scsi: sd: Fix a race between closing an sd device and sd I/O
The scsi_end_request() function calls scsi_cmd_to_driver() indirectly and
hence needs the disk->private_data pointer. Avoid that that pointer is
cleared before all affected I/O requests have finished. This patch avoids
that the following crash occurs:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
Call trace:
scsi_mq_uninit_cmd+0x1c/0x30
scsi_end_request+0x7c/0x1b8
scsi_io_completion+0x464/0x668
scsi_finish_command+0xbc/0x160
scsi_eh_flush_done_q+0x10c/0x170
sas_scsi_recover_host+0x84c/0xa98 [libsas]
scsi_error_handler+0x140/0x5b0
kthread+0x100/0x12c
ret_from_fork+0x10/0x18
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reported-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 251db30..3ffa34d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1415,11 +1415,6 @@ static void sd_release(struct gendisk *disk, fmode_t mode)
scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW);
}
- /*
- * XXX and what if there are packets in flight and this close()
- * XXX is followed by a "rmmod sd_mod"?
- */
-
scsi_disk_put(sdkp);
}
@@ -3505,9 +3500,21 @@ static void scsi_disk_release(struct device *dev)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct gendisk *disk = sdkp->disk;
-
+ struct request_queue *q = disk->queue;
+
ida_free(&sd_index_ida, sdkp->index);
+ /*
+ * Wait until all requests that are in progress have completed.
+ * This is necessary to avoid that e.g. scsi_end_request() crashes
+ * due to clearing the disk->private_data pointer. Wait from inside
+ * scsi_disk_release() instead of from sd_release() to avoid that
+ * freezing and unfreezing the request queue affects user space I/O
+ * in case multiple processes open a /dev/sd... node concurrently.
+ */
+ blk_mq_freeze_queue(q);
+ blk_mq_unfreeze_queue(q);
+
disk->private_data = NULL;
put_disk(disk);
put_device(&sdkp->device->sdev_gendev);
