diff options
Diffstat (limited to 'net/ipv4')
40 files changed, 1779 insertions, 395 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 50d6a9b49f6c..300b06888fdf 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -640,6 +640,21 @@ config TCP_CONG_CDG D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg +config TCP_CONG_BBR + tristate "BBR TCP" + default n + ---help--- + + BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to + maximize network utilization and minimize queues. It builds an explicit + model of the the bottleneck delivery rate and path round-trip + propagation delay. It tolerates packet loss and delay unrelated to + congestion. It can operate over LAN, WAN, cellular, wifi, or cable + modem links. It can coexist with flows that use loss-based congestion + control, and can operate with shallow buffers, deep buffers, + bufferbloat, policers, or AQM schemes that do not provide a delay + signal. It requires the fq ("Fair Queue") pacing packet scheduler. + choice prompt "Default TCP congestion control" default DEFAULT_CUBIC @@ -674,6 +689,9 @@ choice config DEFAULT_CDG bool "CDG" if TCP_CONG_CDG=y + config DEFAULT_BBR + bool "BBR" if TCP_CONG_BBR=y + config DEFAULT_RENO bool "Reno" endchoice diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 24629b6f57cc..bc6a6c8b9bcd 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,7 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ - tcp_recovery.o \ + tcp_rate.o tcp_recovery.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o \ @@ -41,6 +41,7 @@ obj-$(CONFIG_INET_DIAG) += inet_diag.o obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o +obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e94b47be0019..1effc986739e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1192,7 +1192,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { - bool udpfrag = false, fixedid = false, encap; + bool udpfrag = false, fixedid = false, gso_partial, encap; struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; unsigned int offset = 0; @@ -1245,6 +1245,8 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (IS_ERR_OR_NULL(segs)) goto out; + gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); + skb = segs; do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); @@ -1259,9 +1261,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, iph->id = htons(id); id += skb_shinfo(skb)->gso_segs; } - tot_len = skb_shinfo(skb)->gso_size + - SKB_GSO_CB(skb)->data_offset + - skb->head - (unsigned char *)iph; + + if (gso_partial) + tot_len = skb_shinfo(skb)->gso_size + + SKB_GSO_CB(skb)->data_offset + + skb->head - (unsigned char *)iph; + else + tot_len = skb->len - nhoff; } else { if (!fixedid) iph->id = htons(id++); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 415e117967c7..062a67ca9a21 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2232,7 +2232,7 @@ static struct devinet_sysctl_table { }; static int __devinet_sysctl_register(struct net *net, char *dev_name, - struct ipv4_devconf *p) + int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; @@ -2255,6 +2255,8 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, goto free; p->sysctl = t; + + inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p); return 0; free: @@ -2286,7 +2288,7 @@ static int devinet_sysctl_register(struct in_device *idev) if (err) return err; err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, - &idev->cnf); + idev->dev->ifindex, &idev->cnf); if (err) neigh_sysctl_unregister(idev->arp_parms); return err; @@ -2347,11 +2349,12 @@ static __net_init int devinet_init_net(struct net *net) } #ifdef CONFIG_SYSCTL - err = __devinet_sysctl_register(net, "all", all); + err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; - err = __devinet_sysctl_register(net, "default", dflt); + err = __devinet_sysctl_register(net, "default", + NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 317c31939732..4e56a4c20a3c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -503,6 +503,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; + cfg->fc_table = l3mdev_fib_table(dev); if (colon) { struct in_ifaddr *ifa; struct in_device *in_dev = __in_dev_get_rtnl(dev); @@ -1021,7 +1022,7 @@ no_promotions: * First of all, we scan fib_info list searching * for stray nexthop entries, then ignite fib_flush. */ - if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local)) + if (fib_sync_down_addr(dev, ifa->ifa_local)) fib_flush(dev_net(dev)); } } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 6e9ea69e5f75..770bebed6b28 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -56,6 +56,9 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, }; int err; + /* update flow if oif or iif point to device enslaved to l3mdev */ + l3mdev_update_flow(net, flowi4_to_flowi(flp)); + err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg); #ifdef CONFIG_IP_ROUTE_CLASSID if (arg.rule) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 8066ccc48a17..388d3e21629b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1057,6 +1057,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_priority = cfg->fc_priority; fi->fib_prefsrc = cfg->fc_prefsrc; fi->fib_type = cfg->fc_type; + fi->fib_tb_id = cfg->fc_table; fi->fib_nhs = nhs; change_nexthops(fi) { @@ -1337,18 +1338,21 @@ nla_put_failure: * referring to it. * - device went down -> we must shutdown all nexthops going via it. */ -int fib_sync_down_addr(struct net *net, __be32 local) +int fib_sync_down_addr(struct net_device *dev, __be32 local) { int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + struct net *net = dev_net(dev); + int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) return 0; hlist_for_each_entry(fi, head, fib_lhash) { - if (!net_eq(fi->fib_net, net)) + if (!net_eq(fi->fib_net, net) || + fi->fib_tb_id != tb_id) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e2ffc2a5c7db..241f27bbd7ad 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1081,7 +1081,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; - unsigned int nlflags = 0; + u16 nlflags = NLM_F_EXCL; struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; @@ -1126,6 +1126,8 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) if (cfg->fc_nlflags & NLM_F_EXCL) goto out; + nlflags &= ~NLM_F_EXCL; + /* We have 2 goals: * 1. Find exact match for type, scope, fib_info to avoid * duplicate routes @@ -1151,6 +1153,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) struct fib_info *fi_drop; u8 state; + nlflags |= NLM_F_REPLACE; fa = fa_first; if (fa_match) { if (fa == fa_match) @@ -1191,7 +1194,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, - tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); + tb->tb_id, &cfg->fc_nlinfo, nlflags); goto succeeded; } @@ -1203,7 +1206,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) goto out; if (cfg->fc_nlflags & NLM_F_APPEND) - nlflags = NLM_F_APPEND; + nlflags |= NLM_F_APPEND; else fa = fa_first; } @@ -1211,6 +1214,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; + nlflags |= NLM_F_CREATE; err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index ecd1e09dbbf1..96e0efecefa6 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -24,7 +24,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; - bool need_csum, ufo; + bool need_csum, ufo, gso_partial; if (!skb->encapsulation) goto out; @@ -69,6 +69,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, goto out; } + gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); + outer_hlen = skb_tnl_header_len(skb); gre_offset = outer_hlen - tnl_hlen; skb = segs; @@ -96,7 +98,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); - if (skb_is_gso(skb)) { + if (gso_partial) { unsigned int partial_adj; /* Adjust checksum to account for the fact that diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index abfbe492ebfe..e4d16fc5bbb3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -99,6 +99,7 @@ static size_t inet_sk_attr_size(void) + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(4) /* INET_DIAG_MARK */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -109,7 +110,8 @@ static size_t inet_sk_attr_size(void) int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, - struct user_namespace *user_ns) + struct user_namespace *user_ns, + bool net_admin) { const struct inet_sock *inet = inet_sk(sk); @@ -136,6 +138,9 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + goto errout; + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -149,7 +154,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { const struct tcp_congestion_ops *ca_ops; const struct inet_diag_handler *handler; @@ -175,7 +181,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_timer = 0; r->idiag_retrans = 0; - if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns)) + if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) goto errout; if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { @@ -274,10 +280,11 @@ static int inet_csk_diag_fill(struct sock *sk, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { - return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, - user_ns, portid, seq, nlmsg_flags, unlh); + return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns, + portid, seq, nlmsg_flags, unlh, net_admin); } static int inet_twsk_diag_fill(struct sock *sk, @@ -319,8 +326,9 @@ static int inet_twsk_diag_fill(struct sock *sk, static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, bool net_admin) { + struct request_sock *reqsk = inet_reqsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; @@ -334,7 +342,7 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, inet_diag_msg_common_fill(r, sk); r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; - r->idiag_retrans = inet_reqsk(sk)->num_retrans; + r->idiag_retrans = reqsk->num_retrans; BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); @@ -346,6 +354,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_uid = 0; r->idiag_inode = 0; + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, + inet_rsk(reqsk)->ir_mark)) + return -EMSGSIZE; + nlmsg_end(skb, nlh); return 0; } @@ -354,7 +366,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *r, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill(sk, skb, portid, seq, @@ -362,10 +374,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, portid, seq, - nlmsg_flags, unlh); + nlmsg_flags, unlh, net_admin); return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, - nlmsg_flags, unlh); + nlmsg_flags, unlh, net_admin); } struct sock *inet_diag_find_one_icsk(struct net *net, @@ -435,7 +447,8 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); @@ -796,7 +809,8 @@ static int inet_csk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, - const struct nlattr *bc) + const struct nlattr *bc, + bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -804,7 +818,8 @@ static int inet_csk_diag_dump(struct sock *sk, return inet_csk_diag_fill(sk, skb, r, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, + net_admin); } static void twsk_build_assert(void) @@ -840,6 +855,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, struct net *net = sock_net(skb->sk); int i, num, s_i, s_num; u32 idiag_states = r->idiag_states; + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); if (idiag_states & TCPF_SYN_RECV) idiag_states |= TCPF_NEW_SYN_RECV; @@ -880,7 +896,8 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, cb->args[3] > 0) goto next_listen; - if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) { + if (inet_csk_diag_dump(sk, skb, cb, r, + bc, net_admin) < 0) { spin_unlock_bh(&ilb->lock); goto done; } @@ -948,7 +965,7 @@ skip_listen_ht: sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh); + cb->nlh, net_admin); if (res < 0) { spin_unlock_bh(lock); goto done; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 113cc43df789..576f705d8180 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -246,25 +246,6 @@ static void gre_err(struct sk_buff *skb, u32 info) ipgre_err(skb, info, &tpi); } -static __be64 key_to_tunnel_id(__be32 key) -{ -#ifdef __BIG_ENDIAN - return (__force __be64)((__force u32)key); -#else - return (__force __be64)((__force u64)key << 32); -#endif -} - -/* Returns the least-significant 32 bits of a __be64. */ -static __be32 tunnel_id_to_key(__be64 x) -{ -#ifdef __BIG_ENDIAN - return (__force __be32)x; -#else - return (__force __be32)((__force u64)x >> 32); -#endif -} - static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { @@ -290,7 +271,7 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, __be64 tun_id; flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); - tun_id = key_to_tunnel_id(tpi->key); + tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; @@ -446,7 +427,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); gre_build_header(skb, tunnel_hlen, flags, proto, - tunnel_id_to_key(tun_info->key.tun_id), 0); + tunnel_id_to_key32(tun_info->key.tun_id), 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 4b351af3e67b..d6feabb03516 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -312,6 +312,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; + struct net_device *dev = skb->dev; /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -341,7 +342,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) */ if (!skb_valid_dst(skb)) { int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, skb->dev); + iph->tos, dev); if (unlikely(err)) { if (err == -EXDEV) __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); @@ -370,7 +371,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) __IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len); } else if (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + struct in_device *in_dev = __in_dev_get_rcu(dev); /* RFC 1122 3.3.6: * diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 65569274efb8..05d105832bdb 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -99,6 +99,14 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) iph->tot_len = htons(skb->len); ip_send_check(iph); + + /* if egress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip_out(sk, skb); + if (unlikely(!skb)) + return 0; + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); @@ -490,7 +498,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) +#if IS_ENABLED(CONFIG_IP_VS) to->ipvs_property = from->ipvs_property; #endif skb_copy_secmark(to, from); @@ -1574,8 +1582,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, } oif = arg->bound_dev_if; - if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) - oif = skb->skb_iif; + oif = oif ? : skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark), diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 71a52f4d4cff..af4919792b6a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -284,9 +284,12 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->ttl = val; break; case IP_TOS: - if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + if (cmsg->cmsg_len == CMSG_LEN(sizeof(int))) + val = *(int *)CMSG_DATA(cmsg); + else if (cmsg->cmsg_len == CMSG_LEN(sizeof(u8))) + val = *(u8 *)CMSG_DATA(cmsg); + else return -EINVAL; - val = *(int *)CMSG_DATA(cmsg); if (val < 0 || val > 255) return -EINVAL; ipc->tos = val; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 95649ebd2874..5719d6ba0824 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -55,6 +55,7 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/udp.h> +#include <net/dst_metadata.