[PATCH] lockdep: fix blkdev_open() warning

On Wed, 2006-08-09 at 07:57 +0200, Rolf Eike Beer wrote:
> =============================================
> [ INFO: possible recursive locking detected ]
> ---------------------------------------------
> parted/7929 is trying to acquire lock:
>  (&bdev->bd_mutex){--..}, at: [<c105eb8d>] __blkdev_put+0x1e/0x13c
>
> but task is already holding lock:
>  (&bdev->bd_mutex){--..}, at: [<c105eec6>] do_open+0x72/0x3a8
>
> other info that might help us debug this:
> 1 lock held by parted/7929:
>  #0:  (&bdev->bd_mutex){--..}, at: [<c105eec6>] do_open+0x72/0x3a8
> stack backtrace:
>  [<c1003aad>] show_trace_log_lvl+0x58/0x15b
>  [<c100495f>] show_trace+0xd/0x10
>  [<c1004979>] dump_stack+0x17/0x1a
>  [<c102dee5>] __lock_acquire+0x753/0x99c
>  [<c102e3b0>] lock_acquire+0x4a/0x6a
>  [<c1204501>] mutex_lock_nested+0xc8/0x20c
>  [<c105eb8d>] __blkdev_put+0x1e/0x13c
>  [<c105ecc4>] blkdev_put+0xa/0xc
>  [<c105f18a>] do_open+0x336/0x3a8
>  [<c105f21b>] blkdev_open+0x1f/0x4c
>  [<c1057b40>] __dentry_open+0xc7/0x1aa
>  [<c1057c91>] nameidata_to_filp+0x1c/0x2e
>  [<c1057cd1>] do_filp_open+0x2e/0x35
>  [<c1057dd7>] do_sys_open+0x38/0x68
>  [<c1057e33>] sys_open+0x16/0x18
>  [<c1002845>] sysenter_past_esp+0x56/0x8d

OK, I'm having a look here; its all new to me so bear with me.

blkdev_open() calls
  do_open(bdev, ...,BD_MUTEX_NORMAL) and takes
    mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_NORMAL)

then something fails, and we're thrown to:

out_first: where
    if (bdev != bdev->bd_contains)
      blkdev_put(bdev->bd_contains) which is
        __blkdev_put(bdev->bd_contains, BD_MUTEX_NORMAL) which does
          mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_NORMAL) <--- lockdep trigger

When going to out_first, dbev->bd_contains is either bdev or whole, and
since we take the branch it must be whole. So it seems to me the
following patch would be the right one:

[akpm@osdl.org: compile fix]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: NeilBrown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fs/block_dev.c

@@ -884,6 +884,61 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
+static int __blkdev_put(struct block_device *bdev, unsigned int subclass)
+{
+	int ret = 0;
+	struct inode *bd_inode = bdev->bd_inode;
+	struct gendisk *disk = bdev->bd_disk;
+
+	mutex_lock_nested(&bdev->bd_mutex, subclass);
+	lock_kernel();
+	if (!--bdev->bd_openers) {
+		sync_blockdev(bdev);
+		kill_bdev(bdev);
+	}
+	if (bdev->bd_contains == bdev) {
+		if (disk->fops->release)
+			ret = disk->fops->release(bd_inode, NULL);
+	} else {
+		mutex_lock_nested(&bdev->bd_contains->bd_mutex,
+				  subclass + 1);
+		bdev->bd_contains->bd_part_count--;
+		mutex_unlock(&bdev->bd_contains->bd_mutex);
+	}
+	if (!bdev->bd_openers) {
+		struct module *owner = disk->fops->owner;
+
+		put_disk(disk);
+		module_put(owner);
+
+		if (bdev->bd_contains != bdev) {
+			kobject_put(&bdev->bd_part->kobj);
+			bdev->bd_part = NULL;
+		}
+		bdev->bd_disk = NULL;
+		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
+		if (bdev != bdev->bd_contains)
+			__blkdev_put(bdev->bd_contains, subclass + 1);
+		bdev->bd_contains = NULL;
+	}
+	unlock_kernel();
+	mutex_unlock(&bdev->bd_mutex);
+	bdput(bdev);
+	return ret;
+}
+
+int blkdev_put(struct block_device *bdev)
+{
+	return __blkdev_put(bdev, BD_MUTEX_NORMAL);
+}
+EXPORT_SYMBOL(blkdev_put);
+
+int blkdev_put_partition(struct block_device *bdev)
+{
+	return __blkdev_put(bdev, BD_MUTEX_PARTITION);
+}
+EXPORT_SYMBOL(blkdev_put_partition);
+
 static int
 blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags);
 
@@ -980,7 +1035,7 @@ out_first:
 	bdev->bd_disk = NULL;
 	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
 	if (bdev != bdev->bd_contains)
-		blkdev_put(bdev->bd_contains);
+		__blkdev_put(bdev->bd_contains, BD_MUTEX_WHOLE);
 	bdev->bd_contains = NULL;
 	put_disk(disk);
 	module_put(owner);
@@ -1079,63 +1134,6 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	return res;
 }
 
-static int __blkdev_put(struct block_device *bdev, unsigned int subclass)
-{
-	int ret = 0;
-	struct inode *bd_inode = bdev->bd_inode;
-	struct gendisk *disk = bdev->bd_disk;
-
-	mutex_lock_nested(&bdev->bd_mutex, subclass);
-	lock_kernel();
-	if (!--bdev->bd_openers) {
-		sync_blockdev(bdev);
-		kill_bdev(bdev);
-	}
-	if (bdev->bd_contains == bdev) {
-		if (disk->fops->release)
-			ret = disk->fops->release(bd_inode, NULL);
-	} else {
-		mutex_lock_nested(&bdev->bd_contains->bd_mutex,
-				  subclass + 1);
-		bdev->bd_contains->bd_part_count--;
-		mutex_unlock(&bdev->bd_contains->bd_mutex);
-	}
-	if (!bdev->bd_openers) {
-		struct module *owner = disk->fops->owner;
-
-		put_disk(disk);
-		module_put(owner);
-
-		if (bdev->bd_contains != bdev) {
-			kobject_put(&bdev->bd_part->kobj);
-			bdev->bd_part = NULL;
-		}
-		bdev->bd_disk = NULL;
-		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
-		if (bdev != bdev->bd_contains)
-			__blkdev_put(bdev->bd_contains, subclass + 1);
-		bdev->bd_contains = NULL;
-	}
-	unlock_kernel();
-	mutex_unlock(&bdev->bd_mutex);
-	bdput(bdev);
-	return ret;
-}
-
-int blkdev_put(struct block_device *bdev)
-{
-	return __blkdev_put(bdev, BD_MUTEX_NORMAL);
-}
-
-EXPORT_SYMBOL(blkdev_put);
-
-int blkdev_put_partition(struct block_device *bdev)
-{
-	return __blkdev_put(bdev, BD_MUTEX_PARTITION);
-}
-
-EXPORT_SYMBOL(blkdev_put_partition);
-
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev = I_BDEV(filp->f_mapping->host);