1 files changed, 64 insertions, 19 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 206a68b1db1a..592cea54cea0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -33,7 +33,7 @@
 /*
  * 4MB minimal write chunk size
  */
-#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))
+#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_SHIFT - 10))
 
 struct wb_completion {
 	atomic_t		cnt;
@@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi,
 #define WB_FRN_HIST_MAX_SLOTS	(WB_FRN_HIST_THR_SLOTS / 2 + 1)
 					/* one round can affect upto 5 slots */
 
+static atomic_t isw_nr_in_flight = ATOMIC_INIT(0);
+static struct workqueue_struct *isw_wq;
+
 void __inode_attach_wb(struct inode *inode, struct page *page)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -278,13 +281,15 @@ locked_inode_to_wb_and_lock_list(struct inode *inode)
 		wb_get(wb);
 		spin_unlock(&inode->i_lock);
 		spin_lock(&wb->list_lock);
-		wb_put(wb);		/* not gonna deref it anymore */
 
 		/* i_wb may have changed inbetween, can't use inode_to_wb() */
-		if (likely(wb == inode->i_wb))
-			return wb;	/* @inode already has ref */
+		if (likely(wb == inode->i_wb)) {
+			wb_put(wb);	/* @inode already has ref */
+			return wb;
+		}
 
 		spin_unlock(&wb->list_lock);
+		wb_put(wb);
 		cpu_relax();
 		spin_lock(&inode->i_lock);
 	}
@@ -424,6 +429,8 @@ skip_switch:
 
 	iput(inode);
 	kfree(isw);
+
+	atomic_dec(&isw_nr_in_flight);
 }
 
 static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
@@ -433,7 +440,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
 
 	/* needs to grab bh-unsafe locks, bounce to work item */
 	INIT_WORK(&isw->work, inode_switch_wbs_work_fn);
-	schedule_work(&isw->work);
+	queue_work(isw_wq, &isw->work);
 }
 
 /**
@@ -469,7 +476,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 
 	/* while holding I_WB_SWITCH, no one else can update the association */
 	spin_lock(&inode->i_lock);
-	if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
+	if (!(inode->i_sb->s_flags & MS_ACTIVE) ||
+	    inode->i_state & (I_WB_SWITCH | I_FREEING) ||
 	    inode_to_wb(inode) == isw->new_wb) {
 		spin_unlock(&inode->i_lock);
 		goto out_free;
@@ -480,6 +488,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	ihold(inode);
 	isw->inode = inode;
 
+	atomic_inc(&isw_nr_in_flight);
+
 	/*
 	 * In addition to synchronizing among switchers, I_WB_SWITCH tells
 	 * the RCU protected stat update paths to grab the mapping's
@@ -677,9 +687,7 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page,
 	if (!wbc->wb)
 		return;
 
-	rcu_read_lock();
 	id = mem_cgroup_css_from_page(page)->id;
-	rcu_read_unlock();
 
 	if (id == wbc->wb_id) {
 		wbc->wb_bytes += bytes;
@@ -842,6 +850,33 @@ restart:
 		wb_put(last_wb);
 }
 
+/**
+ * cgroup_writeback_umount - flush inode wb switches for umount
+ *
+ * This function is called when a super_block is about to be destroyed and
+ * flushes in-flight inode wb switches.  An inode wb switch goes through
+ * RCU and then workqueue, so the two need to be flushed in order to ensure
+ * that all previously scheduled switches are finished.  As wb switches are
+ * rare occurrences and synchronize_rcu() can take a while, perform
+ * flushing iff wb switches are in flight.
+ */
+void cgroup_writeback_umount(void)
+{
+	if (atomic_read(&isw_nr_in_flight)) {
+		synchronize_rcu();
+		flush_workqueue(isw_wq);
+	}
+}
+
+static int __init cgroup_writeback_init(void)
+{
+	isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0);
+	if (!isw_wq)
+		return -ENOMEM;
+	return 0;
+}
+fs_initcall(cgroup_writeback_init);
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static struct bdi_writeback *
@@ -1304,10 +1339,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
  * 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)
+static int writeback_single_inode(struct inode *inode,
+				  struct writeback_control *wbc)
 {
+	struct bdi_writeback *wb;
 	int ret = 0;
 
 	spin_lock(&inode->i_lock);
@@ -1345,7 +1380,8 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	ret = __writeback_single_inode(inode, wbc);
 
 	wbc_detach_inode(wbc);
-	spin_lock(&wb->list_lock);
+
+	wb = inode_to_wb_and_lock_list(inode);
 	spin_lock(&inode->i_lock);
 	/*
 	 * If inode is clean, remove it from writeback lists. Otherwise don't
@@ -1420,6 +1456,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
+		struct bdi_writeback *tmp_wb;
 
 		if (inode->i_sb != sb) {
 			if (work->sb) {
@@ -1510,15 +1547,23 @@ static long writeback_sb_inodes(struct super_block *sb,
 			cond_resched();
 		}
 
-
-		spin_lock(&wb->list_lock);
+		/*
+		 * Requeue @inode if still dirty.  Be careful as @inode may
+		 * have been switched to another wb in the meantime.
+		 */
+		tmp_wb = inode_to_wb_and_lock_list(inode);
 		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY_ALL))
 			wrote++;
-		requeue_inode(inode, wb, &wbc);
+		requeue_inode(inode, tmp_wb, &wbc);
 		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
 
+		if (unlikely(tmp_wb != wb)) {
+			spin_unlock(&tmp_wb->list_lock);
+			spin_lock(&wb->list_lock);
+		}
+
 		/*
 		 * bail out to wb_writeback() often enough to check
 		 * background threshold and other termination conditions.
@@ -1981,9 +2026,9 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
  * page->mapping->host, so the page-dirtying time is recorded in the internal
  * blockdev inode.
  */
-#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
+#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 	struct super_block *sb = inode->i_sb;
 	int dirtytime;
 
@@ -2093,6 +2138,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 out_unlock_inode:
 	spin_unlock(&inode->i_lock);
 
+#undef I_DIRTY_INODE
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
@@ -2304,7 +2350,6 @@ EXPORT_SYMBOL(sync_inodes_sb);
  */
 int write_inode_now(struct inode *inode, int sync)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
 		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
@@ -2316,7 +2361,7 @@ int write_inode_now(struct inode *inode, int sync)
 		wbc.nr_to_write = 0;
 
 	might_sleep();
-	return writeback_single_inode(inode, wb, &wbc);
+	return writeback_single_inode(inode, &wbc);
 }
 EXPORT_SYMBOL(write_inode_now);
 
@@ -2333,7 +2378,7 @@ EXPORT_SYMBOL(write_inode_now);
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc);
+	return writeback_single_inode(inode, wbc);
 }
 EXPORT_SYMBOL(sync_inode);