From mboxrd@z Thu Jan 1 00:00:00 1970 From: Alexander Drozdov Subject: Re: [net-next,1/2] net: Set sk_txhash from a random number Date: Tue, 8 Dec 2015 11:33:26 +0300 Message-ID: <566695D6.6060603@gmail.com> References: <1438124526-2129341-2-git-send-email-tom@herbertland.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: kernel-team@fb.com To: Tom Herbert , davem@davemloft.net, netdev@vger.kernel.org Return-path: Received: from mail-lb0-f178.google.com ([209.85.217.178]:32803 "EHLO mail-lb0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756031AbbLHIda (ORCPT ); Tue, 8 Dec 2015 03:33:30 -0500 Received: by lbbkw15 with SMTP id kw15so6978551lbb.0 for ; Tue, 08 Dec 2015 00:33:29 -0800 (PST) In-Reply-To: <1438124526-2129341-2-git-send-email-tom@herbertland.com> Sender: netdev-owner@vger.kernel.org List-ID: 29.07.2015 02:02, Tom Herbert wrote: > This patch creates sk_set_txhash and eliminates protocol specific > inet_set_txhash and ip6_set_txhash. sk_set_txhash simply sets a > random number instead of performing flow dissection. sk_set_txash > is also allowed to be called multiple times for the same socket, > we'll need this when redoing the hash for negative routing advice. It seems that this patch and some previous txhash-related ones break af_packet hash features for outgoing packets: - PACKET_FANOUT_HASH - TP_FT_REQ_FILL_RXHASH af_packet now thinks that hashes for for incoming and outgoing packets of the same TCP stream differ. That is true for TCP sessions initiated by the host. > > Signed-off-by: Tom Herbert > --- > include/net/ip.h | 16 ---------------- > include/net/ipv6.h | 19 ------------------- > include/net/sock.h | 8 ++++++++ > net/ipv4/datagram.c | 2 +- > net/ipv4/tcp_ipv4.c | 4 ++-- > net/ipv6/datagram.c | 2 +- > net/ipv6/tcp_ipv6.c | 4 ++-- > 7 files changed, 14 insertions(+), 41 deletions(-) > > diff --git a/include/net/ip.h b/include/net/ip.h > index d5fe9f2..bee5f35 100644 > --- a/include/net/ip.h > +++ b/include/net/ip.h > @@ -370,22 +370,6 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, > flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; > } > > -static inline void inet_set_txhash(struct sock *sk) > -{ > - struct inet_sock *inet = inet_sk(sk); > - struct flow_keys keys; > - > - memset(&keys, 0, sizeof(keys)); > - > - keys.addrs.v4addrs.src = inet->inet_saddr; > - keys.addrs.v4addrs.dst = inet->inet_daddr; > - keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; > - keys.ports.src = inet->inet_sport; > - keys.ports.dst = inet->inet_dport; > - > - sk->sk_txhash = flow_hash_from_keys(&keys); > -} > - > static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) > { > const struct iphdr *iph = skb_gro_network_header(skb); > diff --git a/include/net/ipv6.h b/include/net/ipv6.h > index 82dbdb0..7c79798 100644 > --- a/include/net/ipv6.h > +++ b/include/net/ipv6.h > @@ -707,25 +707,6 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, > } > > #if IS_ENABLED(CONFIG_IPV6) > -static inline void ip6_set_txhash(struct sock *sk) > -{ > - struct inet_sock *inet = inet_sk(sk); > - struct ipv6_pinfo *np = inet6_sk(sk); > - struct flow_keys keys; > - > - memset(&keys, 0, sizeof(keys)); > - > - memcpy(&keys.addrs.v6addrs.src, &np->saddr, > - sizeof(keys.addrs.v6addrs.src)); > - memcpy(&keys.addrs.v6addrs.dst, &sk->sk_v6_daddr, > - sizeof(keys.addrs.v6addrs.dst)); > - keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; > - keys.ports.src = inet->inet_sport; > - keys.ports.dst = inet->inet_dport; > - > - sk->sk_txhash = flow_hash_from_keys(&keys); > -} > - > static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, > __be32 flowlabel, bool autolabel) > { > diff --git a/include/net/sock.h b/include/net/sock.h > index 4353ef7..fe735c4 100644 > --- a/include/net/sock.h > +++ b/include/net/sock.h > @@ -1687,6 +1687,14 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) > kuid_t sock_i_uid(struct sock *sk); > unsigned long sock_i_ino(struct sock *sk); > > +static inline void sk_set_txhash(struct sock *sk) > +{ > + sk->sk_txhash = prandom_u32(); > + > + if (unlikely(!sk->sk_txhash)) > + sk->sk_txhash = 1; > +} > + > static inline struct dst_entry * > __sk_dst_get(struct sock *sk) > { > diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c > index 574fad9..f915abf 100644 > --- a/net/ipv4/datagram.c > +++ b/net/ipv4/datagram.c > @@ -74,7 +74,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len > inet->inet_daddr = fl4->daddr; > inet->inet_dport = usin->sin_port; > sk->sk_state = TCP_ESTABLISHED; > - inet_set_txhash(sk); > + sk_set_txhash(sk); > inet->inet_id = jiffies; > > sk_dst_set(sk, &rt->dst); > diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c > index 486ba96..d27eb54 100644 > --- a/net/ipv4/tcp_ipv4.c > +++ b/net/ipv4/tcp_ipv4.c > @@ -222,7 +222,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) > if (err) > goto failure; > > - inet_set_txhash(sk); > + sk_set_txhash(sk); > > rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, > inet->inet_sport, inet->inet_dport, sk); > @@ -1277,7 +1277,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, > newinet->mc_ttl = ip_hdr(skb)->ttl; > newinet->rcv_tos = ip_hdr(skb)->tos; > inet_csk(newsk)->icsk_ext_hdr_len = 0; > - inet_set_txhash(newsk); > + sk_set_txhash(newsk); > if (inet_opt) > inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; > newinet->inet_id = newtp->write_seq ^ jiffies; > diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c > index 2572a32..9aadd57 100644 > --- a/net/ipv6/datagram.c > +++ b/net/ipv6/datagram.c > @@ -199,7 +199,7 @@ ipv4_connected: > NULL); > > sk->sk_state = TCP_ESTABLISHED; > - ip6_set_txhash(sk); > + sk_set_txhash(sk); > out: > fl6_sock_release(flowlabel); > return err; > diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c > index d540846..52dd0d9 100644 > --- a/net/ipv6/tcp_ipv6.c > +++ b/net/ipv6/tcp_ipv6.c > @@ -276,7 +276,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, > if (err) > goto late_failure; > > - ip6_set_txhash(sk); > + sk_set_txhash(sk); > > if (!tp->write_seq && likely(!tp->repair)) > tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, > @@ -1090,7 +1090,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, > newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; > newsk->sk_bound_dev_if = ireq->ir_iif; > > - ip6_set_txhash(newsk); > + sk_set_txhash(newsk); > > /* Now IPv6 options... >