tmakin/ack-tegra
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nvme-tcp: fix I/O stalls on congested sockets

Browse Source 
[ Upstream commit f42d4796ee100fade86086d1cf98537fb4d326c8 ]

When the socket is busy processing nvme_tcp_try_recv() might return
-EAGAIN, but this doesn't automatically imply that the sending side is
blocked, too.  So check if there are pending requests once
nvme_tcp_try_recv() returns -EAGAIN and continue with the sending loop
to avoid I/O stalls.

Signed-off-by: Hannes Reinecke <hare@kernel.org>
Acked-by: Chris Leech <cleech@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Hannes Reinecke
2025-05-28 08:45:34 +02:00
committed by Greg Kroah-Hartman
parent 519ab9c725
commit 7b86ce1670
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
drivers/nvme/host/tcp.c
View File

@@ -1349,7 +1349,7 @@ static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue)
queue->nr_cqe = 0;
consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
release_sock(sk);
return consumed;
return consumed == -EAGAIN ? 0 : consumed;
}
static void nvme_tcp_io_work(struct work_struct *w)
@@ -1377,6 +1377,11 @@ static void nvme_tcp_io_work(struct work_struct *w)
else if (unlikely(result < 0))
return;
/* did we get some space after spending time in recv? */
if (nvme_tcp_queue_has_pending(queue) &&
sk_stream_is_writeable(queue->sock->sk))
pending = true;
if (!pending || !queue->rd_enabled)
return;