1 files changed, 153 insertions, 32 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c21e8a22fb3b..316ebdf8151d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -79,6 +79,7 @@
 #include <trace/events/tcp.h>
 #include <linux/jump_label_ratelimit.h>
 #include <net/busy_poll.h>
+#include <net/mptcp.h>
 
 int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 
@@ -266,7 +267,7 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 
 static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 {
-	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+	tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
 }
 
 static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
@@ -359,7 +360,8 @@ static void tcp_sndbuf_expand(struct sock *sk)
 	sndmem *= nr_segs * per_mss;
 
 	if (sk->sk_sndbuf < sndmem)
-		sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
+		WRITE_ONCE(sk->sk_sndbuf,
+			   min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -483,8 +485,9 @@ static void tcp_clamp_window(struct sock *sk)
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_under_memory_pressure(sk) &&
 	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
-		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
-				    net->ipv4.sysctl_tcp_rmem[2]);
+		WRITE_ONCE(sk->sk_rcvbuf,
+			   min(atomic_read(&sk->sk_rmem_alloc),
+			       net->ipv4.sysctl_tcp_rmem[2]));
 	}
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -648,7 +651,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
 			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		if (rcvbuf > sk->sk_rcvbuf) {
-			sk->sk_rcvbuf = rcvbuf;
+			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
 			/* Make the window clamp follow along.  */
 			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
@@ -913,9 +916,10 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 /* This must be called before lost_out is incremented */
 static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 {
-	if (!tp->retransmit_skb_hint ||
-	    before(TCP_SKB_CB(skb)->seq,
-		   TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
+	if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
+	    (tp->retransmit_skb_hint &&
+	     before(TCP_SKB_CB(skb)->seq,
+		    TCP_SKB_CB(tp->retransmit_skb_hint)->seq)))
 		tp->retransmit_skb_hint = skb;
 }
 
@@ -1420,7 +1424,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
 		goto fallback;
 
-	if (!tcp_skb_can_collapse_to(prev))
+	if (!tcp_skb_can_collapse(prev, skb))
 		goto fallback;
 
 	in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
@@ -1725,8 +1729,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 		}
 
 		/* Ignore very old stuff early */
-		if (!after(sp[used_sacks].end_seq, prior_snd_una))
+		if (!after(sp[used_sacks].end_seq, prior_snd_una)) {
+			if (i == 0)
+				first_sack_index = -1;
 			continue;
+		}
 
 		used_sacks++;
 	}
@@ -2666,7 +2673,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
-	if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) &&
+	if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) &&
 	    tcp_try_undo_loss(sk, false))
 		return;
 
@@ -2990,7 +2997,7 @@ void tcp_rearm_rto(struct sock *sk)
 	/* If the retrans timer is currently being used by Fast Open
 	 * for SYN-ACK retrans purpose, stay put.
 	 */
-	if (tp->fastopen_rsk)
+	if (rcu_access_pointer(tp->fastopen_rsk))
 		return;
 
 	if (!tp->packets_out) {
@@ -3158,6 +3165,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 			tp->retransmit_skb_hint = NULL;
 		if (unlikely(skb == tp->lost_skb_hint))
 			tp->lost_skb_hint = NULL;
+		tcp_highest_sack_replace(sk, skb, next);
 		tcp_rtx_queue_unlink_and_free(skb, sk);
 	}
 
@@ -3362,7 +3370,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
 
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_received += delta;
-	tp->rcv_nxt = seq;
+	WRITE_ONCE(tp->rcv_nxt, seq);
 }
 
 /* Update our send window.
@@ -3548,7 +3556,7 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit)
 	if (rexmit == REXMIT_NONE || sk->sk_state == TCP_SYN_SENT)
 		return;
 
-	if (unlikely(rexmit == 2)) {
+	if (unlikely(rexmit == REXMIT_NEW)) {
 		__tcp_push_pending_frames(sk, tcp_current_mss(sk),
 					  TCP_NAGLE_OFF);
 		if (after(tp->snd_nxt, tp->high_seq))
@@ -3782,6 +3790,49 @@ static void smc_parse_options(const struct tcphdr *th,
 #endif
 }
 
