1 files changed, 608 insertions, 445 deletions

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index a6a060925e5d..d61cd9b40491 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * linux/net/sunrpc/svcsock.c
  *
@@ -35,6 +36,8 @@
 #include <linux/skbuff.h>
 #include <linux/file.h>
 #include <linux/freezer.h>
+#include <linux/bvec.h>
+
 #include <net/sock.h>
 #include <net/checksum.h>
 #include <net/ip.h>
@@ -42,9 +45,12 @@
 #include <net/udp.h>
 #include <net/tcp.h>
 #include <net/tcp_states.h>
+#include <net/tls_prot.h>
+#include <net/handshake.h>
 #include <linux/uaccess.h>
+#include <linux/highmem.h>
 #include <asm/ioctls.h>
-#include <trace/events/skb.h>
+#include <linux/key.h>
 
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/clnt.h>
@@ -54,10 +60,31 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/xprt.h>
 
+#include <trace/events/sock.h>
+#include <trace/events/sunrpc.h>
+
+#include "socklib.h"
 #include "sunrpc.h"
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
+/*
+ * For UDP:
+ * 1 for header page
+ * enough pages for RPCSVC_MAXPAYLOAD_UDP
+ * 1 in case payload is not aligned
+ * 1 for tail page
+ */
+enum {
+	SUNRPC_MAX_UDP_SENDPAGES = 1 + RPCSVC_MAXPAYLOAD_UDP / PAGE_SIZE + 1 + 1
+};
+
+/* To-do: to avoid tying up an nfsd thread while waiting for a
+ * handshake request, the request could instead be deferred.
+ */
+enum {
+	SVC_HANDSHAKE_TO	= 5U * HZ
+};
 
 static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
 					 int flags);
@@ -106,33 +133,28 @@ static void svc_reclassify_socket(struct socket *sock)
 }
 #endif
 
-/*
- * Release an skbuff after use
+/**
+ * svc_tcp_release_ctxt - Release transport-related resources
+ * @xprt: the transport which owned the context
+ * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt
+ *
  */
-static void svc_release_skb(struct svc_rqst *rqstp)
+static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt)
 {
-	struct sk_buff *skb = rqstp->rq_xprt_ctxt;
-
-	if (skb) {
-		struct svc_sock *svsk =
-			container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
-		rqstp->rq_xprt_ctxt = NULL;
-
-		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
-		skb_free_datagram_locked(svsk->sk_sk, skb);
-	}
 }
 
-static void svc_release_udp_skb(struct svc_rqst *rqstp)
+/**
+ * svc_udp_release_ctxt - Release transport-related resources
+ * @xprt: the transport which owned the context
+ * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt
+ *
+ */
+static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt)
 {
-	struct sk_buff *skb = rqstp->rq_xprt_ctxt;
-
-	if (skb) {
-		rqstp->rq_xprt_ctxt = NULL;
+	struct sk_buff *skb = ctxt;
 
-		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
+	if (skb)
 		consume_skb(skb);
-	}
 }
 
 union svc_pktinfo_u {
@@ -173,109 +195,10 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
 	}
 }
 
-/*
- * send routine intended to be shared by the fore- and back-channel
- */
-int svc_send_common(struct socket *sock, struct xdr_buf *xdr,
-		    struct page *headpage, unsigned long headoffset,
-		    struct page *tailpage, unsigned long tailoffset)
-{
-	int		result;
-	int		size;
-	struct page	**ppage = xdr->pages;
-	size_t		base = xdr->page_base;
-	unsigned int	pglen = xdr->page_len;
-	unsigned int	flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
-	int		slen;
-	int		len = 0;
-
-	slen = xdr->len;
-
-	/* send head */
-	if (slen == xdr->head[0].iov_len)
-		flags = 0;
-	len = kernel_sendpage(sock, headpage, headoffset,
-				  xdr->head[0].iov_len, flags);
-	if (len != xdr->head[0].iov_len)
-		goto out;
-	slen -= xdr->head[0].iov_len;
-	if (slen == 0)
-		goto out;
-
-	/* send page data */
-	size = PAGE_SIZE - base < pglen ? PAGE_SIZE - base : pglen;
-	while (pglen > 0) {
-		if (slen == size)
-			flags = 0;
-		result = kernel_sendpage(sock, *ppage, base, size, flags);
-		if (result > 0)
-			len += result;
-		if (result != size)
-			goto out;
-		slen -= size;
-		pglen -= size;
-		size = PAGE_SIZE < pglen ? PAGE_SIZE : pglen;
-		base = 0;
-		ppage++;
-	}
-
-	/* send tail */
-	if (xdr->tail[0].iov_len) {
-		result = kernel_sendpage(sock, tailpage, tailoffset,
-				   xdr->tail[0].iov_len, 0);
-		if (result > 0)
-			len += result;
-	}
-
-out:
-	return len;
-}
-
-
-/*
- * Generic sendto routine
- */
-static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
+static int svc_sock_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+				   unsigned int length)
 {
-	struct svc_sock	*svsk =
-		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
-	struct socket	*sock = svsk->sk_sock;
-	union {
-		struct cmsghdr	hdr;
-		long		all[SVC_PKTINFO_SPACE / sizeof(long)];
-	} buffer;
-	struct cmsghdr *cmh = &buffer.hdr;
-	int		len = 0;
-	unsigned long tailoff;
-	unsigned long headoff;
-	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
-
-	if (rqstp->rq_prot == IPPROTO_UDP) {
-		struct msghdr msg = {
-			.msg_name	= &rqstp->rq_addr,
-			.msg_namelen	= rqstp->rq_addrlen,
-			.msg_control	= cmh,
-			.msg_controllen	= sizeof(buffer),
-			.msg_flags	= MSG_MORE,
-		};
-
-		svc_set_cmsg_data(rqstp, cmh);
-
-		if (sock_sendmsg(sock, &msg) < 0)
-			goto out;
-	}
-
-	tailoff = ((unsigned long)xdr->tail[0].iov_base) & (PAGE_SIZE-1);
-	headoff = 0;
-	len = svc_send_common(sock, xdr, rqstp->rq_respages[0], headoff,
-			       rqstp->rq_respages[0], tailoff);
-
-out:
-	dprintk("svc: socket %p sendto([%p %zu... ], %d) = %d (addr %s)\n",
-		svsk, xdr->head[0].iov_base, xdr->head[0].iov_len,
-		xdr->len, len, svc_print_addr(rqstp, buf, sizeof(buf)));
-
-	return len;
+	return 0;
 }
 
 /*
@@ -315,46 +238,153 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 	return len;
 }
 
