scsi: core: Change the return type of .eh_timed_out()

Commit 6600593c ("block: rename BLK_EH_NOT_HANDLED to BLK_EH_DONE")
made it impossible for .eh_timed_out() implementations to call
scsi_done() without causing a crash.

Restore support for SCSI timeout handlers to call scsi_done() as follows:

 * Change all .eh_timed_out() handlers as follows:

   - Change the return type into enum scsi_timeout_action.
   - Change BLK_EH_RESET_TIMER into SCSI_EH_RESET_TIMER.
   - Change BLK_EH_DONE into SCSI_EH_NOT_HANDLED.

 * In scsi_timeout(), convert the SCSI_EH_* values into BLK_EH_* values.
Reviewed-by: Lee Duncan <lduncan@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20221018202958.1902564-3-bvanassche@acm.orgReviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

Documentation/scsi/scsi_eh.rst

@@ -92,14 +92,17 @@ The timeout handler is scsi_timeout().  When a timeout occurs, this function
  1. invokes optional hostt->eh_timed_out() callback.  Return value can
     be one of
 
-    - BLK_EH_RESET_TIMER
+    - SCSI_EH_RESET_TIMER
 	This indicates that more time is required to finish the
 	command.  Timer is restarted.
 
-    - BLK_EH_DONE
+    - SCSI_EH_NOT_HANDLED
         eh_timed_out() callback did not handle the command.
 	Step #2 is taken.
 
+    - SCSI_EH_DONE
+        eh_timed_out() completed the command.
+
  2. scsi_abort_command() is invoked to schedule an asynchronous abort which may
     issue a retry scmd->allowed + 1 times.  Asynchronous aborts are not invoked
     for commands for which the SCSI_EH_ABORT_SCHEDULED flag is set (this

drivers/message/fusion/mptsas.c

@@ -1952,12 +1952,12 @@ mptsas_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt)
  *	@sc: scsi command that the midlayer is about to time out
  *
  **/
-static enum blk_eh_timer_return mptsas_eh_timed_out(struct scsi_cmnd *sc)
+static enum scsi_timeout_action mptsas_eh_timed_out(struct scsi_cmnd *sc)
 {
 	MPT_SCSI_HOST *hd;
 	MPT_ADAPTER   *ioc;
 	VirtDevice    *vdevice;
-	enum blk_eh_timer_return rc = BLK_EH_DONE;
+	enum scsi_timeout_action rc = SCSI_EH_NOT_HANDLED;
 
 	hd = shost_priv(sc->device->host);
 	if (hd == NULL) {
@@ -1980,7 +1980,7 @@ static enum blk_eh_timer_return mptsas_eh_timed_out(struct scsi_cmnd *sc)
 		dtmprintk(ioc, printk(MYIOC_s_WARN_FMT ": %s: ioc is in reset,"
 		    "SML need to reset the timer (sc=%p)\n",
 		    ioc->name, __func__, sc));
-		rc = BLK_EH_RESET_TIMER;
+		rc = SCSI_EH_RESET_TIMER;
 	}
 	vdevice = sc->device->hostdata;
 	if (vdevice && vdevice->vtarget && (vdevice->vtarget->inDMD
@@ -1988,7 +1988,7 @@ static enum blk_eh_timer_return mptsas_eh_timed_out(struct scsi_cmnd *sc)
 		dtmprintk(ioc, printk(MYIOC_s_WARN_FMT ": %s: target removed "
 		    "or in device removal delay (sc=%p)\n",
 		    ioc->name, __func__, sc));
-		rc = BLK_EH_RESET_TIMER;
+		rc = SCSI_EH_RESET_TIMER;
 		goto done;
 	}
 

drivers/scsi/libiscsi.c

@@ -2071,9 +2071,9 @@ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn)
 		return 0;
 }
 
-enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
+enum scsi_timeout_action iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 {
-	enum blk_eh_timer_return rc = BLK_EH_DONE;
+	enum scsi_timeout_action rc = SCSI_EH_NOT_HANDLED;
 	struct iscsi_task *task = NULL, *running_task;
 	struct iscsi_cls_session *cls_session;
 	struct iscsi_session *session;
@@ -2093,7 +2093,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 		 * Raced with completion. Blk layer has taken ownership
 		 * so let timeout code complete it now.
 		 */
-		rc = BLK_EH_DONE;
+		rc = SCSI_EH_NOT_HANDLED;
 		spin_unlock(&session->back_lock);
 		goto done;
 	}
@@ -2102,7 +2102,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 		 * Racing with the completion path right now, so give it more
 		 * time so that path can complete it like normal.
 		 */
-		rc = BLK_EH_RESET_TIMER;
+		rc = SCSI_EH_RESET_TIMER;
 		task = NULL;
 		spin_unlock(&session->back_lock);
 		goto done;
@@ -2120,21 +2120,21 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 		if (unlikely(system_state != SYSTEM_RUNNING)) {
 			sc->result = DID_NO_CONNECT << 16;
 			ISCSI_DBG_EH(session, "sc on shutdown, handled\n");
-			rc = BLK_EH_DONE;
+			rc = SCSI_EH_NOT_HANDLED;
 			goto done;
 		}
 		/*
 		 * We are probably in the middle of iscsi recovery so let
 		 * that complete and handle the error.
 		 */
-		rc = BLK_EH_RESET_TIMER;
+		rc = SCSI_EH_RESET_TIMER;
 		goto done;
 	}
 
 	conn = session->leadconn;
 	if (!conn) {
 		/* In the middle of shuting down */
-		rc = BLK_EH_RESET_TIMER;
+		rc = SCSI_EH_RESET_TIMER;
 		goto done;
 	}
 
@@ -2151,7 +2151,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 			     "Last data xfer at %lu. Last timeout was at "
 			     "%lu\n.", task->last_xfer, task->last_timeout);
 		task->have_checked_conn = false;
-		rc = BLK_EH_RESET_TIMER;
+		rc = SCSI_EH_RESET_TIMER;
 		goto done;
 	}
 
@@ -2162,7 +2162,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 	 * and can let the iscsi eh handle it
 	 */
 	if (iscsi_has_ping_timed_out(conn)) {
-		rc = BLK_EH_RESET_TIMER;
+		rc = SCSI_EH_RESET_TIMER;
 		goto done;
 	}
 
@@ -2200,7 +2200,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 				     task->last_xfer, running_task->last_xfer,
 				     task->last_timeout);
 			spin_unlock(&session->back_lock);
-			rc = BLK_EH_RESET_TIMER;
+			rc = SCSI_EH_RESET_TIMER;
 			goto done;
 		}
 	}
@@ -2216,14 +2216,14 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 	 */
 	if (READ_ONCE(conn->ping_task)) {
 		task->have_checked_conn = true;
-		rc = BLK_EH_RESET_TIMER;
+		rc = SCSI_EH_RESET_TIMER;
 		goto done;
 	}
 
 	/* Make sure there is a transport check done */
 	iscsi_send_nopout(conn, NULL);
 	task->have_checked_conn = true;
-	rc = BLK_EH_RESET_TIMER;
+	rc = SCSI_EH_RESET_TIMER;
 
 done:
 	spin_unlock_bh(&session->frwd_lock);
@@ -2232,7 +2232,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 		task->last_timeout = jiffies;
 		iscsi_put_task(task);
 	}
-	ISCSI_DBG_EH(session, "return %s\n", rc == BLK_EH_RESET_TIMER ?
+	ISCSI_DBG_EH(session, "return %s\n", rc == SCSI_EH_RESET_TIMER ?
 		     "timer reset" : "shutdown or nh");
 	return rc;
 }

