1 files changed, 279 insertions, 119 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 51d8638d4b4c..e3167ad96567 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -170,15 +170,14 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 	tp->lsndtime = now;
 
 	/* If it is a reply for ato after last received
-	 * packet, enter pingpong mode.
+	 * packet, increase pingpong count.
 	 */
 	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
-		inet_csk_enter_pingpong_mode(sk);
+		inet_csk_inc_pingpong_cnt(sk);
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
-				      u32 rcv_nxt)
+static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -192,7 +191,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
 
 	if (unlikely(rcv_nxt != tp->rcv_nxt))
 		return;  /* Special ACK sent by DCTCP to reflect ECN */
-	tcp_dec_quickack_mode(sk, pkts);
+	tcp_dec_quickack_mode(sk);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
 
@@ -257,11 +256,19 @@ EXPORT_SYMBOL(tcp_select_initial_window);
 static u16 tcp_select_window(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 old_win = tp->rcv_wnd;
-	u32 cur_win = tcp_receive_window(tp);
-	u32 new_win = __tcp_select_window(sk);
 	struct net *net = sock_net(sk);
+	u32 old_win = tp->rcv_wnd;
+	u32 cur_win, new_win;
+
+	/* Make the window 0 if we failed to queue the data because we
+	 * are out of memory. The window is temporary, so we don't store
+	 * it on the socket.
+	 */
+	if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM))
+		return 0;
 
+	cur_win = tcp_receive_window(tp);
+	new_win = __tcp_select_window(sk);
 	if (new_win < cur_win) {
 		/* Danger Will Robinson!
 		 * Don't update rcv_wup/rcv_wnd here or else
@@ -415,6 +422,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_FAST_OPEN_COOKIE	BIT(8)
 #define OPTION_SMC		BIT(9)
 #define OPTION_MPTCP		BIT(10)
+#define OPTION_AO		BIT(11)
 
 static void smc_options_write(__be32 *ptr, u16 *options)
 {
@@ -593,6 +601,44 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
 }
 #endif
 
+static __be32 *process_tcp_ao_options(struct tcp_sock *tp,
+				      const struct tcp_request_sock *tcprsk,
+				      struct tcp_out_options *opts,
+				      struct tcp_key *key, __be32 *ptr)
+{
+#ifdef CONFIG_TCP_AO
+	u8 maclen = tcp_ao_maclen(key->ao_key);
+
+	if (tcprsk) {
+		u8 aolen = maclen + sizeof(struct tcp_ao_hdr);
+
+		*ptr++ = htonl((TCPOPT_AO << 24) | (aolen << 16) |
+			       (tcprsk->ao_keyid << 8) |
+			       (tcprsk->ao_rcv_next));
+	} else {
+		struct tcp_ao_key *rnext_key;
+		struct tcp_ao_info *ao_info;
+
+		ao_info = rcu_dereference_check(tp->ao_info,
+			lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk));
+		rnext_key = READ_ONCE(ao_info->rnext_key);
+		if (WARN_ON_ONCE(!rnext_key))
+			return ptr;
+		*ptr++ = htonl((TCPOPT_AO << 24) |
+			       (tcp_ao_len(key->ao_key) << 16) |
+			       (key->ao_key->sndid << 8) |
+			       (rnext_key->rcvid));
+	}
+	opts->hash_location = (__u8 *)ptr;
+	ptr += maclen / sizeof(*ptr);
+	if (unlikely(maclen % sizeof(*ptr))) {
+		memset(ptr, TCPOPT_NOP, sizeof(*ptr));
+		ptr++;
+	}
+#endif
+	return ptr;
+}
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of
@@ -607,19 +653,22 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
  * (but it may well be that other scenarios fail similarly).
  */
 static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
-			      struct tcp_out_options *opts)
+			      const struct tcp_request_sock *tcprsk,
+			      struct tcp_out_options *opts,
+			      struct tcp_key *key)
 {
 	__be32 *ptr = (__be32 *)(th + 1);
 	u16 options = opts->options;	/* mungable copy */
 
