Received-SPF: pass (google.com: domain of linux-kernel+bounces-91858-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: Daniel Wagner <dwagner@suse.de>
To: James Smart <james.smart@broadcom.com>
Cc: Keith Busch <kbusch@kernel.org>,
	Christoph Hellwig <hch@lst.de>,
	Sagi Grimberg <sagi@grimberg.me>,
	Hannes Reinecke <hare@suse.de>,
	linux-nvme@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	Daniel Wagner <dwagner@suse.de>
Subject: [PATCH v3 1/2] nvme-tcp: short-circuit reconnect retries
Date: Tue,  5 Mar 2024 09:00:04 +0100
Message-ID: <20240305080005.3638-2-dwagner@suse.de>
In-Reply-To: <20240305080005.3638-1-dwagner@suse.de>
References: <20240305080005.3638-1-dwagner@suse.de>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Hannes Reinecke <hare@suse.de>

Returning an nvme status from nvme_tcp_setup_ctrl() indicates
that the association was established and we have received a status
from the controller; consequently we should honour the DNR bit.
If not any future reconnect attempts will just return the same error, so
we can short-circuit the reconnect attempts and fail the connection
directly.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
---
 drivers/nvme/host/tcp.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 3b20c5ed033f..f9ad5904ed62 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2149,9 +2149,11 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	nvme_tcp_destroy_io_queues(ctrl, remove);
 }
 
-static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
+static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl,
+		int status)
 {
 	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+	bool recon = status > 0 && (status & NVME_SC_DNR) ? false : true;
 
 	/* If we are resetting/deleting then do nothing */
 	if (state != NVME_CTRL_CONNECTING) {
@@ -2159,13 +2161,14 @@ static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
 		return;
 	}
 
-	if (nvmf_should_reconnect(ctrl)) {
+	if (recon && nvmf_should_reconnect(ctrl)) {
 		dev_info(ctrl->device, "Reconnecting in %d seconds...\n",
 			ctrl->opts->reconnect_delay);
 		queue_delayed_work(nvme_wq, &to_tcp_ctrl(ctrl)->connect_work,
 				ctrl->opts->reconnect_delay * HZ);
 	} else {
-		dev_info(ctrl->device, "Removing controller...\n");
+		dev_info(ctrl->device, "Removing controller (%d)...\n",
+			 status);
 		nvme_delete_ctrl(ctrl);
 	}
 }
@@ -2246,10 +2249,12 @@ static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work)
 	struct nvme_tcp_ctrl *tcp_ctrl = container_of(to_delayed_work(work),
 			struct nvme_tcp_ctrl, connect_work);
 	struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl;
+	int ret;
 
 	++ctrl->nr_reconnects;
 
-	if (nvme_tcp_setup_ctrl(ctrl, false))
+	ret = nvme_tcp_setup_ctrl(ctrl, false);
+	if (ret)
 		goto requeue;
 
 	dev_info(ctrl->device, "Successfully reconnected (%d attempt)\n",
@@ -2262,7 +2267,7 @@ static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work)
 requeue:
 	dev_info(ctrl->device, "Failed reconnect attempt %d\n",
 			ctrl->nr_reconnects);
-	nvme_tcp_reconnect_or_remove(ctrl);
+	nvme_tcp_reconnect_or_remove(ctrl, ret);
 }
 
 static void nvme_tcp_error_recovery_work(struct work_struct *work)
@@ -2289,7 +2294,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
 		return;
 	}
 
-	nvme_tcp_reconnect_or_remove(ctrl);
+	nvme_tcp_reconnect_or_remove(ctrl, -ENOTCONN);
 }
 
 static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
@@ -2309,6 +2314,7 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl =
 		container_of(work, struct nvme_ctrl, reset_work);
+	int ret;
 
 	nvme_stop_ctrl(ctrl);
 	nvme_tcp_teardown_ctrl(ctrl, false);
@@ -2322,14 +2328,15 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 		return;
 	}
 
-	if (nvme_tcp_setup_ctrl(ctrl, false))
+	ret = nvme_tcp_setup_ctrl(ctrl, false);
+	if (ret)
 		goto out_fail;
 
 	return;
 
 out_fail:
 	++ctrl->nr_reconnects;
-	nvme_tcp_reconnect_or_remove(ctrl);
+	nvme_tcp_reconnect_or_remove(ctrl, ret);
 }
 
 static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl)
-- 
2.44.0