1 files changed, 126 insertions, 94 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5079832af5c1..c69f4d966024 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -82,6 +82,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 
 	NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
 		      tcp_skb_pcount(skb));
+	tcp_check_space(sk);
 }
 
 /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one
@@ -142,7 +143,7 @@ void tcp_cwnd_restart(struct sock *sk, s32 delta)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
-	u32 cwnd = tp->snd_cwnd;
+	u32 cwnd = tcp_snd_cwnd(tp);
 
 	tcp_ca_event(sk, CA_EVENT_CWND_RESTART);
 
@@ -151,7 +152,7 @@ void tcp_cwnd_restart(struct sock *sk, s32 delta)
 
 	while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd)
 		cwnd >>= 1;
-	tp->snd_cwnd = max(cwnd, restart_cwnd);
+	tcp_snd_cwnd_set(tp, max(cwnd, restart_cwnd));
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 	tp->snd_cwnd_used = 0;
 }
@@ -166,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 	if (tcp_packets_in_flight(tp) == 0)
 		tcp_ca_event(sk, CA_EVENT_TX_START);
 
-	/* If this is the first data packet sent in response to the
-	 * previous received data,
-	 * and it is a reply for ato after last received packet,
-	 * increase pingpong count.
-	 */
-	if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
-	    (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
-		inet_csk_inc_pingpong_cnt(sk);
-
 	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)
+		inet_csk_enter_pingpong_mode(sk);
 }
 
 /* Account for an ACK we sent. */
@@ -229,7 +227,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	 * which we interpret as a sign the remote TCP is not
 	 * misinterpreting the window field as a signed quantity.
 	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
 		(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
 	else
 		(*rcv_wnd) = min_t(u32, space, U16_MAX);
@@ -240,8 +238,8 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	*rcv_wscale = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
-		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
-		space = max_t(u32, space, sysctl_rmem_max);
+		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
+		space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
 		space = min_t(u32, space, *window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
 				      0, TCP_MAX_WSCALE);
@@ -284,7 +282,7 @@ static u16 tcp_select_window(struct sock *sk)
 	 * scaled window.
 	 */
 	if (!tp->rx_opt.rcv_wscale &&
-	    sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
 		new_win = min(new_win, MAX_TCP_WINDOW);
 	else
 		new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -323,7 +321,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk);
-	bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+	bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 ||
 		tcp_ca_needs_ecn(sk) || bpf_needs_ecn;
 
 	if (!use_ecn) {
@@ -345,7 +343,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 
 static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
 {
-	if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback))
 		/* tp->ecn_flags are cleared at a later point in time when
 		 * SYN ACK is ultimatively being received.
 		 */
@@ -444,12 +442,13 @@ struct tcp_out_options {
 	struct mptcp_out_options mptcp;
 };
 
-static void mptcp_options_write(__be32 *ptr, const struct tcp_sock *tp,
+static void mptcp_options_write(struct tcphdr *th, __be32 *ptr,
+				struct tcp_sock *tp,
 				struct tcp_out_options *opts)
 {
 #if IS_ENABLED(CONFIG_MPTCP)
 	if (unlikely(OPTION_MPTCP & opts->options))
-		mptcp_write_options(ptr, tp, &opts->mptcp);
+		mptcp_write_options(th, ptr, tp, &opts->mptcp);
 #endif
 }
 
@@ -605,9 +604,10 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
  * At least SACK_PERM as the first option is known to lead to a disaster
  * (but it may well be that other scenarios fail similarly).
  */
-static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
+static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
 			      struct tcp_out_options *opts)
 {
+	__be32 *ptr = (__be32 *)(th + 1);
 	u16 options = opts->options;	/* mungable copy */
 
 	if (unlikely(OPTION_MD5 & options)) {
@@ -701,7 +701,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
 	smc_options_write(ptr, &options);
 
