Merge tag 'v4.18' into rdma.git for-next

Resolve merge conflicts from the -rc cycle against the rdma.git tree:

Conflicts:
 drivers/infiniband/core/uverbs_cmd.c
  - New ifs added to ib_uverbs_ex_create_flow in -rc and for-next
  - Merge removal of file->ucontext in for-next with new code in -rc
 drivers/infiniband/core/uverbs_main.c
  - for-next removed code from ib_uverbs_write() that was modified
    in for-rc

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

11 files changed, 183 insertions, 94 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 21710a7460c8..bf65501e6ed6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -100,6 +100,22 @@ static struct class *nvme_subsys_class;
 static void nvme_ns_remove(struct nvme_ns *ns);
 static int nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
+static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
+					   unsigned nsid);
+
+static void nvme_set_queue_dying(struct nvme_ns *ns)
+{
+	/*
+	 * Revalidating a dead namespace sets capacity to 0. This will end
+	 * buffered writers dirtying pages that can't be synced.
+	 */
+	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+		return;
+	revalidate_disk(ns->disk);
+	blk_set_queue_dying(ns->queue);
+	/* Forcibly unquiesce queues to avoid blocking dispatch */
+	blk_mq_unquiesce_queue(ns->queue);
+}
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
 {
@@ -1044,14 +1060,17 @@ EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
-	u32 result;
+	u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
 	int status;
 
-	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
-			ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+	if (!supported_aens)
+		return;
+
+	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens,
+			NULL, 0, &result);
 	if (status)
 		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
-			 ctrl->oaes & NVME_AEN_SUPPORTED);
+			 supported_aens);
 }
 
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
@@ -1151,19 +1170,15 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 static void nvme_update_formats(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns, *next;
-	LIST_HEAD(rm_list);
+	struct nvme_ns *ns;
 
-	down_write(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		if (ns->disk && nvme_revalidate_disk(ns->disk)) {
-			list_move_tail(&ns->list, &rm_list);
-		}
-	}
-	up_write(&ctrl->namespaces_rwsem);
+	down_read(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		if (ns->disk && nvme_revalidate_disk(ns->disk))
+			nvme_set_queue_dying(ns);
+	up_read(&ctrl->namespaces_rwsem);
 
-	list_for_each_entry_safe(ns, next, &rm_list, list)
-		nvme_ns_remove(ns);
+	nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
 }
 
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -1218,7 +1233,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata,
+			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
 			0, &cmd.result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
@@ -1808,6 +1823,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 		u32 max_segments =
 			(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
 
+		max_segments = min_not_zero(max_segments, ctrl->max_segments);
 		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
 		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
 	}
@@ -3137,7 +3153,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 
 	down_write(&ctrl->namespaces_rwsem);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->head->ns_id > nsid)
+		if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags))
 			list_move_tail(&ns->list, &rm_list);
 	}
 	up_write(&ctrl->namespaces_rwsem);
@@ -3541,19 +3557,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 	if (ctrl->admin_q)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		/*
-		 * Revalidating a dead namespace sets capacity to 0. This will
-		 * end buffered writers dirtying pages that can't be synced.
-		 */
-		if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
-			continue;
-		revalidate_disk(ns->disk);
-		blk_set_queue_dying(ns->queue);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		nvme_set_queue_dying(ns);
 
-		/* Forcibly unquiesce queues to avoid blocking dispatch */
-		blk_mq_unquiesce_queue(ns->queue);
-	}
 	up_read(&ctrl->namespaces_rwsem);
 }
 EXPORT_SYMBOL_GPL(nvme_kill_queues);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 903eb4545e26..f7efe5a58cc7 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -539,14 +539,18 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 /*
  * For something we're not in a state to send to the device the default action
  * is to busy it and retry it after the controller state is recovered.  However,
- * anything marked for failfast or nvme multipath is immediately failed.
+ * if the controller is deleting or if anything is marked for failfast or
+ * nvme multipath it is immediately failed.
  *
  * Note: commands used to initialize the controller will be marked for failfast.
  * Note: nvme cli/ioctl commands are marked for failfast.
  */
-blk_status_t nvmf_fail_nonready_command(struct request *rq)
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq)
 {
-	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+	if (ctrl->state != NVME_CTRL_DELETING &&
+	    ctrl->state != NVME_CTRL_DEAD &&
+	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
 	return BLK_STS_IOERR;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index e1818a27aa2d..aa2fdb2a2e8f 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -162,7 +162,8 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-blk_status_t nvmf_fail_nonready_command(struct request *rq);
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq);
 bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live);
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index b528a2f5826c..9bac912173ba 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2272,7 +2272,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE ||
 	    !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(rq);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	ret = nvme_setup_cmd(ns, rq, sqe);
 	if (ret)
@@ -2790,6 +2790,9 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
 	/* re-enable the admin_q so anything new can fast fail */
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 
+	/* resume the io queues so that things will fast fail */
+	nvme_start_queues(&ctrl->ctrl);
+
 	nvme_fc_ctlr_inactive_on_rport(ctrl);
 }
 