-	if (unlikely(OPTION_MD5 & options)) {
+	if (tcp_key_is_md5(key)) {
 		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
 			       (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
 		/* overload cookie hash location */
 		opts->hash_location = (__u8 *)ptr;
 		ptr += 4;
+	} else if (tcp_key_is_ao(key)) {
+		ptr = process_tcp_ao_options(tp, tcprsk, opts, key, ptr);
 	}
-
 	if (unlikely(opts->mss)) {
 		*ptr++ = htonl((TCPOPT_MSS << 24) |
 			       (TCPOLEN_MSS << 16) |
@@ -760,23 +809,25 @@ static void mptcp_set_option_cond(const struct request_sock *req,
  */
 static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 				struct tcp_out_options *opts,
-				struct tcp_md5sig_key **md5)
+				struct tcp_key *key)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
 	struct tcp_fastopen_request *fastopen = tp->fastopen_req;
+	bool timestamps;
 
-	*md5 = NULL;
-#ifdef CONFIG_TCP_MD5SIG
-	if (static_branch_unlikely(&tcp_md5_needed.key) &&
-	    rcu_access_pointer(tp->md5sig_info)) {
-		*md5 = tp->af_specific->md5_lookup(sk, sk);
-		if (*md5) {
-			opts->options |= OPTION_MD5;
-			remaining -= TCPOLEN_MD5SIG_ALIGNED;
+	/* Better than switch (key.type) as it has static branches */
+	if (tcp_key_is_md5(key)) {
+		timestamps = false;
+		opts->options |= OPTION_MD5;
+		remaining -= TCPOLEN_MD5SIG_ALIGNED;
+	} else {
+		timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps);
+		if (tcp_key_is_ao(key)) {
+			opts->options |= OPTION_AO;
+			remaining -= tcp_ao_len_aligned(key->ao_key);
 		}
 	}
-#endif
 
 	/* We always get an MSS option.  The option bytes which will be seen in
 	 * normal data packets should timestamps be used, must be in the MSS
@@ -790,9 +841,9 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	opts->mss = tcp_advertise_mss(sk);
 	remaining -= TCPOLEN_MSS_ALIGNED;
 
-	if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) {
+	if (likely(timestamps)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
+		opts->tsval = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -843,7 +894,7 @@ static unsigned int tcp_synack_options(const 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,
+				       const struct tcp_key *key,
 				       struct tcp_fastopen_cookie *foc,
 				       enum tcp_synack_type synack_type,
 				       struct sk_buff *syn_skb)
@@ -851,8 +902,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
 
-#ifdef CONFIG_TCP_MD5SIG
-	if (md5) {
+	if (tcp_key_is_md5(key)) {
 		opts->options |= OPTION_MD5;
 		remaining -= TCPOLEN_MD5SIG_ALIGNED;
 
@@ -863,8 +913,11 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 		 */
 		if (synack_type != TCP_SYNACK_COOKIE)
 			ireq->tstamp_ok &= !ireq->sack_ok;
+	} else if (tcp_key_is_ao(key)) {
+		opts->options |= OPTION_AO;
+		remaining -= tcp_ao_len_aligned(key->ao_key);
+		ireq->tstamp_ok &= !ireq->sack_ok;
 	}
-#endif
 
 	/* We always send an MSS option. */
 	opts->mss = mss;
@@ -877,7 +930,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 	}
 	if (likely(ireq->tstamp_ok)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off;
+		opts->tsval = tcp_skb_timestamp_ts(tcp_rsk(req)->req_usec_ts, skb) +
+			      tcp_rsk(req)->ts_off;
 		opts->tsecr = READ_ONCE(req->ts_recent);
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -914,7 +968,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
  */
 static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb,
 					struct tcp_out_options *opts,
-					struct tcp_md5sig_key **md5)
+					struct tcp_key *key)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int size = 0;
@@ -922,21 +976,19 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	opts->options = 0;
 
