1 files changed, 145 insertions, 187 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c4638e6f0238..86023b9be47f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -274,7 +274,6 @@
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
-#include <net/netdma.h>
 #include <net/sock.h>
 
 #include <asm/uaccess.h>
@@ -285,6 +284,8 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 
 int sysctl_tcp_min_tso_segs __read_mostly = 2;
 
+int sysctl_tcp_autocorking __read_mostly = 1;
+
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
@@ -379,13 +380,13 @@ void tcp_init_sock(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	skb_queue_head_init(&tp->out_of_order_queue);
+	__skb_queue_head_init(&tp->out_of_order_queue);
 	tcp_init_xmit_timers(sk);
 	tcp_prequeue_init(tp);
 	INIT_LIST_HEAD(&tp->tsq_node);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
-	tp->mdev = TCP_TIMEOUT_INIT;
+	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 
 	/* So many TCP implementations out there (incorrectly) count the
 	 * initial SYN frame in their delayed-ACK and congestion control
@@ -403,7 +404,7 @@ void tcp_init_sock(struct sock *sk)
 
 	tp->reordering = sysctl_tcp_reordering;
 	tcp_enable_early_retrans(tp);
-	icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+	tcp_assign_congestion_control(sk);
 
 	tp->tsoffset = 0;
 
@@ -424,6 +425,17 @@ void tcp_init_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
+static void tcp_tx_timestamp(struct sock *sk, struct sk_buff *skb)
+{
+	if (sk->sk_tsflags) {
+		struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+		sock_tx_timestamp(sk, &shinfo->tx_flags);
+		if (shinfo->tx_flags & SKBTX_ANY_TSTAMP)
+			shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
+	}
+}
+
 /*
  *	Wait for a TCP event.
  *
@@ -521,7 +533,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
-	if (sk->sk_err)
+	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
 		mask |= POLLERR;
 
 	return mask;
@@ -596,7 +608,7 @@ static inline bool forced_push(const struct tcp_sock *tp)
 	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
 }
 
-static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
+static 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);
@@ -605,7 +617,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
 	tcb->seq     = tcb->end_seq = tp->write_seq;
 	tcb->tcp_flags = TCPHDR_ACK;
 	tcb->sacked  = 0;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
@@ -619,19 +631,58 @@ static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
 		tp->snd_up = tp->write_seq;
 }
 
-static inline void tcp_push(struct sock *sk, int flags, int mss_now,
-			    int nonagle)
+/* If a not yet filled skb is pushed, do not send it if
+ * we have data packets in Qdisc or NIC queues :
+ * Because TX completion will happen shortly, it gives a chance
+ * to coalesce future sendmsg() payload into this skb, without
+ * need for a timer, and with no latency trade off.
+ * As packets containing data payload have a bigger truesize
+ * than pure acks (dataless) packets, the last checks prevent
+ * autocorking if we only have an ACK in Qdisc/NIC queues,
+ * or if TX completion was delayed after we processed ACK packet.
+ */
+static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
+				int size_goal)
 {
-	if (tcp_send_head(sk)) {
-		struct tcp_sock *tp = tcp_sk(sk);
+	return skb->len < size_goal &&
+	       sysctl_tcp_autocorking &&
+	       skb != tcp_write_queue_head(sk) &&
+	       atomic_read(&sk->sk_wmem_alloc) > skb->truesize;
+}
+
+static void tcp_push(struct sock *sk, int flags, int mss_now,
+		     int nonagle, int size_goal)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *skb;
+
+	if (!tcp_send_head(sk))
+		return;
+
+	skb = tcp_write_queue_tail(sk);
+	if (!(flags & MSG_MORE) || forced_push(tp))
+		tcp_mark_push(tp, skb);
+
+	tcp_mark_urg(tp, flags);
 
-		if (!(flags & MSG_MORE) || forced_push(tp))
-			tcp_mark_push(tp, tcp_write_queue_tail(sk));
+	if (tcp_should_autocork(sk, skb, size_goal)) {
 