@@ -2804,9 +2807,6 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl)
 	 * waiting for io to terminate
 	 */
 	nvme_fc_delete_association(ctrl);
-
-	/* resume the io queues so that things will fast fail */
-	nvme_start_queues(nctrl);
 }
 
 static void
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 231807cbc849..0c4a33df3b2f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -170,6 +170,7 @@ struct nvme_ctrl {
 	u64 cap;
 	u32 page_size;
 	u32 max_hw_sectors;
+	u32 max_segments;
 	u16 oncs;
 	u16 oacs;
 	u16 nssa;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index fc33804662e7..ddd441b1516a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -38,6 +38,13 @@
 
 #define SGES_PER_PAGE	(PAGE_SIZE / sizeof(struct nvme_sgl_desc))
 
+/*
+ * These can be higher, but we need to ensure that any command doesn't
+ * require an sg allocation that needs more than a page of data.
+ */
+#define NVME_MAX_KB_SZ	4096
+#define NVME_MAX_SEGS	127
+
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0);
 
@@ -100,6 +107,8 @@ struct nvme_dev {
 	struct nvme_ctrl ctrl;
 	struct completion ioq_wait;
 
+	mempool_t *iod_mempool;
+
 	/* shadow doorbell buffer support: */
 	u32 *dbbuf_dbs;
 	dma_addr_t dbbuf_dbs_dma_addr;
@@ -477,10 +486,7 @@ static blk_status_t nvme_init_iod(struct request *rq, struct nvme_dev *dev)
 	iod->use_sgl = nvme_pci_use_sgls(dev, rq);
 
 	if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
-		size_t alloc_size = nvme_pci_iod_alloc_size(dev, size, nseg,
-				iod->use_sgl);
-
-		iod->sg = kmalloc(alloc_size, GFP_ATOMIC);
+		iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
 		if (!iod->sg)
 			return BLK_STS_RESOURCE;
 	} else {
@@ -526,7 +532,7 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
 	}
 
 	if (iod->sg != iod->inline_sg)
-		kfree(iod->sg);
+		mempool_free(iod->sg, dev->iod_mempool);
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
@@ -2280,6 +2286,7 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
 	free_opal_dev(dev->ctrl.opal_dev);
+	mempool_destroy(dev->iod_mempool);
 	kfree(dev);
 }
 
@@ -2289,6 +2296,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
 
 	nvme_get_ctrl(&dev->ctrl);
 	nvme_dev_disable(dev, false);
+	nvme_kill_queues(&dev->ctrl);
 	if (!queue_work(nvme_wq, &dev->remove_work))
 		nvme_put_ctrl(&dev->ctrl);
 }
@@ -2333,6 +2341,13 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
+	/*
+	 * Limit the max command size to prevent iod->sg allocations going
+	 * over a single page.
+	 */
+	dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
+	dev->ctrl.max_segments = NVME_MAX_SEGS;
+
 	result = nvme_init_identify(&dev->ctrl);
 	if (result)
 		goto out;
@@ -2405,7 +2420,6 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work)
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
-	nvme_kill_queues(&dev->ctrl);
 	if (pci_get_drvdata(pdev))
 		device_release_driver(&pdev->dev);
 	nvme_put_ctrl(&dev->ctrl);
@@ -2509,6 +2523,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	int node, result = -ENOMEM;
 	struct nvme_dev *dev;
 	unsigned long quirks = id->driver_data;
+	size_t alloc_size;
 
 	node = dev_to_node(&pdev->dev);
 	if (node == NUMA_NO_NODE)
@@ -2541,10 +2556,27 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	quirks |= check_vendor_combination_bug(pdev);
 
