diff options
Diffstat (limited to 'net/ipv4')
71 files changed, 5335 insertions, 1575 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 6d3e8b1bd1f..34708343312 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -53,6 +53,44 @@ config IP_ADVANCED_ROUTER If unsure, say N here. +choice + prompt "Choose IP: FIB lookup algorithm (choose FIB_HASH if unsure)" + depends on IP_ADVANCED_ROUTER + default IP_FIB_HASH + +config IP_FIB_HASH + bool "FIB_HASH" + ---help--- + Current FIB is very proven and good enough for most users. + +config IP_FIB_TRIE + bool "FIB_TRIE" + ---help--- + Use new experimental LC-trie as FIB lookup algoritm. + This improves lookup performance if you have a large + number of routes. + + LC-trie is a longest matching prefix lookup algorithm which + performs better than FIB_HASH for large routing tables. + But, it consumes more memory and is more complex. + + LC-trie is described in: + + IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson + IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999 + An experimental study of compression methods for dynamic tries + Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. + http://www.nada.kth.se/~snilsson/public/papers/dyntrie2/ + +endchoice + +# If the user does not enable advanced routing, he gets the safe +# default of the fib-hash algorithm. +config IP_FIB_HASH + bool + depends on !IP_ADVANCED_ROUTER + default y + config IP_MULTIPLE_TABLES bool "IP: policy routing" depends on IP_ADVANCED_ROUTER @@ -407,5 +445,113 @@ config IP_TCPDIAG config IP_TCPDIAG_IPV6 def_bool (IP_TCPDIAG=y && IPV6=y) || (IP_TCPDIAG=m && IPV6) +config TCP_CONG_ADVANCED + bool "TCP: advanced congestion control" + depends on INET + default y + ---help--- + Support for selection of various TCP congestion control + modules. + + Nearly all users can safely say no here, and a safe default + selection will be made (BIC-TCP with new Reno as a fallback). + + If unsure, say N. + +# TCP Reno is builtin (required as fallback) +menu "TCP congestion control" + depends on TCP_CONG_ADVANCED + +config TCP_CONG_BIC + tristate "Binary Increase Congestion (BIC) control" + depends on INET + default y + ---help--- + BIC-TCP is a sender-side only change that ensures a linear RTT + fairness under large windows while offering both scalability and + bounded TCP-friendliness. The protocol combines two schemes + called additive increase and binary search increase. When the + congestion window is large, additive increase with a large + increment ensures linear RTT fairness as well as good + scalability. Under small congestion windows, binary search + increase provides TCP friendliness. + See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/ + +config TCP_CONG_WESTWOOD + tristate "TCP Westwood+" + depends on INET + default m + ---help--- + TCP Westwood+ is a sender-side only modification of the TCP Reno + protocol stack that optimizes the performance of TCP congestion + control. It is based on end-to-end bandwidth estimation to set + congestion window and slow start threshold after a congestion + episode. Using this estimation, TCP Westwood+ adaptively sets a + slow start threshold and a congestion window which takes into + account the bandwidth used at the time congestion is experienced. + TCP Westwood+ significantly increases fairness wrt TCP Reno in + wired networks and throughput over wireless links. + +config TCP_CONG_HTCP + tristate "H-TCP" + depends on INET + default m + ---help--- + H-TCP is a send-side only modifications of the TCP Reno + protocol stack that optimizes the performance of TCP + congestion control for high speed network links. It uses a + modeswitch to change the alpha and beta parameters of TCP Reno + based on network conditions and in a way so as to be fair with + other Reno and H-TCP flows. + +config TCP_CONG_HSTCP + tristate "High Speed TCP" + depends on INET && EXPERIMENTAL + default n + ---help--- + Sally Floyd's High Speed TCP (RFC 