1 files changed, 159 insertions, 61 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 814af89c1bd3..40ba4249a586 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -277,9 +277,8 @@
 #include <net/ip.h>
 #include <net/sock.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
-#include <asm/unaligned.h>
 #include <net/busy_poll.h>
 
 int sysctl_tcp_min_tso_segs __read_mostly = 2;
@@ -405,10 +404,8 @@ void tcp_init_sock(struct sock *sk)
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tp->snd_cwnd_clamp = ~0;
 	tp->mss_cache = TCP_MSS_DEFAULT;
-	u64_stats_init(&tp->syncp);
 
 	tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
-	tcp_enable_early_retrans(tp);
 	tcp_assign_congestion_control(sk);
 
 	tp->tsoffset = 0;
@@ -423,15 +420,13 @@ void tcp_init_sock(struct sock *sk)
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
-	local_bh_disable();
 	sk_sockets_allocated_inc(sk);
-	local_bh_enable();
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
 static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb)
 {
-	if (tsflags) {
+	if (tsflags && skb) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 		struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
@@ -538,6 +533,12 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 		if (tp->urg_data & TCP_URG_VALID)
 			mask |= POLLPRI;
+	} else if (sk->sk_state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+		/* Active TCP fastopen socket with defer_connect
+		 * Return POLLOUT so application can call write()
+		 * in order for kernel to generate SYN+data
+		 */
+		mask |= POLLOUT | POLLWRNORM;
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
@@ -665,9 +666,9 @@ static void tcp_push(struct sock *sk, int flags, int mss_now,
 	if (tcp_should_autocork(sk, skb, size_goal)) {
 
 		/* avoid atomic op if TSQ_THROTTLED bit is already set */
-		if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) {
+		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
-			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
+			set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
 		}
 		/* It is possible TX completion already happened
 		 * before we set TSQ_THROTTLED.
@@ -772,6 +773,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				ret = -EAGAIN;
 				break;
 			}
+			/* if __tcp_splice_read() got nothing while we have
+			 * an skb in receive queue, we do not want to loop.
+			 * This might happen with URG data.
+			 */
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				break;
 			sk_wait_data(sk, &timeo, NULL);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
@@ -960,10 +967,8 @@ new_segment:
 		copied += copy;
 		offset += copy;
 		size -= copy;
-		if (!size) {
-			tcp_tx_timestamp(sk, sk->sk_tsflags, skb);
+		if (!size)
 			goto out;
-		}
 
 		if (skb->len < size_goal || (flags & MSG_OOB))
 			continue;
@@ -989,8 +994,11 @@ wait_for_memory:
 	}
 
 out:
-	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
-		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+	if (copied) {
+		tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk));
+		if (!(flags & MSG_SENDPAGE_NOTLAST))
+			tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+	}
 	return copied;
 
 do_error:
@@ -998,8 +1006,11 @@ do_error:
 		goto out;
 out_err:
 	/* make sure we wake any epoll edge trigger waiter */
-	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN))
+	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
+		     err == -EAGAIN)) {
 		sk->sk_write_space(sk);
+		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
+	}
 	return sk_stream_error(sk, flags, err);
 }
 
@@ -1072,6 +1083,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_sock *inet = inet_sk(sk);
 	int err, flags;
 
 	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
@@ -1086,11 +1098,26 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	tp->fastopen_req->data = msg;
 	tp->fastopen_req->size = size;
 
+	if (inet->defer_connect) {
+		err = tcp_connect(sk);
+		/* Same failure procedure as in tcp_v4/6_connect */
+		if (err) {
+			tcp_set_state(sk, TCP_CLOSE);
+			inet->inet_dport = 0;
+			sk->sk_route_caps = 0;
+		}
+	}
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
-				    msg->msg_namelen, flags);
-	*copied = tp->fastopen_req->copied;
-	tcp_free_fastopen_req(tp);
+				    msg->msg_namelen, flags, 1);
+	/* fastopen_req could already be freed in __inet_stream_connect
+	 * if the connection times out or gets rst
+	 */
+	if (tp->fastopen_req) {
+		*copied = tp->fastopen_req->copied;
+		tcp_free_fastopen_req(tp);
+		inet->defer_connect = 0;
+	}
 	return err;
 }
 