drivers/scsi/megaraid/megaraid_sas_base.c

@@ -2927,15 +2927,14 @@ static int megasas_generic_reset(struct scsi_cmnd *scmd)
  * Sets the FW busy flag and reduces the host->can_queue if the
  * cmd has not been completed within the timeout period.
  */
-static enum
-blk_eh_timer_return megasas_reset_timer(struct scsi_cmnd *scmd)
+static enum scsi_timeout_action megasas_reset_timer(struct scsi_cmnd *scmd)
 {
 	struct megasas_instance *instance;
 	unsigned long flags;
 
 	if (time_after(jiffies, scmd->jiffies_at_alloc +
 				(scmd_timeout * 2) * HZ)) {
-		return BLK_EH_DONE;
+		return SCSI_EH_NOT_HANDLED;
 	}
 
 	instance = (struct megasas_instance *)scmd->device->host->hostdata;
@@ -2949,7 +2948,7 @@ blk_eh_timer_return megasas_reset_timer(struct scsi_cmnd *scmd)
 
 		spin_unlock_irqrestore(instance->host->host_lock, flags);
 	}
-	return BLK_EH_RESET_TIMER;
+	return SCSI_EH_RESET_TIMER;
 }
 
 /**

drivers/scsi/mvumi.c

@@ -2109,7 +2109,7 @@ static int mvumi_queue_command(struct Scsi_Host *shost,
 	return 0;
 }
 
-static enum blk_eh_timer_return mvumi_timed_out(struct scsi_cmnd *scmd)
+static enum scsi_timeout_action mvumi_timed_out(struct scsi_cmnd *scmd)
 {
 	struct mvumi_cmd *cmd = mvumi_priv(scmd)->cmd_priv;
 	struct Scsi_Host *host = scmd->device->host;
@@ -2137,7 +2137,7 @@ static enum blk_eh_timer_return mvumi_timed_out(struct scsi_cmnd *scmd)
 	mvumi_return_cmd(mhba, cmd);
 	spin_unlock_irqrestore(mhba->shost->host_lock, flags);
 
-	return BLK_EH_DONE;
+	return SCSI_EH_NOT_HANDLED;
 }
 
 static int

drivers/scsi/qla4xxx/ql4_os.c

@@ -116,7 +116,7 @@ static int qla4xxx_iface_set_param(struct Scsi_Host *shost, void *data,
 static int qla4xxx_get_iface_param(struct iscsi_iface *iface,
 				   enum iscsi_param_type param_type,
 				   int param, char *buf);
-static enum blk_eh_timer_return qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc);
+static enum scsi_timeout_action qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc);
 static struct iscsi_endpoint *qla4xxx_ep_connect(struct Scsi_Host *shost,
 						 struct sockaddr *dst_addr,
 						 int non_blocking);
@@ -1871,17 +1871,17 @@ static void qla4xxx_conn_get_stats(struct iscsi_cls_conn *cls_conn,
 	return;
 }
 
-static enum blk_eh_timer_return qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc)
+static enum scsi_timeout_action qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc)
 {
 	struct iscsi_cls_session *session;
 	unsigned long flags;
-	enum blk_eh_timer_return ret = BLK_EH_DONE;
+	enum scsi_timeout_action ret = SCSI_EH_NOT_HANDLED;
 
 	session = starget_to_session(scsi_target(sc->device));
 
 	spin_lock_irqsave(&session->lock, flags);
 	if (session->state == ISCSI_SESSION_FAILED)
-		ret = BLK_EH_RESET_TIMER;
+		ret = SCSI_EH_RESET_TIMER;
 	spin_unlock_irqrestore(&session->lock, flags);
 
 	return ret;

drivers/scsi/scsi_error.c

@@ -328,7 +328,6 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd)
 enum blk_eh_timer_return scsi_timeout(struct request *req)
 {
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
-	enum blk_eh_timer_return rtn = BLK_EH_DONE;
 	struct Scsi_Host *host = scmd->device->host;
 
 	trace_scsi_dispatch_cmd_timeout(scmd);
@@ -338,23 +337,29 @@ enum blk_eh_timer_return scsi_timeout(struct request *req)
 	if (host->eh_deadline != -1 && !host->last_reset)
 		host->last_reset = jiffies;
 
