IB/srp: Retry stale connections

When a host just goes away (crash, power loss, etc.) without tearing
down its IB connections, it can get stale connection errors when it
tries to reconnect to targets upon rebooting. Retrying the connection
a few times will prevent sysadmins from playing the "which disk(s)
went missing?" game.

This would have made things slightly quicker when tracking down some
of the recent bugs, but it also helps quite a bit when you've got a
large number of targets hanging off a wedged server.

Signed-off-by: David Dillow <[e-mail]>
Signed-off-by: Roland Dreier <[e-mail]>

drivers/infiniband/ulp/srp/ib_srp.c

···
 	return ret;
 }
 
+static int srp_new_cm_id(struct srp_target_port *target)
+{
+	struct ib_cm_id *new_cm_id;
+
+	new_cm_id = ib_create_cm_id(target->srp_host->dev->dev,
+				    srp_cm_handler, target);
+	if (IS_ERR(new_cm_id))
+		return PTR_ERR(new_cm_id);
+
+	if (target->cm_id)
+		ib_destroy_cm_id(target->cm_id);
+	target->cm_id = new_cm_id;
+
+	return 0;
+}
+
 static int srp_create_target_ib(struct srp_target_port *target)
 {
 	struct ib_qp_init_attr *init_attr;
···
 
 static int srp_connect_target(struct srp_target_port *target)
 {
+	int retries = 3;
 	int ret;
 
 	ret = srp_lookup_path(target);
···
 			break;
 
 		case SRP_DLID_REDIRECT:
+			break;
+
+		case SRP_STALE_CONN:
+			/* Our current CM id was stale, and is now in timewait.
+			 * Try to reconnect with a new one.
+			 */
+			if (!retries-- || srp_new_cm_id(target)) {
+				shost_printk(KERN_ERR, target->scsi_host, PFX
+					     "giving up on stale connection\n");
+				target->status = -ECONNRESET;
+				return target->status;
+			}
+
+			shost_printk(KERN_ERR, target->scsi_host, PFX
+				     "retrying stale connection\n");
 			break;
 
 		default:
···
 
 static int srp_reconnect_target(struct srp_target_port *target)
 {
-	struct ib_cm_id *new_cm_id;
 	struct ib_qp_attr qp_attr;
 	struct srp_request *req, *tmp;
 	struct ib_wc wc;
···
 	 * Now get a new local CM ID so that we avoid confusing the
 	 * target in case things are really fouled up.
 	 */
-	new_cm_id = ib_create_cm_id(target->srp_host->dev->dev,
-				    srp_cm_handler, target);
-	if (IS_ERR(new_cm_id)) {
-		ret = PTR_ERR(new_cm_id);
+	ret = srp_new_cm_id(target);
+	if (ret)
 		goto err;
-	}
-	ib_destroy_cm_id(target->cm_id);
-	target->cm_id = new_cm_id;
 
 	qp_attr.qp_state = IB_QPS_RESET;
 	ret = ib_modify_qp(target->qp, &qp_attr, IB_QP_STATE);
···
 				     "  REJ reason: IB_CM_REJ_CONSUMER_DEFINED,"
 				     " opcode 0x%02x\n", opcode);
 		target->status = -ECONNRESET;
+		break;
+
+	case IB_CM_REJ_STALE_CONN:
+		shost_printk(KERN_WARNING, shost, "  REJ reason: stale connection\n");
+		target->status = SRP_STALE_CONN;
 		break;
 
 	default:
···
 	if (ret)
 		goto err;
 
-	target->cm_id = ib_create_cm_id(host->dev->dev, srp_cm_handler, target);
-	if (IS_ERR(target->cm_id)) {
-		ret = PTR_ERR(target->cm_id);
+	ret = srp_new_cm_id(target);
+	if (ret)
 		goto err_free;
-	}
 
 	target->qp_in_error = 0;
 	ret = srp_connect_target(target);

drivers/infiniband/ulp/srp/ib_srp.h

···
 
 	SRP_PORT_REDIRECT	= 1,
 	SRP_DLID_REDIRECT	= 2,
+	SRP_STALE_CONN		= 3,
 
 	SRP_MAX_LUN		= 512,
 	SRP_DEF_SG_TABLESIZE	= 12,