tcp: do not delay ACK in DCTCP upon CE status change

BugLink: http://bugs.launchpad.net/bugs/1814813
[ Upstream commit a0496ef2c23b3b180902dd185d0d63ccbc624cf8 ]

Per DCTCP RFC8257 (Section 3.2) the ACK reflecting the CE status change
has to be sent immediately so the sender can respond quickly:

""" When receiving packets, the CE codepoint MUST be processed as follows:

   1.  If the CE codepoint is set and DCTCP.CE is false, set DCTCP.CE to
       true and send an immediate ACK.

   2.  If the CE codepoint is not set and DCTCP.CE is true, set DCTCP.CE
       to false and send an immediate ACK.
"""

Previously DCTCP implementation may continue to delay the ACK. This
patch fixes that to implement the RFC by forcing an immediate ACK.

Tested with this packetdrill script provided by Larry Brakmo

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0

0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
0.110 < [ect0] . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4
   +0 setsockopt(4, SOL_SOCKET, SO_DEBUG, [1], 4) = 0

0.200 < [ect0] . 1:1001(1000) ack 1 win 257
0.200 > [ect01] . 1:1(0) ack 1001

0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 1:2(1) ack 1001

0.200 < [ect0] . 1001:2001(1000) ack 2 win 257
+0.005 < [ce] . 2001:3001(1000) ack 2 win 257

+0.000 > [ect01] . 2:2(0) ack 2001
// Previously the ACK below would be delayed by 40ms
+0.000 > [ect01] E. 2:2(0) ack 3001

+0.500 < F. 9501:9501(0) ack 4 win 257

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 790439f5cba74112e9c7660bd6b4f1599f1ffb61..43fda778cd8ae2805862d67a1b4856530cf3043f 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
                        struct pipe_inode_info *pipe, size_t len,
                        unsigned int flags);
 
+void tcp_enter_quickack_mode(struct sock *sk);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
                                         const unsigned int pkts)
 {

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 39d96d27ff94fc0c82b99b5ef5e4a56d1791e796..c78fb53988a12b279e15bc3d240d8ee9d6ea018e 100644 (file)
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -131,12 +131,15 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
        struct dctcp *ca = inet_csk_ca(sk);
        struct tcp_sock *tp = tcp_sk(sk);
 
-       /* State has changed from CE=0 to CE=1 and delayed
-        * ACK has not sent yet.
-        */
-       if (!ca->ce_state &&
-           inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-               __tcp_send_ack(sk, ca->prior_rcv_nxt);
+       if (!ca->ce_state) {
+               /* State has changed from CE=0 to CE=1, force an immediate
+                * ACK to reflect the new CE state. If an ACK was delayed,
+                * send that first to reflect the prior CE state.
+                */
+               if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+                       __tcp_send_ack(sk, ca->prior_rcv_nxt);
+               tcp_enter_quickack_mode(sk);
+       }
 
        ca->prior_rcv_nxt = tp->rcv_nxt;
        ca->ce_state = 1;
@@ -149,12 +152,15 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
        struct dctcp *ca = inet_csk_ca(sk);
        struct tcp_sock *tp = tcp_sk(sk);
 
-       /* State has changed from CE=1 to CE=0 and delayed
-        * ACK has not sent yet.
-        */
-       if (ca->ce_state &&
-           inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-               __tcp_send_ack(sk, ca->prior_rcv_nxt);
+       if (ca->ce_state) {
+               /* State has changed from CE=1 to CE=0, force an immediate
+                * ACK to reflect the new CE state. If an ACK was delayed,
+                * send that first to reflect the prior CE state.
+                */
+               if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+                       __tcp_send_ack(sk, ca->prior_rcv_nxt);
+               tcp_enter_quickack_mode(sk);
+       }
 
        ca->prior_rcv_nxt = tp->rcv_nxt;
        ca->ce_state = 0;

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 64198744fd188a62ff0b9ea2bcfb193e9a202e77..80038940598fb45249ac7de69f1541b27824c0c2 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -194,13 +194,14 @@ static void tcp_incr_quickack(struct sock *sk)
                icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
 }
 
-static void tcp_enter_quickack_mode(struct sock *sk)
+void tcp_enter_quickack_mode(struct sock *sk)
 {
        struct inet_connection_sock *icsk = inet_csk(sk);
        tcp_incr_quickack(sk);
        icsk->icsk_ack.pingpong = 0;
        icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
 
 /* Send ACKs quickly, if "quick" count is not exhausted
  * and the session is not interactive.