The emergency thaw process uses iterate_super() which holds the
sb->s_umount lock in read mode. The current thaw_super() code takes
the sb->s_umount lock in write mode, hence leading to an instant
deadlock.
Use the unlocked version of thaw_super() to do the thawing and replace
iterate_supers() with iterate_supers_write() so that the unfreeze operation can
be performed with s_umount held as the locking rules for fsfreeze indicate.
As a bonus, by using thaw_super(), which does not nest, instead of thaw_bdev()
when can get rid of the ugly while loop.
Jan Kara pointed out that with this approach we will leave the block devices
frozen, but this is a problem we have had since the introduction of the
superblock level API: if we thaw the filesystem using the superblock level API
(be it through the thaw ioctl or emergency thaw) the bdev level freeze
reference counter (bd_fsfreeze_count) will not be updated and even though
subsequent calls to thaw_bdev() will decrease it it will never get back to 0
(if thaw_super() returns an error, and it will when the superblock is unfrozen,
thaw_bdev() will return without decreasing the counter). The solution I propose
(and will be implementing in the followup patch "fsfreeze: freeze_super and
thaw_bdev don't play well together") is letting bd_fsfreeze_count
become zero when the superblock sitting on top of it is unfrozen, so that
future calls to freeze_bdev() actually try to freeze the superblock.
Cc: linux-fsdevel@xxxxxxxxxxxxxxx
Cc: Josef Bacik <jbacik@xxxxxxxxxxxx>
Cc: Eric Sandeen <sandeen@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Dave Chinner <dchinner@xxxxxxxxxx>
Cc: Luiz Capitulino <lcapitulino@xxxxxxxxxx>
Signed-off-by: Fernando Luis Vazquez Cao <fernando@xxxxxxxxxxxxx>
---
diff -urNp linux-3.8-rc1-orig/drivers/tty/sysrq.c linux-3.8-rc1/drivers/tty/sysrq.c
--- linux-3.8-rc1-orig/drivers/tty/sysrq.c 2012-12-25 10:27:40.614737000 +0900
+++ linux-3.8-rc1/drivers/tty/sysrq.c 2012-12-25 11:40:06.128018000 +0900
@@ -363,7 +363,6 @@ static struct sysrq_key_op sysrq_moom_op
.enable_mask = SYSRQ_ENABLE_SIGNAL,
};
-#ifdef CONFIG_BLOCK
static void sysrq_handle_thaw(int key)
{
emergency_thaw_all();
@@ -374,7 +373,6 @@ static struct sysrq_key_op sysrq_thaw_op
.action_msg = "Emergency Thaw of all frozen filesystems",
.enable_mask = SYSRQ_ENABLE_SIGNAL,
};
-#endif
static void sysrq_handle_kill(int key)
{
diff -urNp linux-3.8-rc1-orig/fs/buffer.c linux-3.8-rc1/fs/buffer.c
--- linux-3.8-rc1-orig/fs/buffer.c 2012-12-25 11:30:38.208018000 +0900
+++ linux-3.8-rc1/fs/buffer.c 2012-12-25 11:40:06.128018000 +0900
@@ -512,15 +512,33 @@ repeat:
static void do_thaw_one(struct super_block *sb, void *unused)
{
- char b[BDEVNAME_SIZE];
- while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
- printk(KERN_WARNING "Emergency Thaw on %s\n",
+ int res;
+
+ if (sb->s_bdev) {
+ char b[BDEVNAME_SIZE];
+ printk(KERN_WARNING "Emergency Thaw on %s.\n",
bdevname(sb->s_bdev, b));
+ }
+
+ /*
+ * We got here from __iterate_supers with the superblock lock taken
+ * so we can call the lockless version of thaw_super() safely.
+ */
+ res = __thaw_super(sb);
+ if (!res) {
+ deactivate_locked_super(sb);
+ /*
+ * We have to re-acquire s_umount because
+ * iterate_supers_write() will unlock it. It still holds
+ * passive reference so sb cannot be freed under us.
+ */
+ down_write(&sb->s_umount);
+ }
}
static void do_thaw_all(struct work_struct *work)
{
- iterate_supers_read(do_thaw_one, NULL);
+ iterate_supers_write(do_thaw_one, NULL);
kfree(work);
printk(KERN_WARNING "Emergency Thaw complete\n");
}
diff -urNp linux-3.8-rc1-orig/include/linux/fs.h linux-3.8-rc1/include/linux/fs.h
--- linux-3.8-rc1-orig/include/linux/fs.h 2012-12-25 11:35:55.488018000 +0900
+++ linux-3.8-rc1/include/linux/fs.h 2012-12-25 11:40:06.132018000 +0900
@@ -1881,6 +1881,7 @@ extern int vfs_ustat(dev_t, struct kstat
extern int freeze_super(struct super_block *super);
extern int __thaw_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
+extern void emergency_thaw_all(void);
extern bool our_mnt(struct vfsmount *mnt);
extern int current_umask(void);
@@ -2053,7 +2054,6 @@ extern void iterate_bdevs(void (*)(struc
extern int sync_blockdev(struct block_device *bdev);
extern void kill_bdev(struct block_device *);
extern struct super_block *freeze_bdev(struct block_device *);
-extern void emergency_thaw_all(void);
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
#else
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