-	*md5 = NULL;
-#ifdef CONFIG_TCP_MD5SIG
-	if (static_branch_unlikely(&tcp_md5_needed.key) &&
-	    rcu_access_pointer(tp->md5sig_info)) {
-		*md5 = tp->af_specific->md5_lookup(sk, sk);
-		if (*md5) {
-			opts->options |= OPTION_MD5;
-			size += TCPOLEN_MD5SIG_ALIGNED;
-		}
+	/* Better than switch (key.type) as it has static branches */
+	if (tcp_key_is_md5(key)) {
+		opts->options |= OPTION_MD5;
+		size += TCPOLEN_MD5SIG_ALIGNED;
+	} else if (tcp_key_is_ao(key)) {
+		opts->options |= OPTION_AO;
+		size += tcp_ao_len_aligned(key->ao_key);
 	}
-#endif
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0;
+		opts->tsval = skb ? tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) +
+				tp->tsoffset : 0;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		size += TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -1069,7 +1121,8 @@ static void tcp_tasklet_func(struct tasklet_struct *t)
 #define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED |		\
 			  TCPF_WRITE_TIMER_DEFERRED |	\
 			  TCPF_DELACK_TIMER_DEFERRED |	\
-			  TCPF_MTU_REDUCED_DEFERRED)
+			  TCPF_MTU_REDUCED_DEFERRED |	\
+			  TCPF_ACK_DEFERRED)
 /**
  * tcp_release_cb - tcp release_sock() callback
  * @sk: socket
@@ -1093,16 +1146,6 @@ void tcp_release_cb(struct sock *sk)
 		tcp_tsq_write(sk);
 		__sock_put(sk);
 	}
-	/* Here begins the tricky part :
-	 * We are called from release_sock() with :
-	 * 1) BH disabled
-	 * 2) sk_lock.slock spinlock held
-	 * 3) socket owned by us (sk->sk_lock.owned == 1)
-	 *
-	 * But following code is meant to be called from BH handlers,
-	 * so we should keep BH disabled, but early release socket ownership
-	 */
-	sock_release_ownership(sk);
 
 	if (flags & TCPF_WRITE_TIMER_DEFERRED) {
 		tcp_write_timer_handler(sk);
@@ -1116,6 +1159,8 @@ void tcp_release_cb(struct sock *sk)
 		inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
 		__sock_put(sk);
 	}
+	if ((flags & TCPF_ACK_DEFERRED) && inet_csk_ack_scheduled(sk))
+		tcp_send_ack(sk);
 }
 EXPORT_SYMBOL(tcp_release_cb);
 
@@ -1200,7 +1245,7 @@ static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb,
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if (sk->sk_pacing_status != SK_PACING_NONE) {
-		unsigned long rate = sk->sk_pacing_rate;
+		unsigned long rate = READ_ONCE(sk->sk_pacing_rate);
 
 		/* Original sch_fq does not pace first 10 MSS
 		 * Note that tp->data_segs_out overflows after 2^32 packets,
@@ -1243,7 +1288,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	struct tcp_out_options opts;
 	unsigned int tcp_options_size, tcp_header_size;
 	struct sk_buff *oskb = NULL;
-	struct tcp_md5sig_key *md5;
+	struct tcp_key key;
 	struct tcphdr *th;
 	u64 prior_wstamp;
 	int err;
@@ -1275,11 +1320,11 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	tcb = TCP_SKB_CB(skb);
 	memset(&opts, 0, sizeof(opts));
 
+	tcp_get_current_key(sk, &key);
 	if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) {
-		tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5);
+		tcp_options_size = tcp_syn_options(sk, skb, &opts, &key);
 	} else {
-		tcp_options_size = tcp_established_options(sk, skb, &opts,
-							   &md5);
+		tcp_options_size = tcp_established_options(sk, skb, &opts, &key);
 		/* Force a PSH flag on all (GSO) packets to expedite GRO flush
 		 * at receiver : This slightly improve GRO performance.
 		 * Note that we do not force the PSH flag for non GSO packets,
@@ -1293,14 +1338,21 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	}
 	tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
 
