scsi: Avoid that .queuecommand() gets called for a blocked SCSI device

Several SCSI transport and LLD drivers surround code that does not
tolerate concurrent calls of .queuecommand() with scsi_target_block() /
scsi_target_unblock(). These last two functions use
blk_mq_quiesce_queue() / blk_mq_unquiesce_queue() for scsi-mq request
queues to prevent concurrent .queuecommand() calls. However, that is
not sufficient to prevent .queuecommand() calls from scsi_send_eh_cmnd().
Hence surround the .queuecommand() call from the SCSI error handler with
code that avoids that .queuecommand() gets called in the blocked state.

Note: converting the .queuecommand() call in scsi_send_eh_cmnd() into
code that calls blk_get_request() + blk_execute_rq() is not an option
since scsi_send_eh_cmnd() must be able to make forward progress even
if all requests have been allocated.

Cc: Ming Lei <ming.lei@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/scsi_error.c

@@ -1055,7 +1055,7 @@ static int scsi_send_eh_cmnd(struct scsi_cmnd *scmd, unsigned char *cmnd,
 	struct scsi_device *sdev = scmd->device;
 	struct Scsi_Host *shost = sdev->host;
 	DECLARE_COMPLETION_ONSTACK(done);
-	unsigned long timeleft = timeout;
+	unsigned long timeleft = timeout, delay;
 	struct scsi_eh_save ses;
 	const unsigned long stall_for = msecs_to_jiffies(100);
 	int rtn;
@@ -1066,7 +1066,29 @@ static int scsi_send_eh_cmnd(struct scsi_cmnd *scmd, unsigned char *cmnd,
 
 	scsi_log_send(scmd);
 	scmd->scsi_done = scsi_eh_done;
+
+	/*
+	 * Lock sdev->state_mutex to avoid that scsi_device_quiesce() can
+	 * change the SCSI device state after we have examined it and before
+	 * .queuecommand() is called.
+	 */
+	mutex_lock(&sdev->state_mutex);
+	while (sdev->sdev_state == SDEV_BLOCK && timeleft > 0) {
+		mutex_unlock(&sdev->state_mutex);
+		SCSI_LOG_ERROR_RECOVERY(5, sdev_printk(KERN_DEBUG, sdev,
+			"%s: state %d <> %d\n", __func__, sdev->sdev_state,
+			SDEV_BLOCK));
+		delay = min(timeleft, stall_for);
+		timeleft -= delay;
+		msleep(jiffies_to_msecs(delay));
+		mutex_lock(&sdev->state_mutex);
+	}
+	if (sdev->sdev_state != SDEV_BLOCK)
 		rtn = shost->hostt->queuecommand(shost, scmd);
+	else
+		rtn = SCSI_MLQUEUE_DEVICE_BUSY;
+	mutex_unlock(&sdev->state_mutex);
+
 	if (rtn) {
 		if (timeleft > stall_for) {
 			scsi_eh_restore_cmnd(scmd, &ses);

drivers/scsi/scsi_lib.c

@@ -2616,10 +2616,6 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_block_nowait);
  * a legal transition). When the device is in this state, command processing
  * is paused until the device leaves the SDEV_BLOCK state. See also
  * scsi_internal_device_unblock().
- *
- * To do: avoid that scsi_send_eh_cmnd() calls queuecommand() after
- * scsi_internal_device_block() has blocked a SCSI device and also
- * remove the rport mutex lock and unlock calls from srp_queuecommand().
  */
 static int scsi_internal_device_block(struct scsi_device *sdev)
 {