Received-SPF: pass (google.com: domain of linux-nfs-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Subject: [PATCH RFC 4/4] SUNRPC: Send RPC message on TCP with a single
 sock_sendmsg() call
From:   Chuck Lever <cel@kernel.org>
To:     linux-nfs@vger.kernel.org
Cc:     David Howells <dhowells@redhat.com>,
        Chuck Lever <chuck.lever@oracle.com>, dhowells@redhat.com
Date:   Sun, 09 Jul 2023 16:05:18 -0400
Message-ID: <168893311819.1949.12216126239653940727.stgit@manet.1015granger.net>
In-Reply-To: <168893265677.1949.1632048925203798962.stgit@manet.1015granger.net>
References: <168893265677.1949.1632048925203798962.stgit@manet.1015granger.net>
User-Agent: StGit/1.5
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Precedence: bulk

From: Chuck Lever <chuck.lever@oracle.com>

There is now enough infrastructure in place to combine the stream
record marker into the biovec array used to send each outgoing RPC
message. The whole message can be more efficiently sent with a
single call to sock_sendmsg() using a bio_vec iterator.

Note that this also helps with RPC-with-TLS: the TLS implementation
can now clearly see where the upper layer message boundaries are.
Before, it would send each component of the xdr_buf in a separate
TLS record.

Suggested-by: David Howells <dhowells@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svcsock.h |    2 ++
 net/sunrpc/svcsock.c           |   33 ++++++++++++++++++---------------
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 4efae760f3cb..55446136499f 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -38,6 +38,8 @@ struct svc_sock {
 	/* Number of queued send requests */
 	atomic_t		sk_sendqlen;
 
+	struct page_frag_cache  sk_frag_cache;
+
 	struct completion	sk_handshake_done;
 
 	struct bio_vec		sk_recv_bvec[RPCSVC_MAXPAGES]
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 6f672cb0b0b3..19cab73229e4 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1247,29 +1247,28 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 static int svc_tcp_sendmsg(struct svc_sock *svsk, struct xdr_buf *xdr,
 			   rpc_fraghdr marker, unsigned int *sentp)
 {
-	struct kvec rm = {
-		.iov_base	= &marker,
-		.iov_len	= sizeof(marker),
-	};
 	struct msghdr msg = {
-		.msg_flags	= MSG_MORE,
+		.msg_flags	= MSG_SPLICE_PAGES,
 	};
 	unsigned int count;
+	void *tmp;
 	int ret;
 
 	*sentp = 0;
 
-	ret = kernel_sendmsg(svsk->sk_sock, &msg, &rm, 1, rm.iov_len);
-	if (ret < 0)
-		return ret;
-	*sentp += ret;
-	if (ret != rm.iov_len)
-		return -EAGAIN;
-
-	count = svc_sock_xdr_to_bvecs(svsk->sk_send_bvec, xdr);
-	msg.msg_flags = MSG_SPLICE_PAGES;
+	/* The stream record marker is copied into a temporary page
+	 * buffer so that it can be included in sk_send_bvec.
+	 */
+	tmp = page_frag_alloc(&svsk->sk_frag_cache, sizeof(marker),
+			      GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+	memcpy(tmp, &marker, sizeof(marker));
+	bvec_set_virt(svsk->sk_send_bvec, tmp, sizeof(marker));
+
+	count = svc_sock_xdr_to_bvecs(svsk->sk_send_bvec + 1, xdr);
 	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_send_bvec,
-		      count, xdr->len);
+		      1 + count, sizeof(marker) + xdr->len);
 	ret = sock_sendmsg(svsk->sk_sock, &msg);
 	if (ret < 0)
 		return ret;
@@ -1648,6 +1647,7 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt)
 static void svc_sock_free(struct svc_xprt *xprt)
 {
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+	struct page_frag_cache *pfc = &svsk->sk_frag_cache;
 	struct socket *sock = svsk->sk_sock;
 
 	trace_svcsock_free(svsk, sock);
@@ -1657,5 +1657,8 @@ static void svc_sock_free(struct svc_xprt *xprt)
 		sockfd_put(sock);
 	else
 		sock_release(sock);
+	if (pfc->va)
+		__page_frag_cache_drain(virt_to_head_page(pfc->va),
+					pfc->pagecnt_bias);
 	kfree(svsk);
 }