-	mptcp_options_write(ptr, tp, opts);
+	mptcp_options_write(th, ptr, tp, opts);
 }
 
 static void smc_set_option(const struct tcp_sock *tp,
@@ -788,18 +788,18 @@ 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(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) {
+	if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) {
 		opts->options |= OPTION_TS;
 		opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
-	if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) {
+	if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) {
 		opts->ws = tp->rx_opt.rcv_wscale;
 		opts->options |= OPTION_WSCALE;
 		remaining -= TCPOLEN_WSCALE_ALIGNED;
 	}
-	if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) {
+	if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) {
 		opts->options |= OPTION_SACK_ADVERTISE;
 		if (unlikely(!(OPTION_TS & opts->options)))
 			remaining -= TCPOLEN_SACKPERM_ALIGNED;
@@ -1013,7 +1013,7 @@ static void tcp_tsq_write(struct sock *sk)
 		struct tcp_sock *tp = tcp_sk(sk);
 
 		if (tp->lost_out > tp->retrans_out &&
-		    tp->snd_cwnd > tcp_packets_in_flight(tp)) {
+		    tcp_snd_cwnd(tp) > tcp_packets_in_flight(tp)) {
 			tcp_mstamp_refresh(tp);
 			tcp_xmit_retransmit_queue(sk);
 		}
@@ -1253,7 +1253,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	tp = tcp_sk(sk);
 	prior_wstamp = tp->tcp_wstamp_ns;
 	tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache);
-	skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
+	skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true);
 	if (clone_it) {
 		oskb = skb;
 
@@ -1354,7 +1354,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		th->window	= htons(min(tp->rcv_wnd, 65535U));
 	}
 
-	tcp_options_write((__be32 *)(th + 1), tp, &opts);
+	tcp_options_write(th, tp, &opts);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Calculate the MD5 hash, as we have all we need now */
@@ -1550,7 +1550,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	 * SO_SNDBUF values.
 	 * Also allow first and last skb in retransmit queue to be split.
 	 */
-	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
+	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_LEGACY_MAX_SIZE);
 	if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
 		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
 		     skb != tcp_rtx_queue_head(sk) &&
@@ -1589,7 +1589,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 
 	skb_split(skb, buff, len);
 
-	buff->tstamp = skb->tstamp;
+	skb_set_delivery_time(buff, skb->tstamp, true);
 	tcp_fragment_tstamp(skb, buff);
 
 	old_factor = tcp_skb_pcount(skb);
@@ -1716,7 +1716,8 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	mss_now -= icsk->icsk_ext_hdr_len;
 
 	/* Then reserve room for full set of TCP options and 8 bytes of data */
-	mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss);
+	mss_now = max(mss_now,
+		      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss));
 	return mss_now;
 }
 
@@ -1759,10 +1760,10 @@ void tcp_mtup_init(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
 
-	icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1;
+	icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1;
 	icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
 			       icsk->icsk_af_ops->net_header_len;
-	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
+	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss));
 	icsk->icsk_mtup.probe_size = 0;
 	if (icsk->icsk_mtup.enabled)
 		icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
@@ -1860,9 +1861,9 @@ static void tcp_cwnd_application_limited(struct sock *sk)
 		/* Limited by application or receiver window. */
 		u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
 		u32 win_used = max(tp->snd_cwnd_used, init_win);
-		if (win_used < tp->snd_cwnd) {
+		if (win_used < tcp_snd_cwnd(tp)) {
 			tp->snd_ssthresh = tcp_current_ssthresh(sk);
-			tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1;
+			tcp_snd_cwnd_set(tp, (tcp_snd_cwnd(tp) + win_used) >> 1);
 		}
 		tp->snd_cwnd_used = 0;
 	}
@@ -1874,15 +1875,20 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* Track the maximum number of outstanding packets in each
-	 * window, and remember whether we were cwnd-limited then.
+	/* Track the strongest available signal of the degree to which the cwnd
+	 * is fully utilized. If cwnd-limited then remember that fact for the
+	 * current window. If not cwnd-limited then track the maximum number of
+	 * outstanding packets in the current window. (If cwnd-limited then we
+	 * chose to not update tp->max_packets_out to avoid an extra else
+	 * clause with no functional impact.)
 	 */
-	if (!before(tp->snd_una, tp->max_packets_seq) ||
-	    tp->packets_out > tp->max_packets_out ||
-	    is_cwnd_limited) {
-		tp->max_packets_out = tp->packets_out;
-		tp->max_packets_seq = tp->snd_nxt;
+	if (!before(tp->snd_una, tp->cwnd_usage_seq) ||
+	    is_cwnd_limited ||
+	    (!tp->is_cwnd_limited &&
+	     tp->packets_out > tp->max_packets_out)) {
 		tp->is_cwnd_limited = is_cwnd_limited;
+		tp->max_packets_out = tp->packets_out;
+		tp->cwnd_usage_seq = tp->snd_nxt;
 	}
 
 	if (tcp_is_cwnd_limited(sk)) {
@@ -1894,7 +1900,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 		if (tp->packets_out > tp->snd_cwnd_used)
 			tp->snd_cwnd_used = tp->packets_out;
 
