diff options
Diffstat (limited to 'net/ipv4')
58 files changed, 798 insertions, 392 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index c9a1c68767f..8e3a1fd938a 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -250,6 +250,20 @@ config IP_MROUTE <file:Documentation/networking/multicast.txt>. If you haven't heard about it, you don't need it. +config IP_MROUTE_MULTIPLE_TABLES + bool "IP: multicast policy routing" + depends on IP_MROUTE && IP_ADVANCED_ROUTER + select FIB_RULES + help + Normally, a multicast router runs a userspace daemon and decides + what to do with a multicast packet based on the source and + destination addresses. If you say Y here, the multicast router + will also be able to take interfaces and packet marks into + account and run multiple instances of userspace daemons + simultaneously, each one handling a single table. + + If unsure, say N. + config IP_PIMSM_V1 bool "IP: PIM-SM version 1 support" depends on IP_MROUTE diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 33b7dffa773..c5376c72550 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -86,6 +86,7 @@ #include <linux/poll.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> +#include <linux/slab.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -153,7 +154,7 @@ void inet_sock_destruct(struct sock *sk) WARN_ON(sk->sk_forward_alloc); kfree(inet->opt); - dst_release(sk->sk_dst_cache); + dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); @@ -418,6 +419,8 @@ int inet_release(struct socket *sock) if (sk) { long timeout; + inet_rps_reset_flow(sk); + /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); @@ -530,6 +533,8 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr, { struct sock *sk = sock->sk; + if (addr_len < sizeof(uaddr->sa_family)) + return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) return sk->sk_prot->disconnect(sk, flags); @@ -573,6 +578,9 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int err; long timeo; + if (addr_len < sizeof(uaddr->sa_family)) + return -EINVAL; + lock_sock(sk); if (uaddr->sa_family == AF_UNSPEC) { @@ -714,6 +722,8 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; + inet_rps_record_flow(sk); + /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; @@ -722,12 +732,13 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(inet_sendmsg); - static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { struct sock *sk = sock->sk; + inet_rps_record_flow(sk); + /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; @@ -737,6 +748,22 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, return sock_no_sendpage(sock, page, offset, size, flags); } +int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct sock *sk = sock->sk; + int addr_len = 0; + int err; + + inet_rps_record_flow(sk); + + err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT, + flags & ~MSG_DONTWAIT, &addr_len); + if (err >= 0) + msg->msg_namelen = addr_len; + return err; +} +EXPORT_SYMBOL(inet_recvmsg); int inet_shutdown(struct socket *sock, int how) { @@ -866,7 +893,7 @@ const struct proto_ops inet_stream_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = tcp_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = tcp_sendpage, .splice_read = tcp_splice_read, @@ -893,7 +920,7 @@ const struct proto_ops inet_dgram_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT @@ -923,7 +950,7 @@ static const struct proto_ops inet_sockraw_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT @@ -1401,10 +1428,10 @@ EXPORT_SYMBOL_GPL(snmp_fold_field); int snmp_mib_init(void __percpu *ptr[2], size_t mibsize) { BUG_ON(ptr == NULL); - ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long long)); + ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long)); if (!ptr[0]) goto err0; - ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long long)); + ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long)); if (!ptr[1]) goto err1; return 0; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 987b47dc69a..880a5ec6dce 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -1,6 +1,7 @@ #include <crypto/hash.h> #include <linux/err.h> #include <linux/module.h> +#include <linux/slab.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ah.h> diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index c4dd1354280..6e747065c20 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -98,6 +98,7 @@ #include <linux/net.h> #include <linux/rcupdate.h> #include <linux/jhash.h> +#include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 1e029dc7545..c97cd9ff697 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -44,6 +44,7 @@ #include <linux/string.h> #include <linux/jhash.h> #include <linux/audit.h> +#include <linux/slab.h> #include <net/ip.h> #include <net/icmp.h> #include <net/tcp.h> diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 51ca946e339..382bc768ed5 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -50,6 +50,7 @@ #include <linux/notifier.h> #include <linux/inetdevice.h> #include <linux/igmp.h> +#include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif @@ -1095,10 +1096,10 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, case NETDEV_DOWN: ip_mc_down(in_dev); break; - case NETDEV_BONDING_OLDTYPE: + case NETDEV_PRE_TYPE_CHANGE: ip_mc_unmap(in_dev); break; - case NETDEV_BONDING_NEWTYPE: + case NETDEV_POST_TYPE_CHANGE: ip_mc_remap(in_dev); break; case NETDEV_CHANGEMTU: @@ -1194,7 +1195,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(dev, node, head, index_hlist) { if (idx < s_idx) goto cont; - if (idx > s_idx) + if (h > s_h || idx > s_idx) s_ip_idx = 0; in_dev = __in_dev_get_rcu(dev); if (!in_dev) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 9b3e28ed524..4f0ed458c88 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -34,6 +34,7 @@ #include <linux/skbuff.h> #include <linux/init.h> #include <linux/list.h> +#include <linux/slab.h> #include <net/ip.h> #include <net/protocol.h> diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 14972017b9c..4ed7e0dea1b 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -32,6 +32,7 @@ #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> +#include <linux/slab.h> #include <net/net_namespace.h> #include <net/ip.h> diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index ca2d07b1c70..3ec84fea5b7 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -213,7 +213,6 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, { struct fib4_rule *rule4 = (struct fib4_rule *) rule; - frh->family = AF_INET; frh->dst_len = rule4->dst_len; frh->src_len = rule4->src_len; frh->tos = rule4->tos; @@ -234,23 +233,6 @@ nla_put_failure: return -ENOBUFS; } -static u32 fib4_rule_default_pref(struct fib_rules_ops *ops) -{ - struct list_head *pos; - struct fib_rule *rule; - - if (!list_empty(&ops->rules_list)) { - pos = ops->rules_list.next; - if (pos->next != &ops->rules_list) { - rule = list_entry(pos->next, struct fib_rule, list); - if (rule->pref) - return rule->pref - 1; - } - } - - return 0; -} - static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(4) /* dst */ @@ -264,7 +246,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops) } static struct fib_rules_ops fib4_rules_ops_template = { - .family = AF_INET, + .family = FIB_RULES_IPV4, .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), .action = fib4_rule_action, @@ -272,7 +254,7 @@ static struct fib_rules_ops fib4_rules_ops_template = { .configure = fib4_rule_configure, .compare = fib4_rule_compare, .fill = fib4_rule_fill, - .default_pref = fib4_rule_default_pref, + .default_pref = fib_default_rule_pref, .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, .nlgroup = RTNLGRP_IPV4_RULE, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 1af0ea0fb6a..20f09c5b31e 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -32,6 +32,7 @@ #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/init.h> +#include <linux/slab.h> #include <net/arp.h> #include <net/ip.h> diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index af5d8979286..59a838795e3 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -71,6 +71,7 @@ #include <linux/netlink.h> #include <linux/init.h> #include <linux/list.h> +#include <linux/slab.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> @@ -961,7 +962,9 @@ fib_find_node(struct trie *t, u32 key) struct node *n; pos = 0; - n = rcu_dereference(t->trie); + n = rcu_dereference_check(t->trie, + rcu_read_lock_held() || + lockdep_rtnl_is_held()); while (n != NULL && NODE_TYPE(n) == T_TNODE) { tn = (struct tnode *) n; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 4b4c2bcd15d..f3d339f728b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -74,6 +74,7 @@ #include <linux/netdevice.h> #include <linux/string.h> #include <linux/netfilter_ipv4.h> +#include <linux/slab.h> #include <net/snmp.h> #include <net/ip.h> #include <net/route.h> @@ -330,9 +331,10 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, if (ip_append_data(sk, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, - ipc, rt, MSG_DONTWAIT) < 0) + ipc, rt, MSG_DONTWAIT) < 0) { + ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_OUTERRORS); ip_flush_pending_frames(sk); - else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { + } else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { struct icmphdr *icmph = icmp_hdr(skb); __wsum csum = 0; struct sk_buff *skb1; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 63bf298ca10..5fff865a4fa 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -71,6 +71,7 @@ */ #include <linux/module.h> +#include <linux/slab.h> #include <asm/uaccess.h> #include <asm/system.h> #include <linux/types.h> @@ -997,7 +998,7 @@ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) - dev_mc_add(dev, buf, dev->addr_len, 0); + dev_mc_add(dev, buf); } /* @@ -1010,7 +1011,7 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) - dev_mc_delete(dev, buf, dev->addr_len, 0); + dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 1aaa8110d84..e5fa2ddce32 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/fcntl.h> #include <linux/random.h> +#include <linux/slab.