When block device is closed, we call inode_detach_wb() in __blkdev_put()
which sets inode->i_wb to NULL. That is contrary to expectations that
inode->i_wb stays valid once set during the whole inode's lifetime and
leads to oops in wb_get() in locked_inode_to_wb_and_lock_list() because
inode_to_wb() returned NULL.
The reason why we called inode_detach_wb() is not valid anymore though.
BDI is guaranteed to stay along until we call bdi_put() from
bdev_evict_inode() so we can postpone calling inode_detach_wb() to that
moment. A complication is that i_wb can point to non-root wb_writeback
structure and in that case we do need to clean it up as bdi_unregister()
blocks waiting for all non-root wb_writeback references to get dropped.
Thus this i_wb reference could block device removal e.g. from
__scsi_remove_device() (which indirectly ends up calling
bdi_unregister()). We cannot rely on block device inode to go away soon
(and thus i_wb reference to get dropped) as the device may got
hot-removed e.g. under a mounted filesystem. We deal with these issues
by switching block device inode from non-root wb_writeback structure to
bdi->wb when needed. Since this is rather expensive (requires
synchronize_rcu()) we do the switching only in del_gendisk() when we
know the device is going away.
Also add a warning to catch if someone uses inode_detach_wb() in a
dangerous way.
Reported-by: Thiago Jung Bauermann <bauerman@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
block/genhd.c | 4 ++--
fs/block_dev.c | 11 ++++-------
include/linux/fs.h | 2 +-
include/linux/writeback.h | 1 +
4 files changed, 8 insertions(+), 10 deletions(-)
diff --git a/block/genhd.c b/block/genhd.c
index 68c613edb93a..721921a140cc 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -649,13 +649,13 @@ void del_gendisk(struct gendisk *disk)
DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
while ((part = disk_part_iter_next(&piter))) {
invalidate_partition(disk, part->partno);
- bdev_unhash_inode(part_devt(part));
+ bdev_cleanup_inode(part_devt(part));
delete_partition(disk, part->partno);
}
disk_part_iter_exit(&piter);
invalidate_partition(disk, 0);
- bdev_unhash_inode(disk_devt(disk));
+ bdev_cleanup_inode(disk_devt(disk));
set_capacity(disk, 0);
disk->flags &= ~GENHD_FL_UP;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 360439373a66..65ac3a60ac8e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -884,6 +884,8 @@ static void bdev_evict_inode(struct inode *inode)
spin_lock(&bdev_lock);
list_del_init(&bdev->bd_list);
spin_unlock(&bdev_lock);
+ /* Detach inode from wb early as bdi_put() may free bdi->wb */
+ inode_detach_wb(inode);
if (bdev->bd_bdi != &noop_backing_dev_info)
bdi_put(bdev->bd_bdi);
}
@@ -960,13 +962,14 @@ static LIST_HEAD(all_bdevs);
* If there is a bdev inode for this device, unhash it so that it gets evicted
* as soon as last inode reference is dropped.
*/
-void bdev_unhash_inode(dev_t dev)
+void bdev_cleanup_inode(dev_t dev)
{
struct inode *inode;
inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev);
if (inode) {
remove_inode_hash(inode);
+ inode_switch_to_default_wb_sync(inode);
iput(inode);
}
}
@@ -1874,12 +1877,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
kill_bdev(bdev);
bdev_write_inode(bdev);
- /*
- * Detaching bdev inode from its wb in __destroy_inode()
- * is too late: the queue which embeds its bdi (along with
- * root wb) can be gone as soon as we put_disk() below.
- */
- inode_detach_wb(bdev->bd_inode);
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 319fb76f9081..f8c86b9c31d5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2344,7 +2344,7 @@ extern struct kmem_cache *names_cachep;
#ifdef CONFIG_BLOCK
extern int register_blkdev(unsigned int, const char *);
extern void unregister_blkdev(unsigned int, const char *);
-extern void bdev_unhash_inode(dev_t dev);
+extern void bdev_cleanup_inode(dev_t dev);
extern struct block_device *bdget(dev_t);
extern struct block_device *bdgrab(struct block_device *bdev);
extern void bd_set_size(struct block_device *, loff_t size);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 0d3ba83a0f7f..6d27b78c9a79 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -237,6 +237,7 @@ static inline void inode_attach_wb(struct inode *inode, struct page *page)
static inline void inode_detach_wb(struct inode *inode)
{
if (inode->i_wb) {
+ WARN_ON_ONCE(!(inode->i_state & I_CLEAR));
wb_put(inode->i_wb);
inode->i_wb = NULL;
}
--
2.10.2
