IB SRP initiator patches for kernel 3.13

index e158f59..b4bd903 100644
@@ -2579,7 +2579,7 @@ enum {
 	SRP_OPT_SG_TABLESIZE	= 1 << 11,
 	SRP_OPT_COMP_VECTOR	= 1 << 12,
 	SRP_OPT_TL_RETRY_COUNT	= 1 << 13,
-	SRP_OPT_CAN_QUEUE	= 1 << 14,
+	SRP_OPT_QUEUE_SIZE	= 1 << 14,
 	SRP_OPT_USE_FAST_REG	= 1 << 15,
 	SRP_OPT_ALL		= (SRP_OPT_ID_EXT	|
 				   SRP_OPT_IOC_GUID	|

@@ -2603,7 +2603,7 @@ static const match_table_t srp_opt_tokens = {
 	{ SRP_OPT_SG_TABLESIZE,		"sg_tablesize=%u"	},
 	{ SRP_OPT_COMP_VECTOR,		"comp_vector=%u"	},
 	{ SRP_OPT_TL_RETRY_COUNT,	"tl_retry_count=%u"	},
-	{ SRP_OPT_CAN_QUEUE,		"can_queue=%d"		},
+	{ SRP_OPT_QUEUE_SIZE,		"queue_size=%d"		},
 	{ SRP_OPT_USE_FAST_REG,		"use_fast_reg=%d"	},
 	{ SRP_OPT_ERR,			NULL 			}
 };

@@ -2699,9 +2699,9 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target)
 			target->scsi_host->max_sectors = token;
 			break;
 
-		case SRP_OPT_CAN_QUEUE:
+		case SRP_OPT_QUEUE_SIZE:
 			if (match_int(args, &token) || token < 1) {
-				pr_warn("bad can_queue parameter '%s'\n", p);
+				pr_warn("bad queue_size parameter '%s'\n", p);
 				goto out;
 			}
 			target->scsi_host->can_queue = token;

@@ -2816,7 +2816,7 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target)
 
 	if (target->scsi_host->cmd_per_lun > target->scsi_host->can_queue
 	    && (opt_mask & SRP_OPT_MAX_CMD_PER_LUN))
-		pr_warn("cmd_per_lun = %d > can_queue = %d\n",
+		pr_warn("cmd_per_lun = %d > queue_size = %d\n",
 			target->scsi_host->cmd_per_lun,
 			target->scsi_host->can_queue);
 

index 8f66ed4..8b9cb22 100644
@@ -423,7 +423,8 @@ static void rport_fast_io_fail_timedout(struct work_struct *work)
 		dev_name(&rport->dev), dev_name(&shost->shost_gendev));
 
 	mutex_lock(&rport->mutex);
-	__rport_fail_io_fast(rport);
+	if (rport->state == SRP_RPORT_BLOCKED)
+		__rport_fail_io_fast(rport);
 	mutex_unlock(&rport->mutex);
 }
 

index 17b58f4..aed5b75 100644
@@ -390,7 +390,7 @@ static int srp_send_req(struct srp_target_port *target)
 	req->param.responder_resources	      = 4;
 	req->param.remote_cm_response_timeout = 20;
 	req->param.local_cm_response_timeout  = 20;
-	req->param.retry_count 		      = 7;
+	req->param.retry_count                = target->tl_retry_count;
 	req->param.rnr_retry_count 	      = 7;
 	req->param.max_cm_retries 	      = 15;
 

@@ -1907,6 +1907,14 @@ static ssize_t show_comp_vector(struct device *dev,
 	return sprintf(buf, "%d\n", target->comp_vector);
 }
 
+static ssize_t show_tl_retry_count(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct srp_target_port *target = host_to_target(class_to_shost(dev));
+
+	return sprintf(buf, "%d\n", target->tl_retry_count);
+}
+
 static ssize_t show_cmd_sg_entries(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {

@@ -1934,6 +1942,7 @@ static DEVICE_ATTR(zero_req_lim,    S_IRUGO, show_zero_req_lim,	   NULL);
 static DEVICE_ATTR(local_ib_port,   S_IRUGO, show_local_ib_port,   NULL);
 static DEVICE_ATTR(local_ib_device, S_IRUGO, show_local_ib_device, NULL);
 static DEVICE_ATTR(comp_vector,     S_IRUGO, show_comp_vector,     NULL);
+static DEVICE_ATTR(tl_retry_count,  S_IRUGO, show_tl_retry_count,  NULL);
 static DEVICE_ATTR(cmd_sg_entries,  S_IRUGO, show_cmd_sg_entries,  NULL);
 static DEVICE_ATTR(allow_ext_sg,    S_IRUGO, show_allow_ext_sg,    NULL);
 

