[PATCH] net-tcp: TCP/IP stack bypass for loopback connections

@@ -332,6 +332,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
  *	@_skb_refdst: destination entry (with norefcount bit)
  *	@sp: the security path, used for xfrm
+ *	@friend: loopback friend socket
  *	@len: Length of actual data
  *	@data_len: Data length
  *	@mac_len: Length of link layer header

@@ -407,6 +408,7 @@ struct sk_buff {
 #ifdef CONFIG_XFRM
 	struct	sec_path	*sp;
 #endif
+	struct sock		*friend;
 	unsigned int		len,
 				data_len;
 	__u16			mac_len,

@@ -63,6 +63,7 @@ struct request_sock {
 	unsigned long			expires;
 	const struct request_sock_ops	*rsk_ops;
 	struct sock			*sk;
+	struct sock			*friend;
 	u32				secid;
 	u32				peer_secid;
 };

@@ -197,6 +197,7 @@ struct cg_proto;
   *	@sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
   *	@sk_lock:	synchronizer
   *	@sk_rcvbuf: size of receive buffer in bytes
+  *	@sk_friend: loopback friend socket
   *	@sk_wq: sock wait queue and async head
   *	@sk_rx_dst: receive input route used by early tcp demux
   *	@sk_dst_cache: destination cache

@@ -286,6 +287,14 @@ struct sock {
 	socket_lock_t		sk_lock;
 	struct sk_buff_head	sk_receive_queue;
 	/*
+	 * If socket has a friend (sk_friend != NULL) then a send skb is
+	 * enqueued directly to the friend's sk_receive_queue such that:
+	 *
+	 *        sk_sndbuf -> sk_sndbuf + sk_friend->sk_rcvbuf
+	 *   sk_wmem_queued -> sk_friend->sk_rmem_alloc
+	 */
+	struct sock		*sk_friend;
+	/*
 	 * The backlog queue is special, it is always used with
 	 * the per-socket spinlock held and requires low latency
 	 * access. Therefore we special case it's implementation.

@@ -673,24 +682,40 @@ static inline bool sk_acceptq_is_full(const struct sock *sk)
 	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
 }
 
+static inline int sk_wmem_queued_get(const struct sock *sk)
+{
+	if (sk->sk_friend)
+		return atomic_read(&sk->sk_friend->sk_rmem_alloc);
+	else
+		return sk->sk_wmem_queued;
+}
+
+static inline int sk_sndbuf_get(const struct sock *sk)
+{
+	if (sk->sk_friend)
+		return sk->sk_sndbuf + sk->sk_friend->sk_rcvbuf;
+	else
+		return sk->sk_sndbuf;
+}
+
 /*
  * Compute minimal free write space needed to queue new packets.
  */
 static inline int sk_stream_min_wspace(const struct sock *sk)
 {
-	return sk->sk_wmem_queued >> 1;
+	return sk_wmem_queued_get(sk) >> 1;
 }
 
 static inline int sk_stream_wspace(const struct sock *sk)
 {
-	return sk->sk_sndbuf - sk->sk_wmem_queued;
+	return sk_sndbuf_get(sk) - sk_wmem_queued_get(sk);
 }
 
 extern void sk_stream_write_space(struct sock *sk);
 
 static inline bool sk_stream_memory_free(const struct sock *sk)
 {
-	return sk->sk_wmem_queued < sk->sk_sndbuf;
+	return sk_wmem_queued_get(sk) < sk_sndbuf_get(sk);
 }
 
 /* OOB backlog add */

@@ -794,6 +819,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
 	})
 
 extern int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
+extern int sk_stream_wait_friend(struct sock *sk, long *timeo_p);
 extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
 extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
 extern int sk_stream_error(struct sock *sk, int flags, int err);

@@ -253,6 +253,7 @@ extern int sysctl_tcp_cookie_size;
 extern int sysctl_tcp_thin_linear_timeouts;
 extern int sysctl_tcp_thin_dupack;
 extern int sysctl_tcp_early_retrans;
+extern int sysctl_tcp_friends;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;

@@ -978,7 +979,7 @@ static inline bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (sysctl_tcp_low_latency || !tp->ucopy.task)
+	if (sysctl_tcp_low_latency || !tp->ucopy.task || sk->sk_friend)
 		return false;
 
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);

@@ -634,6 +634,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif
+	new->friend		= old->friend;
 	memcpy(new->cb, old->cb, sizeof(old->cb));
 	new->csum		= old->csum;
 	new->local_df		= old->local_df;

