diff options
| author | Chris Chiu <chris.chiu@canonical.com> | 2021-03-23 11:52:19 +0300 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2021-04-10 14:36:09 +0300 |
| commit | 037950869be3e79fa90dd52954af24abcbca2445 (patch) | |
| tree | ba5fa541c4da85bc0cabd0b4372506794d627b53 /fs/block_dev.c | |
| parent | 7c73059bf8490b055f77e8fa07388159ffe7c80e (diff) | |
| download | linux-037950869be3e79fa90dd52954af24abcbca2445.tar.xz | |
block: clear GD_NEED_PART_SCAN later in bdev_disk_changed
[ Upstream commit 5116784039f0421e9a619023cfba3e302c3d9adc ]
The GD_NEED_PART_SCAN is set by bdev_check_media_change to initiate
a partition scan while removing a block device. It should be cleared
after blk_drop_paritions because blk_drop_paritions could return
-EBUSY and then the consequence __blkdev_get has no chance to do
delete_partition if GD_NEED_PART_SCAN already cleared.
It causes some problems on some card readers. Ex. Realtek card
reader 0bda:0328 and 0bda:0158. The device node of the partition
will not disappear after the memory card removed. Thus the user
applications can not update the device mapping correctly.
BugLink: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1920874
Signed-off-by: Chris Chiu <chris.chiu@canonical.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210323085219.24428-1-chris.chiu@canonical.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'fs/block_dev.c')
| -rw-r--r-- | fs/block_dev.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c index fe201b757baa..6516051807b8 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1404,13 +1404,13 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate) lockdep_assert_held(&bdev->bd_mutex); - clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); - rescan: ret = blk_drop_partitions(bdev); if (ret) return ret; + clear_bit(GD_NEED_PART_SCAN, &disk->state); + /* * Historically we only set the capacity to zero for devices that * support partitions (independ of actually having partitions created). |