[RFC PATCH v2 6/7] nvme-tcp-offload: Add queue level implementation

Shai Malin smalin at marvell.com
Sun Dec 13 14:14:00 EST 2020


From: Dean Balandin <dbalandin at marvell.com>

In this patch we implement queue level functionality.
The implementation is similar to the nvme-tcp module, the main
difference being that we call the vendor specific create_queue op which
creates the TCP connection, and NVMeTPC connection including
icreq+icresp negotiation.
Once create_queue returns successfully, we can move on to the fabrics
connect.

Signed-off-by: Dean Balandin <dbalandin at marvell.com>
Signed-off-by: Shai Malin <smalin at marvell.com>
Signed-off-by: Ariel Elior <aelior at marvell.com>
Signed-off-by: Michal Kalderon <mkalderon at marvell.com>
---
 drivers/nvme/host/tcp-offload.c | 307 ++++++++++++++++++++++++++++++--
 drivers/nvme/host/tcp-offload.h |   6 +
 2 files changed, 294 insertions(+), 19 deletions(-)

diff --git a/drivers/nvme/host/tcp-offload.c b/drivers/nvme/host/tcp-offload.c
index d9da0fc5eb75..12f675bdd221 100644
--- a/drivers/nvme/host/tcp-offload.c
+++ b/drivers/nvme/host/tcp-offload.c
@@ -23,6 +23,11 @@ to_tcp_ofld_ctrl(struct nvme_ctrl *nctrl)
 	return container_of(nctrl, struct nvme_tcp_ofld_ctrl, nctrl);
 }
 
+static inline int nvme_tcp_ofld_qid(struct nvme_tcp_ofld_queue *queue)
+{
+	return queue - queue->ctrl->queues;
+}
+
 /**
  * nvme_tcp_ofld_register_dev() - NVMeTCP Offload Library registration
  * function.
@@ -190,18 +195,98 @@ nvme_tcp_ofld_alloc_tagset(struct nvme_ctrl *nctrl, bool admin)
 	return set;
 }
 
+static bool nvme_tcp_ofld_poll_queue(struct nvme_tcp_ofld_queue *queue)
+{
+	/* Placeholder - implement logic to determine if poll queue */
+
+	return false;
+}
+
+static void __nvme_tcp_ofld_stop_queue(struct nvme_tcp_ofld_queue *queue)
+{
+	queue->dev->ops->drain_queue(queue);
+	queue->dev->ops->destroy_queue(queue);
+
+	/* Placeholder - additional cleanup such as cancel_work_sync io_work */
+	clear_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags);
+}
+
+static void nvme_tcp_ofld_stop_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl);
+	struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid];
+
+	if (!test_and_clear_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags))
+		return;
+
+	__nvme_tcp_ofld_stop_queue(queue);
+}
+
+static void nvme_tcp_ofld_free_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl);
+	struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid];
+
+	if (!test_and_clear_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags))
+		return;
+
+	/* Placeholder - additional queue cleanup */
+}
+
+static void
+nvme_tcp_ofld_terminate_admin_queue(struct nvme_ctrl *nctrl, bool remove)
+{
+	nvme_tcp_ofld_stop_queue(nctrl, 0);
+	if (remove) {
+		if (nctrl->admin_q && !blk_queue_dead(nctrl->admin_q))
+			blk_cleanup_queue(nctrl->admin_q);
+
+		if (nctrl->fabrics_q)
+			blk_cleanup_queue(nctrl->fabrics_q);
+
+		if (nctrl->admin_tagset)
+			blk_mq_free_tag_set(nctrl->admin_tagset);
+	}
+}
+
 static int nvme_tcp_ofld_start_queue(struct nvme_ctrl *nctrl, int qid)
 {
-	/* Placeholder - start_queue */
-	return 0;
+	struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl);
+	struct nvme_tcp_ofld_queue *queue = &ctrl->queues[qid];
+	int rc;
+
+	set_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags);
+	queue = &ctrl->queues[qid];
+	if (qid)
+		rc = nvmf_connect_io_queue(nctrl, qid,
+					   nvme_tcp_ofld_poll_queue(queue));
+	else
+		rc = nvmf_connect_admin_queue(nctrl);
+
+	if (!rc) {
+		set_bit(NVME_TCP_OFLD_Q_LIVE, &queue->flags);
+	} else {
+		if (test_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags))
+			__nvme_tcp_ofld_stop_queue(queue);
+		dev_err(nctrl->device,
+			"failed to connect queue: %d ret=%d\n", qid, rc);
+	}
+
+	return rc;
 }
 
 static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl,
 					       bool new)
 {
+	struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl);
+	struct nvme_tcp_ofld_queue *queue = &ctrl->queues[0];
 	int rc;
 