+static int
+svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
+			  struct cmsghdr *cmsg, int ret)
+{
+	u8 content_type = tls_get_record_type(sock->sk, cmsg);
+	u8 level, description;
+
+	switch (content_type) {
+	case 0:
+		break;
+	case TLS_RECORD_TYPE_DATA:
+		/* TLS sets EOR at the end of each application data
+		 * record, even though there might be more frames
+		 * waiting to be decrypted.
+		 */
+		msg->msg_flags &= ~MSG_EOR;
+		break;
+	case TLS_RECORD_TYPE_ALERT:
+		tls_alert_recv(sock->sk, msg, &level, &description);
+		ret = (level == TLS_ALERT_LEVEL_FATAL) ?
+			-ENOTCONN : -EAGAIN;
+		break;
+	default:
+		/* discard this record type */
+		ret = -EAGAIN;
+	}
+	return ret;
+}
+
+static int
+svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags)
+{
+	union {
+		struct cmsghdr	cmsg;
+		u8		buf[CMSG_SPACE(sizeof(u8))];
+	} u;
+	u8 alert[2];
+	struct kvec alert_kvec = {
+		.iov_base = alert,
+		.iov_len = sizeof(alert),
+	};
+	struct msghdr msg = {
+		.msg_flags = *msg_flags,
+		.msg_control = &u,
+		.msg_controllen = sizeof(u),
+	};
+	int ret;
+
+	iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
+		      alert_kvec.iov_len);
+	ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT);
+	if (ret > 0 &&
+	    tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
+		iov_iter_revert(&msg.msg_iter, ret);
+		ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN);
+	}
+	return ret;
+}
+
+static int
+svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg)
+{
+	int ret;
+	struct socket *sock = svsk->sk_sock;
+
+	ret = sock_recvmsg(sock, msg, MSG_DONTWAIT);
+	if (msg->msg_flags & MSG_CTRUNC) {
+		msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR);
+		if (ret == 0 || ret == -EIO)
+			ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags);
+	}
+	return ret;
+}
+
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek)
+{
+	struct bvec_iter bi = {
+		.bi_size	= size + seek,
+	};
+	struct bio_vec bv;
+
+	bvec_iter_advance(bvec, &bi, seek & PAGE_MASK);
+	for_each_bvec(bv, bvec, bi, bi)
+		flush_dcache_page(bv.bv_page);
+}
+#else
+static inline void svc_flush_bvec(const struct bio_vec *bvec, size_t size,
+				  size_t seek)
+{
+}
+#endif
+
 /*
- * Generic recvfrom routine.
+ * Read from @rqstp's transport socket. The incoming message fills whole
+ * pages in @rqstp's rq_pages array until the last page of the message
+ * has been received into a partial page.
  */
-static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov,
-			    unsigned int nr, size_t buflen, unsigned int base)
+static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen,
+				size_t seek)
 {
 	struct svc_sock *svsk =
 		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
+	struct bio_vec *bvec = rqstp->rq_bvec;
 	struct msghdr msg = { NULL };
+	unsigned int i;
 	ssize_t len;
-
-	rqstp->rq_xprt_hlen = 0;
+	size_t t;
 
 	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-	iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen);
-	if (base != 0) {
-		iov_iter_advance(&msg.msg_iter, base);
-		buflen -= base;
+
+	for (i = 0, t = 0; t < buflen; i++, t += PAGE_SIZE)
+		bvec_set_page(&bvec[i], rqstp->rq_pages[i], PAGE_SIZE, 0);
+	rqstp->rq_respages = &rqstp->rq_pages[i];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
+	iov_iter_bvec(&msg.msg_iter, ITER_DEST, bvec, i, buflen);
+	if (seek) {
+		iov_iter_advance(&msg.msg_iter, seek);
+		buflen -= seek;
 	}
-	len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT);
+	len = svc_tcp_sock_recvmsg(svsk, &msg);
+	if (len > 0)
+		svc_flush_bvec(bvec, len, seek);
+
 	/* If we read a full record, then assume there may be more
 	 * data to read (stream based sockets only!)
 	 */
 	if (len == buflen)
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
-	dprintk("svc: socket %p recvfrom(%p, %zu) = %zd\n",
-		svsk, iov[0].iov_base, iov[0].iov_len, len);
 	return len;
 }
 
 /*
  * Set socket snd and rcv buffer lengths
  */
-static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
-				unsigned int rcv)
+static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs)
 {
+	unsigned int max_mesg = svsk->sk_xprt.xpt_server->sv_max_mesg;
+	struct socket *sock = svsk->sk_sock;
+
+	nreqs = min(nreqs, INT_MAX / 2 / max_mesg);
+
 	lock_sock(sock->sk);
-	sock->sk->sk_sndbuf = snd * 2;
-	sock->sk->sk_rcvbuf = rcv * 2;
+	sock->sk->sk_sndbuf = nreqs * max_mesg * 2;
+	sock->sk->sk_rcvbuf = nreqs * max_mesg * 2;
 	sock->sk->sk_write_space(sock->sk);
 	release_sock(sock->sk);
 }
@@ -374,14 +404,15 @@ static void svc_data_ready(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 
-	if (svsk) {
-		dprintk("svc: socket %p(inet %p), busy=%d\n",
-			svsk, sk,
-			test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
+	trace_sk_data_ready(sk);
 
+	if (svsk) {
 		/* Refer to svc_setup_socket() for details. */
 		rmb();
 		svsk->sk_odata(sk);
+		trace_svcsock_data_ready(&svsk->sk_xprt, 0);
+		if (test_bit(XPT_HANDSHAKE, &svsk->sk_xprt.xpt_flags))
+			return;
 		if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags))
 			svc_xprt_enqueue(&svsk->sk_xprt);
 	}
@@ -395,11 +426,9 @@ static void svc_write_space(struct sock *sk)
 	struct svc_sock	*svsk = (struct svc_sock *)(sk->sk_user_data);
 
 	if (svsk) {
-		dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
-			svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
-
 		/* Refer to svc_setup_socket() for details. */
 		rmb();
+		trace_svcsock_write_space(&svsk->sk_xprt, 0);
 		svsk->sk_owspace(sk);
 		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
@@ -416,17 +445,91 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt)
 
