tcp: Handle eor bit when coalescing skb

This patch:
1. Prevent next_skb from coalescing to the prev_skb if
   TCP_SKB_CB(prev_skb)->eor is set
2. Update the TCP_SKB_CB(prev_skb)->eor if coalescing is
   allowed

Packetdrill script for testing:
~~~~~~
+0 `sysctl -q -w net.ipv4.tcp_min_tso_segs=10`
+0 `sysctl -q -w net.ipv4.tcp_no_metrics_save=1`
+0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0

0.100 < S 0:0(0) win 32792 <mss 1460,sackOK,nop,nop,nop,wscale 7>
0.100 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>
0.200 < . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4
+0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0

0.200 sendto(4, ..., 730, MSG_EOR, ..., ...) = 730
0.200 sendto(4, ..., 730, MSG_EOR, ..., ...) = 730
0.200 write(4, ..., 11680) = 11680

0.200 > P. 1:731(730) ack 1
0.200 > P. 731:1461(730) ack 1
0.200 > . 1461:8761(7300) ack 1
0.200 > P. 8761:13141(4380) ack 1

0.300 < . 1:1(0) ack 1 win 257 <sack 1461:13141,nop,nop>
0.300 > P. 1:731(730) ack 1
0.300 > P. 731:1461(730) ack 1
0.400 < . 1:1(0) ack 13141 win 257

0.400 close(4) = 0
0.400 > F. 13141:13141(0) ack 1
0.500 < F. 1:1(0) ack 13142 win 257
0.500 > . 13142:13142(0) ack 2

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 70c370b937621b4e5144fe3fd47bb1bddc9fa6bd..1fb19c91e0919b7a9a51e8cb928993a1f5ff1c7b 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1303,6 +1303,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
        }
 
        TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+       TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor;
        if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
                TCP_SKB_CB(prev)->end_seq++;
 
@@ -1368,6 +1369,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
        if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
                goto fallback;
 
+       if (!tcp_skb_can_collapse_to(prev))
+               goto fallback;
+
        in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
                  !before(end_seq, TCP_SKB_CB(skb)->end_seq);
 

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b3a31b4df57c6c2e5f325c6c3e99440986070444..77c6cbb897e6578f97e61356ecd53d5e83588610 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2499,6 +2499,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
         * packet counting does not break.
         */
        TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS;
+       TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor;
 
        /* changed transmit queue under us so clear hints */
        tcp_clear_retrans_hints_partial(tp);
@@ -2550,6 +2551,9 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
                if (!tcp_can_collapse(sk, skb))
                        break;
 
+               if (!tcp_skb_can_collapse_to(to))
+                       break;
+
                space -= skb->len;
 
                if (first) {