-	/* 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.
-	 *
-	 * TODO: Ideally, in-flight pure ACK packets should not matter here.
-	 * One way to get this would be to set skb->truesize = 2 on them.
+	/* We set skb->ooo_okay to one if this packet can select
+	 * a different TX queue than prior packets of this flow,
+	 * to avoid self inflicted reorders.
+	 * The 'other' queue decision is based on current cpu number
+	 * if XPS is enabled, or sk->sk_txhash otherwise.
+	 * We can switch to another (and better) queue if:
+	 * 1) No packet with payload is in qdisc/device queues.
+	 *    Delays in TX completion can defeat the test
+	 *    even if packets were already sent.
+	 * 2) Or rtx queue is empty.
+	 *    This mitigates above case if ACK packets for
+	 *    all prior packets were already processed.
 	 */
-	skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1);
+	skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) ||
+			tcp_rtx_queue_empty(sk);
 
 	/* If we had to use memory reserve to allocate this skb,
 	 * this might cause drops if packet is looped back :
@@ -1317,7 +1369,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree;
 	refcount_add(skb->truesize, &sk->sk_wmem_alloc);
 
-	skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm);
+	skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm));
 
 	/* Build TCP header and checksum it. */
 	th = (struct tcphdr *)skb->data;
@@ -1353,16 +1405,25 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		th->window	= htons(min(tp->rcv_wnd, 65535U));
 	}
 
-	tcp_options_write(th, tp, &opts);
+	tcp_options_write(th, tp, NULL, &opts, &key);
 
+	if (tcp_key_is_md5(&key)) {
 #ifdef CONFIG_TCP_MD5SIG
-	/* Calculate the MD5 hash, as we have all we need now */
-	if (md5) {
+		/* Calculate the MD5 hash, as we have all we need now */
 		sk_gso_disable(sk);
 		tp->af_specific->calc_md5_hash(opts.hash_location,
-					       md5, sk, skb);
-	}
+					       key.md5_key, sk, skb);
 #endif
+	} else if (tcp_key_is_ao(&key)) {
+		int err;
+
+		err = tcp_ao_transmit_skb(sk, skb, key.ao_key, th,
+					  opts.hash_location);
+		if (err) {
+			kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED);
+			return -ENOMEM;
+		}
+	}
 
 	/* BPF prog is the last one writing header option */
 	bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts);
@@ -1372,7 +1433,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 			   sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
+		tcp_event_ack_sent(sk, rcv_nxt);
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
@@ -1689,14 +1750,6 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	 */
 	mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr);
 
-	/* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
-	if (icsk->icsk_af_ops->net_frag_header_len) {
-		const struct dst_entry *dst = __sk_dst_get(sk);
-
-		if (dst && dst_allfrag(dst))
-			mss_now -= icsk->icsk_af_ops->net_frag_header_len;
-	}
-
 	/* Clamp it (mss_clamp does not include tcp options) */
 	if (mss_now > tp->rx_opt.mss_clamp)
 		mss_now = tp->rx_opt.mss_clamp;
@@ -1724,21 +1777,11 @@ int tcp_mss_to_mtu(struct sock *sk, int mss)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	int mtu;
 
-	mtu = mss +
+	return mss +
 	      tp->tcp_header_len +
 	      icsk->icsk_ext_hdr_len +
 	      icsk->icsk_af_ops->net_header_len;
-
-	/* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
-	if (icsk->icsk_af_ops->net_frag_header_len) {
-		const struct dst_entry *dst = __sk_dst_get(sk);
-
-		if (dst && dst_allfrag(dst))
-			mtu += icsk->icsk_af_ops->net_frag_header_len;
-	}
-	return mtu;
 }
 EXPORT_SYMBOL(tcp_mss_to_mtu);
 
@@ -1813,7 +1856,7 @@ unsigned int tcp_current_mss(struct sock *sk)
 	u32 mss_now;
 	unsigned int header_len;
 	struct tcp_out_options opts;
-	struct tcp_md5sig_key *md5;
+	struct tcp_key key;
 
 	mss_now = tp->mss_cache;
 
