Message-Id: <20080125195938t-sato@mail.jp.nec.com>
Date:	Fri, 25 Jan 2008 19:59:38 +0900
From:	"Takashi Sato" <t-sato@...jp.nec.com>
To:	linux-ext4@...r.kernel.org, linux-fsdevel@...r.kernel.org
Cc:	linux-kernel@...r.kernel.org
Subject: [RFC] ext3 freeze feature

Hi,

Currently, ext3 doesn't have the freeze feature which suspends write
requests.  So, we cannot get a backup which keeps the filesystem's
consistency with the storage device's features (snapshot, replication)
while it is mounted.
In many case, a commercial filesystems (e.g. VxFS) has the freeze
feature and it would be used to get the consistent backup.

So I am planning on implementing the ioctl of the freeze feature for ext3.
I think we can get the consistent backup with the following steps.
1. Freeze the filesystem with ioctl.
2. Separate the replication volume or get the snapshot
   with the storage device's feature.
3. Unfreeze the filesystem with ioctl.
4. Get the backup from the separated replication volume
   or the snapshot.

The usage of the ioctl is as below.
 int ioctl(int fd, int cmd, long *timeval)
 fd: The file descriptor of the mountpoint.
 cmd: EXT3_IOC_FREEZE for the freeze or EXT3_IOC_THAW for the unfreeze.
 timeval: The timeout value expressed in seconds.
          If it's 0, the timeout isn't set.
 Return value: 0 if the operation succeeds. Otherwise, -1.

I have made sure that write requests were suspended with the experimental
patch for this feature and attached it in this mail.

The points of the implementation are followings.
- Add calls of the freeze function (freeze_bdev) and
  the unfreeze function (thaw_bdev) in ext3_ioctl().

- ext3_freeze_timeout() which calls the unfreeze function (thaw_bdev)
  is registered to the delayed work queue to unfreeze the filesystem
  automatically after the lapse of the specified time.

Any comments are very welcome.

Signed-off-by: Takashi Sato <t-sato@...jp.nec.com>
---
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/fs/ext3/ioctl.c linux-2.6.24-rc8-freeze/fs/ext3/ioctl.c
--- linux-2.6.24-rc8/fs/ext3/ioctl.c	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/fs/ext3/ioctl.c	2008-01-22 18:20:33.000000000 +0900
@@ -254,6 +254,42 @@ flags_err:
 		return err;
 	}
 
+	case EXT3_IOC_FREEZE: {
+		long timeout_sec;
+		long timeout_msec;
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (inode->i_sb->s_frozen != SB_UNFROZEN)
+			return -EINVAL;
+		/* arg(sec) to tick value */
+		get_user(timeout_sec, (long __user *) arg);
+		timeout_msec = timeout_sec * 1000;
+		if (timeout_msec < 0)
+			return -EINVAL;
+
+		/* Freeze */
+		freeze_bdev(inode->i_sb->s_bdev);
+
+		/* set up unfreeze timer */
+		if (timeout_msec > 0)
+			ext3_add_freeze_timeout(EXT3_SB(inode->i_sb),
+						timeout_msec);
+		return 0;
+	}
+	case EXT3_IOC_THAW: {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (inode->i_sb->s_frozen == SB_UNFROZEN)
+			return -EINVAL;
+
+		/* delete unfreeze timer */
+		ext3_del_freeze_timeout(EXT3_SB(inode->i_sb));
+
+		/* Unfreeze */
+		thaw_bdev(inode->i_sb->s_bdev, inode->i_sb);
+
+		return 0;
+	}
 
 	default:
 		return -ENOTTY;
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/fs/ext3/super.c linux-2.6.24-rc8-freeze/fs/ext3/super.c
--- linux-2.6.24-rc8/fs/ext3/super.c	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/fs/ext3/super.c	2008-01-22 18:20:33.000000000 +0900
@@ -63,6 +63,7 @@ static int ext3_statfs (struct dentry * 
 static void ext3_unlockfs(struct super_block *sb);
 static void ext3_write_super (struct super_block * sb);
 static void ext3_write_super_lockfs(struct super_block *sb);
+static void ext3_freeze_timeout(struct work_struct *work);
 
 /*
  * Wrappers for journal_start/end.
@@ -323,6 +324,44 @@ void ext3_update_dynamic_rev(struct supe
 }
 