 static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt)
 {
-	struct svc_sock *svsk;
-	struct socket *sock;
-	struct linger no_linger = {
-		.l_onoff = 1,
-		.l_linger = 0,
+	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+
+	sock_no_linger(svsk->sk_sock->sk);
+}
+
+/**
+ * svc_tcp_handshake_done - Handshake completion handler
+ * @data: address of xprt to wake
+ * @status: status of handshake
+ * @peerid: serial number of key containing the remote peer's identity
+ *
+ * If a security policy is specified as an export option, we don't
+ * have a specific export here to check. So we set a "TLS session
+ * is present" flag on the xprt and let an upper layer enforce local
+ * security policy.
+ */
+static void svc_tcp_handshake_done(void *data, int status, key_serial_t peerid)
+{
+	struct svc_xprt *xprt = data;
+	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+
+	if (!status) {
+		if (peerid != TLS_NO_PEERID)
+			set_bit(XPT_PEER_AUTH, &xprt->xpt_flags);
+		set_bit(XPT_TLS_SESSION, &xprt->xpt_flags);
+	}
+	clear_bit(XPT_HANDSHAKE, &xprt->xpt_flags);
+	complete_all(&svsk->sk_handshake_done);
+}
+
+/**
+ * svc_tcp_handshake - Perform a transport-layer security handshake
+ * @xprt: connected transport endpoint
+ *
+ */
+static void svc_tcp_handshake(struct svc_xprt *xprt)
+{
+	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+	struct sock *sk = svsk->sk_sock->sk;
+	struct tls_handshake_args args = {
+		.ta_sock	= svsk->sk_sock,
+		.ta_done	= svc_tcp_handshake_done,
+		.ta_data	= xprt,
 	};
+	int ret;
+
+	trace_svc_tls_upcall(xprt);
+
+	clear_bit(XPT_TLS_SESSION, &xprt->xpt_flags);
+	init_completion(&svsk->sk_handshake_done);
+
+	ret = tls_server_hello_x509(&args, GFP_KERNEL);
+	if (ret) {
+		trace_svc_tls_not_started(xprt);
+		goto out_failed;
+	}
+
+	ret = wait_for_completion_interruptible_timeout(&svsk->sk_handshake_done,
+							SVC_HANDSHAKE_TO);
+	if (ret <= 0) {
+		if (tls_handshake_cancel(sk)) {
+			trace_svc_tls_timed_out(xprt);
+			goto out_close;
+		}
+	}
 
-	svsk = container_of(xprt, struct svc_sock, sk_xprt);
-	sock = svsk->sk_sock;
-	kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
-			  (char *)&no_linger, sizeof(no_linger));
+	if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags)) {
+		trace_svc_tls_unavailable(xprt);
+		goto out_close;
+	}
+
+	/* Mark the transport ready in case the remote sent RPC
+	 * traffic before the kernel received the handshake
+	 * completion downcall.
+	 */
+	set_bit(XPT_DATA, &xprt->xpt_flags);
+	svc_xprt_enqueue(xprt);
+	return;
+
+out_close:
+	set_bit(XPT_CLOSE, &xprt->xpt_flags);
+out_failed:
+	clear_bit(XPT_HANDSHAKE, &xprt->xpt_flags);
+	set_bit(XPT_DATA, &xprt->xpt_flags);
+	svc_xprt_enqueue(xprt);
 }
 
 /*
@@ -484,8 +587,15 @@ static int svc_udp_get_dest_address(struct svc_rqst *rqstp,
 	return 0;
 }
 
-/*
- * Receive a datagram from a UDP socket.
+/**
+ * svc_udp_recvfrom - Receive a datagram from a UDP socket.
+ * @rqstp: request structure into which to receive an RPC Call
+ *
+ * Called in a loop when XPT_DATA has been set.
+ *
+ * Returns:
+ *   On success, the number of bytes in a received RPC Call, or
+ *   %0 if a complete RPC Call message was not ready to return
  */
 static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 {
@@ -516,25 +626,17 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 	     * provides an upper bound on the number of threads
 	     * which will access the socket.
 	     */
-	    svc_sock_setbufsize(svsk->sk_sock,
-				(serv->sv_nrthreads+3) * serv->sv_max_mesg,
-				(serv->sv_nrthreads+3) * serv->sv_max_mesg);
+	    svc_sock_setbufsize(svsk, serv->sv_nrthreads + 3);
 
 	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-	skb = NULL;
 	err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
 			     0, 0, MSG_PEEK | MSG_DONTWAIT);
-	if (err >= 0)
-		skb = skb_recv_udp(svsk->sk_sk, 0, 1, &err);
-
-	if (skb == NULL) {
-		if (err != -EAGAIN) {
-			/* possibly an icmp error */
-			dprintk("svc: recvfrom returned error %d\n", -err);
-			set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-		}
-		return 0;
-	}
+	if (err < 0)
+		goto out_recv_err;
+	skb = skb_recv_udp(svsk->sk_sk, MSG_DONTWAIT, &err);
+	if (!skb)
+		goto out_recv_err;
+
 	len = svc_addr_len(svc_addr(rqstp));
 	rqstp->rq_addrlen = len;
 	if (skb->tstamp == 0) {
@@ -545,26 +647,21 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 	sock_write_timestamp(svsk->sk_sk, skb->tstamp);
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
 
-	len  = skb->len;
+	len = skb->len;
 	rqstp->rq_arg.len = len;
+	trace_svcsock_udp_recv(&svsk->sk_xprt, len);
 
 	rqstp->rq_prot = IPPROTO_UDP;
 
-	if (!svc_udp_get_dest_address(rqstp, cmh)) {
-		net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n",
-				     cmh->cmsg_level, cmh->cmsg_type);
-		goto out_free;
-	}
+	if (!svc_udp_get_dest_address(rqstp, cmh))
+		goto out_cmsg_err;
 	rqstp->rq_daddrlen = svc_addr_len(svc_daddr(rqstp));
 
 	if (skb_is_nonlinear(skb)) {
 		/* we have to copy */
 		local_bh_disable();
-		if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) {
-			local_bh_enable();
-			/* checksum error */
-			goto out_free;
-		}
+		if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb))
+			goto out_bh_enable;
 		local_bh_enable();
 		consume_skb(skb);
 	} else {
@@ -591,23 +688,89 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 	if (serv->sv_stats)
 		serv->sv_stats->netudpcnt++;
 
+	svc_sock_secure_port(rqstp);
+	svc_xprt_received(rqstp->rq_xprt);
 	return len;
+
+out_recv_err:
+	if (err != -EAGAIN) {
+		/* possibly an icmp error */
+		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+	}
+	trace_svcsock_udp_recv_err(&svsk->sk_xprt, err);
+	goto out_clear_busy;
+out_cmsg_err:
+	net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n",
+			     cmh->cmsg_level, cmh->cmsg_type);
+	goto out_free;
+out_bh_enable:
+	local_bh_enable();
 out_free:
 	kfree_skb(skb);
+out_clear_busy:
+	svc_xprt_received(rqstp->rq_xprt);
 	return 0;
 }
 