-		if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle &&
+		if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) &&
 		    (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
 		    !ca_ops->cong_control)
 			tcp_cwnd_application_limited(sk);
@@ -1951,25 +1957,34 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
 }
 
 /* Return how many segs we'd like on a TSO packet,
- * to send one TSO packet per ms
+ * depending on current pacing rate, and how close the peer is.
+ *
+ * Rationale is:
+ * - For close peers, we rather send bigger packets to reduce
+ *   cpu costs, because occasional losses will be repaired fast.
+ * - For long distance/rtt flows, we would like to get ACK clocking
+ *   with 1 ACK per ms.
+ *
+ * Use min_rtt to help adapt TSO burst size, with smaller min_rtt resulting
+ * in bigger TSO bursts. We we cut the RTT-based allowance in half
+ * for every 2^9 usec (aka 512 us) of RTT, so that the RTT-based allowance
+ * is below 1500 bytes after 6 * ~500 usec = 3ms.
  */
 static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 			    int min_tso_segs)
 {
-	u32 bytes, segs;
+	unsigned long bytes;
+	u32 r;
 
-	bytes = min_t(unsigned long,
-		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
-		      sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
+	bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift);
 
-	/* Goal is to send at least one packet per ms,
-	 * not one big TSO packet every 100 ms.
-	 * This preserves ACK clocking and is consistent
-	 * with tcp_tso_should_defer() heuristic.
-	 */
-	segs = max_t(u32, bytes / mss_now, min_tso_segs);
+	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))
+		bytes += sk->sk_gso_max_size >> r;
+
+	bytes = min_t(unsigned long, bytes, sk->sk_gso_max_size);
 
-	return segs;
+	return max_t(u32, bytes / mss_now, min_tso_segs);
 }
 
 /* Return the number of segments we want in the skb we are transmitting.
@@ -1982,7 +1997,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 
 	min_tso = ca_ops->min_tso_segs ?
 			ca_ops->min_tso_segs(sk) :
-			sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+			READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
 
 	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
 	return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2034,7 +2049,7 @@ static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
 		return 1;
 
 	in_flight = tcp_packets_in_flight(tp);
-	cwnd = tp->snd_cwnd;
+	cwnd = tcp_snd_cwnd(tp);
 	if (in_flight >= cwnd)
 		return 0;
 
@@ -2187,12 +2202,12 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	in_flight = tcp_packets_in_flight(tp);
 
 	BUG_ON(tcp_skb_pcount(skb) <= 1);
-	BUG_ON(tp->snd_cwnd <= in_flight);
+	BUG_ON(tcp_snd_cwnd(tp) <= in_flight);
 
 	send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
 
 	/* From in_flight test above, we know that cwnd > in_flight.  */
-	cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache;
+	cong_win = (tcp_snd_cwnd(tp) - in_flight) * tp->mss_cache;
 
 	limit = min(send_win, cong_win);
 
@@ -2206,7 +2221,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 
 	win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor);
 	if (win_divisor) {
-		u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
+		u32 chunk = min(tp->snd_wnd, tcp_snd_cwnd(tp) * tp->mss_cache);
 
 		/* If at least some fraction of a window is available,
 		 * just use it.
@@ -2270,7 +2285,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk)
 	u32 interval;
 	s32 delta;
 
-	interval = net->ipv4.sysctl_tcp_probe_interval;
+	interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval);
 	delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp;
 	if (unlikely(delta >= interval * HZ)) {
 		int mss = tcp_current_mss(sk);
@@ -2336,7 +2351,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	if (likely(!icsk->icsk_mtup.enabled ||
 		   icsk->icsk_mtup.probe_size ||
 		   inet_csk(sk)->icsk_ca_state != TCP_CA_Open ||
-		   tp->snd_cwnd < 11 ||
+		   tcp_snd_cwnd(tp) < 11 ||
 		   tp->rx_opt.num_sacks || tp->rx_opt.dsack))
 		return -1;
 
