[XFS] Ensure a frozen filesystem has a clean log before writing the dummy

record.

The current Linux XFS freeze code is a mess. We flush the metadata buffers
out while we are still allowing new transactions to start and then fail to
flush the dirty buffers back out before writing the unmount and dummy
records to the log.

This leads to problems when the frozen filesystem is used for snapshots -
we do log recovery on a readonly image and often it appears that the log
image in the snapshot is not correct. Hence we end up with hangs, oops and
mount failures when trying to mount a snapshot image that has been created
when the filesystem has not been correctly frozen.

To fix this, we need to move th metadata flush to after we wait for all
current transactions to complete in teh second stage of the freeze. This
means that when we write the final log records, the log should be clean
and recovery should never occur on a snapshot image created from a frozen
filesystem.

SGI-PV: 959267
SGI-Modid: xfs-linux-melb:xfs-kern:28010a
Signed-off-by: NDavid Chinner <dgc@sgi.com>
Signed-off-by: NDonald Douwsma <donaldd@sgi.com>
Signed-off-by: NTim Shimmin <tes@sgi.com>

fs/xfs/linux-2.6/xfs_super.c

@@ -659,9 +659,17 @@ xfs_fs_sync_super(
 	int			error;
 	int			flags;
 
-	if (unlikely(sb->s_frozen == SB_FREEZE_WRITE))
-		flags = SYNC_QUIESCE;
-	else
+	if (unlikely(sb->s_frozen == SB_FREEZE_WRITE)) {
+		/*
+		 * First stage of freeze - no more writers will make progress
+		 * now we are here, so we flush delwri and delalloc buffers
+		 * here, then wait for all I/O to complete.  Data is frozen at
+		 * that point. Metadata is not frozen, transactions can still
+		 * occur here so don't bother flushing the buftarg (i.e
+		 * SYNC_QUIESCE) because it'll just get dirty again.
+		 */
+		flags = SYNC_FSDATA | SYNC_DELWRI | SYNC_WAIT | SYNC_DIO_WAIT;
+	} else
 		flags = SYNC_FSDATA | (wait ? SYNC_WAIT : 0);
 
 	error = bhv_vfs_sync(vfsp, flags, NULL);

fs/xfs/linux-2.6/xfs_vfs.h

@@ -92,6 +92,7 @@ typedef enum {
 #define SYNC_REFCACHE		0x0040  /* prune some of the nfs ref cache */
 #define SYNC_REMOUNT		0x0080  /* remount readonly, no dummy LRs */
 #define SYNC_QUIESCE		0x0100  /* quiesce fileystem for a snapshot */
+#define SYNC_DIO_WAIT		0x0200  /* wait for direct I/O to complete */
 
 #define SHUTDOWN_META_IO_ERROR	0x0001	/* write attempt to metadata failed */
 #define SHUTDOWN_LOG_IO_ERROR	0x0002	/* write attempt to the log failed */

fs/xfs/xfs_vfsops.c

@@ -872,6 +872,10 @@ xfs_statvfs(
  *		       this by simply making sure the log gets flushed
  *		       if SYNC_BDFLUSH is set, and by actually writing it
  *		       out otherwise.
+ *	SYNC_DIO_WAIT - The caller wants us to wait for all direct I/Os
+ *		       as well to ensure all data I/O completes before we
+ *		       return. Forms the drain side of the write barrier needed
+ *		       to safely quiesce the filesystem.
  *
  */
 /*ARGSUSED*/
@@ -883,9 +887,6 @@ xfs_sync(
 {
 	xfs_mount_t	*mp = XFS_BHVTOM(bdp);
 
-	if (unlikely(flags == SYNC_QUIESCE))
-		return xfs_quiesce_fs(mp);
-	else
 	return xfs_syncsub(mp, flags, NULL);
 }
 
@@ -1172,6 +1173,12 @@ xfs_sync_inodes(
 			}
 
 		}
+		/*
+		 * When freezing, we need to wait ensure direct I/O is complete
+		 * as well to ensure all data modification is complete here
+		 */
+		if (flags & SYNC_DIO_WAIT)
+			vn_iowait(vp);
 
 		if (flags & SYNC_BDFLUSH) {
 			if ((flags & SYNC_ATTR) &&
@@ -1950,15 +1957,26 @@ xfs_showargs(
 	return 0;
 }
 
+/*
+ * Second stage of a freeze. The data is already frozen, now we have to take
+ * care of the metadata. New transactions are already blocked, so we need to
+ * wait for any remaining transactions to drain out before proceding.
+ */
 STATIC void
 xfs_freeze(
 	bhv_desc_t	*bdp)
 {
 	xfs_mount_t	*mp = XFS_BHVTOM(bdp);
 
+	/* wait for all modifications to complete */
 	while (atomic_read(&mp->m_active_trans) > 0)
 		delay(100);
 
+	/* flush inodes and push all remaining buffers out to disk */
+	xfs_quiesce_fs(mp);
+
+	BUG_ON(atomic_read(&mp->m_active_trans) > 0);
+
 	/* Push the superblock and write an unmount record */
 	xfs_log_unmount_write(mp);
 	xfs_unmountfs_writesb(mp);