lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Tue,  9 Apr 2024 11:35:07 +0200
From: Daniel Wagner <dwagner@...e.de>
To: Christoph Hellwig <hch@....de>
Cc: Keith Busch <kbusch@...nel.org>,
	Sagi Grimberg <sagi@...mberg.me>,
	James Smart <james.smart@...adcom.com>,
	Hannes Reinecke <hare@...e.de>,
	linux-nvme@...ts.infradead.org,
	linux-kernel@...r.kernel.org,
	Daniel Wagner <dwagner@...e.de>
Subject: [PATCH v5 3/6] nvme-tcp: short-circuit reconnect retries

From: Hannes Reinecke <hare@...e.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@...e.de>
[dwagner: add helper to decide to reconnect]
Signed-off-by: Daniel Wagner <dwagner@...e.de>
---
 drivers/nvme/host/nvme.h | 24 ++++++++++++++++++++++++
 drivers/nvme/host/tcp.c  | 23 +++++++++++++++--------
 2 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 9b8904a476b8..dfe103283a3d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -701,6 +701,30 @@ static inline bool nvme_is_path_error(u16 status)
 	return (status & 0x700) == 0x300;
 }
 
+/*
+ * Evaluate the status information returned by the LLDD in order to
+ * decided if a reconnect attempt should be scheduled.
+ *
+ * There are two cases where no reconnect attempt should be attempted:
+ *
+ * 1) The LLDD reports an negative status. There was an error (e.g. no
+ *    memory) on the host side and thus abort the operation.
+ *    Note, there are exception such as ENOTCONN which is
+ *    not an internal driver error, thus we filter these errors
+ *    out and retry later.
+ * 2) The DNR bit is set and the specification states no further
+ *    connect attempts with the same set of paramenters should be
+ *    attempted.
+ */
+static inline bool nvme_ctrl_reconnect(int status)
+{
+	if (status < 0 && status != -ENOTCONN)
+		return false;
+	else if (status > 0 && (status & NVME_SC_DNR))
+		return false;
+	return true;
+}
+
 /*
  * Fill in the status and result information from the CQE, and then figure out
  * if blk-mq will need to use IPI magic to complete the request, and if yes do
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index fdbcdcedcee9..7e25a96e9870 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2155,9 +2155,11 @@ 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 = nvme_ctrl_reconnect(status);
 
 	/* If we are resetting/deleting then do nothing */
 	if (state != NVME_CTRL_CONNECTING) {
@@ -2165,13 +2167,14 @@ 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);
 	}
 }
@@ -2252,10 +2255,12 @@ 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",
@@ -2268,7 +2273,7 @@ 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)
@@ -2295,7 +2300,7 @@ 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)
@@ -2315,6 +2320,7 @@ 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);
@@ -2328,14 +2334,15 @@ 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


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