+/* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped
+ * value on success.
+ */
+static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
+{
+	const unsigned char *ptr = (const unsigned char *)(th + 1);
+	int length = (th->doff * 4) - sizeof(struct tcphdr);
+	u16 mss = 0;
+
+	while (length > 0) {
+		int opcode = *ptr++;
+		int opsize;
+
+		switch (opcode) {
+		case TCPOPT_EOL:
+			return mss;
+		case TCPOPT_NOP:	/* Ref: RFC 793 section 3.1 */
+			length--;
+			continue;
+		default:
+			if (length < 2)
+				return mss;
+			opsize = *ptr++;
+			if (opsize < 2) /* "silly options" */
+				return mss;
+			if (opsize > length)
+				return mss;	/* fail on partial options */
+			if (opcode == TCPOPT_MSS && opsize == TCPOLEN_MSS) {
+				u16 in_mss = get_unaligned_be16(ptr);
+
+				if (in_mss) {
+					if (user_mss && user_mss < in_mss)
+						in_mss = user_mss;
+					mss = in_mss;
+				}
+			}
+			ptr += opsize - 2;
+			length -= opsize;
+		}
+	}
+	return mss;
+}
+
 /* Look for tcp options. Normally only called on SYN and SYNACK packets.
  * But, this can also be called on packets in the established flow when
  * the fast version below fails.
@@ -3875,6 +3926,10 @@ void tcp_parse_options(const struct net *net,
 				 */
 				break;
 #endif
+			case TCPOPT_MPTCP:
+				mptcp_parse_option(skb, ptr, opsize, opt_rx);
+				break;
+
 			case TCPOPT_FASTOPEN:
 				tcp_parse_fastopen_option(
 					opsize - TCPOLEN_FASTOPEN_BASE,
@@ -4216,8 +4271,10 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
 	 * The receiver remembers and reflects via DSACKs. Leverage the
 	 * DSACK state and change the txhash to re-route speculatively.
 	 */
-	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq)
+	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) {
 		sk_rethink_txhash(sk);
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
+	}
 }
 
 static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
@@ -4375,6 +4432,9 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
 		return false;
 
+	if (!mptcp_skb_can_collapse(to, from))
+		return false;
+
 #ifdef CONFIG_TLS_DEVICE
 	if (from->decrypted != to->decrypted)
 		return false;
@@ -4512,6 +4572,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	tp->pred_flags = 0;
 	inet_csk_schedule_ack(sk);
 
+	tp->rcv_ooopack += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE);
 	seq = TCP_SKB_CB(skb)->seq;
 	end_seq = TCP_SKB_CB(skb)->end_seq;
@@ -4712,6 +4773,9 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	bool fragstolen;
 	int eaten;
 
+	if (sk_is_mptcp(sk))
+		mptcp_incoming_options(sk, skb, &tp->rx_opt);
+
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
 		return;
@@ -4883,7 +4947,7 @@ restart:
 		/* The first skb to collapse is:
 		 * - not SYN/FIN and
 		 * - bloated or contains data before "start" or
-		 *   overlaps to the next one.
+		 *   overlaps to the next one and mptcp allow collapsing.
 		 */
 		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
 		    (tcp_win_from_space(sk, skb->truesize) > skb->len ||
@@ -4892,7 +4956,7 @@ restart:
 			break;
 		}
 
-		if (n && n != tail &&
+		if (n && n != tail && mptcp_skb_can_collapse(skb, n) &&
 		    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
 			end_of_skbs = false;
 			break;
@@ -4925,6 +4989,7 @@ restart:
 		else
 			__skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */
 		skb_set_owner_r(nskb, sk);
+		mptcp_skb_ext_move(nskb, skb);
 
 		/* Copy data, releasing collapsed skbs. */
 		while (copy > 0) {
@@ -4944,6 +5009,7 @@ restart:
 				skb = tcp_collapse_one(sk, skb, list, root);
 				if (!skb ||
 				    skb == tail ||
+				    !mptcp_skb_can_collapse(nskb, skb) ||
 				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 					goto end;
 #ifdef CONFIG_TLS_DEVICE
@@ -5312,7 +5378,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
 	}
 
 	tp->urg_data = TCP_URG_NOTYET;
-	tp->urg_seq = ptr;
+	WRITE_ONCE(tp->urg_seq, ptr);
 
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
@@ -5768,6 +5834,10 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
 
 	if (data) { /* Retransmit unacked data in SYN */
+		if (tp->total_retrans)
+			tp->fastopen_client_fail = TFO_SYN_RETRANSMITTED;
+		else
+			tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
 		skb_rbtree_walk_from(data) {
 			if (__tcp_retransmit_skb(sk, data, 1))
 				break;
@@ -5838,8 +5908,14 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 *        the segment and return)"
 		 */
 		if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) ||
-		    after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt))
+		    after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
+			/* Previous FIN/ACK or RST/ACK might be ignored. */
+			if (icsk->icsk_retransmits == 0)
+				inet_csk_reset_xmit_timer(sk,
+						ICSK_TIME_RETRANS,
+						TCP_TIMEOUT_MIN, TCP_RTO_MAX);
 			goto reset_and_undo;
+		}
 
 		if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
 		    !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp,
@@ -5888,7 +5964,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		/* Ok.. it's good. Set up sequence numbers and
 		 * move to established.
 		 */
-		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -5914,10 +5990,13 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
+		if (sk_is_mptcp(sk))
+			mptcp_rcv_synsent(sk);
+
 		/* Remember, tcp_poll() does not lock socket!
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
-		tp->copied_seq = tp->rcv_nxt;
+		WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 
 		smc_check_reset_syn(tp);
 
