From: Hannes Reinecke <hare@kernel.org>
Date: Thu, 18 Apr 2024 10:39:45 +0000 (+0200)
Subject: nvme-tcp: strict pdu pacing to avoid send stalls on TLS
X-Git-Tag: v6.8.12~387
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=c810dd91cca23244e9826761f3a98952e9109b54;p=thirdparty%2Fkernel%2Fstable.git

nvme-tcp: strict pdu pacing to avoid send stalls on TLS

[ Upstream commit 50abcc179e0c9ca667feb223b26ea406d5c4c556 ]

TLS requires a strict pdu pacing via MSG_EOR to signal the end
of a record and subsequent encryption. If we do not set MSG_EOR
at the end of a sequence the record won't be closed, encryption
doesn't start, and we end up with a send stall as the message
will never be passed on to the TCP layer.
So do not check for the queue status when TLS is enabled but
rather make the MSG_MORE setting dependent on the current
request only.

Signed-off-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a6d596e056021..6eeb96578d1b4 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -352,12 +352,18 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
 	} while (ret > 0);
 }
 
-static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+static inline bool nvme_tcp_queue_has_pending(struct nvme_tcp_queue *queue)
 {
 	return !list_empty(&queue->send_list) ||
 		!llist_empty(&queue->req_list);
 }
 
+static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+{
+	return !nvme_tcp_tls(&queue->ctrl->ctrl) &&
+		nvme_tcp_queue_has_pending(queue);
+}
+
 static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 		bool sync, bool last)
 {
@@ -378,7 +384,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 		mutex_unlock(&queue->send_mutex);
 	}
 
-	if (last && nvme_tcp_queue_more(queue))
+	if (last && nvme_tcp_queue_has_pending(queue))
 		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 }