@@ -1822,8 +1865,8 @@ unsigned int tcp_current_mss(struct sock *sk)
 		if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
 			mss_now = tcp_sync_mss(sk, mtu);
 	}
-
-	header_len = tcp_established_options(sk, NULL, &opts, &md5) +
+	tcp_get_current_key(sk, &key);
+	header_len = tcp_established_options(sk, NULL, &opts, &key) +
 		     sizeof(struct tcphdr);
 	/* The mss_cache is sized based on tp->tcp_header_len, which assumes
 	 * some common options. If this is an odd packet (because we have SACK
@@ -1965,7 +2008,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 	unsigned long bytes;
 	u32 r;
 
-	bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift);
+	bytes = READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift);
 
 	r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log);
 	if (r < BITS_PER_TYPE(sk->sk_gso_max_size))
@@ -2442,6 +2485,7 @@ static int tcp_mtu_probe(struct sock *sk)
 
 	/* build the payload, and be prepared to abort if this fails. */
 	if (tcp_clone_payload(sk, nskb, probe_size)) {
+		tcp_skb_tsorted_anchor_cleanup(nskb);
 		consume_skb(nskb);
 		return -1;
 	}
@@ -2527,6 +2571,18 @@ static bool tcp_pacing_check(struct sock *sk)
 	return true;
 }
 
+static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk)
+{
+	const struct rb_node *node = sk->tcp_rtx_queue.rb_node;
+
+	/* No skb in the rtx queue. */
+	if (!node)
+		return true;
+
+	/* Only one skb in rtx queue. */
+	return !node->rb_left && !node->rb_right;
+}
+
 /* TCP Small Queues :
  * Control number of packets in qdisc/devices to two packets / or ~1 ms.
  * (These limits are doubled for retransmits)
@@ -2545,7 +2601,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 
 	limit = max_t(unsigned long,
 		      2 * skb->truesize,
-		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
+		      READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift));
 	if (sk->sk_pacing_status == SK_PACING_NONE)
 		limit = min_t(unsigned long, limit,
 			      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
@@ -2553,7 +2609,8 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 
 	if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
 	    tcp_sk(sk)->tcp_tx_delay) {
-		u64 extra_bytes = (u64)sk->sk_pacing_rate * tcp_sk(sk)->tcp_tx_delay;
+		u64 extra_bytes = (u64)READ_ONCE(sk->sk_pacing_rate) *
+				  tcp_sk(sk)->tcp_tx_delay;
 
 		/* TSQ is based on skb truesize sum (sk_wmem_alloc), so we
 		 * approximate our needs assuming an ~100% skb->truesize overhead.
@@ -2564,12 +2621,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 		limit += extra_bytes;
 	}
 	if (refcount_read(&sk->sk_wmem_alloc) > limit) {
-		/* Always send skb if rtx queue is empty.
+		/* Always send skb if rtx queue is empty or has one skb.
 		 * No need to wait for TX completion to call us back,
 		 * after softirq/tasklet schedule.
 		 * This helps when TX completions are delayed too much.
 		 */
-		if (tcp_rtx_queue_empty(sk))
+		if (tcp_rtx_queue_empty_or_single_skb(sk))
 			return false;
 
 		set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
@@ -2773,7 +2830,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 timeout, rto_delta_us;
+	u32 timeout, timeout_us, rto_delta_us;
 	int early_retrans;
 
 	/* Don't do any loss probe on a Fast Open connection before 3WHS
@@ -2797,11 +2854,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	 * sample is available then probe after TCP_TIMEOUT_INIT.
 	 */
 	if (tp->srtt_us) {
-		timeout = usecs_to_jiffies(tp->srtt_us >> 2);
+		timeout_us = tp->srtt_us >> 2;
 		if (tp->packets_out == 1)
-			timeout += TCP_RTO_MIN;
+			timeout_us += tcp_rto_min_us(sk);
 		else
-			timeout += TCP_TIMEOUT_MIN;
+			timeout_us += TCP_TIMEOUT_MIN_US;
+		timeout = usecs_to_jiffies(timeout_us);
 	} else {
 		timeout = TCP_TIMEOUT_INIT;
 	}
@@ -3235,7 +3293,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	if (skb_still_in_host_queue(sk, skb))
 		return -EBUSY;
 