 /*
+ * ext3_add_freeze_timeout - Add timeout for ext3 freeze.
+ *
+ * @sbi			: ext3 super block
+ * @timeout_msec	: timeout period
+ *
+ * Add the delayed work for ext3 freeze timeout
+ * to the delayed work queue.
+ */
+void ext3_add_freeze_timeout(struct ext3_sb_info *sbi,
+			long timeout_msec)
+{
+	s64 timeout_jiffies = msecs_to_jiffies(timeout_msec);
+
+	/*
+	 * setup freeze timeout function
+	 */
+	INIT_DELAYED_WORK(&sbi->s_freeze_timeout, ext3_freeze_timeout);
+
+	/* set delayed work queue */
+	cancel_delayed_work(&sbi->s_freeze_timeout);
+	schedule_delayed_work(&sbi->s_freeze_timeout, timeout_jiffies);
+}
+
+/*
+ * ext3_del_freeze_timeout - Delete timeout for ext3 freeze.
+ *
+ * @sbi	: ext3 super block
+ *
+ * Delete the delayed work for ext3 freeze timeout
+ * from the delayed work queue.
+ */
+void ext3_del_freeze_timeout(struct ext3_sb_info *sbi)
+{
+	if (delayed_work_pending(&sbi->s_freeze_timeout))
+		cancel_delayed_work(&sbi->s_freeze_timeout);
+}
+
+/*
  * Open the external journal device
  */
 static struct block_device *ext3_blkdev_get(dev_t dev)
@@ -2367,10 +2406,31 @@ static void ext3_unlockfs(struct super_b
 		EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
 		ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
 		unlock_super(sb);
-		journal_unlock_updates(EXT3_SB(sb)->s_journal);
+		journal_unlock_updates_if_needed(EXT3_SB(sb)->s_journal);
 	}
 }
 
+/*
+ * ext3_freeze_timeout - Thaw the filesystem.
+ *
+ * @work	: work queue (delayed_work.work)
+ *
+ * Called by the delayed work when elapsing the timeout period.
+ * Thaw the filesystem.
+ */
+static void ext3_freeze_timeout(struct work_struct *work)
+{
+	struct ext3_sb_info *sbi = container_of(work,
+				struct ext3_sb_info,
+				s_freeze_timeout.work);
+	struct super_block *sb = get_super_block(sbi);
+
+	BUG_ON(sb == NULL);
+
+	if (sb->s_frozen != SB_UNFROZEN)
+		thaw_bdev(sb->s_bdev, sb);
+}
+
 static int ext3_remount (struct super_block * sb, int * flags, char * data)
 {
 	struct ext3_super_block * es;
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/fs/jbd/journal.c linux-2.6.24-rc8-freeze/fs/jbd/journal.c
--- linux-2.6.24-rc8/fs/jbd/journal.c	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/fs/jbd/journal.c	2008-01-22 18:20:33.000000000 +0900
@@ -46,6 +46,7 @@ EXPORT_SYMBOL(journal_extend);
 EXPORT_SYMBOL(journal_stop);
 EXPORT_SYMBOL(journal_lock_updates);
 EXPORT_SYMBOL(journal_unlock_updates);
+EXPORT_SYMBOL(journal_unlock_updates_if_needed);
 EXPORT_SYMBOL(journal_get_write_access);
 EXPORT_SYMBOL(journal_get_create_access);
 EXPORT_SYMBOL(journal_get_undo_access);
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/fs/jbd/transaction.c linux-2.6.24-rc8-freeze/fs/jbd/transaction.c
--- linux-2.6.24-rc8/fs/jbd/transaction.c	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/fs/jbd/transaction.c	2008-01-22 18:20:33.000000000 +0900
@@ -485,6 +485,29 @@ void journal_unlock_updates (journal_t *
 	wake_up(&journal->j_wait_transaction_locked);
 }
 
+/**
+ * journal_unlock_updates_if_needed	 - release barrier if needed.
+ *
+ * @journal:  Journal to release the barrier on.
+ *
+ * Release a transaction barrier obtained if barrier count is not 0.
+ * Should be called without the journal lock held.
+ */
+void journal_unlock_updates_if_needed(journal_t *journal)
+{
+	spin_lock(&journal->j_state_lock);
+
+	if (!journal->j_barrier_count) {
+		spin_unlock(&journal->j_state_lock);
+		return;
+	}
+
+	--journal->j_barrier_count;
+	spin_unlock(&journal->j_state_lock);
+	mutex_unlock(&journal->j_barrier);
+	wake_up(&journal->j_wait_transaction_locked);
+}
+
 /*
  * Report any unexpected dirty buffers which turn up.  Normally those
  * indicate an error, but they can occur if the user is running (say)
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/fs/super.c linux-2.6.24-rc8-freeze/fs/super.c
--- linux-2.6.24-rc8/fs/super.c	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/fs/super.c	2008-01-22 18:20:33.000000000 +0900
@@ -950,3 +950,30 @@ struct vfsmount *kern_mount_data(struct 
 }
 
