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 v4 06/13] svcrdma: svc_rdma_post_recv() should close connection on error
Date: Mon, 22 Feb 2016 15:41:36 -0500	[thread overview]
Message-ID: <20160222204136.3274.39879.stgit@sisley.1015granger.net> (raw)
In-Reply-To: <20160222203550.3274.82777.stgit@sisley.1015granger.net>

Clean up: Most svc_rdma_post_recv() call sites close the transport
connection when a receive cannot be posted. Wrap that in a common
helper.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Devesh Sharma <devesh.sharma@broadcom.com>
Tested-by: Devesh Sharma <devesh.sharma@broadcom.com>
---
 include/linux/sunrpc/svc_rdma.h            |    1 +
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c |   11 ++---------
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c    |   10 +---------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c      |    7 +------
 net/sunrpc/xprtrdma/svc_rdma_transport.c   |   15 +++++++++++++++
 5 files changed, 20 insertions(+), 24 deletions(-)

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 40b6785..aef47dd 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -234,6 +234,7 @@ extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *);
 extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *,
 				enum rpcrdma_errcode);
 extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t);
+extern int svc_rdma_repost_recv(struct svcxprt_rdma *, gfp_t);
 extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
 extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *);
 extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index de39196..254be86 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -111,16 +111,9 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 	if (ret)
 		goto out_err;
 
-	/* Post a recv buffer to handle the reply for this request. */
-	ret = svc_rdma_post_recv(rdma, GFP_NOIO);
-	if (ret) {
-		pr_err("svcrdma: Failed to post bc receive buffer, err=%d.\n",
-		       ret);
-		pr_err("svcrdma: closing transport %p.\n", rdma);
-		set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
-		ret = -ENOTCONN;
+	ret = svc_rdma_repost_recv(rdma, GFP_NOIO);
+	if (ret)
 		goto out_err;
-	}
 
 	ctxt = svc_rdma_get_context(rdma);
 	ctxt->pages[0] = virt_to_page(rqst->rq_buffer);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index c8b8a8b..acf15b8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -711,13 +711,5 @@ defer:
 	return 0;
 
 repost:
-	ret = svc_rdma_post_recv(rdma_xprt, GFP_KERNEL);
-	if (ret) {
-		pr_err("svcrdma: could not post a receive buffer, err=%d.\n",
-		       ret);
-		pr_err("svcrdma: closing transport %p.\n", rdma_xprt);
-		set_bit(XPT_CLOSE, &rdma_xprt->sc_xprt.xpt_flags);
-		ret = -ENOTCONN;
-	}
-	return ret;
+	return svc_rdma_repost_recv(rdma_xprt, GFP_KERNEL);
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 0f8798d..ace9efa 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -475,13 +475,8 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	int pages;
 	int ret;
 
-	/* Post a recv buffer to handle another request. */
-	ret = svc_rdma_post_recv(rdma, GFP_KERNEL);
+	ret = svc_rdma_repost_recv(rdma, GFP_KERNEL);
 	if (ret) {
-		printk(KERN_INFO
-		       "svcrdma: could not post a receive buffer, err=%d."
-		       "Closing transport %p.\n", ret, rdma);
-		set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
 		svc_rdma_put_context(ctxt, 0);
 		return -ENOTCONN;
 	}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 5763825..03fdfce 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -722,6 +722,21 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags)
 	return -ENOMEM;
 }
 
+int svc_rdma_repost_recv(struct svcxprt_rdma *xprt, gfp_t flags)
+{
+	int ret = 0;
+
+	ret = svc_rdma_post_recv(xprt, flags);
+	if (ret) {
+		pr_err("svcrdma: could not post a receive buffer, err=%d.\n",
+		       ret);
+		pr_err("svcrdma: closing transport %p.\n", xprt);
+		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+		ret = -ENOTCONN;
+	}
+	return ret;
+}
+
 /*
  * This function handles the CONNECT_REQUEST event on a listening
  * endpoint. It is passed the cma_id for the _new_ connection. The context in


  parent reply	other threads:[~2016-02-22 20:41 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-22 20:40 [PATCH v4 00/13] NFS/RDMA server patches for v4.6 Chuck Lever
2016-02-22 20:40 ` [PATCH v4 01/13] svcrdma: Find client-provided write and reply chunks once per reply Chuck Lever
2016-02-22 20:41 ` [PATCH v4 02/13] svcrdma: Do not write xdr_buf::tail in a Write chunk Chuck Lever
2016-02-22 20:41 ` [PATCH v4 03/13] svcrdma: Do not send Write chunk XDR pad with inline content Chuck Lever
2016-02-22 20:41 ` [PATCH v4 04/13] nfsd: Lower NFSv4.1 callback message size limit Chuck Lever
2016-02-22 20:41 ` [PATCH v4 05/13] svcrdma: Close connection when a send error occurs Chuck Lever
2016-02-22 20:41 ` Chuck Lever [this message]
2016-02-22 20:41 ` [PATCH v4 07/13] rpcrdma: Add RPCRDMA_HDRLEN_ERR Chuck Lever
2016-02-22 20:41 ` [PATCH v4 08/13] svcrdma: Make RDMA_ERROR messages work Chuck Lever
2016-02-22 20:42 ` [PATCH v4 09/13] svcrdma: Use correct XID in error replies Chuck Lever
2016-02-22 20:42 ` [PATCH v4 10/13] svcrdma: Hook up the logic to return ERR_CHUNK Chuck Lever
2016-02-22 20:42 ` [PATCH v4 11/13] svcrdma: Remove close_out exit path Chuck Lever
2016-02-22 20:42 ` [PATCH v4 12/13] svcrdma: Use new CQ API for RPC-over-RDMA server receive CQs Chuck Lever
2016-02-22 20:42 ` [PATCH v4 13/13] svcrdma: Use new CQ API for RPC-over-RDMA server 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=20160222204136.3274.39879.stgit@sisley.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).