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 v4 20/24] xprtrdma: Update only specific fields in private receive buffer
Date: Wed, 29 Jun 2016 13:54:49 -0400 [thread overview]
Message-ID: <20160629175449.15094.7128.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20160629173231.15094.52660.stgit@manet.1015granger.net>
Now that rpcrdma_inline_fixup() updates only two fields in
rq_rcv_buf, a full memcpy of that structure to rq_private_buf is
unwarranted. Updating rq_private_buf fields only where needed also
better documents what is going on.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
---
net/sunrpc/xprtrdma/rpc_rdma.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index d018eb7..a0e811d 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -750,6 +750,11 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, int wrchunk, __be32 **iptrp)
* The upper layer has set the maximum number of bytes it can
* receive in each component of rq_rcv_buf. These values are set in
* the head.iov_len, page_len, tail.iov_len, and buflen fields.
+ *
+ * Unlike the TCP equivalent (xdr_partial_copy_from_skb), in
+ * many cases this function simply updates iov_base pointers in
+ * rq_rcv_buf to point directly to the received reply data, to
+ * avoid copying reply data.
*/
static void
rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
@@ -763,6 +768,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
* in the receive buffer, to avoid a memcopy.
*/
rqst->rq_rcv_buf.head[0].iov_base = srcp;
+ rqst->rq_private_buf.head[0].iov_base = srcp;
/* The contents of the receive buffer that follow
* head.iov_len bytes are copied into the page list.
@@ -822,16 +828,15 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
/* The tail iovec is redirected to the remaining data
* in the receive buffer, to avoid a memcopy.
*/
- if (copy_len || pad)
+ if (copy_len || pad) {
rqst->rq_rcv_buf.tail[0].iov_base = srcp;
+ rqst->rq_private_buf.tail[0].iov_base = srcp;
+ }
if (copy_len)
dprintk("RPC: %s: %d bytes in"
" %d extra segments (%d lost)\n",
__func__, olen, i, copy_len);
-
- /* TBD avoid a warning from call_decode() */
- rqst->rq_private_buf = rqst->rq_rcv_buf;
}
void
next prev parent reply other threads:[~2016-06-29 17:57 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-29 17:52 [PATCH v4 00/24] NFS/RDMA client patches proposed for v4.8 Chuck Lever
2016-06-29 17:52 ` [PATCH v4 01/24] xprtrdma: Remove FMRs from the unmap list after unmapping Chuck Lever
2016-06-29 17:52 ` [PATCH v4 02/24] xprtrdma: Create common scatterlist fields in rpcrdma_mw Chuck Lever
2016-06-29 17:52 ` [PATCH v4 03/24] xprtrdma: Move init and release helpers Chuck Lever
2016-06-29 17:52 ` [PATCH v4 04/24] xprtrdma: Rename fields in rpcrdma_fmr Chuck Lever
2016-06-29 17:52 ` [PATCH v4 05/24] xprtrdma: Use scatterlist for DMA mapping and unmapping under FMR Chuck Lever
2016-06-29 17:52 ` [PATCH v4 06/24] xprtrdma: Refactor MR recovery work queues Chuck Lever
2016-06-29 17:53 ` [PATCH v4 07/24] xprtrdma: Do not leak an MW during a DMA map failure Chuck Lever
2016-06-29 17:53 ` [PATCH v4 08/24] xprtrdma: Remove ALLPHYSICAL memory registration mode Chuck Lever
2016-06-29 17:53 ` [PATCH v4 09/24] xprtrdma: Remove rpcrdma_map_one() and friends Chuck Lever
2016-06-29 17:53 ` [PATCH v4 10/24] xprtrdma: Clean up device capability detection Chuck Lever
2016-06-29 17:53 ` [PATCH v4 11/24] xprtrdma: Reply buffer exhaustion can be catastrophic Chuck Lever
2016-06-29 17:53 ` [PATCH v4 12/24] xprtrdma: Honor ->send_request API contract Chuck Lever
2016-06-29 17:53 ` [PATCH v4 13/24] xprtrdma: Chunk list encoders must not return zero Chuck Lever
2016-06-29 17:54 ` [PATCH v4 14/24] xprtrdma: Allocate MRs on demand Chuck Lever
2016-06-29 17:54 ` [PATCH v4 15/24] xprtrdma: Release orphaned MRs immediately Chuck Lever
2016-06-29 17:54 ` [PATCH v4 16/24] xprtrdma: Place registered MWs on a per-req list Chuck Lever
2016-06-29 17:54 ` [PATCH v4 17/24] xprtrdma: Chunk list encoders no longer share one rl_segments array Chuck Lever
2016-06-29 17:54 ` [PATCH v4 18/24] xprtrdma: rpcrdma_inline_fixup() overruns the receive page list Chuck Lever
2016-06-29 17:54 ` [PATCH v4 19/24] xprtrdma: Do not update {head, tail}.iov_len in rpcrdma_inline_fixup() Chuck Lever
2016-06-29 17:54 ` Chuck Lever [this message]
2016-06-29 17:54 ` [PATCH v4 21/24] xprtrdma: Clean up fixup_copy_count accounting Chuck Lever
2016-06-29 17:55 ` [PATCH v4 22/24] xprtrdma: No direct data placement with krb5i and krb5p Chuck Lever
2016-06-29 17:55 ` [PATCH v4 23/24] svc: Avoid garbage replies when pc_func() returns rpc_drop_reply Chuck Lever
2016-06-29 17:55 ` [PATCH v4 24/24] NFS: Don't drop CB requests with invalid principals 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=20160629175449.15094.7128.stgit@manet.1015granger.net \
--to=chuck.lever@oracle.com \
--cc=anna.schumaker@netapp.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).