3649) congestion control. + A modification to TCP's congestion control mechanism for use + with large congestion windows. A table indicates how much to + increase the congestion window by when an ACK is received. + For more detail see http://www.icir.org/floyd/hstcp.html + +config TCP_CONG_HYBLA + tristate "TCP-Hybla congestion control algorithm" + depends on INET && EXPERIMENTAL + default n + ---help--- + TCP-Hybla is a sender-side only change that eliminates penalization of + long-RTT, large-bandwidth connections, like when satellite legs are + involved, expecially when sharing a common bottleneck with normal + terrestrial connections. + +config TCP_CONG_VEGAS + tristate "TCP Vegas" + depends on INET && EXPERIMENTAL + default n + ---help--- + TCP Vegas is a sender-side only change to TCP that anticipates + the onset of congestion by estimating the bandwidth. TCP Vegas + adjusts the sending rate by modifying the congestion + window. TCP Vegas should provide less packet loss, but it is + not as aggressive as TCP Reno. + +config TCP_CONG_SCALABLE + tristate "Scalable TCP" + depends on INET && EXPERIMENTAL + default n + ---help--- + Scalable TCP is a sender-side only change to TCP which uses a + MIMD congestion control algorithm which has some nice scaling + properties, though is known to have fairness issues. + See http://www-lce.eng.cam.ac.uk/~ctk21/scalable/ + +endmenu + +config TCP_CONG_BIC + boolean + depends on !TCP_CONG_ADVANCED + default y + source "net/ipv4/ipvs/Kconfig" diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 8b379627ebb..5718cdb3a61 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -5,10 +5,13 @@ obj-y := utils.o route.o inetpeer.o protocol.o \ ip_input.o ip_fragment.o ip_forward.o ip_options.o \ ip_output.o ip_sockglue.o \ - tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o tcp_minisocks.o \ + tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ + tcp_minisocks.o tcp_cong.o \ datagram.o raw.o udp.o arp.o icmp.o devinet.o af_inet.o igmp.o \ - sysctl_net_ipv4.o fib_frontend.o fib_semantics.o fib_hash.o + sysctl_net_ipv4.o fib_frontend.o fib_semantics.o +obj-$(CONFIG_IP_FIB_HASH) += fib_hash.o +obj-$(CONFIG_IP_FIB_TRIE) += fib_trie.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o obj-$(CONFIG_IP_MROUTE) += ipmr.o @@ -28,6 +31,13 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_IP_VS) += ipvs/ obj-$(CONFIG_IP_TCPDIAG) += tcp_diag.o obj-$(CONFIG_IP_ROUTE_MULTIPATH_CACHED) += multipath.o +obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o +obj-$(CONFIG_TCP_CONG_WESTWOOD) += tcp_westwood.o +obj-$(CONFIG_TCP_CONG_HSTCP) += tcp_highspeed.o +obj-$(CONFIG_TCP_CONG_HYBLA) += tcp_hybla.o +obj-$(CONFIG_TCP_CONG_HTCP) += tcp_htcp.o +obj-$(CONFIG_TCP_CONG_VEGAS) += tcp_vegas.o +obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b3cb49ce5fa..658e7977924 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1119,6 +1119,10 @@ module_init(inet_init); #ifdef CONFIG_PROC_FS extern int fib_proc_init(void); extern void fib_proc_exit(void); +#ifdef CONFIG_IP_FIB_TRIE +extern int fib_stat_proc_init(void); +extern void fib_stat_proc_exit(void); +#endif extern int ip_misc_proc_init(void); extern int raw_proc_init(void); extern void raw_proc_exit(void); @@ -1139,11 +1143,19 @@ static int __init ipv4_proc_init(void) goto out_udp; if (fib_proc_init()) goto out_fib; +#ifdef CONFIG_IP_FIB_TRIE + if (fib_stat_proc_init()) + goto out_fib_stat; + #endif if (ip_misc_proc_init()) goto out_misc; out: return rc; out_misc: +#ifdef CONFIG_IP_FIB_TRIE + fib_stat_proc_exit(); +out_fib_stat: +#endif fib_proc_exit(); out_fib: udp4_proc_exit(); @@ -1181,6 +1193,7 @@ EXPORT_SYMBOL(inet_stream_connect); EXPORT_SYMBOL(inet_stream_ops); EXPORT_SYMBOL(inet_unregister_protosw); EXPORT_SYMBOL(net_statistics); +EXPORT_SYMBOL(sysctl_ip_nonlocal_bind); #ifdef INET_REFCNT_DEBUG EXPORT_SYMBOL(inet_sock_nr); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 0e98f2235b6..514c85b2631 