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -546,6 +547,81 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + u32 headroom = sizeof(struct iphdr); + struct ip_tunnel_info *tun_info; + const struct ip_tunnel_key *key; + const struct iphdr *inner_iph; + struct rtable *rt; + struct flowi4 fl4; + __be16 df = 0; + u8 tos, ttl; + + tun_info = skb_tunnel_info(skb); + if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || + ip_tunnel_info_af(tun_info) != AF_INET)) + goto tx_error; + key = &tun_info->key; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + inner_iph = (const struct iphdr *)skb_inner_network_header(skb); + tos = key->tos; + if (tos == 1) { + if (skb->protocol == htons(ETH_P_IP)) + tos = inner_iph->tos; + else if (skb->protocol == htons(ETH_P_IPV6)) + tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); + } + init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, + RT_TOS(tos), tunnel->parms.link); + if (tunnel->encap.type != TUNNEL_ENCAP_NONE) + goto tx_error; + rt = ip_route_output_key(tunnel->net, &fl4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error; + } + if (rt->dst.dev == dev) { + ip_rt_put(rt); + dev->stats.collisions++; + goto tx_error; + } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); + ttl = key->ttl; + if (ttl == 0) { + if (skb->protocol == htons(ETH_P_IP)) + ttl = inner_iph->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; + else + ttl = ip4_dst_hoplimit(&rt->dst); + } + if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + else if (skb->protocol == htons(ETH_P_IP)) + df = inner_iph->frag_off & htons(IP_DF); + headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; + if (headroom > dev->needed_headroom) + dev->needed_headroom = headroom; + + if (skb_cow_head(skb, dev->needed_headroom)) { + ip_rt_put(rt); + goto tx_dropped; + } + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos, + key->ttl, df, !net_eq(tunnel->net, dev_net(dev))); + return; +tx_error: + dev->stats.tx_errors++; + goto kfree; +tx_dropped: + dev->stats.tx_dropped++; +kfree: + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(ip_md_tunnel_xmit); + void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 0f227db0e9ac..777bc1883870 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -69,7 +69,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_scrub_packet(skb, xnet); - skb_clear_hash(skb); + skb_clear_hash_if_not_l4(skb); skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cc701fa70b12..5d7944f394d9 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -88,6 +88,7 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) struct net_device *dev; struct pcpu_sw_netstats *tstats; struct xfrm_state *x; + struct xfrm_mode *inner_mode; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; u32 orig_mark = skb->mark; int ret; @@ -105,7 +106,19 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) } x = xfrm_input_state(skb); - family = x->inner_mode->afinfo->family; + + inner_mode = x->inner_mode; + + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) { + XFRM_INC_STATS(dev_net(skb->dev), + LINUX_MIB_XFRMINSTATEMODEERROR); + return -EINVAL; + } + } + + family = inner_mode->afinfo->family; skb->mark = be32_to_cpu(tunnel->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 4ae3f8e6c6cc..c9392589c415 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -115,6 +115,7 @@ #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/dst_metadata.h> static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); @@ -193,6 +194,7 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -216,7 +218,12 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; - return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); + if (tunnel->collect_md) { + tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); + if (!tun_dst) + return 0; + } + return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } return -1; @@ -270,7 +277,10 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, ipproto); - ip_tunnel_xmit(skb, dev, tiph, ipproto); + if (tunnel->collect_md) + ip_md_tunnel_xmit(skb, dev, ipproto); + else + ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: @@ -380,13 +390,14 @@ static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) } static void ipip_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm *parms, bool *collect_md) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPIP; parms->iph.ihl = 5; + *collect_md = false; if (!data) return; @@ -414,6 +425,9 @@ static void ipip_netlink_parms(struct nlattr *data[], if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_IPTUN_COLLECT_METADATA]) + *collect_md = true; } /* This function returns true when ENCAP attributes are present in the nl msg */ @@ -453,18 +467,18 @@ static bool ipip_netlink_encap_parms(struct nlattr *data[], static int ipip_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { + struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; if (ipip_netlink_encap_parms(data, &ipencap)) { - struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } - ipip_netlink_parms(data, &p); + ipip_netlink_parms(data, &p, &t->collect_md); return ip_tunnel_newlink(dev, tb, &p); } @@ -473,6 +487,7 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], { struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + bool collect_md; if (ipip_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); @@ -482,7 +497,9 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], return err; } - ipip_netlink_parms(data, &p); + ipip_netlink_parms(data, &p, &collect_md); + if (collect_md) + return -EINVAL; if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) @@ -516,6 +533,8 @@ static size_t ipip_get_size(const struct net_device *dev) nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + + /* IFLA_IPTUN_COLLECT_METADATA */ + nla_total_size(0) + 0; } @@ -544,6 +563,9 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) tunnel->encap.flags)) goto nla_put_failure; + if (tunnel->collect_md) + if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) + goto nla_put_failure; return 0; nla_put_failure: @@ -562,6 +584,7 @@ static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, + [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static struct rtnl_link_ops ipip_link_ops __read_mostly = { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 26253328d227..a87bcd2d4a94 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2076,6 +2076,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct rta_mfc_stats mfcs; struct nlattr *mp_attr; struct rtnexthop *nhp; + unsigned long lastuse; int ct; /* If cache is unresolved, don't try to parse IIF and OIF */ @@ -2105,12 +2106,14 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, nla_nest_end(skb, mp_attr); + lastuse = READ_ONCE(c->mfc_un.res.lastuse); + lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; + mfcs.mfcs_packets = c->mfc_un.res.pkt; mfcs.mfcs_bytes = c->mfc_un.res.bytes; mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || - nla_put_u64_64bit(skb, RTA_EXPIRES, - jiffies_to_clock_t(c->mfc_un.res.lastuse), + nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), RTA_PAD)) return -EMSGSIZE; diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index 2375b0a8be46..30493beb611a 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -31,6 +31,7 @@ static unsigned int nf_route_table_hook(void *priv, __be32 saddr, daddr; u_int8_t tos; const struct iphdr *iph; + int err; /* root is playing with raw sockets. */ if (skb->len < sizeof(struct iphdr) || @@ -46,15 +47,17 @@ static unsigned int nf_route_table_hook(void *priv, tos = iph->tos; ret = nft_do_chain(&pkt, priv); - if (ret != NF_DROP && ret != NF_QUEUE) { + if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || iph->daddr != daddr || skb->mark != mark || - iph->tos != tos) - if (ip_route_me_harder(state->net, skb, RTN_UNSPEC)) - ret = NF_DROP; + iph->tos != tos) { + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + if (err < 0) + ret = NF_DROP_ERR(err); + } } return ret; } diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index c24f41c816b3..2c2553b9026c 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -46,6 +46,7 @@ static const struct nft_expr_ops nft_reject_ipv4_ops = { .eval = nft_reject_ipv4_eval, .init = nft_reject_init, .dump = nft_reject_dump, + .validate = nft_reject_validate, }; static struct nft_expr_type nft_reject_ipv4_type __read_mostly = { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 438f50c1a676..90a85c955872 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -606,12 +606,6 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); - if (!saddr && ipc.oif) { - err = l3mdev_get_saddr(net, ipc.oif, &fl4); - if (err < 0) - goto done; - } - if (!inet->hdrincl) { rfv.msg = msg; rfv.hlen = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3e992783c1d0..654a9af20136 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -476,12 +476,18 @@ u32 ip_idents_reserve(u32 hash, int segs) atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; u32 old = ACCESS_ONCE(*p_tstamp); u32 now = (u32)jiffies; - u32 delta = 0; + u32 new, delta = 0; if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); - return atomic_add_return(segs + delta, p_id) - segs; + /* Do not use atomic_add_return() as it makes UBSAN unhappy */ + do { + old = (u32)atomic_read(p_id); + new = old + delta + segs; + } while (atomic_cmpxchg(p_id, old, new) != old); + + return new - segs; } EXPORT_SYMBOL(ip_idents_reserve); @@ -1831,7 +1837,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, * Now we are ready to route packet. */ fl4.flowi4_oif = 0; - fl4.flowi4_iif = l3mdev_fib_oif_rcu(dev); + fl4.flowi4_iif = dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; @@ -2018,7 +2024,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res, return ERR_PTR(-EINVAL); if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) - if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK)) + if (ipv4_is_loopback(fl4->saddr) && + !