-		tcp_mark_urg(tp, flags);
-		__tcp_push_pending_frames(sk, mss_now,
-					  (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
+		/* avoid atomic op if TSQ_THROTTLED bit is already set */
+		if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
+			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
+		}
+		/* It is possible TX completion already happened
+		 * before we set TSQ_THROTTLED.
+		 */
+		if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize)
+			return;
 	}
+
+	if (flags & MSG_MORE)
+		nonagle = TCP_NAGLE_CORK;
+
+	__tcp_push_pending_frames(sk, mss_now, nonagle);
 }
 
 static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
@@ -911,15 +962,17 @@ new_segment:
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		tp->write_seq += copy;
 		TCP_SKB_CB(skb)->end_seq += copy;
-		skb_shinfo(skb)->gso_segs = 0;
+		tcp_skb_pcount_set(skb, 0);
 
 		if (!copied)
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
 		copied += copy;
 		offset += copy;
-		if (!(size -= copy))
+		if (!(size -= copy)) {
+			tcp_tx_timestamp(sk, skb);
 			goto out;
+		}
 
 		if (skb->len < size_goal || (flags & MSG_OOB))
 			continue;
@@ -934,7 +987,8 @@ new_segment:
 wait_for_sndbuf:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-		tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+		tcp_push(sk, flags & ~MSG_MORE, mss_now,
+			 TCP_NAGLE_PUSH, size_goal);
 
 		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 			goto do_error;
@@ -944,7 +998,7 @@ wait_for_memory:
 
 out:
 	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
-		tcp_push(sk, flags, mss_now, tp->nonagle);
+		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	return copied;
 
 do_error:
@@ -1002,7 +1056,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp)
 	}
 }
 
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int err, flags;
@@ -1017,11 +1072,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
 	if (unlikely(tp->fastopen_req == NULL))
 		return -ENOBUFS;
 	tp->fastopen_req->data = msg;
+	tp->fastopen_req->size = size;
 
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
 				    msg->msg_namelen, flags);
-	*size = tp->fastopen_req->copied;
+	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
 	return err;
 }
@@ -1041,7 +1097,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	flags = msg->msg_flags;
 	if (flags & MSG_FASTOPEN) {
-		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
 		else if (err)
@@ -1064,7 +1120,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (unlikely(tp->repair)) {
 		if (tp->repair_queue == TCP_RECV_QUEUE) {
 			copied = tcp_send_rcvq(sk, msg, size);
-			goto out;
+			goto out_nopush;
 		}
 
 		err = -EINVAL;
@@ -1131,13 +1187,6 @@ new_segment:
 					goto wait_for_memory;
 
 				/*
-				 * All packets are restored as if they have
-				 * already been sent.
-				 */
-				if (tp->repair)
-					TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
-				/*
 				 * Check whether we can use HW checksum.
 				 */
 				if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
@@ -1146,6 +1195,13 @@ new_segment:
 				skb_entail(sk, skb);
 				copy = size_goal;
 				max = size_goal;
+
+				/* All packets are restored as if they have
+				 * already been sent. skb_mstamp isn't set to
+				 * avoid wrong rtt estimation.
+				 */
+				if (tp->repair)
+					TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
 			}
 
 			/* Try to append data to the end of skb. */
@@ -1204,12 +1260,14 @@ new_segment:
 
 			tp->write_seq += copy;
 			TCP_SKB_CB(skb)->end_seq += copy;
-			skb_shinfo(skb)->gso_segs = 0;
+			tcp_skb_pcount_set(skb, 0);
 
 			from += copy;
 			copied += copy;
-			if ((seglen -= copy) == 0 && iovlen == 0)
+			if ((seglen -= copy) == 0 && iovlen == 0) {
+				tcp_tx_timestamp(sk, skb);
 				goto out;
+			}
 
 			if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
 				continue;
@@ -1225,7 +1283,8 @@ wait_for_sndbuf:
 			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
 			if (copied)
-				tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+				tcp_push(sk, flags & ~MSG_MORE, mss_now,
+					 TCP_NAGLE_PUSH, size_goal);
 