+start:
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
+		if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+			TCP_SKB_CB(skb)->seq++;
+			goto start;
+		}
 		if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
 			WARN_ON_ONCE(1);
 			return -EINVAL;
@@ -3357,7 +3421,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 
 	/* Save stamp of the first (attempted) retransmit. */
 	if (!tp->retrans_stamp)
-		tp->retrans_stamp = tcp_skb_timestamp(skb);
+		tp->retrans_stamp = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb);
 
 	if (tp->undo_retrans < 0)
 		tp->undo_retrans = 0;
@@ -3459,7 +3523,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size)
 	if (delta <= 0)
 		return;
 	amt = sk_mem_pages(delta);
-	sk->sk_forward_alloc += amt << PAGE_SHIFT;
+	sk_forward_alloc_add(sk, amt << PAGE_SHIFT);
 	sk_memory_allocated_add(sk, amt);
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
@@ -3605,8 +3669,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	const struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_md5sig_key *md5 = NULL;
 	struct tcp_out_options opts;
+	struct tcp_key key = {};
 	struct sk_buff *skb;
 	int tcp_header_size;
 	struct tcphdr *th;
@@ -3656,16 +3720,45 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 			tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb);
 	}
 
-#ifdef CONFIG_TCP_MD5SIG
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
 	rcu_read_lock();
-	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
+	if (tcp_rsk_used_ao(req)) {
+#ifdef CONFIG_TCP_AO
+		struct tcp_ao_key *ao_key = NULL;
+		u8 keyid = tcp_rsk(req)->ao_keyid;
+
+		ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req),
+							    keyid, -1);
+		/* If there is no matching key - avoid sending anything,
+		 * especially usigned segments. It could try harder and lookup
+		 * for another peer-matching key, but the peer has requested
+		 * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here.
+		 */
+		if (unlikely(!ao_key)) {
+			rcu_read_unlock();
+			kfree_skb(skb);
+			net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n",
+					     keyid);
+			return NULL;
+		}
+		key.ao_key = ao_key;
+		key.type = TCP_KEY_AO;
+#endif
+	} else {
+#ifdef CONFIG_TCP_MD5SIG
+		key.md5_key = tcp_rsk(req)->af_specific->req_md5_lookup(sk,
+					req_to_sk(req));
+		if (key.md5_key)
+			key.type = TCP_KEY_MD5;
+#endif
+	}
 	skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4);
 	/* bpf program will be interested in the tcp_flags */
 	TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK;
-	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc, synack_type,
-					     syn_skb) + sizeof(*th);
+	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts,
+					     &key, foc, synack_type, syn_skb)
+					+ sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -3685,15 +3778,24 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
 	th->window = htons(min(req->rsk_rcv_wnd, 65535U));
-	tcp_options_write(th, NULL, &opts);
+	tcp_options_write(th, NULL, tcp_rsk(req), &opts, &key);
 	th->doff = (tcp_header_size >> 2);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
 
-#ifdef CONFIG_TCP_MD5SIG
 	/* Okay, we have all we need - do the md5 hash if needed */
-	if (md5)
+	if (tcp_key_is_md5(&key)) {
+#ifdef CONFIG_TCP_MD5SIG
 		tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location,
-					       md5, req_to_sk(req), skb);
+					key.md5_key, req_to_sk(req), skb);
+#endif
+	} else if (tcp_key_is_ao(&key)) {
+#ifdef CONFIG_TCP_AO
+		tcp_rsk(req)->af_specific->ao_synack_hash(opts.hash_location,
+					key.ao_key, req, skb,
+					opts.hash_location - (u8 *)th, 0);
+#endif
+	}
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
 	rcu_read_unlock();
 #endif
 
@@ -3741,10 +3843,7 @@ static void tcp_connect_init(struct sock *sk)
 	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps))
 		tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED;
 