@@ -2078,6 +2078,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 #ifdef CONFIG_NET_DMA
 	skb_queue_head_init(&sk->sk_async_wait_queue);
 #endif
+	sk->sk_friend		=	NULL;
 
 	sk->sk_send_head	=	NULL;
 

@@ -83,6 +83,42 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
 EXPORT_SYMBOL(sk_stream_wait_connect);
 
 /**
+ * sk_stream_wait_friend - Wait for a socket to make friends
+ * @sk: sock to wait on
+ * @timeo_p: for how long to wait
+ *
+ * Must be called with the socket locked.
+ */
+int sk_stream_wait_friend(struct sock *sk, long *timeo_p)
+{
+	struct task_struct *tsk = current;
+	DEFINE_WAIT(wait);
+	int done;
+
+	do {
+		int err = sock_error(sk);
+		if (err)
+			return err;
+		if (!sk->sk_friend)
+			return -EBADFD;
+		if (!*timeo_p)
+			return -EAGAIN;
+		if (signal_pending(tsk))
+			return sock_intr_errno(*timeo_p);
+
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		sk->sk_write_pending++;
+		done = sk_wait_event(sk, timeo_p,
+				     !sk->sk_err &&
+				     sk->sk_friend->sk_friend);
+		finish_wait(sk_sleep(sk), &wait);
+		sk->sk_write_pending--;
+	} while (!done);
+	return 0;
+}
+EXPORT_SYMBOL(sk_stream_wait_friend);
+
+/**
  * sk_stream_closing - Return 1 if we still have things to send in our buffers.
  * @sk: socket to verify
  */

@@ -626,6 +626,26 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 	if (newsk != NULL) {
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 
+		if (req->friend) {
+			/*
+			 * Make friends with the requestor but the ACK of
+			 * the request is already in-flight so the race is
+			 * on to make friends before the ACK is processed.
+			 * If the requestor's sk_friend value is != NULL
+			 * then the requestor has already processed the
+			 * ACK so indicate state change to wake'm up.
+			 */
+			struct sock *was;
+
+			sock_hold(req->friend);
+			newsk->sk_friend = req->friend;
+			sock_hold(newsk);
+			was = xchg(&req->friend->sk_friend, newsk);
+			/* If requester already connect()ed, maybe sleeping */
+			if (was && !sock_flag(req->friend, SOCK_DEAD))
+				sk->sk_state_change(req->friend);
+		}
+
 		newsk->sk_state = TCP_SYN_RECV;
 		newicsk->icsk_bind_hash = NULL;
 

@@ -716,6 +716,13 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero
 	},
+	{
+		.procname	= "tcp_friends",
+		.data		= &sysctl_tcp_friends,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{ }
 };
 

@@ -309,6 +309,38 @@ struct tcp_splice_state {
 };
 
 /*
+ * Friends? If not a friend return 0, else if friend is also a friend
+ * return 1, else wait for friend to be ready and return 1 if friends
+ * else -errno. In all cases if *friendp != NULL return friend pointer
+ * else NULL.
+ */
+static inline int tcp_friends(struct sock *sk, struct sock **friendp,
+			      long *timeo)
+{
+	struct sock *friend = sk->sk_friend;
+	int ret = 0;
+
+	if (!friend)
+		goto out;
+	if (unlikely(!friend->sk_friend)) {
+		/* Friendship not complete, wait? */
+		if (!timeo) {
+			ret = -EAGAIN;
+			goto out;
+		}
+		ret = sk_stream_wait_friend(sk, timeo);
+		if (ret != 0)
+			goto out;
+		friend = sk->sk_friend;
+	}
+	ret = 1;
+out:
+	if (friendp)
+		*friendp = friend;
+	return ret;
+}
+
+/*
  * Pressure flag: try to collapse.
  * Technical note: it is used by multiple contexts non atomically.
  * All the __sk_mem_schedule() is of this nature: accounting

@@ -587,6 +619,73 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 }
 EXPORT_SYMBOL(tcp_ioctl);
 