 			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 				goto do_error;
@@ -1236,7 +1295,8 @@ wait_for_memory:
 
 out:
 	if (copied)
-		tcp_push(sk, flags, mss_now, tp->nonagle);
+		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+out_nopush:
 	release_sock(sk);
 	return copied + copied_syn;
 
@@ -1333,7 +1393,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-void tcp_cleanup_rbuf(struct sock *sk, int copied)
+static void tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
@@ -1409,39 +1469,6 @@ static void tcp_prequeue_process(struct sock *sk)
 	tp->ucopy.memory = 0;
 }
 
-#ifdef CONFIG_NET_DMA
-static void tcp_service_net_dma(struct sock *sk, bool wait)
-{
-	dma_cookie_t done, used;
-	dma_cookie_t last_issued;
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (!tp->ucopy.dma_chan)
-		return;
-
-	last_issued = tp->ucopy.dma_cookie;
-	dma_async_issue_pending(tp->ucopy.dma_chan);
-
-	do {
-		if (dma_async_is_tx_complete(tp->ucopy.dma_chan,
-					      last_issued, &done,
-					      &used) == DMA_COMPLETE) {
-			/* Safe to free early-copied skbs now */
-			__skb_queue_purge(&sk->sk_async_wait_queue);
-			break;
-		} else {
-			struct sk_buff *skb;
-			while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
-			       (dma_async_is_complete(skb->dma_cookie, done,
-						      used) == DMA_COMPLETE)) {
-				__skb_dequeue(&sk->sk_async_wait_queue);
-				kfree_skb(skb);
-			}
-		}
-	} while (wait);
-}
-#endif
-
 static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
 	struct sk_buff *skb;
@@ -1449,9 +1476,9 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 
 	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
 		offset = seq - TCP_SKB_CB(skb)->seq;
-		if (tcp_hdr(skb)->syn)
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 			offset--;
-		if (offset < skb->len || tcp_hdr(skb)->fin) {
+		if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
 			*off = offset;
 			return skb;
 		}
@@ -1459,7 +1486,7 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 		 * splitted a fat GRO packet, while we released socket lock
 		 * in skb_splice_bits()
 		 */
-		sk_eat_skb(sk, skb, false);
+		sk_eat_skb(sk, skb);
 	}
 	return NULL;
 }
@@ -1524,12 +1551,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 			if (offset + 1 != skb->len)
 				continue;
 		}
-		if (tcp_hdr(skb)->fin) {
-			sk_eat_skb(sk, skb, false);
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
+			sk_eat_skb(sk, skb);
 			++seq;
 			break;
 		}
-		sk_eat_skb(sk, skb, false);
+		sk_eat_skb(sk, skb);
 		if (!desc->count)
 			break;
 		tp->copied_seq = seq;
@@ -1567,10 +1594,12 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	int target;		/* Read at least this many bytes */
 	long timeo;
 	struct task_struct *user_recv = NULL;
-	bool copied_early = false;
 	struct sk_buff *skb;
 	u32 urg_hole = 0;
 
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return ip_recv_error(sk, msg, len, addr_len);
+
 	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
 	    (sk->sk_state == TCP_ESTABLISHED))
 		sk_busy_loop(sk, nonblock);
@@ -1610,28 +1639,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 
-#ifdef CONFIG_NET_DMA
-	tp->ucopy.dma_chan = NULL;
-	preempt_disable();
-	skb = skb_peek_tail(&sk->sk_receive_queue);
-	{
-		int available = 0;
-
-		if (skb)
-			available = TCP_SKB_CB(skb)->seq + skb->len - (*seq);
-		if ((available < target) &&
-		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
-		    !sysctl_tcp_low_latency &&
-		    net_dma_find_channel()) {
-			preempt_enable_no_resched();
-			tp->ucopy.pinned_list =
-					dma_pin_iovec_pages(msg->msg_iov, len);
-		} else {
-			preempt_enable_no_resched();
-		}
-	}
-#endif
-
 	do {
 		u32 offset;
 
