New VFS-lock patch (from 4/1/2004).
- Replaces patch 8 from 2.6.5-rc1-udm1.

--- diff/fs/block_dev.c	2004-04-06 15:54:23.025006488 +0100
+++ source/fs/block_dev.c	2004-04-06 15:54:25.088692760 +0100
@@ -251,6 +251,7 @@ static void init_once(void * foo, kmem_c
 	{
 		memset(bdev, 0, sizeof(*bdev));
 		sema_init(&bdev->bd_sem, 1);
+		sema_init(&bdev->bd_mount_sem, 1);
 		INIT_LIST_HEAD(&bdev->bd_inodes);
 		INIT_LIST_HEAD(&bdev->bd_list);
 		inode_init_once(&ei->vfs_inode);
--- diff/fs/buffer.c	2004-04-06 15:54:23.027006184 +0100
+++ source/fs/buffer.c	2004-04-06 15:54:25.089692608 +0100
@@ -264,6 +264,73 @@ int fsync_bdev(struct block_device *bdev
 }
 
 /*
+ * triggered by the device mapper code to lock a filesystem and force
+ * it into a consistent state.
+ *
+ * This takes the block device bd_mount_sem to make sure no new mounts
+ * happen on bdev until unlockfs is called.  If a super is found on this
+ * block device, we hould a read lock on the s->s_umount sem to make sure
+ * nobody unmounts until the snapshot creation is done
+ */
+struct super_block *freeze_bdev(struct block_device *bdev)
+{
+	struct super_block *sb;
+
+	if (!bdev)
+		return NULL;
+	down(&bdev->bd_mount_sem);
+	sb = get_super(bdev);
+	if (sb && !(sb->s_flags & MS_RDONLY)) {
+		sb->s_frozen = SB_FREEZE_WRITE;
+		wmb();
+
+		sync_inodes_sb(sb, 0);
+		DQUOT_SYNC(sb);
+
+		sb->s_frozen = SB_FREEZE_TRANS;
+		wmb();
+		
+		lock_super(sb);
+		if (sb->s_dirt && sb->s_op->write_super)
+			sb->s_op->write_super(sb);
+		unlock_super(sb);
+
+		if (sb->s_op->sync_fs)
+			sb->s_op->sync_fs(sb, 1);
+	
+		sync_blockdev(sb->s_bdev);
+		sync_inodes_sb(sb, 1);
+		sync_blockdev(sb->s_bdev);
+
+		if (sb->s_op->write_super_lockfs)
+			sb->s_op->write_super_lockfs(sb);
+	}
+
+	sync_blockdev(bdev);
+	return sb;	/* thaw_bdev releases s->s_umount and bd_mount_sem */
+}
+EXPORT_SYMBOL(freeze_bdev);
+
+void thaw_bdev(struct block_device *bdev, struct super_block *sb)
+{
+	if (!bdev)
+		return;
+	if (sb) {
+		BUG_ON(sb->s_bdev != bdev);
+
+		if (sb->s_op->unlockfs)
+			sb->s_op->unlockfs(sb);
+		sb->s_frozen = SB_UNFROZEN;
+		wmb();
+		wake_up(&sb->s_wait_unfrozen);
+		drop_super(sb);
+	}
+
+	up(&bdev->bd_mount_sem);
+}
+EXPORT_SYMBOL(thaw_bdev);
+
+/*
  * sync everything.  Start out by waking pdflush, because that writes back
  * all queues in parallel.
  */
--- diff/fs/super.c	2004-04-06 15:54:23.028006032 +0100
+++ source/fs/super.c	2004-04-06 15:54:25.090692456 +0100
@@ -78,6 +78,7 @@ static struct super_block *alloc_super(v
 		sema_init(&s->s_dquot.dqio_sem, 1);
 		sema_init(&s->s_dquot.dqonoff_sem, 1);
 		init_rwsem(&s->s_dquot.dqptr_sem);
+		init_waitqueue_head(&s->s_wait_unfrozen);
 		s->s_maxbytes = MAX_NON_LFS;
 		s->dq_op = sb_dquot_ops;
 		s->s_qcop = sb_quotactl_ops;
@@ -622,7 +623,14 @@ struct super_block *get_sb_bdev(struct f
 	if (IS_ERR(bdev))
 		return (struct super_block *)bdev;
 
+	/*
+	 * once the super is inserted into the list by sget, s_umount
+	 * will protect the lockfs code from trying to start a snapshot
+	 * while we are mounting
+	 */
+	down(&bdev->bd_mount_sem);
 	s = sget(fs_type, test_bdev_super, set_bdev_super, bdev);
+	up(&bdev->bd_mount_sem);
 	if (IS_ERR(s))
 		goto out;
 
--- diff/include/linux/buffer_head.h	2004-04-06 15:54:23.029005880 +0100
+++ source/include/linux/buffer_head.h	2004-04-06 15:54:25.090692456 +0100
@@ -164,6 +164,8 @@ void __wait_on_buffer(struct buffer_head
 wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
 void wake_up_buffer(struct buffer_head *bh);
 int fsync_bdev(struct block_device *);
+struct super_block *freeze_bdev(struct block_device *);
+void thaw_bdev(struct block_device *, struct super_block *);
 int fsync_super(struct super_block *);
 int fsync_no_super(struct block_device *);
 struct buffer_head *__find_get_block(struct block_device *, sector_t, int);
--- diff/include/linux/fs.h	2004-04-06 15:54:23.030005728 +0100
+++ source/include/linux/fs.h	2004-04-06 15:54:25.091692304 +0100
@@ -345,6 +345,7 @@ struct block_device {
 	struct inode *		bd_inode;	/* will die */
 	int			bd_openers;
 	struct semaphore	bd_sem;	/* open/close mutex */
+	struct semaphore	bd_mount_sem;	/* mount mutex */
 	struct list_head	bd_inodes;
 	void *			bd_holder;
 	int			bd_holders;
@@ -731,6 +732,9 @@ struct super_block {
 	struct list_head	s_instances;
 	struct quota_info	s_dquot;	/* Diskquota specific options */
 
+	int			s_frozen;
+	wait_queue_head_t	s_wait_unfrozen;
+
 	char s_id[32];				/* Informational name */
 
 	struct kobject           kobj;          /* anchor for sysfs */
@@ -744,6 +748,18 @@ struct super_block {
 };
 
 /*
+ * Snapshotting support.
+ */
+enum {
+	SB_UNFROZEN = 0,
+	SB_FREEZE_WRITE	= 1,
+	SB_FREEZE_TRANS = 2,
+};
+
+#define vfs_check_frozen(sb, level) \
+	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
+
+/*
  * Superblock locking.
  */
 static inline void lock_super(struct super_block * sb)
--- diff/mm/filemap.c	2004-04-06 15:53:43.095076760 +0100
+++ source/mm/filemap.c	2004-04-06 15:54:25.092692152 +0100
@@ -1785,6 +1785,8 @@ generic_file_aio_write_nolock(struct kio
 	unsigned long	seg;
 	char __user	*buf;
 
+	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+
 	ocount = 0;
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *iv = &iov[seg];