[PATCH] lockdep: annotate blkdev nesting

Teach special (recursive) locking code to the lock validator.

Effects on non-lockdep kernels:

- the introduction of the following function variants:

  extern struct block_device *open_partition_by_devnum(dev_t, unsigned);

  extern int blkdev_put_partition(struct block_device *);

  static int
  blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags);

 which on non-lockdep are the same as open_by_devnum(), blkdev_put()
 and blkdev_get().

- a subclass parameter to do_open(). [unused on non-lockdep]

- a subclass parameter to __blkdev_put(), which is a new internal
  function for the main blkdev_put*() functions. [parameter unused
  on non-lockdep kernels, except for two sanity check WARN_ON()s]

these functions carry no semantical difference - they only express
object dependencies towards the lockdep subsystem.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 107 insertions, 18 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 2fe32c261922..e4e161372a3e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1404,7 +1404,7 @@ static int lock_rdev(mdk_rdev_t *rdev, dev_t dev)
 	struct block_device *bdev;
 	char b[BDEVNAME_SIZE];
 
-	bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+	bdev = open_partition_by_devnum(dev, FMODE_READ|FMODE_WRITE);
 	if (IS_ERR(bdev)) {
 		printk(KERN_ERR "md: could not open %s.\n",
 			__bdevname(dev, b));
@@ -1414,7 +1414,7 @@ static int lock_rdev(mdk_rdev_t *rdev, dev_t dev)
 	if (err) {
 		printk(KERN_ERR "md: could not bd_claim %s.\n",
 			bdevname(bdev, b));
-		blkdev_put(bdev);
+		blkdev_put_partition(bdev);
 		return err;
 	}
 	rdev->bdev = bdev;
@@ -1428,7 +1428,7 @@ static void unlock_rdev(mdk_rdev_t *rdev)
 	if (!bdev)
 		MD_BUG();
 	bd_release(bdev);
-	blkdev_put(bdev);
+	blkdev_put_partition(bdev);
 }
 
 void md_autodetect_dev(dev_t dev);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9633a490dab0..37534573960b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -739,7 +739,7 @@ static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
 	if (!bo)
 		return -ENOMEM;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_PARTITION);
 	res = bd_claim(bdev, holder);
 	if (res || !add_bd_holder(bdev, bo))
 		free_bd_holder(bo);
@@ -764,7 +764,7 @@ static void bd_release_from_kobject(struct block_device *bdev,
 	if (!kobj)
 		return;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_PARTITION);
 	bd_release(bdev);
 	if ((bo = del_bd_holder(bdev, kobj)))
 		free_bd_holder(bo);
@@ -822,6 +822,22 @@ struct block_device *open_by_devnum(dev_t dev, unsigned mode)
 
 EXPORT_SYMBOL(open_by_devnum);
 
+static int
+blkdev_get_partition(struct block_device *bdev, mode_t mode, unsigned flags);
+
+struct block_device *open_partition_by_devnum(dev_t dev, unsigned mode)
+{
+	struct block_device *bdev = bdget(dev);
+	int err = -ENOMEM;
+	int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY;
+	if (bdev)
+		err = blkdev_get_partition(bdev, mode, flags);
+	return err ? ERR_PTR(err) : bdev;
+}
+
+EXPORT_SYMBOL(open_partition_by_devnum);
+
+
 /*
  * This routine checks whether a removable media has been changed,
  * and invalidates all buffer-cache-entries in that case. This
@@ -868,7 +884,11 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
-static int do_open(struct block_device *bdev, struct file *file)
+static int
+blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags);
+
+static int
+do_open(struct block_device *bdev, struct file *file, unsigned int subclass)
 {
 	struct module *owner = NULL;
 	struct gendisk *disk;
@@ -885,7 +905,8 @@ static int do_open(struct block_device *bdev, struct file *file)
 	}
 	owner = disk->fops->owner;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, subclass);
+
 	if (!bdev->bd_openers) {
 		bdev->bd_disk = disk;
 		bdev->bd_contains = bdev;
@@ -912,11 +933,11 @@ static int do_open(struct block_device *bdev, struct file *file)
 			ret = -ENOMEM;
 			if (!whole)
 				goto out_first;
-			ret = blkdev_get(whole, file->f_mode, file->f_flags);
+			ret = blkdev_get_whole(whole, file->f_mode, file->f_flags);
 			if (ret)
 				goto out_first;
 			bdev->bd_contains = whole;
-			mutex_lock(&whole->bd_mutex);
+			mutex_lock_nested(&whole->bd_mutex, BD_MUTEX_WHOLE);
 			whole->bd_part_count++;
 			p = disk->part[part - 1];
 			bdev->bd_inode->i_data.backing_dev_info =
@@ -944,7 +965,8 @@ static int do_open(struct block_device *bdev, struct file *file)
 			if (bdev->bd_invalidated)
 				rescan_partitions(bdev->bd_disk, bdev);
 		} else {
-			mutex_lock(&bdev->bd_contains->bd_mutex);
+			mutex_lock_nested(&bdev->bd_contains->bd_mutex,
+					  BD_MUTEX_PARTITION);
 			bdev->bd_contains->bd_part_count++;
 			mutex_unlock(&bdev->bd_contains->bd_mutex);
 		}
@@ -985,11 +1007,49 @@ int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags)
 	fake_file.f_dentry = &fake_dentry;
 	fake_dentry.d_inode = bdev->bd_inode;
 