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/time.h> diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index eaf3e2c8646..a2ca6aed763 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -19,6 +19,7 @@ #include <linux/random.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> +#include <linux/slab.h> #include <net/inet_frag.h> diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index cc94cc2d8b2..c5af909cf70 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/kmemcheck.h> +#include <linux/slab.h> #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/ip.h> diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 9f2cd47ceeb..56cdf68a074 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -25,6 +25,7 @@ #include <linux/ip.h> #include <linux/icmp.h> #include <linux/netdevice.h> +#include <linux/slab.h> #include <net/sock.h> #include <net/ip.h> #include <net/tcp.h> diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b59430bc041..75347ea70ea 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -32,6 +32,7 @@ #include <linux/netdevice.h> #include <linux/jhash.h> #include <linux/random.h> +#include <linux/slab.h> #include <net/route.h> #include <net/dst.h> #include <net/sock.h> diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f47c9f76754..fe381d12ecd 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <asm/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> @@ -810,11 +811,13 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev tunnel->err_count = 0; } - max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen; + max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->u.dst.header_len; if (skb_headroom(skb) < max_headroom || skb_shared(skb)|| (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); + if (max_headroom > dev->needed_headroom) + dev->needed_headroom = max_headroom; if (!new_skb) { ip_rt_put(rt); txq->tx_dropped++; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 091b5c7e04e..af76de5f76d 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -119,6 +119,7 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> +#include <linux/slab.h> #include <linux/net.h> #include <linux/socket.h> diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 94bf105ef3c..4c09a31fd14 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -11,6 +11,7 @@ #include <linux/capability.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/types.h> #include <asm/uaccess.h> #include <linux/skbuff.h> diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f09135e1e14..b0b2e3059f1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -51,6 +51,7 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/highmem.h> +#include <linux/slab.h> #include <linux/socket.h> #include <linux/sockios.h> @@ -310,7 +311,7 @@ int ip_output(struct sk_buff *skb) !(IPCB(skb)->flags & IPSKB_REROUTED)); } -int ip_queue_xmit(struct sk_buff *skb, int ipfragok) +int ip_queue_xmit(struct sk_buff *skb) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); @@ -369,7 +370,7 @@ packet_routed: skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff)); - if (ip_dont_fragment(sk, &rt->u.dst) && !ipfragok) + if (ip_dont_fragment(sk, &rt->u.dst) && !skb->local_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 644dc43a55d..b0aa0546a3b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -23,6 +23,7 @@ #include <linux/icmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> +#include <linux/slab.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> @@ -286,12 +287,8 @@ int ip_ra_control(struct sock *sk, unsigned char on, void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { - struct inet_sock *inet = inet_sk(sk); struct sock_exterr_skb *serr; - if (!inet->recverr) - return; - skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 67890928164..b9d84e800cf 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -53,6 +53,7 @@ #include <linux/root_dev.h> #include <linux/delay.h> #include <linux/nfs_fs.h> +#include <linux/slab.h> #include <net/net_namespace.h> #include <net/arp.h> #include <net/ip.h> @@ -975,7 +976,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str /* Is it a reply for the device we are configuring? */ if (b->xid != ic_dev_xid) { if (net_ratelimit()) - printk(KERN_ERR "DHCP/BOOTP: Ignoring delayed packet \n"); + printk(KERN_ERR "DHCP/BOOTP: Ignoring delayed packet\n"); goto drop_unlock; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 2f302d3ac9a..0b27b14dcc9 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -95,6 +95,7 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <asm/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 1d42f6103c8..1aa498d7a0a 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -47,6 +47,7 @@ #include <linux/mroute.h> #include <linux/init.h> #include <linux/if_ether.h> +#include <linux/slab.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> @@ -62,11 +63,40 @@ #include <net/ipip.h> #include <net/checksum.h> #include <net/netlink.h> +#include <net/fib_rules.h> #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) #define CONFIG_IP_PIMSM 1 #endif +struct mr_table { + struct list_head list; +#ifdef CONFIG_NET_NS + struct net *net; +#endif + u32 id; + struct sock *mroute_sk; + struct timer_list ipmr_expire_timer; + struct list_head mfc_unres_queue; + struct list_head mfc_cache_array[MFC_LINES]; + struct vif_device vif_table[MAXVIFS]; + int maxvif; + atomic_t cache_resolve_queue_len; + int mroute_do_assert; + int mroute_do_pim; +#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) + int mroute_reg_vif_num; +#endif +}; + +struct ipmr_rule { + struct fib_rule common; +}; + +struct ipmr_result { + struct mr_table *mrt; +}; + /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ @@ -77,9 +107,7 @@ static DEFINE_RWLOCK(mrt_lock); * Multicast router control variables */ -#define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL) - -static struct mfc_cache *mfc_unres_queue; /* Queue of unresolved entries */ +#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -94,12 +122,215 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; -static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local); -static int ipmr_cache_report(struct net *net, +static struct mr_table *ipmr_new_table(struct net *net, u32 id); +static int ip_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *cache, + int local); +static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); -static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); +static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + struct mfc_cache *c, struct rtmsg *rtm); +static void ipmr_expire_process(unsigned long arg); + +#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES +#define ipmr_for_each_table(mrt, net) \ + list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list) + +static struct mr_table *ipmr_get_table(struct net *net, u32 id) +{ + struct mr_table *mrt; + + ipmr_for_each_table(mrt, net) { + if (mrt->id == id) + return mrt; + } + return NULL; +} + +static int ipmr_fib_lookup(struct net *net, struct flowi *flp, + struct mr_table **mrt) +{ + struct ipmr_result res; + struct fib_lookup_arg arg = { .result = &res, }; + int err; + + err = fib_rules_lookup(net->ipv4.mr_rules_ops, flp, 0, &arg); + if (err < 0) + return err; + *mrt = res.mrt; + return 0; +} + +static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct ipmr_result *res = arg->result; + struct mr_table *mrt; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + return -ENETUNREACH; + case FR_ACT_PROHIBIT: + return -EACCES; + case FR_ACT_BLACKHOLE: + default: + return -EINVAL; + } + + mrt = ipmr_get_table(rule->fr_net, rule->table); + if (mrt == NULL) + return -EAGAIN; + res->mrt = mrt; + return 0; +} + +static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +{ + return 1; +} + +static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = { + FRA_GENERIC_POLICY, +}; + +static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh, struct nlattr **tb) +{ + return 0; +} + +static int ipmr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + return 1; +} + +static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh) +{ + frh->dst_len = 0; + frh->src_len = 0; + frh->tos = 0; + return 0; +} + +static struct fib_rules_ops ipmr_rules_ops_template = { + .family = FIB_RULES_IPMR, + .rule_size = sizeof(struct ipmr_rule), + .addr_size = sizeof(u32), + .action = ipmr_rule_action, + .match = ipmr_rule_match, + .configure = ipmr_rule_configure, + .compare = ipmr_rule_compare, + .default_pref = fib_default_rule_pref, + .fill = ipmr_rule_fill, + .nlgroup = RTNLGRP_IPV4_RULE, + .policy = ipmr_rule_policy, + .owner = THIS_MODULE, +}; + +static int __net_init ipmr_rules_init(struct net *net) +{ + struct fib_rules_ops *ops; + struct mr_table *mrt; + int err; + + ops = fib_rules_register(&ipmr_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + INIT_LIST_HEAD(&net->ipv4.mr_tables); + + mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); + if (mrt == NULL) { + err = -ENOMEM; + goto err1; + } + + err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT, 0); + if (err < 0) + goto err2; + + net->ipv4.mr_rules_ops = ops; + return 0; + +err2: + kfree(mrt); +err1: + fib_rules_unregister(ops); + return err; +} + +static void __net_exit ipmr_rules_exit(struct net *net) +{ + struct mr_table *mrt, *next; + + list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) + kfree(mrt); + fib_rules_unregister(net->ipv4.mr_rules_ops); +} +#else +#define ipmr_for_each_table(mrt, net) \ + for (mrt = net->ipv4.mrt; mrt; mrt = NULL) + +static struct mr_table *ipmr_get_table(struct net *net, u32 id) +{ + return net->ipv4.mrt; +} + +static int ipmr_fib_lookup(struct net *net, struct flowi *flp, + struct mr_table **mrt) +{ + *mrt = net->ipv4.mrt; + return 0; +} + +static int __net_init ipmr_rules_init(struct net *net) +{ + net->ipv4.mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); + return net->ipv4.mrt ? 