linux-nfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Chuck Lever <chuck.lever@oracle.com>
To: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: [PATCH v2 06/12] xprtrdma: Do not wait if ib_post_send() fails
Date: Thu, 18 Feb 2016 12:30:43 -0500	[thread overview]
Message-ID: <20160218173043.14009.19155.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20160218172449.14009.47311.stgit@manet.1015granger.net>

If ib_post_send() in ro_unmap_sync() fails, the WRs have not been
posted, no completions will fire, and wait_for_completion() will
wait forever. Skip the wait in that case.

To ensure the MRs are invalid, disconnect.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/xprtrdma/frwr_ops.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index e165673..ecb005f 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -520,14 +520,18 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * unless ri_id->qp is a valid pointer.
 	 */
 	rc = ib_post_send(ia->ri_id->qp, invalidate_wrs, &bad_wr);
-	if (rc)
+	if (rc) {
 		pr_warn("%s: ib_post_send failed %i\n", __func__, rc);
+		rdma_disconnect(ia->ri_id);
+		goto unmap;
+	}
 
 	wait_for_completion(&f->fr_linv_done);
 
 	/* ORDER: Now DMA unmap all of the req's MRs, and return
 	 * them to the free MW list.
 	 */
+unmap:
 	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
 		seg = &req->rl_segments[i];
 


  parent reply	other threads:[~2016-02-18 17:30 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-18 17:29 [PATCH v2 00/12] NFS/RDMA client patches for v4.6 Chuck Lever
2016-02-18 17:30 ` [PATCH v2 01/12] xprtrdma: rpcrdma_bc_receive_call() should init rq_private_buf.len Chuck Lever
2016-02-18 17:30 ` [PATCH v2 02/12] xprtrdma: Clean up unused RPCRDMA_INLINE_PAD_THRESH macro Chuck Lever
2016-02-18 17:30 ` [PATCH v2 03/12] xprtrdma: Clean up physical_op_map() Chuck Lever
2016-02-18 17:30 ` [PATCH v2 04/12] xprtrdma: Clean up dprintk format string containing a newline Chuck Lever
2016-02-18 17:30 ` [PATCH v2 05/12] xprtrdma: Segment head and tail XDR buffers on page boundaries Chuck Lever
2016-02-18 17:30 ` Chuck Lever [this message]
2016-02-18 17:30 ` [PATCH v2 07/12] rpcrdma: Add RPCRDMA_HDRLEN_ERR Chuck Lever
2016-02-18 17:30 ` [PATCH v2 08/12] xprtrdma: Properly handle RDMA_ERROR replies Chuck Lever
2016-02-18 17:31 ` [PATCH v2 09/12] xprtrdma: Serialize credit accounting again Chuck Lever
2016-02-18 17:31 ` [PATCH v2 10/12] xprtrdma: Use new CQ API for RPC-over-RDMA client receive CQs Chuck Lever
2016-02-18 17:31 ` [PATCH v2 11/12] xprtrdma: Use an anonymous union in struct rpcrdma_mw Chuck Lever
2016-02-18 17:31 ` [PATCH v2 12/12] xprtrdma: Use new CQ API for RPC-over-RDMA client send CQs 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=20160218173043.14009.19155.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).