@@ -1949,6 +1958,7 @@ static struct device_attribute *srp_host_attrs[] = {
 	&dev_attr_local_ib_port,
 	&dev_attr_local_ib_device,
 	&dev_attr_comp_vector,
+	&dev_attr_tl_retry_count,
 	&dev_attr_cmd_sg_entries,
 	&dev_attr_allow_ext_sg,
 	NULL

@@ -2073,6 +2083,7 @@ enum {
 	SRP_OPT_ALLOW_EXT_SG	= 1 << 10,
 	SRP_OPT_SG_TABLESIZE	= 1 << 11,
 	SRP_OPT_COMP_VECTOR	= 1 << 12,
+	SRP_OPT_TL_RETRY_COUNT	= 1 << 13,
 	SRP_OPT_ALL		= (SRP_OPT_ID_EXT	|
 				   SRP_OPT_IOC_GUID	|
 				   SRP_OPT_DGID		|

@@ -2094,6 +2105,7 @@ static const match_table_t srp_opt_tokens = {
 	{ SRP_OPT_ALLOW_EXT_SG,		"allow_ext_sg=%u"	},
 	{ SRP_OPT_SG_TABLESIZE,		"sg_tablesize=%u"	},
 	{ SRP_OPT_COMP_VECTOR,		"comp_vector=%u"	},
+	{ SRP_OPT_TL_RETRY_COUNT,	"tl_retry_count=%u"	},
 	{ SRP_OPT_ERR,			NULL 			}
 };
 

@@ -2257,6 +2269,15 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target)
 			target->comp_vector = token;
 			break;
 
+		case SRP_OPT_TL_RETRY_COUNT:
+			if (match_int(args, &token) || token < 2 || token > 7) {
+				pr_warn("bad tl_retry_count parameter '%s' (must be a number between 2 and 7)\n",
+					p);
+				goto out;
+			}
+			target->tl_retry_count = token;
+			break;
+
 		default:
 			pr_warn("unknown parameter or missing value '%s' in target creation request\n",
 				p);

@@ -2311,6 +2332,7 @@ static ssize_t srp_create_target(struct device *dev,
 	target->cmd_sg_cnt	= cmd_sg_entries;
 	target->sg_tablesize	= indirect_sg_entries ? : cmd_sg_entries;
 	target->allow_ext_sg	= allow_ext_sg;
+	target->tl_retry_count	= 7;
 
 	ret = srp_parse_options(buf, target);
 	if (ret)

index e641088..84d821b 100644
@@ -157,6 +157,7 @@ struct srp_target_port {
 	unsigned int		scsi_id;
 	unsigned int		sg_tablesize;
 	int			comp_vector;
+	int			tl_retry_count;
 
 	struct ib_sa_path_rec	path;
 	__be16			orig_dgid[8];

index aed5b75..414fd02 100644
@@ -528,11 +528,13 @@ static void srp_remove_target(struct srp_target_port *target)
 	WARN_ON_ONCE(target->state != SRP_TARGET_REMOVED);
 
 	srp_del_scsi_host_attr(target->scsi_host);
+	srp_rport_get(target->rport);
 	srp_remove_host(target->scsi_host);
 	scsi_remove_host(target->scsi_host);
 	srp_disconnect_target(target);
 	ib_destroy_cm_id(target->cm_id);
 	srp_free_target_ib(target);
+	srp_rport_put(target->rport);
 	srp_free_req_data(target);
 
 	spin_lock(&target->srp_host->target_lock);

@@ -2004,6 +2006,7 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 	}
 
 	rport->lld_data = target;
+	target->rport = rport;
 
 	spin_lock(&host->target_lock);
 	list_add_tail(&target->list, &host->target_list);

index 84d821b..2a1768f 100644
@@ -153,6 +153,7 @@ struct srp_target_port {
 	u16			io_class;
 	struct srp_host	       *srp_host;
 	struct Scsi_Host       *scsi_host;
+	struct srp_rport       *rport;
 	char			target_name[32];
 	unsigned int		scsi_id;
 	unsigned int		sg_tablesize;

index f379c7f..f7ba94a 100644
@@ -185,6 +185,24 @@ static int srp_host_match(struct attribute_container *cont, struct device *dev)
 }
 
 /**
+ * srp_rport_get() - increment rport reference count
+ */
+void srp_rport_get(struct srp_rport *rport)
+{
+	get_device(&rport->dev);
+}
+EXPORT_SYMBOL(srp_rport_get);
+
+/**
+ * srp_rport_put() - decrement rport reference count
+ */
+void srp_rport_put(struct srp_rport *rport)
+{
+	put_device(&rport->dev);
+}
+EXPORT_SYMBOL(srp_rport_put);
+
+/**
  * srp_rport_add - add a SRP remote port to the device hierarchy
  * @shost:	scsi host the remote port is connected to.
  * @ids:	The port id for the remote port.

index ff0f04a..5a2d2d1 100644
@@ -38,6 +38,8 @@ extern struct scsi_transport_template *
 srp_attach_transport(struct srp_function_template *);
 extern void srp_release_transport(struct scsi_transport_template *);
 
+extern void srp_rport_get(struct srp_rport *rport);
+extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);

index 414fd02..5551f3b 100644
@@ -86,6 +86,27 @@ module_param(topspin_workarounds, int, 0444);
 MODULE_PARM_DESC(topspin_workarounds,
 		 "Enable workarounds for Topspin/Cisco SRP target bugs if != 0");
 
+static struct kernel_param_ops srp_tmo_ops;
+
+static int srp_fast_io_fail_tmo = 15;
+module_param_cb(fast_io_fail_tmo, &srp_tmo_ops, &srp_fast_io_fail_tmo,
+		S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(fast_io_fail_tmo,
+		 "Number of seconds between the observation of a transport"
+		 " layer error and failing all I/O. \"off\" means that this"
+		 " functionality is disabled.");
+
+static int srp_dev_loss_tmo = 60;
+module_param_cb(dev_loss_tmo, &srp_tmo_ops, &srp_dev_loss_tmo,
+		S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dev_loss_tmo,
+		 "Maximum number of seconds that the SRP transport should"
+		 " insulate transport layer errors. After this time has been"
+		 " exceeded the SCSI host is removed. Should be"
+		 " between 1 and " __stringify(SCSI_DEVICE_BLOCK_MAX_TIMEOUT)
+		 " if fast_io_fail_tmo has not been set. \"off\" means that"
+		 " this functionality is disabled.");
+
 static void srp_add_one(struct ib_device *device);
 static void srp_remove_one(struct ib_device *device);
 static void srp_recv_completion(struct ib_cq *cq, void *target_ptr);

@@ -102,6 +123,44 @@ static struct ib_client srp_client = {
 
 static struct ib_sa_client srp_sa_client;
 
+static int srp_tmo_get(char *buffer, const struct kernel_param *kp)
+{
+	int tmo = *(int *)kp->arg;
+
+	if (tmo >= 0)
+		return sprintf(buffer, "%d", tmo);
+	else
+		return sprintf(buffer, "off");
+}
+
+static int srp_tmo_set(const char *val, const struct kernel_param *kp)
+{
+	int tmo, res;
+
+	if (strncmp(val, "off", 3) != 0) {
+		res = kstrtoint(val, 0, &tmo);
+		if (res)
+			goto out;
+	} else {
+		tmo = -1;
+	}
+	if (kp->arg == &srp_fast_io_fail_tmo)
+		res = srp_tmo_valid(tmo, srp_dev_loss_tmo);
+	else
+		res = srp_tmo_valid(srp_fast_io_fail_tmo, tmo);
+	if (res)
+		goto out;
+	*(int *)kp->arg = tmo;
+
+out:
+	return res;
+}
+
+static struct kernel_param_ops srp_tmo_ops = {
+	.get = srp_tmo_get,
+	.set = srp_tmo_set,
+};
+
 static inline struct srp_target_port *host_to_target(struct Scsi_Host *host)
 {
 	return (struct srp_target_port *) host->hostdata;

@@ -689,23 +748,42 @@ static void srp_free_req(struct srp_target_port *target,
 	spin_unlock_irqrestore(&target->lock, flags);
 }
 
-static void srp_reset_req(struct srp_target_port *target, struct srp_request *req)
+static void srp_finish_req(struct srp_target_port *target,
+			   struct srp_request *req, int result)
 {
 	struct scsi_cmnd *scmnd = srp_claim_req(target, req, NULL);
 
 	if (scmnd) {
 		srp_free_req(target, req, scmnd, 0);
-		scmnd->result = DID_RESET << 16;
+		scmnd->result = result;
 		scmnd->scsi_done(scmnd);
 	}
 }
 
-static int srp_reconnect_target(struct srp_target_port *target)
+static void srp_terminate_io(struct srp_rport *rport)
 {
-	struct Scsi_Host *shost = target->scsi_host;
-	int i, ret;
+	struct srp_target_port *target = rport->lld_data;
+	int i;
+
+	for (i = 0; i < SRP_CMD_SQ_SIZE; ++i) {
+		struct srp_request *req = &target->req_ring[i];
+		srp_finish_req(target, req, DID_TRANSPORT_FAILFAST << 16);
+	}
+}
 
-	scsi_target_block(&shost->shost_gendev);
+/*
+ * It is up to the caller to ensure that srp_rport_reconnect() calls are
+ * serialized and that no concurrent srp_queuecommand(), srp_abort(),
+ * srp_reset_device() or srp_reset_host() calls will occur while this function
+ * is in progress. One way to realize that is not to call this function
+ * directly but to call srp_reconnect_rport() instead since that last function
+ * serializes calls of this function via rport->mutex and also blocks
+ * srp_queuecommand() calls before invoking this function.
+ */
+static int srp_rport_reconnect(struct srp_rport *rport)
+{
+	struct srp_target_port *target = rport->lld_data;
+	int i, ret;
 
 	srp_disconnect_target(target);
 	/*

@@ -726,8 +804,7 @@ static int srp_reconnect_target(struct srp_target_port *target)
 
 	for (i = 0; i < SRP_CMD_SQ_SIZE; ++i) {
 		struct srp_request *req = &target->req_ring[i];
-		if (req->scmnd)
-			srp_reset_req(target, req);
+		srp_finish_req(target, req, DID_RESET << 16);
 	}
 
 	INIT_LIST_HEAD(&target->free_tx);

@@ -737,28 +814,9 @@ static int srp_reconnect_target(struct srp_target_port *target)
 	if (ret == 0)
 		ret = srp_connect_target(target);
 
-	scsi_target_unblock(&shost->shost_gendev, ret == 0 ? SDEV_RUNNING :
-			    SDEV_TRANSPORT_OFFLINE);
-	target->transport_offline = !!ret;
-
-	if (ret)
-		goto err;
-
-	shost_printk(KERN_INFO, target->scsi_host, PFX "reconnect succeeded\n");
-
-	return ret;
-
-err:
-	shost_printk(KERN_ERR, target->scsi_host,
-		     PFX "reconnect failed (%d), removing target port.\n", ret);
-
-	/*
-	 * We couldn't reconnect, so kill our target port off.
-	 * However, we have to defer the real removal because we
-	 * are in the context of the SCSI error handler now, which
-	 * will deadlock if we call scsi_remove_host().
-	 */
-	srp_queue_remove_work(target);
+	if (ret == 0)
+		shost_printk(KERN_INFO, target->scsi_host,
+			     PFX "reconnect succeeded\n");
 
 	return ret;
 }

@@ -1356,10 +1414,11 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 	struct srp_cmd *cmd;
 	struct ib_device *dev;
 	unsigned long flags;
-	int len;
+	int len, result;
 
-	if (unlikely(target->transport_offline)) {
-		scmnd->result = DID_NO_CONNECT << 16;
+	result = srp_chkready(target->rport);
+	if (unlikely(result)) {
+		scmnd->result = result;
 		scmnd->scsi_done(scmnd);
 		return 0;
 	}

@@ -1757,7 +1816,7 @@ static int srp_abort(struct scsi_cmnd *scmnd)
 	if (srp_send_tsk_mgmt(target, req->index, scmnd->device->lun,
 			      SRP_TSK_ABORT_TASK) == 0)
 		ret = SUCCESS;
-	else if (target->transport_offline)
+	else if (target->rport->state == SRP_RPORT_LOST)
 		ret = FAST_IO_FAIL;
 	else
 		ret = FAILED;

@@ -1784,7 +1843,7 @@ static int srp_reset_device(struct scsi_cmnd *scmnd)
 	for (i = 0; i < SRP_CMD_SQ_SIZE; ++i) {
 		struct srp_request *req = &target->req_ring[i];
 		if (req->scmnd && req->scmnd->device == scmnd->device)
-			srp_reset_req(target, req);
+			srp_finish_req(target, req, DID_RESET << 16);
 	}
 
 	return SUCCESS;

@@ -1793,14 +1852,10 @@ static int srp_reset_device(struct scsi_cmnd *scmnd)
 static int srp_reset_host(struct scsi_cmnd *scmnd)
 {
 	struct srp_target_port *target = host_to_target(scmnd->device->host);
-	int ret = FAILED;
 
 	shost_printk(KERN_ERR, target->scsi_host, PFX "SRP reset_host called\n");
 
-	if (!srp_reconnect_target(target))
-		ret = SUCCESS;
-
-	return ret;
+	return srp_reconnect_rport(target->rport) == 0 ? SUCCESS : FAILED;
 }
 
 static int srp_slave_configure(struct scsi_device *sdev)

@@ -2637,7 +2692,13 @@ static void srp_remove_one(struct ib_device *device)
 }
 
 static struct srp_function_template ib_srp_transport_functions = {
+	.has_rport_state	 = true,
+	.reset_timer_if_blocked	 = true,
+	.fast_io_fail_tmo	 = &srp_fast_io_fail_tmo,
+	.dev_loss_tmo		 = &srp_dev_loss_tmo,
+	.reconnect		 = srp_rport_reconnect,
 	.rport_delete		 = srp_rport_delete,
+	.terminate_rport_io	 = srp_terminate_io,
 };
 
 static int __init srp_init_module(void)

index 2a1768f..fd1817e 100644
@@ -140,7 +140,6 @@ struct srp_target_port {
 	unsigned int		cmd_sg_cnt;
 	unsigned int		indirect_size;
 	bool			allow_ext_sg;
-	bool			transport_offline;
 
 	/* Everything above this point is used in the hot path of
 	 * command processing. Try to keep them packed into cachelines.

index 5551f3b..ceb84b6 100644
@@ -593,6 +593,7 @@ static void srp_remove_target(struct srp_target_port *target)
 	srp_disconnect_target(target);
 	ib_destroy_cm_id(target->cm_id);
 	srp_free_target_ib(target);
+	cancel_work_sync(&target->tl_err_work);
 	srp_rport_put(target->rport);
 	srp_free_req_data(target);
 

@@ -1363,6 +1364,21 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc)
 			     PFX "Recv failed with error code %d\n", res);
 }
 
+/**
+ * srp_tl_err_work() - handle a transport layer error
+ *
+ * Note: This function may get invoked before the rport has been created,
+ * hence the target->rport test.
+ */
+static void srp_tl_err_work(struct work_struct *work)
+{
+	struct srp_target_port *target;
+
+	target = container_of(work, struct srp_target_port, tl_err_work);
+	if (target->rport)
+		srp_start_tl_fail_timers(target->rport);
+}
+
 static void srp_handle_qp_err(enum ib_wc_status wc_status, bool send_err,
 			      struct srp_target_port *target)
 {

@@ -1371,6 +1387,7 @@ static void srp_handle_qp_err(enum ib_wc_status wc_status, bool send_err,
 			     PFX "failed %s status %d\n",
 			     send_err ? "send" : "receive",
 			     wc_status);
+		queue_work(system_long_wq, &target->tl_err_work);
 	}
 	target->qp_in_error = true;
 }

@@ -1733,6 +1750,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
 		if (ib_send_cm_drep(cm_id, NULL, 0))
 			shost_printk(KERN_ERR, target->scsi_host,
 				     PFX "Sending CM DREP failed\n");
+		queue_work(system_long_wq, &target->tl_err_work);
 		break;
 
 	case IB_CM_TIMEWAIT_EXIT:

@@ -2419,6 +2437,7 @@ static ssize_t srp_create_target(struct device *dev,
 			     sizeof (struct srp_indirect_buf) +
 			     target->cmd_sg_cnt * sizeof (struct srp_direct_buf);
 
+	INIT_WORK(&target->tl_err_work, srp_tl_err_work);
 	INIT_WORK(&target->remove_work, srp_remove_work);
 	spin_lock_init(&target->lock);
 	INIT_LIST_HEAD(&target->free_tx);

index fd1817e..446b045 100644
@@ -177,6 +177,7 @@ struct srp_target_port {
 	struct srp_iu	       *rx_ring[SRP_RQ_SIZE];
 	struct srp_request	req_ring[SRP_CMD_SQ_SIZE];
 
+	struct work_struct	tl_err_work;
 	struct work_struct	remove_work;
 
 	struct list_head	list;

index a120658..4be3eb8 100644
@@ -88,6 +88,11 @@ MODULE_PARM_DESC(topspin_workarounds,
 
 static struct kernel_param_ops srp_tmo_ops;
 
+static int srp_reconnect_delay = 10;
+module_param_cb(reconnect_delay, &srp_tmo_ops, &srp_reconnect_delay,
+		S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reconnect_delay, "Time between successive reconnect attempts");
+
 static int srp_fast_io_fail_tmo = 15;
 module_param_cb(fast_io_fail_tmo, &srp_tmo_ops, &srp_fast_io_fail_tmo,
 		S_IRUGO | S_IWUSR);

@@ -96,7 +101,7 @@ MODULE_PARM_DESC(fast_io_fail_tmo,
 		 " layer error and failing all I/O. \"off\" means that this"
 		 " functionality is disabled.");
 
-static int srp_dev_loss_tmo = 60;
+static int srp_dev_loss_tmo = 600;
 module_param_cb(dev_loss_tmo, &srp_tmo_ops, &srp_dev_loss_tmo,
 		S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(dev_loss_tmo,

@@ -144,10 +149,14 @@ static int srp_tmo_set(const char *val, const struct kernel_param *kp)
 	} else {
 		tmo = -1;
 	}
-	if (kp->arg == &srp_fast_io_fail_tmo)
-		res = srp_tmo_valid(-1, tmo, srp_dev_loss_tmo);
+	if (kp->arg == &srp_reconnect_delay)
+		res = srp_tmo_valid(tmo, srp_fast_io_fail_tmo,
+				    srp_dev_loss_tmo);
+	else if (kp->arg == &srp_fast_io_fail_tmo)
+		res = srp_tmo_valid(srp_reconnect_delay, tmo, srp_dev_loss_tmo);
 	else
-		res = srp_tmo_valid(-1, srp_fast_io_fail_tmo, tmo);
+		res = srp_tmo_valid(srp_reconnect_delay, srp_fast_io_fail_tmo,
+				    tmo);
 	if (res)
 		goto out;
 	*(int *)kp->arg = tmo;

@@ -1426,18 +1435,29 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr)
 static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 {
 	struct srp_target_port *target = host_to_target(shost);
+	struct srp_rport *rport = target->rport;
 	struct srp_request *req;
 	struct srp_iu *iu;
 	struct srp_cmd *cmd;
 	struct ib_device *dev;
 	unsigned long flags;
 	int len, result;
+	const bool in_scsi_eh = !in_interrupt() && current == shost->ehandler;
+
+	/*
+	 * The SCSI EH thread is the only context from which srp_queuecommand()
+	 * can get invoked for blocked devices (SDEV_BLOCK /
+	 * SDEV_CREATED_BLOCK). Avoid racing with srp_reconnect_rport() by
+	 * locking the rport mutex if invoked from inside the SCSI EH.
+	 */
+	if (in_scsi_eh)
+		mutex_lock(&rport->mutex);
 
 	result = srp_chkready(target->rport);
 	if (unlikely(result)) {
 		scmnd->result = result;
 		scmnd->scsi_done(scmnd);
-		return 0;
+		goto unlock_rport;
 	}
 
 	spin_lock_irqsave(&target->lock, flags);

@@ -1482,6 +1502,10 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 		goto err_unmap;
 	}
 
+unlock_rport:
+	if (in_scsi_eh)
+		mutex_unlock(&rport->mutex);
+
 	return 0;
 
 err_unmap:

@@ -1496,6 +1520,9 @@ err_iu:
 err_unlock:
 	spin_unlock_irqrestore(&target->lock, flags);
 
+	if (in_scsi_eh)
+		mutex_unlock(&rport->mutex);
+
 	return SCSI_MLQUEUE_HOST_BUSY;
 }
 

@@ -1780,6 +1807,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
 static int srp_send_tsk_mgmt(struct srp_target_port *target,
 			     u64 req_tag, unsigned int lun, u8 func)
 {
+	struct srp_rport *rport = target->rport;
 	struct ib_device *dev = target->srp_host->srp_dev->dev;
 	struct srp_iu *iu;
 	struct srp_tsk_mgmt *tsk_mgmt;

@@ -1789,12 +1817,20 @@ static int srp_send_tsk_mgmt(struct srp_target_port *target,
 
 	init_completion(&target->tsk_mgmt_done);
 
+	/*
+	 * Lock the rport mutex to avoid that srp_create_target_ib() is
+	 * invoked while a task management function is being sent.
+	 */
+	mutex_lock(&rport->mutex);
 	spin_lock_irq(&target->lock);
 	iu = __srp_get_tx_iu(target, SRP_IU_TSK_MGMT);
 	spin_unlock_irq(&target->lock);
 
-	if (!iu)
+	if (!iu) {
+		mutex_unlock(&rport->mutex);
+
 		return -1;
+	}
 
 	ib_dma_sync_single_for_cpu(dev, iu->dma, sizeof *tsk_mgmt,
 				   DMA_TO_DEVICE);

@@ -1811,8 +1847,11 @@ static int srp_send_tsk_mgmt(struct srp_target_port *target,
 				      DMA_TO_DEVICE);
 	if (srp_post_send(target, iu, sizeof *tsk_mgmt)) {
 		srp_put_tx_iu(target, iu, SRP_IU_TSK_MGMT);
+		mutex_unlock(&rport->mutex);
+
 		return -1;
 	}
+	mutex_unlock(&rport->mutex);
 
 	if (!wait_for_completion_timeout(&target->tsk_mgmt_done,
 					 msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS)))

@@ -2713,6 +2752,7 @@ static void srp_remove_one(struct ib_device *device)
 static struct srp_function_template ib_srp_transport_functions = {
 	.has_rport_state	 = true,
 	.reset_timer_if_blocked	 = true,
+	.reconnect_delay	 = &srp_reconnect_delay,
 	.fast_io_fail_tmo	 = &srp_fast_io_fail_tmo,
 	.dev_loss_tmo		 = &srp_dev_loss_tmo,
 	.reconnect		 = srp_rport_reconnect,

index 4be3eb8..da60d11 100644
@@ -1965,6 +1965,14 @@ static ssize_t show_pkey(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "0x%04x\n", be16_to_cpu(target->path.pkey));
 }
 
+static ssize_t show_sgid(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct srp_target_port *target = host_to_target(class_to_shost(dev));
+
+	return sprintf(buf, "%pI6\n", target->path.sgid.raw);
+}
+
 static ssize_t show_dgid(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {

@@ -2049,6 +2057,7 @@ static DEVICE_ATTR(id_ext,	    S_IRUGO, show_id_ext,	   NULL);
 static DEVICE_ATTR(ioc_guid,	    S_IRUGO, show_ioc_guid,	   NULL);
 static DEVICE_ATTR(service_id,	    S_IRUGO, show_service_id,	   NULL);
 static DEVICE_ATTR(pkey,	    S_IRUGO, show_pkey,		   NULL);
+static DEVICE_ATTR(sgid,	    S_IRUGO, show_sgid,		   NULL);
 static DEVICE_ATTR(dgid,	    S_IRUGO, show_dgid,		   NULL);
 static DEVICE_ATTR(orig_dgid,	    S_IRUGO, show_orig_dgid,	   NULL);
 static DEVICE_ATTR(req_lim,         S_IRUGO, show_req_lim,         NULL);

@@ -2065,6 +2074,7 @@ static struct device_attribute *srp_host_attrs[] = {
 	&dev_attr_ioc_guid,
 	&dev_attr_service_id,
 	&dev_attr_pkey,
+	&dev_attr_sgid,
 	&dev_attr_dgid,
 	&dev_attr_orig_dgid,
 	&dev_attr_req_lim,

index da60d11..fdc0bc1 100644
@@ -576,6 +576,42 @@ static void srp_free_req_data(struct srp_target_port *target)
 	}
 }
 
+static int srp_alloc_req_data(struct srp_target_port *target)
+{
+	struct srp_device *srp_dev = target->srp_host->srp_dev;
+	struct ib_device *ibdev = srp_dev->dev;
+	struct srp_request *req;
+	dma_addr_t dma_addr;
+	int i, ret = -ENOMEM;
+
+	INIT_LIST_HEAD(&target->free_reqs);
+
+	for (i = 0; i < SRP_CMD_SQ_SIZE; ++i) {
+		req = &target->req_ring[i];
+		req->fmr_list = kmalloc(target->cmd_sg_cnt * sizeof(void *),
+					GFP_KERNEL);
+		req->map_page = kmalloc(SRP_FMR_SIZE * sizeof(void *),
+					GFP_KERNEL);
+		req->indirect_desc = kmalloc(target->indirect_size, GFP_KERNEL);
+		if (!req->fmr_list || !req->map_page || !req->indirect_desc)
+			goto out;
+
+		dma_addr = ib_dma_map_single(ibdev, req->indirect_desc,
+					     target->indirect_size,
+					     DMA_TO_DEVICE);
+		if (ib_dma_mapping_error(ibdev, dma_addr))
+			goto out;
+
+		req->indirect_dma_addr = dma_addr;
+		req->index = i;
+		list_add_tail(&req->list, &target->free_reqs);
+	}
+	ret = 0;
+
+out:
+	return ret;
+}
+
 /**
  * srp_del_scsi_host_attr() - Remove attributes defined in the host template.
  * @shost: SCSI host whose attributes to remove from sysfs.

@@ -2433,8 +2469,7 @@ static ssize_t srp_create_target(struct device *dev,
 	struct Scsi_Host *target_host;
 	struct srp_target_port *target;
 	struct ib_device *ibdev = host->srp_dev->dev;
-	dma_addr_t dma_addr;
-	int i, ret;
+	int ret;
 
 	target_host = scsi_host_alloc(&srp_template,
 				      sizeof (struct srp_target_port));

@@ -2490,28 +2525,9 @@ static ssize_t srp_create_target(struct device *dev,
 	INIT_WORK(&target->remove_work, srp_remove_work);
 	spin_lock_init(&target->lock);
 	INIT_LIST_HEAD(&target->free_tx);
-	INIT_LIST_HEAD(&target->free_reqs);
-	for (i = 0; i < SRP_CMD_SQ_SIZE; ++i) {
-		struct srp_request *req = &target->req_ring[i];
-
-		req->fmr_list = kmalloc(target->cmd_sg_cnt * sizeof (void *),
-					GFP_KERNEL);
-		req->map_page = kmalloc(SRP_FMR_SIZE * sizeof (void *),
-					GFP_KERNEL);
-		req->indirect_desc = kmalloc(target->indirect_size, GFP_KERNEL);
-		if (!req->fmr_list || !req->map_page || !req->indirect_desc)
-			goto err_free_mem;
-
-		dma_addr = ib_dma_map_single(ibdev, req->indirect_desc,
-					     target->indirect_size,
-					     DMA_TO_DEVICE);
-		if (ib_dma_mapping_error(ibdev, dma_addr))
-			goto err_free_mem;
-
-		req->indirect_dma_addr = dma_addr;
-		req->index = i;
-		list_add_tail(&req->list, &target->free_reqs);
-	}
+	ret = srp_alloc_req_data(target);
+	if (ret)
+		goto err_free_mem;
 
 	ib_query_gid(ibdev, host->port, 0, &target->path.sgid);
 

287 lines not on this page · raw message

index 446b045..5756810 100644
@@ -57,14 +57,11 @@ enum {
 	SRP_MAX_LUN		= 512,
 	SRP_DEF_SG_TABLESIZE	= 12,
 
-	SRP_RQ_SHIFT    	= 6,
-	SRP_RQ_SIZE		= 1 << SRP_RQ_SHIFT,
-
-	SRP_SQ_SIZE		= SRP_RQ_SIZE,
+	SRP_DEFAULT_QUEUE_SIZE	= 1 << 6,
 	SRP_RSP_SQ_SIZE		= 1,
-	SRP_REQ_SQ_SIZE		= SRP_SQ_SIZE - SRP_RSP_SQ_SIZE,
 	SRP_TSK_MGMT_SQ_SIZE	= 1,
-	SRP_CMD_SQ_SIZE		= SRP_REQ_SQ_SIZE - SRP_TSK_MGMT_SQ_SIZE,
+	SRP_DEFAULT_CMD_SQ_SIZE = SRP_DEFAULT_QUEUE_SIZE - SRP_RSP_SQ_SIZE -
+				  SRP_TSK_MGMT_SQ_SIZE,
 
 	SRP_TAG_NO_REQ		= ~0U,
 	SRP_TAG_TSK_MGMT	= 1U << 31,

@@ -156,6 +153,8 @@ struct srp_target_port {
 	char			target_name[32];
 	unsigned int		scsi_id;
 	unsigned int		sg_tablesize;
+	int			queue_size;
+	int			req_ring_size;
 	int			comp_vector;
 	int			tl_retry_count;
 

@@ -173,9 +172,9 @@ struct srp_target_port {
 
 	int			zero_req_lim;
 
-	struct srp_iu	       *tx_ring[SRP_SQ_SIZE];
-	struct srp_iu	       *rx_ring[SRP_RQ_SIZE];
-	struct srp_request	req_ring[SRP_CMD_SQ_SIZE];
+	struct srp_iu	       **tx_ring;
+	struct srp_iu	       **rx_ring;
+	struct srp_request	*req_ring;
 
 	struct work_struct	tl_err_work;
 	struct work_struct	remove_work;

500 lines not on this page · raw message

96 lines not on this page · raw message

index ceb84b6..a120658 100644
@@ -145,9 +145,9 @@ static int srp_tmo_set(const char *val, const struct kernel_param *kp)
 		tmo = -1;
 	}
 	if (kp->arg == &srp_fast_io_fail_tmo)
-		res = srp_tmo_valid(tmo, srp_dev_loss_tmo);
+		res = srp_tmo_valid(-1, tmo, srp_dev_loss_tmo);
 	else
-		res = srp_tmo_valid(srp_fast_io_fail_tmo, tmo);
+		res = srp_tmo_valid(-1, srp_fast_io_fail_tmo, tmo);
 	if (res)
 		goto out;
 	*(int *)kp->arg = tmo;

183 lines not on this page · raw message

index ee70016..4ebf691 100644
@@ -31,7 +31,8 @@ enum srp_rport_state {
 /**
  * struct srp_rport
  * @lld_data: LLD private data.
- * @mutex:    Protects against concurrent rport fast_io_fail / dev_loss_tmo.
+ * @mutex:    Protects against concurrent rport reconnect / fast_io_fail /
+ *   dev_loss_tmo activity.
  */
 struct srp_rport {
 	/* for initiator and target drivers */

@@ -48,6 +49,9 @@ struct srp_rport {
 	struct mutex		mutex;
 	enum srp_rport_state	state;
 	bool			deleted;
+	int			reconnect_delay;
+	int			failed_reconnects;
+	struct delayed_work	reconnect_work;
 	int			fast_io_fail_tmo;
 	int			dev_loss_tmo;
 	struct delayed_work	fast_io_fail_work;

@@ -60,6 +64,7 @@ struct srp_rport {
  *     dev_loss_tmo sysfs attribute for an rport.
  * @reset_timer_if_blocked: Whether or srp_timed_out() should reset the command
  *     timer if the device on which it has been queued is blocked.
+ * @reconnect_delay: If not NULL, points to the default reconnect_delay value.
  * @fast_io_fail_tmo: If not NULL, points to the default fast_io_fail_tmo value.
  * @dev_loss_tmo: If not NULL, points to the default dev_loss_tmo value.
  * @reconnect: Callback function for reconnecting to the target. See also

@@ -71,6 +76,7 @@ struct srp_function_template {
 	/* for initiator drivers */
 	bool has_rport_state;
 	bool reset_timer_if_blocked;
+	int *reconnect_delay;
 	int *fast_io_fail_tmo;
 	int *dev_loss_tmo;
 	int (*reconnect)(struct srp_rport *rport);

@@ -90,7 +96,8 @@ extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);
-extern int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo);
+extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo,
+			 int dev_loss_tmo);
 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 *);