0 : -ENOMEM; +} + +static void __net_exit ipmr_rules_exit(struct net *net) +{ + kfree(net->ipv4.mrt); +} +#endif + +static struct mr_table *ipmr_new_table(struct net *net, u32 id) +{ + struct mr_table *mrt; + unsigned int i; -static struct timer_list ipmr_expire_timer; + mrt = ipmr_get_table(net, id); + if (mrt != NULL) + return mrt; + + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (mrt == NULL) + return NULL; + write_pnet(&mrt->net, net); + mrt->id = id; + + /* Forwarding cache */ + for (i = 0; i < MFC_LINES; i++) + INIT_LIST_HEAD(&mrt->mfc_cache_array[i]); + + INIT_LIST_HEAD(&mrt->mfc_unres_queue); + + setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, + (unsigned long)mrt); + +#ifdef CONFIG_IP_PIMSM + mrt->mroute_reg_vif_num = -1; +#endif +#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES + list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); +#endif + return mrt; +} /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ @@ -200,12 +431,22 @@ failure: static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); + struct mr_table *mrt; + struct flowi fl = { + .oif = dev->ifindex, + .iif = skb->skb_iif, + .mark = skb->mark, + }; + int err; + + err = ipmr_fib_lookup(net, &fl, &mrt); + if (err < 0) + return err; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; dev->stats.tx_packets++; - ipmr_cache_report(net, skb, net->ipv4.mroute_reg_vif_num, - IGMPMSG_WHOLEPKT); + ipmr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, IGMPMSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); return NETDEV_TX_OK; @@ -225,12 +466,18 @@ static void reg_vif_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static struct net_device *ipmr_reg_vif(struct net *net) +static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; struct in_device *in_dev; + char name[IFNAMSIZ]; - dev = alloc_netdev(0, "pimreg", reg_vif_setup); + if (mrt->id == RT_TABLE_DEFAULT) + sprintf(name, "pimreg"); + else + sprintf(name, "pimreg%u", mrt->id); + + dev = alloc_netdev(0, name, reg_vif_setup); if (dev == NULL) return NULL; @@ -275,17 +522,17 @@ failure: * @notify: Set to 1, if the caller is a notifier_call */ -static int vif_delete(struct net *net, int vifi, int notify, +static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { struct vif_device *v; struct net_device *dev; struct in_device *in_dev; - if (vifi < 0 || vifi >= net->ipv4.maxvif) + if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; - v = &net->ipv4.vif_table[vifi]; + v = &mrt->vif_table[vifi]; write_lock_bh(&mrt_lock); dev = v->dev; @@ -297,17 +544,17 @@ static int vif_delete(struct net *net, int vifi, int notify, } #ifdef CONFIG_IP_PIMSM - if (vifi == net->ipv4.mroute_reg_vif_num) - net->ipv4.mroute_reg_vif_num = -1; + if (vifi == mrt->mroute_reg_vif_num) + mrt->mroute_reg_vif_num = -1; #endif - if (vifi+1 == net->ipv4.maxvif) { + if (vifi+1 == mrt->maxvif) { int tmp; for (tmp=vifi-1; tmp>=0; tmp--) { - if (VIF_EXISTS(net, tmp)) + if (VIF_EXISTS(mrt, tmp)) break; } - net->ipv4.maxvif = tmp+1; + mrt->maxvif = tmp+1; } write_unlock_bh(&mrt_lock); @@ -328,7 +575,6 @@ static int vif_delete(struct net *net, int vifi, int notify, static inline void ipmr_cache_free(struct mfc_cache *c) { - release_net(mfc_net(c)); kmem_cache_free(mrt_cachep, c); } @@ -336,13 +582,13 @@ static inline void ipmr_cache_free(struct mfc_cache *c) and reporting error to netlink readers. */ -static void ipmr_destroy_unres(struct mfc_cache *c) +static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) { + struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; struct nlmsgerr *e; - struct net *net = mfc_net(c); - atomic_dec(&net->ipv4.cache_resolve_queue_len); + atomic_dec(&mrt->cache_resolve_queue_len); while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { @@ -363,42 +609,40 @@ static void ipmr_destroy_unres(struct mfc_cache *c) } -/* Single timer process for all the unresolved queue. */ +/* Timer process for the unresolved queue. */ -static void ipmr_expire_process(unsigned long dummy) +static void ipmr_expire_process(unsigned long arg) { + struct mr_table *mrt = (struct mr_table *)arg; unsigned long now; unsigned long expires; - struct mfc_cache *c, **cp; + struct mfc_cache *c, *next; if (!spin_trylock(&mfc_unres_lock)) { - mod_timer(&ipmr_expire_timer, jiffies+HZ/10); + mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10); return; } - if (mfc_unres_queue == NULL) + if (list_empty(&mrt->mfc_unres_queue)) goto out; now = jiffies; expires = 10*HZ; - cp = &mfc_unres_queue; - while ((c=*cp) != NULL) { + list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; - cp = &c->next; continue; } - *cp = c->next; - - ipmr_destroy_unres(c); + list_del(&c->list); + ipmr_destroy_unres(mrt, c); } - if (mfc_unres_queue != NULL) - mod_timer(&ipmr_expire_timer, jiffies + expires); + if (!list_empty(&mrt->mfc_unres_queue)) + mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); out: spin_unlock(&mfc_unres_lock); @@ -406,17 +650,17 @@ out: /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls) +static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache, + unsigned char *ttls) { int vifi; - struct net *net = mfc_net(cache); cache->mfc_un.res.minvif = MAXVIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXVIFS); - for (vifi = 0; vifi < net->ipv4.maxvif; vifi++) { - if (VIF_EXISTS(net, vifi) && + for (vifi = 0; vifi < mrt->maxvif; vifi++) { + if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) @@ -427,16 +671,17 @@ static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls) } } -static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) +static int vif_add(struct net *net, struct mr_table *mrt, + struct vifctl *vifc, int mrtsock) { int vifi = vifc->vifc_vifi; - struct vif_device *v = &net->ipv4.vif_table[vifi]; + struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; int err; /* Is vif busy ? */ - if (VIF_EXISTS(net, vifi)) + if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->vifc_flags) { @@ -446,9 +691,9 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ - if (net->ipv4.mroute_reg_vif_num >= 0) + if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; - dev = ipmr_reg_vif(net); + dev = ipmr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); @@ -524,49 +769,47 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) v->dev = dev; #ifdef CONFIG_IP_PIMSM if (v->flags&VIFF_REGISTER) - net->ipv4.mroute_reg_vif_num = vifi; + mrt->mroute_reg_vif_num = vifi; #endif - if (vifi+1 > net->ipv4.maxvif) - net->ipv4.maxvif = vifi+1; + if (vifi+1 > mrt->maxvif) + mrt->maxvif = vifi+1; write_unlock_bh(&mrt_lock); return 0; } -static struct mfc_cache *ipmr_cache_find(struct net *net, +static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, __be32 origin, __be32 mcastgrp) { int line = MFC_HASH(mcastgrp, origin); struct mfc_cache *c; - for (c = net->ipv4.mfc_cache_array[line]; c; c = c->next) { - if (c->mfc_origin==origin && c->mfc_mcastgrp==mcastgrp) - break; + list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { + if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp) + return c; } - return c; + return NULL; } /* * Allocate a multicast cache entry */ -static struct mfc_cache *ipmr_cache_alloc(struct net *net) +static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c == NULL) return NULL; c->mfc_un.res.minvif = MAXVIFS; - mfc_net_set(c, net); return c; } -static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net) +static struct mfc_cache *ipmr_cache_alloc_unres(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c == NULL) return NULL; skb_queue_head_init(&c->mfc_un.unres.unresolved); c->mfc_un.unres.expires = jiffies + 10*HZ; - mfc_net_set(c, net); return c; } @@ -574,7 +817,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net) * A cache entry has gone into a resolved state from queued */ -static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) +static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, + struct mfc_cache *uc, struct mfc_cache *c) { struct sk_buff *skb; struct nlmsgerr *e; @@ -587,7 +831,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); - if (ipmr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) { + if (ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) { nlh->nlmsg_len = (skb_tail_pointer(skb) - (u8 *)nlh); } else { @@ -599,9 +843,9 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) memset(&e->msg, 0, sizeof(e->msg)); } - rtnl_unicast(skb, mfc_net(c), NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).pid); } else - ip_mr_forward(skb, c, 0); + ip_mr_forward(net, mrt, skb, c, 0); } } @@ -612,7 +856,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) * Called under mrt_lock. */ -static int ipmr_cache_report(struct net *net, +static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert) { struct sk_buff *skb; @@ -645,7 +889,7 @@ static int ipmr_cache_report(struct net *net, memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); msg->im_msgtype = IGMPMSG_WHOLEPKT; msg->im_mbz = 0; - msg->im_vif = net->ipv4.mroute_reg_vif_num; + msg->im_vif = mrt->mroute_reg_vif_num; ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); @@ -677,7 +921,7 @@ static int ipmr_cache_report(struct net *net, skb->transport_header = skb->network_header; } - if (net->ipv4.mroute_sk == NULL) { + if (mrt->mroute_sk == NULL) { kfree_skb(skb); return -EINVAL; } @@ -685,7 +929,7 @@ static int ipmr_cache_report(struct net *net, /* * Deliver to mrouted */ - ret = sock_queue_rcv_skb(net->ipv4.mroute_sk, skb); + ret = sock_queue_rcv_skb(mrt->mroute_sk, skb); if (ret < 0) { if (net_ratelimit()) printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n"); @@ -700,27 +944,29 @@ static int ipmr_cache_report(struct net *net, */ static int -ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) +ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) { + bool found = false; int err; struct mfc_cache *c; const struct iphdr *iph = ip_hdr(skb); spin_lock_bh(&mfc_unres_lock); - for (c=mfc_unres_queue; c; c=c->next) { - if (net_eq(mfc_net(c), net) && - c->mfc_mcastgrp == iph->daddr && - c->mfc_origin == iph->saddr) + list_for_each_entry(c, &mrt->mfc_unres_queue, list) { + if (c->mfc_mcastgrp == iph->daddr && + c->mfc_origin == iph->saddr) { + found = true; break; + } } - if (c == NULL) { + if (!found) { /* * Create a new entry if allowable */ - if (atomic_read(&net->ipv4.cache_resolve_queue_len) >= 10 || - (c = ipmr_cache_alloc_unres(net)) == NULL) { + if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || + (c = ipmr_cache_alloc_unres()) == NULL) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); @@ -737,7 +983,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) /* * Reflect first query at mrouted. */ - err = ipmr_cache_report(net, skb, vifi, IGMPMSG_NOCACHE); + err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker @@ -749,11 +995,10 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) return err; } - atomic_inc(&net->ipv4.cache_resolve_queue_len); - c->next = mfc_unres_queue; - mfc_unres_queue = c; + atomic_inc(&mrt->cache_resolve_queue_len); + list_add(&c->list, &mrt->mfc_unres_queue); - mod_timer(&ipmr_expire_timer, c->mfc_un.unres.expires); + mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); } /* @@ -775,19 +1020,18 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) * MFC cache manipulation by user space mroute daemon */ -static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc) +static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) { int line; - struct mfc_cache *c, **cp; + struct mfc_cache *c, *next; line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); - for (cp = &net->ipv4.mfc_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ipmr_cache_free(c); @@ -797,24 +1041,30 @@ static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc) return -ENOENT; } -static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) +static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, + struct mfcctl *mfc, int mrtsock) { + bool found = false; int line; - struct mfc_cache *uc, *c, **cp; + struct mfc_cache *uc, *c; + + if (mfc->mfcc_parent >= MAXVIFS) + return -ENFILE; line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); - for (cp = &net->ipv4.mfc_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + found = true; break; + } } - if (c != NULL) { + if (found) { write_lock_bh(&mrt_lock); c->mfc_parent = mfc->mfcc_parent; - ipmr_update_thresholds(c, mfc->mfcc_ttls); + ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); @@ -824,43 +1074,42 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; - c = ipmr_cache_alloc(net); + c = ipmr_cache_alloc(); if (c == NULL) return -ENOMEM; c->mfc_origin = mfc->mfcc_origin.s_addr; c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr; c->mfc_parent = mfc->mfcc_parent; - ipmr_update_thresholds(c, mfc->mfcc_ttls); + ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_lock_bh(&mrt_lock); - c->next = net->ipv4.mfc_cache_array[line]; - net->ipv4.mfc_cache_array[line] = c; + list_add(&c->list, &mrt->mfc_cache_array[line]); write_unlock_bh(&mrt_lock); /* * Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ + found = false; spin_lock_bh(&mfc_unres_lock); - for (cp = &mfc_unres_queue; (uc=*cp) != NULL; - cp = &uc->next) { - if (net_eq(mfc_net(uc), net) && - uc->mfc_origin == c->mfc_origin && + list_for_each_entry(uc, &mrt->mfc_unres_queue, list) { + if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { - *cp = uc->next; - atomic_dec(&net->ipv4.cache_resolve_queue_len); + list_del(&uc->list); + atomic_dec(&mrt->cache_resolve_queue_len); + found = true; break; } } - if (mfc_unres_queue == NULL) - del_timer(&ipmr_expire_timer); + if (list_empty(&mrt->mfc_unres_queue)) + del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); - if (uc) { - ipmr_cache_resolve(uc, c); + if (found) { + ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } return 0; @@ -870,53 +1119,41 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct net *net) +static void mroute_clean_tables(struct mr_table *mrt) { int i; LIST_HEAD(list); + struct mfc_cache *c, *next; /* * Shut down all active vif entries */ - for (i = 0; i < net->ipv4.maxvif; i++) { - if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC)) - vif_delete(net, i, 0, &list); + for (i = 0; i < mrt->maxvif; i++) { + if (!(mrt->vif_table[i].flags&VIFF_STATIC)) + vif_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); /* * Wipe the cache */ - for (i=0; i<MFC_LINES; i++) { - struct mfc_cache *c, **cp; - - cp = &net->ipv4.mfc_cache_array[i]; - while ((c = *cp) != NULL) { - if (c->mfc_flags&MFC_STATIC) { - cp = &c->next; + for (i = 0; i < MFC_LINES; i++) { + list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) { + if (c->mfc_flags&MFC_STATIC) continue; - } write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ipmr_cache_free(c); } } - if (atomic_read(&net->ipv4.cache_resolve_queue_len) != 0) { - struct mfc_cache *c, **cp; - + if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); - cp = &mfc_unres_queue; - while ((c = *cp) != NULL) { - if (!net_eq(mfc_net(c), net)) { - cp = &c->next; - continue; - } - *cp = c->next; - - ipmr_destroy_unres(c); + list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { + list_del(&c->list); + ipmr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); } @@ -925,16 +1162,19 @@ static void mroute_clean_tables(struct net *net) static void mrtsock_destruct(struct sock *sk) { struct net *net = sock_net(sk); + struct mr_table *mrt; rtnl_lock(); - if (sk == net->ipv4.mroute_sk) { - IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; + ipmr_for_each_table(mrt, net) { + if (sk == mrt->mroute_sk) { + IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; - write_lock_bh(&mrt_lock); - net->ipv4.mroute_sk = NULL; - write_unlock_bh(&mrt_lock); + write_lock_bh(&mrt_lock); + mrt->mroute_sk = NULL; + write_unlock_bh(&mrt_lock); - mroute_clean_tables(net); + mroute_clean_tables(mrt); + } } rtnl_unlock(); } @@ -952,9 +1192,14 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi struct vifctl vif; struct mfcctl mfc; struct net *net = sock_net(sk); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; if (optname != MRT_INIT) { - if (sk != net->ipv4.mroute_sk && !capable(CAP_NET_ADMIN)) + if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -967,7 +1212,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENOPROTOOPT; rtnl_lock(); - if (net->ipv4.mroute_sk) { + if (mrt->mroute_sk) { rtnl_unlock(); return -EADDRINUSE; } @@ -975,7 +1220,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { write_lock_bh(&mrt_lock); - net->ipv4.mroute_sk = sk; + mrt->mroute_sk = sk; write_unlock_bh(&mrt_lock); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; @@ -983,7 +1228,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi rtnl_unlock(); return ret; case MRT_DONE: - if (sk != net->ipv4.mroute_sk) + if (sk != mrt->mroute_sk) return -EACCES; return ip_ra_control(sk, 0, NULL); case MRT_ADD_VIF: @@ -996,9 +1241,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENFILE; rtnl_lock(); if (optname == MRT_ADD_VIF) { - ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk); + ret = vif_add(net, mrt, &vif, sk == mrt->mroute_sk); } else { - ret = vif_delete(net, vif.vifc_vifi, 0, NULL); + ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL); } rtnl_unlock(); return ret; @@ -1015,9 +1260,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -EFAULT; rtnl_lock(); if (optname == MRT_DEL_MFC) - ret = ipmr_mfc_delete(net, &mfc); + ret = ipmr_mfc_delete(mrt, &mfc); else - ret = ipmr_mfc_add(net, &mfc, sk == net->ipv4.mroute_sk); + ret = ipmr_mfc_add(net, mrt, &mfc, sk == mrt->mroute_sk); rtnl_unlock(); return ret; /* @@ -1028,7 +1273,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi int v; if (get_user(v,(int __user *)optval)) return -EFAULT; - net->ipv4.mroute_do_assert = (v) ? 1 : 0; + mrt->mroute_do_assert = (v) ? 