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -200,7 +200,7 @@ static void ah4_err(struct sk_buff *skb, u32 info) xfrm_state_put(x); } -static int ah_init_state(struct xfrm_state *x, void *args) +static int ah_init_state(struct xfrm_state *x) { struct ah_data *ahp = NULL; struct xfrm_algo_desc *aalg_desc; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 3cc96730c4e..d8a10e3dd77 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -233,11 +233,14 @@ int inet_addr_onlink(struct in_device *in_dev, u32 a, u32 b) static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, int destroy) { + struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa1 = *ifap; ASSERT_RTNL(); - /* 1. Deleting primary ifaddr forces deletion all secondaries */ + /* 1. Deleting primary ifaddr forces deletion all secondaries + * unless alias promotion is set + **/ if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { struct in_ifaddr *ifa; @@ -251,11 +254,16 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, continue; } - *ifap1 = ifa->ifa_next; + if (!IN_DEV_PROMOTE_SECONDARIES(in_dev)) { + *ifap1 = ifa->ifa_next; - rtmsg_ifa(RTM_DELADDR, ifa); - notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); - inet_free_ifa(ifa); + rtmsg_ifa(RTM_DELADDR, ifa); + notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); + inet_free_ifa(ifa); + } else { + promote = ifa; + break; + } } } @@ -281,6 +289,13 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, if (!in_dev->ifa_list) inetdev_destroy(in_dev); } + + if (promote && IN_DEV_PROMOTE_SECONDARIES(in_dev)) { + /* not sure if we should send a delete notify first? */ + promote->ifa_flags &= ~IFA_F_SECONDARY; + rtmsg_ifa(RTM_NEWADDR, promote); + notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); + } } static int inet_insert_ifa(struct in_ifaddr *ifa) @@ -1015,14 +1030,13 @@ static struct notifier_block ip_netdev_notifier = { }; static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, - u32 pid, u32 seq, int event) + u32 pid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*ifm)); - if (pid) nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); ifm = NLMSG_DATA(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; @@ -1075,7 +1089,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) continue; if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, - RTM_NEWADDR) <= 0) { + RTM_NEWADDR, NLM_F_MULTI) <= 0) { rcu_read_unlock(); goto done; } @@ -1098,7 +1112,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr* ifa) if (!skb) netlink_set_err(rtnl, 0, RTMGRP_IPV4_IFADDR, ENOBUFS); - else if (inet_fill_ifaddr(skb, ifa, 0, 0, event) < 0) { + else if (inet_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) { kfree_skb(skb); netlink_set_err(rtnl, 0, RTMGRP_IPV4_IFADDR, EINVAL); } else { @@ -1384,6 +1398,15 @@ static struct devinet_sysctl_table { .proc_handler = &ipv4_doint_and_flush, .strategy = &ipv4_doint_and_flush_strategy, }, + { + .ctl_name = NET_IPV4_CONF_PROMOTE_SECONDARIES, + .procname = "promote_secondaries", + .data = &ipv4_devconf.promote_secondaries, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &ipv4_doint_and_flush, + .strategy = &ipv4_doint_and_flush_strategy, + }, }, .devinet_dev = { { @@ -1448,7 +1471,7 @@ static void devinet_sysctl_register(struct in_device *in_dev, * by sysctl and we wouldn't want anyone to change it under our feet * (see SIOCSIFNAME). */ - dev_name = net_sysctl_strdup(dev_name); + dev_name = kstrdup(dev_name, GFP_KERNEL); if (!dev_name) goto free; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 053a883247b..ba57446d5d1 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -362,7 +362,7 @@ static void esp_destroy(struct xfrm_state *x) kfree(esp); } -static int esp_init_state(struct xfrm_state *x, void *args) +static int esp_init_state(struct xfrm_state *x) { struct esp_data *esp = NULL; @@ -478,7 +478,7 @@ static int __init esp4_init(void) { struct xfrm_decap_state decap; - if (sizeof(struct