1 files changed, 78 insertions, 74 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b1c218df2c85..cb7ca569052c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -137,12 +137,12 @@ static __u16 tcp_advertise_mss(struct sock *sk)
 }
 
 /* RFC2861. Reset CWND after idle period longer RTO to "restart window".
- * This is the first part of cwnd validation mechanism. */
-static void tcp_cwnd_restart(struct sock *sk, const struct dst_entry *dst)
+ * This is the first part of cwnd validation mechanism.
+ */
+void tcp_cwnd_restart(struct sock *sk, s32 delta)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	s32 delta = tcp_time_stamp - tp->lsndtime;
-	u32 restart_cwnd = tcp_init_cwnd(tp, dst);
+	u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
 	u32 cwnd = tp->snd_cwnd;
 
 	tcp_ca_event(sk, CA_EVENT_CWND_RESTART);
@@ -163,20 +163,17 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const u32 now = tcp_time_stamp;
-	const struct dst_entry *dst = __sk_dst_get(sk);
 
-	if (sysctl_tcp_slow_start_after_idle &&
-	    (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto))
-		tcp_cwnd_restart(sk, __sk_dst_get(sk));
+	if (tcp_packets_in_flight(tp) == 0)
+		tcp_ca_event(sk, CA_EVENT_TX_START);
 
 	tp->lsndtime = now;
 
 	/* If it is a reply for ato after last received
 	 * packet, enter pingpong mode.
 	 */
-	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato &&
-	    (!dst || !dst_metric(dst, RTAX_QUICKACK)))
-			icsk->icsk_ack.pingpong = 1;
+	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+		icsk->icsk_ack.pingpong = 1;
 }
 
 /* Account for an ACK we sent. */
@@ -360,14 +357,10 @@ static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
 }
 
 static void
-tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
-		    struct sock *sk)
+tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th)
 {
-	if (inet_rsk(req)->ecn_ok) {
+	if (inet_rsk(req)->ecn_ok)
 		th->ece = 1;
-		if (tcp_ca_needs_ecn(sk))
-			INET_ECN_xmit(sk);
-	}
 }
 
 /* Set up ECN state for a packet on a ESTABLISHED socket that is about to
@@ -615,12 +608,11 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 }
 
 /* Set up TCP options for SYN-ACKs. */
-static unsigned int tcp_synack_options(struct sock *sk,
-				   struct request_sock *req,
-				   unsigned int mss, struct sk_buff *skb,
-				   struct tcp_out_options *opts,
-				   const struct tcp_md5sig_key *md5,
-				   struct tcp_fastopen_cookie *foc)
+static unsigned int tcp_synack_options(struct request_sock *req,
+				       unsigned int mss, struct sk_buff *skb,
+				       struct tcp_out_options *opts,
+				       const struct tcp_md5sig_key *md5,
+				       struct tcp_fastopen_cookie *foc)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -946,9 +938,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 							   &md5);
 	tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
 
-	if (tcp_packets_in_flight(tp) == 0)
-		tcp_ca_event(sk, CA_EVENT_TX_START);
-
 	/* if no packet is in qdisc/device queue, then allow XPS to select
 	 * another queue. We can be called from tcp_tsq_handler()
 	 * which holds one reference to sk_wmem_alloc.
@@ -1776,7 +1765,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 		goto send_now;
 
-	if (!((1 << icsk->icsk_ca_state) & (TCPF_CA_Open | TCPF_CA_CWR)))
+	if (icsk->icsk_ca_state >= TCP_CA_Recovery)
 		goto send_now;
 
 	/* Avoid bursty behavior by allowing defer
@@ -1833,7 +1822,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 
 	/* Ok, it looks like it is advisable to defer. */
 
