All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
To: anna.schumaker-HgOvQuBEEgTQT0dZR+AlfA@public.gmane.org
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: [PATCH v2 1/5] xprtrdma: Fix Read chunk padding
Date: Mon, 23 Jan 2017 15:52:46 -0500	[thread overview]
Message-ID: <20170123205246.21699.14602.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20170123205159.21699.47373.stgit-FYjufvaPoItvLzlybtyyYzGyq/o6K9yX@public.gmane.org>

When pad optimization is disabled, rpcrdma_convert_iovs still
does not add explicit XDR round-up padding to a Read chunk.

Commit 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling")
incorrectly short-circuited the test for whether round-up padding
is needed that appears later in rpcrdma_convert_iovs.

However, if this is indeed a Read chunk (and not a Position-Zero
Read chunk), the tail iovec _always_ contains the chunk's padding,
and never anything else.

So, it's easy to just skip the tail when padding optimization is
enabled, and add the tail in a subsequent Read chunk segment, if
disabled.

Fixes: 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling")
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
---
 net/sunrpc/xprtrdma/rpc_rdma.c |   10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index c52e0f2..a524d3c 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -226,8 +226,10 @@ static bool rpcrdma_results_inline(struct rpcrdma_xprt *r_xprt,
 	if (len && n == RPCRDMA_MAX_SEGS)
 		goto out_overflow;
 
-	/* When encoding the read list, the tail is always sent inline */
-	if (type == rpcrdma_readch)
+	/* When encoding a Read chunk, the tail iovec contains an
+	 * XDR pad and may be omitted.
+	 */
+	if (type == rpcrdma_readch && xprt_rdma_pad_optimize)
 		return n;
 
 	/* When encoding the Write list, some servers need to see an extra
@@ -238,10 +240,6 @@ static bool rpcrdma_results_inline(struct rpcrdma_xprt *r_xprt,
 		return n;
 
 	if (xdrbuf->tail[0].iov_len) {
-		/* the rpcrdma protocol allows us to omit any trailing
-		 * xdr pad bytes, saving the server an RDMA operation. */
-		if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize)
-			return n;
 		n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n);
 		if (n == RPCRDMA_MAX_SEGS)
 			goto out_overflow;

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

WARNING: multiple messages have this Message-ID (diff)
From: Chuck Lever <chuck.lever@oracle.com>
To: anna.schumaker@netapp.com
Cc: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: [PATCH v2 1/5] xprtrdma: Fix Read chunk padding
Date: Mon, 23 Jan 2017 15:52:46 -0500	[thread overview]
Message-ID: <20170123205246.21699.14602.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20170123205159.21699.47373.stgit@manet.1015granger.net>

When pad optimization is disabled, rpcrdma_convert_iovs still
does not add explicit XDR round-up padding to a Read chunk.

Commit 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling")
incorrectly short-circuited the test for whether round-up padding
is needed that appears later in rpcrdma_convert_iovs.

However, if this is indeed a Read chunk (and not a Position-Zero
Read chunk), the tail iovec _always_ contains the chunk's padding,
and never anything else.

So, it's easy to just skip the tail when padding optimization is
enabled, and add the tail in a subsequent Read chunk segment, if
disabled.

Fixes: 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c |   10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index c52e0f2..a524d3c 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -226,8 +226,10 @@ static bool rpcrdma_results_inline(struct rpcrdma_xprt *r_xprt,
 	if (len && n == RPCRDMA_MAX_SEGS)
 		goto out_overflow;
 
-	/* When encoding the read list, the tail is always sent inline */
-	if (type == rpcrdma_readch)
+	/* When encoding a Read chunk, the tail iovec contains an
+	 * XDR pad and may be omitted.
+	 */
+	if (type == rpcrdma_readch && xprt_rdma_pad_optimize)
 		return n;
 
 	/* When encoding the Write list, some servers need to see an extra
@@ -238,10 +240,6 @@ static bool rpcrdma_results_inline(struct rpcrdma_xprt *r_xprt,
 		return n;
 
 	if (xdrbuf->tail[0].iov_len) {
-		/* the rpcrdma protocol allows us to omit any trailing
-		 * xdr pad bytes, saving the server an RDMA operation. */
-		if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize)
-			return n;
 		n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n);
 		if (n == RPCRDMA_MAX_SEGS)
 			goto out_overflow;


  parent reply	other threads:[~2017-01-23 20:52 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-23 20:52 [PATCH v2 0/5] Fix "support large inline thresholds" Chuck Lever
2017-01-23 20:52 ` Chuck Lever
     [not found] ` <20170123205159.21699.47373.stgit-FYjufvaPoItvLzlybtyyYzGyq/o6K9yX@public.gmane.org>
2017-01-23 20:52   ` Chuck Lever [this message]
2017-01-23 20:52     ` [PATCH v2 1/5] xprtrdma: Fix Read chunk padding Chuck Lever
2017-01-23 20:52   ` [PATCH v2 2/5] xprtrdma: Per-connection pad optimization Chuck Lever
2017-01-23 20:52     ` Chuck Lever
     [not found]     ` <20170123205254.21699.44329.stgit-FYjufvaPoItvLzlybtyyYzGyq/o6K9yX@public.gmane.org>
2017-01-24 19:12       ` Anna Schumaker
2017-01-24 19:12         ` Anna Schumaker
     [not found]         ` <19a00a6f-9502-161a-d37b-7371b07662ed-ZwjVKphTwtPQT0dZR+AlfA@public.gmane.org>
2017-01-24 19:16           ` Chuck Lever
2017-01-24 19:16             ` Chuck Lever
     [not found]             ` <575D5F73-2D4B-4FDA-B196-0D683B459F9D-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2017-01-24 19:23               ` Anna Schumaker
2017-01-24 19:23                 ` Anna Schumaker
2017-01-23 20:53   ` [PATCH v2 3/5] xprtrdma: Disable pad optimization by default Chuck Lever
2017-01-23 20:53     ` Chuck Lever
2017-01-23 20:53   ` [PATCH v2 4/5] xprtrdma: Reduce required number of send SGEs Chuck Lever
2017-01-23 20:53     ` Chuck Lever
2017-01-23 20:53   ` [PATCH v2 5/5] xprtrdma: Shrink send SGEs array Chuck Lever
2017-01-23 20:53     ` Chuck Lever
2017-01-24 21:35   ` [PATCH v2 0/5] Fix "support large inline thresholds" Anna Schumaker
2017-01-24 21:35     ` Anna Schumaker
     [not found]     ` <353a72a5-549d-535b-28b7-411ba81483a1-ZwjVKphTwtPQT0dZR+AlfA@public.gmane.org>
2017-01-24 21:46       ` Chuck Lever
2017-01-24 21:46         ` Chuck Lever
     [not found]         ` <82302622-9524-4020-869E-81F57629EC86-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2017-02-01 18:15           ` Chuck Lever
2017-02-01 18:15             ` Chuck Lever
     [not found]             ` <68619BE7-CBFD-41DE-8227-ABCD797E81F7-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2017-02-08 16:47               ` Chuck Lever
2017-02-08 16:47                 ` Chuck Lever
     [not found]                 ` <D12FEB95-6948-4E51-84EA-6D138C7F8B12-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2017-02-08 18:28                   ` Anna Schumaker
2017-02-08 18:28                     ` Anna Schumaker

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=20170123205246.21699.14602.stgit@manet.1015granger.net \
    --to=chuck.lever-qhclzuegtsvqt0dzr+alfa@public.gmane.org \
    --cc=anna.schumaker-HgOvQuBEEgTQT0dZR+AlfA@public.gmane.org \
    --cc=linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.