[PATCH] block: add unlocked_ioctl support for block devices

This patch allows block device drivers to convert their ioctl functions to
unlocked_ioctl() like character devices and other subsystems.  All
functions that were called with the BKL held before are still used that
way, but I would not be surprised if it could be removed from the ioctl
functions in drivers/block/ioctl.c themselves.

As a side note, I found that compat_blkdev_ioctl() acquires the BKL as
well, which looks like a bug.  I have checked that every user of
disk->fops->compat_ioctl() in the current git tree gets the BKL itself, so
it could easily be removed from compat_blkdev_ioctl().
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

drivers/block/ioctl.c

@@ -133,11 +133,9 @@ static int put_u64(unsigned long arg, u64 val)
 	return put_user(val, (u64 __user *)arg);
 }
 
-int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
-			unsigned long arg)
+static int blkdev_locked_ioctl(struct file *file, struct block_device *bdev,
+				unsigned cmd, unsigned long arg)
 {
-	struct block_device *bdev = inode->i_bdev;
-	struct gendisk *disk = bdev->bd_disk;
 	struct backing_dev_info *bdi;
 	int ret, n;
 
@@ -190,36 +188,72 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
 		return put_ulong(arg, bdev->bd_inode->i_size >> 9);
 	case BLKGETSIZE64:
 		return put_u64(arg, bdev->bd_inode->i_size);
+	}
+	return -ENOIOCTLCMD;
+}
+
+static int blkdev_driver_ioctl(struct inode *inode, struct file *file,
+		struct gendisk *disk, unsigned cmd, unsigned long arg)
+{
+	int ret;
+	if (disk->fops->unlocked_ioctl)
+		return disk->fops->unlocked_ioctl(file, cmd, arg);
+
+	if (disk->fops->ioctl) {
+		lock_kernel();
+		ret = disk->fops->ioctl(inode, file, cmd, arg);
+		unlock_kernel();
+		return ret;
+	}
+
+	return -ENOTTY;
+}
+
+int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
+			unsigned long arg)
+{
+	struct block_device *bdev = inode->i_bdev;
+	struct gendisk *disk = bdev->bd_disk;
+	int ret, n;
+
+	switch(cmd) {
 	case BLKFLSBUF:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		if (disk->fops->ioctl) {
-			ret = disk->fops->ioctl(inode, file, cmd, arg);
-			/* -EINVAL to handle old uncorrected drivers */
-			if (ret != -EINVAL && ret != -ENOTTY)
-				return ret;
-		}
+
+		ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+		/* -EINVAL to handle old uncorrected drivers */
+		if (ret != -EINVAL && ret != -ENOTTY)
+			return ret;
+
+		lock_kernel();
 		fsync_bdev(bdev);
 		invalidate_bdev(bdev, 0);
+		unlock_kernel();
 		return 0;
+
 	case BLKROSET:
-		if (disk->fops->ioctl) {
-			ret = disk->fops->ioctl(inode, file, cmd, arg);
-			/* -EINVAL to handle old uncorrected drivers */
-			if (ret != -EINVAL && ret != -ENOTTY)
-				return ret;
-		}
+		ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+		/* -EINVAL to handle old uncorrected drivers */
+		if (ret != -EINVAL && ret != -ENOTTY)
+			return ret;
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 		if (get_user(n, (int __user *)(arg)))
 			return -EFAULT;
+		lock_kernel();
 		set_device_ro(bdev, n);
+		unlock_kernel();
 		return 0;
-	default:
-		if (disk->fops->ioctl)
-			return disk->fops->ioctl(inode, file, cmd, arg);
 	}
-	return -ENOTTY;
+
+	lock_kernel();
+	ret = blkdev_locked_ioctl(file, bdev, cmd, arg);
+	unlock_kernel();
+	if (ret != -ENOIOCTLCMD)
+		return ret;
+
+	return blkdev_driver_ioctl(inode, file, disk, cmd, arg);
 }
 
 /* Most of the generic ioctls are handled in the normal fallback path.

fs/block_dev.c

@@ -777,8 +777,7 @@ static ssize_t blkdev_file_aio_write(struct kiocb *iocb, const char __user *buf,
 	return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos);
 }
 
-static int block_ioctl(struct inode *inode, struct file *file, unsigned cmd,
-			unsigned long arg)
+static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
 	return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
 }
@@ -803,7 +802,7 @@ struct file_operations def_blk_fops = {
   	.aio_write	= blkdev_file_aio_write, 
 	.mmap		= generic_file_mmap,
 	.fsync		= block_fsync,
-	.ioctl		= block_ioctl,
+	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= compat_blkdev_ioctl,
 #endif

include/linux/fs.h

@@ -884,6 +884,7 @@ struct block_device_operations {
 	int (*open) (struct inode *, struct file *);
 	int (*release) (struct inode *, struct file *);
 	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
+	long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned, unsigned long);
 	int (*media_changed) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);