(dev_out->flags & IFF_LOOPBACK) && + !netif_is_l3_master(dev_out)) return ERR_PTR(-EINVAL); if (ipv4_is_lbcast(fl4->daddr)) @@ -2148,7 +2156,6 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, unsigned int flags = 0; struct fib_result res; struct rtable *rth; - int master_idx; int orig_oif; int err = -ENETUNREACH; @@ -2158,9 +2165,6 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, orig_oif = fl4->flowi4_oif; - master_idx = l3mdev_master_ifindex_by_index(net, fl4->flowi4_oif); - if (master_idx) - fl4->flowi4_oif = master_idx; fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? @@ -2244,10 +2248,6 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } - - rth = l3mdev_get_rtable(dev_out, fl4); - if (rth) - goto out; } if (!fl4->daddr) { @@ -2265,8 +2265,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, if (err) { res.fi = NULL; res.table = NULL; - if (fl4->flowi4_oif && - !netif_index_is_l3_master(net, fl4->flowi4_oif)) { + if (fl4->flowi4_oif) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. @@ -2302,7 +2301,9 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, else fl4->saddr = fl4->daddr; } - dev_out = net->loopback_dev; + + /* L3 master device is the loopback for that domain */ + dev_out = l3mdev_master_dev_rcu(dev_out) ? : net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; @@ -2577,9 +2578,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; - if (netif_index_is_l3_master(net, fl4.flowi4_oif)) - fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF; - if (iif) { struct net_device *dev; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 77311a92275c..f253e5019d22 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -380,14 +380,14 @@ void tcp_init_sock(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - __skb_queue_head_init(&tp->out_of_order_queue); + tp->out_of_order_queue = RB_ROOT; tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - tp->rtt_min[0].rtt = ~0U; + minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -396,6 +396,9 @@ void tcp_init_sock(struct sock *sk) */ tp->snd_cwnd = TCP_INIT_CWND; + /* There's a bubble in the pipe until at least the first ACK. */ + tp->app_limited = ~0U; + /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ @@ -1014,23 +1017,40 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, flags); lock_sock(sk); + + tcp_rate_check_app_limited(sk); /* is sending application-limited? */ + res = do_tcp_sendpages(sk, page, offset, size, flags); release_sock(sk); return res; } EXPORT_SYMBOL(tcp_sendpage); -static inline int select_size(const struct sock *sk, bool sg) +/* Do not bother using a page frag for very small frames. + * But use this heuristic only for the first skb in write queue. + * + * Having no payload in skb->head allows better SACK shifting + * in tcp_shift_skb_data(), reducing sack/rack overhead, because + * write queue has less skbs. + * Each skb can hold up to MAX_SKB_FRAGS * 32Kbytes, or ~0.5 MB. + * This also speeds up tso_fragment(), since it wont fallback + * to tcp_fragment(). + */ +static int linear_payload_sz(bool first_skb) +{ + if (first_skb) + return SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER); + return 0; +} + +static int select_size(const struct sock *sk, bool sg, bool first_skb) { const struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache; if (sg) { if (sk_can_gso(sk)) { - /* Small frames wont use a full page: - * Payload will immediately follow tcp header. - */ - tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER); + tmp = linear_payload_sz(first_skb); } else { int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); @@ -1101,6 +1121,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + tcp_rate_check_app_limited(sk); /* is sending application-limited? */ + /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. @@ -1161,6 +1183,8 @@ restart: } if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { + bool first_skb; + new_segment: /* Allocate new segment. If the interface is SG, * allocate skb fitting to single page. @@ -1172,10 +1196,11 @@ new_segment: process_backlog = false; goto restart; } + first_skb = skb_queue_empty(&sk->sk_write_queue); skb = sk_stream_alloc_skb(sk, - select_size(sk, sg), + select_size(sk, sg, first_skb), sk->sk_allocation, - skb_queue_empty(&sk->sk_write_queue)); + first_skb); if (!skb) goto wait_for_memory; @@ -2243,7 +2268,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); tcp_write_queue_purge(sk); - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; @@ -2687,7 +2712,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_time_stamp, intv; unsigned int start; int notsent_bytes; u64 rate64; @@ -2777,6 +2802,15 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_in = tp->data_segs_in; info->tcpi_data_segs_out = tp->data_segs_out; + + info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; + rate = READ_ONCE(tp->rate_delivered); + intv = READ_ONCE(tp->rate_interval_us); + if (rate && intv) { + rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; + do_div(rate64, intv); + put_unaligned(rate64, &info->tcpi_delivery_rate); + } } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3244,11 +3278,12 @@ static void __init tcp_init_mem(void) void __init tcp_init(void) { - unsigned long limit; int max_rshare, max_wshare, cnt; + unsigned long limit; unsigned int i; - sock_skb_cb_check_size(sizeof(struct tcp_skb_cb)); + BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > + FIELD_SIZEOF(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c new file mode 100644 index 000000000000..0ea66c2c9344 --- /dev/null +++ b/net/ipv4/tcp_bbr.c @@ -0,0 +1,896 @@ +/* Bottleneck Bandwidth and RTT (BBR) congestion control + * + * BBR congestion control computes the sending rate based on the delivery + * rate (throughput) estimated from ACKs. In a nutshell: + * + * On each ACK, update our model of the network path: + * bottleneck_bandwidth = windowed_max(delivered / elapsed, 10 round trips) + * min_rtt = windowed_min(rtt, 10 seconds) + * pacing_rate = pacing_gain * bottleneck_bandwidth + * cwnd = max(cwnd_gain * bottleneck_bandwidth * min_rtt, 4) + * + * The core algorithm does not react directly to packet losses or delays, + * although BBR may adjust the size of next send per ACK when loss is + * observed, or adjust the sending rate if it estimates there is a + * traffic policer, in order to keep the drop rate reasonable. + * + * BBR is described in detail in: + * "BBR: Congestion-Based Congestion Control", + * Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh, + * Van Jacobson. ACM Queue, Vol. 14 No. 5, September-October 2016. + * + * There is a public e-mail list for discussing BBR development and testing: + * https://groups.google.com/forum/#!forum/bbr-dev + * + * NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, + * since pacing is integral to the BBR design and implementation. + * BBR without pacing would not function properly, and may incur unnecessary + * high packet loss rates. + */ +#include <linux/module.h> +#include <net/tcp.h> +#include <linux/inet_diag.h> +#include <linux/inet.h> +#include <linux/random.h> +#include <linux/win_minmax.h> + +/* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth + * estimation. The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps. + * This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32. + * Since the minimum window is >=4 packets, the lower bound isn't + * an issue. The upper bound isn't an issue with existing technologies. + */ +#define BW_SCALE 24 +#define BW_UNIT (1 << BW_SCALE) + +#define BBR_SCALE 8 /* scaling factor for fractions in BBR (e.g. gains) */ +#define BBR_UNIT (1 << BBR_SCALE) + +/* BBR has the following modes for deciding how fast to send: */ +enum bbr_mode { + BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */ + BBR_DRAIN, /* drain any queue created during startup */ + BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */ + BBR_PROBE_RTT, /* cut cwnd to min to probe min_rtt */ +}; + +/* BBR congestion control block */ +struct bbr { + u32 min_rtt_us; /* min RTT in min_rtt_win_sec window */ + u32 min_rtt_stamp; /* timestamp of min_rtt_us */ + u32 probe_rtt_done_stamp; /* end time for BBR_PROBE_RTT mode */ + struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ + u32 rtt_cnt; /* count of packet-timed rounds elapsed */ + u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ + struct skb_mstamp cycle_mstamp; /* time of this cycle phase start */ + u32 mode:3, /* current bbr_mode in state machine */ + prev_ca_state:3, /* CA state on previous ACK */ + packet_conservation:1, /* use packet conservation? */ + restore_cwnd:1, /* decided to revert cwnd to old value */ + round_start:1, /* start of packet-timed tx->ack round? */ + tso_segs_goal:7, /* segments we want in each skb we send */ + idle_restart:1, /* restarting after idle? */ + probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ + unused:5, + lt_is_sampling:1, /* taking long-term ("LT") samples now? */ + lt_rtt_cnt:7, /* round trips in long-term interval */ + lt_use_bw:1; /* use lt_bw as our bw estimate? */ + u32 lt_bw; /* LT est delivery rate in pkts/uS << 24 */ + u32 lt_last_delivered; /* LT intvl start: tp->delivered */ + u32 lt_last_stamp; /* LT intvl start: tp->delivered_mstamp */ + u32 lt_last_lost; /* LT intvl start: tp->lost */ + u32 pacing_gain:10, /* current gain for setting pacing rate */ + cwnd_gain:10, /* current gain for setting cwnd */ + full_bw_cnt:3, /* number of rounds without large bw gains */ + cycle_idx:3, /* current index in pacing_gain cycle array */ + unused_b:6; + u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ + u32 full_bw; /* recent bw, to estimate if pipe is full */ +}; + +#define CYCLE_LEN 8 /* number of phases in a pacing gain cycle */ + +/* Window length of bw filter (in rounds): */ +static const int bbr_bw_rtts = CYCLE_LEN + 2; +/* Window length of min_rtt filter (in sec): */ +static const u32 bbr_min_rtt_win_sec = 10; +/* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */ +static const u32 bbr_probe_rtt_mode_ms = 200; +/* Skip TSO below the following bandwidth (bits/sec): */ +static const int bbr_min_tso_rate = 1200000; + +/* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain + * that will allow a smoothly increasing pacing rate that will double each RTT + * and send the same number of packets per RTT that an un-paced, slow-starting + * Reno or CUBIC flow would: + */ +static const int bbr_high_gain = BBR_UNIT * 2885 / 1000 + 1; +/* The pacing gain of 1/high_gain in BBR_DRAIN is calculated to typically drain + * the queue created in BBR_STARTUP in a single round: + */ +static const int bbr_drain_gain = BBR_UNIT * 1000 / 2885; +/* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */ +static const int bbr_cwnd_gain = BBR_UNIT * 2; +/* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */ +static const int bbr_pacing_gain[] = { + BBR_UNIT * 5 / 4, /* probe for more available bw */ + BBR_UNIT * 3 / 4, /* drain queue and/or yield bw to other flows */ + BBR_UNIT, BBR_UNIT, BBR_UNIT, /* cruise at 1.0*bw to utilize pipe, */ + BBR_UNIT, BBR_UNIT, BBR_UNIT /* without creating excess queue... */ +}; +/* Randomize the starting gain cycling phase over N phases: */ +static const u32 bbr_cycle_rand = 7; + +/* Try to keep at least this many packets in flight, if things go smoothly. For + * smooth functioning, a sliding window protocol ACKing every other packet + * needs at least 4 packets in flight: + */ +static const u32 bbr_cwnd_min_target = 4; + +/* To estimate if BBR_STARTUP mode (i.e. high_gain) has filled pipe... */ +/* If bw has increased significantly (1.25x), there may be more bw available: */ +static const u32 bbr_full_bw_thresh = BBR_UNIT * 5 / 4; +/* But after 3 rounds w/o significant bw growth, estimate pipe is full: */ +static const u32 bbr_full_bw_cnt = 3; + +/* "long-term" ("LT") bandwidth estimator parameters... */ +/* The minimum number of rounds in an LT bw sampling interval: */ +static const u32 bbr_lt_intvl_min_rtts = 4; +/* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */ +static const u32 bbr_lt_loss_thresh = 50; +/* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */ +static const u32 bbr_lt_bw_ratio = BBR_UNIT / 8; +/* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */ +static const u32 bbr_lt_bw_diff = 4000 / 8; +/* If we estimate we're policed, use lt_bw for this many round trips: */ +static const u32 bbr_lt_bw_max_rtts = 48; + +/* Do we estimate that STARTUP filled the pipe? */ +static bool bbr_full_bw_reached(const struct sock *sk) +{ + const struct bbr *bbr = inet_csk_ca(sk); + + return bbr->full_bw_cnt >= bbr_full_bw_cnt; +} + +/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */ +static u32 bbr_max_bw(const struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return minmax_get(&bbr->bw); +} + +/* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */ +static u32 bbr_bw(const struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk); +} + +/* Return rate in bytes per second, optionally with a gain. + * The order here is chosen carefully to avoid overflow of u64. This should + * work for input rates of up to 2.9Tbit/sec and gain of 2.89x. + */ +static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) +{ + rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache); + rate *= gain; + rate >>= BBR_SCALE; + rate *= USEC_PER_SEC; + return rate >> BW_SCALE; +} + +/* Pace using current bw estimate and a gain factor. In order to help drive the + * network toward lower queues while maintaining high utilization and low + * latency, the average pacing rate aims to be slightly (~1%) lower than the + * estimated bandwidth. This is an important aspect of the design. In this + * implementation this slightly lower pacing rate is achieved implicitly by not + * including link-layer headers in the packet size used for the pacing rate. + */ +static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) +{ + struct bbr *bbr = inet_csk_ca(sk); + u64 rate = bw; + + rate = bbr_rate_bytes_per_sec(sk, rate, gain); + rate = min_t(u64, rate, sk->sk_max_pacing_rate); + if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate) + sk->sk_pacing_rate = rate; +} + +/* Return count of segments we want in the skbs we send, or 0 for default. */ +static u32 bbr_tso_segs_goal(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return bbr->tso_segs_goal; +} + +static void bbr_set_tso_segs_goal(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 min_segs; + + min_segs = sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; + bbr->tso_segs_goal = min(tcp_tso_autosize(sk, tp->mss_cache, min_segs), + 0x7FU); +} + +/* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */ +static void bbr_save_cwnd(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (bbr->prev_ca_state < TCP_CA_Recovery && bbr->mode != BBR_PROBE_RTT) + bbr->prior_cwnd = tp->snd_cwnd; /* this cwnd is good enough */ + else /* loss recovery or BBR_PROBE_RTT have temporarily cut cwnd */ + bbr->prior_cwnd = max(bbr->prior_cwnd, tp->snd_cwnd); +} + +static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (event == CA_EVENT_TX_START && tp->app_limited) { + bbr->idle_restart = 1; + /* Avoid pointless buffer overflows: pace at est. bw if we don't + * need more speed (we're restarting from idle and app-limited). + */ + if (bbr->mode == BBR_PROBE_BW) + bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT); + } +} + +/* Find target cwnd. Right-size the cwnd based on min RTT and the + * estimated bottleneck bandwidth: + * + * cwnd = bw * min_rtt * gain = BDP * gain + * + * The key factor, gain, controls the amount of queue. While a small gain + * builds a smaller queue, it becomes more vulnerable to noise in RTT + * measurements (e.g., delayed ACKs or other ACK compression effects). This + * noise may cause BBR to under-estimate the rate. + * + * To achieve full performance in high-speed paths, we budget enough cwnd to + * fit full-sized skbs in-flight on both end hosts to fully utilize the path: + * - one skb in sending host Qdisc, + * - one skb in sending host TSO/GSO engine + * - one skb being received by receiver host LRO/GRO/delayed-ACK engine + * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because + * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, + * which allows 2 outstanding 2-packet sequences, to try to keep pipe + * full even with ACK-every-other-packet delayed ACKs. + */ +static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 cwnd; + u64 w; + + /* If we've never had a valid RTT sample, cap cwnd at the initial + * default. This should only happen when the connection is not using TCP + * timestamps and has retransmitted all of the SYN/SYNACK/data packets + * ACKed so far. In this case, an RTO can cut cwnd to 1, in which + * case we need to slow-start up toward something safe: TCP_INIT_CWND. + */ + if (unlikely(bbr->min_rtt_us == ~0U)) /* no valid RTT samples yet? */ + return TCP_INIT_CWND; /* be safe: cap at default initial cwnd*/ + + w = (u64)bw * bbr->min_rtt_us; + + /* Apply a gain to the given value, then remove the BW_SCALE shift. */ + cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; + + /* Allow enough full-sized skbs in flight to utilize end systems. */ + cwnd += 3 * bbr->tso_segs_goal; + + /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ + cwnd = (cwnd + 1) & ~1U; + + return cwnd; +} + +/* An optimization in BBR to reduce losses: On the first round of recovery, we + * follow the packet conservation principle: send P packets per P packets acked. + * After that, we slow-start and send at most 2*P packets per P packets acked. + * After recovery finishes, or upon undo, we restore the cwnd we had when + * recovery started (capped by the target cwnd based on estimated BDP). + * + * TODO(ycheng/ncardwell): implement a rate-based approach. + */ +static bool bbr_set_cwnd_to_recover_or_restore( + struct sock *sk, const struct rate_sample *rs, u32 acked, u32 *new_cwnd) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u8 prev_state = bbr->prev_ca_state, state = inet_csk(sk)->icsk_ca_state; + u32 cwnd = tp->snd_cwnd; + + /* An ACK for P pkts should release at most 2*P packets. We do this + * in two steps. First, here we deduct the number of lost packets. + * Then, in bbr_set_cwnd() we slow start up toward the target cwnd. + */ + if (rs->losses > 0) + cwnd = max_t(s32, cwnd - rs->losses, 1); + + if (state == TCP_CA_Recovery && prev_state != TCP_CA_Recovery) { + /* Starting 1st round of Recovery, so do packet conservation. */ + bbr->packet_conservation = 1; + bbr->next_rtt_delivered = tp->delivered; /* start round now */ + /* Cut unused cwnd from app behavior, TSQ, or TSO deferral: */ + cwnd = tcp_packets_in_flight(tp) + acked; + } else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) { + /* Exiting loss recovery; restore cwnd saved before recovery. */ + bbr->restore_cwnd = 1; + bbr->packet_conservation = 0; + } + bbr->prev_ca_state = state; + + if (bbr->restore_cwnd) { + /* Restore cwnd after exiting loss recovery or PROBE_RTT. */ + cwnd = max(cwnd, bbr->prior_cwnd); + bbr->restore_cwnd = 0; + } + + if (bbr->packet_conservation) { + *new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked); + return true; /* yes, using packet conservation */ + } + *new_cwnd = cwnd; + return false; +} + +/* Slow-start up toward target cwnd (if bw estimate is growing, or packet loss + * has drawn us down below target), or snap down to target if we're above it. + */ +static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, + u32 acked, u32 bw, int gain) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 cwnd = 0, target_cwnd = 0; + + if (!acked) + return; + + if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) + goto done; + + /* If we're below target cwnd, slow start cwnd toward target cwnd. */ + target_cwnd = bbr_target_cwnd(sk, bw, gain); + if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ + cwnd = min(cwnd + acked, target_cwnd); + else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND) + cwnd = cwnd + acked; + cwnd = max(cwnd, bbr_cwnd_min_target); + +done: + tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); /* apply global cap */ + if (bbr->mode == BBR_PROBE_RTT) /* drain queue, refresh min_rtt */ + tp->snd_cwnd = min(tp->snd_cwnd, bbr_cwnd_min_target); +} + +/* End cycle phase if it's time and/or we hit the phase's in-flight target. */ +static bool bbr_is_next_cycle_phase(struct sock *sk, + const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + bool is_full_length = + skb_mstamp_us_delta(&tp->delivered_mstamp, &bbr->cycle_mstamp) > + bbr->min_rtt_us; + u32 inflight, bw; + + /* The pacing_gain of 1.0 paces at the estimated bw to try to fully + * use the pipe without increasing the queue. + */ + if (bbr->pacing_gain == BBR_UNIT) + return is_full_length; /* just use wall clock time */ + + inflight = rs->prior_in_flight; /* what was in-flight before ACK? */ + bw = bbr_max_bw(sk); + + /* A pacing_gain > 1.0 probes for bw by trying to raise inflight to at + * least pacing_gain*BDP; this may take more than min_rtt if min_rtt is + * small (e.g. on a LAN). We do not persist if packets are lost, since + * a path with small buffers may not hold that much. + */ + if (bbr->pacing_gain > BBR_UNIT) + return is_full_length && + (rs->losses || /* perhaps pacing_gain*BDP won't fit */ + inflight >= bbr_target_cwnd(sk, bw, bbr->pacing_gain)); + + /* A pacing_gain < 1.0 tries to drain extra queue we added if bw + * probing didn't find more bw. If inflight falls to match BDP then we + * estimate queue is drained; persisting would underutilize the pipe. + */ + return is_full_length || + inflight <= bbr_target_cwnd(sk, bw, BBR_UNIT); +} + +static void bbr_advance_cycle_phase(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); + bbr->cycle_mstamp = tp->delivered_mstamp; + bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx]; +} + +/* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ +static void bbr_update_cycle_phase(struct sock *sk, + const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw && + bbr_is_next_cycle_phase(sk, rs)) + bbr_advance_cycle_phase(sk); +} + +static void bbr_reset_startup_mode(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->mode = BBR_STARTUP; + bbr->pacing_gain = bbr_high_gain; + bbr->cwnd_gain = bbr_high_gain; +} + +static void bbr_reset_probe_bw_mode(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->mode = BBR_PROBE_BW; + bbr->pacing_gain = BBR_UNIT; + bbr->cwnd_gain = bbr_cwnd_gain; + bbr->cycle_idx = CYCLE_LEN - 1 - prandom_u32_max(bbr_cycle_rand); + bbr_advance_cycle_phase(sk); /* flip to next phase of gain cycle */ +} + +static void bbr_reset_mode(struct sock *sk) +{ + if (!bbr_full_bw_reached(sk)) + bbr_reset_startup_mode(sk); + else + bbr_reset_probe_bw_mode(sk); +} + +/* Start a new long-term sampling interval. */ +static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + bbr->lt_last_stamp = tp->delivered_mstamp.stamp_jiffies; + bbr->lt_last_delivered = tp->delivered; + bbr->lt_last_lost = tp->lost; + bbr->lt_rtt_cnt = 0; +} + +/* Completely reset long-term bandwidth sampling. */ +static void bbr_reset_lt_bw_sampling(struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + bbr->lt_bw = 0; + bbr->lt_use_bw = 0; + bbr->lt_is_sampling = false; + bbr_reset_lt_bw_sampling_interval(sk); +} + +/* Long-term bw sampling interval is done. Estimate whether we're policed. */ +static void bbr_lt_bw_interval_done(struct sock *sk, u32 bw) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 diff; + + if (bbr->lt_bw) { /* do we have bw from a previous interval? */ + /* Is new bw close to the lt_bw from the previous interval? */ + diff = abs(bw - bbr->lt_bw); + if ((diff * BBR_UNIT <= bbr_lt_bw_ratio * bbr->lt_bw) || + (bbr_rate_bytes_per_sec(sk, diff, BBR_UNIT) <= + bbr_lt_bw_diff)) { + /* All criteria are met; estimate we're policed. */ + bbr->lt_bw = (bw + bbr->lt_bw) >> 1; /* avg 2 intvls */ + bbr->lt_use_bw = 1; + bbr->pacing_gain = BBR_UNIT; /* try to avoid drops */ + bbr->lt_rtt_cnt = 0; + return; + } + } + bbr->lt_bw = bw; + bbr_reset_lt_bw_sampling_interval(sk); +} + +/* Token-bucket traffic policers are common (see "An Internet-Wide Analysis of + * Traffic Policing", SIGCOMM 2016). BBR detects token-bucket policers and + * explicitly models their policed rate, to reduce unnecessary losses. We + * estimate that we're policed if we see 2 consecutive sampling intervals with + * consistent throughput and high packet loss. If we think we're being policed, + * set lt_bw to the "long-term" average delivery rate from those 2 intervals. + */ +static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u32 lost, delivered; + u64 bw; + s32 t; + + if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ + if (bbr->mode == BBR_PROBE_BW && bbr->round_start && + ++bbr->lt_rtt_cnt >= bbr_lt_bw_max_rtts) { + bbr_reset_lt_bw_sampling(sk); /* stop using lt_bw */ + bbr_reset_probe_bw_mode(sk); /* restart gain cycling */ + } + return; + } + + /* Wait for the first loss before sampling, to let the policer exhaust + * its tokens and estimate the steady-state rate allowed by the policer. + * Starting samples earlier includes bursts that over-estimate the bw. + */ + if (!bbr->lt_is_sampling) { + if (!rs->losses) + return; + bbr_reset_lt_bw_sampling_interval(sk); + bbr->lt_is_sampling = true; + } + + /* To avoid underestimates, reset sampling if we run out of data. */ + if (rs->is_app_limited) { + bbr_reset_lt_bw_sampling(sk); + return; + } + + if (bbr->round_start) + bbr->lt_rtt_cnt++; /* count round trips in this interval */ + if (bbr->lt_rtt_cnt < bbr_lt_intvl_min_rtts) + return; /* sampling interval needs to be longer */ + if (bbr->lt_rtt_cnt > 4 * bbr_lt_intvl_min_rtts) { + bbr_reset_lt_bw_sampling(sk); /* interval is too long */ + return; + } + + /* End sampling interval when a packet is lost, so we estimate the + * policer tokens were exhausted. Stopping the sampling before the + * tokens are exhausted under-estimates the policed rate. + */ + if (!rs->losses) + return; + + /* Calculate packets lost and delivered in sampling interval. */ + lost = tp->lost - bbr->lt_last_lost; + delivered = tp->delivered - bbr->lt_last_delivered; + /* Is loss rate (lost/delivered) >= lt_loss_thresh? If not, wait. */ + if (!delivered || (lost << BBR_SCALE) < bbr_lt_loss_thresh * delivered) + return; + + /* Find average delivery rate in this sampling interval. */ + t = (s32)(tp->delivered_mstamp.stamp_jiffies - bbr->lt_last_stamp); + if (t < 1) + return; /* interval is less than one jiffy, so wait */ + t = jiffies_to_usecs(t); + /* Interval long enough for jiffies_to_usecs() to return a bogus 0? */ + if (t < 1) { + bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ + return; + } + bw = (u64)delivered * BW_UNIT; + do_div(bw, t); + bbr_lt_bw_interval_done(sk, bw); +} + +/* Estimate the bandwidth based on how fast packets are delivered */ +static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + + bbr->round_start = 0; + if (rs->delivered < 0 || rs->interval_us <= 0) + return; /* Not a valid observation */ + + /* See if we've reached the next RTT */ + if (!before(rs->prior_delivered, bbr->next_rtt_delivered)) { + bbr->next_rtt_delivered = tp->delivered; + bbr->rtt_cnt++; + bbr->round_start = 1; + bbr->packet_conservation = 0; + } + + bbr_lt_bw_sampling(sk, rs); + + /* Divide delivered by the interval to find a (lower bound) bottleneck + * bandwidth sample. Delivered is in packets and interval_us in uS and + * ratio will be <<1 for most connections. So delivered is first scaled. + */ + bw = (u64)rs->delivered * BW_UNIT; + do_div(bw, rs->interval_us); + + /* If this sample is application-limited, it is likely to have a very + * low delivered count that represents application behavior rather than + * the available network rate. Such a sample could drag down estimated + * bw, causing needless slow-down. Thus, to continue to send at the + * last measured network rate, we filter out app-limited samples unless + * they describe the path bw at least as well as our bw model. + * + * So the goal during app-limited phase is to proceed with the best + * network rate no matter how long. We automatically leave this + * phase when app writes faster than the network can deliver :) + */ + if (!rs->is_app_limited || bw >= bbr_max_bw(sk)) { + /* Incorporate new sample into our max bw filter. */ + minmax_running_max(&bbr->bw, bbr_bw_rtts, bbr->rtt_cnt, bw); + } +} + +/* Estimate when the pipe is full, using the change in delivery rate: BBR + * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by + * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited + * rounds. Why 3 rounds: 1: rwin autotuning grows the rwin, 2: we fill the + * higher rwin, 3: we get higher delivery rate samples. Or transient + * cross-traffic or radio noise can go away. CUBIC Hystart shares a similar + * design goal, but uses delay and inter-ACK spacing instead of bandwidth. + */ +static void bbr_check_full_bw_reached(struct sock *sk, + const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 bw_thresh; + + if (bbr_full_bw_reached(sk) || !bbr->round_start || rs->is_app_limited) + return; + + bw_thresh = (u64)bbr->full_bw * bbr_full_bw_thresh >> BBR_SCALE; + if (bbr_max_bw(sk) >= bw_thresh) { + bbr->full_bw = bbr_max_bw(sk); + bbr->full_bw_cnt = 0; + return; + } + ++bbr->full_bw_cnt; +} + +/* If pipe is probably full, drain the queue and then enter steady-state. */ +static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) { + bbr->mode = BBR_DRAIN; /* drain queue we created */ + bbr->pacing_gain = bbr_drain_gain; /* pace slow to drain */ + bbr->cwnd_gain = bbr_high_gain; /* maintain cwnd */ + } /* fall through to check if in-flight is already small: */ + if (bbr->mode == BBR_DRAIN && + tcp_packets_in_flight(tcp_sk(sk)) <= + bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT)) + bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ +} + +/* The goal of PROBE_RTT mode is to have BBR flows cooperatively and + * periodically drain the bottleneck queue, to converge to measure the true + * min_rtt (unloaded propagation delay). This allows the flows to keep queues + * small (reducing queuing delay and packet loss) and achieve fairness among + * BBR flows. + * + * The min_rtt filter window is 10 seconds. When the min_rtt estimate expires, + * we enter PROBE_RTT mode and cap the cwnd at bbr_cwnd_min_target=4 packets. + * After at least bbr_probe_rtt_mode_ms=200ms and at least one packet-timed + * round trip elapsed with that flight size <= 4, we leave PROBE_RTT mode and + * re-enter the previous mode. BBR uses 200ms to approximately bound the + * performance penalty of PROBE_RTT's cwnd capping to roughly 2% (200ms/10s). + * + * Note that flows need only pay 2% if they are busy sending over the last 10 + * seconds. Interactive applications (e.g., Web, RPCs, video chunks) often have + * natural silences or low-rate periods within 10 seconds where the rate is low + * enough for long enough to drain its queue in the bottleneck. We pick up + * these min RTT measurements opportunistically with our min_rtt filter. :-) + */ +static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + bool filter_expired; + + /* Track min RTT seen in the min_rtt_win_sec filter window: */ + filter_expired = after(tcp_time_stamp, + bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); + if (rs->rtt_us >= 0 && + (rs->rtt_us <= bbr->min_rtt_us || filter_expired)) { + bbr->min_rtt_us = rs->rtt_us; + bbr->min_rtt_stamp = tcp_time_stamp; + } + + if (bbr_probe_rtt_mode_ms > 0 && filter_expired && + !bbr->idle_restart && bbr->mode != BBR_PROBE_RTT) { + bbr->mode = BBR_PROBE_RTT; /* dip, drain queue */ + bbr->pacing_gain = BBR_UNIT; + bbr->cwnd_gain = BBR_UNIT; + bbr_save_cwnd(sk); /* note cwnd so we can restore it */ + bbr->probe_rtt_done_stamp = 0; + } + + if (bbr->mode == BBR_PROBE_RTT) { + /* Ignore low rate samples during this mode. */ + tp->app_limited = + (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; + /* Maintain min packets in flight for max(200 ms, 1 round). */ + if (!bbr->probe_rtt_done_stamp && + tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) { + bbr->probe_rtt_done_stamp = tcp_time_stamp + + msecs_to_jiffies(bbr_probe_rtt_mode_ms); + bbr->probe_rtt_round_done = 0; + bbr->next_rtt_delivered = tp->delivered; + } else if (bbr->probe_rtt_done_stamp) { + if (bbr->round_start) + bbr->probe_rtt_round_done = 1; + if (bbr->probe_rtt_round_done && + after(tcp_time_stamp, bbr->probe_rtt_done_stamp)) { + bbr->min_rtt_stamp = tcp_time_stamp; + bbr->restore_cwnd = 1; /* snap to prior_cwnd */ + bbr_reset_mode(sk); + } + } + } + bbr->idle_restart = 0; +} + +static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) +{ + bbr_update_bw(sk, rs); + bbr_update_cycle_phase(sk, rs); + bbr_check_full_bw_reached(sk, rs); + bbr_check_drain(sk, rs); + bbr_update_min_rtt(sk, rs); +} + +static void bbr_main(struct sock *sk, const struct rate_sample *rs) +{ + struct bbr *bbr = inet_csk_ca(sk); + u32 bw; + + bbr_update_model(sk, rs); + + bw = bbr_bw(sk); + bbr_set_pacing_rate(sk, bw, bbr->pacing_gain); + bbr_set_tso_segs_goal(sk); + bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); +} + +static void bbr_init(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw; + + bbr->prior_cwnd = 0; + bbr->tso_segs_goal = 0; /* default segs per skb until first ACK */ + bbr->rtt_cnt = 0; + bbr->next_rtt_delivered = 0; + bbr->prev_ca_state = TCP_CA_Open; + bbr->packet_conservation = 0; + + bbr->probe_rtt_done_stamp = 0; + bbr->probe_rtt_round_done = 0; + bbr->min_rtt_us = tcp_min_rtt(tp); + bbr->min_rtt_stamp = tcp_time_stamp; + + minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ + + /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ + bw = (u64)tp->snd_cwnd * BW_UNIT; + do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC); + sk->sk_pacing_rate = 0; /* force an update of sk_pacing_rate */ + bbr_set_pacing_rate(sk, bw, bbr_high_gain); + + bbr->restore_cwnd = 0; + bbr->round_start = 0; + bbr->idle_restart = 0; + bbr->full_bw = 0; + bbr->full_bw_cnt = 0; + bbr->cycle_mstamp.v64 = 0; + bbr->cycle_idx = 0; + bbr_reset_lt_bw_sampling(sk); + bbr_reset_startup_mode(sk); +} + +static u32 bbr_sndbuf_expand(struct sock *sk) +{ + /* Provision 3 * cwnd since BBR may slow-start even during recovery. */ + return 3; +} + +/* In theory BBR does not need to undo the cwnd since it does not + * always reduce cwnd on losses (see bbr_main()). Keep it for now. + */ +static u32 bbr_undo_cwnd(struct sock *sk) +{ + return tcp_sk(sk)->snd_cwnd; +} + +/* Entering loss recovery, so save cwnd for when we exit or undo recovery. */ +static u32 bbr_ssthresh(struct sock *sk) +{ + bbr_save_cwnd(sk); + return TCP_INFINITE_SSTHRESH; /* BBR does not use ssthresh */ +} + +static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) +{ + if (ext & (1 << (INET_DIAG_BBRINFO - 1)) || + ext & (1 << (INET_DIAG_VEGASINFO - 1))) { + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + u64 bw = bbr_bw(sk); + + bw = bw * tp->mss_cache * USEC_PER_SEC >> BW_SCALE; + memset(&info->bbr, 0, sizeof(info->bbr)); + info->bbr.bbr_bw_lo = (u32)bw; + info->bbr.bbr_bw_hi = (u32)(bw >> 32); + info->bbr.bbr_min_rtt = bbr->min_rtt_us; + info->bbr.bbr_pacing_gain = bbr->pacing_gain; + info->bbr.bbr_cwnd_gain = bbr->cwnd_gain; + *attr = INET_DIAG_BBRINFO; + return sizeof(info->bbr); + } + return 0; +} + +static void bbr_set_state(struct sock *sk, u8 new_state) +{ + struct bbr *bbr = inet_csk_ca(sk); + + if (new_state == TCP_CA_Loss) { + struct rate_sample rs = { .losses = 1 }; + + bbr->prev_ca_state = TCP_CA_Loss; + bbr->full_bw = 0; + bbr->round_start = 1; /* treat RTO like end of a round */ + bbr_lt_bw_sampling(sk, &rs); + } +} + +static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { + .flags = TCP_CONG_NON_RESTRICTED, + .name = "bbr", + .owner = THIS_MODULE, + .init = bbr_init, + .cong_control = bbr_main, + .sndbuf_expand = bbr_sndbuf_expand, + .undo_cwnd = bbr_undo_cwnd, + .cwnd_event = bbr_cwnd_event, + .ssthresh = bbr_ssthresh, + .tso_segs_goal = bbr_tso_segs_goal, + .get_info = bbr_get_info, + .set_state = bbr_set_state, +}; + +static int __init bbr_register(void) +{ + BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); + return tcp_register_congestion_control(&tcp_bbr_cong_ops); +} + +static void __exit bbr_unregister(void) +{ + tcp_unregister_congestion_control(&tcp_bbr_cong_ops); +} + +module_init(bbr_register); +module_exit(bbr_unregister); + +MODULE_AUTHOR("Van Jacobson <vanj@google.com>"); +MODULE_AUTHOR("Neal Cardwell <ncardwell@google.com>"); +MODULE_AUTHOR("Yuchung Cheng <ycheng@google.com>"); +MODULE_AUTHOR("Soheil Hassas Yeganeh <soheil@google.com>"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("TCP BBR (Bottleneck Bandwidth and RTT)"); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 03725b294286..35b280361cb2 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -56,7 +56,7 @@ MODULE_PARM_DESC(use_shadow, "use shadow window heuristic"); module_param(use_tolerance, bool, 0644); MODULE_PARM_DESC(use_tolerance, "use loss tolerance heuristic"); -struct minmax { +struct cdg_minmax { union { struct { s32 min; @@ -74,10 +74,10 @@ enum cdg_state { }; struct cdg { - struct minmax rtt; - struct minmax rtt_prev; - struct minmax *gradients; - struct minmax gsum; + struct cdg_minmax rtt; + struct cdg_minmax rtt_prev; + struct cdg_minmax *gradients; + struct cdg_minmax gsum; bool gfilled; u8 tail; u8 state; @@ -353,7 +353,7 @@ static void tcp_cdg_cwnd_event(struct sock *sk, const enum tcp_ca_event ev) { struct cdg *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - struct minmax *gradients; + struct cdg_minmax *gradients; switch (ev) { case CA_EVENT_CWND_RESTART: diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 882caa4e72bc..1294af4e0127 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -69,7 +69,7 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) int ret = 0; /* all algorithms must implement ssthresh and cong_avoid ops */ - if (!ca->ssthresh || !ca->cong_avoid) { + if (!ca->ssthresh || !(ca->cong_avoid || ca->cong_control)) { pr_err("%s does not implement required ops\n", ca->name); return -EINVAL; } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 54d9f9b0120f..4e777a3243f9 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -150,6 +150,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) tp->segs_in = 0; tcp_segs_in(tp, skb); __skb_pull(skb, tcp_hdrlen(skb)); + sk_forced_mem_schedule(sk, skb->truesize); skb_set_owner_r(skb, sk); TCP_SKB_CB(skb)->seq++; @@ -226,6 +227,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, tcp_fastopen_add_skb(child, skb); tcp_rsk(req)->rcv_nxt = tp->rcv_nxt; + tp->rcv_wup = tp->rcv_nxt; /* tcp_conn_request() is sending the SYNACK, * and queues the child into listener accept queue. */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f3a9f3c2c8d8..8c6ad2d319d6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -289,6 +289,7 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr static void tcp_sndbuf_expand(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; int sndmem, per_mss; u32 nr_segs; @@ -309,7 +310,8 @@ static void tcp_sndbuf_expand(struct sock *sk) * Cubic needs 1.7 factor, rounded to 2 to include * extra cushion (application might react slowly to POLLOUT) */ - sndmem = 2 * nr_segs * per_mss; + sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2; + sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]); @@ -899,12 +901,29 @@ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) tp->retransmit_high = TCP_SKB_CB(skb)->end_seq; } +/* Sum the number of packets on the wire we have marked as lost. + * There are two cases we care about here: + * a) Packet hasn't been marked lost (nor retransmitted), + * and this is the first loss. + * b) Packet has been marked both lost and retransmitted, + * and this means we think it was lost again. + */ +static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb) +{ + __u8 sacked = TCP_SKB_CB(skb)->sacked; + + if (!(sacked & TCPCB_LOST) || + ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS))) + tp->lost += tcp_skb_pcount(skb); +} + static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) { if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { tcp_verify_retransmit_hint(tp, skb); tp->lost_out += tcp_skb_pcount(skb); + tcp_sum_lost(tp, skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; } } @@ -913,6 +932,7 @@ void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) { tcp_verify_retransmit_hint(tp, skb); + tcp_sum_lost(tp, skb); if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { tp->lost_out += tcp_skb_pcount(skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; @@ -1094,6 +1114,7 @@ struct tcp_sacktag_state { */ struct skb_mstamp first_sackt; struct skb_mstamp last_sackt; + struct rate_sample *rate; int flag; }; @@ -1261,6 +1282,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, &skb->skb_mstamp); + tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1311,6 +1333,9 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_advance_highest_sack(sk, skb); tcp_skb_collapse_tstamp(prev, skb); + if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64)) + TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0; + tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); @@ -1540,6 +1565,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, dup_sack, tcp_skb_pcount(skb), &skb->skb_mstamp); + tcp_rate_skb_delivered(sk, skb, state->rate); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1622,8 +1648,10 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire, num_sacks, prior_snd_una); - if (found_dup_sack) + if (found_dup_sack) { state->flag |= FLAG_DSACKING_ACK; + tp->delivered++; /* A spurious retransmission is delivered */ + } /* Eliminate too old ACKs, but take into * account more or less fresh ones, they can @@ -1890,6 +1918,7 @@ void tcp_enter_loss(struct sock *sk) struct sk_buff *skb; bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; bool is_reneg; /* is receiver reneging on SACKs? */ + bool mark_lost; /* Reduce ssthresh if it has not yet been made inside this window. */ if (icsk->icsk_ca_state <= TCP_CA_Disorder || @@ -1923,8 +1952,12 @@ void tcp_enter_loss(struct sock *sk) if (skb == tcp_send_head(sk)) break; + mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || + is_reneg); + if (mark_lost) + tcp_sum_lost(tp, skb); TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; - if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) { + if (mark_lost) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; tp->lost_out += tcp_skb_pcount(skb); @@ -2503,6 +2536,9 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + if (inet_csk(sk)->icsk_ca_ops->cong_control) + return; + /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { @@ -2879,67 +2915,13 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, *rexmit = REXMIT_LOST; } -/* Kathleen Nichols' algorithm for tracking the minimum value of - * a data stream over some fixed time interval. (E.g., the minimum - * RTT over the past five minutes.) It uses constant space and constant - * time per update yet almost always delivers the same minimum as an - * implementation that has to keep all the data in the window. - * - * The algorithm keeps track of the best, 2nd best & 3rd best min - * values, maintaining an invariant that the measurement time of the - * n'th best >= n-1'th best. It also makes sure that the three values - * are widely separated in the time window since that bounds the worse - * case error when that data is monotonically increasing over the window. - * - * Upon getting a new min, we can forget everything earlier because it - * has no value - the new min is <= everything else in the window by - * definition and it's the most recent. So we restart fresh on every new min - * and overwrites 2nd & 3rd choices. The same property holds for 2nd & 3rd - * best. - */ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { - const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; - struct rtt_meas *m = tcp_sk(sk)->rtt_min; - struct rtt_meas rttm = { - .rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1), - .ts = now, - }; - u32 elapsed; - - /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ - if (unlikely(rttm.rtt <= m[0].rtt)) - m[0] = m[1] = m[2] = rttm; - else if (rttm.rtt <= m[1].rtt) - m[1] = m[2] = rttm; - else if (rttm.rtt <= m[2].rtt) - m[2] = rttm; - - elapsed = now - m[0].ts; - if (unlikely(elapsed > wlen)) { - /* Passed entire window without a new min so make 2nd choice - * the new min & 3rd choice the new 2nd. So forth and so on. - */ - m[0] = m[1]; - m[1] = m[2]; - m[2] = rttm; - if (now - m[0].ts > wlen) { - m[0] = m[1]; - m[1] = rttm; - if (now - m[0].ts > wlen) - m[0] = rttm; - } - } else if (m[1].ts == m[0].ts && elapsed > wlen / 4) { - /* Passed a quarter of the window without a new min so - * take 2nd choice from the 2nd quarter of the window. - */ - m[2] = m[1] = rttm; - } else if (m[2].ts == m[1].ts && elapsed > wlen / 2) { - /* Passed half the window without a new min so take the 3rd - * choice from the last half of the window. - */ - m[2] = rttm; - } + struct tcp_sock *tp = tcp_sk(sk); + u32 wlen = sysctl_tcp_min_rtt_wlen * HZ; + + minmax_running_min(&tp->rtt_min, wlen, tcp_time_stamp, + rtt_us ? : jiffies_to_usecs(1)); } static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, @@ -3102,10 +3084,11 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, u32 prior_snd_una, int *acked, - struct tcp_sacktag_state *sack) + struct tcp_sacktag_state *sack, + struct skb_mstamp *now) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct skb_mstamp first_ackt, last_ackt, now; + struct skb_mstamp first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; @@ -3137,7 +3120,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, acked_pcount = tcp_tso_acked(sk, skb); if (!acked_pcount) break; - fully_acked = false; } else { /* Speedup tcp_unlink_write_queue() and next loop */ @@ -3173,6 +3155,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->packets_out -= acked_pcount; pkts_acked += acked_pcount; + tcp_rate_skb_delivered(sk, skb, sack->rate); /* Initial outgoing SYN's get put onto the write_queue * just like anything else we transmit. It is not @@ -3205,16 +3188,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - skb_mstamp_get(&now); if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { - seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); - ca_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt); + ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt); } if (sack->first_sackt.v64) { - sack_rtt_us = skb_mstamp_us_delta(&now, &sack->first_sackt); - ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt); + sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt); + ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt); } - + sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, ca_rtt_us); @@ -3242,7 +3224,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); } else if (skb && rtt_update && sack_rtt_us >= 0 && - sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { + sack_rtt_us > skb_mstamp_us_delta(now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3333,8 +3315,15 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) * information. All transmission or retransmission are delayed afterwards. */ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked, - int flag) + int flag, const struct rate_sample *rs) { + const struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ca_ops->cong_control) { + icsk->icsk_ca_ops->cong_control(sk, rs); + return; + } + if (tcp_in_cwnd_reduction(sk)) { /* Reduce cwnd if state mandates */ tcp_cwnd_reduction(sk, acked_sacked, flag); @@ -3579,17 +3568,21 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_sacktag_state sack_state; + struct rate_sample rs = { .prior_delivered = 0 }; u32 prior_snd_una = tp->snd_una; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; u32 prior_fackets; int prior_packets = tp->packets_out; - u32 prior_delivered = tp->delivered; + u32 delivered = tp->delivered; + u32 lost = tp->lost; int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ + struct skb_mstamp now; sack_state.first_sackt.v64 = 0; + sack_state.rate = &rs; /* We very likely will need to access write queue head. */ prefetchw(sk->sk_write_queue.next); @@ -3612,6 +3605,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; + skb_mstamp_get(&now); + if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -3622,6 +3617,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) } prior_fackets = tp->fackets_out; + rs.prior_in_flight = tcp_packets_in_flight(tp); /* ts_recent update must be made after we are sure that the packet * is in window. @@ -3677,7 +3673,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked, - &sack_state); + &sack_state, &now); if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); @@ -3694,7 +3690,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); - tcp_cong_control(sk, ack, tp->delivered - prior_delivered, flag); + delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ + lost = tp->lost - lost; /* freshly marked lost */ + tcp_rate_gen(sk, delivered, lost, &now, &rs); + tcp_cong_control(sk, ack, delivered, flag, &rs); tcp_xmit_recovery(sk, rexmit); return 1; @@ -4108,7 +4107,7 @@ void tcp_fin(struct sock *sk) /* It _is_ possible, that we have something out-of-order _after_ FIN. * Probably, we should reset in this case. For now drop them. */ - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); if (tcp_is_sack(tp)) tcp_sack_reset(&tp->rx_opt); sk_mem_reclaim(sk); @@ -4268,7 +4267,7 @@ static void tcp_sack_remove(struct tcp_sock *tp) int this_sack; /* Empty ofo queue, hence, all the SACKs are eaten. Clear. */ - if (skb_queue_empty(&tp->out_of_order_queue)) { + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tp->rx_opt.num_sacks = 0; return; } @@ -4344,10 +4343,13 @@ static void tcp_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); __u32 dsack_high = tp->rcv_nxt; + bool fin, fragstolen, eaten; struct sk_buff *skb, *tail; - bool fragstolen, eaten; + struct rb_node *p; - while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) { + p = rb_first(&tp->out_of_order_queue); + while (p) { + skb = rb_entry(p, struct sk_buff, rbnode); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; @@ -4357,9 +4359,10 @@ static void tcp_ofo_queue(struct sock *sk) dsack_high = TCP_SKB_CB(skb)->end_seq; tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack); } + p = rb_next(p); + rb_erase(&skb->rbnode, &tp->out_of_order_queue); - __skb_unlink(skb, &tp->out_of_order_queue); - if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { + if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) { SOCK_DEBUG(sk, "ofo packet was already received\n"); tcp_drop(sk, skb); continue; @@ -4371,12 +4374,19 @@ static void tcp_ofo_queue(struct sock *sk) tail = skb_peek_tail(&sk->sk_receive_queue); eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); + fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) __skb_queue_tail(&sk->sk_receive_queue, skb); - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) - tcp_fin(sk); - if (eaten) + else kfree_skb_partial(skb, fragstolen); + + if (unlikely(fin)) { + tcp_fin(sk); + /* tcp_fin() purges tp->out_of_order_queue, + * so we must end this loop right now. + */ + break; + } } } @@ -4403,8 +4413,10 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + struct rb_node **p, *q, *parent; struct sk_buff *skb1; u32 seq, end_seq; + bool fragstolen; tcp_ecn_check_ce(tp, skb); @@ -4419,88 +4431,92 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) inet_csk_schedule_ack(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); + seq = TCP_SKB_CB(skb)->seq; + end_seq = TCP_SKB_CB(skb)->end_seq; SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", - tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); + tp->rcv_nxt, seq, end_seq); - skb1 = skb_peek_tail(&tp->out_of_order_queue); - if (!skb1) { + p = &tp->out_of_order_queue.rb_node; + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { /* Initial out of order segment, build 1 SACK. */ if (tcp_is_sack(tp)) { tp->rx_opt.num_sacks = 1; - tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq; - tp->selective_acks[0].end_seq = - TCP_SKB_CB(skb)->end_seq; + tp->selective_acks[0].start_seq = seq; + tp->selective_acks[0].end_seq = end_seq; } - __skb_queue_head(&tp->out_of_order_queue, skb); + rb_link_node(&skb->rbnode, NULL, p); + rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); + tp->ooo_last_skb = skb; goto end; } - seq = TCP_SKB_CB(skb)->seq; - end_seq = TCP_SKB_CB(skb)->end_seq; - - if (seq == TCP_SKB_CB(skb1)->end_seq) { - bool fragstolen; - - if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - } else { - tcp_grow_window(sk, skb); - kfree_skb_partial(skb, fragstolen); - skb = NULL; - } - - if (!tp->rx_opt.num_sacks || - tp->selective_acks[0].end_seq != seq) - goto add_sack; - - /* Common case: data arrive in order after hole. */ - tp->selective_acks[0].end_seq = end_seq; - goto end; - } - - /* Find place to insert this segment. */ - while (1) { - if (!after(TCP_SKB_CB(skb1)->seq, seq)) - break; - if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { - skb1 = NULL; - break; - } - skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); - } - - /* Do skb overlap to previous one? */ - if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { - if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { - /* All the bits are present. Drop. */ - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - tcp_drop(sk, skb); - skb = NULL; - tcp_dsack_set(sk, seq, end_seq); - goto add_sack; + /* In the typical case, we are adding an skb to the end of the list. + * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. + */ + if (tcp_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { +coalesce_done: + tcp_grow_window(sk, skb); + kfree_skb_partial(skb, fragstolen); + skb = NULL; + goto add_sack; + } + /* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ + if (!before(seq, TCP_SKB_CB(tp->ooo_last_skb)->end_seq)) { + parent = &tp->ooo_last_skb->rbnode; + p = &parent->rb_right; + goto insert; + } + + /* Find place to insert this segment. Handle overlaps on the way. */ + parent = NULL; + while (*p) { + parent = *p; + skb1 = rb_entry(parent, struct sk_buff, rbnode); + if (before(seq, TCP_SKB_CB(skb1)->seq)) { + p = &parent->rb_left; + continue; } - if (after(seq, TCP_SKB_CB(skb1)->seq)) { - /* Partial overlap. */ - tcp_dsack_set(sk, seq, - TCP_SKB_CB(skb1)->end_seq); - } else { - if (skb_queue_is_first(&tp->out_of_order_queue, - skb1)) - skb1 = NULL; - else - skb1 = skb_queue_prev( - &tp->out_of_order_queue, - skb1); + if (before(seq, TCP_SKB_CB(skb1)->end_seq)) { + if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { + /* All the bits are present. Drop. */ + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); + __kfree_skb(skb); + skb = NULL; + tcp_dsack_set(sk, seq, end_seq); + goto add_sack; + } + if (after(seq, TCP_SKB_CB(skb1)->seq)) { + /* Partial overlap. */ + tcp_dsack_set(sk, seq, TCP_SKB_CB(skb1)->end_seq); + } else { + /* skb's seq == skb1's seq and skb covers skb1. + * Replace skb1 with skb. + */ + rb_replace_node(&skb1->rbnode, &skb->rbnode, + &tp->out_of_order_queue); + tcp_dsack_extend(sk, + TCP_SKB_CB(skb1)->seq, + TCP_SKB_CB(skb1)->end_seq); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); + __kfree_skb(skb1); + goto merge_right; + } + } else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { + goto coalesce_done; } + p = &parent->rb_right; } - if (!skb1) - __skb_queue_head(&tp->out_of_order_queue, skb); - else - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); +insert: + /* Insert segment into RB tree. */ + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); - /* And clean segments covered by new one as whole. */ - while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { - skb1 = skb_queue_next(&tp->out_of_order_queue, skb); +merge_right: + /* Remove other segments covered by skb. */ + while ((q = rb_next(&skb->rbnode)) != NULL) { + skb1 = rb_entry(q, struct sk_buff, rbnode); if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; @@ -4509,12 +4525,15 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) end_seq); break; } - __skb_unlink(skb1, &tp->out_of_order_queue); + rb_erase(&skb1->rbnode, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); tcp_drop(sk, skb1); } + /* If there is no skb after us, we are the last_skb ! */ + if (!q) + tp->ooo_last_skb = skb; add_sack: if (tcp_is_sack(tp)) @@ -4651,13 +4670,13 @@ queue_and_out: if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) tcp_fin(sk); - if (!skb_queue_empty(&tp->out_of_order_queue)) { + if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tcp_ofo_queue(sk); /* RFC2581. 