-	return do_open(bdev, &fake_file);
+	return do_open(bdev, &fake_file, BD_MUTEX_NORMAL);
 }
 
 EXPORT_SYMBOL(blkdev_get);
 
+static int
+blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags)
+{
+	/*
+	 * This crockload is due to bad choice of ->open() type.
+	 * It will go away.
+	 * For now, block device ->open() routine must _not_
+	 * examine anything in 'inode' argument except ->i_rdev.
+	 */
+	struct file fake_file = {};
+	struct dentry fake_dentry = {};
+	fake_file.f_mode = mode;
+	fake_file.f_flags = flags;
+	fake_file.f_dentry = &fake_dentry;
+	fake_dentry.d_inode = bdev->bd_inode;
+
+	return do_open(bdev, &fake_file, BD_MUTEX_WHOLE);
+}
+
+static int
+blkdev_get_partition(struct block_device *bdev, mode_t mode, unsigned flags)
+{
+	/*
+	 * This crockload is due to bad choice of ->open() type.
+	 * It will go away.
+	 * For now, block device ->open() routine must _not_
+	 * examine anything in 'inode' argument except ->i_rdev.
+	 */
+	struct file fake_file = {};
+	struct dentry fake_dentry = {};
+	fake_file.f_mode = mode;
+	fake_file.f_flags = flags;
+	fake_file.f_dentry = &fake_dentry;
+	fake_dentry.d_inode = bdev->bd_inode;
+
+	return do_open(bdev, &fake_file, BD_MUTEX_PARTITION);
+}
+
 static int blkdev_open(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev;
@@ -1005,7 +1065,7 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 
 	bdev = bd_acquire(inode);
 
-	res = do_open(bdev, filp);
+	res = do_open(bdev, filp, BD_MUTEX_NORMAL);
 	if (res)
 		return res;
 
@@ -1019,13 +1079,13 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	return res;
 }
 
-int blkdev_put(struct block_device *bdev)
+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(&bdev->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, subclass);
 	lock_kernel();
 	if (!--bdev->bd_openers) {
 		sync_blockdev(bdev);
@@ -1035,7 +1095,8 @@ int blkdev_put(struct block_device *bdev)
 		if (disk->fops->release)
 			ret = disk->fops->release(bd_inode, NULL);
 	} else {
-		mutex_lock(&bdev->bd_contains->bd_mutex);
+		mutex_lock_nested(&bdev->bd_contains->bd_mutex,
+				  subclass + 1);
 		bdev->bd_contains->bd_part_count--;
 		mutex_unlock(&bdev->bd_contains->bd_mutex);
 	}
@@ -1051,9 +1112,8 @@ int blkdev_put(struct block_device *bdev)
 		}
 		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);
-		}
+		if (bdev != bdev->bd_contains)
+			__blkdev_put(bdev->bd_contains, subclass + 1);
 		bdev->bd_contains = NULL;
 	}
 	unlock_kernel();
@@ -1062,8 +1122,20 @@ int blkdev_put(struct block_device *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);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e26de68059af..134b32068246 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -436,6 +436,21 @@ struct block_device {
 };
 
 /*
+ * bdev->bd_mutex nesting subclasses for the lock validator:
+ *
+ * 0: normal
+ * 1: 'whole'
+ * 2: 'partition'
+ */
+enum bdev_bd_mutex_lock_class
+{
+	BD_MUTEX_NORMAL,
+	BD_MUTEX_WHOLE,
+	BD_MUTEX_PARTITION
+};
+
+
+/*
  * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
  * radix trees
  */
@@ -1425,6 +1440,7 @@ extern void bd_set_size(struct block_device *, loff_t size);
 extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
 extern struct block_device *open_by_devnum(dev_t, unsigned);
+extern struct block_device *open_partition_by_devnum(dev_t, unsigned);
 extern const struct file_operations def_blk_fops;
 extern const struct address_space_operations def_blk_aops;
 extern const struct file_operations def_chr_fops;
@@ -1435,6 +1451,7 @@ extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
 extern int blkdev_get(struct block_device *, mode_t, unsigned);
 extern int blkdev_put(struct block_device *);
+extern int blkdev_put_partition(struct block_device *);
 extern int bd_claim(struct block_device *, void *);
 extern void bd_release(struct block_device *);
 #ifdef CONFIG_SYSFS