From: Ingo Molnar 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 Signed-off-by: Arjan van de Ven Signed-off-by: Andrew Morton --- drivers/md/md.c | 6 +- fs/block_dev.c | 101 +++++++++++++++++++++++++++++++++++++------ include/linux/fs.h | 17 +++++++ 3 files changed, 108 insertions(+), 16 deletions(-) diff -puN drivers/md/md.c~lockdep-annotate-blkdev-nesting drivers/md/md.c --- a/drivers/md/md.c~lockdep-annotate-blkdev-nesting +++ a/drivers/md/md.c @@ -1410,7 +1410,7 @@ static int lock_rdev(mdk_rdev_t *rdev, d 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)); @@ -1420,7 +1420,7 @@ static int lock_rdev(mdk_rdev_t *rdev, d 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; @@ -1434,7 +1434,7 @@ 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 -puN fs/block_dev.c~lockdep-annotate-blkdev-nesting fs/block_dev.c --- a/fs/block_dev.c~lockdep-annotate-blkdev-nesting +++ a/fs/block_dev.c @@ -741,7 +741,7 @@ static int bd_claim_by_kobject(struct bl 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); @@ -766,7 +766,7 @@ static void bd_release_from_kobject(stru 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); @@ -824,6 +824,22 @@ struct block_device *open_by_devnum(dev_ 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 @@ -874,7 +890,11 @@ void bd_set_size(struct block_device *bd } 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; @@ -891,7 +911,8 @@ static int do_open(struct block_device * } 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; @@ -918,11 +939,11 @@ static int do_open(struct block_device * 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 = @@ -950,7 +971,8 @@ static int do_open(struct block_device * 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); } @@ -991,11 +1013,49 @@ int blkdev_get(struct block_device *bdev 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; @@ -1011,7 +1071,7 @@ static int blkdev_open(struct inode * in bdev = bd_acquire(inode); - res = do_open(bdev, filp); + res = do_open(bdev, filp, BD_MUTEX_NORMAL); if (res) return res; @@ -1025,13 +1085,13 @@ static int blkdev_open(struct inode * in 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); @@ -1041,7 +1101,9 @@ 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); + WARN_ON(subclass != 0); + mutex_lock_nested(&bdev->bd_contains->bd_mutex, + BD_MUTEX_PARTITION); bdev->bd_contains->bd_part_count--; mutex_unlock(&bdev->bd_contains->bd_mutex); } @@ -1058,7 +1120,8 @@ 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); + WARN_ON(subclass != 0); + __blkdev_put(bdev->bd_contains, 1); } bdev->bd_contains = NULL; } @@ -1068,8 +1131,20 @@ 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 -puN include/linux/fs.h~lockdep-annotate-blkdev-nesting include/linux/fs.h --- a/include/linux/fs.h~lockdep-annotate-blkdev-nesting +++ a/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 */ @@ -1486,6 +1501,7 @@ extern void bd_set_size(struct block_dev 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; @@ -1499,6 +1515,7 @@ extern int blkdev_driver_ioctl(struct in 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 _