summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_output.c
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-12-09 21:27:48 -0800
committerDavid S. Miller <davem@davemloft.net>2018-12-09 21:43:31 -0800
commit4cc1feeb6ffc2799f8badb4dea77c637d340cb0d (patch)
treec41c1e4c05f016298246ad7b3a6034dc1e65c154 /net/ipv4/tcp_output.c
parenta60956ed72f7b715e9918df93fcf2f63a30fdda1 (diff)
parent40e020c129cfc991e8ab4736d2665351ffd1468d (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Several conflicts, seemingly all over the place. I used Stephen Rothwell's sample resolutions for many of these, if not just to double check my own work, so definitely the credit largely goes to him. The NFP conflict consisted of a bug fix (moving operations past the rhashtable operation) while chaning the initial argument in the function call in the moved code. The net/dsa/master.c conflict had to do with a bug fix intermixing of making dsa_master_set_mtu() static with the fixing of the tagging attribute location. cls_flower had a conflict because the dup reject fix from Or overlapped with the addition of port range classifiction. __set_phy_supported()'s conflict was relatively easy to resolve because Andrew fixed it in both trees, so it was just a matter of taking the net-next copy. Or at least I think it was :-) Joe Stringer's fix to the handling of netns id 0 in bpf_sk_lookup() intermixed with changes on how the sdif and caller_net are calculated in these code paths in net-next. The remaining BPF conflicts were largely about the addition of the __bpf_md_ptr stuff in 'net' overlapping with adjustments and additions to the relevant data structure where the MD pointer macros are used. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_output.c')
-rw-r--r--net/ipv4/tcp_output.c45
1 files changed, 32 insertions, 13 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d3b691f3a9e8..c31badfee806 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1904,7 +1904,9 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
* This algorithm is from John Heffner.
*/
static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
- bool *is_cwnd_limited, u32 max_segs)
+ bool *is_cwnd_limited,
+ bool *is_rwnd_limited,
+ u32 max_segs)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 send_win, cong_win, limit, in_flight;
@@ -1913,9 +1915,6 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
int win_divisor;
s64 delta;
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
- goto send_now;
-
if (icsk->icsk_ca_state >= TCP_CA_Recovery)
goto send_now;
@@ -1981,10 +1980,27 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
goto send_now;
- /* Ok, it looks like it is advisable to defer. */
+ /* Ok, it looks like it is advisable to defer.
+ * Three cases are tracked :
+ * 1) We are cwnd-limited
+ * 2) We are rwnd-limited
+ * 3) We are application limited.
+ */
+ if (cong_win < send_win) {
+ if (cong_win <= skb->len) {
+ *is_cwnd_limited = true;
+ return true;
+ }
+ } else {
+ if (send_win <= skb->len) {
+ *is_rwnd_limited = true;
+ return true;
+ }
+ }
- if (cong_win < send_win && cong_win <= skb->len)
- *is_cwnd_limited = true;
+ /* If this packet won't get more data, do not wait. */
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ goto send_now;
return true;
@@ -2365,7 +2381,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
} else {
if (!push_one &&
tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
- max_segs))
+ &is_rwnd_limited, max_segs))
break;
}
@@ -2503,15 +2519,18 @@ void tcp_send_loss_probe(struct sock *sk)
goto rearm_timer;
}
skb = skb_rb_last(&sk->tcp_rtx_queue);
+ if (unlikely(!skb)) {
+ WARN_ONCE(tp->packets_out,
+ "invalid inflight: %u state %u cwnd %u mss %d\n",
+ tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+ inet_csk(sk)->icsk_pending = 0;
+ return;
+ }
/* At most one outstanding TLP retransmission. */
if (tp->tlp_high_seq)
goto rearm_timer;
- /* Retransmit last segment. */
- if (WARN_ON(!skb))
- goto rearm_timer;
-
if (skb_still_in_host_queue(sk, skb))
goto rearm_timer;
@@ -2929,7 +2948,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
trace_tcp_retransmit_skb(sk, skb);
} else if (err != -EBUSY) {
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs);
}
return err;
}