tcp: Handle eor bit when fragmenting a skb

When fragmenting a skb, the next_skb should carry
the eor from prev_skb.  The eor of prev_skb should
also be reset.

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, ..., 15330, MSG_EOR, ..., ...) = 15330
0.200 sendto(4, ..., 730, 0, ..., ...) = 730

0.200 > .  1:7301(7300) ack 1
0.200 > . 7301:14601(7300) ack 1

0.300 < . 1:1(0) ack 14601 win 257
0.300 > P. 14601:15331(730) ack 1
0.300 > P. 15331:16061(730) ack 1

0.400 < . 1:1(0) ack 16061 win 257
0.400 close(4) = 0
0.400 > F. 16061:16061(0) ack 1
0.400 < F. 1:1(0) ack 16062 win 257
0.400 > . 16062:16062(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_output.c b/net/ipv4/tcp_output.c
index 77c6cbb897e6578f97e61356ecd53d5e83588610..1a487ff95d4c0572737e4f972666229f12ef1e08 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1134,6 +1134,12 @@ static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2)
        }
 }
 
+static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2)
+{
+       TCP_SKB_CB(skb2)->eor = TCP_SKB_CB(skb)->eor;
+       TCP_SKB_CB(skb)->eor = 0;
+}
+
 /* Function to create two new TCP segments.  Shrinks the given segment
  * to the specified size and appends a new segment with the rest of the
  * packet to the list.  This won't be called frequently, I hope.
@@ -1179,6 +1185,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
        TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH);
        TCP_SKB_CB(buff)->tcp_flags = flags;
        TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked;
+       tcp_skb_fragment_eor(skb, buff);
 
        if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) {
                /* Copy and checksum data tail into the new buffer. */
@@ -1739,6 +1746,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
        /* This packet was never sent out yet, so no SACK bits. */
        TCP_SKB_CB(buff)->sacked = 0;
 
+       tcp_skb_fragment_eor(skb, buff);
+
        buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL;
        skb_split(skb, buff, len);
        tcp_fragment_tstamp(skb, buff);