 EXPORT_SYMBOL_GPL(kern_mount_data);
+
+/**
+ * get_super_block - get super_block
+ * @s_fs_info	: filesystem dependent information
+ * 		  (super_block.s_fs_info)
+ *
+ * Get super_block which holds s_fs_info from super_blocks.
+ * get_super_block() returns a pointer of super block or
+ * %NULL if it have failed.
+ */
+struct super_block *get_super_block(void *s_fs_info)
+{
+	struct super_block *sb;
+
+	spin_lock(&sb_lock);
+	sb = sb_entry(super_blocks.prev);
+	for (; sb != sb_entry(&super_blocks);
+				sb = sb_entry(sb->s_list.prev)) {
+		if (sb->s_fs_info == s_fs_info) {
+			spin_unlock(&sb_lock);
+			return sb;
+		}
+	}
+	spin_unlock(&sb_lock);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(get_super_block);
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/include/linux/ext3_fs.h linux-2.6.24-rc8-freeze/include/linux/ext3_fs.h
--- linux-2.6.24-rc8/include/linux/ext3_fs.h	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/include/linux/ext3_fs.h	2008-01-22 18:20:33.000000000 +0900
@@ -225,6 +225,8 @@ struct ext3_new_group_data {
 #endif
 #define EXT3_IOC_GETRSVSZ		_IOR('f', 5, long)
 #define EXT3_IOC_SETRSVSZ		_IOW('f', 6, long)
+#define EXT3_IOC_FREEZE			_IOW('f', 9, long)
+#define EXT3_IOC_THAW			_IOW('f', 10, long)
 
 /*
  * ioctl commands in 32 bit emulation
@@ -864,6 +866,9 @@ extern void ext3_abort (struct super_blo
 extern void ext3_warning (struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
 extern void ext3_update_dynamic_rev (struct super_block *sb);
+extern void ext3_add_freeze_timeout(struct ext3_sb_info *sbi,
+			long timeout_msec);
+extern void ext3_del_freeze_timeout(struct ext3_sb_info *sbi);
 
 #define ext3_std_error(sb, errno)				\
 do {								\
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/include/linux/ext3_fs_sb.h linux-2.6.24-rc8-freeze/include/linux/ext3_fs_sb.h
--- linux-2.6.24-rc8/include/linux/ext3_fs_sb.h	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/include/linux/ext3_fs_sb.h	2008-01-22 18:20:33.000000000 +0900
@@ -81,6 +81,8 @@ struct ext3_sb_info {
 	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
 	int s_jquota_fmt;			/* Format of quota to use */
 #endif
+	/* Delayed work for freeze */
+	struct delayed_work s_freeze_timeout;
 };
 
 #endif	/* _LINUX_EXT3_FS_SB */
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/include/linux/fs.h linux-2.6.24-rc8-freeze/include/linux/fs.h
--- linux-2.6.24-rc8/include/linux/fs.h	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/include/linux/fs.h	2008-01-22 18:20:33.000000000 +0900
@@ -2095,6 +2095,7 @@ struct ctl_table;
 int proc_nr_files(struct ctl_table *table, int write, struct file *filp,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
 
+extern struct super_block *get_super_block(void *s_fs_info);
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_FS_H */
diff -uprN -X linux-2.6.24-rc8/Documentation/dontdiff linux-2.6.24-rc8/include/linux/jbd.h linux-2.6.24-rc8-freeze/include/linux/jbd.h
--- linux-2.6.24-rc8/include/linux/jbd.h	2008-01-16 13:22:48.000000000 +0900
+++ linux-2.6.24-rc8-freeze/include/linux/jbd.h	2008-01-22 18:20:33.000000000 +0900
@@ -905,6 +905,7 @@ extern int	 journal_stop(handle_t *);
 extern int	 journal_flush (journal_t *);
 extern void	 journal_lock_updates (journal_t *);
 extern void	 journal_unlock_updates (journal_t *);
+extern void	 journal_unlock_updates_if_needed(journal_t *);
 
 extern journal_t * journal_init_dev(struct block_device *bdev,
 				struct block_device *fs_dev,

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists