4 files changed, 58 insertions, 12 deletions

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index af075e998944..be49d0f79381 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2545,10 +2545,10 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
 	nvme_fc_abort_aen_ops(ctrl);
 
 	/* wait for all io that had to be aborted */
-	spin_lock_irqsave(&ctrl->lock, flags);
+	spin_lock_irq(&ctrl->lock);
 	wait_event_lock_irq(ctrl->ioabort_wait, ctrl->iocnt == 0, ctrl->lock);
 	ctrl->flags &= ~FCCTRL_TERMIO;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
+	spin_unlock_irq(&ctrl->lock);
 
 	nvme_fc_term_aen_ops(ctrl);
 
@@ -2734,7 +2734,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 {
 	struct nvme_fc_ctrl *ctrl;
 	unsigned long flags;
-	int ret, idx;
+	int ret, idx, retry;
 
 	if (!(rport->remoteport.port_role &
 	    (FC_PORT_ROLE_NVME_DISCOVERY | FC_PORT_ROLE_NVME_TARGET))) {
@@ -2760,6 +2760,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	ctrl->rport = rport;
 	ctrl->dev = lport->dev;
 	ctrl->cnum = idx;
+	init_waitqueue_head(&ctrl->ioabort_wait);
 
 	get_device(ctrl->dev);
 	kref_init(&ctrl->ref);
@@ -2825,9 +2826,37 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
 	spin_unlock_irqrestore(&rport->lock, flags);
 
-	ret = nvme_fc_create_association(ctrl);
+	/*
+	 * It's possible that transactions used to create the association
+	 * may fail. Examples: CreateAssociation LS or CreateIOConnection
+	 * LS gets dropped/corrupted/fails; or a frame gets dropped or a
+	 * command times out for one of the actions to init the controller
+	 * (Connect, Get/Set_Property, Set_Features, etc). Many of these
+	 * transport errors (frame drop, LS failure) inherently must kill
+	 * the association. The transport is coded so that any command used
+	 * to create the association (prior to a LIVE state transition
+	 * while NEW or RECONNECTING) will fail if it completes in error or
+	 * times out.
+	 *
+	 * As such: as the connect request was mostly likely due to a
+	 * udev event that discovered the remote port, meaning there is
+	 * not an admin or script there to restart if the connect
+	 * request fails, retry the initial connection creation up to
+	 * three times before giving up and declaring failure.
+	 */
+	for (retry = 0; retry < 3; retry++) {
+		ret = nvme_fc_create_association(ctrl);
+		if (!ret)
+			break;
+	}
+
 	if (ret) {
+		/* couldn't schedule retry - fail out */
+		dev_err(ctrl->ctrl.device,
+			"NVME-FC{%d}: Connect retry failed\n", ctrl->cnum);
+
 		ctrl->ctrl.opts = NULL;
+
 		/* initiate nvme ctrl ref counting teardown */
 		nvme_uninit_ctrl(&ctrl->ctrl);
 		nvme_put_ctrl(&ctrl->ctrl);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 92a03ff5fb4d..87bac27ec64b 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -571,6 +571,12 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
 	if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags))
 		return;
 
+	if (nvme_rdma_queue_idx(queue) == 0) {
+		nvme_rdma_free_qe(queue->device->dev,
+			&queue->ctrl->async_event_sqe,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+	}
+
 	nvme_rdma_destroy_queue_ib(queue);
 	rdma_destroy_id(queue->cm_id);
 }
@@ -739,8 +745,6 @@ out:
 static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe,
-			sizeof(struct nvme_command), DMA_TO_DEVICE);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (remove) {
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
@@ -765,8 +769,10 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 
 	if (new) {
 		ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
-		if (IS_ERR(ctrl->ctrl.admin_tagset))
+		if (IS_ERR(ctrl->ctrl.admin_tagset)) {
+			error = PTR_ERR(ctrl->ctrl.admin_tagset);
 			goto out_free_queue;
+		}
 
 		ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
 		if (IS_ERR(ctrl->ctrl.admin_q)) {
@@ -846,8 +852,10 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
 	if (new) {
 		ctrl->ctrl.tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, false);
-		if (IS_ERR(ctrl->ctrl.tagset))
+		if (IS_ERR(ctrl->ctrl.tagset)) {
+			ret = PTR_ERR(ctrl->ctrl.tagset);
 			goto out_free_io_queues;
+		}
 
 		ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
 		if (IS_ERR(ctrl->ctrl.connect_q)) {
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 1b208beeef50..645ba7eee35d 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -387,12 +387,21 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 
 static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
 {
+	u32 old_sqhd, new_sqhd;
+	u16 sqhd;
+
 	if (status)
 		nvmet_set_status(req, status);
 
-	if (req->sq->size)
-		req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size;
-	req->rsp->sq_head = cpu_to_le16(req->sq->sqhd);
+	if (req->sq->size) {
+		do {
+			old_sqhd = req->sq->sqhd;
+			new_sqhd = (old_sqhd + 1) % req->sq->size;
+		} while (cmpxchg(&req->sq->sqhd, old_sqhd, new_sqhd) !=
+					old_sqhd);
+	}
+	sqhd = req->sq->sqhd & 0x0000FFFF;
+	req->rsp->sq_head = cpu_to_le16(sqhd);
 	req->rsp->sq_id = cpu_to_le16(req->sq->qid);
 	req->rsp->command_id = req->cmd->common.command_id;
 
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 7b8e20adf760..87e429bfcd8a 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -74,7 +74,7 @@ struct nvmet_sq {
 	struct percpu_ref	ref;
 	u16			qid;
 	u16			size;
-	u16			sqhd;
+	u32			sqhd;
 	struct completion	free_done;
 	struct completion	confirm_done;
 };