-static int
-svc_udp_sendto(struct svc_rqst *rqstp)
+/**
+ * svc_udp_sendto - Send out a reply on a UDP socket
+ * @rqstp: completed svc_rqst
+ *
+ * xpt_mutex ensures @rqstp's whole message is written to the socket
+ * without interruption.
+ *
+ * Returns the number of bytes sent, or a negative errno.
+ */
+static int svc_udp_sendto(struct svc_rqst *rqstp)
 {
-	int		error;
+	struct svc_xprt *xprt = rqstp->rq_xprt;
+	struct svc_sock	*svsk = container_of(xprt, struct svc_sock, sk_xprt);
+	struct xdr_buf *xdr = &rqstp->rq_res;
+	union {
+		struct cmsghdr	hdr;
+		long		all[SVC_PKTINFO_SPACE / sizeof(long)];
+	} buffer;
+	struct cmsghdr *cmh = &buffer.hdr;
+	struct msghdr msg = {
+		.msg_name	= &rqstp->rq_addr,
+		.msg_namelen	= rqstp->rq_addrlen,
+		.msg_control	= cmh,
+		.msg_flags	= MSG_SPLICE_PAGES,
+		.msg_controllen	= sizeof(buffer),
+	};
+	unsigned int count;
+	int err;
+
+	svc_udp_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
+	rqstp->rq_xprt_ctxt = NULL;
+
+	svc_set_cmsg_data(rqstp, cmh);
+
+	mutex_lock(&xprt->xpt_mutex);
+
+	if (svc_xprt_is_dead(xprt))
+		goto out_notconn;
 
-	error = svc_sendto(rqstp, &rqstp->rq_res);
-	if (error == -ECONNREFUSED)
+	count = xdr_buf_to_bvec(svsk->sk_bvec, SUNRPC_MAX_UDP_SENDPAGES, xdr);
+
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
+		      count, rqstp->rq_res.len);
+	err = sock_sendmsg(svsk->sk_sock, &msg);
+	if (err == -ECONNREFUSED) {
 		/* ICMP error on earlier request. */
-		error = svc_sendto(rqstp, &rqstp->rq_res);
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
+			      count, rqstp->rq_res.len);
+		err = sock_sendmsg(svsk->sk_sock, &msg);
+	}
+
+	trace_svcsock_udp_send(xprt, err);
+
+	mutex_unlock(&xprt->xpt_mutex);
+	return err;
 
-	return error;
+out_notconn:
+	mutex_unlock(&xprt->xpt_mutex);
+	return -ENOTCONN;
 }
 
 static int svc_udp_has_wspace(struct svc_xprt *xprt)
@@ -650,12 +813,12 @@ static const struct svc_xprt_ops svc_udp_ops = {
 	.xpo_create = svc_udp_create,
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
-	.xpo_release_rqst = svc_release_udp_skb,
+	.xpo_result_payload = svc_sock_result_payload,
+	.xpo_release_ctxt = svc_udp_release_ctxt,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
 	.xpo_has_wspace = svc_udp_has_wspace,
 	.xpo_accept = svc_udp_accept,
-	.xpo_secure_port = svc_sock_secure_port,
 	.xpo_kill_temp_xprt = svc_udp_kill_temp_xprt,
 };
 
@@ -669,8 +832,6 @@ static struct svc_xprt_class svc_udp_class = {
 
 static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
 {
-	int err, level, optname, one = 1;
-
 	svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class,
 		      &svsk->sk_xprt, serv);
 	clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
@@ -681,30 +842,24 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	 * receive and respond to one request.
 	 * svc_udp_recvfrom will re-adjust if necessary
 	 */
-	svc_sock_setbufsize(svsk->sk_sock,
-			    3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
-			    3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
+	svc_sock_setbufsize(svsk, 3);
 
 	/* data might have come in before data_ready set up */
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 	set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
+	set_bit(XPT_RPCB_UNREG, &svsk->sk_xprt.xpt_flags);
 
 	/* make sure we get destination address info */
 	switch (svsk->sk_sk->sk_family) {
 	case AF_INET:
-		level = SOL_IP;
-		optname = IP_PKTINFO;
+		ip_sock_set_pktinfo(svsk->sk_sock->sk);
 		break;
 	case AF_INET6:
-		level = SOL_IPV6;
-		optname = IPV6_RECVPKTINFO;
+		ip6_sock_set_recvpktinfo(svsk->sk_sock->sk);
 		break;
 	default:
 		BUG();
 	}
-	err = kernel_setsockopt(svsk->sk_sock, level, optname,
-					(char *)&one, sizeof(one));
-	dprintk("svc: kernel_setsockopt returned %d\n", err);
 }
 
 /*
@@ -715,14 +870,7 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 
-	dprintk("svc: socket %p TCP (listen) state change %d\n",
-		sk, sk->sk_state);
-
-	if (svsk) {
-		/* Refer to svc_setup_socket() for details. */
-		rmb();
-		svsk->sk_odata(sk);
-	}
+	trace_sk_data_ready(sk);
 
 	/*
 	 * This callback may called twice when a new connection
@@ -732,14 +880,18 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
 	 *    when one of child sockets become ESTABLISHED.
 	 * 2) data_ready method of the child socket may be called
 	 *    when it receives data before the socket is accepted.
-	 * In case of 2, we should ignore it silently.
+	 * In case of 2, we should ignore it silently and DO NOT
+	 * dereference svsk.
 	 */
-	if (sk->sk_state == TCP_LISTEN) {
-		if (svsk) {
-			set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
-			svc_xprt_enqueue(&svsk->sk_xprt);
-		} else
-			printk("svc: socket %p: no user data\n", sk);
+	if (sk->sk_state != TCP_LISTEN)
+		return;
+
+	if (svsk) {
+		/* Refer to svc_setup_socket() for details. */
+		rmb();
+		svsk->sk_odata(sk);
+		set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
+		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
 }
 
@@ -750,19 +902,13 @@ static void svc_tcp_state_change(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 
-	dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n",
-		sk, sk->sk_state, sk->sk_user_data);
-
-	if (!svsk)
-		printk("svc: socket %p: no user data\n", sk);
-	else {
+	if (svsk) {
 		/* Refer to svc_setup_socket() for details. */
 		rmb();
 		svsk->sk_ostate(sk);
-		if (sk->sk_state != TCP_ESTABLISHED) {
-			set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
-			svc_xprt_enqueue(&svsk->sk_xprt);
-		}
+		trace_svcsock_tcp_state(&svsk->sk_xprt, svsk->sk_sock);
+		if (sk->sk_state != TCP_ESTABLISHED)
+			svc_xprt_deferred_close(&svsk->sk_xprt);
 	}
 }
 