+static inline struct sk_buff *tcp_friend_tail(struct sock *sk, int *copy)
+{
+	struct sock	*friend = sk->sk_friend;
+	struct sk_buff	*skb = NULL;
+	int		sz = 0;
+
+	if (skb_peek_tail(&friend->sk_receive_queue)) {
+		spin_lock_bh(&friend->sk_lock.slock);
+		skb = skb_peek_tail(&friend->sk_receive_queue);
+		if (skb && skb->friend) {
+			if (!*copy)
+				sz = skb_tailroom(skb);
+			else
+				sz = *copy - skb->len;
+		}
+		if (!skb || sz <= 0)
+			spin_unlock_bh(&friend->sk_lock.slock);
+	}
+
+	*copy = sz;
+	return skb;
+}
+
+static inline void tcp_friend_seq(struct sock *sk, int copy, int charge)
+{
+	struct sock	*friend = sk->sk_friend;
+	struct tcp_sock *tp = tcp_sk(friend);
+
+	if (charge) {
+		sk_mem_charge(friend, charge);
+		atomic_add(charge, &friend->sk_rmem_alloc);
+	}
+	tp->rcv_nxt += copy;
+	tp->rcv_wup += copy;
+	spin_unlock_bh(&friend->sk_lock.slock);
+
+	friend->sk_data_ready(friend, copy);
+
+	tp = tcp_sk(sk);
+	tp->snd_nxt += copy;
+	tp->pushed_seq += copy;
+	tp->snd_una += copy;
+	tp->snd_up += copy;
+}
+
+static inline int tcp_friend_push(struct sock *sk, struct sk_buff *skb)
+{
+	struct sock	*friend = sk->sk_friend;
+	int		ret = 0;
+
+	if (friend->sk_shutdown & RCV_SHUTDOWN) {
+		__kfree_skb(skb);
+		return -ECONNRESET;
+	}
+
+	spin_lock_bh(&friend->sk_lock.slock);
+	skb->friend = sk;
+	skb_set_owner_r(skb, friend);
+	__skb_queue_tail(&friend->sk_receive_queue, skb);
+	if (!sk_rmem_schedule(friend, skb->truesize))
+		ret = 1;
+
+	tcp_friend_seq(sk, skb->len, 0);
+
+	return ret;
+}
+
 static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
 {
 	TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;

@@ -603,8 +702,12 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
-	skb->csum    = 0;
 	tcb->seq     = tcb->end_seq = tp->write_seq;
+	if (sk->sk_friend) {
+		skb->friend = sk->sk_friend;
+		return;
+	}
+	skb->csum    = 0;
 	tcb->tcp_flags = TCPHDR_ACK;
 	tcb->sacked  = 0;
 	skb_header_release(skb);

@@ -756,6 +859,21 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 }
 EXPORT_SYMBOL(tcp_splice_read);
 
+static inline struct sk_buff *tcp_friend_alloc_skb(struct sock *sk, int size)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb(size, sk->sk_allocation);
+	if (skb)
+		skb->avail_size = skb_tailroom(skb);
+	else {
+		sk->sk_prot->enter_memory_pressure(sk);
+		sk_stream_moderate_sndbuf(sk);
+	}
+
+	return skb;
+}
+
 struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
 {
 	struct sk_buff *skb;

@@ -813,13 +931,47 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 	return max(xmit_size_goal, mss_now);
 }
 
+static unsigned int tcp_friend_xmit_size_goal(struct sock *sk, int size_goal)
+{
+	u32 tmp = SKB_TRUESIZE(size_goal);
+
+	/*
+	 * If goal is zero (for non linear) or truesize of goal >= largest
+	 * skb return largest, else for tail fill find smallest order that
+	 * fits 8 or more truesized, else use requested truesize.
+	 */
+	if (size_goal == 0 || tmp >= SKB_MAX_ORDER(0, 3))
+		tmp = SKB_MAX_ORDER(0, 3);
+	else if (tmp <= (SKB_MAX_ORDER(0, 0) >> 3))
+		tmp = SKB_MAX_ORDER(0, 0);
+	else if (tmp <= (SKB_MAX_ORDER(0, 1) >> 3))
+		tmp = SKB_MAX_ORDER(0, 1);
+	else if (tmp <= (SKB_MAX_ORDER(0, 2) >> 3))
+		tmp = SKB_MAX_ORDER(0, 2);
+	else if (tmp <= (SKB_MAX_ORDER(0, 3) >> 3))
+		tmp = SKB_MAX_ORDER(0, 3);
+
+	/* At least 2 truesized in sk_buf */
+	if (tmp > (sk_sndbuf_get(sk) >> 1))
+		tmp = (sk_sndbuf_get(sk) >> 1) - SKB_TRUESIZE(0);
+
+	return tmp;
+}
+
 static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
 {
 	int mss_now;
+	int tmp;
 