+	/*
+	 * Double check that our mempool alloc size will cover the biggest
+	 * command we support.
+	 */
+	alloc_size = nvme_pci_iod_alloc_size(dev, NVME_MAX_KB_SZ,
+						NVME_MAX_SEGS, true);
+	WARN_ON_ONCE(alloc_size > PAGE_SIZE);
+
+	dev->iod_mempool = mempool_create_node(1, mempool_kmalloc,
+						mempool_kfree,
+						(void *) alloc_size,
+						GFP_KERNEL, node);
+	if (!dev->iod_mempool) {
+		result = -ENOMEM;
+		goto release_pools;
+	}
+
 	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
 			quirks);
 	if (result)
-		goto release_pools;
+		goto release_mempool;
 
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
@@ -2553,6 +2585,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+ release_mempool:
+	mempool_destroy(dev->iod_mempool);
  release_pools:
 	nvme_release_prp_pools(dev);
  unmap:
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index a7fe5479732d..72e8e8e7d2d7 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -560,12 +560,6 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
 	if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &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);
 }
@@ -698,7 +692,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
 		set = &ctrl->tag_set;
 		memset(set, 0, sizeof(*set));
 		set->ops = &nvme_rdma_mq_ops;
-		set->queue_depth = nctrl->opts->queue_size;
+		set->queue_depth = nctrl->sqsize + 1;
 		set->reserved_tags = 1; /* fabric connect */
 		set->numa_node = NUMA_NO_NODE;
 		set->flags = BLK_MQ_F_SHOULD_MERGE;
@@ -734,11 +728,15 @@ out:
 static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (remove) {
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
 		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
 	}
+	if (ctrl->async_event_sqe.data) {
+		nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+				sizeof(struct nvme_command), DMA_TO_DEVICE);
+		ctrl->async_event_sqe.data = NULL;
+	}
 	nvme_rdma_free_queue(&ctrl->queues[0]);
 }
 
@@ -755,11 +753,16 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 
 	ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev);
 
+	error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+	if (error)
+		goto out_free_queue;
+
 	if (new) {
 		ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
 		if (IS_ERR(ctrl->ctrl.admin_tagset)) {
 			error = PTR_ERR(ctrl->ctrl.admin_tagset);
-			goto out_free_queue;
+			goto out_free_async_qe;
 		}
 
 		ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
@@ -795,12 +798,6 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (error)
 		goto out_stop_queue;
 
-	error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
-			&ctrl->async_event_sqe, sizeof(struct nvme_command),
-			DMA_TO_DEVICE);
-	if (error)
-		goto out_stop_queue;
-
 	return 0;
 
 out_stop_queue:
@@ -811,6 +808,9 @@ out_cleanup_queue:
 out_free_tagset:
 	if (new)
 		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
+out_free_async_qe:
+	nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+		sizeof(struct nvme_command), DMA_TO_DEVICE);
 out_free_queue:
 	nvme_rdma_free_queue(&ctrl->queues[0]);
 	return error;
@@ -819,7 +819,6 @@ out_free_queue:
 static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	nvme_rdma_stop_io_queues(ctrl);
 	if (remove) {
 		blk_cleanup_queue(ctrl->ctrl.connect_q);
 		nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
@@ -888,9 +887,9 @@ static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
 	list_del(&ctrl->list);
 	mutex_unlock(&nvme_rdma_ctrl_mutex);
 
-	kfree(ctrl->queues);
 	nvmf_free_options(nctrl->opts);
 free_ctrl:
+	kfree(ctrl->queues);
 	kfree(ctrl);
 }
 
@@ -949,6 +948,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	return;
 
 destroy_admin:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	nvme_rdma_destroy_admin_queue(ctrl, false);
 requeue:
 	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
@@ -965,12 +965,14 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_stop_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
 		blk_mq_tagset_busy_iter(&ctrl->tag_set,
 					nvme_cancel_request, &ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, false);
 	}
 