@@ -779,45 +925,29 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	struct socket	*newsock;
 	struct svc_sock	*newsvsk;
 	int		err, slen;
-	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
 
-	dprintk("svc: tcp_accept %p sock %p\n", svsk, sock);
 	if (!sock)
 		return NULL;
 
 	clear_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
 	err = kernel_accept(sock, &newsock, O_NONBLOCK);
 	if (err < 0) {
-		if (err == -ENOMEM)
-			printk(KERN_WARNING "%s: no more sockets!\n",
-			       serv->sv_name);
-		else if (err != -EAGAIN)
-			net_warn_ratelimited("%s: accept failed (err %d)!\n",
-					     serv->sv_name, -err);
+		if (err != -EAGAIN)
+			trace_svcsock_accept_err(xprt, serv->sv_name, err);
 		return NULL;
 	}
+	if (IS_ERR(sock_alloc_file(newsock, O_NONBLOCK, NULL)))
+		return NULL;
+
 	set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
 
 	err = kernel_getpeername(newsock, sin);
 	if (err < 0) {
-		net_warn_ratelimited("%s: peername failed (err %d)!\n",
-				     serv->sv_name, -err);
+		trace_svcsock_getpeername_err(xprt, serv->sv_name, err);
 		goto failed;		/* aborted connection or whatever */
 	}
 	slen = err;
 
-	/* Ideally, we would want to reject connections from unauthorized
-	 * hosts here, but when we get encryption, the IP of the host won't
-	 * tell us anything.  For now just warn about unpriv connections.
-	 */
-	if (!svc_port_is_privileged(sin)) {
-		dprintk("%s: connect from unprivileged port: %s\n",
-			serv->sv_name,
-			__svc_print_addr(sin, buf, sizeof(buf)));
-	}
-	dprintk("%s: connect from %s\n", serv->sv_name,
-		__svc_print_addr(sin, buf, sizeof(buf)));
-
 	/* Reset the inherited callbacks before calling svc_setup_socket */
 	newsock->sk->sk_state_change = svsk->sk_ostate;
 	newsock->sk->sk_data_ready = svsk->sk_odata;
@@ -835,10 +965,8 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen);
 	err = kernel_getsockname(newsock, sin);
 	slen = err;
-	if (unlikely(err < 0)) {
-		dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err);
+	if (unlikely(err < 0))
 		slen = offsetof(struct sockaddr, sa_data);
-	}
 	svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen);
 
 	if (sock_is_loopback(newsock->sk))
@@ -851,17 +979,18 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	return &newsvsk->sk_xprt;
 
 failed:
-	sock_release(newsock);
+	sockfd_put(newsock);
 	return NULL;
 }
 
-static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
+static size_t svc_tcp_restore_pages(struct svc_sock *svsk,
+				    struct svc_rqst *rqstp)
 {
-	unsigned int i, len, npages;
+	size_t len = svsk->sk_datalen;
+	unsigned int i, npages;
 
-	if (svsk->sk_datalen == 0)
+	if (!len)
 		return 0;
-	len = svsk->sk_datalen;
 	npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	for (i = 0; i < npages; i++) {
 		if (rqstp->rq_pages[i] != NULL)
@@ -910,47 +1039,46 @@ out:
 }
 
 /*
- * Receive fragment record header.
- * If we haven't gotten the record length yet, get the next four bytes.
+ * Receive fragment record header into sk_marker.
  */
-static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
+static ssize_t svc_tcp_read_marker(struct svc_sock *svsk,
+				   struct svc_rqst *rqstp)
 {
-	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
-	unsigned int want;
-	int len;
+	ssize_t want, len;
 
+	/* If we haven't gotten the record length yet,
+	 * get the next four bytes.
+	 */
 	if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
+		struct msghdr	msg = { NULL };
 		struct kvec	iov;
 
 		want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
-		iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
+		iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen;
 		iov.iov_len  = want;
-		len = svc_recvfrom(rqstp, &iov, 1, want, 0);
+		iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want);
+		len = svc_tcp_sock_recvmsg(svsk, &msg);
 		if (len < 0)
-			goto error;
+			return len;
 		svsk->sk_tcplen += len;
-
 		if (len < want) {
-			dprintk("svc: short recvfrom while reading record "
-				"length (%d of %d)\n", len, want);
-			return -EAGAIN;
+			/* call again to read the remaining bytes */
+			goto err_short;
 		}
-
-		dprintk("svc: TCP record, %d bytes\n", svc_sock_reclen(svsk));
+		trace_svcsock_marker(&svsk->sk_xprt, svsk->sk_marker);
 		if (svc_sock_reclen(svsk) + svsk->sk_datalen >
-							serv->sv_max_mesg) {
-			net_notice_ratelimited("RPC: fragment too large: %d\n",
-					svc_sock_reclen(svsk));
-			goto err_delete;
-		}
+		    svsk->sk_xprt.xpt_server->sv_max_mesg)
+			goto err_too_large;
 	}
-
 	return svc_sock_reclen(svsk);
-error:
-	dprintk("RPC: TCP recv_record got %d\n", len);
-	return len;
-err_delete:
-	set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+
+err_too_large:
+	net_notice_ratelimited("svc: %s oversized RPC fragment (%u octets) from %pISpc\n",
+			       svsk->sk_xprt.xpt_server->sv_name,
+			       svc_sock_reclen(svsk),
+			       (struct sockaddr *)&svsk->sk_xprt.xpt_remote);
+	svc_xprt_deferred_close(&svsk->sk_xprt);
+err_short:
 	return -EAGAIN;
 }
 
@@ -960,18 +1088,14 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	struct rpc_rqst *req = NULL;
 	struct kvec *src, *dst;
 	__be32 *p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
-	__be32 xid;
-	__be32 calldir;
-
-	xid = *p++;
-	calldir = *p;
+	__be32 xid = *p;
 
 	if (!bc_xprt)
 		return -EAGAIN;
 	spin_lock(&bc_xprt->queue_lock);
 	req = xprt_lookup_rqst(bc_xprt, xid);
 	if (!req)
-		goto unlock_notfound;
+		goto unlock_eagain;
 
 	memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));
 	/*
@@ -988,98 +1112,63 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	rqstp->rq_arg.len = 0;
 	spin_unlock(&bc_xprt->queue_lock);
 	return 0;
-unlock_notfound:
-	printk(KERN_NOTICE
-		"%s: Got unrecognized reply: "
-		"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
-		__func__, ntohl(calldir),
-		bc_xprt, ntohl(xid));
 unlock_eagain:
 	spin_unlock(&bc_xprt->queue_lock);
 	return -EAGAIN;
 }
 