-	mss_now = tcp_current_mss(sk);
-	*size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB));
+	if (sk->sk_friend) {
+		mss_now = tcp_friend_xmit_size_goal(sk, *size_goal);
+		tmp = mss_now;
+	} else {
+		mss_now = tcp_current_mss(sk);
+		tmp = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB));
+	}
 
+	*size_goal = tmp;
 	return mss_now;
 }
 

@@ -830,6 +982,8 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse
 	int mss_now, size_goal;
 	int err;
 	ssize_t copied;
+	struct sock *friend;
+	bool friend_tail = false;
 	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 
 	/* Wait for a connection to finish. */

@@ -837,6 +991,10 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse
 		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
 			goto out_err;
 
+	err = tcp_friends(sk, &friend, &timeo);
+	if (err < 0)
+		goto out_err;
+
 	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
 
 	mss_now = tcp_send_mss(sk, &size_goal, flags);

@@ -847,19 +1005,40 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse
 		goto out_err;
 
 	while (psize > 0) {
-		struct sk_buff *skb = tcp_write_queue_tail(sk);
+		struct sk_buff *skb;
 		struct page *page = pages[poffset / PAGE_SIZE];
 		int copy, i;
 		int offset = poffset % PAGE_SIZE;
 		int size = min_t(size_t, psize, PAGE_SIZE - offset);
 		bool can_coalesce;
 
-		if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) {
+		if (sk->sk_friend) {
+			if (sk->sk_friend->sk_shutdown & RCV_SHUTDOWN) {
+				sk->sk_err = ECONNRESET;
+				err = -EPIPE;
+				goto out_err;
+			}
+			copy = size_goal;
+			skb = tcp_friend_tail(sk, &copy);
+			if (copy > 0)
+				friend_tail = true;
+		} else if (!tcp_send_head(sk)) {
+			copy = 0;
+		} else {
+			skb = tcp_write_queue_tail(sk);
+			copy = size_goal - skb->len;
+		}
+
+		if (copy <= 0) {
 new_segment:
 			if (!sk_stream_memory_free(sk))
 				goto wait_for_sndbuf;
 
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+			if (sk->sk_friend)
+				skb = tcp_friend_alloc_skb(sk, 0);
+			else
+				skb = sk_stream_alloc_skb(sk, 0,
+							  sk->sk_allocation);
 			if (!skb)
 				goto wait_for_memory;
 

@@ -873,10 +1052,16 @@ new_segment:
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
 		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
-			tcp_mark_push(tp, skb);
+			if (friend) {
+				if (friend_tail) {
+					tcp_friend_seq(sk, 0, 0);
+					friend_tail = false;
+				}
+			} else
+				tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
-		if (!sk_wmem_schedule(sk, copy))
+		if (!friend && !sk_wmem_schedule(sk, copy))
 			goto wait_for_memory;
 
 		if (can_coalesce) {

@@ -889,19 +1074,40 @@ new_segment:
 		skb->len += copy;
 		skb->data_len += copy;
 		skb->truesize += copy;
-		sk->sk_wmem_queued += copy;
-		sk_mem_charge(sk, copy);
-		skb->ip_summed = CHECKSUM_PARTIAL;
 		tp->write_seq += copy;
 		TCP_SKB_CB(skb)->end_seq += copy;
 		skb_shinfo(skb)->gso_segs = 0;
 
-		if (!copied)
-			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
-
 		copied += copy;
 		poffset += copy;
-		if (!(psize -= copy))
+		psize -= copy;
+
+		if (friend) {
+			if (friend_tail) {
+				tcp_friend_seq(sk, copy, copy);
+				friend_tail = false;
+			} else {
+				err = tcp_friend_push(sk, skb);
+				if (err < 0) {
+					sk->sk_err = -err;
+					goto out_err;
+				}
+				if (err > 0)
+					goto wait_for_sndbuf;
+			}
+			if (!psize)
+				goto out;
+			continue;
+		}
+
+		sk->sk_wmem_queued += copy;
+		sk_mem_charge(sk, copy);
+		skb->ip_summed = CHECKSUM_PARTIAL;
+
+		if (copied == copy)
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+
+		if (!psize)
 			goto out;
 
 		if (skb->len < size_goal || (flags & MSG_OOB))

@@ -922,6 +1128,7 @@ wait_for_memory:
 		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 			goto do_error;
 
