From 76a9ebe811fb3d0605cb084f1ae6be5610541865 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Oct 2018 09:37:53 -0700 Subject: net: extend sk_pacing_rate to unsigned long sk_pacing_rate has beed introduced as a u32 field in 2013, effectively limiting per flow pacing to 34Gbit. We believe it is time to allow TCP to pace high speed flows on 64bit hosts, as we now can reach 100Gbit on one TCP flow. This patch adds no cost for 32bit kernels. The tcpi_pacing_rate and tcpi_max_pacing_rate were already exported as 64bit, so iproute2/ss command require no changes. Unfortunately the SO_MAX_PACING_RATE socket option will stay 32bit and we will need to add a new option to let applications control high pacing rates. State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 1787144 10.246.9.76:49992 10.246.9.77:36741 timer:(on,003ms,0) ino:91863 sk:2 <-> skmem:(r0,rb540000,t66440,tb2363904,f605944,w1822984,o0,bl0,d0) ts sack bbr wscale:8,8 rto:201 rtt:0.057/0.006 mss:1448 rcvmss:536 advmss:1448 cwnd:138 ssthresh:178 bytes_acked:256699822585 segs_out:177279177 segs_in:3916318 data_segs_out:177279175 bbr:(bw:31276.8Mbps,mrtt:0,pacing_gain:1.25,cwnd_gain:2) send 28045.5Mbps lastrcv:73333 pacing_rate 38705.0Mbps delivery_rate 22997.6Mbps busy:73333ms unacked:135 retrans:0/157 rcv_space:14480 notsent:2085120 minrtt:0.013 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'net/ipv4/tcp_output.c') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f14df66a0c85..f4aa4109334a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -991,14 +991,14 @@ static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb) skb->skb_mstamp_ns = tp->tcp_wstamp_ns; if (sk->sk_pacing_status != SK_PACING_NONE) { - u32 rate = sk->sk_pacing_rate; + unsigned long rate = sk->sk_pacing_rate; /* Original sch_fq does not pace first 10 MSS * Note that tp->data_segs_out overflows after 2^32 packets, * this is a minor annoyance. */ - if (rate != ~0U && rate && tp->data_segs_out >= 10) { - tp->tcp_wstamp_ns += div_u64((u64)skb->len * NSEC_PER_SEC, rate); + if (rate != ~0UL && rate && tp->data_segs_out >= 10) { + tp->tcp_wstamp_ns += div64_ul((u64)skb->len * NSEC_PER_SEC, rate); tcp_internal_pacing(sk); } @@ -1704,8 +1704,9 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, { u32 bytes, segs; - bytes = min(sk->sk_pacing_rate >> sk->sk_pacing_shift, - sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); + bytes = min_t(unsigned long, + sk->sk_pacing_rate >> sk->sk_pacing_shift, + sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, * not one big TSO packet every 100 ms. @@ -2198,10 +2199,12 @@ static bool tcp_pacing_check(const struct sock *sk) static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, unsigned int factor) { - unsigned int limit; + unsigned long limit; - limit = max(2 * skb->truesize, sk->sk_pacing_rate >> sk->sk_pacing_shift); - limit = min_t(u32, limit, + limit = max_t(unsigned long, + 2 * skb->truesize, + sk->sk_pacing_rate >> sk->sk_pacing_shift); + limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); limit <<= factor; -- cgit v1.2.3