Signed-off-by: Sagi Grimberg <s...@grimberg.me>
---
drivers/nvme/host/rdma.c | 148 ++++++++++++++++++++++++++---------------------
1 file changed, 83 insertions(+), 65 deletions(-)
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 700aef42c4f2..c1ffdb823cbb 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -506,6 +506,72 @@ static int nvme_rdma_create_queue_ib(struct
nvme_rdma_queue *queue)
return ret;
}
+static void nvme_rdma_free_tagset(struct nvme_ctrl *nctrl, bool admin)
+{
+ struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+ struct blk_mq_tag_set *set = admin ?
+ &ctrl->admin_tag_set : &ctrl->tag_set;
+
+ nvme_rdma_dev_put(ctrl->device);
+ blk_mq_free_tag_set(set);
+}
+
+static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
+ bool admin)
+{
+ struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+ struct blk_mq_tag_set *set;
+ int ret;
+
+ if (admin) {
+ set = &ctrl->admin_tag_set;
+ memset(set, 0, sizeof(*set));
+ set->ops = &nvme_rdma_admin_mq_ops;
+ set->queue_depth = NVME_RDMA_AQ_BLKMQ_DEPTH;
+ set->reserved_tags = 2; /* connect + keep-alive */
+ set->numa_node = NUMA_NO_NODE;
+ set->cmd_size = sizeof(struct nvme_rdma_request) +
+ SG_CHUNK_SIZE * sizeof(struct scatterlist);
+ set->driver_data = ctrl;
+ set->nr_hw_queues = 1;
+ set->timeout = ADMIN_TIMEOUT;
+ } else {
+ set = &ctrl->tag_set;
+ memset(set, 0, sizeof(*set));
+ set->ops = &nvme_rdma_mq_ops;
+ set->queue_depth = nctrl->opts->queue_size;
+ set->reserved_tags = 1; /* fabric connect */
+ set->numa_node = NUMA_NO_NODE;
+ set->flags = BLK_MQ_F_SHOULD_MERGE;
+ set->cmd_size = sizeof(struct nvme_rdma_request) +
+ SG_CHUNK_SIZE * sizeof(struct scatterlist);
+ set->driver_data = ctrl;
+ set->nr_hw_queues = nctrl->queue_count - 1;
+ set->timeout = NVME_IO_TIMEOUT;
+ }
+
+ ret = blk_mq_alloc_tag_set(set);
+ if (ret)
+ goto out;
+
+ /*
+ * We need a reference on the device as long as the tag_set is alive,
+ * as the MRs in the request structures need a valid ib_device.
+ */
+ ret = nvme_rdma_dev_get(ctrl->device);
+ if (!ret) {
+ ret = -EINVAL;
+ goto out_free_tagset;
+ }
+
+ return set;
+
+out_free_tagset:
+ blk_mq_free_tag_set(set);
+out:
+ return ERR_PTR(ret);
+}
+
static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl,
int idx, size_t queue_size)
{
@@ -602,8 +668,7 @@ 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);
- blk_mq_free_tag_set(&ctrl->tag_set);
- nvme_rdma_dev_put(ctrl->device);
+ nvme_rdma_free_tagset(&ctrl->ctrl, false);
}
nvme_rdma_free_io_queues(ctrl);
}
@@ -694,38 +759,19 @@ static int nvme_rdma_configure_io_queues(struct
nvme_rdma_ctrl *ctrl, bool new)
return ret;
if (new) {
- /*
- * We need a reference on the device as long as the tag_set is
alive,
- * as the MRs in the request structures need a valid ib_device.
