Merge tag 'lazytime_fix' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull lazytime fixes from Ted Ts'o:
 "This fixes a problem in the lazy time patches, which can cause
  frequently updated inods to never have their timestamps updated.

  These changes guarantee that no timestamp on disk will be stale by
  more than 24 hours"

* tag 'lazytime_fix' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  fs: add dirtytime_expire_seconds sysctl
  fs: make sure the timestamps for lazytime inodes eventually get written

4 files changed, 95 insertions, 10 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e907052eeadb..32a8bbd7a9ad 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -53,6 +53,18 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
+/*
+ * If an inode is constantly having its pages dirtied, but then the
+ * updates stop dirtytime_expire_interval seconds in the past, it's
+ * possible for the worst case time between when an inode has its
+ * timestamps updated and when they finally get written out to be two
+ * dirtytime_expire_intervals.  We set the default to 12 hours (in
+ * seconds), which means most of the time inodes will have their
+ * timestamps written to disk after 12 hours, but in the worst case a
+ * few inodes might not their timestamps updated for 24 hours.
+ */
+unsigned int dirtytime_expire_interval = 12 * 60 * 60;
+
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
@@ -275,8 +287,8 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 
 	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
 		older_than_this = work->older_than_this;
-	else if ((work->reason == WB_REASON_SYNC) == 0) {
-		expire_time = jiffies - (HZ * 86400);
+	else if (!work->for_sync) {
+		expire_time = jiffies - (dirtytime_expire_interval * HZ);
 		older_than_this = &expire_time;
 	}
 	while (!list_empty(delaying_queue)) {
@@ -458,6 +470,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 */
 		redirty_tail(inode, wb);
 	} else if (inode->i_state & I_DIRTY_TIME) {
+		inode->dirtied_when = jiffies;
 		list_move(&inode->i_wb_list, &wb->b_dirty_time);
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
@@ -505,12 +518,17 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	spin_lock(&inode->i_lock);
 
 	dirty = inode->i_state & I_DIRTY;
-	if (((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) &&
-	     (inode->i_state & I_DIRTY_TIME)) ||
-	    (inode->i_state & I_DIRTY_TIME_EXPIRED)) {
-		dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
-		trace_writeback_lazytime(inode);
-	}
+	if (inode->i_state & I_DIRTY_TIME) {
+		if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
+		    unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
+		    unlikely(time_after(jiffies,
+					(inode->dirtied_time_when +
+					 dirtytime_expire_interval * HZ)))) {
+			dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
+			trace_writeback_lazytime(inode);
+		}
+	} else
+		inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
 	inode->i_state &= ~dirty;
 
 	/*
@@ -1131,6 +1149,56 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
 	rcu_read_unlock();
 }
 
+/*
+ * Wake up bdi's periodically to make sure dirtytime inodes gets
+ * written back periodically.  We deliberately do *not* check the
+ * b_dirtytime list in wb_has_dirty_io(), since this would cause the
+ * kernel to be constantly waking up once there are any dirtytime
+ * inodes on the system.  So instead we define a separate delayed work
+ * function which gets called much more rarely.  (By default, only
+ * once every 12 hours.)
+ *
+ * If there is any other write activity going on in the file system,
+ * this function won't be necessary.  But if the only thing that has
+ * happened on the file system is a dirtytime inode caused by an atime
+ * update, we need this infrastructure below to make sure that inode
+ * eventually gets pushed out to disk.
+ */
+static void wakeup_dirtytime_writeback(struct work_struct *w);
+static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback);
+
+static void wakeup_dirtytime_writeback(struct work_struct *w)
+{
+	struct backing_dev_info *bdi;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
+		if (list_empty(&bdi->wb.b_dirty_time))
+			continue;
+		bdi_wakeup_thread(bdi);
+	}
+	rcu_read_unlock();
+	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
+}
+
+static int __init start_dirtytime_writeback(void)
+{
+	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
+	return 0;
+}
+__initcall(start_dirtytime_writeback);
+
+int dirtytime_interval_handler(struct ctl_table *table, int write,
+			       void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		mod_delayed_work(system_wq, &dirtytime_work, 0);
+	return ret;
+}
+
 static noinline void block_dump___mark_inode_dirty(struct inode *inode)
 {
 	if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
@@ -1269,8 +1337,13 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			}
 
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_wb_list, dirtytime ?
-				  &bdi->wb.b_dirty_time : &bdi->wb.b_dirty);
+			if (dirtytime)
+				inode->dirtied_time_when = jiffies;
+			if (inode->i_state & (I_DIRTY_INODE | I_DIRTY_PAGES))
+				list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
+			else
+				list_move(&inode->i_wb_list,
+					  &bdi->wb.b_dirty_time);
 			spin_unlock(&bdi->wb.list_lock);
 			trace_writeback_dirty_inode_enqueue(inode);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b4d71b5e1ff2..f4131e8ead74 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -604,6 +604,7 @@ struct inode {
 	struct mutex		i_mutex;
 
 	unsigned long		dirtied_when;	/* jiffies of first dirtying */
+	unsigned long		dirtied_time_when;
 
 	struct hlist_node	i_hash;
 	struct list_head	i_wb_list;	/* backing dev IO list */
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 00048339c23e..b2dd371ec0ca 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -130,6 +130,7 @@ extern int vm_dirty_ratio;
 extern unsigned long vm_dirty_bytes;
 extern unsigned int dirty_writeback_interval;
 extern unsigned int dirty_expire_interval;
+extern unsigned int dirtytime_expire_interval;
 extern int vm_highmem_is_dirtyable;
 extern int block_dump;
 extern int laptop_mode;
@@ -146,6 +147,8 @@ extern int dirty_ratio_handler(struct ctl_table *table, int write,
 extern int dirty_bytes_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
+int dirtytime_interval_handler(struct ctl_table *table, int write,
+			       void __user *buffer, size_t *lenp, loff_t *ppos);
 
 struct ctl_table;
 int dirty_writeback_centisecs_handler(struct ctl_table *, int,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 88ea2d6e0031..ce410bb9f2e1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1228,6 +1228,14 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &zero,
 	},
 	{
+		.procname	= "dirtytime_expire_seconds",
+		.data		= &dirtytime_expire_interval,
+		.maxlen		= sizeof(dirty_expire_interval),
+		.mode		= 0644,
+		.proc_handler	= dirtytime_interval_handler,
+		.extra1		= &zero,
+	},
+	{
 		.procname       = "nr_pdflush_threads",
 		.mode           = 0444 /* read-only */,
 		.proc_handler   = pdflush_proc_obsolete,