@@ -1108,7 +1135,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	lock_sock(sk);
 
 	flags = msg->msg_flags;
-	if (flags & MSG_FASTOPEN) {
+	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
 		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
@@ -1266,7 +1293,7 @@ new_segment:
 			} else {
 				skb_fill_page_desc(skb, i, pfrag->page,
 						   pfrag->offset, copy);
-				get_page(pfrag->page);
+				page_ref_inc(pfrag->page);
 			}
 			pfrag->offset += copy;
 		}
@@ -1280,7 +1307,6 @@ new_segment:
 
 		copied += copy;
 		if (!msg_data_left(msg)) {
-			tcp_tx_timestamp(sk, sockc.tsflags, skb);
 			if (unlikely(flags & MSG_EOR))
 				TCP_SKB_CB(skb)->eor = 1;
 			goto out;
@@ -1311,8 +1337,10 @@ wait_for_memory:
 	}
 
 out:
-	if (copied)
+	if (copied) {
+		tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk));
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+	}
 out_nopush:
 	release_sock(sk);
 	return copied + copied_syn;
@@ -1333,8 +1361,11 @@ do_error:
 out_err:
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
-	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN))
+	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
+		     err == -EAGAIN)) {
 		sk->sk_write_space(sk);
+		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
+	}
 	release_sock(sk);
 	return err;
 }
@@ -2291,6 +2322,11 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
+	tcp_saved_syn_free(tp);
+
+	/* Clean up fastopen related fields */
+	tcp_free_fastopen_req(tp);
+	inet->defer_connect = 0;
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
@@ -2302,7 +2338,7 @@ EXPORT_SYMBOL(tcp_disconnect);
 static inline bool tcp_can_repair_sock(const struct sock *sk)
 {
 	return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
-		((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED));
+		(sk->sk_state != TCP_LISTEN);
 }
 
 static int tcp_repair_set_window(struct tcp_sock *tp, char __user *optbuf, int len)
@@ -2469,11 +2505,6 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_THIN_DUPACK:
 		if (val < 0 || val > 1)
 			err = -EINVAL;
-		else {
-			tp->thin_dupack = val;
-			if (tp->thin_dupack)
-				tcp_disable_early_retrans(tp);
-		}
 		break;
 
 	case TCP_REPAIR:
@@ -2658,6 +2689,18 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EINVAL;
 		}
 		break;
+	case TCP_FASTOPEN_CONNECT:
+		if (val > 1 || val < 0) {
+			err = -EINVAL;
+		} else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+			if (sk->sk_state == TCP_CLOSE)
+				tp->fastopen_connect = val;
+			else
+				err = -EINVAL;
+		} else {
+			err = -EOPNOTSUPP;
+		}
+		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
 			err = -EPERM;
@@ -2704,15 +2747,33 @@ int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_tcp_setsockopt);
 #endif
 
+static void tcp_get_info_chrono_stats(const struct tcp_sock *tp,
+				      struct tcp_info *info)
+{
+	u64 stats[__TCP_CHRONO_MAX], total = 0;
+	enum tcp_chrono i;
+
+	for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) {
+		stats[i] = tp->chrono_stat[i - 1];
+		if (i == tp->chrono_type)
+			stats[i] += tcp_time_stamp - tp->chrono_start;
+		stats[i] *= USEC_PER_SEC / HZ;
+		total += stats[i];
+	}
+
+	info->tcpi_busy_time = total;
+	info->tcpi_rwnd_limited = stats[TCP_CHRONO_RWND_LIMITED];
+	info->tcpi_sndbuf_limited = stats[TCP_CHRONO_SNDBUF_LIMITED];
+}
+
 /* Return information about state of tcp endpoint in API format. */
 void tcp_get_info(struct sock *sk, struct tcp_info *info)
 {
 	const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 now = tcp_time_stamp, intv;
-	unsigned int start;
-	int notsent_bytes;
+	u32 now, intv;
 	u64 rate64;
+	bool slow;
 	u32 rate;
 
 	memset(info, 0, sizeof(*info));
@@ -2721,6 +2782,30 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 
 	info->tcpi_state = sk_state_load(sk);
 
+	/* Report meaningful fields for all TCP states, including listeners */
+	rate = READ_ONCE(sk->sk_pacing_rate);
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	info->tcpi_pacing_rate = rate64;
+
+	rate = READ_ONCE(sk->sk_max_pacing_rate);
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	info->tcpi_max_pacing_rate = rate64;
+
+	info->tcpi_reordering = tp->reordering;
+	info->tcpi_snd_cwnd = tp->snd_cwnd;
+
+	if (info->tcpi_state == TCP_LISTEN) {
+		/* listeners aliased fields :
+		 * tcpi_unacked -> Number of children ready for accept()
+		 * tcpi_sacked  -> max backlog
+		 */
+		info->tcpi_unacked = sk->sk_ack_backlog;
+		info->tcpi_sacked = sk->sk_max_ack_backlog;
+		return;
+	}
+
+	slow = lock_sock_fast(sk);
+
 	info->tcpi_ca_state = icsk->icsk_ca_state;
 	info->tcpi_retransmits = icsk->icsk_retransmits;
 	info->tcpi_probes = icsk->icsk_probes_out;
@@ -2748,17 +2833,14 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_snd_mss = tp->mss_cache;
 	info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
 