-	if (cong_win < send_win && cong_win < skb->len)
+	if (cong_win < send_win && cong_win <= skb->len)
 		*is_cwnd_limited = true;
 
 	return true;
@@ -2066,7 +2055,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		cwnd_quota = tcp_cwnd_test(tp, skb);
 		if (!cwnd_quota) {
-			is_cwnd_limited = true;
 			if (push_one == 2)
 				/* Force out a loss probe pkt. */
 				cwnd_quota = 1;
@@ -2148,10 +2136,11 @@ repair:
 		/* Send one loss probe per tail loss episode. */
 		if (push_one != 2)
 			tcp_schedule_loss_probe(sk);
+		is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
 		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
 	}
-	return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));
+	return !tp->packets_out && tcp_send_head(sk);
 }
 
 bool tcp_schedule_loss_probe(struct sock *sk)
@@ -2171,7 +2160,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	/* Don't do any loss probe on a Fast Open connection before 3WHS
 	 * finishes.
 	 */
-	if (sk->sk_state == TCP_SYN_RECV)
+	if (tp->fastopen_rsk)
 		return false;
 
 	/* TLP is only scheduled when next timer event is RTO. */
@@ -2181,7 +2170,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out ||
+	if (sysctl_tcp_early_retrans < 3 || !tp->packets_out ||
 	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
 		return false;
 
@@ -2190,9 +2179,10 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 		return false;
 
 	/* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account
-	 * for delayed ack when there's one outstanding packet.
+	 * for delayed ack when there's one outstanding packet. If no RTT
+	 * sample is available then probe after TCP_TIMEOUT_INIT.
 	 */
-	timeout = rtt << 1;
+	timeout = rtt << 1 ? : TCP_TIMEOUT_INIT;
 	if (tp->packets_out == 1)
 		timeout = max_t(u32, timeout,
 				(rtt + (rtt >> 1) + TCP_DELACK_MAX));
@@ -2228,7 +2218,7 @@ static bool skb_still_in_host_queue(const struct sock *sk,
 	return false;
 }
 
-/* When probe timeout (PTO) fires, send a new segment if one exists, else
+/* When probe timeout (PTO) fires, try send a new segment if possible, else
  * retransmit the last segment.
  */
 void tcp_send_loss_probe(struct sock *sk)
@@ -2237,11 +2227,19 @@ void tcp_send_loss_probe(struct sock *sk)
 	struct sk_buff *skb;
 	int pcount;
 	int mss = tcp_current_mss(sk);
-	int err = -1;
 
-	if (tcp_send_head(sk)) {
-		err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
-		goto rearm_timer;
+	skb = tcp_send_head(sk);
+	if (skb) {
+		if (tcp_snd_wnd_test(tp, skb, mss)) {
+			pcount = tp->packets_out;
+			tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
+			if (tp->packets_out > pcount)
+				goto probe_sent;
+			goto rearm_timer;
+		}
+		skb = tcp_write_queue_prev(sk, skb);
+	} else {
+		skb = tcp_write_queue_tail(sk);
 	}
 
 	/* At most one outstanding TLP retransmission. */
@@ -2249,7 +2247,6 @@ void tcp_send_loss_probe(struct sock *sk)
 		goto rearm_timer;
 
 	/* Retransmit last segment. */
-	skb = tcp_write_queue_tail(sk);
 	if (WARN_ON(!skb))
 		goto rearm_timer;
 
@@ -2264,26 +2261,24 @@ void tcp_send_loss_probe(struct sock *sk)
 		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss,
 					  GFP_ATOMIC)))
 			goto rearm_timer;
-		skb = tcp_write_queue_tail(sk);
+		skb = tcp_write_queue_next(sk, skb);
 	}
 
 	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
 		goto rearm_timer;
 
-	err = __tcp_retransmit_skb(sk, skb);
+	if (__tcp_retransmit_skb(sk, skb))
+		goto rearm_timer;
 
 	/* Record snd_nxt for loss detection. */
-	if (likely(!err))
-		tp->tlp_high_seq = tp->snd_nxt;
+	tp->tlp_high_seq = tp->snd_nxt;
 
+probe_sent:
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
+	/* Reset s.t. tcp_rearm_rto will restart timer from now */
+	inet_csk(sk)->icsk_pending = 0;
 rearm_timer:
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-				  inet_csk(sk)->icsk_rto,
-				  TCP_RTO_MAX);
-
-	if (likely(!err))
-		NET_INC_STATS_BH(sock_net(sk),
-				 LINUX_MIB_TCPLOSSPROBES);
+	tcp_rearm_rto(sk);
 }
 
