From 523e1d399ce0e23bec562abe2b2f8d297af81161 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 19 Oct 2011 14:31:07 +0200 Subject: [PATCH] block: make gendisk hold a reference to its queue The following command sequence triggers an oops. # mount /dev/sdb1 /mnt # echo 1 > /sys/class/scsi_device/0\:0\:1\:0/device/delete # umount /mnt general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 791, comm: umount Not tainted 3.1.0-rc3-work+ #8 Bochs Bochs RIP: 0010:[] [] __lock_acquire+0x389/0x1d60 ... Call Trace: [] lock_acquire+0x95/0x140 [] _raw_spin_lock+0x3b/0x50 [] bdi_lock_two+0x5c/0x70 [] bdev_inode_switch_bdi+0x4c/0xf0 [] __blkdev_put+0x11b/0x1d0 [] __blkdev_put+0x160/0x1d0 [] blkdev_put+0x5f/0x190 [] kill_block_super+0x4d/0x80 [] deactivate_locked_super+0x45/0x70 [] deactivate_super+0x4a/0x70 [] mntput_no_expire+0xed/0x130 [] sys_umount+0x7e/0x3a0 [] system_call_fastpath+0x16/0x1b This is because bdev holds on to disk but disk doesn't pin the associated queue. If a SCSI device is removed while the device is still open, the sdev puts the base reference to the queue on release. When the bdev is finally released, the associated queue is already gone along with the bdi and bdev_inode_switch_bdi() ends up dereferencing already freed bdi. Even if it were not for this bug, disk not holding onto the associated queue is very unusual and error-prone. Fix it by making add_disk() take an extra reference to its queue and put it on disk_release() and ensuring that disk and its fops owner are put in that order after all accesses to the disk and queue are complete. Signed-off-by: Tejun Heo Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/genhd.c | 8 ++++++++ fs/block_dev.c | 13 ++++++++----- 2 files changed, 16 insertions(+), 5 deletions(-) diff --git a/block/genhd.c b/block/genhd.c index e2f67902dd02..d261b73b9744 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -611,6 +611,12 @@ void add_disk(struct gendisk *disk) register_disk(disk); blk_register_queue(disk); + /* + * Take an extra ref on queue which will be put on disk_release() + * so that it sticks around as long as @disk is there. + */ + WARN_ON_ONCE(blk_get_queue(disk->queue)); + retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj, "bdi"); WARN_ON(retval); @@ -1095,6 +1101,8 @@ static void disk_release(struct device *dev) disk_replace_part_tbl(disk, NULL); free_part_stats(&disk->part0); free_part_info(&disk->part0); + if (disk->queue) + blk_put_queue(disk->queue); kfree(disk); } struct class block_class = { diff --git a/fs/block_dev.c b/fs/block_dev.c index 95f786ec7f08..1c44b8d54504 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1085,6 +1085,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) { struct gendisk *disk; + struct module *owner; int ret; int partno; int perm = 0; @@ -1110,6 +1111,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) disk = get_gendisk(bdev->bd_dev, &partno); if (!disk) goto out; + owner = disk->fops->owner; disk_block_events(disk); mutex_lock_nested(&bdev->bd_mutex, for_part); @@ -1137,8 +1139,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = NULL; mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); - module_put(disk->fops->owner); put_disk(disk); + module_put(owner); goto restart; } } @@ -1194,8 +1196,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_unlock_bdev; } /* only one opener holds refs to the module and disk */ - module_put(disk->fops->owner); put_disk(disk); + module_put(owner); } bdev->bd_openers++; if (for_part) @@ -1215,8 +1217,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) out_unlock_bdev: mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); - module_put(disk->fops->owner); put_disk(disk); + module_put(owner); out: bdput(bdev); @@ -1442,14 +1444,15 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) if (!bdev->bd_openers) { struct module *owner = disk->fops->owner; - put_disk(disk); - module_put(owner); disk_put_part(bdev->bd_part); bdev->bd_part = NULL; bdev->bd_disk = NULL; if (bdev != bdev->bd_contains) victim = bdev->bd_contains; bdev->bd_contains = NULL; + + put_disk(disk); + module_put(owner); } mutex_unlock(&bdev->bd_mutex); bdput(bdev); -- 2.20.1