[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200914130358.1804194-1-sashal@kernel.org>
Date: Mon, 14 Sep 2020 09:03:30 -0400
From: Sasha Levin <sashal@...nel.org>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc: Chuck Lever <chuck.lever@...cle.com>, Dan Aloni <dan@...nelim.com>,
Anna Schumaker <Anna.Schumaker@...app.com>,
Sasha Levin <sashal@...nel.org>, linux-nfs@...r.kernel.org,
netdev@...r.kernel.org
Subject: [PATCH AUTOSEL 5.8 01/29] xprtrdma: Release in-flight MRs on disconnect
From: Chuck Lever <chuck.lever@...cle.com>
[ Upstream commit 5de55ce951a1466e31ff68a7bc6b0a7ce3cb5947 ]
Dan Aloni reports that when a server disconnects abruptly, a few
memory regions are left DMA mapped. Over time this leak could pin
enough I/O resources to slow or even deadlock an NFS/RDMA client.
I found that if a transport disconnects before pending Send and
FastReg WRs can be posted, the to-be-registered MRs are stranded on
the req's rl_registered list and never released -- since they
weren't posted, there's no Send completion to DMA unmap them.
Reported-by: Dan Aloni <dan@...nelim.com>
Signed-off-by: Chuck Lever <chuck.lever@...cle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@...app.com>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
net/sunrpc/xprtrdma/verbs.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 75c646743df3e..ca89f24a1590b 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -933,6 +933,8 @@ static void rpcrdma_req_reset(struct rpcrdma_req *req)
rpcrdma_regbuf_dma_unmap(req->rl_sendbuf);
rpcrdma_regbuf_dma_unmap(req->rl_recvbuf);
+
+ frwr_reset(req);
}
/* ASSUMPTION: the rb_allreqs list is stable for the duration,
--
2.25.1
Powered by blists - more mailing lists