1 : 0; return 0; } #ifdef CONFIG_IP_PIMSM @@ -1042,14 +1287,35 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi rtnl_lock(); ret = 0; - if (v != net->ipv4.mroute_do_pim) { - net->ipv4.mroute_do_pim = v; - net->ipv4.mroute_do_assert = v; + if (v != mrt->mroute_do_pim) { + mrt->mroute_do_pim = v; + mrt->mroute_do_assert = v; } rtnl_unlock(); return ret; } #endif +#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES + case MRT_TABLE: + { + u32 v; + + if (optlen != sizeof(u32)) + return -EINVAL; + if (get_user(v, (u32 __user *)optval)) + return -EFAULT; + if (sk == mrt->mroute_sk) + return -EBUSY; + + rtnl_lock(); + ret = 0; + if (!ipmr_new_table(net, v)) + ret = -ENOMEM; + raw_sk(sk)->ipmr_table = v; + rtnl_unlock(); + return ret; + } +#endif /* * Spurious command, or MRT_VERSION which you cannot * set. @@ -1068,6 +1334,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int int olr; int val; struct net *net = sock_net(sk); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; if (optname != MRT_VERSION && #ifdef CONFIG_IP_PIMSM @@ -1089,10 +1360,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int val = 0x0305; #ifdef CONFIG_IP_PIMSM else if (optname == MRT_PIM) - val = net->ipv4.mroute_do_pim; + val = mrt->mroute_do_pim; #endif else - val = net->ipv4.mroute_do_assert; + val = mrt->mroute_do_assert; if (copy_to_user(optval, &val, olr)) return -EFAULT; return 0; @@ -1109,16 +1380,21 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; switch (cmd) { case SIOCGETVIFCNT: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; - if (vr.vifi >= net->ipv4.maxvif) + if (vr.vifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &net->ipv4.vif_table[vr.vifi]; - if (VIF_EXISTS(net, vr.vifi)) { + vif = &mrt->vif_table[vr.vifi]; + if (VIF_EXISTS(mrt, vr.vifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1136,7 +1412,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; read_lock(&mrt_lock); - c = ipmr_cache_find(net, sr.src.s_addr, sr.grp.s_addr); + c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { sr.pktcnt = c->mfc_un.res.pkt; sr.bytecnt = c->mfc_un.res.bytes; @@ -1159,16 +1435,20 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct mr_table *mrt; struct vif_device *v; int ct; LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - v = &net->ipv4.vif_table[0]; - for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) { - if (v->dev == dev) - vif_delete(net, ct, 1, &list); + + ipmr_for_each_table(mrt, net) { + v = &mrt->vif_table[0]; + for (ct = 0; ct < mrt->maxvif; ct++, v++) { + if (v->dev == dev) + vif_delete(mrt, ct, 1, &list); + } } unregister_netdevice_many(&list); return NOTIFY_DONE; @@ -1227,11 +1507,11 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) * Processing handlers for ipmr_forward */ -static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) +static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *c, int vifi) { - struct net *net = mfc_net(c); const struct iphdr *iph = ip_hdr(skb); - struct vif_device *vif = &net->ipv4.vif_table[vifi]; + struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *dev; struct rtable *rt; int encap = 0; @@ -1245,7 +1525,7 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) vif->bytes_out += skb->len; vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - ipmr_cache_report(net, skb, vifi, IGMPMSG_WHOLEPKT); + ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); goto out_free; } #endif @@ -1328,12 +1608,12 @@ out_free: return; } -static int ipmr_find_vif(struct net_device *dev) +static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev) { - struct net *net = dev_net(dev); int ct; - for (ct = net->ipv4.maxvif-1; ct >= 0; ct--) { - if (net->ipv4.vif_table[ct].dev == dev) + + for (ct = mrt->maxvif-1; ct >= 0; ct--) { + if (mrt->vif_table[ct].dev == dev) break; } return ct; @@ -1341,11 +1621,12 @@ static int ipmr_find_vif(struct net_device *dev) /* "local" means that we should preserve one skb (for local delivery) */ -static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local) +static int ip_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *cache, + int local) { int psend = -1; int vif, ct; - struct net *net = mfc_net(cache); vif = cache->mfc_parent; cache->mfc_un.res.pkt++; @@ -1354,7 +1635,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (net->ipv4.vif_table[vif].dev != skb->dev) { + if (mrt->vif_table[vif].dev != skb->dev) { int true_vifi; if (skb_rtable(skb)->fl.iif == 0) { @@ -1373,26 +1654,26 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local } cache->mfc_un.res.wrong_if++; - true_vifi = ipmr_find_vif(skb->dev); + true_vifi = ipmr_find_vif(mrt, skb->dev); - if (true_vifi >= 0 && net->ipv4.mroute_do_assert && + if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ - (net->ipv4.mroute_do_pim || + (mrt->mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { cache->mfc_un.res.last_assert = jiffies; - ipmr_cache_report(net, skb, true_vifi, IGMPMSG_WRONGVIF); + ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); } goto dont_forward; } - net->ipv4.vif_table[vif].pkt_in++; - net->ipv4.vif_table[vif].bytes_in += skb->len; + mrt->vif_table[vif].pkt_in++; + mrt->vif_table[vif].bytes_in += skb->len; /* * Forward the frame @@ -1402,7 +1683,8 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(skb2, cache, psend); + ipmr_queue_xmit(net, mrt, skb2, cache, + psend); } psend = ct; } @@ -1411,9 +1693,9 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(skb2, cache, psend); + ipmr_queue_xmit(net, mrt, skb2, cache, psend); } else { - ipmr_queue_xmit(skb, cache, psend); + ipmr_queue_xmit(net, mrt, skb, cache, psend); return 0; } } @@ -1434,6 +1716,8 @@ int ip_mr_input(struct sk_buff *skb) struct mfc_cache *cache; struct net *net = dev_net(skb->dev); int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; + struct mr_table *mrt; + int err; /* Packet is looped back after forward, it should not be forwarded second time, but still can be delivered locally. @@ -1441,6 +1725,10 @@ int ip_mr_input(struct sk_buff *skb) if (IPCB(skb)->flags&IPSKB_FORWARDED) goto dont_forward; + err = ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt); + if (err < 0) + return err; + if (!local) { if (IPCB(skb)->opt.router_alert) { if (ip_call_ra_chain(skb)) @@ -1453,9 +1741,9 @@ int ip_mr_input(struct sk_buff *skb) that we can forward NO IGMP messages. */ read_lock(&mrt_lock); - if (net->ipv4.mroute_sk) { + if (mrt->mroute_sk) { nf_reset(skb); - raw_rcv(net->ipv4.mroute_sk, skb); + raw_rcv(mrt->mroute_sk, skb); read_unlock(&mrt_lock); return 0; } @@ -1464,7 +1752,7 @@ int ip_mr_input(struct sk_buff *skb) } read_lock(&mrt_lock); - cache = ipmr_cache_find(net, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); + cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); /* * No usable cache entry @@ -1482,9 +1770,9 @@ int ip_mr_input(struct sk_buff *skb) skb = skb2; } - vif = ipmr_find_vif(skb->dev); + vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) { - int err = ipmr_cache_unresolved(net, vif, skb); + int err = ipmr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); return err; @@ -1494,7 +1782,7 @@ int ip_mr_input(struct sk_buff *skb) return -ENODEV; } - ip_mr_forward(skb, cache, local); + ip_mr_forward(net, mrt, skb, cache, local); read_unlock(&mrt_lock); @@ -1511,11 +1799,11 @@ dont_forward: } #ifdef CONFIG_IP_PIMSM -static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) +static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, + unsigned int pimlen) { struct net_device *reg_dev = NULL; struct iphdr *encap; - struct net *net = dev_net(skb->dev); encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* @@ -1530,8 +1818,8 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) return 1; read_lock(&mrt_lock); - if (net->ipv4.mroute_reg_vif_num >= 0) - reg_dev = net->ipv4.vif_table[net->ipv4.mroute_reg_vif_num].dev; + if (mrt->mroute_reg_vif_num >= 0) + reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev; if (reg_dev) dev_hold(reg_dev); read_unlock(&mrt_lock); @@ -1566,17 +1854,21 @@ int pim_rcv_v1(struct sk_buff * skb) { struct igmphdr *pim; struct net *net = dev_net(skb->dev); + struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = igmp_hdr(skb); - if (!net->ipv4.mroute_do_pim || + if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0) + goto drop; + + if (!mrt->mroute_do_pim || pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) goto drop; - if (__pim_rcv(skb, sizeof(*pim))) { + if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } @@ -1588,6 +1880,8 @@ drop: static int pim_rcv(struct sk_buff * skb) { struct pimreghdr *pim; + struct net *net = dev_net(skb->dev); + struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; @@ -1599,7 +1893,10 @@ static int pim_rcv(struct sk_buff * skb) csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; - if (__pim_rcv(skb, sizeof(*pim))) { + if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0) + goto drop; + + if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } @@ -1608,28 +1905,31 @@ drop: #endif static int -ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm) +ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, + struct rtmsg *rtm) { int ct; struct rtnexthop *nhp; - struct net *net = mfc_net(c); - struct net_device *dev = net->ipv4.vif_table[c->mfc_parent].dev; u8 *b = skb_tail_pointer(skb); struct rtattr *mp_head; - if (dev) - RTA_PUT(skb, RTA_IIF, 4, &dev->ifindex); + /* If cache is unresolved, don't try to parse IIF and OIF */ + if (c->mfc_parent > MAXVIFS) + return -ENOENT; + + if (VIF_EXISTS(mrt, c->mfc_parent)) + RTA_PUT(skb, RTA_IIF, 4, &mrt->vif_table[c->mfc_parent].dev->ifindex); mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (c->mfc_un.res.ttls[ct] < 255) { + if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) goto rtattr_failure; nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = net->ipv4.vif_table[ct].dev->ifindex; + nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } @@ -1647,11 +1947,16 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait) { int err; + struct mr_table *mrt; struct mfc_cache *cache; struct rtable *rt = skb_rtable(skb); + mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; + read_lock(&mrt_lock); - cache = ipmr_cache_find(net, rt->rt_src, rt->rt_dst); + cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst); if (cache == NULL) { struct sk_buff *skb2; @@ -1665,7 +1970,7 @@ int ipmr_get_route(struct net *net, } dev = skb->dev; - if (dev == NULL || (vif = ipmr_find_vif(dev)) < 0) { + if (dev == NULL || (vif = ipmr_find_vif(mrt, dev)) < 0) { read_unlock(&mrt_lock); return -ENODEV; } @@ -1682,14 +1987,14 @@ int ipmr_get_route(struct net *net, iph->saddr = rt->rt_src; iph->daddr = rt->rt_dst; iph->version = 0; - err = ipmr_cache_unresolved(net, vif, skb2); + err = ipmr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); return err; } if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) cache->mfc_flags |= MFC_NOTIFY; - err = ipmr_fill_mroute(skb, cache, rtm); + err = ipmr_fill_mroute(mrt, skb, cache, rtm); read_unlock(&mrt_lock); return err; } @@ -1700,6 +2005,7 @@ int ipmr_get_route(struct net *net, */ struct ipmr_vif_iter { struct seq_net_private p; + struct mr_table *mrt; int ct; }; @@ -1707,11 +2013,13 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net, struct ipmr_vif_iter *iter, loff_t pos) { - for (iter->ct = 0; iter->ct < net->ipv4.maxvif; ++iter->ct) { - if (!VIF_EXISTS(net, iter->ct)) + struct mr_table *mrt = iter->mrt; + + for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { + if (!VIF_EXISTS(mrt, iter->ct)) continue; if (pos-- == 0) - return &net->ipv4.vif_table[iter->ct]; + return &mrt->vif_table[iter->ct]; } return NULL; } @@ -1719,7 +2027,15 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net, static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { + struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + + iter->mrt = mrt; read_lock(&mrt_lock); return *pos ? ipmr_vif_seq_idx(net, seq->private, *pos - 1) @@ -1730,15 +2046,16 @@ static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt = iter->mrt; ++*pos; if (v == SEQ_START_TOKEN) return ipmr_vif_seq_idx(net, iter, 0); - while (++iter->ct < net->ipv4.maxvif) { - if (!VIF_EXISTS(net, iter->ct)) + while (++iter->ct < mrt->maxvif) { + if (!VIF_EXISTS(mrt, iter->ct)) continue; - return &net->ipv4.vif_table[iter->ct]; + return &mrt->vif_table[iter->ct]; } return NULL; } @@ -1751,7 +2068,8 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) static int ipmr_vif_seq_show(struct seq_file *seq, void *v) { - struct net *net = seq_file_net(seq); + struct ipmr_vif_iter *iter = seq->private; + struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -1762,7 +2080,7 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%2Zd %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n", - vif - net->ipv4.vif_table, + vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags, vif->local, vif->remote); @@ -1793,7 +2111,8 @@ static const struct file_operations ipmr_vif_fops = { struct ipmr_mfc_iter { struct seq_net_private p; - struct mfc_cache **cache; + struct mr_table *mrt; + struct list_head *cache; int ct; }; @@ -1801,22 +2120,22 @@ struct ipmr_mfc_iter { static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, struct ipmr_mfc_iter *it, loff_t pos) { + struct mr_table *mrt = it->mrt; struct mfc_cache *mfc; - it->cache = net->ipv4.mfc_cache_array; read_lock(&mrt_lock); - for (it->ct = 0; it->ct < MFC_LINES; it->ct++) - for (mfc = net->ipv4.mfc_cache_array[it->ct]; - mfc; mfc = mfc->next) + for (it->ct = 0; it->ct < MFC_LINES; it->ct++) { + it->cache = &mrt->mfc_cache_array[it->ct]; + list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; + } read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; spin_lock_bh(&mfc_unres_lock); - for (mfc = mfc_unres_queue; mfc; mfc = mfc->next) - if (net_eq(mfc_net(mfc), net) && - pos-- == 0) + it->cache = &mrt->mfc_unres_queue; + list_for_each_entry(mfc, it->cache, list) + if (pos-- == 0) return mfc; spin_unlock_bh(&mfc_unres_lock); @@ -1829,7 +2148,13 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + it->mrt = mrt; it->cache = NULL; it->ct = 0; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) @@ -1841,37 +2166,36 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct mfc_cache *mfc = v; struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt = it->mrt; ++*pos; if (v == SEQ_START_TOKEN) return ipmr_mfc_seq_idx(net, seq->private, 0); - if (mfc->next) - return mfc->next; + if (mfc->list.next != it->cache) + return list_entry(mfc->list.next, struct mfc_cache, list); - if (it->cache == &mfc_unres_queue) + if (it->cache == &mrt->mfc_unres_queue) goto end_of_list; - BUG_ON(it->cache != net->ipv4.mfc_cache_array); + BUG_ON(it->cache != &mrt->mfc_cache_array[it->ct]); while (++it->ct < MFC_LINES) { - mfc = net->ipv4.mfc_cache_array[it->ct]; - if (mfc) - return mfc; + it->cache = &mrt->mfc_cache_array[it->ct]; + if (list_empty(it->cache)) + continue; + return list_first_entry(it->cache, struct mfc_cache, list); } /* exhausted cache_array, show unresolved */ read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; + it->cache = &mrt->mfc_unres_queue; it->ct = 0; spin_lock_bh(&mfc_unres_lock); - mfc = mfc_unres_queue; - while (mfc && !net_eq(mfc_net(mfc), net)) - mfc = mfc->next; - if (mfc) - return mfc; + if (!list_empty(it->cache)) + return list_first_entry(it->cache, struct mfc_cache, list); end_of_list: spin_unlock_bh(&mfc_unres_lock); @@ -1883,18 +2207,17 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) { struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); + struct mr_table *mrt = it->mrt; - if (it->cache == &mfc_unres_queue) + if (it->cache == &mrt->mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == net->ipv4.mfc_cache_array) + else if (it->cache == &mrt->mfc_cache_array[it->ct]) read_unlock(&mrt_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; - struct net *net = seq_file_net(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -1902,20 +2225,21 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) } else { const struct mfc_cache *mfc = v; const struct ipmr_mfc_iter *it = seq->private; + const struct mr_table *mrt = it->mrt; seq_printf(seq, "%08lX %08lX %-3hd", (unsigned long) mfc->mfc_mcastgrp, (unsigned long) mfc->mfc_origin, mfc->mfc_parent); - if (it->cache != &mfc_unres_queue) { + if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->mfc_un.res.pkt, mfc->mfc_un.res.bytes, mfc->mfc_un.res.wrong_if); for (n = mfc->mfc_un.res.minvif; n < mfc->mfc_un.res.maxvif; n++ ) { - if (VIF_EXISTS(net, n) && + if (VIF_EXISTS(mrt, n) && mfc->mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", @@ -1967,27 +2291,11 @@ static const struct net_protocol pim_protocol = { */ static int __net_init ipmr_net_init(struct net *net) { - int err = 0; + int err; - net->ipv4.vif_table = kcalloc(MAXVIFS, sizeof(struct vif_device), - GFP_KERNEL); - if (!net->ipv4.vif_table) { - err = -ENOMEM; + err = ipmr_rules_init(net); + if (err < 0) goto fail; - } - - /* Forwarding cache */ - net->ipv4.mfc_cache_array = kcalloc(MFC_LINES, - sizeof(struct mfc_cache *), - GFP_KERNEL); - if (!net->ipv4.mfc_cache_array) { - err = -ENOMEM; - goto fail_mfc_cache; - } - -#ifdef CONFIG_IP_PIMSM - net->ipv4.mroute_reg_vif_num = -1; -#endif #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -2002,10 +2310,8 @@ static int __net_init ipmr_net_init(struct net *net) proc_cache_fail: proc_net_remove(net, "ip_mr_vif"); proc_vif_fail: - kfree(net->ipv4.mfc_cache_array); + ipmr_rules_exit(net); #endif -fail_mfc_cache: - kfree(net->ipv4.vif_table); fail: return err; } @@ -2016,8 +2322,7 @@ static void __net_exit ipmr_net_exit(struct net *net) proc_net_remove(net, "ip_mr_cache"); proc_net_remove(net, "ip_mr_vif"); #endif - kfree(net->ipv4.mfc_cache_array); - kfree(net->ipv4.vif_table); + ipmr_rules_exit(net); } static struct pernet_operations ipmr_net_ops = { @@ -2040,7 +2345,6 @@ int __init ip_mr_init(void) if (err) goto reg_pernet_fail; - setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); err = register_netdevice_notifier(&ip_mr_notifier); if (err) goto reg_notif_fail; @@ -2058,7 +2362,6 @@ add_proto_fail: unregister_netdevice_notifier(&ip_mr_notifier); #endif reg_notif_fail: - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ipmr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index c14623fc4d5..82fb43c5c59 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -4,6 +4,7 @@ #include <linux/netfilter_ipv4.h> #include <linux/ip.h> #include <linux/skbuff.h> +#include <linux/gfp.h> #include <net/route.h> #include <net/xfrm.h> #include <net/ip.h> diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index bfe26f32b93..79ca5e70d49 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp/arp_tables.h> +#include <linux/slab.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("David S. Miller <davem@redhat.com>"); diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index d781513282d..c838238104f 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -26,6 +26,7 @@ #include <linux/security.h> #include <linux/net.h> #include <linux/mutex.h> +#include <linux/slab.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/route.h> diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index c6be74e5726..8815d458de4 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -15,6 +15,7 @@ #include <linux/jhash.h> #include <linux/bitops.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/udp.h> @@ -88,7 +89,7 @@ clusterip_config_entry_put(struct clusterip_config *c) list_del(&c->list); write_unlock_bh(&clusterip_lock); - dev_mc_delete(c->dev, c->clustermac, ETH_ALEN, 0); + dev_mc_del(c->dev, c->clustermac); dev_put(c->dev); /* In case anyone still accesses the file, the open/close @@ -397,7 +398,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) dev_put(dev); return -ENOMEM; } - dev_mc_add(config->dev,config->clustermac, ETH_ALEN, 0); + dev_mc_add(config->dev, config->clustermac); } } cipinfo->config = config; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 038fa0bb8f6..a86135a2805 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <linux/ip.h> #include <linux/udp.h> #include <linux/icmp.h> diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 04c86dc5d53..8f60749e87a 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -33,6 +33,7 @@ #include <linux/module.h> #include <linux/spinlock.h> #include <linux/socket.h> +#include <linux/slab.h> #include <linux/skbuff.h> #include <linux/kernel.h> #include <linux/timer.h> diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index c8dc9800d62..55392466daa 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/slab.h> #include <net/ip.h> MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index b9b83464cbf..294a2a32f29 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -12,6 +12,7 @@ #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <net/sock.h> #include <net/route.h> #include <linux/ip.h> diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 06fb9d11953..07fb710cd72 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -5,6 +5,7 @@ */ #include <linux/module.h> #include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/slab.h> #include <net/ip.h> #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index cce2f64e6f2..be45bdc4c60 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -17,6 +17,7 @@ */ #include <linux/module.h> #include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/slab.h> #include <net/ip.h> MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 4595281c286..4f8bddb760c 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -12,6 +12,7 @@ #include <linux/types.h> #include <linux/timer.h> #include <linux/skbuff.h> +#include <linux/gfp.h> #include <net/checksum.h> #include <net/icmp.h> #include <net/ip.h> diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 4b6af4bb1f5..4a0c6b548ee 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -8,6 +8,7 @@ * published by the Free Software Foundation. */ #include <linux/module.h> +#include <linux/gfp.h> #include <linux/kmod.h> #include <linux/types.h> #include <linux/timer.h> diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index b66137c80bc..b48a0fc3d9e 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -16,6 +16,7 @@ #include <linux/kmod.