From: Chuck Lever <chuck.lever@oracle.com>
To: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: [PATCH v1 7/8] xprtrdma: Fix cwnd update ordering
Date: Wed, 31 Mar 2021 15:36:41 -0400 [thread overview]
Message-ID: <161721940170.515226.389858159579607870.stgit@manet.1015granger.net> (raw)
In-Reply-To: <161721926778.515226.9805598788670386587.stgit@manet.1015granger.net>
After a reconnect, the reply handler is opening the cwnd (and thus
enabling more RPC Calls to be sent) /before/ rpcrdma_post_recvs()
can post enough Receive WRs to receive their replies. This causes an
RNR and the new connection is lost immediately.
The race is most clearly exposed when KASAN and disconnect injection
are enabled. This slows down rpcrdma_rep_create() considerably.
Fixes: 2ae50ad68cd7 ("xprtrdma: Close window between waking RPC senders and posting Receives")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
net/sunrpc/xprtrdma/rpc_rdma.c | 3 ++-
net/sunrpc/xprtrdma/verbs.c | 10 +++++-----
net/sunrpc/xprtrdma/xprt_rdma.h | 2 +-
3 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 292f066d006e..21ddd78a8c35 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1430,9 +1430,10 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
credits = 1; /* don't deadlock */
else if (credits > r_xprt->rx_ep->re_max_requests)
credits = r_xprt->rx_ep->re_max_requests;
+ rpcrdma_post_recvs(r_xprt, credits + (buf->rb_bc_srv_max_requests << 1),
+ false);
if (buf->rb_credits != credits)
rpcrdma_update_cwnd(r_xprt, credits);
- rpcrdma_post_recvs(r_xprt, false);
req = rpcr_to_rdmar(rqst);
if (unlikely(req->rl_reply))
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 2fde805edb64..82489f527ece 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -537,7 +537,7 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt)
* outstanding Receives.
*/
rpcrdma_ep_get(ep);
- rpcrdma_post_recvs(r_xprt, true);
+ rpcrdma_post_recvs(r_xprt, 1, true);
rc = rdma_connect(ep->re_id, &ep->re_remote_cma);
if (rc)
@@ -1388,10 +1388,11 @@ int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
/**
* rpcrdma_post_recvs - Refill the Receive Queue
* @r_xprt: controlling transport instance
- * @temp: mark Receive buffers to be deleted after use
+ * @needed: current credit grant
+ * @temp: mark Receive buffers to be deleted after one use
*
*/
-void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
+void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp)
{
struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
struct rpcrdma_ep *ep = r_xprt->rx_ep;
@@ -1399,12 +1400,11 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
struct ib_recv_wr *wr, *bad_wr;
struct rpcrdma_rep *rep;
struct ib_qp_attr attr;
- int needed, count, rc;
+ int count, rc;
rc = 0;
count = 0;
- needed = buf->rb_credits + (buf->rb_bc_srv_max_requests << 1);
if (likely(ep->re_receive_count > needed))
goto out;
needed -= ep->re_receive_count;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index fe3be985e239..28af11fbe643 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -461,7 +461,7 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt);
void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt);
int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
-void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp);
+void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp);
/*
* Buffer calls - xprtrdma/verbs.c
next prev parent reply other threads:[~2021-03-31 19:37 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-31 19:35 [PATCH v1 0/8] xprtrdma Receive Queue fixes Chuck Lever
2021-03-31 19:36 ` [PATCH v1 1/8] xprtrdma: Avoid Receive Queue wrapping Chuck Lever
2021-03-31 20:05 ` Tom Talpey
2021-03-31 19:36 ` [PATCH v1 2/8] xprtrdma: Do not post Receives after disconnect Chuck Lever
2021-03-31 19:59 ` Tom Talpey
2021-03-31 20:31 ` Chuck Lever
2021-03-31 21:22 ` Tom Talpey
2021-04-01 16:56 ` Chuck Lever
2021-03-31 19:36 ` [PATCH v1 3/8] xprtrdma: Put flushed Receives on free list instead of destroying them Chuck Lever
2021-03-31 20:02 ` Tom Talpey
2021-03-31 19:36 ` [PATCH v1 4/8] xprtrdma: Improve locking around rpcrdma_rep destruction Chuck Lever
2021-03-31 19:36 ` [PATCH v1 5/8] xprtrdma: Improve commentary around rpcrdma_reps_unmap() Chuck Lever
2021-03-31 19:36 ` [PATCH v1 6/8] xprtrdma: Improve locking around rpcrdma_rep creation Chuck Lever
2021-03-31 19:36 ` Chuck Lever [this message]
2021-03-31 19:36 ` [PATCH v1 8/8] xprtrdma: Delete rpcrdma_recv_buffer_put() Chuck Lever
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=161721940170.515226.389858159579607870.stgit@manet.1015granger.net \
--to=chuck.lever@oracle.com \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).