- */
- ret = -EINVAL;
- if (!nvme_rdma_dev_get(ctrl->device))
+ ctrl->ctrl.tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, false);
+ if (IS_ERR(ctrl->ctrl.tagset)) {
+ ret = PTR_ERR(ctrl->ctrl.tagset);
goto out_free_io_queues;
+ }
- memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
- ctrl->tag_set.ops = &nvme_rdma_mq_ops;
- ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
- ctrl->tag_set.reserved_tags = 1; /* fabric connect */
- ctrl->tag_set.numa_node = NUMA_NO_NODE;
- ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
- ctrl->tag_set.cmd_size = sizeof(struct nvme_rdma_request) +
- SG_CHUNK_SIZE * sizeof(struct scatterlist);
- ctrl->tag_set.driver_data = ctrl;
- ctrl->tag_set.nr_hw_queues = ctrl->ctrl.max_queues - 1;
- ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
-
- ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
- if (ret)
- goto out_put_dev;
- ctrl->ctrl.tagset = &ctrl->tag_set;
-
- ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
+ ctrl->ctrl.connect_q = blk_mq_init_queue(ctrl->ctrl.tagset);
if (IS_ERR(ctrl->ctrl.connect_q)) {
ret = PTR_ERR(ctrl->ctrl.connect_q);
goto out_free_tag_set;
}
} else {
- ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+ ret = blk_mq_reinit_tagset(ctrl->ctrl.tagset);
if (ret)
goto out_free_io_queues;
}
@@ -741,10 +787,7 @@ static int nvme_rdma_configure_io_queues(struct
nvme_rdma_ctrl *ctrl, bool new)
blk_cleanup_queue(ctrl->ctrl.connect_q);
out_free_tag_set:
if (new)
- blk_mq_free_tag_set(&ctrl->tag_set);
-out_put_dev:
- if (new)
- nvme_rdma_dev_put(ctrl->device);
+ nvme_rdma_free_tagset(&ctrl->ctrl, false);
out_free_io_queues:
nvme_rdma_free_io_queues(ctrl);
return ret;
@@ -756,8 +799,7 @@ static void nvme_rdma_destroy_admin_queue(struct
nvme_rdma_ctrl *ctrl, bool remo
if (remove) {
blk_cleanup_queue(ctrl->ctrl.admin_connect_q);
blk_cleanup_queue(ctrl->ctrl.admin_q);
- blk_mq_free_tag_set(&ctrl->admin_tag_set);
- nvme_rdma_dev_put(ctrl->device);
+ nvme_rdma_free_tagset(&ctrl->ctrl, true);
}
nvme_rdma_free_qe(ctrl->queues[0].device->dev, &ctrl->async_event_sqe,
@@ -778,43 +820,25 @@ static int nvme_rdma_configure_admin_queue(struct
nvme_rdma_ctrl *ctrl, bool new
ctrl->device->dev->attrs.max_fast_reg_page_list_len);
if (new) {
- /*
- * We need a reference on the device as long as the tag_set is
alive,
- * as the MRs in the request structures need a valid ib_device.
- */
- error = -EINVAL;
- if (!nvme_rdma_dev_get(ctrl->device))
+ 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;
+ }
- memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
- ctrl->admin_tag_set.ops = &nvme_rdma_admin_mq_ops;
- ctrl->admin_tag_set.queue_depth = NVME_RDMA_AQ_BLKMQ_DEPTH;
- ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive
*/
- ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
- ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_rdma_request)
+
- SG_CHUNK_SIZE * sizeof(struct scatterlist);
- ctrl->admin_tag_set.driver_data = ctrl;
- ctrl->admin_tag_set.nr_hw_queues = 1;
- ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
-
- error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
- if (error)
- goto out_put_dev;
- ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set;
-
- ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+ ctrl->ctrl.admin_q = blk_mq_init_queue(ctrl->ctrl.admin_tagset);
if (IS_ERR(ctrl->ctrl.admin_q)) {
error = PTR_ERR(ctrl->ctrl.admin_q);
goto out_free_tagset;
}
- ctrl->ctrl.admin_connect_q =
blk_mq_init_queue(&ctrl->admin_tag_set);
+ ctrl->ctrl.admin_connect_q =
blk_mq_init_queue(ctrl->ctrl.admin_tagset);
if (IS_ERR(ctrl->ctrl.admin_connect_q)) {
error = PTR_ERR(ctrl->ctrl.admin_connect_q);
goto out_cleanup_queue;
}
} else {
- error = blk_mq_reinit_tagset(&ctrl->admin_tag_set);
+ error = blk_mq_reinit_tagset(ctrl->ctrl.admin_tagset);
if (error)
goto out_free_queue;
}
@@ -861,14 +885,8 @@ static int nvme_rdma_configure_admin_queue(struct
nvme_rdma_ctrl *ctrl, bool new
if (new)
blk_cleanup_queue(ctrl->ctrl.admin_q);
out_free_tagset:
- if (new) {
- /* disconnect and drain the queue before freeing the tagset */
- nvme_rdma_stop_queue(ctrl, 0);
- blk_mq_free_tag_set(&ctrl->admin_tag_set);
- }
-out_put_dev:
if (new)
- nvme_rdma_dev_put(ctrl->device);
+ nvme_rdma_free_tagset(&ctrl->ctrl, true);
out_free_queue:
nvme_rdma_free_queue(ctrl, 0);
return error;
--
2.7.4