@@ -2354,7 +2369,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	 * probing process by not resetting search range to its orignal.
 	 */
 	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
-		interval < net->ipv4.sysctl_tcp_probe_threshold) {
+	    interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) {
 		/* Check whether enough time has elaplased for
 		 * another round of probing.
 		 */
@@ -2372,7 +2387,7 @@ static int tcp_mtu_probe(struct sock *sk)
 		return 0;
 
 	/* Do we need to wait to drain cwnd? With none in flight, don't stall */
-	if (tcp_packets_in_flight(tp) + 2 > tp->snd_cwnd) {
+	if (tcp_packets_in_flight(tp) + 2 > tcp_snd_cwnd(tp)) {
 		if (!tcp_packets_in_flight(tp))
 			return -1;
 		else
@@ -2441,7 +2456,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
 		/* Decrement cwnd here because we are sending
 		 * effectively two packets. */
-		tp->snd_cwnd--;
+		tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - 1);
 		tcp_event_new_data_sent(sk, nskb);
 
 		icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len);
@@ -2494,7 +2509,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
 	if (sk->sk_pacing_status == SK_PACING_NONE)
 		limit = min_t(unsigned long, limit,
-			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+			      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
 	limit <<= factor;
 
 	if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
@@ -2616,7 +2631,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
 			/* "skb_mstamp_ns" is used as a start point for the retransmit timer */
-			skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache;
+			tp->tcp_wstamp_ns = tp->tcp_clock_cache;
+			skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true);
 			list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
 			tcp_init_tso_segs(skb, mss_now);
 			goto repair; /* Skip network transmission */
@@ -2698,7 +2714,7 @@ repair:
 	else
 		tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED);
 
-	is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
+	is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tcp_snd_cwnd(tp));
 	if (likely(sent_pkts || is_cwnd_limited))
 		tcp_cwnd_validate(sk, is_cwnd_limited);
 
@@ -2727,7 +2743,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	if (rcu_access_pointer(tp->fastopen_rsk))
 		return false;
 
-	early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
+	early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans);
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * not in loss recovery, that are either limited by cwnd or application.
 	 */
@@ -2808,7 +2824,7 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (unlikely(!skb)) {
 		WARN_ONCE(tp->packets_out,
 			  "invalid inflight: %u state %u cwnd %u mss %d\n",
-			  tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+			  tp->packets_out, sk->sk_state, tcp_snd_cwnd(tp), mss);
 		inet_csk(sk)->icsk_pending = 0;
 		return;
 	}
@@ -3091,7 +3107,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 	struct sk_buff *skb = to, *tmp;
 	bool first = true;
 
-	if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)
+	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse))
 		return;
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 		return;
@@ -3131,7 +3147,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int cur_mss;
 	int diff, len, err;
-
+	int avail_wnd;
 
 	/* Inconclusive MTU probe */
 	if (icsk->icsk_mtup.probe_size)
@@ -3153,17 +3169,25 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		return -EHOSTUNREACH; /* Routing failure or similar. */
 
 	cur_mss = tcp_current_mss(sk);
+	avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
 
 	/* If receiver has shrunk his window, and skb is out of
 	 * new window, do not retransmit it. The exception is the
 	 * case, when window is shrunk to zero. In this case
-	 * our retransmit serves as a zero window probe.
+	 * our retransmit of one segment serves as a zero window probe.
 	 */
-	if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) &&
-	    TCP_SKB_CB(skb)->seq != tp->snd_una)
-		return -EAGAIN;
+	if (avail_wnd <= 0) {
+		if (TCP_SKB_CB(skb)->seq != tp->snd_una)
+			return -EAGAIN;
+		avail_wnd = cur_mss;
+	}
 
 	len = cur_mss * segs;
+	if (len > avail_wnd) {
+		len = rounddown(avail_wnd, cur_mss);
+		if (!len)
+			len = avail_wnd;
+	}
 	if (skb->len > len) {
 		if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len,
 				 cur_mss, GFP_ATOMIC))
@@ -3177,8 +3201,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		diff -= tcp_skb_pcount(skb);
 		if (diff)
 			tcp_adjust_pcount(sk, skb, diff);
-		if (skb->len < cur_mss)
-			tcp_retrans_try_collapse(sk, skb, cur_mss);
+		avail_wnd = min_t(int, avail_wnd, cur_mss);
+		if (skb->len < avail_wnd)
+			tcp_retrans_try_collapse(sk, skb, avail_wnd);
 	}
 