4.2. SHOULD send immediate ACK, when * gap in queue is filled. */ - if (skb_queue_empty(&tp->out_of_order_queue)) + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) inet_csk(sk)->icsk_ack.pingpong = 0; } @@ -4711,48 +4730,76 @@ drop: tcp_data_queue_ofo(sk, skb); } +static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *list) +{ + if (list) + return !skb_queue_is_last(list, skb) ? skb->next : NULL; + + return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode); +} + static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *list) + struct sk_buff_head *list, + struct rb_root *root) { - struct sk_buff *next = NULL; + struct sk_buff *next = tcp_skb_next(skb, list); - if (!skb_queue_is_last(list, skb)) - next = skb_queue_next(list, skb); + if (list) + __skb_unlink(skb, list); + else + rb_erase(&skb->rbnode, root); - __skb_unlink(skb, list); __kfree_skb(skb); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOLLAPSED); return next; } +/* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ +static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct sk_buff *skb1; + + while (*p) { + parent = *p; + skb1 = rb_entry(parent, struct sk_buff, rbnode); + if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, root); +} + /* Collapse contiguous sequence of skbs head..tail with * sequence numbers start..end. * - * If tail is NULL, this means until the end of the list. + * If tail is NULL, this means until the end of the queue. * * Segments with FIN/SYN are not collapsed (only because this * simplifies code) */ static void -tcp_collapse(struct sock *sk, struct sk_buff_head *list, - struct sk_buff *head, struct sk_buff *tail, - u32 start, u32 end) +tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, + struct sk_buff *head, struct sk_buff *tail, u32 start, u32 end) { - struct sk_buff *skb, *n; + struct sk_buff *skb = head, *n; + struct sk_buff_head tmp; bool end_of_skbs; /* First, check that queue is collapsible and find - * the point where collapsing can be useful. */ - skb = head; + * the point where collapsing can be useful. + */ restart: - end_of_skbs = true; - skb_queue_walk_from_safe(list, skb, n) { - if (skb == tail) - break; + for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { + n = tcp_skb_next(skb, list); + /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { - skb = tcp_collapse_one(sk, skb, list); + skb = tcp_collapse_one(sk, skb, list, root); if (!skb) break; goto restart; @@ -4770,13 +4817,10 @@ restart: break; } - if (!skb_queue_is_last(list, skb)) { - struct sk_buff *next = skb_queue_next(list, skb); - if (next != tail && - TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(next)->seq) { - end_of_skbs = false; - break; - } + if (n && n != tail && + TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { + end_of_skbs = false; + break; } /* Decided to skip this, advance start seq. */ @@ -4786,17 +4830,22 @@ restart: (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) return; + __skb_queue_head_init(&tmp); + while (before(start, end)) { int copy = min_t(int, SKB_MAX_ORDER(0, 0), end - start); struct sk_buff *nskb; nskb = alloc_skb(copy, GFP_ATOMIC); if (!nskb) - return; + break; memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start; - __skb_queue_before(list, skb, nskb); + if (list) + __skb_queue_before(list, skb, nskb); + else + __skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */ skb_set_owner_r(nskb, sk); /* Copy data, releasing collapsed skbs. */ @@ -4814,14 +4863,17 @@ restart: start += size; } if (!before(start, TCP_SKB_CB(skb)->end_seq)) { - skb = tcp_collapse_one(sk, skb, list); + skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) - return; + goto end; } } } +end: + skb_queue_walk_safe(&tmp, skb, n) + tcp_rbtree_insert(root, skb); } /* Collapse ofo queue. Algorithm: select contiguous sequence of skbs @@ -4830,43 +4882,43 @@ restart: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = skb_peek(&tp->out_of_order_queue); - struct sk_buff *head; + struct sk_buff *skb, *head; + struct rb_node *p; u32 start, end; - if (!skb) + p = rb_first(&tp->out_of_order_queue); + skb = rb_entry_safe(p, struct sk_buff, rbnode); +new_range: + if (!skb) { + p = rb_last(&tp->out_of_order_queue); + /* Note: This is possible p is NULL here. We do not + * use rb_entry_safe(), as ooo_last_skb is valid only + * if rbtree is not empty. + */ + tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode); return; - + } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; - head = skb; - - for (;;) { - struct sk_buff *next = NULL; - if (!skb_queue_is_last(&tp->out_of_order_queue, skb)) - next = skb_queue_next(&tp->out_of_order_queue, skb); - skb = next; + for (head = skb;;) { + skb = tcp_skb_next(skb, NULL); - /* Segment is terminated when we see gap or when - * we are at the end of all the queue. */ + /* Range is terminated when we see a gap or when + * we are at the queue end. + */ if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, &tp->out_of_order_queue, + tcp_collapse(sk, NULL, &tp->out_of_order_queue, head, skb, start, end); - head = skb; - if (!skb) - break; - /* Start new segment */ + goto new_range; + } + + if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; + if (after(TCP_SKB_CB(skb)->end_seq, end)) end = TCP_SKB_CB(skb)->end_seq; - } else { - if (before(TCP_SKB_CB(skb)->seq, start)) - start = TCP_SKB_CB(skb)->seq; - if (after(TCP_SKB_CB(skb)->end_seq, end)) - end = TCP_SKB_CB(skb)->end_seq; - } } } @@ -4883,20 +4935,24 @@ static void tcp_collapse_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; + struct rb_node *node, *prev; - if (skb_queue_empty(&tp->out_of_order_queue)) + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); - - while ((skb = __skb_dequeue_tail(&tp->out_of_order_queue)) != NULL) { - tcp_drop(sk, skb); + node = &tp->ooo_last_skb->rbnode; + do { + prev = rb_prev(node); + rb_erase(node, &tp->out_of_order_queue); + tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; - } + node = prev; + } while (node); + tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); /* Reset SACK state. A conforming SACK implementation will * do the same at a timeout based retransmit. When a connection @@ -4930,7 +4986,7 @@ static int tcp_prune_queue(struct sock *sk) tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) - tcp_collapse(sk, &sk->sk_receive_queue, + tcp_collapse(sk, &sk->sk_receive_queue, NULL, skb_peek(&sk->sk_receive_queue), NULL, tp->copied_seq, tp->rcv_nxt); @@ -5035,7 +5091,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ - (ofo_possible && skb_peek(&tp->out_of_order_queue))) { + (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) { /* Then ack it now */ tcp_send_ack(sk); } else { @@ -5894,7 +5950,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) * so release it. */ if (req) { - tp->total_retrans = req->num_retrans; + inet_csk(sk)->icsk_retransmits = 0; reqsk_fastopen_remove(sk, req, false); } else { /* Make sure socket is routed, for correct metrics. */ @@ -5936,7 +5992,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } else tcp_init_metrics(sk); - tcp_update_pacing_rate(sk); + if (!inet_csk(sk)->icsk_ca_ops->cong_control) + tcp_update_pacing_rate(sk); /* Prevent spurious tcp_cwnd_restart() on first data packet */ tp->lsndtime = tcp_time_stamp; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 13b05adf9d3e..7ac37c314312 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1844,7 +1844,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_write_queue_purge(sk); /* Cleans up our, hopefully empty, out_of_order_queue. */ - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4b95ec4ed2c8..6234ebaa7db1 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -464,7 +464,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->srtt_us = 0; newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - newtp->rtt_min[0].rtt = ~0U; + minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U); newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; @@ -487,8 +487,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; + /* There's a bubble in the pipe until at least the first ACK. */ + newtp->app_limited = ~0U; + tcp_init_xmit_timers(newsk); - __skb_queue_head_init(&newtp->out_of_order_queue); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; newtp->rx_opt.saw_tstamp = 0; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 5c5964962d0c..bc68da38ea86 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -90,12 +90,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, goto out; } - /* GSO partial only requires splitting the frame into an MSS - * multiple and possibly a remainder. So update the mss now. - */ - if (features & NETIF_F_GSO_PARTIAL) - mss = skb->len - (skb->len % mss); - copy_destructor = gso_skb->destructor == tcp_wfree; ooo_okay = gso_skb->ooo_okay; /* All segments but the first should have ooo_okay cleared */ @@ -108,6 +102,13 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, /* Only first segment might have ooo_okay set */ segs->ooo_okay = ooo_okay; + /* GSO partial and frag_list segmentation only requires splitting + * the frame into an MSS multiple and possibly a remainder, both + * cases return a GSO skb. So update the mss now. + */ + if (skb_is_gso(segs)) + mss *= skb_shinfo(segs)->gso_segs; + delta = htonl(oldlen + (thlen + mss)); skb = segs; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8b45794eb6b2..7c777089a4d6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -734,9 +734,16 @@ static void tcp_tsq_handler(struct sock *sk) { if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | - TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) - tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle, + TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) { + struct tcp_sock *tp = tcp_sk(sk); + + if (tp->lost_out > tp->retrans_out && + tp->snd_cwnd > tcp_packets_in_flight(tp)) + tcp_xmit_retransmit_queue(sk); + + tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle, 0, GFP_ATOMIC); + } } /* * One tasklet per cpu tries to send more skbs. @@ -918,6 +925,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_mstamp_get(&skb->skb_mstamp); TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; + tcp_rate_skb_sent(sk, skb); if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); @@ -1213,6 +1221,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); + /* Update delivered info for the new segment */ + TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx; + /* If this packet has been sent out already, we must * adjust the various packet counters. */ @@ -1358,6 +1369,7 @@ int tcp_mss_to_mtu(struct sock *sk, int mss) } return mtu; } +EXPORT_SYMBOL(tcp_mss_to_mtu); /* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) @@ -1545,7 +1557,8 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, /* Return how many segs we'd like on a TSO packet, * to send one TSO packet per ms */ -static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now) +u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, + int min_tso_segs) { u32 bytes, segs; @@ -1557,10 +1570,23 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now) * This preserves ACK clocking and is consistent * with tcp_tso_should_defer() heuristic. */ - segs = max_t(u32, bytes / mss_now, sysctl_tcp_min_tso_segs); + segs = max_t(u32, bytes / mss_now, min_tso_segs); return min_t(u32, segs, sk->sk_gso_max_segs); } +EXPORT_SYMBOL(tcp_tso_autosize); + +/* Return the number of segments we want in the skb we are transmitting. + * See if congestion control module wants to decide; otherwise, autosize. + */ +static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) +{ + const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; + u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0; + + return tso_segs ? : + tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs); +} /* Returns the portion of skb which can be sent right away */ static unsigned int tcp_mss_split_point(const struct sock *sk, @@ -2020,6 +2046,39 @@ static int tcp_mtu_probe(struct sock *sk) return -1; } +/* TCP Small Queues : + * Control number of packets in qdisc/devices to two packets / or ~1 ms. + * (These limits are doubled for retransmits) + * This allows for : + * - better RTT estimation and ACK scheduling + * - faster recovery + * - high rates + * Alas, some drivers / subsystems require a fair amount + * of queued bytes to ensure line rate. + * One example is wifi aggregation (802.11 AMPDU) + */ +static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, + unsigned int factor) +{ + unsigned int limit; + + limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10); + limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); + limit <<= factor; + + if (atomic_read(&sk->sk_wmem_alloc) > limit) { + set_bit(TSQ_THROTTLED, &tcp_sk(sk)->tsq_flags); + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED, so we must + * test again the condition. + */ + smp_mb__after_atomic(); + if (atomic_read(&sk->sk_wmem_alloc) > limit) + return true; + } + return false; +} + /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. @@ -2057,7 +2116,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } } - max_segs = tcp_tso_autosize(sk, mss_now); + max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; @@ -2106,29 +2165,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) break; - /* TCP Small Queues : - * Control number of packets in qdisc/devices to two packets / or ~1 ms. - * This allows for : - * - better RTT estimation and ACK scheduling - * - faster recovery - * - high rates - * Alas, some drivers / subsystems require a fair amount - * of queued bytes to ensure line rate. - * One example is wifi aggregation (802.11 AMPDU) - */ - limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10); - limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); - - if (atomic_read(&sk->sk_wmem_alloc) > limit) { - set_bit(TSQ_THROTTLED, &tp->tsq_flags); - /* It is possible TX completion already happened - * before we set TSQ_THROTTLED, so we must - * test again the condition. - */ - smp_mb__after_atomic(); - if (atomic_read(&sk->sk_wmem_alloc) > limit) - break; - } + if (tcp_small_queue_check(sk, skb, 0)) + break; if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -2605,7 +2643,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) * copying overhead: fragmentation, tunneling, mangling etc. */ if (atomic_read(&sk->sk_wmem_alloc) > - min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) + min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), + sk->sk_sndbuf)) return -EAGAIN; if (skb_still_in_host_queue(sk, skb)) @@ -2774,7 +2813,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) last_lost = tp->snd_una; } - max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk)); + max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); tcp_for_write_queue_from(skb, sk) { __u8 sacked; int segs; @@ -2828,10 +2867,13 @@ begin_fwd: if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; + if (tcp_small_queue_check(sk, skb, 1)) + return; + if (tcp_retransmit_skb(sk, skb, segs)) return; - NET_INC_STATS(sock_net(sk), mib_idx); + NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb)); if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); @@ -3568,6 +3610,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) if (!res) { __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + if (unlikely(tcp_passive_fastopen(sk))) + tcp_sk(sk)->total_retrans++; } return res; } diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c new file mode 100644 index 000000000000..9be1581a5a08 --- /dev/null +++ b/net/ipv4/tcp_rate.c @@ -0,0 +1,186 @@ +#include <net/tcp.h> + +/* The bandwidth estimator estimates the rate at which the network + * can currently deliver outbound data packets for this flow. At a high + * level, it operates by taking a delivery rate sample for each ACK. + * + * A rate sample records the rate at which the network delivered packets + * for this flow, calculated over the time interval between the transmission + * of a data packet and the acknowledgment of that packet. + * + * Specifically, over the interval between each transmit and corresponding ACK, + * the estimator generates a delivery rate sample. Typically it uses the rate + * at which packets were acknowledged. However, the approach of using only the + * acknowledgment rate faces a challenge under the prevalent ACK decimation or + * compression: packets can temporarily appear to be delivered much quicker + * than the bottleneck rate. Since it is physically impossible to do that in a + * sustained fashion, when the estimator notices that the ACK rate is faster + * than the transmit rate, it uses the latter: + * + * send_rate = #pkts_delivered/(last_snd_time - first_snd_time) + * ack_rate = #pkts_delivered/(last_ack_time - first_ack_time) + * bw = min(send_rate, ack_rate) + * + * Notice the estimator essentially estimates the goodput, not always the + * network bottleneck link rate when the sending or receiving is limited by + * other factors like applications or receiver window limits. The estimator + * deliberately avoids using the inter-packet spacing approach because that + * approach requires a large number of samples and sophisticated filtering. + * + * TCP flows can often be application-limited in request/response workloads. + * The estimator marks a bandwidth sample as application-limited if there + * was some moment during the sampled window of packets when there was no data + * ready to send in the write queue. + */ + +/* Snapshot the current delivery information in the skb, to generate + * a rate sample later when the skb is (s)acked in tcp_rate_skb_delivered(). + */ +void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + + /* In general we need to start delivery rate samples from the + * time we received the most recent ACK, to ensure we include + * the full time the network needs to deliver all in-flight + * packets. If there are no packets in flight yet, then we + * know that any ACKs after now indicate that the network was + * able to deliver those packets completely in the sampling + * interval between now and the next ACK. + * + * Note that we use packets_out instead of tcp_packets_in_flight(tp) + * because the latter is a guess based on RTO and loss-marking + * heuristics. We don't want spurious RTOs or loss markings to cause + * a spuriously small time interval, causing a spuriously high + * bandwidth estimate. + */ + if (!tp->packets_out) { + tp->first_tx_mstamp = skb->skb_mstamp; + tp->delivered_mstamp = skb->skb_mstamp; + } + + TCP_SKB_CB(skb)->tx.first_tx_mstamp = tp->first_tx_mstamp; + TCP_SKB_CB(skb)->tx.delivered_mstamp = tp->delivered_mstamp; + TCP_SKB_CB(skb)->tx.delivered = tp->delivered; + TCP_SKB_CB(skb)->tx.is_app_limited = tp->app_limited ? 1 : 0; +} + +/* When an skb is sacked or acked, we fill in the rate sample with the (prior) + * delivery information when the skb was last transmitted. + * + * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is + * called multiple times. We favor the information from the most recently + * sent skb, i.e., the skb with the highest prior_delivered count. + */ +void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, + struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + + if (!scb->tx.delivered_mstamp.v64) + return; + + if (!rs->prior_delivered || + after(scb->tx.delivered, rs->prior_delivered)) { + rs->prior_delivered = scb->tx.delivered; + rs->prior_mstamp = scb->tx.delivered_mstamp; + rs->is_app_limited = scb->tx.is_app_limited; + rs->is_retrans = scb->sacked & TCPCB_RETRANS; + + /* Find the duration of the "send phase" of this window: */ + rs->interval_us = skb_mstamp_us_delta( + &skb->skb_mstamp, + &scb->tx.first_tx_mstamp); + + /* Record send time of most recently ACKed packet: */ + tp->first_tx_mstamp = skb->skb_mstamp; + } + /* Mark off the skb delivered once it's sacked to avoid being + * used again when it's cumulatively acked. For acked packets + * we don't need to reset since it'll be freed soon. + */ + if (scb->sacked & TCPCB_SACKED_ACKED) + scb->tx.delivered_mstamp.v64 = 0; +} + +/* Update the connection delivery information and generate a rate sample. */ +void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, + struct skb_mstamp *now, struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + u32 snd_us, ack_us; + + /* Clear app limited if bubble is acked and gone. */ + if (tp->app_limited && after(tp->delivered, tp->app_limited)) + tp->app_limited = 0; + + /* TODO: there are multiple places throughout tcp_ack() to get + * current time. Refactor the code using a new "tcp_acktag_state" + * to carry current time, flags, stats like "tcp_sacktag_state". + */ + if (delivered) + tp->delivered_mstamp = *now; + + rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ + rs->losses = lost; /* freshly marked lost */ + /* Return an invalid sample if no timing information is available. */ + if (!rs->prior_mstamp.v64) { + rs->delivered = -1; + rs->interval_us = -1; + return; + } + rs->delivered = tp->delivered - rs->prior_delivered; + + /* Model sending data and receiving ACKs as separate pipeline phases + * for a window. Usually the ACK phase is longer, but with ACK + * compression the send phase can be longer. To be safe we use the + * longer phase. + */ + snd_us = rs->interval_us; /* send phase */ + ack_us = skb_mstamp_us_delta(now, &rs->prior_mstamp); /* ack phase */ + rs->interval_us = max(snd_us, ack_us); + + /* Normally we expect interval_us >= min-rtt. + * Note that rate may still be over-estimated when a spuriously + * retransmistted skb was first (s)acked because "interval_us" + * is under-estimated (up to an RTT). However continuously + * measuring the delivery rate during loss recovery is crucial + * for connections suffer heavy or prolonged losses. + */ + if (unlikely(rs->interval_us < tcp_min_rtt(tp))) { + if (!rs->is_retrans) + pr_debug("tcp rate: %ld %d %u %u %u\n", + rs->interval_us, rs->delivered, + inet_csk(sk)->icsk_ca_state, + tp->rx_opt.sack_ok, tcp_min_rtt(tp)); + rs->interval_us = -1; + return; + } + + /* Record the last non-app-limited or the highest app-limited bw */ + if (!rs->is_app_limited || + ((u64)rs->delivered * tp->rate_interval_us >= + (u64)tp->rate_delivered * rs->interval_us)) { + tp->rate_delivered = rs->delivered; + tp->rate_interval_us = rs->interval_us; + tp->rate_app_limited = rs->is_app_limited; + } +} + +/* If a gap is detected between sends, mark the socket application-limited. */ +void tcp_rate_check_app_limited(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (/* We have less than one packet to send. */ + tp->write_seq - tp->snd_nxt < tp->mss_cache && + /* Nothing in sending host's qdisc queues or NIC tx queue. */ + sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) && + /* We are not limited by CWND. */ + tcp_packets_in_flight(tp) < tp->snd_cwnd && + /* All lost packets have been retransmitted. */ + tp->lost_out <= tp->retrans_out) + tp->app_limited = + (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; +} diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d84930b2dd95..f712b411f6ed 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -384,6 +384,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) */ inet_rtx_syn_ack(sk, req); req->num_timeout++; + icsk->icsk_retransmits++; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); } diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 028eb046ea40..9c5fc973267f 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -76,7 +76,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else if (!yeah->doing_reno_now) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 058c31286ce1..7d96dc2d3d08 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1021,12 +1021,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flow_flags, faddr, saddr, dport, inet->inet_sport); - if (!saddr && ipc.oif) { - err = l3mdev_get_saddr(net, ipc.oif, fl4); - if (err < 0) - goto out; - } - security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) { diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 8a9f6e535caa..9a89c10a55f0 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -20,7 +20,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, - struct nlattr *bc) + struct nlattr *bc, bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -28,7 +28,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, return inet_sk_diag_fill(sk, NULL, skb, req, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, net_admin); } static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, @@ -76,7 +76,8 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, err = inet_sk_diag_fill(sk, NULL, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); @@ -97,6 +98,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, struct nlattr *bc) { + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); int num, s_num, slot, s_slot; @@ -132,7 +134,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, r->id.idiag_dport) goto next; - if (sk_diag_dump(sk, skb, cb, r, bc) < 0) { + if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) { spin_unlock_bh(&hslot->lock); goto done; } @@ -186,8 +188,8 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = __udp4_lib_lookup(net, - req->id.idiag_dst[0], req->id.idiag_dport, - req->id.idiag_src[0], req->id.idiag_sport, + req->id.idiag_dst[3], req->id.idiag_dport, + req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if, tbl, NULL); else diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 81f253b6ff36..f9333c963607 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -21,7 +21,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, __be16 new_protocol, bool is_ipv6) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); - bool remcsum, need_csum, offload_csum, ufo; + bool remcsum, need_csum, offload_csum, ufo, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; @@ -88,6 +88,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, goto out; } + gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); + outer_hlen = skb_tnl_header_len(skb); udp_offset = outer_hlen - tnl_hlen; skb = segs; @@ -117,7 +119,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ - if (skb_is_gso(skb)) { + if (gso_partial) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index b644a23c3db0..6a7ff6957535 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -29,7 +29,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; - fl4->flowi4_oif = oif; + fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif); if (saddr) fl4->saddr = saddr->a4; @@ -112,7 +112,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) int oif = 0; if (skb_dst(skb)) - oif = l3mdev_fib_oif(skb_dst(skb)->dev); + oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; |