-	/* Placeholder - alloc_admin_queue */
+	rc = ctrl->dev->ops->create_queue(queue, 0, NVME_AQ_DEPTH);
+	if (rc)
+		return rc;
+
+	set_bit(NVME_TCP_OFLD_Q_ALLOCATED, &queue->flags);
 	if (new) {
 		nctrl->admin_tagset =
 				nvme_tcp_ofld_alloc_tagset(nctrl, true);
@@ -243,7 +328,7 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl,
 	return 0;
 
 out_stop_queue:
-	/* Placeholder - stop admin queue */
+	nvme_tcp_ofld_stop_queue(nctrl, 0);
 out_cleanup_queue:
 	if (new)
 		blk_cleanup_queue(nctrl->admin_q);
@@ -254,7 +339,115 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl,
 	if (new)
 		blk_mq_free_tag_set(nctrl->admin_tagset);
 out_free_queue:
-	/* Placeholder - free admin queue */
+	nvme_tcp_ofld_free_queue(nctrl, 0);
+
+	return rc;
+}
+
+static unsigned int nvme_tcp_ofld_nr_io_queues(struct nvme_ctrl *nctrl)
+{
+	unsigned int nr_io_queues;
+
+	nr_io_queues = min(nctrl->opts->nr_io_queues, num_online_cpus());
+	nr_io_queues += min(nctrl->opts->nr_write_queues, num_online_cpus());
+	nr_io_queues += min(nctrl->opts->nr_poll_queues, num_online_cpus());
+
+	return nr_io_queues;
+}
+
+static void
+nvme_tcp_ofld_set_io_queues(struct nvme_ctrl *nctrl, unsigned int nr_io_queues)
+{
+	struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl);
+	struct nvmf_ctrl_options *opts = nctrl->opts;
+
+	if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) {
+		/*
+		 * separate read/write queues
+		 * hand out dedicated default queues only after we have
+		 * sufficient read queues.
+		 */
+		ctrl->queue_type_mapping[HCTX_TYPE_READ] = opts->nr_io_queues;
+		nr_io_queues -= ctrl->queue_type_mapping[HCTX_TYPE_READ];
+		ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT] =
+			min(opts->nr_write_queues, nr_io_queues);
+		nr_io_queues -= ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT];
+	} else {
+		/*
+		 * shared read/write queues
+		 * either no write queues were requested, or we don't have
+		 * sufficient queue count to have dedicated default queues.
+		 */
+		ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT] =
+			min(opts->nr_io_queues, nr_io_queues);
+		nr_io_queues -= ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT];
+	}
+}
+
+static void
+nvme_tcp_ofld_terminate_io_queues(struct nvme_ctrl *nctrl, int start_from)
+{
+	int i;
+
+	/* admin-q will be ignored because of the loop condition */
+	for (i = start_from; i >= 1; i--)
+		nvme_tcp_ofld_stop_queue(nctrl, i);
+}
+
+static int nvme_tcp_ofld_create_io_queues(struct nvme_ctrl *nctrl)
+{
+	struct nvme_tcp_ofld_ctrl *ctrl = to_tcp_ofld_ctrl(nctrl);
+	int i, rc;
+
+	for (i = 1; i < nctrl->queue_count; i++) {
+		rc = ctrl->dev->ops->create_queue(&ctrl->queues[i],
+						  i, nctrl->sqsize + 1);
+		if (rc)
+			goto out_free_queues;
+	}
+
+	return 0;
+
+out_free_queues:
+	nvme_tcp_ofld_terminate_io_queues(nctrl, --i);
+
+	return rc;
+}
+
+static int nvme_tcp_ofld_alloc_io_queues(struct nvme_ctrl *nctrl)
+{
+	unsigned int nr_io_queues;
+	int rc;
+
+	nr_io_queues = nvme_tcp_ofld_nr_io_queues(nctrl);
+	rc = nvme_set_queue_count(nctrl, &nr_io_queues);
+	if (rc)
+		return rc;
+
+	nctrl->queue_count = nr_io_queues + 1;
+	if (nctrl->queue_count < 2)
+		return 0;
+
+	dev_info(nctrl->device, "creating %d I/O queues.\n", nr_io_queues);
+	nvme_tcp_ofld_set_io_queues(nctrl, nr_io_queues);
+
+	return nvme_tcp_ofld_create_io_queues(nctrl);
+}
+
+static int nvme_tcp_ofld_start_io_queues(struct nvme_ctrl *nctrl)
+{
+	int i, rc = 0;
+
+	for (i = 1; i < nctrl->queue_count; i++) {
+		rc = nvme_tcp_ofld_start_queue(nctrl, i);
+		if (rc)
+			goto terminate_queues;
+	}
+
+	return 0;
+
+terminate_queues:
+	nvme_tcp_ofld_terminate_io_queues(nctrl, --i);
 