 /* Push out any pending frames which were held back due to
@@ -2660,8 +2655,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 			net_dbg_ratelimited("retrans_out leaked\n");
 		}
 #endif
-		if (!tp->retrans_out)
-			tp->lost_retrans_low = tp->snd_nxt;
 		TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS;
 		tp->retrans_out += tcp_skb_pcount(skb);
 
@@ -2669,10 +2662,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		if (!tp->retrans_stamp)
 			tp->retrans_stamp = tcp_skb_timestamp(skb);
 
-		/* snd_nxt is stored to detect loss of retransmitted segment,
-		 * see tcp_input.c tcp_sacktag_write_queue().
-		 */
-		TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
 	} else if (err != -EBUSY) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
@@ -2898,6 +2887,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	skb_reserve(skb, MAX_TCP_HEADER);
 	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
+	skb_mstamp_get(&skb->skb_mstamp);
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
@@ -2949,20 +2939,22 @@ int tcp_send_synack(struct sock *sk)
  * Allocate one skb and build a SYNACK packet.
  * @dst is consumed : Caller should not use it again.
  */
-struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
+struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
-				struct tcp_fastopen_cookie *foc)
+				struct tcp_fastopen_cookie *foc,
+				bool attach_req)
 {
-	struct tcp_out_options opts;
 	struct inet_request_sock *ireq = inet_rsk(req);
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcphdr *th;
-	struct sk_buff *skb;
+	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *md5 = NULL;
+	struct tcp_out_options opts;
+	struct sk_buff *skb;
 	int tcp_header_size;
+	struct tcphdr *th;
+	u16 user_mss;
 	int mss;
 
-	skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC);
+	skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
 	if (unlikely(!skb)) {
 		dst_release(dst);
 		return NULL;
@@ -2970,11 +2962,21 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	/* Reserve space for headers. */
 	skb_reserve(skb, MAX_TCP_HEADER);
 
+	if (attach_req) {
+		skb_set_owner_w(skb, req_to_sk(req));
+	} else {
+		/* sk is a const pointer, because we want to express multiple
+		 * cpu might call us concurrently.
+		 * sk->sk_wmem_alloc in an atomic, we can promote to rw.
+		 */
+		skb_set_owner_w(skb, (struct sock *)sk);
+	}
 	skb_dst_set(skb, dst);
 
 	mss = dst_metric_advmss(dst);
-	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
-		mss = tp->rx_opt.user_mss;
+	user_mss = READ_ONCE(tp->rx_opt.user_mss);
+	if (user_mss && user_mss < mss)
+		mss = user_mss;
 
 	memset(&opts, 0, sizeof(opts));
 #ifdef CONFIG_SYN_COOKIES
@@ -2988,8 +2990,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	rcu_read_lock();
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
-	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc) + sizeof(*th);
+	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
+	tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) +
+			  sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -2998,7 +3001,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	memset(th, 0, sizeof(struct tcphdr));
 	th->syn = 1;
 	th->ack = 1;
-	tcp_ecn_make_synack(req, th, sk);
+	tcp_ecn_make_synack(req, th);
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
 	/* Setting of flags are superfluous here for callers (and ECE is
@@ -3012,8 +3015,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
-	th->window = htons(min(req->rcv_wnd, 65535U));
-	tcp_options_write((__be32 *)(th + 1), tp, &opts);
+	th->window = htons(min(req->rsk_rcv_wnd, 65535U));
+	tcp_options_write((__be32 *)(th + 1), NULL, &opts);
 	th->doff = (tcp_header_size >> 2);
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS);
 
@@ -3405,7 +3408,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib)
 	 */
 	tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
 	skb_mstamp_get(&skb->skb_mstamp);
-	NET_INC_STATS_BH(sock_net(sk), mib);
+	NET_INC_STATS(sock_net(sk), mib);
 	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
@@ -3500,13 +3503,14 @@ void tcp_send_probe0(struct sock *sk)
 				  TCP_RTO_MAX);
 }
 
-int tcp_rtx_synack(struct sock *sk, struct request_sock *req)
+int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 {
 	const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific;
 	struct flowi fl;
 	int res;
 
-	res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL);
+	tcp_rsk(req)->txhash = net_tx_rndhash();
+	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, true);
 	if (!res) {
 		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);