1 files changed, 37 insertions, 43 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f0723460753c..ca4d7594efd4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -170,10 +170,10 @@ 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. */
@@ -799,7 +799,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 
 	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->tsval = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -884,7 +884,8 @@ 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;
 	}
@@ -943,7 +944,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	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;
 	}
@@ -1076,7 +1078,8 @@ 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
@@ -1100,16 +1103,6 @@ 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);
@@ -1123,6 +1116,8 @@ 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);
 
@@ -1207,7 +1202,7 @@ 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,
@@ -1331,7 +1326,7 @@ 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;
@@ -1703,14 +1698,6 @@ 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;
@@ -1738,21 +1725,11 @@ 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);
 
@@ -1979,7 +1956,7 @@ 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))
@@ -2572,7 +2549,7 @@ 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));
@@ -2580,7 +2557,8 @@ 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.
@@ -3385,7 +3363,7 @@ 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;
@@ -3671,6 +3649,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
 
 	memset(&opts, 0, sizeof(opts));
+	if (tcp_rsk(req)->req_usec_ts < 0)
+		tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst);
 	now = tcp_clock_ns();
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok))
@@ -3967,7 +3947,7 @@ 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);
@@ -3997,6 +3977,20 @@ 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.
@@ -4032,7 +4026,7 @@ 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;