@@ -1245,9 +1245,17 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
lockdep_assert_held(&bdev->bd_mutex);
rescan:
+ down_read(&bdev_lookup_sem);
+ if (!(disk->flags & GENHD_FL_UP)) {
+ up_read(&bdev_lookup_sem);
+ return -ENXIO;
+ }
+
ret = blk_drop_partitions(bdev);
- if (ret)
+ if (ret) {
+ up_read(&bdev_lookup_sem);
return ret;
+ }
clear_bit(GD_NEED_PART_SCAN, &disk->state);
@@ -1270,8 +1278,10 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
if (get_capacity(disk)) {
ret = blk_add_partitions(disk, bdev);
- if (ret == -EAGAIN)
+ if (ret == -EAGAIN) {
+ up_read(&bdev_lookup_sem);
goto rescan;
+ }
} else if (invalidate) {
/*
* Tell userspace that the media / partition table may have
@@ -1280,6 +1290,7 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
}
+ up_read(&bdev_lookup_sem);
return ret;
}
/*
Problem description: During the kernel patching, customer was switching between the iscsi disks. To switch between the iscsi disks, it was logging out the currently connected iscsi disk and then logging in to the new iscsi disk. This was being done using a script. Customer was also using the "parted" command in the script to list the partition details just before the iscsi logout. This usage of "parted" command was creating an issue and we were seeing stale links of the disks in /sys/class/block. Analysis: As part of iscsi logout, the partitions and the disk will be removed in the function del_gendisk() which is done through a kworker. The parted command, used to list the partitions, will open the disk in RW mode which results in systemd-udevd re-reading the partitions. The ioctl used to re-read partitions is BLKRRPART. This will trigger the rescanning of partitions which will also delete and re-add the partitions. So, both iscsi logout processing (through kworker) and the "parted" command (through systemd-udevd) will be involved in add/delete of partitions. In our case, the following sequence of operations happened (the iscsi device is /dev/sdb with partition sdb1): 1. sdb1 was removed by PARTED 2. kworker, as part of iscsi logout, couldn't remove sdb1 as it was already removed by PARTED 3. sdb1 was added by parted 4. sdb was NOW removed as part of iscsi logout (the last part of the device removal after remoing the partitions) Since the symlink /sys/class/block/sdb1 points to /sys/class/devices/platform/hostx/sessionx/targetx:x/block/sdb/sdb1 and since sdb is already removed, the symlink /sys/class/block/sdb1 will be orphan and stale. So, this stale link is a result of the race condition in kernel between the systemd-udevd and iscsi-logout processing as described above. We were able to reproduce this even with latest upstream kernel. Fix: While Dropping/Adding partitions as part of BLKRRPART ioctl, take the read lock for "bdev_lookup_sem" to sync with del_gendisk(). Signed-off-by: Gulam Mohamed <gulam.mohamed@oracle.com> --- fs/block_dev.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)