summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMartin KaFai Lau <kafai@fb.com>2016-04-25 14:44:49 -0700
committerDavid S. Miller <davem@davemloft.net>2016-04-28 16:14:19 -0400
commita643b5d41c95164c14b111d19c05d6913bedb80b (patch)
treeafafddb31327dd4dbd718bb44d4b06cb4cbbd552
parentc134ecb87817ce70fd62b2dc48bb079c44fc08df (diff)
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>
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/ipv4/tcp_output.c4
2 files changed, 8 insertions, 0 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 70c370b93762..1fb19c91e091 100644
--- 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 b3a31b4df57c..77c6cbb897e6 100644
--- 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) {