@@ -5991,8 +6070,8 @@ discard:
 			tp->tcp_header_len = sizeof(struct tcphdr);
 		}
 
-		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
-		tp->copied_seq = tp->rcv_nxt;
+		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
+		WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -6043,6 +6122,8 @@ reset_and_undo:
 
 static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 {
+	struct request_sock *req;
+
 	tcp_try_undo_loss(sk, false);
 
 	/* Reset rtx states to prevent spurious retransmits_timed_out() */
@@ -6052,7 +6133,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 	/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
 	 * we no longer need req so release it.
 	 */
-	reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false);
+	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+					lockdep_sock_is_held(sk));
+	reqsk_fastopen_remove(sk, req, false);
 
 	/* Re-arm the timer because data may have been sent out.
 	 * This is similar to the regular data transmission case
@@ -6127,7 +6210,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 	tcp_mstamp_refresh(tp);
 	tp->rx_opt.saw_tstamp = 0;
-	req = tp->fastopen_rsk;
+	req = rcu_dereference_protected(tp->fastopen_rsk,
+					lockdep_sock_is_held(sk));
 	if (req) {
 		bool req_stolen;
 
@@ -6167,7 +6251,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			tcp_try_undo_spurious_syn(sk);
 			tp->retrans_stamp = 0;
 			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-			tp->copied_seq = tp->rcv_nxt;
+			WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		}
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);
@@ -6274,8 +6358,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_CLOSE_WAIT:
 	case TCP_CLOSING:
 	case TCP_LAST_ACK:
-		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
+		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
+			if (sk_is_mptcp(sk))
+				mptcp_incoming_options(sk, skb, &tp->rx_opt);
 			break;
+		}
 		/* fall through */
 	case TCP_FIN_WAIT1:
 	case TCP_FIN_WAIT2:
@@ -6422,9 +6509,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc);
 /*
  * Return true if a syncookie should be sent
  */
-static bool tcp_syn_flood_action(const struct sock *sk,
-				 const struct sk_buff *skb,
-				 const char *proto)
+static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	const char *msg = "Dropping request";
@@ -6444,7 +6529,7 @@ static bool tcp_syn_flood_action(const struct sock *sk,
 	    net->ipv4.sysctl_tcp_syncookies != 2 &&
 	    xchg(&queue->synflood_warned, 1) == 0)
 		net_info_ratelimited("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
-				     proto, ntohs(tcp_hdr(skb)->dest), msg);
+				     proto, sk->sk_num, msg);
 
 	return want_cookie;
 }
@@ -6466,6 +6551,36 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
 	}
 }
 
+/* If a SYN cookie is required and supported, returns a clamped MSS value to be
+ * used for SYN cookie generation.
+ */
+u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
+			  const struct tcp_request_sock_ops *af_ops,
+			  struct sock *sk, struct tcphdr *th)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	u16 mss;
+
+	if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 &&
+	    !inet_csk_reqsk_queue_is_full(sk))
+		return 0;
+
+	if (!tcp_syn_flood_action(sk, rsk_ops->slab_name))
+		return 0;
+
+	if (sk_acceptq_is_full(sk)) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+		return 0;
+	}
+
+	mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss);
+	if (!mss)
+		mss = af_ops->mss_clamp;
+
+	return mss;
+}
+EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss);
+
 int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		     const struct tcp_request_sock_ops *af_ops,
 		     struct sock *sk, struct sk_buff *skb)
@@ -6487,7 +6602,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	 */
 	if ((net->ipv4.sysctl_tcp_syncookies == 2 ||
 	     inet_csk_reqsk_queue_is_full(sk)) && !isn) {
-		want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name);
+		want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name);
 		if (!want_cookie)
 			goto drop;
 	}
@@ -6503,6 +6618,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	tcp_rsk(req)->af_specific = af_ops;
 	tcp_rsk(req)->ts_off = 0;
+#if IS_ENABLED(CONFIG_MPTCP)
+	tcp_rsk(req)->is_mptcp = 0;
+#endif
 
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = af_ops->mss_clamp;
@@ -6525,6 +6643,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	af_ops->init_req(req, sk, skb);
 
+	if (IS_ENABLED(CONFIG_MPTCP) && want_cookie)
+		tcp_rsk(req)->is_mptcp = 0;
+
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_free;