 	/* RFC3168, section 6.1.1.1. ECN fallback */
@@ -3292,7 +3317,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		if (!hole)
 			tp->retransmit_skb_hint = skb;
 
-		segs = tp->snd_cwnd - tcp_packets_in_flight(tp);
+		segs = tcp_snd_cwnd(tp) - tcp_packets_in_flight(tp);
 		if (segs <= 0)
 			break;
 		sacked = TCP_SKB_CB(skb)->sacked;
@@ -3349,12 +3374,13 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
  */
 void sk_forced_mem_schedule(struct sock *sk, int size)
 {
-	int amt;
+	int delta, amt;
 
-	if (size <= sk->sk_forward_alloc)
+	delta = size - sk->sk_forward_alloc;
+	if (delta <= 0)
 		return;
-	amt = sk_mem_pages(size);
-	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	amt = sk_mem_pages(delta);
+	sk->sk_forward_alloc += amt << PAGE_SHIFT;
 	sk_memory_allocated_add(sk, amt);
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
@@ -3541,11 +3567,12 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	now = tcp_clock_ns();
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok))
-		skb->skb_mstamp_ns = cookie_init_timestamp(req, now);
+		skb_set_delivery_time(skb, cookie_init_timestamp(req, now),
+				      true);
 	else
 #endif
 	{
-		skb->skb_mstamp_ns = now;
+		skb_set_delivery_time(skb, now, true);
 		if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */
 			tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb);
 	}
@@ -3579,7 +3606,7 @@ 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((__be32 *)(th + 1), NULL, &opts);
+	tcp_options_write(th, NULL, &opts);
 	th->doff = (tcp_header_size >> 2);
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
 
@@ -3594,7 +3621,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb,
 				synack_type, &opts);
 
-	skb->skb_mstamp_ns = now;
+	skb_set_delivery_time(skb, now, true);
 	tcp_add_tx_delay(skb, tp);
 
 	return skb;
@@ -3632,7 +3659,7 @@ static void tcp_connect_init(struct sock *sk)
 	 * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
 	 */
 	tp->tcp_header_len = sizeof(struct tcphdr);
-	if (sock_net(sk)->ipv4.sysctl_tcp_timestamps)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps))
 		tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -3668,7 +3695,7 @@ static void tcp_connect_init(struct sock *sk)
 				  tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
 				  &tp->rcv_wnd,
 				  &tp->window_clamp,
-				  sock_net(sk)->ipv4.sysctl_tcp_window_scaling,
+				  READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling),
 				  &rcv_wscale,
 				  rcv_wnd);
 
@@ -3719,6 +3746,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
  */
 static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
 	int space, err = 0;
@@ -3733,8 +3761,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	 * private TCP options. The cost is reduced data space in SYN :(
 	 */
 	tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp);
+	/* Sync mss_cache after updating the mss_clamp */
+	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 
-	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+	space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
 	space = min_t(size_t, space, fo->size);
@@ -3771,7 +3801,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 
 	err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
 
-	syn->skb_mstamp_ns = syn_data->skb_mstamp_ns;
+	skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, true);
 
 	/* Now full SYN+DATA was cloned and sent (or not),
 	 * remove the SYN from the original skb (syn_data)
@@ -4072,7 +4102,7 @@ void tcp_send_probe0(struct sock *sk)
 
 	icsk->icsk_probes_out++;
 	if (err <= 0) {
-		if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2)
+		if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))
 			icsk->icsk_backoff++;
 		timeout = tcp_probe0_when(sk, TCP_RTO_MAX);
 	} else {
@@ -4092,12 +4122,14 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 	struct flowi fl;
 	int res;
 
-	tcp_rsk(req)->txhash = net_tx_rndhash();
+	/* Paired with WRITE_ONCE() in sock_setsockopt() */
+	if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED)
+		tcp_rsk(req)->txhash = net_tx_rndhash();
 	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
 				  NULL);
 	if (!res) {
-		__TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+		TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
 		if (unlikely(tcp_passive_fastopen(sk)))
 			tcp_sk(sk)->total_retrans++;
 		trace_tcp_retransmit_synack(sk, req);