-	if (host->hostt->eh_timed_out)
-		rtn = host->hostt->eh_timed_out(scmd);
-
-	if (rtn == BLK_EH_DONE) {
-		/*
-		 * If scsi_done() has already set SCMD_STATE_COMPLETE, do not
-		 * modify *scmd.
-		 */
-		if (test_and_set_bit(SCMD_STATE_COMPLETE, &scmd->state))
+	if (host->hostt->eh_timed_out) {
+		switch (host->hostt->eh_timed_out(scmd)) {
+		case SCSI_EH_DONE:
 			return BLK_EH_DONE;
-		if (scsi_abort_command(scmd) != SUCCESS) {
-			set_host_byte(scmd, DID_TIME_OUT);
-			scsi_eh_scmd_add(scmd);
+		case SCSI_EH_RESET_TIMER:
+			return BLK_EH_RESET_TIMER;
+		case SCSI_EH_NOT_HANDLED:
+			break;
 		}
 	}
 
-	return rtn;
+	/*
+	 * If scsi_done() has already set SCMD_STATE_COMPLETE, do not modify
+	 * *scmd.
+	 */
+	if (test_and_set_bit(SCMD_STATE_COMPLETE, &scmd->state))
+		return BLK_EH_DONE;
+	if (scsi_abort_command(scmd) != SUCCESS) {
+		set_host_byte(scmd, DID_TIME_OUT);
+		scsi_eh_scmd_add(scmd);
+	}
+
+	return BLK_EH_DONE;
 }
 
 /**

drivers/scsi/scsi_transport_fc.c

@@ -2530,15 +2530,14 @@ static int fc_vport_match(struct attribute_container *cont,
  * Notes:
  *	This routine assumes no locks are held on entry.
  */
-enum blk_eh_timer_return
-fc_eh_timed_out(struct scsi_cmnd *scmd)
+enum scsi_timeout_action fc_eh_timed_out(struct scsi_cmnd *scmd)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(scmd->device));
 
 	if (rport->port_state == FC_PORTSTATE_BLOCKED)
-		return BLK_EH_RESET_TIMER;
+		return SCSI_EH_RESET_TIMER;
 
-	return BLK_EH_DONE;
+	return SCSI_EH_NOT_HANDLED;
 }
 EXPORT_SYMBOL(fc_eh_timed_out);
 

drivers/scsi/scsi_transport_srp.c

@@ -594,13 +594,13 @@ EXPORT_SYMBOL(srp_reconnect_rport);
  * @scmd: SCSI command.
  *
  * If a timeout occurs while an rport is in the blocked state, ask the SCSI
- * EH to continue waiting (BLK_EH_RESET_TIMER). Otherwise let the SCSI core
- * handle the timeout (BLK_EH_DONE).
+ * EH to continue waiting (SCSI_EH_RESET_TIMER). Otherwise let the SCSI core
+ * handle the timeout (SCSI_EH_NOT_HANDLED).
  *
  * Note: This function is called from soft-IRQ context and with the request
  * queue lock held.
  */
-enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
+enum scsi_timeout_action srp_timed_out(struct scsi_cmnd *scmd)
 {
 	struct scsi_device *sdev = scmd->device;
 	struct Scsi_Host *shost = sdev->host;
@@ -611,7 +611,7 @@ enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
 	return rport && rport->fast_io_fail_tmo < 0 &&
 		rport->dev_loss_tmo < 0 &&
 		i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ?
-		BLK_EH_RESET_TIMER : BLK_EH_DONE;
+		SCSI_EH_RESET_TIMER : SCSI_EH_NOT_HANDLED;
 }
 EXPORT_SYMBOL(srp_timed_out);
 