-static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
-{
-	int i = 0;
-	int t = 0;
-
-	while (t < len) {
-		vec[i].iov_base = page_address(pages[i]);
-		vec[i].iov_len = PAGE_SIZE;
-		i++;
-		t += PAGE_SIZE;
-	}
-	return i;
-}
-
 static void svc_tcp_fragment_received(struct svc_sock *svsk)
 {
 	/* If we have more data, signal svc_xprt_enqueue() to try again */
-	dprintk("svc: TCP %s record (%d bytes)\n",
-		svc_sock_final_rec(svsk) ? "final" : "nonfinal",
-		svc_sock_reclen(svsk));
 	svsk->sk_tcplen = 0;
-	svsk->sk_reclen = 0;
+	svsk->sk_marker = xdr_zero;
 }
 
-/*
- * Receive data from a TCP socket.
+/**
+ * svc_tcp_recvfrom - Receive data from a TCP socket
+ * @rqstp: request structure into which to receive an RPC Call
+ *
+ * Called in a loop when XPT_DATA has been set.
+ *
+ * Read the 4-byte stream record marker, then use the record length
+ * in that marker to set up exactly the resources needed to receive
+ * the next RPC message into @rqstp.
+ *
+ * Returns:
+ *   On success, the number of bytes in a received RPC Call, or
+ *   %0 if a complete RPC Call message was not ready to return
+ *
+ * The zero return case handles partial receives and callback Replies.
+ * The state of a partial receive is preserved in the svc_sock for
+ * the next call to svc_tcp_recvfrom.
  */
 static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 {
 	struct svc_sock	*svsk =
 		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
 	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
-	int		len;
-	struct kvec *vec;
-	unsigned int want, base;
+	size_t want, base;
+	ssize_t len;
 	__be32 *p;
 	__be32 calldir;
-	int pnum;
-
-	dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
-		svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
-		test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
-		test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
 
-	len = svc_tcp_recv_record(svsk, rqstp);
+	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+	len = svc_tcp_read_marker(svsk, rqstp);
 	if (len < 0)
 		goto error;
 
 	base = svc_tcp_restore_pages(svsk, rqstp);
-	want = svc_sock_reclen(svsk) - (svsk->sk_tcplen - sizeof(rpc_fraghdr));
-
-	vec = rqstp->rq_vec;
-
-	pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], base + want);
-
-	rqstp->rq_respages = &rqstp->rq_pages[pnum];
-	rqstp->rq_next_page = rqstp->rq_respages + 1;
-
-	/* Now receive data */
-	len = svc_recvfrom(rqstp, vec, pnum, base + want, base);
+	want = len - (svsk->sk_tcplen - sizeof(rpc_fraghdr));
+	len = svc_tcp_read_msg(rqstp, base + want, base);
 	if (len >= 0) {
+		trace_svcsock_tcp_recv(&svsk->sk_xprt, len);
 		svsk->sk_tcplen += len;
 		svsk->sk_datalen += len;
 	}
-	if (len != want || !svc_sock_final_rec(svsk)) {
-		svc_tcp_save_pages(svsk, rqstp);
-		if (len < 0 && len != -EAGAIN)
-			goto err_delete;
-		if (len == want)
-			svc_tcp_fragment_received(svsk);
-		else
-			dprintk("svc: incomplete TCP record (%d of %d)\n",
-				(int)(svsk->sk_tcplen - sizeof(rpc_fraghdr)),
-				svc_sock_reclen(svsk));
-		goto err_noclose;
-	}
-
-	if (svsk->sk_datalen < 8) {
-		svsk->sk_datalen = 0;
-		goto err_delete; /* client is nuts. */
-	}
+	if (len != want || !svc_sock_final_rec(svsk))
+		goto err_incomplete;
+	if (svsk->sk_datalen < 8)
+		goto err_nuts;
 
 	rqstp->rq_arg.len = svsk->sk_datalen;
 	rqstp->rq_arg.page_base = 0;
@@ -1112,50 +1201,113 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 	if (serv->sv_stats)
 		serv->sv_stats->nettcpcnt++;
 
+	svc_sock_secure_port(rqstp);
+	svc_xprt_received(rqstp->rq_xprt);
 	return rqstp->rq_arg.len;
 
+err_incomplete:
+	svc_tcp_save_pages(svsk, rqstp);
+	if (len < 0 && len != -EAGAIN)
+		goto err_delete;
+	if (len == want)
+		svc_tcp_fragment_received(svsk);
+	else
+		trace_svcsock_tcp_recv_short(&svsk->sk_xprt,
+				svc_sock_reclen(svsk),
+				svsk->sk_tcplen - sizeof(rpc_fraghdr));
+	goto err_noclose;
 error:
 	if (len != -EAGAIN)
 		goto err_delete;
-	dprintk("RPC: TCP recvfrom got EAGAIN\n");
-	return 0;
+	trace_svcsock_tcp_recv_eagain(&svsk->sk_xprt, 0);
+	goto err_noclose;
+err_nuts:
+	svsk->sk_datalen = 0;
 err_delete:
-	printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
-	       svsk->sk_xprt.xpt_server->sv_name, -len);
-	set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+	trace_svcsock_tcp_recv_err(&svsk->sk_xprt, len);
+	svc_xprt_deferred_close(&svsk->sk_xprt);
 err_noclose:
+	svc_xprt_received(rqstp->rq_xprt);
 	return 0;	/* record not complete */
 }
 
 /*
- * Send out data on TCP socket.
+ * MSG_SPLICE_PAGES is used exclusively to reduce the number of
+ * copy operations in this path. Therefore the caller must ensure
+ * that the pages backing @xdr are unchanging.
+ */
+static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
+			   rpc_fraghdr marker)
+{
+	struct msghdr msg = {
+		.msg_flags	= MSG_SPLICE_PAGES,
+	};
+	unsigned int count;
+	void *buf;
+	int ret;
+
+	/* The stream record marker is copied into a temporary page
+	 * fragment buffer so that it can be included in sk_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(svsk->sk_bvec, buf, sizeof(marker));
+
+	count = xdr_buf_to_bvec(svsk->sk_bvec + 1, rqstp->rq_maxpages,
+				&rqstp->rq_res);
+
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, svsk->sk_bvec,
+		      1 + count, sizeof(marker) + rqstp->rq_res.len);
+	ret = sock_sendmsg(svsk->sk_sock, &msg);
+	page_frag_free(buf);
+	return ret;
+}
+
+/**
+ * svc_tcp_sendto - Send out a reply on a TCP socket
+ * @rqstp: completed svc_rqst
+ *
+ * xpt_mutex ensures @rqstp's whole message is written to the socket
+ * without interruption.
+ *
+ * Returns the number of bytes sent, or a negative errno.
  */
 static int svc_tcp_sendto(struct svc_rqst *rqstp)
 {
-	struct xdr_buf	*xbufp = &rqstp->rq_res;
+	struct svc_xprt *xprt = rqstp->rq_xprt;
+	struct svc_sock	*svsk = container_of(xprt, struct svc_sock, sk_xprt);
+	struct xdr_buf *xdr = &rqstp->rq_res;
+	rpc_fraghdr marker = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT |
+					 (u32)xdr->len);
 	int sent;
-	__be32 reclen;
 
