From 0a6b2a1dc2a2105f178255fe495eb914b09cb37a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 19 Feb 2018 11:56:47 -0800 Subject: tcp: switch to GSO being always on Oleksandr Natalenko reported performance issues with BBR without FQ packet scheduler that were root caused to lack of SG and GSO/TSO on his configuration. In this mode, TCP internal pacing has to setup a high resolution timer for each MSS sent. We could implement in TCP a strategy similar to the one adopted in commit fefa569a9d4b ("net_sched: sch_fq: account for schedule/timers drifts") or decide to finally switch TCP stack to a GSO only mode. This has many benefits : 1) Most TCP developments are done with TSO in mind. 2) Less high-resolution timers needs to be armed for TCP-pacing 3) GSO can benefit of xmit_more hint 4) Receiver GRO is more effective (as if TSO was used for real on sender) -> Lower ACK traffic 5) Write queues have less overhead (one skb holds about 64KB of payload) 6) SACK coalescing just works. 7) rtx rb-tree contains less packets, SACK is cheaper. This patch implements the minimum patch, but we can remove some legacy code as follow ups. Tested: On 40Gbit link, one netperf -t TCP_STREAM BBR+fq: sg on: 26 Gbits/sec sg off: 15.7 Gbits/sec (was 2.3 Gbit before patch) BBR+pfifo_fast: sg on: 24.2 Gbits/sec sg off: 14.9 Gbits/sec (was 0.66 Gbit before patch !!! ) BBR+fq_codel: sg on: 24.4 Gbits/sec sg off: 15 Gbits/sec (was 0.66 Gbit before patch !!! ) Signed-off-by: Eric Dumazet Reported-by: Oleksandr Natalenko Signed-off-by: David S. Miller --- include/net/sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 3aa7b7d6e6c7..f0f576ff5603 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -417,6 +417,7 @@ struct sock { struct page_frag sk_frag; netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; + netdev_features_t sk_route_forced_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; -- cgit v1.2.3 From dead7cdb0daec58490891e59f4fae0c5c76fa5f3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 19 Feb 2018 11:56:49 -0800 Subject: tcp: remove sk_check_csum_caps() Since TCP relies on GSO, we do not need this helper anymore. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 9 --------- net/ipv4/tcp.c | 11 +++-------- 2 files changed, 3 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index f0f576ff5603..b9624581d639 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1863,15 +1863,6 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) sk->sk_route_caps &= ~flags; } -static inline bool sk_check_csum_caps(struct sock *sk) -{ - return (sk->sk_route_caps & NETIF_F_HW_CSUM) || - (sk->sk_family == PF_INET && - (sk->sk_route_caps & NETIF_F_IP_CSUM)) || - (sk->sk_family == PF_INET6 && - (sk->sk_route_caps & NETIF_F_IPV6_CSUM)); -} - static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6f35c12af85a..7c4140271887 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1063,8 +1063,7 @@ EXPORT_SYMBOL_GPL(do_tcp_sendpages); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { - if (!(sk->sk_route_caps & NETIF_F_SG) || - !sk_check_csum_caps(sk)) + if (!(sk->sk_route_caps & NETIF_F_SG)) return sock_no_sendpage_locked(sk, page, offset, size, flags); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ @@ -1190,7 +1189,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - zc = sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG; + zc = sk->sk_route_caps & NETIF_F_SG; if (!zc) uarg->zerocopy = 0; } @@ -1287,11 +1286,7 @@ new_segment: goto wait_for_memory; process_backlog = true; - /* - * Check whether we can use HW checksum. - */ - if (sk_check_csum_caps(sk)) - skb->ip_summed = CHECKSUM_PARTIAL; + skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); copy = size_goal; -- cgit v1.2.3