 	return rc;
 }
@@ -262,9 +455,10 @@ static int nvme_tcp_ofld_configure_admin_queue(struct nvme_ctrl *nctrl,
 static int
 nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new)
 {
-	int rc;
+	int rc = nvme_tcp_ofld_alloc_io_queues(nctrl);
 
-	/* Placeholder - alloc_io_queues */
+	if (rc)
+		return rc;
 
 	if (new) {
 		nctrl->tagset = nvme_tcp_ofld_alloc_tagset(nctrl, false);
@@ -282,7 +476,9 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new)
 		}
 	}
 
-	/* Placeholder - start_io_queues */
+	rc = nvme_tcp_ofld_start_io_queues(nctrl);
+	if (rc)
+		goto out_cleanup_connect_q;
 
 	if (!new) {
 		nvme_start_queues(nctrl);
@@ -294,11 +490,14 @@ nvme_tcp_ofld_configure_io_queues(struct nvme_ctrl *nctrl, bool new)
 
 	return 0;
 
+out_cleanup_connect_q:
+	if (new && nctrl->connect_q)
+		blk_cleanup_queue(nctrl->connect_q);
 out_free_tag_set:
 	if (new)
 		blk_mq_free_tag_set(nctrl->tagset);
 out_free_io_queues:
-	/* Placeholder - free_io_queues */
+	nvme_tcp_ofld_terminate_io_queues(nctrl, nctrl->queue_count);
 
 	return rc;
 }
@@ -374,9 +573,9 @@ static int nvme_tcp_ofld_setup_ctrl(struct nvme_ctrl *nctrl, bool new)
 	return 0;
 
 destroy_io:
-	/* Placeholder - stop and destroy io queues*/
+	nvme_tcp_ofld_terminate_io_queues(nctrl, nctrl->queue_count);
 destroy_admin:
-	/* Placeholder - stop and destroy admin queue*/
+	nvme_tcp_ofld_terminate_admin_queue(nctrl, new);
 