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
 	nvme_rdma_destroy_admin_queue(ctrl, false);
@@ -1636,7 +1638,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	WARN_ON_ONCE(rq->tag < 0);
 
 	if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(rq);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	dev = queue->device->dev;
 	ib_dma_sync_single_for_cpu(dev, sqe->dma,
@@ -1735,6 +1737,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
 {
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_stop_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
 		blk_mq_tagset_busy_iter(&ctrl->tag_set,
 					nvme_cancel_request, &ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, shutdown);
@@ -1746,6 +1749,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
 		nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
 
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
@@ -1931,11 +1935,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		goto out_free_ctrl;
 	}
 
-	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
-				0 /* no quirks, we're perfect! */);
-	if (ret)
-		goto out_free_ctrl;
-
 	INIT_DELAYED_WORK(&ctrl->reconnect_work,
 			nvme_rdma_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
@@ -1949,14 +1948,19 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues),
 				GFP_KERNEL);
 	if (!ctrl->queues)
-		goto out_uninit_ctrl;
+		goto out_free_ctrl;
+
+	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
+				0 /* no quirks, we're perfect! */);
+	if (ret)
+		goto out_kfree_queues;
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
 	WARN_ON_ONCE(!changed);
 
 	ret = nvme_rdma_configure_admin_queue(ctrl, true);
 	if (ret)
-		goto out_kfree_queues;
+		goto out_uninit_ctrl;
 
 	/* sanity check icdoff */
 	if (ctrl->ctrl.icdoff) {
@@ -1973,20 +1977,19 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		goto out_remove_admin_queue;
 	}
 
-	if (opts->queue_size > ctrl->ctrl.maxcmd) {
-		/* warn if maxcmd is lower than queue_size */
-		dev_warn(ctrl->ctrl.device,
-			"queue_size %zu > ctrl maxcmd %u, clamping down\n",
-			opts->queue_size, ctrl->ctrl.maxcmd);
-		opts->queue_size = ctrl->ctrl.maxcmd;
-	}
-
+	/* only warn if argument is too large here, will clamp later */
 	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
-		/* warn if sqsize is lower than queue_size */
 		dev_warn(ctrl->ctrl.device,
 			"queue_size %zu > ctrl sqsize %u, clamping down\n",
 			opts->queue_size, ctrl->ctrl.sqsize + 1);
-		opts->queue_size = ctrl->ctrl.sqsize + 1;
+	}
+
+	/* warn if maxcmd is lower than sqsize+1 */
+	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+		dev_warn(ctrl->ctrl.device,
+			"sqsize %u > ctrl maxcmd %u, clamping down\n",
+			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
 	}
 
 	if (opts->nr_io_queues) {
@@ -2012,15 +2015,16 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	return &ctrl->ctrl;
 
 out_remove_admin_queue:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	nvme_rdma_destroy_admin_queue(ctrl, true);
-out_kfree_queues:
-	kfree(ctrl->queues);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);
+out_kfree_queues:
+	kfree(ctrl->queues);
 out_free_ctrl:
 	kfree(ctrl);
 	return ERR_PTR(ret);
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index d3f3b3ec4d1a..ebea1373d1b7 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -282,6 +282,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 {
 	struct nvmet_ns *ns = to_nvmet_ns(item);
 	struct nvmet_subsys *subsys = ns->subsys;
+	size_t len;
 	int ret;
 
 	mutex_lock(&subsys->lock);
@@ -289,10 +290,14 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 	if (ns->enabled)
 		goto out_unlock;
 
-	kfree(ns->device_path);
+	ret = -EINVAL;
+	len = strcspn(page, "\n");
+	if (!len)
+		goto out_unlock;
 
+	kfree(ns->device_path);
 	ret = -ENOMEM;
-	ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL);
+	ns->device_path = kstrndup(page, len, GFP_KERNEL);
 	if (!ns->device_path)
 		goto out_unlock;
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index a03da764ecae..9838103f2d62 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -339,7 +339,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 		goto out_unlock;
 
 	ret = nvmet_bdev_ns_enable(ns);
-	if (ret)
+	if (ret == -ENOTBLK)
 		ret = nvmet_file_ns_enable(ns);
 	if (ret)
 		goto out_unlock;
@@ -686,6 +686,14 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
 	}
 
 	ctrl->csts = NVME_CSTS_RDY;
+
+	/*
+	 * Controllers that are not yet enabled should not really enforce the
+	 * keep alive timeout, but we still want to track a timeout and cleanup
+	 * in case a host died before it enabled the controller.  Hence, simply
+	 * reset the keep alive timer when the controller is enabled.
+	 */
+	mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 408279cb6f2c..29b4b236afd8 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -58,8 +58,8 @@ struct nvmet_fc_ls_iod {
 	struct work_struct		work;
 } __aligned(sizeof(unsigned long long));
 