esp_decap_data) < + if (sizeof(struct esp_decap_data) > sizeof(decap.decap_data)) { extern void decap_data_too_small(void); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 563e7d61270..cd8e45ab958 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -516,6 +516,60 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) #undef BRD1_OK } +static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) +{ + + struct fib_result res; + struct flowi fl = { .nl_u = { .ip4_u = { .daddr = frn->fl_addr, + .fwmark = frn->fl_fwmark, + .tos = frn->fl_tos, + .scope = frn->fl_scope } } }; + if (tb) { + local_bh_disable(); + + frn->tb_id = tb->tb_id; + frn->err = tb->tb_lookup(tb, &fl, &res); + + if (!frn->err) { + frn->prefixlen = res.prefixlen; + frn->nh_sel = res.nh_sel; + frn->type = res.type; + frn->scope = res.scope; + } + local_bh_enable(); + } +} + +static void nl_fib_input(struct sock *sk, int len) +{ + struct sk_buff *skb = NULL; + struct nlmsghdr *nlh = NULL; + struct fib_result_nl *frn; + int err; + u32 pid; + struct fib_table *tb; + + skb = skb_recv_datagram(sk, 0, 0, &err); + nlh = (struct nlmsghdr *)skb->data; + + frn = (struct fib_result_nl *) NLMSG_DATA(nlh); + tb = fib_get_table(frn->tb_id_in); + + nl_fib_lookup(frn, tb); + + pid = nlh->nlmsg_pid; /*pid of sending process */ + NETLINK_CB(skb).groups = 0; /* not in mcast group */ + NETLINK_CB(skb).pid = 0; /* from kernel */ + NETLINK_CB(skb).dst_pid = pid; + NETLINK_CB(skb).dst_groups = 0; /* unicast */ + netlink_unicast(sk, skb, pid, MSG_DONTWAIT); +} + +static void nl_fib_lookup_init(void) +{ + netlink_kernel_create(NETLINK_FIB_LOOKUP, nl_fib_input); +} + static void fib_disable_ip(struct net_device *dev, int force) { if (fib_sync_down(0, dev, force)) @@ -604,6 +658,7 @@ void __init ip_fib_init(void) register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); + nl_fib_lookup_init(); } EXPORT_SYMBOL(inet_addr_type); diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 6506dcc01b4..b10d6bb5ef3 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -703,7 +703,8 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, &f->fn_key, fz->fz_order, fa->fa_tos, - fa->fa_info) < 0) { + fa->fa_info, + NLM_F_MULTI) < 0) { cb->args[3] = i; return -1; } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index ac4485f75e9..b729d97cfa9 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -30,7 +30,8 @@ extern int fib_nh_match(struct rtmsg *r, struct nlmsghdr *, struct kern_rta *rta, struct fib_info *fi); extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u8 tb_id, u8 type, u8 scope, void *dst, - int dst_len, u8 tos, struct fib_info *fi); + int dst_len, u8 tos, struct fib_info *fi, + unsigned int); extern void rtmsg_fib(int event, u32 key, struct fib_alias *fa, int z, int tb_id, struct nlmsghdr *n, struct netlink_skb_parms *req); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 39d0aadb9a2..0b298bbc151 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -367,13 +367,14 @@ static struct notifier_block fib_rules_notifier = { static __inline__ int inet_fill_rule(struct sk_buff *skb, struct fib_rule *r, - struct netlink_callback *cb) + struct netlink_callback *cb, + unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, NETLINK_CREDS(cb->skb)->pid, cb->nlh->nlmsg_seq, RTM_NEWRULE, sizeof(*rtm)); + nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWRULE, sizeof(*rtm), flags); rtm = NLMSG_DATA(nlh); rtm->rtm_family = AF_INET; rtm->rtm_dst_len = r->r_dst_len; @@ -422,7 +423,7 @@ int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) for (r=fib_rules, idx=0; r; r = r->r_next, idx++) { if (idx < s_idx) continue; - if (inet_fill_rule(skb, r, cb) < 0) + if (inet_fill_rule(skb, r, cb, NLM_F_MULTI) < 0) break; } read_unlock(&fib_rules_lock); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 029362d6613..c886b28ba9f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -276,7 +276,7 @@ void rtmsg_fib(int event, u32 key, struct fib_alia |