@@ -1658,11 +1665,11 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				break;
 
 			offset = *seq - TCP_SKB_CB(skb)->seq;
-			if (tcp_hdr(skb)->syn)
+			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 				offset--;
 			if (offset < skb->len)
 				goto found_ok_skb;
-			if (tcp_hdr(skb)->fin)
+			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 				goto found_fin_ok;
 			WARN(!(flags & MSG_PEEK),
 			     "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
@@ -1762,16 +1769,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			/* __ Set realtime policy in scheduler __ */
 		}
 
-#ifdef CONFIG_NET_DMA
-		if (tp->ucopy.dma_chan) {
-			if (tp->rcv_wnd == 0 &&
-			    !skb_queue_empty(&sk->sk_async_wait_queue)) {
-				tcp_service_net_dma(sk, true);
-				tcp_cleanup_rbuf(sk, copied);
-			} else
-				dma_async_issue_pending(tp->ucopy.dma_chan);
-		}
-#endif
 		if (copied >= target) {
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
@@ -1779,11 +1776,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		} else
 			sk_wait_data(sk, &timeo);
 
-#ifdef CONFIG_NET_DMA
-		tcp_service_net_dma(sk, false);  /* Don't block */
-		tp->ucopy.wakeup = 0;
-#endif
-
 		if (user_recv) {
 			int chunk;
 
@@ -1841,43 +1833,13 @@ do_prequeue:
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-#ifdef CONFIG_NET_DMA
-			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-				tp->ucopy.dma_chan = net_dma_find_channel();
-
-			if (tp->ucopy.dma_chan) {
-				tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
-					tp->ucopy.dma_chan, skb, offset,
-					msg->msg_iov, used,
-					tp->ucopy.pinned_list);
-
-				if (tp->ucopy.dma_cookie < 0) {
-
-					pr_alert("%s: dma_cookie < 0\n",
-						 __func__);
-
-					/* Exception. Bailout! */
-					if (!copied)
-						copied = -EFAULT;
-					break;
-				}
-
-				dma_async_issue_pending(tp->ucopy.dma_chan);
-
-				if ((offset + used) == skb->len)
-					copied_early = true;
-
-			} else
-#endif
-			{
-				err = skb_copy_datagram_iovec(skb, offset,
-						msg->msg_iov, used);
-				if (err) {
-					/* Exception. Bailout! */
-					if (!copied)
-						copied = -EFAULT;
-					break;
-				}
+			err = skb_copy_datagram_iovec(skb, offset,
+						      msg->msg_iov, used);
+			if (err) {
+				/* Exception. Bailout! */
+				if (!copied)
+					copied = -EFAULT;
+				break;
 			}
 		}
 
@@ -1895,21 +1857,17 @@ skip_copy:
 		if (used + offset < skb->len)
 			continue;
 
-		if (tcp_hdr(skb)->fin)
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
-		if (!(flags & MSG_PEEK)) {
-			sk_eat_skb(sk, skb, copied_early);
-			copied_early = false;
-		}
+		if (!(flags & MSG_PEEK))
+			sk_eat_skb(sk, skb);
 		continue;
 
 	found_fin_ok:
 		/* Process the FIN. */
 		++*seq;
-		if (!(flags & MSG_PEEK)) {
-			sk_eat_skb(sk, skb, copied_early);
-			copied_early = false;
-		}
+		if (!(flags & MSG_PEEK))
+			sk_eat_skb(sk, skb);
 		break;
 	} while (len > 0);
 
