[PATCH] Add a sync_fs super_block operation

This is infrastructure for fixing the journalled-data ext3 unmount data
loss problem. It was sent for comment to linux-fsdevel a week ago; there
was none.

Add a `sync_fs' superblock operation whose mandate is to perform
filesystem-specific operations to ensure a successful sync.

It is called in two places:

1: fsync_super() - for umount.

2: sys_sync() - for global sync.

In the sys_sync() case we call all the ->write_super() methods first.
write_super() is an async flushing operation.  It should not block.

After that, we call all the ->sync_fs functions.  This is independent
of the state of s_dirt!  That was all confused up before, and in this
patch ->write_super() and ->sync_fs() are quite separate.

With ext3 as an example, the initial ->write_super() will start a
transaction, but will not wait on it.  (But only if s_dirt was set!)

The first ->sync_fs() call will get the IO underway.

The second ->sync_fs() call will wait on the IO.

And we really do need to be this elaborate, because all the testing of
s_dirt in there makes ->write_super() an unreliable way of detecting
when the VFS is trying to sync the filesystem.

Documentation/filesystems/Locking

@@ -92,6 +92,7 @@ prototypes:
 	void (*delete_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	void (*write_super) (struct super_block *);
+	void (*sync_fs) (struct super_block *sb, int wait);
 	int (*statfs) (struct super_block *, struct statfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
 	void (*clear_inode) (struct inode *);
@@ -108,6 +109,7 @@ delete_inode:	no
 clear_inode:	no	
 put_super:	yes	yes	maybe		(see below)
 write_super:	no	yes	maybe		(see below)
+sync_fs:	no	no	maybe		(see below)
 statfs:		no	no	no
 remount_fs:	yes	yes	maybe		(see below)
 umount_begin:	yes	no	maybe		(see below)

fs/buffer.c

@@ -221,6 +221,9 @@ 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, 1);
+	}
 	unlock_super(sb);
 	sync_blockdev(sb->s_bdev);
 	sync_inodes_sb(sb, 1);
@@ -251,10 +254,12 @@ int fsync_bdev(struct block_device *bdev)
 asmlinkage long sys_sync(void)
 {
 	wakeup_bdflush(0);
-	sync_inodes(0);	/* All mappings and inodes, including block devices */
+	sync_inodes(0);		/* All mappings, inodes and their blockdevs */
 	DQUOT_SYNC(NULL);
-	sync_supers();	/* Write the superblocks */
-	sync_inodes(1);	/* All the mappings and inodes, again. */
+	sync_supers();		/* Write the superblocks */
+	sync_filesystems(0);	/* Start syncing the filesystems */
+	sync_filesystems(1);	/* Waitingly sync the filesystems */
+	sync_inodes(1);		/* Mappings, inodes and blockdevs, again. */
 	return 0;
 }
 

fs/super.c

@@ -189,6 +189,8 @@ void generic_shutdown_super(struct super_block *sb)
 		if (sop) {
 			if (sop->write_super && sb->s_dirt)
 				sop->write_super(sb);
+			if (sop->sync_fs)
+				sop->sync_fs(sb, 1);
 			if (sop->put_super)
 				sop->put_super(sb);
 		}
@@ -266,8 +268,8 @@ void drop_super(struct super_block *sb)
 static inline void write_super(struct super_block *sb)
 {
 	lock_super(sb);
-	if (sb->s_root && sb->s_dirt)
-		if (sb->s_op && sb->s_op->write_super)
+	if (sb->s_op && sb->s_root && sb->s_dirt)
+		if (sb->s_op->write_super)
 			sb->s_op->write_super(sb);
 	unlock_super(sb);
 }
@@ -296,6 +298,46 @@ void sync_supers(void)
 	spin_unlock(&sb_lock);
 }
 
+/*
+ * Call the ->sync_fs super_op against all filesytems which are r/w and
+ * which implement it.
+ */
+void sync_filesystems(int wait)
+{
+	struct super_block * sb;
+
+	spin_lock(&sb_lock);
+	for (sb = sb_entry(super_blocks.next); sb != sb_entry(&super_blocks);
+			sb = sb_entry(sb->s_list.next)) {
+		if (!sb->s_op)
+			continue;
+		if (!sb->s_op->sync_fs);
+			continue;
+		if (sb->s_flags & MS_RDONLY)
+			continue;
+		sb->s_need_sync_fs = 1;
+	}
+	spin_unlock(&sb_lock);
+
+restart:
+	spin_lock(&sb_lock);
+	for (sb = sb_entry(super_blocks.next); sb != sb_entry(&super_blocks);
+			sb = sb_entry(sb->s_list.next)) {
+		if (!sb->s_need_sync_fs)
+			continue;
+		sb->s_need_sync_fs = 0;
+		if (sb->s_flags & MS_RDONLY)
+			continue;	/* hm.  Was remounted r/w meanwhile */
+		sb->s_count++;
+		spin_unlock(&sb_lock);
+		down_read(&sb->s_umount);
+		sb->s_op->sync_fs(sb, wait);
+		drop_super(sb);
+		goto restart;
+	}
+	spin_unlock(&sb_lock);
+}
+
 /**
  *	get_super	-	get the superblock of a device
  *	@dev: device to get the superblock for

include/linux/fs.h

@@ -631,6 +631,7 @@ struct super_block {
 	struct semaphore	s_lock;
 	int			s_count;
 	int			s_syncing;
+	int			s_need_sync_fs;
 	atomic_t		s_active;
 	void                    *s_security;
 
@@ -810,6 +811,7 @@ 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 *sb, int wait);
 	void (*write_super_lockfs) (struct super_block *);
 	void (*unlockfs) (struct super_block *);
 	int (*statfs) (struct super_block *, struct statfs *);
@@ -1143,6 +1145,7 @@ extern void write_inode_now(struct inode *, int);
 extern int filemap_fdatawrite(struct address_space *);
 extern int filemap_fdatawait(struct address_space *);
 extern void sync_supers(void);
+extern void sync_filesystems(int wait);
 extern sector_t bmap(struct inode *, sector_t);
 extern int setattr_mask(unsigned int);
 extern int notify_change(struct dentry *, struct iattr *);