nvme: make fabrics command run on a separate request queue

We have a fundamental issue that fabric commands use the admin_q.
The reason is, that admin-connect, register reads and writes and
admin commands cannot be guaranteed ordering while we are running
controller resets.

For example, when we reset a controller we perform:
1. disable the controller
2. teardown the admin queue
3. re-establish the admin queue
4. enable the controller

In order to perform (3), we need to unquiesce the admin queue, however
we may have some admin commands that are already pending on the
quiesced admin_q and will immediate execute when we unquiesce it before
we execute (4). The host must not send admin commands to the controller
before enabling the controller.

To fix this, we have the fabric commands (admin connect and property
get/set, but not I/O queue connect) use a separate fabrics_q and make
sure to quiesce the admin_q before we disable the controller, and
unquiesce it only after we enable the controller.

This fixes the error prints from nvmet in a controller reset storm test:
kernel: nvmet: got cmd 6 while CC.EN == 0 on qid = 0
Which indicate that the host is sending an admin command when the
controller is not enabled.

Reviewed-by:  James Smart <james.smart@broadcom.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

1 files changed, 13 insertions, 3 deletions

diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index ec0bc57d26fc..9ee093b9fc74 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -253,6 +253,7 @@ static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
 	clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
 	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 }
 
@@ -357,10 +358,16 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 		goto out_free_sq;
 	ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set;
 
+	ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+	if (IS_ERR(ctrl->ctrl.fabrics_q)) {
+		error = PTR_ERR(ctrl->ctrl.fabrics_q);
+		goto out_free_tagset;
+	}
+
 	ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
 	if (IS_ERR(ctrl->ctrl.admin_q)) {
 		error = PTR_ERR(ctrl->ctrl.admin_q);
-		goto out_free_tagset;
+		goto out_cleanup_fabrics_q;
 	}
 
 	error = nvmf_connect_admin_queue(&ctrl->ctrl);
@@ -376,6 +383,8 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 	ctrl->ctrl.max_hw_sectors =
 		(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
 
+	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+
 	error = nvme_init_identify(&ctrl->ctrl);
 	if (error)
 		goto out_cleanup_queue;
@@ -384,6 +393,8 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 
 out_cleanup_queue:
 	blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_cleanup_fabrics_q:
+	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
 out_free_tagset:
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 out_free_sq:
@@ -401,14 +412,13 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 		nvme_loop_destroy_io_queues(ctrl);
 	}
 
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
 		nvme_shutdown_ctrl(&ctrl->ctrl);
 
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
 	blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_loop_destroy_admin_queue(ctrl);
 }