super: fix emergency thaw deadlock on frozen block devices

do_thaw_all_callback() calls bdev_thaw() while holding sb->s_umount
exclusively. If the block device was frozen via bdev_freeze() dropping
the last block layer freeze reference calls fs_bdev_thaw() which
reacquires s_umount:

  do_thaw_all_callback(sb)
    super_lock_excl(sb)                     # holds sb->s_umount
    bdev_thaw(sb->s_bdev)
      mutex_lock(&bdev->bd_fsfreeze_mutex)
      # bd_fsfreeze_count drops 1 -> 0
      bd_holder_ops->thaw == fs_bdev_thaw
        get_bdev_super(bdev)
          bdev_super_lock(bdev, true)
            super_lock(sb, true)
              down_write(&sb->s_umount)     # same task: deadlock

The emergency thaw worker deadlocks against itself holding both
s_umount and bd_fsfreeze_mutex. That fscks any subsequent unmount,
freeze, or thaw of that filesystem and block device.

  [   81.878470] sysrq: Show Blocked State
  [   81.880140] task:kworker/0:1     state:D stack:0     pid:11    tgid:11    ppid:2      task_flags:0x4208060 flags:0x00080000
  [   81.884876] Workqueue: events do_thaw_all
  [   81.886656] Call Trace:
  [   81.887759]  <TASK>
  [   81.888763]  __schedule+0x579/0x1420
  [   81.890372]  schedule+0x3a/0x100
  [   81.891794]  schedule_preempt_disabled+0x15/0x30
  [   81.893848]  rwsem_down_write_slowpath+0x1ea/0x900
  [   81.895191]  ? __pfx_do_thaw_all_callback+0x10/0x10
  [   81.896528]  down_write+0xbd/0xc0
  [   81.897505]  super_lock+0x91/0x180
  [   81.898457]  ? __mutex_lock+0xa99/0x1140
  [   81.900748]  ? __mutex_unlock_slowpath+0x1f/0x400
  [   81.902069]  bdev_super_lock+0x5b/0x150
  [   81.903132]  get_bdev_super+0x10/0x60
  [   81.904042]  fs_bdev_thaw+0x23/0xf0
  [   81.904755]  bdev_thaw+0x82/0x100
  [   81.905484]  do_thaw_all_callback+0x2c/0x50
  [   81.906298]  __iterate_supers+0x5d/0x130
  [   81.907067]  do_thaw_all+0x20/0x40
  [   81.907739]  process_one_work+0x206/0x5e0
  [   81.908545]  worker_thread+0x1e2/0x3c0
  [   81.909339]  ? __pfx_worker_thread+0x10/0x10
  [   81.910171]  kthread+0xf4/0x130
  [   81.910799]  ? __pfx_kthread+0x10/0x10
  [   81.911528]  ret_from_fork+0x2e2/0x3b0
  [   81.912259]  ? __pfx_kthread+0x10/0x10
  [   81.913010]  ret_from_fork_asm+0x1a/0x30
  [   81.913806]  </TASK>

bdev_super_lock() even documents the violated requirement with
lockdep_assert_not_held(&sb->s_umount).

Acquiring bd_fsfreeze_mutex under s_umount also inverts the
bd_fsfreeze_mutex vs. s_umount ordering established by
bdev_{freeze,thaw}() and can thus ABBA against a concurrent block-layer
freeze even when the recursive path isn't hit.

Fix this by not holding s_umount around the bdev_thaw() loop at all. Pin
the superblock with an active reference instead as
filesystems_freeze_callback() does. The active reference keeps the
superblock from being shut down and so ->s_bdev stays valid without
holding s_umount. The block-layer-held freeze is dropped by
fs_bdev_thaw() with FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE exactly as
a regular unfreeze would and thaw_super_locked() handles
filesystem-level freezes as before.

The emergency thaw path has deadlocked like this in one form or
another for a long long time but the current exclusively-held
shape dates back to commit [1] where thaw_bdev() already ended in
thaw_super() with s_umount held by do_thaw_all_callback().

Fixes: 08fdc8a0138a ("buffer.c: call thaw_super during emergency thaw") [1]
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260723-work-super-emergency_thaw-v1-1-7c315c600245@kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

diff --git a/fs/super.c b/fs/super.c
index 70dcb07e7fa538b694757989da24c051f406ef4c..ffdcc6a2e0debd510b2106a9f71ff5661987a031 100644 (file)
--- a/fs/super.c
+++ b/fs/super.c
@@ -1082,16 +1082,30 @@ void emergency_remount(void)
        }
 }
 
+static inline bool get_active_super(struct super_block *sb)
+{
+       bool active = false;
+
+       if (super_lock_excl(sb)) {
+               active = atomic_inc_not_zero(&sb->s_active);
+               super_unlock_excl(sb);
+       }
+       return active;
+}
+
 static void do_thaw_all_callback(struct super_block *sb, void *unused)
 {
-       if (!super_lock_excl(sb))
+       if (!get_active_super(sb))
                return;
 
+       /* fs_bdev_thaw() acquires s_umount so it must not be held here */
        if (IS_ENABLED(CONFIG_BLOCK))
                while (sb->s_bdev && !bdev_thaw(sb->s_bdev))
                        pr_warn("Emergency Thaw on %pg\n", sb->s_bdev);
 
-       thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE, NULL);
+       if (super_lock_excl(sb))
+               thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE, NULL);
+       deactivate_super(sb);
 }
 
 static void do_thaw_all(struct work_struct *work)
@@ -1117,17 +1131,6 @@ void emergency_thaw_all(void)
        }
 }
 
-static inline bool get_active_super(struct super_block *sb)
-{
-       bool active = false;
-
-       if (super_lock_excl(sb)) {
-               active = atomic_inc_not_zero(&sb->s_active);
-               super_unlock_excl(sb);
-       }
-       return active;
-}
-
 static const char *filesystems_freeze_ptr = "filesystems_freeze";
 
 static void filesystems_freeze_callback(struct super_block *sb, void *freeze_all_ptr)