From: Chuck Lever <chuck.lever@oracle.com>
To: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: [PATCH v1 05/22] SUNRPC: Separate buffer pointers for RPC Call and Reply messages
Date: Mon, 15 Aug 2016 16:50:55 -0400 [thread overview]
Message-ID: <20160815205055.11652.59194.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20160815195649.11652.32252.stgit@manet.1015granger.net>
For xprtrdma, the RPC Call and Reply buffers are involved in real
I/O operations.
To start with, the DMA direction of the I/O for a Call is opposite
that of a Reply.
In the current arrangement, the Reply buffer address is on a
four-byte alignment just past the call buffer. Would be friendlier
on some platforms if that was at a DMA cache alignment instead.
Because the current arrangement allocates a single memory region
which contains both buffers, the RPC Reply buffer often contains a
page boundary in it when the Call buffer is large enough (which is
frequent).
It would be a little nicer for setting up DMA operations (and
possible registration of the Reply buffer) if the two buffers were
separated, well-aligned, and contained as few page boundaries as
possible.
Now, I could just pad out the single memory region used for the pair
of buffers. But frequently that would mean a lot of unused space to
ensure the Reply buffer did not have a page boundary.
Add a separate pointer to rpc_rqst that points right to the RPC
Reply buffer. This makes no difference to xprtsock, but it will help
xprtrdma in subsequent patches.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
include/linux/sunrpc/xprt.h | 5 +++--
net/sunrpc/clnt.c | 2 +-
net/sunrpc/sched.c | 2 ++
net/sunrpc/xprtrdma/transport.c | 2 ++
4 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 272c108..8e3f292 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -84,8 +84,9 @@ struct rpc_rqst {
struct list_head rq_list;
__be32 *rq_buffer; /* Call XDR encode buffer */
- size_t rq_callsize,
- rq_rcvsize;
+ size_t rq_callsize;
+ __be32 *rq_rbuffer; /* Reply XDR decode buffer */
+ size_t rq_rcvsize;
size_t rq_xmit_bytes_sent; /* total bytes sent */
size_t rq_reply_bytes_recvd; /* total reply bytes */
/* received */
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 601b3ca..4c933a8 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1768,7 +1768,7 @@ rpc_xdr_encode(struct rpc_task *task)
req->rq_buffer,
req->rq_callsize);
xdr_buf_init(&req->rq_rcv_buf,
- (__be32 *)((char *)req->rq_buffer + req->rq_callsize),
+ req->rq_rbuffer,
req->rq_rcvsize);
p = rpc_encode_header(task);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 6690ebc..8ed0c87 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -891,6 +891,8 @@ int rpc_malloc(struct rpc_task *task)
dprintk("RPC: %5u allocated buffer of size %zu at %p\n",
task->tk_pid, size, buf);
rqst->rq_buffer = buf->data;
+ rqst->rq_rbuffer = (__be32 *)((char *)rqst->rq_buffer +
+ rqst->rq_callsize);
return 0;
}
EXPORT_SYMBOL_GPL(rpc_malloc);
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index e7f222f..1f5dc19 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -524,6 +524,8 @@ out:
dprintk("RPC: %s: size %zd, request 0x%p\n", __func__, size, req);
req->rl_connect_cookie = 0; /* our reserved value */
rqst->rq_buffer = req->rl_sendbuf->rg_base;
+ rqst->rq_rbuffer = (__be32 *)((char *)rqst->rq_buffer +
+ rqst->rq_rcvsize);
return 0;
out_rdmabuf:
next prev parent reply other threads:[~2016-08-15 20:50 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-15 20:50 [PATCH v1 00/22] client-side NFS/RDMA patches proposed for v4.9 Chuck Lever
2016-08-15 20:50 ` [PATCH v1 01/22] xprtrdma: Eliminate INLINE_THRESHOLD macros Chuck Lever
2016-08-15 20:50 ` [PATCH v1 02/22] SUNRPC: Refactor rpc_xdr_buf_init() Chuck Lever
2016-08-15 21:51 ` Trond Myklebust
2016-08-16 1:24 ` Chuck Lever
2016-08-15 20:50 ` [PATCH v1 03/22] SUNRPC: Generalize the RPC buffer allocation API Chuck Lever
2016-08-15 21:59 ` Trond Myklebust
2016-08-16 1:20 ` Chuck Lever
2016-08-15 20:50 ` [PATCH v1 04/22] SUNRPC: Generalize the RPC buffer release API Chuck Lever
2016-08-15 20:50 ` Chuck Lever [this message]
2016-08-15 20:51 ` [PATCH v1 06/22] SUNRPC: Add a transport-specific private field in rpc_rqst Chuck Lever
2016-08-15 20:51 ` [PATCH v1 07/22] xprtrdma: Initialize separate RPC call and reply buffers Chuck Lever
2016-08-15 20:51 ` [PATCH v1 08/22] xprtrdma: Use smaller buffers for RPC-over-RDMA headers Chuck Lever
2016-08-15 20:51 ` [PATCH v1 09/22] xprtrdma: Replace DMA_BIDIRECTIONAL Chuck Lever
2016-08-15 20:51 ` [PATCH v1 10/22] xprtrdma: Delay DMA mapping Send and Receive buffers Chuck Lever
2016-08-15 20:51 ` [PATCH v1 11/22] xprtrdma: Eliminate "ia" argument in rpcrdma_{alloc, free}_regbuf Chuck Lever
2016-08-15 20:51 ` [PATCH v1 12/22] xprtrdma: Simplify rpcrdma_ep_post_recv() Chuck Lever
2016-08-15 20:52 ` [PATCH v1 13/22] xprtrdma: Move send_wr to struct rpcrdma_req Chuck Lever
2016-08-15 20:52 ` [PATCH v1 14/22] xprtrdma: Move recv_wr to struct rpcrdma_rep Chuck Lever
2016-08-15 20:52 ` [PATCH v1 15/22] xprtrmda: Report address of frmr, not mw Chuck Lever
2016-08-15 20:52 ` [PATCH v1 16/22] rpcrdma: RDMA/CM private message data structure Chuck Lever
2016-08-15 20:52 ` [PATCH v1 17/22] xprtrdma: Client-side support for rpcrdma_connect_private Chuck Lever
2016-08-15 20:52 ` [PATCH v1 18/22] xprtrdma: Basic support for Remote Invalidation Chuck Lever
2016-08-15 20:52 ` [PATCH v1 19/22] xprtrdma: Use gathered Send for large inline messages Chuck Lever
2016-08-15 21:46 ` kbuild test robot
2016-08-15 20:52 ` [PATCH v1 20/22] xprtrdma: Support larger inline thresholds Chuck Lever
2016-08-15 20:53 ` [PATCH v1 21/22] xprtrdma: Rename rpcrdma_receive_wc() Chuck Lever
2016-08-15 20:53 ` [PATCH v1 22/22] xprtrdma: Eliminate rpcrdma_receive_worker() 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=20160815205055.11652.59194.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).