summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorMartin KaFai Lau <kafai@fb.com>2016-04-19 22:39:28 -0700
committerDavid S. Miller <davem@davemloft.net>2016-04-21 14:40:55 -0400
commit082ac2d51d9f19ec1c29bdaaaf7fb49889e4fade (patch)
treef867d0e38df6b0ac9ff8fa422185f0536d82cb3e /net
parent3fa88c51c73a67e7eeda1fcafd809f9185790b31 (diff)
downloadlinux-082ac2d51d9f19ec1c29bdaaaf7fb49889e4fade.tar.bz2
tcp: Merge tx_flags and tskey in tcp_collapse_retrans
If two skbs are merged/collapsed during retransmission, the current logic does not merge the tx_flags and tskey. The end result is the SCM_TSTAMP_ACK timestamp could be missing for a packet. The patch: 1. Merge the tx_flags 2. Overwrite the prev_skb's tskey with the next_skb's tskey BPF Output Before: ~~~~~~ <no-output-due-to-missing-tstamp-event> BPF Output After: ~~~~~~ packetdrill-2092 [001] d.s. 453.998486: : ee_data:1459 Packetdrill Script: ~~~~~~ +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 write(4, ..., 730) = 730 +0 setsockopt(4, SOL_SOCKET, 37, [2688], 4) = 0 0.200 write(4, ..., 730) = 730 +0 setsockopt(4, SOL_SOCKET, 37, [2176], 4) = 0 0.200 write(4, ..., 11680) = 11680 +0 setsockopt(4, SOL_SOCKET, 37, [2688], 4) = 0 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 1461:2921,nop,nop> 0.300 < . 1:1(0) ack 1 win 257 <sack 1461:4381,nop,nop> 0.300 < . 1:1(0) ack 1 win 257 <sack 1461:5841,nop,nop> 0.300 > P. 1:1461(1460) 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: Soheil Hassas Yeganeh <soheil@google.com> Tested-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/tcp_output.c16
1 files changed, 16 insertions, 0 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7d2dc015cd19..5bc3c3062672 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2441,6 +2441,20 @@ u32 __tcp_select_window(struct sock *sk)
return window;
}
+static void tcp_skb_collapse_tstamp(struct sk_buff *skb,
+ const struct sk_buff *next_skb)
+{
+ const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb);
+ u8 tsflags = next_shinfo->tx_flags & SKBTX_ANY_TSTAMP;
+
+ if (unlikely(tsflags)) {
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+ shinfo->tx_flags |= tsflags;
+ shinfo->tskey = next_shinfo->tskey;
+ }
+}
+
/* Collapses two adjacent SKB's during retransmission. */
static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
{
@@ -2484,6 +2498,8 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb));
+ tcp_skb_collapse_tstamp(skb, next_skb);
+
sk_wmem_free_skb(sk, next_skb);
}