+		size_goal = -mss_now;
 		mss_now = tcp_send_mss(sk, &size_goal, flags);
 	}
 

@@ -984,8 +1191,9 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	int iovlen, flags, err, copied;
-	int mss_now = 0, size_goal;
-	bool sg;
+	int mss_now = 0, size_goal = size;
+	struct sock *friend;
+	bool sg, friend_tail = false;
 	long timeo;
 
 	lock_sock(sk);

@@ -998,6 +1206,10 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
 			goto out_err;
 
+	err = tcp_friends(sk, &friend, &timeo);
+	if (err < 0)
+		goto out_err;
+
 	if (unlikely(tp->repair)) {
 		if (tp->repair_queue == TCP_RECV_QUEUE) {
 			copied = tcp_send_rcvq(sk, msg, size);

@@ -1037,24 +1249,40 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			int copy = 0;
 			int max = size_goal;
 
-			skb = tcp_write_queue_tail(sk);
-			if (tcp_send_head(sk)) {
-				if (skb->ip_summed == CHECKSUM_NONE)
-					max = mss_now;
-				copy = max - skb->len;
+			if (friend) {
+				if (friend->sk_shutdown & RCV_SHUTDOWN) {
+					sk->sk_err = ECONNRESET;
+					err = -EPIPE;
+					goto out_err;
+				}
+				skb = tcp_friend_tail(sk, &copy);
+				if (copy)
+					friend_tail = true;
+			} else {
+				skb = tcp_write_queue_tail(sk);
+				if (tcp_send_head(sk)) {
+					if (skb->ip_summed == CHECKSUM_NONE)
+						max = mss_now;
+					copy = max - skb->len;
+				}
 			}
 
 			if (copy <= 0) {
 new_segment:
-				/* Allocate new segment. If the interface is SG,
-				 * allocate skb fitting to single page.
-				 */
 				if (!sk_stream_memory_free(sk))
 					goto wait_for_sndbuf;
 
-				skb = sk_stream_alloc_skb(sk,
-							  select_size(sk, sg),
-							  sk->sk_allocation);
+				if (friend)
+					skb = tcp_friend_alloc_skb(sk, max);
+				else {
+					/* Allocate new segment. If the
+					 * interface is SG, allocate skb
+					 * fitting to single page.
+					 */
+					skb = sk_stream_alloc_skb(sk,
+							select_size(sk, sg),
+							sk->sk_allocation);
+				}
 				if (!skb)
 					goto wait_for_memory;
 

@@ -1086,6 +1314,8 @@ new_segment:
 				struct page *page = sk->sk_sndmsg_page;
 				int off;
 
+				BUG_ON(friend);
+
 				if (page && page_count(page) == 1)
 					sk->sk_sndmsg_off = 0;
 

@@ -1155,16 +1385,34 @@ new_segment:
 				sk->sk_sndmsg_off = off + copy;
 			}
 
-			if (!copied)
-				TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
-
 			tp->write_seq += copy;
 			TCP_SKB_CB(skb)->end_seq += copy;
 			skb_shinfo(skb)->gso_segs = 0;
 
 			from += copy;
 			copied += copy;
-			if ((seglen -= copy) == 0 && iovlen == 0)
+			seglen -= copy;
+
+			if (friend) {
+				if (friend_tail) {
+					tcp_friend_seq(sk, copy, 0);
+					friend_tail = false;
+				} else {
+					err = tcp_friend_push(sk, skb);
+					if (err < 0) {
+						sk->sk_err = -err;
+						goto out_err;
+					}
+					if (err > 0)
+						goto wait_for_sndbuf;
+				}
+				continue;
+			}
+
+			if (copied == copy)
+				TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+
+			if (seglen == 0 && iovlen == 0)
 				goto out;
 
 			if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))

@@ -1186,6 +1434,7 @@ wait_for_memory:
 			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 				goto do_error;
 
+			size_goal = -mss_now;
 			mss_now = tcp_send_mss(sk, &size_goal, flags);
 		}
 	}

