SUNRPC: Send RPC message on TCP with a single sock_sendmsg() call

There is now enough infrastructure in place to combine the stream
record marker into the biovec array used to send each outgoing RPC
message on TCP. 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 (record marker,
head, page payload, tail) in separate TLS records.

Suggested-by: David Howells <[email protected]>
Reviewed-by: David Howells <[email protected]>
Signed-off-by: Chuck Lever <[email protected]>

Author: chucklever

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 page *		sk_pages[RPCSVC_MAXPAGES];	/* received data */

net/sunrpc/svcsock.c

@@ -1213,31 +1213,30 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
 			   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 *buf;
 	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;
+	/* The stream record marker is copied into a temporary page
+	 * fragment buffer so that it can be included in rq_bvec.
+	 */
+	buf = page_frag_alloc(&svsk->sk_frag_cache, sizeof(marker),
+			      GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	memcpy(buf, &marker, sizeof(marker));
+	bvec_set_virt(rqstp->rq_bvec, buf, sizeof(marker));
 
-	count = xdr_buf_to_bvec(rqstp->rq_bvec, ARRAY_SIZE(rqstp->rq_bvec),
-				&rqstp->rq_res);
+	count = xdr_buf_to_bvec(rqstp->rq_bvec + 1,
+				ARRAY_SIZE(rqstp->rq_bvec) - 1, &rqstp->rq_res);
 
-	msg.msg_flags = MSG_SPLICE_PAGES;
 	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
-		      count, rqstp->rq_res.len);
+		      1 + count, sizeof(marker) + rqstp->rq_res.len);
 	ret = sock_sendmsg(svsk->sk_sock, &msg);
 	if (ret < 0)
 		return ret;
@@ -1616,6 +1615,7 @@ 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);
@@ -1625,5 +1625,8 @@ 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);
 }