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> +#include <linux/slab.h> #include <net/checksum.h> #include <net/route.h> #include <linux/bitops.h> diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 0b9c7ce3d6c..4d85b6e55f2 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -43,6 +43,7 @@ #include <linux/moduleparam.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/udp.h> diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 0b49248e34f..84c7974f583 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -7,6 +7,7 @@ */ #include <linux/types.h> #include <linux/icmp.h> +#include <linux/gfp.h> #include <linux/ip.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 4f1f337f433..3dc9914c1dc 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -251,6 +251,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSackShiftFallback", LINUX_MIB_SACKSHIFTFALLBACK), SNMP_MIB_ITEM("TCPBacklogDrop", LINUX_MIB_TCPBACKLOGDROP), SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP), + SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 34d9adb8359..bbda0d5f924 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -60,7 +60,6 @@ #include <net/net_namespace.h> #include <net/dst.h> #include <net/sock.h> -#include <linux/gfp.h> #include <linux/ip.h> #include <linux/net.h> #include <net/ip.h> diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a770df2493d..cb562fdd9b9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -90,6 +90,7 @@ #include <linux/jhash.h> #include <linux/rcupdate.h> #include <linux/times.h> +#include <linux/slab.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -1097,7 +1098,7 @@ static int slow_chain_length(const struct rtable *head) } static int rt_intern_hash(unsigned hash, struct rtable *rt, - struct rtable **rp, struct sk_buff *skb) + struct rtable **rp, struct sk_buff *skb, int ifindex) { struct rtable *rth, **rthp; unsigned long now; @@ -1212,11 +1213,16 @@ restart: slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) { struct net *net = dev_net(rt->u.dst.dev); int num = ++net->ipv4.current_rt_cache_rebuild_count; - if (!rt_caching(dev_net(rt->u.dst.dev))) { + if (!rt_caching(net)) { printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n", rt->u.dst.dev->name, num); } - rt_emergency_hash_rebuild(dev_net(rt->u.dst.dev)); + rt_emergency_hash_rebuild(net); + spin_unlock_bh(rt_hash_lock_addr(hash)); + + hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, + ifindex, rt_genid(net)); + goto restart; } } @@ -1441,7 +1447,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, dev_hold(rt->u.dst.dev); if (rt->idev) in_dev_hold(rt->idev); - rt->u.dst.obsolete = 0; + rt->u.dst.obsolete = -1; rt->u.dst.lastuse = jiffies; rt->u.dst.path = &rt->u.dst; rt->u.dst.neighbour = NULL; @@ -1477,7 +1483,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, &netevent); rt_del(hash, rth); - if (!rt_intern_hash(hash, rt, &rt, NULL)) + if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif)) ip_rt_put(rt); goto do_next; } @@ -1506,11 +1512,12 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) struct dst_entry *ret = dst; if (rt) { - if (dst->obsolete) { + if (dst->obsolete > 0) { ip_rt_put(rt); ret = NULL; } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->u.dst.expires) { + (rt->u.dst.expires && + time_after_eq(jiffies, rt->u.dst.expires))) { unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, rt->fl.oif, rt_genid(dev_net(dst->dev))); @@ -1726,7 +1733,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { - return NULL; + if (rt_is_expired((struct rtable *)dst)) + return NULL; + return dst; } static void ipv4_dst_destroy(struct dst_entry *dst) @@ -1888,7 +1897,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (!rth) goto e_nobufs; - rth->u.dst.output= ip_rt_bug; + rth->u.dst.output = ip_rt_bug; + rth->u.dst.obsolete = -1; atomic_set(&rth->u.dst.__refcnt, 1); rth->u.dst.flags= DST_HOST; @@ -1927,7 +1937,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, in_dev_put(in_dev); hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); - return rt_intern_hash(hash, rth, NULL, skb); + return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex); e_nobufs: in_dev_put(in_dev); @@ -2054,6 +2064,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->fl.oif = 0; rth->rt_spec_dst= spec_dst; + rth->u.dst.obsolete = -1; rth->u.dst.input = ip_forward; rth->u.dst.output = ip_output; rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev)); @@ -2093,7 +2104,7 @@ static int ip_mkroute_input(struct sk_buff *skb, /* put it into the cache */ hash = rt_hash(daddr, saddr, fl->iif, rt_genid(dev_net(rth->u.dst.dev))); - return rt_intern_hash(hash, rth, NULL, skb); + return rt_intern_hash(hash, rth, NULL, skb, fl->iif); } /* @@ -2218,6 +2229,7 @@ local_input: goto e_nobufs; rth->u.dst.output= ip_rt_bug; + rth->u.dst.obsolete = -1; rth->rt_genid = rt_genid(net); atomic_set(&rth->u.dst.__refcnt, 1); @@ -2249,7 +2261,7 @@ local_input: } rth->rt_type = res.type; hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net)); - err = rt_intern_hash(hash, rth, NULL, skb); + err = rt_intern_hash(hash, rth, NULL, skb, fl.iif); goto done; no_route: @@ -2444,6 +2456,7 @@ static int __mkroute_output(struct rtable **result, rth->rt_spec_dst= fl->fl4_src; rth->u.dst.output=ip_output; + rth->u.dst.obsolete = -1; rth->rt_genid = rt_genid(dev_net(dev_out)); RT_CACHE_STAT_INC(out_slow_tot); @@ -2495,7 +2508,7 @@ static int ip_mkroute_output(struct rtable **rp, if (err == 0) { hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif, rt_genid(dev_net(dev_out))); - err = rt_intern_hash(hash, rth, rp, NULL); + err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif); } return err; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index c1bc074f61b..1cd5c15174b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -12,6 +12,7 @@ #include <linux/inetdevice.h> #include <linux/seqlock.h> #include <linux/init.h> +#include <linux/slab.h> #include <net/snmp.h> #include <net/icmp.h> #include <net/ip.h> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5901010fad5..0f8caf64caa 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -265,6 +265,7 @@ #include <linux/err.h> #include <linux/crypto.h> #include <linux/time.h> +#include <linux/slab.h> #include <net/icmp.h> #include <net/tcp.h> @@ -429,7 +430,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tp->urg_seq == tp->copied_seq && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) - target--; + target++; /* Potential race condition. If read of tp below will * escape above sk->sk_state, we can be illegally awaken @@ -1254,6 +1255,39 @@ static void tcp_prequeue_process(struct sock *sk) tp->ucopy.memory = 0; } +#ifdef CONFIG_NET_DMA +static void tcp_service_net_dma(struct sock *sk, bool wait) +{ + dma_cookie_t done, used; + dma_cookie_t last_issued; + struct tcp_sock *tp = tcp_sk(sk); + + if (!tp->ucopy.dma_chan) + return; + + last_issued = tp->ucopy.dma_cookie; + dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + + do { + if (dma_async_memcpy_complete(tp->ucopy.dma_chan, + last_issued, &done, + &used) == DMA_SUCCESS) { + /* Safe to free early-copied skbs now */ + __skb_queue_purge(&sk->sk_async_wait_queue); + break; + } else { + struct sk_buff *skb; + while ((skb = skb_peek(&sk->sk_async_wait_queue)) && + (dma_async_is_complete(skb->dma_cookie, done, + used) == DMA_SUCCESS)) { + __skb_dequeue(&sk->sk_async_wait_queue); + kfree_skb(skb); + } + } + } while (wait); +} +#endif + static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; @@ -1335,6 +1369,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_eat_skb(sk, skb, 0); if (!desc->count) break; + tp->copied_seq = seq; } tp->copied_seq = seq; @@ -1546,6 +1581,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* __ Set realtime policy in scheduler __ */ } +#ifdef CONFIG_NET_DMA + if (tp->ucopy.dma_chan) + dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); +#endif if (copied >= target) { /* Do not sleep, just process backlog. */ release_sock(sk); @@ -1554,6 +1593,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sk_wait_data(sk, &timeo); #ifdef CONFIG_NET_DMA + tcp_service_net_dma(sk, false); /* Don't block */ tp->ucopy.wakeup = 0; #endif @@ -1633,6 +1673,9 @@ do_prequeue: copied = -EFAULT; break; } + + dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + if ((offset + used) == skb->len) copied_early = 1; @@ -1702,27 +1745,9 @@ skip_copy: } #ifdef CONFIG_NET_DMA - if (tp->ucopy.dma_chan) { - dma_cookie_t done, used; - - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); - - while (dma_async_memcpy_complete(tp->ucopy.dma_chan, - tp->ucopy.dma_cookie, &done, - &used) == DMA_IN_PROGRESS) { - /* do partial cleanup of sk_async_wait_queue */ - while ((skb = skb_peek(&sk->sk_async_wait_queue)) && - (dma_async_is_complete(skb->dma_cookie, done, - used) == DMA_SUCCESS)) { - __skb_dequeue(&sk->sk_async_wait_queue); - kfree_skb(skb); - } - } + tcp_service_net_dma(sk, true); /* Wait for queue to drain */ + tp->ucopy.dma_chan = NULL; - /* Safe to free early-copied skbs now */ - __skb_queue_purge(&sk->sk_async_wait_queue); - tp->ucopy.dma_chan = NULL; - } if (tp->ucopy.pinned_list) { dma_unpin_iovec_pages(tp->ucopy.pinned_list); tp->ucopy.pinned_list = NULL; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 6428b342b16..0ec9bd0ae94 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/types.h> #include <linux/list.h> +#include <linux/gfp.h> #include <net/tcp.h> int sysctl_tcp_max_ssthresh = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 788851ca8c5..ae3ec15fb63 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -62,6 +62,7 @@ */ #include <linux/mm.h> +#include <linux/slab.h> #include <linux/module.h> #include <linux/sysctl.h> #include <linux/kernel.h> @@ -2511,6 +2512,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) int err; unsigned int mss; + if (packets == 0) + return; + WARN_ON(packets > tp->packets_out); if (tp->lost_skb_hint) { skb = tp->lost_skb_hint; @@ -3706,7 +3710,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) } if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) - dst_confirm(sk->sk_dst_cache); + dst_confirm(__sk_dst_get(sk)); return 1; @@ -4315,7 +4319,7 @@ static void tcp_ofo_queue(struct sock *sk) } if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { - SOCK_DEBUG(sk, "ofo packet was already received \n"); + SOCK_DEBUG(sk, "ofo packet was already received\n"); __skb_unlink(skb, &tp->out_of_order_queue); __kfree_skb(skb); continue; @@ -5829,7 +5833,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (tp->snd_una == tp->write_seq) { tcp_set_state(sk, TCP_FIN_WAIT2); sk->sk_shutdown |= SEND_SHUTDOWN; - dst_confirm(sk->sk_dst_cache); + dst_confirm(__sk_dst_get(sk)); if (!sock_flag(sk, SOCK_DEAD)) /* Wake up lingering close() */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 70df40980a8..ad08392a738 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -60,6 +60,7 @@ #include <linux/jhash.h> #include <linux/init.h> #include <linux/times.h> +#include <linux/slab.h> #include <net/net_namespace.h> #include <net/icmp.h> @@ -370,6 +371,11 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (sk->sk_state == TCP_CLOSE) goto out; + if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto out; + } + icsk = inet_csk(sk); tp = tcp_sk(sk); seq = ntohl(th->seq); @@ -513,26 +519,31 @@ out: sock_put(sk); } -/* This routine computes an IPv4 TCP checksum. */ -void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) +static void __tcp_v4_send_check(struct sk_buff *skb, + __be32 saddr, __be32 daddr) { - struct inet_sock *inet = inet_sk(sk); struct tcphdr *th = tcp_hdr(skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(len, inet->inet_saddr, - inet->inet_daddr, 0); + th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } else { - th->check = tcp_v4_check(len, inet->inet_saddr, - inet->inet_daddr, + th->check = tcp_v4_check(skb->len, saddr, daddr, csum_partial(th, th->doff << 2, skb->csum)); } } +/* This routine computes an IPv4 TCP checksum. */ +void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) +{ + struct inet_sock *inet = inet_sk(sk); + + __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); +} + int tcp_v4_gso_send_check(struct sk_buff *skb) { const struct iphdr *iph; @@ -545,10 +556,8 @@ int tcp_v4_gso_send_check(struct sk_buff *skb) th = tcp_hdr(skb); th->check = 0; - th->check = ~tcp_v4_check(skb->len, iph->saddr, iph->daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; + __tcp_v4_send_check(skb, iph->saddr, iph->daddr); return 0; } @@ -757,13 +766,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { - struct tcphdr *th = tcp_hdr(skb); - - th->check = tcp_v4_check(skb->len, - ireq->loc_addr, - ireq->rmt_addr, - csum_partial(th, skb->len, - skb->csum)); + __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr); err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, ireq->rmt_addr, @@ -1669,6 +1672,8 @@ process: skb->dev = NULL; + inet_rps_save_rxhash(sk, skb->rxhash); + bh_lock_sock_nested(sk); ret = 0; if (!sock_owned_by_user(sk)) { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4199bc6915c..794c2e122a4 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/sysctl.h> #include <linux/workqueue.h> #include <net/tcp.h> @@ -671,6 +672,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { inet_rsk(req)->acked = 1; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP); return NULL; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f181b78f238..2b7d71fb843 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -37,6 +37,7 @@ #include <net/tcp.h> #include <linux/compiler.h> +#include <linux/gfp.h> #include <linux/module.h> /* People can turn this off for buggy TCP's found in printers etc. */ @@ -349,6 +350,7 @@ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb, */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { + skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; TCP_SKB_CB(skb)->flags = flags; @@ -877,7 +879,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, } #endif - icsk->icsk_af_ops->send_check(sk, skb->len, skb); + icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->flags & TCPCB_FLAG_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); @@ -888,7 +890,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); - err = icsk->icsk_af_ops->queue_xmit(skb, 0); + err = icsk->icsk_af_ops->queue_xmit(skb); if (likely(err <= 0)) return err; diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 9bc805df95d..f8efada580e 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -22,6 +22,7 @@ #include <linux/kprobes.h> #include <linux/socket.h> #include <linux/tcp.h> +#include <linux/slab.h> #include <linux/proc_fs.h> #include <linux/module.h> #include <linux/ktime.h> diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b2e6bbccaee..c732be00606 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -19,6 +19,7 @@ */ #include <linux/module.h> +#include <linux/gfp.h> #include <net/tcp.h> int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; @@ -171,14 +172,14 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) - dst_negative_advice(&sk->sk_dst_cache, sk); + dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; } else { if (retransmits_timed_out(sk, sysctl_tcp_retries1)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); - dst_negative_advice(&sk->sk_dst_cache, sk); + dst_negative_advice(sk); } retry_until = sysctl_tcp_retries2; diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index 3959e0ca456..3b3813cc80b 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -8,6 +8,7 @@ #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <net/icmp.h> #include <net/ip.h> #include <net/protocol.h> diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7af756d0f93..666b963496f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -95,6 +95,7 @@ #include <linux/mm.h> #include <linux/inet.h> #include <linux/netdevice.h> +#include <linux/slab.h> #include <net/tcp_states.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> @@ -471,8 +472,8 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, if (hslot->count < hslot2->count) goto begin; - result = udp4_lib_lookup2(net, INADDR_ANY, sport, - daddr, hnum, dif, + result = udp4_lib_lookup2(net, saddr, sport, + INADDR_ANY, hnum, dif, hslot2, slot2); } rcu_read_unlock(); @@ -1216,6 +1217,7 @@ int udp_disconnect(struct sock *sk, int flags) sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; + inet_rps_save_rxhash(sk, 0); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -1257,8 +1259,12 @@ EXPORT_SYMBOL(udp_lib_unhash); static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int rc = sock_queue_rcv_skb(sk, skb); + int rc; + + if (inet_sk(sk)->inet_daddr) + inet_rps_save_rxhash(sk, skb->rxhash); + rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index c3969e0f96c..abcd7ed65db 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -9,6 +9,7 @@ * */ +#include <linux/slab.h> #include <linux/module.h> #include <linux/string.h> #include <linux/netfilter.h> diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 3444f3b34ec..6f368413eb0 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -4,6 +4,7 @@ * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au> */ +#include <linux/gfp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index e4a1483fba7..1705476670e 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -59,27 +59,6 @@ static int xfrm4_get_saddr(struct net *net, return 0; } -static struct dst_entry * -__xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy) -{ - struct dst_entry *dst; - - read_lock_bh(&policy->lock); - for (dst = policy->bundles; dst; dst = dst->next) { - struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (xdst->u.rt.fl.oif == fl->oif && /*XXX*/ - xdst->u.rt.fl.fl4_dst == fl->fl4_dst && - xdst->u.rt.fl.fl4_src == fl->fl4_src && - xdst->u.rt.fl.fl4_tos == fl->fl4_tos && - xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) { - dst_clone(dst); - break; - } - } - read_unlock_bh(&policy->lock); - return dst; -} - static int xfrm4_get_tos(struct flowi *fl) { return fl->fl4_tos; @@ -259,7 +238,6 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .dst_ops = &xfrm4_dst_ops, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, - .find_bundle = __xfrm4_find_bundle, .decode_session = _decode_session4, .get_tos = xfrm4_get_tos, .init_path = xfrm4_init_path, |