From 466466dc6c28ca9dc401f10e235b9cde9a7c9162 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 9 Aug 2018 09:38:09 -0700 Subject: tcp: mandate a one-time immediate ACK Add a new flag to indicate a one-time immediate ACK. This flag is occasionaly set under specific TCP protocol states in addition to the more common quickack mechanism for interactive application. In several cases in the TCP code we want to force an immediate ACK but do not want to call tcp_enter_quickack_mode() because we do not want to forget the icsk_ack.pingpong or icsk_ack.ato state. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 ++- net/ipv4/tcp_input.c | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 0a6c9e0f2b5a..fa43b82607d9 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -167,7 +167,8 @@ enum inet_csk_ack_state_t { ICSK_ACK_SCHED = 1, ICSK_ACK_TIMER = 2, ICSK_ACK_PUSHED = 4, - ICSK_ACK_PUSHED2 = 8 + ICSK_ACK_PUSHED2 = 8, + ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */ }; void inet_csk_init_xmit_timers(struct sock *sk, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 715d541b52dd..b8849588c440 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5179,7 +5179,9 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat || __tcp_select_window(sk) >= tp->rcv_wnd)) || /* We ACK each frame or... */ - tcp_in_quickack_mode(sk)) { + tcp_in_quickack_mode(sk) || + /* Protocol state mandates a one-time immediate ACK */ + inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOW) { send_now: tcp_send_ack(sk); return; -- cgit v1.2.3 From d2ccd7bc8acdcb9166c07a0255fb85bf877edb1f Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 9 Aug 2018 09:38:10 -0700 Subject: tcp: avoid resetting ACK timer in DCTCP The recent fix of acking immediately in DCTCP on CE status change has an undesirable side-effect: it also resets TCP ack timer and disables pingpong mode (interactive session). But the CE status change has nothing to do with them. This patch addresses that by using the new one-time immediate ACK flag instead of calling tcp_enter_quickack_mode(). Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_dctcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 8b637f9f23a2..ca61e2a659e7 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -136,7 +136,7 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) */ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) __tcp_send_ack(sk, ca->prior_rcv_nxt); - tcp_enter_quickack_mode(sk, 1); + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -157,7 +157,7 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) */ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) __tcp_send_ack(sk, ca->prior_rcv_nxt); - tcp_enter_quickack_mode(sk, 1); + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } ca->prior_rcv_nxt = tp->rcv_nxt; -- cgit v1.2.3 From 15bdd5686c2c61373680b9015e95abf31778e4fd Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 9 Aug 2018 09:38:11 -0700 Subject: tcp: always ACK immediately on hole repairs RFC 5681 sec 4.2: To provide feedback to senders recovering from losses, the receiver SHOULD send an immediate ACK when it receives a data segment that fills in all or part of a gap in the sequence space. When a gap is partially filled, __tcp_ack_snd_check already checks the out-of-order queue and correctly send an immediate ACK. However when a gap is fully filled, the previous implementation only resets pingpong mode which does not guarantee an immediate ACK because the quick ACK counter may be zero. This patch addresses this issue by marking the one-time immediate ACK flag instead. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b8849588c440..9a09ff3afef2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4735,11 +4735,11 @@ queue_and_out: if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tcp_ofo_queue(sk); - /* RFC2581. 4.2. SHOULD send immediate ACK, when + /* RFC5681. 4.2. SHOULD send immediate ACK, when * gap in queue is filled. */ if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) - inet_csk(sk)->icsk_ack.pingpong = 0; + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } if (tp->rx_opt.num_sacks) -- cgit v1.2.3 From fd2123a3d7527d4c7092633d55e877c0cc1d84a3 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 9 Aug 2018 09:38:12 -0700 Subject: tcp: avoid resetting ACK timer upon receiving packet with ECN CWR flag Previously commit 9aee40006190 ("tcp: ack immediately when a cwr packet arrives") calls tcp_enter_quickack_mode to force sending two immediate ACKs upon receiving a packet w/ CWR flag. The side effect is it'll also reset the delayed ACK timer and interactive session tracking. This patch removes that side effect by using the new ACK_NOW flag to force an immmediate ACK. Packetdrill to demonstrate: 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 +0 < [ect0] SEW 0:0(0) win 32792 +0 > SE. 0:0(0) ack 1 +.1 < [ect0] . 1:1(0) ack 1 win 257 +0 accept(3, ..., ...) = 4 +0 < [ect0] . 1:1001(1000) ack 1 win 257 +0 > [ect01] . 1:1(0) ack 1001 +0 write(4, ..., 1) = 1 +0 > [ect01] P. 1:2(1) ack 1001 +0 < [ect0] . 1001:2001(1000) ack 2 win 257 +0 write(4, ..., 1) = 1 +0 > [ect01] P. 2:3(1) ack 2001 +0 < [ect0] . 2001:3001(1000) ack 3 win 257 +0 < [ect0] . 3001:4001(1000) ack 3 win 257 // Ack delayed ... +.01 < [ce] P. 4001:4501(500) ack 3 win 257 +0 > [ect01] . 3:3(0) ack 4001 +0 > [ect01] E. 3:3(0) ack 4501 +.001 read(4, ..., 4500) = 4500 +0 write(4, ..., 1) = 1 +0 > [ect01] PE. 3:4(1) ack 4501 win 100 +.01 < [ect0] W. 4501:5501(1000) ack 4 win 257 // No delayed ACK on CWR flag +0 > [ect01] . 4:4(0) ack 5501 +.31 < [ect0] . 5501:6501(1000) ack 4 win 257 +0 > [ect01] . 4:4(0) ack 6501 Fixes: 9aee40006190 ("tcp: ack immediately when a cwr packet arrives") Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9a09ff3afef2..4c2dd9f863f7 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -245,16 +245,16 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp) tp->ecn_flags |= TCP_ECN_QUEUE_CWR; } -static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb) +static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb) { if (tcp_hdr(skb)->cwr) { - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; + tcp_sk(sk)->ecn_flags &= ~TCP_ECN_DEMAND_CWR; /* If the sender is telling us it has entered CWR, then its * cwnd may be very low (even just 1 packet), so we should ACK * immediately. */ - tcp_enter_quickack_mode((struct sock *)tp, 2); + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } } @@ -4703,7 +4703,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); - tcp_ecn_accept_cwr(tp, skb); + tcp_ecn_accept_cwr(sk, skb); tp->rx_opt.dsack = 0; -- cgit v1.2.3