+/* desired maximum for a single sequence - if sg list allows it */
 #define NVMET_FC_MAX_SEQ_LENGTH		(256 * 1024)
-#define NVMET_FC_MAX_XFR_SGENTS		(NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE)
 
 enum nvmet_fcp_datadir {
 	NVMET_FCP_NODATA,
@@ -74,6 +74,7 @@ struct nvmet_fc_fcp_iod {
 	struct nvme_fc_cmd_iu		cmdiubuf;
 	struct nvme_fc_ersp_iu		rspiubuf;
 	dma_addr_t			rspdma;
+	struct scatterlist		*next_sg;
 	struct scatterlist		*data_sg;
 	int				data_sg_cnt;
 	u32				offset;
@@ -1025,8 +1026,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 	INIT_LIST_HEAD(&newrec->assoc_list);
 	kref_init(&newrec->ref);
 	ida_init(&newrec->assoc_cnt);
-	newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS,
-					template->max_sgl_segments);
+	newrec->max_sg_cnt = template->max_sgl_segments;
 
 	ret = nvmet_fc_alloc_ls_iodlist(newrec);
 	if (ret) {
@@ -1722,6 +1722,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod)
 				((fod->io_dir == NVMET_FCP_WRITE) ?
 					DMA_FROM_DEVICE : DMA_TO_DEVICE));
 				/* note: write from initiator perspective */
+	fod->next_sg = fod->data_sg;
 
 	return 0;
 
@@ -1866,24 +1867,49 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 				struct nvmet_fc_fcp_iod *fod, u8 op)
 {
 	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+	struct scatterlist *sg = fod->next_sg;
 	unsigned long flags;
-	u32 tlen;
+	u32 remaininglen = fod->req.transfer_len - fod->offset;
+	u32 tlen = 0;
 	int ret;
 
 	fcpreq->op = op;
 	fcpreq->offset = fod->offset;
 	fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC;
 
-	tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE,
-			(fod->req.transfer_len - fod->offset));
+	/*
+	 * for next sequence:
+	 *  break at a sg element boundary
+	 *  attempt to keep sequence length capped at
+	 *    NVMET_FC_MAX_SEQ_LENGTH but allow sequence to
+	 *    be longer if a single sg element is larger
+	 *    than that amount. This is done to avoid creating
+	 *    a new sg list to use for the tgtport api.
+	 */
+	fcpreq->sg = sg;
+	fcpreq->sg_cnt = 0;
+	while (tlen < remaininglen &&
+	       fcpreq->sg_cnt < tgtport->max_sg_cnt &&
+	       tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) {
+		fcpreq->sg_cnt++;
+		tlen += sg_dma_len(sg);
+		sg = sg_next(sg);
+	}
+	if (tlen < remaininglen && fcpreq->sg_cnt == 0) {
+		fcpreq->sg_cnt++;
+		tlen += min_t(u32, sg_dma_len(sg), remaininglen);
+		sg = sg_next(sg);
+	}
+	if (tlen < remaininglen)
+		fod->next_sg = sg;
+	else
+		fod->next_sg = NULL;
+
 	fcpreq->transfer_length = tlen;
 	fcpreq->transferred_length = 0;
 	fcpreq->fcp_error = 0;
 	fcpreq->rsplen = 0;
 
-	fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE];
-	fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE);
-
 	/*
 	 * If the last READDATA request: check if LLDD supports
 	 * combined xfr with response.
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index d8d91f04bd7e..ae7586b8be07 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -162,7 +162,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_status_t ret;
 
 	if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready))
-		return nvmf_fail_nonready_command(req);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req);
 
 	ret = nvme_setup_cmd(ns, req, &iod->cmd);
 	if (ret)