drivers/scsi/storvsc_drv.c

@@ -1652,13 +1652,13 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
  * be unbounded on Azure.  Reset the timer unconditionally to give the host a
  * chance to perform EH.
  */
-static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
+static enum scsi_timeout_action storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
 {
 #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
 	if (scmnd->device->host->transportt == fc_transport_template)
 		return fc_eh_timed_out(scmnd);
 #endif
-	return BLK_EH_RESET_TIMER;
+	return SCSI_EH_RESET_TIMER;
 }
 
 static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd)

drivers/scsi/virtio_scsi.c

@@ -731,9 +731,9 @@ static void virtscsi_commit_rqs(struct Scsi_Host *shost, u16 hwq)
  * latencies might be higher than on bare metal.  Reset the timer
  * unconditionally to give the host a chance to perform EH.
  */
-static enum blk_eh_timer_return virtscsi_eh_timed_out(struct scsi_cmnd *scmnd)
+static enum scsi_timeout_action virtscsi_eh_timed_out(struct scsi_cmnd *scmnd)
 {
-	return BLK_EH_RESET_TIMER;
+	return SCSI_EH_RESET_TIMER;
 }
 
 static struct scsi_host_template virtscsi_host_template = {

include/scsi/libiscsi.h

@@ -393,7 +393,7 @@ extern int iscsi_eh_recover_target(struct scsi_cmnd *sc);
 extern int iscsi_eh_session_reset(struct scsi_cmnd *sc);
 extern int iscsi_eh_device_reset(struct scsi_cmnd *sc);
 extern int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc);
-extern enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc);
+extern enum scsi_timeout_action iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc);
 
 /*
  * iSCSI host helpers.

include/scsi/scsi_host.h

@@ -27,6 +27,18 @@ struct scsi_transport_template;
 #define MODE_INITIATOR 0x01
 #define MODE_TARGET 0x02
 
+/**
+ * enum scsi_timeout_action - How to handle a command that timed out.
+ * @SCSI_EH_DONE: The command has already been completed.
+ * @SCSI_EH_RESET_TIMER: Reset the timer and continue waiting for completion.
+ * @SCSI_EH_NOT_HANDLED: The command has not yet finished. Abort the command.
+ */
+enum scsi_timeout_action {
+	SCSI_EH_DONE,
+	SCSI_EH_RESET_TIMER,
+	SCSI_EH_NOT_HANDLED,
+};
+
 struct scsi_host_template {
 	/*
 	 * Put fields referenced in IO submission path together in
@@ -331,7 +343,7 @@ struct scsi_host_template {
 	 *
 	 * Status: OPTIONAL
 	 */
-	enum blk_eh_timer_return (*eh_timed_out)(struct scsi_cmnd *);
+	enum scsi_timeout_action (*eh_timed_out)(struct scsi_cmnd *);
 	/*
 	 * Optional routine that allows the transport to decide if a cmd
 	 * is retryable. Return true if the transport is in a state the

include/scsi/scsi_transport_fc.h

@@ -862,7 +862,7 @@ struct fc_vport *fc_vport_create(struct Scsi_Host *shost, int channel,
 int fc_vport_terminate(struct fc_vport *vport);
 int fc_block_rport(struct fc_rport *rport);
 int fc_block_scsi_eh(struct scsi_cmnd *cmnd);
-enum blk_eh_timer_return fc_eh_timed_out(struct scsi_cmnd *scmd);
+enum scsi_timeout_action fc_eh_timed_out(struct scsi_cmnd *scmd);
 bool fc_eh_should_retry_cmd(struct scsi_cmnd *scmd);
 
 static inline struct Scsi_Host *fc_bsg_to_shost(struct bsg_job *job)

include/scsi/scsi_transport_srp.h

@@ -118,7 +118,7 @@ extern int srp_reconnect_rport(struct srp_rport *rport);
 extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
 extern void srp_stop_rport_timers(struct srp_rport *rport);
-enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd);
+enum scsi_timeout_action srp_timed_out(struct scsi_cmnd *scmd);
 
 /**
  * srp_chkready() - evaluate the transport layer state before I/O