 	return rc;
 }
@@ -559,22 +758,92 @@ nvme_tcp_ofld_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
+static void
+nvme_tcp_ofld_exit_request(struct blk_mq_tag_set *set,
+			   struct request *rq, unsigned int hctx_idx)
+{
+	/* Placeholder */
+}
+
+static int
+nvme_tcp_ofld_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
+			unsigned int hctx_idx)
+{
+	struct nvme_tcp_ofld_ctrl *ctrl = data;
+	struct nvme_tcp_ofld_queue *queue = &ctrl->queues[hctx_idx + 1];
+
+	hctx->driver_data = queue;
+	return 0;
+}
+
+static int nvme_tcp_ofld_map_queues(struct blk_mq_tag_set *set)
+{
+	struct nvme_tcp_ofld_ctrl *ctrl = set->driver_data;
+	struct nvmf_ctrl_options *opts = ctrl->nctrl.opts;
+
+	if (opts->nr_write_queues && ctrl->queue_type_mapping[HCTX_TYPE_READ]) {
+		/* separate read/write queues */
+		set->map[HCTX_TYPE_DEFAULT].nr_queues =
+			ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+		set->map[HCTX_TYPE_READ].nr_queues =
+			ctrl->queue_type_mapping[HCTX_TYPE_READ];
+		set->map[HCTX_TYPE_READ].queue_offset =
+			ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT];
+	} else {
+		/* shared read/write queues */
+		set->map[HCTX_TYPE_DEFAULT].nr_queues =
+			ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_DEFAULT].queue_offset = 0;
+		set->map[HCTX_TYPE_READ].nr_queues =
+			ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT];
+		set->map[HCTX_TYPE_READ].queue_offset = 0;
+	}
+	blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
+	blk_mq_map_queues(&set->map[HCTX_TYPE_READ]);
+
+	if (opts->nr_poll_queues && ctrl->queue_type_mapping[HCTX_TYPE_POLL]) {
+		/* map dedicated poll queues only if we have queues left */
+		set->map[HCTX_TYPE_POLL].nr_queues =
+				ctrl->queue_type_mapping[HCTX_TYPE_POLL];
+		set->map[HCTX_TYPE_POLL].queue_offset =
+			ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT] +
+			ctrl->queue_type_mapping[HCTX_TYPE_READ];
+		blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]);
+	}
+
+	dev_info(ctrl->nctrl.device,
+		 "mapped %d/%d/%d default/read/poll queues.\n",
+		 ctrl->queue_type_mapping[HCTX_TYPE_DEFAULT],
+		 ctrl->queue_type_mapping[HCTX_TYPE_READ],
+		 ctrl->queue_type_mapping[HCTX_TYPE_POLL]);
+
+	return 0;
+}
+
+static int nvme_tcp_ofld_poll(struct blk_mq_hw_ctx *hctx)
+{
+	/* Placeholder - Implement polling mechanism */
+
+	return 0;
+}
+
 static struct blk_mq_ops nvme_tcp_ofld_mq_ops = {
 	.queue_rq	= nvme_tcp_ofld_queue_rq,
 	.init_request	= nvme_tcp_ofld_init_request,
-	/*
-	 * All additional ops will be also implemented and registered similar to
-	 * tcp.c
-	 */
+	.complete	= nvme_complete_rq,
+	.exit_request	= nvme_tcp_ofld_exit_request,
+	.init_hctx	= nvme_tcp_ofld_init_hctx,
+	.map_queues	= nvme_tcp_ofld_map_queues,
+	.poll		= nvme_tcp_ofld_poll,
 };
 
 static struct blk_mq_ops nvme_tcp_ofld_admin_mq_ops = {
 	.queue_rq	= nvme_tcp_ofld_queue_rq,
 	.init_request	= nvme_tcp_ofld_init_request,
-	/*
-	 * All additional ops will be also implemented and registered similar to
-	 * tcp.c
-	 */
+	.complete	= nvme_complete_rq,
+	.exit_request	= nvme_tcp_ofld_exit_request,
+	.init_hctx	= nvme_tcp_ofld_init_hctx,
 };
 
 static const struct nvme_ctrl_ops nvme_tcp_ofld_ctrl_ops = {
diff --git a/drivers/nvme/host/tcp-offload.h b/drivers/nvme/host/tcp-offload.h
index c3f74f700c6a..02a2592d4dca 100644
--- a/drivers/nvme/host/tcp-offload.h
+++ b/drivers/nvme/host/tcp-offload.h
@@ -42,11 +42,17 @@ struct nvme_tcp_ofld_req {
 		     __le16 status);
 };
 
+enum nvme_tcp_ofld_queue_flags {
+	NVME_TCP_OFLD_Q_ALLOCATED = 0,
+	NVME_TCP_OFLD_Q_LIVE = 1,
+};
+
 /* Allocated by nvme_tcp_ofld */
 struct nvme_tcp_ofld_queue {
 	/* Offload device associated to this queue */
 	struct nvme_tcp_ofld_dev *dev;
 	struct nvme_tcp_ofld_ctrl *ctrl;
+	unsigned long flags;
 
 	/* Vendor specific driver context */
 	void *private_data;
-- 
2.22.0




More information about the Linux-nvme mailing list