-	if (info->tcpi_state == TCP_LISTEN) {
-		info->tcpi_unacked = sk->sk_ack_backlog;
-		info->tcpi_sacked = sk->sk_max_ack_backlog;
-	} else {
-		info->tcpi_unacked = tp->packets_out;
-		info->tcpi_sacked = tp->sacked_out;
-	}
+	info->tcpi_unacked = tp->packets_out;
+	info->tcpi_sacked = tp->sacked_out;
+
 	info->tcpi_lost = tp->lost_out;
 	info->tcpi_retrans = tp->retrans_out;
 	info->tcpi_fackets = tp->fackets_out;
 
+	now = tcp_time_stamp;
 	info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
 	info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
 	info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);
@@ -2768,34 +2850,21 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	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;
-	info->tcpi_reordering = tp->reordering;
 
 	info->tcpi_rcv_rtt = jiffies_to_usecs(tp->rcv_rtt_est.rtt)>>3;
 	info->tcpi_rcv_space = tp->rcvq_space.space;
 
 	info->tcpi_total_retrans = tp->total_retrans;
 
-	rate = READ_ONCE(sk->sk_pacing_rate);
-	rate64 = rate != ~0U ? rate : ~0ULL;
-	put_unaligned(rate64, &info->tcpi_pacing_rate);
+	info->tcpi_bytes_acked = tp->bytes_acked;
+	info->tcpi_bytes_received = tp->bytes_received;
+	info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt);
+	tcp_get_info_chrono_stats(tp, info);
 
-	rate = READ_ONCE(sk->sk_max_pacing_rate);
-	rate64 = rate != ~0U ? rate : ~0ULL;
-	put_unaligned(rate64, &info->tcpi_max_pacing_rate);
-
-	do {
-		start = u64_stats_fetch_begin_irq(&tp->syncp);
-		put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
-		put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
-	} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
 	info->tcpi_segs_out = tp->segs_out;
 	info->tcpi_segs_in = tp->segs_in;
 
-	notsent_bytes = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt);
-	info->tcpi_notsent_bytes = max(0, notsent_bytes);
-
 	info->tcpi_min_rtt = tcp_min_rtt(tp);
 	info->tcpi_data_segs_in = tp->data_segs_in;
 	info->tcpi_data_segs_out = tp->data_segs_out;
@@ -2806,11 +2875,36 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	if (rate && intv) {
 		rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC;
 		do_div(rate64, intv);
-		put_unaligned(rate64, &info->tcpi_delivery_rate);
+		info->tcpi_delivery_rate = rate64;
 	}
+	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
+struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *stats;
+	struct tcp_info info;
+
+	stats = alloc_skb(5 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC);
+	if (!stats)
+		return NULL;
+
+	tcp_get_info_chrono_stats(tp, &info);
+	nla_put_u64_64bit(stats, TCP_NLA_BUSY,
+			  info.tcpi_busy_time, TCP_NLA_PAD);
+	nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED,
+			  info.tcpi_rwnd_limited, TCP_NLA_PAD);
+	nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED,
+			  info.tcpi_sndbuf_limited, TCP_NLA_PAD);
+	nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT,
+			  tp->data_segs_out, TCP_NLA_PAD);
+	nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS,
+			  tp->total_retrans, TCP_NLA_PAD);
+	return stats;
+}
+
 static int do_tcp_getsockopt(struct sock *sk, int level,
 		int optname, char __user *optval, int __user *optlen)
 {
@@ -2917,8 +3011,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_THIN_LINEAR_TIMEOUTS:
 		val = tp->thin_lto;
 		break;
+
 	case TCP_THIN_DUPACK:
-		val = tp->thin_dupack;
+		val = 0;
 		break;
 
 	case TCP_REPAIR:
@@ -2971,6 +3066,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = icsk->icsk_accept_queue.fastopenq.max_qlen;
 		break;
 
+	case TCP_FASTOPEN_CONNECT:
+		val = tp->fastopen_connect;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp + tp->tsoffset;
 		break;
@@ -3284,6 +3383,7 @@ void __init tcp_init(void)
 
 	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
 	percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
+	inet_hashinfo_init(&tcp_hashinfo);
 	tcp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("tcp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
@@ -3327,10 +3427,7 @@ void __init tcp_init(void)
 
 
 	cnt = tcp_hashinfo.ehash_mask + 1;
-
-	tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
 	sysctl_tcp_max_orphans = cnt / 2;
-	sysctl_max_syn_backlog = max(128, cnt / 256);
 
 	tcp_init_mem();
 	/* Set per-socket limits to no more than 1/128 the pressure threshold */
@@ -3349,6 +3446,7 @@ void __init tcp_init(void)
 	pr_info("Hash tables configured (established %u bind %u)\n",
 		tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
 
+	tcp_v4_init();
 	tcp_metrics_init();
 	BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
 	tcp_tasklet_init();