+			list_move(&inode->i_list, &bdi->wb.b_dirty);
 		}
 	}
 out:
 	spin_unlock(&inode_lock);
+
+	if (wakeup_bdi)
+		bdi_wakeup_thread_delayed(bdi);
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
@@ -1002,7 +1049,7 @@ static void wait_sb_inodes(struct super_block *sb)
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		struct address_space *mapping;
 
-		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
 			continue;
 		mapping = inode->i_mapping;
 		if (mapping->nrpages == 0)