Merge branch 'tcp_openreq_child'

davem330 · davem330 · commit 435f3f267780 · 2019-01-17T22:19:05.000-08:00
Eric Dumazet says:

====================
tcp: remove code from tcp_create_openreq_child()

tcp_create_openreq_child() is essentially cloning a listener, then
must initialize some fields that can not be inherited.

Listeners are either fresh sockets, or sockets that came through
tcp_disconnect() after a session that dirtied many fields.

By moving code to tcp_disconnect(), we can shorten time taken
to create a clone, since tcp_disconnect() operation is very
unlikely.
====================

Acked-by: Yuchung Cheng &lt;ycheng@google.com&gt;
Acked-by: Soheil Hassas Yeganeh &lt;soheil@google.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
@@ -2572,14 +2572,16 @@ int tcp_disconnect(struct sock *sk, int flags)
 	sk->sk_shutdown = 0;
 	sock_reset_flag(sk, SOCK_DONE);
 	tp->srtt_us = 0;
+	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	tp->rcv_rtt_last_tsecr = 0;
 	tp->write_seq += tp->max_window + 2;
 	if (tp->write_seq == 0)
 		tp->write_seq = 1;
 	icsk->icsk_backoff = 0;
-	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
+	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+	tp->snd_cwnd = TCP_INIT_CWND;
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
 	tp->delivered_ce = 0;
@@ -2603,6 +2605,23 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->duplicate_sack[0].end_seq = 0;
 	tp->dsack_dups = 0;
 	tp->reord_seen = 0;
+	tp->retrans_out = 0;
+	tp->sacked_out = 0;
+	tp->tlp_high_seq = 0;
+	tp->last_oow_ack_time = 0;
+	/* There's a bubble in the pipe until at least the first ACK. */
+	tp->app_limited = ~0U;
+	tp->rack.mstamp = 0;
+	tp->rack.advanced = 0;
+	tp->rack.reo_wnd_steps = 1;
+	tp->rack.last_delivered = 0;
+	tp->rack.reo_wnd_persist = 0;
+	tp->rack.dsack_seen = 0;
+	tp->syn_data_acked = 0;
+	tp->rx_opt.saw_tstamp = 0;
+	tp->rx_opt.dsack = 0;
+	tp->rx_opt.num_sacks = 0;
+
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
@@ -479,43 +479,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 	tcp_init_wl(newtp, treq->rcv_isn);
 
-	newtp->srtt_us = 0;
-	newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U);
-	newicsk->icsk_rto = TCP_TIMEOUT_INIT;
 	newicsk->icsk_ack.lrcvtime = tcp_jiffies32;
 
-	newtp->packets_out = 0;
-	newtp->retrans_out = 0;
-	newtp->sacked_out = 0;
-	newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-	newtp->tlp_high_seq = 0;
 	newtp->lsndtime = tcp_jiffies32;
 	newsk->sk_txhash = treq->txhash;
-	newtp->last_oow_ack_time = 0;
 	newtp->total_retrans = req->num_retrans;
 
-	/* So many TCP implementations out there (incorrectly) count the
-	 * initial SYN frame in their delayed-ACK and congestion control
-	 * algorithms that we must have the following bandaid to talk
-	 * efficiently to them.  -DaveM
-	 */
-	newtp->snd_cwnd = TCP_INIT_CWND;
-	newtp->snd_cwnd_cnt = 0;
-
-	/* There's a bubble in the pipe until at least the first ACK. */
-	newtp->app_limited = ~0U;
-
 	tcp_init_xmit_timers(newsk);
 	newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
 
-	newtp->rx_opt.saw_tstamp = 0;
-
-	newtp->rx_opt.dsack = 0;
-	newtp->rx_opt.num_sacks = 0;
-
-	newtp->urg_data = 0;
-
 	if (sock_flag(newsk, SOCK_KEEPOPEN))
 		inet_csk_reset_keepalive_timer(newsk,
 					       keepalive_time_when(newtp));
@@ -556,13 +529,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	tcp_ecn_openreq_child(newtp, req);
 	newtp->fastopen_req = NULL;
 	newtp->fastopen_rsk = NULL;
-	newtp->syn_data_acked = 0;
-	newtp->rack.mstamp = 0;
-	newtp->rack.advanced = 0;
-	newtp->rack.reo_wnd_steps = 1;
-	newtp->rack.last_delivered = 0;
-	newtp->rack.reo_wnd_persist = 0;
-	newtp->rack.dsack_seen = 0;
 
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
 