@@ -1197,13 +1446,19 @@ out:
 	return copied;
 
 do_fault:
-	if (!skb->len) {
-		tcp_unlink_write_queue(skb, sk);
-		/* It is the one place in all of TCP, except connection
-		 * reset, where we can be unlinking the send_head.
-		 */
-		tcp_check_send_head(sk, skb);
-		sk_wmem_free_skb(sk, skb);
+	if (friend_tail)
+		spin_unlock_bh(&friend->sk_lock.slock);
+	else if (!skb->len) {
+		if (friend) {
+			__kfree_skb(skb);
+		} else {
+			tcp_unlink_write_queue(skb, sk);
+			/* It is the one place in all of TCP, except connection
+			 * reset, where we can be unlinking the send_head.
+			 */
+			tcp_check_send_head(sk, skb);
+			sk_wmem_free_skb(sk, skb);
+		}
 	}
 
 do_error:

@@ -1216,6 +1471,13 @@ out_err:
 }
 EXPORT_SYMBOL(tcp_sendmsg);
 
+static inline void tcp_friend_write_space(struct sock *sk)
+{
+	/* Queued data below 1/4th of sndbuf? */
+	if ((sk_sndbuf_get(sk) >> 2) > sk_wmem_queued_get(sk))
+		sk->sk_friend->sk_write_space(sk->sk_friend);
+}
+
 /*
  *	Handle reading urgent data. BSD has very simple semantics for
  *	this, no blocking and very strange errors 8)

@@ -1294,7 +1556,12 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
 
-	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+	struct sk_buff *skb;
+
+	if (sk->sk_friend)
+		return;
+
+	skb = skb_peek(&sk->sk_receive_queue);
 
 	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
 	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",

@@ -1405,9 +1672,9 @@ static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 
 	skb_queue_walk(&sk->sk_receive_queue, skb) {
 		offset = seq - TCP_SKB_CB(skb)->seq;
-		if (tcp_hdr(skb)->syn)
+		if (!skb->friend && tcp_hdr(skb)->syn)
 			offset--;
-		if (offset < skb->len || tcp_hdr(skb)->fin) {
+		if (offset < skb->len || (!skb->friend && tcp_hdr(skb)->fin)) {
 			*off = offset;
 			return skb;
 		}

@@ -1434,14 +1701,27 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 	u32 seq = tp->copied_seq;
 	u32 offset;
 	int copied = 0;
+	struct sock *friend = sk->sk_friend;
 
 	if (sk->sk_state == TCP_LISTEN)
 		return -ENOTCONN;
+
+	if (friend) {
+		int err;
+		long timeo = sock_rcvtimeo(sk, false);
+
+		err = tcp_friends(sk, &friend, &timeo);
+		if (err < 0)
+			return err;
+		spin_lock_bh(&sk->sk_lock.slock);
+	}
+
 	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
 		if (offset < skb->len) {
 			int used;
 			size_t len;
 
+	again:
 			len = skb->len - offset;
 			/* Stop reading if we hit a patch of urgent data */
 			if (tp->urg_data) {

@@ -1451,7 +1731,13 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 				if (!len)
 					break;
 			}
+			if (sk->sk_friend)
+				spin_unlock_bh(&sk->sk_lock.slock);
+
 			used = recv_actor(desc, skb, offset, len);
+
+			if (sk->sk_friend)
+				spin_lock_bh(&sk->sk_lock.slock);
 			if (used < 0) {
 				if (!copied)
 					copied = used;

@@ -1461,17 +1747,31 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 				copied += used;
 				offset += used;
 			}
-			/*
-			 * If recv_actor drops the lock (e.g. TCP splice
-			 * receive) the skb pointer might be invalid when
-			 * getting here: tcp_collapse might have deleted it
-			 * while aggregating skbs from the socket queue.
-			 */
-			skb = tcp_recv_skb(sk, seq-1, &offset);
-			if (!skb || (offset+1 != skb->len))
-				break;
+			if (skb->friend) {
+				if (offset < skb->len) {
+					/*
+					 * Friend did an skb_put() while we
+					 * were away so process the same skb.
+					 */
+					tp->copied_seq = seq;
+					if (!desc->count)
+						break;
+					goto again;
+				}
+			} else {
+				/*
+				 * If recv_actor drops the lock (e.g. TCP
+				 * splice receive) the skb pointer might be
+				 * invalid when getting here: tcp_collapse
+				 * might have deleted it while aggregating
+				 * skbs from the socket queue.
+				 */
+				skb = tcp_recv_skb(sk, seq-1, &offset);
+				if (!skb || (offset+1 != skb->len))
+					break;
+			}
 		}
-		if (tcp_hdr(skb)->fin) {
+		if (!skb->friend && tcp_hdr(skb)->fin) {
 			sk_eat_skb(sk, skb, false);
 			++seq;
 			break;