From fadc0f3bb2de8c570ced6d9c1f97222213d93140 Mon Sep 17 00:00:00 2001 From: Nikhil Jha Date: Wed, 19 Mar 2025 13:02:40 -0400 Subject: sunrpc: don't immediately retransmit on seqno miss RFC2203 requires that retransmitted messages use a new gss sequence number, but the same XID. This means that if the server is just slow (e.x. overloaded), the client might receive a response using an older seqno than the one it has recorded. Currently, Linux's client immediately retransmits in this case. However, this leads to a lot of wasted retransmits until the server eventually responds faster than the client can resend. Client -> SEQ 1 -> Server Client -> SEQ 2 -> Server Client <- SEQ 1 <- Server (misses, expecting seqno = 2) Client -> SEQ 3 -> Server (immediate retransmission on miss) Client <- SEQ 2 <- Server (misses, expecting seqno = 3) Client -> SEQ 4 -> Server (immediate retransmission on miss) ... and so on ... This commit makes it so that we ignore messages with bad checksums due to seqnum mismatch, and rely on the usual timeout behavior for retransmission instead of doing so immediately. Signed-off-by: Nikhil Jha Acked-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/clnt.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 6f75862d9782..21426c3049d3 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2771,8 +2771,13 @@ out_verifier: case -EPROTONOSUPPORT: goto out_err; case -EACCES: - /* Re-encode with a fresh cred */ - fallthrough; + /* possible RPCSEC_GSS out-of-sequence event (RFC2203), + * reset recv state and keep waiting, don't retransmit + */ + task->tk_rqstp->rq_reply_bytes_recvd = 0; + task->tk_status = xprt_request_enqueue_receive(task); + task->tk_action = call_transmit_status; + return -EBADMSG; default: goto out_garbage; } -- cgit v1.2.3