fix for the ext3 data=journal unmount problem

fix for the ext3 data=journal unmount problem

[Andrew Morton]

Well here's what I have, for 2.4.20:

- Add a new super_block operation `sync_fs'.  It is called when the
  VFS wants to sync the filesystem for "data integrity" purposes.
  That's sys_sync and unmount.

- Implement ext3_sync_fs().  It runs a commit and waits on it.

  Which is cheating, really - there's still unwritten data.  But
  we "know" that the VFS will write that.

ext3_write_super() is used on the kupdate path, and is nonblocking.



 fs/buffer.c        |    6 ++++--
 fs/ext3/super.c    |   25 +++++++++++++------------
 fs/super.c         |    6 +++++-
 include/linux/fs.h |    3 ++-
 4 files changed, 24 insertions(+), 16 deletions(-)

--- linux-akpm/fs/buffer.c~sync_fs	Tue Dec  3 12:08:59 2002
+++ linux-akpm-akpm/fs/buffer.c	Tue Dec  3 12:09:54 2002
@@ -327,6 +327,8 @@ int fsync_super(struct super_block *sb)
 	lock_super(sb);
 	if (sb->s_dirt && sb->s_op && sb->s_op->write_super)
 		sb->s_op->write_super(sb);
+	if (sb->s_op && sb->s_op->sync_fs)
+		sb->s_op->sync_fs(sb);
 	unlock_super(sb);
 	unlock_kernel();
 
@@ -346,7 +348,7 @@ int fsync_dev(kdev_t dev)
 	lock_kernel();
 	sync_inodes(dev);
 	DQUOT_SYNC(dev);
-	sync_supers(dev);
+	sync_supers(dev, 1);
 	unlock_kernel();
 
 	return sync_buffers(dev, 1);
@@ -2833,7 +2835,7 @@ static int sync_old_buffers(void)
 {
 	lock_kernel();
 	sync_unlocked_inodes();
-	sync_supers(0);
+	sync_supers(0, 0);
 	unlock_kernel();
 
 	for (;;) {
--- linux-akpm/include/linux/fs.h~sync_fs	Tue Dec  3 12:08:59 2002
+++ linux-akpm-akpm/include/linux/fs.h	Tue Dec  3 21:02:03 2002
@@ -894,6 +894,7 @@ struct super_operations {
 	void (*delete_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	void (*write_super) (struct super_block *);
+	int (*sync_fs) (struct super_block *);
 	void (*write_super_lockfs) (struct super_block *);
 	void (*unlockfs) (struct super_block *);
 	int (*statfs) (struct super_block *, struct statfs *);
@@ -1240,7 +1241,7 @@ static inline int fsync_inode_data_buffe
 extern int inode_has_buffers(struct inode *);
 extern int filemap_fdatasync(struct address_space *);
 extern int filemap_fdatawait(struct address_space *);
-extern void sync_supers(kdev_t);
+extern void sync_supers(kdev_t dev, int wait);
 extern int bmap(struct inode *, int);
 extern int notify_change(struct dentry *, struct iattr *);
 extern int permission(struct inode *, int);
--- linux-akpm/fs/super.c~sync_fs	Tue Dec  3 12:08:59 2002
+++ linux-akpm-akpm/fs/super.c	Tue Dec  3 12:10:24 2002
@@ -445,7 +445,7 @@ static inline void write_super(struct su
  * hold up the sync while mounting a device. (The newly
  * mounted device won't need syncing.)
  */
-void sync_supers(kdev_t dev)
+void sync_supers(kdev_t dev, int wait)
 {
 	struct super_block * sb;
 
@@ -454,6 +454,8 @@ void sync_supers(kdev_t dev)
 		if (sb) {
 			if (sb->s_dirt)
 				write_super(sb);
+			if (wait && sb->s_op && sb->s_op->sync_fs)
+				sb->s_op->sync_fs(sb);
 			drop_super(sb);
 		}
 		return;
@@ -467,6 +469,8 @@ restart:
 			spin_unlock(&sb_lock);
 			down_read(&sb->s_umount);
 			write_super(sb);
+			if (wait && sb->s_op && sb->s_op->sync_fs)
+				sb->s_op->sync_fs(sb);
 			drop_super(sb);
 			goto restart;
 		} else
--- linux-akpm/fs/ext3/super.c~sync_fs	Tue Dec  3 21:12:57 2002
+++ linux-akpm-akpm/fs/ext3/super.c	Tue Dec  3 21:13:04 2002
@@ -47,6 +47,8 @@ static void ext3_mark_recovery_complete(
 static void ext3_clear_journal_err(struct super_block * sb,
 				   struct ext3_super_block * es);
 
+static int ext3_sync_fs(struct super_block * sb);
+
 #ifdef CONFIG_JBD_DEBUG
 int journal_no_write[2];
 
@@ -454,6 +456,7 @@ static struct super_operations ext3_sops
 	delete_inode:	ext3_delete_inode,	/* BKL not held.  We take it */
 	put_super:	ext3_put_super,		/* BKL held */
 	write_super:	ext3_write_super,	/* BKL held */
+	sync_fs:	ext3_sync_fs,
 	write_super_lockfs: ext3_write_super_lockfs, /* BKL not held. Take it */
 	unlockfs:	ext3_unlockfs,		/* BKL not held.  We take it */
 	statfs:		ext3_statfs,		/* BKL held */
@@ -1577,24 +1580,22 @@ int ext3_force_commit(struct super_block
  * This implicitly triggers the writebehind on sync().
  */
 
-static int do_sync_supers = 0;
-MODULE_PARM(do_sync_supers, "i");
-MODULE_PARM_DESC(do_sync_supers, "Write superblocks synchronously");
-
 void ext3_write_super (struct super_block * sb)
 {
+	if (down_trylock(&sb->s_lock) == 0)
+		BUG();
+	sb->s_dirt = 0;
+	log_start_commit(EXT3_SB(sb)->s_journal, NULL);
+}
+
+static int ext3_sync_fs(struct super_block *sb)
+{
 	tid_t target;
 	
-	if (down_trylock(&sb->s_lock) == 0)
-		BUG();		/* aviro detector */
 	sb->s_dirt = 0;
 	target = log_start_commit(EXT3_SB(sb)->s_journal, NULL);
-
-	if (do_sync_supers) {
-		unlock_super(sb);
-		log_wait_commit(EXT3_SB(sb)->s_journal, target);
-		lock_super(sb);
-	}
+	log_wait_commit(EXT3_SB(sb)->s_journal, target);
+	return 0;
 }
 
 /*

_

Re: fix for the ext3 data=journal unmount problem

[Stephen C. Tweedie]

Hi,

On Wed, 2002-12-04 at 05:27, Andrew Morton wrote:

> Well here's what I have, for 2.4.20:

Looks good, and fixes the problem in testing.

Cheers,
 Stephen



-------------------------------------------------------
This sf.net email is sponsored by:ThinkGeek
Welcome to geek heaven.
http://thinkgeek.com/sf

Re: [Ext2-devel] fix for the ext3 data=journal unmount problem

[Stephen C. Tweedie]

Hi,

On Thu, 2002-12-05 at 16:34, Stephen C. Tweedie wrote:

> Looks good, and fixes the problem in testing.

In the absense of other comments, I've forwarded it to Marcelo.

Cheers,
 Stephen