-	/* Set up the first element of the reply kvec.
-	 * Any other kvecs that may be in use have been taken
-	 * care of by the server implementation itself.
-	 */
-	reclen = htonl(0x80000000|((xbufp->len ) - 4));
-	memcpy(xbufp->head[0].iov_base, &reclen, 4);
-
-	sent = svc_sendto(rqstp, &rqstp->rq_res);
-	if (sent != xbufp->len) {
-		printk(KERN_NOTICE
-		       "rpc-srv/tcp: %s: %s %d when sending %d bytes "
-		       "- shutting down socket\n",
-		       rqstp->rq_xprt->xpt_server->sv_name,
-		       (sent<0)?"got error":"sent only",
-		       sent, xbufp->len);
-		set_bit(XPT_CLOSE, &rqstp->rq_xprt->xpt_flags);
-		svc_xprt_enqueue(rqstp->rq_xprt);
-		sent = -EAGAIN;
-	}
+	svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
+	rqstp->rq_xprt_ctxt = NULL;
+
+	mutex_lock(&xprt->xpt_mutex);
+	if (svc_xprt_is_dead(xprt))
+		goto out_notconn;
+	sent = svc_tcp_sendmsg(svsk, rqstp, marker);
+	trace_svcsock_tcp_send(xprt, sent);
+	if (sent < 0 || sent != (xdr->len + sizeof(marker)))
+		goto out_close;
+	mutex_unlock(&xprt->xpt_mutex);
 	return sent;
+
+out_notconn:
+	mutex_unlock(&xprt->xpt_mutex);
+	return -ENOTCONN;
+out_close:
+	pr_notice("rpc-srv/tcp: %s: %s %d when sending %zu bytes - shutting down socket\n",
+		  xprt->xpt_server->sv_name,
+		  (sent < 0) ? "got error" : "sent",
+		  sent, xdr->len + sizeof(marker));
+	svc_xprt_deferred_close(xprt);
+	mutex_unlock(&xprt->xpt_mutex);
+	return -EAGAIN;
 }
 
 static struct svc_xprt *svc_tcp_create(struct svc_serv *serv,
@@ -1170,13 +1322,14 @@ static const struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_create = svc_tcp_create,
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
-	.xpo_release_rqst = svc_release_skb,
+	.xpo_result_payload = svc_sock_result_payload,
+	.xpo_release_ctxt = svc_tcp_release_ctxt,
 	.xpo_detach = svc_tcp_sock_detach,
 	.xpo_free = svc_sock_free,
 	.xpo_has_wspace = svc_tcp_has_wspace,
 	.xpo_accept = svc_tcp_accept,
-	.xpo_secure_port = svc_sock_secure_port,
 	.xpo_kill_temp_xprt = svc_tcp_kill_temp_xprt,
+	.xpo_handshake = svc_tcp_handshake,
 };
 
 static struct svc_xprt_class svc_tcp_class = {
@@ -1208,23 +1361,23 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 	set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
 	set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags);
 	if (sk->sk_state == TCP_LISTEN) {
-		dprintk("setting up TCP socket for listening\n");
 		strcpy(svsk->sk_xprt.xpt_remotebuf, "listener");
 		set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
+		set_bit(XPT_RPCB_UNREG, &svsk->sk_xprt.xpt_flags);
 		sk->sk_data_ready = svc_tcp_listen_data_ready;
 		set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
 	} else {
-		dprintk("setting up TCP socket for reading\n");
 		sk->sk_state_change = svc_tcp_state_change;
 		sk->sk_data_ready = svc_data_ready;
 		sk->sk_write_space = svc_write_space;
 
-		svsk->sk_reclen = 0;
+		svsk->sk_marker = xdr_zero;
 		svsk->sk_tcplen = 0;
 		svsk->sk_datalen = 0;
-		memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
+		memset(&svsk->sk_pages[0], 0,
+		       svsk->sk_maxpages * sizeof(struct page *));
 
-		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
+		tcp_sock_set_nodelay(sk);
 
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		switch (sk->sk_state) {
@@ -1232,7 +1385,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 		case TCP_ESTABLISHED:
 			break;
 		default:
-			set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+			svc_xprt_deferred_close(&svsk->sk_xprt);
 		}
 	}
 }
@@ -1250,7 +1403,20 @@ void svc_sock_update_bufs(struct svc_serv *serv)
 		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
 	spin_unlock_bh(&serv->sv_lock);
 }
-EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
+
+static int svc_sock_sendpages(struct svc_serv *serv, struct socket *sock, int flags)
+{
+	switch (sock->type) {
+	case SOCK_STREAM:
+		/* +1 for TCP record marker */
+		if (flags & SVC_SOCK_TEMPORARY)
+			return svc_serv_maxpages(serv) + 1;
+		return 0;
+	case SOCK_DGRAM:
+		return SUNRPC_MAX_UDP_SENDPAGES;
+	}
+	return -EINVAL;
+}
 
 /*
  * Initialize socket for RPC use and create svc_sock struct
@@ -1262,24 +1428,41 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	struct svc_sock	*svsk;
 	struct sock	*inet;
 	int		pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
-	int		err = 0;
+	int		sendpages;
+	unsigned long	pages;
 
-	dprintk("svc: svc_setup_socket %p\n", sock);
-	svsk = kzalloc(sizeof(*svsk), GFP_KERNEL);
+	sendpages = svc_sock_sendpages(serv, sock, flags);
+	if (sendpages < 0)
+		return ERR_PTR(sendpages);
+
+	pages = svc_serv_maxpages(serv);
+	svsk = kzalloc(struct_size(svsk, sk_pages, pages), GFP_KERNEL);
 	if (!svsk)
 		return ERR_PTR(-ENOMEM);
 