-#ifdef CONFIG_TCP_MD5SIG
-	if (tp->af_specific->md5_lookup(sk, sk))
-		tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
-#endif
+	tcp_ao_connect_init(sk);
 
 	/* If user gave his TCP_MAXSEG, record it to clamp */
 	if (tp->rx_opt.user_mss)
@@ -3928,6 +4027,53 @@ int tcp_connect(struct sock *sk)
 
 	tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL);
 
+#if defined(CONFIG_TCP_MD5SIG) && defined(CONFIG_TCP_AO)
+	/* Has to be checked late, after setting daddr/saddr/ops.
+	 * Return error if the peer has both a md5 and a tcp-ao key
+	 * configured as this is ambiguous.
+	 */
+	if (unlikely(rcu_dereference_protected(tp->md5sig_info,
+					       lockdep_sock_is_held(sk)))) {
+		bool needs_ao = !!tp->af_specific->ao_lookup(sk, sk, -1, -1);
+		bool needs_md5 = !!tp->af_specific->md5_lookup(sk, sk);
+		struct tcp_ao_info *ao_info;
+
+		ao_info = rcu_dereference_check(tp->ao_info,
+						lockdep_sock_is_held(sk));
+		if (ao_info) {
+			/* This is an extra check: tcp_ao_required() in
+			 * tcp_v{4,6}_parse_md5_keys() should prevent adding
+			 * md5 keys on ao_required socket.
+			 */
+			needs_ao |= ao_info->ao_required;
+			WARN_ON_ONCE(ao_info->ao_required && needs_md5);
+		}
+		if (needs_md5 && needs_ao)
+			return -EKEYREJECTED;
+
+		/* If we have a matching md5 key and no matching tcp-ao key
+		 * then free up ao_info if allocated.
+		 */
+		if (needs_md5) {
+			tcp_ao_destroy_sock(sk, false);
+		} else if (needs_ao) {
+			tcp_clear_md5_list(sk);
+			kfree(rcu_replace_pointer(tp->md5sig_info, NULL,
+						  lockdep_sock_is_held(sk)));
+		}
+	}
+#endif
+#ifdef CONFIG_TCP_AO
+	if (unlikely(rcu_dereference_protected(tp->ao_info,
+					       lockdep_sock_is_held(sk)))) {
+		/* Don't allow connecting if ao is configured but no
+		 * matching key is found.
+		 */
+		if (!tp->af_specific->ao_lookup(sk, sk, -1, -1))
+			return -EKEYREJECTED;
+	}
+#endif
+
 	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
 		return -EHOSTUNREACH; /* Routing failure or similar. */
 
@@ -3944,7 +4090,7 @@ int tcp_connect(struct sock *sk)
 
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
 	tcp_mstamp_refresh(tp);
-	tp->retrans_stamp = tcp_time_stamp(tp);
+	tp->retrans_stamp = tcp_time_stamp_ts(tp);
 	tcp_connect_queue_skb(sk, buff);
 	tcp_ecn_send_syn(sk, buff);
 	tcp_rbtree_insert(&sk->tcp_rtx_queue, buff);
@@ -3974,6 +4120,20 @@ int tcp_connect(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_connect);
 
+u32 tcp_delack_max(const struct sock *sk)
+{
+	const struct dst_entry *dst = __sk_dst_get(sk);
+	u32 delack_max = inet_csk(sk)->icsk_delack_max;
+
+	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) {
+		u32 rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
+		u32 delack_from_rto_min = max_t(int, 1, rto_min - 1);
+
+		delack_max = min_t(u32, delack_max, delack_from_rto_min);
+	}
+	return delack_max;
+}
+
 /* Send out a delayed ack, the caller does the policy checking
  * to see if we should even be here.  See tcp_input.c:tcp_ack_snd_check()
  * for details.
@@ -4009,7 +4169,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 		ato = min(ato, max_ato);
 	}
 
-	ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max);
+	ato = min_t(u32, ato, tcp_delack_max(sk));
 
 	/* Stay within the limit we were given */
 	timeout = jiffies + ato;