@@ -1932,16 +1890,6 @@ skip_copy:
 		tp->ucopy.len = 0;
 	}
 
-#ifdef CONFIG_NET_DMA
-	tcp_service_net_dma(sk, true);  /* Wait for queue to drain */
-	tp->ucopy.dma_chan = NULL;
-
-	if (tp->ucopy.pinned_list) {
-		dma_unpin_iovec_pages(tp->ucopy.pinned_list);
-		tp->ucopy.pinned_list = NULL;
-	}
-#endif
-
 	/* According to UNIX98, msg_name/msg_namelen are ignored
 	 * on connected socket. I was just happy when found this 8) --ANK
 	 */
@@ -2096,8 +2044,10 @@ void tcp_close(struct sock *sk, long timeout)
 	 *  reader process may not have drained the data yet!
 	 */
 	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
-		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
-			  tcp_hdr(skb)->fin;
+		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq;
+
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+			len--;
 		data_was_unread += len;
 		__kfree_skb(skb);
 	}
@@ -2186,7 +2136,7 @@ adjudge_to_death:
 	/*	This is a (useful) BSD violating of the RFC. There is a
 	 *	problem with TCP as specified in that the other end could
 	 *	keep a socket open forever with no application left this end.
-	 *	We use a 3 minute timeout (about the same as BSD) then kill
+	 *	We use a 1 minute timeout (about the same as BSD) then kill
 	 *	our end. If they send after that then tough - BUT: long enough
 	 *	that we won't make the old 4*rto = almost no time - whoops
 	 *	reset mistake.
@@ -2285,9 +2235,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	__skb_queue_purge(&sk->sk_receive_queue);
 	tcp_write_queue_purge(sk);
 	__skb_queue_purge(&tp->out_of_order_queue);
-#ifdef CONFIG_NET_DMA
-	__skb_queue_purge(&sk->sk_async_wait_queue);
-#endif
 
 	inet->inet_dport = 0;
 
@@ -2296,7 +2243,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	sk->sk_shutdown = 0;
 	sock_reset_flag(sk, SOCK_DONE);
-	tp->srtt = 0;
+	tp->srtt_us = 0;
 	if ((tp->write_seq += tp->max_window + 2) == 0)
 		tp->write_seq = 1;
 	icsk->icsk_backoff = 0;
@@ -2627,7 +2574,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
-		/* Cap the max timeout in ms TCP will retry/retrans
+		/* Cap the max time in ms TCP will retry or probe the window
 		 * before giving up and aborting (ETIMEDOUT) a connection.
 		 */
 		if (val < 0)
@@ -2740,8 +2687,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 
 	info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
 	info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
-	info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3;
-	info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2;
+	info->tcpi_rtt = tp->srtt_us >> 3;
+	info->tcpi_rttvar = tp->mdev_us >> 2;
 	info->tcpi_snd_ssthresh = tp->snd_ssthresh;
 	info->tcpi_snd_cwnd = tp->snd_cwnd;
 	info->tcpi_advmss = tp->advmss;
@@ -2751,6 +2698,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 	info->tcpi_rcv_space = tp->rcvq_space.space;
 
 	info->tcpi_total_retrans = tp->total_retrans;
+
+	info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ?
+					sk->sk_pacing_rate : ~0ULL;
+	info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
+					sk->sk_max_pacing_rate : ~0ULL;
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
@@ -2866,6 +2818,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_USER_TIMEOUT:
 		val = jiffies_to_msecs(icsk->icsk_user_timeout);
 		break;
+
+	case TCP_FASTOPEN:
+		if (icsk->icsk_accept_queue.fastopenq != NULL)
+			val = icsk->icsk_accept_queue.fastopenq->max_qlen;
+		else
+			val = 0;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp + tp->tsoffset;
 		break;
@@ -3093,7 +3053,7 @@ static int __init set_thash_entries(char *str)
 }
 __setup("thash_entries=", set_thash_entries);
 
-static void tcp_init_mem(void)
+static void __init tcp_init_mem(void)
 {
 	unsigned long limit = nr_free_buffer_pages() / 8;
 	limit = max(limit, 128UL);
@@ -3111,8 +3071,8 @@ void __init tcp_init(void)
 
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
-	percpu_counter_init(&tcp_sockets_allocated, 0);
-	percpu_counter_init(&tcp_orphan_count, 0);
+	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
+	percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
 	tcp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("tcp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
@@ -3179,8 +3139,6 @@ void __init tcp_init(void)
 		tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
 
 	tcp_metrics_init();
-
-	tcp_register_congestion_control(&tcp_reno);
-
+	BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
 	tcp_tasklet_init();
 }