+	if (sendpages) {
+		svsk->sk_bvec = kcalloc(sendpages, sizeof(*svsk->sk_bvec), GFP_KERNEL);
+		if (!svsk->sk_bvec) {
+			kfree(svsk);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
+	svsk->sk_maxpages = pages;
+
 	inet = sock->sk;
 
-	/* Register socket with portmapper */
-	if (pmap_register)
+	if (pmap_register) {
+		int err;
+
 		err = svc_register(serv, sock_net(sock->sk), inet->sk_family,
 				     inet->sk_protocol,
 				     ntohs(inet_sk(inet)->inet_sport));
-
-	if (err < 0) {
-		kfree(svsk);
-		return ERR_PTR(err);
+		if (err < 0) {
+			kfree(svsk->sk_bvec);
+			kfree(svsk);
+			return ERR_PTR(err);
+		}
 	}
 
 	svsk->sk_sock = sock;
@@ -1289,7 +1472,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	svsk->sk_owspace = inet->sk_write_space;
 	/*
 	 * This barrier is necessary in order to prevent race condition
-	 * with svc_data_ready(), svc_listen_data_ready() and others
+	 * with svc_data_ready(), svc_tcp_listen_data_ready(), and others
 	 * when calling callbacks above.
 	 */
 	wmb();
@@ -1301,44 +1484,25 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	else
 		svc_tcp_init(svsk, serv);
 
-	dprintk("svc: svc_setup_socket created %p (inet %p), "
-			"listen %d close %d\n",
-			svsk, svsk->sk_sk,
-			test_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags),
-			test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
-
+	trace_svcsock_new(svsk, sock);
 	return svsk;
 }
 
-bool svc_alien_sock(struct net *net, int fd)
-{
-	int err;
-	struct socket *sock = sockfd_lookup(fd, &err);
-	bool ret = false;
-
-	if (!sock)
-		goto out;
-	if (sock_net(sock->sk) != net)
-		ret = true;
-	sockfd_put(sock);
-out:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(svc_alien_sock);
-
 /**
  * svc_addsock - add a listener socket to an RPC service
  * @serv: pointer to RPC service to which to add a new listener
+ * @net: caller's network namespace
  * @fd: file descriptor of the new listener
  * @name_return: pointer to buffer to fill in with name of listener
  * @len: size of the buffer
+ * @cred: credential
  *
  * Fills in socket name and returns positive length of name if successful.
  * Name is terminated with '\n'.  On error, returns a negative errno
  * value.
  */
-int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
-		const size_t len)
+int svc_addsock(struct svc_serv *serv, struct net *net, const int fd,
+		char *name_return, const size_t len, const struct cred *cred)
 {
 	int err = 0;
 	struct socket *so = sockfd_lookup(fd, &err);
@@ -1349,6 +1513,9 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
 
 	if (!so)
 		return err;
+	err = -EINVAL;
+	if (sock_net(so->sk) != net)
+		goto out;
 	err = -EAFNOSUPPORT;
 	if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6))
 		goto out;
@@ -1371,6 +1538,7 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
 	salen = kernel_getsockname(svsk->sk_sock, sin);
 	if (salen >= 0)
 		svc_xprt_set_local(&svsk->sk_xprt, sin, salen);
+	svsk->sk_xprt.xpt_cred = get_cred(cred);
 	svc_add_new_perm_xprt(serv, &svsk->sk_xprt);
 	return svc_one_sock_name(svsk, name_return, len);
 out:
@@ -1396,12 +1564,6 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 	struct sockaddr *newsin = (struct sockaddr *)&addr;
 	int		newlen;
 	int		family;
-	int		val;
-	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
-
-	dprintk("svc: svc_create_socket(%s, %d, %s)\n",
-			serv->sv_program->pg_name, protocol,
-			__svc_print_addr(sin, buf, sizeof(buf)));
 
 	if (protocol != IPPROTO_UDP && protocol != IPPROTO_TCP) {
 		printk(KERN_WARNING "svc: only UDP and TCP "
@@ -1432,14 +1594,11 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 	 * getting requests from IPv4 remotes.  Those should
 	 * be shunted to a PF_INET listener via rpcbind.
 	 */
-	val = 1;
 	if (family == PF_INET6)
-		kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
-					(char *)&val, sizeof(val));
-
+		ip6_sock_set_v6only(sock->sk);
 	if (type == SOCK_STREAM)
 		sock->sk->sk_reuse = SK_CAN_REUSE; /* allow address reuse */
-	error = kernel_bind(sock, sin, len);
+	error = kernel_bind(sock, (struct sockaddr_unsized *)sin, len);
 	if (error < 0)
 		goto bummer;
 
@@ -1449,7 +1608,8 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 	newlen = error;
 
 	if (protocol == IPPROTO_TCP) {
-		if ((error = kernel_listen(sock, 64)) < 0)
+		sk_net_refcnt_upgrade(sock->sk);
+		if ((error = kernel_listen(sock, SOMAXCONN)) < 0)
 			goto bummer;
 	}
 
@@ -1461,7 +1621,6 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 	svc_xprt_set_local(&svsk->sk_xprt, newsin, newlen);
 	return (struct svc_xprt *)svsk;
 bummer:
-	dprintk("svc: svc_create_socket error = %d\n", -error);
 	sock_release(sock);
 	return ERR_PTR(error);
 }
@@ -1475,8 +1634,6 @@ static void svc_sock_detach(struct svc_xprt *xprt)
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
 	struct sock *sk = svsk->sk_sk;
 
-	dprintk("svc: svc_sock_detach(%p)\n", svsk);
-
 	/* put back the old socket callbacks */
 	lock_sock(sk);
 	sk->sk_state_change = svsk->sk_ostate;
@@ -1493,7 +1650,7 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt)
 {
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
 
-	dprintk("svc: svc_tcp_sock_detach(%p)\n", svsk);
+	tls_handshake_close(svsk->sk_sock);
 
 	svc_sock_detach(xprt);
 
@@ -1509,11 +1666,17 @@ 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);
-	dprintk("svc: svc_sock_free(%p)\n", svsk);
+	struct socket *sock = svsk->sk_sock;
 
-	if (svsk->sk_sock->file)
-		sockfd_put(svsk->sk_sock);
+	trace_svcsock_free(svsk, sock);
+
+	tls_handshake_cancel(sock->sk);
+	if (sock->file)
+		sockfd_put(sock);
 	else
-		sock_release(svsk->sk_sock);
+		sock_release(sock);
+
+	page_frag_cache_drain(&svsk->sk_frag_cache);
+	kfree(svsk->sk_bvec);
 	kfree(svsk);
 }